Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 911b2c060c |
@@ -1 +0,0 @@
|
||||
compat
|
||||
@@ -1 +0,0 @@
|
||||
compat/*
|
||||
@@ -0,0 +1,138 @@
|
||||
#!/usr/make
|
||||
#
|
||||
# Makefile for SQLITE
|
||||
#
|
||||
# This is a template makefile for SQLite. Most people prefer to
|
||||
# use the autoconf generated "configure" script to generate the
|
||||
# makefile automatically. But that does not work for everybody
|
||||
# and in every situation. If you are having problems with the
|
||||
# "configure" script, you might want to try this makefile as an
|
||||
# alternative. Create a copy of this file, edit the parameters
|
||||
# below and type "make".
|
||||
#
|
||||
|
||||
#### The directory where to find the mingw32ce tools
|
||||
MINGW32CE = /opt/mingw32ce/bin
|
||||
|
||||
#### The target prefix of the mingw32ce tools
|
||||
TARGET = arm-wince-mingw32ce
|
||||
|
||||
#### The toplevel directory of the source tree. This is the directory
|
||||
# that contains this "Makefile.in" and the "configure.in" script.
|
||||
#
|
||||
TOP = ../sqlite
|
||||
|
||||
#### C Compiler and options for use in building executables that
|
||||
# will run on the platform that is doing the build.
|
||||
#
|
||||
BCC = gcc -g -O2
|
||||
#BCC = /opt/ancic/bin/c89 -0
|
||||
|
||||
#### If the target operating system supports the "usleep()" system
|
||||
# call, then define the HAVE_USLEEP macro for all C modules.
|
||||
#
|
||||
USLEEP =
|
||||
#USLEEP = -DHAVE_USLEEP=1
|
||||
|
||||
#### If you want the SQLite library to be safe for use within a
|
||||
# multi-threaded program, then define the following macro
|
||||
# appropriately:
|
||||
#
|
||||
THREADSAFE = -DTHREADSAFE=1
|
||||
#THREADSAFE = -DTHREADSAFE=0
|
||||
|
||||
#### Specify any extra linker options needed to make the library
|
||||
# thread safe
|
||||
#
|
||||
#THREADLIB = -lpthread
|
||||
THREADLIB =
|
||||
|
||||
#### Specify any extra libraries needed to access required functions.
|
||||
#
|
||||
#TLIBS = -lrt # fdatasync on Solaris 8
|
||||
TLIBS =
|
||||
|
||||
#### Leave SQLITE_DEBUG undefined for maximum speed. Use SQLITE_DEBUG=1
|
||||
# to check for memory leaks. Use SQLITE_DEBUG=2 to print a log of all
|
||||
# malloc()s and free()s in order to track down memory leaks.
|
||||
#
|
||||
# SQLite uses some expensive assert() statements in the inner loop.
|
||||
# You can make the library go almost twice as fast if you compile
|
||||
# with -DNDEBUG=1
|
||||
#
|
||||
#OPTS = -DSQLITE_DEBUG=2
|
||||
#OPTS = -DSQLITE_DEBUG=1
|
||||
#OPTS =
|
||||
OPTS = -DNDEBUG=1 -DSQLITE_OS_WIN=1 -D_WIN32_WCE=1
|
||||
#OPTS += -DHAVE_FDATASYNC=1
|
||||
|
||||
#### The suffix to add to executable files. ".exe" for windows.
|
||||
# Nothing for unix.
|
||||
#
|
||||
EXE = .exe
|
||||
#EXE =
|
||||
|
||||
#### C Compile and options for use in building executables that
|
||||
# will run on the target platform. This is usually the same
|
||||
# as BCC, unless you are cross-compiling.
|
||||
#
|
||||
#TCC = gcc -O6
|
||||
#TCC = gcc -g -O0 -Wall
|
||||
#TCC = gcc -g -O0 -Wall -fprofile-arcs -ftest-coverage
|
||||
#TCC = /opt/mingw/bin/i386-mingw32-gcc -O6
|
||||
TCC = $(MINGW32CE)/$(TARGET)-gcc -O2
|
||||
#TCC = /opt/ansic/bin/c89 -O +z -Wl,-a,archive
|
||||
|
||||
#### Tools used to build a static library.
|
||||
#
|
||||
#AR = ar cr
|
||||
#AR = /opt/mingw/bin/i386-mingw32-ar cr
|
||||
AR = $(MINGW32CE)/$(TARGET)-ar cr
|
||||
#RANLIB = ranlib
|
||||
#RANLIB = /opt/mingw/bin/i386-mingw32-ranlib
|
||||
RANLIB = $(MINGW32CE)/$(TARGET)-ranlib
|
||||
|
||||
#MKSHLIB = gcc -shared
|
||||
#SO = so
|
||||
#SHPREFIX = lib
|
||||
MKSHLIB = $(MINGW32CE)/$(TARGET)-gcc -shared
|
||||
SO = dll
|
||||
SHPREFIX =
|
||||
|
||||
#### Extra compiler options needed for programs that use the TCL library.
|
||||
#
|
||||
#TCL_FLAGS =
|
||||
#TCL_FLAGS = -DSTATIC_BUILD=1
|
||||
TCL_FLAGS = -I/home/drh/tcltk/8.5linux
|
||||
#TCL_FLAGS = -I/home/drh/tcltk/8.5win -DSTATIC_BUILD=1
|
||||
#TCL_FLAGS = -I/home/drh/tcltk/8.3hpux
|
||||
|
||||
#### Linker options needed to link against the TCL library.
|
||||
#
|
||||
#LIBTCL = -ltcl -lm -ldl
|
||||
LIBTCL = /home/drh/tcltk/8.5linux/libtcl8.5g.a -lm -ldl
|
||||
#LIBTCL = /home/drh/tcltk/8.5win/libtcl85s.a -lmsvcrt
|
||||
#LIBTCL = /home/drh/tcltk/8.3hpux/libtcl8.3.a -ldld -lm -lc
|
||||
|
||||
#### Additional objects for SQLite library when TCL support is enabled.
|
||||
TCLOBJ =
|
||||
#TCLOBJ = tclsqlite.o
|
||||
|
||||
#### Compiler options needed for programs that use the readline() library.
|
||||
#
|
||||
READLINE_FLAGS =
|
||||
#READLINE_FLAGS = -DHAVE_READLINE=1 -I/usr/include/readline
|
||||
|
||||
#### Linker options needed by programs using readline() must link against.
|
||||
#
|
||||
LIBREADLINE =
|
||||
#LIBREADLINE = -static -lreadline -ltermcap
|
||||
|
||||
#### Which "awk" program provides nawk compatibilty
|
||||
#
|
||||
# NAWK = nawk
|
||||
NAWK = awk
|
||||
|
||||
# You should not have to change anything below this line
|
||||
###############################################################################
|
||||
include $(TOP)/main.mk
|
||||
+90
-608
File diff suppressed because it is too large
Load Diff
@@ -118,6 +118,11 @@ READLINE_FLAGS =
|
||||
LIBREADLINE =
|
||||
#LIBREADLINE = -static -lreadline -ltermcap
|
||||
|
||||
#### Which "awk" program provides nawk compatibilty
|
||||
#
|
||||
# NAWK = nawk
|
||||
NAWK = awk
|
||||
|
||||
# You should not have to change anything below this line
|
||||
###############################################################################
|
||||
include $(TOP)/main.mk
|
||||
|
||||
+372
-1909
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,663 @@
|
||||
#!/usr/make
|
||||
#
|
||||
# Makefile for SQLITE on VxWorks
|
||||
|
||||
ifeq ($(FORCPU),)
|
||||
FORCPU = SH32gnule
|
||||
endif
|
||||
|
||||
TOOL_FAMILY = gnu
|
||||
|
||||
include $(WIND_USR)/tool/gnu/make.$(FORCPU)
|
||||
|
||||
#### The toplevel directory of the source tree. This is the directory
|
||||
# that contains this "Makefile.in" and the "configure.in" script.
|
||||
#
|
||||
TOP = .
|
||||
|
||||
#### C Compiler and options for use in building executables that
|
||||
# will run on the platform that is doing the build.
|
||||
#
|
||||
BCC = gcc -g -O2
|
||||
#BCC = /opt/ancic/bin/c89 -0
|
||||
|
||||
#### If the target operating system supports the "usleep()" system
|
||||
# call, then define the HAVE_USLEEP macro for all C modules.
|
||||
#
|
||||
USLEEP =
|
||||
#USLEEP = -DHAVE_USLEEP=1
|
||||
|
||||
#### If you want the SQLite library to be safe for use within a
|
||||
# multi-threaded program, then define the following macro
|
||||
# appropriately:
|
||||
#
|
||||
THREADSAFE = -DSQLITE_THREADSAFE=1
|
||||
#THREADSAFE = -DSQLITE_THREADSAFE=0
|
||||
|
||||
#### Specify any extra linker options needed to make the library
|
||||
# thread safe
|
||||
#
|
||||
#THREADLIB = -lpthread
|
||||
THREADLIB =
|
||||
|
||||
#### Specify any extra libraries needed to access required functions.
|
||||
#
|
||||
ifeq ($(CPU),SH32)
|
||||
# for SH4 shared library
|
||||
TLIBS_SHARED += -L$(WIND_USR)/lib/sh/SH32/commonle/PIC
|
||||
else
|
||||
# for all other CPUs shared library
|
||||
TLIBS_SHARED += $(LD_LINK_PATH_ATEND) $(LD_PARTIAL_LAST_FLAGS)
|
||||
endif
|
||||
# for static library
|
||||
TLIBS += $(LD_LINK_PATH_ATEND) $(LD_PARTIAL_LAST_FLAGS)
|
||||
|
||||
#### Leave SQLITE_DEBUG undefined for maximum speed. Use SQLITE_DEBUG=1
|
||||
# to check for memory leaks. Use SQLITE_DEBUG=2 to print a log of all
|
||||
# malloc()s and free()s in order to track down memory leaks.
|
||||
#
|
||||
# SQLite uses some expensive assert() statements in the inner loop.
|
||||
# You can make the library go almost twice as fast if you compile
|
||||
# with -DNDEBUG=1
|
||||
#
|
||||
#OPTS = -DSQLITE_DEBUG=2
|
||||
#OPTS = -DSQLITE_DEBUG=1
|
||||
#OPTS =
|
||||
OPTS = -DNDEBUG=1 -DSQLITE_OS_UNIX=1 $(THREADSAFE)
|
||||
OPTS += -DSQLITE_OMIT_LOAD_EXTENSION=1
|
||||
OPTS += -DSQLITE_ENABLE_LOCKING_STYLE=1
|
||||
OPTS += -DSQLITE_THREAD_OVERRIDE_LOCK=0
|
||||
OPTS += -DSQLITE_ENABLE_COLUMN_METADATA=1
|
||||
OPTS += -DHAVE_FDATASYNC=1
|
||||
|
||||
#### The suffix to add to executable files. ".exe" for windows.
|
||||
# Nothing for unix.
|
||||
#
|
||||
EXE = .vxe
|
||||
#EXE =
|
||||
|
||||
#### C Compile and options for use in building executables that
|
||||
# will run on the target platform. This is usually the same
|
||||
# as BCC, unless you are cross-compiling.
|
||||
#
|
||||
#TCC = gcc -O6
|
||||
#TCC = gcc -g -O0 -Wall
|
||||
#TCC = gcc -g -O0 -Wall -fprofile-arcs -ftest-coverage
|
||||
#TCC = /opt/mingw/bin/i386-mingw32-gcc -O6
|
||||
TCC = $(CC) $(DEFINE_CC) -O2 -g -mrtp $(CC_ARCH_SPEC) -D_REENTRANT=1 -D_VX_CPU=_VX_$(CPU) -D_VX_TOOL_FAMILY=$(TOOL_FAMILY) -D_VX_TOOL=$(TOOL)
|
||||
TCC += -I$(WIND_USR)/h -I$(WIND_USR)/h/wrn/coreip
|
||||
#TCC = /opt/ansic/bin/c89 -O +z -Wl,-a,archive
|
||||
|
||||
#TCC_SHARED = $(TCC) -fPIC
|
||||
TCC_SHARED = $(TCC)
|
||||
|
||||
#### Tools used to build a static library.
|
||||
#
|
||||
#ARX = ar cr
|
||||
#ARX = /opt/mingw/bin/i386-mingw32-ar cr
|
||||
AR += cr
|
||||
#RANLIB = ranlib
|
||||
#RANLIB = /opt/mingw/bin/i386-mingw32-ranlib
|
||||
|
||||
#MKSHLIB = gcc -shared
|
||||
#SO = so
|
||||
#SHPREFIX = lib
|
||||
MKSHLIB = $(CC) $(DEFINE_CC) -mrtp -shared $(CC_ARCH_SPEC) -D_VX_CPU=_VX_$(CPU) -D_VX_TOOL_FAMILY=$(TOOL_FAMILY) -D_VX_TOOL=$(TOOL)
|
||||
SO = so
|
||||
SHPREFIX = lib
|
||||
|
||||
#### Extra compiler options needed for programs that use the TCL library.
|
||||
#
|
||||
#TCL_FLAGS =
|
||||
#TCL_FLAGS = -DSTATIC_BUILD=1
|
||||
TCL_FLAGS = -I/home/drh/tcltk/8.5linux
|
||||
#TCL_FLAGS = -I/home/drh/tcltk/8.5win -DSTATIC_BUILD=1
|
||||
#TCL_FLAGS = -I/home/drh/tcltk/8.3hpux
|
||||
|
||||
#### Linker options needed to link against the TCL library.
|
||||
#
|
||||
#LIBTCL = -ltcl -lm -ldl
|
||||
LIBTCL = /home/drh/tcltk/8.5linux/libtcl8.5g.a -lm -ldl
|
||||
#LIBTCL = /home/drh/tcltk/8.5win/libtcl85s.a -lmsvcrt
|
||||
#LIBTCL = /home/drh/tcltk/8.3hpux/libtcl8.3.a -ldld -lm -lc
|
||||
|
||||
#### Additional objects for SQLite library when TCL support is enabled.
|
||||
TCLOBJ =
|
||||
#TCLOBJ = tclsqlite.o
|
||||
|
||||
#### Compiler options needed for programs that use the readline() library.
|
||||
#
|
||||
READLINE_FLAGS =
|
||||
#READLINE_FLAGS = -DHAVE_READLINE=1 -I/usr/include/readline
|
||||
|
||||
#### Linker options needed by programs using readline() must link against.
|
||||
#
|
||||
LIBREADLINE =
|
||||
#LIBREADLINE = -static -lreadline -ltermcap
|
||||
|
||||
#### Which "awk" program provides nawk compatibilty
|
||||
#
|
||||
# NAWK = nawk
|
||||
NAWK = awk
|
||||
|
||||
|
||||
#### Pasted and adapted main.mk file
|
||||
###############################################################################
|
||||
# The following macros should be defined before this script is
|
||||
# invoked:
|
||||
#
|
||||
# TOP The toplevel directory of the source tree. This is the
|
||||
# directory that contains this "Makefile.in" and the
|
||||
# "configure.in" script.
|
||||
#
|
||||
# BCC C Compiler and options for use in building executables that
|
||||
# will run on the platform that is doing the build.
|
||||
#
|
||||
# THREADLIB Specify any extra linker options needed to make the library
|
||||
# thread safe
|
||||
#
|
||||
# OPTS Extra compiler command-line options.
|
||||
#
|
||||
# EXE The suffix to add to executable files. ".exe" for windows
|
||||
# and "" for Unix.
|
||||
#
|
||||
# TCC C Compiler and options for use in building executables that
|
||||
# will run on the target platform. This is usually the same
|
||||
# as BCC, unless you are cross-compiling.
|
||||
#
|
||||
# AR Tools used to build a static library.
|
||||
# RANLIB
|
||||
#
|
||||
# TCL_FLAGS Extra compiler options needed for programs that use the
|
||||
# TCL library.
|
||||
#
|
||||
# LIBTCL Linker options needed to link against the TCL library.
|
||||
#
|
||||
# READLINE_FLAGS Compiler options needed for programs that use the
|
||||
# readline() library.
|
||||
#
|
||||
# LIBREADLINE Linker options needed by programs using readline() must
|
||||
# link against.
|
||||
#
|
||||
# NAWK Nawk compatible awk program. Older (obsolete?) solaris
|
||||
# systems need this to avoid using the original AT&T AWK.
|
||||
#
|
||||
# Once the macros above are defined, the rest of this make script will
|
||||
# build the SQLite library and testing tools.
|
||||
################################################################################
|
||||
|
||||
# This is how we compile
|
||||
#
|
||||
TCCX = $(TCC) $(OPTS) -I. -I$(TOP)/src -I$(TOP)
|
||||
TCCX_SHARED = $(TCC_SHARED) $(OPTS) -I. -I$(TOP)/src -I$(TOP) \
|
||||
-I$(TOP)/ext/rtree -I$(TOP)/ext/icu -I$(TOP)/ext/fts3 \
|
||||
-I$(TOP)/ext/async
|
||||
|
||||
# Object files for the SQLite library.
|
||||
#
|
||||
LIBOBJ+= alter.o analyze.o attach.o auth.o \
|
||||
backup.o bitvec.o btmutex.o btree.o build.o \
|
||||
callback.o complete.o date.o delete.o expr.o fault.o \
|
||||
fts3.o fts3_expr.o fts3_hash.o fts3_icu.o fts3_porter.o \
|
||||
fts3_tokenizer.o fts3_tokenizer1.o \
|
||||
func.o global.o hash.o \
|
||||
icu.o insert.o journal.o legacy.o loadext.o \
|
||||
main.o malloc.o mem0.o mem1.o mem2.o mem3.o mem5.o \
|
||||
memjournal.o \
|
||||
mutex.o mutex_noop.o mutex_os2.o mutex_unix.o mutex_w32.o \
|
||||
notify.o opcodes.o os.o os_os2.o os_unix.o os_win.o \
|
||||
pager.o parse.o pcache.o pcache1.o pragma.o prepare.o printf.o \
|
||||
random.o resolve.o rowset.o rtree.o select.o status.o \
|
||||
table.o tokenize.o trigger.o \
|
||||
update.o util.o vacuum.o \
|
||||
vdbe.o vdbeapi.o vdbeaux.o vdbeblob.o vdbemem.o \
|
||||
walker.o where.o utf.o vtab.o
|
||||
|
||||
|
||||
|
||||
# All of the source code files.
|
||||
#
|
||||
SRC = \
|
||||
$(TOP)/src/alter.c \
|
||||
$(TOP)/src/analyze.c \
|
||||
$(TOP)/src/attach.c \
|
||||
$(TOP)/src/auth.c \
|
||||
$(TOP)/src/backup.c \
|
||||
$(TOP)/src/bitvec.c \
|
||||
$(TOP)/src/btmutex.c \
|
||||
$(TOP)/src/btree.c \
|
||||
$(TOP)/src/btree.h \
|
||||
$(TOP)/src/btreeInt.h \
|
||||
$(TOP)/src/build.c \
|
||||
$(TOP)/src/callback.c \
|
||||
$(TOP)/src/complete.c \
|
||||
$(TOP)/src/ctime.c \
|
||||
$(TOP)/src/date.c \
|
||||
$(TOP)/src/delete.c \
|
||||
$(TOP)/src/expr.c \
|
||||
$(TOP)/src/fault.c \
|
||||
$(TOP)/src/func.c \
|
||||
$(TOP)/src/global.c \
|
||||
$(TOP)/src/hash.c \
|
||||
$(TOP)/src/hash.h \
|
||||
$(TOP)/src/hwtime.h \
|
||||
$(TOP)/src/insert.c \
|
||||
$(TOP)/src/journal.c \
|
||||
$(TOP)/src/legacy.c \
|
||||
$(TOP)/src/loadext.c \
|
||||
$(TOP)/src/main.c \
|
||||
$(TOP)/src/malloc.c \
|
||||
$(TOP)/src/mem0.c \
|
||||
$(TOP)/src/mem1.c \
|
||||
$(TOP)/src/mem2.c \
|
||||
$(TOP)/src/mem3.c \
|
||||
$(TOP)/src/mem5.c \
|
||||
$(TOP)/src/memjournal.c \
|
||||
$(TOP)/src/mutex.c \
|
||||
$(TOP)/src/mutex.h \
|
||||
$(TOP)/src/mutex_noop.c \
|
||||
$(TOP)/src/mutex_os2.c \
|
||||
$(TOP)/src/mutex_unix.c \
|
||||
$(TOP)/src/mutex_w32.c \
|
||||
$(TOP)/src/notify.c \
|
||||
$(TOP)/src/os.c \
|
||||
$(TOP)/src/os.h \
|
||||
$(TOP)/src/os_common.h \
|
||||
$(TOP)/src/os_os2.c \
|
||||
$(TOP)/src/os_unix.c \
|
||||
$(TOP)/src/os_win.c \
|
||||
$(TOP)/src/pager.c \
|
||||
$(TOP)/src/pager.h \
|
||||
$(TOP)/src/parse.y \
|
||||
$(TOP)/src/pcache.c \
|
||||
$(TOP)/src/pcache.h \
|
||||
$(TOP)/src/pcache1.c \
|
||||
$(TOP)/src/pragma.c \
|
||||
$(TOP)/src/prepare.c \
|
||||
$(TOP)/src/printf.c \
|
||||
$(TOP)/src/random.c \
|
||||
$(TOP)/src/resolve.c \
|
||||
$(TOP)/src/rowset.c \
|
||||
$(TOP)/src/select.c \
|
||||
$(TOP)/src/status.c \
|
||||
$(TOP)/src/shell.c \
|
||||
$(TOP)/src/sqlite.h.in \
|
||||
$(TOP)/src/sqlite3ext.h \
|
||||
$(TOP)/src/sqliteInt.h \
|
||||
$(TOP)/src/sqliteLimit.h \
|
||||
$(TOP)/src/table.c \
|
||||
$(TOP)/src/tclsqlite.c \
|
||||
$(TOP)/src/tokenize.c \
|
||||
$(TOP)/src/trigger.c \
|
||||
$(TOP)/src/utf.c \
|
||||
$(TOP)/src/update.c \
|
||||
$(TOP)/src/util.c \
|
||||
$(TOP)/src/vacuum.c \
|
||||
$(TOP)/src/vdbe.c \
|
||||
$(TOP)/src/vdbe.h \
|
||||
$(TOP)/src/vdbeapi.c \
|
||||
$(TOP)/src/vdbeaux.c \
|
||||
$(TOP)/src/vdbeblob.c \
|
||||
$(TOP)/src/vdbemem.c \
|
||||
$(TOP)/src/vdbeInt.h \
|
||||
$(TOP)/src/vtab.c \
|
||||
$(TOP)/src/walker.c \
|
||||
$(TOP)/src/where.c
|
||||
|
||||
# Source code for extensions
|
||||
#
|
||||
SRC += \
|
||||
$(TOP)/ext/fts1/fts1.c \
|
||||
$(TOP)/ext/fts1/fts1.h \
|
||||
$(TOP)/ext/fts1/fts1_hash.c \
|
||||
$(TOP)/ext/fts1/fts1_hash.h \
|
||||
$(TOP)/ext/fts1/fts1_porter.c \
|
||||
$(TOP)/ext/fts1/fts1_tokenizer.h \
|
||||
$(TOP)/ext/fts1/fts1_tokenizer1.c
|
||||
SRC += \
|
||||
$(TOP)/ext/fts2/fts2.c \
|
||||
$(TOP)/ext/fts2/fts2.h \
|
||||
$(TOP)/ext/fts2/fts2_hash.c \
|
||||
$(TOP)/ext/fts2/fts2_hash.h \
|
||||
$(TOP)/ext/fts2/fts2_icu.c \
|
||||
$(TOP)/ext/fts2/fts2_porter.c \
|
||||
$(TOP)/ext/fts2/fts2_tokenizer.h \
|
||||
$(TOP)/ext/fts2/fts2_tokenizer.c \
|
||||
$(TOP)/ext/fts2/fts2_tokenizer1.c
|
||||
SRC += \
|
||||
$(TOP)/ext/fts3/fts3.c \
|
||||
$(TOP)/ext/fts3/fts3.h \
|
||||
$(TOP)/ext/fts3/fts3_expr.c \
|
||||
$(TOP)/ext/fts3/fts3_expr.h \
|
||||
$(TOP)/ext/fts3/fts3_hash.c \
|
||||
$(TOP)/ext/fts3/fts3_hash.h \
|
||||
$(TOP)/ext/fts3/fts3_icu.c \
|
||||
$(TOP)/ext/fts3/fts3_porter.c \
|
||||
$(TOP)/ext/fts3/fts3_tokenizer.h \
|
||||
$(TOP)/ext/fts3/fts3_tokenizer.c \
|
||||
$(TOP)/ext/fts3/fts3_tokenizer1.c
|
||||
SRC += \
|
||||
$(TOP)/ext/icu/sqliteicu.h \
|
||||
$(TOP)/ext/icu/icu.c
|
||||
SRC += \
|
||||
$(TOP)/ext/rtree/rtree.h \
|
||||
$(TOP)/ext/rtree/rtree.c
|
||||
|
||||
|
||||
# Generated source code files
|
||||
#
|
||||
SRC += \
|
||||
keywordhash.h \
|
||||
opcodes.c \
|
||||
opcodes.h \
|
||||
parse.c \
|
||||
parse.h \
|
||||
sqlite3.h
|
||||
|
||||
|
||||
# Source code to the test files.
|
||||
#
|
||||
TESTSRC = \
|
||||
$(TOP)/src/test1.c \
|
||||
$(TOP)/src/test2.c \
|
||||
$(TOP)/src/test3.c \
|
||||
$(TOP)/src/test4.c \
|
||||
$(TOP)/src/test5.c \
|
||||
$(TOP)/src/test6.c \
|
||||
$(TOP)/src/test7.c \
|
||||
$(TOP)/src/test8.c \
|
||||
$(TOP)/src/test9.c \
|
||||
$(TOP)/src/test_autoext.c \
|
||||
$(TOP)/src/test_async.c \
|
||||
$(TOP)/src/test_backup.c \
|
||||
$(TOP)/src/test_btree.c \
|
||||
$(TOP)/src/test_config.c \
|
||||
$(TOP)/src/test_devsym.c \
|
||||
$(TOP)/src/test_func.c \
|
||||
$(TOP)/src/test_hexio.c \
|
||||
$(TOP)/src/test_journal.c \
|
||||
$(TOP)/src/test_malloc.c \
|
||||
$(TOP)/src/test_md5.c \
|
||||
$(TOP)/src/test_mutex.c \
|
||||
$(TOP)/src/test_onefile.c \
|
||||
$(TOP)/src/test_osinst.c \
|
||||
$(TOP)/src/test_pcache.c \
|
||||
$(TOP)/src/test_schema.c \
|
||||
$(TOP)/src/test_server.c \
|
||||
$(TOP)/src/test_tclvar.c \
|
||||
$(TOP)/src/test_thread.c \
|
||||
$(TOP)/src/test_vfs.c \
|
||||
$(TOP)/src/test_wsd.c \
|
||||
|
||||
#TESTSRC += $(TOP)/ext/fts2/fts2_tokenizer.c
|
||||
#TESTSRC += $(TOP)/ext/fts3/fts3_tokenizer.c
|
||||
|
||||
TESTSRC2 = \
|
||||
$(TOP)/src/attach.c $(TOP)/src/backup.c $(TOP)/src/btree.c \
|
||||
$(TOP)/src/build.c $(TOP)/src/ctime.c $(TOP)/src/date.c \
|
||||
$(TOP)/src/expr.c $(TOP)/src/func.c $(TOP)/src/insert.c $(TOP)/src/os.c \
|
||||
$(TOP)/src/os_os2.c $(TOP)/src/os_unix.c $(TOP)/src/os_win.c \
|
||||
$(TOP)/src/pager.c $(TOP)/src/pragma.c $(TOP)/src/prepare.c \
|
||||
$(TOP)/src/printf.c $(TOP)/src/random.c $(TOP)/src/pcache.c \
|
||||
$(TOP)/src/pcache1.c $(TOP)/src/select.c $(TOP)/src/tokenize.c \
|
||||
$(TOP)/src/utf.c $(TOP)/src/util.c $(TOP)/src/vdbeapi.c $(TOP)/src/vdbeaux.c \
|
||||
$(TOP)/src/vdbe.c $(TOP)/src/vdbemem.c $(TOP)/src/where.c parse.c \
|
||||
$(TOP)/ext/fts3/fts3.c $(TOP)/ext/fts3/fts3_expr.c \
|
||||
$(TOP)/ext/fts3/fts3_tokenizer.c \
|
||||
$(TOP)/ext/async/sqlite3async.c
|
||||
|
||||
# Header files used by all library source files.
|
||||
#
|
||||
HDR = \
|
||||
$(TOP)/src/btree.h \
|
||||
$(TOP)/src/btreeInt.h \
|
||||
$(TOP)/src/hash.h \
|
||||
$(TOP)/src/hwtime.h \
|
||||
keywordhash.h \
|
||||
$(TOP)/src/mutex.h \
|
||||
opcodes.h \
|
||||
$(TOP)/src/os.h \
|
||||
$(TOP)/src/os_common.h \
|
||||
$(TOP)/src/pager.h \
|
||||
$(TOP)/src/pcache.h \
|
||||
parse.h \
|
||||
sqlite3.h \
|
||||
$(TOP)/src/sqlite3ext.h \
|
||||
$(TOP)/src/sqliteInt.h \
|
||||
$(TOP)/src/sqliteLimit.h \
|
||||
$(TOP)/src/vdbe.h \
|
||||
$(TOP)/src/vdbeInt.h
|
||||
|
||||
# Header files used by extensions
|
||||
#
|
||||
EXTHDR += \
|
||||
$(TOP)/ext/fts1/fts1.h \
|
||||
$(TOP)/ext/fts1/fts1_hash.h \
|
||||
$(TOP)/ext/fts1/fts1_tokenizer.h
|
||||
EXTHDR += \
|
||||
$(TOP)/ext/fts2/fts2.h \
|
||||
$(TOP)/ext/fts2/fts2_hash.h \
|
||||
$(TOP)/ext/fts2/fts2_tokenizer.h
|
||||
EXTHDR += \
|
||||
$(TOP)/ext/fts3/fts3.h \
|
||||
$(TOP)/ext/fts3/fts3_expr.h \
|
||||
$(TOP)/ext/fts3/fts3_hash.h \
|
||||
$(TOP)/ext/fts3/fts3_tokenizer.h
|
||||
EXTHDR += \
|
||||
$(TOP)/ext/rtree/rtree.h
|
||||
EXTHDR += \
|
||||
$(TOP)/ext/icu/sqliteicu.h
|
||||
|
||||
# This is the default Makefile target. The objects listed here
|
||||
# are what get build when you type just "make" with no arguments.
|
||||
#
|
||||
all: sqlite3.h libsqlite3.a sqlite3$(EXE)
|
||||
|
||||
libsqlite3.a: $(LIBOBJ)
|
||||
$(AR) libsqlite3.a $(LIBOBJ)
|
||||
$(RANLIB) libsqlite3.a
|
||||
|
||||
$(SHPREFIX)sqlite3.$(SO): $(LIBOBJ)
|
||||
$(MKSHLIB) -o $(SHPREFIX)sqlite3.$(SO) $(LIBOBJ) $(TLIBS_SHARED)
|
||||
|
||||
sqlite3$(EXE): $(TOP)/src/shell.c libsqlite3.a sqlite3.h
|
||||
$(TCCX) $(READLINE_FLAGS) -o sqlite3$(EXE) \
|
||||
$(TOP)/src/shell.c \
|
||||
$(LIBREADLINE) $(TLIBS) $(THREADLIB) -L. -lsqlite3
|
||||
|
||||
# This target creates a directory named "tsrc" and fills it with
|
||||
# copies of all of the C source code and header files needed to
|
||||
# build on the target system. Some of the C source code and header
|
||||
# files are automatically generated. This target takes care of
|
||||
# all that automatic generation.
|
||||
#
|
||||
target_source: $(SRC)
|
||||
rm -rf tsrc
|
||||
mkdir tsrc
|
||||
cp -f $(SRC) tsrc
|
||||
rm tsrc/sqlite.h.in tsrc/parse.y
|
||||
touch target_source
|
||||
|
||||
sqlite3.c: target_source $(TOP)/tool/mksqlite3c.tcl
|
||||
tclsh $(TOP)/tool/mksqlite3c.tcl
|
||||
cp sqlite3.c tclsqlite3.c
|
||||
cat $(TOP)/src/tclsqlite.c >>tclsqlite3.c
|
||||
|
||||
fts2amal.c: target_source $(TOP)/ext/fts2/mkfts2amal.tcl
|
||||
tclsh $(TOP)/ext/fts2/mkfts2amal.tcl
|
||||
|
||||
fts3amal.c: target_source $(TOP)/ext/fts3/mkfts3amal.tcl
|
||||
tclsh $(TOP)/ext/fts3/mkfts3amal.tcl
|
||||
|
||||
# Rules to build the LEMON compiler generator
|
||||
#
|
||||
lemon: $(TOP)/tool/lemon.c $(TOP)/src/lempar.c
|
||||
$(BCC) -o lemon $(TOP)/tool/lemon.c
|
||||
cp $(TOP)/src/lempar.c .
|
||||
|
||||
# Rules to build individual *.o files from generated *.c files. This
|
||||
# applies to:
|
||||
#
|
||||
# parse.o
|
||||
# opcodes.o
|
||||
#
|
||||
%.o: %.c $(HDR)
|
||||
$(TCCX_SHARED) -c $<
|
||||
|
||||
# Rules to build individual *.o files from files in the src directory.
|
||||
#
|
||||
%.o: $(TOP)/src/%.c $(HDR)
|
||||
$(TCCX_SHARED) -c $<
|
||||
|
||||
tclsqlite.o: $(TOP)/src/tclsqlite.c $(HDR)
|
||||
$(TCCX_SHARED) $(TCL_FLAGS) -c $(TOP)/src/tclsqlite.c
|
||||
|
||||
|
||||
|
||||
# Rules to build opcodes.c and opcodes.h
|
||||
#
|
||||
opcodes.c: opcodes.h $(TOP)/mkopcodec.awk
|
||||
$(NAWK) -f $(TOP)/mkopcodec.awk opcodes.h >opcodes.c
|
||||
|
||||
opcodes.h: parse.h $(TOP)/src/vdbe.c $(TOP)/mkopcodeh.awk
|
||||
cat parse.h $(TOP)/src/vdbe.c | \
|
||||
$(NAWK) -f $(TOP)/mkopcodeh.awk >opcodes.h
|
||||
|
||||
# Rules to build parse.c and parse.h - the outputs of lemon.
|
||||
#
|
||||
parse.h: parse.c
|
||||
|
||||
parse.c: $(TOP)/src/parse.y lemon $(TOP)/addopcodes.awk
|
||||
cp $(TOP)/src/parse.y .
|
||||
rm -f parse.h
|
||||
./lemon $(OPTS) parse.y
|
||||
mv parse.h parse.h.temp
|
||||
awk -f $(TOP)/addopcodes.awk parse.h.temp >parse.h
|
||||
|
||||
sqlite3.h: $(TOP)/src/sqlite.h.in
|
||||
sed -e s/--VERS--/`cat ${TOP}/VERSION`/ \
|
||||
-e s/--VERSION-NUMBER--/`cat ${TOP}/VERSION | sed 's/[^0-9]/ /g' | $(NAWK) '{printf "%d%03d%03d",$$1,$$2,$$3}'`/ \
|
||||
$(TOP)/src/sqlite.h.in >sqlite3.h
|
||||
|
||||
keywordhash.h: $(TOP)/tool/mkkeywordhash.c
|
||||
$(BCC) -o mkkeywordhash $(OPTS) $(TOP)/tool/mkkeywordhash.c
|
||||
./mkkeywordhash >keywordhash.h
|
||||
|
||||
|
||||
|
||||
# Rules to build the extension objects.
|
||||
#
|
||||
icu.o: $(TOP)/ext/icu/icu.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/icu/icu.c
|
||||
|
||||
fts2.o: $(TOP)/ext/fts2/fts2.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2.c
|
||||
|
||||
fts2_hash.o: $(TOP)/ext/fts2/fts2_hash.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2_hash.c
|
||||
|
||||
fts2_icu.o: $(TOP)/ext/fts2/fts2_icu.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2_icu.c
|
||||
|
||||
fts2_porter.o: $(TOP)/ext/fts2/fts2_porter.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2_porter.c
|
||||
|
||||
fts2_tokenizer.o: $(TOP)/ext/fts2/fts2_tokenizer.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2_tokenizer.c
|
||||
|
||||
fts2_tokenizer1.o: $(TOP)/ext/fts2/fts2_tokenizer1.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts2/fts2_tokenizer1.c
|
||||
|
||||
fts3.o: $(TOP)/ext/fts3/fts3.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3.c
|
||||
|
||||
fts3_expr.o: $(TOP)/ext/fts3/fts3_expr.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_expr.c
|
||||
|
||||
fts3_hash.o: $(TOP)/ext/fts3/fts3_hash.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_hash.c
|
||||
|
||||
fts3_icu.o: $(TOP)/ext/fts3/fts3_icu.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_icu.c
|
||||
|
||||
fts3_porter.o: $(TOP)/ext/fts3/fts3_porter.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_porter.c
|
||||
|
||||
fts3_tokenizer.o: $(TOP)/ext/fts3/fts3_tokenizer.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_tokenizer.c
|
||||
|
||||
fts3_tokenizer1.o: $(TOP)/ext/fts3/fts3_tokenizer1.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/fts3/fts3_tokenizer1.c
|
||||
|
||||
rtree.o: $(TOP)/ext/rtree/rtree.c $(HDR) $(EXTHDR)
|
||||
$(TCCX_SHARED) -DSQLITE_CORE -c $(TOP)/ext/rtree/rtree.c
|
||||
|
||||
|
||||
# Rules for building test programs and for running tests
|
||||
#
|
||||
tclsqlite3: $(TOP)/src/tclsqlite.c libsqlite3.a
|
||||
$(TCCX_SHARED) $(TCL_FLAGS) -DTCLSH=1 -o tclsqlite3 \
|
||||
$(TOP)/src/tclsqlite.c libsqlite3.a $(LIBTCL) $(THREADLIB)
|
||||
|
||||
|
||||
# Rules to build the 'testfixture' application.
|
||||
#
|
||||
TESTFIXTURE_FLAGS = -DTCLSH=1 -DSQLITE_TEST=1 -DSQLITE_CRASH_TEST=1
|
||||
TESTFIXTURE_FLAGS += -DSQLITE_SERVER=1 -DSQLITE_PRIVATE="" -DSQLITE_CORE
|
||||
|
||||
testfixture$(EXE): $(TESTSRC2) libsqlite3.a $(TESTSRC) $(TOP)/src/tclsqlite.c
|
||||
$(TCCX) $(TCL_FLAGS) $(TESTFIXTURE_FLAGS) \
|
||||
$(TESTSRC) $(TESTSRC2) $(TOP)/src/tclsqlite.c \
|
||||
-o testfixture$(EXE) $(LIBTCL) $(THREADLIB) libsqlite3.a
|
||||
|
||||
amalgamation-testfixture$(EXE): sqlite3.c $(TESTSRC) $(TOP)/src/tclsqlite.c
|
||||
$(TCCX) $(TCL_FLAGS) $(TESTFIXTURE_FLAGS) \
|
||||
$(TESTSRC) $(TOP)/src/tclsqlite.c sqlite3.c \
|
||||
-o testfixture$(EXE) $(LIBTCL) $(THREADLIB)
|
||||
|
||||
fts3-testfixture$(EXE): sqlite3.c fts3amal.c $(TESTSRC) $(TOP)/src/tclsqlite.c
|
||||
$(TCCX) $(TCL_FLAGS) $(TESTFIXTURE_FLAGS) \
|
||||
-DSQLITE_ENABLE_FTS3=1 \
|
||||
$(TESTSRC) $(TOP)/src/tclsqlite.c sqlite3.c fts3amal.c \
|
||||
-o testfixture$(EXE) $(LIBTCL) $(THREADLIB)
|
||||
|
||||
fulltest: testfixture$(EXE) sqlite3$(EXE)
|
||||
./testfixture$(EXE) $(TOP)/test/all.test
|
||||
|
||||
soaktest: testfixture$(EXE) sqlite3$(EXE)
|
||||
./testfixture$(EXE) $(TOP)/test/all.test -soak=1
|
||||
|
||||
test: testfixture$(EXE) sqlite3$(EXE)
|
||||
./testfixture$(EXE) $(TOP)/test/veryquick.test
|
||||
|
||||
sqlite3_analyzer$(EXE): $(TOP)/src/tclsqlite.c sqlite3.c $(TESTSRC) \
|
||||
$(TOP)/tool/spaceanal.tcl
|
||||
sed \
|
||||
-e '/^#/d' \
|
||||
-e 's,\\,\\\\,g' \
|
||||
-e 's,",\\",g' \
|
||||
-e 's,^,",' \
|
||||
-e 's,$$,\\n",' \
|
||||
$(TOP)/tool/spaceanal.tcl >spaceanal_tcl.h
|
||||
$(TCCX) $(TCL_FLAGS) $(TESTFIXTURE_FLAGS) \
|
||||
-DTCLSH=2 -DSQLITE_TEST=1 -DSQLITE_DEBUG=1 -DSQLITE_PRIVATE="" \
|
||||
$(TESTSRC) $(TOP)/src/tclsqlite.c sqlite3.c \
|
||||
-o sqlite3_analyzer$(EXE) \
|
||||
$(LIBTCL) $(THREADLIB)
|
||||
|
||||
TEST_EXTENSION = $(SHPREFIX)testloadext.$(SO)
|
||||
$(TEST_EXTENSION): $(TOP)/src/test_loadext.c
|
||||
$(MKSHLIB) $(TOP)/src/test_loadext.c -o $(TEST_EXTENSION)
|
||||
|
||||
extensiontest: testfixture$(EXE) $(TEST_EXTENSION)
|
||||
./testfixture$(EXE) $(TOP)/test/loadext.test
|
||||
|
||||
clean:
|
||||
rm -f *.o sqlite3$(EXE) libsqlite3.a sqlite3.h opcodes.*
|
||||
rm -f lemon lempar.c parse.* sqlite*.tar.gz mkkeywordhash keywordhash.h
|
||||
rm -f $(PUBLISH)
|
||||
rm -f *.da *.bb *.bbg gmon.out
|
||||
rm -rf tsrc target_source
|
||||
rm -f testloadext.dll libtestloadext.so
|
||||
rm -f sqlite3.c fts?amal.c tclsqlite3.c
|
||||
rm -f $(SHPREFIX)sqlite3.$(SO)
|
||||
@@ -0,0 +1,39 @@
|
||||
This directory contains source code to
|
||||
|
||||
SQLite: An Embeddable SQL Database Engine
|
||||
|
||||
To compile the project, first create a directory in which to place
|
||||
the build products. It is recommended, but not required, that the
|
||||
build directory be separate from the source directory. Cd into the
|
||||
build directory and then from the build directory run the configure
|
||||
script found at the root of the source tree. Then run "make".
|
||||
|
||||
For example:
|
||||
|
||||
tar xzf sqlite.tar.gz ;# Unpack the source tree into "sqlite"
|
||||
mkdir bld ;# Build will occur in a sibling directory
|
||||
cd bld ;# Change to the build directory
|
||||
../sqlite/configure ;# Run the configure script
|
||||
make ;# Run the makefile.
|
||||
make install ;# (Optional) Install the build products
|
||||
|
||||
The configure script uses autoconf 2.61 and libtool. If the configure
|
||||
script does not work out for you, there is a generic makefile named
|
||||
"Makefile.linux-gcc" in the top directory of the source tree that you
|
||||
can copy and edit to suit your needs. Comments on the generic makefile
|
||||
show what changes are needed.
|
||||
|
||||
The linux binaries on the website are created using the generic makefile,
|
||||
not the configure script. The windows binaries on the website are created
|
||||
using MinGW32 configured as a cross-compiler running under Linux. For
|
||||
details, see the ./publish.sh script at the top-level of the source tree.
|
||||
The developers do not use teh configure script.
|
||||
|
||||
SQLite does not require TCL to run, but a TCL installation is required
|
||||
by the makefiles. SQLite contains a lot of generated code and TCL is
|
||||
used to do much of that code generation. The makefile also requires
|
||||
AWK.
|
||||
|
||||
Contacts:
|
||||
|
||||
http://www.sqlite.org/
|
||||
@@ -1,303 +0,0 @@
|
||||
<h1 align="center">SQLite Source Repository</h1>
|
||||
|
||||
This repository contains the complete source code for the
|
||||
[SQLite database engine](https://sqlite.org/). Some test scripts
|
||||
are also included. However, many other test scripts
|
||||
and most of the documentation are managed separately.
|
||||
|
||||
SQLite [does not use Git](https://sqlite.org/whynotgit.html).
|
||||
If you are reading this on GitHub, then you are looking at an
|
||||
unofficial mirror. See <https://sqlite.org/src> for the official
|
||||
repository.
|
||||
|
||||
## Obtaining The Code
|
||||
|
||||
SQLite sources are managed using the
|
||||
[Fossil](https://www.fossil-scm.org/), a distributed version control system
|
||||
that was specifically designed to support SQLite development.
|
||||
If you do not want to use Fossil, you can download tarballs or ZIP
|
||||
archives or [SQLite archives](https://sqlite.org/cli.html#sqlar) as follows:
|
||||
|
||||
* Lastest trunk check-in as
|
||||
[Tarball](https://www.sqlite.org/src/tarball/sqlite.tar.gz),
|
||||
[ZIP-archive](https://www.sqlite.org/src/zip/sqlite.zip), or
|
||||
[SQLite-archive](https://www.sqlite.org/src/sqlar/sqlite.sqlar).
|
||||
|
||||
* Latest release as
|
||||
[Tarball](https://www.sqlite.org/src/tarball/sqlite.tar.gz?r=release),
|
||||
[ZIP-archive](https://www.sqlite.org/src/zip/sqlite.zip?r=release), or
|
||||
[SQLite-archive](https://www.sqlite.org/src/sqlar/sqlite.sqlar?r=release).
|
||||
|
||||
* For other check-ins, substitute an appropriate branch name or
|
||||
tag or hash prefix for "release" in the URLs of the previous
|
||||
bullet. Or browse the [timeline](https://www.sqlite.org/src/timeline)
|
||||
to locate the check-in desired, click on its information page link,
|
||||
then click on the "Tarball" or "ZIP Archive" links on the information
|
||||
page.
|
||||
|
||||
If you do want to use Fossil to check out the source tree,
|
||||
first install Fossil version 2.0 or later.
|
||||
(Source tarballs and precompiled binaries available
|
||||
[here](https://www.fossil-scm.org/fossil/uv/download.html). Fossil is
|
||||
a stand-alone program. To install, simply download or build the single
|
||||
executable file and put that file someplace on your $PATH.)
|
||||
Then run commands like this:
|
||||
|
||||
mkdir ~/sqlite
|
||||
cd ~/sqlite
|
||||
fossil clone https://www.sqlite.org/src sqlite.fossil
|
||||
fossil open sqlite.fossil
|
||||
|
||||
After setting up a repository using the steps above, you can always
|
||||
update to the lastest version using:
|
||||
|
||||
fossil update trunk ;# latest trunk check-in
|
||||
fossil update release ;# latest official release
|
||||
|
||||
Or type "fossil ui" to get a web-based user interface.
|
||||
|
||||
## Compiling
|
||||
|
||||
First create a directory in which to place
|
||||
the build products. It is recommended, but not required, that the
|
||||
build directory be separate from the source directory. Cd into the
|
||||
build directory and then from the build directory run the configure
|
||||
script found at the root of the source tree. Then run "make".
|
||||
|
||||
For example:
|
||||
|
||||
tar xzf sqlite.tar.gz ;# Unpack the source tree into "sqlite"
|
||||
mkdir bld ;# Build will occur in a sibling directory
|
||||
cd bld ;# Change to the build directory
|
||||
../sqlite/configure ;# Run the configure script
|
||||
make ;# Run the makefile.
|
||||
make sqlite3.c ;# Build the "amalgamation" source file
|
||||
make test ;# Run some tests (requires Tcl)
|
||||
|
||||
See the makefile for additional targets.
|
||||
|
||||
The configure script uses autoconf 2.61 and libtool. If the configure
|
||||
script does not work out for you, there is a generic makefile named
|
||||
"Makefile.linux-gcc" in the top directory of the source tree that you
|
||||
can copy and edit to suit your needs. Comments on the generic makefile
|
||||
show what changes are needed.
|
||||
|
||||
## Using MSVC
|
||||
|
||||
On Windows, all applicable build products can be compiled with MSVC.
|
||||
First open the command prompt window associated with the desired compiler
|
||||
version (e.g. "Developer Command Prompt for VS2013"). Next, use NMAKE
|
||||
with the provided "Makefile.msc" to build one of the supported targets.
|
||||
|
||||
For example:
|
||||
|
||||
mkdir bld
|
||||
cd bld
|
||||
nmake /f Makefile.msc TOP=..\sqlite
|
||||
nmake /f Makefile.msc sqlite3.c TOP=..\sqlite
|
||||
nmake /f Makefile.msc sqlite3.dll TOP=..\sqlite
|
||||
nmake /f Makefile.msc sqlite3.exe TOP=..\sqlite
|
||||
nmake /f Makefile.msc test TOP=..\sqlite
|
||||
|
||||
There are several build options that can be set via the NMAKE command
|
||||
line. For example, to build for WinRT, simply add "FOR_WINRT=1" argument
|
||||
to the "sqlite3.dll" command line above. When debugging into the SQLite
|
||||
code, adding the "DEBUG=1" argument to one of the above command lines is
|
||||
recommended.
|
||||
|
||||
SQLite does not require [Tcl](http://www.tcl.tk/) to run, but a Tcl installation
|
||||
is required by the makefiles (including those for MSVC). SQLite contains
|
||||
a lot of generated code and Tcl is used to do much of that code generation.
|
||||
|
||||
## Source Code Tour
|
||||
|
||||
Most of the core source files are in the **src/** subdirectory. The
|
||||
**src/** folder also contains files used to build the "testfixture" test
|
||||
harness. The names of the source files used by "testfixture" all begin
|
||||
with "test".
|
||||
The **src/** also contains the "shell.c" file
|
||||
which is the main program for the "sqlite3.exe"
|
||||
[command-line shell](https://sqlite.org/cli.html) and
|
||||
the "tclsqlite.c" file which implements the
|
||||
[Tcl bindings](https://sqlite.org/tclsqlite.html) for SQLite.
|
||||
(Historical note: SQLite began as a Tcl
|
||||
extension and only later escaped to the wild as an independent library.)
|
||||
|
||||
Test scripts and programs are found in the **test/** subdirectory.
|
||||
Addtional test code is found in other source repositories.
|
||||
See [How SQLite Is Tested](http://www.sqlite.org/testing.html) for
|
||||
additional information.
|
||||
|
||||
The **ext/** subdirectory contains code for extensions. The
|
||||
Full-text search engine is in **ext/fts3**. The R-Tree engine is in
|
||||
**ext/rtree**. The **ext/misc** subdirectory contains a number of
|
||||
smaller, single-file extensions, such as a REGEXP operator.
|
||||
|
||||
The **tool/** subdirectory contains various scripts and programs used
|
||||
for building generated source code files or for testing or for generating
|
||||
accessory programs such as "sqlite3_analyzer(.exe)".
|
||||
|
||||
### Generated Source Code Files
|
||||
|
||||
Several of the C-language source files used by SQLite are generated from
|
||||
other sources rather than being typed in manually by a programmer. This
|
||||
section will summarize those automatically-generated files. To create all
|
||||
of the automatically-generated files, simply run "make target_source".
|
||||
The "target_source" make target will create a subdirectory "tsrc/" and
|
||||
fill it with all the source files needed to build SQLite, both
|
||||
manually-edited files and automatically-generated files.
|
||||
|
||||
The SQLite interface is defined by the **sqlite3.h** header file, which is
|
||||
generated from src/sqlite.h.in, ./manifest.uuid, and ./VERSION. The
|
||||
[Tcl script](http://www.tcl.tk) at tool/mksqlite3h.tcl does the conversion.
|
||||
The manifest.uuid file contains the SHA3 hash of the particular check-in
|
||||
and is used to generate the SQLITE\_SOURCE\_ID macro. The VERSION file
|
||||
contains the current SQLite version number. The sqlite3.h header is really
|
||||
just a copy of src/sqlite.h.in with the source-id and version number inserted
|
||||
at just the right spots. Note that comment text in the sqlite3.h file is
|
||||
used to generate much of the SQLite API documentation. The Tcl scripts
|
||||
used to generate that documentation are in a separate source repository.
|
||||
|
||||
The SQL language parser is **parse.c** which is generate from a grammar in
|
||||
the src/parse.y file. The conversion of "parse.y" into "parse.c" is done
|
||||
by the [lemon](./doc/lemon.html) LALR(1) parser generator. The source code
|
||||
for lemon is at tool/lemon.c. Lemon uses the tool/lempar.c file as a
|
||||
template for generating its parser.
|
||||
|
||||
Lemon also generates the **parse.h** header file, at the same time it
|
||||
generates parse.c. But the parse.h header file is
|
||||
modified further (to add additional symbols) using the ./addopcodes.tcl
|
||||
Tcl script.
|
||||
|
||||
The **opcodes.h** header file contains macros that define the numbers
|
||||
corresponding to opcodes in the "VDBE" virtual machine. The opcodes.h
|
||||
file is generated by the scanning the src/vdbe.c source file. The
|
||||
Tcl script at ./mkopcodeh.tcl does this scan and generates opcodes.h.
|
||||
A second Tcl script, ./mkopcodec.tcl, then scans opcodes.h to generate
|
||||
the **opcodes.c** source file, which contains a reverse mapping from
|
||||
opcode-number to opcode-name that is used for EXPLAIN output.
|
||||
|
||||
The **keywordhash.h** header file contains the definition of a hash table
|
||||
that maps SQL language keywords (ex: "CREATE", "SELECT", "INDEX", etc.) into
|
||||
the numeric codes used by the parse.c parser. The keywordhash.h file is
|
||||
generated by a C-language program at tool mkkeywordhash.c.
|
||||
|
||||
The **pragma.h** header file contains various definitions used to parse
|
||||
and implement the PRAGMA statements. The header is generated by a
|
||||
script **tool/mkpragmatab.tcl**. If you want to add a new PRAGMA, edit
|
||||
the **tool/mkpragmatab.tcl** file to insert the information needed by the
|
||||
parser for your new PRAGMA, then run the script to regenerate the
|
||||
**pragma.h** header file.
|
||||
|
||||
### The Amalgamation
|
||||
|
||||
All of the individual C source code and header files (both manually-edited
|
||||
and automatically-generated) can be combined into a single big source file
|
||||
**sqlite3.c** called "the amalgamation". The amalgamation is the recommended
|
||||
way of using SQLite in a larger application. Combining all individual
|
||||
source code files into a single big source code file allows the C compiler
|
||||
to perform more cross-procedure analysis and generate better code. SQLite
|
||||
runs about 5% faster when compiled from the amalgamation versus when compiled
|
||||
from individual source files.
|
||||
|
||||
The amalgamation is generated from the tool/mksqlite3c.tcl Tcl script.
|
||||
First, all of the individual source files must be gathered into the tsrc/
|
||||
subdirectory (using the equivalent of "make target_source") then the
|
||||
tool/mksqlite3c.tcl script is run to copy them all together in just the
|
||||
right order while resolving internal "#include" references.
|
||||
|
||||
The amalgamation source file is more than 200K lines long. Some symbolic
|
||||
debuggers (most notably MSVC) are unable to deal with files longer than 64K
|
||||
lines. To work around this, a separate Tcl script, tool/split-sqlite3c.tcl,
|
||||
can be run on the amalgamation to break it up into a single small C file
|
||||
called **sqlite3-all.c** that does #include on about seven other files
|
||||
named **sqlite3-1.c**, **sqlite3-2.c**, ..., **sqlite3-7.c**. In this way,
|
||||
all of the source code is contained within a single translation unit so
|
||||
that the compiler can do extra cross-procedure optimization, but no
|
||||
individual source file exceeds 32K lines in length.
|
||||
|
||||
## How It All Fits Together
|
||||
|
||||
SQLite is modular in design.
|
||||
See the [architectural description](http://www.sqlite.org/arch.html)
|
||||
for details. Other documents that are useful in
|
||||
(helping to understand how SQLite works include the
|
||||
[file format](http://www.sqlite.org/fileformat2.html) description,
|
||||
the [virtual machine](http://www.sqlite.org/opcode.html) that runs
|
||||
prepared statements, the description of
|
||||
[how transactions work](http://www.sqlite.org/atomiccommit.html), and
|
||||
the [overview of the query planner](http://www.sqlite.org/optoverview.html).
|
||||
|
||||
Years of effort have gone into optimizating SQLite, both
|
||||
for small size and high performance. And optimizations tend to result in
|
||||
complex code. So there is a lot of complexity in the current SQLite
|
||||
implementation. It will not be the easiest library in the world to hack.
|
||||
|
||||
Key files:
|
||||
|
||||
* **sqlite.h.in** - This file defines the public interface to the SQLite
|
||||
library. Readers will need to be familiar with this interface before
|
||||
trying to understand how the library works internally.
|
||||
|
||||
* **sqliteInt.h** - this header file defines many of the data objects
|
||||
used internally by SQLite. In addition to "sqliteInt.h", some
|
||||
subsystems have their own header files.
|
||||
|
||||
* **parse.y** - This file describes the LALR(1) grammar that SQLite uses
|
||||
to parse SQL statements, and the actions that are taken at each step
|
||||
in the parsing process.
|
||||
|
||||
* **vdbe.c** - This file implements the virtual machine that runs
|
||||
prepared statements. There are various helper files whose names
|
||||
begin with "vdbe". The VDBE has access to the vdbeInt.h header file
|
||||
which defines internal data objects. The rest of SQLite interacts
|
||||
with the VDBE through an interface defined by vdbe.h.
|
||||
|
||||
* **where.c** - This file (together with its helper files named
|
||||
by "where*.c") analyzes the WHERE clause and generates
|
||||
virtual machine code to run queries efficiently. This file is
|
||||
sometimes called the "query optimizer". It has its own private
|
||||
header file, whereInt.h, that defines data objects used internally.
|
||||
|
||||
* **btree.c** - This file contains the implementation of the B-Tree
|
||||
storage engine used by SQLite. The interface to the rest of the system
|
||||
is defined by "btree.h". The "btreeInt.h" header defines objects
|
||||
used internally by btree.c and not published to the rest of the system.
|
||||
|
||||
* **pager.c** - This file contains the "pager" implementation, the
|
||||
module that implements transactions. The "pager.h" header file
|
||||
defines the interface between pager.c and the rest of the system.
|
||||
|
||||
* **os_unix.c** and **os_win.c** - These two files implement the interface
|
||||
between SQLite and the underlying operating system using the run-time
|
||||
pluggable VFS interface.
|
||||
|
||||
* **shell.c.in** - This file is not part of the core SQLite library. This
|
||||
is the file that, when linked against sqlite3.a, generates the
|
||||
"sqlite3.exe" command-line shell. The "shell.c.in" file is transformed
|
||||
into "shell.c" as part of the build process.
|
||||
|
||||
* **tclsqlite.c** - This file implements the Tcl bindings for SQLite. It
|
||||
is not part of the core SQLite library. But as most of the tests in this
|
||||
repository are written in Tcl, the Tcl language bindings are important.
|
||||
|
||||
* **test*.c** - Files in the src/ folder that begin with "test" go into
|
||||
building the "testfixture.exe" program. The testfixture.exe program is
|
||||
an enhanced Tcl shell. The testfixture.exe program runs scripts in the
|
||||
test/ folder to validate the core SQLite code. The testfixture program
|
||||
(and some other test programs too) is build and run when you type
|
||||
"make test".
|
||||
|
||||
* **ext/misc/json1.c** - This file implements the various JSON functions
|
||||
that are build into SQLite.
|
||||
|
||||
There are many other source files. Each has a succinct header comment that
|
||||
describes its purpose and role within the larger system.
|
||||
|
||||
|
||||
## Contacts
|
||||
|
||||
The main SQLite webpage is [http://www.sqlite.org/](http://www.sqlite.org/)
|
||||
with geographically distributed backups at
|
||||
[http://www2.sqlite.org/](http://www2.sqlite.org) and
|
||||
[http://www3.sqlite.org/](http://www3.sqlite.org).
|
||||
@@ -0,0 +1,34 @@
|
||||
#!/usr/bin/awk
|
||||
#
|
||||
# This script appends additional token codes to the end of the
|
||||
# parse.h file that lemon generates. These extra token codes are
|
||||
# not used by the parser. But they are used by the tokenizer and/or
|
||||
# the code generator.
|
||||
#
|
||||
#
|
||||
BEGIN {
|
||||
max = 0
|
||||
}
|
||||
/^#define TK_/ {
|
||||
print $0
|
||||
if( max<$3 ) max = $3
|
||||
}
|
||||
END {
|
||||
printf "#define TK_%-29s %4d\n", "TO_TEXT", ++max
|
||||
printf "#define TK_%-29s %4d\n", "TO_BLOB", ++max
|
||||
printf "#define TK_%-29s %4d\n", "TO_NUMERIC", ++max
|
||||
printf "#define TK_%-29s %4d\n", "TO_INT", ++max
|
||||
printf "#define TK_%-29s %4d\n", "TO_REAL", ++max
|
||||
printf "#define TK_%-29s %4d\n", "ISNOT", ++max
|
||||
printf "#define TK_%-29s %4d\n", "END_OF_FILE", ++max
|
||||
printf "#define TK_%-29s %4d\n", "ILLEGAL", ++max
|
||||
printf "#define TK_%-29s %4d\n", "SPACE", ++max
|
||||
printf "#define TK_%-29s %4d\n", "UNCLOSED_STRING", ++max
|
||||
printf "#define TK_%-29s %4d\n", "FUNCTION", ++max
|
||||
printf "#define TK_%-29s %4d\n", "COLUMN", ++max
|
||||
printf "#define TK_%-29s %4d\n", "AGG_FUNCTION", ++max
|
||||
printf "#define TK_%-29s %4d\n", "AGG_COLUMN", ++max
|
||||
printf "#define TK_%-29s %4d\n", "CONST_FUNC", ++max
|
||||
printf "#define TK_%-29s %4d\n", "UMINUS", ++max
|
||||
printf "#define TK_%-29s %4d\n", "UPLUS", ++max
|
||||
}
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 3.7 KiB |
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 3.0 KiB |
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 7.3 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 3.4 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 3.3 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 3.3 KiB |
@@ -1,370 +0,0 @@
|
||||
Installation Instructions
|
||||
*************************
|
||||
|
||||
Copyright (C) 1994-1996, 1999-2002, 2004-2011 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
Copying and distribution of this file, with or without modification,
|
||||
are permitted in any medium without royalty provided the copyright
|
||||
notice and this notice are preserved. This file is offered as-is,
|
||||
without warranty of any kind.
|
||||
|
||||
Basic Installation
|
||||
==================
|
||||
|
||||
Briefly, the shell commands `./configure; make; make install' should
|
||||
configure, build, and install this package. The following
|
||||
more-detailed instructions are generic; see the `README' file for
|
||||
instructions specific to this package. Some packages provide this
|
||||
`INSTALL' file but do not implement all of the features documented
|
||||
below. The lack of an optional feature in a given package is not
|
||||
necessarily a bug. More recommendations for GNU packages can be found
|
||||
in *note Makefile Conventions: (standards)Makefile Conventions.
|
||||
|
||||
The `configure' shell script attempts to guess correct values for
|
||||
various system-dependent variables used during compilation. It uses
|
||||
those values to create a `Makefile' in each directory of the package.
|
||||
It may also create one or more `.h' files containing system-dependent
|
||||
definitions. Finally, it creates a shell script `config.status' that
|
||||
you can run in the future to recreate the current configuration, and a
|
||||
file `config.log' containing compiler output (useful mainly for
|
||||
debugging `configure').
|
||||
|
||||
It can also use an optional file (typically called `config.cache'
|
||||
and enabled with `--cache-file=config.cache' or simply `-C') that saves
|
||||
the results of its tests to speed up reconfiguring. Caching is
|
||||
disabled by default to prevent problems with accidental use of stale
|
||||
cache files.
|
||||
|
||||
If you need to do unusual things to compile the package, please try
|
||||
to figure out how `configure' could check whether to do them, and mail
|
||||
diffs or instructions to the address given in the `README' so they can
|
||||
be considered for the next release. If you are using the cache, and at
|
||||
some point `config.cache' contains results you don't want to keep, you
|
||||
may remove or edit it.
|
||||
|
||||
The file `configure.ac' (or `configure.in') is used to create
|
||||
`configure' by a program called `autoconf'. You need `configure.ac' if
|
||||
you want to change it or regenerate `configure' using a newer version
|
||||
of `autoconf'.
|
||||
|
||||
The simplest way to compile this package is:
|
||||
|
||||
1. `cd' to the directory containing the package's source code and type
|
||||
`./configure' to configure the package for your system.
|
||||
|
||||
Running `configure' might take a while. While running, it prints
|
||||
some messages telling which features it is checking for.
|
||||
|
||||
2. Type `make' to compile the package.
|
||||
|
||||
3. Optionally, type `make check' to run any self-tests that come with
|
||||
the package, generally using the just-built uninstalled binaries.
|
||||
|
||||
4. Type `make install' to install the programs and any data files and
|
||||
documentation. When installing into a prefix owned by root, it is
|
||||
recommended that the package be configured and built as a regular
|
||||
user, and only the `make install' phase executed with root
|
||||
privileges.
|
||||
|
||||
5. Optionally, type `make installcheck' to repeat any self-tests, but
|
||||
this time using the binaries in their final installed location.
|
||||
This target does not install anything. Running this target as a
|
||||
regular user, particularly if the prior `make install' required
|
||||
root privileges, verifies that the installation completed
|
||||
correctly.
|
||||
|
||||
6. You can remove the program binaries and object files from the
|
||||
source code directory by typing `make clean'. To also remove the
|
||||
files that `configure' created (so you can compile the package for
|
||||
a different kind of computer), type `make distclean'. There is
|
||||
also a `make maintainer-clean' target, but that is intended mainly
|
||||
for the package's developers. If you use it, you may have to get
|
||||
all sorts of other programs in order to regenerate files that came
|
||||
with the distribution.
|
||||
|
||||
7. Often, you can also type `make uninstall' to remove the installed
|
||||
files again. In practice, not all packages have tested that
|
||||
uninstallation works correctly, even though it is required by the
|
||||
GNU Coding Standards.
|
||||
|
||||
8. Some packages, particularly those that use Automake, provide `make
|
||||
distcheck', which can by used by developers to test that all other
|
||||
targets like `make install' and `make uninstall' work correctly.
|
||||
This target is generally not run by end users.
|
||||
|
||||
Compilers and Options
|
||||
=====================
|
||||
|
||||
Some systems require unusual options for compilation or linking that
|
||||
the `configure' script does not know about. Run `./configure --help'
|
||||
for details on some of the pertinent environment variables.
|
||||
|
||||
You can give `configure' initial values for configuration parameters
|
||||
by setting variables in the command line or in the environment. Here
|
||||
is an example:
|
||||
|
||||
./configure CC=c99 CFLAGS=-g LIBS=-lposix
|
||||
|
||||
*Note Defining Variables::, for more details.
|
||||
|
||||
Compiling For Multiple Architectures
|
||||
====================================
|
||||
|
||||
You can compile the package for more than one kind of computer at the
|
||||
same time, by placing the object files for each architecture in their
|
||||
own directory. To do this, you can use GNU `make'. `cd' to the
|
||||
directory where you want the object files and executables to go and run
|
||||
the `configure' script. `configure' automatically checks for the
|
||||
source code in the directory that `configure' is in and in `..'. This
|
||||
is known as a "VPATH" build.
|
||||
|
||||
With a non-GNU `make', it is safer to compile the package for one
|
||||
architecture at a time in the source code directory. After you have
|
||||
installed the package for one architecture, use `make distclean' before
|
||||
reconfiguring for another architecture.
|
||||
|
||||
On MacOS X 10.5 and later systems, you can create libraries and
|
||||
executables that work on multiple system types--known as "fat" or
|
||||
"universal" binaries--by specifying multiple `-arch' options to the
|
||||
compiler but only a single `-arch' option to the preprocessor. Like
|
||||
this:
|
||||
|
||||
./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
|
||||
CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
|
||||
CPP="gcc -E" CXXCPP="g++ -E"
|
||||
|
||||
This is not guaranteed to produce working output in all cases, you
|
||||
may have to build one architecture at a time and combine the results
|
||||
using the `lipo' tool if you have problems.
|
||||
|
||||
Installation Names
|
||||
==================
|
||||
|
||||
By default, `make install' installs the package's commands under
|
||||
`/usr/local/bin', include files under `/usr/local/include', etc. You
|
||||
can specify an installation prefix other than `/usr/local' by giving
|
||||
`configure' the option `--prefix=PREFIX', where PREFIX must be an
|
||||
absolute file name.
|
||||
|
||||
You can specify separate installation prefixes for
|
||||
architecture-specific files and architecture-independent files. If you
|
||||
pass the option `--exec-prefix=PREFIX' to `configure', the package uses
|
||||
PREFIX as the prefix for installing programs and libraries.
|
||||
Documentation and other data files still use the regular prefix.
|
||||
|
||||
In addition, if you use an unusual directory layout you can give
|
||||
options like `--bindir=DIR' to specify different values for particular
|
||||
kinds of files. Run `configure --help' for a list of the directories
|
||||
you can set and what kinds of files go in them. In general, the
|
||||
default for these options is expressed in terms of `${prefix}', so that
|
||||
specifying just `--prefix' will affect all of the other directory
|
||||
specifications that were not explicitly provided.
|
||||
|
||||
The most portable way to affect installation locations is to pass the
|
||||
correct locations to `configure'; however, many packages provide one or
|
||||
both of the following shortcuts of passing variable assignments to the
|
||||
`make install' command line to change installation locations without
|
||||
having to reconfigure or recompile.
|
||||
|
||||
The first method involves providing an override variable for each
|
||||
affected directory. For example, `make install
|
||||
prefix=/alternate/directory' will choose an alternate location for all
|
||||
directory configuration variables that were expressed in terms of
|
||||
`${prefix}'. Any directories that were specified during `configure',
|
||||
but not in terms of `${prefix}', must each be overridden at install
|
||||
time for the entire installation to be relocated. The approach of
|
||||
makefile variable overrides for each directory variable is required by
|
||||
the GNU Coding Standards, and ideally causes no recompilation.
|
||||
However, some platforms have known limitations with the semantics of
|
||||
shared libraries that end up requiring recompilation when using this
|
||||
method, particularly noticeable in packages that use GNU Libtool.
|
||||
|
||||
The second method involves providing the `DESTDIR' variable. For
|
||||
example, `make install DESTDIR=/alternate/directory' will prepend
|
||||
`/alternate/directory' before all installation names. The approach of
|
||||
`DESTDIR' overrides is not required by the GNU Coding Standards, and
|
||||
does not work on platforms that have drive letters. On the other hand,
|
||||
it does better at avoiding recompilation issues, and works well even
|
||||
when some directory options were not specified in terms of `${prefix}'
|
||||
at `configure' time.
|
||||
|
||||
Optional Features
|
||||
=================
|
||||
|
||||
If the package supports it, you can cause programs to be installed
|
||||
with an extra prefix or suffix on their names by giving `configure' the
|
||||
option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
|
||||
|
||||
Some packages pay attention to `--enable-FEATURE' options to
|
||||
`configure', where FEATURE indicates an optional part of the package.
|
||||
They may also pay attention to `--with-PACKAGE' options, where PACKAGE
|
||||
is something like `gnu-as' or `x' (for the X Window System). The
|
||||
`README' should mention any `--enable-' and `--with-' options that the
|
||||
package recognizes.
|
||||
|
||||
For packages that use the X Window System, `configure' can usually
|
||||
find the X include and library files automatically, but if it doesn't,
|
||||
you can use the `configure' options `--x-includes=DIR' and
|
||||
`--x-libraries=DIR' to specify their locations.
|
||||
|
||||
Some packages offer the ability to configure how verbose the
|
||||
execution of `make' will be. For these packages, running `./configure
|
||||
--enable-silent-rules' sets the default to minimal output, which can be
|
||||
overridden with `make V=1'; while running `./configure
|
||||
--disable-silent-rules' sets the default to verbose, which can be
|
||||
overridden with `make V=0'.
|
||||
|
||||
Particular systems
|
||||
==================
|
||||
|
||||
On HP-UX, the default C compiler is not ANSI C compatible. If GNU
|
||||
CC is not installed, it is recommended to use the following options in
|
||||
order to use an ANSI C compiler:
|
||||
|
||||
./configure CC="cc -Ae -D_XOPEN_SOURCE=500"
|
||||
|
||||
and if that doesn't work, install pre-built binaries of GCC for HP-UX.
|
||||
|
||||
HP-UX `make' updates targets which have the same time stamps as
|
||||
their prerequisites, which makes it generally unusable when shipped
|
||||
generated files such as `configure' are involved. Use GNU `make'
|
||||
instead.
|
||||
|
||||
On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot
|
||||
parse its `<wchar.h>' header file. The option `-nodtk' can be used as
|
||||
a workaround. If GNU CC is not installed, it is therefore recommended
|
||||
to try
|
||||
|
||||
./configure CC="cc"
|
||||
|
||||
and if that doesn't work, try
|
||||
|
||||
./configure CC="cc -nodtk"
|
||||
|
||||
On Solaris, don't put `/usr/ucb' early in your `PATH'. This
|
||||
directory contains several dysfunctional programs; working variants of
|
||||
these programs are available in `/usr/bin'. So, if you need `/usr/ucb'
|
||||
in your `PATH', put it _after_ `/usr/bin'.
|
||||
|
||||
On Haiku, software installed for all users goes in `/boot/common',
|
||||
not `/usr/local'. It is recommended to use the following options:
|
||||
|
||||
./configure --prefix=/boot/common
|
||||
|
||||
Specifying the System Type
|
||||
==========================
|
||||
|
||||
There may be some features `configure' cannot figure out
|
||||
automatically, but needs to determine by the type of machine the package
|
||||
will run on. Usually, assuming the package is built to be run on the
|
||||
_same_ architectures, `configure' can figure that out, but if it prints
|
||||
a message saying it cannot guess the machine type, give it the
|
||||
`--build=TYPE' option. TYPE can either be a short name for the system
|
||||
type, such as `sun4', or a canonical name which has the form:
|
||||
|
||||
CPU-COMPANY-SYSTEM
|
||||
|
||||
where SYSTEM can have one of these forms:
|
||||
|
||||
OS
|
||||
KERNEL-OS
|
||||
|
||||
See the file `config.sub' for the possible values of each field. If
|
||||
`config.sub' isn't included in this package, then this package doesn't
|
||||
need to know the machine type.
|
||||
|
||||
If you are _building_ compiler tools for cross-compiling, you should
|
||||
use the option `--target=TYPE' to select the type of system they will
|
||||
produce code for.
|
||||
|
||||
If you want to _use_ a cross compiler, that generates code for a
|
||||
platform different from the build platform, you should specify the
|
||||
"host" platform (i.e., that on which the generated programs will
|
||||
eventually be run) with `--host=TYPE'.
|
||||
|
||||
Sharing Defaults
|
||||
================
|
||||
|
||||
If you want to set default values for `configure' scripts to share,
|
||||
you can create a site shell script called `config.site' that gives
|
||||
default values for variables like `CC', `cache_file', and `prefix'.
|
||||
`configure' looks for `PREFIX/share/config.site' if it exists, then
|
||||
`PREFIX/etc/config.site' if it exists. Or, you can set the
|
||||
`CONFIG_SITE' environment variable to the location of the site script.
|
||||
A warning: not all `configure' scripts look for a site script.
|
||||
|
||||
Defining Variables
|
||||
==================
|
||||
|
||||
Variables not defined in a site shell script can be set in the
|
||||
environment passed to `configure'. However, some packages may run
|
||||
configure again during the build, and the customized values of these
|
||||
variables may be lost. In order to avoid this problem, you should set
|
||||
them in the `configure' command line, using `VAR=value'. For example:
|
||||
|
||||
./configure CC=/usr/local2/bin/gcc
|
||||
|
||||
causes the specified `gcc' to be used as the C compiler (unless it is
|
||||
overridden in the site shell script).
|
||||
|
||||
Unfortunately, this technique does not work for `CONFIG_SHELL' due to
|
||||
an Autoconf bug. Until the bug is fixed you can use this workaround:
|
||||
|
||||
CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash
|
||||
|
||||
`configure' Invocation
|
||||
======================
|
||||
|
||||
`configure' recognizes the following options to control how it
|
||||
operates.
|
||||
|
||||
`--help'
|
||||
`-h'
|
||||
Print a summary of all of the options to `configure', and exit.
|
||||
|
||||
`--help=short'
|
||||
`--help=recursive'
|
||||
Print a summary of the options unique to this package's
|
||||
`configure', and exit. The `short' variant lists options used
|
||||
only in the top level, while the `recursive' variant lists options
|
||||
also present in any nested packages.
|
||||
|
||||
`--version'
|
||||
`-V'
|
||||
Print the version of Autoconf used to generate the `configure'
|
||||
script, and exit.
|
||||
|
||||
`--cache-file=FILE'
|
||||
Enable the cache: use and save the results of the tests in FILE,
|
||||
traditionally `config.cache'. FILE defaults to `/dev/null' to
|
||||
disable caching.
|
||||
|
||||
`--config-cache'
|
||||
`-C'
|
||||
Alias for `--cache-file=config.cache'.
|
||||
|
||||
`--quiet'
|
||||
`--silent'
|
||||
`-q'
|
||||
Do not print messages saying which checks are being made. To
|
||||
suppress all normal output, redirect it to `/dev/null' (any error
|
||||
messages will still be shown).
|
||||
|
||||
`--srcdir=DIR'
|
||||
Look for the package's source code in directory DIR. Usually
|
||||
`configure' can determine that directory automatically.
|
||||
|
||||
`--prefix=DIR'
|
||||
Use DIR as the installation prefix. *note Installation Names::
|
||||
for more details, including other options available for fine-tuning
|
||||
the installation locations.
|
||||
|
||||
`--no-create'
|
||||
`-n'
|
||||
Run the configure checks, but stop before creating any output
|
||||
files.
|
||||
|
||||
`configure' also accepts some other, not widely useful, options. Run
|
||||
`configure --help' for more details.
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
|
||||
AM_CFLAGS = @BUILD_CFLAGS@
|
||||
lib_LTLIBRARIES = libsqlite3.la
|
||||
libsqlite3_la_SOURCES = sqlite3.c
|
||||
libsqlite3_la_LDFLAGS = -no-undefined -version-info 8:6:8
|
||||
|
||||
bin_PROGRAMS = sqlite3
|
||||
sqlite3_SOURCES = shell.c sqlite3.h
|
||||
EXTRA_sqlite3_SOURCES = sqlite3.c
|
||||
sqlite3_LDADD = @EXTRA_SHELL_OBJ@ @READLINE_LIBS@
|
||||
sqlite3_DEPENDENCIES = @EXTRA_SHELL_OBJ@
|
||||
sqlite3_CFLAGS = $(AM_CFLAGS) -DSQLITE_ENABLE_EXPLAIN_COMMENTS -DSQLITE_ENABLE_DBPAGE_VTAB -DSQLITE_ENABLE_STMTVTAB -DSQLITE_ENABLE_DBSTAT_VTAB $(SHELL_CFLAGS)
|
||||
|
||||
include_HEADERS = sqlite3.h sqlite3ext.h
|
||||
|
||||
EXTRA_DIST = sqlite3.1 tea Makefile.msc sqlite3.rc README.txt Replace.cs Makefile.fallback
|
||||
pkgconfigdir = ${libdir}/pkgconfig
|
||||
pkgconfig_DATA = sqlite3.pc
|
||||
|
||||
man_MANS = sqlite3.1
|
||||
@@ -1,19 +0,0 @@
|
||||
#!/usr/bin/make
|
||||
#
|
||||
# If the configure script does not work, then this Makefile is available
|
||||
# as a backup. Manually configure the variables below.
|
||||
#
|
||||
# Note: This makefile works out-of-the-box on MacOS 10.2 (Jaguar)
|
||||
#
|
||||
CC = gcc
|
||||
CFLAGS = -O0 -I.
|
||||
LIBS = -lz
|
||||
COPTS += -D_BSD_SOURCE
|
||||
COPTS += -DSQLITE_ENABLE_LOCKING_STYLE=0
|
||||
COPTS += -DSQLITE_THREADSAFE=0
|
||||
COPTS += -DSQLITE_OMIT_LOAD_EXTENSION
|
||||
COPTS += -DSQLITE_WITHOUT_ZONEMALLOC
|
||||
COPTS += -DSQLITE_ENABLE_RTREE
|
||||
|
||||
sqlite3: shell.c sqlite3.c
|
||||
$(CC) $(CFLAGS) $(COPTS) -o sqlite3 shell.c sqlite3.c $(LIBS)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,11 +0,0 @@
|
||||
This directory contains components use to build an autoconf-ready package
|
||||
of the SQLite amalgamation: sqlite-autoconf-30XXXXXX.tar.gz
|
||||
|
||||
To build the autoconf amalgamation, run from the top-level:
|
||||
|
||||
./configure
|
||||
make amalgamation-tarball
|
||||
|
||||
The amalgamation-tarball target (also available in "main.mk") runs the
|
||||
script tool/mkautoconfamal.sh which does the work. Refer to that script
|
||||
for details.
|
||||
@@ -1,113 +0,0 @@
|
||||
This package contains:
|
||||
|
||||
* the SQLite library amalgamation source code file: sqlite3.c
|
||||
* the sqlite3.h and sqlite3ext.h header files that define the C-language
|
||||
interface to the sqlite3.c library file
|
||||
* the shell.c file used to build the sqlite3 command-line shell program
|
||||
* autoconf/automake installation infrastucture for building on POSIX
|
||||
compliant systems
|
||||
* a Makefile.msc, sqlite3.rc, and Replace.cs for building with Microsoft
|
||||
Visual C++ on Windows
|
||||
|
||||
SUMMARY OF HOW TO BUILD
|
||||
=======================
|
||||
|
||||
Unix: ./configure; make
|
||||
Windows: nmake /f Makefile.msc
|
||||
|
||||
BUILDING ON POSIX
|
||||
=================
|
||||
|
||||
The generic installation instructions for autoconf/automake are found
|
||||
in the INSTALL file.
|
||||
|
||||
The following SQLite specific boolean options are supported:
|
||||
|
||||
--enable-readline use readline in shell tool [default=yes]
|
||||
--enable-threadsafe build a thread-safe library [default=yes]
|
||||
--enable-dynamic-extensions support loadable extensions [default=yes]
|
||||
|
||||
The default value for the CFLAGS variable (options passed to the C
|
||||
compiler) includes debugging symbols in the build, resulting in larger
|
||||
binaries than are necessary. Override it on the configure command
|
||||
line like this:
|
||||
|
||||
$ CFLAGS="-Os" ./configure
|
||||
|
||||
to produce a smaller installation footprint.
|
||||
|
||||
Other SQLite compilation parameters can also be set using CFLAGS. For
|
||||
example:
|
||||
|
||||
$ CFLAGS="-Os -DSQLITE_THREADSAFE=0" ./configure
|
||||
|
||||
|
||||
BUILDING WITH MICROSOFT VISUAL C++
|
||||
==================================
|
||||
|
||||
To compile for Windows using Microsoft Visual C++:
|
||||
|
||||
$ nmake /f Makefile.msc
|
||||
|
||||
Using Microsoft Visual C++ 2005 (or later) is recommended. Several Windows
|
||||
platform variants may be built by adding additional macros to the NMAKE
|
||||
command line.
|
||||
|
||||
Building for WinRT 8.0
|
||||
----------------------
|
||||
|
||||
FOR_WINRT=1
|
||||
|
||||
Using Microsoft Visual C++ 2012 (or later) is required. When using the
|
||||
above, something like the following macro will need to be added to the
|
||||
NMAKE command line as well:
|
||||
|
||||
"NSDKLIBPATH=%WindowsSdkDir%\..\8.0\lib\win8\um\x86"
|
||||
|
||||
Building for WinRT 8.1
|
||||
----------------------
|
||||
|
||||
FOR_WINRT=1
|
||||
|
||||
Using Microsoft Visual C++ 2013 (or later) is required. When using the
|
||||
above, something like the following macro will need to be added to the
|
||||
NMAKE command line as well:
|
||||
|
||||
"NSDKLIBPATH=%WindowsSdkDir%\..\8.1\lib\winv6.3\um\x86"
|
||||
|
||||
Building for UWP 10.0
|
||||
---------------------
|
||||
|
||||
FOR_WINRT=1 FOR_UWP=1
|
||||
|
||||
Using Microsoft Visual C++ 2015 (or later) is required. When using the
|
||||
above, something like the following macros will need to be added to the
|
||||
NMAKE command line as well:
|
||||
|
||||
"NSDKLIBPATH=%WindowsSdkDir%\..\10\lib\10.0.10586.0\um\x86"
|
||||
"PSDKLIBPATH=%WindowsSdkDir%\..\10\lib\10.0.10586.0\um\x86"
|
||||
"NUCRTLIBPATH=%UniversalCRTSdkDir%\..\10\lib\10.0.10586.0\ucrt\x86"
|
||||
|
||||
Building for the Windows 10 SDK
|
||||
-------------------------------
|
||||
|
||||
FOR_WIN10=1
|
||||
|
||||
Using Microsoft Visual C++ 2015 (or later) is required. When using the
|
||||
above, no other macros should be needed on the NMAKE command line.
|
||||
|
||||
Other preprocessor defines
|
||||
--------------------------
|
||||
|
||||
Additionally, preprocessor defines may be specified by using the OPTS macro
|
||||
on the NMAKE command line. However, not all possible preprocessor defines
|
||||
may be specified in this manner as some require the amalgamation to be built
|
||||
with them enabled (see http://www.sqlite.org/compile.html). For example, the
|
||||
following will work:
|
||||
|
||||
"OPTS=-DSQLITE_ENABLE_STAT4=1 -DSQLITE_ENABLE_JSON1=1"
|
||||
|
||||
However, the following will not compile unless the amalgamation was built
|
||||
with it enabled:
|
||||
|
||||
"OPTS=-DSQLITE_ENABLE_UPDATE_DELETE_LIMIT=1"
|
||||
@@ -1,239 +0,0 @@
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Supports the following non-standard switches.
|
||||
#
|
||||
# --enable-threadsafe
|
||||
# --enable-readline
|
||||
# --enable-editline
|
||||
# --enable-static-shell
|
||||
# --enable-dynamic-extensions
|
||||
#
|
||||
|
||||
AC_PREREQ(2.61)
|
||||
AC_INIT(sqlite, --SQLITE-VERSION--, http://www.sqlite.org)
|
||||
AC_CONFIG_SRCDIR([sqlite3.c])
|
||||
AC_CONFIG_AUX_DIR([.])
|
||||
|
||||
# Use automake.
|
||||
AM_INIT_AUTOMAKE([foreign])
|
||||
|
||||
AC_SYS_LARGEFILE
|
||||
|
||||
# Check for required programs.
|
||||
AC_PROG_CC
|
||||
AC_PROG_LIBTOOL
|
||||
AC_PROG_MKDIR_P
|
||||
|
||||
# Check for library functions that SQLite can optionally use.
|
||||
AC_CHECK_FUNCS([fdatasync usleep fullfsync localtime_r gmtime_r])
|
||||
AC_FUNC_STRERROR_R
|
||||
|
||||
AC_CONFIG_FILES([Makefile sqlite3.pc])
|
||||
BUILD_CFLAGS=
|
||||
AC_SUBST(BUILD_CFLAGS)
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Two options to enable readline compatible libraries:
|
||||
#
|
||||
# --enable-editline
|
||||
# --enable-readline
|
||||
#
|
||||
# Both are enabled by default. If, after command line processing both are
|
||||
# still enabled, the script searches for editline first and automatically
|
||||
# disables readline if it is found. So, to use readline explicitly, the
|
||||
# user must pass "--disable-editline". To disable command line editing
|
||||
# support altogether, "--disable-editline --disable-readline".
|
||||
#
|
||||
# When searching for either library, check for headers before libraries
|
||||
# as some distros supply packages that contain libraries but not header
|
||||
# files, which come as a separate development package.
|
||||
#
|
||||
AC_ARG_ENABLE(editline, [AS_HELP_STRING([--enable-editline],[use BSD libedit])])
|
||||
AC_ARG_ENABLE(readline, [AS_HELP_STRING([--enable-readline],[use readline])])
|
||||
|
||||
AS_IF([ test x"$enable_editline" != xno ],[
|
||||
AC_CHECK_HEADERS([editline/readline.h],[
|
||||
sLIBS=$LIBS
|
||||
LIBS=""
|
||||
AC_SEARCH_LIBS([readline],[edit],[
|
||||
AC_DEFINE([HAVE_EDITLINE],1,Define to use BSD editline)
|
||||
READLINE_LIBS="$LIBS -ltinfo"
|
||||
enable_readline=no
|
||||
],[],[-ltinfo])
|
||||
AS_UNSET(ac_cv_search_readline)
|
||||
LIBS=$sLIBS
|
||||
])
|
||||
])
|
||||
|
||||
AS_IF([ test x"$enable_readline" != xno ],[
|
||||
AC_CHECK_HEADERS([readline/readline.h],[
|
||||
sLIBS=$LIBS
|
||||
LIBS=""
|
||||
AC_SEARCH_LIBS(tgetent, termcap curses ncurses ncursesw, [], [])
|
||||
AC_SEARCH_LIBS(readline,[readline edit], [
|
||||
AC_DEFINE([HAVE_READLINE],1,Define to use readline or wrapper)
|
||||
READLINE_LIBS=$LIBS
|
||||
])
|
||||
LIBS=$sLIBS
|
||||
])
|
||||
])
|
||||
|
||||
AC_SUBST(READLINE_LIBS)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-threadsafe
|
||||
#
|
||||
AC_ARG_ENABLE(threadsafe, [AS_HELP_STRING(
|
||||
[--enable-threadsafe], [build a thread-safe library [default=yes]])],
|
||||
[], [enable_threadsafe=yes])
|
||||
if test x"$enable_threadsafe" != "xno"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -D_REENTRANT=1 -DSQLITE_THREADSAFE=1"
|
||||
AC_SEARCH_LIBS(pthread_create, pthread)
|
||||
AC_SEARCH_LIBS(pthread_mutexattr_init, pthread)
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-dynamic-extensions
|
||||
#
|
||||
AC_ARG_ENABLE(dynamic-extensions, [AS_HELP_STRING(
|
||||
[--enable-dynamic-extensions], [support loadable extensions [default=yes]])],
|
||||
[], [enable_dynamic_extensions=yes])
|
||||
if test x"$enable_dynamic_extensions" != "xno"; then
|
||||
AC_SEARCH_LIBS(dlopen, dl)
|
||||
else
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_OMIT_LOAD_EXTENSION=1"
|
||||
fi
|
||||
AC_MSG_CHECKING([for whether to support dynamic extensions])
|
||||
AC_MSG_RESULT($enable_dynamic_extensions)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-fts4
|
||||
#
|
||||
AC_ARG_ENABLE(fts4, [AS_HELP_STRING(
|
||||
[--enable-fts4], [include fts4 support [default=yes]])],
|
||||
[], [enable_fts4=yes])
|
||||
if test x"$enable_fts4" = "xyes"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_FTS4"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-fts3
|
||||
#
|
||||
AC_ARG_ENABLE(fts3, [AS_HELP_STRING(
|
||||
[--enable-fts3], [include fts3 support [default=no]])],
|
||||
[], [])
|
||||
if test x"$enable_fts3" = "xyes" -a x"$enable_fts4" = "xno"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_FTS3"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-fts5
|
||||
#
|
||||
AC_ARG_ENABLE(fts5, [AS_HELP_STRING(
|
||||
[--enable-fts5], [include fts5 support [default=yes]])],
|
||||
[], [enable_fts5=yes])
|
||||
if test x"$enable_fts5" = "xyes"; then
|
||||
AC_SEARCH_LIBS(log, m)
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_FTS5"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-json1
|
||||
#
|
||||
AC_ARG_ENABLE(json1, [AS_HELP_STRING(
|
||||
[--enable-json1], [include json1 support [default=yes]])],
|
||||
[],[enable_json1=yes])
|
||||
if test x"$enable_json1" = "xyes"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_JSON1"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-rtree
|
||||
#
|
||||
AC_ARG_ENABLE(rtree, [AS_HELP_STRING(
|
||||
[--enable-rtree], [include rtree support [default=yes]])],
|
||||
[], [enable_rtree=yes])
|
||||
if test x"$enable_rtree" = "xyes"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_RTREE"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-session
|
||||
#
|
||||
AC_ARG_ENABLE(session, [AS_HELP_STRING(
|
||||
[--enable-session], [enable the session extension [default=no]])],
|
||||
[], [])
|
||||
if test x"$enable_session" = "xyes"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_ENABLE_SESSION -DSQLITE_ENABLE_PREUPDATE_HOOK"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-debug
|
||||
#
|
||||
AC_ARG_ENABLE(debug, [AS_HELP_STRING(
|
||||
[--enable-debug], [build with debugging features enabled [default=no]])],
|
||||
[], [])
|
||||
if test x"$enable_debug" = "xyes"; then
|
||||
BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_DEBUG -DSQLITE_ENABLE_SELECTTRACE -DSQLITE_ENABLE_WHERETRACE"
|
||||
CFLAGS="-g -O0"
|
||||
fi
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-static-shell
|
||||
#
|
||||
AC_ARG_ENABLE(static-shell, [AS_HELP_STRING(
|
||||
[--enable-static-shell],
|
||||
[statically link libsqlite3 into shell tool [default=yes]])],
|
||||
[], [enable_static_shell=yes])
|
||||
if test x"$enable_static_shell" = "xyes"; then
|
||||
EXTRA_SHELL_OBJ=sqlite3-sqlite3.$OBJEXT
|
||||
else
|
||||
EXTRA_SHELL_OBJ=libsqlite3.la
|
||||
fi
|
||||
AC_SUBST(EXTRA_SHELL_OBJ)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
AC_CHECK_FUNCS(posix_fallocate)
|
||||
AC_CHECK_HEADERS(zlib.h,[
|
||||
AC_SEARCH_LIBS(deflate,z,[BUILD_CFLAGS="$BUILD_CFLAGS -DSQLITE_HAVE_ZLIB"])
|
||||
])
|
||||
|
||||
AC_SEARCH_LIBS(system,,,[SHELL_CFLAGS="-DSQLITE_NOHAVE_SYSTEM"])
|
||||
AC_SUBST(SHELL_CFLAGS)
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# UPDATE: Maybe it's better if users just set CFLAGS before invoking
|
||||
# configure. This option doesn't really add much...
|
||||
#
|
||||
# --enable-tempstore
|
||||
#
|
||||
# AC_ARG_ENABLE(tempstore, [AS_HELP_STRING(
|
||||
# [--enable-tempstore],
|
||||
# [in-memory temporary tables (never, no, yes, always) [default=no]])],
|
||||
# [], [enable_tempstore=no])
|
||||
# AC_MSG_CHECKING([for whether or not to store temp tables in-memory])
|
||||
# case "$enable_tempstore" in
|
||||
# never ) TEMP_STORE=0 ;;
|
||||
# no ) TEMP_STORE=1 ;;
|
||||
# always ) TEMP_STORE=3 ;;
|
||||
# yes ) TEMP_STORE=3 ;;
|
||||
# * )
|
||||
# TEMP_STORE=1
|
||||
# enable_tempstore=yes
|
||||
# ;;
|
||||
# esac
|
||||
# AC_MSG_RESULT($enable_tempstore)
|
||||
# AC_SUBST(TEMP_STORE)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
AC_OUTPUT
|
||||
@@ -1,440 +0,0 @@
|
||||
# Makefile.in --
|
||||
#
|
||||
# This file is a Makefile for Sample TEA Extension. If it has the name
|
||||
# "Makefile.in" then it is a template for a Makefile; to generate the
|
||||
# actual Makefile, run "./configure", which is a configuration script
|
||||
# generated by the "autoconf" program (constructs like "@foo@" will get
|
||||
# replaced in the actual Makefile.
|
||||
#
|
||||
# Copyright (c) 1999 Scriptics Corporation.
|
||||
# Copyright (c) 2002-2005 ActiveState Corporation.
|
||||
#
|
||||
# See the file "license.terms" for information on usage and redistribution
|
||||
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
|
||||
#
|
||||
# RCS: @(#) $Id: Makefile.in,v 1.59 2005/07/26 19:17:02 mdejong Exp $
|
||||
|
||||
#========================================================================
|
||||
# Add additional lines to handle any additional AC_SUBST cases that
|
||||
# have been added in a customized configure script.
|
||||
#========================================================================
|
||||
|
||||
#SAMPLE_NEW_VAR = @SAMPLE_NEW_VAR@
|
||||
|
||||
#========================================================================
|
||||
# Nothing of the variables below this line should need to be changed.
|
||||
# Please check the TARGETS section below to make sure the make targets
|
||||
# are correct.
|
||||
#========================================================================
|
||||
|
||||
#========================================================================
|
||||
# The names of the source files is defined in the configure script.
|
||||
# The object files are used for linking into the final library.
|
||||
# This will be used when a dist target is added to the Makefile.
|
||||
# It is not important to specify the directory, as long as it is the
|
||||
# $(srcdir) or in the generic, win or unix subdirectory.
|
||||
#========================================================================
|
||||
|
||||
PKG_SOURCES = @PKG_SOURCES@
|
||||
PKG_OBJECTS = @PKG_OBJECTS@
|
||||
|
||||
PKG_STUB_SOURCES = @PKG_STUB_SOURCES@
|
||||
PKG_STUB_OBJECTS = @PKG_STUB_OBJECTS@
|
||||
|
||||
#========================================================================
|
||||
# PKG_TCL_SOURCES identifies Tcl runtime files that are associated with
|
||||
# this package that need to be installed, if any.
|
||||
#========================================================================
|
||||
|
||||
PKG_TCL_SOURCES = @PKG_TCL_SOURCES@
|
||||
|
||||
#========================================================================
|
||||
# This is a list of public header files to be installed, if any.
|
||||
#========================================================================
|
||||
|
||||
PKG_HEADERS = @PKG_HEADERS@
|
||||
|
||||
#========================================================================
|
||||
# "PKG_LIB_FILE" refers to the library (dynamic or static as per
|
||||
# configuration options) composed of the named objects.
|
||||
#========================================================================
|
||||
|
||||
PKG_LIB_FILE = @PKG_LIB_FILE@
|
||||
PKG_STUB_LIB_FILE = @PKG_STUB_LIB_FILE@
|
||||
|
||||
lib_BINARIES = $(PKG_LIB_FILE)
|
||||
BINARIES = $(lib_BINARIES)
|
||||
|
||||
SHELL = @SHELL@
|
||||
|
||||
srcdir = @srcdir@
|
||||
prefix = @prefix@
|
||||
exec_prefix = @exec_prefix@
|
||||
|
||||
bindir = @bindir@
|
||||
libdir = @libdir@
|
||||
datarootdir = @datarootdir@
|
||||
datadir = @datadir@
|
||||
mandir = @mandir@
|
||||
includedir = @includedir@
|
||||
|
||||
DESTDIR =
|
||||
|
||||
PKG_DIR = $(PACKAGE_NAME)$(PACKAGE_VERSION)
|
||||
pkgdatadir = $(datadir)/$(PKG_DIR)
|
||||
pkglibdir = $(libdir)/$(PKG_DIR)
|
||||
pkgincludedir = $(includedir)/$(PKG_DIR)
|
||||
|
||||
top_builddir = .
|
||||
|
||||
INSTALL = @INSTALL@
|
||||
INSTALL_PROGRAM = @INSTALL_PROGRAM@
|
||||
INSTALL_DATA = @INSTALL_DATA@
|
||||
INSTALL_SCRIPT = @INSTALL_SCRIPT@
|
||||
|
||||
PACKAGE_NAME = @PACKAGE_NAME@
|
||||
PACKAGE_VERSION = @PACKAGE_VERSION@
|
||||
CC = @CC@
|
||||
CFLAGS_DEFAULT = @CFLAGS_DEFAULT@
|
||||
CFLAGS_WARNING = @CFLAGS_WARNING@
|
||||
CLEANFILES = @CLEANFILES@
|
||||
EXEEXT = @EXEEXT@
|
||||
LDFLAGS_DEFAULT = @LDFLAGS_DEFAULT@
|
||||
MAKE_LIB = @MAKE_LIB@
|
||||
MAKE_SHARED_LIB = @MAKE_SHARED_LIB@
|
||||
MAKE_STATIC_LIB = @MAKE_STATIC_LIB@
|
||||
MAKE_STUB_LIB = @MAKE_STUB_LIB@
|
||||
OBJEXT = @OBJEXT@
|
||||
RANLIB = @RANLIB@
|
||||
RANLIB_STUB = @RANLIB_STUB@
|
||||
SHLIB_CFLAGS = @SHLIB_CFLAGS@
|
||||
SHLIB_LD = @SHLIB_LD@
|
||||
SHLIB_LD_LIBS = @SHLIB_LD_LIBS@
|
||||
STLIB_LD = @STLIB_LD@
|
||||
#TCL_DEFS = @TCL_DEFS@
|
||||
TCL_BIN_DIR = @TCL_BIN_DIR@
|
||||
TCL_SRC_DIR = @TCL_SRC_DIR@
|
||||
#TK_BIN_DIR = @TK_BIN_DIR@
|
||||
#TK_SRC_DIR = @TK_SRC_DIR@
|
||||
|
||||
# This is no longer necessary even for packages that use private Tcl headers
|
||||
#TCL_TOP_DIR_NATIVE = @TCL_TOP_DIR_NATIVE@
|
||||
# Not used, but retained for reference of what libs Tcl required
|
||||
#TCL_LIBS = @TCL_LIBS@
|
||||
|
||||
#========================================================================
|
||||
# TCLLIBPATH seeds the auto_path in Tcl's init.tcl so we can test our
|
||||
# package without installing. The other environment variables allow us
|
||||
# to test against an uninstalled Tcl. Add special env vars that you
|
||||
# require for testing here (like TCLX_LIBRARY).
|
||||
#========================================================================
|
||||
|
||||
EXTRA_PATH = $(top_builddir):$(TCL_BIN_DIR)
|
||||
#EXTRA_PATH = $(top_builddir):$(TCL_BIN_DIR):$(TK_BIN_DIR)
|
||||
TCLLIBPATH = $(top_builddir)
|
||||
TCLSH_ENV = TCL_LIBRARY=`@CYGPATH@ $(TCL_SRC_DIR)/library` \
|
||||
@LD_LIBRARY_PATH_VAR@="$(EXTRA_PATH):$(@LD_LIBRARY_PATH_VAR@)" \
|
||||
PATH="$(EXTRA_PATH):$(PATH)" \
|
||||
TCLLIBPATH="$(TCLLIBPATH)"
|
||||
# TK_LIBRARY=`@CYGPATH@ $(TK_SRC_DIR)/library`
|
||||
|
||||
TCLSH_PROG = @TCLSH_PROG@
|
||||
TCLSH = $(TCLSH_ENV) $(TCLSH_PROG)
|
||||
|
||||
#WISH_PROG = @WISH_PROG@
|
||||
#WISH = $(TCLSH_ENV) $(WISH_PROG)
|
||||
|
||||
|
||||
SHARED_BUILD = @SHARED_BUILD@
|
||||
|
||||
INCLUDES = @PKG_INCLUDES@ @TCL_INCLUDES@ -I$(srcdir)/..
|
||||
#INCLUDES = @PKG_INCLUDES@ @TCL_INCLUDES@ @TK_INCLUDES@ @TK_XINCLUDES@
|
||||
|
||||
PKG_CFLAGS = @PKG_CFLAGS@
|
||||
|
||||
# TCL_DEFS is not strictly need here, but if you remove it, then you
|
||||
# must make sure that configure.in checks for the necessary components
|
||||
# that your library may use. TCL_DEFS can actually be a problem if
|
||||
# you do not compile with a similar machine setup as the Tcl core was
|
||||
# compiled with.
|
||||
#DEFS = $(TCL_DEFS) @DEFS@ $(PKG_CFLAGS)
|
||||
DEFS = @DEFS@ $(PKG_CFLAGS)
|
||||
|
||||
CONFIG_CLEAN_FILES = Makefile pkgIndex.tcl
|
||||
|
||||
CPPFLAGS = @CPPFLAGS@
|
||||
LIBS = @PKG_LIBS@ @LIBS@
|
||||
AR = @AR@
|
||||
CFLAGS = @CFLAGS@
|
||||
COMPILE = $(CC) $(DEFS) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
|
||||
|
||||
#========================================================================
|
||||
# Start of user-definable TARGETS section
|
||||
#========================================================================
|
||||
|
||||
#========================================================================
|
||||
# TEA TARGETS. Please note that the "libraries:" target refers to platform
|
||||
# independent files, and the "binaries:" target inclues executable programs and
|
||||
# platform-dependent libraries. Modify these targets so that they install
|
||||
# the various pieces of your package. The make and install rules
|
||||
# for the BINARIES that you specified above have already been done.
|
||||
#========================================================================
|
||||
|
||||
all: binaries libraries doc
|
||||
|
||||
#========================================================================
|
||||
# The binaries target builds executable programs, Windows .dll's, unix
|
||||
# shared/static libraries, and any other platform-dependent files.
|
||||
# The list of targets to build for "binaries:" is specified at the top
|
||||
# of the Makefile, in the "BINARIES" variable.
|
||||
#========================================================================
|
||||
|
||||
binaries: $(BINARIES)
|
||||
|
||||
libraries:
|
||||
|
||||
|
||||
#========================================================================
|
||||
# Your doc target should differentiate from doc builds (by the developer)
|
||||
# and doc installs (see install-doc), which just install the docs on the
|
||||
# end user machine when building from source.
|
||||
#========================================================================
|
||||
|
||||
doc:
|
||||
@echo "If you have documentation to create, place the commands to"
|
||||
@echo "build the docs in the 'doc:' target. For example:"
|
||||
@echo " xml2nroff sample.xml > sample.n"
|
||||
@echo " xml2html sample.xml > sample.html"
|
||||
|
||||
install: all install-binaries install-libraries install-doc
|
||||
|
||||
install-binaries: binaries install-lib-binaries install-bin-binaries
|
||||
|
||||
#========================================================================
|
||||
# This rule installs platform-independent files, such as header files.
|
||||
# The list=...; for p in $$list handles the empty list case x-platform.
|
||||
#========================================================================
|
||||
|
||||
install-libraries: libraries
|
||||
@mkdir -p $(DESTDIR)$(includedir)
|
||||
@echo "Installing header files in $(DESTDIR)$(includedir)"
|
||||
@list='$(PKG_HEADERS)'; for i in $$list; do \
|
||||
echo "Installing $(srcdir)/$$i" ; \
|
||||
$(INSTALL_DATA) $(srcdir)/$$i $(DESTDIR)$(includedir) ; \
|
||||
done;
|
||||
|
||||
#========================================================================
|
||||
# Install documentation. Unix manpages should go in the $(mandir)
|
||||
# directory.
|
||||
#========================================================================
|
||||
|
||||
install-doc: doc
|
||||
@mkdir -p $(DESTDIR)$(mandir)/mann
|
||||
@echo "Installing documentation in $(DESTDIR)$(mandir)"
|
||||
@list='$(srcdir)/doc/*.n'; for i in $$list; do \
|
||||
echo "Installing $$i"; \
|
||||
rm -f $(DESTDIR)$(mandir)/mann/`basename $$i`; \
|
||||
$(INSTALL_DATA) $$i $(DESTDIR)$(mandir)/mann ; \
|
||||
done
|
||||
|
||||
test: binaries libraries
|
||||
@echo "SQLite TEA distribution does not include tests"
|
||||
|
||||
shell: binaries libraries
|
||||
@$(TCLSH) $(SCRIPT)
|
||||
|
||||
gdb:
|
||||
$(TCLSH_ENV) gdb $(TCLSH_PROG) $(SCRIPT)
|
||||
|
||||
depend:
|
||||
|
||||
#========================================================================
|
||||
# $(PKG_LIB_FILE) should be listed as part of the BINARIES variable
|
||||
# mentioned above. That will ensure that this target is built when you
|
||||
# run "make binaries".
|
||||
#
|
||||
# The $(PKG_OBJECTS) objects are created and linked into the final
|
||||
# library. In most cases these object files will correspond to the
|
||||
# source files above.
|
||||
#========================================================================
|
||||
|
||||
$(PKG_LIB_FILE): $(PKG_OBJECTS)
|
||||
-rm -f $(PKG_LIB_FILE)
|
||||
${MAKE_LIB}
|
||||
$(RANLIB) $(PKG_LIB_FILE)
|
||||
|
||||
$(PKG_STUB_LIB_FILE): $(PKG_STUB_OBJECTS)
|
||||
-rm -f $(PKG_STUB_LIB_FILE)
|
||||
${MAKE_STUB_LIB}
|
||||
$(RANLIB_STUB) $(PKG_STUB_LIB_FILE)
|
||||
|
||||
#========================================================================
|
||||
# We need to enumerate the list of .c to .o lines here.
|
||||
#
|
||||
# In the following lines, $(srcdir) refers to the toplevel directory
|
||||
# containing your extension. If your sources are in a subdirectory,
|
||||
# you will have to modify the paths to reflect this:
|
||||
#
|
||||
# sample.$(OBJEXT): $(srcdir)/generic/sample.c
|
||||
# $(COMPILE) -c `@CYGPATH@ $(srcdir)/generic/sample.c` -o $@
|
||||
#
|
||||
# Setting the VPATH variable to a list of paths will cause the makefile
|
||||
# to look into these paths when resolving .c to .obj dependencies.
|
||||
# As necessary, add $(srcdir):$(srcdir)/compat:....
|
||||
#========================================================================
|
||||
|
||||
VPATH = $(srcdir):$(srcdir)/generic:$(srcdir)/unix:$(srcdir)/win
|
||||
|
||||
.c.@OBJEXT@:
|
||||
$(COMPILE) -c `@CYGPATH@ $<` -o $@
|
||||
|
||||
#========================================================================
|
||||
# Distribution creation
|
||||
# You may need to tweak this target to make it work correctly.
|
||||
#========================================================================
|
||||
|
||||
#COMPRESS = tar cvf $(PKG_DIR).tar $(PKG_DIR); compress $(PKG_DIR).tar
|
||||
COMPRESS = gtar zcvf $(PKG_DIR).tar.gz $(PKG_DIR)
|
||||
DIST_ROOT = /tmp/dist
|
||||
DIST_DIR = $(DIST_ROOT)/$(PKG_DIR)
|
||||
|
||||
dist-clean:
|
||||
rm -rf $(DIST_DIR) $(DIST_ROOT)/$(PKG_DIR).tar.*
|
||||
|
||||
dist: dist-clean
|
||||
mkdir -p $(DIST_DIR)
|
||||
cp -p $(srcdir)/README* $(srcdir)/license* \
|
||||
$(srcdir)/aclocal.m4 $(srcdir)/configure $(srcdir)/*.in \
|
||||
$(DIST_DIR)/
|
||||
chmod 664 $(DIST_DIR)/Makefile.in $(DIST_DIR)/aclocal.m4
|
||||
chmod 775 $(DIST_DIR)/configure $(DIST_DIR)/configure.in
|
||||
|
||||
for i in $(srcdir)/*.[ch]; do \
|
||||
if [ -f $$i ]; then \
|
||||
cp -p $$i $(DIST_DIR)/ ; \
|
||||
fi; \
|
||||
done;
|
||||
|
||||
mkdir $(DIST_DIR)/tclconfig
|
||||
cp $(srcdir)/tclconfig/install-sh $(srcdir)/tclconfig/tcl.m4 \
|
||||
$(DIST_DIR)/tclconfig/
|
||||
chmod 664 $(DIST_DIR)/tclconfig/tcl.m4
|
||||
chmod +x $(DIST_DIR)/tclconfig/install-sh
|
||||
|
||||
list='demos doc generic library mac tests unix win'; \
|
||||
for p in $$list; do \
|
||||
if test -d $(srcdir)/$$p ; then \
|
||||
mkdir $(DIST_DIR)/$$p; \
|
||||
cp -p $(srcdir)/$$p/*.* $(DIST_DIR)/$$p/; \
|
||||
fi; \
|
||||
done
|
||||
|
||||
(cd $(DIST_ROOT); $(COMPRESS);)
|
||||
|
||||
#========================================================================
|
||||
# End of user-definable section
|
||||
#========================================================================
|
||||
|
||||
#========================================================================
|
||||
# Don't modify the file to clean here. Instead, set the "CLEANFILES"
|
||||
# variable in configure.in
|
||||
#========================================================================
|
||||
|
||||
clean:
|
||||
-test -z "$(BINARIES)" || rm -f $(BINARIES)
|
||||
-rm -f *.$(OBJEXT) core *.core
|
||||
-test -z "$(CLEANFILES)" || rm -f $(CLEANFILES)
|
||||
|
||||
distclean: clean
|
||||
-rm -f *.tab.c
|
||||
-rm -f $(CONFIG_CLEAN_FILES)
|
||||
-rm -f config.h config.cache config.log config.status
|
||||
|
||||
#========================================================================
|
||||
# Install binary object libraries. On Windows this includes both .dll and
|
||||
# .lib files. Because the .lib files are not explicitly listed anywhere,
|
||||
# we need to deduce their existence from the .dll file of the same name.
|
||||
# Library files go into the lib directory.
|
||||
# In addition, this will generate the pkgIndex.tcl
|
||||
# file in the install location (assuming it can find a usable tclsh shell)
|
||||
#
|
||||
# You should not have to modify this target.
|
||||
#========================================================================
|
||||
|
||||
install-lib-binaries: binaries
|
||||
@mkdir -p $(DESTDIR)$(pkglibdir)
|
||||
@list='$(lib_BINARIES)'; for p in $$list; do \
|
||||
if test -f $$p; then \
|
||||
echo " $(INSTALL_PROGRAM) $$p $(DESTDIR)$(pkglibdir)/$$p"; \
|
||||
$(INSTALL_PROGRAM) $$p $(DESTDIR)$(pkglibdir)/$$p; \
|
||||
stub=`echo $$p|sed -e "s/.*\(stub\).*/\1/"`; \
|
||||
if test "x$$stub" = "xstub"; then \
|
||||
echo " $(RANLIB_STUB) $(DESTDIR)$(pkglibdir)/$$p"; \
|
||||
$(RANLIB_STUB) $(DESTDIR)$(pkglibdir)/$$p; \
|
||||
else \
|
||||
echo " $(RANLIB) $(DESTDIR)$(pkglibdir)/$$p"; \
|
||||
$(RANLIB) $(DESTDIR)$(pkglibdir)/$$p; \
|
||||
fi; \
|
||||
ext=`echo $$p|sed -e "s/.*\.//"`; \
|
||||
if test "x$$ext" = "xdll"; then \
|
||||
lib=`basename $$p|sed -e 's/.[^.]*$$//'`.lib; \
|
||||
if test -f $$lib; then \
|
||||
echo " $(INSTALL_DATA) $$lib $(DESTDIR)$(pkglibdir)/$$lib"; \
|
||||
$(INSTALL_DATA) $$lib $(DESTDIR)$(pkglibdir)/$$lib; \
|
||||
fi; \
|
||||
fi; \
|
||||
fi; \
|
||||
done
|
||||
@list='$(PKG_TCL_SOURCES)'; for p in $$list; do \
|
||||
if test -f $(srcdir)/$$p; then \
|
||||
destp=`basename $$p`; \
|
||||
echo " Install $$destp $(DESTDIR)$(pkglibdir)/$$destp"; \
|
||||
$(INSTALL_DATA) $(srcdir)/$$p $(DESTDIR)$(pkglibdir)/$$destp; \
|
||||
fi; \
|
||||
done
|
||||
@if test "x$(SHARED_BUILD)" = "x1"; then \
|
||||
echo " Install pkgIndex.tcl $(DESTDIR)$(pkglibdir)"; \
|
||||
$(INSTALL_DATA) pkgIndex.tcl $(DESTDIR)$(pkglibdir); \
|
||||
fi
|
||||
|
||||
#========================================================================
|
||||
# Install binary executables (e.g. .exe files and dependent .dll files)
|
||||
# This is for files that must go in the bin directory (located next to
|
||||
# wish and tclsh), like dependent .dll files on Windows.
|
||||
#
|
||||
# You should not have to modify this target, except to define bin_BINARIES
|
||||
# above if necessary.
|
||||
#========================================================================
|
||||
|
||||
install-bin-binaries: binaries
|
||||
@mkdir -p $(DESTDIR)$(bindir)
|
||||
@list='$(bin_BINARIES)'; for p in $$list; do \
|
||||
if test -f $$p; then \
|
||||
echo " $(INSTALL_PROGRAM) $$p $(DESTDIR)$(bindir)/$$p"; \
|
||||
$(INSTALL_PROGRAM) $$p $(DESTDIR)$(bindir)/$$p; \
|
||||
fi; \
|
||||
done
|
||||
|
||||
.SUFFIXES: .c .$(OBJEXT)
|
||||
|
||||
Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
|
||||
cd $(top_builddir) \
|
||||
&& CONFIG_FILES=$@ CONFIG_HEADERS= $(SHELL) ./config.status
|
||||
|
||||
uninstall-binaries:
|
||||
list='$(lib_BINARIES)'; for p in $$list; do \
|
||||
rm -f $(DESTDIR)$(pkglibdir)/$$p; \
|
||||
done
|
||||
list='$(PKG_TCL_SOURCES)'; for p in $$list; do \
|
||||
p=`basename $$p`; \
|
||||
rm -f $(DESTDIR)$(pkglibdir)/$$p; \
|
||||
done
|
||||
list='$(bin_BINARIES)'; for p in $$list; do \
|
||||
rm -f $(DESTDIR)$(bindir)/$$p; \
|
||||
done
|
||||
|
||||
.PHONY: all binaries clean depend distclean doc install libraries test
|
||||
|
||||
# Tell versions [3.59,3.63) of GNU make to not export all variables.
|
||||
# Otherwise a system limit (for SysV at least) may be exceeded.
|
||||
.NOEXPORT:
|
||||
@@ -1,36 +0,0 @@
|
||||
This is the SQLite extension for Tcl using the Tcl Extension
|
||||
Architecture (TEA). For additional information on SQLite see
|
||||
|
||||
http://www.sqlite.org/
|
||||
|
||||
|
||||
UNIX BUILD
|
||||
==========
|
||||
|
||||
Building under most UNIX systems is easy, just run the configure script
|
||||
and then run make. For more information about the build process, see
|
||||
the tcl/unix/README file in the Tcl src dist. The following minimal
|
||||
example will install the extension in the /opt/tcl directory.
|
||||
|
||||
$ cd sqlite-*-tea
|
||||
$ ./configure --prefix=/opt/tcl
|
||||
$ make
|
||||
$ make install
|
||||
|
||||
WINDOWS BUILD
|
||||
=============
|
||||
|
||||
The recommended method to build extensions under windows is to use the
|
||||
Msys + Mingw build process. This provides a Unix-style build while
|
||||
generating native Windows binaries. Using the Msys + Mingw build tools
|
||||
means that you can use the same configure script as per the Unix build
|
||||
to create a Makefile. See the tcl/win/README file for the URL of
|
||||
the Msys + Mingw download.
|
||||
|
||||
If you have VC++ then you may wish to use the files in the win
|
||||
subdirectory and build the extension using just VC++. These files have
|
||||
been designed to be as generic as possible but will require some
|
||||
additional maintenance by the project developer to synchronise with
|
||||
the TEA configure.in and Makefile.in files. Instructions for using the
|
||||
VC++ makefile are written in the first part of the Makefile.vc
|
||||
file.
|
||||
Vendored
-9
@@ -1,9 +0,0 @@
|
||||
#
|
||||
# Include the TEA standard macro set
|
||||
#
|
||||
|
||||
builtin(include,tclconfig/tcl.m4)
|
||||
|
||||
#
|
||||
# Add here whatever m4 macros you want to define for your package
|
||||
#
|
||||
@@ -1,201 +0,0 @@
|
||||
#!/bin/bash -norc
|
||||
dnl This file is an input file used by the GNU "autoconf" program to
|
||||
dnl generate the file "configure", which is run during Tcl installation
|
||||
dnl to configure the system for the local environment.
|
||||
#
|
||||
# RCS: @(#) $Id: configure.in,v 1.43 2005/07/26 19:17:05 mdejong Exp $
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Sample configure.in for Tcl Extensions. The only places you should
|
||||
# need to modify this file are marked by the string __CHANGE__
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# __CHANGE__
|
||||
# Set your package name and version numbers here.
|
||||
#
|
||||
# This initializes the environment with PACKAGE_NAME and PACKAGE_VERSION
|
||||
# set as provided. These will also be added as -D defs in your Makefile
|
||||
# so you can encode the package version directly into the source files.
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
AC_INIT([sqlite], [3.7.4])
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Call TEA_INIT as the first TEA_ macro to set up initial vars.
|
||||
# This will define a ${TEA_PLATFORM} variable == "unix" or "windows"
|
||||
# as well as PKG_LIB_FILE and PKG_STUB_LIB_FILE.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_INIT([3.9])
|
||||
|
||||
AC_CONFIG_AUX_DIR(tclconfig)
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Load the tclConfig.sh file
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_PATH_TCLCONFIG
|
||||
TEA_LOAD_TCLCONFIG
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Load the tkConfig.sh file if necessary (Tk extension)
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
#TEA_PATH_TKCONFIG
|
||||
#TEA_LOAD_TKCONFIG
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Handle the --prefix=... option by defaulting to what Tcl gave.
|
||||
# Must be called after TEA_LOAD_TCLCONFIG and before TEA_SETUP_COMPILER.
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
TEA_PREFIX
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Standard compiler checks.
|
||||
# This sets up CC by using the CC env var, or looks for gcc otherwise.
|
||||
# This also calls AC_PROG_CC, AC_PROG_INSTALL and a few others to create
|
||||
# the basic setup necessary to compile executables.
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
TEA_SETUP_COMPILER
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# __CHANGE__
|
||||
# Specify the C source files to compile in TEA_ADD_SOURCES,
|
||||
# public headers that need to be installed in TEA_ADD_HEADERS,
|
||||
# stub library C source files to compile in TEA_ADD_STUB_SOURCES,
|
||||
# and runtime Tcl library files in TEA_ADD_TCL_SOURCES.
|
||||
# This defines PKG(_STUB)_SOURCES, PKG(_STUB)_OBJECTS, PKG_HEADERS
|
||||
# and PKG_TCL_SOURCES.
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
TEA_ADD_SOURCES([tclsqlite3.c])
|
||||
TEA_ADD_HEADERS([])
|
||||
TEA_ADD_INCLUDES([-I\"`\${CYGPATH} \${srcdir}/generic`\"])
|
||||
TEA_ADD_LIBS([])
|
||||
TEA_ADD_CFLAGS([-DSQLITE_ENABLE_FTS3=1])
|
||||
TEA_ADD_CFLAGS([-DSQLITE_3_SUFFIX_ONLY=1])
|
||||
TEA_ADD_CFLAGS([-DSQLITE_ENABLE_RTREE=1])
|
||||
TEA_ADD_STUB_SOURCES([])
|
||||
TEA_ADD_TCL_SOURCES([])
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# The --with-system-sqlite causes the TCL bindings to SQLite to use
|
||||
# the system shared library for SQLite rather than statically linking
|
||||
# against its own private copy. This is dangerous and leads to
|
||||
# undersirable dependences and is not recommended.
|
||||
# Patchs from rmax.
|
||||
#--------------------------------------------------------------------
|
||||
AC_ARG_WITH([system-sqlite],
|
||||
[AC_HELP_STRING([--with-system-sqlite],
|
||||
[use a system-supplied libsqlite3 instead of the bundled one])],
|
||||
[], [with_system_sqlite=no])
|
||||
if test x$with_system_sqlite != xno; then
|
||||
AC_CHECK_HEADER([sqlite3.h],
|
||||
[AC_CHECK_LIB([sqlite3],[sqlite3_initialize],
|
||||
[AC_DEFINE(USE_SYSTEM_SQLITE)
|
||||
LIBS="$LIBS -lsqlite3"])])
|
||||
fi
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# __CHANGE__
|
||||
# Choose which headers you need. Extension authors should try very
|
||||
# hard to only rely on the Tcl public header files. Internal headers
|
||||
# contain private data structures and are subject to change without
|
||||
# notice.
|
||||
# This MUST be called after TEA_LOAD_TCLCONFIG / TEA_LOAD_TKCONFIG
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_PUBLIC_TCL_HEADERS
|
||||
#TEA_PRIVATE_TCL_HEADERS
|
||||
|
||||
#TEA_PUBLIC_TK_HEADERS
|
||||
#TEA_PRIVATE_TK_HEADERS
|
||||
#TEA_PATH_X
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Check whether --enable-threads or --disable-threads was given.
|
||||
# This auto-enables if Tcl was compiled threaded.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_ENABLE_THREADS
|
||||
if test "${TCL_THREADS}" = "1" ; then
|
||||
AC_DEFINE(SQLITE_THREADSAFE, 1, [Trigger sqlite threadsafe build])
|
||||
# Not automatically added by Tcl because its assumed Tcl links to them,
|
||||
# but it may not if it isn't really a threaded build.
|
||||
TEA_ADD_LIBS([$THREADS_LIBS])
|
||||
else
|
||||
AC_DEFINE(SQLITE_THREADSAFE, 0, [Trigger sqlite non-threadsafe build])
|
||||
fi
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# The statement below defines a collection of symbols related to
|
||||
# building as a shared library instead of a static library.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_ENABLE_SHARED
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# This macro figures out what flags to use with the compiler/linker
|
||||
# when building shared/static debug/optimized objects. This information
|
||||
# can be taken from the tclConfig.sh file, but this figures it all out.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_CONFIG_CFLAGS
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Set the default compiler switches based on the --enable-symbols option.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_ENABLE_SYMBOLS
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Everyone should be linking against the Tcl stub library. If you
|
||||
# can't for some reason, remove this definition. If you aren't using
|
||||
# stubs, you also need to modify the SHLIB_LD_LIBS setting below to
|
||||
# link against the non-stubbed Tcl library. Add Tk too if necessary.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
AC_DEFINE(USE_TCL_STUBS, 1, [Use Tcl stubs])
|
||||
#AC_DEFINE(USE_TK_STUBS, 1, [Use Tk stubs])
|
||||
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Redefine fdatasync as fsync on systems that lack fdatasync
|
||||
#--------------------------------------------------------------------
|
||||
#
|
||||
#AC_CHECK_FUNC(fdatasync, , AC_DEFINE(fdatasync, fsync))
|
||||
# Check for library functions that SQLite can optionally use.
|
||||
AC_CHECK_FUNCS([fdatasync usleep fullfsync localtime_r gmtime_r])
|
||||
|
||||
AC_FUNC_STRERROR_R
|
||||
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# This macro generates a line to use when building a library. It
|
||||
# depends on values set by the TEA_ENABLE_SHARED, TEA_ENABLE_SYMBOLS,
|
||||
# and TEA_LOAD_TCLCONFIG macros above.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_MAKE_LIB
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Determine the name of the tclsh and/or wish executables in the
|
||||
# Tcl and Tk build directories or the location they were installed
|
||||
# into. These paths are used to support running test cases only,
|
||||
# the Makefile should not be making use of these paths to generate
|
||||
# a pkgIndex.tcl file or anything else at extension build time.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
TEA_PROG_TCLSH
|
||||
#TEA_PROG_WISH
|
||||
|
||||
#--------------------------------------------------------------------
|
||||
# Finally, substitute all of the various values into the Makefile.
|
||||
# You may alternatively have a special pkgIndex.tcl.in or other files
|
||||
# which require substituting th AC variables in. Include these here.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
AC_OUTPUT([Makefile pkgIndex.tcl])
|
||||
@@ -1,15 +0,0 @@
|
||||
.TH sqlite3 n 4.1 "Tcl-Extensions"
|
||||
.HS sqlite3 tcl
|
||||
.BS
|
||||
.SH NAME
|
||||
sqlite3 \- an interface to the SQLite3 database engine
|
||||
.SH SYNOPSIS
|
||||
\fBsqlite3\fI command_name ?filename?\fR
|
||||
.br
|
||||
.SH DESCRIPTION
|
||||
SQLite3 is a self-contains, zero-configuration, transactional SQL database
|
||||
engine. This extension provides an easy to use interface for accessing
|
||||
SQLite database files from Tcl.
|
||||
.PP
|
||||
For full documentation see \fIhttp://www.sqlite.org/\fR and
|
||||
in particular \fIhttp://www.sqlite.org/tclsqlite.html\fR.
|
||||
@@ -1,6 +0,0 @@
|
||||
The author disclaims copyright to this source code. In place of
|
||||
a legal notice, here is a blessing:
|
||||
|
||||
May you do good and not evil.
|
||||
May you find forgiveness for yourself and forgive others.
|
||||
May you share freely, never taking more than you give.
|
||||
@@ -1,7 +0,0 @@
|
||||
#
|
||||
# Tcl package index file
|
||||
#
|
||||
# Note sqlite*3* init specifically
|
||||
#
|
||||
package ifneeded sqlite3 @PACKAGE_VERSION@ \
|
||||
[list load [file join $dir @PKG_LIB_FILE@] Sqlite3]
|
||||
@@ -1,528 +0,0 @@
|
||||
#!/bin/sh
|
||||
# install - install a program, script, or datafile
|
||||
|
||||
scriptversion=2011-04-20.01; # UTC
|
||||
|
||||
# This originates from X11R5 (mit/util/scripts/install.sh), which was
|
||||
# later released in X11R6 (xc/config/util/install.sh) with the
|
||||
# following copyright and license.
|
||||
#
|
||||
# Copyright (C) 1994 X Consortium
|
||||
#
|
||||
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
# of this software and associated documentation files (the "Software"), to
|
||||
# deal in the Software without restriction, including without limitation the
|
||||
# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
|
||||
# sell copies of the Software, and to permit persons to whom the Software is
|
||||
# furnished to do so, subject to the following conditions:
|
||||
#
|
||||
# The above copyright notice and this permission notice shall be included in
|
||||
# all copies or substantial portions of the Software.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
# X CONSORTIUM BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
|
||||
# AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNEC-
|
||||
# TION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
#
|
||||
# Except as contained in this notice, the name of the X Consortium shall not
|
||||
# be used in advertising or otherwise to promote the sale, use or other deal-
|
||||
# ings in this Software without prior written authorization from the X Consor-
|
||||
# tium.
|
||||
#
|
||||
#
|
||||
# FSF changes to this file are in the public domain.
|
||||
#
|
||||
# Calling this script install-sh is preferred over install.sh, to prevent
|
||||
# `make' implicit rules from creating a file called install from it
|
||||
# when there is no Makefile.
|
||||
#
|
||||
# This script is compatible with the BSD install script, but was written
|
||||
# from scratch.
|
||||
|
||||
nl='
|
||||
'
|
||||
IFS=" "" $nl"
|
||||
|
||||
# set DOITPROG to echo to test this script
|
||||
|
||||
# Don't use :- since 4.3BSD and earlier shells don't like it.
|
||||
doit=${DOITPROG-}
|
||||
if test -z "$doit"; then
|
||||
doit_exec=exec
|
||||
else
|
||||
doit_exec=$doit
|
||||
fi
|
||||
|
||||
# Put in absolute file names if you don't have them in your path;
|
||||
# or use environment vars.
|
||||
|
||||
chgrpprog=${CHGRPPROG-chgrp}
|
||||
chmodprog=${CHMODPROG-chmod}
|
||||
chownprog=${CHOWNPROG-chown}
|
||||
cmpprog=${CMPPROG-cmp}
|
||||
cpprog=${CPPROG-cp}
|
||||
mkdirprog=${MKDIRPROG-mkdir}
|
||||
mvprog=${MVPROG-mv}
|
||||
rmprog=${RMPROG-rm}
|
||||
stripprog=${STRIPPROG-strip}
|
||||
|
||||
posix_glob='?'
|
||||
initialize_posix_glob='
|
||||
test "$posix_glob" != "?" || {
|
||||
if (set -f) 2>/dev/null; then
|
||||
posix_glob=
|
||||
else
|
||||
posix_glob=:
|
||||
fi
|
||||
}
|
||||
'
|
||||
|
||||
posix_mkdir=
|
||||
|
||||
# Desired mode of installed file.
|
||||
mode=0755
|
||||
|
||||
chgrpcmd=
|
||||
chmodcmd=$chmodprog
|
||||
chowncmd=
|
||||
mvcmd=$mvprog
|
||||
rmcmd="$rmprog -f"
|
||||
stripcmd=
|
||||
|
||||
src=
|
||||
dst=
|
||||
dir_arg=
|
||||
dst_arg=
|
||||
|
||||
copy_on_change=false
|
||||
no_target_directory=
|
||||
|
||||
usage="\
|
||||
Usage: $0 [OPTION]... [-T] SRCFILE DSTFILE
|
||||
or: $0 [OPTION]... SRCFILES... DIRECTORY
|
||||
or: $0 [OPTION]... -t DIRECTORY SRCFILES...
|
||||
or: $0 [OPTION]... -d DIRECTORIES...
|
||||
|
||||
In the 1st form, copy SRCFILE to DSTFILE.
|
||||
In the 2nd and 3rd, copy all SRCFILES to DIRECTORY.
|
||||
In the 4th, create DIRECTORIES.
|
||||
|
||||
Options:
|
||||
--help display this help and exit.
|
||||
--version display version info and exit.
|
||||
|
||||
-c (ignored)
|
||||
-C install only if different (preserve the last data modification time)
|
||||
-d create directories instead of installing files.
|
||||
-g GROUP $chgrpprog installed files to GROUP.
|
||||
-m MODE $chmodprog installed files to MODE.
|
||||
-o USER $chownprog installed files to USER.
|
||||
-s $stripprog installed files.
|
||||
-S $stripprog installed files.
|
||||
-t DIRECTORY install into DIRECTORY.
|
||||
-T report an error if DSTFILE is a directory.
|
||||
|
||||
Environment variables override the default commands:
|
||||
CHGRPPROG CHMODPROG CHOWNPROG CMPPROG CPPROG MKDIRPROG MVPROG
|
||||
RMPROG STRIPPROG
|
||||
"
|
||||
|
||||
while test $# -ne 0; do
|
||||
case $1 in
|
||||
-c) ;;
|
||||
|
||||
-C) copy_on_change=true;;
|
||||
|
||||
-d) dir_arg=true;;
|
||||
|
||||
-g) chgrpcmd="$chgrpprog $2"
|
||||
shift;;
|
||||
|
||||
--help) echo "$usage"; exit $?;;
|
||||
|
||||
-m) mode=$2
|
||||
case $mode in
|
||||
*' '* | *' '* | *'
|
||||
'* | *'*'* | *'?'* | *'['*)
|
||||
echo "$0: invalid mode: $mode" >&2
|
||||
exit 1;;
|
||||
esac
|
||||
shift;;
|
||||
|
||||
-o) chowncmd="$chownprog $2"
|
||||
shift;;
|
||||
|
||||
-s) stripcmd=$stripprog;;
|
||||
|
||||
-S) stripcmd="$stripprog $2"
|
||||
shift;;
|
||||
|
||||
-t) dst_arg=$2
|
||||
shift;;
|
||||
|
||||
-T) no_target_directory=true;;
|
||||
|
||||
--version) echo "$0 $scriptversion"; exit $?;;
|
||||
|
||||
--) shift
|
||||
break;;
|
||||
|
||||
-*) echo "$0: invalid option: $1" >&2
|
||||
exit 1;;
|
||||
|
||||
*) break;;
|
||||
esac
|
||||
shift
|
||||
done
|
||||
|
||||
if test $# -ne 0 && test -z "$dir_arg$dst_arg"; then
|
||||
# When -d is used, all remaining arguments are directories to create.
|
||||
# When -t is used, the destination is already specified.
|
||||
# Otherwise, the last argument is the destination. Remove it from $@.
|
||||
for arg
|
||||
do
|
||||
if test -n "$dst_arg"; then
|
||||
# $@ is not empty: it contains at least $arg.
|
||||
set fnord "$@" "$dst_arg"
|
||||
shift # fnord
|
||||
fi
|
||||
shift # arg
|
||||
dst_arg=$arg
|
||||
done
|
||||
fi
|
||||
|
||||
if test $# -eq 0; then
|
||||
if test -z "$dir_arg"; then
|
||||
echo "$0: no input file specified." >&2
|
||||
exit 1
|
||||
fi
|
||||
# It's OK to call `install-sh -d' without argument.
|
||||
# This can happen when creating conditional directories.
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if test -z "$dir_arg"; then
|
||||
do_exit='(exit $ret); exit $ret'
|
||||
trap "ret=129; $do_exit" 1
|
||||
trap "ret=130; $do_exit" 2
|
||||
trap "ret=141; $do_exit" 13
|
||||
trap "ret=143; $do_exit" 15
|
||||
|
||||
# Set umask so as not to create temps with too-generous modes.
|
||||
# However, 'strip' requires both read and write access to temps.
|
||||
case $mode in
|
||||
# Optimize common cases.
|
||||
*644) cp_umask=133;;
|
||||
*755) cp_umask=22;;
|
||||
|
||||
*[0-7])
|
||||
if test -z "$stripcmd"; then
|
||||
u_plus_rw=
|
||||
else
|
||||
u_plus_rw='% 200'
|
||||
fi
|
||||
cp_umask=`expr '(' 777 - $mode % 1000 ')' $u_plus_rw`;;
|
||||
*)
|
||||
if test -z "$stripcmd"; then
|
||||
u_plus_rw=
|
||||
else
|
||||
u_plus_rw=,u+rw
|
||||
fi
|
||||
cp_umask=$mode$u_plus_rw;;
|
||||
esac
|
||||
fi
|
||||
|
||||
for src
|
||||
do
|
||||
# Protect names starting with `-'.
|
||||
case $src in
|
||||
-*) src=./$src;;
|
||||
esac
|
||||
|
||||
if test -n "$dir_arg"; then
|
||||
dst=$src
|
||||
dstdir=$dst
|
||||
test -d "$dstdir"
|
||||
dstdir_status=$?
|
||||
else
|
||||
|
||||
# Waiting for this to be detected by the "$cpprog $src $dsttmp" command
|
||||
# might cause directories to be created, which would be especially bad
|
||||
# if $src (and thus $dsttmp) contains '*'.
|
||||
if test ! -f "$src" && test ! -d "$src"; then
|
||||
echo "$0: $src does not exist." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if test -z "$dst_arg"; then
|
||||
echo "$0: no destination specified." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
dst=$dst_arg
|
||||
# Protect names starting with `-'.
|
||||
case $dst in
|
||||
-*) dst=./$dst;;
|
||||
esac
|
||||
|
||||
# If destination is a directory, append the input filename; won't work
|
||||
# if double slashes aren't ignored.
|
||||
if test -d "$dst"; then
|
||||
if test -n "$no_target_directory"; then
|
||||
echo "$0: $dst_arg: Is a directory" >&2
|
||||
exit 1
|
||||
fi
|
||||
dstdir=$dst
|
||||
dst=$dstdir/`basename "$src"`
|
||||
dstdir_status=0
|
||||
else
|
||||
# Prefer dirname, but fall back on a substitute if dirname fails.
|
||||
dstdir=`
|
||||
(dirname "$dst") 2>/dev/null ||
|
||||
expr X"$dst" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
|
||||
X"$dst" : 'X\(//\)[^/]' \| \
|
||||
X"$dst" : 'X\(//\)$' \| \
|
||||
X"$dst" : 'X\(/\)' \| . 2>/dev/null ||
|
||||
echo X"$dst" |
|
||||
sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{
|
||||
s//\1/
|
||||
q
|
||||
}
|
||||
/^X\(\/\/\)[^/].*/{
|
||||
s//\1/
|
||||
q
|
||||
}
|
||||
/^X\(\/\/\)$/{
|
||||
s//\1/
|
||||
q
|
||||
}
|
||||
/^X\(\/\).*/{
|
||||
s//\1/
|
||||
q
|
||||
}
|
||||
s/.*/./; q'
|
||||
`
|
||||
|
||||
test -d "$dstdir"
|
||||
dstdir_status=$?
|
||||
fi
|
||||
fi
|
||||
|
||||
obsolete_mkdir_used=false
|
||||
|
||||
if test $dstdir_status != 0; then
|
||||
case $posix_mkdir in
|
||||
'')
|
||||
# Create intermediate dirs using mode 755 as modified by the umask.
|
||||
# This is like FreeBSD 'install' as of 1997-10-28.
|
||||
umask=`umask`
|
||||
case $stripcmd.$umask in
|
||||
# Optimize common cases.
|
||||
*[2367][2367]) mkdir_umask=$umask;;
|
||||
.*0[02][02] | .[02][02] | .[02]) mkdir_umask=22;;
|
||||
|
||||
*[0-7])
|
||||
mkdir_umask=`expr $umask + 22 \
|
||||
- $umask % 100 % 40 + $umask % 20 \
|
||||
- $umask % 10 % 4 + $umask % 2
|
||||
`;;
|
||||
*) mkdir_umask=$umask,go-w;;
|
||||
esac
|
||||
|
||||
# With -d, create the new directory with the user-specified mode.
|
||||
# Otherwise, rely on $mkdir_umask.
|
||||
if test -n "$dir_arg"; then
|
||||
mkdir_mode=-m$mode
|
||||
else
|
||||
mkdir_mode=
|
||||
fi
|
||||
|
||||
posix_mkdir=false
|
||||
case $umask in
|
||||
*[123567][0-7][0-7])
|
||||
# POSIX mkdir -p sets u+wx bits regardless of umask, which
|
||||
# is incompatible with FreeBSD 'install' when (umask & 300) != 0.
|
||||
;;
|
||||
*)
|
||||
tmpdir=${TMPDIR-/tmp}/ins$RANDOM-$$
|
||||
trap 'ret=$?; rmdir "$tmpdir/d" "$tmpdir" 2>/dev/null; exit $ret' 0
|
||||
|
||||
if (umask $mkdir_umask &&
|
||||
exec $mkdirprog $mkdir_mode -p -- "$tmpdir/d") >/dev/null 2>&1
|
||||
then
|
||||
if test -z "$dir_arg" || {
|
||||
# Check for POSIX incompatibilities with -m.
|
||||
# HP-UX 11.23 and IRIX 6.5 mkdir -m -p sets group- or
|
||||
# other-writeable bit of parent directory when it shouldn't.
|
||||
# FreeBSD 6.1 mkdir -m -p sets mode of existing directory.
|
||||
ls_ld_tmpdir=`ls -ld "$tmpdir"`
|
||||
case $ls_ld_tmpdir in
|
||||
d????-?r-*) different_mode=700;;
|
||||
d????-?--*) different_mode=755;;
|
||||
*) false;;
|
||||
esac &&
|
||||
$mkdirprog -m$different_mode -p -- "$tmpdir" && {
|
||||
ls_ld_tmpdir_1=`ls -ld "$tmpdir"`
|
||||
test "$ls_ld_tmpdir" = "$ls_ld_tmpdir_1"
|
||||
}
|
||||
}
|
||||
then posix_mkdir=:
|
||||
fi
|
||||
rmdir "$tmpdir/d" "$tmpdir"
|
||||
else
|
||||
# Remove any dirs left behind by ancient mkdir implementations.
|
||||
rmdir ./$mkdir_mode ./-p ./-- 2>/dev/null
|
||||
fi
|
||||
trap '' 0;;
|
||||
esac;;
|
||||
esac
|
||||
|
||||
if
|
||||
$posix_mkdir && (
|
||||
umask $mkdir_umask &&
|
||||
$doit_exec $mkdirprog $mkdir_mode -p -- "$dstdir"
|
||||
)
|
||||
then :
|
||||
else
|
||||
|
||||
# The umask is ridiculous, or mkdir does not conform to POSIX,
|
||||
# or it failed possibly due to a race condition. Create the
|
||||
# directory the slow way, step by step, checking for races as we go.
|
||||
|
||||
case $dstdir in
|
||||
/*) prefix='/';;
|
||||
-*) prefix='./';;
|
||||
*) prefix='';;
|
||||
esac
|
||||
|
||||
eval "$initialize_posix_glob"
|
||||
|
||||
oIFS=$IFS
|
||||
IFS=/
|
||||
$posix_glob set -f
|
||||
set fnord $dstdir
|
||||
shift
|
||||
$posix_glob set +f
|
||||
IFS=$oIFS
|
||||
|
||||
prefixes=
|
||||
|
||||
for d
|
||||
do
|
||||
test -z "$d" && continue
|
||||
|
||||
prefix=$prefix$d
|
||||
if test -d "$prefix"; then
|
||||
prefixes=
|
||||
else
|
||||
if $posix_mkdir; then
|
||||
(umask=$mkdir_umask &&
|
||||
$doit_exec $mkdirprog $mkdir_mode -p -- "$dstdir") && break
|
||||
# Don't fail if two instances are running concurrently.
|
||||
test -d "$prefix" || exit 1
|
||||
else
|
||||
case $prefix in
|
||||
*\'*) qprefix=`echo "$prefix" | sed "s/'/'\\\\\\\\''/g"`;;
|
||||
*) qprefix=$prefix;;
|
||||
esac
|
||||
prefixes="$prefixes '$qprefix'"
|
||||
fi
|
||||
fi
|
||||
prefix=$prefix/
|
||||
done
|
||||
|
||||
if test -n "$prefixes"; then
|
||||
# Don't fail if two instances are running concurrently.
|
||||
(umask $mkdir_umask &&
|
||||
eval "\$doit_exec \$mkdirprog $prefixes") ||
|
||||
test -d "$dstdir" || exit 1
|
||||
obsolete_mkdir_used=true
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
if test -n "$dir_arg"; then
|
||||
{ test -z "$chowncmd" || $doit $chowncmd "$dst"; } &&
|
||||
{ test -z "$chgrpcmd" || $doit $chgrpcmd "$dst"; } &&
|
||||
{ test "$obsolete_mkdir_used$chowncmd$chgrpcmd" = false ||
|
||||
test -z "$chmodcmd" || $doit $chmodcmd $mode "$dst"; } || exit 1
|
||||
else
|
||||
|
||||
# Make a couple of temp file names in the proper directory.
|
||||
dsttmp=$dstdir/_inst.$$_
|
||||
rmtmp=$dstdir/_rm.$$_
|
||||
|
||||
# Trap to clean up those temp files at exit.
|
||||
trap 'ret=$?; rm -f "$dsttmp" "$rmtmp" && exit $ret' 0
|
||||
|
||||
# Copy the file name to the temp name.
|
||||
(umask $cp_umask && $doit_exec $cpprog "$src" "$dsttmp") &&
|
||||
|
||||
# and set any options; do chmod last to preserve setuid bits.
|
||||
#
|
||||
# If any of these fail, we abort the whole thing. If we want to
|
||||
# ignore errors from any of these, just make sure not to ignore
|
||||
# errors from the above "$doit $cpprog $src $dsttmp" command.
|
||||
#
|
||||
{ test -z "$chowncmd" || $doit $chowncmd "$dsttmp"; } &&
|
||||
{ test -z "$chgrpcmd" || $doit $chgrpcmd "$dsttmp"; } &&
|
||||
{ test -z "$stripcmd" || $doit $stripcmd "$dsttmp"; } &&
|
||||
{ test -z "$chmodcmd" || $doit $chmodcmd $mode "$dsttmp"; } &&
|
||||
|
||||
# If -C, don't bother to copy if it wouldn't change the file.
|
||||
if $copy_on_change &&
|
||||
old=`LC_ALL=C ls -dlL "$dst" 2>/dev/null` &&
|
||||
new=`LC_ALL=C ls -dlL "$dsttmp" 2>/dev/null` &&
|
||||
|
||||
eval "$initialize_posix_glob" &&
|
||||
$posix_glob set -f &&
|
||||
set X $old && old=:$2:$4:$5:$6 &&
|
||||
set X $new && new=:$2:$4:$5:$6 &&
|
||||
$posix_glob set +f &&
|
||||
|
||||
test "$old" = "$new" &&
|
||||
$cmpprog "$dst" "$dsttmp" >/dev/null 2>&1
|
||||
then
|
||||
rm -f "$dsttmp"
|
||||
else
|
||||
# Rename the file to the real destination.
|
||||
$doit $mvcmd -f "$dsttmp" "$dst" 2>/dev/null ||
|
||||
|
||||
# The rename failed, perhaps because mv can't rename something else
|
||||
# to itself, or perhaps because mv is so ancient that it does not
|
||||
# support -f.
|
||||
{
|
||||
# Now remove or move aside any old file at destination location.
|
||||
# We try this two ways since rm can't unlink itself on some
|
||||
# systems and the destination file might be busy for other
|
||||
# reasons. In this case, the final cleanup might fail but the new
|
||||
# file should still install successfully.
|
||||
{
|
||||
test ! -f "$dst" ||
|
||||
$doit $rmcmd -f "$dst" 2>/dev/null ||
|
||||
{ $doit $mvcmd -f "$dst" "$rmtmp" 2>/dev/null &&
|
||||
{ $doit $rmcmd -f "$rmtmp" 2>/dev/null; :; }
|
||||
} ||
|
||||
{ echo "$0: cannot unlink or rename $dst" >&2
|
||||
(exit 1); exit 1
|
||||
}
|
||||
} &&
|
||||
|
||||
# Now rename the file to the real destination.
|
||||
$doit $mvcmd "$dsttmp" "$dst"
|
||||
}
|
||||
fi || exit 1
|
||||
|
||||
trap '' 0
|
||||
fi
|
||||
done
|
||||
|
||||
# Local variables:
|
||||
# eval: (add-hook 'write-file-hooks 'time-stamp)
|
||||
# time-stamp-start: "scriptversion="
|
||||
# time-stamp-format: "%:y-%02m-%02d.%02H"
|
||||
# time-stamp-time-zone: "UTC"
|
||||
# time-stamp-end: "; # UTC"
|
||||
# End:
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,414 +0,0 @@
|
||||
# makefile.vc -- -*- Makefile -*-
|
||||
#
|
||||
# Microsoft Visual C++ makefile for use with nmake.exe v1.62+ (VC++ 5.0+)
|
||||
#
|
||||
# This makefile is based upon the Tcl 8.4 Makefile.vc and modified to
|
||||
# make it suitable as a general package makefile. Look for the word EDIT
|
||||
# which marks sections that may need modification. As a minumum you will
|
||||
# need to change the PROJECT, DOTVERSION and DLLOBJS variables to values
|
||||
# relevant to your package.
|
||||
#
|
||||
# See the file "license.terms" for information on usage and redistribution
|
||||
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
|
||||
#
|
||||
# Copyright (c) 1995-1996 Sun Microsystems, Inc.
|
||||
# Copyright (c) 1998-2000 Ajuba Solutions.
|
||||
# Copyright (c) 2001 ActiveState Corporation.
|
||||
# Copyright (c) 2001-2002 David Gravereaux.
|
||||
# Copyright (c) 2003 Pat Thoyts
|
||||
#
|
||||
#-------------------------------------------------------------------------
|
||||
# RCS: @(#)$Id: makefile.vc,v 1.4 2004/07/26 08:22:05 patthoyts Exp $
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
!if !defined(MSDEVDIR) && !defined(MSVCDIR) && !defined(VCINSTALLDIR) && !defined(MSSDK) && !defined(WINDOWSSDKDIR)
|
||||
MSG = ^
|
||||
You will need to run vcvars32.bat from Developer Studio, first, to setup^
|
||||
the environment. Jump to this line to read the new instructions.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
|
||||
#------------------------------------------------------------------------------
|
||||
# HOW TO USE this makefile:
|
||||
#
|
||||
# 1) It is now necessary to have %MSVCDir% set in the environment. This is
|
||||
# used as a check to see if vcvars32.bat had been run prior to running
|
||||
# nmake or during the installation of Microsoft Visual C++, MSVCDir had
|
||||
# been set globally and the PATH adjusted. Either way is valid.
|
||||
#
|
||||
# You'll need to run vcvars32.bat contained in the MsDev's vc(98)/bin
|
||||
# directory to setup the proper environment, if needed, for your current
|
||||
# setup. This is a needed bootstrap requirement and allows the swapping of
|
||||
# different environments to be easier.
|
||||
#
|
||||
# 2) To use the Platform SDK (not expressly needed), run setenv.bat after
|
||||
# vcvars32.bat according to the instructions for it. This can also turn on
|
||||
# the 64-bit compiler, if your SDK has it.
|
||||
#
|
||||
# 3) Targets are:
|
||||
# all -- Builds everything.
|
||||
# <project> -- Builds the project (eg: nmake sample)
|
||||
# test -- Builds and runs the test suite.
|
||||
# install -- Installs the built binaries and libraries to $(INSTALLDIR)
|
||||
# in an appropriate subdirectory.
|
||||
# clean/realclean/distclean -- varying levels of cleaning.
|
||||
#
|
||||
# 4) Macros usable on the commandline:
|
||||
# INSTALLDIR=<path>
|
||||
# Sets where to install Tcl from the built binaries.
|
||||
# C:\Progra~1\Tcl is assumed when not specified.
|
||||
#
|
||||
# OPTS=static,msvcrt,staticpkg,threads,symbols,profile,loimpact,none
|
||||
# Sets special options for the core. The default is for none.
|
||||
# Any combination of the above may be used (comma separated).
|
||||
# 'none' will over-ride everything to nothing.
|
||||
#
|
||||
# static = Builds a static library of the core instead of a
|
||||
# dll. The shell will be static (and large), as well.
|
||||
# msvcrt = Effects the static option only to switch it from
|
||||
# using libcmt(d) as the C runtime [by default] to
|
||||
# msvcrt(d). This is useful for static embedding
|
||||
# support.
|
||||
# staticpkg = Effects the static option only to switch
|
||||
# tclshXX.exe to have the dde and reg extension linked
|
||||
# inside it.
|
||||
# threads = Turns on full multithreading support.
|
||||
# thrdalloc = Use the thread allocator (shared global free pool).
|
||||
# symbols = Adds symbols for step debugging.
|
||||
# profile = Adds profiling hooks. Map file is assumed.
|
||||
# loimpact = Adds a flag for how NT treats the heap to keep memory
|
||||
# in use, low. This is said to impact alloc performance.
|
||||
#
|
||||
# STATS=memdbg,compdbg,none
|
||||
# Sets optional memory and bytecode compiler debugging code added
|
||||
# to the core. The default is for none. Any combination of the
|
||||
# above may be used (comma separated). 'none' will over-ride
|
||||
# everything to nothing.
|
||||
#
|
||||
# memdbg = Enables the debugging memory allocator.
|
||||
# compdbg = Enables byte compilation logging.
|
||||
#
|
||||
# MACHINE=(IX86|IA64|ALPHA)
|
||||
# Set the machine type used for the compiler, linker, and
|
||||
# resource compiler. This hook is needed to tell the tools
|
||||
# when alternate platforms are requested. IX86 is the default
|
||||
# when not specified.
|
||||
#
|
||||
# TMP_DIR=<path>
|
||||
# OUT_DIR=<path>
|
||||
# Hooks to allow the intermediate and output directories to be
|
||||
# changed. $(OUT_DIR) is assumed to be
|
||||
# $(BINROOT)\(Release|Debug) based on if symbols are requested.
|
||||
# $(TMP_DIR) will de $(OUT_DIR)\<buildtype> by default.
|
||||
#
|
||||
# TESTPAT=<file>
|
||||
# Reads the tests requested to be run from this file.
|
||||
#
|
||||
# CFG_ENCODING=encoding
|
||||
# name of encoding for configuration information. Defaults
|
||||
# to cp1252
|
||||
#
|
||||
# 5) Examples:
|
||||
#
|
||||
# Basic syntax of calling nmake looks like this:
|
||||
# nmake [-nologo] -f makefile.vc [target|macrodef [target|macrodef] [...]]
|
||||
#
|
||||
# Standard (no frills)
|
||||
# c:\tcl_src\win\>c:\progra~1\micros~1\vc98\bin\vcvars32.bat
|
||||
# Setting environment for using Microsoft Visual C++ tools.
|
||||
# c:\tcl_src\win\>nmake -f makefile.vc all
|
||||
# c:\tcl_src\win\>nmake -f makefile.vc install INSTALLDIR=c:\progra~1\tcl
|
||||
#
|
||||
# Building for Win64
|
||||
# c:\tcl_src\win\>c:\progra~1\micros~1\vc98\bin\vcvars32.bat
|
||||
# Setting environment for using Microsoft Visual C++ tools.
|
||||
# c:\tcl_src\win\>c:\progra~1\platfo~1\setenv.bat /pre64 /RETAIL
|
||||
# Targeting Windows pre64 RETAIL
|
||||
# c:\tcl_src\win\>nmake -f makefile.vc MACHINE=IA64
|
||||
#
|
||||
#------------------------------------------------------------------------------
|
||||
#==============================================================================
|
||||
###############################################################################
|
||||
#------------------------------------------------------------------------------
|
||||
|
||||
!if !exist("makefile.vc")
|
||||
MSG = ^
|
||||
You must run this makefile only from the directory it is in.^
|
||||
Please `cd` to its location first.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Project specific information (EDIT)
|
||||
#
|
||||
# You should edit this with the name and version of your project. This
|
||||
# information is used to generate the name of the package library and
|
||||
# it's install location.
|
||||
#
|
||||
# For example, the sample extension is going to build sample04.dll and
|
||||
# would install it into $(INSTALLDIR)\lib\sample04
|
||||
#
|
||||
# You need to specify the object files that need to be linked into your
|
||||
# binary here.
|
||||
#
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
PROJECT = sqlite3
|
||||
!include "rules.vc"
|
||||
|
||||
# nmakehelp -V <file> <tag> will search the file for tag, skips until a
|
||||
# number and returns all character until a character not in [0-9.ab]
|
||||
# is read.
|
||||
|
||||
!if [echo REM = This file is generated from Makefile.vc > versions.vc]
|
||||
!endif
|
||||
# get project version from row "AC_INIT([sqlite], [3.7.14])"
|
||||
!if [echo DOTVERSION = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\configure.in AC_INIT >> versions.vc]
|
||||
!endif
|
||||
!include "versions.vc"
|
||||
|
||||
VERSION = $(DOTVERSION:.=)
|
||||
STUBPREFIX = $(PROJECT)stub
|
||||
|
||||
DLLOBJS = \
|
||||
$(TMP_DIR)\tclsqlite3.obj
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Target names and paths ( shouldn't need changing )
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
BINROOT = .
|
||||
ROOT = ..
|
||||
|
||||
PRJIMPLIB = $(OUT_DIR)\$(PROJECT)$(VERSION)$(SUFX).lib
|
||||
PRJLIBNAME = $(PROJECT)$(VERSION)$(SUFX).$(EXT)
|
||||
PRJLIB = $(OUT_DIR)\$(PRJLIBNAME)
|
||||
|
||||
PRJSTUBLIBNAME = $(STUBPREFIX)$(VERSION).lib
|
||||
PRJSTUBLIB = $(OUT_DIR)\$(PRJSTUBLIBNAME)
|
||||
|
||||
### Make sure we use backslash only.
|
||||
PRJ_INSTALL_DIR = $(_INSTALLDIR)\$(PROJECT)$(DOTVERSION)
|
||||
LIB_INSTALL_DIR = $(PRJ_INSTALL_DIR)
|
||||
BIN_INSTALL_DIR = $(PRJ_INSTALL_DIR)
|
||||
DOC_INSTALL_DIR = $(PRJ_INSTALL_DIR)
|
||||
SCRIPT_INSTALL_DIR = $(PRJ_INSTALL_DIR)
|
||||
INCLUDE_INSTALL_DIR = $(_TCLDIR)\include
|
||||
|
||||
### The following paths CANNOT have spaces in them.
|
||||
GENERICDIR = $(ROOT)\generic
|
||||
WINDIR = $(ROOT)\win
|
||||
LIBDIR = $(ROOT)\library
|
||||
DOCDIR = $(ROOT)\doc
|
||||
TOOLSDIR = $(ROOT)\tools
|
||||
COMPATDIR = $(ROOT)\compat
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Compile flags
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
!if !$(DEBUG)
|
||||
!if $(OPTIMIZING)
|
||||
### This cranks the optimization level to maximize speed
|
||||
cdebug = -O2 -Op -Gs
|
||||
!else
|
||||
cdebug =
|
||||
!endif
|
||||
!else if "$(MACHINE)" == "IA64"
|
||||
### Warnings are too many, can't support warnings into errors.
|
||||
cdebug = -Z7 -Od -GZ
|
||||
!else
|
||||
cdebug = -Z7 -WX -Od -GZ
|
||||
!endif
|
||||
|
||||
### Declarations common to all compiler options
|
||||
cflags = -nologo -c -W3 -YX -Fp$(TMP_DIR)^\
|
||||
|
||||
!if $(MSVCRT)
|
||||
!if $(DEBUG)
|
||||
crt = -MDd
|
||||
!else
|
||||
crt = -MD
|
||||
!endif
|
||||
!else
|
||||
!if $(DEBUG)
|
||||
crt = -MTd
|
||||
!else
|
||||
crt = -MT
|
||||
!endif
|
||||
!endif
|
||||
|
||||
INCLUDES = $(TCL_INCLUDES) -I"$(WINDIR)" -I"$(GENERICDIR)" \
|
||||
-I"$(ROOT)\.."
|
||||
BASE_CLFAGS = $(cflags) $(cdebug) $(crt) $(INCLUDES) \
|
||||
-DSQLITE_3_SUFFIX_ONLY=1 -DSQLITE_ENABLE_RTREE=1 \
|
||||
-DSQLITE_ENABLE_FTS3=1 -DSQLITE_OMIT_DEPRECATED=1
|
||||
CON_CFLAGS = $(cflags) $(cdebug) $(crt) -DCONSOLE -DSQLITE_ENABLE_FTS3=1
|
||||
TCL_CFLAGS = -DBUILD_sqlite -DUSE_TCL_STUBS \
|
||||
-DPACKAGE_VERSION="\"$(DOTVERSION)\"" $(BASE_CLFAGS) \
|
||||
$(OPTDEFINES)
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Link flags
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
!if $(DEBUG)
|
||||
ldebug = -debug:full -debugtype:cv
|
||||
!else
|
||||
ldebug = -release -opt:ref -opt:icf,3
|
||||
!endif
|
||||
|
||||
### Declarations common to all linker options
|
||||
lflags = -nologo -machine:$(MACHINE) $(ldebug)
|
||||
|
||||
!if $(PROFILE)
|
||||
lflags = $(lflags) -profile
|
||||
!endif
|
||||
|
||||
!if $(ALIGN98_HACK) && !$(STATIC_BUILD)
|
||||
### Align sections for PE size savings.
|
||||
lflags = $(lflags) -opt:nowin98
|
||||
!else if !$(ALIGN98_HACK) && $(STATIC_BUILD)
|
||||
### Align sections for speed in loading by choosing the virtual page size.
|
||||
lflags = $(lflags) -align:4096
|
||||
!endif
|
||||
|
||||
!if $(LOIMPACT)
|
||||
lflags = $(lflags) -ws:aggressive
|
||||
!endif
|
||||
|
||||
dlllflags = $(lflags) -dll
|
||||
conlflags = $(lflags) -subsystem:console
|
||||
guilflags = $(lflags) -subsystem:windows
|
||||
baselibs = $(TCLSTUBLIB)
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# TclTest flags
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
!IF "$(TESTPAT)" != ""
|
||||
TESTFLAGS = $(TESTFLAGS) -file $(TESTPAT)
|
||||
!ENDIF
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Project specific targets (EDIT)
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
all: setup $(PROJECT)
|
||||
$(PROJECT): setup $(PRJLIB)
|
||||
install: install-binaries install-libraries install-docs
|
||||
|
||||
# Tests need to ensure we load the right dll file we
|
||||
# have to handle the output differently on Win9x.
|
||||
#
|
||||
!if "$(OS)" == "Windows_NT" || "$(MSVCDIR)" == "IDE"
|
||||
test: setup $(PROJECT)
|
||||
set TCL_LIBRARY=$(ROOT)/library
|
||||
$(TCLSH) <<
|
||||
load $(PRJLIB:\=/)
|
||||
cd "$(ROOT)/tests"
|
||||
set argv "$(TESTFLAGS)"
|
||||
source all.tcl
|
||||
<<
|
||||
!else
|
||||
test: setup $(PROJECT)
|
||||
echo Please wait while the test results are collected
|
||||
set TCL_LIBRARY=$(ROOT)/library
|
||||
$(TCLSH) << >tests.log
|
||||
load $(PRJLIB:\=/)
|
||||
cd "$(ROOT)/tests"
|
||||
set argv "$(TESTFLAGS)"
|
||||
source all.tcl
|
||||
<<
|
||||
type tests.log | more
|
||||
!endif
|
||||
|
||||
setup:
|
||||
@if not exist $(OUT_DIR)\nul mkdir $(OUT_DIR)
|
||||
@if not exist $(TMP_DIR)\nul mkdir $(TMP_DIR)
|
||||
|
||||
$(PRJLIB): $(DLLOBJS)
|
||||
$(link32) $(dlllflags) -out:$@ $(baselibs) @<<
|
||||
$**
|
||||
<<
|
||||
-@del $*.exp
|
||||
|
||||
$(PRJSTUBLIB): $(PRJSTUBOBJS)
|
||||
$(lib32) -nologo -out:$@ $(PRJSTUBOBJS)
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Implicit rules
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
{$(WINDIR)}.c{$(TMP_DIR)}.obj::
|
||||
$(cc32) $(TCL_CFLAGS) -DBUILD_$(PROJECT) -Fo$(TMP_DIR)\ @<<
|
||||
$<
|
||||
<<
|
||||
|
||||
{$(GENERICDIR)}.c{$(TMP_DIR)}.obj::
|
||||
$(cc32) $(TCL_CFLAGS) -DBUILD_$(PROJECT) -Fo$(TMP_DIR)\ @<<
|
||||
$<
|
||||
<<
|
||||
|
||||
{$(COMPATDIR)}.c{$(TMP_DIR)}.obj::
|
||||
$(cc32) $(TCL_CFLAGS) -DBUILD_$(PROJECT) -Fo$(TMP_DIR)\ @<<
|
||||
$<
|
||||
<<
|
||||
|
||||
{$(WINDIR)}.rc{$(TMP_DIR)}.res:
|
||||
$(rc32) -fo $@ -r -i "$(GENERICDIR)" -D__WIN32__ \
|
||||
!if $(DEBUG)
|
||||
-d DEBUG \
|
||||
!endif
|
||||
!if $(TCL_THREADS)
|
||||
-d TCL_THREADS \
|
||||
!endif
|
||||
!if $(STATIC_BUILD)
|
||||
-d STATIC_BUILD \
|
||||
!endif
|
||||
$<
|
||||
|
||||
.SUFFIXES:
|
||||
.SUFFIXES:.c .rc
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Installation. (EDIT)
|
||||
#
|
||||
# You may need to modify this section to reflect the final distribution
|
||||
# of your files and possibly to generate documentation.
|
||||
#
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
install-binaries:
|
||||
@echo Installing binaries to '$(SCRIPT_INSTALL_DIR)'
|
||||
@if not exist "$(SCRIPT_INSTALL_DIR)" mkdir "$(SCRIPT_INSTALL_DIR)"
|
||||
@$(CPY) $(PRJLIB) "$(SCRIPT_INSTALL_DIR)" >NUL
|
||||
|
||||
install-libraries:
|
||||
@echo Installing libraries to '$(SCRIPT_INSTALL_DIR)'
|
||||
@if exist $(LIBDIR) $(CPY) $(LIBDIR)\*.tcl "$(SCRIPT_INSTALL_DIR)"
|
||||
@echo Installing package index in '$(SCRIPT_INSTALL_DIR)'
|
||||
@type << >"$(SCRIPT_INSTALL_DIR)\pkgIndex.tcl"
|
||||
package ifneeded $(PROJECT) $(DOTVERSION) \
|
||||
[list load [file join $$dir $(PRJLIBNAME)] sqlite3]
|
||||
<<
|
||||
|
||||
install-docs:
|
||||
@echo Installing documentation files to '$(DOC_INSTALL_DIR)'
|
||||
@if exist $(DOCDIR) $(CPY) $(DOCDIR)\*.n "$(DOC_INSTALL_DIR)"
|
||||
|
||||
#---------------------------------------------------------------------
|
||||
# Clean up
|
||||
#---------------------------------------------------------------------
|
||||
|
||||
clean:
|
||||
@if exist $(TMP_DIR)\nul $(RMDIR) $(TMP_DIR)
|
||||
@if exist $(WINDIR)\version.vc del $(WINDIR)\version.vc
|
||||
|
||||
realclean: clean
|
||||
@if exist $(OUT_DIR)\nul $(RMDIR) $(OUT_DIR)
|
||||
|
||||
distclean: realclean
|
||||
@if exist $(WINDIR)\nmakehlp.exe del $(WINDIR)\nmakehlp.exe
|
||||
@if exist $(WINDIR)\nmakehlp.obj del $(WINDIR)\nmakehlp.obj
|
||||
@@ -1,694 +0,0 @@
|
||||
/*
|
||||
* ----------------------------------------------------------------------------
|
||||
* nmakehlp.c --
|
||||
*
|
||||
* This is used to fix limitations within nmake and the environment.
|
||||
*
|
||||
* Copyright (c) 2002 by David Gravereaux.
|
||||
* Copyright (c) 2006 by Pat Thoyts
|
||||
*
|
||||
* See the file "license.terms" for information on usage and redistribution of
|
||||
* this file, and for a DISCLAIMER OF ALL WARRANTIES.
|
||||
* ----------------------------------------------------------------------------
|
||||
*/
|
||||
|
||||
#define _CRT_SECURE_NO_DEPRECATE
|
||||
#include <windows.h>
|
||||
#define NO_SHLWAPI_GDI
|
||||
#define NO_SHLWAPI_STREAM
|
||||
#define NO_SHLWAPI_REG
|
||||
#include <shlwapi.h>
|
||||
#pragma comment (lib, "user32.lib")
|
||||
#pragma comment (lib, "kernel32.lib")
|
||||
#pragma comment (lib, "shlwapi.lib")
|
||||
#include <stdio.h>
|
||||
#include <math.h>
|
||||
|
||||
/*
|
||||
* This library is required for x64 builds with _some_ versions of MSVC
|
||||
*/
|
||||
#if defined(_M_IA64) || defined(_M_AMD64)
|
||||
#if _MSC_VER >= 1400 && _MSC_VER < 1500
|
||||
#pragma comment(lib, "bufferoverflowU")
|
||||
#endif
|
||||
#endif
|
||||
|
||||
/* ISO hack for dumb VC++ */
|
||||
#ifdef _MSC_VER
|
||||
#define snprintf _snprintf
|
||||
#endif
|
||||
|
||||
|
||||
|
||||
/* protos */
|
||||
|
||||
static int CheckForCompilerFeature(const char *option);
|
||||
static int CheckForLinkerFeature(const char *option);
|
||||
static int IsIn(const char *string, const char *substring);
|
||||
static int SubstituteFile(const char *substs, const char *filename);
|
||||
static int QualifyPath(const char *path);
|
||||
static const char *GetVersionFromFile(const char *filename, const char *match);
|
||||
static DWORD WINAPI ReadFromPipe(LPVOID args);
|
||||
|
||||
/* globals */
|
||||
|
||||
#define CHUNK 25
|
||||
#define STATICBUFFERSIZE 1000
|
||||
typedef struct {
|
||||
HANDLE pipe;
|
||||
char buffer[STATICBUFFERSIZE];
|
||||
} pipeinfo;
|
||||
|
||||
pipeinfo Out = {INVALID_HANDLE_VALUE, '\0'};
|
||||
pipeinfo Err = {INVALID_HANDLE_VALUE, '\0'};
|
||||
|
||||
/*
|
||||
* exitcodes: 0 == no, 1 == yes, 2 == error
|
||||
*/
|
||||
|
||||
int
|
||||
main(
|
||||
int argc,
|
||||
char *argv[])
|
||||
{
|
||||
char msg[300];
|
||||
DWORD dwWritten;
|
||||
int chars;
|
||||
|
||||
/*
|
||||
* Make sure children (cl.exe and link.exe) are kept quiet.
|
||||
*/
|
||||
|
||||
SetErrorMode(SEM_FAILCRITICALERRORS | SEM_NOOPENFILEERRORBOX);
|
||||
|
||||
/*
|
||||
* Make sure the compiler and linker aren't effected by the outside world.
|
||||
*/
|
||||
|
||||
SetEnvironmentVariable("CL", "");
|
||||
SetEnvironmentVariable("LINK", "");
|
||||
|
||||
if (argc > 1 && *argv[1] == '-') {
|
||||
switch (*(argv[1]+1)) {
|
||||
case 'c':
|
||||
if (argc != 3) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -c <compiler option>\n"
|
||||
"Tests for whether cl.exe supports an option\n"
|
||||
"exitcodes: 0 == no, 1 == yes, 2 == error\n", argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 2;
|
||||
}
|
||||
return CheckForCompilerFeature(argv[2]);
|
||||
case 'l':
|
||||
if (argc != 3) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -l <linker option>\n"
|
||||
"Tests for whether link.exe supports an option\n"
|
||||
"exitcodes: 0 == no, 1 == yes, 2 == error\n", argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 2;
|
||||
}
|
||||
return CheckForLinkerFeature(argv[2]);
|
||||
case 'f':
|
||||
if (argc == 2) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -f <string> <substring>\n"
|
||||
"Find a substring within another\n"
|
||||
"exitcodes: 0 == no, 1 == yes, 2 == error\n", argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 2;
|
||||
} else if (argc == 3) {
|
||||
/*
|
||||
* If the string is blank, there is no match.
|
||||
*/
|
||||
|
||||
return 0;
|
||||
} else {
|
||||
return IsIn(argv[2], argv[3]);
|
||||
}
|
||||
case 's':
|
||||
if (argc == 2) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -s <substitutions file> <file>\n"
|
||||
"Perform a set of string map type substutitions on a file\n"
|
||||
"exitcodes: 0\n",
|
||||
argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 2;
|
||||
}
|
||||
return SubstituteFile(argv[2], argv[3]);
|
||||
case 'V':
|
||||
if (argc != 4) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -V filename matchstring\n"
|
||||
"Extract a version from a file:\n"
|
||||
"eg: pkgIndex.tcl \"package ifneeded http\"",
|
||||
argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 0;
|
||||
}
|
||||
printf("%s\n", GetVersionFromFile(argv[2], argv[3]));
|
||||
return 0;
|
||||
case 'Q':
|
||||
if (argc != 3) {
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -Q path\n"
|
||||
"Emit the fully qualified path\n"
|
||||
"exitcodes: 0 == no, 1 == yes, 2 == error\n", argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars,
|
||||
&dwWritten, NULL);
|
||||
return 2;
|
||||
}
|
||||
return QualifyPath(argv[2]);
|
||||
}
|
||||
}
|
||||
chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"usage: %s -c|-f|-l|-Q|-s|-V ...\n"
|
||||
"This is a little helper app to equalize shell differences between WinNT and\n"
|
||||
"Win9x and get nmake.exe to accomplish its job.\n",
|
||||
argv[0]);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, chars, &dwWritten, NULL);
|
||||
return 2;
|
||||
}
|
||||
|
||||
static int
|
||||
CheckForCompilerFeature(
|
||||
const char *option)
|
||||
{
|
||||
STARTUPINFO si;
|
||||
PROCESS_INFORMATION pi;
|
||||
SECURITY_ATTRIBUTES sa;
|
||||
DWORD threadID;
|
||||
char msg[300];
|
||||
BOOL ok;
|
||||
HANDLE hProcess, h, pipeThreads[2];
|
||||
char cmdline[100];
|
||||
|
||||
hProcess = GetCurrentProcess();
|
||||
|
||||
ZeroMemory(&pi, sizeof(PROCESS_INFORMATION));
|
||||
ZeroMemory(&si, sizeof(STARTUPINFO));
|
||||
si.cb = sizeof(STARTUPINFO);
|
||||
si.dwFlags = STARTF_USESTDHANDLES;
|
||||
si.hStdInput = INVALID_HANDLE_VALUE;
|
||||
|
||||
ZeroMemory(&sa, sizeof(SECURITY_ATTRIBUTES));
|
||||
sa.nLength = sizeof(SECURITY_ATTRIBUTES);
|
||||
sa.lpSecurityDescriptor = NULL;
|
||||
sa.bInheritHandle = FALSE;
|
||||
|
||||
/*
|
||||
* Create a non-inheritible pipe.
|
||||
*/
|
||||
|
||||
CreatePipe(&Out.pipe, &h, &sa, 0);
|
||||
|
||||
/*
|
||||
* Dupe the write side, make it inheritible, and close the original.
|
||||
*/
|
||||
|
||||
DuplicateHandle(hProcess, h, hProcess, &si.hStdOutput, 0, TRUE,
|
||||
DUPLICATE_SAME_ACCESS | DUPLICATE_CLOSE_SOURCE);
|
||||
|
||||
/*
|
||||
* Same as above, but for the error side.
|
||||
*/
|
||||
|
||||
CreatePipe(&Err.pipe, &h, &sa, 0);
|
||||
DuplicateHandle(hProcess, h, hProcess, &si.hStdError, 0, TRUE,
|
||||
DUPLICATE_SAME_ACCESS | DUPLICATE_CLOSE_SOURCE);
|
||||
|
||||
/*
|
||||
* Base command line.
|
||||
*/
|
||||
|
||||
lstrcpy(cmdline, "cl.exe -nologo -c -TC -Zs -X -Fp.\\_junk.pch ");
|
||||
|
||||
/*
|
||||
* Append our option for testing
|
||||
*/
|
||||
|
||||
lstrcat(cmdline, option);
|
||||
|
||||
/*
|
||||
* Filename to compile, which exists, but is nothing and empty.
|
||||
*/
|
||||
|
||||
lstrcat(cmdline, " .\\nul");
|
||||
|
||||
ok = CreateProcess(
|
||||
NULL, /* Module name. */
|
||||
cmdline, /* Command line. */
|
||||
NULL, /* Process handle not inheritable. */
|
||||
NULL, /* Thread handle not inheritable. */
|
||||
TRUE, /* yes, inherit handles. */
|
||||
DETACHED_PROCESS, /* No console for you. */
|
||||
NULL, /* Use parent's environment block. */
|
||||
NULL, /* Use parent's starting directory. */
|
||||
&si, /* Pointer to STARTUPINFO structure. */
|
||||
&pi); /* Pointer to PROCESS_INFORMATION structure. */
|
||||
|
||||
if (!ok) {
|
||||
DWORD err = GetLastError();
|
||||
int chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"Tried to launch: \"%s\", but got error [%u]: ", cmdline, err);
|
||||
|
||||
FormatMessage(FORMAT_MESSAGE_FROM_SYSTEM|FORMAT_MESSAGE_IGNORE_INSERTS|
|
||||
FORMAT_MESSAGE_MAX_WIDTH_MASK, 0L, err, 0, (LPVOID)&msg[chars],
|
||||
(300-chars), 0);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, lstrlen(msg), &err,NULL);
|
||||
return 2;
|
||||
}
|
||||
|
||||
/*
|
||||
* Close our references to the write handles that have now been inherited.
|
||||
*/
|
||||
|
||||
CloseHandle(si.hStdOutput);
|
||||
CloseHandle(si.hStdError);
|
||||
|
||||
WaitForInputIdle(pi.hProcess, 5000);
|
||||
CloseHandle(pi.hThread);
|
||||
|
||||
/*
|
||||
* Start the pipe reader threads.
|
||||
*/
|
||||
|
||||
pipeThreads[0] = CreateThread(NULL, 0, ReadFromPipe, &Out, 0, &threadID);
|
||||
pipeThreads[1] = CreateThread(NULL, 0, ReadFromPipe, &Err, 0, &threadID);
|
||||
|
||||
/*
|
||||
* Block waiting for the process to end.
|
||||
*/
|
||||
|
||||
WaitForSingleObject(pi.hProcess, INFINITE);
|
||||
CloseHandle(pi.hProcess);
|
||||
|
||||
/*
|
||||
* Wait for our pipe to get done reading, should it be a little slow.
|
||||
*/
|
||||
|
||||
WaitForMultipleObjects(2, pipeThreads, TRUE, 500);
|
||||
CloseHandle(pipeThreads[0]);
|
||||
CloseHandle(pipeThreads[1]);
|
||||
|
||||
/*
|
||||
* Look for the commandline warning code in both streams.
|
||||
* - in MSVC 6 & 7 we get D4002, in MSVC 8 we get D9002.
|
||||
*/
|
||||
|
||||
return !(strstr(Out.buffer, "D4002") != NULL
|
||||
|| strstr(Err.buffer, "D4002") != NULL
|
||||
|| strstr(Out.buffer, "D9002") != NULL
|
||||
|| strstr(Err.buffer, "D9002") != NULL
|
||||
|| strstr(Out.buffer, "D2021") != NULL
|
||||
|| strstr(Err.buffer, "D2021") != NULL);
|
||||
}
|
||||
|
||||
static int
|
||||
CheckForLinkerFeature(
|
||||
const char *option)
|
||||
{
|
||||
STARTUPINFO si;
|
||||
PROCESS_INFORMATION pi;
|
||||
SECURITY_ATTRIBUTES sa;
|
||||
DWORD threadID;
|
||||
char msg[300];
|
||||
BOOL ok;
|
||||
HANDLE hProcess, h, pipeThreads[2];
|
||||
char cmdline[100];
|
||||
|
||||
hProcess = GetCurrentProcess();
|
||||
|
||||
ZeroMemory(&pi, sizeof(PROCESS_INFORMATION));
|
||||
ZeroMemory(&si, sizeof(STARTUPINFO));
|
||||
si.cb = sizeof(STARTUPINFO);
|
||||
si.dwFlags = STARTF_USESTDHANDLES;
|
||||
si.hStdInput = INVALID_HANDLE_VALUE;
|
||||
|
||||
ZeroMemory(&sa, sizeof(SECURITY_ATTRIBUTES));
|
||||
sa.nLength = sizeof(SECURITY_ATTRIBUTES);
|
||||
sa.lpSecurityDescriptor = NULL;
|
||||
sa.bInheritHandle = TRUE;
|
||||
|
||||
/*
|
||||
* Create a non-inheritible pipe.
|
||||
*/
|
||||
|
||||
CreatePipe(&Out.pipe, &h, &sa, 0);
|
||||
|
||||
/*
|
||||
* Dupe the write side, make it inheritible, and close the original.
|
||||
*/
|
||||
|
||||
DuplicateHandle(hProcess, h, hProcess, &si.hStdOutput, 0, TRUE,
|
||||
DUPLICATE_SAME_ACCESS | DUPLICATE_CLOSE_SOURCE);
|
||||
|
||||
/*
|
||||
* Same as above, but for the error side.
|
||||
*/
|
||||
|
||||
CreatePipe(&Err.pipe, &h, &sa, 0);
|
||||
DuplicateHandle(hProcess, h, hProcess, &si.hStdError, 0, TRUE,
|
||||
DUPLICATE_SAME_ACCESS | DUPLICATE_CLOSE_SOURCE);
|
||||
|
||||
/*
|
||||
* Base command line.
|
||||
*/
|
||||
|
||||
lstrcpy(cmdline, "link.exe -nologo ");
|
||||
|
||||
/*
|
||||
* Append our option for testing.
|
||||
*/
|
||||
|
||||
lstrcat(cmdline, option);
|
||||
|
||||
ok = CreateProcess(
|
||||
NULL, /* Module name. */
|
||||
cmdline, /* Command line. */
|
||||
NULL, /* Process handle not inheritable. */
|
||||
NULL, /* Thread handle not inheritable. */
|
||||
TRUE, /* yes, inherit handles. */
|
||||
DETACHED_PROCESS, /* No console for you. */
|
||||
NULL, /* Use parent's environment block. */
|
||||
NULL, /* Use parent's starting directory. */
|
||||
&si, /* Pointer to STARTUPINFO structure. */
|
||||
&pi); /* Pointer to PROCESS_INFORMATION structure. */
|
||||
|
||||
if (!ok) {
|
||||
DWORD err = GetLastError();
|
||||
int chars = snprintf(msg, sizeof(msg) - 1,
|
||||
"Tried to launch: \"%s\", but got error [%u]: ", cmdline, err);
|
||||
|
||||
FormatMessage(FORMAT_MESSAGE_FROM_SYSTEM|FORMAT_MESSAGE_IGNORE_INSERTS|
|
||||
FORMAT_MESSAGE_MAX_WIDTH_MASK, 0L, err, 0, (LPVOID)&msg[chars],
|
||||
(300-chars), 0);
|
||||
WriteFile(GetStdHandle(STD_ERROR_HANDLE), msg, lstrlen(msg), &err,NULL);
|
||||
return 2;
|
||||
}
|
||||
|
||||
/*
|
||||
* Close our references to the write handles that have now been inherited.
|
||||
*/
|
||||
|
||||
CloseHandle(si.hStdOutput);
|
||||
CloseHandle(si.hStdError);
|
||||
|
||||
WaitForInputIdle(pi.hProcess, 5000);
|
||||
CloseHandle(pi.hThread);
|
||||
|
||||
/*
|
||||
* Start the pipe reader threads.
|
||||
*/
|
||||
|
||||
pipeThreads[0] = CreateThread(NULL, 0, ReadFromPipe, &Out, 0, &threadID);
|
||||
pipeThreads[1] = CreateThread(NULL, 0, ReadFromPipe, &Err, 0, &threadID);
|
||||
|
||||
/*
|
||||
* Block waiting for the process to end.
|
||||
*/
|
||||
|
||||
WaitForSingleObject(pi.hProcess, INFINITE);
|
||||
CloseHandle(pi.hProcess);
|
||||
|
||||
/*
|
||||
* Wait for our pipe to get done reading, should it be a little slow.
|
||||
*/
|
||||
|
||||
WaitForMultipleObjects(2, pipeThreads, TRUE, 500);
|
||||
CloseHandle(pipeThreads[0]);
|
||||
CloseHandle(pipeThreads[1]);
|
||||
|
||||
/*
|
||||
* Look for the commandline warning code in the stderr stream.
|
||||
*/
|
||||
|
||||
return !(strstr(Out.buffer, "LNK1117") != NULL ||
|
||||
strstr(Err.buffer, "LNK1117") != NULL ||
|
||||
strstr(Out.buffer, "LNK4044") != NULL ||
|
||||
strstr(Err.buffer, "LNK4044") != NULL);
|
||||
}
|
||||
|
||||
static DWORD WINAPI
|
||||
ReadFromPipe(
|
||||
LPVOID args)
|
||||
{
|
||||
pipeinfo *pi = (pipeinfo *) args;
|
||||
char *lastBuf = pi->buffer;
|
||||
DWORD dwRead;
|
||||
BOOL ok;
|
||||
|
||||
again:
|
||||
if (lastBuf - pi->buffer + CHUNK > STATICBUFFERSIZE) {
|
||||
CloseHandle(pi->pipe);
|
||||
return (DWORD)-1;
|
||||
}
|
||||
ok = ReadFile(pi->pipe, lastBuf, CHUNK, &dwRead, 0L);
|
||||
if (!ok || dwRead == 0) {
|
||||
CloseHandle(pi->pipe);
|
||||
return 0;
|
||||
}
|
||||
lastBuf += dwRead;
|
||||
goto again;
|
||||
|
||||
return 0; /* makes the compiler happy */
|
||||
}
|
||||
|
||||
static int
|
||||
IsIn(
|
||||
const char *string,
|
||||
const char *substring)
|
||||
{
|
||||
return (strstr(string, substring) != NULL);
|
||||
}
|
||||
|
||||
/*
|
||||
* GetVersionFromFile --
|
||||
* Looks for a match string in a file and then returns the version
|
||||
* following the match where a version is anything acceptable to
|
||||
* package provide or package ifneeded.
|
||||
*/
|
||||
|
||||
static const char *
|
||||
GetVersionFromFile(
|
||||
const char *filename,
|
||||
const char *match)
|
||||
{
|
||||
size_t cbBuffer = 100;
|
||||
static char szBuffer[100];
|
||||
char *szResult = NULL;
|
||||
FILE *fp = fopen(filename, "rt");
|
||||
|
||||
if (fp != NULL) {
|
||||
/*
|
||||
* Read data until we see our match string.
|
||||
*/
|
||||
|
||||
while (fgets(szBuffer, cbBuffer, fp) != NULL) {
|
||||
LPSTR p, q;
|
||||
|
||||
p = strstr(szBuffer, match);
|
||||
if (p != NULL) {
|
||||
/*
|
||||
* Skip to first digit.
|
||||
*/
|
||||
|
||||
while (*p && !isdigit(*p)) {
|
||||
++p;
|
||||
}
|
||||
|
||||
/*
|
||||
* Find ending whitespace.
|
||||
*/
|
||||
|
||||
q = p;
|
||||
while (*q && (isalnum(*q) || *q == '.')) {
|
||||
++q;
|
||||
}
|
||||
|
||||
memcpy(szBuffer, p, q - p);
|
||||
szBuffer[q-p] = 0;
|
||||
szResult = szBuffer;
|
||||
break;
|
||||
}
|
||||
}
|
||||
fclose(fp);
|
||||
}
|
||||
return szResult;
|
||||
}
|
||||
|
||||
/*
|
||||
* List helpers for the SubstituteFile function
|
||||
*/
|
||||
|
||||
typedef struct list_item_t {
|
||||
struct list_item_t *nextPtr;
|
||||
char * key;
|
||||
char * value;
|
||||
} list_item_t;
|
||||
|
||||
/* insert a list item into the list (list may be null) */
|
||||
static list_item_t *
|
||||
list_insert(list_item_t **listPtrPtr, const char *key, const char *value)
|
||||
{
|
||||
list_item_t *itemPtr = malloc(sizeof(list_item_t));
|
||||
if (itemPtr) {
|
||||
itemPtr->key = strdup(key);
|
||||
itemPtr->value = strdup(value);
|
||||
itemPtr->nextPtr = NULL;
|
||||
|
||||
while(*listPtrPtr) {
|
||||
listPtrPtr = &(*listPtrPtr)->nextPtr;
|
||||
}
|
||||
*listPtrPtr = itemPtr;
|
||||
}
|
||||
return itemPtr;
|
||||
}
|
||||
|
||||
static void
|
||||
list_free(list_item_t **listPtrPtr)
|
||||
{
|
||||
list_item_t *tmpPtr, *listPtr = *listPtrPtr;
|
||||
while (listPtr) {
|
||||
tmpPtr = listPtr;
|
||||
listPtr = listPtr->nextPtr;
|
||||
free(tmpPtr->key);
|
||||
free(tmpPtr->value);
|
||||
free(tmpPtr);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* SubstituteFile --
|
||||
* As windows doesn't provide anything useful like sed and it's unreliable
|
||||
* to use the tclsh you are building against (consider x-platform builds -
|
||||
* eg compiling AMD64 target from IX86) we provide a simple substitution
|
||||
* option here to handle autoconf style substitutions.
|
||||
* The substitution file is whitespace and line delimited. The file should
|
||||
* consist of lines matching the regular expression:
|
||||
* \s*\S+\s+\S*$
|
||||
*
|
||||
* Usage is something like:
|
||||
* nmakehlp -S << $** > $@
|
||||
* @PACKAGE_NAME@ $(PACKAGE_NAME)
|
||||
* @PACKAGE_VERSION@ $(PACKAGE_VERSION)
|
||||
* <<
|
||||
*/
|
||||
|
||||
static int
|
||||
SubstituteFile(
|
||||
const char *substitutions,
|
||||
const char *filename)
|
||||
{
|
||||
size_t cbBuffer = 1024;
|
||||
static char szBuffer[1024], szCopy[1024];
|
||||
char *szResult = NULL;
|
||||
list_item_t *substPtr = NULL;
|
||||
FILE *fp, *sp;
|
||||
|
||||
fp = fopen(filename, "rt");
|
||||
if (fp != NULL) {
|
||||
|
||||
/*
|
||||
* Build a list of substutitions from the first filename
|
||||
*/
|
||||
|
||||
sp = fopen(substitutions, "rt");
|
||||
if (sp != NULL) {
|
||||
while (fgets(szBuffer, cbBuffer, sp) != NULL) {
|
||||
unsigned char *ks, *ke, *vs, *ve;
|
||||
ks = (unsigned char*)szBuffer;
|
||||
while (ks && *ks && isspace(*ks)) ++ks;
|
||||
ke = ks;
|
||||
while (ke && *ke && !isspace(*ke)) ++ke;
|
||||
vs = ke;
|
||||
while (vs && *vs && isspace(*vs)) ++vs;
|
||||
ve = vs;
|
||||
while (ve && *ve && !(*ve == '\r' || *ve == '\n')) ++ve;
|
||||
*ke = 0, *ve = 0;
|
||||
list_insert(&substPtr, (char*)ks, (char*)vs);
|
||||
}
|
||||
fclose(sp);
|
||||
}
|
||||
|
||||
/* debug: dump the list */
|
||||
#ifdef _DEBUG
|
||||
{
|
||||
int n = 0;
|
||||
list_item_t *p = NULL;
|
||||
for (p = substPtr; p != NULL; p = p->nextPtr, ++n) {
|
||||
fprintf(stderr, "% 3d '%s' => '%s'\n", n, p->key, p->value);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Run the substitutions over each line of the input
|
||||
*/
|
||||
|
||||
while (fgets(szBuffer, cbBuffer, fp) != NULL) {
|
||||
list_item_t *p = NULL;
|
||||
for (p = substPtr; p != NULL; p = p->nextPtr) {
|
||||
char *m = strstr(szBuffer, p->key);
|
||||
if (m) {
|
||||
char *cp, *op, *sp;
|
||||
cp = szCopy;
|
||||
op = szBuffer;
|
||||
while (op != m) *cp++ = *op++;
|
||||
sp = p->value;
|
||||
while (sp && *sp) *cp++ = *sp++;
|
||||
op += strlen(p->key);
|
||||
while (*op) *cp++ = *op++;
|
||||
*cp = 0;
|
||||
memcpy(szBuffer, szCopy, sizeof(szCopy));
|
||||
}
|
||||
}
|
||||
printf(szBuffer);
|
||||
}
|
||||
|
||||
list_free(&substPtr);
|
||||
}
|
||||
fclose(fp);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* QualifyPath --
|
||||
*
|
||||
* This composes the current working directory with a provided path
|
||||
* and returns the fully qualified and normalized path.
|
||||
* Mostly needed to setup paths for testing.
|
||||
*/
|
||||
|
||||
static int
|
||||
QualifyPath(
|
||||
const char *szPath)
|
||||
{
|
||||
char szCwd[MAX_PATH + 1];
|
||||
char szTmp[MAX_PATH + 1];
|
||||
char *p;
|
||||
GetCurrentDirectory(MAX_PATH, szCwd);
|
||||
while ((p = strchr(szPath, '/')) && *p)
|
||||
*p = '\\';
|
||||
PathCombine(szTmp, szCwd, szPath);
|
||||
PathCanonicalize(szCwd, szTmp);
|
||||
printf("%s\n", szCwd);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Local variables:
|
||||
* mode: c
|
||||
* c-basic-offset: 4
|
||||
* fill-column: 78
|
||||
* indent-tabs-mode: t
|
||||
* tab-width: 8
|
||||
* End:
|
||||
*/
|
||||
@@ -1,711 +0,0 @@
|
||||
#------------------------------------------------------------------------------
|
||||
# rules.vc --
|
||||
#
|
||||
# Microsoft Visual C++ makefile include for decoding the commandline
|
||||
# macros. This file does not need editing to build Tcl.
|
||||
#
|
||||
# See the file "license.terms" for information on usage and redistribution
|
||||
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
|
||||
#
|
||||
# Copyright (c) 2001-2003 David Gravereaux.
|
||||
# Copyright (c) 2003-2008 Patrick Thoyts
|
||||
#------------------------------------------------------------------------------
|
||||
|
||||
!ifndef _RULES_VC
|
||||
_RULES_VC = 1
|
||||
|
||||
cc32 = $(CC) # built-in default.
|
||||
link32 = link
|
||||
lib32 = lib
|
||||
rc32 = $(RC) # built-in default.
|
||||
|
||||
!ifndef INSTALLDIR
|
||||
### Assume the normal default.
|
||||
_INSTALLDIR = C:\Program Files\Tcl
|
||||
!else
|
||||
### Fix the path separators.
|
||||
_INSTALLDIR = $(INSTALLDIR:/=\)
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Set the proper copy method to avoid overwrite questions
|
||||
# to the user when copying files and selecting the right
|
||||
# "delete all" method.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if "$(OS)" == "Windows_NT"
|
||||
RMDIR = rmdir /S /Q
|
||||
ERRNULL = 2>NUL
|
||||
!if ![ver | find "4.0" > nul]
|
||||
CPY = echo y | xcopy /i >NUL
|
||||
COPY = copy >NUL
|
||||
!else
|
||||
CPY = xcopy /i /y >NUL
|
||||
COPY = copy /y >NUL
|
||||
!endif
|
||||
!else # "$(OS)" != "Windows_NT"
|
||||
CPY = xcopy /i >_JUNK.OUT # On Win98 NUL does not work here.
|
||||
COPY = copy >_JUNK.OUT # On Win98 NUL does not work here.
|
||||
RMDIR = deltree /Y
|
||||
NULL = \NUL # Used in testing directory existence
|
||||
ERRNULL = >NUL # Win9x shell cannot redirect stderr
|
||||
!endif
|
||||
MKDIR = mkdir
|
||||
|
||||
#------------------------------------------------------------------------------
|
||||
# Determine the host and target architectures and compiler version.
|
||||
#------------------------------------------------------------------------------
|
||||
|
||||
_HASH=^#
|
||||
_VC_MANIFEST_EMBED_EXE=
|
||||
_VC_MANIFEST_EMBED_DLL=
|
||||
VCVER=0
|
||||
!if ![echo VCVERSION=_MSC_VER > vercl.x] \
|
||||
&& ![echo $(_HASH)if defined(_M_IX86) >> vercl.x] \
|
||||
&& ![echo ARCH=IX86 >> vercl.x] \
|
||||
&& ![echo $(_HASH)elif defined(_M_AMD64) >> vercl.x] \
|
||||
&& ![echo ARCH=AMD64 >> vercl.x] \
|
||||
&& ![echo $(_HASH)endif >> vercl.x] \
|
||||
&& ![cl -nologo -TC -P vercl.x $(ERRNULL)]
|
||||
!include vercl.i
|
||||
!if ![echo VCVER= ^\> vercl.vc] \
|
||||
&& ![set /a $(VCVERSION) / 100 - 6 >> vercl.vc]
|
||||
!include vercl.vc
|
||||
!endif
|
||||
!endif
|
||||
!if ![del $(ERRNUL) /q/f vercl.x vercl.i vercl.vc]
|
||||
!endif
|
||||
|
||||
!if ![reg query HKLM\Hardware\Description\System\CentralProcessor\0 /v Identifier | findstr /i x86]
|
||||
NATIVE_ARCH=IX86
|
||||
!else
|
||||
NATIVE_ARCH=AMD64
|
||||
!endif
|
||||
|
||||
# Since MSVC8 we must deal with manifest resources.
|
||||
!if $(VCVERSION) >= 1400
|
||||
_VC_MANIFEST_EMBED_EXE=if exist $@.manifest mt -nologo -manifest $@.manifest -outputresource:$@;1
|
||||
_VC_MANIFEST_EMBED_DLL=if exist $@.manifest mt -nologo -manifest $@.manifest -outputresource:$@;2
|
||||
!endif
|
||||
|
||||
!ifndef MACHINE
|
||||
MACHINE=$(ARCH)
|
||||
!endif
|
||||
|
||||
!ifndef CFG_ENCODING
|
||||
CFG_ENCODING = \"cp1252\"
|
||||
!endif
|
||||
|
||||
!message ===============================================================================
|
||||
|
||||
#----------------------------------------------------------
|
||||
# build the helper app we need to overcome nmake's limiting
|
||||
# environment.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if !exist(nmakehlp.exe)
|
||||
!if [$(cc32) -nologo nmakehlp.c -link -subsystem:console > nul]
|
||||
!endif
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Test for compiler features
|
||||
#----------------------------------------------------------
|
||||
|
||||
### test for optimizations
|
||||
!if [nmakehlp -c -Ot]
|
||||
!message *** Compiler has 'Optimizations'
|
||||
OPTIMIZING = 1
|
||||
!else
|
||||
!message *** Compiler does not have 'Optimizations'
|
||||
OPTIMIZING = 0
|
||||
!endif
|
||||
|
||||
OPTIMIZATIONS =
|
||||
|
||||
!if [nmakehlp -c -Ot]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -Ot
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -Oi]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -Oi
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -Op]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -Op
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -fp:strict]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -fp:strict
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -Gs]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -Gs
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -GS]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -GS
|
||||
!endif
|
||||
|
||||
!if [nmakehlp -c -GL]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -GL
|
||||
!endif
|
||||
|
||||
DEBUGFLAGS =
|
||||
|
||||
!if [nmakehlp -c -RTC1]
|
||||
DEBUGFLAGS = $(DEBUGFLAGS) -RTC1
|
||||
!elseif [nmakehlp -c -GZ]
|
||||
DEBUGFLAGS = $(DEBUGFLAGS) -GZ
|
||||
!endif
|
||||
|
||||
COMPILERFLAGS =-W3 -DUNICODE -D_UNICODE
|
||||
|
||||
# In v13 -GL and -YX are incompatible.
|
||||
!if [nmakehlp -c -YX]
|
||||
!if ![nmakehlp -c -GL]
|
||||
OPTIMIZATIONS = $(OPTIMIZATIONS) -YX
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!if "$(MACHINE)" == "IX86"
|
||||
### test for pentium errata
|
||||
!if [nmakehlp -c -QI0f]
|
||||
!message *** Compiler has 'Pentium 0x0f fix'
|
||||
COMPILERFLAGS = $(COMPILERFLAGS) -QI0f
|
||||
!else
|
||||
!message *** Compiler does not have 'Pentium 0x0f fix'
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!if "$(MACHINE)" == "IA64"
|
||||
### test for Itanium errata
|
||||
!if [nmakehlp -c -QIA64_Bx]
|
||||
!message *** Compiler has 'B-stepping errata workarounds'
|
||||
COMPILERFLAGS = $(COMPILERFLAGS) -QIA64_Bx
|
||||
!else
|
||||
!message *** Compiler does not have 'B-stepping errata workarounds'
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!if "$(MACHINE)" == "IX86"
|
||||
### test for -align:4096, when align:512 will do.
|
||||
!if [nmakehlp -l -opt:nowin98]
|
||||
!message *** Linker has 'Win98 alignment problem'
|
||||
ALIGN98_HACK = 1
|
||||
!else
|
||||
!message *** Linker does not have 'Win98 alignment problem'
|
||||
ALIGN98_HACK = 0
|
||||
!endif
|
||||
!else
|
||||
ALIGN98_HACK = 0
|
||||
!endif
|
||||
|
||||
LINKERFLAGS =
|
||||
|
||||
!if [nmakehlp -l -ltcg]
|
||||
LINKERFLAGS =-ltcg
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Decode the options requested.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if "$(OPTS)" == "" || [nmakehlp -f "$(OPTS)" "none"]
|
||||
STATIC_BUILD = 0
|
||||
TCL_THREADS = 1
|
||||
DEBUG = 0
|
||||
SYMBOLS = 0
|
||||
PROFILE = 0
|
||||
PGO = 0
|
||||
MSVCRT = 0
|
||||
LOIMPACT = 0
|
||||
TCL_USE_STATIC_PACKAGES = 0
|
||||
USE_THREAD_ALLOC = 1
|
||||
UNCHECKED = 0
|
||||
!else
|
||||
!if [nmakehlp -f $(OPTS) "static"]
|
||||
!message *** Doing static
|
||||
STATIC_BUILD = 1
|
||||
!else
|
||||
STATIC_BUILD = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "msvcrt"]
|
||||
!message *** Doing msvcrt
|
||||
MSVCRT = 1
|
||||
!else
|
||||
MSVCRT = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "staticpkg"]
|
||||
!message *** Doing staticpkg
|
||||
TCL_USE_STATIC_PACKAGES = 1
|
||||
!else
|
||||
TCL_USE_STATIC_PACKAGES = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "nothreads"]
|
||||
!message *** Compile explicitly for non-threaded tcl
|
||||
TCL_THREADS = 0
|
||||
!else
|
||||
TCL_THREADS = 1
|
||||
USE_THREAD_ALLOC= 1
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "symbols"]
|
||||
!message *** Doing symbols
|
||||
DEBUG = 1
|
||||
!else
|
||||
DEBUG = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "pdbs"]
|
||||
!message *** Doing pdbs
|
||||
SYMBOLS = 1
|
||||
!else
|
||||
SYMBOLS = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "profile"]
|
||||
!message *** Doing profile
|
||||
PROFILE = 1
|
||||
!else
|
||||
PROFILE = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "pgi"]
|
||||
!message *** Doing profile guided optimization instrumentation
|
||||
PGO = 1
|
||||
!elseif [nmakehlp -f $(OPTS) "pgo"]
|
||||
!message *** Doing profile guided optimization
|
||||
PGO = 2
|
||||
!else
|
||||
PGO = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "loimpact"]
|
||||
!message *** Doing loimpact
|
||||
LOIMPACT = 1
|
||||
!else
|
||||
LOIMPACT = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "thrdalloc"]
|
||||
!message *** Doing thrdalloc
|
||||
USE_THREAD_ALLOC = 1
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "tclalloc"]
|
||||
!message *** Doing tclalloc
|
||||
USE_THREAD_ALLOC = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(OPTS) "unchecked"]
|
||||
!message *** Doing unchecked
|
||||
UNCHECKED = 1
|
||||
!else
|
||||
UNCHECKED = 0
|
||||
!endif
|
||||
!endif
|
||||
|
||||
|
||||
!if !$(STATIC_BUILD)
|
||||
# Make sure we don't build overly fat DLLs.
|
||||
MSVCRT = 1
|
||||
# We shouldn't statically put the extensions inside the shell when dynamic.
|
||||
TCL_USE_STATIC_PACKAGES = 0
|
||||
!endif
|
||||
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Figure-out how to name our intermediate and output directories.
|
||||
# We wouldn't want different builds to use the same .obj files
|
||||
# by accident.
|
||||
#----------------------------------------------------------
|
||||
|
||||
#----------------------------------------
|
||||
# Naming convention:
|
||||
# t = full thread support.
|
||||
# s = static library (as opposed to an
|
||||
# import library)
|
||||
# g = linked to the debug enabled C
|
||||
# run-time.
|
||||
# x = special static build when it
|
||||
# links to the dynamic C run-time.
|
||||
#----------------------------------------
|
||||
SUFX = tsgx
|
||||
|
||||
!if $(DEBUG)
|
||||
BUILDDIRTOP = Debug
|
||||
!else
|
||||
BUILDDIRTOP = Release
|
||||
!endif
|
||||
|
||||
!if "$(MACHINE)" != "IX86"
|
||||
BUILDDIRTOP =$(BUILDDIRTOP)_$(MACHINE)
|
||||
!endif
|
||||
!if $(VCVER) > 6
|
||||
BUILDDIRTOP =$(BUILDDIRTOP)_VC$(VCVER)
|
||||
!endif
|
||||
|
||||
!if !$(DEBUG) || $(DEBUG) && $(UNCHECKED)
|
||||
SUFX = $(SUFX:g=)
|
||||
!endif
|
||||
|
||||
TMP_DIRFULL = .\$(BUILDDIRTOP)\$(PROJECT)_ThreadedDynamicStaticX
|
||||
|
||||
!if !$(STATIC_BUILD)
|
||||
TMP_DIRFULL = $(TMP_DIRFULL:Static=)
|
||||
SUFX = $(SUFX:s=)
|
||||
EXT = dll
|
||||
!if $(MSVCRT)
|
||||
TMP_DIRFULL = $(TMP_DIRFULL:X=)
|
||||
SUFX = $(SUFX:x=)
|
||||
!endif
|
||||
!else
|
||||
TMP_DIRFULL = $(TMP_DIRFULL:Dynamic=)
|
||||
EXT = lib
|
||||
!if !$(MSVCRT)
|
||||
TMP_DIRFULL = $(TMP_DIRFULL:X=)
|
||||
SUFX = $(SUFX:x=)
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!if !$(TCL_THREADS)
|
||||
TMP_DIRFULL = $(TMP_DIRFULL:Threaded=)
|
||||
SUFX = $(SUFX:t=)
|
||||
!endif
|
||||
|
||||
!ifndef TMP_DIR
|
||||
TMP_DIR = $(TMP_DIRFULL)
|
||||
!ifndef OUT_DIR
|
||||
OUT_DIR = .\$(BUILDDIRTOP)
|
||||
!endif
|
||||
!else
|
||||
!ifndef OUT_DIR
|
||||
OUT_DIR = $(TMP_DIR)
|
||||
!endif
|
||||
!endif
|
||||
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Decode the statistics requested.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if "$(STATS)" == "" || [nmakehlp -f "$(STATS)" "none"]
|
||||
TCL_MEM_DEBUG = 0
|
||||
TCL_COMPILE_DEBUG = 0
|
||||
!else
|
||||
!if [nmakehlp -f $(STATS) "memdbg"]
|
||||
!message *** Doing memdbg
|
||||
TCL_MEM_DEBUG = 1
|
||||
!else
|
||||
TCL_MEM_DEBUG = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(STATS) "compdbg"]
|
||||
!message *** Doing compdbg
|
||||
TCL_COMPILE_DEBUG = 1
|
||||
!else
|
||||
TCL_COMPILE_DEBUG = 0
|
||||
!endif
|
||||
!endif
|
||||
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Decode the checks requested.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if "$(CHECKS)" == "" || [nmakehlp -f "$(CHECKS)" "none"]
|
||||
TCL_NO_DEPRECATED = 0
|
||||
WARNINGS = -W3
|
||||
!else
|
||||
!if [nmakehlp -f $(CHECKS) "nodep"]
|
||||
!message *** Doing nodep check
|
||||
TCL_NO_DEPRECATED = 1
|
||||
!else
|
||||
TCL_NO_DEPRECATED = 0
|
||||
!endif
|
||||
!if [nmakehlp -f $(CHECKS) "fullwarn"]
|
||||
!message *** Doing full warnings check
|
||||
WARNINGS = -W4
|
||||
!if [nmakehlp -l -warn:3]
|
||||
LINKERFLAGS = $(LINKERFLAGS) -warn:3
|
||||
!endif
|
||||
!else
|
||||
WARNINGS = -W3
|
||||
!endif
|
||||
!if [nmakehlp -f $(CHECKS) "64bit"] && [nmakehlp -c -Wp64]
|
||||
!message *** Doing 64bit portability warnings
|
||||
WARNINGS = $(WARNINGS) -Wp64
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!if $(PGO) > 1
|
||||
!if [nmakehlp -l -ltcg:pgoptimize]
|
||||
LINKERFLAGS = $(LINKERFLAGS:-ltcg=) -ltcg:pgoptimize
|
||||
!else
|
||||
MSG=^
|
||||
This compiler does not support profile guided optimization.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
!elseif $(PGO) > 0
|
||||
!if [nmakehlp -l -ltcg:pginstrument]
|
||||
LINKERFLAGS = $(LINKERFLAGS:-ltcg=) -ltcg:pginstrument
|
||||
!else
|
||||
MSG=^
|
||||
This compiler does not support profile guided optimization.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Set our defines now armed with our options.
|
||||
#----------------------------------------------------------
|
||||
|
||||
OPTDEFINES = -DTCL_CFGVAL_ENCODING=$(CFG_ENCODING) -DSTDC_HEADERS
|
||||
|
||||
!if $(TCL_MEM_DEBUG)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_MEM_DEBUG
|
||||
!endif
|
||||
!if $(TCL_COMPILE_DEBUG)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_COMPILE_DEBUG -DTCL_COMPILE_STATS
|
||||
!endif
|
||||
!if $(TCL_THREADS)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_THREADS=1
|
||||
!if $(USE_THREAD_ALLOC)
|
||||
OPTDEFINES = $(OPTDEFINES) -DUSE_THREAD_ALLOC=1
|
||||
!endif
|
||||
!endif
|
||||
!if $(STATIC_BUILD)
|
||||
OPTDEFINES = $(OPTDEFINES) -DSTATIC_BUILD
|
||||
!endif
|
||||
!if $(TCL_NO_DEPRECATED)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_NO_DEPRECATED
|
||||
!endif
|
||||
|
||||
!if !$(DEBUG)
|
||||
OPTDEFINES = $(OPTDEFINES) -DNDEBUG
|
||||
!if $(OPTIMIZING)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_CFG_OPTIMIZED
|
||||
!endif
|
||||
!endif
|
||||
!if $(PROFILE)
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_CFG_PROFILED
|
||||
!endif
|
||||
!if "$(MACHINE)" == "IA64" || "$(MACHINE)" == "AMD64"
|
||||
OPTDEFINES = $(OPTDEFINES) -DTCL_CFG_DO64BIT
|
||||
!endif
|
||||
!if $(VCVERSION) < 1300
|
||||
OPTDEFINES = $(OPTDEFINES) -DNO_STRTOI64
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Locate the Tcl headers to build against
|
||||
#----------------------------------------------------------
|
||||
|
||||
!if "$(PROJECT)" == "tcl"
|
||||
|
||||
_TCL_H = ..\generic\tcl.h
|
||||
|
||||
!else
|
||||
|
||||
# If INSTALLDIR set to tcl root dir then reset to the lib dir.
|
||||
!if exist("$(_INSTALLDIR)\include\tcl.h")
|
||||
_INSTALLDIR=$(_INSTALLDIR)\lib
|
||||
!endif
|
||||
|
||||
!if !defined(TCLDIR)
|
||||
!if exist("$(_INSTALLDIR)\..\include\tcl.h")
|
||||
TCLINSTALL = 1
|
||||
_TCLDIR = $(_INSTALLDIR)\..
|
||||
_TCL_H = $(_INSTALLDIR)\..\include\tcl.h
|
||||
TCLDIR = $(_INSTALLDIR)\..
|
||||
!else
|
||||
MSG=^
|
||||
Failed to find tcl.h. Set the TCLDIR macro.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
!else
|
||||
_TCLDIR = $(TCLDIR:/=\)
|
||||
!if exist("$(_TCLDIR)\include\tcl.h")
|
||||
TCLINSTALL = 1
|
||||
_TCL_H = $(_TCLDIR)\include\tcl.h
|
||||
!elseif exist("$(_TCLDIR)\generic\tcl.h")
|
||||
TCLINSTALL = 0
|
||||
_TCL_H = $(_TCLDIR)\generic\tcl.h
|
||||
!else
|
||||
MSG =^
|
||||
Failed to find tcl.h. The TCLDIR macro does not appear correct.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
!endif
|
||||
!endif
|
||||
|
||||
#--------------------------------------------------------------
|
||||
# Extract various version numbers from tcl headers
|
||||
# The generated file is then included in the makefile.
|
||||
#--------------------------------------------------------------
|
||||
|
||||
!if [echo REM = This file is generated from rules.vc > versions.vc]
|
||||
!endif
|
||||
!if [echo TCL_MAJOR_VERSION = \>> versions.vc] \
|
||||
&& [nmakehlp -V "$(_TCL_H)" TCL_MAJOR_VERSION >> versions.vc]
|
||||
!endif
|
||||
!if [echo TCL_MINOR_VERSION = \>> versions.vc] \
|
||||
&& [nmakehlp -V "$(_TCL_H)" TCL_MINOR_VERSION >> versions.vc]
|
||||
!endif
|
||||
!if [echo TCL_PATCH_LEVEL = \>> versions.vc] \
|
||||
&& [nmakehlp -V "$(_TCL_H)" TCL_PATCH_LEVEL >> versions.vc]
|
||||
!endif
|
||||
|
||||
# If building the tcl core then we need additional package versions
|
||||
!if "$(PROJECT)" == "tcl"
|
||||
!if [echo PKG_HTTP_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\http\pkgIndex.tcl http >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_TCLTEST_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\tcltest\pkgIndex.tcl tcltest >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_MSGCAT_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\msgcat\pkgIndex.tcl msgcat >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_PLATFORM_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\platform\pkgIndex.tcl "platform " >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_SHELL_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\platform\pkgIndex.tcl "platform::shell" >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_DDE_VER = \>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\dde\pkgIndex.tcl "dde " >> versions.vc]
|
||||
!endif
|
||||
!if [echo PKG_REG_VER =\>> versions.vc] \
|
||||
&& [nmakehlp -V ..\library\reg\pkgIndex.tcl registry >> versions.vc]
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!include versions.vc
|
||||
|
||||
#--------------------------------------------------------------
|
||||
# Setup tcl version dependent stuff headers
|
||||
#--------------------------------------------------------------
|
||||
|
||||
!if "$(PROJECT)" != "tcl"
|
||||
|
||||
TCL_VERSION = $(TCL_MAJOR_VERSION)$(TCL_MINOR_VERSION)
|
||||
|
||||
!if $(TCL_VERSION) < 81
|
||||
TCL_DOES_STUBS = 0
|
||||
!else
|
||||
TCL_DOES_STUBS = 1
|
||||
!endif
|
||||
|
||||
!if $(TCLINSTALL)
|
||||
TCLSH = "$(_TCLDIR)\bin\tclsh$(TCL_VERSION)$(SUFX).exe"
|
||||
!if !exist($(TCLSH)) && $(TCL_THREADS)
|
||||
TCLSH = "$(_TCLDIR)\bin\tclsh$(TCL_VERSION)t$(SUFX).exe"
|
||||
!endif
|
||||
TCLSTUBLIB = "$(_TCLDIR)\lib\tclstub$(TCL_VERSION).lib"
|
||||
TCLIMPLIB = "$(_TCLDIR)\lib\tcl$(TCL_VERSION)$(SUFX).lib"
|
||||
TCL_LIBRARY = $(_TCLDIR)\lib
|
||||
TCLREGLIB = "$(_TCLDIR)\lib\tclreg13$(SUFX:t=).lib"
|
||||
TCLDDELIB = "$(_TCLDIR)\lib\tcldde14$(SUFX:t=).lib"
|
||||
COFFBASE = \must\have\tcl\sources\to\build\this\target
|
||||
TCLTOOLSDIR = \must\have\tcl\sources\to\build\this\target
|
||||
TCL_INCLUDES = -I"$(_TCLDIR)\include"
|
||||
!else
|
||||
TCLSH = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tclsh$(TCL_VERSION)$(SUFX).exe"
|
||||
!if !exist($(TCLSH)) && $(TCL_THREADS)
|
||||
TCLSH = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tclsh$(TCL_VERSION)t$(SUFX).exe"
|
||||
!endif
|
||||
TCLSTUBLIB = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tclstub$(TCL_VERSION).lib"
|
||||
TCLIMPLIB = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tcl$(TCL_VERSION)$(SUFX).lib"
|
||||
TCL_LIBRARY = $(_TCLDIR)\library
|
||||
TCLREGLIB = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tclreg13$(SUFX:t=).lib"
|
||||
TCLDDELIB = "$(_TCLDIR)\win\$(BUILDDIRTOP)\tcldde14$(SUFX:t=).lib"
|
||||
COFFBASE = "$(_TCLDIR)\win\coffbase.txt"
|
||||
TCLTOOLSDIR = $(_TCLDIR)\tools
|
||||
TCL_INCLUDES = -I"$(_TCLDIR)\generic" -I"$(_TCLDIR)\win"
|
||||
!endif
|
||||
|
||||
!endif
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Locate the Tk headers to build against
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
!if "$(PROJECT)" == "tk"
|
||||
_TK_H = ..\generic\tk.h
|
||||
_INSTALLDIR = $(_INSTALLDIR)\..
|
||||
!endif
|
||||
|
||||
!ifdef PROJECT_REQUIRES_TK
|
||||
!if !defined(TKDIR)
|
||||
!if exist("$(_INSTALLDIR)\..\include\tk.h")
|
||||
TKINSTALL = 1
|
||||
_TKDIR = $(_INSTALLDIR)\..
|
||||
_TK_H = $(_TKDIR)\include\tk.h
|
||||
TKDIR = $(_TKDIR)
|
||||
!elseif exist("$(_TCLDIR)\include\tk.h")
|
||||
TKINSTALL = 1
|
||||
_TKDIR = $(_TCLDIR)
|
||||
_TK_H = $(_TKDIR)\include\tk.h
|
||||
TKDIR = $(_TKDIR)
|
||||
!endif
|
||||
!else
|
||||
_TKDIR = $(TKDIR:/=\)
|
||||
!if exist("$(_TKDIR)\include\tk.h")
|
||||
TKINSTALL = 1
|
||||
_TK_H = $(_TKDIR)\include\tk.h
|
||||
!elseif exist("$(_TKDIR)\generic\tk.h")
|
||||
TKINSTALL = 0
|
||||
_TK_H = $(_TKDIR)\generic\tk.h
|
||||
!else
|
||||
MSG =^
|
||||
Failed to find tk.h. The TKDIR macro does not appear correct.
|
||||
!error $(MSG)
|
||||
!endif
|
||||
!endif
|
||||
!endif
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Extract Tk version numbers
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
!if defined(PROJECT_REQUIRES_TK) || "$(PROJECT)" == "tk"
|
||||
|
||||
!if [echo TK_MAJOR_VERSION = \>> versions.vc] \
|
||||
&& [nmakehlp -V $(_TK_H) TK_MAJOR_VERSION >> versions.vc]
|
||||
!endif
|
||||
!if [echo TK_MINOR_VERSION = \>> versions.vc] \
|
||||
&& [nmakehlp -V $(_TK_H) TK_MINOR_VERSION >> versions.vc]
|
||||
!endif
|
||||
!if [echo TK_PATCH_LEVEL = \>> versions.vc] \
|
||||
&& [nmakehlp -V $(_TK_H) TK_PATCH_LEVEL >> versions.vc]
|
||||
!endif
|
||||
|
||||
!include versions.vc
|
||||
|
||||
TK_DOTVERSION = $(TK_MAJOR_VERSION).$(TK_MINOR_VERSION)
|
||||
TK_VERSION = $(TK_MAJOR_VERSION)$(TK_MINOR_VERSION)
|
||||
|
||||
!if "$(PROJECT)" != "tk"
|
||||
!if $(TKINSTALL)
|
||||
WISH = "$(_TKDIR)\bin\wish$(TK_VERSION)$(SUFX).exe"
|
||||
TKSTUBLIB = "$(_TKDIR)\lib\tkstub$(TK_VERSION).lib"
|
||||
TKIMPLIB = "$(_TKDIR)\lib\tk$(TK_VERSION)$(SUFX).lib"
|
||||
TK_INCLUDES = -I"$(_TKDIR)\include"
|
||||
!else
|
||||
WISH = "$(_TKDIR)\win\$(BUILDDIRTOP)\wish$(TCL_VERSION)$(SUFX).exe"
|
||||
TKSTUBLIB = "$(_TKDIR)\win\$(BUILDDIRTOP)\tkstub$(TCL_VERSION).lib"
|
||||
TKIMPLIB = "$(_TKDIR)\win\$(BUILDDIRTOP)\tk$(TCL_VERSION)$(SUFX).lib"
|
||||
TK_INCLUDES = -I"$(_TKDIR)\generic" -I"$(_TKDIR)\win" -I"$(_TKDIR)\xlib"
|
||||
!endif
|
||||
!endif
|
||||
|
||||
!endif
|
||||
|
||||
#----------------------------------------------------------
|
||||
# Display stats being used.
|
||||
#----------------------------------------------------------
|
||||
|
||||
!message *** Intermediate directory will be '$(TMP_DIR)'
|
||||
!message *** Output directory will be '$(OUT_DIR)'
|
||||
!message *** Suffix for binaries will be '$(SUFX)'
|
||||
!message *** Optional defines are '$(OPTDEFINES)'
|
||||
!message *** Compiler version $(VCVER). Target machine is $(MACHINE)
|
||||
!message *** Host architecture is $(NATIVE_ARCH)
|
||||
!message *** Compiler options '$(COMPILERFLAGS) $(OPTIMIZATIONS) $(DEBUGFLAGS) $(WARNINGS)'
|
||||
!message *** Link options '$(LINKERFLAGS)'
|
||||
|
||||
!endif
|
||||
|
||||
-18
@@ -27,9 +27,6 @@
|
||||
/* Define to 1 if you have the <inttypes.h> header file. */
|
||||
#undef HAVE_INTTYPES_H
|
||||
|
||||
/* Define to 1 if you have the `isnan' function. */
|
||||
#undef HAVE_ISNAN
|
||||
|
||||
/* Define to 1 if you have the `localtime_r' function. */
|
||||
#undef HAVE_LOCALTIME_R
|
||||
|
||||
@@ -45,27 +42,12 @@
|
||||
/* Define to 1 if you have the <memory.h> header file. */
|
||||
#undef HAVE_MEMORY_H
|
||||
|
||||
/* Define to 1 if you have the pread() function. */
|
||||
#undef HAVE_PREAD
|
||||
|
||||
/* Define to 1 if you have the pread64() function. */
|
||||
#undef HAVE_PREAD64
|
||||
|
||||
/* Define to 1 if you have the pwrite() function. */
|
||||
#undef HAVE_PWRITE
|
||||
|
||||
/* Define to 1 if you have the pwrite64() function. */
|
||||
#undef HAVE_PWRITE64
|
||||
|
||||
/* Define to 1 if you have the <stdint.h> header file. */
|
||||
#undef HAVE_STDINT_H
|
||||
|
||||
/* Define to 1 if you have the <stdlib.h> header file. */
|
||||
#undef HAVE_STDLIB_H
|
||||
|
||||
/* Define to 1 if you have the strchrnul() function */
|
||||
#undef HAVE_STRCHRNUL
|
||||
|
||||
/* Define to 1 if you have the <strings.h> header file. */
|
||||
#undef HAVE_STRINGS_H
|
||||
|
||||
|
||||
+111
-162
@@ -69,6 +69,19 @@
|
||||
# The filename extension for executables on the
|
||||
# target platform. "" for Unix and ".exe" for windows.
|
||||
#
|
||||
# The generated configure script will make an attempt to guess
|
||||
# at all of the above parameters. You can override any of
|
||||
# the guesses by setting the environment variable named
|
||||
# "config_AAAA" where "AAAA" is the name of the parameter
|
||||
# described above. (Exception: srcdir cannot be set this way.)
|
||||
# If you have a file that sets one or more of these environment
|
||||
# variables, you can invoke configure as follows:
|
||||
#
|
||||
# configure --with-hints=FILE
|
||||
#
|
||||
# where FILE is the name of the file that sets the environment
|
||||
# variables. FILE should be an absolute pathname.
|
||||
#
|
||||
# This configure.in file is easy to reuse on other projects. Just
|
||||
# change the argument to AC_INIT(). And disable any features that
|
||||
# you don't need (for example BLT) by erasing or commenting out
|
||||
@@ -85,11 +98,17 @@ AC_MSG_ERROR([configure script is out of date:
|
||||
please regen with autoconf])
|
||||
fi
|
||||
|
||||
dnl Put the RCS revision string after AC_INIT so that it will also
|
||||
dnl show in in configure.
|
||||
# The following RCS revision string applies to configure.in
|
||||
# $Revision: 1.56 $
|
||||
|
||||
#########
|
||||
# Programs needed
|
||||
#
|
||||
AC_PROG_LIBTOOL
|
||||
AC_PROG_INSTALL
|
||||
AC_PROG_AWK
|
||||
|
||||
#########
|
||||
# Enable large file support (if special flags are necessary)
|
||||
@@ -108,7 +127,7 @@ AC_CHECK_HEADERS([sys/types.h stdlib.h stdint.h inttypes.h malloc.h])
|
||||
#########
|
||||
# Figure out whether or not we have these functions
|
||||
#
|
||||
AC_CHECK_FUNCS([fdatasync gmtime_r isnan localtime_r localtime_s malloc_usable_size strchrnul usleep utime pread pread64 pwrite pwrite64])
|
||||
AC_CHECK_FUNCS([usleep fdatasync localtime_r gmtime_r localtime_s utime malloc_usable_size])
|
||||
|
||||
#########
|
||||
# By default, we use the amalgamation (this may be changed below...)
|
||||
@@ -120,7 +139,7 @@ USE_AMALGAMATION=1
|
||||
# if not, then we fall back to plain tclsh.
|
||||
# TODO: try other versions before falling back?
|
||||
#
|
||||
AC_CHECK_PROGS(TCLSH_CMD, [tclsh8.7 tclsh8.6 tclsh8.5 tclsh], none)
|
||||
AC_CHECK_PROGS(TCLSH_CMD, [tclsh8.5 tclsh], none)
|
||||
if test "$TCLSH_CMD" = "none"; then
|
||||
# If we can't find a local tclsh, then building the amalgamation will fail.
|
||||
# We act as though --disable-amalgamation has been used.
|
||||
@@ -161,6 +180,41 @@ VERSION_NUMBER=[`cat $srcdir/VERSION \
|
||||
AC_MSG_NOTICE(Version number set to $VERSION_NUMBER)
|
||||
AC_SUBST(VERSION_NUMBER)
|
||||
|
||||
#########
|
||||
# Check to see if the --with-hints=FILE option is used. If there is none,
|
||||
# then check for a files named "$host.hints" and ../$hosts.hints where
|
||||
# $host is the hostname of the build system. If still no hints are
|
||||
# found, try looking in $system.hints and ../$system.hints where
|
||||
# $system is the result of uname -s.
|
||||
#
|
||||
AC_ARG_WITH(hints,
|
||||
AC_HELP_STRING([--with-hints=FILE],[Read configuration options from FILE]),
|
||||
hints=$withval)
|
||||
if test "$hints" = ""; then
|
||||
host=`hostname | sed 's/\..*//'`
|
||||
if test -r $host.hints; then
|
||||
hints=$host.hints
|
||||
else
|
||||
if test -r ../$host.hints; then
|
||||
hints=../$host.hints
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
if test "$hints" = ""; then
|
||||
sys=`uname -s`
|
||||
if test -r $sys.hints; then
|
||||
hints=$sys.hints
|
||||
else
|
||||
if test -r ../$sys.hints; then
|
||||
hints=../$sys.hints
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
if test "$hints" != ""; then
|
||||
AC_MSG_RESULT(reading hints from $hints)
|
||||
. $hints
|
||||
fi
|
||||
|
||||
#########
|
||||
# Locate a compiler for the build machine. This compiler should
|
||||
# generate command-line programs that run on the build machine.
|
||||
@@ -182,7 +236,7 @@ AC_SUBST(BUILD_CC)
|
||||
# Do we want to support multithreaded use of sqlite
|
||||
#
|
||||
AC_ARG_ENABLE(threadsafe,
|
||||
AC_HELP_STRING([--disable-threadsafe],[Disable mutexing]))
|
||||
AC_HELP_STRING([--enable-threadsafe],[Support threadsafe operation]),,enable_threadsafe=yes)
|
||||
AC_MSG_CHECKING([whether to support threadsafe operation])
|
||||
if test "$enable_threadsafe" = "no"; then
|
||||
SQLITE_THREADSAFE=0
|
||||
@@ -195,9 +249,25 @@ AC_SUBST(SQLITE_THREADSAFE)
|
||||
|
||||
if test "$SQLITE_THREADSAFE" = "1"; then
|
||||
AC_SEARCH_LIBS(pthread_create, pthread)
|
||||
AC_SEARCH_LIBS(pthread_mutexattr_init, pthread)
|
||||
fi
|
||||
|
||||
##########
|
||||
# Do we want to allow a connection created in one thread to be used
|
||||
# in another thread. This does not work on many Linux systems (ex: RedHat 9)
|
||||
# due to bugs in the threading implementations. This is thus off by default.
|
||||
#
|
||||
AC_ARG_ENABLE(cross-thread-connections,
|
||||
AC_HELP_STRING([--enable-cross-thread-connections],[Allow connection sharing across threads]),,enable_xthreadconnect=no)
|
||||
AC_MSG_CHECKING([whether to allow connections to be shared across threads])
|
||||
if test "$enable_xthreadconnect" = "no"; then
|
||||
XTHREADCONNECT=''
|
||||
AC_MSG_RESULT([no])
|
||||
else
|
||||
XTHREADCONNECT='-DSQLITE_ALLOW_XTHREAD_CONNECT=1'
|
||||
AC_MSG_RESULT([yes])
|
||||
fi
|
||||
AC_SUBST(XTHREADCONNECT)
|
||||
|
||||
##########
|
||||
# Do we want to support release
|
||||
#
|
||||
@@ -270,18 +340,28 @@ else
|
||||
TARGET_EXEEXT=$config_TARGET_EXEEXT
|
||||
fi
|
||||
if test "$TARGET_EXEEXT" = ".exe"; then
|
||||
SQLITE_OS_UNIX=0
|
||||
SQLITE_OS_WIN=1
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_WIN=1"
|
||||
if test $OS2_SHELL ; then
|
||||
SQLITE_OS_UNIX=0
|
||||
SQLITE_OS_WIN=0
|
||||
SQLITE_OS_OS2=1
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_OS2=1"
|
||||
else
|
||||
SQLITE_OS_UNIX=0
|
||||
SQLITE_OS_WIN=1
|
||||
SQLITE_OS_OS2=0
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_WIN=1"
|
||||
fi
|
||||
else
|
||||
SQLITE_OS_UNIX=1
|
||||
SQLITE_OS_WIN=0
|
||||
SQLITE_OS_OS2=0
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_UNIX=1"
|
||||
fi
|
||||
|
||||
AC_SUBST(BUILD_EXEEXT)
|
||||
AC_SUBST(SQLITE_OS_UNIX)
|
||||
AC_SUBST(SQLITE_OS_WIN)
|
||||
AC_SUBST(SQLITE_OS_OS2)
|
||||
AC_SUBST(TARGET_EXEEXT)
|
||||
|
||||
##########
|
||||
@@ -308,44 +388,14 @@ if test "${use_tcl}" = "yes" ; then
|
||||
fi
|
||||
|
||||
# Start autosearch by asking tclsh
|
||||
if test x"${ac_cv_c_tclconfig}" = x ; then
|
||||
if test x"$cross_compiling" = xno; then
|
||||
for i in `echo 'puts stdout $auto_path' | ${TCLSH_CMD}`
|
||||
do
|
||||
if test -f "$i/tclConfig.sh" ; then
|
||||
ac_cv_c_tclconfig="$i"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
fi
|
||||
|
||||
# On ubuntu 14.10, $auto_path on tclsh is not quite correct.
|
||||
# So try again after applying corrections.
|
||||
if test x"${ac_cv_c_tclconfig}" = x ; then
|
||||
if test x"$cross_compiling" = xno; then
|
||||
for i in `echo 'puts stdout $auto_path' | ${TCLSH_CMD} | sed 's,/tcltk/tcl,/tcl,g'`
|
||||
do
|
||||
if test -f "$i/tclConfig.sh" ; then
|
||||
ac_cv_c_tclconfig="$i"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
fi
|
||||
|
||||
# Recent versions of Xcode on Macs hid the tclConfig.sh file
|
||||
# in a strange place.
|
||||
if test x"${ac_cv_c_tclconfig}" = x ; then
|
||||
if test x"$cross_compiling" = xno; then
|
||||
for i in /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX*.sdk/usr/lib
|
||||
do
|
||||
if test -f "$i/tclConfig.sh" ; then
|
||||
ac_cv_c_tclconfig="$i"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
if test x"$cross_compiling" = xno; then
|
||||
for i in `echo 'puts stdout $auto_path' | ${TCLSH_CMD}`
|
||||
do
|
||||
if test -f "$i/tclConfig.sh" ; then
|
||||
ac_cv_c_tclconfig="$i"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
# then check for a private Tcl installation
|
||||
@@ -449,6 +499,7 @@ if test "${use_tcl}" = "yes" ; then
|
||||
AC_SUBST(TCL_VERSION)
|
||||
AC_SUBST(TCL_BIN_DIR)
|
||||
AC_SUBST(TCL_SRC_DIR)
|
||||
AC_SUBST(TCL_LIBS)
|
||||
AC_SUBST(TCL_INCLUDE_SPEC)
|
||||
|
||||
AC_SUBST(TCL_LIB_FILE)
|
||||
@@ -458,7 +509,6 @@ if test "${use_tcl}" = "yes" ; then
|
||||
AC_SUBST(TCL_STUB_LIB_FILE)
|
||||
AC_SUBST(TCL_STUB_LIB_FLAG)
|
||||
AC_SUBST(TCL_STUB_LIB_SPEC)
|
||||
AC_SUBST(TCL_SHLIB_SUFFIX)
|
||||
fi
|
||||
fi
|
||||
if test "${use_tcl}" = "no" ; then
|
||||
@@ -475,24 +525,11 @@ AC_SUBST(HAVE_TCL)
|
||||
TARGET_READLINE_LIBS=""
|
||||
TARGET_READLINE_INC=""
|
||||
TARGET_HAVE_READLINE=0
|
||||
TARGET_HAVE_EDITLINE=0
|
||||
AC_ARG_ENABLE([editline],
|
||||
[AC_HELP_STRING([--enable-editline],[enable BSD editline support])],
|
||||
[with_editline=$enableval],
|
||||
[with_editline=auto])
|
||||
AC_ARG_ENABLE([readline],
|
||||
[AC_HELP_STRING([--disable-readline],[disable readline support])],
|
||||
[AC_HELP_STRING([--disable-readline],[disable readline support [default=detect]])],
|
||||
[with_readline=$enableval],
|
||||
[with_readline=auto])
|
||||
|
||||
if test x"$with_editline" != xno; then
|
||||
sLIBS=$LIBS
|
||||
LIBS=""
|
||||
TARGET_HAVE_EDITLINE=1
|
||||
AC_SEARCH_LIBS(readline,edit,[with_readline=no],[TARGET_HAVE_EDITLINE=0])
|
||||
TARGET_READLINE_LIBS=$LIBS
|
||||
LIBS=$sLIBS
|
||||
fi
|
||||
if test x"$with_readline" != xno; then
|
||||
found="yes"
|
||||
|
||||
@@ -547,7 +584,6 @@ fi
|
||||
AC_SUBST(TARGET_READLINE_LIBS)
|
||||
AC_SUBST(TARGET_READLINE_INC)
|
||||
AC_SUBST(TARGET_HAVE_READLINE)
|
||||
AC_SUBST(TARGET_HAVE_EDITLINE)
|
||||
|
||||
##########
|
||||
# Figure out what C libraries are required to compile programs
|
||||
@@ -557,9 +593,10 @@ AC_SEARCH_LIBS(fdatasync, [rt])
|
||||
|
||||
#########
|
||||
# check for debug enabled
|
||||
AC_ARG_ENABLE(debug, AC_HELP_STRING([--enable-debug],[enable debugging & verbose explain]))
|
||||
if test "${enable_debug}" = "yes" ; then
|
||||
TARGET_DEBUG="-DSQLITE_DEBUG=1 -DSQLITE_ENABLE_SELECTTRACE -DSQLITE_ENABLE_WHERETRACE -O0"
|
||||
AC_ARG_ENABLE(debug, AC_HELP_STRING([--enable-debug],[enable debugging & verbose explain]),
|
||||
[use_debug=$enableval],[use_debug=no])
|
||||
if test "${use_debug}" = "yes" ; then
|
||||
TARGET_DEBUG="-DSQLITE_DEBUG=1"
|
||||
else
|
||||
TARGET_DEBUG="-DNDEBUG"
|
||||
fi
|
||||
@@ -568,116 +605,27 @@ AC_SUBST(TARGET_DEBUG)
|
||||
#########
|
||||
# See whether we should use the amalgamation to build
|
||||
AC_ARG_ENABLE(amalgamation, AC_HELP_STRING([--disable-amalgamation],
|
||||
[Disable the amalgamation and instead build all files separately]))
|
||||
if test "${enable_amalgamation}" == "no" ; then
|
||||
[Disable the amalgamation and instead build all files separately]),
|
||||
[use_amalgamation=$enableval],[use_amalgamation=yes])
|
||||
if test "${use_amalgamation}" != "yes" ; then
|
||||
USE_AMALGAMATION=0
|
||||
fi
|
||||
AC_SUBST(USE_AMALGAMATION)
|
||||
|
||||
#########
|
||||
# Look for zlib. Only needed by extensions and by the sqlite3.exe shell
|
||||
AC_CHECK_HEADERS(zlib.h)
|
||||
AC_SEARCH_LIBS(deflate, z, [HAVE_ZLIB="-DSQLITE_HAVE_ZLIB=1"], [HAVE_ZLIB=""])
|
||||
AC_SUBST(HAVE_ZLIB)
|
||||
|
||||
#########
|
||||
# See whether we should allow loadable extensions
|
||||
AC_ARG_ENABLE(load-extension, AC_HELP_STRING([--disable-load-extension],
|
||||
[Disable loading of external extensions]),,[enable_load_extension=yes])
|
||||
if test "${enable_load_extension}" = "yes" ; then
|
||||
AC_ARG_ENABLE(load-extension, AC_HELP_STRING([--enable-load-extension],
|
||||
[Enable loading of external extensions]),
|
||||
[use_loadextension=$enableval],[use_loadextension=no])
|
||||
if test "${use_loadextension}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS=""
|
||||
AC_SEARCH_LIBS(dlopen, dl)
|
||||
else
|
||||
OPT_FEATURE_FLAGS="-DSQLITE_OMIT_LOAD_EXTENSION=1"
|
||||
fi
|
||||
|
||||
##########
|
||||
# Do we want to support memsys3 and/or memsys5
|
||||
#
|
||||
AC_ARG_ENABLE(memsys5,
|
||||
AC_HELP_STRING([--enable-memsys5],[Enable MEMSYS5]))
|
||||
AC_MSG_CHECKING([whether to support MEMSYS5])
|
||||
if test "${enable_memsys5}" = "yes"; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_MEMSYS5"
|
||||
AC_MSG_RESULT([yes])
|
||||
else
|
||||
AC_MSG_RESULT([no])
|
||||
fi
|
||||
AC_ARG_ENABLE(memsys3,
|
||||
AC_HELP_STRING([--enable-memsys3],[Enable MEMSYS3]))
|
||||
AC_MSG_CHECKING([whether to support MEMSYS3])
|
||||
if test "${enable_memsys3}" = "yes" -a "${enable_memsys5}" = "no"; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_MEMSYS3"
|
||||
AC_MSG_RESULT([yes])
|
||||
else
|
||||
AC_MSG_RESULT([no])
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable Full Text Search extensions
|
||||
AC_ARG_ENABLE(fts3, AC_HELP_STRING([--enable-fts3],
|
||||
[Enable the FTS3 extension]))
|
||||
if test "${enable_fts3}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_FTS3"
|
||||
fi
|
||||
AC_ARG_ENABLE(fts4, AC_HELP_STRING([--enable-fts4],
|
||||
[Enable the FTS4 extension]))
|
||||
if test "${enable_fts4}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_FTS4"
|
||||
AC_SEARCH_LIBS([log],[m])
|
||||
fi
|
||||
AC_ARG_ENABLE(fts5, AC_HELP_STRING([--enable-fts5],
|
||||
[Enable the FTS5 extension]))
|
||||
if test "${enable_fts5}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_FTS5"
|
||||
AC_SEARCH_LIBS([log],[m])
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable JSON1
|
||||
AC_ARG_ENABLE(json1, AC_HELP_STRING([--enable-json1],[Enable the JSON1 extension]))
|
||||
if test "${enable_json1}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_JSON1"
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable the LIMIT clause on UPDATE and DELETE
|
||||
# statements.
|
||||
AC_ARG_ENABLE(update-limit, AC_HELP_STRING([--enable-update-limit],
|
||||
[Enable the UPDATE/DELETE LIMIT clause]))
|
||||
if test "${enable_udlimit}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_UPDATE_DELETE_LIMIT"
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable GEOPOLY
|
||||
AC_ARG_ENABLE(geopoly, AC_HELP_STRING([--enable-geopoly],
|
||||
[Enable the GEOPOLY extension]),
|
||||
[enable_geopoly=yes],[enable_geopoly=no])
|
||||
if test "${enable_geopoly}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_GEOPOLY"
|
||||
enable_rtree=yes
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable RTREE
|
||||
AC_ARG_ENABLE(rtree, AC_HELP_STRING([--enable-rtree],
|
||||
[Enable the RTREE extension]))
|
||||
if test "${enable_rtree}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_RTREE"
|
||||
fi
|
||||
|
||||
#########
|
||||
# See whether we should enable the SESSION extension
|
||||
AC_ARG_ENABLE(session, AC_HELP_STRING([--enable-session],
|
||||
[Enable the SESSION extension]))
|
||||
if test "${enable_session}" = "yes" ; then
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_SESSION"
|
||||
OPT_FEATURE_FLAGS="${OPT_FEATURE_FLAGS} -DSQLITE_ENABLE_PREUPDATE_HOOK"
|
||||
fi
|
||||
|
||||
#########
|
||||
# attempt to duplicate any OMITS and ENABLES into the ${OPT_FEATURE_FLAGS} parameter
|
||||
# attempt to duplicate any OMITS and ENABLES into the $(OPT_FEATURE_FLAGS) parameter
|
||||
for option in $CFLAGS $CPPFLAGS
|
||||
do
|
||||
case $option in
|
||||
@@ -730,7 +678,8 @@ BUILD_CFLAGS=$ac_temp_BUILD_CFLAGS
|
||||
#########
|
||||
# See whether we should use GCOV
|
||||
AC_ARG_ENABLE(gcov, AC_HELP_STRING([--enable-gcov],
|
||||
[Enable coverage testing using gcov]))
|
||||
[Enable coverage testing using gcov]),
|
||||
[use_gcov=$enableval],[use_gcov=no])
|
||||
if test "${use_gcov}" = "yes" ; then
|
||||
USE_GCOV=1
|
||||
else
|
||||
|
||||
@@ -1,87 +0,0 @@
|
||||
|
||||
SQLite's OS layer contains the following definitions used in F2FS related
|
||||
calls:
|
||||
|
||||
#define F2FS_IOCTL_MAGIC 0xf5
|
||||
#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
|
||||
#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
|
||||
#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
|
||||
#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
|
||||
#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, u32)
|
||||
#define F2FS_FEATURE_ATOMIC_WRITE 0x0004
|
||||
|
||||
After opening a database file on Linux (including Android), SQLite determines
|
||||
whether or not a file supports F2FS atomic commits as follows:
|
||||
|
||||
u32 flags = 0;
|
||||
rc = ioctl(fd, F2FS_IOC_GET_FEATURES, &flags);
|
||||
if( rc==0 && (flags & F2FS_FEATURE_ATOMIC_WRITE) ){
|
||||
/* File supports F2FS atomic commits */
|
||||
}else{
|
||||
/* File does NOT support F2FS atomic commits */
|
||||
}
|
||||
|
||||
where "fd" is the file-descriptor open on the database file.
|
||||
|
||||
Usually, when writing to a database file that supports atomic commits, SQLite
|
||||
accumulates the entire transaction in heap memory, deferring all writes to the
|
||||
db file until the transaction is committed.
|
||||
|
||||
When it is time to commit a transaction on a file that supports atomic
|
||||
commits, SQLite does:
|
||||
|
||||
/* Take an F_WRLCK lock on the database file. This prevents any other
|
||||
** SQLite clients from reading or writing the file until the lock
|
||||
** is released. */
|
||||
rc = fcntl(fd, F_SETLK, ...);
|
||||
if( rc!=0 ) goto failed;
|
||||
|
||||
rc = ioctl(fd, F2FS_IOC_START_ATOMIC_WRITE);
|
||||
if( rc!=0 ) goto fallback_to_legacy_journal_commit;
|
||||
|
||||
foreach (dirty page){
|
||||
rc = write(fd, ...dirty page...);
|
||||
if( rc!=0 ){
|
||||
ioctl(fd, F2FS_IOC_ABORT_VOLATILE_WRITE);
|
||||
goto fallback_to_legacy_journal_commit;
|
||||
}
|
||||
}
|
||||
|
||||
rc = ioctl(fd, F2FS_IOC_COMMIT_ATOMIC_WRITE);
|
||||
if( rc!=0 ){
|
||||
ioctl(fd, F2FS_IOC_ABORT_VOLATILE_WRITE);
|
||||
goto fallback_to_legacy_journal_commit;
|
||||
}
|
||||
|
||||
/* If we get there, the transaction has been successfully
|
||||
** committed to persistent storage. The following call
|
||||
** relinquishes the F_WRLCK lock. */
|
||||
fcntl(fd, F_SETLK, ...);
|
||||
|
||||
Assumptions:
|
||||
|
||||
1. After either of the F2FS_IOC_ABORT_VOLATILE_WRITE calls return,
|
||||
the database file is in the state that it was in before
|
||||
F2FS_IOC_START_ATOMIC_WRITE was invoked. Even if the ioctl()
|
||||
fails - we're ignoring the return code.
|
||||
|
||||
This is true regardless of the type of error that occurred in
|
||||
ioctl() or write().
|
||||
|
||||
2. If the system fails before the F2FS_IOC_COMMIT_ATOMIC_WRITE is
|
||||
completed, then following a reboot the database file is in the
|
||||
state that it was in before F2FS_IOC_START_ATOMIC_WRITE was invoked.
|
||||
Or, if the write was commited right before the system failed, in a
|
||||
state indicating that all write() calls were successfully committed
|
||||
to persistent storage before the failure occurred.
|
||||
|
||||
3. If the process crashes before the F2FS_IOC_COMMIT_ATOMIC_WRITE is
|
||||
completed then the file is automatically restored to the state that
|
||||
it was in before F2FS_IOC_START_ATOMIC_WRITE was called. This occurs
|
||||
before the posix advisory lock is automatically dropped - there is
|
||||
no chance that another client will be able to read the file in a
|
||||
half-committed state before the rollback operation occurs.
|
||||
|
||||
|
||||
|
||||
|
||||
+211
-383
@@ -2,47 +2,24 @@
|
||||
<head>
|
||||
<title>The Lemon Parser Generator</title>
|
||||
</head>
|
||||
<body bgcolor='white'>
|
||||
<h1 align='center'>The Lemon Parser Generator</h1>
|
||||
<body bgcolor=white>
|
||||
<h1 align=center>The Lemon Parser Generator</h1>
|
||||
|
||||
<p>Lemon is an LALR(1) parser generator for C.
|
||||
It does the same job as "bison" and "yacc".
|
||||
But Lemon is not a bison or yacc clone. Lemon
|
||||
<p>Lemon is an LALR(1) parser generator for C or C++.
|
||||
It does the same job as ``bison'' and ``yacc''.
|
||||
But lemon is not another bison or yacc clone. It
|
||||
uses a different grammar syntax which is designed to
|
||||
reduce the number of coding errors. Lemon also uses a
|
||||
parsing engine that is faster than yacc and
|
||||
bison and which is both reentrant and threadsafe.
|
||||
(Update: Since the previous sentence was written, bison
|
||||
has also been updated so that it too can generate a
|
||||
reentrant and threadsafe parser.)
|
||||
Lemon also implements features that can be used
|
||||
to eliminate resource leaks, making it suitable for use
|
||||
reduce the number of coding errors. Lemon also uses a more
|
||||
sophisticated parsing engine that is faster than yacc and
|
||||
bison and which is both reentrant and thread-safe.
|
||||
Furthermore, Lemon implements features that can be used
|
||||
to eliminate resource leaks, making is suitable for use
|
||||
in long-running programs such as graphical user interfaces
|
||||
or embedded controllers.</p>
|
||||
|
||||
<p>This document is an introduction to the Lemon
|
||||
parser generator.</p>
|
||||
|
||||
<h2>Security Note</h2>
|
||||
|
||||
<p>The language parser code created by Lemon is very robust and
|
||||
is well-suited for use in internet-facing applications that need to
|
||||
safely process maliciously crafted inputs.
|
||||
|
||||
<p>The "lemon.exe" command-line tool itself works great when given a valid
|
||||
input grammar file and almost always gives helpful
|
||||
error messages for malformed inputs. However, it is possible for
|
||||
a malicious user to craft a grammar file that will cause
|
||||
lemon.exe to crash.
|
||||
We do not see this as a problem, as lemon.exe is not intended to be used
|
||||
with hostile inputs.
|
||||
To summarize:</p>
|
||||
|
||||
<ul>
|
||||
<li>Parser code generated by lemon → Robust and secure
|
||||
<li>The "lemon.exe" command line tool itself → Not so much
|
||||
</ul>
|
||||
|
||||
<h2>Theory of Operation</h2>
|
||||
|
||||
<p>The main goal of Lemon is to translate a context free grammar (CFG)
|
||||
@@ -58,8 +35,8 @@ Lemon comes with a default parser template which works fine for most
|
||||
applications. But the user is free to substitute a different parser
|
||||
template if desired.</p>
|
||||
|
||||
<p>Depending on command-line options, Lemon will generate up to
|
||||
three output files.
|
||||
<p>Depending on command-line options, Lemon will generate between
|
||||
one and three files of outputs.
|
||||
<ul>
|
||||
<li>C code to implement the parser.
|
||||
<li>A header file defining an integer ID for each terminal symbol.
|
||||
@@ -67,18 +44,18 @@ three output files.
|
||||
automaton.
|
||||
</ul>
|
||||
By default, all three of these output files are generated.
|
||||
The header file is suppressed if the "-m" command-line option is
|
||||
used and the report file is omitted when "-q" is selected.</p>
|
||||
The header file is suppressed if the ``-m'' command-line option is
|
||||
used and the report file is omitted when ``-q'' is selected.</p>
|
||||
|
||||
<p>The grammar specification file uses a ".y" suffix, by convention.
|
||||
<p>The grammar specification file uses a ``.y'' suffix, by convention.
|
||||
In the examples used in this document, we'll assume the name of the
|
||||
grammar file is "gram.y". A typical use of Lemon would be the
|
||||
grammar file is ``gram.y''. A typical use of Lemon would be the
|
||||
following command:
|
||||
<pre>
|
||||
lemon gram.y
|
||||
</pre>
|
||||
This command will generate three output files named "gram.c",
|
||||
"gram.h" and "gram.out".
|
||||
This command will generate three output files named ``gram.c'',
|
||||
``gram.h'' and ``gram.out''.
|
||||
The first is C code to implement the parser. The second
|
||||
is the header file that defines numerical values for all
|
||||
terminal symbols, and the last is the report that explains
|
||||
@@ -90,45 +67,43 @@ the states used by the parser automaton.</p>
|
||||
You can obtain a list of the available command-line options together
|
||||
with a brief explanation of what each does by typing
|
||||
<pre>
|
||||
lemon "-?"
|
||||
lemon -?
|
||||
</pre>
|
||||
As of this writing, the following command-line options are supported:
|
||||
<ul>
|
||||
<li><b>-b</b>
|
||||
Show only the basis for each parser state in the report file.
|
||||
<li><b>-c</b>
|
||||
Do not compress the generated action tables. The parser will be a
|
||||
little larger and slower, but it will detect syntax errors sooner.
|
||||
<li><b>-d</b><i>directory</i>
|
||||
Write all output files into <i>directory</i>. Normally, output files
|
||||
are written into the directory that contains the input grammar file.
|
||||
<li><b>-D<i>name</i></b>
|
||||
Define C preprocessor macro <i>name</i>. This macro is usable by
|
||||
"<tt><a href='#pifdef'>%ifdef</a></tt>" and
|
||||
"<tt><a href='#pifdef'>%ifndef</a></tt>" lines
|
||||
in the grammar file.
|
||||
<li><b>-g</b>
|
||||
Do not generate a parser. Instead write the input grammar to standard
|
||||
output with all comments, actions, and other extraneous text removed.
|
||||
<li><b>-l</b>
|
||||
Omit "#line" directives in the generated parser C code.
|
||||
<li><b>-m</b>
|
||||
Cause the output C source code to be compatible with the "makeheaders"
|
||||
program.
|
||||
<li><b>-p</b>
|
||||
Display all conflicts that are resolved by
|
||||
<a href='#precrules'>precedence rules</a>.
|
||||
<li><b>-q</b>
|
||||
Suppress generation of the report file.
|
||||
<li><b>-r</b>
|
||||
Do not sort or renumber the parser states as part of optimization.
|
||||
<li><b>-s</b>
|
||||
Show parser statistics before existing.
|
||||
<li><b>-T<i>file</i></b>
|
||||
Use <i>file</i> as the template for the generated C-code parser implementation.
|
||||
<li><b>-x</b>
|
||||
Print the Lemon version number.
|
||||
<li><tt>-b</tt>
|
||||
<li><tt>-c</tt>
|
||||
<li><tt>-g</tt>
|
||||
<li><tt>-m</tt>
|
||||
<li><tt>-q</tt>
|
||||
<li><tt>-s</tt>
|
||||
<li><tt>-x</tt>
|
||||
</ul>
|
||||
The ``-b'' option reduces the amount of text in the report file by
|
||||
printing only the basis of each parser state, rather than the full
|
||||
configuration.
|
||||
The ``-c'' option suppresses action table compression. Using -c
|
||||
will make the parser a little larger and slower but it will detect
|
||||
syntax errors sooner.
|
||||
The ``-g'' option causes no output files to be generated at all.
|
||||
Instead, the input grammar file is printed on standard output but
|
||||
with all comments, actions and other extraneous text deleted. This
|
||||
is a useful way to get a quick summary of a grammar.
|
||||
The ``-m'' option causes the output C source file to be compatible
|
||||
with the ``makeheaders'' program.
|
||||
Makeheaders is a program that automatically generates header files
|
||||
from C source code. When the ``-m'' option is used, the header
|
||||
file is not output since the makeheaders program will take care
|
||||
of generated all header files automatically.
|
||||
The ``-q'' option suppresses the report file.
|
||||
Using ``-s'' causes a brief summary of parser statistics to be
|
||||
printed. Like this:
|
||||
<pre>
|
||||
Parser statistics: 74 terminals, 70 nonterminals, 179 rules
|
||||
340 states, 2026 parser table entries, 0 conflicts
|
||||
</pre>
|
||||
Finally, the ``-x'' option causes Lemon to print its version number
|
||||
and then stops without attempting to read the grammar or generate a parser.</p>
|
||||
|
||||
<h3>The Parser Interface</h3>
|
||||
|
||||
@@ -146,12 +121,12 @@ A new parser is created as follows:
|
||||
</pre>
|
||||
The ParseAlloc() routine allocates and initializes a new parser and
|
||||
returns a pointer to it.
|
||||
The actual data structure used to represent a parser is opaque —
|
||||
The actual data structure used to represent a parser is opaque --
|
||||
its internal structure is not visible or usable by the calling routine.
|
||||
For this reason, the ParseAlloc() routine returns a pointer to void
|
||||
rather than a pointer to some particular structure.
|
||||
The sole argument to the ParseAlloc() routine is a pointer to the
|
||||
subroutine used to allocate memory. Typically this means malloc().</p>
|
||||
subroutine used to allocate memory. Typically this means ``malloc()''.</p>
|
||||
|
||||
<p>After a program is finished using a parser, it can reclaim all
|
||||
memory allocated by that parser by calling
|
||||
@@ -171,24 +146,23 @@ once for each token:
|
||||
</pre>
|
||||
The first argument to the Parse() routine is the pointer returned by
|
||||
ParseAlloc().
|
||||
The second argument is a small positive integer that tells the parser the
|
||||
The second argument is a small positive integer that tells the parse the
|
||||
type of the next token in the data stream.
|
||||
There is one token type for each terminal symbol in the grammar.
|
||||
The gram.h file generated by Lemon contains #define statements that
|
||||
map symbolic terminal symbol names into appropriate integer values.
|
||||
A value of 0 for the second argument is a special flag to the
|
||||
parser to indicate that the end of input has been reached.
|
||||
(A value of 0 for the second argument is a special flag to the
|
||||
parser to indicate that the end of input has been reached.)
|
||||
The third argument is the value of the given token. By default,
|
||||
the type of the third argument is "void*", but the grammar will
|
||||
the type of the third argument is integer, but the grammar will
|
||||
usually redefine this type to be some kind of structure.
|
||||
Typically the second argument will be a broad category of tokens
|
||||
such as "identifier" or "number" and the third argument will
|
||||
such as ``identifier'' or ``number'' and the third argument will
|
||||
be the name of the identifier or the value of the number.</p>
|
||||
|
||||
<p>The Parse() function may have either three or four arguments,
|
||||
depending on the grammar. If the grammar specification file requests
|
||||
it (via the <tt><a href='#extraarg'>%extra_argument</a></tt> directive),
|
||||
the Parse() function will have a fourth parameter that can be
|
||||
depending on the grammar. If the grammar specification file request
|
||||
it, the Parse() function will have a fourth parameter that can be
|
||||
of any type chosen by the programmer. The parser doesn't do anything
|
||||
with this argument except to pass it through to action routines.
|
||||
This is a convenient mechanism for passing state information down
|
||||
@@ -197,20 +171,20 @@ to the action routines without having to use global variables.</p>
|
||||
<p>A typical use of a Lemon parser might look something like the
|
||||
following:
|
||||
<pre>
|
||||
1 ParseTree *ParseFile(const char *zFilename){
|
||||
2 Tokenizer *pTokenizer;
|
||||
3 void *pParser;
|
||||
4 Token sToken;
|
||||
5 int hTokenId;
|
||||
6 ParserState sState;
|
||||
7
|
||||
8 pTokenizer = TokenizerCreate(zFilename);
|
||||
9 pParser = ParseAlloc( malloc );
|
||||
10 InitParserState(&sState);
|
||||
11 while( GetNextToken(pTokenizer, &hTokenId, &sToken) ){
|
||||
12 Parse(pParser, hTokenId, sToken, &sState);
|
||||
01 ParseTree *ParseFile(const char *zFilename){
|
||||
02 Tokenizer *pTokenizer;
|
||||
03 void *pParser;
|
||||
04 Token sToken;
|
||||
05 int hTokenId;
|
||||
06 ParserState sState;
|
||||
07
|
||||
08 pTokenizer = TokenizerCreate(zFilename);
|
||||
09 pParser = ParseAlloc( malloc );
|
||||
10 InitParserState(&sState);
|
||||
11 while( GetNextToken(pTokenizer, &hTokenId, &sToken) ){
|
||||
12 Parse(pParser, hTokenId, sToken, &sState);
|
||||
13 }
|
||||
14 Parse(pParser, 0, sToken, &sState);
|
||||
14 Parse(pParser, 0, sToken, &sState);
|
||||
15 ParseFree(pParser, free );
|
||||
16 TokenizerFree(pTokenizer);
|
||||
17 return sState.treeRoot;
|
||||
@@ -218,15 +192,15 @@ following:
|
||||
</pre>
|
||||
This example shows a user-written routine that parses a file of
|
||||
text and returns a pointer to the parse tree.
|
||||
(All error-handling code is omitted from this example to keep it
|
||||
(We've omitted all error-handling from this example to keep it
|
||||
simple.)
|
||||
We assume the existence of some kind of tokenizer which is created
|
||||
using TokenizerCreate() on line 8 and deleted by TokenizerFree()
|
||||
on line 16. The GetNextToken() function on line 11 retrieves the
|
||||
next token from the input file and puts its type in the
|
||||
next token from the input file and puts its type in the
|
||||
integer variable hTokenId. The sToken variable is assumed to be
|
||||
some kind of structure that contains details about each token,
|
||||
such as its complete text, what line it occurs on, etc.</p>
|
||||
such as its complete text, what line it occurs on, etc. </p>
|
||||
|
||||
<p>This example also assumes the existence of structure of type
|
||||
ParserState that holds state information about a particular parse.
|
||||
@@ -243,7 +217,7 @@ tree.</p>
|
||||
<pre>
|
||||
ParseFile(){
|
||||
pParser = ParseAlloc( malloc );
|
||||
while( GetNextToken(pTokenizer,&hTokenId, &sToken) ){
|
||||
while( GetNextToken(pTokenizer,&hTokenId, &sToken) ){
|
||||
Parse(pParser, hTokenId, sToken);
|
||||
}
|
||||
Parse(pParser, 0, sToken);
|
||||
@@ -289,12 +263,6 @@ with prior yacc and bison experience.
|
||||
But after years of experience using Lemon, I firmly
|
||||
believe that the Lemon way of doing things is better.</p>
|
||||
|
||||
<p><i>Updated as of 2016-02-16:</i>
|
||||
The text above was written in the 1990s.
|
||||
We are told that Bison has lately been enhanced to support the
|
||||
tokenizer-calls-parser paradigm used by Lemon, and to obviate the
|
||||
need for global variables.</p>
|
||||
|
||||
<h2>Input File Syntax</h2>
|
||||
|
||||
<p>The main purpose of the grammar specification file for Lemon is
|
||||
@@ -303,25 +271,25 @@ specifies additional information Lemon requires to do its job.
|
||||
Most of the work in using Lemon is in writing an appropriate
|
||||
grammar file.</p>
|
||||
|
||||
<p>The grammar file for Lemon is, for the most part, free format.
|
||||
<p>The grammar file for lemon is, for the most part, free format.
|
||||
It does not have sections or divisions like yacc or bison. Any
|
||||
declaration can occur at any point in the file.
|
||||
Lemon ignores whitespace (except where it is needed to separate
|
||||
tokens), and it honors the same commenting conventions as C and C++.</p>
|
||||
tokens) and it honors the same commenting conventions as C and C++.</p>
|
||||
|
||||
<h3>Terminals and Nonterminals</h3>
|
||||
|
||||
<p>A terminal symbol (token) is any string of alphanumeric
|
||||
and/or underscore characters
|
||||
that begins with an uppercase letter.
|
||||
and underscore characters
|
||||
that begins with an upper case letter.
|
||||
A terminal can contain lowercase letters after the first character,
|
||||
but the usual convention is to make terminals all uppercase.
|
||||
but the usual convention is to make terminals all upper case.
|
||||
A nonterminal, on the other hand, is any string of alphanumeric
|
||||
and underscore characters than begins with a lowercase letter.
|
||||
Again, the usual convention is to make nonterminals use all lowercase
|
||||
letters.</p>
|
||||
and underscore characters than begins with a lower case letter.
|
||||
Again, the usual convention is to make nonterminals use all lower
|
||||
case letters.</p>
|
||||
|
||||
<p>In Lemon, terminal and nonterminal symbols do not need to
|
||||
<p>In Lemon, terminal and nonterminal symbols do not need to
|
||||
be declared or identified in a separate section of the grammar file.
|
||||
Lemon is able to generate a list of all terminals and nonterminals
|
||||
by examining the grammar rules, and it can always distinguish a
|
||||
@@ -339,14 +307,13 @@ must have alphanumeric names.</p>
|
||||
<p>The main component of a Lemon grammar file is a sequence of grammar
|
||||
rules.
|
||||
Each grammar rule consists of a nonterminal symbol followed by
|
||||
the special symbol "::=" and then a list of terminals and/or nonterminals.
|
||||
the special symbol ``::='' and then a list of terminals and/or nonterminals.
|
||||
The rule is terminated by a period.
|
||||
The list of terminals and nonterminals on the right-hand side of the
|
||||
rule can be empty.
|
||||
Rules can occur in any order, except that the left-hand side of the
|
||||
first rule is assumed to be the start symbol for the grammar (unless
|
||||
specified otherwise using the <tt><a href='#start_symbol'>%start_symbol</a></tt>
|
||||
directive described below.)
|
||||
specified otherwise using the <tt>%start</tt> directive described below.)
|
||||
A typical sequence of grammar rules might look something like this:
|
||||
<pre>
|
||||
expr ::= expr PLUS expr.
|
||||
@@ -356,9 +323,9 @@ A typical sequence of grammar rules might look something like this:
|
||||
</pre>
|
||||
</p>
|
||||
|
||||
<p>There is one non-terminal in this example, "expr", and five
|
||||
terminal symbols or tokens: "PLUS", "TIMES", "LPAREN",
|
||||
"RPAREN" and "VALUE".</p>
|
||||
<p>There is one non-terminal in this example, ``expr'', and five
|
||||
terminal symbols or tokens: ``PLUS'', ``TIMES'', ``LPAREN'',
|
||||
``RPAREN'' and ``VALUE''.</p>
|
||||
|
||||
<p>Like yacc and bison, Lemon allows the grammar to specify a block
|
||||
of C code that will be executed whenever a grammar rule is reduced
|
||||
@@ -374,22 +341,22 @@ For example:
|
||||
|
||||
<p>In order to be useful, grammar actions must normally be linked to
|
||||
their associated grammar rules.
|
||||
In yacc and bison, this is accomplished by embedding a "$$" in the
|
||||
In yacc and bison, this is accomplished by embedding a ``$$'' in the
|
||||
action to stand for the value of the left-hand side of the rule and
|
||||
symbols "$1", "$2", and so forth to stand for the value of
|
||||
symbols ``$1'', ``$2'', and so forth to stand for the value of
|
||||
the terminal or nonterminal at position 1, 2 and so forth on the
|
||||
right-hand side of the rule.
|
||||
This idea is very powerful, but it is also very error-prone. The
|
||||
single most common source of errors in a yacc or bison grammar is
|
||||
to miscount the number of symbols on the right-hand side of a grammar
|
||||
rule and say "$7" when you really mean "$8".</p>
|
||||
rule and say ``$7'' when you really mean ``$8''.</p>
|
||||
|
||||
<p>Lemon avoids the need to count grammar symbols by assigning symbolic
|
||||
names to each symbol in a grammar rule and then using those symbolic
|
||||
names in the action.
|
||||
In yacc or bison, one would write this:
|
||||
<pre>
|
||||
expr -> expr PLUS expr { $$ = $1 + $3; };
|
||||
expr -> expr PLUS expr { $$ = $1 + $3; };
|
||||
</pre>
|
||||
But in Lemon, the same rule becomes the following:
|
||||
<pre>
|
||||
@@ -412,7 +379,7 @@ For example, the rule
|
||||
<pre>
|
||||
expr(A) ::= expr(B) PLUS expr(C). { A = B; }
|
||||
</pre>
|
||||
will generate an error because the linking symbol "C" is used
|
||||
will generate an error because the linking symbol ``C'' is used
|
||||
in the grammar rule but not in the reduce action.</p>
|
||||
|
||||
<p>The Lemon notation for linking grammar rules to reduce actions
|
||||
@@ -420,7 +387,6 @@ also facilitates the use of destructors for reclaiming memory
|
||||
allocated by the values of terminals and nonterminals on the
|
||||
right-hand side of a rule.</p>
|
||||
|
||||
<a name='precrules'></a>
|
||||
<h3>Precedence Rules</h3>
|
||||
|
||||
<p>Lemon resolves parsing ambiguities in exactly the same way as
|
||||
@@ -429,14 +395,11 @@ of the shift, and a reduce-reduce conflict is resolved by reducing
|
||||
whichever rule comes first in the grammar file.</p>
|
||||
|
||||
<p>Just like in
|
||||
yacc and bison, Lemon allows a measure of control
|
||||
over the resolution of parsing conflicts using precedence rules.
|
||||
yacc and bison, Lemon allows a measure of control
|
||||
over the resolution of paring conflicts using precedence rules.
|
||||
A precedence value can be assigned to any terminal symbol
|
||||
using the
|
||||
<tt><a href='#pleft'>%left</a></tt>,
|
||||
<tt><a href='#pright'>%right</a></tt> or
|
||||
<tt><a href='#pnonassoc'>%nonassoc</a></tt> directives. Terminal symbols
|
||||
mentioned in earlier directives have a lower precedence than
|
||||
using the %left, %right or %nonassoc directives. Terminal symbols
|
||||
mentioned in earlier directives have a lower precedence that
|
||||
terminal symbols mentioned in later directives. For example:</p>
|
||||
|
||||
<p><pre>
|
||||
@@ -512,29 +475,29 @@ as follows:
|
||||
<li> If the precedence of the token to be shifted is greater than
|
||||
the precedence of the rule to reduce, then resolve in favor
|
||||
of the shift. No parsing conflict is reported.
|
||||
<li> If the precedence of the token to be shifted is less than the
|
||||
<li> If the precedence of the token it be shifted is less than the
|
||||
precedence of the rule to reduce, then resolve in favor of the
|
||||
reduce action. No parsing conflict is reported.
|
||||
<li> If the precedences are the same and the shift token is
|
||||
right-associative, then resolve in favor of the shift.
|
||||
No parsing conflict is reported.
|
||||
<li> If the precedences are the same and the shift token is
|
||||
<li> If the precedences are the same the the shift token is
|
||||
left-associative, then resolve in favor of the reduce.
|
||||
No parsing conflict is reported.
|
||||
<li> Otherwise, resolve the conflict by doing the shift, and
|
||||
report a parsing conflict.
|
||||
<li> Otherwise, resolve the conflict by doing the shift and
|
||||
report the parsing conflict.
|
||||
</ul>
|
||||
Reduce-reduce conflicts are resolved this way:
|
||||
<ul>
|
||||
<li> If either reduce rule
|
||||
<li> If either reduce rule
|
||||
lacks precedence information, then resolve in favor of the
|
||||
rule that appears first in the grammar, and report a parsing
|
||||
rule that appears first in the grammar and report a parsing
|
||||
conflict.
|
||||
<li> If both rules have precedence and the precedence is different,
|
||||
<li> If both rules have precedence and the precedence is different
|
||||
then resolve the dispute in favor of the rule with the highest
|
||||
precedence, and do not report a conflict.
|
||||
precedence and do not report a conflict.
|
||||
<li> Otherwise, resolve the conflict by reducing by the rule that
|
||||
appears first in the grammar, and report a parsing conflict.
|
||||
appears first in the grammar and report a parsing conflict.
|
||||
</ul>
|
||||
|
||||
<h3>Special Directives</h3>
|
||||
@@ -543,84 +506,73 @@ Reduce-reduce conflicts are resolved this way:
|
||||
directives. We've described all the grammar rules, so now we'll
|
||||
talk about the special directives.</p>
|
||||
|
||||
<p>Directives in Lemon can occur in any order. You can put them before
|
||||
the grammar rules, or after the grammar rules, or in the midst of the
|
||||
<p>Directives in lemon can occur in any order. You can put them before
|
||||
the grammar rules, or after the grammar rules, or in the mist of the
|
||||
grammar rules. It doesn't matter. The relative order of
|
||||
directives used to assign precedence to terminals is important, but
|
||||
other than that, the order of directives in Lemon is arbitrary.</p>
|
||||
|
||||
<p>Lemon supports the following special directives:
|
||||
<ul>
|
||||
<li><tt><a href='#pcode'>%code</a></tt>
|
||||
<li><tt><a href='#default_destructor'>%default_destructor</a></tt>
|
||||
<li><tt><a href='#default_type'>%default_type</a></tt>
|
||||
<li><tt><a href='#destructor'>%destructor</a></tt>
|
||||
<li><tt><a href='#pifdef'>%endif</a></tt>
|
||||
<li><tt><a href='#extraarg'>%extra_argument</a></tt>
|
||||
<li><tt><a href='#pfallback'>%fallback</a></tt>
|
||||
<li><tt><a href='#pifdef'>%ifdef</a></tt>
|
||||
<li><tt><a href='#pifdef'>%ifndef</a></tt>
|
||||
<li><tt><a href='#pinclude'>%include</a></tt>
|
||||
<li><tt><a href='#pleft'>%left</a></tt>
|
||||
<li><tt><a href='#pname'>%name</a></tt>
|
||||
<li><tt><a href='#pnonassoc'>%nonassoc</a></tt>
|
||||
<li><tt><a href='#parse_accept'>%parse_accept</a></tt>
|
||||
<li><tt><a href='#parse_failure'>%parse_failure</a></tt>
|
||||
<li><tt><a href='#pright'>%right</a></tt>
|
||||
<li><tt><a href='#stack_overflow'>%stack_overflow</a></tt>
|
||||
<li><tt><a href='#stack_size'>%stack_size</a></tt>
|
||||
<li><tt><a href='#start_symbol'>%start_symbol</a></tt>
|
||||
<li><tt><a href='#syntax_error'>%syntax_error</a></tt>
|
||||
<li><tt><a href='#token_class'>%token_class</a></tt>
|
||||
<li><tt><a href='#token_destructor'>%token_destructor</a></tt>
|
||||
<li><tt><a href='#token_prefix'>%token_prefix</a></tt>
|
||||
<li><tt><a href='#token_type'>%token_type</a></tt>
|
||||
<li><tt><a href='#ptype'>%type</a></tt>
|
||||
<li><tt><a href='#pwildcard'>%wildcard</a></tt>
|
||||
<li><tt>%code</tt>
|
||||
<li><tt>%default_destructor</tt>
|
||||
<li><tt>%default_type</tt>
|
||||
<li><tt>%destructor</tt>
|
||||
<li><tt>%extra_argument</tt>
|
||||
<li><tt>%include</tt>
|
||||
<li><tt>%left</tt>
|
||||
<li><tt>%name</tt>
|
||||
<li><tt>%nonassoc</tt>
|
||||
<li><tt>%parse_accept</tt>
|
||||
<li><tt>%parse_failure </tt>
|
||||
<li><tt>%right</tt>
|
||||
<li><tt>%stack_overflow</tt>
|
||||
<li><tt>%stack_size</tt>
|
||||
<li><tt>%start_symbol</tt>
|
||||
<li><tt>%syntax_error</tt>
|
||||
<li><tt>%token_destructor</tt>
|
||||
<li><tt>%token_prefix</tt>
|
||||
<li><tt>%token_type</tt>
|
||||
<li><tt>%type</tt>
|
||||
</ul>
|
||||
Each of these directives will be described separately in the
|
||||
following sections:</p>
|
||||
|
||||
<a name='pcode'></a>
|
||||
<h4>The <tt>%code</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%code</tt> directive is used to specify additional C code that
|
||||
<p>The %code directive is used to specify addition C/C++ code that
|
||||
is added to the end of the main output file. This is similar to
|
||||
the <tt><a href='#pinclude'>%include</a></tt> directive except that
|
||||
<tt>%include</tt> is inserted at the beginning of the main output file.</p>
|
||||
the %include directive except that %include is inserted at the
|
||||
beginning of the main output file.</p>
|
||||
|
||||
<p><tt>%code</tt> is typically used to include some action routines or perhaps
|
||||
a tokenizer or even the "main()" function
|
||||
as part of the output file.</p>
|
||||
<p>%code is typically used to include some action routines or perhaps
|
||||
a tokenizer as part of the output file.</p>
|
||||
|
||||
<a name='default_destructor'></a>
|
||||
<h4>The <tt>%default_destructor</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%default_destructor</tt> directive specifies a destructor to
|
||||
<p>The %default_destructor directive specifies a destructor to
|
||||
use for non-terminals that do not have their own destructor
|
||||
specified by a separate <tt>%destructor</tt> directive. See the documentation
|
||||
on the <tt><a name='#destructor'>%destructor</a></tt> directive below for
|
||||
additional information.</p>
|
||||
specified by a separate %destructor directive. See the documentation
|
||||
on the %destructor directive below for additional information.</p>
|
||||
|
||||
<p>In some grammars, many different non-terminal symbols have the
|
||||
same data type and hence the same destructor. This directive is
|
||||
a convenient way to specify the same destructor for all those
|
||||
<p>In some grammers, many different non-terminal symbols have the
|
||||
same datatype and hence the same destructor. This directive is
|
||||
a convenience way to specify the same destructor for all those
|
||||
non-terminals using a single statement.</p>
|
||||
|
||||
<a name='default_type'></a>
|
||||
<h4>The <tt>%default_type</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%default_type</tt> directive specifies the data type of non-terminal
|
||||
symbols that do not have their own data type defined using a separate
|
||||
<tt><a href='#ptype'>%type</a></tt> directive.</p>
|
||||
<p>The %default_type directive specifies the datatype of non-terminal
|
||||
symbols that do no have their own datatype defined using a separate
|
||||
%type directive. See the documentation on %type below for addition
|
||||
information.</p>
|
||||
|
||||
<a name='destructor'></a>
|
||||
<h4>The <tt>%destructor</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%destructor</tt> directive is used to specify a destructor for
|
||||
<p>The %destructor directive is used to specify a destructor for
|
||||
a non-terminal symbol.
|
||||
(See also the <tt><a href='#token_destructor'>%token_destructor</a></tt>
|
||||
directive which is used to specify a destructor for terminal symbols.)</p>
|
||||
(See also the %token_destructor directive which is used to
|
||||
specify a destructor for terminal symbols.)</p>
|
||||
|
||||
<p>A non-terminal's destructor is called to dispose of the
|
||||
non-terminal's value whenever the non-terminal is popped from
|
||||
@@ -641,33 +593,33 @@ or other resources held by that non-terminal.</p>
|
||||
%destructor nt { free($$); }
|
||||
nt(A) ::= ID NUM. { A = malloc( 100 ); }
|
||||
</pre>
|
||||
This example is a bit contrived, but it serves to illustrate how
|
||||
This example is a bit contrived but it serves to illustrate how
|
||||
destructors work. The example shows a non-terminal named
|
||||
"nt" that holds values of type "void*". When the rule for
|
||||
an "nt" reduces, it sets the value of the non-terminal to
|
||||
``nt'' that holds values of type ``void*''. When the rule for
|
||||
an ``nt'' reduces, it sets the value of the non-terminal to
|
||||
space obtained from malloc(). Later, when the nt non-terminal
|
||||
is popped from the stack, the destructor will fire and call
|
||||
free() on this malloced space, thus avoiding a memory leak.
|
||||
(Note that the symbol "$$" in the destructor code is replaced
|
||||
(Note that the symbol ``$$'' in the destructor code is replaced
|
||||
by the value of the non-terminal.)</p>
|
||||
|
||||
<p>It is important to note that the value of a non-terminal is passed
|
||||
to the destructor whenever the non-terminal is removed from the
|
||||
stack, unless the non-terminal is used in a C-code action. If
|
||||
the non-terminal is used by C-code, then it is assumed that the
|
||||
C-code will take care of destroying it.
|
||||
More commonly, the value is used to build some
|
||||
larger structure, and we don't want to destroy it, which is why
|
||||
C-code will take care of destroying it if it should really
|
||||
be destroyed. More commonly, the value is used to build some
|
||||
larger structure and we don't want to destroy it, which is why
|
||||
the destructor is not called in this circumstance.</p>
|
||||
|
||||
<p>Destructors help avoid memory leaks by automatically freeing
|
||||
allocated objects when they go out of scope.
|
||||
<p>By appropriate use of destructors, it is possible to
|
||||
build a parser using Lemon that can be used within a long-running
|
||||
program, such as a GUI, that will not leak memory or other resources.
|
||||
To do the same using yacc or bison is much more difficult.</p>
|
||||
|
||||
<a name='extraarg'></a>
|
||||
<h4>The <tt>%extra_argument</tt> directive</h4>
|
||||
|
||||
The <tt>%extra_argument</tt> directive instructs Lemon to add a 4th parameter
|
||||
The %extra_argument directive instructs Lemon to add a 4th parameter
|
||||
to the parameter list of the Parse() function it generates. Lemon
|
||||
doesn't do anything itself with this extra argument, but it does
|
||||
make the argument available to C-code action routines, destructors,
|
||||
@@ -678,95 +630,19 @@ and so forth. For example, if the grammar file contains:</p>
|
||||
</pre></p>
|
||||
|
||||
<p>Then the Parse() function generated will have an 4th parameter
|
||||
of type "MyStruct*" and all action routines will have access to
|
||||
a variable named "pAbc" that is the value of the 4th parameter
|
||||
of type ``MyStruct*'' and all action routines will have access to
|
||||
a variable named ``pAbc'' that is the value of the 4th parameter
|
||||
in the most recent call to Parse().</p>
|
||||
|
||||
<p>The <tt>%extra_context</tt> directive works the same except that it
|
||||
is passed in on the ParseAlloc() or ParseInit() routines instead of
|
||||
on Parse().
|
||||
|
||||
<a name='extractx'></a>
|
||||
<h4>The <tt>%extra_context</tt> directive</h4>
|
||||
|
||||
The <tt>%extra_context</tt> directive instructs Lemon to add a 2th parameter
|
||||
to the parameter list of the ParseAlloc() and ParseInif() functions. Lemon
|
||||
doesn't do anything itself with these extra argument, but it does
|
||||
store the value make it available to C-code action routines, destructors,
|
||||
and so forth. For example, if the grammar file contains:</p>
|
||||
|
||||
<p><pre>
|
||||
%extra_context { MyStruct *pAbc }
|
||||
</pre></p>
|
||||
|
||||
<p>Then the ParseAlloc() and ParseInit() functions will have an 2th parameter
|
||||
of type "MyStruct*" and all action routines will have access to
|
||||
a variable named "pAbc" that is the value of that 2th parameter.</p>
|
||||
|
||||
<p>The <tt>%extra_argument</tt> directive works the same except that it
|
||||
is passed in on the Parse() routine instead of on ParseAlloc()/ParseInit().
|
||||
|
||||
<a name='pfallback'></a>
|
||||
<h4>The <tt>%fallback</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%fallback</tt> directive specifies an alternative meaning for one
|
||||
or more tokens. The alternative meaning is tried if the original token
|
||||
would have generated a syntax error.</p>
|
||||
|
||||
<p>The <tt>%fallback</tt> directive was added to support robust parsing of SQL
|
||||
syntax in <a href='https://www.sqlite.org/'>SQLite</a>.
|
||||
The SQL language contains a large assortment of keywords, each of which
|
||||
appears as a different token to the language parser. SQL contains so
|
||||
many keywords that it can be difficult for programmers to keep up with
|
||||
them all. Programmers will, therefore, sometimes mistakenly use an
|
||||
obscure language keyword for an identifier. The <tt>%fallback</tt> directive
|
||||
provides a mechanism to tell the parser: "If you are unable to parse
|
||||
this keyword, try treating it as an identifier instead."</p>
|
||||
|
||||
<p>The syntax of <tt>%fallback</tt> is as follows:
|
||||
|
||||
<blockquote>
|
||||
<tt>%fallback</tt> <i>ID</i> <i>TOKEN...</i> <b>.</b>
|
||||
</blockquote></p>
|
||||
|
||||
<p>In words, the <tt>%fallback</tt> directive is followed by a list of token
|
||||
names terminated by a period.
|
||||
The first token name is the fallback token — the
|
||||
token to which all the other tokens fall back to. The second and subsequent
|
||||
arguments are tokens which fall back to the token identified by the first
|
||||
argument.</p>
|
||||
|
||||
<a name='pifdef'></a>
|
||||
<h4>The <tt>%ifdef</tt>, <tt>%ifndef</tt>, and <tt>%endif</tt> directives</h4>
|
||||
|
||||
<p>The <tt>%ifdef</tt>, <tt>%ifndef</tt>, and <tt>%endif</tt> directives
|
||||
are similar to #ifdef, #ifndef, and #endif in the C-preprocessor,
|
||||
just not as general.
|
||||
Each of these directives must begin at the left margin. No whitespace
|
||||
is allowed between the "%" and the directive name.</p>
|
||||
|
||||
<p>Grammar text in between "<tt>%ifdef MACRO</tt>" and the next nested
|
||||
"<tt>%endif</tt>" is
|
||||
ignored unless the "-DMACRO" command-line option is used. Grammar text
|
||||
betwen "<tt>%ifndef MACRO</tt>" and the next nested "<tt>%endif</tt>" is
|
||||
included except when the "-DMACRO" command-line option is used.</p>
|
||||
|
||||
<p>Note that the argument to <tt>%ifdef</tt> and <tt>%ifndef</tt> must
|
||||
be a single preprocessor symbol name, not a general expression.
|
||||
There is no "<tt>%else</tt>" directive.</p>
|
||||
|
||||
|
||||
<a name='pinclude'></a>
|
||||
<h4>The <tt>%include</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%include</tt> directive specifies C code that is included at the
|
||||
top of the generated parser. You can include any text you want —
|
||||
<p>The %include directive specifies C code that is included at the
|
||||
top of the generated parser. You can include any text you want --
|
||||
the Lemon parser generator copies it blindly. If you have multiple
|
||||
<tt>%include</tt> directives in your grammar file, their values are concatenated
|
||||
so that all <tt>%include</tt> code ultimately appears near the top of the
|
||||
generated parser, in the same order as it appeared in the grammar.</p>
|
||||
%include directives in your grammar file the value of the last
|
||||
%include directive overwrites all the others.</p.
|
||||
|
||||
<p>The <tt>%include</tt> directive is very handy for getting some extra #include
|
||||
<p>The %include directive is very handy for getting some extra #include
|
||||
preprocessor statements at the beginning of the generated parser.
|
||||
For example:</p>
|
||||
|
||||
@@ -775,22 +651,16 @@ For example:</p>
|
||||
</pre></p>
|
||||
|
||||
<p>This might be needed, for example, if some of the C actions in the
|
||||
grammar call functions that are prototyped in unistd.h.</p>
|
||||
grammar call functions that are prototyed in unistd.h.</p>
|
||||
|
||||
<p>Use the <tt><a href="#pcode">%code</a></tt> directive to add code to
|
||||
the end of the generated parser.</p>
|
||||
|
||||
<a name='pleft'></a>
|
||||
<h4>The <tt>%left</tt> directive</h4>
|
||||
|
||||
The <tt>%left</tt> directive is used (along with the
|
||||
<tt><a href='#pright'>%right</a></tt> and
|
||||
<tt><a href='#pnonassoc'>%nonassoc</a></tt> directives) to declare
|
||||
precedences of terminal symbols.
|
||||
Every terminal symbol whose name appears after
|
||||
a <tt>%left</tt> directive but before the next period (".") is
|
||||
The %left directive is used (along with the %right and
|
||||
%nonassoc directives) to declare precedences of terminal
|
||||
symbols. Every terminal symbol whose name appears after
|
||||
a %left directive but before the next period (``.'') is
|
||||
given the same left-associative precedence value. Subsequent
|
||||
<tt>%left</tt> directives have higher precedence. For example:</p>
|
||||
%left directives have higher precedence. For example:</p>
|
||||
|
||||
<p><pre>
|
||||
%left AND.
|
||||
@@ -801,21 +671,19 @@ given the same left-associative precedence value. Subsequent
|
||||
%right EXP NOT.
|
||||
</pre></p>
|
||||
|
||||
<p>Note the period that terminates each <tt>%left</tt>,
|
||||
<tt>%right</tt> or <tt>%nonassoc</tt>
|
||||
<p>Note the period that terminates each %left, %right or %nonassoc
|
||||
directive.</p>
|
||||
|
||||
<p>LALR(1) grammars can get into a situation where they require
|
||||
a large amount of stack space if you make heavy use or right-associative
|
||||
operators. For this reason, it is recommended that you use <tt>%left</tt>
|
||||
rather than <tt>%right</tt> whenever possible.</p>
|
||||
operators. For this reason, it is recommended that you use %left
|
||||
rather than %right whenever possible.</p>
|
||||
|
||||
<a name='pname'></a>
|
||||
<h4>The <tt>%name</tt> directive</h4>
|
||||
|
||||
<p>By default, the functions generated by Lemon all begin with the
|
||||
five-character string "Parse". You can change this string to something
|
||||
different using the <tt>%name</tt> directive. For instance:</p>
|
||||
five-character string ``Parse''. You can change this string to something
|
||||
different using the %name directive. For instance:</p>
|
||||
|
||||
<p><pre>
|
||||
%name Abcde
|
||||
@@ -829,23 +697,20 @@ functions named
|
||||
<li> AbcdeTrace(), and
|
||||
<li> Abcde().
|
||||
</ul>
|
||||
The <tt>%name</tt> directive allows you to generate two or more different
|
||||
parsers and link them all into the same executable.</p>
|
||||
The %name directive allows you to generator two or more different
|
||||
parsers and link them all into the same executable.
|
||||
</p>
|
||||
|
||||
<a name='pnonassoc'></a>
|
||||
<h4>The <tt>%nonassoc</tt> directive</h4>
|
||||
|
||||
<p>This directive is used to assign non-associative precedence to
|
||||
one or more terminal symbols. See the section on
|
||||
<a href='#precrules'>precedence rules</a>
|
||||
or on the <tt><a href='#pleft'>%left</a></tt> directive
|
||||
for additional information.</p>
|
||||
one or more terminal symbols. See the section on precedence rules
|
||||
or on the %left directive for additional information.</p>
|
||||
|
||||
<a name='parse_accept'></a>
|
||||
<h4>The <tt>%parse_accept</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%parse_accept</tt> directive specifies a block of C code that is
|
||||
executed whenever the parser accepts its input string. To "accept"
|
||||
<p>The %parse_accept directive specifies a block of C code that is
|
||||
executed whenever the parser accepts its input string. To ``accept''
|
||||
an input string means that the parser was able to process all tokens
|
||||
without error.</p>
|
||||
|
||||
@@ -857,10 +722,10 @@ without error.</p>
|
||||
}
|
||||
</pre></p>
|
||||
|
||||
<a name='parse_failure'></a>
|
||||
|
||||
<h4>The <tt>%parse_failure</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%parse_failure</tt> directive specifies a block of C code that
|
||||
<p>The %parse_failure directive specifies a block of C code that
|
||||
is executed whenever the parser fails complete. This code is not
|
||||
executed until the parser has tried and failed to resolve an input
|
||||
error using is usual error recovery strategy. The routine is
|
||||
@@ -872,18 +737,15 @@ only invoked when parsing is unable to continue.</p>
|
||||
}
|
||||
</pre></p>
|
||||
|
||||
<a name='pright'></a>
|
||||
<h4>The <tt>%right</tt> directive</h4>
|
||||
|
||||
<p>This directive is used to assign right-associative precedence to
|
||||
one or more terminal symbols. See the section on
|
||||
<a href='#precrules'>precedence rules</a>
|
||||
or on the <a href='#pleft'>%left</a> directive for additional information.</p>
|
||||
one or more terminal symbols. See the section on precedence rules
|
||||
or on the %left directive for additional information.</p>
|
||||
|
||||
<a name='stack_overflow'></a>
|
||||
<h4>The <tt>%stack_overflow</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%stack_overflow</tt> directive specifies a block of C code that
|
||||
<p>The %stack_overflow directive specifies a block of C code that
|
||||
is executed if the parser's internal stack ever overflows. Typically
|
||||
this just prints an error message. After a stack overflow, the parser
|
||||
will be unable to continue and must be reset.</p>
|
||||
@@ -896,7 +758,7 @@ will be unable to continue and must be reset.</p>
|
||||
|
||||
<p>You can help prevent parser stack overflows by avoiding the use
|
||||
of right recursion and right-precedence operators in your grammar.
|
||||
Use left recursion and and left-precedence operators instead to
|
||||
Use left recursion and and left-precedence operators instead, to
|
||||
encourage rules to reduce sooner and keep the stack size down.
|
||||
For example, do rules like this:
|
||||
<pre>
|
||||
@@ -907,69 +769,49 @@ Not like this:
|
||||
<pre>
|
||||
list ::= element list. // right-recursion. Bad!
|
||||
list ::= .
|
||||
</pre></p>
|
||||
</pre>
|
||||
|
||||
<a name='stack_size'></a>
|
||||
<h4>The <tt>%stack_size</tt> directive</h4>
|
||||
|
||||
<p>If stack overflow is a problem and you can't resolve the trouble
|
||||
by using left-recursion, then you might want to increase the size
|
||||
of the parser's stack using this directive. Put an positive integer
|
||||
after the <tt>%stack_size</tt> directive and Lemon will generate a parse
|
||||
after the %stack_size directive and Lemon will generate a parse
|
||||
with a stack of the requested size. The default value is 100.</p>
|
||||
|
||||
<p><pre>
|
||||
%stack_size 2000
|
||||
</pre></p>
|
||||
|
||||
<a name='start_symbol'></a>
|
||||
<h4>The <tt>%start_symbol</tt> directive</h4>
|
||||
|
||||
<p>By default, the start symbol for the grammar that Lemon generates
|
||||
<p>By default, the start-symbol for the grammar that Lemon generates
|
||||
is the first non-terminal that appears in the grammar file. But you
|
||||
can choose a different start symbol using the
|
||||
<tt>%start_symbol</tt> directive.</p>
|
||||
can choose a different start-symbol using the %start_symbol directive.</p>
|
||||
|
||||
<p><pre>
|
||||
%start_symbol prog
|
||||
</pre></p>
|
||||
|
||||
<a name='syntax_error'></a>
|
||||
<h4>The <tt>%syntax_error</tt> directive</h4>
|
||||
|
||||
<p>See <a href='#error_processing'>Error Processing</a>.</p>
|
||||
|
||||
<a name='token_class'></a>
|
||||
<h4>The <tt>%token_class</tt> directive</h4>
|
||||
|
||||
<p>Undocumented. Appears to be related to the MULTITERMINAL concept.
|
||||
<a href='http://sqlite.org/src/fdiff?v1=796930d5fc2036c7&v2=624b24c5dc048e09&sbs=0'>Implementation</a>.</p>
|
||||
|
||||
<a name='token_destructor'></a>
|
||||
<h4>The <tt>%token_destructor</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%destructor</tt> directive assigns a destructor to a non-terminal
|
||||
symbol. (See the description of the
|
||||
<tt><a href='%destructor'>%destructor</a></tt> directive above.)
|
||||
The <tt>%token_destructor</tt> directive does the same thing
|
||||
for all terminal symbols.</p>
|
||||
<p>The %destructor directive assigns a destructor to a non-terminal
|
||||
symbol. (See the description of the %destructor directive above.)
|
||||
This directive does the same thing for all terminal symbols.</p>
|
||||
|
||||
<p>Unlike non-terminal symbols which may each have a different data type
|
||||
for their values, terminals all use the same data type (defined by
|
||||
the <tt><a href='#token_type'>%token_type</a></tt> directive)
|
||||
and so they use a common destructor.
|
||||
Other than that, the token destructor works just like the non-terminal
|
||||
the %token_type directive) and so they use a common destructor. Other
|
||||
than that, the token destructor works just like the non-terminal
|
||||
destructors.</p>
|
||||
|
||||
<a name='token_prefix'></a>
|
||||
<h4>The <tt>%token_prefix</tt> directive</h4>
|
||||
|
||||
<p>Lemon generates #defines that assign small integer constants
|
||||
to each terminal symbol in the grammar. If desired, Lemon will
|
||||
add a prefix specified by this directive
|
||||
to each of the #defines it generates.</p>
|
||||
|
||||
<p>So if the default output of Lemon looked like this:
|
||||
to each of the #defines it generates.
|
||||
So if the default output of Lemon looked like this:
|
||||
<pre>
|
||||
#define AND 1
|
||||
#define MINUS 2
|
||||
@@ -986,9 +828,8 @@ to cause Lemon to produce these symbols instead:
|
||||
#define TOKEN_MINUS 2
|
||||
#define TOKEN_OR 3
|
||||
#define TOKEN_PLUS 4
|
||||
</pre></p>
|
||||
</pre>
|
||||
|
||||
<a name='token_type'></a><a name='ptype'></a>
|
||||
<h4>The <tt>%token_type</tt> and <tt>%type</tt> directives</h4>
|
||||
|
||||
<p>These directives are used to specify the data types for values
|
||||
@@ -1004,10 +845,10 @@ token structure. Like this:</p>
|
||||
</pre></p>
|
||||
|
||||
<p>If the data type of terminals is not specified, the default value
|
||||
is "void*".</p>
|
||||
is ``int''.</p>
|
||||
|
||||
<p>Non-terminal symbols can each have their own data types. Typically
|
||||
the data type of a non-terminal is a pointer to the root of a parse tree
|
||||
the data type of a non-terminal is a pointer to the root of a parse-tree
|
||||
structure that contains all information about that non-terminal.
|
||||
For example:</p>
|
||||
|
||||
@@ -1025,18 +866,6 @@ non-terminal whose data type requires 1K of storage, then your 100
|
||||
entry parser stack will require 100K of heap space. If you are willing
|
||||
and able to pay that price, fine. You just need to know.</p>
|
||||
|
||||
<a name='pwildcard'></a>
|
||||
<h4>The <tt>%wildcard</tt> directive</h4>
|
||||
|
||||
<p>The <tt>%wildcard</tt> directive is followed by a single token name and a
|
||||
period. This directive specifies that the identified token should
|
||||
match any input token.</p>
|
||||
|
||||
<p>When the generated parser has the choice of matching an input against
|
||||
the wildcard token and some other token, the other token is always used.
|
||||
The wildcard token is only matched if there are no alternatives.</p>
|
||||
|
||||
<a name='error_processing'></a>
|
||||
<h3>Error Processing</h3>
|
||||
|
||||
<p>After extensive experimentation over several years, it has been
|
||||
@@ -1044,21 +873,20 @@ discovered that the error recovery strategy used by yacc is about
|
||||
as good as it gets. And so that is what Lemon uses.</p>
|
||||
|
||||
<p>When a Lemon-generated parser encounters a syntax error, it
|
||||
first invokes the code specified by the <tt>%syntax_error</tt> directive, if
|
||||
first invokes the code specified by the %syntax_error directive, if
|
||||
any. It then enters its error recovery strategy. The error recovery
|
||||
strategy is to begin popping the parsers stack until it enters a
|
||||
state where it is permitted to shift a special non-terminal symbol
|
||||
named "error". It then shifts this non-terminal and continues
|
||||
parsing. The <tt>%syntax_error</tt> routine will not be called again
|
||||
named ``error''. It then shifts this non-terminal and continues
|
||||
parsing. But the %syntax_error routine will not be called again
|
||||
until at least three new tokens have been successfully shifted.</p>
|
||||
|
||||
<p>If the parser pops its stack until the stack is empty, and it still
|
||||
is unable to shift the error symbol, then the
|
||||
<tt><a href='#parse_failure'>%parse_failure</a></tt> routine
|
||||
is unable to shift the error symbol, then the %parse_failed routine
|
||||
is invoked and the parser resets itself to its start state, ready
|
||||
to begin parsing a new file. This is what will happen at the very
|
||||
first syntax error, of course, if there are no instances of the
|
||||
"error" non-terminal in your grammar.</p>
|
||||
first syntax error, of course, if there are no instances of the
|
||||
``error'' non-terminal in your grammar.</p>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
@@ -44,7 +44,7 @@
|
||||
|
||||
*** Definition: Two databases (or the same database at two points it time)
|
||||
are said to be "logically equivalent" if they give the same answer to
|
||||
all queries. Note in particular the content of freelist leaf
|
||||
all queries. Note in particular the the content of freelist leaf
|
||||
pages can be changed arbitarily without effecting the logical equivalence
|
||||
of the database.
|
||||
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
## Loadable Extensions
|
||||
|
||||
Various [loadable extensions](https://www.sqlite.org/loadext.html) for
|
||||
SQLite are found in subfolders.
|
||||
|
||||
Most subfolders are dedicated to a single loadable extension (for
|
||||
example FTS5, or RTREE). But the misc/ subfolder contains a collection
|
||||
of smaller single-file extensions.
|
||||
@@ -0,0 +1,2 @@
|
||||
Version loadable extensions to SQLite are found in subfolders
|
||||
of this folder.
|
||||
@@ -1,10 +1,3 @@
|
||||
NOTE (2012-11-29):
|
||||
|
||||
The functionality implemented by this extension has been superseded
|
||||
by WAL-mode. This module is no longer supported or maintained. The
|
||||
code is retained for historical reference only.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
Normally, when SQLite writes to a database file, it waits until the write
|
||||
operation is finished before returning control to the calling application.
|
||||
@@ -168,3 +161,4 @@ the database, eliminating the bottleneck.
|
||||
|
||||
The functionality required of each of the above functions is described
|
||||
in comments in sqlite3async.c.
|
||||
|
||||
|
||||
@@ -1510,7 +1510,6 @@ static void asyncWriterThread(void){
|
||||
case ASYNC_DELETE:
|
||||
ASYNC_TRACE(("DELETE %s\n", p->zBuf));
|
||||
rc = pVfs->xDelete(pVfs, p->zBuf, (int)p->iOffset);
|
||||
if( rc==SQLITE_IOERR_DELETE_NOENT ) rc = SQLITE_OK;
|
||||
break;
|
||||
|
||||
case ASYNC_OPENEXCLUSIVE: {
|
||||
@@ -1636,7 +1635,6 @@ void sqlite3async_run(void){
|
||||
** Control/configure the asynchronous IO system.
|
||||
*/
|
||||
int sqlite3async_control(int op, ...){
|
||||
int rc = SQLITE_OK;
|
||||
va_list ap;
|
||||
va_start(ap, op);
|
||||
switch( op ){
|
||||
@@ -1646,8 +1644,7 @@ int sqlite3async_control(int op, ...){
|
||||
&& eWhen!=SQLITEASYNC_HALT_NOW
|
||||
&& eWhen!=SQLITEASYNC_HALT_IDLE
|
||||
){
|
||||
rc = SQLITE_MISUSE;
|
||||
break;
|
||||
return SQLITE_MISUSE;
|
||||
}
|
||||
async.eHalt = eWhen;
|
||||
async_mutex_enter(ASYNC_MUTEX_QUEUE);
|
||||
@@ -1659,8 +1656,7 @@ int sqlite3async_control(int op, ...){
|
||||
case SQLITEASYNC_DELAY: {
|
||||
int iDelay = va_arg(ap, int);
|
||||
if( iDelay<0 ){
|
||||
rc = SQLITE_MISUSE;
|
||||
break;
|
||||
return SQLITE_MISUSE;
|
||||
}
|
||||
async.ioDelay = iDelay;
|
||||
break;
|
||||
@@ -1671,8 +1667,7 @@ int sqlite3async_control(int op, ...){
|
||||
async_mutex_enter(ASYNC_MUTEX_QUEUE);
|
||||
if( async.nFile || async.pQueueFirst ){
|
||||
async_mutex_leave(ASYNC_MUTEX_QUEUE);
|
||||
rc = SQLITE_MISUSE;
|
||||
break;
|
||||
return SQLITE_MISUSE;
|
||||
}
|
||||
async.bLockFiles = bLock;
|
||||
async_mutex_leave(ASYNC_MUTEX_QUEUE);
|
||||
@@ -1696,11 +1691,9 @@ int sqlite3async_control(int op, ...){
|
||||
}
|
||||
|
||||
default:
|
||||
rc = SQLITE_ERROR;
|
||||
break;
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
va_end(ap);
|
||||
return rc;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_ASYNCIO) */
|
||||
|
||||
@@ -75,7 +75,7 @@ int sqlite3async_initialize(const char *zParent, int isDefault);
|
||||
** On win32 platforms, this function also releases the small number of
|
||||
** critical section and event objects created by sqlite3async_initialize().
|
||||
*/
|
||||
void sqlite3async_shutdown(void);
|
||||
void sqlite3async_shutdown();
|
||||
|
||||
/*
|
||||
** This function may only be called when the asynchronous IO VFS is
|
||||
@@ -94,7 +94,7 @@ void sqlite3async_shutdown(void);
|
||||
** If multiple simultaneous calls are made to sqlite3async_run() from two
|
||||
** or more threads, then the calls are serialized internally.
|
||||
*/
|
||||
void sqlite3async_run(void);
|
||||
void sqlite3async_run();
|
||||
|
||||
/*
|
||||
** This function may only be called when the asynchronous IO VFS is
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
## SQLite Expert Extension
|
||||
|
||||
This folder contains code for a simple system to propose useful indexes
|
||||
given a database and a set of SQL queries. It works as follows:
|
||||
|
||||
1. The user database schema is copied to a temporary database.
|
||||
|
||||
1. All SQL queries are prepared against the temporary database.
|
||||
Information regarding the WHERE and ORDER BY clauses, and other query
|
||||
features that affect index selection are recorded.
|
||||
|
||||
1. The information gathered in step 2 is used to create candidate
|
||||
indexes - indexes that the planner might have made use of in the previous
|
||||
step, had they been available.
|
||||
|
||||
1. A subset of the data in the user database is used to generate statistics
|
||||
for all existing indexes and the candidate indexes generated in step 3
|
||||
above.
|
||||
|
||||
1. The SQL queries are prepared a second time. If the planner uses any
|
||||
of the indexes created in step 3, they are recommended to the user.
|
||||
|
||||
# C API
|
||||
|
||||
The SQLite expert C API is defined in sqlite3expert.h. Most uses will proceed
|
||||
as follows:
|
||||
|
||||
1. An sqlite3expert object is created by calling **sqlite3\_expert\_new()**.
|
||||
A database handle opened by the user is passed as an argument.
|
||||
|
||||
1. The sqlite3expert object is configured with one or more SQL statements
|
||||
by making one or more calls to **sqlite3\_expert\_sql()**. Each call may
|
||||
specify a single SQL statement, or multiple statements separated by
|
||||
semi-colons.
|
||||
|
||||
1. Optionally, the **sqlite3\_expert\_config()** API may be used to
|
||||
configure the size of the data subset used to generate index statistics.
|
||||
Using a smaller subset of the data can speed up the analysis.
|
||||
|
||||
1. **sqlite3\_expert\_analyze()** is called to run the analysis.
|
||||
|
||||
1. One or more calls are made to **sqlite3\_expert\_report()** to extract
|
||||
components of the results of the analysis.
|
||||
|
||||
1. **sqlite3\_expert\_destroy()** is called to free all resources.
|
||||
|
||||
Refer to comments in sqlite3expert.h for further details.
|
||||
|
||||
# sqlite3_expert application
|
||||
|
||||
The file "expert.c" contains the code for a command line application that
|
||||
uses the API described above. It can be compiled with (for example):
|
||||
|
||||
<pre>
|
||||
gcc -O2 sqlite3.c expert.c sqlite3expert.c -o sqlite3_expert
|
||||
</pre>
|
||||
|
||||
Assuming the database is named "test.db", it can then be run to analyze a
|
||||
single query:
|
||||
|
||||
<pre>
|
||||
./sqlite3_expert -sql <sql-query> test.db
|
||||
</pre>
|
||||
|
||||
Or an entire text file worth of queries with:
|
||||
|
||||
<pre>
|
||||
./sqlite3_expert -file <text-file> test.db
|
||||
</pre>
|
||||
|
||||
By default, sqlite3\_expert generates index statistics using all the data in
|
||||
the user database. For a large database, this may be prohibitively time
|
||||
consuming. The "-sample" option may be used to configure sqlite3\_expert to
|
||||
generate statistics based on an integer percentage of the user database as
|
||||
follows:
|
||||
|
||||
<pre>
|
||||
# Generate statistics based on 25% of the user database rows:
|
||||
./sqlite3_expert -sample 25 -sql <sql-query> test.db
|
||||
|
||||
# Do not generate any statistics at all:
|
||||
./sqlite3_expert -sample 0 -sql <sql-query> test.db
|
||||
</pre>
|
||||
@@ -1,156 +0,0 @@
|
||||
/*
|
||||
** 2017 April 07
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
*/
|
||||
|
||||
|
||||
#include <sqlite3.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include "sqlite3expert.h"
|
||||
|
||||
|
||||
static void option_requires_argument(const char *zOpt){
|
||||
fprintf(stderr, "Option requires an argument: %s\n", zOpt);
|
||||
exit(-3);
|
||||
}
|
||||
|
||||
static int option_integer_arg(const char *zVal){
|
||||
return atoi(zVal);
|
||||
}
|
||||
|
||||
static void usage(char **argv){
|
||||
fprintf(stderr, "\n");
|
||||
fprintf(stderr, "Usage %s ?OPTIONS? DATABASE\n", argv[0]);
|
||||
fprintf(stderr, "\n");
|
||||
fprintf(stderr, "Options are:\n");
|
||||
fprintf(stderr, " -sql SQL (analyze SQL statements passed as argument)\n");
|
||||
fprintf(stderr, " -file FILE (read SQL statements from file FILE)\n");
|
||||
fprintf(stderr, " -verbose LEVEL (integer verbosity level. default 1)\n");
|
||||
fprintf(stderr, " -sample PERCENT (percent of db to sample. default 100)\n");
|
||||
exit(-1);
|
||||
}
|
||||
|
||||
static int readSqlFromFile(sqlite3expert *p, const char *zFile, char **pzErr){
|
||||
FILE *in = fopen(zFile, "rb");
|
||||
long nIn;
|
||||
size_t nRead;
|
||||
char *pBuf;
|
||||
int rc;
|
||||
if( in==0 ){
|
||||
*pzErr = sqlite3_mprintf("failed to open file %s\n", zFile);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
fseek(in, 0, SEEK_END);
|
||||
nIn = ftell(in);
|
||||
rewind(in);
|
||||
pBuf = sqlite3_malloc64( nIn+1 );
|
||||
nRead = fread(pBuf, nIn, 1, in);
|
||||
fclose(in);
|
||||
if( nRead!=1 ){
|
||||
sqlite3_free(pBuf);
|
||||
*pzErr = sqlite3_mprintf("failed to read file %s\n", zFile);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
pBuf[nIn] = 0;
|
||||
rc = sqlite3_expert_sql(p, pBuf, pzErr);
|
||||
sqlite3_free(pBuf);
|
||||
return rc;
|
||||
}
|
||||
|
||||
int main(int argc, char **argv){
|
||||
const char *zDb;
|
||||
int rc = 0;
|
||||
char *zErr = 0;
|
||||
int i;
|
||||
int iVerbose = 1; /* -verbose option */
|
||||
|
||||
sqlite3 *db = 0;
|
||||
sqlite3expert *p = 0;
|
||||
|
||||
if( argc<2 ) usage(argv);
|
||||
zDb = argv[argc-1];
|
||||
if( zDb[0]=='-' ) usage(argv);
|
||||
rc = sqlite3_open(zDb, &db);
|
||||
if( rc!=SQLITE_OK ){
|
||||
fprintf(stderr, "Cannot open db file: %s - %s\n", zDb, sqlite3_errmsg(db));
|
||||
exit(-2);
|
||||
}
|
||||
|
||||
p = sqlite3_expert_new(db, &zErr);
|
||||
if( p==0 ){
|
||||
fprintf(stderr, "Cannot run analysis: %s\n", zErr);
|
||||
rc = 1;
|
||||
}else{
|
||||
for(i=1; i<(argc-1); i++){
|
||||
char *zArg = argv[i];
|
||||
int nArg;
|
||||
if( zArg[0]=='-' && zArg[1]=='-' && zArg[2]!=0 ) zArg++;
|
||||
nArg = (int)strlen(zArg);
|
||||
if( nArg>=2 && 0==sqlite3_strnicmp(zArg, "-file", nArg) ){
|
||||
if( ++i==(argc-1) ) option_requires_argument("-file");
|
||||
rc = readSqlFromFile(p, argv[i], &zErr);
|
||||
}
|
||||
|
||||
else if( nArg>=3 && 0==sqlite3_strnicmp(zArg, "-sql", nArg) ){
|
||||
if( ++i==(argc-1) ) option_requires_argument("-sql");
|
||||
rc = sqlite3_expert_sql(p, argv[i], &zErr);
|
||||
}
|
||||
|
||||
else if( nArg>=3 && 0==sqlite3_strnicmp(zArg, "-sample", nArg) ){
|
||||
int iSample;
|
||||
if( ++i==(argc-1) ) option_requires_argument("-sample");
|
||||
iSample = option_integer_arg(argv[i]);
|
||||
sqlite3_expert_config(p, EXPERT_CONFIG_SAMPLE, iSample);
|
||||
}
|
||||
|
||||
else if( nArg>=2 && 0==sqlite3_strnicmp(zArg, "-verbose", nArg) ){
|
||||
if( ++i==(argc-1) ) option_requires_argument("-verbose");
|
||||
iVerbose = option_integer_arg(argv[i]);
|
||||
}
|
||||
|
||||
else{
|
||||
usage(argv);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = sqlite3_expert_analyze(p, &zErr);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
int nQuery = sqlite3_expert_count(p);
|
||||
if( iVerbose>0 ){
|
||||
const char *zCand = sqlite3_expert_report(p,0,EXPERT_REPORT_CANDIDATES);
|
||||
fprintf(stdout, "-- Candidates -------------------------------\n");
|
||||
fprintf(stdout, "%s\n", zCand);
|
||||
}
|
||||
for(i=0; i<nQuery; i++){
|
||||
const char *zSql = sqlite3_expert_report(p, i, EXPERT_REPORT_SQL);
|
||||
const char *zIdx = sqlite3_expert_report(p, i, EXPERT_REPORT_INDEXES);
|
||||
const char *zEQP = sqlite3_expert_report(p, i, EXPERT_REPORT_PLAN);
|
||||
if( zIdx==0 ) zIdx = "(no new indexes)\n";
|
||||
if( iVerbose>0 ){
|
||||
fprintf(stdout, "-- Query %d ----------------------------------\n",i+1);
|
||||
fprintf(stdout, "%s\n\n", zSql);
|
||||
}
|
||||
fprintf(stdout, "%s\n%s\n", zIdx, zEQP);
|
||||
}
|
||||
}else{
|
||||
fprintf(stderr, "Error: %s\n", zErr ? zErr : "?");
|
||||
}
|
||||
|
||||
sqlite3_expert_destroy(p);
|
||||
sqlite3_free(zErr);
|
||||
return rc;
|
||||
}
|
||||
@@ -1,384 +0,0 @@
|
||||
# 2009 Nov 11
|
||||
#
|
||||
# The author disclaims copyright to this source code. In place of
|
||||
# a legal notice, here is a blessing:
|
||||
#
|
||||
# May you do good and not evil.
|
||||
# May you find forgiveness for yourself and forgive others.
|
||||
# May you share freely, never taking more than you give.
|
||||
#
|
||||
#***********************************************************************
|
||||
#
|
||||
# The focus of this file is testing the CLI shell tool. Specifically,
|
||||
# the ".recommend" command.
|
||||
#
|
||||
#
|
||||
|
||||
# Test plan:
|
||||
#
|
||||
#
|
||||
if {![info exists testdir]} {
|
||||
set testdir [file join [file dirname [info script]] .. .. test]
|
||||
}
|
||||
source $testdir/tester.tcl
|
||||
set testprefix expert1
|
||||
|
||||
if {[info commands sqlite3_expert_new]==""} {
|
||||
finish_test
|
||||
return
|
||||
}
|
||||
|
||||
set CLI [test_binary_name sqlite3]
|
||||
set CMD [test_binary_name sqlite3_expert]
|
||||
|
||||
proc squish {txt} {
|
||||
regsub -all {[[:space:]]+} $txt { }
|
||||
}
|
||||
|
||||
proc do_setup_rec_test {tn setup sql res} {
|
||||
reset_db
|
||||
db eval $setup
|
||||
uplevel [list do_rec_test $tn $sql $res]
|
||||
}
|
||||
|
||||
foreach {tn setup} {
|
||||
1 {
|
||||
if {![file executable $CMD]} { continue }
|
||||
|
||||
proc do_rec_test {tn sql res} {
|
||||
set res [squish [string trim $res]]
|
||||
set tst [subst -nocommands {
|
||||
squish [string trim [exec $::CMD -verbose 0 -sql {$sql;} test.db]]
|
||||
}]
|
||||
uplevel [list do_test $tn $tst $res]
|
||||
}
|
||||
}
|
||||
2 {
|
||||
if {[info commands sqlite3_expert_new]==""} { continue }
|
||||
|
||||
proc do_rec_test {tn sql res} {
|
||||
set expert [sqlite3_expert_new db]
|
||||
$expert sql $sql
|
||||
$expert analyze
|
||||
|
||||
set result [list]
|
||||
for {set i 0} {$i < [$expert count]} {incr i} {
|
||||
set idx [string trim [$expert report $i indexes]]
|
||||
if {$idx==""} {set idx "(no new indexes)"}
|
||||
lappend result $idx
|
||||
lappend result [string trim [$expert report $i plan]]
|
||||
}
|
||||
|
||||
$expert destroy
|
||||
|
||||
set tst [subst -nocommands {set {} [squish [join {$result}]]}]
|
||||
uplevel [list do_test $tn $tst [string trim [squish $res]]]
|
||||
}
|
||||
}
|
||||
3 {
|
||||
if {![file executable $CLI]} { continue }
|
||||
|
||||
proc do_rec_test {tn sql res} {
|
||||
set res [squish [string trim $res]]
|
||||
set tst [subst -nocommands {
|
||||
squish [string trim [exec $::CLI test.db ".expert" {$sql;}]]
|
||||
}]
|
||||
uplevel [list do_test $tn $tst $res]
|
||||
}
|
||||
}
|
||||
} {
|
||||
|
||||
eval $setup
|
||||
|
||||
|
||||
do_setup_rec_test $tn.1 { CREATE TABLE t1(a, b, c) } {
|
||||
SELECT * FROM t1
|
||||
} {
|
||||
(no new indexes)
|
||||
SCAN TABLE t1
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.2 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT * FROM t1 WHERE b>?;
|
||||
} {
|
||||
CREATE INDEX t1_idx_00000062 ON t1(b);
|
||||
SEARCH TABLE t1 USING INDEX t1_idx_00000062 (b>?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.3 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT * FROM t1 WHERE b COLLATE nocase BETWEEN ? AND ?
|
||||
} {
|
||||
CREATE INDEX t1_idx_3e094c27 ON t1(b COLLATE NOCASE);
|
||||
SEARCH TABLE t1 USING INDEX t1_idx_3e094c27 (b>? AND b<?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.4 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT a FROM t1 ORDER BY b;
|
||||
} {
|
||||
CREATE INDEX t1_idx_00000062 ON t1(b);
|
||||
SCAN TABLE t1 USING INDEX t1_idx_00000062
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.5 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT a FROM t1 WHERE a=? ORDER BY b;
|
||||
} {
|
||||
CREATE INDEX t1_idx_000123a7 ON t1(a, b);
|
||||
SEARCH TABLE t1 USING COVERING INDEX t1_idx_000123a7 (a=?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.6 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT min(a) FROM t1
|
||||
} {
|
||||
CREATE INDEX t1_idx_00000061 ON t1(a);
|
||||
SEARCH TABLE t1 USING COVERING INDEX t1_idx_00000061
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.7 {
|
||||
CREATE TABLE t1(a, b, c);
|
||||
} {
|
||||
SELECT * FROM t1 ORDER BY a, b, c;
|
||||
} {
|
||||
CREATE INDEX t1_idx_033e95fe ON t1(a, b, c);
|
||||
SCAN TABLE t1 USING COVERING INDEX t1_idx_033e95fe
|
||||
}
|
||||
|
||||
#do_setup_rec_test $tn.1.8 {
|
||||
# CREATE TABLE t1(a, b, c);
|
||||
#} {
|
||||
# SELECT * FROM t1 ORDER BY a ASC, b COLLATE nocase DESC, c ASC;
|
||||
#} {
|
||||
# CREATE INDEX t1_idx_5be6e222 ON t1(a, b COLLATE NOCASE DESC, c);
|
||||
# 0|0|0|SCAN TABLE t1 USING COVERING INDEX t1_idx_5be6e222
|
||||
#}
|
||||
|
||||
do_setup_rec_test $tn.8.1 {
|
||||
CREATE TABLE t1(a COLLATE NOCase, b, c);
|
||||
} {
|
||||
SELECT * FROM t1 WHERE a=?
|
||||
} {
|
||||
CREATE INDEX t1_idx_00000061 ON t1(a);
|
||||
SEARCH TABLE t1 USING INDEX t1_idx_00000061 (a=?)
|
||||
}
|
||||
do_setup_rec_test $tn.8.2 {
|
||||
CREATE TABLE t1(a, b COLLATE nocase, c);
|
||||
} {
|
||||
SELECT * FROM t1 ORDER BY a ASC, b DESC, c ASC;
|
||||
} {
|
||||
CREATE INDEX t1_idx_5cb97285 ON t1(a, b DESC, c);
|
||||
SCAN TABLE t1 USING COVERING INDEX t1_idx_5cb97285
|
||||
}
|
||||
|
||||
|
||||
# Tables with names that require quotes.
|
||||
#
|
||||
do_setup_rec_test $tn.9.1 {
|
||||
CREATE TABLE "t t"(a, b, c);
|
||||
} {
|
||||
SELECT * FROM "t t" WHERE a=?
|
||||
} {
|
||||
CREATE INDEX 't t_idx_00000061' ON 't t'(a);
|
||||
SEARCH TABLE t t USING INDEX t t_idx_00000061 (a=?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.9.2 {
|
||||
CREATE TABLE "t t"(a, b, c);
|
||||
} {
|
||||
SELECT * FROM "t t" WHERE b BETWEEN ? AND ?
|
||||
} {
|
||||
CREATE INDEX 't t_idx_00000062' ON 't t'(b);
|
||||
SEARCH TABLE t t USING INDEX t t_idx_00000062 (b>? AND b<?)
|
||||
}
|
||||
|
||||
# Columns with names that require quotes.
|
||||
#
|
||||
do_setup_rec_test $tn.10.1 {
|
||||
CREATE TABLE t3(a, "b b", c);
|
||||
} {
|
||||
SELECT * FROM t3 WHERE "b b" = ?
|
||||
} {
|
||||
CREATE INDEX t3_idx_00050c52 ON t3('b b');
|
||||
SEARCH TABLE t3 USING INDEX t3_idx_00050c52 (b b=?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.10.2 {
|
||||
CREATE TABLE t3(a, "b b", c);
|
||||
} {
|
||||
SELECT * FROM t3 ORDER BY "b b"
|
||||
} {
|
||||
CREATE INDEX t3_idx_00050c52 ON t3('b b');
|
||||
SCAN TABLE t3 USING INDEX t3_idx_00050c52
|
||||
}
|
||||
|
||||
# Transitive constraints
|
||||
#
|
||||
do_setup_rec_test $tn.11.1 {
|
||||
CREATE TABLE t5(a, b);
|
||||
CREATE TABLE t6(c, d);
|
||||
} {
|
||||
SELECT * FROM t5, t6 WHERE a=? AND b=c AND c=?
|
||||
} {
|
||||
CREATE INDEX t5_idx_000123a7 ON t5(a, b);
|
||||
CREATE INDEX t6_idx_00000063 ON t6(c);
|
||||
SEARCH TABLE t6 USING INDEX t6_idx_00000063 (c=?)
|
||||
SEARCH TABLE t5 USING COVERING INDEX t5_idx_000123a7 (a=? AND b=?)
|
||||
}
|
||||
|
||||
# OR terms.
|
||||
#
|
||||
do_setup_rec_test $tn.12.1 {
|
||||
CREATE TABLE t7(a, b);
|
||||
} {
|
||||
SELECT * FROM t7 WHERE a=? OR b=?
|
||||
} {
|
||||
CREATE INDEX t7_idx_00000062 ON t7(b);
|
||||
CREATE INDEX t7_idx_00000061 ON t7(a);
|
||||
MULTI-INDEX OR
|
||||
INDEX 1
|
||||
SEARCH TABLE t7 USING INDEX t7_idx_00000061 (a=?)
|
||||
INDEX 2
|
||||
SEARCH TABLE t7 USING INDEX t7_idx_00000062 (b=?)
|
||||
}
|
||||
|
||||
# rowid terms.
|
||||
#
|
||||
do_setup_rec_test $tn.13.1 {
|
||||
CREATE TABLE t8(a, b);
|
||||
} {
|
||||
SELECT * FROM t8 WHERE rowid=?
|
||||
} {
|
||||
(no new indexes)
|
||||
SEARCH TABLE t8 USING INTEGER PRIMARY KEY (rowid=?)
|
||||
}
|
||||
do_setup_rec_test $tn.13.2 {
|
||||
CREATE TABLE t8(a, b);
|
||||
} {
|
||||
SELECT * FROM t8 ORDER BY rowid
|
||||
} {
|
||||
(no new indexes)
|
||||
SCAN TABLE t8
|
||||
}
|
||||
do_setup_rec_test $tn.13.3 {
|
||||
CREATE TABLE t8(a, b);
|
||||
} {
|
||||
SELECT * FROM t8 WHERE a=? ORDER BY rowid
|
||||
} {
|
||||
CREATE INDEX t8_idx_00000061 ON t8(a);
|
||||
SEARCH TABLE t8 USING INDEX t8_idx_00000061 (a=?)
|
||||
}
|
||||
|
||||
# Triggers
|
||||
#
|
||||
do_setup_rec_test $tn.14 {
|
||||
CREATE TABLE t9(a, b, c);
|
||||
CREATE TABLE t10(a, b, c);
|
||||
CREATE TRIGGER t9t AFTER INSERT ON t9 BEGIN
|
||||
UPDATE t10 SET a=new.a WHERE b = new.b;
|
||||
END;
|
||||
} {
|
||||
INSERT INTO t9 VALUES(?, ?, ?);
|
||||
} {
|
||||
CREATE INDEX t10_idx_00000062 ON t10(b);
|
||||
SEARCH TABLE t10 USING INDEX t10_idx_00000062 (b=?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.15 {
|
||||
CREATE TABLE t1(a, b);
|
||||
CREATE TABLE t2(c, d);
|
||||
|
||||
WITH s(i) AS ( VALUES(1) UNION ALL SELECT i+1 FROM s WHERE i<100)
|
||||
INSERT INTO t1 SELECT (i-1)/50, (i-1)/20 FROM s;
|
||||
|
||||
WITH s(i) AS ( VALUES(1) UNION ALL SELECT i+1 FROM s WHERE i<100)
|
||||
INSERT INTO t2 SELECT (i-1)/20, (i-1)/5 FROM s;
|
||||
} {
|
||||
SELECT * FROM t2, t1 WHERE b=? AND d=? AND t2.rowid=t1.rowid
|
||||
} {
|
||||
CREATE INDEX t2_idx_00000064 ON t2(d);
|
||||
SEARCH TABLE t2 USING INDEX t2_idx_00000064 (d=?)
|
||||
SEARCH TABLE t1 USING INTEGER PRIMARY KEY (rowid=?)
|
||||
}
|
||||
|
||||
do_setup_rec_test $tn.16 {
|
||||
CREATE TABLE t1(a, b);
|
||||
} {
|
||||
SELECT * FROM t1 WHERE b IS NOT NULL;
|
||||
} {
|
||||
(no new indexes)
|
||||
SCAN TABLE t1
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
proc do_candidates_test {tn sql res} {
|
||||
set res [squish [string trim $res]]
|
||||
|
||||
set expert [sqlite3_expert_new db]
|
||||
$expert sql $sql
|
||||
$expert analyze
|
||||
|
||||
set candidates [squish [string trim [$expert report 0 candidates]]]
|
||||
$expert destroy
|
||||
|
||||
uplevel [list do_test $tn [list set {} $candidates] $res]
|
||||
}
|
||||
|
||||
|
||||
reset_db
|
||||
do_execsql_test 4.0 {
|
||||
CREATE TABLE t1(a, b);
|
||||
CREATE TABLE t2(c, d);
|
||||
|
||||
WITH s(i) AS ( VALUES(1) UNION ALL SELECT i+1 FROM s WHERE i<100)
|
||||
INSERT INTO t1 SELECT (i-1)/50, (i-1)/20 FROM s;
|
||||
|
||||
WITH s(i) AS ( VALUES(1) UNION ALL SELECT i+1 FROM s WHERE i<100)
|
||||
INSERT INTO t2 SELECT (i-1)/20, (i-1)/5 FROM s;
|
||||
}
|
||||
do_candidates_test 4.1 {
|
||||
SELECT * FROM t1,t2 WHERE (b=? OR a=?) AND (c=? OR d=?)
|
||||
} {
|
||||
CREATE INDEX t1_idx_00000062 ON t1(b); -- stat1: 100 20
|
||||
CREATE INDEX t1_idx_00000061 ON t1(a); -- stat1: 100 50
|
||||
CREATE INDEX t2_idx_00000063 ON t2(c); -- stat1: 100 20
|
||||
CREATE INDEX t2_idx_00000064 ON t2(d); -- stat1: 100 5
|
||||
}
|
||||
|
||||
do_candidates_test 4.2 {
|
||||
SELECT * FROM t1,t2 WHERE a=? AND b=? AND c=? AND d=?
|
||||
} {
|
||||
CREATE INDEX t1_idx_000123a7 ON t1(a, b); -- stat1: 100 50 17
|
||||
CREATE INDEX t2_idx_0001295b ON t2(c, d); -- stat1: 100 20 5
|
||||
}
|
||||
|
||||
do_execsql_test 4.3 {
|
||||
CREATE INDEX t1_idx_00000061 ON t1(a); -- stat1: 100 50
|
||||
CREATE INDEX t1_idx_00000062 ON t1(b); -- stat1: 100 20
|
||||
CREATE INDEX t1_idx_000123a7 ON t1(a, b); -- stat1: 100 50 16
|
||||
|
||||
CREATE INDEX t2_idx_00000063 ON t2(c); -- stat1: 100 20
|
||||
CREATE INDEX t2_idx_00000064 ON t2(d); -- stat1: 100 5
|
||||
CREATE INDEX t2_idx_0001295b ON t2(c, d); -- stat1: 100 20 5
|
||||
|
||||
ANALYZE;
|
||||
SELECT * FROM sqlite_stat1 ORDER BY 1, 2;
|
||||
} {
|
||||
t1 t1_idx_00000061 {100 50}
|
||||
t1 t1_idx_00000062 {100 20}
|
||||
t1 t1_idx_000123a7 {100 50 17}
|
||||
t2 t2_idx_00000063 {100 20}
|
||||
t2 t2_idx_00000064 {100 5}
|
||||
t2 t2_idx_0001295b {100 20 5}
|
||||
}
|
||||
|
||||
|
||||
finish_test
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,168 +0,0 @@
|
||||
/*
|
||||
** 2017 April 07
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
*/
|
||||
|
||||
|
||||
#include "sqlite3.h"
|
||||
|
||||
typedef struct sqlite3expert sqlite3expert;
|
||||
|
||||
/*
|
||||
** Create a new sqlite3expert object.
|
||||
**
|
||||
** If successful, a pointer to the new object is returned and (*pzErr) set
|
||||
** to NULL. Or, if an error occurs, NULL is returned and (*pzErr) set to
|
||||
** an English-language error message. In this case it is the responsibility
|
||||
** of the caller to eventually free the error message buffer using
|
||||
** sqlite3_free().
|
||||
*/
|
||||
sqlite3expert *sqlite3_expert_new(sqlite3 *db, char **pzErr);
|
||||
|
||||
/*
|
||||
** Configure an sqlite3expert object.
|
||||
**
|
||||
** EXPERT_CONFIG_SAMPLE:
|
||||
** By default, sqlite3_expert_analyze() generates sqlite_stat1 data for
|
||||
** each candidate index. This involves scanning and sorting the entire
|
||||
** contents of each user database table once for each candidate index
|
||||
** associated with the table. For large databases, this can be
|
||||
** prohibitively slow. This option allows the sqlite3expert object to
|
||||
** be configured so that sqlite_stat1 data is instead generated based on a
|
||||
** subset of each table, or so that no sqlite_stat1 data is used at all.
|
||||
**
|
||||
** A single integer argument is passed to this option. If the value is less
|
||||
** than or equal to zero, then no sqlite_stat1 data is generated or used by
|
||||
** the analysis - indexes are recommended based on the database schema only.
|
||||
** Or, if the value is 100 or greater, complete sqlite_stat1 data is
|
||||
** generated for each candidate index (this is the default). Finally, if the
|
||||
** value falls between 0 and 100, then it represents the percentage of user
|
||||
** table rows that should be considered when generating sqlite_stat1 data.
|
||||
**
|
||||
** Examples:
|
||||
**
|
||||
** // Do not generate any sqlite_stat1 data
|
||||
** sqlite3_expert_config(pExpert, EXPERT_CONFIG_SAMPLE, 0);
|
||||
**
|
||||
** // Generate sqlite_stat1 data based on 10% of the rows in each table.
|
||||
** sqlite3_expert_config(pExpert, EXPERT_CONFIG_SAMPLE, 10);
|
||||
*/
|
||||
int sqlite3_expert_config(sqlite3expert *p, int op, ...);
|
||||
|
||||
#define EXPERT_CONFIG_SAMPLE 1 /* int */
|
||||
|
||||
/*
|
||||
** Specify zero or more SQL statements to be included in the analysis.
|
||||
**
|
||||
** Buffer zSql must contain zero or more complete SQL statements. This
|
||||
** function parses all statements contained in the buffer and adds them
|
||||
** to the internal list of statements to analyze. If successful, SQLITE_OK
|
||||
** is returned and (*pzErr) set to NULL. Or, if an error occurs - for example
|
||||
** due to a error in the SQL - an SQLite error code is returned and (*pzErr)
|
||||
** may be set to point to an English language error message. In this case
|
||||
** the caller is responsible for eventually freeing the error message buffer
|
||||
** using sqlite3_free().
|
||||
**
|
||||
** If an error does occur while processing one of the statements in the
|
||||
** buffer passed as the second argument, none of the statements in the
|
||||
** buffer are added to the analysis.
|
||||
**
|
||||
** This function must be called before sqlite3_expert_analyze(). If a call
|
||||
** to this function is made on an sqlite3expert object that has already
|
||||
** been passed to sqlite3_expert_analyze() SQLITE_MISUSE is returned
|
||||
** immediately and no statements are added to the analysis.
|
||||
*/
|
||||
int sqlite3_expert_sql(
|
||||
sqlite3expert *p, /* From a successful sqlite3_expert_new() */
|
||||
const char *zSql, /* SQL statement(s) to add */
|
||||
char **pzErr /* OUT: Error message (if any) */
|
||||
);
|
||||
|
||||
|
||||
/*
|
||||
** This function is called after the sqlite3expert object has been configured
|
||||
** with all SQL statements using sqlite3_expert_sql() to actually perform
|
||||
** the analysis. Once this function has been called, it is not possible to
|
||||
** add further SQL statements to the analysis.
|
||||
**
|
||||
** If successful, SQLITE_OK is returned and (*pzErr) is set to NULL. Or, if
|
||||
** an error occurs, an SQLite error code is returned and (*pzErr) set to
|
||||
** point to a buffer containing an English language error message. In this
|
||||
** case it is the responsibility of the caller to eventually free the buffer
|
||||
** using sqlite3_free().
|
||||
**
|
||||
** If an error does occur within this function, the sqlite3expert object
|
||||
** is no longer useful for any purpose. At that point it is no longer
|
||||
** possible to add further SQL statements to the object or to re-attempt
|
||||
** the analysis. The sqlite3expert object must still be freed using a call
|
||||
** sqlite3_expert_destroy().
|
||||
*/
|
||||
int sqlite3_expert_analyze(sqlite3expert *p, char **pzErr);
|
||||
|
||||
/*
|
||||
** Return the total number of statements loaded using sqlite3_expert_sql().
|
||||
** The total number of SQL statements may be different from the total number
|
||||
** to calls to sqlite3_expert_sql().
|
||||
*/
|
||||
int sqlite3_expert_count(sqlite3expert*);
|
||||
|
||||
/*
|
||||
** Return a component of the report.
|
||||
**
|
||||
** This function is called after sqlite3_expert_analyze() to extract the
|
||||
** results of the analysis. Each call to this function returns either a
|
||||
** NULL pointer or a pointer to a buffer containing a nul-terminated string.
|
||||
** The value passed as the third argument must be one of the EXPERT_REPORT_*
|
||||
** #define constants defined below.
|
||||
**
|
||||
** For some EXPERT_REPORT_* parameters, the buffer returned contains
|
||||
** information relating to a specific SQL statement. In these cases that
|
||||
** SQL statement is identified by the value passed as the second argument.
|
||||
** SQL statements are numbered from 0 in the order in which they are parsed.
|
||||
** If an out-of-range value (less than zero or equal to or greater than the
|
||||
** value returned by sqlite3_expert_count()) is passed as the second argument
|
||||
** along with such an EXPERT_REPORT_* parameter, NULL is always returned.
|
||||
**
|
||||
** EXPERT_REPORT_SQL:
|
||||
** Return the text of SQL statement iStmt.
|
||||
**
|
||||
** EXPERT_REPORT_INDEXES:
|
||||
** Return a buffer containing the CREATE INDEX statements for all recommended
|
||||
** indexes for statement iStmt. If there are no new recommeded indexes, NULL
|
||||
** is returned.
|
||||
**
|
||||
** EXPERT_REPORT_PLAN:
|
||||
** Return a buffer containing the EXPLAIN QUERY PLAN output for SQL query
|
||||
** iStmt after the proposed indexes have been added to the database schema.
|
||||
**
|
||||
** EXPERT_REPORT_CANDIDATES:
|
||||
** Return a pointer to a buffer containing the CREATE INDEX statements
|
||||
** for all indexes that were tested (for all SQL statements). The iStmt
|
||||
** parameter is ignored for EXPERT_REPORT_CANDIDATES calls.
|
||||
*/
|
||||
const char *sqlite3_expert_report(sqlite3expert*, int iStmt, int eReport);
|
||||
|
||||
/*
|
||||
** Values for the third argument passed to sqlite3_expert_report().
|
||||
*/
|
||||
#define EXPERT_REPORT_SQL 1
|
||||
#define EXPERT_REPORT_INDEXES 2
|
||||
#define EXPERT_REPORT_PLAN 3
|
||||
#define EXPERT_REPORT_CANDIDATES 4
|
||||
|
||||
/*
|
||||
** Free an (sqlite3expert*) handle and all associated resources. There
|
||||
** should be one call to this function for each successful call to
|
||||
** sqlite3-expert_new().
|
||||
*/
|
||||
void sqlite3_expert_destroy(sqlite3expert*);
|
||||
|
||||
|
||||
@@ -1,220 +0,0 @@
|
||||
/*
|
||||
** 2017 April 07
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
*/
|
||||
|
||||
#if defined(SQLITE_TEST)
|
||||
|
||||
#include "sqlite3expert.h"
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
|
||||
#if defined(INCLUDE_SQLITE_TCL_H)
|
||||
# include "sqlite_tcl.h"
|
||||
#else
|
||||
# include "tcl.h"
|
||||
# ifndef SQLITE_TCLAPI
|
||||
# define SQLITE_TCLAPI
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#ifndef SQLITE_OMIT_VIRTUALTABLE
|
||||
|
||||
/*
|
||||
** Extract an sqlite3* db handle from the object passed as the second
|
||||
** argument. If successful, set *pDb to point to the db handle and return
|
||||
** TCL_OK. Otherwise, return TCL_ERROR.
|
||||
*/
|
||||
static int dbHandleFromObj(Tcl_Interp *interp, Tcl_Obj *pObj, sqlite3 **pDb){
|
||||
Tcl_CmdInfo info;
|
||||
if( 0==Tcl_GetCommandInfo(interp, Tcl_GetString(pObj), &info) ){
|
||||
Tcl_AppendResult(interp, "no such handle: ", Tcl_GetString(pObj), 0);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
*pDb = *(sqlite3 **)info.objClientData;
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Tclcmd: $expert sql SQL
|
||||
** $expert analyze
|
||||
** $expert count
|
||||
** $expert report STMT EREPORT
|
||||
** $expert destroy
|
||||
*/
|
||||
static int SQLITE_TCLAPI testExpertCmd(
|
||||
void *clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
sqlite3expert *pExpert = (sqlite3expert*)clientData;
|
||||
struct Subcmd {
|
||||
const char *zSub;
|
||||
int nArg;
|
||||
const char *zMsg;
|
||||
} aSub[] = {
|
||||
{ "sql", 1, "TABLE", }, /* 0 */
|
||||
{ "analyze", 0, "", }, /* 1 */
|
||||
{ "count", 0, "", }, /* 2 */
|
||||
{ "report", 2, "STMT EREPORT", }, /* 3 */
|
||||
{ "destroy", 0, "", }, /* 4 */
|
||||
{ 0 }
|
||||
};
|
||||
int iSub;
|
||||
int rc = TCL_OK;
|
||||
char *zErr = 0;
|
||||
|
||||
if( objc<2 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "SUBCOMMAND ...");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
rc = Tcl_GetIndexFromObjStruct(interp,
|
||||
objv[1], aSub, sizeof(aSub[0]), "sub-command", 0, &iSub
|
||||
);
|
||||
if( rc!=TCL_OK ) return rc;
|
||||
if( objc!=2+aSub[iSub].nArg ){
|
||||
Tcl_WrongNumArgs(interp, 2, objv, aSub[iSub].zMsg);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
switch( iSub ){
|
||||
case 0: { /* sql */
|
||||
char *zArg = Tcl_GetString(objv[2]);
|
||||
rc = sqlite3_expert_sql(pExpert, zArg, &zErr);
|
||||
break;
|
||||
}
|
||||
|
||||
case 1: { /* analyze */
|
||||
rc = sqlite3_expert_analyze(pExpert, &zErr);
|
||||
break;
|
||||
}
|
||||
|
||||
case 2: { /* count */
|
||||
int n = sqlite3_expert_count(pExpert);
|
||||
Tcl_SetObjResult(interp, Tcl_NewIntObj(n));
|
||||
break;
|
||||
}
|
||||
|
||||
case 3: { /* report */
|
||||
const char *aEnum[] = {
|
||||
"sql", "indexes", "plan", "candidates", 0
|
||||
};
|
||||
int iEnum;
|
||||
int iStmt;
|
||||
const char *zReport;
|
||||
|
||||
if( Tcl_GetIntFromObj(interp, objv[2], &iStmt)
|
||||
|| Tcl_GetIndexFromObj(interp, objv[3], aEnum, "report", 0, &iEnum)
|
||||
){
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
assert( EXPERT_REPORT_SQL==1 );
|
||||
assert( EXPERT_REPORT_INDEXES==2 );
|
||||
assert( EXPERT_REPORT_PLAN==3 );
|
||||
assert( EXPERT_REPORT_CANDIDATES==4 );
|
||||
zReport = sqlite3_expert_report(pExpert, iStmt, 1+iEnum);
|
||||
Tcl_SetObjResult(interp, Tcl_NewStringObj(zReport, -1));
|
||||
break;
|
||||
}
|
||||
|
||||
default: /* destroy */
|
||||
assert( iSub==4 );
|
||||
Tcl_DeleteCommand(interp, Tcl_GetString(objv[0]));
|
||||
break;
|
||||
}
|
||||
|
||||
if( rc!=TCL_OK ){
|
||||
if( zErr ){
|
||||
Tcl_SetObjResult(interp, Tcl_NewStringObj(zErr, -1));
|
||||
}else{
|
||||
extern const char *sqlite3ErrName(int);
|
||||
Tcl_SetObjResult(interp, Tcl_NewStringObj(sqlite3ErrName(rc), -1));
|
||||
}
|
||||
}
|
||||
sqlite3_free(zErr);
|
||||
return rc;
|
||||
}
|
||||
|
||||
static void SQLITE_TCLAPI testExpertDel(void *clientData){
|
||||
sqlite3expert *pExpert = (sqlite3expert*)clientData;
|
||||
sqlite3_expert_destroy(pExpert);
|
||||
}
|
||||
|
||||
/*
|
||||
** sqlite3_expert_new DB
|
||||
*/
|
||||
static int SQLITE_TCLAPI test_sqlite3_expert_new(
|
||||
void * clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
static int iCmd = 0;
|
||||
sqlite3 *db;
|
||||
char *zCmd = 0;
|
||||
char *zErr = 0;
|
||||
sqlite3expert *pExpert;
|
||||
int rc = TCL_OK;
|
||||
|
||||
if( objc!=2 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "DB");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
if( dbHandleFromObj(interp, objv[1], &db) ){
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
zCmd = sqlite3_mprintf("sqlite3expert%d", ++iCmd);
|
||||
if( zCmd==0 ){
|
||||
Tcl_AppendResult(interp, "out of memory", (char*)0);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
pExpert = sqlite3_expert_new(db, &zErr);
|
||||
if( pExpert==0 ){
|
||||
Tcl_AppendResult(interp, zErr, (char*)0);
|
||||
rc = TCL_ERROR;
|
||||
}else{
|
||||
void *p = (void*)pExpert;
|
||||
Tcl_CreateObjCommand(interp, zCmd, testExpertCmd, p, testExpertDel);
|
||||
Tcl_SetObjResult(interp, Tcl_NewStringObj(zCmd, -1));
|
||||
}
|
||||
|
||||
sqlite3_free(zCmd);
|
||||
sqlite3_free(zErr);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* ifndef SQLITE_OMIT_VIRTUALTABLE */
|
||||
|
||||
int TestExpert_Init(Tcl_Interp *interp){
|
||||
#ifndef SQLITE_OMIT_VIRTUALTABLE
|
||||
struct Cmd {
|
||||
const char *zCmd;
|
||||
Tcl_ObjCmdProc *xProc;
|
||||
} aCmd[] = {
|
||||
{ "sqlite3_expert_new", test_sqlite3_expert_new },
|
||||
};
|
||||
int i;
|
||||
|
||||
for(i=0; i<sizeof(aCmd)/sizeof(struct Cmd); i++){
|
||||
struct Cmd *p = &aCmd[i];
|
||||
Tcl_CreateObjCommand(interp, p->zCmd, p->xProc, 0, 0);
|
||||
}
|
||||
#endif
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
#endif
|
||||
+1
-1
@@ -9,7 +9,7 @@
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
** This is the header file for the generic hash-table implementation
|
||||
** This is the header file for the generic hash-table implemenation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
|
||||
+5
-8
@@ -205,13 +205,13 @@ static int getVarint32(const char *p, int *pi){
|
||||
*/
|
||||
/* TODO(shess) Is __isascii() a portable version of (c&0x80)==0? */
|
||||
static int safe_isspace(char c){
|
||||
return (c&0x80)==0 ? isspace((unsigned char)c) : 0;
|
||||
return (c&0x80)==0 ? isspace(c) : 0;
|
||||
}
|
||||
static int safe_tolower(char c){
|
||||
return (c&0x80)==0 ? tolower((unsigned char)c) : c;
|
||||
return (c&0x80)==0 ? tolower(c) : c;
|
||||
}
|
||||
static int safe_isalnum(char c){
|
||||
return (c&0x80)==0 ? isalnum((unsigned char)c) : 0;
|
||||
return (c&0x80)==0 ? isalnum(c) : 0;
|
||||
}
|
||||
|
||||
typedef enum DocListType {
|
||||
@@ -3335,11 +3335,8 @@ int sqlite3Fts1Init(sqlite3 *db){
|
||||
}
|
||||
|
||||
#if !SQLITE_CORE
|
||||
#ifdef _WIN32
|
||||
__declspec(dllexport)
|
||||
#endif
|
||||
int sqlite3_fts1_init(sqlite3 *db, char **pzErrMsg,
|
||||
const sqlite3_api_routines *pApi){
|
||||
int sqlite3_extension_init(sqlite3 *db, char **pzErrMsg,
|
||||
const sqlite3_api_routines *pApi){
|
||||
SQLITE_EXTENSION_INIT2(pApi)
|
||||
return sqlite3Fts1Init(db);
|
||||
}
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
** This is the header file for the generic hash-table implementation
|
||||
** This is the header file for the generic hash-table implemenation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
|
||||
+7
-22
@@ -852,14 +852,8 @@ static void fulltext_vtab_destroy(fulltext_vtab *v){
|
||||
** argv[3] - tokenizer name (optional, a sensible default is provided)
|
||||
** argv[4..] - passed to tokenizer (optional based on tokenizer)
|
||||
**/
|
||||
static int fulltextConnect(
|
||||
sqlite3 *db,
|
||||
void *pAux,
|
||||
int argc,
|
||||
const char * const *argv,
|
||||
sqlite3_vtab **ppVTab,
|
||||
char **pzErr
|
||||
){
|
||||
static int fulltextConnect(sqlite3 *db, void *pAux, int argc, char **argv,
|
||||
sqlite3_vtab **ppVTab){
|
||||
int rc;
|
||||
fulltext_vtab *v;
|
||||
sqlite3_tokenizer_module *m = NULL;
|
||||
@@ -904,14 +898,8 @@ static int fulltextConnect(
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int fulltextCreate(
|
||||
sqlite3 *db,
|
||||
void *pAux,
|
||||
int argc,
|
||||
const char * const *argv,
|
||||
sqlite3_vtab **ppVTab,
|
||||
char **pzErr
|
||||
){
|
||||
static int fulltextCreate(sqlite3 *db, void *pAux, int argc, char **argv,
|
||||
sqlite3_vtab **ppVTab){
|
||||
int rc;
|
||||
assert( argc>=3 );
|
||||
|
||||
@@ -946,7 +934,7 @@ static int fulltextCreate(
|
||||
"create index %_index on %_term(term, first)");
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
|
||||
return fulltextConnect(db, pAux, argc, argv, ppVTab, pzErr);
|
||||
return fulltextConnect(db, pAux, argc, argv, ppVTab);
|
||||
}
|
||||
|
||||
/* Decide how to handle an SQL query.
|
||||
@@ -1500,11 +1488,8 @@ int fulltext_init(sqlite3 *db){
|
||||
}
|
||||
|
||||
#if !SQLITE_CORE
|
||||
#ifdef _WIN32
|
||||
__declspec(dllexport)
|
||||
#endif
|
||||
int sqlite3_fulltext_init(sqlite3 *db, char **pzErrMsg,
|
||||
const sqlite3_api_routines *pApi){
|
||||
int sqlite3_extension_init(sqlite3 *db, char **pzErrMsg,
|
||||
const sqlite3_api_routines *pApi){
|
||||
SQLITE_EXTENSION_INIT2(pApi)
|
||||
return fulltext_init(db);
|
||||
}
|
||||
|
||||
@@ -138,7 +138,7 @@ static int simpleNext(
|
||||
** case-insensitivity.
|
||||
*/
|
||||
char ch = c->pCurrent[ii];
|
||||
c->zToken[ii] = (unsigned char)ch<0x80 ? tolower((unsigned char)ch):ch;
|
||||
c->zToken[ii] = (unsigned char)ch<0x80 ? tolower(ch) : ch;
|
||||
}
|
||||
c->zToken[n] = '\0';
|
||||
*ppToken = c->zToken;
|
||||
|
||||
+4
-7
@@ -5051,7 +5051,7 @@ static int leavesReaderAtEnd(LeavesReader *pReader){
|
||||
** modification to control flow all over the place, though, so for now
|
||||
** just punt.
|
||||
**
|
||||
** Note the current system assumes that segment merges will run to
|
||||
** Note the the current system assumes that segment merges will run to
|
||||
** completion, which is why this particular probably hasn't arisen in
|
||||
** this case. Probably a brittle assumption.
|
||||
*/
|
||||
@@ -6779,7 +6779,7 @@ void sqlite3Fts2IcuTokenizerModule(sqlite3_tokenizer_module const**ppModule);
|
||||
int sqlite3Fts2InitHashTable(sqlite3 *, fts2Hash *, const char *);
|
||||
|
||||
/*
|
||||
** Initialize the fts2 extension. If this extension is built as part
|
||||
** Initialise the fts2 extension. If this extension is built as part
|
||||
** of the sqlite library, then this function is called directly by
|
||||
** SQLite. If fts2 is built as a dynamically loadable extension, this
|
||||
** function is called by the sqlite3_extension_init() entry point.
|
||||
@@ -6797,7 +6797,7 @@ int sqlite3Fts2Init(sqlite3 *db){
|
||||
sqlite3Fts2IcuTokenizerModule(&pIcu);
|
||||
#endif
|
||||
|
||||
/* Allocate and initialize the hash-table used to store tokenizers. */
|
||||
/* Allocate and initialise the hash-table used to store tokenizers. */
|
||||
pHash = sqlite3_malloc(sizeof(fts2Hash));
|
||||
if( !pHash ){
|
||||
rc = SQLITE_NOMEM;
|
||||
@@ -6844,10 +6844,7 @@ int sqlite3Fts2Init(sqlite3 *db){
|
||||
}
|
||||
|
||||
#if !SQLITE_CORE
|
||||
#ifdef _WIN32
|
||||
__declspec(dllexport)
|
||||
#endif
|
||||
int sqlite3_fts2_init(
|
||||
int sqlite3_extension_init(
|
||||
sqlite3 *db,
|
||||
char **pzErrMsg,
|
||||
const sqlite3_api_routines *pApi
|
||||
|
||||
@@ -30,8 +30,6 @@
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_hash.h"
|
||||
|
||||
/*
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
** This is the header file for the generic hash-table implementation
|
||||
** This is the header file for the generic hash-table implemenation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
|
||||
+2
-2
@@ -118,7 +118,7 @@ static int icuOpen(
|
||||
nChar = nInput+1;
|
||||
pCsr = (IcuCursor *)sqlite3_malloc(
|
||||
sizeof(IcuCursor) + /* IcuCursor */
|
||||
((nChar+3)&~3) * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
nChar * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
(nChar+1) * sizeof(int) /* IcuCursor.aOffset[] */
|
||||
);
|
||||
if( !pCsr ){
|
||||
@@ -126,7 +126,7 @@ static int icuOpen(
|
||||
}
|
||||
memset(pCsr, 0, sizeof(IcuCursor));
|
||||
pCsr->aChar = (UChar *)&pCsr[1];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[(nChar+3)&~3];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[nChar];
|
||||
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
|
||||
@@ -30,9 +30,6 @@
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_tokenizer.h"
|
||||
|
||||
/*
|
||||
|
||||
@@ -28,7 +28,7 @@
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
SQLITE_EXTENSION_INIT1
|
||||
|
||||
#include "fts2_hash.h"
|
||||
#include "fts2_tokenizer.h"
|
||||
@@ -99,11 +99,7 @@ static void scalarFunc(
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
#if defined(INCLUDE_SQLITE_TCL_H)
|
||||
# include "sqlite_tcl.h"
|
||||
#else
|
||||
# include "tcl.h"
|
||||
#endif
|
||||
#include <tcl.h>
|
||||
#include <string.h>
|
||||
|
||||
/*
|
||||
@@ -323,7 +319,7 @@ static void intTestFunc(
|
||||
/*
|
||||
** Set up SQL objects in database db used to access the contents of
|
||||
** the hash table pointed to by argument pHash. The hash table must
|
||||
** been initialized to use string keys, and to take a private copy
|
||||
** been initialised to use string keys, and to take a private copy
|
||||
** of the key when a value is inserted. i.e. by a call similar to:
|
||||
**
|
||||
** sqlite3Fts2HashInit(pHash, FTS2_HASH_STRING, 1);
|
||||
|
||||
@@ -70,7 +70,7 @@ struct sqlite3_tokenizer_module {
|
||||
** This method should return either SQLITE_OK (0), or an SQLite error
|
||||
** code. If SQLITE_OK is returned, then *ppTokenizer should be set
|
||||
** to point at the newly created tokenizer structure. The generic
|
||||
** sqlite3_tokenizer.pModule variable should not be initialized by
|
||||
** sqlite3_tokenizer.pModule variable should not be initialised by
|
||||
** this callback. The caller will do so.
|
||||
*/
|
||||
int (*xCreate)(
|
||||
|
||||
@@ -30,9 +30,6 @@
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_tokenizer.h"
|
||||
|
||||
typedef struct simple_tokenizer {
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
);
|
||||
|
||||
The built-in tokenizers (valid values to pass as <tokenizer name>) are
|
||||
"simple", "porter" and "unicode".
|
||||
"simple" and "porter".
|
||||
|
||||
<tokenizer-args> should consist of zero or more white-space separated
|
||||
arguments to pass to the selected tokenizer implementation. The
|
||||
|
||||
+380
-1290
File diff suppressed because it is too large
Load Diff
+28
-138
@@ -18,12 +18,6 @@
|
||||
# define NDEBUG 1
|
||||
#endif
|
||||
|
||||
/* FTS3/FTS4 require virtual tables */
|
||||
#ifdef SQLITE_OMIT_VIRTUALTABLE
|
||||
# undef SQLITE_ENABLE_FTS3
|
||||
# undef SQLITE_ENABLE_FTS4
|
||||
#endif
|
||||
|
||||
/*
|
||||
** FTS4 is really an extension for FTS3. It is enabled using the
|
||||
** SQLITE_ENABLE_FTS3 macro. But to avoid confusion we also all
|
||||
@@ -38,25 +32,13 @@
|
||||
/* If not building as part of the core, include sqlite3ext.h. */
|
||||
#ifndef SQLITE_CORE
|
||||
# include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
extern const sqlite3_api_routines *sqlite3_api;
|
||||
#endif
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "fts3_tokenizer.h"
|
||||
#include "fts3_hash.h"
|
||||
|
||||
/*
|
||||
** This constant determines the maximum depth of an FTS expression tree
|
||||
** that the library will create and use. FTS uses recursion to perform
|
||||
** various operations on the query tree, so the disadvantage of a large
|
||||
** limit is that it may allow very large queries to use large amounts
|
||||
** of stack space (perhaps causing a stack overflow).
|
||||
*/
|
||||
#ifndef SQLITE_FTS3_MAX_EXPR_DEPTH
|
||||
# define SQLITE_FTS3_MAX_EXPR_DEPTH 12
|
||||
#endif
|
||||
|
||||
|
||||
/*
|
||||
** This constant controls how often segments are merged. Once there are
|
||||
** FTS3_MERGE_COUNT segments of level N, they are merged into a single
|
||||
@@ -85,9 +67,6 @@ SQLITE_EXTENSION_INIT3
|
||||
#ifndef MIN
|
||||
# define MIN(x,y) ((x)<(y)?(x):(y))
|
||||
#endif
|
||||
#ifndef MAX
|
||||
# define MAX(x,y) ((x)>(y)?(x):(y))
|
||||
#endif
|
||||
|
||||
/*
|
||||
** Maximum length of a varint encoded integer. The varint format is different
|
||||
@@ -95,8 +74,6 @@ SQLITE_EXTENSION_INIT3
|
||||
*/
|
||||
#define FTS3_VARINT_MAX 10
|
||||
|
||||
#define FTS3_BUFFER_PADDING 8
|
||||
|
||||
/*
|
||||
** FTS4 virtual tables may maintain multiple indexes - one index of all terms
|
||||
** in the document set and zero or more prefix indexes. All indexes are stored
|
||||
@@ -129,18 +106,6 @@ SQLITE_EXTENSION_INIT3
|
||||
#define POS_COLUMN (1) /* Column-list terminator */
|
||||
#define POS_END (0) /* Position-list terminator */
|
||||
|
||||
/*
|
||||
** The assert_fts3_nc() macro is similar to the assert() macro, except that it
|
||||
** is used for assert() conditions that are true only if it can be
|
||||
** guranteed that the database is not corrupt.
|
||||
*/
|
||||
#if defined(SQLITE_DEBUG) || defined(SQLITE_TEST)
|
||||
extern int sqlite3_fts3_may_be_corrupt;
|
||||
# define assert_fts3_nc(x) assert(sqlite3_fts3_may_be_corrupt || (x))
|
||||
#else
|
||||
# define assert_fts3_nc(x) assert(x)
|
||||
#endif
|
||||
|
||||
/*
|
||||
** This section provides definitions to allow the
|
||||
** FTS3 extension to be compiled outside of the
|
||||
@@ -154,14 +119,9 @@ extern int sqlite3_fts3_may_be_corrupt;
|
||||
#ifdef SQLITE_COVERAGE_TEST
|
||||
# define ALWAYS(x) (1)
|
||||
# define NEVER(X) (0)
|
||||
#elif defined(SQLITE_DEBUG)
|
||||
# define ALWAYS(x) sqlite3Fts3Always((x)!=0)
|
||||
# define NEVER(x) sqlite3Fts3Never((x)!=0)
|
||||
int sqlite3Fts3Always(int b);
|
||||
int sqlite3Fts3Never(int b);
|
||||
#else
|
||||
# define ALWAYS(x) (x)
|
||||
# define NEVER(x) (x)
|
||||
# define NEVER(X) (x)
|
||||
#endif
|
||||
|
||||
/*
|
||||
@@ -171,7 +131,6 @@ typedef unsigned char u8; /* 1-byte (or larger) unsigned integer */
|
||||
typedef short int i16; /* 2-byte (or larger) signed integer */
|
||||
typedef unsigned int u32; /* 4-byte unsigned integer */
|
||||
typedef sqlite3_uint64 u64; /* 8-byte unsigned integer */
|
||||
typedef sqlite3_int64 i64; /* 8-byte signed integer */
|
||||
|
||||
/*
|
||||
** Macro used to suppress compiler warnings for unused parameters.
|
||||
@@ -217,8 +176,6 @@ typedef struct Fts3DeferredToken Fts3DeferredToken;
|
||||
typedef struct Fts3SegReader Fts3SegReader;
|
||||
typedef struct Fts3MultiSegReader Fts3MultiSegReader;
|
||||
|
||||
typedef struct MatchinfoBuffer MatchinfoBuffer;
|
||||
|
||||
/*
|
||||
** A connection to a fulltext index is an instance of the following
|
||||
** structure. The xCreate and xConnect methods create an instance
|
||||
@@ -233,48 +190,38 @@ struct Fts3Table {
|
||||
const char *zName; /* virtual table name */
|
||||
int nColumn; /* number of named columns in virtual table */
|
||||
char **azColumn; /* column names. malloced */
|
||||
u8 *abNotindexed; /* True for 'notindexed' columns */
|
||||
sqlite3_tokenizer *pTokenizer; /* tokenizer for inserts and queries */
|
||||
char *zContentTbl; /* content=xxx option, or NULL */
|
||||
char *zLanguageid; /* languageid=xxx option, or NULL */
|
||||
int nAutoincrmerge; /* Value configured by 'automerge' */
|
||||
u32 nLeafAdd; /* Number of leaf blocks added this trans */
|
||||
|
||||
/* Precompiled statements used by the implementation. Each of these
|
||||
** statements is run and reset within a single virtual table API call.
|
||||
*/
|
||||
sqlite3_stmt *aStmt[40];
|
||||
sqlite3_stmt *pSeekStmt; /* Cache for fts3CursorSeekStmt() */
|
||||
sqlite3_stmt *aStmt[27];
|
||||
|
||||
char *zReadExprlist;
|
||||
char *zWriteExprlist;
|
||||
|
||||
int nNodeSize; /* Soft limit for node size */
|
||||
u8 bFts4; /* True for FTS4, false for FTS3 */
|
||||
u8 bHasStat; /* True if %_stat table exists (2==unknown) */
|
||||
u8 bHasStat; /* True if %_stat table exists */
|
||||
u8 bHasDocsize; /* True if %_docsize table exists */
|
||||
u8 bDescIdx; /* True if doclists are in reverse order */
|
||||
u8 bIgnoreSavepoint; /* True to ignore xSavepoint invocations */
|
||||
int nPgsz; /* Page size for host database */
|
||||
char *zSegmentsTbl; /* Name of %_segments table */
|
||||
sqlite3_blob *pSegments; /* Blob handle open on %_segments table */
|
||||
|
||||
/*
|
||||
** The following array of hash tables is used to buffer pending index
|
||||
** updates during transactions. All pending updates buffered at any one
|
||||
** time must share a common language-id (see the FTS4 langid= feature).
|
||||
** The current language id is stored in variable iPrevLangid.
|
||||
/* TODO: Fix the first paragraph of this comment.
|
||||
**
|
||||
** The following hash table is used to buffer pending index updates during
|
||||
** transactions. Variable nPendingData estimates the memory size of the
|
||||
** pending data, including hash table overhead, but not malloc overhead.
|
||||
** When nPendingData exceeds nMaxPendingData, the buffer is flushed
|
||||
** automatically. Variable iPrevDocid is the docid of the most recently
|
||||
** inserted record.
|
||||
**
|
||||
** A single FTS4 table may have multiple full-text indexes. For each index
|
||||
** there is an entry in the aIndex[] array. Index 0 is an index of all the
|
||||
** terms that appear in the document set. Each subsequent index in aIndex[]
|
||||
** is an index of prefixes of a specific length.
|
||||
**
|
||||
** Variable nPendingData contains an estimate the memory consumed by the
|
||||
** pending data structures, including hash table overhead, but not including
|
||||
** malloc overhead. When nPendingData exceeds nMaxPendingData, all hash
|
||||
** tables are flushed to disk. Variable iPrevDocid is the docid of the most
|
||||
** recently inserted record.
|
||||
*/
|
||||
int nIndex; /* Size of aIndex[] */
|
||||
struct Fts3Index {
|
||||
@@ -284,24 +231,16 @@ struct Fts3Table {
|
||||
int nMaxPendingData; /* Max pending data before flush to disk */
|
||||
int nPendingData; /* Current bytes of pending data */
|
||||
sqlite_int64 iPrevDocid; /* Docid of most recently inserted document */
|
||||
int iPrevLangid; /* Langid of recently inserted document */
|
||||
int bPrevDelete; /* True if last operation was a delete */
|
||||
|
||||
#if defined(SQLITE_DEBUG) || defined(SQLITE_COVERAGE_TEST)
|
||||
/* State variables used for validating that the transaction control
|
||||
** methods of the virtual table are called at appropriate times. These
|
||||
** values do not contribute to FTS functionality; they are used for
|
||||
** verifying the operation of the SQLite core.
|
||||
** values do not contribution to the FTS computation; they are used for
|
||||
** verifying the SQLite core.
|
||||
*/
|
||||
int inTransaction; /* True after xBegin but before xCommit/xRollback */
|
||||
int mxSavepoint; /* Largest valid xSavepoint integer */
|
||||
#endif
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
/* True to disable the incremental doclist optimization. This is controled
|
||||
** by special insert command 'test-no-incr-doclist'. */
|
||||
int bNoIncrDoclist;
|
||||
#endif
|
||||
};
|
||||
|
||||
/*
|
||||
@@ -314,10 +253,8 @@ struct Fts3Cursor {
|
||||
i16 eSearch; /* Search strategy (see below) */
|
||||
u8 isEof; /* True if at End Of Results */
|
||||
u8 isRequireSeek; /* True if must seek pStmt to %_content row */
|
||||
u8 bSeekStmt; /* True if pStmt is a seek */
|
||||
sqlite3_stmt *pStmt; /* Prepared statement in use by the cursor */
|
||||
Fts3Expr *pExpr; /* Parsed MATCH query string */
|
||||
int iLangid; /* Language being queried for */
|
||||
int nPhrase; /* Number of matchable phrases in query */
|
||||
Fts3DeferredToken *pDeferred; /* Deferred search tokens, if any */
|
||||
sqlite3_int64 iPrevId; /* Previous id read from aDoclist */
|
||||
@@ -328,10 +265,11 @@ struct Fts3Cursor {
|
||||
int eEvalmode; /* An FTS3_EVAL_XX constant */
|
||||
int nRowAvg; /* Average size of database rows, in pages */
|
||||
sqlite3_int64 nDoc; /* Documents in table */
|
||||
i64 iMinDocid; /* Minimum docid to return */
|
||||
i64 iMaxDocid; /* Maximum docid to return */
|
||||
|
||||
int isMatchinfoNeeded; /* True when aMatchinfo[] needs filling in */
|
||||
MatchinfoBuffer *pMIBuffer; /* Buffer for matchinfo data */
|
||||
u32 *aMatchinfo; /* Information about most recent match */
|
||||
int nMatchinfo; /* Number of elements in aMatchinfo[] */
|
||||
char *zMatchinfo; /* Matchinfo specification */
|
||||
};
|
||||
|
||||
#define FTS3_EVAL_FILTER 0
|
||||
@@ -357,15 +295,6 @@ struct Fts3Cursor {
|
||||
#define FTS3_DOCID_SEARCH 1 /* Lookup by rowid on %_content table */
|
||||
#define FTS3_FULLTEXT_SEARCH 2 /* Full-text index search */
|
||||
|
||||
/*
|
||||
** The lower 16-bits of the sqlite3_index_info.idxNum value set by
|
||||
** the xBestIndex() method contains the Fts3Cursor.eSearch value described
|
||||
** above. The upper 16-bits contain a combination of the following
|
||||
** bits, used to describe extra constraints on full-text searches.
|
||||
*/
|
||||
#define FTS3_HAVE_LANGID 0x00010000 /* languageid=? */
|
||||
#define FTS3_HAVE_DOCID_GE 0x00020000 /* docid>=? */
|
||||
#define FTS3_HAVE_DOCID_LE 0x00040000 /* docid<=? */
|
||||
|
||||
struct Fts3Doclist {
|
||||
char *aAll; /* Array containing doclist (or NULL) */
|
||||
@@ -403,11 +332,6 @@ struct Fts3Phrase {
|
||||
int bIncr; /* True if doclist is loaded incrementally */
|
||||
int iDoclistToken;
|
||||
|
||||
/* Used by sqlite3Fts3EvalPhrasePoslist() if this is a descendent of an
|
||||
** OR condition. */
|
||||
char *pOrPoslist;
|
||||
i64 iOrDocid;
|
||||
|
||||
/* Variables below this point are populated by fts3_expr.c when parsing
|
||||
** a MATCH expression. Everything above is part of the evaluation phase.
|
||||
*/
|
||||
@@ -451,9 +375,7 @@ struct Fts3Expr {
|
||||
u8 bStart; /* True if iDocid is valid */
|
||||
u8 bDeferred; /* True if this expression is entirely deferred */
|
||||
|
||||
/* The following are used by the fts3_snippet.c module. */
|
||||
int iPhrase; /* Index of this phrase in matchinfo() results */
|
||||
u32 *aMI; /* See above */
|
||||
u32 *aMI;
|
||||
};
|
||||
|
||||
/*
|
||||
@@ -484,28 +406,18 @@ int sqlite3Fts3SegReaderNew(int, int, sqlite3_int64,
|
||||
int sqlite3Fts3SegReaderPending(
|
||||
Fts3Table*,int,const char*,int,int,Fts3SegReader**);
|
||||
void sqlite3Fts3SegReaderFree(Fts3SegReader *);
|
||||
int sqlite3Fts3AllSegdirs(Fts3Table*, int, int, int, sqlite3_stmt **);
|
||||
int sqlite3Fts3AllSegdirs(Fts3Table*, int, int, sqlite3_stmt **);
|
||||
int sqlite3Fts3ReadLock(Fts3Table *);
|
||||
int sqlite3Fts3ReadBlock(Fts3Table*, sqlite3_int64, char **, int*, int*);
|
||||
|
||||
int sqlite3Fts3SelectDoctotal(Fts3Table *, sqlite3_stmt **);
|
||||
int sqlite3Fts3SelectDocsize(Fts3Table *, sqlite3_int64, sqlite3_stmt **);
|
||||
|
||||
#ifndef SQLITE_DISABLE_FTS4_DEFERRED
|
||||
void sqlite3Fts3FreeDeferredTokens(Fts3Cursor *);
|
||||
int sqlite3Fts3DeferToken(Fts3Cursor *, Fts3PhraseToken *, int);
|
||||
int sqlite3Fts3CacheDeferredDoclists(Fts3Cursor *);
|
||||
void sqlite3Fts3FreeDeferredDoclists(Fts3Cursor *);
|
||||
int sqlite3Fts3DeferredTokenList(Fts3DeferredToken *, char **, int *);
|
||||
#else
|
||||
# define sqlite3Fts3FreeDeferredTokens(x)
|
||||
# define sqlite3Fts3DeferToken(x,y,z) SQLITE_OK
|
||||
# define sqlite3Fts3CacheDeferredDoclists(x) SQLITE_OK
|
||||
# define sqlite3Fts3FreeDeferredDoclists(x)
|
||||
# define sqlite3Fts3DeferredTokenList(x,y,z) SQLITE_OK
|
||||
#endif
|
||||
|
||||
void sqlite3Fts3SegmentsClose(Fts3Table *);
|
||||
int sqlite3Fts3MaxLevel(Fts3Table *, int *);
|
||||
|
||||
/* Special values interpreted by sqlite3SegReaderCursor() */
|
||||
#define FTS3_SEGCURSOR_PENDING -1
|
||||
@@ -515,8 +427,8 @@ int sqlite3Fts3SegReaderStart(Fts3Table*, Fts3MultiSegReader*, Fts3SegFilter*);
|
||||
int sqlite3Fts3SegReaderStep(Fts3Table *, Fts3MultiSegReader *);
|
||||
void sqlite3Fts3SegReaderFinish(Fts3MultiSegReader *);
|
||||
|
||||
int sqlite3Fts3SegReaderCursor(Fts3Table *,
|
||||
int, int, int, const char *, int, int, int, Fts3MultiSegReader *);
|
||||
int sqlite3Fts3SegReaderCursor(
|
||||
Fts3Table *, int, int, const char *, int, int, int, Fts3MultiSegReader *);
|
||||
|
||||
/* Flags allowed as part of the 4th argument to SegmentReaderIterate() */
|
||||
#define FTS3_SEGMENT_REQUIRE_POS 0x00000001
|
||||
@@ -557,14 +469,7 @@ struct Fts3MultiSegReader {
|
||||
int nDoclist; /* Size of aDoclist[] in bytes */
|
||||
};
|
||||
|
||||
int sqlite3Fts3Incrmerge(Fts3Table*,int,int);
|
||||
|
||||
#define fts3GetVarint32(p, piVal) ( \
|
||||
(*(u8*)(p)&0x80) ? sqlite3Fts3GetVarint32(p, piVal) : (*piVal=*(u8*)(p), 1) \
|
||||
)
|
||||
|
||||
/* fts3.c */
|
||||
void sqlite3Fts3ErrMsg(char**,const char*,...);
|
||||
int sqlite3Fts3PutVarint(char *, sqlite3_int64);
|
||||
int sqlite3Fts3GetVarint(const char *, sqlite_int64 *);
|
||||
int sqlite3Fts3GetVarint32(const char *, int *);
|
||||
@@ -573,8 +478,6 @@ void sqlite3Fts3Dequote(char *);
|
||||
void sqlite3Fts3DoclistPrev(int,char*,int,char**,sqlite3_int64*,int*,u8*);
|
||||
int sqlite3Fts3EvalPhraseStats(Fts3Cursor *, Fts3Expr *, u32 *);
|
||||
int sqlite3Fts3FirstFilter(sqlite3_int64, char *, int, char *);
|
||||
void sqlite3Fts3CreateStatTable(int*, Fts3Table*);
|
||||
int sqlite3Fts3EvalTestDeferred(Fts3Cursor *pCsr, int *pRc);
|
||||
|
||||
/* fts3_tokenizer.c */
|
||||
const char *sqlite3Fts3NextToken(const char *, int *);
|
||||
@@ -590,22 +493,17 @@ void sqlite3Fts3Snippet(sqlite3_context *, Fts3Cursor *, const char *,
|
||||
const char *, const char *, int, int
|
||||
);
|
||||
void sqlite3Fts3Matchinfo(sqlite3_context *, Fts3Cursor *, const char *);
|
||||
void sqlite3Fts3MIBufferFree(MatchinfoBuffer *p);
|
||||
|
||||
/* fts3_expr.c */
|
||||
int sqlite3Fts3ExprParse(sqlite3_tokenizer *, int,
|
||||
char **, int, int, int, const char *, int, Fts3Expr **, char **
|
||||
int sqlite3Fts3ExprParse(sqlite3_tokenizer *,
|
||||
char **, int, int, int, const char *, int, Fts3Expr **
|
||||
);
|
||||
void sqlite3Fts3ExprFree(Fts3Expr *);
|
||||
#ifdef SQLITE_TEST
|
||||
int sqlite3Fts3ExprInitTestInterface(sqlite3 *db, Fts3Hash*);
|
||||
int sqlite3Fts3ExprInitTestInterface(sqlite3 *db);
|
||||
int sqlite3Fts3InitTerm(sqlite3 *db);
|
||||
#endif
|
||||
|
||||
int sqlite3Fts3OpenTokenizer(sqlite3_tokenizer *, int, const char *, int,
|
||||
sqlite3_tokenizer_cursor **
|
||||
);
|
||||
|
||||
/* fts3_aux.c */
|
||||
int sqlite3Fts3InitAux(sqlite3 *db);
|
||||
|
||||
@@ -615,19 +513,11 @@ int sqlite3Fts3MsrIncrStart(
|
||||
Fts3Table*, Fts3MultiSegReader*, int, const char*, int);
|
||||
int sqlite3Fts3MsrIncrNext(
|
||||
Fts3Table *, Fts3MultiSegReader *, sqlite3_int64 *, char **, int *);
|
||||
int sqlite3Fts3EvalPhrasePoslist(Fts3Cursor *, Fts3Expr *, int iCol, char **);
|
||||
char *sqlite3Fts3EvalPhrasePoslist(Fts3Cursor *, Fts3Expr *, int iCol);
|
||||
int sqlite3Fts3MsrOvfl(Fts3Cursor *, Fts3MultiSegReader *, int *);
|
||||
int sqlite3Fts3MsrIncrRestart(Fts3MultiSegReader *pCsr);
|
||||
|
||||
/* fts3_tokenize_vtab.c */
|
||||
int sqlite3Fts3InitTok(sqlite3*, Fts3Hash *);
|
||||
|
||||
/* fts3_unicode2.c (functions generated by parsing unicode text files) */
|
||||
#ifndef SQLITE_DISABLE_FTS3_UNICODE
|
||||
int sqlite3FtsUnicodeFold(int, int);
|
||||
int sqlite3FtsUnicodeIsalnum(int);
|
||||
int sqlite3FtsUnicodeIsdiacritic(int);
|
||||
#endif
|
||||
int sqlite3Fts3DeferredTokenList(Fts3DeferredToken *, char **, int *);
|
||||
|
||||
#endif /* !SQLITE_CORE || SQLITE_ENABLE_FTS3 */
|
||||
#endif /* _FTSINT_H */
|
||||
|
||||
+48
-125
@@ -31,7 +31,6 @@ struct Fts3auxCursor {
|
||||
Fts3SegFilter filter;
|
||||
char *zStop;
|
||||
int nStop; /* Byte-length of string zStop */
|
||||
int iLangid; /* Language id to query */
|
||||
int isEof; /* True if cursor is at EOF */
|
||||
sqlite3_int64 iRowid; /* Current rowid */
|
||||
|
||||
@@ -46,8 +45,7 @@ struct Fts3auxCursor {
|
||||
/*
|
||||
** Schema of the terms table.
|
||||
*/
|
||||
#define FTS3_AUX_SCHEMA \
|
||||
"CREATE TABLE x(term, col, documents, occurrences, languageid HIDDEN)"
|
||||
#define FTS3_TERMS_SCHEMA "CREATE TABLE x(term, col, documents, occurrences)"
|
||||
|
||||
/*
|
||||
** This function does all the work for both the xConnect and xCreate methods.
|
||||
@@ -66,39 +64,30 @@ static int fts3auxConnectMethod(
|
||||
char const *zFts3; /* Name of fts3 table */
|
||||
int nDb; /* Result of strlen(zDb) */
|
||||
int nFts3; /* Result of strlen(zFts3) */
|
||||
sqlite3_int64 nByte; /* Bytes of space to allocate here */
|
||||
int nByte; /* Bytes of space to allocate here */
|
||||
int rc; /* value returned by declare_vtab() */
|
||||
Fts3auxTable *p; /* Virtual table object to return */
|
||||
|
||||
UNUSED_PARAMETER(pUnused);
|
||||
|
||||
/* The user should invoke this in one of two forms:
|
||||
**
|
||||
** CREATE VIRTUAL TABLE xxx USING fts4aux(fts4-table);
|
||||
** CREATE VIRTUAL TABLE xxx USING fts4aux(fts4-table-db, fts4-table);
|
||||
*/
|
||||
if( argc!=4 && argc!=5 ) goto bad_args;
|
||||
/* The user should specify a single argument - the name of an fts3 table. */
|
||||
if( argc!=4 ){
|
||||
*pzErr = sqlite3_mprintf(
|
||||
"wrong number of arguments to fts4aux constructor"
|
||||
);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
zDb = argv[1];
|
||||
nDb = (int)strlen(zDb);
|
||||
if( argc==5 ){
|
||||
if( nDb==4 && 0==sqlite3_strnicmp("temp", zDb, 4) ){
|
||||
zDb = argv[3];
|
||||
nDb = (int)strlen(zDb);
|
||||
zFts3 = argv[4];
|
||||
}else{
|
||||
goto bad_args;
|
||||
}
|
||||
}else{
|
||||
zFts3 = argv[3];
|
||||
}
|
||||
nFts3 = (int)strlen(zFts3);
|
||||
nDb = strlen(zDb);
|
||||
zFts3 = argv[3];
|
||||
nFts3 = strlen(zFts3);
|
||||
|
||||
rc = sqlite3_declare_vtab(db, FTS3_AUX_SCHEMA);
|
||||
rc = sqlite3_declare_vtab(db, FTS3_TERMS_SCHEMA);
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
|
||||
nByte = sizeof(Fts3auxTable) + sizeof(Fts3Table) + nDb + nFts3 + 2;
|
||||
p = (Fts3auxTable *)sqlite3_malloc64(nByte);
|
||||
p = (Fts3auxTable *)sqlite3_malloc(nByte);
|
||||
if( !p ) return SQLITE_NOMEM;
|
||||
memset(p, 0, nByte);
|
||||
|
||||
@@ -114,10 +103,6 @@ static int fts3auxConnectMethod(
|
||||
|
||||
*ppVtab = (sqlite3_vtab *)p;
|
||||
return SQLITE_OK;
|
||||
|
||||
bad_args:
|
||||
sqlite3Fts3ErrMsg(pzErr, "invalid arguments to fts4aux constructor");
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -154,8 +139,6 @@ static int fts3auxBestIndexMethod(
|
||||
int iEq = -1;
|
||||
int iGe = -1;
|
||||
int iLe = -1;
|
||||
int iLangid = -1;
|
||||
int iNext = 1; /* Next free argvIndex value */
|
||||
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
@@ -167,48 +150,36 @@ static int fts3auxBestIndexMethod(
|
||||
pInfo->orderByConsumed = 1;
|
||||
}
|
||||
|
||||
/* Search for equality and range constraints on the "term" column.
|
||||
** And equality constraints on the hidden "languageid" column. */
|
||||
/* Search for equality and range constraints on the "term" column. */
|
||||
for(i=0; i<pInfo->nConstraint; i++){
|
||||
if( pInfo->aConstraint[i].usable ){
|
||||
if( pInfo->aConstraint[i].usable && pInfo->aConstraint[i].iColumn==0 ){
|
||||
int op = pInfo->aConstraint[i].op;
|
||||
int iCol = pInfo->aConstraint[i].iColumn;
|
||||
|
||||
if( iCol==0 ){
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_EQ ) iEq = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_LT ) iLe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_LE ) iLe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_GT ) iGe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_GE ) iGe = i;
|
||||
}
|
||||
if( iCol==4 ){
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_EQ ) iLangid = i;
|
||||
}
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_EQ ) iEq = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_LT ) iLe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_LE ) iLe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_GT ) iGe = i;
|
||||
if( op==SQLITE_INDEX_CONSTRAINT_GE ) iGe = i;
|
||||
}
|
||||
}
|
||||
|
||||
if( iEq>=0 ){
|
||||
pInfo->idxNum = FTS4AUX_EQ_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iEq].argvIndex = iNext++;
|
||||
pInfo->aConstraintUsage[iEq].argvIndex = 1;
|
||||
pInfo->estimatedCost = 5;
|
||||
}else{
|
||||
pInfo->idxNum = 0;
|
||||
pInfo->estimatedCost = 20000;
|
||||
if( iGe>=0 ){
|
||||
pInfo->idxNum += FTS4AUX_GE_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iGe].argvIndex = iNext++;
|
||||
pInfo->aConstraintUsage[iGe].argvIndex = 1;
|
||||
pInfo->estimatedCost /= 2;
|
||||
}
|
||||
if( iLe>=0 ){
|
||||
pInfo->idxNum += FTS4AUX_LE_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iLe].argvIndex = iNext++;
|
||||
pInfo->aConstraintUsage[iLe].argvIndex = 1 + (iGe>=0);
|
||||
pInfo->estimatedCost /= 2;
|
||||
}
|
||||
}
|
||||
if( iLangid>=0 ){
|
||||
pInfo->aConstraintUsage[iLangid].argvIndex = iNext++;
|
||||
pInfo->estimatedCost--;
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
@@ -248,7 +219,7 @@ static int fts3auxCloseMethod(sqlite3_vtab_cursor *pCursor){
|
||||
static int fts3auxGrowStatArray(Fts3auxCursor *pCsr, int nSize){
|
||||
if( nSize>pCsr->nStat ){
|
||||
struct Fts3auxColstats *aNew;
|
||||
aNew = (struct Fts3auxColstats *)sqlite3_realloc64(pCsr->aStat,
|
||||
aNew = (struct Fts3auxColstats *)sqlite3_realloc(pCsr->aStat,
|
||||
sizeof(struct Fts3auxColstats) * nSize
|
||||
);
|
||||
if( aNew==0 ) return SQLITE_NOMEM;
|
||||
@@ -368,14 +339,7 @@ static int fts3auxFilterMethod(
|
||||
Fts3auxCursor *pCsr = (Fts3auxCursor *)pCursor;
|
||||
Fts3Table *pFts3 = ((Fts3auxTable *)pCursor->pVtab)->pFts3Tab;
|
||||
int rc;
|
||||
int isScan = 0;
|
||||
int iLangVal = 0; /* Language id to query */
|
||||
|
||||
int iEq = -1; /* Index of term=? value in apVal */
|
||||
int iGe = -1; /* Index of term>=? value in apVal */
|
||||
int iLe = -1; /* Index of term<=? value in apVal */
|
||||
int iLangid = -1; /* Index of languageid=? value in apVal */
|
||||
int iNext = 0;
|
||||
int isScan;
|
||||
|
||||
UNUSED_PARAMETER(nVal);
|
||||
UNUSED_PARAMETER(idxStr);
|
||||
@@ -385,21 +349,7 @@ static int fts3auxFilterMethod(
|
||||
|| idxNum==FTS4AUX_LE_CONSTRAINT || idxNum==FTS4AUX_GE_CONSTRAINT
|
||||
|| idxNum==(FTS4AUX_LE_CONSTRAINT|FTS4AUX_GE_CONSTRAINT)
|
||||
);
|
||||
|
||||
if( idxNum==FTS4AUX_EQ_CONSTRAINT ){
|
||||
iEq = iNext++;
|
||||
}else{
|
||||
isScan = 1;
|
||||
if( idxNum & FTS4AUX_GE_CONSTRAINT ){
|
||||
iGe = iNext++;
|
||||
}
|
||||
if( idxNum & FTS4AUX_LE_CONSTRAINT ){
|
||||
iLe = iNext++;
|
||||
}
|
||||
}
|
||||
if( iNext<nVal ){
|
||||
iLangid = iNext++;
|
||||
}
|
||||
isScan = (idxNum!=FTS4AUX_EQ_CONSTRAINT);
|
||||
|
||||
/* In case this cursor is being reused, close and zero it. */
|
||||
testcase(pCsr->filter.zTerm);
|
||||
@@ -411,35 +361,22 @@ static int fts3auxFilterMethod(
|
||||
pCsr->filter.flags = FTS3_SEGMENT_REQUIRE_POS|FTS3_SEGMENT_IGNORE_EMPTY;
|
||||
if( isScan ) pCsr->filter.flags |= FTS3_SEGMENT_SCAN;
|
||||
|
||||
if( iEq>=0 || iGe>=0 ){
|
||||
if( idxNum&(FTS4AUX_EQ_CONSTRAINT|FTS4AUX_GE_CONSTRAINT) ){
|
||||
const unsigned char *zStr = sqlite3_value_text(apVal[0]);
|
||||
assert( (iEq==0 && iGe==-1) || (iEq==-1 && iGe==0) );
|
||||
if( zStr ){
|
||||
pCsr->filter.zTerm = sqlite3_mprintf("%s", zStr);
|
||||
pCsr->filter.nTerm = sqlite3_value_bytes(apVal[0]);
|
||||
if( pCsr->filter.zTerm==0 ) return SQLITE_NOMEM;
|
||||
pCsr->filter.nTerm = (int)strlen(pCsr->filter.zTerm);
|
||||
}
|
||||
}
|
||||
|
||||
if( iLe>=0 ){
|
||||
pCsr->zStop = sqlite3_mprintf("%s", sqlite3_value_text(apVal[iLe]));
|
||||
if( idxNum&FTS4AUX_LE_CONSTRAINT ){
|
||||
int iIdx = (idxNum&FTS4AUX_GE_CONSTRAINT) ? 1 : 0;
|
||||
pCsr->zStop = sqlite3_mprintf("%s", sqlite3_value_text(apVal[iIdx]));
|
||||
pCsr->nStop = sqlite3_value_bytes(apVal[iIdx]);
|
||||
if( pCsr->zStop==0 ) return SQLITE_NOMEM;
|
||||
pCsr->nStop = (int)strlen(pCsr->zStop);
|
||||
}
|
||||
|
||||
if( iLangid>=0 ){
|
||||
iLangVal = sqlite3_value_int(apVal[iLangid]);
|
||||
|
||||
/* If the user specified a negative value for the languageid, use zero
|
||||
** instead. This works, as the "languageid=?" constraint will also
|
||||
** be tested by the VDBE layer. The test will always be false (since
|
||||
** this module will not return a row with a negative languageid), and
|
||||
** so the overall query will return zero rows. */
|
||||
if( iLangVal<0 ) iLangVal = 0;
|
||||
}
|
||||
pCsr->iLangid = iLangVal;
|
||||
|
||||
rc = sqlite3Fts3SegReaderCursor(pFts3, iLangVal, 0, FTS3_SEGCURSOR_ALL,
|
||||
rc = sqlite3Fts3SegReaderCursor(pFts3, 0, FTS3_SEGCURSOR_ALL,
|
||||
pCsr->filter.zTerm, pCsr->filter.nTerm, 0, isScan, &pCsr->csr
|
||||
);
|
||||
if( rc==SQLITE_OK ){
|
||||
@@ -463,37 +400,24 @@ static int fts3auxEofMethod(sqlite3_vtab_cursor *pCursor){
|
||||
*/
|
||||
static int fts3auxColumnMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* Cursor to retrieve value from */
|
||||
sqlite3_context *pCtx, /* Context for sqlite3_result_xxx() calls */
|
||||
sqlite3_context *pContext, /* Context for sqlite3_result_xxx() calls */
|
||||
int iCol /* Index of column to read value from */
|
||||
){
|
||||
Fts3auxCursor *p = (Fts3auxCursor *)pCursor;
|
||||
|
||||
assert( p->isEof==0 );
|
||||
switch( iCol ){
|
||||
case 0: /* term */
|
||||
sqlite3_result_text(pCtx, p->csr.zTerm, p->csr.nTerm, SQLITE_TRANSIENT);
|
||||
break;
|
||||
|
||||
case 1: /* col */
|
||||
if( p->iCol ){
|
||||
sqlite3_result_int(pCtx, p->iCol-1);
|
||||
}else{
|
||||
sqlite3_result_text(pCtx, "*", -1, SQLITE_STATIC);
|
||||
}
|
||||
break;
|
||||
|
||||
case 2: /* documents */
|
||||
sqlite3_result_int64(pCtx, p->aStat[p->iCol].nDoc);
|
||||
break;
|
||||
|
||||
case 3: /* occurrences */
|
||||
sqlite3_result_int64(pCtx, p->aStat[p->iCol].nOcc);
|
||||
break;
|
||||
|
||||
default: /* languageid */
|
||||
assert( iCol==4 );
|
||||
sqlite3_result_int(pCtx, p->iLangid);
|
||||
break;
|
||||
if( iCol==0 ){ /* Column "term" */
|
||||
sqlite3_result_text(pContext, p->csr.zTerm, p->csr.nTerm, SQLITE_TRANSIENT);
|
||||
}else if( iCol==1 ){ /* Column "col" */
|
||||
if( p->iCol ){
|
||||
sqlite3_result_int(pContext, p->iCol-1);
|
||||
}else{
|
||||
sqlite3_result_text(pContext, "*", -1, SQLITE_STATIC);
|
||||
}
|
||||
}else if( iCol==2 ){ /* Column "documents" */
|
||||
sqlite3_result_int64(pContext, p->aStat[p->iCol].nDoc);
|
||||
}else{ /* Column "occurrences" */
|
||||
sqlite3_result_int64(pContext, p->aStat[p->iCol].nOcc);
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
@@ -539,8 +463,7 @@ int sqlite3Fts3InitAux(sqlite3 *db){
|
||||
0, /* xRename */
|
||||
0, /* xSavepoint */
|
||||
0, /* xRelease */
|
||||
0, /* xRollbackTo */
|
||||
0 /* xShadowName */
|
||||
0 /* xRollbackTo */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
|
||||
+198
-505
@@ -92,7 +92,6 @@ int sqlite3_fts3_enable_parentheses = 0;
|
||||
typedef struct ParseContext ParseContext;
|
||||
struct ParseContext {
|
||||
sqlite3_tokenizer *pTokenizer; /* Tokenizer module */
|
||||
int iLangid; /* Language id used with tokenizer */
|
||||
const char **azCol; /* Array of column names for fts3 table */
|
||||
int bFts4; /* True to allow FTS4-only syntax */
|
||||
int nCol; /* Number of entries in azCol[] */
|
||||
@@ -106,7 +105,7 @@ struct ParseContext {
|
||||
** This function is equivalent to the standard isspace() function.
|
||||
**
|
||||
** The standard isspace() can be awkward to use safely, because although it
|
||||
** is defined to accept an argument of type int, its behavior when passed
|
||||
** is defined to accept an argument of type int, its behaviour when passed
|
||||
** an integer that falls outside of the range of the unsigned char type
|
||||
** is undefined (and sometimes, "undefined" means segfault). This wrapper
|
||||
** is defined to accept an argument of type char, and always returns 0 for
|
||||
@@ -122,44 +121,12 @@ static int fts3isspace(char c){
|
||||
** zero the memory before returning a pointer to it. If unsuccessful,
|
||||
** return NULL.
|
||||
*/
|
||||
static void *fts3MallocZero(sqlite3_int64 nByte){
|
||||
void *pRet = sqlite3_malloc64(nByte);
|
||||
static void *fts3MallocZero(int nByte){
|
||||
void *pRet = sqlite3_malloc(nByte);
|
||||
if( pRet ) memset(pRet, 0, nByte);
|
||||
return pRet;
|
||||
}
|
||||
|
||||
int sqlite3Fts3OpenTokenizer(
|
||||
sqlite3_tokenizer *pTokenizer,
|
||||
int iLangid,
|
||||
const char *z,
|
||||
int n,
|
||||
sqlite3_tokenizer_cursor **ppCsr
|
||||
){
|
||||
sqlite3_tokenizer_module const *pModule = pTokenizer->pModule;
|
||||
sqlite3_tokenizer_cursor *pCsr = 0;
|
||||
int rc;
|
||||
|
||||
rc = pModule->xOpen(pTokenizer, z, n, &pCsr);
|
||||
assert( rc==SQLITE_OK || pCsr==0 );
|
||||
if( rc==SQLITE_OK ){
|
||||
pCsr->pTokenizer = pTokenizer;
|
||||
if( pModule->iVersion>=1 ){
|
||||
rc = pModule->xLanguageid(pCsr, iLangid);
|
||||
if( rc!=SQLITE_OK ){
|
||||
pModule->xClose(pCsr);
|
||||
pCsr = 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
*ppCsr = pCsr;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Function getNextNode(), which is called by fts3ExprParse(), may itself
|
||||
** call fts3ExprParse(). So this forward declaration is required.
|
||||
*/
|
||||
static int fts3ExprParse(ParseContext *, const char *, int, Fts3Expr **, int *);
|
||||
|
||||
/*
|
||||
** Extract the next token from buffer z (length n) using the tokenizer
|
||||
@@ -185,22 +152,17 @@ static int getNextToken(
|
||||
int rc;
|
||||
sqlite3_tokenizer_cursor *pCursor;
|
||||
Fts3Expr *pRet = 0;
|
||||
int i = 0;
|
||||
int nConsumed = 0;
|
||||
|
||||
/* Set variable i to the maximum number of bytes of input to tokenize. */
|
||||
for(i=0; i<n; i++){
|
||||
if( sqlite3_fts3_enable_parentheses && (z[i]=='(' || z[i]==')') ) break;
|
||||
if( z[i]=='"' ) break;
|
||||
}
|
||||
|
||||
*pnConsumed = i;
|
||||
rc = sqlite3Fts3OpenTokenizer(pTokenizer, pParse->iLangid, z, i, &pCursor);
|
||||
rc = pModule->xOpen(pTokenizer, z, n, &pCursor);
|
||||
if( rc==SQLITE_OK ){
|
||||
const char *zToken;
|
||||
int nToken = 0, iStart = 0, iEnd = 0, iPosition = 0;
|
||||
sqlite3_int64 nByte; /* total space to allocate */
|
||||
int nToken, iStart, iEnd, iPosition;
|
||||
int nByte; /* total space to allocate */
|
||||
|
||||
pCursor->pTokenizer = pTokenizer;
|
||||
rc = pModule->xNext(pCursor, &zToken, &nToken, &iStart, &iEnd, &iPosition);
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
nByte = sizeof(Fts3Expr) + sizeof(Fts3Phrase) + nToken;
|
||||
pRet = (Fts3Expr *)fts3MallocZero(nByte);
|
||||
@@ -235,14 +197,13 @@ static int getNextToken(
|
||||
}
|
||||
|
||||
}
|
||||
*pnConsumed = iEnd;
|
||||
}else if( i && rc==SQLITE_DONE ){
|
||||
rc = SQLITE_OK;
|
||||
nConsumed = iEnd;
|
||||
}
|
||||
|
||||
pModule->xClose(pCursor);
|
||||
}
|
||||
|
||||
*pnConsumed = nConsumed;
|
||||
*ppExpr = pRet;
|
||||
return rc;
|
||||
}
|
||||
@@ -252,8 +213,8 @@ static int getNextToken(
|
||||
** Enlarge a memory allocation. If an out-of-memory allocation occurs,
|
||||
** then free the old allocation.
|
||||
*/
|
||||
static void *fts3ReallocOrFree(void *pOrig, sqlite3_int64 nNew){
|
||||
void *pRet = sqlite3_realloc64(pOrig, nNew);
|
||||
static void *fts3ReallocOrFree(void *pOrig, int nNew){
|
||||
void *pRet = sqlite3_realloc(pOrig, nNew);
|
||||
if( !pRet ){
|
||||
sqlite3_free(pOrig);
|
||||
}
|
||||
@@ -307,13 +268,13 @@ static int getNextString(
|
||||
** appends buffer zTemp to buffer p, and fills in the Fts3Expr and Fts3Phrase
|
||||
** structures.
|
||||
*/
|
||||
rc = sqlite3Fts3OpenTokenizer(
|
||||
pTokenizer, pParse->iLangid, zInput, nInput, &pCursor);
|
||||
rc = pModule->xOpen(pTokenizer, zInput, nInput, &pCursor);
|
||||
if( rc==SQLITE_OK ){
|
||||
int ii;
|
||||
pCursor->pTokenizer = pTokenizer;
|
||||
for(ii=0; rc==SQLITE_OK; ii++){
|
||||
const char *zByte;
|
||||
int nByte = 0, iBegin = 0, iEnd = 0, iPos = 0;
|
||||
int nByte, iBegin, iEnd, iPos;
|
||||
rc = pModule->xNext(pCursor, &zByte, &nByte, &iBegin, &iEnd, &iPos);
|
||||
if( rc==SQLITE_OK ){
|
||||
Fts3PhraseToken *pToken;
|
||||
@@ -382,6 +343,12 @@ no_mem:
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
|
||||
/*
|
||||
** Function getNextNode(), which is called by fts3ExprParse(), may itself
|
||||
** call fts3ExprParse(). So this forward declaration is required.
|
||||
*/
|
||||
static int fts3ExprParse(ParseContext *, const char *, int, Fts3Expr **, int *);
|
||||
|
||||
/*
|
||||
** The output variable *ppExpr is populated with an allocated Fts3Expr
|
||||
** structure, or set to 0 if the end of the input buffer is reached.
|
||||
@@ -478,6 +445,27 @@ static int getNextNode(
|
||||
}
|
||||
}
|
||||
|
||||
/* Check for an open bracket. */
|
||||
if( sqlite3_fts3_enable_parentheses ){
|
||||
if( *zInput=='(' ){
|
||||
int nConsumed;
|
||||
pParse->nNest++;
|
||||
rc = fts3ExprParse(pParse, &zInput[1], nInput-1, ppExpr, &nConsumed);
|
||||
if( rc==SQLITE_OK && !*ppExpr ){
|
||||
rc = SQLITE_DONE;
|
||||
}
|
||||
*pnConsumed = (int)((zInput - z) + 1 + nConsumed);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/* Check for a close bracket. */
|
||||
if( *zInput==')' ){
|
||||
pParse->nNest--;
|
||||
*pnConsumed = (int)((zInput - z) + 1);
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
/* See if we are dealing with a quoted phrase. If this is the case, then
|
||||
** search for the closing quote and pass the whole string to getNextString()
|
||||
** for processing. This is easy to do, as fts3 has no syntax for escaping
|
||||
@@ -492,20 +480,6 @@ static int getNextNode(
|
||||
return getNextString(pParse, &zInput[1], ii-1, ppExpr);
|
||||
}
|
||||
|
||||
if( sqlite3_fts3_enable_parentheses ){
|
||||
if( *zInput=='(' ){
|
||||
int nConsumed = 0;
|
||||
pParse->nNest++;
|
||||
rc = fts3ExprParse(pParse, zInput+1, nInput-1, ppExpr, &nConsumed);
|
||||
*pnConsumed = (int)(zInput - z) + 1 + nConsumed;
|
||||
return rc;
|
||||
}else if( *zInput==')' ){
|
||||
pParse->nNest--;
|
||||
*pnConsumed = (int)((zInput - z) + 1);
|
||||
*ppExpr = 0;
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
/* If control flows to this point, this must be a regular token, or
|
||||
** the end of the input. Read a regular token using the sqlite3_tokenizer
|
||||
@@ -624,100 +598,94 @@ static int fts3ExprParse(
|
||||
while( rc==SQLITE_OK ){
|
||||
Fts3Expr *p = 0;
|
||||
int nByte = 0;
|
||||
|
||||
rc = getNextNode(pParse, zIn, nIn, &p, &nByte);
|
||||
assert( nByte>0 || (rc!=SQLITE_OK && p==0) );
|
||||
if( rc==SQLITE_OK ){
|
||||
if( p ){
|
||||
int isPhrase;
|
||||
int isPhrase;
|
||||
|
||||
if( !sqlite3_fts3_enable_parentheses
|
||||
&& p->eType==FTSQUERY_PHRASE && pParse->isNot
|
||||
){
|
||||
/* Create an implicit NOT operator. */
|
||||
Fts3Expr *pNot = fts3MallocZero(sizeof(Fts3Expr));
|
||||
if( !pNot ){
|
||||
if( !sqlite3_fts3_enable_parentheses
|
||||
&& p->eType==FTSQUERY_PHRASE && pParse->isNot
|
||||
){
|
||||
/* Create an implicit NOT operator. */
|
||||
Fts3Expr *pNot = fts3MallocZero(sizeof(Fts3Expr));
|
||||
if( !pNot ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_NOMEM;
|
||||
goto exprparse_out;
|
||||
}
|
||||
pNot->eType = FTSQUERY_NOT;
|
||||
pNot->pRight = p;
|
||||
if( pNotBranch ){
|
||||
pNot->pLeft = pNotBranch;
|
||||
}
|
||||
pNotBranch = pNot;
|
||||
p = pPrev;
|
||||
}else{
|
||||
int eType = p->eType;
|
||||
isPhrase = (eType==FTSQUERY_PHRASE || p->pLeft);
|
||||
|
||||
/* The isRequirePhrase variable is set to true if a phrase or
|
||||
** an expression contained in parenthesis is required. If a
|
||||
** binary operator (AND, OR, NOT or NEAR) is encounted when
|
||||
** isRequirePhrase is set, this is a syntax error.
|
||||
*/
|
||||
if( !isPhrase && isRequirePhrase ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_ERROR;
|
||||
goto exprparse_out;
|
||||
}
|
||||
|
||||
if( isPhrase && !isRequirePhrase ){
|
||||
/* Insert an implicit AND operator. */
|
||||
Fts3Expr *pAnd;
|
||||
assert( pRet && pPrev );
|
||||
pAnd = fts3MallocZero(sizeof(Fts3Expr));
|
||||
if( !pAnd ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_NOMEM;
|
||||
goto exprparse_out;
|
||||
}
|
||||
pNot->eType = FTSQUERY_NOT;
|
||||
pNot->pRight = p;
|
||||
p->pParent = pNot;
|
||||
if( pNotBranch ){
|
||||
pNot->pLeft = pNotBranch;
|
||||
pNotBranch->pParent = pNot;
|
||||
}
|
||||
pNotBranch = pNot;
|
||||
p = pPrev;
|
||||
}else{
|
||||
int eType = p->eType;
|
||||
isPhrase = (eType==FTSQUERY_PHRASE || p->pLeft);
|
||||
pAnd->eType = FTSQUERY_AND;
|
||||
insertBinaryOperator(&pRet, pPrev, pAnd);
|
||||
pPrev = pAnd;
|
||||
}
|
||||
|
||||
/* The isRequirePhrase variable is set to true if a phrase or
|
||||
** an expression contained in parenthesis is required. If a
|
||||
** binary operator (AND, OR, NOT or NEAR) is encounted when
|
||||
** isRequirePhrase is set, this is a syntax error.
|
||||
*/
|
||||
if( !isPhrase && isRequirePhrase ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_ERROR;
|
||||
goto exprparse_out;
|
||||
}
|
||||
|
||||
if( isPhrase && !isRequirePhrase ){
|
||||
/* Insert an implicit AND operator. */
|
||||
Fts3Expr *pAnd;
|
||||
assert( pRet && pPrev );
|
||||
pAnd = fts3MallocZero(sizeof(Fts3Expr));
|
||||
if( !pAnd ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_NOMEM;
|
||||
goto exprparse_out;
|
||||
}
|
||||
pAnd->eType = FTSQUERY_AND;
|
||||
insertBinaryOperator(&pRet, pPrev, pAnd);
|
||||
pPrev = pAnd;
|
||||
}
|
||||
|
||||
/* This test catches attempts to make either operand of a NEAR
|
||||
** operator something other than a phrase. For example, either of
|
||||
** the following:
|
||||
**
|
||||
** (bracketed expression) NEAR phrase
|
||||
** phrase NEAR (bracketed expression)
|
||||
**
|
||||
** Return an error in either case.
|
||||
*/
|
||||
if( pPrev && (
|
||||
/* This test catches attempts to make either operand of a NEAR
|
||||
** operator something other than a phrase. For example, either of
|
||||
** the following:
|
||||
**
|
||||
** (bracketed expression) NEAR phrase
|
||||
** phrase NEAR (bracketed expression)
|
||||
**
|
||||
** Return an error in either case.
|
||||
*/
|
||||
if( pPrev && (
|
||||
(eType==FTSQUERY_NEAR && !isPhrase && pPrev->eType!=FTSQUERY_PHRASE)
|
||||
|| (eType!=FTSQUERY_PHRASE && isPhrase && pPrev->eType==FTSQUERY_NEAR)
|
||||
)){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_ERROR;
|
||||
goto exprparse_out;
|
||||
}
|
||||
|
||||
if( isPhrase ){
|
||||
if( pRet ){
|
||||
assert( pPrev && pPrev->pLeft && pPrev->pRight==0 );
|
||||
pPrev->pRight = p;
|
||||
p->pParent = pPrev;
|
||||
}else{
|
||||
pRet = p;
|
||||
}
|
||||
}else{
|
||||
insertBinaryOperator(&pRet, pPrev, p);
|
||||
}
|
||||
isRequirePhrase = !isPhrase;
|
||||
)){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_ERROR;
|
||||
goto exprparse_out;
|
||||
}
|
||||
pPrev = p;
|
||||
|
||||
if( isPhrase ){
|
||||
if( pRet ){
|
||||
assert( pPrev && pPrev->pLeft && pPrev->pRight==0 );
|
||||
pPrev->pRight = p;
|
||||
p->pParent = pPrev;
|
||||
}else{
|
||||
pRet = p;
|
||||
}
|
||||
}else{
|
||||
insertBinaryOperator(&pRet, pPrev, p);
|
||||
}
|
||||
isRequirePhrase = !isPhrase;
|
||||
}
|
||||
assert( nByte>0 );
|
||||
}
|
||||
assert( rc!=SQLITE_OK || (nByte>0 && nByte<=nIn) );
|
||||
nIn -= nByte;
|
||||
zIn += nByte;
|
||||
pPrev = p;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_DONE && pRet && isRequirePhrase ){
|
||||
@@ -735,7 +703,6 @@ static int fts3ExprParse(
|
||||
pIter = pIter->pLeft;
|
||||
}
|
||||
pIter->pLeft = pRet;
|
||||
pRet->pParent = pIter;
|
||||
pRet = pNotBranch;
|
||||
}
|
||||
}
|
||||
@@ -752,249 +719,6 @@ exprparse_out:
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return SQLITE_ERROR if the maximum depth of the expression tree passed
|
||||
** as the only argument is more than nMaxDepth.
|
||||
*/
|
||||
static int fts3ExprCheckDepth(Fts3Expr *p, int nMaxDepth){
|
||||
int rc = SQLITE_OK;
|
||||
if( p ){
|
||||
if( nMaxDepth<0 ){
|
||||
rc = SQLITE_TOOBIG;
|
||||
}else{
|
||||
rc = fts3ExprCheckDepth(p->pLeft, nMaxDepth-1);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts3ExprCheckDepth(p->pRight, nMaxDepth-1);
|
||||
}
|
||||
}
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** This function attempts to transform the expression tree at (*pp) to
|
||||
** an equivalent but more balanced form. The tree is modified in place.
|
||||
** If successful, SQLITE_OK is returned and (*pp) set to point to the
|
||||
** new root expression node.
|
||||
**
|
||||
** nMaxDepth is the maximum allowable depth of the balanced sub-tree.
|
||||
**
|
||||
** Otherwise, if an error occurs, an SQLite error code is returned and
|
||||
** expression (*pp) freed.
|
||||
*/
|
||||
static int fts3ExprBalance(Fts3Expr **pp, int nMaxDepth){
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
Fts3Expr *pRoot = *pp; /* Initial root node */
|
||||
Fts3Expr *pFree = 0; /* List of free nodes. Linked by pParent. */
|
||||
int eType = pRoot->eType; /* Type of node in this tree */
|
||||
|
||||
if( nMaxDepth==0 ){
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
if( (eType==FTSQUERY_AND || eType==FTSQUERY_OR) ){
|
||||
Fts3Expr **apLeaf;
|
||||
apLeaf = (Fts3Expr **)sqlite3_malloc64(sizeof(Fts3Expr *) * nMaxDepth);
|
||||
if( 0==apLeaf ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memset(apLeaf, 0, sizeof(Fts3Expr *) * nMaxDepth);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
int i;
|
||||
Fts3Expr *p;
|
||||
|
||||
/* Set $p to point to the left-most leaf in the tree of eType nodes. */
|
||||
for(p=pRoot; p->eType==eType; p=p->pLeft){
|
||||
assert( p->pParent==0 || p->pParent->pLeft==p );
|
||||
assert( p->pLeft && p->pRight );
|
||||
}
|
||||
|
||||
/* This loop runs once for each leaf in the tree of eType nodes. */
|
||||
while( 1 ){
|
||||
int iLvl;
|
||||
Fts3Expr *pParent = p->pParent; /* Current parent of p */
|
||||
|
||||
assert( pParent==0 || pParent->pLeft==p );
|
||||
p->pParent = 0;
|
||||
if( pParent ){
|
||||
pParent->pLeft = 0;
|
||||
}else{
|
||||
pRoot = 0;
|
||||
}
|
||||
rc = fts3ExprBalance(&p, nMaxDepth-1);
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
|
||||
for(iLvl=0; p && iLvl<nMaxDepth; iLvl++){
|
||||
if( apLeaf[iLvl]==0 ){
|
||||
apLeaf[iLvl] = p;
|
||||
p = 0;
|
||||
}else{
|
||||
assert( pFree );
|
||||
pFree->pLeft = apLeaf[iLvl];
|
||||
pFree->pRight = p;
|
||||
pFree->pLeft->pParent = pFree;
|
||||
pFree->pRight->pParent = pFree;
|
||||
|
||||
p = pFree;
|
||||
pFree = pFree->pParent;
|
||||
p->pParent = 0;
|
||||
apLeaf[iLvl] = 0;
|
||||
}
|
||||
}
|
||||
if( p ){
|
||||
sqlite3Fts3ExprFree(p);
|
||||
rc = SQLITE_TOOBIG;
|
||||
break;
|
||||
}
|
||||
|
||||
/* If that was the last leaf node, break out of the loop */
|
||||
if( pParent==0 ) break;
|
||||
|
||||
/* Set $p to point to the next leaf in the tree of eType nodes */
|
||||
for(p=pParent->pRight; p->eType==eType; p=p->pLeft);
|
||||
|
||||
/* Remove pParent from the original tree. */
|
||||
assert( pParent->pParent==0 || pParent->pParent->pLeft==pParent );
|
||||
pParent->pRight->pParent = pParent->pParent;
|
||||
if( pParent->pParent ){
|
||||
pParent->pParent->pLeft = pParent->pRight;
|
||||
}else{
|
||||
assert( pParent==pRoot );
|
||||
pRoot = pParent->pRight;
|
||||
}
|
||||
|
||||
/* Link pParent into the free node list. It will be used as an
|
||||
** internal node of the new tree. */
|
||||
pParent->pParent = pFree;
|
||||
pFree = pParent;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
p = 0;
|
||||
for(i=0; i<nMaxDepth; i++){
|
||||
if( apLeaf[i] ){
|
||||
if( p==0 ){
|
||||
p = apLeaf[i];
|
||||
p->pParent = 0;
|
||||
}else{
|
||||
assert( pFree!=0 );
|
||||
pFree->pRight = p;
|
||||
pFree->pLeft = apLeaf[i];
|
||||
pFree->pLeft->pParent = pFree;
|
||||
pFree->pRight->pParent = pFree;
|
||||
|
||||
p = pFree;
|
||||
pFree = pFree->pParent;
|
||||
p->pParent = 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
pRoot = p;
|
||||
}else{
|
||||
/* An error occurred. Delete the contents of the apLeaf[] array
|
||||
** and pFree list. Everything else is cleaned up by the call to
|
||||
** sqlite3Fts3ExprFree(pRoot) below. */
|
||||
Fts3Expr *pDel;
|
||||
for(i=0; i<nMaxDepth; i++){
|
||||
sqlite3Fts3ExprFree(apLeaf[i]);
|
||||
}
|
||||
while( (pDel=pFree)!=0 ){
|
||||
pFree = pDel->pParent;
|
||||
sqlite3_free(pDel);
|
||||
}
|
||||
}
|
||||
|
||||
assert( pFree==0 );
|
||||
sqlite3_free( apLeaf );
|
||||
}
|
||||
}else if( eType==FTSQUERY_NOT ){
|
||||
Fts3Expr *pLeft = pRoot->pLeft;
|
||||
Fts3Expr *pRight = pRoot->pRight;
|
||||
|
||||
pRoot->pLeft = 0;
|
||||
pRoot->pRight = 0;
|
||||
pLeft->pParent = 0;
|
||||
pRight->pParent = 0;
|
||||
|
||||
rc = fts3ExprBalance(&pLeft, nMaxDepth-1);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts3ExprBalance(&pRight, nMaxDepth-1);
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3Fts3ExprFree(pRight);
|
||||
sqlite3Fts3ExprFree(pLeft);
|
||||
}else{
|
||||
assert( pLeft && pRight );
|
||||
pRoot->pLeft = pLeft;
|
||||
pLeft->pParent = pRoot;
|
||||
pRoot->pRight = pRight;
|
||||
pRight->pParent = pRoot;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3Fts3ExprFree(pRoot);
|
||||
pRoot = 0;
|
||||
}
|
||||
*pp = pRoot;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** This function is similar to sqlite3Fts3ExprParse(), with the following
|
||||
** differences:
|
||||
**
|
||||
** 1. It does not do expression rebalancing.
|
||||
** 2. It does not check that the expression does not exceed the
|
||||
** maximum allowable depth.
|
||||
** 3. Even if it fails, *ppExpr may still be set to point to an
|
||||
** expression tree. It should be deleted using sqlite3Fts3ExprFree()
|
||||
** in this case.
|
||||
*/
|
||||
static int fts3ExprParseUnbalanced(
|
||||
sqlite3_tokenizer *pTokenizer, /* Tokenizer module */
|
||||
int iLangid, /* Language id for tokenizer */
|
||||
char **azCol, /* Array of column names for fts3 table */
|
||||
int bFts4, /* True to allow FTS4-only syntax */
|
||||
int nCol, /* Number of entries in azCol[] */
|
||||
int iDefaultCol, /* Default column to query */
|
||||
const char *z, int n, /* Text of MATCH query */
|
||||
Fts3Expr **ppExpr /* OUT: Parsed query structure */
|
||||
){
|
||||
int nParsed;
|
||||
int rc;
|
||||
ParseContext sParse;
|
||||
|
||||
memset(&sParse, 0, sizeof(ParseContext));
|
||||
sParse.pTokenizer = pTokenizer;
|
||||
sParse.iLangid = iLangid;
|
||||
sParse.azCol = (const char **)azCol;
|
||||
sParse.nCol = nCol;
|
||||
sParse.iDefaultCol = iDefaultCol;
|
||||
sParse.bFts4 = bFts4;
|
||||
if( z==0 ){
|
||||
*ppExpr = 0;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
if( n<0 ){
|
||||
n = (int)strlen(z);
|
||||
}
|
||||
rc = fts3ExprParse(&sParse, z, n, ppExpr, &nParsed);
|
||||
assert( rc==SQLITE_OK || *ppExpr==0 );
|
||||
|
||||
/* Check for mismatched parenthesis */
|
||||
if( rc==SQLITE_OK && sParse.nNest ){
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Parameters z and n contain a pointer to and length of a buffer containing
|
||||
** an fts3 query expression, respectively. This function attempts to parse the
|
||||
@@ -1021,80 +745,52 @@ static int fts3ExprParseUnbalanced(
|
||||
*/
|
||||
int sqlite3Fts3ExprParse(
|
||||
sqlite3_tokenizer *pTokenizer, /* Tokenizer module */
|
||||
int iLangid, /* Language id for tokenizer */
|
||||
char **azCol, /* Array of column names for fts3 table */
|
||||
int bFts4, /* True to allow FTS4-only syntax */
|
||||
int nCol, /* Number of entries in azCol[] */
|
||||
int iDefaultCol, /* Default column to query */
|
||||
const char *z, int n, /* Text of MATCH query */
|
||||
Fts3Expr **ppExpr, /* OUT: Parsed query structure */
|
||||
char **pzErr /* OUT: Error message (sqlite3_malloc) */
|
||||
Fts3Expr **ppExpr /* OUT: Parsed query structure */
|
||||
){
|
||||
int rc = fts3ExprParseUnbalanced(
|
||||
pTokenizer, iLangid, azCol, bFts4, nCol, iDefaultCol, z, n, ppExpr
|
||||
);
|
||||
|
||||
/* Rebalance the expression. And check that its depth does not exceed
|
||||
** SQLITE_FTS3_MAX_EXPR_DEPTH. */
|
||||
if( rc==SQLITE_OK && *ppExpr ){
|
||||
rc = fts3ExprBalance(ppExpr, SQLITE_FTS3_MAX_EXPR_DEPTH);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts3ExprCheckDepth(*ppExpr, SQLITE_FTS3_MAX_EXPR_DEPTH);
|
||||
}
|
||||
int nParsed;
|
||||
int rc;
|
||||
ParseContext sParse;
|
||||
sParse.pTokenizer = pTokenizer;
|
||||
sParse.azCol = (const char **)azCol;
|
||||
sParse.nCol = nCol;
|
||||
sParse.iDefaultCol = iDefaultCol;
|
||||
sParse.nNest = 0;
|
||||
sParse.bFts4 = bFts4;
|
||||
if( z==0 ){
|
||||
*ppExpr = 0;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
if( n<0 ){
|
||||
n = (int)strlen(z);
|
||||
}
|
||||
rc = fts3ExprParse(&sParse, z, n, ppExpr, &nParsed);
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
/* Check for mismatched parenthesis */
|
||||
if( rc==SQLITE_OK && sParse.nNest ){
|
||||
rc = SQLITE_ERROR;
|
||||
sqlite3Fts3ExprFree(*ppExpr);
|
||||
*ppExpr = 0;
|
||||
if( rc==SQLITE_TOOBIG ){
|
||||
sqlite3Fts3ErrMsg(pzErr,
|
||||
"FTS expression tree is too large (maximum depth %d)",
|
||||
SQLITE_FTS3_MAX_EXPR_DEPTH
|
||||
);
|
||||
rc = SQLITE_ERROR;
|
||||
}else if( rc==SQLITE_ERROR ){
|
||||
sqlite3Fts3ErrMsg(pzErr, "malformed MATCH expression: [%s]", z);
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Free a single node of an expression tree.
|
||||
*/
|
||||
static void fts3FreeExprNode(Fts3Expr *p){
|
||||
assert( p->eType==FTSQUERY_PHRASE || p->pPhrase==0 );
|
||||
sqlite3Fts3EvalPhraseCleanup(p->pPhrase);
|
||||
sqlite3_free(p->aMI);
|
||||
sqlite3_free(p);
|
||||
}
|
||||
|
||||
/*
|
||||
** Free a parsed fts3 query expression allocated by sqlite3Fts3ExprParse().
|
||||
**
|
||||
** This function would be simpler if it recursively called itself. But
|
||||
** that would mean passing a sufficiently large expression to ExprParse()
|
||||
** could cause a stack overflow.
|
||||
*/
|
||||
void sqlite3Fts3ExprFree(Fts3Expr *pDel){
|
||||
Fts3Expr *p;
|
||||
assert( pDel==0 || pDel->pParent==0 );
|
||||
for(p=pDel; p && (p->pLeft||p->pRight); p=(p->pLeft ? p->pLeft : p->pRight)){
|
||||
assert( p->pParent==0 || p==p->pParent->pRight || p==p->pParent->pLeft );
|
||||
}
|
||||
while( p ){
|
||||
Fts3Expr *pParent = p->pParent;
|
||||
fts3FreeExprNode(p);
|
||||
if( pParent && p==pParent->pLeft && pParent->pRight ){
|
||||
p = pParent->pRight;
|
||||
while( p && (p->pLeft || p->pRight) ){
|
||||
assert( p==p->pParent->pRight || p==p->pParent->pLeft );
|
||||
p = (p->pLeft ? p->pLeft : p->pRight);
|
||||
}
|
||||
}else{
|
||||
p = pParent;
|
||||
}
|
||||
void sqlite3Fts3ExprFree(Fts3Expr *p){
|
||||
if( p ){
|
||||
assert( p->eType==FTSQUERY_PHRASE || p->pPhrase==0 );
|
||||
sqlite3Fts3ExprFree(p->pLeft);
|
||||
sqlite3Fts3ExprFree(p->pRight);
|
||||
sqlite3Fts3EvalPhraseCleanup(p->pPhrase);
|
||||
sqlite3_free(p->aMI);
|
||||
sqlite3_free(p);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1107,6 +803,34 @@ void sqlite3Fts3ExprFree(Fts3Expr *pDel){
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
/*
|
||||
** Function to query the hash-table of tokenizers (see README.tokenizers).
|
||||
*/
|
||||
static int queryTestTokenizer(
|
||||
sqlite3 *db,
|
||||
const char *zName,
|
||||
const sqlite3_tokenizer_module **pp
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts3_tokenizer(?)";
|
||||
|
||||
*pp = 0;
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
|
||||
sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC);
|
||||
if( SQLITE_ROW==sqlite3_step(pStmt) ){
|
||||
if( sqlite3_column_type(pStmt, 0)==SQLITE_BLOB ){
|
||||
memcpy((void *)pp, sqlite3_column_blob(pStmt, 0), sizeof(*pp));
|
||||
}
|
||||
}
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to a buffer containing a text representation of the
|
||||
** expression passed as the first argument. The buffer is obtained from
|
||||
@@ -1118,9 +842,6 @@ void sqlite3Fts3ExprFree(Fts3Expr *pDel){
|
||||
** the returned expression text and then freed using sqlite3_free().
|
||||
*/
|
||||
static char *exprToString(Fts3Expr *pExpr, char *zBuf){
|
||||
if( pExpr==0 ){
|
||||
return sqlite3_mprintf("");
|
||||
}
|
||||
switch( pExpr->eType ){
|
||||
case FTSQUERY_PHRASE: {
|
||||
Fts3Phrase *pPhrase = pExpr->pPhrase;
|
||||
@@ -1174,12 +895,12 @@ static char *exprToString(Fts3Expr *pExpr, char *zBuf){
|
||||
**
|
||||
** SELECT fts3_exprtest('simple', 'Bill col2:Bloggs', 'col1', 'col2');
|
||||
*/
|
||||
static void fts3ExprTestCommon(
|
||||
int bRebalance,
|
||||
static void fts3ExprTest(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
sqlite3_tokenizer_module const *pModule = 0;
|
||||
sqlite3_tokenizer *pTokenizer = 0;
|
||||
int rc;
|
||||
char **azCol = 0;
|
||||
@@ -1189,9 +910,7 @@ static void fts3ExprTestCommon(
|
||||
int ii;
|
||||
Fts3Expr *pExpr;
|
||||
char *zBuf = 0;
|
||||
Fts3Hash *pHash = (Fts3Hash*)sqlite3_user_data(context);
|
||||
const char *zTokenizer = 0;
|
||||
char *zErr = 0;
|
||||
sqlite3 *db = sqlite3_context_db_handle(context);
|
||||
|
||||
if( argc<3 ){
|
||||
sqlite3_result_error(context,
|
||||
@@ -1200,22 +919,28 @@ static void fts3ExprTestCommon(
|
||||
return;
|
||||
}
|
||||
|
||||
zTokenizer = (const char*)sqlite3_value_text(argv[0]);
|
||||
rc = sqlite3Fts3InitTokenizer(pHash, zTokenizer, &pTokenizer, &zErr);
|
||||
if( rc!=SQLITE_OK ){
|
||||
if( rc==SQLITE_NOMEM ){
|
||||
sqlite3_result_error_nomem(context);
|
||||
}else{
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
}
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
rc = queryTestTokenizer(db,
|
||||
(const char *)sqlite3_value_text(argv[0]), &pModule);
|
||||
if( rc==SQLITE_NOMEM ){
|
||||
sqlite3_result_error_nomem(context);
|
||||
goto exprtest_out;
|
||||
}else if( !pModule ){
|
||||
sqlite3_result_error(context, "No such tokenizer module", -1);
|
||||
goto exprtest_out;
|
||||
}
|
||||
|
||||
rc = pModule->xCreate(0, 0, &pTokenizer);
|
||||
assert( rc==SQLITE_NOMEM || rc==SQLITE_OK );
|
||||
if( rc==SQLITE_NOMEM ){
|
||||
sqlite3_result_error_nomem(context);
|
||||
goto exprtest_out;
|
||||
}
|
||||
pTokenizer->pModule = pModule;
|
||||
|
||||
zExpr = (const char *)sqlite3_value_text(argv[1]);
|
||||
nExpr = sqlite3_value_bytes(argv[1]);
|
||||
nCol = argc-2;
|
||||
azCol = (char **)sqlite3_malloc64(nCol*sizeof(char *));
|
||||
azCol = (char **)sqlite3_malloc(nCol*sizeof(char *));
|
||||
if( !azCol ){
|
||||
sqlite3_result_error_nomem(context);
|
||||
goto exprtest_out;
|
||||
@@ -1224,21 +949,10 @@ static void fts3ExprTestCommon(
|
||||
azCol[ii] = (char *)sqlite3_value_text(argv[ii+2]);
|
||||
}
|
||||
|
||||
if( bRebalance ){
|
||||
char *zDummy = 0;
|
||||
rc = sqlite3Fts3ExprParse(
|
||||
pTokenizer, 0, azCol, 0, nCol, nCol, zExpr, nExpr, &pExpr, &zDummy
|
||||
);
|
||||
assert( rc==SQLITE_OK || pExpr==0 );
|
||||
sqlite3_free(zDummy);
|
||||
}else{
|
||||
rc = fts3ExprParseUnbalanced(
|
||||
pTokenizer, 0, azCol, 0, nCol, nCol, zExpr, nExpr, &pExpr
|
||||
);
|
||||
}
|
||||
|
||||
rc = sqlite3Fts3ExprParse(
|
||||
pTokenizer, azCol, 0, nCol, nCol, zExpr, nExpr, &pExpr
|
||||
);
|
||||
if( rc!=SQLITE_OK && rc!=SQLITE_NOMEM ){
|
||||
sqlite3Fts3ExprFree(pExpr);
|
||||
sqlite3_result_error(context, "Error parsing expression", -1);
|
||||
}else if( rc==SQLITE_NOMEM || !(zBuf = exprToString(pExpr, 0)) ){
|
||||
sqlite3_result_error_nomem(context);
|
||||
@@ -1250,41 +964,20 @@ static void fts3ExprTestCommon(
|
||||
sqlite3Fts3ExprFree(pExpr);
|
||||
|
||||
exprtest_out:
|
||||
if( pTokenizer ){
|
||||
rc = pTokenizer->pModule->xDestroy(pTokenizer);
|
||||
if( pModule && pTokenizer ){
|
||||
rc = pModule->xDestroy(pTokenizer);
|
||||
}
|
||||
sqlite3_free(azCol);
|
||||
}
|
||||
|
||||
static void fts3ExprTest(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
fts3ExprTestCommon(0, context, argc, argv);
|
||||
}
|
||||
static void fts3ExprTestRebalance(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
fts3ExprTestCommon(1, context, argc, argv);
|
||||
}
|
||||
|
||||
/*
|
||||
** Register the query expression parser test function fts3_exprtest()
|
||||
** with database connection db.
|
||||
*/
|
||||
int sqlite3Fts3ExprInitTestInterface(sqlite3 *db, Fts3Hash *pHash){
|
||||
int rc = sqlite3_create_function(
|
||||
db, "fts3_exprtest", -1, SQLITE_UTF8, (void*)pHash, fts3ExprTest, 0, 0
|
||||
int sqlite3Fts3ExprInitTestInterface(sqlite3* db){
|
||||
return sqlite3_create_function(
|
||||
db, "fts3_exprtest", -1, SQLITE_UTF8, 0, fts3ExprTest, 0, 0
|
||||
);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = sqlite3_create_function(db, "fts3_exprtest_rebalance",
|
||||
-1, SQLITE_UTF8, (void*)pHash, fts3ExprTestRebalance, 0, 0
|
||||
);
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
@@ -35,8 +35,8 @@
|
||||
/*
|
||||
** Malloc and Free functions
|
||||
*/
|
||||
static void *fts3HashMalloc(sqlite3_int64 n){
|
||||
void *p = sqlite3_malloc64(n);
|
||||
static void *fts3HashMalloc(int n){
|
||||
void *p = sqlite3_malloc(n);
|
||||
if( p ){
|
||||
memset(p, 0, n);
|
||||
}
|
||||
@@ -96,13 +96,13 @@ void sqlite3Fts3HashClear(Fts3Hash *pH){
|
||||
*/
|
||||
static int fts3StrHash(const void *pKey, int nKey){
|
||||
const char *z = (const char *)pKey;
|
||||
unsigned h = 0;
|
||||
int h = 0;
|
||||
if( nKey<=0 ) nKey = (int) strlen(z);
|
||||
while( nKey > 0 ){
|
||||
h = (h<<3) ^ h ^ *z++;
|
||||
nKey--;
|
||||
}
|
||||
return (int)(h & 0x7fffffff);
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int fts3StrCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
*************************************************************************
|
||||
** This is the header file for the generic hash-table implementation
|
||||
** This is the header file for the generic hash-table implemenation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
|
||||
+12
-16
@@ -60,7 +60,7 @@ static int icuCreate(
|
||||
if( argc>0 ){
|
||||
n = strlen(argv[0])+1;
|
||||
}
|
||||
p = (IcuTokenizer *)sqlite3_malloc64(sizeof(IcuTokenizer)+n);
|
||||
p = (IcuTokenizer *)sqlite3_malloc(sizeof(IcuTokenizer)+n);
|
||||
if( !p ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
@@ -110,16 +110,13 @@ static int icuOpen(
|
||||
|
||||
*ppCursor = 0;
|
||||
|
||||
if( zInput==0 ){
|
||||
nInput = 0;
|
||||
zInput = "";
|
||||
}else if( nInput<0 ){
|
||||
if( nInput<0 ){
|
||||
nInput = strlen(zInput);
|
||||
}
|
||||
nChar = nInput+1;
|
||||
pCsr = (IcuCursor *)sqlite3_malloc64(
|
||||
pCsr = (IcuCursor *)sqlite3_malloc(
|
||||
sizeof(IcuCursor) + /* IcuCursor */
|
||||
((nChar+3)&~3) * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
nChar * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
(nChar+1) * sizeof(int) /* IcuCursor.aOffset[] */
|
||||
);
|
||||
if( !pCsr ){
|
||||
@@ -127,7 +124,7 @@ static int icuOpen(
|
||||
}
|
||||
memset(pCsr, 0, sizeof(IcuCursor));
|
||||
pCsr->aChar = (UChar *)&pCsr[1];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[(nChar+3)&~3];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[nChar];
|
||||
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
@@ -199,7 +196,7 @@ static int icuNext(
|
||||
|
||||
while( iStart<iEnd ){
|
||||
int iWhite = iStart;
|
||||
U16_NEXT(pCsr->aChar, iWhite, pCsr->nChar, c);
|
||||
U8_NEXT(pCsr->aChar, iWhite, pCsr->nChar, c);
|
||||
if( u_isspace(c) ){
|
||||
iStart = iWhite;
|
||||
}else{
|
||||
@@ -240,13 +237,12 @@ static int icuNext(
|
||||
** The set of routines that implement the simple tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module icuTokenizerModule = {
|
||||
0, /* iVersion */
|
||||
icuCreate, /* xCreate */
|
||||
icuDestroy, /* xCreate */
|
||||
icuOpen, /* xOpen */
|
||||
icuClose, /* xClose */
|
||||
icuNext, /* xNext */
|
||||
0, /* xLanguageid */
|
||||
0, /* iVersion */
|
||||
icuCreate, /* xCreate */
|
||||
icuDestroy, /* xCreate */
|
||||
icuOpen, /* xOpen */
|
||||
icuClose, /* xClose */
|
||||
icuNext, /* xNext */
|
||||
};
|
||||
|
||||
/*
|
||||
|
||||
+30
-47
@@ -183,7 +183,7 @@ static int isVowel(const char *z){
|
||||
** by a consonant.
|
||||
**
|
||||
** In this routine z[] is in reverse order. So we are really looking
|
||||
** for an instance of a consonant followed by a vowel.
|
||||
** for an instance of of a consonant followed by a vowel.
|
||||
*/
|
||||
static int m_gt_0(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
@@ -403,14 +403,12 @@ static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
/* Step 2 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
if( !stem(&z, "lanoita", "ate", m_gt_0) ){
|
||||
stem(&z, "lanoit", "tion", m_gt_0);
|
||||
}
|
||||
stem(&z, "lanoita", "ate", m_gt_0) ||
|
||||
stem(&z, "lanoit", "tion", m_gt_0);
|
||||
break;
|
||||
case 'c':
|
||||
if( !stem(&z, "icne", "ence", m_gt_0) ){
|
||||
stem(&z, "icna", "ance", m_gt_0);
|
||||
}
|
||||
stem(&z, "icne", "ence", m_gt_0) ||
|
||||
stem(&z, "icna", "ance", m_gt_0);
|
||||
break;
|
||||
case 'e':
|
||||
stem(&z, "rezi", "ize", m_gt_0);
|
||||
@@ -419,54 +417,43 @@ static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
stem(&z, "igol", "log", m_gt_0);
|
||||
break;
|
||||
case 'l':
|
||||
if( !stem(&z, "ilb", "ble", m_gt_0)
|
||||
&& !stem(&z, "illa", "al", m_gt_0)
|
||||
&& !stem(&z, "iltne", "ent", m_gt_0)
|
||||
&& !stem(&z, "ile", "e", m_gt_0)
|
||||
){
|
||||
stem(&z, "ilsuo", "ous", m_gt_0);
|
||||
}
|
||||
stem(&z, "ilb", "ble", m_gt_0) ||
|
||||
stem(&z, "illa", "al", m_gt_0) ||
|
||||
stem(&z, "iltne", "ent", m_gt_0) ||
|
||||
stem(&z, "ile", "e", m_gt_0) ||
|
||||
stem(&z, "ilsuo", "ous", m_gt_0);
|
||||
break;
|
||||
case 'o':
|
||||
if( !stem(&z, "noitazi", "ize", m_gt_0)
|
||||
&& !stem(&z, "noita", "ate", m_gt_0)
|
||||
){
|
||||
stem(&z, "rota", "ate", m_gt_0);
|
||||
}
|
||||
stem(&z, "noitazi", "ize", m_gt_0) ||
|
||||
stem(&z, "noita", "ate", m_gt_0) ||
|
||||
stem(&z, "rota", "ate", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
if( !stem(&z, "msila", "al", m_gt_0)
|
||||
&& !stem(&z, "ssenevi", "ive", m_gt_0)
|
||||
&& !stem(&z, "ssenluf", "ful", m_gt_0)
|
||||
){
|
||||
stem(&z, "ssensuo", "ous", m_gt_0);
|
||||
}
|
||||
stem(&z, "msila", "al", m_gt_0) ||
|
||||
stem(&z, "ssenevi", "ive", m_gt_0) ||
|
||||
stem(&z, "ssenluf", "ful", m_gt_0) ||
|
||||
stem(&z, "ssensuo", "ous", m_gt_0);
|
||||
break;
|
||||
case 't':
|
||||
if( !stem(&z, "itila", "al", m_gt_0)
|
||||
&& !stem(&z, "itivi", "ive", m_gt_0)
|
||||
){
|
||||
stem(&z, "itilib", "ble", m_gt_0);
|
||||
}
|
||||
stem(&z, "itila", "al", m_gt_0) ||
|
||||
stem(&z, "itivi", "ive", m_gt_0) ||
|
||||
stem(&z, "itilib", "ble", m_gt_0);
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 3 */
|
||||
switch( z[0] ){
|
||||
case 'e':
|
||||
if( !stem(&z, "etaci", "ic", m_gt_0)
|
||||
&& !stem(&z, "evita", "", m_gt_0)
|
||||
){
|
||||
stem(&z, "ezila", "al", m_gt_0);
|
||||
}
|
||||
stem(&z, "etaci", "ic", m_gt_0) ||
|
||||
stem(&z, "evita", "", m_gt_0) ||
|
||||
stem(&z, "ezila", "al", m_gt_0);
|
||||
break;
|
||||
case 'i':
|
||||
stem(&z, "itici", "ic", m_gt_0);
|
||||
break;
|
||||
case 'l':
|
||||
if( !stem(&z, "laci", "ic", m_gt_0) ){
|
||||
stem(&z, "luf", "", m_gt_0);
|
||||
}
|
||||
stem(&z, "laci", "ic", m_gt_0) ||
|
||||
stem(&z, "luf", "", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
stem(&z, "ssen", "", m_gt_0);
|
||||
@@ -507,11 +494,9 @@ static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
z += 3;
|
||||
}
|
||||
}else if( z[2]=='e' ){
|
||||
if( !stem(&z, "tneme", "", m_gt_1)
|
||||
&& !stem(&z, "tnem", "", m_gt_1)
|
||||
){
|
||||
stem(&z, "tne", "", m_gt_1);
|
||||
}
|
||||
stem(&z, "tneme", "", m_gt_1) ||
|
||||
stem(&z, "tnem", "", m_gt_1) ||
|
||||
stem(&z, "tne", "", m_gt_1);
|
||||
}
|
||||
}
|
||||
break;
|
||||
@@ -530,9 +515,8 @@ static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
}
|
||||
break;
|
||||
case 't':
|
||||
if( !stem(&z, "eta", "", m_gt_1) ){
|
||||
stem(&z, "iti", "", m_gt_1);
|
||||
}
|
||||
stem(&z, "eta", "", m_gt_1) ||
|
||||
stem(&z, "iti", "", m_gt_1);
|
||||
break;
|
||||
case 'u':
|
||||
if( z[0]=='s' && z[2]=='o' && m_gt_1(z+3) ){
|
||||
@@ -646,7 +630,6 @@ static const sqlite3_tokenizer_module porterTokenizerModule = {
|
||||
porterOpen,
|
||||
porterClose,
|
||||
porterNext,
|
||||
0
|
||||
};
|
||||
|
||||
/*
|
||||
|
||||
+124
-348
@@ -27,8 +27,6 @@
|
||||
#define FTS3_MATCHINFO_LENGTH 'l' /* nCol values */
|
||||
#define FTS3_MATCHINFO_LCS 's' /* nCol values */
|
||||
#define FTS3_MATCHINFO_HITS 'x' /* 3*nCol*nPhrase values */
|
||||
#define FTS3_MATCHINFO_LHITS 'y' /* nCol*nPhrase values */
|
||||
#define FTS3_MATCHINFO_LHITS_BM 'b' /* nCol*nPhrase values */
|
||||
|
||||
/*
|
||||
** The default value for the second argument to matchinfo().
|
||||
@@ -90,22 +88,9 @@ struct MatchInfo {
|
||||
int nCol; /* Number of columns in table */
|
||||
int nPhrase; /* Number of matchable phrases in query */
|
||||
sqlite3_int64 nDoc; /* Number of docs in database */
|
||||
char flag;
|
||||
u32 *aMatchinfo; /* Pre-allocated buffer */
|
||||
};
|
||||
|
||||
/*
|
||||
** An instance of this structure is used to manage a pair of buffers, each
|
||||
** (nElem * sizeof(u32)) bytes in size. See the MatchinfoBuffer code below
|
||||
** for details.
|
||||
*/
|
||||
struct MatchinfoBuffer {
|
||||
u8 aRef[3];
|
||||
int nElem;
|
||||
int bGlobal; /* Set if global data is loaded */
|
||||
char *zMatchinfo;
|
||||
u32 aMatchinfo[1];
|
||||
};
|
||||
|
||||
|
||||
/*
|
||||
@@ -121,97 +106,6 @@ struct StrBuffer {
|
||||
};
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
** Start of MatchinfoBuffer code.
|
||||
*/
|
||||
|
||||
/*
|
||||
** Allocate a two-slot MatchinfoBuffer object.
|
||||
*/
|
||||
static MatchinfoBuffer *fts3MIBufferNew(int nElem, const char *zMatchinfo){
|
||||
MatchinfoBuffer *pRet;
|
||||
int nByte = sizeof(u32) * (2*nElem + 1) + sizeof(MatchinfoBuffer);
|
||||
int nStr = (int)strlen(zMatchinfo);
|
||||
|
||||
pRet = sqlite3_malloc(nByte + nStr+1);
|
||||
if( pRet ){
|
||||
memset(pRet, 0, nByte);
|
||||
pRet->aMatchinfo[0] = (u8*)(&pRet->aMatchinfo[1]) - (u8*)pRet;
|
||||
pRet->aMatchinfo[1+nElem] = pRet->aMatchinfo[0] + sizeof(u32)*(nElem+1);
|
||||
pRet->nElem = nElem;
|
||||
pRet->zMatchinfo = ((char*)pRet) + nByte;
|
||||
memcpy(pRet->zMatchinfo, zMatchinfo, nStr+1);
|
||||
pRet->aRef[0] = 1;
|
||||
}
|
||||
|
||||
return pRet;
|
||||
}
|
||||
|
||||
static void fts3MIBufferFree(void *p){
|
||||
MatchinfoBuffer *pBuf = (MatchinfoBuffer*)((u8*)p - ((u32*)p)[-1]);
|
||||
|
||||
assert( (u32*)p==&pBuf->aMatchinfo[1]
|
||||
|| (u32*)p==&pBuf->aMatchinfo[pBuf->nElem+2]
|
||||
);
|
||||
if( (u32*)p==&pBuf->aMatchinfo[1] ){
|
||||
pBuf->aRef[1] = 0;
|
||||
}else{
|
||||
pBuf->aRef[2] = 0;
|
||||
}
|
||||
|
||||
if( pBuf->aRef[0]==0 && pBuf->aRef[1]==0 && pBuf->aRef[2]==0 ){
|
||||
sqlite3_free(pBuf);
|
||||
}
|
||||
}
|
||||
|
||||
static void (*fts3MIBufferAlloc(MatchinfoBuffer *p, u32 **paOut))(void*){
|
||||
void (*xRet)(void*) = 0;
|
||||
u32 *aOut = 0;
|
||||
|
||||
if( p->aRef[1]==0 ){
|
||||
p->aRef[1] = 1;
|
||||
aOut = &p->aMatchinfo[1];
|
||||
xRet = fts3MIBufferFree;
|
||||
}
|
||||
else if( p->aRef[2]==0 ){
|
||||
p->aRef[2] = 1;
|
||||
aOut = &p->aMatchinfo[p->nElem+2];
|
||||
xRet = fts3MIBufferFree;
|
||||
}else{
|
||||
aOut = (u32*)sqlite3_malloc64(p->nElem * sizeof(u32));
|
||||
if( aOut ){
|
||||
xRet = sqlite3_free;
|
||||
if( p->bGlobal ) memcpy(aOut, &p->aMatchinfo[1], p->nElem*sizeof(u32));
|
||||
}
|
||||
}
|
||||
|
||||
*paOut = aOut;
|
||||
return xRet;
|
||||
}
|
||||
|
||||
static void fts3MIBufferSetGlobal(MatchinfoBuffer *p){
|
||||
p->bGlobal = 1;
|
||||
memcpy(&p->aMatchinfo[2+p->nElem], &p->aMatchinfo[1], p->nElem*sizeof(u32));
|
||||
}
|
||||
|
||||
/*
|
||||
** Free a MatchinfoBuffer object allocated using fts3MIBufferNew()
|
||||
*/
|
||||
void sqlite3Fts3MIBufferFree(MatchinfoBuffer *p){
|
||||
if( p ){
|
||||
assert( p->aRef[0]==1 );
|
||||
p->aRef[0] = 0;
|
||||
if( p->aRef[0]==0 && p->aRef[1]==0 && p->aRef[2]==0 ){
|
||||
sqlite3_free(p);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** End of MatchinfoBuffer code.
|
||||
*************************************************************************/
|
||||
|
||||
|
||||
/*
|
||||
** This function is used to help iterate through a position-list. A position
|
||||
** list is a list of unique integers, sorted from smallest to largest. Each
|
||||
@@ -234,7 +128,7 @@ void sqlite3Fts3MIBufferFree(MatchinfoBuffer *p){
|
||||
*/
|
||||
static void fts3GetDeltaPosition(char **pp, int *piPos){
|
||||
int iVal;
|
||||
*pp += fts3GetVarint32(*pp, &iVal);
|
||||
*pp += sqlite3Fts3GetVarint32(*pp, &iVal);
|
||||
*piPos += (iVal-2);
|
||||
}
|
||||
|
||||
@@ -248,7 +142,7 @@ static int fts3ExprIterate2(
|
||||
void *pCtx /* Second argument to pass to callback */
|
||||
){
|
||||
int rc; /* Return code */
|
||||
int eType = pExpr->eType; /* Type of expression node pExpr */
|
||||
int eType = pExpr->eType; /* Type of expression node pExpr */
|
||||
|
||||
if( eType!=FTSQUERY_PHRASE ){
|
||||
assert( pExpr->pLeft && pExpr->pRight );
|
||||
@@ -282,7 +176,6 @@ static int fts3ExprIterate(
|
||||
return fts3ExprIterate2(pExpr, &iPhrase, x, pCtx);
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** This is an fts3ExprIterate() callback used while loading the doclists
|
||||
** for each phrase into Fts3Expr.aDoclist[]/nDoclist. See also
|
||||
@@ -327,7 +220,8 @@ static int fts3ExprLoadDoclists(
|
||||
|
||||
static int fts3ExprPhraseCountCb(Fts3Expr *pExpr, int iPhrase, void *ctx){
|
||||
(*(int *)ctx)++;
|
||||
pExpr->iPhrase = iPhrase;
|
||||
UNUSED_PARAMETER(pExpr);
|
||||
UNUSED_PARAMETER(iPhrase);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
static int fts3ExprPhraseCount(Fts3Expr *pExpr){
|
||||
@@ -433,8 +327,7 @@ static void fts3SnippetDetails(
|
||||
int j;
|
||||
u64 mPhrase = (u64)1 << i;
|
||||
u64 mPos = (u64)1 << (iCsr - iStart);
|
||||
assert( iCsr>=iStart && (iCsr - iStart)<=64 );
|
||||
assert( i>=0 && i<=64 );
|
||||
assert( iCsr>=iStart );
|
||||
if( (mCover|mCovered)&mPhrase ){
|
||||
iScore++;
|
||||
}else{
|
||||
@@ -467,30 +360,24 @@ static int fts3SnippetFindPositions(Fts3Expr *pExpr, int iPhrase, void *ctx){
|
||||
SnippetIter *p = (SnippetIter *)ctx;
|
||||
SnippetPhrase *pPhrase = &p->aPhrase[iPhrase];
|
||||
char *pCsr;
|
||||
int rc;
|
||||
|
||||
pPhrase->nToken = pExpr->pPhrase->nToken;
|
||||
rc = sqlite3Fts3EvalPhrasePoslist(p->pCsr, pExpr, p->iCol, &pCsr);
|
||||
assert( rc==SQLITE_OK || pCsr==0 );
|
||||
|
||||
pCsr = sqlite3Fts3EvalPhrasePoslist(p->pCsr, pExpr, p->iCol);
|
||||
if( pCsr ){
|
||||
int iFirst = 0;
|
||||
pPhrase->pList = pCsr;
|
||||
fts3GetDeltaPosition(&pCsr, &iFirst);
|
||||
if( iFirst<0 ){
|
||||
rc = FTS_CORRUPT_VTAB;
|
||||
}else{
|
||||
pPhrase->pHead = pCsr;
|
||||
pPhrase->pTail = pCsr;
|
||||
pPhrase->iHead = iFirst;
|
||||
pPhrase->iTail = iFirst;
|
||||
}
|
||||
assert( iFirst>=0 );
|
||||
pPhrase->pHead = pCsr;
|
||||
pPhrase->pTail = pCsr;
|
||||
pPhrase->iHead = iFirst;
|
||||
pPhrase->iTail = iFirst;
|
||||
}else{
|
||||
assert( rc!=SQLITE_OK || (
|
||||
pPhrase->pList==0 && pPhrase->pHead==0 && pPhrase->pTail==0
|
||||
));
|
||||
assert( pPhrase->pList==0 && pPhrase->pHead==0 && pPhrase->pTail==0 );
|
||||
}
|
||||
|
||||
return rc;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -499,9 +386,9 @@ static int fts3SnippetFindPositions(Fts3Expr *pExpr, int iPhrase, void *ctx){
|
||||
** is the snippet with the highest score, where scores are calculated
|
||||
** by adding:
|
||||
**
|
||||
** (a) +1 point for each occurrence of a matchable phrase in the snippet.
|
||||
** (a) +1 point for each occurence of a matchable phrase in the snippet.
|
||||
**
|
||||
** (b) +1000 points for the first occurrence of each matchable phrase in
|
||||
** (b) +1000 points for the first occurence of each matchable phrase in
|
||||
** the snippet for which the corresponding mCovered bit is not set.
|
||||
**
|
||||
** The selected snippet parameters are stored in structure *pFragment before
|
||||
@@ -520,7 +407,7 @@ static int fts3BestSnippet(
|
||||
int rc; /* Return Code */
|
||||
int nList; /* Number of phrases in expression */
|
||||
SnippetIter sIter; /* Iterates through snippet candidates */
|
||||
sqlite3_int64 nByte; /* Number of bytes of space to allocate */
|
||||
int nByte; /* Number of bytes of space to allocate */
|
||||
int iBestScore = -1; /* Best snippet score found so far */
|
||||
int i; /* Loop counter */
|
||||
|
||||
@@ -538,7 +425,7 @@ static int fts3BestSnippet(
|
||||
** the required space using malloc().
|
||||
*/
|
||||
nByte = sizeof(SnippetPhrase) * nList;
|
||||
sIter.aPhrase = (SnippetPhrase *)sqlite3_malloc64(nByte);
|
||||
sIter.aPhrase = (SnippetPhrase *)sqlite3_malloc(nByte);
|
||||
if( !sIter.aPhrase ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
@@ -552,39 +439,37 @@ static int fts3BestSnippet(
|
||||
sIter.nSnippet = nSnippet;
|
||||
sIter.nPhrase = nList;
|
||||
sIter.iCurrent = -1;
|
||||
rc = fts3ExprIterate(pCsr->pExpr, fts3SnippetFindPositions, (void*)&sIter);
|
||||
if( rc==SQLITE_OK ){
|
||||
(void)fts3ExprIterate(pCsr->pExpr, fts3SnippetFindPositions, (void *)&sIter);
|
||||
|
||||
/* Set the *pmSeen output variable. */
|
||||
for(i=0; i<nList; i++){
|
||||
if( sIter.aPhrase[i].pHead ){
|
||||
*pmSeen |= (u64)1 << i;
|
||||
}
|
||||
/* Set the *pmSeen output variable. */
|
||||
for(i=0; i<nList; i++){
|
||||
if( sIter.aPhrase[i].pHead ){
|
||||
*pmSeen |= (u64)1 << i;
|
||||
}
|
||||
|
||||
/* Loop through all candidate snippets. Store the best snippet in
|
||||
** *pFragment. Store its associated 'score' in iBestScore.
|
||||
*/
|
||||
pFragment->iCol = iCol;
|
||||
while( !fts3SnippetNextCandidate(&sIter) ){
|
||||
int iPos;
|
||||
int iScore;
|
||||
u64 mCover;
|
||||
u64 mHighlite;
|
||||
fts3SnippetDetails(&sIter, mCovered, &iPos, &iScore, &mCover,&mHighlite);
|
||||
assert( iScore>=0 );
|
||||
if( iScore>iBestScore ){
|
||||
pFragment->iPos = iPos;
|
||||
pFragment->hlmask = mHighlite;
|
||||
pFragment->covered = mCover;
|
||||
iBestScore = iScore;
|
||||
}
|
||||
}
|
||||
|
||||
*piScore = iBestScore;
|
||||
}
|
||||
|
||||
/* Loop through all candidate snippets. Store the best snippet in
|
||||
** *pFragment. Store its associated 'score' in iBestScore.
|
||||
*/
|
||||
pFragment->iCol = iCol;
|
||||
while( !fts3SnippetNextCandidate(&sIter) ){
|
||||
int iPos;
|
||||
int iScore;
|
||||
u64 mCover;
|
||||
u64 mHighlight;
|
||||
fts3SnippetDetails(&sIter, mCovered, &iPos, &iScore, &mCover, &mHighlight);
|
||||
assert( iScore>=0 );
|
||||
if( iScore>iBestScore ){
|
||||
pFragment->iPos = iPos;
|
||||
pFragment->hlmask = mHighlight;
|
||||
pFragment->covered = mCover;
|
||||
iBestScore = iScore;
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_free(sIter.aPhrase);
|
||||
return rc;
|
||||
*piScore = iBestScore;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
|
||||
@@ -608,15 +493,14 @@ static int fts3StringAppend(
|
||||
** appended data.
|
||||
*/
|
||||
if( pStr->n+nAppend+1>=pStr->nAlloc ){
|
||||
sqlite3_int64 nAlloc = pStr->nAlloc+(sqlite3_int64)nAppend+100;
|
||||
char *zNew = sqlite3_realloc64(pStr->z, nAlloc);
|
||||
int nAlloc = pStr->nAlloc+nAppend+100;
|
||||
char *zNew = sqlite3_realloc(pStr->z, nAlloc);
|
||||
if( !zNew ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
pStr->z = zNew;
|
||||
pStr->nAlloc = nAlloc;
|
||||
}
|
||||
assert( pStr->z!=0 && (pStr->nAlloc >= pStr->n+nAppend+1) );
|
||||
|
||||
/* Append the data to the string buffer. */
|
||||
memcpy(&pStr->z[pStr->n], zAppend, nAppend);
|
||||
@@ -648,7 +532,6 @@ static int fts3StringAppend(
|
||||
*/
|
||||
static int fts3SnippetShift(
|
||||
Fts3Table *pTab, /* FTS3 table snippet comes from */
|
||||
int iLangid, /* Language id to use in tokenizing */
|
||||
int nSnippet, /* Number of tokens desired for snippet */
|
||||
const char *zDoc, /* Document text to extract snippet from */
|
||||
int nDoc, /* Size of buffer zDoc in bytes */
|
||||
@@ -664,7 +547,6 @@ static int fts3SnippetShift(
|
||||
|
||||
for(nLeft=0; !(hlmask & ((u64)1 << nLeft)); nLeft++);
|
||||
for(nRight=0; !(hlmask & ((u64)1 << (nSnippet-1-nRight))); nRight++);
|
||||
assert( (nSnippet-1-nRight)<=63 && (nSnippet-1-nRight)>=0 );
|
||||
nDesired = (nLeft-nRight)/2;
|
||||
|
||||
/* Ideally, the start of the snippet should be pushed forward in the
|
||||
@@ -685,12 +567,13 @@ static int fts3SnippetShift(
|
||||
/* Open a cursor on zDoc/nDoc. Check if there are (nSnippet+nDesired)
|
||||
** or more tokens in zDoc/nDoc.
|
||||
*/
|
||||
rc = sqlite3Fts3OpenTokenizer(pTab->pTokenizer, iLangid, zDoc, nDoc, &pC);
|
||||
rc = pMod->xOpen(pTab->pTokenizer, zDoc, nDoc, &pC);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
pC->pTokenizer = pTab->pTokenizer;
|
||||
while( rc==SQLITE_OK && iCurrent<(nSnippet+nDesired) ){
|
||||
const char *ZDUMMY; int DUMMY1 = 0, DUMMY2 = 0, DUMMY3 = 0;
|
||||
const char *ZDUMMY; int DUMMY1, DUMMY2, DUMMY3;
|
||||
rc = pMod->xNext(pC, &ZDUMMY, &DUMMY1, &DUMMY2, &DUMMY3, &iCurrent);
|
||||
}
|
||||
pMod->xClose(pC);
|
||||
@@ -734,6 +617,8 @@ static int fts3SnippetText(
|
||||
int iCol = pFragment->iCol+1; /* Query column to extract text from */
|
||||
sqlite3_tokenizer_module *pMod; /* Tokenizer module methods object */
|
||||
sqlite3_tokenizer_cursor *pC; /* Tokenizer cursor open on zDoc/nDoc */
|
||||
const char *ZDUMMY; /* Dummy argument used with tokenizer */
|
||||
int DUMMY1; /* Dummy argument used with tokenizer */
|
||||
|
||||
zDoc = (const char *)sqlite3_column_text(pCsr->pStmt, iCol);
|
||||
if( zDoc==0 ){
|
||||
@@ -746,29 +631,17 @@ static int fts3SnippetText(
|
||||
|
||||
/* Open a token cursor on the document. */
|
||||
pMod = (sqlite3_tokenizer_module *)pTab->pTokenizer->pModule;
|
||||
rc = sqlite3Fts3OpenTokenizer(pTab->pTokenizer, pCsr->iLangid, zDoc,nDoc,&pC);
|
||||
rc = pMod->xOpen(pTab->pTokenizer, zDoc, nDoc, &pC);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
pC->pTokenizer = pTab->pTokenizer;
|
||||
|
||||
while( rc==SQLITE_OK ){
|
||||
const char *ZDUMMY; /* Dummy argument used with tokenizer */
|
||||
int DUMMY1 = -1; /* Dummy argument used with tokenizer */
|
||||
int iBegin = 0; /* Offset in zDoc of start of token */
|
||||
int iFin = 0; /* Offset in zDoc of end of token */
|
||||
int isHighlight = 0; /* True for highlighted terms */
|
||||
int iBegin; /* Offset in zDoc of start of token */
|
||||
int iFin; /* Offset in zDoc of end of token */
|
||||
int isHighlight; /* True for highlighted terms */
|
||||
|
||||
/* Variable DUMMY1 is initialized to a negative value above. Elsewhere
|
||||
** in the FTS code the variable that the third argument to xNext points to
|
||||
** is initialized to zero before the first (*but not necessarily
|
||||
** subsequent*) call to xNext(). This is done for a particular application
|
||||
** that needs to know whether or not the tokenizer is being used for
|
||||
** snippet generation or for some other purpose.
|
||||
**
|
||||
** Extreme care is required when writing code to depend on this
|
||||
** initialization. It is not a documented part of the tokenizer interface.
|
||||
** If a tokenizer is used directly by any code outside of FTS, this
|
||||
** convention might not be respected. */
|
||||
rc = pMod->xNext(pC, &ZDUMMY, &DUMMY1, &iBegin, &iFin, &iCurrent);
|
||||
if( rc!=SQLITE_OK ){
|
||||
if( rc==SQLITE_DONE ){
|
||||
@@ -784,21 +657,15 @@ static int fts3SnippetText(
|
||||
|
||||
if( !isShiftDone ){
|
||||
int n = nDoc - iBegin;
|
||||
rc = fts3SnippetShift(
|
||||
pTab, pCsr->iLangid, nSnippet, &zDoc[iBegin], n, &iPos, &hlmask
|
||||
);
|
||||
rc = fts3SnippetShift(pTab, nSnippet, &zDoc[iBegin], n, &iPos, &hlmask);
|
||||
isShiftDone = 1;
|
||||
|
||||
/* Now that the shift has been done, check if the initial "..." are
|
||||
** required. They are required if (a) this is not the first fragment,
|
||||
** or (b) this fragment does not begin at position 0 of its column.
|
||||
*/
|
||||
if( rc==SQLITE_OK ){
|
||||
if( iPos>0 || iFragment>0 ){
|
||||
rc = fts3StringAppend(pOut, zEllipsis, -1);
|
||||
}else if( iBegin ){
|
||||
rc = fts3StringAppend(pOut, zDoc, iBegin);
|
||||
}
|
||||
if( rc==SQLITE_OK && (iPos>0 || iFragment>0) ){
|
||||
rc = fts3StringAppend(pOut, zEllipsis, -1);
|
||||
}
|
||||
if( rc!=SQLITE_OK || iCurrent<iPos ) continue;
|
||||
}
|
||||
@@ -854,64 +721,6 @@ static int fts3ColumnlistCount(char **ppCollist){
|
||||
return nEntry;
|
||||
}
|
||||
|
||||
/*
|
||||
** This function gathers 'y' or 'b' data for a single phrase.
|
||||
*/
|
||||
static int fts3ExprLHits(
|
||||
Fts3Expr *pExpr, /* Phrase expression node */
|
||||
MatchInfo *p /* Matchinfo context */
|
||||
){
|
||||
Fts3Table *pTab = (Fts3Table *)p->pCursor->base.pVtab;
|
||||
int iStart;
|
||||
Fts3Phrase *pPhrase = pExpr->pPhrase;
|
||||
char *pIter = pPhrase->doclist.pList;
|
||||
int iCol = 0;
|
||||
|
||||
assert( p->flag==FTS3_MATCHINFO_LHITS_BM || p->flag==FTS3_MATCHINFO_LHITS );
|
||||
if( p->flag==FTS3_MATCHINFO_LHITS ){
|
||||
iStart = pExpr->iPhrase * p->nCol;
|
||||
}else{
|
||||
iStart = pExpr->iPhrase * ((p->nCol + 31) / 32);
|
||||
}
|
||||
|
||||
while( 1 ){
|
||||
int nHit = fts3ColumnlistCount(&pIter);
|
||||
if( (pPhrase->iColumn>=pTab->nColumn || pPhrase->iColumn==iCol) ){
|
||||
if( p->flag==FTS3_MATCHINFO_LHITS ){
|
||||
p->aMatchinfo[iStart + iCol] = (u32)nHit;
|
||||
}else if( nHit ){
|
||||
p->aMatchinfo[iStart + (iCol+1)/32] |= (1 << (iCol&0x1F));
|
||||
}
|
||||
}
|
||||
assert( *pIter==0x00 || *pIter==0x01 );
|
||||
if( *pIter!=0x01 ) break;
|
||||
pIter++;
|
||||
pIter += fts3GetVarint32(pIter, &iCol);
|
||||
if( iCol>=p->nCol ) return FTS_CORRUPT_VTAB;
|
||||
}
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Gather the results for matchinfo directives 'y' and 'b'.
|
||||
*/
|
||||
static int fts3ExprLHitGather(
|
||||
Fts3Expr *pExpr,
|
||||
MatchInfo *p
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
assert( (pExpr->pLeft==0)==(pExpr->pRight==0) );
|
||||
if( pExpr->bEof==0 && pExpr->iDocid==p->pCursor->iPrevId ){
|
||||
if( pExpr->pLeft ){
|
||||
rc = fts3ExprLHitGather(pExpr->pLeft, p);
|
||||
if( rc==SQLITE_OK ) rc = fts3ExprLHitGather(pExpr->pRight, p);
|
||||
}else{
|
||||
rc = fts3ExprLHits(pExpr, p);
|
||||
}
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** fts3ExprIterate() callback used to collect the "global" matchinfo stats
|
||||
** for a single query.
|
||||
@@ -960,14 +769,13 @@ static int fts3ExprLocalHitsCb(
|
||||
int iPhrase, /* Phrase number */
|
||||
void *pCtx /* Pointer to MatchInfo structure */
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
MatchInfo *p = (MatchInfo *)pCtx;
|
||||
int iStart = iPhrase * p->nCol * 3;
|
||||
int i;
|
||||
|
||||
for(i=0; i<p->nCol && rc==SQLITE_OK; i++){
|
||||
for(i=0; i<p->nCol; i++){
|
||||
char *pCsr;
|
||||
rc = sqlite3Fts3EvalPhrasePoslist(p->pCursor, pExpr, i, &pCsr);
|
||||
pCsr = sqlite3Fts3EvalPhrasePoslist(p->pCursor, pExpr, i);
|
||||
if( pCsr ){
|
||||
p->aMatchinfo[iStart+i*3] = fts3ColumnlistCount(&pCsr);
|
||||
}else{
|
||||
@@ -975,7 +783,7 @@ static int fts3ExprLocalHitsCb(
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int fts3MatchinfoCheck(
|
||||
@@ -985,17 +793,15 @@ static int fts3MatchinfoCheck(
|
||||
){
|
||||
if( (cArg==FTS3_MATCHINFO_NPHRASE)
|
||||
|| (cArg==FTS3_MATCHINFO_NCOL)
|
||||
|| (cArg==FTS3_MATCHINFO_NDOC && pTab->bFts4)
|
||||
|| (cArg==FTS3_MATCHINFO_AVGLENGTH && pTab->bFts4)
|
||||
|| (cArg==FTS3_MATCHINFO_NDOC && pTab->bHasStat)
|
||||
|| (cArg==FTS3_MATCHINFO_AVGLENGTH && pTab->bHasStat)
|
||||
|| (cArg==FTS3_MATCHINFO_LENGTH && pTab->bHasDocsize)
|
||||
|| (cArg==FTS3_MATCHINFO_LCS)
|
||||
|| (cArg==FTS3_MATCHINFO_HITS)
|
||||
|| (cArg==FTS3_MATCHINFO_LHITS)
|
||||
|| (cArg==FTS3_MATCHINFO_LHITS_BM)
|
||||
){
|
||||
return SQLITE_OK;
|
||||
}
|
||||
sqlite3Fts3ErrMsg(pzErr, "unrecognized matchinfo request: %c", cArg);
|
||||
*pzErr = sqlite3_mprintf("unrecognized matchinfo request: %c", cArg);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
@@ -1015,14 +821,6 @@ static int fts3MatchinfoSize(MatchInfo *pInfo, char cArg){
|
||||
nVal = pInfo->nCol;
|
||||
break;
|
||||
|
||||
case FTS3_MATCHINFO_LHITS:
|
||||
nVal = pInfo->nCol * pInfo->nPhrase;
|
||||
break;
|
||||
|
||||
case FTS3_MATCHINFO_LHITS_BM:
|
||||
nVal = pInfo->nPhrase * ((pInfo->nCol + 31) / 32);
|
||||
break;
|
||||
|
||||
default:
|
||||
assert( cArg==FTS3_MATCHINFO_HITS );
|
||||
nVal = pInfo->nCol * pInfo->nPhrase * 3;
|
||||
@@ -1126,12 +924,11 @@ static int fts3MatchinfoLcs(Fts3Cursor *pCsr, MatchInfo *pInfo){
|
||||
int i;
|
||||
int iCol;
|
||||
int nToken = 0;
|
||||
int rc = SQLITE_OK;
|
||||
|
||||
/* Allocate and populate the array of LcsIterator objects. The array
|
||||
** contains one element for each matchable phrase in the query.
|
||||
**/
|
||||
aIter = sqlite3_malloc64(sizeof(LcsIterator) * pCsr->nPhrase);
|
||||
aIter = sqlite3_malloc(sizeof(LcsIterator) * pCsr->nPhrase);
|
||||
if( !aIter ) return SQLITE_NOMEM;
|
||||
memset(aIter, 0, sizeof(LcsIterator) * pCsr->nPhrase);
|
||||
(void)fts3ExprIterate(pCsr->pExpr, fts3MatchinfoLcsCb, (void*)aIter);
|
||||
@@ -1148,15 +945,10 @@ static int fts3MatchinfoLcs(Fts3Cursor *pCsr, MatchInfo *pInfo){
|
||||
|
||||
for(i=0; i<pInfo->nPhrase; i++){
|
||||
LcsIterator *pIt = &aIter[i];
|
||||
rc = sqlite3Fts3EvalPhrasePoslist(pCsr, pIt->pExpr, iCol, &pIt->pRead);
|
||||
if( rc!=SQLITE_OK ) goto matchinfo_lcs_out;
|
||||
pIt->pRead = sqlite3Fts3EvalPhrasePoslist(pCsr, pIt->pExpr, iCol);
|
||||
if( pIt->pRead ){
|
||||
pIt->iPos = pIt->iPosOffset;
|
||||
fts3LcsIteratorAdvance(pIt);
|
||||
if( pIt->pRead==0 ){
|
||||
rc = FTS_CORRUPT_VTAB;
|
||||
goto matchinfo_lcs_out;
|
||||
}
|
||||
fts3LcsIteratorAdvance(&aIter[i]);
|
||||
nLive++;
|
||||
}
|
||||
}
|
||||
@@ -1188,9 +980,8 @@ static int fts3MatchinfoLcs(Fts3Cursor *pCsr, MatchInfo *pInfo){
|
||||
pInfo->aMatchinfo[iCol] = nLcs;
|
||||
}
|
||||
|
||||
matchinfo_lcs_out:
|
||||
sqlite3_free(aIter);
|
||||
return rc;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1222,7 +1013,7 @@ static int fts3MatchinfoValues(
|
||||
sqlite3_stmt *pSelect = 0;
|
||||
|
||||
for(i=0; rc==SQLITE_OK && zArg[i]; i++){
|
||||
pInfo->flag = zArg[i];
|
||||
|
||||
switch( zArg[i] ){
|
||||
case FTS3_MATCHINFO_NPHRASE:
|
||||
if( bGlobal ) pInfo->aMatchinfo[0] = pInfo->nPhrase;
|
||||
@@ -1282,14 +1073,6 @@ static int fts3MatchinfoValues(
|
||||
}
|
||||
break;
|
||||
|
||||
case FTS3_MATCHINFO_LHITS_BM:
|
||||
case FTS3_MATCHINFO_LHITS: {
|
||||
int nZero = fts3MatchinfoSize(pInfo, zArg[i]) * sizeof(u32);
|
||||
memset(pInfo->aMatchinfo, 0, nZero);
|
||||
rc = fts3ExprLHitGather(pCsr->pExpr, pInfo);
|
||||
break;
|
||||
}
|
||||
|
||||
default: {
|
||||
Fts3Expr *pExpr;
|
||||
assert( zArg[i]==FTS3_MATCHINFO_HITS );
|
||||
@@ -1302,7 +1085,6 @@ static int fts3MatchinfoValues(
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
}
|
||||
rc = fts3ExprIterate(pExpr, fts3ExprGlobalHitsCb,(void*)pInfo);
|
||||
sqlite3Fts3EvalTestDeferred(pCsr, &rc);
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
}
|
||||
(void)fts3ExprIterate(pExpr, fts3ExprLocalHitsCb,(void*)pInfo);
|
||||
@@ -1322,8 +1104,7 @@ static int fts3MatchinfoValues(
|
||||
** Populate pCsr->aMatchinfo[] with data for the current row. The
|
||||
** 'matchinfo' data is an array of 32-bit unsigned integers (C type u32).
|
||||
*/
|
||||
static void fts3GetMatchinfo(
|
||||
sqlite3_context *pCtx, /* Return results here */
|
||||
static int fts3GetMatchinfo(
|
||||
Fts3Cursor *pCsr, /* FTS3 Cursor object */
|
||||
const char *zArg /* Second argument to matchinfo() function */
|
||||
){
|
||||
@@ -1332,9 +1113,6 @@ static void fts3GetMatchinfo(
|
||||
int rc = SQLITE_OK;
|
||||
int bGlobal = 0; /* Collect 'global' stats as well as local */
|
||||
|
||||
u32 *aOut = 0;
|
||||
void (*xDestroyOut)(void*) = 0;
|
||||
|
||||
memset(&sInfo, 0, sizeof(MatchInfo));
|
||||
sInfo.pCursor = pCsr;
|
||||
sInfo.nCol = pTab->nColumn;
|
||||
@@ -1342,18 +1120,21 @@ static void fts3GetMatchinfo(
|
||||
/* If there is cached matchinfo() data, but the format string for the
|
||||
** cache does not match the format string for this request, discard
|
||||
** the cached data. */
|
||||
if( pCsr->pMIBuffer && strcmp(pCsr->pMIBuffer->zMatchinfo, zArg) ){
|
||||
sqlite3Fts3MIBufferFree(pCsr->pMIBuffer);
|
||||
pCsr->pMIBuffer = 0;
|
||||
if( pCsr->zMatchinfo && strcmp(pCsr->zMatchinfo, zArg) ){
|
||||
assert( pCsr->aMatchinfo );
|
||||
sqlite3_free(pCsr->aMatchinfo);
|
||||
pCsr->zMatchinfo = 0;
|
||||
pCsr->aMatchinfo = 0;
|
||||
}
|
||||
|
||||
/* If Fts3Cursor.pMIBuffer is NULL, then this is the first time the
|
||||
/* If Fts3Cursor.aMatchinfo[] is NULL, then this is the first time the
|
||||
** matchinfo function has been called for this query. In this case
|
||||
** allocate the array used to accumulate the matchinfo data and
|
||||
** initialize those elements that are constant for every row.
|
||||
*/
|
||||
if( pCsr->pMIBuffer==0 ){
|
||||
if( pCsr->aMatchinfo==0 ){
|
||||
int nMatchinfo = 0; /* Number of u32 elements in match-info */
|
||||
int nArg; /* Bytes in zArg */
|
||||
int i; /* Used to iterate through zArg */
|
||||
|
||||
/* Determine the number of phrases in the query */
|
||||
@@ -1362,46 +1143,30 @@ static void fts3GetMatchinfo(
|
||||
|
||||
/* Determine the number of integers in the buffer returned by this call. */
|
||||
for(i=0; zArg[i]; i++){
|
||||
char *zErr = 0;
|
||||
if( fts3MatchinfoCheck(pTab, zArg[i], &zErr) ){
|
||||
sqlite3_result_error(pCtx, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
nMatchinfo += fts3MatchinfoSize(&sInfo, zArg[i]);
|
||||
}
|
||||
|
||||
/* Allocate space for Fts3Cursor.aMatchinfo[] and Fts3Cursor.zMatchinfo. */
|
||||
pCsr->pMIBuffer = fts3MIBufferNew(nMatchinfo, zArg);
|
||||
if( !pCsr->pMIBuffer ) rc = SQLITE_NOMEM;
|
||||
nArg = (int)strlen(zArg);
|
||||
pCsr->aMatchinfo = (u32 *)sqlite3_malloc(sizeof(u32)*nMatchinfo + nArg + 1);
|
||||
if( !pCsr->aMatchinfo ) return SQLITE_NOMEM;
|
||||
|
||||
pCsr->zMatchinfo = (char *)&pCsr->aMatchinfo[nMatchinfo];
|
||||
pCsr->nMatchinfo = nMatchinfo;
|
||||
memcpy(pCsr->zMatchinfo, zArg, nArg+1);
|
||||
memset(pCsr->aMatchinfo, 0, sizeof(u32)*nMatchinfo);
|
||||
pCsr->isMatchinfoNeeded = 1;
|
||||
bGlobal = 1;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
xDestroyOut = fts3MIBufferAlloc(pCsr->pMIBuffer, &aOut);
|
||||
if( xDestroyOut==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
sInfo.aMatchinfo = aOut;
|
||||
sInfo.nPhrase = pCsr->nPhrase;
|
||||
sInfo.aMatchinfo = pCsr->aMatchinfo;
|
||||
sInfo.nPhrase = pCsr->nPhrase;
|
||||
if( pCsr->isMatchinfoNeeded ){
|
||||
rc = fts3MatchinfoValues(pCsr, bGlobal, &sInfo, zArg);
|
||||
if( bGlobal ){
|
||||
fts3MIBufferSetGlobal(pCsr->pMIBuffer);
|
||||
}
|
||||
pCsr->isMatchinfoNeeded = 0;
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3_result_error_code(pCtx, rc);
|
||||
if( xDestroyOut ) xDestroyOut(aOut);
|
||||
}else{
|
||||
int n = pCsr->pMIBuffer->nElem * sizeof(u32);
|
||||
sqlite3_result_blob(pCtx, aOut, n, xDestroyOut);
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1438,10 +1203,6 @@ void sqlite3Fts3Snippet(
|
||||
return;
|
||||
}
|
||||
|
||||
/* Limit the snippet length to 64 tokens. */
|
||||
if( nToken<-64 ) nToken = -64;
|
||||
if( nToken>+64 ) nToken = +64;
|
||||
|
||||
for(nSnippet=1; 1; nSnippet++){
|
||||
|
||||
int iSnip; /* Loop counter 0..nSnippet-1 */
|
||||
@@ -1467,7 +1228,7 @@ void sqlite3Fts3Snippet(
|
||||
*/
|
||||
for(iRead=0; iRead<pTab->nColumn; iRead++){
|
||||
SnippetFragment sF = {0, 0, 0, 0};
|
||||
int iS = 0;
|
||||
int iS;
|
||||
if( iCol>=0 && iRead!=iCol ) continue;
|
||||
|
||||
/* Find the best snippet of nFToken tokens in column iRead. */
|
||||
@@ -1536,10 +1297,9 @@ static int fts3ExprTermOffsetInit(Fts3Expr *pExpr, int iPhrase, void *ctx){
|
||||
int iTerm; /* For looping through nTerm phrase terms */
|
||||
char *pList; /* Pointer to position list for phrase */
|
||||
int iPos = 0; /* First position in position-list */
|
||||
int rc;
|
||||
|
||||
UNUSED_PARAMETER(iPhrase);
|
||||
rc = sqlite3Fts3EvalPhrasePoslist(p->pCsr, pExpr, p->iCol, &pList);
|
||||
pList = sqlite3Fts3EvalPhrasePoslist(p->pCsr, pExpr, p->iCol);
|
||||
nTerm = pExpr->pPhrase->nToken;
|
||||
if( pList ){
|
||||
fts3GetDeltaPosition(&pList, &iPos);
|
||||
@@ -1553,7 +1313,7 @@ static int fts3ExprTermOffsetInit(Fts3Expr *pExpr, int iPhrase, void *ctx){
|
||||
pT->iPos = iPos;
|
||||
}
|
||||
|
||||
return rc;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1565,6 +1325,8 @@ void sqlite3Fts3Offsets(
|
||||
){
|
||||
Fts3Table *pTab = (Fts3Table *)pCsr->base.pVtab;
|
||||
sqlite3_tokenizer_module const *pMod = pTab->pTokenizer->pModule;
|
||||
const char *ZDUMMY; /* Dummy argument used with xNext() */
|
||||
int NDUMMY; /* Dummy argument used with xNext() */
|
||||
int rc; /* Return Code */
|
||||
int nToken; /* Number of tokens in query */
|
||||
int iCol; /* Column currently being processed */
|
||||
@@ -1584,7 +1346,7 @@ void sqlite3Fts3Offsets(
|
||||
if( rc!=SQLITE_OK ) goto offsets_out;
|
||||
|
||||
/* Allocate the array of TermOffset iterators. */
|
||||
sCtx.aTerm = (TermOffset *)sqlite3_malloc64(sizeof(TermOffset)*nToken);
|
||||
sCtx.aTerm = (TermOffset *)sqlite3_malloc(sizeof(TermOffset)*nToken);
|
||||
if( 0==sCtx.aTerm ){
|
||||
rc = SQLITE_NOMEM;
|
||||
goto offsets_out;
|
||||
@@ -1597,11 +1359,9 @@ void sqlite3Fts3Offsets(
|
||||
*/
|
||||
for(iCol=0; iCol<pTab->nColumn; iCol++){
|
||||
sqlite3_tokenizer_cursor *pC; /* Tokenizer cursor */
|
||||
const char *ZDUMMY; /* Dummy argument used with xNext() */
|
||||
int NDUMMY = 0; /* Dummy argument used with xNext() */
|
||||
int iStart = 0;
|
||||
int iEnd = 0;
|
||||
int iCurrent = 0;
|
||||
int iStart;
|
||||
int iEnd;
|
||||
int iCurrent;
|
||||
const char *zDoc;
|
||||
int nDoc;
|
||||
|
||||
@@ -1611,7 +1371,7 @@ void sqlite3Fts3Offsets(
|
||||
*/
|
||||
sCtx.iCol = iCol;
|
||||
sCtx.iTerm = 0;
|
||||
(void)fts3ExprIterate(pCsr->pExpr, fts3ExprTermOffsetInit, (void*)&sCtx);
|
||||
(void)fts3ExprIterate(pCsr->pExpr, fts3ExprTermOffsetInit, (void *)&sCtx);
|
||||
|
||||
/* Retreive the text stored in column iCol. If an SQL NULL is stored
|
||||
** in column iCol, jump immediately to the next iteration of the loop.
|
||||
@@ -1630,10 +1390,9 @@ void sqlite3Fts3Offsets(
|
||||
}
|
||||
|
||||
/* Initialize a tokenizer iterator to iterate through column iCol. */
|
||||
rc = sqlite3Fts3OpenTokenizer(pTab->pTokenizer, pCsr->iLangid,
|
||||
zDoc, nDoc, &pC
|
||||
);
|
||||
rc = pMod->xOpen(pTab->pTokenizer, zDoc, nDoc, &pC);
|
||||
if( rc!=SQLITE_OK ) goto offsets_out;
|
||||
pC->pTokenizer = pTab->pTokenizer;
|
||||
|
||||
rc = pMod->xNext(pC, &ZDUMMY, &NDUMMY, &iStart, &iEnd, &iCurrent);
|
||||
while( rc==SQLITE_OK ){
|
||||
@@ -1703,9 +1462,19 @@ void sqlite3Fts3Matchinfo(
|
||||
const char *zArg /* Second arg to matchinfo() function */
|
||||
){
|
||||
Fts3Table *pTab = (Fts3Table *)pCsr->base.pVtab;
|
||||
int rc;
|
||||
int i;
|
||||
const char *zFormat;
|
||||
|
||||
if( zArg ){
|
||||
for(i=0; zArg[i]; i++){
|
||||
char *zErr = 0;
|
||||
if( fts3MatchinfoCheck(pTab, zArg[i], &zErr) ){
|
||||
sqlite3_result_error(pContext, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
}
|
||||
zFormat = zArg;
|
||||
}else{
|
||||
zFormat = FTS3_MATCHINFO_DEFAULT;
|
||||
@@ -1714,10 +1483,17 @@ void sqlite3Fts3Matchinfo(
|
||||
if( !pCsr->pExpr ){
|
||||
sqlite3_result_blob(pContext, "", 0, SQLITE_STATIC);
|
||||
return;
|
||||
}
|
||||
|
||||
/* Retrieve matchinfo() data. */
|
||||
rc = fts3GetMatchinfo(pCsr, zFormat);
|
||||
sqlite3Fts3SegmentsClose(pTab);
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3_result_error_code(pContext, rc);
|
||||
}else{
|
||||
/* Retrieve matchinfo() data. */
|
||||
fts3GetMatchinfo(pContext, pCsr, zFormat);
|
||||
sqlite3Fts3SegmentsClose(pTab);
|
||||
int n = pCsr->nMatchinfo * sizeof(u32);
|
||||
sqlite3_result_blob(pContext, pCsr->aMatchinfo, n, SQLITE_TRANSIENT);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+10
-15
@@ -68,12 +68,11 @@ static int fts3termConnectMethod(
|
||||
char const *zFts3; /* Name of fts3 table */
|
||||
int nDb; /* Result of strlen(zDb) */
|
||||
int nFts3; /* Result of strlen(zFts3) */
|
||||
sqlite3_int64 nByte; /* Bytes of space to allocate here */
|
||||
int nByte; /* Bytes of space to allocate here */
|
||||
int rc; /* value returned by declare_vtab() */
|
||||
Fts3termTable *p; /* Virtual table object to return */
|
||||
Fts3termTable *p; /* Virtual table object to return */
|
||||
int iIndex = 0;
|
||||
|
||||
UNUSED_PARAMETER(pCtx);
|
||||
if( argc==5 ){
|
||||
iIndex = atoi(argv[4]);
|
||||
argc--;
|
||||
@@ -81,22 +80,22 @@ static int fts3termConnectMethod(
|
||||
|
||||
/* The user should specify a single argument - the name of an fts3 table. */
|
||||
if( argc!=4 ){
|
||||
sqlite3Fts3ErrMsg(pzErr,
|
||||
*pzErr = sqlite3_mprintf(
|
||||
"wrong number of arguments to fts4term constructor"
|
||||
);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
zDb = argv[1];
|
||||
nDb = (int)strlen(zDb);
|
||||
nDb = strlen(zDb);
|
||||
zFts3 = argv[3];
|
||||
nFts3 = (int)strlen(zFts3);
|
||||
nFts3 = strlen(zFts3);
|
||||
|
||||
rc = sqlite3_declare_vtab(db, FTS3_TERMS_SCHEMA);
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
|
||||
nByte = sizeof(Fts3termTable) + sizeof(Fts3Table) + nDb + nFts3 + 2;
|
||||
p = (Fts3termTable *)sqlite3_malloc64(nByte);
|
||||
p = (Fts3termTable *)sqlite3_malloc(nByte);
|
||||
if( !p ) return SQLITE_NOMEM;
|
||||
memset(p, 0, nByte);
|
||||
|
||||
@@ -232,12 +231,12 @@ static int fts3termNextMethod(sqlite3_vtab_cursor *pCursor){
|
||||
|
||||
if( v==1 ){
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
pCsr->iCol += (int)v;
|
||||
pCsr->iCol += v;
|
||||
pCsr->iPos = 0;
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
}
|
||||
|
||||
pCsr->iPos += (int)(v - 2);
|
||||
pCsr->iPos += (v - 2);
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
@@ -272,7 +271,7 @@ static int fts3termFilterMethod(
|
||||
pCsr->filter.flags = FTS3_SEGMENT_REQUIRE_POS|FTS3_SEGMENT_IGNORE_EMPTY;
|
||||
pCsr->filter.flags |= FTS3_SEGMENT_SCAN;
|
||||
|
||||
rc = sqlite3Fts3SegReaderCursor(pFts3, 0, p->iIndex, FTS3_SEGCURSOR_ALL,
|
||||
rc = sqlite3Fts3SegReaderCursor(pFts3, p->iIndex, FTS3_SEGCURSOR_ALL,
|
||||
pCsr->filter.zTerm, pCsr->filter.nTerm, 0, 1, &pCsr->csr
|
||||
);
|
||||
if( rc==SQLITE_OK ){
|
||||
@@ -358,11 +357,7 @@ int sqlite3Fts3InitTerm(sqlite3 *db){
|
||||
0, /* xCommit */
|
||||
0, /* xRollback */
|
||||
0, /* xFindFunction */
|
||||
0, /* xRename */
|
||||
0, /* xSavepoint */
|
||||
0, /* xRelease */
|
||||
0, /* xRollbackTo */
|
||||
0 /* xShadowName */
|
||||
0 /* xRename */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
|
||||
+5
-302
@@ -13,24 +13,13 @@
|
||||
** This file is not part of the production FTS code. It is only used for
|
||||
** testing. It contains a Tcl command that can be used to test if a document
|
||||
** matches an FTS NEAR expression.
|
||||
**
|
||||
** As of March 2012, it also contains a version 1 tokenizer used for testing
|
||||
** that the sqlite3_tokenizer_module.xLanguage() method is invoked correctly.
|
||||
*/
|
||||
|
||||
#if defined(INCLUDE_SQLITE_TCL_H)
|
||||
# include "sqlite_tcl.h"
|
||||
#else
|
||||
# include "tcl.h"
|
||||
# ifndef SQLITE_TCLAPI
|
||||
# define SQLITE_TCLAPI
|
||||
# endif
|
||||
#endif
|
||||
#include <tcl.h>
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
|
||||
#if defined(SQLITE_TEST)
|
||||
#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
/* Required so that the "ifdef SQLITE_ENABLE_FTS3" below works */
|
||||
#include "fts3Int.h"
|
||||
@@ -150,7 +139,7 @@ static int nm_match_count(
|
||||
/*
|
||||
** Tclcmd: fts3_near_match DOCUMENT EXPR ?OPTIONS?
|
||||
*/
|
||||
static int SQLITE_TCLAPI fts3_near_match_cmd(
|
||||
static int fts3_near_match_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
@@ -169,8 +158,6 @@ static int SQLITE_TCLAPI fts3_near_match_cmd(
|
||||
Tcl_Obj **apExprToken;
|
||||
int nExprToken;
|
||||
|
||||
UNUSED_PARAMETER(clientData);
|
||||
|
||||
/* Must have 3 or more arguments. */
|
||||
if( objc<3 || (objc%2)==0 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "DOCUMENT EXPR ?OPTION VALUE?...");
|
||||
@@ -274,7 +261,7 @@ static int SQLITE_TCLAPI fts3_near_match_cmd(
|
||||
**
|
||||
** Whether or not the arguments are present, this command returns a list of
|
||||
** two integers - the initial chunksize and threshold when the command is
|
||||
** invoked. This can be used to restore the default behavior after running
|
||||
** invoked. This can be used to restore the default behaviour after running
|
||||
** tests. For example:
|
||||
**
|
||||
** # Override incr-load settings for testing:
|
||||
@@ -285,7 +272,7 @@ static int SQLITE_TCLAPI fts3_near_match_cmd(
|
||||
** # Restore initial incr-load settings:
|
||||
** eval fts3_configure_incr_load $cfg
|
||||
*/
|
||||
static int SQLITE_TCLAPI fts3_configure_incr_load_cmd(
|
||||
static int fts3_configure_incr_load_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
@@ -324,280 +311,6 @@ static int SQLITE_TCLAPI fts3_configure_incr_load_cmd(
|
||||
Tcl_SetObjResult(interp, pRet);
|
||||
Tcl_DecrRefCount(pRet);
|
||||
#endif
|
||||
UNUSED_PARAMETER(clientData);
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
#ifdef SQLITE_ENABLE_FTS3
|
||||
/**************************************************************************
|
||||
** Beginning of test tokenizer code.
|
||||
**
|
||||
** For language 0, this tokenizer is similar to the default 'simple'
|
||||
** tokenizer. For other languages L, the following:
|
||||
**
|
||||
** * Odd numbered languages are case-sensitive. Even numbered
|
||||
** languages are not.
|
||||
**
|
||||
** * Language ids 100 or greater are considered an error.
|
||||
**
|
||||
** The implementation assumes that the input contains only ASCII characters
|
||||
** (i.e. those that may be encoded in UTF-8 using a single byte).
|
||||
*/
|
||||
typedef struct test_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
} test_tokenizer;
|
||||
|
||||
typedef struct test_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *aInput; /* Input being tokenized */
|
||||
int nInput; /* Size of the input in bytes */
|
||||
int iInput; /* Current offset in aInput */
|
||||
int iToken; /* Index of next token to be returned */
|
||||
char *aBuffer; /* Buffer containing current token */
|
||||
int nBuffer; /* Number of bytes allocated at pToken */
|
||||
int iLangid; /* Configured language id */
|
||||
} test_tokenizer_cursor;
|
||||
|
||||
static int testTokenizerCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
test_tokenizer *pNew;
|
||||
UNUSED_PARAMETER(argc);
|
||||
UNUSED_PARAMETER(argv);
|
||||
|
||||
pNew = sqlite3_malloc(sizeof(test_tokenizer));
|
||||
if( !pNew ) return SQLITE_NOMEM;
|
||||
memset(pNew, 0, sizeof(test_tokenizer));
|
||||
|
||||
*ppTokenizer = (sqlite3_tokenizer *)pNew;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int testTokenizerDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
test_tokenizer *p = (test_tokenizer *)pTokenizer;
|
||||
sqlite3_free(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int testTokenizerOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *pInput, int nBytes, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
test_tokenizer_cursor *pCsr; /* New cursor object */
|
||||
|
||||
UNUSED_PARAMETER(pTokenizer);
|
||||
|
||||
pCsr = (test_tokenizer_cursor *)sqlite3_malloc(sizeof(test_tokenizer_cursor));
|
||||
if( pCsr==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memset(pCsr, 0, sizeof(test_tokenizer_cursor));
|
||||
pCsr->aInput = pInput;
|
||||
if( nBytes<0 ){
|
||||
pCsr->nInput = (int)strlen(pInput);
|
||||
}else{
|
||||
pCsr->nInput = nBytes;
|
||||
}
|
||||
}
|
||||
|
||||
*ppCursor = (sqlite3_tokenizer_cursor *)pCsr;
|
||||
return rc;
|
||||
}
|
||||
|
||||
static int testTokenizerClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
test_tokenizer_cursor *pCsr = (test_tokenizer_cursor *)pCursor;
|
||||
sqlite3_free(pCsr->aBuffer);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int testIsTokenChar(char c){
|
||||
return (c>='a' && c<='z') || (c>='A' && c<='Z');
|
||||
}
|
||||
static int testTolower(char c){
|
||||
char ret = c;
|
||||
if( ret>='A' && ret<='Z') ret = ret - ('A'-'a');
|
||||
return ret;
|
||||
}
|
||||
|
||||
static int testTokenizerNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by testTokenizerOpen */
|
||||
const char **ppToken, /* OUT: *ppToken is the token text */
|
||||
int *pnBytes, /* OUT: Number of bytes in token */
|
||||
int *piStartOffset, /* OUT: Starting offset of token */
|
||||
int *piEndOffset, /* OUT: Ending offset of token */
|
||||
int *piPosition /* OUT: Position integer of token */
|
||||
){
|
||||
test_tokenizer_cursor *pCsr = (test_tokenizer_cursor *)pCursor;
|
||||
int rc = SQLITE_OK;
|
||||
const char *p;
|
||||
const char *pEnd;
|
||||
|
||||
p = &pCsr->aInput[pCsr->iInput];
|
||||
pEnd = &pCsr->aInput[pCsr->nInput];
|
||||
|
||||
/* Skip past any white-space */
|
||||
assert( p<=pEnd );
|
||||
while( p<pEnd && testIsTokenChar(*p)==0 ) p++;
|
||||
|
||||
if( p==pEnd ){
|
||||
rc = SQLITE_DONE;
|
||||
}else{
|
||||
/* Advance to the end of the token */
|
||||
const char *pToken = p;
|
||||
int nToken;
|
||||
while( p<pEnd && testIsTokenChar(*p) ) p++;
|
||||
nToken = (int)(p-pToken);
|
||||
|
||||
/* Copy the token into the buffer */
|
||||
if( nToken>pCsr->nBuffer ){
|
||||
sqlite3_free(pCsr->aBuffer);
|
||||
pCsr->aBuffer = sqlite3_malloc(nToken);
|
||||
}
|
||||
if( pCsr->aBuffer==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
int i;
|
||||
|
||||
if( pCsr->iLangid & 0x00000001 ){
|
||||
for(i=0; i<nToken; i++) pCsr->aBuffer[i] = pToken[i];
|
||||
}else{
|
||||
for(i=0; i<nToken; i++) pCsr->aBuffer[i] = (char)testTolower(pToken[i]);
|
||||
}
|
||||
pCsr->iToken++;
|
||||
pCsr->iInput = (int)(p - pCsr->aInput);
|
||||
|
||||
*ppToken = pCsr->aBuffer;
|
||||
*pnBytes = nToken;
|
||||
*piStartOffset = (int)(pToken - pCsr->aInput);
|
||||
*piEndOffset = (int)(p - pCsr->aInput);
|
||||
*piPosition = pCsr->iToken;
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
static int testTokenizerLanguage(
|
||||
sqlite3_tokenizer_cursor *pCursor,
|
||||
int iLangid
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
test_tokenizer_cursor *pCsr = (test_tokenizer_cursor *)pCursor;
|
||||
pCsr->iLangid = iLangid;
|
||||
if( pCsr->iLangid>=100 ){
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
#endif
|
||||
|
||||
static int SQLITE_TCLAPI fts3_test_tokenizer_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
#ifdef SQLITE_ENABLE_FTS3
|
||||
static const sqlite3_tokenizer_module testTokenizerModule = {
|
||||
1,
|
||||
testTokenizerCreate,
|
||||
testTokenizerDestroy,
|
||||
testTokenizerOpen,
|
||||
testTokenizerClose,
|
||||
testTokenizerNext,
|
||||
testTokenizerLanguage
|
||||
};
|
||||
const sqlite3_tokenizer_module *pPtr = &testTokenizerModule;
|
||||
if( objc!=1 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
Tcl_SetObjResult(interp, Tcl_NewByteArrayObj(
|
||||
(const unsigned char *)&pPtr, sizeof(sqlite3_tokenizer_module *)
|
||||
));
|
||||
#endif
|
||||
UNUSED_PARAMETER(clientData);
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
static int SQLITE_TCLAPI fts3_test_varint_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
#ifdef SQLITE_ENABLE_FTS3
|
||||
char aBuf[24];
|
||||
int rc;
|
||||
Tcl_WideInt w;
|
||||
sqlite3_int64 w2;
|
||||
int nByte, nByte2;
|
||||
|
||||
if( objc!=2 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "INTEGER");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
rc = Tcl_GetWideIntFromObj(interp, objv[1], &w);
|
||||
if( rc!=TCL_OK ) return rc;
|
||||
|
||||
nByte = sqlite3Fts3PutVarint(aBuf, w);
|
||||
nByte2 = sqlite3Fts3GetVarint(aBuf, &w2);
|
||||
if( w!=w2 || nByte!=nByte2 ){
|
||||
char *zErr = sqlite3_mprintf("error testing %lld", w);
|
||||
Tcl_ResetResult(interp);
|
||||
Tcl_AppendResult(interp, zErr, 0);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
if( w<=2147483647 && w>=0 ){
|
||||
int i;
|
||||
nByte2 = fts3GetVarint32(aBuf, &i);
|
||||
if( (int)w!=i || nByte!=nByte2 ){
|
||||
char *zErr = sqlite3_mprintf("error testing %lld (32-bit)", w);
|
||||
Tcl_ResetResult(interp);
|
||||
Tcl_AppendResult(interp, zErr, 0);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
}
|
||||
|
||||
#endif
|
||||
UNUSED_PARAMETER(clientData);
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** End of tokenizer code.
|
||||
**************************************************************************/
|
||||
|
||||
/*
|
||||
** sqlite3_fts3_may_be_corrupt BOOLEAN
|
||||
**
|
||||
** Set or clear the global "may-be-corrupt" flag. Return the old value.
|
||||
*/
|
||||
static int SQLITE_TCLAPI fts3_may_be_corrupt(
|
||||
void * clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
int bOld = sqlite3_fts3_may_be_corrupt;
|
||||
|
||||
if( objc!=2 && objc!=1 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "?BOOLEAN?");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
if( objc==2 ){
|
||||
int bNew;
|
||||
if( Tcl_GetBooleanFromObj(interp, objv[1], &bNew) ) return TCL_ERROR;
|
||||
sqlite3_fts3_may_be_corrupt = bNew;
|
||||
}
|
||||
|
||||
Tcl_SetObjResult(interp, Tcl_NewIntObj(bOld));
|
||||
return TCL_OK;
|
||||
}
|
||||
|
||||
@@ -606,16 +319,6 @@ int Sqlitetestfts3_Init(Tcl_Interp *interp){
|
||||
Tcl_CreateObjCommand(interp,
|
||||
"fts3_configure_incr_load", fts3_configure_incr_load_cmd, 0, 0
|
||||
);
|
||||
Tcl_CreateObjCommand(
|
||||
interp, "fts3_test_tokenizer", fts3_test_tokenizer_cmd, 0, 0
|
||||
);
|
||||
Tcl_CreateObjCommand(
|
||||
interp, "fts3_test_varint", fts3_test_varint_cmd, 0, 0
|
||||
);
|
||||
Tcl_CreateObjCommand(
|
||||
interp, "sqlite3_fts3_may_be_corrupt", fts3_may_be_corrupt, 0, 0
|
||||
);
|
||||
return TCL_OK;
|
||||
}
|
||||
#endif /* SQLITE_ENABLE_FTS3 || SQLITE_ENABLE_FTS4 */
|
||||
#endif /* ifdef SQLITE_TEST */
|
||||
|
||||
@@ -1,455 +0,0 @@
|
||||
/*
|
||||
** 2013 Apr 22
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
**
|
||||
** This file contains code for the "fts3tokenize" virtual table module.
|
||||
** An fts3tokenize virtual table is created as follows:
|
||||
**
|
||||
** CREATE VIRTUAL TABLE <tbl> USING fts3tokenize(
|
||||
** <tokenizer-name>, <arg-1>, ...
|
||||
** );
|
||||
**
|
||||
** The table created has the following schema:
|
||||
**
|
||||
** CREATE TABLE <tbl>(input, token, start, end, position)
|
||||
**
|
||||
** When queried, the query must include a WHERE clause of type:
|
||||
**
|
||||
** input = <string>
|
||||
**
|
||||
** The virtual table module tokenizes this <string>, using the FTS3
|
||||
** tokenizer specified by the arguments to the CREATE VIRTUAL TABLE
|
||||
** statement and returns one row for each token in the result. With
|
||||
** fields set as follows:
|
||||
**
|
||||
** input: Always set to a copy of <string>
|
||||
** token: A token from the input.
|
||||
** start: Byte offset of the token within the input <string>.
|
||||
** end: Byte offset of the byte immediately following the end of the
|
||||
** token within the input string.
|
||||
** pos: Token offset of token within input.
|
||||
**
|
||||
*/
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
|
||||
typedef struct Fts3tokTable Fts3tokTable;
|
||||
typedef struct Fts3tokCursor Fts3tokCursor;
|
||||
|
||||
/*
|
||||
** Virtual table structure.
|
||||
*/
|
||||
struct Fts3tokTable {
|
||||
sqlite3_vtab base; /* Base class used by SQLite core */
|
||||
const sqlite3_tokenizer_module *pMod;
|
||||
sqlite3_tokenizer *pTok;
|
||||
};
|
||||
|
||||
/*
|
||||
** Virtual table cursor structure.
|
||||
*/
|
||||
struct Fts3tokCursor {
|
||||
sqlite3_vtab_cursor base; /* Base class used by SQLite core */
|
||||
char *zInput; /* Input string */
|
||||
sqlite3_tokenizer_cursor *pCsr; /* Cursor to iterate through zInput */
|
||||
int iRowid; /* Current 'rowid' value */
|
||||
const char *zToken; /* Current 'token' value */
|
||||
int nToken; /* Size of zToken in bytes */
|
||||
int iStart; /* Current 'start' value */
|
||||
int iEnd; /* Current 'end' value */
|
||||
int iPos; /* Current 'pos' value */
|
||||
};
|
||||
|
||||
/*
|
||||
** Query FTS for the tokenizer implementation named zName.
|
||||
*/
|
||||
static int fts3tokQueryTokenizer(
|
||||
Fts3Hash *pHash,
|
||||
const char *zName,
|
||||
const sqlite3_tokenizer_module **pp,
|
||||
char **pzErr
|
||||
){
|
||||
sqlite3_tokenizer_module *p;
|
||||
int nName = (int)strlen(zName);
|
||||
|
||||
p = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash, zName, nName+1);
|
||||
if( !p ){
|
||||
sqlite3Fts3ErrMsg(pzErr, "unknown tokenizer: %s", zName);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
*pp = p;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** The second argument, argv[], is an array of pointers to nul-terminated
|
||||
** strings. This function makes a copy of the array and strings into a
|
||||
** single block of memory. It then dequotes any of the strings that appear
|
||||
** to be quoted.
|
||||
**
|
||||
** If successful, output parameter *pazDequote is set to point at the
|
||||
** array of dequoted strings and SQLITE_OK is returned. The caller is
|
||||
** responsible for eventually calling sqlite3_free() to free the array
|
||||
** in this case. Or, if an error occurs, an SQLite error code is returned.
|
||||
** The final value of *pazDequote is undefined in this case.
|
||||
*/
|
||||
static int fts3tokDequoteArray(
|
||||
int argc, /* Number of elements in argv[] */
|
||||
const char * const *argv, /* Input array */
|
||||
char ***pazDequote /* Output array */
|
||||
){
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
if( argc==0 ){
|
||||
*pazDequote = 0;
|
||||
}else{
|
||||
int i;
|
||||
int nByte = 0;
|
||||
char **azDequote;
|
||||
|
||||
for(i=0; i<argc; i++){
|
||||
nByte += (int)(strlen(argv[i]) + 1);
|
||||
}
|
||||
|
||||
*pazDequote = azDequote = sqlite3_malloc64(sizeof(char *)*argc + nByte);
|
||||
if( azDequote==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
char *pSpace = (char *)&azDequote[argc];
|
||||
for(i=0; i<argc; i++){
|
||||
int n = (int)strlen(argv[i]);
|
||||
azDequote[i] = pSpace;
|
||||
memcpy(pSpace, argv[i], n+1);
|
||||
sqlite3Fts3Dequote(pSpace);
|
||||
pSpace += (n+1);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Schema of the tokenizer table.
|
||||
*/
|
||||
#define FTS3_TOK_SCHEMA "CREATE TABLE x(input, token, start, end, position)"
|
||||
|
||||
/*
|
||||
** This function does all the work for both the xConnect and xCreate methods.
|
||||
** These tables have no persistent representation of their own, so xConnect
|
||||
** and xCreate are identical operations.
|
||||
**
|
||||
** argv[0]: module name
|
||||
** argv[1]: database name
|
||||
** argv[2]: table name
|
||||
** argv[3]: first argument (tokenizer name)
|
||||
*/
|
||||
static int fts3tokConnectMethod(
|
||||
sqlite3 *db, /* Database connection */
|
||||
void *pHash, /* Hash table of tokenizers */
|
||||
int argc, /* Number of elements in argv array */
|
||||
const char * const *argv, /* xCreate/xConnect argument array */
|
||||
sqlite3_vtab **ppVtab, /* OUT: New sqlite3_vtab object */
|
||||
char **pzErr /* OUT: sqlite3_malloc'd error message */
|
||||
){
|
||||
Fts3tokTable *pTab = 0;
|
||||
const sqlite3_tokenizer_module *pMod = 0;
|
||||
sqlite3_tokenizer *pTok = 0;
|
||||
int rc;
|
||||
char **azDequote = 0;
|
||||
int nDequote;
|
||||
|
||||
rc = sqlite3_declare_vtab(db, FTS3_TOK_SCHEMA);
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
|
||||
nDequote = argc-3;
|
||||
rc = fts3tokDequoteArray(nDequote, &argv[3], &azDequote);
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
const char *zModule;
|
||||
if( nDequote<1 ){
|
||||
zModule = "simple";
|
||||
}else{
|
||||
zModule = azDequote[0];
|
||||
}
|
||||
rc = fts3tokQueryTokenizer((Fts3Hash*)pHash, zModule, &pMod, pzErr);
|
||||
}
|
||||
|
||||
assert( (rc==SQLITE_OK)==(pMod!=0) );
|
||||
if( rc==SQLITE_OK ){
|
||||
const char * const *azArg = (const char * const *)&azDequote[1];
|
||||
rc = pMod->xCreate((nDequote>1 ? nDequote-1 : 0), azArg, &pTok);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
pTab = (Fts3tokTable *)sqlite3_malloc(sizeof(Fts3tokTable));
|
||||
if( pTab==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
memset(pTab, 0, sizeof(Fts3tokTable));
|
||||
pTab->pMod = pMod;
|
||||
pTab->pTok = pTok;
|
||||
*ppVtab = &pTab->base;
|
||||
}else{
|
||||
if( pTok ){
|
||||
pMod->xDestroy(pTok);
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_free(azDequote);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** This function does the work for both the xDisconnect and xDestroy methods.
|
||||
** These tables have no persistent representation of their own, so xDisconnect
|
||||
** and xDestroy are identical operations.
|
||||
*/
|
||||
static int fts3tokDisconnectMethod(sqlite3_vtab *pVtab){
|
||||
Fts3tokTable *pTab = (Fts3tokTable *)pVtab;
|
||||
|
||||
pTab->pMod->xDestroy(pTab->pTok);
|
||||
sqlite3_free(pTab);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xBestIndex - Analyze a WHERE and ORDER BY clause.
|
||||
*/
|
||||
static int fts3tokBestIndexMethod(
|
||||
sqlite3_vtab *pVTab,
|
||||
sqlite3_index_info *pInfo
|
||||
){
|
||||
int i;
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
for(i=0; i<pInfo->nConstraint; i++){
|
||||
if( pInfo->aConstraint[i].usable
|
||||
&& pInfo->aConstraint[i].iColumn==0
|
||||
&& pInfo->aConstraint[i].op==SQLITE_INDEX_CONSTRAINT_EQ
|
||||
){
|
||||
pInfo->idxNum = 1;
|
||||
pInfo->aConstraintUsage[i].argvIndex = 1;
|
||||
pInfo->aConstraintUsage[i].omit = 1;
|
||||
pInfo->estimatedCost = 1;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
|
||||
pInfo->idxNum = 0;
|
||||
assert( pInfo->estimatedCost>1000000.0 );
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xOpen - Open a cursor.
|
||||
*/
|
||||
static int fts3tokOpenMethod(sqlite3_vtab *pVTab, sqlite3_vtab_cursor **ppCsr){
|
||||
Fts3tokCursor *pCsr;
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
pCsr = (Fts3tokCursor *)sqlite3_malloc(sizeof(Fts3tokCursor));
|
||||
if( pCsr==0 ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(pCsr, 0, sizeof(Fts3tokCursor));
|
||||
|
||||
*ppCsr = (sqlite3_vtab_cursor *)pCsr;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Reset the tokenizer cursor passed as the only argument. As if it had
|
||||
** just been returned by fts3tokOpenMethod().
|
||||
*/
|
||||
static void fts3tokResetCursor(Fts3tokCursor *pCsr){
|
||||
if( pCsr->pCsr ){
|
||||
Fts3tokTable *pTab = (Fts3tokTable *)(pCsr->base.pVtab);
|
||||
pTab->pMod->xClose(pCsr->pCsr);
|
||||
pCsr->pCsr = 0;
|
||||
}
|
||||
sqlite3_free(pCsr->zInput);
|
||||
pCsr->zInput = 0;
|
||||
pCsr->zToken = 0;
|
||||
pCsr->nToken = 0;
|
||||
pCsr->iStart = 0;
|
||||
pCsr->iEnd = 0;
|
||||
pCsr->iPos = 0;
|
||||
pCsr->iRowid = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** xClose - Close a cursor.
|
||||
*/
|
||||
static int fts3tokCloseMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
|
||||
fts3tokResetCursor(pCsr);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xNext - Advance the cursor to the next row, if any.
|
||||
*/
|
||||
static int fts3tokNextMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
Fts3tokTable *pTab = (Fts3tokTable *)(pCursor->pVtab);
|
||||
int rc; /* Return code */
|
||||
|
||||
pCsr->iRowid++;
|
||||
rc = pTab->pMod->xNext(pCsr->pCsr,
|
||||
&pCsr->zToken, &pCsr->nToken,
|
||||
&pCsr->iStart, &pCsr->iEnd, &pCsr->iPos
|
||||
);
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
fts3tokResetCursor(pCsr);
|
||||
if( rc==SQLITE_DONE ) rc = SQLITE_OK;
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** xFilter - Initialize a cursor to point at the start of its data.
|
||||
*/
|
||||
static int fts3tokFilterMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* The cursor used for this query */
|
||||
int idxNum, /* Strategy index */
|
||||
const char *idxStr, /* Unused */
|
||||
int nVal, /* Number of elements in apVal */
|
||||
sqlite3_value **apVal /* Arguments for the indexing scheme */
|
||||
){
|
||||
int rc = SQLITE_ERROR;
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
Fts3tokTable *pTab = (Fts3tokTable *)(pCursor->pVtab);
|
||||
UNUSED_PARAMETER(idxStr);
|
||||
UNUSED_PARAMETER(nVal);
|
||||
|
||||
fts3tokResetCursor(pCsr);
|
||||
if( idxNum==1 ){
|
||||
const char *zByte = (const char *)sqlite3_value_text(apVal[0]);
|
||||
int nByte = sqlite3_value_bytes(apVal[0]);
|
||||
pCsr->zInput = sqlite3_malloc(nByte+1);
|
||||
if( pCsr->zInput==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memcpy(pCsr->zInput, zByte, nByte);
|
||||
pCsr->zInput[nByte] = 0;
|
||||
rc = pTab->pMod->xOpen(pTab->pTok, pCsr->zInput, nByte, &pCsr->pCsr);
|
||||
if( rc==SQLITE_OK ){
|
||||
pCsr->pCsr->pTokenizer = pTab->pTok;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
return fts3tokNextMethod(pCursor);
|
||||
}
|
||||
|
||||
/*
|
||||
** xEof - Return true if the cursor is at EOF, or false otherwise.
|
||||
*/
|
||||
static int fts3tokEofMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
return (pCsr->zToken==0);
|
||||
}
|
||||
|
||||
/*
|
||||
** xColumn - Return a column value.
|
||||
*/
|
||||
static int fts3tokColumnMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* Cursor to retrieve value from */
|
||||
sqlite3_context *pCtx, /* Context for sqlite3_result_xxx() calls */
|
||||
int iCol /* Index of column to read value from */
|
||||
){
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
|
||||
/* CREATE TABLE x(input, token, start, end, position) */
|
||||
switch( iCol ){
|
||||
case 0:
|
||||
sqlite3_result_text(pCtx, pCsr->zInput, -1, SQLITE_TRANSIENT);
|
||||
break;
|
||||
case 1:
|
||||
sqlite3_result_text(pCtx, pCsr->zToken, pCsr->nToken, SQLITE_TRANSIENT);
|
||||
break;
|
||||
case 2:
|
||||
sqlite3_result_int(pCtx, pCsr->iStart);
|
||||
break;
|
||||
case 3:
|
||||
sqlite3_result_int(pCtx, pCsr->iEnd);
|
||||
break;
|
||||
default:
|
||||
assert( iCol==4 );
|
||||
sqlite3_result_int(pCtx, pCsr->iPos);
|
||||
break;
|
||||
}
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xRowid - Return the current rowid for the cursor.
|
||||
*/
|
||||
static int fts3tokRowidMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* Cursor to retrieve value from */
|
||||
sqlite_int64 *pRowid /* OUT: Rowid value */
|
||||
){
|
||||
Fts3tokCursor *pCsr = (Fts3tokCursor *)pCursor;
|
||||
*pRowid = (sqlite3_int64)pCsr->iRowid;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Register the fts3tok module with database connection db. Return SQLITE_OK
|
||||
** if successful or an error code if sqlite3_create_module() fails.
|
||||
*/
|
||||
int sqlite3Fts3InitTok(sqlite3 *db, Fts3Hash *pHash){
|
||||
static const sqlite3_module fts3tok_module = {
|
||||
0, /* iVersion */
|
||||
fts3tokConnectMethod, /* xCreate */
|
||||
fts3tokConnectMethod, /* xConnect */
|
||||
fts3tokBestIndexMethod, /* xBestIndex */
|
||||
fts3tokDisconnectMethod, /* xDisconnect */
|
||||
fts3tokDisconnectMethod, /* xDestroy */
|
||||
fts3tokOpenMethod, /* xOpen */
|
||||
fts3tokCloseMethod, /* xClose */
|
||||
fts3tokFilterMethod, /* xFilter */
|
||||
fts3tokNextMethod, /* xNext */
|
||||
fts3tokEofMethod, /* xEof */
|
||||
fts3tokColumnMethod, /* xColumn */
|
||||
fts3tokRowidMethod, /* xRowid */
|
||||
0, /* xUpdate */
|
||||
0, /* xBegin */
|
||||
0, /* xSync */
|
||||
0, /* xCommit */
|
||||
0, /* xRollback */
|
||||
0, /* xFindFunction */
|
||||
0, /* xRename */
|
||||
0, /* xSavepoint */
|
||||
0, /* xRelease */
|
||||
0, /* xRollbackTo */
|
||||
0 /* xShadowName */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
rc = sqlite3_create_module(db, "fts3tokenize", &fts3tok_module, (void*)pHash);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
+48
-75
@@ -29,18 +29,6 @@
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
|
||||
/*
|
||||
** Return true if the two-argument version of fts3_tokenizer()
|
||||
** has been activated via a prior call to sqlite3_db_config(db,
|
||||
** SQLITE_DBCONFIG_ENABLE_FTS3_TOKENIZER, 1, 0);
|
||||
*/
|
||||
static int fts3TokenizerEnabled(sqlite3_context *context){
|
||||
sqlite3 *db = sqlite3_context_db_handle(context);
|
||||
int isEnabled = 0;
|
||||
sqlite3_db_config(db,SQLITE_DBCONFIG_ENABLE_FTS3_TOKENIZER,-1,&isEnabled);
|
||||
return isEnabled;
|
||||
}
|
||||
|
||||
/*
|
||||
** Implementation of the SQL scalar function for accessing the underlying
|
||||
** hash table. This function may be called as follows:
|
||||
@@ -61,7 +49,7 @@ static int fts3TokenizerEnabled(sqlite3_context *context){
|
||||
** is a blob containing the pointer stored as the hash data corresponding
|
||||
** to string <key-name> (after the hash-table is updated, if applicable).
|
||||
*/
|
||||
static void fts3TokenizerFunc(
|
||||
static void scalarFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
@@ -79,26 +67,20 @@ static void fts3TokenizerFunc(
|
||||
nName = sqlite3_value_bytes(argv[0])+1;
|
||||
|
||||
if( argc==2 ){
|
||||
if( fts3TokenizerEnabled(context) ){
|
||||
void *pOld;
|
||||
int n = sqlite3_value_bytes(argv[1]);
|
||||
if( zName==0 || n!=sizeof(pPtr) ){
|
||||
sqlite3_result_error(context, "argument type mismatch", -1);
|
||||
return;
|
||||
}
|
||||
pPtr = *(void **)sqlite3_value_blob(argv[1]);
|
||||
pOld = sqlite3Fts3HashInsert(pHash, (void *)zName, nName, pPtr);
|
||||
if( pOld==pPtr ){
|
||||
sqlite3_result_error(context, "out of memory", -1);
|
||||
}
|
||||
}else{
|
||||
sqlite3_result_error(context, "fts3tokenize disabled", -1);
|
||||
void *pOld;
|
||||
int n = sqlite3_value_bytes(argv[1]);
|
||||
if( n!=sizeof(pPtr) ){
|
||||
sqlite3_result_error(context, "argument type mismatch", -1);
|
||||
return;
|
||||
}
|
||||
pPtr = *(void **)sqlite3_value_blob(argv[1]);
|
||||
pOld = sqlite3Fts3HashInsert(pHash, (void *)zName, nName, pPtr);
|
||||
if( pOld==pPtr ){
|
||||
sqlite3_result_error(context, "out of memory", -1);
|
||||
return;
|
||||
}
|
||||
}else{
|
||||
if( zName ){
|
||||
pPtr = sqlite3Fts3HashFind(pHash, zName, nName);
|
||||
}
|
||||
pPtr = sqlite3Fts3HashFind(pHash, zName, nName);
|
||||
if( !pPtr ){
|
||||
char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
@@ -106,6 +88,7 @@ static void fts3TokenizerFunc(
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_result_blob(context, (void *)&pPtr, sizeof(pPtr), SQLITE_TRANSIENT);
|
||||
}
|
||||
|
||||
@@ -178,16 +161,12 @@ int sqlite3Fts3InitTokenizer(
|
||||
zEnd = &zCopy[strlen(zCopy)];
|
||||
|
||||
z = (char *)sqlite3Fts3NextToken(zCopy, &n);
|
||||
if( z==0 ){
|
||||
assert( n==0 );
|
||||
z = zCopy;
|
||||
}
|
||||
z[n] = '\0';
|
||||
sqlite3Fts3Dequote(z);
|
||||
|
||||
m = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash,z,(int)strlen(z)+1);
|
||||
if( !m ){
|
||||
sqlite3Fts3ErrMsg(pzErr, "unknown tokenizer: %s", z);
|
||||
*pzErr = sqlite3_mprintf("unknown tokenizer: %s", z);
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
char const **aArg = 0;
|
||||
@@ -210,7 +189,7 @@ int sqlite3Fts3InitTokenizer(
|
||||
rc = m->xCreate(iArg, aArg, ppTok);
|
||||
assert( rc!=SQLITE_OK || *ppTok );
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3Fts3ErrMsg(pzErr, "unknown tokenizer");
|
||||
*pzErr = sqlite3_mprintf("unknown tokenizer");
|
||||
}else{
|
||||
(*ppTok)->pModule = m;
|
||||
}
|
||||
@@ -224,19 +203,16 @@ int sqlite3Fts3InitTokenizer(
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
#if defined(INCLUDE_SQLITE_TCL_H)
|
||||
# include "sqlite_tcl.h"
|
||||
#else
|
||||
# include "tcl.h"
|
||||
#endif
|
||||
#include <tcl.h>
|
||||
#include <string.h>
|
||||
|
||||
/*
|
||||
** Implementation of a special SQL scalar function for testing tokenizers
|
||||
** designed to be used in concert with the Tcl testing framework. This
|
||||
** function must be called with two or more arguments:
|
||||
** function must be called with two arguments:
|
||||
**
|
||||
** SELECT <function-name>(<key-name>, ..., <input-string>);
|
||||
** SELECT <function-name>(<key-name>, <input-string>);
|
||||
** SELECT <function-name>(<key-name>, <pointer>);
|
||||
**
|
||||
** where <function-name> is the name passed as the second argument
|
||||
** to the sqlite3Fts3InitHashTable() function (e.g. 'fts3_tokenizer')
|
||||
@@ -273,53 +249,50 @@ static void testFunc(
|
||||
const char *zInput;
|
||||
int nInput;
|
||||
|
||||
const char *azArg[64];
|
||||
const char *zArg = 0;
|
||||
|
||||
const char *zToken;
|
||||
int nToken = 0;
|
||||
int iStart = 0;
|
||||
int iEnd = 0;
|
||||
int iPos = 0;
|
||||
int i;
|
||||
int nToken;
|
||||
int iStart;
|
||||
int iEnd;
|
||||
int iPos;
|
||||
|
||||
Tcl_Obj *pRet;
|
||||
|
||||
if( argc<2 ){
|
||||
sqlite3_result_error(context, "insufficient arguments", -1);
|
||||
return;
|
||||
}
|
||||
assert( argc==2 || argc==3 );
|
||||
|
||||
nName = sqlite3_value_bytes(argv[0]);
|
||||
zName = (const char *)sqlite3_value_text(argv[0]);
|
||||
nInput = sqlite3_value_bytes(argv[argc-1]);
|
||||
zInput = (const char *)sqlite3_value_text(argv[argc-1]);
|
||||
|
||||
if( argc==3 ){
|
||||
zArg = (const char *)sqlite3_value_text(argv[1]);
|
||||
}
|
||||
|
||||
pHash = (Fts3Hash *)sqlite3_user_data(context);
|
||||
p = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash, zName, nName+1);
|
||||
|
||||
if( !p ){
|
||||
char *zErr2 = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr2, -1);
|
||||
sqlite3_free(zErr2);
|
||||
char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
|
||||
pRet = Tcl_NewObj();
|
||||
Tcl_IncrRefCount(pRet);
|
||||
|
||||
for(i=1; i<argc-1; i++){
|
||||
azArg[i-1] = (const char *)sqlite3_value_text(argv[i]);
|
||||
}
|
||||
|
||||
if( SQLITE_OK!=p->xCreate(argc-2, azArg, &pTokenizer) ){
|
||||
if( SQLITE_OK!=p->xCreate(zArg ? 1 : 0, &zArg, &pTokenizer) ){
|
||||
zErr = "error in xCreate()";
|
||||
goto finish;
|
||||
}
|
||||
pTokenizer->pModule = p;
|
||||
if( sqlite3Fts3OpenTokenizer(pTokenizer, 0, zInput, nInput, &pCsr) ){
|
||||
if( SQLITE_OK!=p->xOpen(pTokenizer, zInput, nInput, &pCsr) ){
|
||||
zErr = "error in xOpen()";
|
||||
goto finish;
|
||||
}
|
||||
pCsr->pTokenizer = pTokenizer;
|
||||
|
||||
while( SQLITE_OK==p->xNext(pCsr, &zToken, &nToken, &iStart, &iEnd, &iPos) ){
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewIntObj(iPos));
|
||||
@@ -369,7 +342,6 @@ int registerTokenizer(
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
|
||||
static
|
||||
int queryTokenizer(
|
||||
sqlite3 *db,
|
||||
@@ -440,13 +412,11 @@ static void intTestFunc(
|
||||
assert( 0==strcmp(sqlite3_errmsg(db), "unknown tokenizer: nosuchtokenizer") );
|
||||
|
||||
/* Test the storage function */
|
||||
if( fts3TokenizerEnabled(context) ){
|
||||
rc = registerTokenizer(db, "nosuchtokenizer", p1);
|
||||
assert( rc==SQLITE_OK );
|
||||
rc = queryTokenizer(db, "nosuchtokenizer", &p2);
|
||||
assert( rc==SQLITE_OK );
|
||||
assert( p2==p1 );
|
||||
}
|
||||
rc = registerTokenizer(db, "nosuchtokenizer", p1);
|
||||
assert( rc==SQLITE_OK );
|
||||
rc = queryTokenizer(db, "nosuchtokenizer", &p2);
|
||||
assert( rc==SQLITE_OK );
|
||||
assert( p2==p1 );
|
||||
|
||||
sqlite3_result_text(context, "ok", -1, SQLITE_STATIC);
|
||||
}
|
||||
@@ -456,13 +426,13 @@ static void intTestFunc(
|
||||
/*
|
||||
** Set up SQL objects in database db used to access the contents of
|
||||
** the hash table pointed to by argument pHash. The hash table must
|
||||
** been initialized to use string keys, and to take a private copy
|
||||
** been initialised to use string keys, and to take a private copy
|
||||
** of the key when a value is inserted. i.e. by a call similar to:
|
||||
**
|
||||
** sqlite3Fts3HashInit(pHash, FTS3_HASH_STRING, 1);
|
||||
**
|
||||
** This function adds a scalar function (see header comment above
|
||||
** fts3TokenizerFunc() in this file for details) and, if ENABLE_TABLE is
|
||||
** scalarFunc() in this file for details) and, if ENABLE_TABLE is
|
||||
** defined at compilation time, a temporary virtual table (see header
|
||||
** comment above struct HashTableVtab) to the database schema. Both
|
||||
** provide read/write access to the contents of *pHash.
|
||||
@@ -491,14 +461,17 @@ int sqlite3Fts3InitHashTable(
|
||||
#endif
|
||||
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zName, 1, any, p, fts3TokenizerFunc, 0, 0);
|
||||
rc = sqlite3_create_function(db, zName, 1, any, p, scalarFunc, 0, 0);
|
||||
}
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zName, 2, any, p, fts3TokenizerFunc, 0, 0);
|
||||
rc = sqlite3_create_function(db, zName, 2, any, p, scalarFunc, 0, 0);
|
||||
}
|
||||
#ifdef SQLITE_TEST
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zTest, -1, any, p, testFunc, 0, 0);
|
||||
rc = sqlite3_create_function(db, zTest, 2, any, p, testFunc, 0, 0);
|
||||
}
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zTest, 3, any, p, testFunc, 0, 0);
|
||||
}
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zTest2, 0, any, pdb, intTestFunc, 0, 0);
|
||||
|
||||
@@ -52,7 +52,7 @@ typedef struct sqlite3_tokenizer_cursor sqlite3_tokenizer_cursor;
|
||||
struct sqlite3_tokenizer_module {
|
||||
|
||||
/*
|
||||
** Structure version. Should always be set to 0 or 1.
|
||||
** Structure version. Should always be set to 0.
|
||||
*/
|
||||
int iVersion;
|
||||
|
||||
@@ -70,7 +70,7 @@ struct sqlite3_tokenizer_module {
|
||||
** This method should return either SQLITE_OK (0), or an SQLite error
|
||||
** code. If SQLITE_OK is returned, then *ppTokenizer should be set
|
||||
** to point at the newly created tokenizer structure. The generic
|
||||
** sqlite3_tokenizer.pModule variable should not be initialized by
|
||||
** sqlite3_tokenizer.pModule variable should not be initialised by
|
||||
** this callback. The caller will do so.
|
||||
*/
|
||||
int (*xCreate)(
|
||||
@@ -133,15 +133,6 @@ struct sqlite3_tokenizer_module {
|
||||
int *piEndOffset, /* OUT: Byte offset of end of token in input buffer */
|
||||
int *piPosition /* OUT: Number of tokens returned before this one */
|
||||
);
|
||||
|
||||
/***********************************************************************
|
||||
** Methods below this point are only available if iVersion>=1.
|
||||
*/
|
||||
|
||||
/*
|
||||
** Configure the language id of a tokenizer cursor.
|
||||
*/
|
||||
int (*xLanguageid)(sqlite3_tokenizer_cursor *pCsr, int iLangid);
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer {
|
||||
|
||||
@@ -218,7 +218,6 @@ static const sqlite3_tokenizer_module simpleTokenizerModule = {
|
||||
simpleOpen,
|
||||
simpleClose,
|
||||
simpleNext,
|
||||
0,
|
||||
};
|
||||
|
||||
/*
|
||||
|
||||
@@ -1,396 +0,0 @@
|
||||
/*
|
||||
** 2012 May 24
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
**
|
||||
** Implementation of the "unicode" full-text-search tokenizer.
|
||||
*/
|
||||
|
||||
#ifndef SQLITE_DISABLE_FTS3_UNICODE
|
||||
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "fts3_tokenizer.h"
|
||||
|
||||
/*
|
||||
** The following two macros - READ_UTF8 and WRITE_UTF8 - have been copied
|
||||
** from the sqlite3 source file utf.c. If this file is compiled as part
|
||||
** of the amalgamation, they are not required.
|
||||
*/
|
||||
#ifndef SQLITE_AMALGAMATION
|
||||
|
||||
static const unsigned char sqlite3Utf8Trans1[] = {
|
||||
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
|
||||
0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
||||
0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
|
||||
0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
|
||||
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
|
||||
0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
||||
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
|
||||
0x00, 0x01, 0x02, 0x03, 0x00, 0x01, 0x00, 0x00,
|
||||
};
|
||||
|
||||
#define READ_UTF8(zIn, zTerm, c) \
|
||||
c = *(zIn++); \
|
||||
if( c>=0xc0 ){ \
|
||||
c = sqlite3Utf8Trans1[c-0xc0]; \
|
||||
while( zIn!=zTerm && (*zIn & 0xc0)==0x80 ){ \
|
||||
c = (c<<6) + (0x3f & *(zIn++)); \
|
||||
} \
|
||||
if( c<0x80 \
|
||||
|| (c&0xFFFFF800)==0xD800 \
|
||||
|| (c&0xFFFFFFFE)==0xFFFE ){ c = 0xFFFD; } \
|
||||
}
|
||||
|
||||
#define WRITE_UTF8(zOut, c) { \
|
||||
if( c<0x00080 ){ \
|
||||
*zOut++ = (u8)(c&0xFF); \
|
||||
} \
|
||||
else if( c<0x00800 ){ \
|
||||
*zOut++ = 0xC0 + (u8)((c>>6)&0x1F); \
|
||||
*zOut++ = 0x80 + (u8)(c & 0x3F); \
|
||||
} \
|
||||
else if( c<0x10000 ){ \
|
||||
*zOut++ = 0xE0 + (u8)((c>>12)&0x0F); \
|
||||
*zOut++ = 0x80 + (u8)((c>>6) & 0x3F); \
|
||||
*zOut++ = 0x80 + (u8)(c & 0x3F); \
|
||||
}else{ \
|
||||
*zOut++ = 0xF0 + (u8)((c>>18) & 0x07); \
|
||||
*zOut++ = 0x80 + (u8)((c>>12) & 0x3F); \
|
||||
*zOut++ = 0x80 + (u8)((c>>6) & 0x3F); \
|
||||
*zOut++ = 0x80 + (u8)(c & 0x3F); \
|
||||
} \
|
||||
}
|
||||
|
||||
#endif /* ifndef SQLITE_AMALGAMATION */
|
||||
|
||||
typedef struct unicode_tokenizer unicode_tokenizer;
|
||||
typedef struct unicode_cursor unicode_cursor;
|
||||
|
||||
struct unicode_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
int eRemoveDiacritic;
|
||||
int nException;
|
||||
int *aiException;
|
||||
};
|
||||
|
||||
struct unicode_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const unsigned char *aInput; /* Input text being tokenized */
|
||||
int nInput; /* Size of aInput[] in bytes */
|
||||
int iOff; /* Current offset within aInput[] */
|
||||
int iToken; /* Index of next token to be returned */
|
||||
char *zToken; /* storage for current token */
|
||||
int nAlloc; /* space allocated at zToken */
|
||||
};
|
||||
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer allocated by unicodeCreate().
|
||||
*/
|
||||
static int unicodeDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
if( pTokenizer ){
|
||||
unicode_tokenizer *p = (unicode_tokenizer *)pTokenizer;
|
||||
sqlite3_free(p->aiException);
|
||||
sqlite3_free(p);
|
||||
}
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** As part of a tokenchars= or separators= option, the CREATE VIRTUAL TABLE
|
||||
** statement has specified that the tokenizer for this table shall consider
|
||||
** all characters in string zIn/nIn to be separators (if bAlnum==0) or
|
||||
** token characters (if bAlnum==1).
|
||||
**
|
||||
** For each codepoint in the zIn/nIn string, this function checks if the
|
||||
** sqlite3FtsUnicodeIsalnum() function already returns the desired result.
|
||||
** If so, no action is taken. Otherwise, the codepoint is added to the
|
||||
** unicode_tokenizer.aiException[] array. For the purposes of tokenization,
|
||||
** the return value of sqlite3FtsUnicodeIsalnum() is inverted for all
|
||||
** codepoints in the aiException[] array.
|
||||
**
|
||||
** If a standalone diacritic mark (one that sqlite3FtsUnicodeIsdiacritic()
|
||||
** identifies as a diacritic) occurs in the zIn/nIn string it is ignored.
|
||||
** It is not possible to change the behavior of the tokenizer with respect
|
||||
** to these codepoints.
|
||||
*/
|
||||
static int unicodeAddExceptions(
|
||||
unicode_tokenizer *p, /* Tokenizer to add exceptions to */
|
||||
int bAlnum, /* Replace Isalnum() return value with this */
|
||||
const char *zIn, /* Array of characters to make exceptions */
|
||||
int nIn /* Length of z in bytes */
|
||||
){
|
||||
const unsigned char *z = (const unsigned char *)zIn;
|
||||
const unsigned char *zTerm = &z[nIn];
|
||||
unsigned int iCode;
|
||||
int nEntry = 0;
|
||||
|
||||
assert( bAlnum==0 || bAlnum==1 );
|
||||
|
||||
while( z<zTerm ){
|
||||
READ_UTF8(z, zTerm, iCode);
|
||||
assert( (sqlite3FtsUnicodeIsalnum((int)iCode) & 0xFFFFFFFE)==0 );
|
||||
if( sqlite3FtsUnicodeIsalnum((int)iCode)!=bAlnum
|
||||
&& sqlite3FtsUnicodeIsdiacritic((int)iCode)==0
|
||||
){
|
||||
nEntry++;
|
||||
}
|
||||
}
|
||||
|
||||
if( nEntry ){
|
||||
int *aNew; /* New aiException[] array */
|
||||
int nNew; /* Number of valid entries in array aNew[] */
|
||||
|
||||
aNew = sqlite3_realloc64(p->aiException,(p->nException+nEntry)*sizeof(int));
|
||||
if( aNew==0 ) return SQLITE_NOMEM;
|
||||
nNew = p->nException;
|
||||
|
||||
z = (const unsigned char *)zIn;
|
||||
while( z<zTerm ){
|
||||
READ_UTF8(z, zTerm, iCode);
|
||||
if( sqlite3FtsUnicodeIsalnum((int)iCode)!=bAlnum
|
||||
&& sqlite3FtsUnicodeIsdiacritic((int)iCode)==0
|
||||
){
|
||||
int i, j;
|
||||
for(i=0; i<nNew && aNew[i]<(int)iCode; i++);
|
||||
for(j=nNew; j>i; j--) aNew[j] = aNew[j-1];
|
||||
aNew[i] = (int)iCode;
|
||||
nNew++;
|
||||
}
|
||||
}
|
||||
p->aiException = aNew;
|
||||
p->nException = nNew;
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return true if the p->aiException[] array contains the value iCode.
|
||||
*/
|
||||
static int unicodeIsException(unicode_tokenizer *p, int iCode){
|
||||
if( p->nException>0 ){
|
||||
int *a = p->aiException;
|
||||
int iLo = 0;
|
||||
int iHi = p->nException-1;
|
||||
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
if( iCode==a[iTest] ){
|
||||
return 1;
|
||||
}else if( iCode>a[iTest] ){
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return true if, for the purposes of tokenization, codepoint iCode is
|
||||
** considered a token character (not a separator).
|
||||
*/
|
||||
static int unicodeIsAlnum(unicode_tokenizer *p, int iCode){
|
||||
assert( (sqlite3FtsUnicodeIsalnum(iCode) & 0xFFFFFFFE)==0 );
|
||||
return sqlite3FtsUnicodeIsalnum(iCode) ^ unicodeIsException(p, iCode);
|
||||
}
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int unicodeCreate(
|
||||
int nArg, /* Size of array argv[] */
|
||||
const char * const *azArg, /* Tokenizer creation arguments */
|
||||
sqlite3_tokenizer **pp /* OUT: New tokenizer handle */
|
||||
){
|
||||
unicode_tokenizer *pNew; /* New tokenizer object */
|
||||
int i;
|
||||
int rc = SQLITE_OK;
|
||||
|
||||
pNew = (unicode_tokenizer *) sqlite3_malloc(sizeof(unicode_tokenizer));
|
||||
if( pNew==NULL ) return SQLITE_NOMEM;
|
||||
memset(pNew, 0, sizeof(unicode_tokenizer));
|
||||
pNew->eRemoveDiacritic = 1;
|
||||
|
||||
for(i=0; rc==SQLITE_OK && i<nArg; i++){
|
||||
const char *z = azArg[i];
|
||||
int n = (int)strlen(z);
|
||||
|
||||
if( n==19 && memcmp("remove_diacritics=1", z, 19)==0 ){
|
||||
pNew->eRemoveDiacritic = 1;
|
||||
}
|
||||
else if( n==19 && memcmp("remove_diacritics=0", z, 19)==0 ){
|
||||
pNew->eRemoveDiacritic = 0;
|
||||
}
|
||||
else if( n==19 && memcmp("remove_diacritics=2", z, 19)==0 ){
|
||||
pNew->eRemoveDiacritic = 2;
|
||||
}
|
||||
else if( n>=11 && memcmp("tokenchars=", z, 11)==0 ){
|
||||
rc = unicodeAddExceptions(pNew, 1, &z[11], n-11);
|
||||
}
|
||||
else if( n>=11 && memcmp("separators=", z, 11)==0 ){
|
||||
rc = unicodeAddExceptions(pNew, 0, &z[11], n-11);
|
||||
}
|
||||
else{
|
||||
/* Unrecognized argument */
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
unicodeDestroy((sqlite3_tokenizer *)pNew);
|
||||
pNew = 0;
|
||||
}
|
||||
*pp = (sqlite3_tokenizer *)pNew;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Prepare to begin tokenizing a particular string. The input
|
||||
** string to be tokenized is pInput[0..nBytes-1]. A cursor
|
||||
** used to incrementally tokenize this string is returned in
|
||||
** *ppCursor.
|
||||
*/
|
||||
static int unicodeOpen(
|
||||
sqlite3_tokenizer *p, /* The tokenizer */
|
||||
const char *aInput, /* Input string */
|
||||
int nInput, /* Size of string aInput in bytes */
|
||||
sqlite3_tokenizer_cursor **pp /* OUT: New cursor object */
|
||||
){
|
||||
unicode_cursor *pCsr;
|
||||
|
||||
pCsr = (unicode_cursor *)sqlite3_malloc(sizeof(unicode_cursor));
|
||||
if( pCsr==0 ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(pCsr, 0, sizeof(unicode_cursor));
|
||||
|
||||
pCsr->aInput = (const unsigned char *)aInput;
|
||||
if( aInput==0 ){
|
||||
pCsr->nInput = 0;
|
||||
}else if( nInput<0 ){
|
||||
pCsr->nInput = (int)strlen(aInput);
|
||||
}else{
|
||||
pCsr->nInput = nInput;
|
||||
}
|
||||
|
||||
*pp = &pCsr->base;
|
||||
UNUSED_PARAMETER(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** simpleOpen() above.
|
||||
*/
|
||||
static int unicodeClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
unicode_cursor *pCsr = (unicode_cursor *) pCursor;
|
||||
sqlite3_free(pCsr->zToken);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor. The cursor must
|
||||
** have been opened by a prior call to simpleOpen().
|
||||
*/
|
||||
static int unicodeNext(
|
||||
sqlite3_tokenizer_cursor *pC, /* Cursor returned by simpleOpen */
|
||||
const char **paToken, /* OUT: Token text */
|
||||
int *pnToken, /* OUT: Number of bytes at *paToken */
|
||||
int *piStart, /* OUT: Starting offset of token */
|
||||
int *piEnd, /* OUT: Ending offset of token */
|
||||
int *piPos /* OUT: Position integer of token */
|
||||
){
|
||||
unicode_cursor *pCsr = (unicode_cursor *)pC;
|
||||
unicode_tokenizer *p = ((unicode_tokenizer *)pCsr->base.pTokenizer);
|
||||
unsigned int iCode = 0;
|
||||
char *zOut;
|
||||
const unsigned char *z = &pCsr->aInput[pCsr->iOff];
|
||||
const unsigned char *zStart = z;
|
||||
const unsigned char *zEnd;
|
||||
const unsigned char *zTerm = &pCsr->aInput[pCsr->nInput];
|
||||
|
||||
/* Scan past any delimiter characters before the start of the next token.
|
||||
** Return SQLITE_DONE early if this takes us all the way to the end of
|
||||
** the input. */
|
||||
while( z<zTerm ){
|
||||
READ_UTF8(z, zTerm, iCode);
|
||||
if( unicodeIsAlnum(p, (int)iCode) ) break;
|
||||
zStart = z;
|
||||
}
|
||||
if( zStart>=zTerm ) return SQLITE_DONE;
|
||||
|
||||
zOut = pCsr->zToken;
|
||||
do {
|
||||
int iOut;
|
||||
|
||||
/* Grow the output buffer if required. */
|
||||
if( (zOut-pCsr->zToken)>=(pCsr->nAlloc-4) ){
|
||||
char *zNew = sqlite3_realloc64(pCsr->zToken, pCsr->nAlloc+64);
|
||||
if( !zNew ) return SQLITE_NOMEM;
|
||||
zOut = &zNew[zOut - pCsr->zToken];
|
||||
pCsr->zToken = zNew;
|
||||
pCsr->nAlloc += 64;
|
||||
}
|
||||
|
||||
/* Write the folded case of the last character read to the output */
|
||||
zEnd = z;
|
||||
iOut = sqlite3FtsUnicodeFold((int)iCode, p->eRemoveDiacritic);
|
||||
if( iOut ){
|
||||
WRITE_UTF8(zOut, iOut);
|
||||
}
|
||||
|
||||
/* If the cursor is not at EOF, read the next character */
|
||||
if( z>=zTerm ) break;
|
||||
READ_UTF8(z, zTerm, iCode);
|
||||
}while( unicodeIsAlnum(p, (int)iCode)
|
||||
|| sqlite3FtsUnicodeIsdiacritic((int)iCode)
|
||||
);
|
||||
|
||||
/* Set the output variables and return. */
|
||||
pCsr->iOff = (int)(z - pCsr->aInput);
|
||||
*paToken = pCsr->zToken;
|
||||
*pnToken = (int)(zOut - pCsr->zToken);
|
||||
*piStart = (int)(zStart - pCsr->aInput);
|
||||
*piEnd = (int)(zEnd - pCsr->aInput);
|
||||
*piPos = pCsr->iToken++;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Set *ppModule to a pointer to the sqlite3_tokenizer_module
|
||||
** structure for the unicode tokenizer.
|
||||
*/
|
||||
void sqlite3Fts3UnicodeTokenizer(sqlite3_tokenizer_module const **ppModule){
|
||||
static const sqlite3_tokenizer_module module = {
|
||||
0,
|
||||
unicodeCreate,
|
||||
unicodeDestroy,
|
||||
unicodeOpen,
|
||||
unicodeClose,
|
||||
unicodeNext,
|
||||
0,
|
||||
};
|
||||
*ppModule = &module;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
#endif /* ifndef SQLITE_DISABLE_FTS3_UNICODE */
|
||||
@@ -1,383 +0,0 @@
|
||||
/*
|
||||
** 2012-05-25
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
*/
|
||||
|
||||
/*
|
||||
** DO NOT EDIT THIS MACHINE GENERATED FILE.
|
||||
*/
|
||||
|
||||
#ifndef SQLITE_DISABLE_FTS3_UNICODE
|
||||
#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)
|
||||
|
||||
#include <assert.h>
|
||||
|
||||
/*
|
||||
** Return true if the argument corresponds to a unicode codepoint
|
||||
** classified as either a letter or a number. Otherwise false.
|
||||
**
|
||||
** The results are undefined if the value passed to this function
|
||||
** is less than zero.
|
||||
*/
|
||||
int sqlite3FtsUnicodeIsalnum(int c){
|
||||
/* Each unsigned integer in the following array corresponds to a contiguous
|
||||
** range of unicode codepoints that are not either letters or numbers (i.e.
|
||||
** codepoints for which this function should return 0).
|
||||
**
|
||||
** The most significant 22 bits in each 32-bit value contain the first
|
||||
** codepoint in the range. The least significant 10 bits are used to store
|
||||
** the size of the range (always at least 1). In other words, the value
|
||||
** ((C<<22) + N) represents a range of N codepoints starting with codepoint
|
||||
** C. It is not possible to represent a range larger than 1023 codepoints
|
||||
** using this format.
|
||||
*/
|
||||
static const unsigned int aEntry[] = {
|
||||
0x00000030, 0x0000E807, 0x00016C06, 0x0001EC2F, 0x0002AC07,
|
||||
0x0002D001, 0x0002D803, 0x0002EC01, 0x0002FC01, 0x00035C01,
|
||||
0x0003DC01, 0x000B0804, 0x000B480E, 0x000B9407, 0x000BB401,
|
||||
0x000BBC81, 0x000DD401, 0x000DF801, 0x000E1002, 0x000E1C01,
|
||||
0x000FD801, 0x00120808, 0x00156806, 0x00162402, 0x00163C01,
|
||||
0x00164437, 0x0017CC02, 0x00180005, 0x00181816, 0x00187802,
|
||||
0x00192C15, 0x0019A804, 0x0019C001, 0x001B5001, 0x001B580F,
|
||||
0x001B9C07, 0x001BF402, 0x001C000E, 0x001C3C01, 0x001C4401,
|
||||
0x001CC01B, 0x001E980B, 0x001FAC09, 0x001FD804, 0x00205804,
|
||||
0x00206C09, 0x00209403, 0x0020A405, 0x0020C00F, 0x00216403,
|
||||
0x00217801, 0x0023901B, 0x00240004, 0x0024E803, 0x0024F812,
|
||||
0x00254407, 0x00258804, 0x0025C001, 0x00260403, 0x0026F001,
|
||||
0x0026F807, 0x00271C02, 0x00272C03, 0x00275C01, 0x00278802,
|
||||
0x0027C802, 0x0027E802, 0x00280403, 0x0028F001, 0x0028F805,
|
||||
0x00291C02, 0x00292C03, 0x00294401, 0x0029C002, 0x0029D401,
|
||||
0x002A0403, 0x002AF001, 0x002AF808, 0x002B1C03, 0x002B2C03,
|
||||
0x002B8802, 0x002BC002, 0x002C0403, 0x002CF001, 0x002CF807,
|
||||
0x002D1C02, 0x002D2C03, 0x002D5802, 0x002D8802, 0x002DC001,
|
||||
0x002E0801, 0x002EF805, 0x002F1803, 0x002F2804, 0x002F5C01,
|
||||
0x002FCC08, 0x00300403, 0x0030F807, 0x00311803, 0x00312804,
|
||||
0x00315402, 0x00318802, 0x0031FC01, 0x00320802, 0x0032F001,
|
||||
0x0032F807, 0x00331803, 0x00332804, 0x00335402, 0x00338802,
|
||||
0x00340802, 0x0034F807, 0x00351803, 0x00352804, 0x00355C01,
|
||||
0x00358802, 0x0035E401, 0x00360802, 0x00372801, 0x00373C06,
|
||||
0x00375801, 0x00376008, 0x0037C803, 0x0038C401, 0x0038D007,
|
||||
0x0038FC01, 0x00391C09, 0x00396802, 0x003AC401, 0x003AD006,
|
||||
0x003AEC02, 0x003B2006, 0x003C041F, 0x003CD00C, 0x003DC417,
|
||||
0x003E340B, 0x003E6424, 0x003EF80F, 0x003F380D, 0x0040AC14,
|
||||
0x00412806, 0x00415804, 0x00417803, 0x00418803, 0x00419C07,
|
||||
0x0041C404, 0x0042080C, 0x00423C01, 0x00426806, 0x0043EC01,
|
||||
0x004D740C, 0x004E400A, 0x00500001, 0x0059B402, 0x005A0001,
|
||||
0x005A6C02, 0x005BAC03, 0x005C4803, 0x005CC805, 0x005D4802,
|
||||
0x005DC802, 0x005ED023, 0x005F6004, 0x005F7401, 0x0060000F,
|
||||
0x0062A401, 0x0064800C, 0x0064C00C, 0x00650001, 0x00651002,
|
||||
0x0066C011, 0x00672002, 0x00677822, 0x00685C05, 0x00687802,
|
||||
0x0069540A, 0x0069801D, 0x0069FC01, 0x006A8007, 0x006AA006,
|
||||
0x006C0005, 0x006CD011, 0x006D6823, 0x006E0003, 0x006E840D,
|
||||
0x006F980E, 0x006FF004, 0x00709014, 0x0070EC05, 0x0071F802,
|
||||
0x00730008, 0x00734019, 0x0073B401, 0x0073C803, 0x00770027,
|
||||
0x0077F004, 0x007EF401, 0x007EFC03, 0x007F3403, 0x007F7403,
|
||||
0x007FB403, 0x007FF402, 0x00800065, 0x0081A806, 0x0081E805,
|
||||
0x00822805, 0x0082801A, 0x00834021, 0x00840002, 0x00840C04,
|
||||
0x00842002, 0x00845001, 0x00845803, 0x00847806, 0x00849401,
|
||||
0x00849C01, 0x0084A401, 0x0084B801, 0x0084E802, 0x00850005,
|
||||
0x00852804, 0x00853C01, 0x00864264, 0x00900027, 0x0091000B,
|
||||
0x0092704E, 0x00940200, 0x009C0475, 0x009E53B9, 0x00AD400A,
|
||||
0x00B39406, 0x00B3BC03, 0x00B3E404, 0x00B3F802, 0x00B5C001,
|
||||
0x00B5FC01, 0x00B7804F, 0x00B8C00C, 0x00BA001A, 0x00BA6C59,
|
||||
0x00BC00D6, 0x00BFC00C, 0x00C00005, 0x00C02019, 0x00C0A807,
|
||||
0x00C0D802, 0x00C0F403, 0x00C26404, 0x00C28001, 0x00C3EC01,
|
||||
0x00C64002, 0x00C6580A, 0x00C70024, 0x00C8001F, 0x00C8A81E,
|
||||
0x00C94001, 0x00C98020, 0x00CA2827, 0x00CB003F, 0x00CC0100,
|
||||
0x01370040, 0x02924037, 0x0293F802, 0x02983403, 0x0299BC10,
|
||||
0x029A7C01, 0x029BC008, 0x029C0017, 0x029C8002, 0x029E2402,
|
||||
0x02A00801, 0x02A01801, 0x02A02C01, 0x02A08C09, 0x02A0D804,
|
||||
0x02A1D004, 0x02A20002, 0x02A2D011, 0x02A33802, 0x02A38012,
|
||||
0x02A3E003, 0x02A4980A, 0x02A51C0D, 0x02A57C01, 0x02A60004,
|
||||
0x02A6CC1B, 0x02A77802, 0x02A8A40E, 0x02A90C01, 0x02A93002,
|
||||
0x02A97004, 0x02A9DC03, 0x02A9EC01, 0x02AAC001, 0x02AAC803,
|
||||
0x02AADC02, 0x02AAF802, 0x02AB0401, 0x02AB7802, 0x02ABAC07,
|
||||
0x02ABD402, 0x02AF8C0B, 0x03600001, 0x036DFC02, 0x036FFC02,
|
||||
0x037FFC01, 0x03EC7801, 0x03ECA401, 0x03EEC810, 0x03F4F802,
|
||||
0x03F7F002, 0x03F8001A, 0x03F88007, 0x03F8C023, 0x03F95013,
|
||||
0x03F9A004, 0x03FBFC01, 0x03FC040F, 0x03FC6807, 0x03FCEC06,
|
||||
0x03FD6C0B, 0x03FF8007, 0x03FFA007, 0x03FFE405, 0x04040003,
|
||||
0x0404DC09, 0x0405E411, 0x0406400C, 0x0407402E, 0x040E7C01,
|
||||
0x040F4001, 0x04215C01, 0x04247C01, 0x0424FC01, 0x04280403,
|
||||
0x04281402, 0x04283004, 0x0428E003, 0x0428FC01, 0x04294009,
|
||||
0x0429FC01, 0x042CE407, 0x04400003, 0x0440E016, 0x04420003,
|
||||
0x0442C012, 0x04440003, 0x04449C0E, 0x04450004, 0x04460003,
|
||||
0x0446CC0E, 0x04471404, 0x045AAC0D, 0x0491C004, 0x05BD442E,
|
||||
0x05BE3C04, 0x074000F6, 0x07440027, 0x0744A4B5, 0x07480046,
|
||||
0x074C0057, 0x075B0401, 0x075B6C01, 0x075BEC01, 0x075C5401,
|
||||
0x075CD401, 0x075D3C01, 0x075DBC01, 0x075E2401, 0x075EA401,
|
||||
0x075F0C01, 0x07BBC002, 0x07C0002C, 0x07C0C064, 0x07C2800F,
|
||||
0x07C2C40E, 0x07C3040F, 0x07C3440F, 0x07C4401F, 0x07C4C03C,
|
||||
0x07C5C02B, 0x07C7981D, 0x07C8402B, 0x07C90009, 0x07C94002,
|
||||
0x07CC0021, 0x07CCC006, 0x07CCDC46, 0x07CE0014, 0x07CE8025,
|
||||
0x07CF1805, 0x07CF8011, 0x07D0003F, 0x07D10001, 0x07D108B6,
|
||||
0x07D3E404, 0x07D4003E, 0x07D50004, 0x07D54018, 0x07D7EC46,
|
||||
0x07D9140B, 0x07DA0046, 0x07DC0074, 0x38000401, 0x38008060,
|
||||
0x380400F0,
|
||||
};
|
||||
static const unsigned int aAscii[4] = {
|
||||
0xFFFFFFFF, 0xFC00FFFF, 0xF8000001, 0xF8000001,
|
||||
};
|
||||
|
||||
if( (unsigned int)c<128 ){
|
||||
return ( (aAscii[c >> 5] & ((unsigned int)1 << (c & 0x001F)))==0 );
|
||||
}else if( (unsigned int)c<(1<<22) ){
|
||||
unsigned int key = (((unsigned int)c)<<10) | 0x000003FF;
|
||||
int iRes = 0;
|
||||
int iHi = sizeof(aEntry)/sizeof(aEntry[0]) - 1;
|
||||
int iLo = 0;
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
if( key >= aEntry[iTest] ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
assert( aEntry[0]<key );
|
||||
assert( key>=aEntry[iRes] );
|
||||
return (((unsigned int)c) >= ((aEntry[iRes]>>10) + (aEntry[iRes]&0x3FF)));
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** If the argument is a codepoint corresponding to a lowercase letter
|
||||
** in the ASCII range with a diacritic added, return the codepoint
|
||||
** of the ASCII letter only. For example, if passed 235 - "LATIN
|
||||
** SMALL LETTER E WITH DIAERESIS" - return 65 ("LATIN SMALL LETTER
|
||||
** E"). The resuls of passing a codepoint that corresponds to an
|
||||
** uppercase letter are undefined.
|
||||
*/
|
||||
static int remove_diacritic(int c, int bComplex){
|
||||
unsigned short aDia[] = {
|
||||
0, 1797, 1848, 1859, 1891, 1928, 1940, 1995,
|
||||
2024, 2040, 2060, 2110, 2168, 2206, 2264, 2286,
|
||||
2344, 2383, 2472, 2488, 2516, 2596, 2668, 2732,
|
||||
2782, 2842, 2894, 2954, 2984, 3000, 3028, 3336,
|
||||
3456, 3696, 3712, 3728, 3744, 3766, 3832, 3896,
|
||||
3912, 3928, 3944, 3968, 4008, 4040, 4056, 4106,
|
||||
4138, 4170, 4202, 4234, 4266, 4296, 4312, 4344,
|
||||
4408, 4424, 4442, 4472, 4488, 4504, 6148, 6198,
|
||||
6264, 6280, 6360, 6429, 6505, 6529, 61448, 61468,
|
||||
61512, 61534, 61592, 61610, 61642, 61672, 61688, 61704,
|
||||
61726, 61784, 61800, 61816, 61836, 61880, 61896, 61914,
|
||||
61948, 61998, 62062, 62122, 62154, 62184, 62200, 62218,
|
||||
62252, 62302, 62364, 62410, 62442, 62478, 62536, 62554,
|
||||
62584, 62604, 62640, 62648, 62656, 62664, 62730, 62766,
|
||||
62830, 62890, 62924, 62974, 63032, 63050, 63082, 63118,
|
||||
63182, 63242, 63274, 63310, 63368, 63390,
|
||||
};
|
||||
#define HIBIT ((unsigned char)0x80)
|
||||
unsigned char aChar[] = {
|
||||
'\0', 'a', 'c', 'e', 'i', 'n',
|
||||
'o', 'u', 'y', 'y', 'a', 'c',
|
||||
'd', 'e', 'e', 'g', 'h', 'i',
|
||||
'j', 'k', 'l', 'n', 'o', 'r',
|
||||
's', 't', 'u', 'u', 'w', 'y',
|
||||
'z', 'o', 'u', 'a', 'i', 'o',
|
||||
'u', 'u'|HIBIT, 'a'|HIBIT, 'g', 'k', 'o',
|
||||
'o'|HIBIT, 'j', 'g', 'n', 'a'|HIBIT, 'a',
|
||||
'e', 'i', 'o', 'r', 'u', 's',
|
||||
't', 'h', 'a', 'e', 'o'|HIBIT, 'o',
|
||||
'o'|HIBIT, 'y', '\0', '\0', '\0', '\0',
|
||||
'\0', '\0', '\0', '\0', 'a', 'b',
|
||||
'c'|HIBIT, 'd', 'd', 'e'|HIBIT, 'e', 'e'|HIBIT,
|
||||
'f', 'g', 'h', 'h', 'i', 'i'|HIBIT,
|
||||
'k', 'l', 'l'|HIBIT, 'l', 'm', 'n',
|
||||
'o'|HIBIT, 'p', 'r', 'r'|HIBIT, 'r', 's',
|
||||
's'|HIBIT, 't', 'u', 'u'|HIBIT, 'v', 'w',
|
||||
'w', 'x', 'y', 'z', 'h', 't',
|
||||
'w', 'y', 'a', 'a'|HIBIT, 'a'|HIBIT, 'a'|HIBIT,
|
||||
'e', 'e'|HIBIT, 'e'|HIBIT, 'i', 'o', 'o'|HIBIT,
|
||||
'o'|HIBIT, 'o'|HIBIT, 'u', 'u'|HIBIT, 'u'|HIBIT, 'y',
|
||||
};
|
||||
|
||||
unsigned int key = (((unsigned int)c)<<3) | 0x00000007;
|
||||
int iRes = 0;
|
||||
int iHi = sizeof(aDia)/sizeof(aDia[0]) - 1;
|
||||
int iLo = 0;
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
if( key >= aDia[iTest] ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
assert( key>=aDia[iRes] );
|
||||
if( bComplex==0 && (aChar[iRes] & 0x80) ) return c;
|
||||
return (c > (aDia[iRes]>>3) + (aDia[iRes]&0x07)) ? c : ((int)aChar[iRes] & 0x7F);
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Return true if the argument interpreted as a unicode codepoint
|
||||
** is a diacritical modifier character.
|
||||
*/
|
||||
int sqlite3FtsUnicodeIsdiacritic(int c){
|
||||
unsigned int mask0 = 0x08029FDF;
|
||||
unsigned int mask1 = 0x000361F8;
|
||||
if( c<768 || c>817 ) return 0;
|
||||
return (c < 768+32) ?
|
||||
(mask0 & ((unsigned int)1 << (c-768))) :
|
||||
(mask1 & ((unsigned int)1 << (c-768-32)));
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Interpret the argument as a unicode codepoint. If the codepoint
|
||||
** is an upper case character that has a lower case equivalent,
|
||||
** return the codepoint corresponding to the lower case version.
|
||||
** Otherwise, return a copy of the argument.
|
||||
**
|
||||
** The results are undefined if the value passed to this function
|
||||
** is less than zero.
|
||||
*/
|
||||
int sqlite3FtsUnicodeFold(int c, int eRemoveDiacritic){
|
||||
/* Each entry in the following array defines a rule for folding a range
|
||||
** of codepoints to lower case. The rule applies to a range of nRange
|
||||
** codepoints starting at codepoint iCode.
|
||||
**
|
||||
** If the least significant bit in flags is clear, then the rule applies
|
||||
** to all nRange codepoints (i.e. all nRange codepoints are upper case and
|
||||
** need to be folded). Or, if it is set, then the rule only applies to
|
||||
** every second codepoint in the range, starting with codepoint C.
|
||||
**
|
||||
** The 7 most significant bits in flags are an index into the aiOff[]
|
||||
** array. If a specific codepoint C does require folding, then its lower
|
||||
** case equivalent is ((C + aiOff[flags>>1]) & 0xFFFF).
|
||||
**
|
||||
** The contents of this array are generated by parsing the CaseFolding.txt
|
||||
** file distributed as part of the "Unicode Character Database". See
|
||||
** http://www.unicode.org for details.
|
||||
*/
|
||||
static const struct TableEntry {
|
||||
unsigned short iCode;
|
||||
unsigned char flags;
|
||||
unsigned char nRange;
|
||||
} aEntry[] = {
|
||||
{65, 14, 26}, {181, 64, 1}, {192, 14, 23},
|
||||
{216, 14, 7}, {256, 1, 48}, {306, 1, 6},
|
||||
{313, 1, 16}, {330, 1, 46}, {376, 116, 1},
|
||||
{377, 1, 6}, {383, 104, 1}, {385, 50, 1},
|
||||
{386, 1, 4}, {390, 44, 1}, {391, 0, 1},
|
||||
{393, 42, 2}, {395, 0, 1}, {398, 32, 1},
|
||||
{399, 38, 1}, {400, 40, 1}, {401, 0, 1},
|
||||
{403, 42, 1}, {404, 46, 1}, {406, 52, 1},
|
||||
{407, 48, 1}, {408, 0, 1}, {412, 52, 1},
|
||||
{413, 54, 1}, {415, 56, 1}, {416, 1, 6},
|
||||
{422, 60, 1}, {423, 0, 1}, {425, 60, 1},
|
||||
{428, 0, 1}, {430, 60, 1}, {431, 0, 1},
|
||||
{433, 58, 2}, {435, 1, 4}, {439, 62, 1},
|
||||
{440, 0, 1}, {444, 0, 1}, {452, 2, 1},
|
||||
{453, 0, 1}, {455, 2, 1}, {456, 0, 1},
|
||||
{458, 2, 1}, {459, 1, 18}, {478, 1, 18},
|
||||
{497, 2, 1}, {498, 1, 4}, {502, 122, 1},
|
||||
{503, 134, 1}, {504, 1, 40}, {544, 110, 1},
|
||||
{546, 1, 18}, {570, 70, 1}, {571, 0, 1},
|
||||
{573, 108, 1}, {574, 68, 1}, {577, 0, 1},
|
||||
{579, 106, 1}, {580, 28, 1}, {581, 30, 1},
|
||||
{582, 1, 10}, {837, 36, 1}, {880, 1, 4},
|
||||
{886, 0, 1}, {902, 18, 1}, {904, 16, 3},
|
||||
{908, 26, 1}, {910, 24, 2}, {913, 14, 17},
|
||||
{931, 14, 9}, {962, 0, 1}, {975, 4, 1},
|
||||
{976, 140, 1}, {977, 142, 1}, {981, 146, 1},
|
||||
{982, 144, 1}, {984, 1, 24}, {1008, 136, 1},
|
||||
{1009, 138, 1}, {1012, 130, 1}, {1013, 128, 1},
|
||||
{1015, 0, 1}, {1017, 152, 1}, {1018, 0, 1},
|
||||
{1021, 110, 3}, {1024, 34, 16}, {1040, 14, 32},
|
||||
{1120, 1, 34}, {1162, 1, 54}, {1216, 6, 1},
|
||||
{1217, 1, 14}, {1232, 1, 88}, {1329, 22, 38},
|
||||
{4256, 66, 38}, {4295, 66, 1}, {4301, 66, 1},
|
||||
{7680, 1, 150}, {7835, 132, 1}, {7838, 96, 1},
|
||||
{7840, 1, 96}, {7944, 150, 8}, {7960, 150, 6},
|
||||
{7976, 150, 8}, {7992, 150, 8}, {8008, 150, 6},
|
||||
{8025, 151, 8}, {8040, 150, 8}, {8072, 150, 8},
|
||||
{8088, 150, 8}, {8104, 150, 8}, {8120, 150, 2},
|
||||
{8122, 126, 2}, {8124, 148, 1}, {8126, 100, 1},
|
||||
{8136, 124, 4}, {8140, 148, 1}, {8152, 150, 2},
|
||||
{8154, 120, 2}, {8168, 150, 2}, {8170, 118, 2},
|
||||
{8172, 152, 1}, {8184, 112, 2}, {8186, 114, 2},
|
||||
{8188, 148, 1}, {8486, 98, 1}, {8490, 92, 1},
|
||||
{8491, 94, 1}, {8498, 12, 1}, {8544, 8, 16},
|
||||
{8579, 0, 1}, {9398, 10, 26}, {11264, 22, 47},
|
||||
{11360, 0, 1}, {11362, 88, 1}, {11363, 102, 1},
|
||||
{11364, 90, 1}, {11367, 1, 6}, {11373, 84, 1},
|
||||
{11374, 86, 1}, {11375, 80, 1}, {11376, 82, 1},
|
||||
{11378, 0, 1}, {11381, 0, 1}, {11390, 78, 2},
|
||||
{11392, 1, 100}, {11499, 1, 4}, {11506, 0, 1},
|
||||
{42560, 1, 46}, {42624, 1, 24}, {42786, 1, 14},
|
||||
{42802, 1, 62}, {42873, 1, 4}, {42877, 76, 1},
|
||||
{42878, 1, 10}, {42891, 0, 1}, {42893, 74, 1},
|
||||
{42896, 1, 4}, {42912, 1, 10}, {42922, 72, 1},
|
||||
{65313, 14, 26},
|
||||
};
|
||||
static const unsigned short aiOff[] = {
|
||||
1, 2, 8, 15, 16, 26, 28, 32,
|
||||
37, 38, 40, 48, 63, 64, 69, 71,
|
||||
79, 80, 116, 202, 203, 205, 206, 207,
|
||||
209, 210, 211, 213, 214, 217, 218, 219,
|
||||
775, 7264, 10792, 10795, 23228, 23256, 30204, 54721,
|
||||
54753, 54754, 54756, 54787, 54793, 54809, 57153, 57274,
|
||||
57921, 58019, 58363, 61722, 65268, 65341, 65373, 65406,
|
||||
65408, 65410, 65415, 65424, 65436, 65439, 65450, 65462,
|
||||
65472, 65476, 65478, 65480, 65482, 65488, 65506, 65511,
|
||||
65514, 65521, 65527, 65528, 65529,
|
||||
};
|
||||
|
||||
int ret = c;
|
||||
|
||||
assert( sizeof(unsigned short)==2 && sizeof(unsigned char)==1 );
|
||||
|
||||
if( c<128 ){
|
||||
if( c>='A' && c<='Z' ) ret = c + ('a' - 'A');
|
||||
}else if( c<65536 ){
|
||||
const struct TableEntry *p;
|
||||
int iHi = sizeof(aEntry)/sizeof(aEntry[0]) - 1;
|
||||
int iLo = 0;
|
||||
int iRes = -1;
|
||||
|
||||
assert( c>aEntry[0].iCode );
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
int cmp = (c - aEntry[iTest].iCode);
|
||||
if( cmp>=0 ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
|
||||
assert( iRes>=0 && c>=aEntry[iRes].iCode );
|
||||
p = &aEntry[iRes];
|
||||
if( c<(p->iCode + p->nRange) && 0==(0x01 & p->flags & (p->iCode ^ c)) ){
|
||||
ret = (c + (aiOff[p->flags>>1])) & 0x0000FFFF;
|
||||
assert( ret>0 );
|
||||
}
|
||||
|
||||
if( eRemoveDiacritic ){
|
||||
ret = remove_diacritic(ret, eRemoveDiacritic==2);
|
||||
}
|
||||
}
|
||||
|
||||
else if( c>=66560 && c<66600 ){
|
||||
ret = c + 40;
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
#endif /* defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4) */
|
||||
#endif /* !defined(SQLITE_DISABLE_FTS3_UNICODE) */
|
||||
+240
-2533
File diff suppressed because it is too large
Load Diff
@@ -1,16 +0,0 @@
|
||||
#!/bin/sh
|
||||
|
||||
set -e
|
||||
|
||||
srcdir=`dirname $(dirname $(dirname $(dirname $0)))`
|
||||
./testfixture $srcdir/test/fts3.test --output=fts3cov-out.txt
|
||||
|
||||
echo ""
|
||||
|
||||
for f in `ls $srcdir/ext/fts3/*.c`
|
||||
do
|
||||
f=`basename $f`
|
||||
echo -ne "$f: "
|
||||
gcov -b $f | grep Taken | sed 's/Taken at least once://'
|
||||
done
|
||||
|
||||
@@ -1,875 +0,0 @@
|
||||
/*
|
||||
** This program is a debugging and analysis utility that displays
|
||||
** information about an FTS3 or FTS4 index.
|
||||
**
|
||||
** Link this program against the SQLite3 amalgamation with the
|
||||
** SQLITE_ENABLE_FTS4 compile-time option. Then run it as:
|
||||
**
|
||||
** fts3view DATABASE
|
||||
**
|
||||
** to get a list of all FTS3/4 tables in DATABASE, or do
|
||||
**
|
||||
** fts3view DATABASE TABLE COMMAND ....
|
||||
**
|
||||
** to see various aspects of the TABLE table. Type fts3view with no
|
||||
** arguments for a list of available COMMANDs.
|
||||
*/
|
||||
#include <stdio.h>
|
||||
#include <stdarg.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <ctype.h>
|
||||
#include "sqlite3.h"
|
||||
|
||||
/*
|
||||
** Extra command-line arguments:
|
||||
*/
|
||||
int nExtra;
|
||||
char **azExtra;
|
||||
|
||||
/*
|
||||
** Look for a command-line argument.
|
||||
*/
|
||||
const char *findOption(const char *zName, int hasArg, const char *zDefault){
|
||||
int i;
|
||||
const char *zResult = zDefault;
|
||||
for(i=0; i<nExtra; i++){
|
||||
const char *z = azExtra[i];
|
||||
while( z[0]=='-' ) z++;
|
||||
if( strcmp(z, zName)==0 ){
|
||||
int j = 1;
|
||||
if( hasArg==0 || i==nExtra-1 ) j = 0;
|
||||
zResult = azExtra[i+j];
|
||||
while( i+j<nExtra ){
|
||||
azExtra[i] = azExtra[i+j+1];
|
||||
i++;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
return zResult;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Prepare an SQL query
|
||||
*/
|
||||
static sqlite3_stmt *prepare(sqlite3 *db, const char *zFormat, ...){
|
||||
va_list ap;
|
||||
char *zSql;
|
||||
sqlite3_stmt *pStmt;
|
||||
int rc;
|
||||
|
||||
va_start(ap, zFormat);
|
||||
zSql = sqlite3_vmprintf(zFormat, ap);
|
||||
va_end(ap);
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc ){
|
||||
fprintf(stderr, "Error: %s\nSQL: %s\n", sqlite3_errmsg(db), zSql);
|
||||
exit(1);
|
||||
}
|
||||
sqlite3_free(zSql);
|
||||
return pStmt;
|
||||
}
|
||||
|
||||
/*
|
||||
** Run an SQL statement
|
||||
*/
|
||||
static int runSql(sqlite3 *db, const char *zFormat, ...){
|
||||
va_list ap;
|
||||
char *zSql;
|
||||
int rc;
|
||||
|
||||
va_start(ap, zFormat);
|
||||
zSql = sqlite3_vmprintf(zFormat, ap);
|
||||
rc = sqlite3_exec(db, zSql, 0, 0, 0);
|
||||
va_end(ap);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Show the table schema
|
||||
*/
|
||||
static void showSchema(sqlite3 *db, const char *zTab){
|
||||
sqlite3_stmt *pStmt;
|
||||
pStmt = prepare(db,
|
||||
"SELECT sql FROM sqlite_master"
|
||||
" WHERE name LIKE '%q%%'"
|
||||
" ORDER BY 1",
|
||||
zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
printf("%s;\n", sqlite3_column_text(pStmt, 0));
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db, "PRAGMA page_size");
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
printf("PRAGMA page_size=%s;\n", sqlite3_column_text(pStmt, 0));
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db, "PRAGMA journal_mode");
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
printf("PRAGMA journal_mode=%s;\n", sqlite3_column_text(pStmt, 0));
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db, "PRAGMA auto_vacuum");
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
const char *zType = "???";
|
||||
switch( sqlite3_column_int(pStmt, 0) ){
|
||||
case 0: zType = "OFF"; break;
|
||||
case 1: zType = "FULL"; break;
|
||||
case 2: zType = "INCREMENTAL"; break;
|
||||
}
|
||||
printf("PRAGMA auto_vacuum=%s;\n", zType);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db, "PRAGMA encoding");
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
printf("PRAGMA encoding=%s;\n", sqlite3_column_text(pStmt, 0));
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
/*
|
||||
** Read a 64-bit variable-length integer from memory starting at p[0].
|
||||
** Return the number of bytes read, or 0 on error.
|
||||
** The value is stored in *v.
|
||||
*/
|
||||
int getVarint(const unsigned char *p, sqlite_int64 *v){
|
||||
const unsigned char *q = p;
|
||||
sqlite_uint64 x = 0, y = 1;
|
||||
while( (*q&0x80)==0x80 && q-(unsigned char *)p<9 ){
|
||||
x += y * (*q++ & 0x7f);
|
||||
y <<= 7;
|
||||
}
|
||||
x += y * (*q++);
|
||||
*v = (sqlite_int64) x;
|
||||
return (int) (q - (unsigned char *)p);
|
||||
}
|
||||
|
||||
|
||||
/* Show the content of the %_stat table
|
||||
*/
|
||||
static void showStat(sqlite3 *db, const char *zTab){
|
||||
sqlite3_stmt *pStmt;
|
||||
pStmt = prepare(db, "SELECT id, value FROM '%q_stat'", zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
printf("stat[%d] =", sqlite3_column_int(pStmt, 0));
|
||||
switch( sqlite3_column_type(pStmt, 1) ){
|
||||
case SQLITE_INTEGER: {
|
||||
printf(" %d\n", sqlite3_column_int(pStmt, 1));
|
||||
break;
|
||||
}
|
||||
case SQLITE_BLOB: {
|
||||
unsigned char *x = (unsigned char*)sqlite3_column_blob(pStmt, 1);
|
||||
int len = sqlite3_column_bytes(pStmt, 1);
|
||||
int i = 0;
|
||||
sqlite3_int64 v;
|
||||
while( i<len ){
|
||||
i += getVarint(x, &v);
|
||||
printf(" %lld", v);
|
||||
}
|
||||
printf("\n");
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
/*
|
||||
** Report on the vocabulary. This creates an fts4aux table with a random
|
||||
** name, but deletes it in the end.
|
||||
*/
|
||||
static void showVocabulary(sqlite3 *db, const char *zTab){
|
||||
char *zAux;
|
||||
sqlite3_uint64 r;
|
||||
sqlite3_stmt *pStmt;
|
||||
int nDoc = 0;
|
||||
int nToken = 0;
|
||||
int nOccurrence = 0;
|
||||
int nTop;
|
||||
int n, i;
|
||||
|
||||
sqlite3_randomness(sizeof(r), &r);
|
||||
zAux = sqlite3_mprintf("viewer_%llx", zTab, r);
|
||||
runSql(db, "BEGIN");
|
||||
pStmt = prepare(db, "SELECT count(*) FROM %Q", zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
nDoc = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Number of documents...................... %9d\n", nDoc);
|
||||
|
||||
runSql(db, "CREATE VIRTUAL TABLE %s USING fts4aux(%Q)", zAux, zTab);
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*), sum(occurrences) FROM %s WHERE col='*'",
|
||||
zAux);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
nToken = sqlite3_column_int(pStmt, 0);
|
||||
nOccurrence = sqlite3_column_int(pStmt, 1);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Total tokens in all documents............ %9d\n", nOccurrence);
|
||||
printf("Total number of distinct tokens.......... %9d\n", nToken);
|
||||
if( nToken==0 ) goto end_vocab;
|
||||
|
||||
n = 0;
|
||||
pStmt = prepare(db, "SELECT count(*) FROM %s"
|
||||
" WHERE col='*' AND occurrences==1", zAux);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
n = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Tokens used exactly once................. %9d %5.2f%%\n",
|
||||
n, n*100.0/nToken);
|
||||
|
||||
n = 0;
|
||||
pStmt = prepare(db, "SELECT count(*) FROM %s"
|
||||
" WHERE col='*' AND documents==1", zAux);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
n = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Tokens used in only one document......... %9d %5.2f%%\n",
|
||||
n, n*100.0/nToken);
|
||||
|
||||
if( nDoc>=2000 ){
|
||||
n = 0;
|
||||
pStmt = prepare(db, "SELECT count(*) FROM %s"
|
||||
" WHERE col='*' AND occurrences<=%d", zAux, nDoc/1000);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
n = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Tokens used in 0.1%% or less of docs...... %9d %5.2f%%\n",
|
||||
n, n*100.0/nToken);
|
||||
}
|
||||
|
||||
if( nDoc>=200 ){
|
||||
n = 0;
|
||||
pStmt = prepare(db, "SELECT count(*) FROM %s"
|
||||
" WHERE col='*' AND occurrences<=%d", zAux, nDoc/100);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
n = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Tokens used in 1%% or less of docs........ %9d %5.2f%%\n",
|
||||
n, n*100.0/nToken);
|
||||
}
|
||||
|
||||
nTop = atoi(findOption("top", 1, "25"));
|
||||
printf("The %d most common tokens:\n", nTop);
|
||||
pStmt = prepare(db,
|
||||
"SELECT term, documents FROM %s"
|
||||
" WHERE col='*'"
|
||||
" ORDER BY documents DESC, term"
|
||||
" LIMIT %d", zAux, nTop);
|
||||
i = 0;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
i++;
|
||||
n = sqlite3_column_int(pStmt, 1);
|
||||
printf(" %2d. %-30s %9d docs %5.2f%%\n", i,
|
||||
sqlite3_column_text(pStmt, 0), n, n*100.0/nDoc);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
|
||||
end_vocab:
|
||||
runSql(db, "ROLLBACK");
|
||||
sqlite3_free(zAux);
|
||||
}
|
||||
|
||||
/*
|
||||
** Report on the number and sizes of segments
|
||||
*/
|
||||
static void showSegmentStats(sqlite3 *db, const char *zTab){
|
||||
sqlite3_stmt *pStmt;
|
||||
int nSeg = 0;
|
||||
sqlite3_int64 szSeg = 0, mxSeg = 0;
|
||||
int nIdx = 0;
|
||||
sqlite3_int64 szIdx = 0, mxIdx = 0;
|
||||
int nRoot = 0;
|
||||
sqlite3_int64 szRoot = 0, mxRoot = 0;
|
||||
sqlite3_int64 mx;
|
||||
int nLeaf;
|
||||
int n;
|
||||
int pgsz;
|
||||
int mxLevel;
|
||||
int i;
|
||||
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*), sum(length(block)), max(length(block))"
|
||||
" FROM '%q_segments'",
|
||||
zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
nSeg = sqlite3_column_int(pStmt, 0);
|
||||
szSeg = sqlite3_column_int64(pStmt, 1);
|
||||
mxSeg = sqlite3_column_int64(pStmt, 2);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*), sum(length(block)), max(length(block))"
|
||||
" FROM '%q_segments' a JOIN '%q_segdir' b"
|
||||
" WHERE a.blockid BETWEEN b.leaves_end_block+1 AND b.end_block",
|
||||
zTab, zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
nIdx = sqlite3_column_int(pStmt, 0);
|
||||
szIdx = sqlite3_column_int64(pStmt, 1);
|
||||
mxIdx = sqlite3_column_int64(pStmt, 2);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*), sum(length(root)), max(length(root))"
|
||||
" FROM '%q_segdir'",
|
||||
zTab);
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
nRoot = sqlite3_column_int(pStmt, 0);
|
||||
szRoot = sqlite3_column_int64(pStmt, 1);
|
||||
mxRoot = sqlite3_column_int64(pStmt, 2);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
|
||||
printf("Number of segments....................... %9d\n", nSeg+nRoot);
|
||||
printf("Number of leaf segments.................. %9d\n", nSeg-nIdx);
|
||||
printf("Number of index segments................. %9d\n", nIdx);
|
||||
printf("Number of root segments.................. %9d\n", nRoot);
|
||||
printf("Total size of all segments............... %9lld\n", szSeg+szRoot);
|
||||
printf("Total size of all leaf segments.......... %9lld\n", szSeg-szIdx);
|
||||
printf("Total size of all index segments......... %9lld\n", szIdx);
|
||||
printf("Total size of all root segments.......... %9lld\n", szRoot);
|
||||
if( nSeg>0 ){
|
||||
printf("Average size of all segments............. %11.1f\n",
|
||||
(double)(szSeg+szRoot)/(double)(nSeg+nRoot));
|
||||
printf("Average size of leaf segments............ %11.1f\n",
|
||||
(double)(szSeg-szIdx)/(double)(nSeg-nIdx));
|
||||
}
|
||||
if( nIdx>0 ){
|
||||
printf("Average size of index segments........... %11.1f\n",
|
||||
(double)szIdx/(double)nIdx);
|
||||
}
|
||||
if( nRoot>0 ){
|
||||
printf("Average size of root segments............ %11.1f\n",
|
||||
(double)szRoot/(double)nRoot);
|
||||
}
|
||||
mx = mxSeg;
|
||||
if( mx<mxRoot ) mx = mxRoot;
|
||||
printf("Maximum segment size..................... %9lld\n", mx);
|
||||
printf("Maximum index segment size............... %9lld\n", mxIdx);
|
||||
printf("Maximum root segment size................ %9lld\n", mxRoot);
|
||||
|
||||
pStmt = prepare(db, "PRAGMA page_size");
|
||||
pgsz = 1024;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
pgsz = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
printf("Database page size....................... %9d\n", pgsz);
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*)"
|
||||
" FROM '%q_segments' a JOIN '%q_segdir' b"
|
||||
" WHERE a.blockid BETWEEN b.start_block AND b.leaves_end_block"
|
||||
" AND length(a.block)>%d",
|
||||
zTab, zTab, pgsz-45);
|
||||
n = 0;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
n = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
nLeaf = nSeg - nIdx;
|
||||
printf("Leaf segments larger than %5d bytes.... %9d %5.2f%%\n",
|
||||
pgsz-45, n, nLeaf>0 ? n*100.0/nLeaf : 0.0);
|
||||
|
||||
pStmt = prepare(db, "SELECT max(level%%1024) FROM '%q_segdir'", zTab);
|
||||
mxLevel = 0;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
mxLevel = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
|
||||
for(i=0; i<=mxLevel; i++){
|
||||
pStmt = prepare(db,
|
||||
"SELECT count(*), sum(len), avg(len), max(len), sum(len>%d),"
|
||||
" count(distinct idx)"
|
||||
" FROM (SELECT length(a.block) AS len, idx"
|
||||
" FROM '%q_segments' a JOIN '%q_segdir' b"
|
||||
" WHERE (a.blockid BETWEEN b.start_block"
|
||||
" AND b.leaves_end_block)"
|
||||
" AND (b.level%%1024)==%d)",
|
||||
pgsz-45, zTab, zTab, i);
|
||||
if( sqlite3_step(pStmt)==SQLITE_ROW
|
||||
&& (nLeaf = sqlite3_column_int(pStmt, 0))>0
|
||||
){
|
||||
sqlite3_int64 sz;
|
||||
nIdx = sqlite3_column_int(pStmt, 5);
|
||||
printf("For level %d:\n", i);
|
||||
printf(" Number of indexes...................... %9d\n", nIdx);
|
||||
printf(" Number of leaf segments................ %9d\n", nLeaf);
|
||||
if( nIdx>1 ){
|
||||
printf(" Average leaf segments per index........ %11.1f\n",
|
||||
(double)nLeaf/(double)nIdx);
|
||||
}
|
||||
printf(" Total size of all leaf segments........ %9lld\n",
|
||||
(sz = sqlite3_column_int64(pStmt, 1)));
|
||||
printf(" Average size of leaf segments.......... %11.1f\n",
|
||||
sqlite3_column_double(pStmt, 2));
|
||||
if( nIdx>1 ){
|
||||
printf(" Average leaf segment size per index.... %11.1f\n",
|
||||
(double)sz/(double)nIdx);
|
||||
}
|
||||
printf(" Maximum leaf segment size.............. %9lld\n",
|
||||
sqlite3_column_int64(pStmt, 3));
|
||||
n = sqlite3_column_int(pStmt, 4);
|
||||
printf(" Leaf segments larger than %5d bytes.. %9d %5.2f%%\n",
|
||||
pgsz-45, n, n*100.0/nLeaf);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Print a single "tree" line of the segdir map output.
|
||||
*/
|
||||
static void printTreeLine(sqlite3_int64 iLower, sqlite3_int64 iUpper){
|
||||
printf(" tree %9lld", iLower);
|
||||
if( iUpper>iLower ){
|
||||
printf(" thru %9lld (%lld blocks)", iUpper, iUpper-iLower+1);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
|
||||
/*
|
||||
** Check to see if the block of a %_segments entry is NULL.
|
||||
*/
|
||||
static int isNullSegment(sqlite3 *db, const char *zTab, sqlite3_int64 iBlockId){
|
||||
sqlite3_stmt *pStmt;
|
||||
int rc = 1;
|
||||
|
||||
pStmt = prepare(db, "SELECT block IS NULL FROM '%q_segments'"
|
||||
" WHERE blockid=%lld", zTab, iBlockId);
|
||||
if( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
rc = sqlite3_column_int(pStmt, 0);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Show a map of segments derived from the %_segdir table.
|
||||
*/
|
||||
static void showSegdirMap(sqlite3 *db, const char *zTab){
|
||||
int mxIndex, iIndex;
|
||||
sqlite3_stmt *pStmt = 0;
|
||||
sqlite3_stmt *pStmt2 = 0;
|
||||
int prevLevel;
|
||||
|
||||
pStmt = prepare(db, "SELECT max(level/1024) FROM '%q_segdir'", zTab);
|
||||
if( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
mxIndex = sqlite3_column_int(pStmt, 0);
|
||||
}else{
|
||||
mxIndex = 0;
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
|
||||
printf("Number of inverted indices............... %3d\n", mxIndex+1);
|
||||
pStmt = prepare(db,
|
||||
"SELECT level, idx, start_block, leaves_end_block, end_block, rowid"
|
||||
" FROM '%q_segdir'"
|
||||
" WHERE level/1024==?"
|
||||
" ORDER BY level DESC, idx",
|
||||
zTab);
|
||||
pStmt2 = prepare(db,
|
||||
"SELECT blockid FROM '%q_segments'"
|
||||
" WHERE blockid BETWEEN ? AND ? ORDER BY blockid",
|
||||
zTab);
|
||||
for(iIndex=0; iIndex<=mxIndex; iIndex++){
|
||||
if( mxIndex>0 ){
|
||||
printf("**************************** Index %d "
|
||||
"****************************\n", iIndex);
|
||||
}
|
||||
sqlite3_bind_int(pStmt, 1, iIndex);
|
||||
prevLevel = -1;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
int iLevel = sqlite3_column_int(pStmt, 0)%1024;
|
||||
int iIdx = sqlite3_column_int(pStmt, 1);
|
||||
sqlite3_int64 iStart = sqlite3_column_int64(pStmt, 2);
|
||||
sqlite3_int64 iLEnd = sqlite3_column_int64(pStmt, 3);
|
||||
sqlite3_int64 iEnd = sqlite3_column_int64(pStmt, 4);
|
||||
char rtag[20];
|
||||
if( iLevel!=prevLevel ){
|
||||
printf("level %2d idx %2d", iLevel, iIdx);
|
||||
prevLevel = iLevel;
|
||||
}else{
|
||||
printf(" idx %2d", iIdx);
|
||||
}
|
||||
sqlite3_snprintf(sizeof(rtag), rtag, "r%lld",
|
||||
sqlite3_column_int64(pStmt,5));
|
||||
printf(" root %9s\n", rtag);
|
||||
if( iLEnd>iStart ){
|
||||
sqlite3_int64 iLower, iPrev = 0, iX;
|
||||
if( iLEnd+1<=iEnd ){
|
||||
sqlite3_bind_int64(pStmt2, 1, iLEnd+1);
|
||||
sqlite3_bind_int64(pStmt2, 2, iEnd);
|
||||
iLower = -1;
|
||||
while( sqlite3_step(pStmt2)==SQLITE_ROW ){
|
||||
iX = sqlite3_column_int64(pStmt2, 0);
|
||||
if( iLower<0 ){
|
||||
iLower = iPrev = iX;
|
||||
}else if( iX==iPrev+1 ){
|
||||
iPrev = iX;
|
||||
}else{
|
||||
printTreeLine(iLower, iPrev);
|
||||
iLower = iPrev = iX;
|
||||
}
|
||||
}
|
||||
sqlite3_reset(pStmt2);
|
||||
if( iLower>=0 ){
|
||||
if( iLower==iPrev && iLower==iEnd
|
||||
&& isNullSegment(db,zTab,iLower)
|
||||
){
|
||||
printf(" null %9lld\n", iLower);
|
||||
}else{
|
||||
printTreeLine(iLower, iPrev);
|
||||
}
|
||||
}
|
||||
}
|
||||
printf(" leaves %9lld thru %9lld (%lld blocks)\n",
|
||||
iStart, iLEnd, iLEnd - iStart + 1);
|
||||
}
|
||||
}
|
||||
sqlite3_reset(pStmt);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
sqlite3_finalize(pStmt2);
|
||||
}
|
||||
|
||||
/*
|
||||
** Decode a single segment block and display the results on stdout.
|
||||
*/
|
||||
static void decodeSegment(
|
||||
const unsigned char *aData, /* Content to print */
|
||||
int nData /* Number of bytes of content */
|
||||
){
|
||||
sqlite3_int64 iChild = 0;
|
||||
sqlite3_int64 iPrefix;
|
||||
sqlite3_int64 nTerm;
|
||||
sqlite3_int64 n;
|
||||
sqlite3_int64 iDocsz;
|
||||
int iHeight;
|
||||
sqlite3_int64 i = 0;
|
||||
int cnt = 0;
|
||||
char zTerm[1000];
|
||||
|
||||
i += getVarint(aData, &n);
|
||||
iHeight = (int)n;
|
||||
printf("height: %d\n", iHeight);
|
||||
if( iHeight>0 ){
|
||||
i += getVarint(aData+i, &iChild);
|
||||
printf("left-child: %lld\n", iChild);
|
||||
}
|
||||
while( i<nData ){
|
||||
if( (cnt++)>0 ){
|
||||
i += getVarint(aData+i, &iPrefix);
|
||||
}else{
|
||||
iPrefix = 0;
|
||||
}
|
||||
i += getVarint(aData+i, &nTerm);
|
||||
if( iPrefix+nTerm+1 >= sizeof(zTerm) ){
|
||||
fprintf(stderr, "term to long\n");
|
||||
exit(1);
|
||||
}
|
||||
memcpy(zTerm+iPrefix, aData+i, (size_t)nTerm);
|
||||
zTerm[iPrefix+nTerm] = 0;
|
||||
i += nTerm;
|
||||
if( iHeight==0 ){
|
||||
i += getVarint(aData+i, &iDocsz);
|
||||
printf("term: %-25s doclist %7lld bytes offset %lld\n", zTerm, iDocsz, i);
|
||||
i += iDocsz;
|
||||
}else{
|
||||
printf("term: %-25s child %lld\n", zTerm, ++iChild);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Print a a blob as hex and ascii.
|
||||
*/
|
||||
static void printBlob(
|
||||
const unsigned char *aData, /* Content to print */
|
||||
int nData /* Number of bytes of content */
|
||||
){
|
||||
int i, j;
|
||||
const char *zOfstFmt;
|
||||
const int perLine = 16;
|
||||
|
||||
if( (nData&~0xfff)==0 ){
|
||||
zOfstFmt = " %03x: ";
|
||||
}else if( (nData&~0xffff)==0 ){
|
||||
zOfstFmt = " %04x: ";
|
||||
}else if( (nData&~0xfffff)==0 ){
|
||||
zOfstFmt = " %05x: ";
|
||||
}else if( (nData&~0xffffff)==0 ){
|
||||
zOfstFmt = " %06x: ";
|
||||
}else{
|
||||
zOfstFmt = " %08x: ";
|
||||
}
|
||||
|
||||
for(i=0; i<nData; i += perLine){
|
||||
fprintf(stdout, zOfstFmt, i);
|
||||
for(j=0; j<perLine; j++){
|
||||
if( i+j>nData ){
|
||||
fprintf(stdout, " ");
|
||||
}else{
|
||||
fprintf(stdout,"%02x ", aData[i+j]);
|
||||
}
|
||||
}
|
||||
for(j=0; j<perLine; j++){
|
||||
if( i+j>nData ){
|
||||
fprintf(stdout, " ");
|
||||
}else{
|
||||
fprintf(stdout,"%c", isprint(aData[i+j]) ? aData[i+j] : '.');
|
||||
}
|
||||
}
|
||||
fprintf(stdout,"\n");
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Convert text to a 64-bit integer
|
||||
*/
|
||||
static sqlite3_int64 atoi64(const char *z){
|
||||
sqlite3_int64 v = 0;
|
||||
while( z[0]>='0' && z[0]<='9' ){
|
||||
v = v*10 + z[0] - '0';
|
||||
z++;
|
||||
}
|
||||
return v;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a prepared statement which, when stepped, will return in its
|
||||
** first column the blob associated with segment zId. If zId begins with
|
||||
** 'r' then it is a rowid of a %_segdir entry. Otherwise it is a
|
||||
** %_segment entry.
|
||||
*/
|
||||
static sqlite3_stmt *prepareToGetSegment(
|
||||
sqlite3 *db, /* The database */
|
||||
const char *zTab, /* The FTS3/4 table name */
|
||||
const char *zId /* ID of the segment to open */
|
||||
){
|
||||
sqlite3_stmt *pStmt;
|
||||
if( zId[0]=='r' ){
|
||||
pStmt = prepare(db, "SELECT root FROM '%q_segdir' WHERE rowid=%lld",
|
||||
zTab, atoi64(zId+1));
|
||||
}else{
|
||||
pStmt = prepare(db, "SELECT block FROM '%q_segments' WHERE blockid=%lld",
|
||||
zTab, atoi64(zId));
|
||||
}
|
||||
return pStmt;
|
||||
}
|
||||
|
||||
/*
|
||||
** Print the content of a segment or of the root of a segdir. The segment
|
||||
** or root is identified by azExtra[0]. If the first character of azExtra[0]
|
||||
** is 'r' then the remainder is the integer rowid of the %_segdir entry.
|
||||
** If the first character of azExtra[0] is not 'r' then, then all of
|
||||
** azExtra[0] is an integer which is the block number.
|
||||
**
|
||||
** If the --raw option is present in azExtra, then a hex dump is provided.
|
||||
** Otherwise a decoding is shown.
|
||||
*/
|
||||
static void showSegment(sqlite3 *db, const char *zTab){
|
||||
const unsigned char *aData;
|
||||
int nData;
|
||||
sqlite3_stmt *pStmt;
|
||||
|
||||
pStmt = prepareToGetSegment(db, zTab, azExtra[0]);
|
||||
if( sqlite3_step(pStmt)!=SQLITE_ROW ){
|
||||
sqlite3_finalize(pStmt);
|
||||
return;
|
||||
}
|
||||
nData = sqlite3_column_bytes(pStmt, 0);
|
||||
aData = sqlite3_column_blob(pStmt, 0);
|
||||
printf("Segment %s of size %d bytes:\n", azExtra[0], nData);
|
||||
if( findOption("raw", 0, 0)!=0 ){
|
||||
printBlob(aData, nData);
|
||||
}else{
|
||||
decodeSegment(aData, nData);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
/*
|
||||
** Decode a single doclist and display the results on stdout.
|
||||
*/
|
||||
static void decodeDoclist(
|
||||
const unsigned char *aData, /* Content to print */
|
||||
int nData /* Number of bytes of content */
|
||||
){
|
||||
sqlite3_int64 iPrevDocid = 0;
|
||||
sqlite3_int64 iDocid;
|
||||
sqlite3_int64 iPos;
|
||||
sqlite3_int64 iPrevPos = 0;
|
||||
sqlite3_int64 iCol;
|
||||
int i = 0;
|
||||
|
||||
while( i<nData ){
|
||||
i += getVarint(aData+i, &iDocid);
|
||||
printf("docid %lld col0", iDocid+iPrevDocid);
|
||||
iPrevDocid += iDocid;
|
||||
iPrevPos = 0;
|
||||
while( 1 ){
|
||||
i += getVarint(aData+i, &iPos);
|
||||
if( iPos==1 ){
|
||||
i += getVarint(aData+i, &iCol);
|
||||
printf(" col%lld", iCol);
|
||||
iPrevPos = 0;
|
||||
}else if( iPos==0 ){
|
||||
printf("\n");
|
||||
break;
|
||||
}else{
|
||||
iPrevPos += iPos - 2;
|
||||
printf(" %lld", iPrevPos);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Print the content of a doclist. The segment or segdir-root is
|
||||
** identified by azExtra[0]. If the first character of azExtra[0]
|
||||
** is 'r' then the remainder is the integer rowid of the %_segdir entry.
|
||||
** If the first character of azExtra[0] is not 'r' then, then all of
|
||||
** azExtra[0] is an integer which is the block number. The offset
|
||||
** into the segment is identified by azExtra[1]. The size of the doclist
|
||||
** is azExtra[2].
|
||||
**
|
||||
** If the --raw option is present in azExtra, then a hex dump is provided.
|
||||
** Otherwise a decoding is shown.
|
||||
*/
|
||||
static void showDoclist(sqlite3 *db, const char *zTab){
|
||||
const unsigned char *aData;
|
||||
sqlite3_int64 offset;
|
||||
int nData;
|
||||
sqlite3_stmt *pStmt;
|
||||
|
||||
offset = atoi64(azExtra[1]);
|
||||
nData = atoi(azExtra[2]);
|
||||
pStmt = prepareToGetSegment(db, zTab, azExtra[0]);
|
||||
if( sqlite3_step(pStmt)!=SQLITE_ROW ){
|
||||
sqlite3_finalize(pStmt);
|
||||
return;
|
||||
}
|
||||
aData = sqlite3_column_blob(pStmt, 0);
|
||||
printf("Doclist at %s offset %lld of size %d bytes:\n",
|
||||
azExtra[0], offset, nData);
|
||||
if( findOption("raw", 0, 0)!=0 ){
|
||||
printBlob(aData+offset, nData);
|
||||
}else{
|
||||
decodeDoclist(aData+offset, nData);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
/*
|
||||
** Show the top N largest segments
|
||||
*/
|
||||
static void listBigSegments(sqlite3 *db, const char *zTab){
|
||||
int nTop, i;
|
||||
sqlite3_stmt *pStmt;
|
||||
sqlite3_int64 sz;
|
||||
sqlite3_int64 id;
|
||||
|
||||
nTop = atoi(findOption("top", 1, "25"));
|
||||
printf("The %d largest segments:\n", nTop);
|
||||
pStmt = prepare(db,
|
||||
"SELECT blockid, length(block) AS len FROM '%q_segments'"
|
||||
" ORDER BY 2 DESC, 1"
|
||||
" LIMIT %d", zTab, nTop);
|
||||
i = 0;
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
i++;
|
||||
id = sqlite3_column_int64(pStmt, 0);
|
||||
sz = sqlite3_column_int64(pStmt, 1);
|
||||
printf(" %2d. %9lld size %lld\n", i, id, sz);
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
|
||||
|
||||
static void usage(const char *argv0){
|
||||
fprintf(stderr, "Usage: %s DATABASE\n"
|
||||
" or: %s DATABASE FTS3TABLE ARGS...\n", argv0, argv0);
|
||||
fprintf(stderr,
|
||||
"ARGS:\n"
|
||||
" big-segments [--top N] show the largest segments\n"
|
||||
" doclist BLOCKID OFFSET SIZE [--raw] Decode a doclist\n"
|
||||
" schema FTS table schema\n"
|
||||
" segdir directory of segments\n"
|
||||
" segment BLOCKID [--raw] content of a segment\n"
|
||||
" segment-stats info on segment sizes\n"
|
||||
" stat the %%_stat table\n"
|
||||
" vocabulary [--top N] document vocabulary\n"
|
||||
);
|
||||
exit(1);
|
||||
}
|
||||
|
||||
int main(int argc, char **argv){
|
||||
sqlite3 *db;
|
||||
int rc;
|
||||
const char *zTab;
|
||||
const char *zCmd;
|
||||
|
||||
if( argc<2 ) usage(argv[0]);
|
||||
rc = sqlite3_open(argv[1], &db);
|
||||
if( rc ){
|
||||
fprintf(stderr, "Cannot open %s\n", argv[1]);
|
||||
exit(1);
|
||||
}
|
||||
if( argc==2 ){
|
||||
sqlite3_stmt *pStmt;
|
||||
int cnt = 0;
|
||||
pStmt = prepare(db, "SELECT b.sql"
|
||||
" FROM sqlite_master a, sqlite_master b"
|
||||
" WHERE a.name GLOB '*_segdir'"
|
||||
" AND b.name=substr(a.name,1,length(a.name)-7)"
|
||||
" ORDER BY 1");
|
||||
while( sqlite3_step(pStmt)==SQLITE_ROW ){
|
||||
cnt++;
|
||||
printf("%s;\n", sqlite3_column_text(pStmt, 0));
|
||||
}
|
||||
sqlite3_finalize(pStmt);
|
||||
if( cnt==0 ){
|
||||
printf("/* No FTS3/4 tables found in database %s */\n", argv[1]);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
if( argc<4 ) usage(argv[0]);
|
||||
zTab = argv[2];
|
||||
zCmd = argv[3];
|
||||
nExtra = argc-4;
|
||||
azExtra = argv+4;
|
||||
if( strcmp(zCmd,"big-segments")==0 ){
|
||||
listBigSegments(db, zTab);
|
||||
}else if( strcmp(zCmd,"doclist")==0 ){
|
||||
if( argc<7 ) usage(argv[0]);
|
||||
showDoclist(db, zTab);
|
||||
}else if( strcmp(zCmd,"schema")==0 ){
|
||||
showSchema(db, zTab);
|
||||
}else if( strcmp(zCmd,"segdir")==0 ){
|
||||
showSegdirMap(db, zTab);
|
||||
}else if( strcmp(zCmd,"segment")==0 ){
|
||||
if( argc<5 ) usage(argv[0]);
|
||||
showSegment(db, zTab);
|
||||
}else if( strcmp(zCmd,"segment-stats")==0 ){
|
||||
showSegmentStats(db, zTab);
|
||||
}else if( strcmp(zCmd,"stat")==0 ){
|
||||
showStat(db, zTab);
|
||||
}else if( strcmp(zCmd,"vocabulary")==0 ){
|
||||
showVocabulary(db, zTab);
|
||||
}else{
|
||||
usage(argv[0]);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,983 +0,0 @@
|
||||
|
||||
source [file join [file dirname [info script]] parseunicode.tcl]
|
||||
|
||||
proc print_rd {map} {
|
||||
global tl_lookup_table
|
||||
set aChar [list]
|
||||
set lRange [list]
|
||||
|
||||
set nRange 1
|
||||
set iFirst [lindex $map 0 0]
|
||||
set cPrev [lindex $map 0 1]
|
||||
set fPrev [lindex $map 0 2]
|
||||
|
||||
foreach m [lrange $map 1 end] {
|
||||
foreach {i c f} $m {}
|
||||
|
||||
if {$cPrev == $c && $fPrev==$f} {
|
||||
for {set j [expr $iFirst+$nRange]} {$j<$i} {incr j} {
|
||||
if {[info exists tl_lookup_table($j)]==0} break
|
||||
}
|
||||
|
||||
if {$j==$i} {
|
||||
set nNew [expr {(1 + $i - $iFirst)}]
|
||||
if {$nNew<=8} {
|
||||
set nRange $nNew
|
||||
continue
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lappend lRange [list $iFirst $nRange]
|
||||
lappend aChar $cPrev
|
||||
lappend aFlag $fPrev
|
||||
|
||||
set iFirst $i
|
||||
set cPrev $c
|
||||
set fPrev $f
|
||||
set nRange 1
|
||||
}
|
||||
lappend lRange [list $iFirst $nRange]
|
||||
lappend aChar $cPrev
|
||||
lappend aFlag $fPrev
|
||||
|
||||
puts "/*"
|
||||
puts "** If the argument is a codepoint corresponding to a lowercase letter"
|
||||
puts "** in the ASCII range with a diacritic added, return the codepoint"
|
||||
puts "** of the ASCII letter only. For example, if passed 235 - \"LATIN"
|
||||
puts "** SMALL LETTER E WITH DIAERESIS\" - return 65 (\"LATIN SMALL LETTER"
|
||||
puts "** E\"). The resuls of passing a codepoint that corresponds to an"
|
||||
puts "** uppercase letter are undefined."
|
||||
puts "*/"
|
||||
puts "static int ${::remove_diacritic}(int c, int bComplex)\{"
|
||||
puts " unsigned short aDia\[\] = \{"
|
||||
puts -nonewline " 0, "
|
||||
set i 1
|
||||
foreach r $lRange {
|
||||
foreach {iCode nRange} $r {}
|
||||
if {($i % 8)==0} {puts "" ; puts -nonewline " " }
|
||||
incr i
|
||||
|
||||
puts -nonewline [format "%5d" [expr ($iCode<<3) + $nRange-1]]
|
||||
puts -nonewline ", "
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
puts "#define HIBIT ((unsigned char)0x80)"
|
||||
puts " unsigned char aChar\[\] = \{"
|
||||
puts -nonewline " '\\0', "
|
||||
set i 1
|
||||
foreach c $aChar f $aFlag {
|
||||
if { $f } {
|
||||
set str "'$c'|HIBIT, "
|
||||
} else {
|
||||
set str "'$c', "
|
||||
}
|
||||
if {$c == ""} { set str "'\\0', " }
|
||||
|
||||
if {($i % 6)==0} {puts "" ; puts -nonewline " " }
|
||||
incr i
|
||||
puts -nonewline "$str"
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
puts {
|
||||
unsigned int key = (((unsigned int)c)<<3) | 0x00000007;
|
||||
int iRes = 0;
|
||||
int iHi = sizeof(aDia)/sizeof(aDia[0]) - 1;
|
||||
int iLo = 0;
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
if( key >= aDia[iTest] ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
assert( key>=aDia[iRes] );
|
||||
if( bComplex==0 && (aChar[iRes] & 0x80) ) return c;
|
||||
return (c > (aDia[iRes]>>3) + (aDia[iRes]&0x07)) ? c : ((int)aChar[iRes] & 0x7F);}
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
proc print_isdiacritic {zFunc map} {
|
||||
|
||||
set lCode [list]
|
||||
foreach m $map {
|
||||
foreach {code char flag} $m {}
|
||||
if {$flag} continue
|
||||
if {$code && $char == ""} { lappend lCode $code }
|
||||
}
|
||||
set lCode [lsort -integer $lCode]
|
||||
set iFirst [lindex $lCode 0]
|
||||
set iLast [lindex $lCode end]
|
||||
|
||||
set i1 0
|
||||
set i2 0
|
||||
|
||||
foreach c $lCode {
|
||||
set i [expr $c - $iFirst]
|
||||
if {$i < 32} {
|
||||
set i1 [expr {$i1 | (1<<$i)}]
|
||||
} else {
|
||||
set i2 [expr {$i2 | (1<<($i-32))}]
|
||||
}
|
||||
}
|
||||
|
||||
puts "/*"
|
||||
puts "** Return true if the argument interpreted as a unicode codepoint"
|
||||
puts "** is a diacritical modifier character."
|
||||
puts "*/"
|
||||
puts "int ${zFunc}\(int c)\{"
|
||||
puts " unsigned int mask0 = [format "0x%08X" $i1];"
|
||||
puts " unsigned int mask1 = [format "0x%08X" $i2];"
|
||||
|
||||
puts " if( c<$iFirst || c>$iLast ) return 0;"
|
||||
puts " return (c < $iFirst+32) ?"
|
||||
puts " (mask0 & ((unsigned int)1 << (c-$iFirst))) :"
|
||||
puts " (mask1 & ((unsigned int)1 << (c-$iFirst-32)));"
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
proc an_load_separator_ranges {} {
|
||||
global unicodedata.txt
|
||||
set lSep [an_load_unicodedata_text ${unicodedata.txt}]
|
||||
unset -nocomplain iFirst
|
||||
unset -nocomplain nRange
|
||||
set lRange [list]
|
||||
foreach sep $lSep {
|
||||
if {0==[info exists iFirst]} {
|
||||
set iFirst $sep
|
||||
set nRange 1
|
||||
} elseif { $sep == ($iFirst+$nRange) } {
|
||||
incr nRange
|
||||
} else {
|
||||
lappend lRange [list $iFirst $nRange]
|
||||
set iFirst $sep
|
||||
set nRange 1
|
||||
}
|
||||
}
|
||||
lappend lRange [list $iFirst $nRange]
|
||||
set lRange
|
||||
}
|
||||
|
||||
proc an_print_range_array {lRange} {
|
||||
set iFirstMax 0
|
||||
set nRangeMax 0
|
||||
foreach range $lRange {
|
||||
foreach {iFirst nRange} $range {}
|
||||
if {$iFirst > $iFirstMax} {set iFirstMax $iFirst}
|
||||
if {$nRange > $nRangeMax} {set nRangeMax $nRange}
|
||||
}
|
||||
if {$iFirstMax >= (1<<22)} {error "first-max is too large for format"}
|
||||
if {$nRangeMax >= (1<<10)} {error "range-max is too large for format"}
|
||||
|
||||
puts -nonewline " "
|
||||
puts [string trim {
|
||||
/* Each unsigned integer in the following array corresponds to a contiguous
|
||||
** range of unicode codepoints that are not either letters or numbers (i.e.
|
||||
** codepoints for which this function should return 0).
|
||||
**
|
||||
** The most significant 22 bits in each 32-bit value contain the first
|
||||
** codepoint in the range. The least significant 10 bits are used to store
|
||||
** the size of the range (always at least 1). In other words, the value
|
||||
** ((C<<22) + N) represents a range of N codepoints starting with codepoint
|
||||
** C. It is not possible to represent a range larger than 1023 codepoints
|
||||
** using this format.
|
||||
*/
|
||||
}]
|
||||
puts -nonewline " static const unsigned int aEntry\[\] = \{"
|
||||
set i 0
|
||||
foreach range $lRange {
|
||||
foreach {iFirst nRange} $range {}
|
||||
set u32 [format "0x%08X" [expr ($iFirst<<10) + $nRange]]
|
||||
|
||||
if {($i % 5)==0} {puts "" ; puts -nonewline " "}
|
||||
puts -nonewline " $u32,"
|
||||
incr i
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
}
|
||||
|
||||
proc an_print_ascii_bitmap {lRange} {
|
||||
foreach range $lRange {
|
||||
foreach {iFirst nRange} $range {}
|
||||
for {set i $iFirst} {$i < ($iFirst+$nRange)} {incr i} {
|
||||
if {$i<=127} { set a($i) 1 }
|
||||
}
|
||||
}
|
||||
|
||||
set aAscii [list 0 0 0 0]
|
||||
foreach key [array names a] {
|
||||
set idx [expr $key >> 5]
|
||||
lset aAscii $idx [expr [lindex $aAscii $idx] | (1 << ($key&0x001F))]
|
||||
}
|
||||
|
||||
puts " static const unsigned int aAscii\[4\] = \{"
|
||||
puts -nonewline " "
|
||||
foreach v $aAscii { puts -nonewline [format " 0x%08X," $v] }
|
||||
puts ""
|
||||
puts " \};"
|
||||
}
|
||||
|
||||
proc print_isalnum {zFunc lRange} {
|
||||
puts "/*"
|
||||
puts "** Return true if the argument corresponds to a unicode codepoint"
|
||||
puts "** classified as either a letter or a number. Otherwise false."
|
||||
puts "**"
|
||||
puts "** The results are undefined if the value passed to this function"
|
||||
puts "** is less than zero."
|
||||
puts "*/"
|
||||
puts "int ${zFunc}\(int c)\{"
|
||||
an_print_range_array $lRange
|
||||
an_print_ascii_bitmap $lRange
|
||||
puts {
|
||||
if( (unsigned int)c<128 ){
|
||||
return ( (aAscii[c >> 5] & ((unsigned int)1 << (c & 0x001F)))==0 );
|
||||
}else if( (unsigned int)c<(1<<22) ){
|
||||
unsigned int key = (((unsigned int)c)<<10) | 0x000003FF;
|
||||
int iRes = 0;
|
||||
int iHi = sizeof(aEntry)/sizeof(aEntry[0]) - 1;
|
||||
int iLo = 0;
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
if( key >= aEntry[iTest] ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
assert( aEntry[0]<key );
|
||||
assert( key>=aEntry[iRes] );
|
||||
return (((unsigned int)c) >= ((aEntry[iRes]>>10) + (aEntry[iRes]&0x3FF)));
|
||||
}
|
||||
return 1;}
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
proc print_test_isalnum {zFunc lRange} {
|
||||
foreach range $lRange {
|
||||
foreach {iFirst nRange} $range {}
|
||||
for {set i $iFirst} {$i < ($iFirst+$nRange)} {incr i} { set a($i) 1 }
|
||||
}
|
||||
|
||||
puts "static int isalnum_test(int *piCode)\{"
|
||||
puts -nonewline " unsigned char aAlnum\[\] = \{"
|
||||
for {set i 0} {$i < 70000} {incr i} {
|
||||
if {($i % 32)==0} { puts "" ; puts -nonewline " " }
|
||||
set bFlag [expr ![info exists a($i)]]
|
||||
puts -nonewline "${bFlag},"
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
|
||||
puts -nonewline " int aLargeSep\[\] = \{"
|
||||
set i 0
|
||||
foreach iSep [lsort -integer [array names a]] {
|
||||
if {$iSep<70000} continue
|
||||
if {($i % 8)==0} { puts "" ; puts -nonewline " " }
|
||||
puts -nonewline " $iSep,"
|
||||
incr i
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
puts -nonewline " int aLargeOther\[\] = \{"
|
||||
set i 0
|
||||
foreach iSep [lsort -integer [array names a]] {
|
||||
if {$iSep<70000} continue
|
||||
if {[info exists a([expr $iSep-1])]==0} {
|
||||
if {($i % 8)==0} { puts "" ; puts -nonewline " " }
|
||||
puts -nonewline " [expr $iSep-1],"
|
||||
incr i
|
||||
}
|
||||
if {[info exists a([expr $iSep+1])]==0} {
|
||||
if {($i % 8)==0} { puts "" ; puts -nonewline " " }
|
||||
puts -nonewline " [expr $iSep+1],"
|
||||
incr i
|
||||
}
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
|
||||
puts [subst -nocommands {
|
||||
int i;
|
||||
for(i=0; i<sizeof(aAlnum)/sizeof(aAlnum[0]); i++){
|
||||
if( ${zFunc}(i)!=aAlnum[i] ){
|
||||
*piCode = i;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
for(i=0; i<sizeof(aLargeSep)/sizeof(aLargeSep[0]); i++){
|
||||
if( ${zFunc}(aLargeSep[i])!=0 ){
|
||||
*piCode = aLargeSep[i];
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
for(i=0; i<sizeof(aLargeOther)/sizeof(aLargeOther[0]); i++){
|
||||
if( ${zFunc}(aLargeOther[i])!=1 ){
|
||||
*piCode = aLargeOther[i];
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
}]
|
||||
puts " return 0;"
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
proc tl_create_records {} {
|
||||
global tl_lookup_table
|
||||
|
||||
set iFirst ""
|
||||
set nOff 0
|
||||
set nRange 0
|
||||
set nIncr 0
|
||||
|
||||
set lRecord [list]
|
||||
foreach code [lsort -integer [array names tl_lookup_table]] {
|
||||
set mapping $tl_lookup_table($code)
|
||||
if {$iFirst == ""} {
|
||||
set iFirst $code
|
||||
set nOff [expr $mapping - $code]
|
||||
set nRange 1
|
||||
set nIncr 1
|
||||
} else {
|
||||
set diff [expr $code - ($iFirst + ($nIncr * ($nRange - 1)))]
|
||||
if { $nRange==1 && ($diff==1 || $diff==2) } {
|
||||
set nIncr $diff
|
||||
}
|
||||
|
||||
if {$diff != $nIncr || ($mapping - $code)!=$nOff} {
|
||||
if { $nRange==1 } {set nIncr 1}
|
||||
lappend lRecord [list $iFirst $nIncr $nRange $nOff]
|
||||
set iFirst $code
|
||||
set nOff [expr $mapping - $code]
|
||||
set nRange 1
|
||||
set nIncr 1
|
||||
} else {
|
||||
incr nRange
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lappend lRecord [list $iFirst $nIncr $nRange $nOff]
|
||||
|
||||
set lRecord
|
||||
}
|
||||
|
||||
proc tl_print_table_header {} {
|
||||
puts -nonewline " "
|
||||
puts [string trim {
|
||||
/* Each entry in the following array defines a rule for folding a range
|
||||
** of codepoints to lower case. The rule applies to a range of nRange
|
||||
** codepoints starting at codepoint iCode.
|
||||
**
|
||||
** If the least significant bit in flags is clear, then the rule applies
|
||||
** to all nRange codepoints (i.e. all nRange codepoints are upper case and
|
||||
** need to be folded). Or, if it is set, then the rule only applies to
|
||||
** every second codepoint in the range, starting with codepoint C.
|
||||
**
|
||||
** The 7 most significant bits in flags are an index into the aiOff[]
|
||||
** array. If a specific codepoint C does require folding, then its lower
|
||||
** case equivalent is ((C + aiOff[flags>>1]) & 0xFFFF).
|
||||
**
|
||||
** The contents of this array are generated by parsing the CaseFolding.txt
|
||||
** file distributed as part of the "Unicode Character Database". See
|
||||
** http://www.unicode.org for details.
|
||||
*/
|
||||
}]
|
||||
puts " static const struct TableEntry \{"
|
||||
puts " unsigned short iCode;"
|
||||
puts " unsigned char flags;"
|
||||
puts " unsigned char nRange;"
|
||||
puts " \} aEntry\[\] = \{"
|
||||
}
|
||||
|
||||
proc tl_print_table_entry {togglevar entry liOff} {
|
||||
upvar $togglevar t
|
||||
foreach {iFirst nIncr nRange nOff} $entry {}
|
||||
|
||||
if {$iFirst > (1<<16)} { return 1 }
|
||||
|
||||
if {[info exists t]==0} {set t 0}
|
||||
if {$t==0} { puts -nonewline " " }
|
||||
|
||||
set flags 0
|
||||
if {$nIncr==2} { set flags 1 ; set nRange [expr $nRange * 2]}
|
||||
if {$nOff<0} { incr nOff [expr (1<<16)] }
|
||||
|
||||
set idx [lsearch $liOff $nOff]
|
||||
if {$idx<0} {error "malfunction generating aiOff"}
|
||||
set flags [expr $flags + $idx*2]
|
||||
|
||||
set txt "{$iFirst, $flags, $nRange},"
|
||||
if {$t==2} {
|
||||
puts $txt
|
||||
} else {
|
||||
puts -nonewline [format "% -23s" $txt]
|
||||
}
|
||||
set t [expr ($t+1)%3]
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
proc tl_print_table_footer {togglevar} {
|
||||
upvar $togglevar t
|
||||
if {$t!=0} {puts ""}
|
||||
puts " \};"
|
||||
}
|
||||
|
||||
proc tl_print_if_entry {entry} {
|
||||
foreach {iFirst nIncr nRange nOff} $entry {}
|
||||
if {$nIncr==2} {error "tl_print_if_entry needs improvement!"}
|
||||
|
||||
puts " else if( c>=$iFirst && c<[expr $iFirst+$nRange] )\{"
|
||||
puts " ret = c + $nOff;"
|
||||
puts " \}"
|
||||
}
|
||||
|
||||
proc tl_generate_ioff_table {lRecord} {
|
||||
foreach entry $lRecord {
|
||||
foreach {iFirst nIncr nRange iOff} $entry {}
|
||||
if {$iOff<0} { incr iOff [expr (1<<16)] }
|
||||
if {[info exists a($iOff)]} continue
|
||||
set a($iOff) 1
|
||||
}
|
||||
|
||||
set liOff [lsort -integer [array names a]]
|
||||
if {[llength $liOff]>128} { error "Too many distinct ioffs" }
|
||||
return $liOff
|
||||
}
|
||||
|
||||
proc tl_print_ioff_table {liOff} {
|
||||
puts -nonewline " static const unsigned short aiOff\[\] = \{"
|
||||
set i 0
|
||||
foreach off $liOff {
|
||||
if {($i % 8)==0} {puts "" ; puts -nonewline " "}
|
||||
puts -nonewline [format "% -7s" "$off,"]
|
||||
incr i
|
||||
}
|
||||
puts ""
|
||||
puts " \};"
|
||||
|
||||
}
|
||||
|
||||
proc print_fold {zFunc} {
|
||||
|
||||
set lRecord [tl_create_records]
|
||||
|
||||
set lHigh [list]
|
||||
puts "/*"
|
||||
puts "** Interpret the argument as a unicode codepoint. If the codepoint"
|
||||
puts "** is an upper case character that has a lower case equivalent,"
|
||||
puts "** return the codepoint corresponding to the lower case version."
|
||||
puts "** Otherwise, return a copy of the argument."
|
||||
puts "**"
|
||||
puts "** The results are undefined if the value passed to this function"
|
||||
puts "** is less than zero."
|
||||
puts "*/"
|
||||
puts "int ${zFunc}\(int c, int eRemoveDiacritic)\{"
|
||||
|
||||
set liOff [tl_generate_ioff_table $lRecord]
|
||||
tl_print_table_header
|
||||
foreach entry $lRecord {
|
||||
if {[tl_print_table_entry toggle $entry $liOff]} {
|
||||
lappend lHigh $entry
|
||||
}
|
||||
}
|
||||
tl_print_table_footer toggle
|
||||
tl_print_ioff_table $liOff
|
||||
|
||||
puts [subst -nocommands {
|
||||
int ret = c;
|
||||
|
||||
assert( sizeof(unsigned short)==2 && sizeof(unsigned char)==1 );
|
||||
|
||||
if( c<128 ){
|
||||
if( c>='A' && c<='Z' ) ret = c + ('a' - 'A');
|
||||
}else if( c<65536 ){
|
||||
const struct TableEntry *p;
|
||||
int iHi = sizeof(aEntry)/sizeof(aEntry[0]) - 1;
|
||||
int iLo = 0;
|
||||
int iRes = -1;
|
||||
|
||||
assert( c>aEntry[0].iCode );
|
||||
while( iHi>=iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
int cmp = (c - aEntry[iTest].iCode);
|
||||
if( cmp>=0 ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest-1;
|
||||
}
|
||||
}
|
||||
|
||||
assert( iRes>=0 && c>=aEntry[iRes].iCode );
|
||||
p = &aEntry[iRes];
|
||||
if( c<(p->iCode + p->nRange) && 0==(0x01 & p->flags & (p->iCode ^ c)) ){
|
||||
ret = (c + (aiOff[p->flags>>1])) & 0x0000FFFF;
|
||||
assert( ret>0 );
|
||||
}
|
||||
|
||||
if( eRemoveDiacritic ){
|
||||
ret = ${::remove_diacritic}(ret, eRemoveDiacritic==2);
|
||||
}
|
||||
}
|
||||
}]
|
||||
|
||||
foreach entry $lHigh {
|
||||
tl_print_if_entry $entry
|
||||
}
|
||||
|
||||
puts ""
|
||||
puts " return ret;"
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
proc code {txt} {
|
||||
set txt [string trimright $txt]
|
||||
set txt [string trimleft $txt "\n"]
|
||||
set n [expr {[string length $txt] - [string length [string trim $txt]]}]
|
||||
set ret ""
|
||||
foreach L [split $txt "\n"] {
|
||||
append ret "[string range $L $n end]\n"
|
||||
}
|
||||
return [uplevel "subst -nocommands {$ret}"]
|
||||
}
|
||||
|
||||
proc intarray {lInt} {
|
||||
set ret ""
|
||||
set n [llength $lInt]
|
||||
for {set i 0} {$i < $n} {incr i 10} {
|
||||
append ret "\n "
|
||||
foreach int [lrange $lInt $i [expr $i+9]] {
|
||||
append ret [format "%-7s" "$int, "]
|
||||
}
|
||||
}
|
||||
append ret "\n "
|
||||
set ret
|
||||
}
|
||||
|
||||
proc categories_switch {Cvar first lSecond} {
|
||||
upvar $Cvar C
|
||||
set ret ""
|
||||
append ret "case '$first':\n"
|
||||
append ret " switch( zCat\[1\] ){\n"
|
||||
foreach s $lSecond {
|
||||
append ret " case '$s': aArray\[$C($first$s)\] = 1; break;\n"
|
||||
}
|
||||
append ret " case '*': \n"
|
||||
foreach s $lSecond {
|
||||
append ret " aArray\[$C($first$s)\] = 1;\n"
|
||||
}
|
||||
append ret " break;\n"
|
||||
append ret " default: return 1;"
|
||||
append ret " }\n"
|
||||
append ret " break;\n"
|
||||
}
|
||||
|
||||
# Argument is a list. Each element of which is itself a list of two elements:
|
||||
#
|
||||
# * the codepoint
|
||||
# * the category
|
||||
#
|
||||
# List elements are sorted in order of codepoint.
|
||||
#
|
||||
proc print_categories {lMap} {
|
||||
set categories {
|
||||
Cc Cf Cn Cs
|
||||
Ll Lm Lo Lt Lu
|
||||
Mc Me Mn
|
||||
Nd Nl No
|
||||
Pc Pd Pe Pf Pi Po Ps
|
||||
Sc Sk Sm So
|
||||
Zl Zp Zs
|
||||
|
||||
LC Co
|
||||
}
|
||||
|
||||
for {set i 0} {$i < [llength $categories]} {incr i} {
|
||||
set C([lindex $categories $i]) [expr 1+$i]
|
||||
}
|
||||
|
||||
set caseC [categories_switch C C {c f n s o}]
|
||||
set caseL [categories_switch C L {l m o t u C}]
|
||||
set caseM [categories_switch C M {c e n}]
|
||||
set caseN [categories_switch C N {d l o}]
|
||||
set caseP [categories_switch C P {c d e f i o s}]
|
||||
set caseS [categories_switch C S {c k m o}]
|
||||
set caseZ [categories_switch C Z {l p s}]
|
||||
|
||||
set nCat [expr [llength [array names C]] + 1]
|
||||
puts [code {
|
||||
int sqlite3Fts5UnicodeCatParse(const char *zCat, u8 *aArray){
|
||||
aArray[0] = 1;
|
||||
switch( zCat[0] ){
|
||||
$caseC
|
||||
$caseL
|
||||
$caseM
|
||||
$caseN
|
||||
$caseP
|
||||
$caseS
|
||||
$caseZ
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
}]
|
||||
|
||||
set nRepeat 0
|
||||
set first [lindex $lMap 0 0]
|
||||
set class [lindex $lMap 0 1]
|
||||
set prev -1
|
||||
|
||||
set CASE(0) "Lu"
|
||||
set CASE(1) "Ll"
|
||||
|
||||
foreach m $lMap {
|
||||
foreach {codepoint cl} $m {}
|
||||
set codepoint [expr "0x$codepoint"]
|
||||
if {$codepoint>=(1<<20)} continue
|
||||
|
||||
set bNew 0
|
||||
if {$codepoint!=($prev+1)} {
|
||||
set bNew 1
|
||||
} elseif {
|
||||
$cl==$class || ($class=="LC" && $cl==$CASE([expr $nRepeat & 0x01]))
|
||||
} {
|
||||
incr nRepeat
|
||||
} elseif {$class=="Lu" && $nRepeat==1 && $cl=="Ll"} {
|
||||
set class LC
|
||||
incr nRepeat
|
||||
} else {
|
||||
set bNew 1
|
||||
}
|
||||
if {$bNew} {
|
||||
lappend lEntries [list $first $class $nRepeat]
|
||||
set nRepeat 1
|
||||
set first $codepoint
|
||||
set class $cl
|
||||
}
|
||||
set prev $codepoint
|
||||
}
|
||||
if {$nRepeat>0} {
|
||||
lappend lEntries [list $first $class $nRepeat]
|
||||
}
|
||||
|
||||
set aBlock [list 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
|
||||
set aMap [list]
|
||||
foreach e $lEntries {
|
||||
foreach {cp class nRepeat} $e {}
|
||||
set block [expr ($cp>>16)]
|
||||
if {$block>0 && [lindex $aBlock $block]==0} {
|
||||
for {set i 1} {$i<=$block} {incr i} {
|
||||
if {[lindex $aBlock $i]==0} {
|
||||
lset aBlock $i [llength $aMap]
|
||||
}
|
||||
}
|
||||
}
|
||||
lappend aMap [expr {$cp & 0xFFFF}]
|
||||
lappend aData [expr {($nRepeat << 5) + $C($class)}]
|
||||
}
|
||||
for {set i 1} {$i<[llength $aBlock]} {incr i} {
|
||||
if {[lindex $aBlock $i]==0} {
|
||||
lset aBlock $i [llength $aMap]
|
||||
}
|
||||
}
|
||||
|
||||
set aBlockArray [intarray $aBlock]
|
||||
set aMapArray [intarray $aMap]
|
||||
set aDataArray [intarray $aData]
|
||||
puts [code {
|
||||
static u16 aFts5UnicodeBlock[] = {$aBlockArray};
|
||||
static u16 aFts5UnicodeMap[] = {$aMapArray};
|
||||
static u16 aFts5UnicodeData[] = {$aDataArray};
|
||||
|
||||
int sqlite3Fts5UnicodeCategory(u32 iCode) {
|
||||
int iRes = -1;
|
||||
int iHi;
|
||||
int iLo;
|
||||
int ret;
|
||||
u16 iKey;
|
||||
|
||||
if( iCode>=(1<<20) ){
|
||||
return 0;
|
||||
}
|
||||
iLo = aFts5UnicodeBlock[(iCode>>16)];
|
||||
iHi = aFts5UnicodeBlock[1+(iCode>>16)];
|
||||
iKey = (iCode & 0xFFFF);
|
||||
while( iHi>iLo ){
|
||||
int iTest = (iHi + iLo) / 2;
|
||||
assert( iTest>=iLo && iTest<iHi );
|
||||
if( iKey>=aFts5UnicodeMap[iTest] ){
|
||||
iRes = iTest;
|
||||
iLo = iTest+1;
|
||||
}else{
|
||||
iHi = iTest;
|
||||
}
|
||||
}
|
||||
|
||||
if( iRes<0 ) return 0;
|
||||
if( iKey>=(aFts5UnicodeMap[iRes]+(aFts5UnicodeData[iRes]>>5)) ) return 0;
|
||||
ret = aFts5UnicodeData[iRes] & 0x1F;
|
||||
if( ret!=$C(LC) ) return ret;
|
||||
return ((iKey - aFts5UnicodeMap[iRes]) & 0x01) ? $C(Ll) : $C(Lu);
|
||||
}
|
||||
|
||||
void sqlite3Fts5UnicodeAscii(u8 *aArray, u8 *aAscii){
|
||||
int i = 0;
|
||||
int iTbl = 0;
|
||||
while( i<128 ){
|
||||
int bToken = aArray[ aFts5UnicodeData[iTbl] & 0x1F ];
|
||||
int n = (aFts5UnicodeData[iTbl] >> 5) + i;
|
||||
for(; i<128 && i<n; i++){
|
||||
aAscii[i] = bToken;
|
||||
}
|
||||
iTbl++;
|
||||
}
|
||||
}
|
||||
}]
|
||||
}
|
||||
|
||||
proc print_test_categories {lMap} {
|
||||
|
||||
set lCP [list]
|
||||
foreach e $lMap {
|
||||
foreach {cp cat} $e {}
|
||||
if {[expr 0x$cp] < (1<<20)} {
|
||||
lappend lCP "{0x$cp, \"$cat\"}, "
|
||||
}
|
||||
}
|
||||
|
||||
set aCP "\n"
|
||||
for {set i 0} {$i < [llength $lCP]} {incr i 4} {
|
||||
append aCP " [join [lrange $lCP $i $i+3]]\n"
|
||||
}
|
||||
|
||||
|
||||
puts [code {
|
||||
static int categories_test (int *piCode){
|
||||
struct Codepoint {
|
||||
int iCode;
|
||||
const char *zCat;
|
||||
} aCP[] = {$aCP};
|
||||
int i;
|
||||
int iCP = 0;
|
||||
|
||||
for(i=0; i<1000000; i++){
|
||||
u8 aArray[40];
|
||||
int cat = 0;
|
||||
int c = 0;
|
||||
memset(aArray, 0, sizeof(aArray));
|
||||
if( aCP[iCP].iCode==i ){
|
||||
sqlite3Fts5UnicodeCatParse(aCP[iCP].zCat, aArray);
|
||||
iCP++;
|
||||
}else{
|
||||
aArray[0] = 1;
|
||||
}
|
||||
|
||||
c = sqlite3Fts5UnicodeCategory((u32)i);
|
||||
if( aArray[c]==0 ){
|
||||
*piCode = i;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
}]
|
||||
}
|
||||
|
||||
proc print_fold_test {zFunc mappings} {
|
||||
global tl_lookup_table
|
||||
|
||||
foreach m $mappings {
|
||||
set c [lindex $m 1]
|
||||
if {$c == ""} {
|
||||
set extra([lindex $m 0]) 0
|
||||
} else {
|
||||
scan $c %c i
|
||||
set extra([lindex $m 0]) $i
|
||||
}
|
||||
}
|
||||
|
||||
puts "static int fold_test(int *piCode)\{"
|
||||
puts -nonewline " static int aLookup\[\] = \{"
|
||||
for {set i 0} {$i < 70000} {incr i} {
|
||||
|
||||
set expected $i
|
||||
catch { set expected $tl_lookup_table($i) }
|
||||
set expected2 $expected
|
||||
catch { set expected2 $extra($expected2) }
|
||||
|
||||
if {($i % 4)==0} { puts "" ; puts -nonewline " " }
|
||||
puts -nonewline "$expected, $expected2, "
|
||||
}
|
||||
puts " \};"
|
||||
puts " int i;"
|
||||
puts " for(i=0; i<sizeof(aLookup)/sizeof(aLookup\[0\]); i++)\{"
|
||||
puts " int iCode = (i/2);"
|
||||
puts " int bFlag = i & 0x0001;"
|
||||
puts " if( ${zFunc}\(iCode, bFlag)!=aLookup\[i\] )\{"
|
||||
puts " *piCode = iCode;"
|
||||
puts " return 1;"
|
||||
puts " \}"
|
||||
puts " \}"
|
||||
puts " return 0;"
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
|
||||
proc print_fileheader {} {
|
||||
puts [string trim {
|
||||
/*
|
||||
** 2012-05-25
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
*/
|
||||
|
||||
/*
|
||||
** DO NOT EDIT THIS MACHINE GENERATED FILE.
|
||||
*/
|
||||
}]
|
||||
puts ""
|
||||
if {$::generate_fts5_code} {
|
||||
# no-op
|
||||
} else {
|
||||
puts "#ifndef SQLITE_DISABLE_FTS3_UNICODE"
|
||||
puts "#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)"
|
||||
}
|
||||
puts ""
|
||||
puts "#include <assert.h>"
|
||||
puts ""
|
||||
}
|
||||
|
||||
proc print_test_main {} {
|
||||
puts ""
|
||||
puts "#include <stdio.h>"
|
||||
puts ""
|
||||
puts "int main(int argc, char **argv)\{"
|
||||
puts " int r1, r2, r3;"
|
||||
puts " int code;"
|
||||
puts " r3 = 0;"
|
||||
puts " r1 = isalnum_test(&code);"
|
||||
puts " if( r1 ) printf(\"isalnum(): Problem with code %d\\n\",code);"
|
||||
puts " else printf(\"isalnum(): test passed\\n\");"
|
||||
puts " r2 = fold_test(&code);"
|
||||
puts " if( r2 ) printf(\"fold(): Problem with code %d\\n\",code);"
|
||||
puts " else printf(\"fold(): test passed\\n\");"
|
||||
if {$::generate_fts5_code} {
|
||||
puts " r3 = categories_test(&code);"
|
||||
puts " if( r3 ) printf(\"categories(): Problem with code %d\\n\",code);"
|
||||
puts " else printf(\"categories(): test passed\\n\");"
|
||||
}
|
||||
puts " return (r1 || r2 || r3);"
|
||||
puts "\}"
|
||||
}
|
||||
|
||||
# Proces the command line arguments. Exit early if they are not to
|
||||
# our liking.
|
||||
#
|
||||
proc usage {} {
|
||||
puts -nonewline stderr "Usage: $::argv0 ?-test? ?-fts5? "
|
||||
puts stderr "<CaseFolding.txt file> <UnicodeData.txt file>"
|
||||
exit 1
|
||||
}
|
||||
if {[llength $argv]<2} usage
|
||||
set unicodedata.txt [lindex $argv end]
|
||||
set casefolding.txt [lindex $argv end-1]
|
||||
|
||||
set remove_diacritic remove_diacritic
|
||||
set generate_test_code 0
|
||||
set generate_fts5_code 0
|
||||
set function_prefix "sqlite3Fts"
|
||||
for {set i 0} {$i < [llength $argv]-2} {incr i} {
|
||||
switch -- [lindex $argv $i] {
|
||||
-test {
|
||||
set generate_test_code 1
|
||||
}
|
||||
-fts5 {
|
||||
set function_prefix sqlite3Fts5
|
||||
set generate_fts5_code 1
|
||||
set remove_diacritic fts5_remove_diacritic
|
||||
}
|
||||
default {
|
||||
usage
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
print_fileheader
|
||||
|
||||
if {$::generate_test_code} {
|
||||
puts "typedef unsigned short int u16;"
|
||||
puts "typedef unsigned char u8;"
|
||||
puts "#include <string.h>"
|
||||
}
|
||||
|
||||
# Print the isalnum() function to stdout.
|
||||
#
|
||||
set lRange [an_load_separator_ranges]
|
||||
if {$generate_fts5_code==0} {
|
||||
print_isalnum ${function_prefix}UnicodeIsalnum $lRange
|
||||
}
|
||||
|
||||
# Leave a gap between the two generated C functions.
|
||||
#
|
||||
puts ""
|
||||
puts ""
|
||||
|
||||
# Load the fold data. This is used by the [rd_XXX] commands
|
||||
# as well as [print_fold].
|
||||
tl_load_casefolding_txt ${casefolding.txt}
|
||||
|
||||
set mappings [rd_load_unicodedata_text ${unicodedata.txt}]
|
||||
print_rd $mappings
|
||||
puts ""
|
||||
puts ""
|
||||
print_isdiacritic ${function_prefix}UnicodeIsdiacritic $mappings
|
||||
puts ""
|
||||
puts ""
|
||||
|
||||
# Print the fold() function to stdout.
|
||||
#
|
||||
print_fold ${function_prefix}UnicodeFold
|
||||
|
||||
if {$generate_fts5_code} {
|
||||
puts ""
|
||||
puts ""
|
||||
print_categories [cc_load_unicodedata_text ${unicodedata.txt}]
|
||||
}
|
||||
|
||||
# Print the test routines and main() function to stdout, if -test
|
||||
# was specified.
|
||||
#
|
||||
if {$::generate_test_code} {
|
||||
if {$generate_fts5_code==0} {
|
||||
print_test_isalnum ${function_prefix}UnicodeIsalnum $lRange
|
||||
}
|
||||
print_fold_test ${function_prefix}UnicodeFold $mappings
|
||||
print_test_categories [cc_load_unicodedata_text ${unicodedata.txt}]
|
||||
print_test_main
|
||||
}
|
||||
|
||||
if {$generate_fts5_code} {
|
||||
# no-op
|
||||
} else {
|
||||
puts "#endif /* defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4) */"
|
||||
puts "#endif /* !defined(SQLITE_DISABLE_FTS3_UNICODE) */"
|
||||
}
|
||||
@@ -1,205 +0,0 @@
|
||||
|
||||
#--------------------------------------------------------------------------
|
||||
# Parameter $zName must be a path to the file UnicodeData.txt. This command
|
||||
# reads the file and returns a list of mappings required to remove all
|
||||
# diacritical marks from a unicode string. Each mapping is itself a list
|
||||
# consisting of two elements - the unicode codepoint and the single ASCII
|
||||
# character that it should be replaced with, or an empty string if the
|
||||
# codepoint should simply be removed from the input. Examples:
|
||||
#
|
||||
# { 224 a 0 } (replace codepoint 224 to "a")
|
||||
# { 769 "" 0 } (remove codepoint 769 from input)
|
||||
#
|
||||
# Mappings are only returned for non-upper case codepoints. It is assumed
|
||||
# that the input has already been folded to lower case.
|
||||
#
|
||||
# The third value in the list is always either 0 or 1. 0 if the
|
||||
# UnicodeData.txt file maps the codepoint to a single ASCII character and
|
||||
# a diacritic, or 1 if the mapping is indirect. For example, consider the
|
||||
# two entries:
|
||||
#
|
||||
# 1ECD;LATIN SMALL LETTER O WITH DOT BELOW;Ll;0;L;006F 0323;;;;N;;;1ECC;;1ECC
|
||||
# 1ED9;LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW;Ll;0;L;1ECD 0302;;;;N;;;1ED8;;1ED8
|
||||
#
|
||||
# The first codepoint is a direct mapping (as 006F is ASCII and 0323 is a
|
||||
# diacritic). The second is an indirect mapping, as it maps to the
|
||||
# first codepoint plus 0302 (a diacritic).
|
||||
#
|
||||
proc rd_load_unicodedata_text {zName} {
|
||||
global tl_lookup_table
|
||||
|
||||
set fd [open $zName]
|
||||
set lField {
|
||||
code
|
||||
character_name
|
||||
general_category
|
||||
canonical_combining_classes
|
||||
bidirectional_category
|
||||
character_decomposition_mapping
|
||||
decimal_digit_value
|
||||
digit_value
|
||||
numeric_value
|
||||
mirrored
|
||||
unicode_1_name
|
||||
iso10646_comment_field
|
||||
uppercase_mapping
|
||||
lowercase_mapping
|
||||
titlecase_mapping
|
||||
}
|
||||
set lRet [list]
|
||||
|
||||
while { ![eof $fd] } {
|
||||
set line [gets $fd]
|
||||
if {$line == ""} continue
|
||||
|
||||
set fields [split $line ";"]
|
||||
if {[llength $fields] != [llength $lField]} { error "parse error: $line" }
|
||||
foreach $lField $fields {}
|
||||
if { [llength $character_decomposition_mapping]!=2
|
||||
|| [string is xdigit [lindex $character_decomposition_mapping 0]]==0
|
||||
} {
|
||||
continue
|
||||
}
|
||||
|
||||
set iCode [expr "0x$code"]
|
||||
set iAscii [expr "0x[lindex $character_decomposition_mapping 0]"]
|
||||
set iDia [expr "0x[lindex $character_decomposition_mapping 1]"]
|
||||
|
||||
# Filter out upper-case characters, as they will be mapped to their
|
||||
# lower-case equivalents before this data is used.
|
||||
if {[info exists tl_lookup_table($iCode)]} continue
|
||||
|
||||
# Check if this is an indirect mapping. If so, set bIndirect to true
|
||||
# and change $iAscii to the indirectly mappped ASCII character.
|
||||
set bIndirect 0
|
||||
if {[info exists dia($iDia)] && [info exists mapping($iAscii)]} {
|
||||
set iAscii $mapping($iAscii)
|
||||
set bIndirect 1
|
||||
}
|
||||
|
||||
if { ($iAscii >= 97 && $iAscii <= 122)
|
||||
|| ($iAscii >= 65 && $iAscii <= 90)
|
||||
} {
|
||||
lappend lRet [list $iCode [string tolower [format %c $iAscii]] $bIndirect]
|
||||
set mapping($iCode) $iAscii
|
||||
set dia($iDia) 1
|
||||
}
|
||||
}
|
||||
|
||||
foreach d [array names dia] {
|
||||
lappend lRet [list $d "" 0]
|
||||
}
|
||||
set lRet [lsort -integer -index 0 $lRet]
|
||||
|
||||
close $fd
|
||||
set lRet
|
||||
}
|
||||
|
||||
#-------------------------------------------------------------------------
|
||||
# Parameter $zName must be a path to the file UnicodeData.txt. This command
|
||||
# reads the file and returns a list of codepoints (integers). The list
|
||||
# contains all codepoints in the UnicodeData.txt assigned to any "General
|
||||
# Category" that is not a "Letter" or "Number".
|
||||
#
|
||||
proc an_load_unicodedata_text {zName} {
|
||||
set fd [open $zName]
|
||||
set lField {
|
||||
code
|
||||
character_name
|
||||
general_category
|
||||
canonical_combining_classes
|
||||
bidirectional_category
|
||||
character_decomposition_mapping
|
||||
decimal_digit_value
|
||||
digit_value
|
||||
numeric_value
|
||||
mirrored
|
||||
unicode_1_name
|
||||
iso10646_comment_field
|
||||
uppercase_mapping
|
||||
lowercase_mapping
|
||||
titlecase_mapping
|
||||
}
|
||||
set lRet [list]
|
||||
|
||||
while { ![eof $fd] } {
|
||||
set line [gets $fd]
|
||||
if {$line == ""} continue
|
||||
|
||||
set fields [split $line ";"]
|
||||
if {[llength $fields] != [llength $lField]} { error "parse error: $line" }
|
||||
foreach $lField $fields {}
|
||||
|
||||
set iCode [expr "0x$code"]
|
||||
set bAlnum [expr {
|
||||
[lsearch {L N} [string range $general_category 0 0]] >= 0
|
||||
|| $general_category=="Co"
|
||||
}]
|
||||
|
||||
if { !$bAlnum } { lappend lRet $iCode }
|
||||
}
|
||||
|
||||
close $fd
|
||||
set lRet
|
||||
}
|
||||
|
||||
proc tl_load_casefolding_txt {zName} {
|
||||
global tl_lookup_table
|
||||
|
||||
set fd [open $zName]
|
||||
while { ![eof $fd] } {
|
||||
set line [gets $fd]
|
||||
if {[string range $line 0 0] == "#"} continue
|
||||
if {$line == ""} continue
|
||||
|
||||
foreach x {a b c d} {unset -nocomplain $x}
|
||||
foreach {a b c d} [split $line ";"] {}
|
||||
|
||||
set a2 [list]
|
||||
set c2 [list]
|
||||
foreach elem $a { lappend a2 [expr "0x[string trim $elem]"] }
|
||||
foreach elem $c { lappend c2 [expr "0x[string trim $elem]"] }
|
||||
set b [string trim $b]
|
||||
set d [string trim $d]
|
||||
|
||||
if {$b=="C" || $b=="S"} { set tl_lookup_table($a2) $c2 }
|
||||
}
|
||||
}
|
||||
|
||||
proc cc_load_unicodedata_text {zName} {
|
||||
set fd [open $zName]
|
||||
set lField {
|
||||
code
|
||||
character_name
|
||||
general_category
|
||||
canonical_combining_classes
|
||||
bidirectional_category
|
||||
character_decomposition_mapping
|
||||
decimal_digit_value
|
||||
digit_value
|
||||
numeric_value
|
||||
mirrored
|
||||
unicode_1_name
|
||||
iso10646_comment_field
|
||||
uppercase_mapping
|
||||
lowercase_mapping
|
||||
titlecase_mapping
|
||||
}
|
||||
set lRet [list]
|
||||
|
||||
while { ![eof $fd] } {
|
||||
set line [gets $fd]
|
||||
if {$line == ""} continue
|
||||
|
||||
set fields [split $line ";"]
|
||||
if {[llength $fields] != [llength $lField]} { error "parse error: $line" }
|
||||
foreach $lField $fields {}
|
||||
|
||||
lappend lRet [list $code $general_category]
|
||||
}
|
||||
|
||||
close $fd
|
||||
set lRet
|
||||
}
|
||||
|
||||
|
||||
@@ -1,252 +0,0 @@
|
||||
#
|
||||
# 2014 August 24
|
||||
#
|
||||
# The author disclaims copyright to this source code. In place of
|
||||
# a legal notice, here is a blessing:
|
||||
#
|
||||
# May you do good and not evil.
|
||||
# May you find forgiveness for yourself and forgive others.
|
||||
# May you share freely, never taking more than you give.
|
||||
#
|
||||
#--------------------------------------------------------------------------
|
||||
#
|
||||
# This script extracts the documentation for the API used by fts5 auxiliary
|
||||
# functions from header file fts5.h. It outputs html text on stdout that
|
||||
# is included in the documentation on the web.
|
||||
#
|
||||
|
||||
set ::fts5_docs_output ""
|
||||
if {[info commands hd_putsnl]==""} {
|
||||
if {[llength $argv]>0} { set ::extract_api_docs_mode [lindex $argv 0] }
|
||||
proc output {text} {
|
||||
puts $text
|
||||
}
|
||||
} else {
|
||||
proc output {text} {
|
||||
append ::fts5_docs_output "$text\n"
|
||||
}
|
||||
}
|
||||
if {[info exists ::extract_api_docs_mode]==0} {set ::extract_api_docs_mode api}
|
||||
|
||||
|
||||
set input_file [file join [file dir [info script]] fts5.h]
|
||||
set fd [open $input_file]
|
||||
set data [read $fd]
|
||||
close $fd
|
||||
|
||||
|
||||
# Argument $data is the entire text of the fts5.h file. This function
|
||||
# extracts the definition of the Fts5ExtensionApi structure from it and
|
||||
# returns a key/value list of structure member names and definitions. i.e.
|
||||
#
|
||||
# iVersion {int iVersion} xUserData {void *(*xUserData)(Fts5Context*)} ...
|
||||
#
|
||||
proc get_struct_members {data} {
|
||||
|
||||
# Extract the structure definition from the fts5.h file.
|
||||
regexp "struct Fts5ExtensionApi {(.*?)};" $data -> defn
|
||||
|
||||
# Remove all comments from the structure definition
|
||||
regsub -all {/[*].*?[*]/} $defn {} defn2
|
||||
|
||||
set res [list]
|
||||
foreach member [split $defn2 {;}] {
|
||||
|
||||
set member [string trim $member]
|
||||
if {$member!=""} {
|
||||
catch { set name [lindex $member end] }
|
||||
regexp {.*?[(][*]([^)]*)[)]} $member -> name
|
||||
lappend res $name $member
|
||||
}
|
||||
}
|
||||
|
||||
set res
|
||||
}
|
||||
|
||||
proc get_struct_docs {data names} {
|
||||
# Extract the structure definition from the fts5.h file.
|
||||
regexp {EXTENSION API FUNCTIONS(.*?)[*]/} $data -> docs
|
||||
|
||||
set current_doc ""
|
||||
set current_header ""
|
||||
|
||||
foreach line [split $docs "\n"] {
|
||||
regsub {[*]*} $line {} line
|
||||
if {[regexp {^ } $line]} {
|
||||
append current_doc "$line\n"
|
||||
} elseif {[string trim $line]==""} {
|
||||
if {$current_header!=""} { append current_doc "\n" }
|
||||
} else {
|
||||
if {$current_doc != ""} {
|
||||
lappend res $current_header $current_doc
|
||||
set current_doc ""
|
||||
}
|
||||
set subject n/a
|
||||
regexp {^ *([[:alpha:]]*)} $line -> subject
|
||||
if {[lsearch $names $subject]>=0} {
|
||||
set current_header $subject
|
||||
} else {
|
||||
set current_header [string trim $line]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if {$current_doc != ""} {
|
||||
lappend res $current_header $current_doc
|
||||
}
|
||||
|
||||
set res
|
||||
}
|
||||
|
||||
proc get_tokenizer_docs {data} {
|
||||
regexp {(xCreate:.*?)[*]/} $data -> docs
|
||||
|
||||
set res "<dl>\n"
|
||||
foreach line [split [string trim $docs] "\n"] {
|
||||
regexp {[*][*](.*)} $line -> line
|
||||
if {[regexp {^ ?x.*:} $line]} {
|
||||
append res "<dt><b>$line</b></dt><dd><p style=margin-top:0>\n"
|
||||
continue
|
||||
}
|
||||
if {[regexp {SYNONYM SUPPORT} $line]} {
|
||||
set line "</dl><h3>Synonym Support</h3>"
|
||||
}
|
||||
if {[string trim $line] == ""} {
|
||||
append res "<p>\n"
|
||||
} else {
|
||||
append res "$line\n"
|
||||
}
|
||||
}
|
||||
|
||||
set res
|
||||
}
|
||||
|
||||
proc get_api_docs {data} {
|
||||
# Initialize global array M as a map from Fts5StructureApi member name
|
||||
# to member definition. i.e.
|
||||
#
|
||||
# iVersion -> {int iVersion}
|
||||
# xUserData -> {void *(*xUserData)(Fts5Context*)}
|
||||
# ...
|
||||
#
|
||||
array set M [get_struct_members $data]
|
||||
|
||||
# Initialize global list D as a map from section name to documentation
|
||||
# text. Most (all?) section names are structure member names.
|
||||
#
|
||||
set D [get_struct_docs $data [array names M]]
|
||||
|
||||
output "<dl>"
|
||||
foreach {sub docs} $D {
|
||||
if {[info exists M($sub)]} {
|
||||
set hdr $M($sub)
|
||||
set link " id=$sub"
|
||||
} else {
|
||||
set link ""
|
||||
}
|
||||
|
||||
#output "<hr color=#eeeee style=\"margin:1em 8.4ex 0 8.4ex;\"$link>"
|
||||
#set style "padding-left:6ex;font-size:1.4em;display:block"
|
||||
#output "<h style=\"$style\"><pre>$hdr</pre></h>"
|
||||
|
||||
regsub -line {^ *[)]} $hdr ")" hdr
|
||||
output "<dt style=\"white-space:pre;font-family:monospace;font-size:120%\""
|
||||
output "$link>"
|
||||
output "<b>$hdr</b></dt><dd>"
|
||||
|
||||
set mode ""
|
||||
set margin " style=margin-top:0.1em"
|
||||
foreach line [split [string trim $docs] "\n"] {
|
||||
if {[string trim $line]==""} {
|
||||
if {$mode != ""} {output "</$mode>"}
|
||||
set mode ""
|
||||
} elseif {$mode == ""} {
|
||||
if {[regexp {^ } $line]} {
|
||||
set mode codeblock
|
||||
} else {
|
||||
set mode p
|
||||
}
|
||||
output "<$mode$margin>"
|
||||
set margin ""
|
||||
}
|
||||
output $line
|
||||
}
|
||||
if {$mode != ""} {output "</$mode>"}
|
||||
output "</dd>"
|
||||
}
|
||||
output "</dl>"
|
||||
}
|
||||
|
||||
proc get_fts5_struct {data start end} {
|
||||
set res ""
|
||||
set bOut 0
|
||||
foreach line [split $data "\n"] {
|
||||
if {$bOut==0} {
|
||||
if {[regexp $start $line]} {
|
||||
set bOut 1
|
||||
}
|
||||
}
|
||||
|
||||
if {$bOut} {
|
||||
append res "$line\n"
|
||||
}
|
||||
|
||||
if {$bOut} {
|
||||
if {[regexp $end $line]} {
|
||||
set bOut 0
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
set map [list /* <i>/* */ */</i>]
|
||||
string map $map $res
|
||||
}
|
||||
|
||||
proc main {data} {
|
||||
switch $::extract_api_docs_mode {
|
||||
fts5_api {
|
||||
output [get_fts5_struct $data "typedef struct fts5_api" "^\};"]
|
||||
}
|
||||
|
||||
fts5_tokenizer {
|
||||
output [get_fts5_struct $data "typedef struct Fts5Tokenizer" "^\};"]
|
||||
output [get_fts5_struct $data \
|
||||
"Flags that may be passed as the third argument to xTokenize()" \
|
||||
"#define FTS5_TOKEN_COLOCATED"
|
||||
]
|
||||
}
|
||||
|
||||
fts5_extension {
|
||||
output [get_fts5_struct $data "typedef.*Fts5ExtensionApi" "^.;"]
|
||||
}
|
||||
|
||||
Fts5ExtensionApi {
|
||||
set struct [get_fts5_struct $data "^struct Fts5ExtensionApi" "^.;"]
|
||||
set map [list]
|
||||
foreach {k v} [get_struct_members $data] {
|
||||
if {[string match x* $k]==0} continue
|
||||
lappend map $k "<a href=#$k>$k</a>"
|
||||
}
|
||||
output [string map $map $struct]
|
||||
}
|
||||
|
||||
api {
|
||||
get_api_docs $data
|
||||
}
|
||||
|
||||
tokenizer_api {
|
||||
output [get_tokenizer_docs $data]
|
||||
}
|
||||
|
||||
default {
|
||||
}
|
||||
}
|
||||
}
|
||||
main $data
|
||||
|
||||
set ::fts5_docs_output
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
-575
@@ -1,575 +0,0 @@
|
||||
/*
|
||||
** 2014 May 31
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
**
|
||||
** Interfaces to extend FTS5. Using the interfaces defined in this file,
|
||||
** FTS5 may be extended with:
|
||||
**
|
||||
** * custom tokenizers, and
|
||||
** * custom auxiliary functions.
|
||||
*/
|
||||
|
||||
|
||||
#ifndef _FTS5_H
|
||||
#define _FTS5_H
|
||||
|
||||
#include "sqlite3.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/*************************************************************************
|
||||
** CUSTOM AUXILIARY FUNCTIONS
|
||||
**
|
||||
** Virtual table implementations may overload SQL functions by implementing
|
||||
** the sqlite3_module.xFindFunction() method.
|
||||
*/
|
||||
|
||||
typedef struct Fts5ExtensionApi Fts5ExtensionApi;
|
||||
typedef struct Fts5Context Fts5Context;
|
||||
typedef struct Fts5PhraseIter Fts5PhraseIter;
|
||||
|
||||
typedef void (*fts5_extension_function)(
|
||||
const Fts5ExtensionApi *pApi, /* API offered by current FTS version */
|
||||
Fts5Context *pFts, /* First arg to pass to pApi functions */
|
||||
sqlite3_context *pCtx, /* Context for returning result/error */
|
||||
int nVal, /* Number of values in apVal[] array */
|
||||
sqlite3_value **apVal /* Array of trailing arguments */
|
||||
);
|
||||
|
||||
struct Fts5PhraseIter {
|
||||
const unsigned char *a;
|
||||
const unsigned char *b;
|
||||
};
|
||||
|
||||
/*
|
||||
** EXTENSION API FUNCTIONS
|
||||
**
|
||||
** xUserData(pFts):
|
||||
** Return a copy of the context pointer the extension function was
|
||||
** registered with.
|
||||
**
|
||||
** xColumnTotalSize(pFts, iCol, pnToken):
|
||||
** If parameter iCol is less than zero, set output variable *pnToken
|
||||
** to the total number of tokens in the FTS5 table. Or, if iCol is
|
||||
** non-negative but less than the number of columns in the table, return
|
||||
** the total number of tokens in column iCol, considering all rows in
|
||||
** the FTS5 table.
|
||||
**
|
||||
** If parameter iCol is greater than or equal to the number of columns
|
||||
** in the table, SQLITE_RANGE is returned. Or, if an error occurs (e.g.
|
||||
** an OOM condition or IO error), an appropriate SQLite error code is
|
||||
** returned.
|
||||
**
|
||||
** xColumnCount(pFts):
|
||||
** Return the number of columns in the table.
|
||||
**
|
||||
** xColumnSize(pFts, iCol, pnToken):
|
||||
** If parameter iCol is less than zero, set output variable *pnToken
|
||||
** to the total number of tokens in the current row. Or, if iCol is
|
||||
** non-negative but less than the number of columns in the table, set
|
||||
** *pnToken to the number of tokens in column iCol of the current row.
|
||||
**
|
||||
** If parameter iCol is greater than or equal to the number of columns
|
||||
** in the table, SQLITE_RANGE is returned. Or, if an error occurs (e.g.
|
||||
** an OOM condition or IO error), an appropriate SQLite error code is
|
||||
** returned.
|
||||
**
|
||||
** This function may be quite inefficient if used with an FTS5 table
|
||||
** created with the "columnsize=0" option.
|
||||
**
|
||||
** xColumnText:
|
||||
** This function attempts to retrieve the text of column iCol of the
|
||||
** current document. If successful, (*pz) is set to point to a buffer
|
||||
** containing the text in utf-8 encoding, (*pn) is set to the size in bytes
|
||||
** (not characters) of the buffer and SQLITE_OK is returned. Otherwise,
|
||||
** if an error occurs, an SQLite error code is returned and the final values
|
||||
** of (*pz) and (*pn) are undefined.
|
||||
**
|
||||
** xPhraseCount:
|
||||
** Returns the number of phrases in the current query expression.
|
||||
**
|
||||
** xPhraseSize:
|
||||
** Returns the number of tokens in phrase iPhrase of the query. Phrases
|
||||
** are numbered starting from zero.
|
||||
**
|
||||
** xInstCount:
|
||||
** Set *pnInst to the total number of occurrences of all phrases within
|
||||
** the query within the current row. Return SQLITE_OK if successful, or
|
||||
** an error code (i.e. SQLITE_NOMEM) if an error occurs.
|
||||
**
|
||||
** This API can be quite slow if used with an FTS5 table created with the
|
||||
** "detail=none" or "detail=column" option. If the FTS5 table is created
|
||||
** with either "detail=none" or "detail=column" and "content=" option
|
||||
** (i.e. if it is a contentless table), then this API always returns 0.
|
||||
**
|
||||
** xInst:
|
||||
** Query for the details of phrase match iIdx within the current row.
|
||||
** Phrase matches are numbered starting from zero, so the iIdx argument
|
||||
** should be greater than or equal to zero and smaller than the value
|
||||
** output by xInstCount().
|
||||
**
|
||||
** Usually, output parameter *piPhrase is set to the phrase number, *piCol
|
||||
** to the column in which it occurs and *piOff the token offset of the
|
||||
** first token of the phrase. Returns SQLITE_OK if successful, or an error
|
||||
** code (i.e. SQLITE_NOMEM) if an error occurs.
|
||||
**
|
||||
** This API can be quite slow if used with an FTS5 table created with the
|
||||
** "detail=none" or "detail=column" option.
|
||||
**
|
||||
** xRowid:
|
||||
** Returns the rowid of the current row.
|
||||
**
|
||||
** xTokenize:
|
||||
** Tokenize text using the tokenizer belonging to the FTS5 table.
|
||||
**
|
||||
** xQueryPhrase(pFts5, iPhrase, pUserData, xCallback):
|
||||
** This API function is used to query the FTS table for phrase iPhrase
|
||||
** of the current query. Specifically, a query equivalent to:
|
||||
**
|
||||
** ... FROM ftstable WHERE ftstable MATCH $p ORDER BY rowid
|
||||
**
|
||||
** with $p set to a phrase equivalent to the phrase iPhrase of the
|
||||
** current query is executed. Any column filter that applies to
|
||||
** phrase iPhrase of the current query is included in $p. For each
|
||||
** row visited, the callback function passed as the fourth argument
|
||||
** is invoked. The context and API objects passed to the callback
|
||||
** function may be used to access the properties of each matched row.
|
||||
** Invoking Api.xUserData() returns a copy of the pointer passed as
|
||||
** the third argument to pUserData.
|
||||
**
|
||||
** If the callback function returns any value other than SQLITE_OK, the
|
||||
** query is abandoned and the xQueryPhrase function returns immediately.
|
||||
** If the returned value is SQLITE_DONE, xQueryPhrase returns SQLITE_OK.
|
||||
** Otherwise, the error code is propagated upwards.
|
||||
**
|
||||
** If the query runs to completion without incident, SQLITE_OK is returned.
|
||||
** Or, if some error occurs before the query completes or is aborted by
|
||||
** the callback, an SQLite error code is returned.
|
||||
**
|
||||
**
|
||||
** xSetAuxdata(pFts5, pAux, xDelete)
|
||||
**
|
||||
** Save the pointer passed as the second argument as the extension functions
|
||||
** "auxiliary data". The pointer may then be retrieved by the current or any
|
||||
** future invocation of the same fts5 extension function made as part of
|
||||
** of the same MATCH query using the xGetAuxdata() API.
|
||||
**
|
||||
** Each extension function is allocated a single auxiliary data slot for
|
||||
** each FTS query (MATCH expression). If the extension function is invoked
|
||||
** more than once for a single FTS query, then all invocations share a
|
||||
** single auxiliary data context.
|
||||
**
|
||||
** If there is already an auxiliary data pointer when this function is
|
||||
** invoked, then it is replaced by the new pointer. If an xDelete callback
|
||||
** was specified along with the original pointer, it is invoked at this
|
||||
** point.
|
||||
**
|
||||
** The xDelete callback, if one is specified, is also invoked on the
|
||||
** auxiliary data pointer after the FTS5 query has finished.
|
||||
**
|
||||
** If an error (e.g. an OOM condition) occurs within this function, an
|
||||
** the auxiliary data is set to NULL and an error code returned. If the
|
||||
** xDelete parameter was not NULL, it is invoked on the auxiliary data
|
||||
** pointer before returning.
|
||||
**
|
||||
**
|
||||
** xGetAuxdata(pFts5, bClear)
|
||||
**
|
||||
** Returns the current auxiliary data pointer for the fts5 extension
|
||||
** function. See the xSetAuxdata() method for details.
|
||||
**
|
||||
** If the bClear argument is non-zero, then the auxiliary data is cleared
|
||||
** (set to NULL) before this function returns. In this case the xDelete,
|
||||
** if any, is not invoked.
|
||||
**
|
||||
**
|
||||
** xRowCount(pFts5, pnRow)
|
||||
**
|
||||
** This function is used to retrieve the total number of rows in the table.
|
||||
** In other words, the same value that would be returned by:
|
||||
**
|
||||
** SELECT count(*) FROM ftstable;
|
||||
**
|
||||
** xPhraseFirst()
|
||||
** This function is used, along with type Fts5PhraseIter and the xPhraseNext
|
||||
** method, to iterate through all instances of a single query phrase within
|
||||
** the current row. This is the same information as is accessible via the
|
||||
** xInstCount/xInst APIs. While the xInstCount/xInst APIs are more convenient
|
||||
** to use, this API may be faster under some circumstances. To iterate
|
||||
** through instances of phrase iPhrase, use the following code:
|
||||
**
|
||||
** Fts5PhraseIter iter;
|
||||
** int iCol, iOff;
|
||||
** for(pApi->xPhraseFirst(pFts, iPhrase, &iter, &iCol, &iOff);
|
||||
** iCol>=0;
|
||||
** pApi->xPhraseNext(pFts, &iter, &iCol, &iOff)
|
||||
** ){
|
||||
** // An instance of phrase iPhrase at offset iOff of column iCol
|
||||
** }
|
||||
**
|
||||
** The Fts5PhraseIter structure is defined above. Applications should not
|
||||
** modify this structure directly - it should only be used as shown above
|
||||
** with the xPhraseFirst() and xPhraseNext() API methods (and by
|
||||
** xPhraseFirstColumn() and xPhraseNextColumn() as illustrated below).
|
||||
**
|
||||
** This API can be quite slow if used with an FTS5 table created with the
|
||||
** "detail=none" or "detail=column" option. If the FTS5 table is created
|
||||
** with either "detail=none" or "detail=column" and "content=" option
|
||||
** (i.e. if it is a contentless table), then this API always iterates
|
||||
** through an empty set (all calls to xPhraseFirst() set iCol to -1).
|
||||
**
|
||||
** xPhraseNext()
|
||||
** See xPhraseFirst above.
|
||||
**
|
||||
** xPhraseFirstColumn()
|
||||
** This function and xPhraseNextColumn() are similar to the xPhraseFirst()
|
||||
** and xPhraseNext() APIs described above. The difference is that instead
|
||||
** of iterating through all instances of a phrase in the current row, these
|
||||
** APIs are used to iterate through the set of columns in the current row
|
||||
** that contain one or more instances of a specified phrase. For example:
|
||||
**
|
||||
** Fts5PhraseIter iter;
|
||||
** int iCol;
|
||||
** for(pApi->xPhraseFirstColumn(pFts, iPhrase, &iter, &iCol);
|
||||
** iCol>=0;
|
||||
** pApi->xPhraseNextColumn(pFts, &iter, &iCol)
|
||||
** ){
|
||||
** // Column iCol contains at least one instance of phrase iPhrase
|
||||
** }
|
||||
**
|
||||
** This API can be quite slow if used with an FTS5 table created with the
|
||||
** "detail=none" option. If the FTS5 table is created with either
|
||||
** "detail=none" "content=" option (i.e. if it is a contentless table),
|
||||
** then this API always iterates through an empty set (all calls to
|
||||
** xPhraseFirstColumn() set iCol to -1).
|
||||
**
|
||||
** The information accessed using this API and its companion
|
||||
** xPhraseFirstColumn() may also be obtained using xPhraseFirst/xPhraseNext
|
||||
** (or xInst/xInstCount). The chief advantage of this API is that it is
|
||||
** significantly more efficient than those alternatives when used with
|
||||
** "detail=column" tables.
|
||||
**
|
||||
** xPhraseNextColumn()
|
||||
** See xPhraseFirstColumn above.
|
||||
*/
|
||||
struct Fts5ExtensionApi {
|
||||
int iVersion; /* Currently always set to 3 */
|
||||
|
||||
void *(*xUserData)(Fts5Context*);
|
||||
|
||||
int (*xColumnCount)(Fts5Context*);
|
||||
int (*xRowCount)(Fts5Context*, sqlite3_int64 *pnRow);
|
||||
int (*xColumnTotalSize)(Fts5Context*, int iCol, sqlite3_int64 *pnToken);
|
||||
|
||||
int (*xTokenize)(Fts5Context*,
|
||||
const char *pText, int nText, /* Text to tokenize */
|
||||
void *pCtx, /* Context passed to xToken() */
|
||||
int (*xToken)(void*, int, const char*, int, int, int) /* Callback */
|
||||
);
|
||||
|
||||
int (*xPhraseCount)(Fts5Context*);
|
||||
int (*xPhraseSize)(Fts5Context*, int iPhrase);
|
||||
|
||||
int (*xInstCount)(Fts5Context*, int *pnInst);
|
||||
int (*xInst)(Fts5Context*, int iIdx, int *piPhrase, int *piCol, int *piOff);
|
||||
|
||||
sqlite3_int64 (*xRowid)(Fts5Context*);
|
||||
int (*xColumnText)(Fts5Context*, int iCol, const char **pz, int *pn);
|
||||
int (*xColumnSize)(Fts5Context*, int iCol, int *pnToken);
|
||||
|
||||
int (*xQueryPhrase)(Fts5Context*, int iPhrase, void *pUserData,
|
||||
int(*)(const Fts5ExtensionApi*,Fts5Context*,void*)
|
||||
);
|
||||
int (*xSetAuxdata)(Fts5Context*, void *pAux, void(*xDelete)(void*));
|
||||
void *(*xGetAuxdata)(Fts5Context*, int bClear);
|
||||
|
||||
int (*xPhraseFirst)(Fts5Context*, int iPhrase, Fts5PhraseIter*, int*, int*);
|
||||
void (*xPhraseNext)(Fts5Context*, Fts5PhraseIter*, int *piCol, int *piOff);
|
||||
|
||||
int (*xPhraseFirstColumn)(Fts5Context*, int iPhrase, Fts5PhraseIter*, int*);
|
||||
void (*xPhraseNextColumn)(Fts5Context*, Fts5PhraseIter*, int *piCol);
|
||||
};
|
||||
|
||||
/*
|
||||
** CUSTOM AUXILIARY FUNCTIONS
|
||||
*************************************************************************/
|
||||
|
||||
/*************************************************************************
|
||||
** CUSTOM TOKENIZERS
|
||||
**
|
||||
** Applications may also register custom tokenizer types. A tokenizer
|
||||
** is registered by providing fts5 with a populated instance of the
|
||||
** following structure. All structure methods must be defined, setting
|
||||
** any member of the fts5_tokenizer struct to NULL leads to undefined
|
||||
** behaviour. The structure methods are expected to function as follows:
|
||||
**
|
||||
** xCreate:
|
||||
** This function is used to allocate and initialize a tokenizer instance.
|
||||
** A tokenizer instance is required to actually tokenize text.
|
||||
**
|
||||
** The first argument passed to this function is a copy of the (void*)
|
||||
** pointer provided by the application when the fts5_tokenizer object
|
||||
** was registered with FTS5 (the third argument to xCreateTokenizer()).
|
||||
** The second and third arguments are an array of nul-terminated strings
|
||||
** containing the tokenizer arguments, if any, specified following the
|
||||
** tokenizer name as part of the CREATE VIRTUAL TABLE statement used
|
||||
** to create the FTS5 table.
|
||||
**
|
||||
** The final argument is an output variable. If successful, (*ppOut)
|
||||
** should be set to point to the new tokenizer handle and SQLITE_OK
|
||||
** returned. If an error occurs, some value other than SQLITE_OK should
|
||||
** be returned. In this case, fts5 assumes that the final value of *ppOut
|
||||
** is undefined.
|
||||
**
|
||||
** xDelete:
|
||||
** This function is invoked to delete a tokenizer handle previously
|
||||
** allocated using xCreate(). Fts5 guarantees that this function will
|
||||
** be invoked exactly once for each successful call to xCreate().
|
||||
**
|
||||
** xTokenize:
|
||||
** This function is expected to tokenize the nText byte string indicated
|
||||
** by argument pText. pText may or may not be nul-terminated. The first
|
||||
** argument passed to this function is a pointer to an Fts5Tokenizer object
|
||||
** returned by an earlier call to xCreate().
|
||||
**
|
||||
** The second argument indicates the reason that FTS5 is requesting
|
||||
** tokenization of the supplied text. This is always one of the following
|
||||
** four values:
|
||||
**
|
||||
** <ul><li> <b>FTS5_TOKENIZE_DOCUMENT</b> - A document is being inserted into
|
||||
** or removed from the FTS table. The tokenizer is being invoked to
|
||||
** determine the set of tokens to add to (or delete from) the
|
||||
** FTS index.
|
||||
**
|
||||
** <li> <b>FTS5_TOKENIZE_QUERY</b> - A MATCH query is being executed
|
||||
** against the FTS index. The tokenizer is being called to tokenize
|
||||
** a bareword or quoted string specified as part of the query.
|
||||
**
|
||||
** <li> <b>(FTS5_TOKENIZE_QUERY | FTS5_TOKENIZE_PREFIX)</b> - Same as
|
||||
** FTS5_TOKENIZE_QUERY, except that the bareword or quoted string is
|
||||
** followed by a "*" character, indicating that the last token
|
||||
** returned by the tokenizer will be treated as a token prefix.
|
||||
**
|
||||
** <li> <b>FTS5_TOKENIZE_AUX</b> - The tokenizer is being invoked to
|
||||
** satisfy an fts5_api.xTokenize() request made by an auxiliary
|
||||
** function. Or an fts5_api.xColumnSize() request made by the same
|
||||
** on a columnsize=0 database.
|
||||
** </ul>
|
||||
**
|
||||
** For each token in the input string, the supplied callback xToken() must
|
||||
** be invoked. The first argument to it should be a copy of the pointer
|
||||
** passed as the second argument to xTokenize(). The third and fourth
|
||||
** arguments are a pointer to a buffer containing the token text, and the
|
||||
** size of the token in bytes. The 4th and 5th arguments are the byte offsets
|
||||
** of the first byte of and first byte immediately following the text from
|
||||
** which the token is derived within the input.
|
||||
**
|
||||
** The second argument passed to the xToken() callback ("tflags") should
|
||||
** normally be set to 0. The exception is if the tokenizer supports
|
||||
** synonyms. In this case see the discussion below for details.
|
||||
**
|
||||
** FTS5 assumes the xToken() callback is invoked for each token in the
|
||||
** order that they occur within the input text.
|
||||
**
|
||||
** If an xToken() callback returns any value other than SQLITE_OK, then
|
||||
** the tokenization should be abandoned and the xTokenize() method should
|
||||
** immediately return a copy of the xToken() return value. Or, if the
|
||||
** input buffer is exhausted, xTokenize() should return SQLITE_OK. Finally,
|
||||
** if an error occurs with the xTokenize() implementation itself, it
|
||||
** may abandon the tokenization and return any error code other than
|
||||
** SQLITE_OK or SQLITE_DONE.
|
||||
**
|
||||
** SYNONYM SUPPORT
|
||||
**
|
||||
** Custom tokenizers may also support synonyms. Consider a case in which a
|
||||
** user wishes to query for a phrase such as "first place". Using the
|
||||
** built-in tokenizers, the FTS5 query 'first + place' will match instances
|
||||
** of "first place" within the document set, but not alternative forms
|
||||
** such as "1st place". In some applications, it would be better to match
|
||||
** all instances of "first place" or "1st place" regardless of which form
|
||||
** the user specified in the MATCH query text.
|
||||
**
|
||||
** There are several ways to approach this in FTS5:
|
||||
**
|
||||
** <ol><li> By mapping all synonyms to a single token. In this case, the
|
||||
** In the above example, this means that the tokenizer returns the
|
||||
** same token for inputs "first" and "1st". Say that token is in
|
||||
** fact "first", so that when the user inserts the document "I won
|
||||
** 1st place" entries are added to the index for tokens "i", "won",
|
||||
** "first" and "place". If the user then queries for '1st + place',
|
||||
** the tokenizer substitutes "first" for "1st" and the query works
|
||||
** as expected.
|
||||
**
|
||||
** <li> By querying the index for all synonyms of each query term
|
||||
** separately. In this case, when tokenizing query text, the
|
||||
** tokenizer may provide multiple synonyms for a single term
|
||||
** within the document. FTS5 then queries the index for each
|
||||
** synonym individually. For example, faced with the query:
|
||||
**
|
||||
** <codeblock>
|
||||
** ... MATCH 'first place'</codeblock>
|
||||
**
|
||||
** the tokenizer offers both "1st" and "first" as synonyms for the
|
||||
** first token in the MATCH query and FTS5 effectively runs a query
|
||||
** similar to:
|
||||
**
|
||||
** <codeblock>
|
||||
** ... MATCH '(first OR 1st) place'</codeblock>
|
||||
**
|
||||
** except that, for the purposes of auxiliary functions, the query
|
||||
** still appears to contain just two phrases - "(first OR 1st)"
|
||||
** being treated as a single phrase.
|
||||
**
|
||||
** <li> By adding multiple synonyms for a single term to the FTS index.
|
||||
** Using this method, when tokenizing document text, the tokenizer
|
||||
** provides multiple synonyms for each token. So that when a
|
||||
** document such as "I won first place" is tokenized, entries are
|
||||
** added to the FTS index for "i", "won", "first", "1st" and
|
||||
** "place".
|
||||
**
|
||||
** This way, even if the tokenizer does not provide synonyms
|
||||
** when tokenizing query text (it should not - to do so would be
|
||||
** inefficient), it doesn't matter if the user queries for
|
||||
** 'first + place' or '1st + place', as there are entries in the
|
||||
** FTS index corresponding to both forms of the first token.
|
||||
** </ol>
|
||||
**
|
||||
** Whether it is parsing document or query text, any call to xToken that
|
||||
** specifies a <i>tflags</i> argument with the FTS5_TOKEN_COLOCATED bit
|
||||
** is considered to supply a synonym for the previous token. For example,
|
||||
** when parsing the document "I won first place", a tokenizer that supports
|
||||
** synonyms would call xToken() 5 times, as follows:
|
||||
**
|
||||
** <codeblock>
|
||||
** xToken(pCtx, 0, "i", 1, 0, 1);
|
||||
** xToken(pCtx, 0, "won", 3, 2, 5);
|
||||
** xToken(pCtx, 0, "first", 5, 6, 11);
|
||||
** xToken(pCtx, FTS5_TOKEN_COLOCATED, "1st", 3, 6, 11);
|
||||
** xToken(pCtx, 0, "place", 5, 12, 17);
|
||||
**</codeblock>
|
||||
**
|
||||
** It is an error to specify the FTS5_TOKEN_COLOCATED flag the first time
|
||||
** xToken() is called. Multiple synonyms may be specified for a single token
|
||||
** by making multiple calls to xToken(FTS5_TOKEN_COLOCATED) in sequence.
|
||||
** There is no limit to the number of synonyms that may be provided for a
|
||||
** single token.
|
||||
**
|
||||
** In many cases, method (1) above is the best approach. It does not add
|
||||
** extra data to the FTS index or require FTS5 to query for multiple terms,
|
||||
** so it is efficient in terms of disk space and query speed. However, it
|
||||
** does not support prefix queries very well. If, as suggested above, the
|
||||
** token "first" is substituted for "1st" by the tokenizer, then the query:
|
||||
**
|
||||
** <codeblock>
|
||||
** ... MATCH '1s*'</codeblock>
|
||||
**
|
||||
** will not match documents that contain the token "1st" (as the tokenizer
|
||||
** will probably not map "1s" to any prefix of "first").
|
||||
**
|
||||
** For full prefix support, method (3) may be preferred. In this case,
|
||||
** because the index contains entries for both "first" and "1st", prefix
|
||||
** queries such as 'fi*' or '1s*' will match correctly. However, because
|
||||
** extra entries are added to the FTS index, this method uses more space
|
||||
** within the database.
|
||||
**
|
||||
** Method (2) offers a midpoint between (1) and (3). Using this method,
|
||||
** a query such as '1s*' will match documents that contain the literal
|
||||
** token "1st", but not "first" (assuming the tokenizer is not able to
|
||||
** provide synonyms for prefixes). However, a non-prefix query like '1st'
|
||||
** will match against "1st" and "first". This method does not require
|
||||
** extra disk space, as no extra entries are added to the FTS index.
|
||||
** On the other hand, it may require more CPU cycles to run MATCH queries,
|
||||
** as separate queries of the FTS index are required for each synonym.
|
||||
**
|
||||
** When using methods (2) or (3), it is important that the tokenizer only
|
||||
** provide synonyms when tokenizing document text (method (2)) or query
|
||||
** text (method (3)), not both. Doing so will not cause any errors, but is
|
||||
** inefficient.
|
||||
*/
|
||||
typedef struct Fts5Tokenizer Fts5Tokenizer;
|
||||
typedef struct fts5_tokenizer fts5_tokenizer;
|
||||
struct fts5_tokenizer {
|
||||
int (*xCreate)(void*, const char **azArg, int nArg, Fts5Tokenizer **ppOut);
|
||||
void (*xDelete)(Fts5Tokenizer*);
|
||||
int (*xTokenize)(Fts5Tokenizer*,
|
||||
void *pCtx,
|
||||
int flags, /* Mask of FTS5_TOKENIZE_* flags */
|
||||
const char *pText, int nText,
|
||||
int (*xToken)(
|
||||
void *pCtx, /* Copy of 2nd argument to xTokenize() */
|
||||
int tflags, /* Mask of FTS5_TOKEN_* flags */
|
||||
const char *pToken, /* Pointer to buffer containing token */
|
||||
int nToken, /* Size of token in bytes */
|
||||
int iStart, /* Byte offset of token within input text */
|
||||
int iEnd /* Byte offset of end of token within input text */
|
||||
)
|
||||
);
|
||||
};
|
||||
|
||||
/* Flags that may be passed as the third argument to xTokenize() */
|
||||
#define FTS5_TOKENIZE_QUERY 0x0001
|
||||
#define FTS5_TOKENIZE_PREFIX 0x0002
|
||||
#define FTS5_TOKENIZE_DOCUMENT 0x0004
|
||||
#define FTS5_TOKENIZE_AUX 0x0008
|
||||
|
||||
/* Flags that may be passed by the tokenizer implementation back to FTS5
|
||||
** as the third argument to the supplied xToken callback. */
|
||||
#define FTS5_TOKEN_COLOCATED 0x0001 /* Same position as prev. token */
|
||||
|
||||
/*
|
||||
** END OF CUSTOM TOKENIZERS
|
||||
*************************************************************************/
|
||||
|
||||
/*************************************************************************
|
||||
** FTS5 EXTENSION REGISTRATION API
|
||||
*/
|
||||
typedef struct fts5_api fts5_api;
|
||||
struct fts5_api {
|
||||
int iVersion; /* Currently always set to 2 */
|
||||
|
||||
/* Create a new tokenizer */
|
||||
int (*xCreateTokenizer)(
|
||||
fts5_api *pApi,
|
||||
const char *zName,
|
||||
void *pContext,
|
||||
fts5_tokenizer *pTokenizer,
|
||||
void (*xDestroy)(void*)
|
||||
);
|
||||
|
||||
/* Find an existing tokenizer */
|
||||
int (*xFindTokenizer)(
|
||||
fts5_api *pApi,
|
||||
const char *zName,
|
||||
void **ppContext,
|
||||
fts5_tokenizer *pTokenizer
|
||||
);
|
||||
|
||||
/* Create a new auxiliary function */
|
||||
int (*xCreateFunction)(
|
||||
fts5_api *pApi,
|
||||
const char *zName,
|
||||
void *pContext,
|
||||
fts5_extension_function xFunction,
|
||||
void (*xDestroy)(void*)
|
||||
);
|
||||
};
|
||||
|
||||
/*
|
||||
** END OF REGISTRATION API
|
||||
*************************************************************************/
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* end of the 'extern "C"' block */
|
||||
#endif
|
||||
|
||||
#endif /* _FTS5_H */
|
||||
@@ -1,815 +0,0 @@
|
||||
/*
|
||||
** 2014 May 31
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
**
|
||||
*/
|
||||
#ifndef _FTS5INT_H
|
||||
#define _FTS5INT_H
|
||||
|
||||
#include "fts5.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT1
|
||||
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
|
||||
#ifndef SQLITE_AMALGAMATION
|
||||
|
||||
typedef unsigned char u8;
|
||||
typedef unsigned int u32;
|
||||
typedef unsigned short u16;
|
||||
typedef short i16;
|
||||
typedef sqlite3_int64 i64;
|
||||
typedef sqlite3_uint64 u64;
|
||||
|
||||
#ifndef ArraySize
|
||||
# define ArraySize(x) ((int)(sizeof(x) / sizeof(x[0])))
|
||||
#endif
|
||||
|
||||
#define testcase(x)
|
||||
#define ALWAYS(x) 1
|
||||
#define NEVER(x) 0
|
||||
|
||||
#define MIN(x,y) (((x) < (y)) ? (x) : (y))
|
||||
#define MAX(x,y) (((x) > (y)) ? (x) : (y))
|
||||
|
||||
/*
|
||||
** Constants for the largest and smallest possible 64-bit signed integers.
|
||||
*/
|
||||
# define LARGEST_INT64 (0xffffffff|(((i64)0x7fffffff)<<32))
|
||||
# define SMALLEST_INT64 (((i64)-1) - LARGEST_INT64)
|
||||
|
||||
#endif
|
||||
|
||||
/* Truncate very long tokens to this many bytes. Hard limit is
|
||||
** (65536-1-1-4-9)==65521 bytes. The limiting factor is the 16-bit offset
|
||||
** field that occurs at the start of each leaf page (see fts5_index.c). */
|
||||
#define FTS5_MAX_TOKEN_SIZE 32768
|
||||
|
||||
/*
|
||||
** Maximum number of prefix indexes on single FTS5 table. This must be
|
||||
** less than 32. If it is set to anything large than that, an #error
|
||||
** directive in fts5_index.c will cause the build to fail.
|
||||
*/
|
||||
#define FTS5_MAX_PREFIX_INDEXES 31
|
||||
|
||||
#define FTS5_DEFAULT_NEARDIST 10
|
||||
#define FTS5_DEFAULT_RANK "bm25"
|
||||
|
||||
/* Name of rank and rowid columns */
|
||||
#define FTS5_RANK_NAME "rank"
|
||||
#define FTS5_ROWID_NAME "rowid"
|
||||
|
||||
#ifdef SQLITE_DEBUG
|
||||
# define FTS5_CORRUPT sqlite3Fts5Corrupt()
|
||||
int sqlite3Fts5Corrupt(void);
|
||||
#else
|
||||
# define FTS5_CORRUPT SQLITE_CORRUPT_VTAB
|
||||
#endif
|
||||
|
||||
/*
|
||||
** The assert_nc() macro is similar to the assert() macro, except that it
|
||||
** is used for assert() conditions that are true only if it can be
|
||||
** guranteed that the database is not corrupt.
|
||||
*/
|
||||
#ifdef SQLITE_DEBUG
|
||||
extern int sqlite3_fts5_may_be_corrupt;
|
||||
# define assert_nc(x) assert(sqlite3_fts5_may_be_corrupt || (x))
|
||||
#else
|
||||
# define assert_nc(x) assert(x)
|
||||
#endif
|
||||
|
||||
/*
|
||||
** A version of memcmp() that does not cause asan errors if one of the pointer
|
||||
** parameters is NULL and the number of bytes to compare is zero.
|
||||
*/
|
||||
#define fts5Memcmp(s1, s2, n) ((n)==0 ? 0 : memcmp((s1), (s2), (n)))
|
||||
|
||||
/* Mark a function parameter as unused, to suppress nuisance compiler
|
||||
** warnings. */
|
||||
#ifndef UNUSED_PARAM
|
||||
# define UNUSED_PARAM(X) (void)(X)
|
||||
#endif
|
||||
|
||||
#ifndef UNUSED_PARAM2
|
||||
# define UNUSED_PARAM2(X, Y) (void)(X), (void)(Y)
|
||||
#endif
|
||||
|
||||
typedef struct Fts5Global Fts5Global;
|
||||
typedef struct Fts5Colset Fts5Colset;
|
||||
|
||||
/* If a NEAR() clump or phrase may only match a specific set of columns,
|
||||
** then an object of the following type is used to record the set of columns.
|
||||
** Each entry in the aiCol[] array is a column that may be matched.
|
||||
**
|
||||
** This object is used by fts5_expr.c and fts5_index.c.
|
||||
*/
|
||||
struct Fts5Colset {
|
||||
int nCol;
|
||||
int aiCol[1];
|
||||
};
|
||||
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_config.c. fts5_config.c contains contains code
|
||||
** to parse the arguments passed to the CREATE VIRTUAL TABLE statement.
|
||||
*/
|
||||
|
||||
typedef struct Fts5Config Fts5Config;
|
||||
|
||||
/*
|
||||
** An instance of the following structure encodes all information that can
|
||||
** be gleaned from the CREATE VIRTUAL TABLE statement.
|
||||
**
|
||||
** And all information loaded from the %_config table.
|
||||
**
|
||||
** nAutomerge:
|
||||
** The minimum number of segments that an auto-merge operation should
|
||||
** attempt to merge together. A value of 1 sets the object to use the
|
||||
** compile time default. Zero disables auto-merge altogether.
|
||||
**
|
||||
** zContent:
|
||||
**
|
||||
** zContentRowid:
|
||||
** The value of the content_rowid= option, if one was specified. Or
|
||||
** the string "rowid" otherwise. This text is not quoted - if it is
|
||||
** used as part of an SQL statement it needs to be quoted appropriately.
|
||||
**
|
||||
** zContentExprlist:
|
||||
**
|
||||
** pzErrmsg:
|
||||
** This exists in order to allow the fts5_index.c module to return a
|
||||
** decent error message if it encounters a file-format version it does
|
||||
** not understand.
|
||||
**
|
||||
** bColumnsize:
|
||||
** True if the %_docsize table is created.
|
||||
**
|
||||
** bPrefixIndex:
|
||||
** This is only used for debugging. If set to false, any prefix indexes
|
||||
** are ignored. This value is configured using:
|
||||
**
|
||||
** INSERT INTO tbl(tbl, rank) VALUES('prefix-index', $bPrefixIndex);
|
||||
**
|
||||
*/
|
||||
struct Fts5Config {
|
||||
sqlite3 *db; /* Database handle */
|
||||
char *zDb; /* Database holding FTS index (e.g. "main") */
|
||||
char *zName; /* Name of FTS index */
|
||||
int nCol; /* Number of columns */
|
||||
char **azCol; /* Column names */
|
||||
u8 *abUnindexed; /* True for unindexed columns */
|
||||
int nPrefix; /* Number of prefix indexes */
|
||||
int *aPrefix; /* Sizes in bytes of nPrefix prefix indexes */
|
||||
int eContent; /* An FTS5_CONTENT value */
|
||||
char *zContent; /* content table */
|
||||
char *zContentRowid; /* "content_rowid=" option value */
|
||||
int bColumnsize; /* "columnsize=" option value (dflt==1) */
|
||||
int eDetail; /* FTS5_DETAIL_XXX value */
|
||||
char *zContentExprlist;
|
||||
Fts5Tokenizer *pTok;
|
||||
fts5_tokenizer *pTokApi;
|
||||
|
||||
/* Values loaded from the %_config table */
|
||||
int iCookie; /* Incremented when %_config is modified */
|
||||
int pgsz; /* Approximate page size used in %_data */
|
||||
int nAutomerge; /* 'automerge' setting */
|
||||
int nCrisisMerge; /* Maximum allowed segments per level */
|
||||
int nUsermerge; /* 'usermerge' setting */
|
||||
int nHashSize; /* Bytes of memory for in-memory hash */
|
||||
char *zRank; /* Name of rank function */
|
||||
char *zRankArgs; /* Arguments to rank function */
|
||||
|
||||
/* If non-NULL, points to sqlite3_vtab.base.zErrmsg. Often NULL. */
|
||||
char **pzErrmsg;
|
||||
|
||||
#ifdef SQLITE_DEBUG
|
||||
int bPrefixIndex; /* True to use prefix-indexes */
|
||||
#endif
|
||||
};
|
||||
|
||||
/* Current expected value of %_config table 'version' field */
|
||||
#define FTS5_CURRENT_VERSION 4
|
||||
|
||||
#define FTS5_CONTENT_NORMAL 0
|
||||
#define FTS5_CONTENT_NONE 1
|
||||
#define FTS5_CONTENT_EXTERNAL 2
|
||||
|
||||
#define FTS5_DETAIL_FULL 0
|
||||
#define FTS5_DETAIL_NONE 1
|
||||
#define FTS5_DETAIL_COLUMNS 2
|
||||
|
||||
|
||||
|
||||
int sqlite3Fts5ConfigParse(
|
||||
Fts5Global*, sqlite3*, int, const char **, Fts5Config**, char**
|
||||
);
|
||||
void sqlite3Fts5ConfigFree(Fts5Config*);
|
||||
|
||||
int sqlite3Fts5ConfigDeclareVtab(Fts5Config *pConfig);
|
||||
|
||||
int sqlite3Fts5Tokenize(
|
||||
Fts5Config *pConfig, /* FTS5 Configuration object */
|
||||
int flags, /* FTS5_TOKENIZE_* flags */
|
||||
const char *pText, int nText, /* Text to tokenize */
|
||||
void *pCtx, /* Context passed to xToken() */
|
||||
int (*xToken)(void*, int, const char*, int, int, int) /* Callback */
|
||||
);
|
||||
|
||||
void sqlite3Fts5Dequote(char *z);
|
||||
|
||||
/* Load the contents of the %_config table */
|
||||
int sqlite3Fts5ConfigLoad(Fts5Config*, int);
|
||||
|
||||
/* Set the value of a single config attribute */
|
||||
int sqlite3Fts5ConfigSetValue(Fts5Config*, const char*, sqlite3_value*, int*);
|
||||
|
||||
int sqlite3Fts5ConfigParseRank(const char*, char**, char**);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_config.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_buffer.c.
|
||||
*/
|
||||
|
||||
/*
|
||||
** Buffer object for the incremental building of string data.
|
||||
*/
|
||||
typedef struct Fts5Buffer Fts5Buffer;
|
||||
struct Fts5Buffer {
|
||||
u8 *p;
|
||||
int n;
|
||||
int nSpace;
|
||||
};
|
||||
|
||||
int sqlite3Fts5BufferSize(int*, Fts5Buffer*, u32);
|
||||
void sqlite3Fts5BufferAppendVarint(int*, Fts5Buffer*, i64);
|
||||
void sqlite3Fts5BufferAppendBlob(int*, Fts5Buffer*, u32, const u8*);
|
||||
void sqlite3Fts5BufferAppendString(int *, Fts5Buffer*, const char*);
|
||||
void sqlite3Fts5BufferFree(Fts5Buffer*);
|
||||
void sqlite3Fts5BufferZero(Fts5Buffer*);
|
||||
void sqlite3Fts5BufferSet(int*, Fts5Buffer*, int, const u8*);
|
||||
void sqlite3Fts5BufferAppendPrintf(int *, Fts5Buffer*, char *zFmt, ...);
|
||||
|
||||
char *sqlite3Fts5Mprintf(int *pRc, const char *zFmt, ...);
|
||||
|
||||
#define fts5BufferZero(x) sqlite3Fts5BufferZero(x)
|
||||
#define fts5BufferAppendVarint(a,b,c) sqlite3Fts5BufferAppendVarint(a,b,c)
|
||||
#define fts5BufferFree(a) sqlite3Fts5BufferFree(a)
|
||||
#define fts5BufferAppendBlob(a,b,c,d) sqlite3Fts5BufferAppendBlob(a,b,c,d)
|
||||
#define fts5BufferSet(a,b,c,d) sqlite3Fts5BufferSet(a,b,c,d)
|
||||
|
||||
#define fts5BufferGrow(pRc,pBuf,nn) ( \
|
||||
(u32)((pBuf)->n) + (u32)(nn) <= (u32)((pBuf)->nSpace) ? 0 : \
|
||||
sqlite3Fts5BufferSize((pRc),(pBuf),(nn)+(pBuf)->n) \
|
||||
)
|
||||
|
||||
/* Write and decode big-endian 32-bit integer values */
|
||||
void sqlite3Fts5Put32(u8*, int);
|
||||
int sqlite3Fts5Get32(const u8*);
|
||||
|
||||
#define FTS5_POS2COLUMN(iPos) (int)(iPos >> 32)
|
||||
#define FTS5_POS2OFFSET(iPos) (int)(iPos & 0x7FFFFFFF)
|
||||
|
||||
typedef struct Fts5PoslistReader Fts5PoslistReader;
|
||||
struct Fts5PoslistReader {
|
||||
/* Variables used only by sqlite3Fts5PoslistIterXXX() functions. */
|
||||
const u8 *a; /* Position list to iterate through */
|
||||
int n; /* Size of buffer at a[] in bytes */
|
||||
int i; /* Current offset in a[] */
|
||||
|
||||
u8 bFlag; /* For client use (any custom purpose) */
|
||||
|
||||
/* Output variables */
|
||||
u8 bEof; /* Set to true at EOF */
|
||||
i64 iPos; /* (iCol<<32) + iPos */
|
||||
};
|
||||
int sqlite3Fts5PoslistReaderInit(
|
||||
const u8 *a, int n, /* Poslist buffer to iterate through */
|
||||
Fts5PoslistReader *pIter /* Iterator object to initialize */
|
||||
);
|
||||
int sqlite3Fts5PoslistReaderNext(Fts5PoslistReader*);
|
||||
|
||||
typedef struct Fts5PoslistWriter Fts5PoslistWriter;
|
||||
struct Fts5PoslistWriter {
|
||||
i64 iPrev;
|
||||
};
|
||||
int sqlite3Fts5PoslistWriterAppend(Fts5Buffer*, Fts5PoslistWriter*, i64);
|
||||
void sqlite3Fts5PoslistSafeAppend(Fts5Buffer*, i64*, i64);
|
||||
|
||||
int sqlite3Fts5PoslistNext64(
|
||||
const u8 *a, int n, /* Buffer containing poslist */
|
||||
int *pi, /* IN/OUT: Offset within a[] */
|
||||
i64 *piOff /* IN/OUT: Current offset */
|
||||
);
|
||||
|
||||
/* Malloc utility */
|
||||
void *sqlite3Fts5MallocZero(int *pRc, sqlite3_int64 nByte);
|
||||
char *sqlite3Fts5Strndup(int *pRc, const char *pIn, int nIn);
|
||||
|
||||
/* Character set tests (like isspace(), isalpha() etc.) */
|
||||
int sqlite3Fts5IsBareword(char t);
|
||||
|
||||
|
||||
/* Bucket of terms object used by the integrity-check in offsets=0 mode. */
|
||||
typedef struct Fts5Termset Fts5Termset;
|
||||
int sqlite3Fts5TermsetNew(Fts5Termset**);
|
||||
int sqlite3Fts5TermsetAdd(Fts5Termset*, int, const char*, int, int *pbPresent);
|
||||
void sqlite3Fts5TermsetFree(Fts5Termset*);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_buffer.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_index.c. fts5_index.c contains contains code
|
||||
** to access the data stored in the %_data table.
|
||||
*/
|
||||
|
||||
typedef struct Fts5Index Fts5Index;
|
||||
typedef struct Fts5IndexIter Fts5IndexIter;
|
||||
|
||||
struct Fts5IndexIter {
|
||||
i64 iRowid;
|
||||
const u8 *pData;
|
||||
int nData;
|
||||
u8 bEof;
|
||||
};
|
||||
|
||||
#define sqlite3Fts5IterEof(x) ((x)->bEof)
|
||||
|
||||
/*
|
||||
** Values used as part of the flags argument passed to IndexQuery().
|
||||
*/
|
||||
#define FTS5INDEX_QUERY_PREFIX 0x0001 /* Prefix query */
|
||||
#define FTS5INDEX_QUERY_DESC 0x0002 /* Docs in descending rowid order */
|
||||
#define FTS5INDEX_QUERY_TEST_NOIDX 0x0004 /* Do not use prefix index */
|
||||
#define FTS5INDEX_QUERY_SCAN 0x0008 /* Scan query (fts5vocab) */
|
||||
|
||||
/* The following are used internally by the fts5_index.c module. They are
|
||||
** defined here only to make it easier to avoid clashes with the flags
|
||||
** above. */
|
||||
#define FTS5INDEX_QUERY_SKIPEMPTY 0x0010
|
||||
#define FTS5INDEX_QUERY_NOOUTPUT 0x0020
|
||||
|
||||
/*
|
||||
** Create/destroy an Fts5Index object.
|
||||
*/
|
||||
int sqlite3Fts5IndexOpen(Fts5Config *pConfig, int bCreate, Fts5Index**, char**);
|
||||
int sqlite3Fts5IndexClose(Fts5Index *p);
|
||||
|
||||
/*
|
||||
** Return a simple checksum value based on the arguments.
|
||||
*/
|
||||
u64 sqlite3Fts5IndexEntryCksum(
|
||||
i64 iRowid,
|
||||
int iCol,
|
||||
int iPos,
|
||||
int iIdx,
|
||||
const char *pTerm,
|
||||
int nTerm
|
||||
);
|
||||
|
||||
/*
|
||||
** Argument p points to a buffer containing utf-8 text that is n bytes in
|
||||
** size. Return the number of bytes in the nChar character prefix of the
|
||||
** buffer, or 0 if there are less than nChar characters in total.
|
||||
*/
|
||||
int sqlite3Fts5IndexCharlenToBytelen(
|
||||
const char *p,
|
||||
int nByte,
|
||||
int nChar
|
||||
);
|
||||
|
||||
/*
|
||||
** Open a new iterator to iterate though all rowids that match the
|
||||
** specified token or token prefix.
|
||||
*/
|
||||
int sqlite3Fts5IndexQuery(
|
||||
Fts5Index *p, /* FTS index to query */
|
||||
const char *pToken, int nToken, /* Token (or prefix) to query for */
|
||||
int flags, /* Mask of FTS5INDEX_QUERY_X flags */
|
||||
Fts5Colset *pColset, /* Match these columns only */
|
||||
Fts5IndexIter **ppIter /* OUT: New iterator object */
|
||||
);
|
||||
|
||||
/*
|
||||
** The various operations on open token or token prefix iterators opened
|
||||
** using sqlite3Fts5IndexQuery().
|
||||
*/
|
||||
int sqlite3Fts5IterNext(Fts5IndexIter*);
|
||||
int sqlite3Fts5IterNextFrom(Fts5IndexIter*, i64 iMatch);
|
||||
|
||||
/*
|
||||
** Close an iterator opened by sqlite3Fts5IndexQuery().
|
||||
*/
|
||||
void sqlite3Fts5IterClose(Fts5IndexIter*);
|
||||
|
||||
/*
|
||||
** This interface is used by the fts5vocab module.
|
||||
*/
|
||||
const char *sqlite3Fts5IterTerm(Fts5IndexIter*, int*);
|
||||
int sqlite3Fts5IterNextScan(Fts5IndexIter*);
|
||||
|
||||
|
||||
/*
|
||||
** Insert or remove data to or from the index. Each time a document is
|
||||
** added to or removed from the index, this function is called one or more
|
||||
** times.
|
||||
**
|
||||
** For an insert, it must be called once for each token in the new document.
|
||||
** If the operation is a delete, it must be called (at least) once for each
|
||||
** unique token in the document with an iCol value less than zero. The iPos
|
||||
** argument is ignored for a delete.
|
||||
*/
|
||||
int sqlite3Fts5IndexWrite(
|
||||
Fts5Index *p, /* Index to write to */
|
||||
int iCol, /* Column token appears in (-ve -> delete) */
|
||||
int iPos, /* Position of token within column */
|
||||
const char *pToken, int nToken /* Token to add or remove to or from index */
|
||||
);
|
||||
|
||||
/*
|
||||
** Indicate that subsequent calls to sqlite3Fts5IndexWrite() pertain to
|
||||
** document iDocid.
|
||||
*/
|
||||
int sqlite3Fts5IndexBeginWrite(
|
||||
Fts5Index *p, /* Index to write to */
|
||||
int bDelete, /* True if current operation is a delete */
|
||||
i64 iDocid /* Docid to add or remove data from */
|
||||
);
|
||||
|
||||
/*
|
||||
** Flush any data stored in the in-memory hash tables to the database.
|
||||
** Also close any open blob handles.
|
||||
*/
|
||||
int sqlite3Fts5IndexSync(Fts5Index *p);
|
||||
|
||||
/*
|
||||
** Discard any data stored in the in-memory hash tables. Do not write it
|
||||
** to the database. Additionally, assume that the contents of the %_data
|
||||
** table may have changed on disk. So any in-memory caches of %_data
|
||||
** records must be invalidated.
|
||||
*/
|
||||
int sqlite3Fts5IndexRollback(Fts5Index *p);
|
||||
|
||||
/*
|
||||
** Get or set the "averages" values.
|
||||
*/
|
||||
int sqlite3Fts5IndexGetAverages(Fts5Index *p, i64 *pnRow, i64 *anSize);
|
||||
int sqlite3Fts5IndexSetAverages(Fts5Index *p, const u8*, int);
|
||||
|
||||
/*
|
||||
** Functions called by the storage module as part of integrity-check.
|
||||
*/
|
||||
int sqlite3Fts5IndexIntegrityCheck(Fts5Index*, u64 cksum);
|
||||
|
||||
/*
|
||||
** Called during virtual module initialization to register UDF
|
||||
** fts5_decode() with SQLite
|
||||
*/
|
||||
int sqlite3Fts5IndexInit(sqlite3*);
|
||||
|
||||
int sqlite3Fts5IndexSetCookie(Fts5Index*, int);
|
||||
|
||||
/*
|
||||
** Return the total number of entries read from the %_data table by
|
||||
** this connection since it was created.
|
||||
*/
|
||||
int sqlite3Fts5IndexReads(Fts5Index *p);
|
||||
|
||||
int sqlite3Fts5IndexReinit(Fts5Index *p);
|
||||
int sqlite3Fts5IndexOptimize(Fts5Index *p);
|
||||
int sqlite3Fts5IndexMerge(Fts5Index *p, int nMerge);
|
||||
int sqlite3Fts5IndexReset(Fts5Index *p);
|
||||
|
||||
int sqlite3Fts5IndexLoadConfig(Fts5Index *p);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_index.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_varint.c.
|
||||
*/
|
||||
int sqlite3Fts5GetVarint32(const unsigned char *p, u32 *v);
|
||||
int sqlite3Fts5GetVarintLen(u32 iVal);
|
||||
u8 sqlite3Fts5GetVarint(const unsigned char*, u64*);
|
||||
int sqlite3Fts5PutVarint(unsigned char *p, u64 v);
|
||||
|
||||
#define fts5GetVarint32(a,b) sqlite3Fts5GetVarint32(a,(u32*)&b)
|
||||
#define fts5GetVarint sqlite3Fts5GetVarint
|
||||
|
||||
#define fts5FastGetVarint32(a, iOff, nVal) { \
|
||||
nVal = (a)[iOff++]; \
|
||||
if( nVal & 0x80 ){ \
|
||||
iOff--; \
|
||||
iOff += fts5GetVarint32(&(a)[iOff], nVal); \
|
||||
} \
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_varint.c.
|
||||
**************************************************************************/
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_main.c.
|
||||
*/
|
||||
|
||||
/*
|
||||
** Virtual-table object.
|
||||
*/
|
||||
typedef struct Fts5Table Fts5Table;
|
||||
struct Fts5Table {
|
||||
sqlite3_vtab base; /* Base class used by SQLite core */
|
||||
Fts5Config *pConfig; /* Virtual table configuration */
|
||||
Fts5Index *pIndex; /* Full-text index */
|
||||
};
|
||||
|
||||
int sqlite3Fts5GetTokenizer(
|
||||
Fts5Global*,
|
||||
const char **azArg,
|
||||
int nArg,
|
||||
Fts5Tokenizer**,
|
||||
fts5_tokenizer**,
|
||||
char **pzErr
|
||||
);
|
||||
|
||||
Fts5Table *sqlite3Fts5TableFromCsrid(Fts5Global*, i64);
|
||||
|
||||
int sqlite3Fts5FlushToDisk(Fts5Table*);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_hash.c.
|
||||
*/
|
||||
typedef struct Fts5Hash Fts5Hash;
|
||||
|
||||
/*
|
||||
** Create a hash table, free a hash table.
|
||||
*/
|
||||
int sqlite3Fts5HashNew(Fts5Config*, Fts5Hash**, int *pnSize);
|
||||
void sqlite3Fts5HashFree(Fts5Hash*);
|
||||
|
||||
int sqlite3Fts5HashWrite(
|
||||
Fts5Hash*,
|
||||
i64 iRowid, /* Rowid for this entry */
|
||||
int iCol, /* Column token appears in (-ve -> delete) */
|
||||
int iPos, /* Position of token within column */
|
||||
char bByte,
|
||||
const char *pToken, int nToken /* Token to add or remove to or from index */
|
||||
);
|
||||
|
||||
/*
|
||||
** Empty (but do not delete) a hash table.
|
||||
*/
|
||||
void sqlite3Fts5HashClear(Fts5Hash*);
|
||||
|
||||
int sqlite3Fts5HashQuery(
|
||||
Fts5Hash*, /* Hash table to query */
|
||||
const char *pTerm, int nTerm, /* Query term */
|
||||
const u8 **ppDoclist, /* OUT: Pointer to doclist for pTerm */
|
||||
int *pnDoclist /* OUT: Size of doclist in bytes */
|
||||
);
|
||||
|
||||
int sqlite3Fts5HashScanInit(
|
||||
Fts5Hash*, /* Hash table to query */
|
||||
const char *pTerm, int nTerm /* Query prefix */
|
||||
);
|
||||
void sqlite3Fts5HashScanNext(Fts5Hash*);
|
||||
int sqlite3Fts5HashScanEof(Fts5Hash*);
|
||||
void sqlite3Fts5HashScanEntry(Fts5Hash *,
|
||||
const char **pzTerm, /* OUT: term (nul-terminated) */
|
||||
const u8 **ppDoclist, /* OUT: pointer to doclist */
|
||||
int *pnDoclist /* OUT: size of doclist in bytes */
|
||||
);
|
||||
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_hash.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_storage.c. fts5_storage.c contains contains
|
||||
** code to access the data stored in the %_content and %_docsize tables.
|
||||
*/
|
||||
|
||||
#define FTS5_STMT_SCAN_ASC 0 /* SELECT rowid, * FROM ... ORDER BY 1 ASC */
|
||||
#define FTS5_STMT_SCAN_DESC 1 /* SELECT rowid, * FROM ... ORDER BY 1 DESC */
|
||||
#define FTS5_STMT_LOOKUP 2 /* SELECT rowid, * FROM ... WHERE rowid=? */
|
||||
|
||||
typedef struct Fts5Storage Fts5Storage;
|
||||
|
||||
int sqlite3Fts5StorageOpen(Fts5Config*, Fts5Index*, int, Fts5Storage**, char**);
|
||||
int sqlite3Fts5StorageClose(Fts5Storage *p);
|
||||
int sqlite3Fts5StorageRename(Fts5Storage*, const char *zName);
|
||||
|
||||
int sqlite3Fts5DropAll(Fts5Config*);
|
||||
int sqlite3Fts5CreateTable(Fts5Config*, const char*, const char*, int, char **);
|
||||
|
||||
int sqlite3Fts5StorageDelete(Fts5Storage *p, i64, sqlite3_value**);
|
||||
int sqlite3Fts5StorageContentInsert(Fts5Storage *p, sqlite3_value**, i64*);
|
||||
int sqlite3Fts5StorageIndexInsert(Fts5Storage *p, sqlite3_value**, i64);
|
||||
|
||||
int sqlite3Fts5StorageIntegrity(Fts5Storage *p);
|
||||
|
||||
int sqlite3Fts5StorageStmt(Fts5Storage *p, int eStmt, sqlite3_stmt**, char**);
|
||||
void sqlite3Fts5StorageStmtRelease(Fts5Storage *p, int eStmt, sqlite3_stmt*);
|
||||
|
||||
int sqlite3Fts5StorageDocsize(Fts5Storage *p, i64 iRowid, int *aCol);
|
||||
int sqlite3Fts5StorageSize(Fts5Storage *p, int iCol, i64 *pnAvg);
|
||||
int sqlite3Fts5StorageRowCount(Fts5Storage *p, i64 *pnRow);
|
||||
|
||||
int sqlite3Fts5StorageSync(Fts5Storage *p);
|
||||
int sqlite3Fts5StorageRollback(Fts5Storage *p);
|
||||
|
||||
int sqlite3Fts5StorageConfigValue(
|
||||
Fts5Storage *p, const char*, sqlite3_value*, int
|
||||
);
|
||||
|
||||
int sqlite3Fts5StorageDeleteAll(Fts5Storage *p);
|
||||
int sqlite3Fts5StorageRebuild(Fts5Storage *p);
|
||||
int sqlite3Fts5StorageOptimize(Fts5Storage *p);
|
||||
int sqlite3Fts5StorageMerge(Fts5Storage *p, int nMerge);
|
||||
int sqlite3Fts5StorageReset(Fts5Storage *p);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_storage.c.
|
||||
**************************************************************************/
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_expr.c.
|
||||
*/
|
||||
typedef struct Fts5Expr Fts5Expr;
|
||||
typedef struct Fts5ExprNode Fts5ExprNode;
|
||||
typedef struct Fts5Parse Fts5Parse;
|
||||
typedef struct Fts5Token Fts5Token;
|
||||
typedef struct Fts5ExprPhrase Fts5ExprPhrase;
|
||||
typedef struct Fts5ExprNearset Fts5ExprNearset;
|
||||
|
||||
struct Fts5Token {
|
||||
const char *p; /* Token text (not NULL terminated) */
|
||||
int n; /* Size of buffer p in bytes */
|
||||
};
|
||||
|
||||
/* Parse a MATCH expression. */
|
||||
int sqlite3Fts5ExprNew(
|
||||
Fts5Config *pConfig,
|
||||
int iCol, /* Column on LHS of MATCH operator */
|
||||
const char *zExpr,
|
||||
Fts5Expr **ppNew,
|
||||
char **pzErr
|
||||
);
|
||||
|
||||
/*
|
||||
** for(rc = sqlite3Fts5ExprFirst(pExpr, pIdx, bDesc);
|
||||
** rc==SQLITE_OK && 0==sqlite3Fts5ExprEof(pExpr);
|
||||
** rc = sqlite3Fts5ExprNext(pExpr)
|
||||
** ){
|
||||
** // The document with rowid iRowid matches the expression!
|
||||
** i64 iRowid = sqlite3Fts5ExprRowid(pExpr);
|
||||
** }
|
||||
*/
|
||||
int sqlite3Fts5ExprFirst(Fts5Expr*, Fts5Index *pIdx, i64 iMin, int bDesc);
|
||||
int sqlite3Fts5ExprNext(Fts5Expr*, i64 iMax);
|
||||
int sqlite3Fts5ExprEof(Fts5Expr*);
|
||||
i64 sqlite3Fts5ExprRowid(Fts5Expr*);
|
||||
|
||||
void sqlite3Fts5ExprFree(Fts5Expr*);
|
||||
|
||||
/* Called during startup to register a UDF with SQLite */
|
||||
int sqlite3Fts5ExprInit(Fts5Global*, sqlite3*);
|
||||
|
||||
int sqlite3Fts5ExprPhraseCount(Fts5Expr*);
|
||||
int sqlite3Fts5ExprPhraseSize(Fts5Expr*, int iPhrase);
|
||||
int sqlite3Fts5ExprPoslist(Fts5Expr*, int, const u8 **);
|
||||
|
||||
typedef struct Fts5PoslistPopulator Fts5PoslistPopulator;
|
||||
Fts5PoslistPopulator *sqlite3Fts5ExprClearPoslists(Fts5Expr*, int);
|
||||
int sqlite3Fts5ExprPopulatePoslists(
|
||||
Fts5Config*, Fts5Expr*, Fts5PoslistPopulator*, int, const char*, int
|
||||
);
|
||||
void sqlite3Fts5ExprCheckPoslists(Fts5Expr*, i64);
|
||||
|
||||
int sqlite3Fts5ExprClonePhrase(Fts5Expr*, int, Fts5Expr**);
|
||||
|
||||
int sqlite3Fts5ExprPhraseCollist(Fts5Expr *, int, const u8 **, int *);
|
||||
|
||||
/*******************************************
|
||||
** The fts5_expr.c API above this point is used by the other hand-written
|
||||
** C code in this module. The interfaces below this point are called by
|
||||
** the parser code in fts5parse.y. */
|
||||
|
||||
void sqlite3Fts5ParseError(Fts5Parse *pParse, const char *zFmt, ...);
|
||||
|
||||
Fts5ExprNode *sqlite3Fts5ParseNode(
|
||||
Fts5Parse *pParse,
|
||||
int eType,
|
||||
Fts5ExprNode *pLeft,
|
||||
Fts5ExprNode *pRight,
|
||||
Fts5ExprNearset *pNear
|
||||
);
|
||||
|
||||
Fts5ExprNode *sqlite3Fts5ParseImplicitAnd(
|
||||
Fts5Parse *pParse,
|
||||
Fts5ExprNode *pLeft,
|
||||
Fts5ExprNode *pRight
|
||||
);
|
||||
|
||||
Fts5ExprPhrase *sqlite3Fts5ParseTerm(
|
||||
Fts5Parse *pParse,
|
||||
Fts5ExprPhrase *pPhrase,
|
||||
Fts5Token *pToken,
|
||||
int bPrefix
|
||||
);
|
||||
|
||||
void sqlite3Fts5ParseSetCaret(Fts5ExprPhrase*);
|
||||
|
||||
Fts5ExprNearset *sqlite3Fts5ParseNearset(
|
||||
Fts5Parse*,
|
||||
Fts5ExprNearset*,
|
||||
Fts5ExprPhrase*
|
||||
);
|
||||
|
||||
Fts5Colset *sqlite3Fts5ParseColset(
|
||||
Fts5Parse*,
|
||||
Fts5Colset*,
|
||||
Fts5Token *
|
||||
);
|
||||
|
||||
void sqlite3Fts5ParsePhraseFree(Fts5ExprPhrase*);
|
||||
void sqlite3Fts5ParseNearsetFree(Fts5ExprNearset*);
|
||||
void sqlite3Fts5ParseNodeFree(Fts5ExprNode*);
|
||||
|
||||
void sqlite3Fts5ParseSetDistance(Fts5Parse*, Fts5ExprNearset*, Fts5Token*);
|
||||
void sqlite3Fts5ParseSetColset(Fts5Parse*, Fts5ExprNode*, Fts5Colset*);
|
||||
Fts5Colset *sqlite3Fts5ParseColsetInvert(Fts5Parse*, Fts5Colset*);
|
||||
void sqlite3Fts5ParseFinished(Fts5Parse *pParse, Fts5ExprNode *p);
|
||||
void sqlite3Fts5ParseNear(Fts5Parse *pParse, Fts5Token*);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_expr.c.
|
||||
**************************************************************************/
|
||||
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_aux.c.
|
||||
*/
|
||||
|
||||
int sqlite3Fts5AuxInit(fts5_api*);
|
||||
/*
|
||||
** End of interface to code in fts5_aux.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_tokenizer.c.
|
||||
*/
|
||||
|
||||
int sqlite3Fts5TokenizerInit(fts5_api*);
|
||||
/*
|
||||
** End of interface to code in fts5_tokenizer.c.
|
||||
**************************************************************************/
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to code in fts5_vocab.c.
|
||||
*/
|
||||
|
||||
int sqlite3Fts5VocabInit(Fts5Global*, sqlite3*);
|
||||
|
||||
/*
|
||||
** End of interface to code in fts5_vocab.c.
|
||||
**************************************************************************/
|
||||
|
||||
|
||||
/**************************************************************************
|
||||
** Interface to automatically generated code in fts5_unicode2.c.
|
||||
*/
|
||||
int sqlite3Fts5UnicodeIsdiacritic(int c);
|
||||
int sqlite3Fts5UnicodeFold(int c, int bRemoveDiacritic);
|
||||
|
||||
int sqlite3Fts5UnicodeCatParse(const char*, u8*);
|
||||
int sqlite3Fts5UnicodeCategory(u32 iCode);
|
||||
void sqlite3Fts5UnicodeAscii(u8*, u8*);
|
||||
/*
|
||||
** End of interface to code in fts5_unicode2.c.
|
||||
**************************************************************************/
|
||||
|
||||
#endif
|
||||
@@ -1,716 +0,0 @@
|
||||
/*
|
||||
** 2014 May 31
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
*/
|
||||
|
||||
|
||||
#include "fts5Int.h"
|
||||
#include <math.h> /* amalgamator: keep */
|
||||
|
||||
/*
|
||||
** Object used to iterate through all "coalesced phrase instances" in
|
||||
** a single column of the current row. If the phrase instances in the
|
||||
** column being considered do not overlap, this object simply iterates
|
||||
** through them. Or, if they do overlap (share one or more tokens in
|
||||
** common), each set of overlapping instances is treated as a single
|
||||
** match. See documentation for the highlight() auxiliary function for
|
||||
** details.
|
||||
**
|
||||
** Usage is:
|
||||
**
|
||||
** for(rc = fts5CInstIterNext(pApi, pFts, iCol, &iter);
|
||||
** (rc==SQLITE_OK && 0==fts5CInstIterEof(&iter);
|
||||
** rc = fts5CInstIterNext(&iter)
|
||||
** ){
|
||||
** printf("instance starts at %d, ends at %d\n", iter.iStart, iter.iEnd);
|
||||
** }
|
||||
**
|
||||
*/
|
||||
typedef struct CInstIter CInstIter;
|
||||
struct CInstIter {
|
||||
const Fts5ExtensionApi *pApi; /* API offered by current FTS version */
|
||||
Fts5Context *pFts; /* First arg to pass to pApi functions */
|
||||
int iCol; /* Column to search */
|
||||
int iInst; /* Next phrase instance index */
|
||||
int nInst; /* Total number of phrase instances */
|
||||
|
||||
/* Output variables */
|
||||
int iStart; /* First token in coalesced phrase instance */
|
||||
int iEnd; /* Last token in coalesced phrase instance */
|
||||
};
|
||||
|
||||
/*
|
||||
** Advance the iterator to the next coalesced phrase instance. Return
|
||||
** an SQLite error code if an error occurs, or SQLITE_OK otherwise.
|
||||
*/
|
||||
static int fts5CInstIterNext(CInstIter *pIter){
|
||||
int rc = SQLITE_OK;
|
||||
pIter->iStart = -1;
|
||||
pIter->iEnd = -1;
|
||||
|
||||
while( rc==SQLITE_OK && pIter->iInst<pIter->nInst ){
|
||||
int ip; int ic; int io;
|
||||
rc = pIter->pApi->xInst(pIter->pFts, pIter->iInst, &ip, &ic, &io);
|
||||
if( rc==SQLITE_OK ){
|
||||
if( ic==pIter->iCol ){
|
||||
int iEnd = io - 1 + pIter->pApi->xPhraseSize(pIter->pFts, ip);
|
||||
if( pIter->iStart<0 ){
|
||||
pIter->iStart = io;
|
||||
pIter->iEnd = iEnd;
|
||||
}else if( io<=pIter->iEnd ){
|
||||
if( iEnd>pIter->iEnd ) pIter->iEnd = iEnd;
|
||||
}else{
|
||||
break;
|
||||
}
|
||||
}
|
||||
pIter->iInst++;
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Initialize the iterator object indicated by the final parameter to
|
||||
** iterate through coalesced phrase instances in column iCol.
|
||||
*/
|
||||
static int fts5CInstIterInit(
|
||||
const Fts5ExtensionApi *pApi,
|
||||
Fts5Context *pFts,
|
||||
int iCol,
|
||||
CInstIter *pIter
|
||||
){
|
||||
int rc;
|
||||
|
||||
memset(pIter, 0, sizeof(CInstIter));
|
||||
pIter->pApi = pApi;
|
||||
pIter->pFts = pFts;
|
||||
pIter->iCol = iCol;
|
||||
rc = pApi->xInstCount(pFts, &pIter->nInst);
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts5CInstIterNext(pIter);
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
** Start of highlight() implementation.
|
||||
*/
|
||||
typedef struct HighlightContext HighlightContext;
|
||||
struct HighlightContext {
|
||||
CInstIter iter; /* Coalesced Instance Iterator */
|
||||
int iPos; /* Current token offset in zIn[] */
|
||||
int iRangeStart; /* First token to include */
|
||||
int iRangeEnd; /* If non-zero, last token to include */
|
||||
const char *zOpen; /* Opening highlight */
|
||||
const char *zClose; /* Closing highlight */
|
||||
const char *zIn; /* Input text */
|
||||
int nIn; /* Size of input text in bytes */
|
||||
int iOff; /* Current offset within zIn[] */
|
||||
char *zOut; /* Output value */
|
||||
};
|
||||
|
||||
/*
|
||||
** Append text to the HighlightContext output string - p->zOut. Argument
|
||||
** z points to a buffer containing n bytes of text to append. If n is
|
||||
** negative, everything up until the first '\0' is appended to the output.
|
||||
**
|
||||
** If *pRc is set to any value other than SQLITE_OK when this function is
|
||||
** called, it is a no-op. If an error (i.e. an OOM condition) is encountered,
|
||||
** *pRc is set to an error code before returning.
|
||||
*/
|
||||
static void fts5HighlightAppend(
|
||||
int *pRc,
|
||||
HighlightContext *p,
|
||||
const char *z, int n
|
||||
){
|
||||
if( *pRc==SQLITE_OK && z ){
|
||||
if( n<0 ) n = (int)strlen(z);
|
||||
p->zOut = sqlite3_mprintf("%z%.*s", p->zOut, n, z);
|
||||
if( p->zOut==0 ) *pRc = SQLITE_NOMEM;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Tokenizer callback used by implementation of highlight() function.
|
||||
*/
|
||||
static int fts5HighlightCb(
|
||||
void *pContext, /* Pointer to HighlightContext object */
|
||||
int tflags, /* Mask of FTS5_TOKEN_* flags */
|
||||
const char *pToken, /* Buffer containing token */
|
||||
int nToken, /* Size of token in bytes */
|
||||
int iStartOff, /* Start offset of token */
|
||||
int iEndOff /* End offset of token */
|
||||
){
|
||||
HighlightContext *p = (HighlightContext*)pContext;
|
||||
int rc = SQLITE_OK;
|
||||
int iPos;
|
||||
|
||||
UNUSED_PARAM2(pToken, nToken);
|
||||
|
||||
if( tflags & FTS5_TOKEN_COLOCATED ) return SQLITE_OK;
|
||||
iPos = p->iPos++;
|
||||
|
||||
if( p->iRangeEnd>0 ){
|
||||
if( iPos<p->iRangeStart || iPos>p->iRangeEnd ) return SQLITE_OK;
|
||||
if( p->iRangeStart && iPos==p->iRangeStart ) p->iOff = iStartOff;
|
||||
}
|
||||
|
||||
if( iPos==p->iter.iStart ){
|
||||
fts5HighlightAppend(&rc, p, &p->zIn[p->iOff], iStartOff - p->iOff);
|
||||
fts5HighlightAppend(&rc, p, p->zOpen, -1);
|
||||
p->iOff = iStartOff;
|
||||
}
|
||||
|
||||
if( iPos==p->iter.iEnd ){
|
||||
if( p->iRangeEnd && p->iter.iStart<p->iRangeStart ){
|
||||
fts5HighlightAppend(&rc, p, p->zOpen, -1);
|
||||
}
|
||||
fts5HighlightAppend(&rc, p, &p->zIn[p->iOff], iEndOff - p->iOff);
|
||||
fts5HighlightAppend(&rc, p, p->zClose, -1);
|
||||
p->iOff = iEndOff;
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts5CInstIterNext(&p->iter);
|
||||
}
|
||||
}
|
||||
|
||||
if( p->iRangeEnd>0 && iPos==p->iRangeEnd ){
|
||||
fts5HighlightAppend(&rc, p, &p->zIn[p->iOff], iEndOff - p->iOff);
|
||||
p->iOff = iEndOff;
|
||||
if( iPos>=p->iter.iStart && iPos<p->iter.iEnd ){
|
||||
fts5HighlightAppend(&rc, p, p->zClose, -1);
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Implementation of highlight() function.
|
||||
*/
|
||||
static void fts5HighlightFunction(
|
||||
const Fts5ExtensionApi *pApi, /* API offered by current FTS version */
|
||||
Fts5Context *pFts, /* First arg to pass to pApi functions */
|
||||
sqlite3_context *pCtx, /* Context for returning result/error */
|
||||
int nVal, /* Number of values in apVal[] array */
|
||||
sqlite3_value **apVal /* Array of trailing arguments */
|
||||
){
|
||||
HighlightContext ctx;
|
||||
int rc;
|
||||
int iCol;
|
||||
|
||||
if( nVal!=3 ){
|
||||
const char *zErr = "wrong number of arguments to function highlight()";
|
||||
sqlite3_result_error(pCtx, zErr, -1);
|
||||
return;
|
||||
}
|
||||
|
||||
iCol = sqlite3_value_int(apVal[0]);
|
||||
memset(&ctx, 0, sizeof(HighlightContext));
|
||||
ctx.zOpen = (const char*)sqlite3_value_text(apVal[1]);
|
||||
ctx.zClose = (const char*)sqlite3_value_text(apVal[2]);
|
||||
rc = pApi->xColumnText(pFts, iCol, &ctx.zIn, &ctx.nIn);
|
||||
|
||||
if( ctx.zIn ){
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts5CInstIterInit(pApi, pFts, iCol, &ctx.iter);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = pApi->xTokenize(pFts, ctx.zIn, ctx.nIn, (void*)&ctx,fts5HighlightCb);
|
||||
}
|
||||
fts5HighlightAppend(&rc, &ctx, &ctx.zIn[ctx.iOff], ctx.nIn - ctx.iOff);
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
sqlite3_result_text(pCtx, (const char*)ctx.zOut, -1, SQLITE_TRANSIENT);
|
||||
}
|
||||
sqlite3_free(ctx.zOut);
|
||||
}
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3_result_error_code(pCtx, rc);
|
||||
}
|
||||
}
|
||||
/*
|
||||
** End of highlight() implementation.
|
||||
**************************************************************************/
|
||||
|
||||
/*
|
||||
** Context object passed to the fts5SentenceFinderCb() function.
|
||||
*/
|
||||
typedef struct Fts5SFinder Fts5SFinder;
|
||||
struct Fts5SFinder {
|
||||
int iPos; /* Current token position */
|
||||
int nFirstAlloc; /* Allocated size of aFirst[] */
|
||||
int nFirst; /* Number of entries in aFirst[] */
|
||||
int *aFirst; /* Array of first token in each sentence */
|
||||
const char *zDoc; /* Document being tokenized */
|
||||
};
|
||||
|
||||
/*
|
||||
** Add an entry to the Fts5SFinder.aFirst[] array. Grow the array if
|
||||
** necessary. Return SQLITE_OK if successful, or SQLITE_NOMEM if an
|
||||
** error occurs.
|
||||
*/
|
||||
static int fts5SentenceFinderAdd(Fts5SFinder *p, int iAdd){
|
||||
if( p->nFirstAlloc==p->nFirst ){
|
||||
int nNew = p->nFirstAlloc ? p->nFirstAlloc*2 : 64;
|
||||
int *aNew;
|
||||
|
||||
aNew = (int*)sqlite3_realloc64(p->aFirst, nNew*sizeof(int));
|
||||
if( aNew==0 ) return SQLITE_NOMEM;
|
||||
p->aFirst = aNew;
|
||||
p->nFirstAlloc = nNew;
|
||||
}
|
||||
p->aFirst[p->nFirst++] = iAdd;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** This function is an xTokenize() callback used by the auxiliary snippet()
|
||||
** function. Its job is to identify tokens that are the first in a sentence.
|
||||
** For each such token, an entry is added to the SFinder.aFirst[] array.
|
||||
*/
|
||||
static int fts5SentenceFinderCb(
|
||||
void *pContext, /* Pointer to HighlightContext object */
|
||||
int tflags, /* Mask of FTS5_TOKEN_* flags */
|
||||
const char *pToken, /* Buffer containing token */
|
||||
int nToken, /* Size of token in bytes */
|
||||
int iStartOff, /* Start offset of token */
|
||||
int iEndOff /* End offset of token */
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
|
||||
UNUSED_PARAM2(pToken, nToken);
|
||||
UNUSED_PARAM(iEndOff);
|
||||
|
||||
if( (tflags & FTS5_TOKEN_COLOCATED)==0 ){
|
||||
Fts5SFinder *p = (Fts5SFinder*)pContext;
|
||||
if( p->iPos>0 ){
|
||||
int i;
|
||||
char c = 0;
|
||||
for(i=iStartOff-1; i>=0; i--){
|
||||
c = p->zDoc[i];
|
||||
if( c!=' ' && c!='\t' && c!='\n' && c!='\r' ) break;
|
||||
}
|
||||
if( i!=iStartOff-1 && (c=='.' || c==':') ){
|
||||
rc = fts5SentenceFinderAdd(p, p->iPos);
|
||||
}
|
||||
}else{
|
||||
rc = fts5SentenceFinderAdd(p, 0);
|
||||
}
|
||||
p->iPos++;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
static int fts5SnippetScore(
|
||||
const Fts5ExtensionApi *pApi, /* API offered by current FTS version */
|
||||
Fts5Context *pFts, /* First arg to pass to pApi functions */
|
||||
int nDocsize, /* Size of column in tokens */
|
||||
unsigned char *aSeen, /* Array with one element per query phrase */
|
||||
int iCol, /* Column to score */
|
||||
int iPos, /* Starting offset to score */
|
||||
int nToken, /* Max tokens per snippet */
|
||||
int *pnScore, /* OUT: Score */
|
||||
int *piPos /* OUT: Adjusted offset */
|
||||
){
|
||||
int rc;
|
||||
int i;
|
||||
int ip = 0;
|
||||
int ic = 0;
|
||||
int iOff = 0;
|
||||
int iFirst = -1;
|
||||
int nInst;
|
||||
int nScore = 0;
|
||||
int iLast = 0;
|
||||
sqlite3_int64 iEnd = (sqlite3_int64)iPos + nToken;
|
||||
|
||||
rc = pApi->xInstCount(pFts, &nInst);
|
||||
for(i=0; i<nInst && rc==SQLITE_OK; i++){
|
||||
rc = pApi->xInst(pFts, i, &ip, &ic, &iOff);
|
||||
if( rc==SQLITE_OK && ic==iCol && iOff>=iPos && iOff<iEnd ){
|
||||
nScore += (aSeen[ip] ? 1 : 1000);
|
||||
aSeen[ip] = 1;
|
||||
if( iFirst<0 ) iFirst = iOff;
|
||||
iLast = iOff + pApi->xPhraseSize(pFts, ip);
|
||||
}
|
||||
}
|
||||
|
||||
*pnScore = nScore;
|
||||
if( piPos ){
|
||||
sqlite3_int64 iAdj = iFirst - (nToken - (iLast-iFirst)) / 2;
|
||||
if( (iAdj+nToken)>nDocsize ) iAdj = nDocsize - nToken;
|
||||
if( iAdj<0 ) iAdj = 0;
|
||||
*piPos = iAdj;
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return the value in pVal interpreted as utf-8 text. Except, if pVal
|
||||
** contains a NULL value, return a pointer to a static string zero
|
||||
** bytes in length instead of a NULL pointer.
|
||||
*/
|
||||
static const char *fts5ValueToText(sqlite3_value *pVal){
|
||||
const char *zRet = (const char*)sqlite3_value_text(pVal);
|
||||
return zRet ? zRet : "";
|
||||
}
|
||||
|
||||
/*
|
||||
** Implementation of snippet() function.
|
||||
*/
|
||||
static void fts5SnippetFunction(
|
||||
const Fts5ExtensionApi *pApi, /* API offered by current FTS version */
|
||||
Fts5Context *pFts, /* First arg to pass to pApi functions */
|
||||
sqlite3_context *pCtx, /* Context for returning result/error */
|
||||
int nVal, /* Number of values in apVal[] array */
|
||||
sqlite3_value **apVal /* Array of trailing arguments */
|
||||
){
|
||||
HighlightContext ctx;
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
int iCol; /* 1st argument to snippet() */
|
||||
const char *zEllips; /* 4th argument to snippet() */
|
||||
int nToken; /* 5th argument to snippet() */
|
||||
int nInst = 0; /* Number of instance matches this row */
|
||||
int i; /* Used to iterate through instances */
|
||||
int nPhrase; /* Number of phrases in query */
|
||||
unsigned char *aSeen; /* Array of "seen instance" flags */
|
||||
int iBestCol; /* Column containing best snippet */
|
||||
int iBestStart = 0; /* First token of best snippet */
|
||||
int nBestScore = 0; /* Score of best snippet */
|
||||
int nColSize = 0; /* Total size of iBestCol in tokens */
|
||||
Fts5SFinder sFinder; /* Used to find the beginnings of sentences */
|
||||
int nCol;
|
||||
|
||||
if( nVal!=5 ){
|
||||
const char *zErr = "wrong number of arguments to function snippet()";
|
||||
sqlite3_result_error(pCtx, zErr, -1);
|
||||
return;
|
||||
}
|
||||
|
||||
nCol = pApi->xColumnCount(pFts);
|
||||
memset(&ctx, 0, sizeof(HighlightContext));
|
||||
iCol = sqlite3_value_int(apVal[0]);
|
||||
ctx.zOpen = fts5ValueToText(apVal[1]);
|
||||
ctx.zClose = fts5ValueToText(apVal[2]);
|
||||
zEllips = fts5ValueToText(apVal[3]);
|
||||
nToken = sqlite3_value_int(apVal[4]);
|
||||
|
||||
iBestCol = (iCol>=0 ? iCol : 0);
|
||||
nPhrase = pApi->xPhraseCount(pFts);
|
||||
aSeen = sqlite3_malloc(nPhrase);
|
||||
if( aSeen==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = pApi->xInstCount(pFts, &nInst);
|
||||
}
|
||||
|
||||
memset(&sFinder, 0, sizeof(Fts5SFinder));
|
||||
for(i=0; i<nCol; i++){
|
||||
if( iCol<0 || iCol==i ){
|
||||
int nDoc;
|
||||
int nDocsize;
|
||||
int ii;
|
||||
sFinder.iPos = 0;
|
||||
sFinder.nFirst = 0;
|
||||
rc = pApi->xColumnText(pFts, i, &sFinder.zDoc, &nDoc);
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
rc = pApi->xTokenize(pFts,
|
||||
sFinder.zDoc, nDoc, (void*)&sFinder,fts5SentenceFinderCb
|
||||
);
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
rc = pApi->xColumnSize(pFts, i, &nDocsize);
|
||||
if( rc!=SQLITE_OK ) break;
|
||||
|
||||
for(ii=0; rc==SQLITE_OK && ii<nInst; ii++){
|
||||
int ip, ic, io;
|
||||
int iAdj;
|
||||
int nScore;
|
||||
int jj;
|
||||
|
||||
rc = pApi->xInst(pFts, ii, &ip, &ic, &io);
|
||||
if( ic!=i ) continue;
|
||||
if( io>nDocsize ) rc = FTS5_CORRUPT;
|
||||
if( rc!=SQLITE_OK ) continue;
|
||||
memset(aSeen, 0, nPhrase);
|
||||
rc = fts5SnippetScore(pApi, pFts, nDocsize, aSeen, i,
|
||||
io, nToken, &nScore, &iAdj
|
||||
);
|
||||
if( rc==SQLITE_OK && nScore>nBestScore ){
|
||||
nBestScore = nScore;
|
||||
iBestCol = i;
|
||||
iBestStart = iAdj;
|
||||
nColSize = nDocsize;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK && sFinder.nFirst && nDocsize>nToken ){
|
||||
for(jj=0; jj<(sFinder.nFirst-1); jj++){
|
||||
if( sFinder.aFirst[jj+1]>io ) break;
|
||||
}
|
||||
|
||||
if( sFinder.aFirst[jj]<io ){
|
||||
memset(aSeen, 0, nPhrase);
|
||||
rc = fts5SnippetScore(pApi, pFts, nDocsize, aSeen, i,
|
||||
sFinder.aFirst[jj], nToken, &nScore, 0
|
||||
);
|
||||
|
||||
nScore += (sFinder.aFirst[jj]==0 ? 120 : 100);
|
||||
if( rc==SQLITE_OK && nScore>nBestScore ){
|
||||
nBestScore = nScore;
|
||||
iBestCol = i;
|
||||
iBestStart = sFinder.aFirst[jj];
|
||||
nColSize = nDocsize;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = pApi->xColumnText(pFts, iBestCol, &ctx.zIn, &ctx.nIn);
|
||||
}
|
||||
if( rc==SQLITE_OK && nColSize==0 ){
|
||||
rc = pApi->xColumnSize(pFts, iBestCol, &nColSize);
|
||||
}
|
||||
if( ctx.zIn ){
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts5CInstIterInit(pApi, pFts, iBestCol, &ctx.iter);
|
||||
}
|
||||
|
||||
ctx.iRangeStart = iBestStart;
|
||||
ctx.iRangeEnd = iBestStart + nToken - 1;
|
||||
|
||||
if( iBestStart>0 ){
|
||||
fts5HighlightAppend(&rc, &ctx, zEllips, -1);
|
||||
}
|
||||
|
||||
/* Advance iterator ctx.iter so that it points to the first coalesced
|
||||
** phrase instance at or following position iBestStart. */
|
||||
while( ctx.iter.iStart>=0 && ctx.iter.iStart<iBestStart && rc==SQLITE_OK ){
|
||||
rc = fts5CInstIterNext(&ctx.iter);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = pApi->xTokenize(pFts, ctx.zIn, ctx.nIn, (void*)&ctx,fts5HighlightCb);
|
||||
}
|
||||
if( ctx.iRangeEnd>=(nColSize-1) ){
|
||||
fts5HighlightAppend(&rc, &ctx, &ctx.zIn[ctx.iOff], ctx.nIn - ctx.iOff);
|
||||
}else{
|
||||
fts5HighlightAppend(&rc, &ctx, zEllips, -1);
|
||||
}
|
||||
}
|
||||
if( rc==SQLITE_OK ){
|
||||
sqlite3_result_text(pCtx, (const char*)ctx.zOut, -1, SQLITE_TRANSIENT);
|
||||
}else{
|
||||
sqlite3_result_error_code(pCtx, rc);
|
||||
}
|
||||
sqlite3_free(ctx.zOut);
|
||||
sqlite3_free(aSeen);
|
||||
sqlite3_free(sFinder.aFirst);
|
||||
}
|
||||
|
||||
/************************************************************************/
|
||||
|
||||
/*
|
||||
** The first time the bm25() function is called for a query, an instance
|
||||
** of the following structure is allocated and populated.
|
||||
*/
|
||||
typedef struct Fts5Bm25Data Fts5Bm25Data;
|
||||
struct Fts5Bm25Data {
|
||||
int nPhrase; /* Number of phrases in query */
|
||||
double avgdl; /* Average number of tokens in each row */
|
||||
double *aIDF; /* IDF for each phrase */
|
||||
double *aFreq; /* Array used to calculate phrase freq. */
|
||||
};
|
||||
|
||||
/*
|
||||
** Callback used by fts5Bm25GetData() to count the number of rows in the
|
||||
** table matched by each individual phrase within the query.
|
||||
*/
|
||||
static int fts5CountCb(
|
||||
const Fts5ExtensionApi *pApi,
|
||||
Fts5Context *pFts,
|
||||
void *pUserData /* Pointer to sqlite3_int64 variable */
|
||||
){
|
||||
sqlite3_int64 *pn = (sqlite3_int64*)pUserData;
|
||||
UNUSED_PARAM2(pApi, pFts);
|
||||
(*pn)++;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Set *ppData to point to the Fts5Bm25Data object for the current query.
|
||||
** If the object has not already been allocated, allocate and populate it
|
||||
** now.
|
||||
*/
|
||||
static int fts5Bm25GetData(
|
||||
const Fts5ExtensionApi *pApi,
|
||||
Fts5Context *pFts,
|
||||
Fts5Bm25Data **ppData /* OUT: bm25-data object for this query */
|
||||
){
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
Fts5Bm25Data *p; /* Object to return */
|
||||
|
||||
p = pApi->xGetAuxdata(pFts, 0);
|
||||
if( p==0 ){
|
||||
int nPhrase; /* Number of phrases in query */
|
||||
sqlite3_int64 nRow = 0; /* Number of rows in table */
|
||||
sqlite3_int64 nToken = 0; /* Number of tokens in table */
|
||||
sqlite3_int64 nByte; /* Bytes of space to allocate */
|
||||
int i;
|
||||
|
||||
/* Allocate the Fts5Bm25Data object */
|
||||
nPhrase = pApi->xPhraseCount(pFts);
|
||||
nByte = sizeof(Fts5Bm25Data) + nPhrase*2*sizeof(double);
|
||||
p = (Fts5Bm25Data*)sqlite3_malloc64(nByte);
|
||||
if( p==0 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memset(p, 0, nByte);
|
||||
p->nPhrase = nPhrase;
|
||||
p->aIDF = (double*)&p[1];
|
||||
p->aFreq = &p->aIDF[nPhrase];
|
||||
}
|
||||
|
||||
/* Calculate the average document length for this FTS5 table */
|
||||
if( rc==SQLITE_OK ) rc = pApi->xRowCount(pFts, &nRow);
|
||||
assert( rc!=SQLITE_OK || nRow>0 );
|
||||
if( rc==SQLITE_OK ) rc = pApi->xColumnTotalSize(pFts, -1, &nToken);
|
||||
if( rc==SQLITE_OK ) p->avgdl = (double)nToken / (double)nRow;
|
||||
|
||||
/* Calculate an IDF for each phrase in the query */
|
||||
for(i=0; rc==SQLITE_OK && i<nPhrase; i++){
|
||||
sqlite3_int64 nHit = 0;
|
||||
rc = pApi->xQueryPhrase(pFts, i, (void*)&nHit, fts5CountCb);
|
||||
if( rc==SQLITE_OK ){
|
||||
/* Calculate the IDF (Inverse Document Frequency) for phrase i.
|
||||
** This is done using the standard BM25 formula as found on wikipedia:
|
||||
**
|
||||
** IDF = log( (N - nHit + 0.5) / (nHit + 0.5) )
|
||||
**
|
||||
** where "N" is the total number of documents in the set and nHit
|
||||
** is the number that contain at least one instance of the phrase
|
||||
** under consideration.
|
||||
**
|
||||
** The problem with this is that if (N < 2*nHit), the IDF is
|
||||
** negative. Which is undesirable. So the mimimum allowable IDF is
|
||||
** (1e-6) - roughly the same as a term that appears in just over
|
||||
** half of set of 5,000,000 documents. */
|
||||
double idf = log( (nRow - nHit + 0.5) / (nHit + 0.5) );
|
||||
if( idf<=0.0 ) idf = 1e-6;
|
||||
p->aIDF[i] = idf;
|
||||
}
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3_free(p);
|
||||
}else{
|
||||
rc = pApi->xSetAuxdata(pFts, p, sqlite3_free);
|
||||
}
|
||||
if( rc!=SQLITE_OK ) p = 0;
|
||||
}
|
||||
*ppData = p;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Implementation of bm25() function.
|
||||
*/
|
||||
static void fts5Bm25Function(
|
||||
const Fts5ExtensionApi *pApi, /* API offered by current FTS version */
|
||||
Fts5Context *pFts, /* First arg to pass to pApi functions */
|
||||
sqlite3_context *pCtx, /* Context for returning result/error */
|
||||
int nVal, /* Number of values in apVal[] array */
|
||||
sqlite3_value **apVal /* Array of trailing arguments */
|
||||
){
|
||||
const double k1 = 1.2; /* Constant "k1" from BM25 formula */
|
||||
const double b = 0.75; /* Constant "b" from BM25 formula */
|
||||
int rc = SQLITE_OK; /* Error code */
|
||||
double score = 0.0; /* SQL function return value */
|
||||
Fts5Bm25Data *pData; /* Values allocated/calculated once only */
|
||||
int i; /* Iterator variable */
|
||||
int nInst = 0; /* Value returned by xInstCount() */
|
||||
double D = 0.0; /* Total number of tokens in row */
|
||||
double *aFreq = 0; /* Array of phrase freq. for current row */
|
||||
|
||||
/* Calculate the phrase frequency (symbol "f(qi,D)" in the documentation)
|
||||
** for each phrase in the query for the current row. */
|
||||
rc = fts5Bm25GetData(pApi, pFts, &pData);
|
||||
if( rc==SQLITE_OK ){
|
||||
aFreq = pData->aFreq;
|
||||
memset(aFreq, 0, sizeof(double) * pData->nPhrase);
|
||||
rc = pApi->xInstCount(pFts, &nInst);
|
||||
}
|
||||
for(i=0; rc==SQLITE_OK && i<nInst; i++){
|
||||
int ip; int ic; int io;
|
||||
rc = pApi->xInst(pFts, i, &ip, &ic, &io);
|
||||
if( rc==SQLITE_OK ){
|
||||
double w = (nVal > ic) ? sqlite3_value_double(apVal[ic]) : 1.0;
|
||||
aFreq[ip] += w;
|
||||
}
|
||||
}
|
||||
|
||||
/* Figure out the total size of the current row in tokens. */
|
||||
if( rc==SQLITE_OK ){
|
||||
int nTok;
|
||||
rc = pApi->xColumnSize(pFts, -1, &nTok);
|
||||
D = (double)nTok;
|
||||
}
|
||||
|
||||
/* Determine the BM25 score for the current row. */
|
||||
for(i=0; rc==SQLITE_OK && i<pData->nPhrase; i++){
|
||||
score += pData->aIDF[i] * (
|
||||
( aFreq[i] * (k1 + 1.0) ) /
|
||||
( aFreq[i] + k1 * (1 - b + b * D / pData->avgdl) )
|
||||
);
|
||||
}
|
||||
|
||||
/* If no error has occurred, return the calculated score. Otherwise,
|
||||
** throw an SQL exception. */
|
||||
if( rc==SQLITE_OK ){
|
||||
sqlite3_result_double(pCtx, -1.0 * score);
|
||||
}else{
|
||||
sqlite3_result_error_code(pCtx, rc);
|
||||
}
|
||||
}
|
||||
|
||||
int sqlite3Fts5AuxInit(fts5_api *pApi){
|
||||
struct Builtin {
|
||||
const char *zFunc; /* Function name (nul-terminated) */
|
||||
void *pUserData; /* User-data pointer */
|
||||
fts5_extension_function xFunc;/* Callback function */
|
||||
void (*xDestroy)(void*); /* Destructor function */
|
||||
} aBuiltin [] = {
|
||||
{ "snippet", 0, fts5SnippetFunction, 0 },
|
||||
{ "highlight", 0, fts5HighlightFunction, 0 },
|
||||
{ "bm25", 0, fts5Bm25Function, 0 },
|
||||
};
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
int i; /* To iterate through builtin functions */
|
||||
|
||||
for(i=0; rc==SQLITE_OK && i<ArraySize(aBuiltin); i++){
|
||||
rc = pApi->xCreateFunction(pApi,
|
||||
aBuiltin[i].zFunc,
|
||||
aBuiltin[i].pUserData,
|
||||
aBuiltin[i].xFunc,
|
||||
aBuiltin[i].xDestroy
|
||||
);
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
@@ -1,394 +0,0 @@
|
||||
/*
|
||||
** 2014 May 31
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
*/
|
||||
|
||||
|
||||
|
||||
#include "fts5Int.h"
|
||||
|
||||
int sqlite3Fts5BufferSize(int *pRc, Fts5Buffer *pBuf, u32 nByte){
|
||||
if( (u32)pBuf->nSpace<nByte ){
|
||||
u64 nNew = pBuf->nSpace ? pBuf->nSpace : 64;
|
||||
u8 *pNew;
|
||||
while( nNew<nByte ){
|
||||
nNew = nNew * 2;
|
||||
}
|
||||
pNew = sqlite3_realloc64(pBuf->p, nNew);
|
||||
if( pNew==0 ){
|
||||
*pRc = SQLITE_NOMEM;
|
||||
return 1;
|
||||
}else{
|
||||
pBuf->nSpace = nNew;
|
||||
pBuf->p = pNew;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Encode value iVal as an SQLite varint and append it to the buffer object
|
||||
** pBuf. If an OOM error occurs, set the error code in p.
|
||||
*/
|
||||
void sqlite3Fts5BufferAppendVarint(int *pRc, Fts5Buffer *pBuf, i64 iVal){
|
||||
if( fts5BufferGrow(pRc, pBuf, 9) ) return;
|
||||
pBuf->n += sqlite3Fts5PutVarint(&pBuf->p[pBuf->n], iVal);
|
||||
}
|
||||
|
||||
void sqlite3Fts5Put32(u8 *aBuf, int iVal){
|
||||
aBuf[0] = (iVal>>24) & 0x00FF;
|
||||
aBuf[1] = (iVal>>16) & 0x00FF;
|
||||
aBuf[2] = (iVal>> 8) & 0x00FF;
|
||||
aBuf[3] = (iVal>> 0) & 0x00FF;
|
||||
}
|
||||
|
||||
int sqlite3Fts5Get32(const u8 *aBuf){
|
||||
return (int)((((u32)aBuf[0])<<24) + (aBuf[1]<<16) + (aBuf[2]<<8) + aBuf[3]);
|
||||
}
|
||||
|
||||
/*
|
||||
** Append buffer nData/pData to buffer pBuf. If an OOM error occurs, set
|
||||
** the error code in p. If an error has already occurred when this function
|
||||
** is called, it is a no-op.
|
||||
*/
|
||||
void sqlite3Fts5BufferAppendBlob(
|
||||
int *pRc,
|
||||
Fts5Buffer *pBuf,
|
||||
u32 nData,
|
||||
const u8 *pData
|
||||
){
|
||||
assert_nc( *pRc || nData>=0 );
|
||||
if( nData ){
|
||||
if( fts5BufferGrow(pRc, pBuf, nData) ) return;
|
||||
memcpy(&pBuf->p[pBuf->n], pData, nData);
|
||||
pBuf->n += nData;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Append the nul-terminated string zStr to the buffer pBuf. This function
|
||||
** ensures that the byte following the buffer data is set to 0x00, even
|
||||
** though this byte is not included in the pBuf->n count.
|
||||
*/
|
||||
void sqlite3Fts5BufferAppendString(
|
||||
int *pRc,
|
||||
Fts5Buffer *pBuf,
|
||||
const char *zStr
|
||||
){
|
||||
int nStr = (int)strlen(zStr);
|
||||
sqlite3Fts5BufferAppendBlob(pRc, pBuf, nStr+1, (const u8*)zStr);
|
||||
pBuf->n--;
|
||||
}
|
||||
|
||||
/*
|
||||
** Argument zFmt is a printf() style format string. This function performs
|
||||
** the printf() style processing, then appends the results to buffer pBuf.
|
||||
**
|
||||
** Like sqlite3Fts5BufferAppendString(), this function ensures that the byte
|
||||
** following the buffer data is set to 0x00, even though this byte is not
|
||||
** included in the pBuf->n count.
|
||||
*/
|
||||
void sqlite3Fts5BufferAppendPrintf(
|
||||
int *pRc,
|
||||
Fts5Buffer *pBuf,
|
||||
char *zFmt, ...
|
||||
){
|
||||
if( *pRc==SQLITE_OK ){
|
||||
char *zTmp;
|
||||
va_list ap;
|
||||
va_start(ap, zFmt);
|
||||
zTmp = sqlite3_vmprintf(zFmt, ap);
|
||||
va_end(ap);
|
||||
|
||||
if( zTmp==0 ){
|
||||
*pRc = SQLITE_NOMEM;
|
||||
}else{
|
||||
sqlite3Fts5BufferAppendString(pRc, pBuf, zTmp);
|
||||
sqlite3_free(zTmp);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
char *sqlite3Fts5Mprintf(int *pRc, const char *zFmt, ...){
|
||||
char *zRet = 0;
|
||||
if( *pRc==SQLITE_OK ){
|
||||
va_list ap;
|
||||
va_start(ap, zFmt);
|
||||
zRet = sqlite3_vmprintf(zFmt, ap);
|
||||
va_end(ap);
|
||||
if( zRet==0 ){
|
||||
*pRc = SQLITE_NOMEM;
|
||||
}
|
||||
}
|
||||
return zRet;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Free any buffer allocated by pBuf. Zero the structure before returning.
|
||||
*/
|
||||
void sqlite3Fts5BufferFree(Fts5Buffer *pBuf){
|
||||
sqlite3_free(pBuf->p);
|
||||
memset(pBuf, 0, sizeof(Fts5Buffer));
|
||||
}
|
||||
|
||||
/*
|
||||
** Zero the contents of the buffer object. But do not free the associated
|
||||
** memory allocation.
|
||||
*/
|
||||
void sqlite3Fts5BufferZero(Fts5Buffer *pBuf){
|
||||
pBuf->n = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Set the buffer to contain nData/pData. If an OOM error occurs, leave an
|
||||
** the error code in p. If an error has already occurred when this function
|
||||
** is called, it is a no-op.
|
||||
*/
|
||||
void sqlite3Fts5BufferSet(
|
||||
int *pRc,
|
||||
Fts5Buffer *pBuf,
|
||||
int nData,
|
||||
const u8 *pData
|
||||
){
|
||||
pBuf->n = 0;
|
||||
sqlite3Fts5BufferAppendBlob(pRc, pBuf, nData, pData);
|
||||
}
|
||||
|
||||
int sqlite3Fts5PoslistNext64(
|
||||
const u8 *a, int n, /* Buffer containing poslist */
|
||||
int *pi, /* IN/OUT: Offset within a[] */
|
||||
i64 *piOff /* IN/OUT: Current offset */
|
||||
){
|
||||
int i = *pi;
|
||||
if( i>=n ){
|
||||
/* EOF */
|
||||
*piOff = -1;
|
||||
return 1;
|
||||
}else{
|
||||
i64 iOff = *piOff;
|
||||
int iVal;
|
||||
fts5FastGetVarint32(a, i, iVal);
|
||||
if( iVal==1 ){
|
||||
fts5FastGetVarint32(a, i, iVal);
|
||||
iOff = ((i64)iVal) << 32;
|
||||
fts5FastGetVarint32(a, i, iVal);
|
||||
}
|
||||
*piOff = iOff + ((iVal-2) & 0x7FFFFFFF);
|
||||
*pi = i;
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Advance the iterator object passed as the only argument. Return true
|
||||
** if the iterator reaches EOF, or false otherwise.
|
||||
*/
|
||||
int sqlite3Fts5PoslistReaderNext(Fts5PoslistReader *pIter){
|
||||
if( sqlite3Fts5PoslistNext64(pIter->a, pIter->n, &pIter->i, &pIter->iPos) ){
|
||||
pIter->bEof = 1;
|
||||
}
|
||||
return pIter->bEof;
|
||||
}
|
||||
|
||||
int sqlite3Fts5PoslistReaderInit(
|
||||
const u8 *a, int n, /* Poslist buffer to iterate through */
|
||||
Fts5PoslistReader *pIter /* Iterator object to initialize */
|
||||
){
|
||||
memset(pIter, 0, sizeof(*pIter));
|
||||
pIter->a = a;
|
||||
pIter->n = n;
|
||||
sqlite3Fts5PoslistReaderNext(pIter);
|
||||
return pIter->bEof;
|
||||
}
|
||||
|
||||
/*
|
||||
** Append position iPos to the position list being accumulated in buffer
|
||||
** pBuf, which must be already be large enough to hold the new data.
|
||||
** The previous position written to this list is *piPrev. *piPrev is set
|
||||
** to iPos before returning.
|
||||
*/
|
||||
void sqlite3Fts5PoslistSafeAppend(
|
||||
Fts5Buffer *pBuf,
|
||||
i64 *piPrev,
|
||||
i64 iPos
|
||||
){
|
||||
static const i64 colmask = ((i64)(0x7FFFFFFF)) << 32;
|
||||
if( (iPos & colmask) != (*piPrev & colmask) ){
|
||||
pBuf->p[pBuf->n++] = 1;
|
||||
pBuf->n += sqlite3Fts5PutVarint(&pBuf->p[pBuf->n], (iPos>>32));
|
||||
*piPrev = (iPos & colmask);
|
||||
}
|
||||
pBuf->n += sqlite3Fts5PutVarint(&pBuf->p[pBuf->n], (iPos-*piPrev)+2);
|
||||
*piPrev = iPos;
|
||||
}
|
||||
|
||||
int sqlite3Fts5PoslistWriterAppend(
|
||||
Fts5Buffer *pBuf,
|
||||
Fts5PoslistWriter *pWriter,
|
||||
i64 iPos
|
||||
){
|
||||
int rc = 0; /* Initialized only to suppress erroneous warning from Clang */
|
||||
if( fts5BufferGrow(&rc, pBuf, 5+5+5) ) return rc;
|
||||
sqlite3Fts5PoslistSafeAppend(pBuf, &pWriter->iPrev, iPos);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
void *sqlite3Fts5MallocZero(int *pRc, sqlite3_int64 nByte){
|
||||
void *pRet = 0;
|
||||
if( *pRc==SQLITE_OK ){
|
||||
pRet = sqlite3_malloc64(nByte);
|
||||
if( pRet==0 ){
|
||||
if( nByte>0 ) *pRc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memset(pRet, 0, nByte);
|
||||
}
|
||||
}
|
||||
return pRet;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a nul-terminated copy of the string indicated by pIn. If nIn
|
||||
** is non-negative, then it is the length of the string in bytes. Otherwise,
|
||||
** the length of the string is determined using strlen().
|
||||
**
|
||||
** It is the responsibility of the caller to eventually free the returned
|
||||
** buffer using sqlite3_free(). If an OOM error occurs, NULL is returned.
|
||||
*/
|
||||
char *sqlite3Fts5Strndup(int *pRc, const char *pIn, int nIn){
|
||||
char *zRet = 0;
|
||||
if( *pRc==SQLITE_OK ){
|
||||
if( nIn<0 ){
|
||||
nIn = (int)strlen(pIn);
|
||||
}
|
||||
zRet = (char*)sqlite3_malloc(nIn+1);
|
||||
if( zRet ){
|
||||
memcpy(zRet, pIn, nIn);
|
||||
zRet[nIn] = '\0';
|
||||
}else{
|
||||
*pRc = SQLITE_NOMEM;
|
||||
}
|
||||
}
|
||||
return zRet;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Return true if character 't' may be part of an FTS5 bareword, or false
|
||||
** otherwise. Characters that may be part of barewords:
|
||||
**
|
||||
** * All non-ASCII characters,
|
||||
** * The 52 upper and lower case ASCII characters, and
|
||||
** * The 10 integer ASCII characters.
|
||||
** * The underscore character "_" (0x5F).
|
||||
** * The unicode "subsitute" character (0x1A).
|
||||
*/
|
||||
int sqlite3Fts5IsBareword(char t){
|
||||
u8 aBareword[128] = {
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x00 .. 0x0F */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, /* 0x10 .. 0x1F */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x20 .. 0x2F */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, /* 0x30 .. 0x3F */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x40 .. 0x4F */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, /* 0x50 .. 0x5F */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x60 .. 0x6F */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 /* 0x70 .. 0x7F */
|
||||
};
|
||||
|
||||
return (t & 0x80) || aBareword[(int)t];
|
||||
}
|
||||
|
||||
|
||||
/*************************************************************************
|
||||
*/
|
||||
typedef struct Fts5TermsetEntry Fts5TermsetEntry;
|
||||
struct Fts5TermsetEntry {
|
||||
char *pTerm;
|
||||
int nTerm;
|
||||
int iIdx; /* Index (main or aPrefix[] entry) */
|
||||
Fts5TermsetEntry *pNext;
|
||||
};
|
||||
|
||||
struct Fts5Termset {
|
||||
Fts5TermsetEntry *apHash[512];
|
||||
};
|
||||
|
||||
int sqlite3Fts5TermsetNew(Fts5Termset **pp){
|
||||
int rc = SQLITE_OK;
|
||||
*pp = sqlite3Fts5MallocZero(&rc, sizeof(Fts5Termset));
|
||||
return rc;
|
||||
}
|
||||
|
||||
int sqlite3Fts5TermsetAdd(
|
||||
Fts5Termset *p,
|
||||
int iIdx,
|
||||
const char *pTerm, int nTerm,
|
||||
int *pbPresent
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
*pbPresent = 0;
|
||||
if( p ){
|
||||
int i;
|
||||
u32 hash = 13;
|
||||
Fts5TermsetEntry *pEntry;
|
||||
|
||||
/* Calculate a hash value for this term. This is the same hash checksum
|
||||
** used by the fts5_hash.c module. This is not important for correct
|
||||
** operation of the module, but is necessary to ensure that some tests
|
||||
** designed to produce hash table collisions really do work. */
|
||||
for(i=nTerm-1; i>=0; i--){
|
||||
hash = (hash << 3) ^ hash ^ pTerm[i];
|
||||
}
|
||||
hash = (hash << 3) ^ hash ^ iIdx;
|
||||
hash = hash % ArraySize(p->apHash);
|
||||
|
||||
for(pEntry=p->apHash[hash]; pEntry; pEntry=pEntry->pNext){
|
||||
if( pEntry->iIdx==iIdx
|
||||
&& pEntry->nTerm==nTerm
|
||||
&& memcmp(pEntry->pTerm, pTerm, nTerm)==0
|
||||
){
|
||||
*pbPresent = 1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if( pEntry==0 ){
|
||||
pEntry = sqlite3Fts5MallocZero(&rc, sizeof(Fts5TermsetEntry) + nTerm);
|
||||
if( pEntry ){
|
||||
pEntry->pTerm = (char*)&pEntry[1];
|
||||
pEntry->nTerm = nTerm;
|
||||
pEntry->iIdx = iIdx;
|
||||
memcpy(pEntry->pTerm, pTerm, nTerm);
|
||||
pEntry->pNext = p->apHash[hash];
|
||||
p->apHash[hash] = pEntry;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
void sqlite3Fts5TermsetFree(Fts5Termset *p){
|
||||
if( p ){
|
||||
u32 i;
|
||||
for(i=0; i<ArraySize(p->apHash); i++){
|
||||
Fts5TermsetEntry *pEntry = p->apHash[i];
|
||||
while( pEntry ){
|
||||
Fts5TermsetEntry *pDel = pEntry;
|
||||
pEntry = pEntry->pNext;
|
||||
sqlite3_free(pDel);
|
||||
}
|
||||
}
|
||||
sqlite3_free(p);
|
||||
}
|
||||
}
|
||||
@@ -1,961 +0,0 @@
|
||||
/*
|
||||
** 2014 Jun 09
|
||||
**
|
||||
** The author disclaims copyright to this source code. In place of
|
||||
** a legal notice, here is a blessing:
|
||||
**
|
||||
** May you do good and not evil.
|
||||
** May you find forgiveness for yourself and forgive others.
|
||||
** May you share freely, never taking more than you give.
|
||||
**
|
||||
******************************************************************************
|
||||
**
|
||||
** This is an SQLite module implementing full-text search.
|
||||
*/
|
||||
|
||||
|
||||
#include "fts5Int.h"
|
||||
|
||||
#define FTS5_DEFAULT_PAGE_SIZE 4050
|
||||
#define FTS5_DEFAULT_AUTOMERGE 4
|
||||
#define FTS5_DEFAULT_USERMERGE 4
|
||||
#define FTS5_DEFAULT_CRISISMERGE 16
|
||||
#define FTS5_DEFAULT_HASHSIZE (1024*1024)
|
||||
|
||||
/* Maximum allowed page size */
|
||||
#define FTS5_MAX_PAGE_SIZE (128*1024)
|
||||
|
||||
static int fts5_iswhitespace(char x){
|
||||
return (x==' ');
|
||||
}
|
||||
|
||||
static int fts5_isopenquote(char x){
|
||||
return (x=='"' || x=='\'' || x=='[' || x=='`');
|
||||
}
|
||||
|
||||
/*
|
||||
** Argument pIn points to a character that is part of a nul-terminated
|
||||
** string. Return a pointer to the first character following *pIn in
|
||||
** the string that is not a white-space character.
|
||||
*/
|
||||
static const char *fts5ConfigSkipWhitespace(const char *pIn){
|
||||
const char *p = pIn;
|
||||
if( p ){
|
||||
while( fts5_iswhitespace(*p) ){ p++; }
|
||||
}
|
||||
return p;
|
||||
}
|
||||
|
||||
/*
|
||||
** Argument pIn points to a character that is part of a nul-terminated
|
||||
** string. Return a pointer to the first character following *pIn in
|
||||
** the string that is not a "bareword" character.
|
||||
*/
|
||||
static const char *fts5ConfigSkipBareword(const char *pIn){
|
||||
const char *p = pIn;
|
||||
while ( sqlite3Fts5IsBareword(*p) ) p++;
|
||||
if( p==pIn ) p = 0;
|
||||
return p;
|
||||
}
|
||||
|
||||
static int fts5_isdigit(char a){
|
||||
return (a>='0' && a<='9');
|
||||
}
|
||||
|
||||
|
||||
|
||||
static const char *fts5ConfigSkipLiteral(const char *pIn){
|
||||
const char *p = pIn;
|
||||
switch( *p ){
|
||||
case 'n': case 'N':
|
||||
if( sqlite3_strnicmp("null", p, 4)==0 ){
|
||||
p = &p[4];
|
||||
}else{
|
||||
p = 0;
|
||||
}
|
||||
break;
|
||||
|
||||
case 'x': case 'X':
|
||||
p++;
|
||||
if( *p=='\'' ){
|
||||
p++;
|
||||
while( (*p>='a' && *p<='f')
|
||||
|| (*p>='A' && *p<='F')
|
||||
|| (*p>='0' && *p<='9')
|
||||
){
|
||||
p++;
|
||||
}
|
||||
if( *p=='\'' && 0==((p-pIn)%2) ){
|
||||
p++;
|
||||
}else{
|
||||
p = 0;
|
||||
}
|
||||
}else{
|
||||
p = 0;
|
||||
}
|
||||
break;
|
||||
|
||||
case '\'':
|
||||
p++;
|
||||
while( p ){
|
||||
if( *p=='\'' ){
|
||||
p++;
|
||||
if( *p!='\'' ) break;
|
||||
}
|
||||
p++;
|
||||
if( *p==0 ) p = 0;
|
||||
}
|
||||
break;
|
||||
|
||||
default:
|
||||
/* maybe a number */
|
||||
if( *p=='+' || *p=='-' ) p++;
|
||||
while( fts5_isdigit(*p) ) p++;
|
||||
|
||||
/* At this point, if the literal was an integer, the parse is
|
||||
** finished. Or, if it is a floating point value, it may continue
|
||||
** with either a decimal point or an 'E' character. */
|
||||
if( *p=='.' && fts5_isdigit(p[1]) ){
|
||||
p += 2;
|
||||
while( fts5_isdigit(*p) ) p++;
|
||||
}
|
||||
if( p==pIn ) p = 0;
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
return p;
|
||||
}
|
||||
|
||||
/*
|
||||
** The first character of the string pointed to by argument z is guaranteed
|
||||
** to be an open-quote character (see function fts5_isopenquote()).
|
||||
**
|
||||
** This function searches for the corresponding close-quote character within
|
||||
** the string and, if found, dequotes the string in place and adds a new
|
||||
** nul-terminator byte.
|
||||
**
|
||||
** If the close-quote is found, the value returned is the byte offset of
|
||||
** the character immediately following it. Or, if the close-quote is not
|
||||
** found, -1 is returned. If -1 is returned, the buffer is left in an
|
||||
** undefined state.
|
||||
*/
|
||||
static int fts5Dequote(char *z){
|
||||
char q;
|
||||
int iIn = 1;
|
||||
int iOut = 0;
|
||||
q = z[0];
|
||||
|
||||
/* Set stack variable q to the close-quote character */
|
||||
assert( q=='[' || q=='\'' || q=='"' || q=='`' );
|
||||
if( q=='[' ) q = ']';
|
||||
|
||||
while( ALWAYS(z[iIn]) ){
|
||||
if( z[iIn]==q ){
|
||||
if( z[iIn+1]!=q ){
|
||||
/* Character iIn was the close quote. */
|
||||
iIn++;
|
||||
break;
|
||||
}else{
|
||||
/* Character iIn and iIn+1 form an escaped quote character. Skip
|
||||
** the input cursor past both and copy a single quote character
|
||||
** to the output buffer. */
|
||||
iIn += 2;
|
||||
z[iOut++] = q;
|
||||
}
|
||||
}else{
|
||||
z[iOut++] = z[iIn++];
|
||||
}
|
||||
}
|
||||
|
||||
z[iOut] = '\0';
|
||||
return iIn;
|
||||
}
|
||||
|
||||
/*
|
||||
** Convert an SQL-style quoted string into a normal string by removing
|
||||
** the quote characters. The conversion is done in-place. If the
|
||||
** input does not begin with a quote character, then this routine
|
||||
** is a no-op.
|
||||
**
|
||||
** Examples:
|
||||
**
|
||||
** "abc" becomes abc
|
||||
** 'xyz' becomes xyz
|
||||
** [pqr] becomes pqr
|
||||
** `mno` becomes mno
|
||||
*/
|
||||
void sqlite3Fts5Dequote(char *z){
|
||||
char quote; /* Quote character (if any ) */
|
||||
|
||||
assert( 0==fts5_iswhitespace(z[0]) );
|
||||
quote = z[0];
|
||||
if( quote=='[' || quote=='\'' || quote=='"' || quote=='`' ){
|
||||
fts5Dequote(z);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
struct Fts5Enum {
|
||||
const char *zName;
|
||||
int eVal;
|
||||
};
|
||||
typedef struct Fts5Enum Fts5Enum;
|
||||
|
||||
static int fts5ConfigSetEnum(
|
||||
const Fts5Enum *aEnum,
|
||||
const char *zEnum,
|
||||
int *peVal
|
||||
){
|
||||
int nEnum = (int)strlen(zEnum);
|
||||
int i;
|
||||
int iVal = -1;
|
||||
|
||||
for(i=0; aEnum[i].zName; i++){
|
||||
if( sqlite3_strnicmp(aEnum[i].zName, zEnum, nEnum)==0 ){
|
||||
if( iVal>=0 ) return SQLITE_ERROR;
|
||||
iVal = aEnum[i].eVal;
|
||||
}
|
||||
}
|
||||
|
||||
*peVal = iVal;
|
||||
return iVal<0 ? SQLITE_ERROR : SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Parse a "special" CREATE VIRTUAL TABLE directive and update
|
||||
** configuration object pConfig as appropriate.
|
||||
**
|
||||
** If successful, object pConfig is updated and SQLITE_OK returned. If
|
||||
** an error occurs, an SQLite error code is returned and an error message
|
||||
** may be left in *pzErr. It is the responsibility of the caller to
|
||||
** eventually free any such error message using sqlite3_free().
|
||||
*/
|
||||
static int fts5ConfigParseSpecial(
|
||||
Fts5Global *pGlobal,
|
||||
Fts5Config *pConfig, /* Configuration object to update */
|
||||
const char *zCmd, /* Special command to parse */
|
||||
const char *zArg, /* Argument to parse */
|
||||
char **pzErr /* OUT: Error message */
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
int nCmd = (int)strlen(zCmd);
|
||||
if( sqlite3_strnicmp("prefix", zCmd, nCmd)==0 ){
|
||||
const int nByte = sizeof(int) * FTS5_MAX_PREFIX_INDEXES;
|
||||
const char *p;
|
||||
int bFirst = 1;
|
||||
if( pConfig->aPrefix==0 ){
|
||||
pConfig->aPrefix = sqlite3Fts5MallocZero(&rc, nByte);
|
||||
if( rc ) return rc;
|
||||
}
|
||||
|
||||
p = zArg;
|
||||
while( 1 ){
|
||||
int nPre = 0;
|
||||
|
||||
while( p[0]==' ' ) p++;
|
||||
if( bFirst==0 && p[0]==',' ){
|
||||
p++;
|
||||
while( p[0]==' ' ) p++;
|
||||
}else if( p[0]=='\0' ){
|
||||
break;
|
||||
}
|
||||
if( p[0]<'0' || p[0]>'9' ){
|
||||
*pzErr = sqlite3_mprintf("malformed prefix=... directive");
|
||||
rc = SQLITE_ERROR;
|
||||
break;
|
||||
}
|
||||
|
||||
if( pConfig->nPrefix==FTS5_MAX_PREFIX_INDEXES ){
|
||||
*pzErr = sqlite3_mprintf(
|
||||
"too many prefix indexes (max %d)", FTS5_MAX_PREFIX_INDEXES
|
||||
);
|
||||
rc = SQLITE_ERROR;
|
||||
break;
|
||||
}
|
||||
|
||||
while( p[0]>='0' && p[0]<='9' && nPre<1000 ){
|
||||
nPre = nPre*10 + (p[0] - '0');
|
||||
p++;
|
||||
}
|
||||
|
||||
if( nPre<=0 || nPre>=1000 ){
|
||||
*pzErr = sqlite3_mprintf("prefix length out of range (max 999)");
|
||||
rc = SQLITE_ERROR;
|
||||
break;
|
||||
}
|
||||
|
||||
pConfig->aPrefix[pConfig->nPrefix] = nPre;
|
||||
pConfig->nPrefix++;
|
||||
bFirst = 0;
|
||||
}
|
||||
assert( pConfig->nPrefix<=FTS5_MAX_PREFIX_INDEXES );
|
||||
return rc;
|
||||
}
|
||||
|
||||
if( sqlite3_strnicmp("tokenize", zCmd, nCmd)==0 ){
|
||||
const char *p = (const char*)zArg;
|
||||
sqlite3_int64 nArg = strlen(zArg) + 1;
|
||||
char **azArg = sqlite3Fts5MallocZero(&rc, sizeof(char*) * nArg);
|
||||
char *pDel = sqlite3Fts5MallocZero(&rc, nArg * 2);
|
||||
char *pSpace = pDel;
|
||||
|
||||
if( azArg && pSpace ){
|
||||
if( pConfig->pTok ){
|
||||
*pzErr = sqlite3_mprintf("multiple tokenize=... directives");
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
for(nArg=0; p && *p; nArg++){
|
||||
const char *p2 = fts5ConfigSkipWhitespace(p);
|
||||
if( *p2=='\'' ){
|
||||
p = fts5ConfigSkipLiteral(p2);
|
||||
}else{
|
||||
p = fts5ConfigSkipBareword(p2);
|
||||
}
|
||||
if( p ){
|
||||
memcpy(pSpace, p2, p-p2);
|
||||
azArg[nArg] = pSpace;
|
||||
sqlite3Fts5Dequote(pSpace);
|
||||
pSpace += (p - p2) + 1;
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
}
|
||||
}
|
||||
if( p==0 ){
|
||||
*pzErr = sqlite3_mprintf("parse error in tokenize directive");
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
rc = sqlite3Fts5GetTokenizer(pGlobal,
|
||||
(const char**)azArg, nArg, &pConfig->pTok, &pConfig->pTokApi,
|
||||
pzErr
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_free(azArg);
|
||||
sqlite3_free(pDel);
|
||||
return rc;
|
||||
}
|
||||
|
||||
if( sqlite3_strnicmp("content", zCmd, nCmd)==0 ){
|
||||
if( pConfig->eContent!=FTS5_CONTENT_NORMAL ){
|
||||
*pzErr = sqlite3_mprintf("multiple content=... directives");
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
if( zArg[0] ){
|
||||
pConfig->eContent = FTS5_CONTENT_EXTERNAL;
|
||||
pConfig->zContent = sqlite3Fts5Mprintf(&rc, "%Q.%Q", pConfig->zDb,zArg);
|
||||
}else{
|
||||
pConfig->eContent = FTS5_CONTENT_NONE;
|
||||
}
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
if( sqlite3_strnicmp("content_rowid", zCmd, nCmd)==0 ){
|
||||
if( pConfig->zContentRowid ){
|
||||
*pzErr = sqlite3_mprintf("multiple content_rowid=... directives");
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
pConfig->zContentRowid = sqlite3Fts5Strndup(&rc, zArg, -1);
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
if( sqlite3_strnicmp("columnsize", zCmd, nCmd)==0 ){
|
||||
if( (zArg[0]!='0' && zArg[0]!='1') || zArg[1]!='\0' ){
|
||||
*pzErr = sqlite3_mprintf("malformed columnsize=... directive");
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
pConfig->bColumnsize = (zArg[0]=='1');
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
if( sqlite3_strnicmp("detail", zCmd, nCmd)==0 ){
|
||||
const Fts5Enum aDetail[] = {
|
||||
{ "none", FTS5_DETAIL_NONE },
|
||||
{ "full", FTS5_DETAIL_FULL },
|
||||
{ "columns", FTS5_DETAIL_COLUMNS },
|
||||
{ 0, 0 }
|
||||
};
|
||||
|
||||
if( (rc = fts5ConfigSetEnum(aDetail, zArg, &pConfig->eDetail)) ){
|
||||
*pzErr = sqlite3_mprintf("malformed detail=... directive");
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
*pzErr = sqlite3_mprintf("unrecognized option: \"%.*s\"", nCmd, zCmd);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
/*
|
||||
** Allocate an instance of the default tokenizer ("simple") at
|
||||
** Fts5Config.pTokenizer. Return SQLITE_OK if successful, or an SQLite error
|
||||
** code if an error occurs.
|
||||
*/
|
||||
static int fts5ConfigDefaultTokenizer(Fts5Global *pGlobal, Fts5Config *pConfig){
|
||||
assert( pConfig->pTok==0 && pConfig->pTokApi==0 );
|
||||
return sqlite3Fts5GetTokenizer(
|
||||
pGlobal, 0, 0, &pConfig->pTok, &pConfig->pTokApi, 0
|
||||
);
|
||||
}
|
||||
|
||||
/*
|
||||
** Gobble up the first bareword or quoted word from the input buffer zIn.
|
||||
** Return a pointer to the character immediately following the last in
|
||||
** the gobbled word if successful, or a NULL pointer otherwise (failed
|
||||
** to find close-quote character).
|
||||
**
|
||||
** Before returning, set pzOut to point to a new buffer containing a
|
||||
** nul-terminated, dequoted copy of the gobbled word. If the word was
|
||||
** quoted, *pbQuoted is also set to 1 before returning.
|
||||
**
|
||||
** If *pRc is other than SQLITE_OK when this function is called, it is
|
||||
** a no-op (NULL is returned). Otherwise, if an OOM occurs within this
|
||||
** function, *pRc is set to SQLITE_NOMEM before returning. *pRc is *not*
|
||||
** set if a parse error (failed to find close quote) occurs.
|
||||
*/
|
||||
static const char *fts5ConfigGobbleWord(
|
||||
int *pRc, /* IN/OUT: Error code */
|
||||
const char *zIn, /* Buffer to gobble string/bareword from */
|
||||
char **pzOut, /* OUT: malloc'd buffer containing str/bw */
|
||||
int *pbQuoted /* OUT: Set to true if dequoting required */
|
||||
){
|
||||
const char *zRet = 0;
|
||||
|
||||
sqlite3_int64 nIn = strlen(zIn);
|
||||
char *zOut = sqlite3_malloc64(nIn+1);
|
||||
|
||||
assert( *pRc==SQLITE_OK );
|
||||
*pbQuoted = 0;
|
||||
*pzOut = 0;
|
||||
|
||||
if( zOut==0 ){
|
||||
*pRc = SQLITE_NOMEM;
|
||||
}else{
|
||||
memcpy(zOut, zIn, nIn+1);
|
||||
if( fts5_isopenquote(zOut[0]) ){
|
||||
int ii = fts5Dequote(zOut);
|
||||
zRet = &zIn[ii];
|
||||
*pbQuoted = 1;
|
||||
}else{
|
||||
zRet = fts5ConfigSkipBareword(zIn);
|
||||
if( zRet ){
|
||||
zOut[zRet-zIn] = '\0';
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( zRet==0 ){
|
||||
sqlite3_free(zOut);
|
||||
}else{
|
||||
*pzOut = zOut;
|
||||
}
|
||||
|
||||
return zRet;
|
||||
}
|
||||
|
||||
static int fts5ConfigParseColumn(
|
||||
Fts5Config *p,
|
||||
char *zCol,
|
||||
char *zArg,
|
||||
char **pzErr
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
if( 0==sqlite3_stricmp(zCol, FTS5_RANK_NAME)
|
||||
|| 0==sqlite3_stricmp(zCol, FTS5_ROWID_NAME)
|
||||
){
|
||||
*pzErr = sqlite3_mprintf("reserved fts5 column name: %s", zCol);
|
||||
rc = SQLITE_ERROR;
|
||||
}else if( zArg ){
|
||||
if( 0==sqlite3_stricmp(zArg, "unindexed") ){
|
||||
p->abUnindexed[p->nCol] = 1;
|
||||
}else{
|
||||
*pzErr = sqlite3_mprintf("unrecognized column option: %s", zArg);
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
}
|
||||
|
||||
p->azCol[p->nCol++] = zCol;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Populate the Fts5Config.zContentExprlist string.
|
||||
*/
|
||||
static int fts5ConfigMakeExprlist(Fts5Config *p){
|
||||
int i;
|
||||
int rc = SQLITE_OK;
|
||||
Fts5Buffer buf = {0, 0, 0};
|
||||
|
||||
sqlite3Fts5BufferAppendPrintf(&rc, &buf, "T.%Q", p->zContentRowid);
|
||||
if( p->eContent!=FTS5_CONTENT_NONE ){
|
||||
for(i=0; i<p->nCol; i++){
|
||||
if( p->eContent==FTS5_CONTENT_EXTERNAL ){
|
||||
sqlite3Fts5BufferAppendPrintf(&rc, &buf, ", T.%Q", p->azCol[i]);
|
||||
}else{
|
||||
sqlite3Fts5BufferAppendPrintf(&rc, &buf, ", T.c%d", i);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
assert( p->zContentExprlist==0 );
|
||||
p->zContentExprlist = (char*)buf.p;
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Arguments nArg/azArg contain the string arguments passed to the xCreate
|
||||
** or xConnect method of the virtual table. This function attempts to
|
||||
** allocate an instance of Fts5Config containing the results of parsing
|
||||
** those arguments.
|
||||
**
|
||||
** If successful, SQLITE_OK is returned and *ppOut is set to point to the
|
||||
** new Fts5Config object. If an error occurs, an SQLite error code is
|
||||
** returned, *ppOut is set to NULL and an error message may be left in
|
||||
** *pzErr. It is the responsibility of the caller to eventually free any
|
||||
** such error message using sqlite3_free().
|
||||
*/
|
||||
int sqlite3Fts5ConfigParse(
|
||||
Fts5Global *pGlobal,
|
||||
sqlite3 *db,
|
||||
int nArg, /* Number of arguments */
|
||||
const char **azArg, /* Array of nArg CREATE VIRTUAL TABLE args */
|
||||
Fts5Config **ppOut, /* OUT: Results of parse */
|
||||
char **pzErr /* OUT: Error message */
|
||||
){
|
||||
int rc = SQLITE_OK; /* Return code */
|
||||
Fts5Config *pRet; /* New object to return */
|
||||
int i;
|
||||
sqlite3_int64 nByte;
|
||||
|
||||
*ppOut = pRet = (Fts5Config*)sqlite3_malloc(sizeof(Fts5Config));
|
||||
if( pRet==0 ) return SQLITE_NOMEM;
|
||||
memset(pRet, 0, sizeof(Fts5Config));
|
||||
pRet->db = db;
|
||||
pRet->iCookie = -1;
|
||||
|
||||
nByte = nArg * (sizeof(char*) + sizeof(u8));
|
||||
pRet->azCol = (char**)sqlite3Fts5MallocZero(&rc, nByte);
|
||||
pRet->abUnindexed = (u8*)&pRet->azCol[nArg];
|
||||
pRet->zDb = sqlite3Fts5Strndup(&rc, azArg[1], -1);
|
||||
pRet->zName = sqlite3Fts5Strndup(&rc, azArg[2], -1);
|
||||
pRet->bColumnsize = 1;
|
||||
pRet->eDetail = FTS5_DETAIL_FULL;
|
||||
#ifdef SQLITE_DEBUG
|
||||
pRet->bPrefixIndex = 1;
|
||||
#endif
|
||||
if( rc==SQLITE_OK && sqlite3_stricmp(pRet->zName, FTS5_RANK_NAME)==0 ){
|
||||
*pzErr = sqlite3_mprintf("reserved fts5 table name: %s", pRet->zName);
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
|
||||
for(i=3; rc==SQLITE_OK && i<nArg; i++){
|
||||
const char *zOrig = azArg[i];
|
||||
const char *z;
|
||||
char *zOne = 0;
|
||||
char *zTwo = 0;
|
||||
int bOption = 0;
|
||||
int bMustBeCol = 0;
|
||||
|
||||
z = fts5ConfigGobbleWord(&rc, zOrig, &zOne, &bMustBeCol);
|
||||
z = fts5ConfigSkipWhitespace(z);
|
||||
if( z && *z=='=' ){
|
||||
bOption = 1;
|
||||
z++;
|
||||
if( bMustBeCol ) z = 0;
|
||||
}
|
||||
z = fts5ConfigSkipWhitespace(z);
|
||||
if( z && z[0] ){
|
||||
int bDummy;
|
||||
z = fts5ConfigGobbleWord(&rc, z, &zTwo, &bDummy);
|
||||
if( z && z[0] ) z = 0;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
if( z==0 ){
|
||||
*pzErr = sqlite3_mprintf("parse error in \"%s\"", zOrig);
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
if( bOption ){
|
||||
rc = fts5ConfigParseSpecial(pGlobal, pRet, zOne, zTwo?zTwo:"", pzErr);
|
||||
}else{
|
||||
rc = fts5ConfigParseColumn(pRet, zOne, zTwo, pzErr);
|
||||
zOne = 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_free(zOne);
|
||||
sqlite3_free(zTwo);
|
||||
}
|
||||
|
||||
/* If a tokenizer= option was successfully parsed, the tokenizer has
|
||||
** already been allocated. Otherwise, allocate an instance of the default
|
||||
** tokenizer (unicode61) now. */
|
||||
if( rc==SQLITE_OK && pRet->pTok==0 ){
|
||||
rc = fts5ConfigDefaultTokenizer(pGlobal, pRet);
|
||||
}
|
||||
|
||||
/* If no zContent option was specified, fill in the default values. */
|
||||
if( rc==SQLITE_OK && pRet->zContent==0 ){
|
||||
const char *zTail = 0;
|
||||
assert( pRet->eContent==FTS5_CONTENT_NORMAL
|
||||
|| pRet->eContent==FTS5_CONTENT_NONE
|
||||
);
|
||||
if( pRet->eContent==FTS5_CONTENT_NORMAL ){
|
||||
zTail = "content";
|
||||
}else if( pRet->bColumnsize ){
|
||||
zTail = "docsize";
|
||||
}
|
||||
|
||||
if( zTail ){
|
||||
pRet->zContent = sqlite3Fts5Mprintf(
|
||||
&rc, "%Q.'%q_%s'", pRet->zDb, pRet->zName, zTail
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK && pRet->zContentRowid==0 ){
|
||||
pRet->zContentRowid = sqlite3Fts5Strndup(&rc, "rowid", -1);
|
||||
}
|
||||
|
||||
/* Formulate the zContentExprlist text */
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts5ConfigMakeExprlist(pRet);
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3Fts5ConfigFree(pRet);
|
||||
*ppOut = 0;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Free the configuration object passed as the only argument.
|
||||
*/
|
||||
void sqlite3Fts5ConfigFree(Fts5Config *pConfig){
|
||||
if( pConfig ){
|
||||
int i;
|
||||
if( pConfig->pTok ){
|
||||
pConfig->pTokApi->xDelete(pConfig->pTok);
|
||||
}
|
||||
sqlite3_free(pConfig->zDb);
|
||||
sqlite3_free(pConfig->zName);
|
||||
for(i=0; i<pConfig->nCol; i++){
|
||||
sqlite3_free(pConfig->azCol[i]);
|
||||
}
|
||||
sqlite3_free(pConfig->azCol);
|
||||
sqlite3_free(pConfig->aPrefix);
|
||||
sqlite3_free(pConfig->zRank);
|
||||
sqlite3_free(pConfig->zRankArgs);
|
||||
sqlite3_free(pConfig->zContent);
|
||||
sqlite3_free(pConfig->zContentRowid);
|
||||
sqlite3_free(pConfig->zContentExprlist);
|
||||
sqlite3_free(pConfig);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Call sqlite3_declare_vtab() based on the contents of the configuration
|
||||
** object passed as the only argument. Return SQLITE_OK if successful, or
|
||||
** an SQLite error code if an error occurs.
|
||||
*/
|
||||
int sqlite3Fts5ConfigDeclareVtab(Fts5Config *pConfig){
|
||||
int i;
|
||||
int rc = SQLITE_OK;
|
||||
char *zSql;
|
||||
|
||||
zSql = sqlite3Fts5Mprintf(&rc, "CREATE TABLE x(");
|
||||
for(i=0; zSql && i<pConfig->nCol; i++){
|
||||
const char *zSep = (i==0?"":", ");
|
||||
zSql = sqlite3Fts5Mprintf(&rc, "%z%s%Q", zSql, zSep, pConfig->azCol[i]);
|
||||
}
|
||||
zSql = sqlite3Fts5Mprintf(&rc, "%z, %Q HIDDEN, %s HIDDEN)",
|
||||
zSql, pConfig->zName, FTS5_RANK_NAME
|
||||
);
|
||||
|
||||
assert( zSql || rc==SQLITE_NOMEM );
|
||||
if( zSql ){
|
||||
rc = sqlite3_declare_vtab(pConfig->db, zSql);
|
||||
sqlite3_free(zSql);
|
||||
}
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Tokenize the text passed via the second and third arguments.
|
||||
**
|
||||
** The callback is invoked once for each token in the input text. The
|
||||
** arguments passed to it are, in order:
|
||||
**
|
||||
** void *pCtx // Copy of 4th argument to sqlite3Fts5Tokenize()
|
||||
** const char *pToken // Pointer to buffer containing token
|
||||
** int nToken // Size of token in bytes
|
||||
** int iStart // Byte offset of start of token within input text
|
||||
** int iEnd // Byte offset of end of token within input text
|
||||
** int iPos // Position of token in input (first token is 0)
|
||||
**
|
||||
** If the callback returns a non-zero value the tokenization is abandoned
|
||||
** and no further callbacks are issued.
|
||||
**
|
||||
** This function returns SQLITE_OK if successful or an SQLite error code
|
||||
** if an error occurs. If the tokenization was abandoned early because
|
||||
** the callback returned SQLITE_DONE, this is not an error and this function
|
||||
** still returns SQLITE_OK. Or, if the tokenization was abandoned early
|
||||
** because the callback returned another non-zero value, it is assumed
|
||||
** to be an SQLite error code and returned to the caller.
|
||||
*/
|
||||
int sqlite3Fts5Tokenize(
|
||||
Fts5Config *pConfig, /* FTS5 Configuration object */
|
||||
int flags, /* FTS5_TOKENIZE_* flags */
|
||||
const char *pText, int nText, /* Text to tokenize */
|
||||
void *pCtx, /* Context passed to xToken() */
|
||||
int (*xToken)(void*, int, const char*, int, int, int) /* Callback */
|
||||
){
|
||||
if( pText==0 ) return SQLITE_OK;
|
||||
return pConfig->pTokApi->xTokenize(
|
||||
pConfig->pTok, pCtx, flags, pText, nText, xToken
|
||||
);
|
||||
}
|
||||
|
||||
/*
|
||||
** Argument pIn points to the first character in what is expected to be
|
||||
** a comma-separated list of SQL literals followed by a ')' character.
|
||||
** If it actually is this, return a pointer to the ')'. Otherwise, return
|
||||
** NULL to indicate a parse error.
|
||||
*/
|
||||
static const char *fts5ConfigSkipArgs(const char *pIn){
|
||||
const char *p = pIn;
|
||||
|
||||
while( 1 ){
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
p = fts5ConfigSkipLiteral(p);
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
if( p==0 || *p==')' ) break;
|
||||
if( *p!=',' ){
|
||||
p = 0;
|
||||
break;
|
||||
}
|
||||
p++;
|
||||
}
|
||||
|
||||
return p;
|
||||
}
|
||||
|
||||
/*
|
||||
** Parameter zIn contains a rank() function specification. The format of
|
||||
** this is:
|
||||
**
|
||||
** + Bareword (function name)
|
||||
** + Open parenthesis - "("
|
||||
** + Zero or more SQL literals in a comma separated list
|
||||
** + Close parenthesis - ")"
|
||||
*/
|
||||
int sqlite3Fts5ConfigParseRank(
|
||||
const char *zIn, /* Input string */
|
||||
char **pzRank, /* OUT: Rank function name */
|
||||
char **pzRankArgs /* OUT: Rank function arguments */
|
||||
){
|
||||
const char *p = zIn;
|
||||
const char *pRank;
|
||||
char *zRank = 0;
|
||||
char *zRankArgs = 0;
|
||||
int rc = SQLITE_OK;
|
||||
|
||||
*pzRank = 0;
|
||||
*pzRankArgs = 0;
|
||||
|
||||
if( p==0 ){
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
pRank = p;
|
||||
p = fts5ConfigSkipBareword(p);
|
||||
|
||||
if( p ){
|
||||
zRank = sqlite3Fts5MallocZero(&rc, 1 + p - pRank);
|
||||
if( zRank ) memcpy(zRank, pRank, p-pRank);
|
||||
}else{
|
||||
rc = SQLITE_ERROR;
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
if( *p!='(' ) rc = SQLITE_ERROR;
|
||||
p++;
|
||||
}
|
||||
if( rc==SQLITE_OK ){
|
||||
const char *pArgs;
|
||||
p = fts5ConfigSkipWhitespace(p);
|
||||
pArgs = p;
|
||||
if( *p!=')' ){
|
||||
p = fts5ConfigSkipArgs(p);
|
||||
if( p==0 ){
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
zRankArgs = sqlite3Fts5MallocZero(&rc, 1 + p - pArgs);
|
||||
if( zRankArgs ) memcpy(zRankArgs, pArgs, p-pArgs);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if( rc!=SQLITE_OK ){
|
||||
sqlite3_free(zRank);
|
||||
assert( zRankArgs==0 );
|
||||
}else{
|
||||
*pzRank = zRank;
|
||||
*pzRankArgs = zRankArgs;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
int sqlite3Fts5ConfigSetValue(
|
||||
Fts5Config *pConfig,
|
||||
const char *zKey,
|
||||
sqlite3_value *pVal,
|
||||
int *pbBadkey
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
|
||||
if( 0==sqlite3_stricmp(zKey, "pgsz") ){
|
||||
int pgsz = 0;
|
||||
if( SQLITE_INTEGER==sqlite3_value_numeric_type(pVal) ){
|
||||
pgsz = sqlite3_value_int(pVal);
|
||||
}
|
||||
if( pgsz<=0 || pgsz>FTS5_MAX_PAGE_SIZE ){
|
||||
*pbBadkey = 1;
|
||||
}else{
|
||||
pConfig->pgsz = pgsz;
|
||||
}
|
||||
}
|
||||
|
||||
else if( 0==sqlite3_stricmp(zKey, "hashsize") ){
|
||||
int nHashSize = -1;
|
||||
if( SQLITE_INTEGER==sqlite3_value_numeric_type(pVal) ){
|
||||
nHashSize = sqlite3_value_int(pVal);
|
||||
}
|
||||
if( nHashSize<=0 ){
|
||||
*pbBadkey = 1;
|
||||
}else{
|
||||
pConfig->nHashSize = nHashSize;
|
||||
}
|
||||
}
|
||||
|
||||
else if( 0==sqlite3_stricmp(zKey, "automerge") ){
|
||||
int nAutomerge = -1;
|
||||
if( SQLITE_INTEGER==sqlite3_value_numeric_type(pVal) ){
|
||||
nAutomerge = sqlite3_value_int(pVal);
|
||||
}
|
||||
if( nAutomerge<0 || nAutomerge>64 ){
|
||||
*pbBadkey = 1;
|
||||
}else{
|
||||
if( nAutomerge==1 ) nAutomerge = FTS5_DEFAULT_AUTOMERGE;
|
||||
pConfig->nAutomerge = nAutomerge;
|
||||
}
|
||||
}
|
||||
|
||||
else if( 0==sqlite3_stricmp(zKey, "usermerge") ){
|
||||
int nUsermerge = -1;
|
||||
if( SQLITE_INTEGER==sqlite3_value_numeric_type(pVal) ){
|
||||
nUsermerge = sqlite3_value_int(pVal);
|
||||
}
|
||||
if( nUsermerge<2 || nUsermerge>16 ){
|
||||
*pbBadkey = 1;
|
||||
}else{
|
||||
pConfig->nUsermerge = nUsermerge;
|
||||
}
|
||||
}
|
||||
|
||||
else if( 0==sqlite3_stricmp(zKey, "crisismerge") ){
|
||||
int nCrisisMerge = -1;
|
||||
if( SQLITE_INTEGER==sqlite3_value_numeric_type(pVal) ){
|
||||
nCrisisMerge = sqlite3_value_int(pVal);
|
||||
}
|
||||
if( nCrisisMerge<0 ){
|
||||
*pbBadkey = 1;
|
||||
}else{
|
||||
if( nCrisisMerge<=1 ) nCrisisMerge = FTS5_DEFAULT_CRISISMERGE;
|
||||
pConfig->nCrisisMerge = nCrisisMerge;
|
||||
}
|
||||
}
|
||||
|
||||
else if( 0==sqlite3_stricmp(zKey, "rank") ){
|
||||
const char *zIn = (const char*)sqlite3_value_text(pVal);
|
||||
char *zRank;
|
||||
char *zRankArgs;
|
||||
rc = sqlite3Fts5ConfigParseRank(zIn, &zRank, &zRankArgs);
|
||||
if( rc==SQLITE_OK ){
|
||||
sqlite3_free(pConfig->zRank);
|
||||
sqlite3_free(pConfig->zRankArgs);
|
||||
pConfig->zRank = zRank;
|
||||
pConfig->zRankArgs = zRankArgs;
|
||||
}else if( rc==SQLITE_ERROR ){
|
||||
rc = SQLITE_OK;
|
||||
*pbBadkey = 1;
|
||||
}
|
||||
}else{
|
||||
*pbBadkey = 1;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Load the contents of the %_config table into memory.
|
||||
*/
|
||||
int sqlite3Fts5ConfigLoad(Fts5Config *pConfig, int iCookie){
|
||||
const char *zSelect = "SELECT k, v FROM %Q.'%q_config'";
|
||||
char *zSql;
|
||||
sqlite3_stmt *p = 0;
|
||||
int rc = SQLITE_OK;
|
||||
int iVersion = 0;
|
||||
|
||||
/* Set default values */
|
||||
pConfig->pgsz = FTS5_DEFAULT_PAGE_SIZE;
|
||||
pConfig->nAutomerge = FTS5_DEFAULT_AUTOMERGE;
|
||||
pConfig->nUsermerge = FTS5_DEFAULT_USERMERGE;
|
||||
pConfig->nCrisisMerge = FTS5_DEFAULT_CRISISMERGE;
|
||||
pConfig->nHashSize = FTS5_DEFAULT_HASHSIZE;
|
||||
|
||||
zSql = sqlite3Fts5Mprintf(&rc, zSelect, pConfig->zDb, pConfig->zName);
|
||||
if( zSql ){
|
||||
rc = sqlite3_prepare_v2(pConfig->db, zSql, -1, &p, 0);
|
||||
sqlite3_free(zSql);
|
||||
}
|
||||
|
||||
assert( rc==SQLITE_OK || p==0 );
|
||||
if( rc==SQLITE_OK ){
|
||||
while( SQLITE_ROW==sqlite3_step(p) ){
|
||||
const char *zK = (const char*)sqlite3_column_text(p, 0);
|
||||
sqlite3_value *pVal = sqlite3_column_value(p, 1);
|
||||
if( 0==sqlite3_stricmp(zK, "version") ){
|
||||
iVersion = sqlite3_value_int(pVal);
|
||||
}else{
|
||||
int bDummy = 0;
|
||||
sqlite3Fts5ConfigSetValue(pConfig, zK, pVal, &bDummy);
|
||||
}
|
||||
}
|
||||
rc = sqlite3_finalize(p);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK && iVersion!=FTS5_CURRENT_VERSION ){
|
||||
rc = SQLITE_ERROR;
|
||||
if( pConfig->pzErrmsg ){
|
||||
assert( 0==*pConfig->pzErrmsg );
|
||||
*pConfig->pzErrmsg = sqlite3_mprintf(
|
||||
"invalid fts5 file format (found %d, expected %d) - run 'rebuild'",
|
||||
iVersion, FTS5_CURRENT_VERSION
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ){
|
||||
pConfig->iCookie = iCookie;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user