Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 739aab893a | |||
| 6a42c8f368 | |||
| 523de6a830 |
@@ -1,138 +0,0 @@
|
||||
#!/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
|
||||
+361
-735
File diff suppressed because it is too large
Load Diff
+7
-23
@@ -41,11 +41,6 @@ THREADSAFE = -DTHREADSAFE=0
|
||||
#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.
|
||||
@@ -58,7 +53,6 @@ TLIBS =
|
||||
#OPTS = -DSQLITE_DEBUG=1
|
||||
#OPTS =
|
||||
OPTS = -DNDEBUG=1
|
||||
OPTS += -DHAVE_FDATASYNC=1
|
||||
|
||||
#### The suffix to add to executable files. ".exe" for windows.
|
||||
# Nothing for unix.
|
||||
@@ -83,31 +77,21 @@ AR = ar cr
|
||||
RANLIB = ranlib
|
||||
#RANLIB = /opt/mingw/bin/i386-mingw32-ranlib
|
||||
|
||||
MKSHLIB = gcc -shared
|
||||
SO = so
|
||||
SHPREFIX = lib
|
||||
# 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/8.4linux
|
||||
#TCL_FLAGS = -I/home/drh/tcltk/8.4win -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/8.4linux/libtcl8.4g.a -lm -ldl
|
||||
#LIBTCL = /home/drh/tcltk/8.4win/libtcl84s.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 =
|
||||
@@ -118,10 +102,10 @@ READLINE_FLAGS =
|
||||
LIBREADLINE =
|
||||
#LIBREADLINE = -static -lreadline -ltermcap
|
||||
|
||||
#### Which "awk" program provides nawk compatibilty
|
||||
#### Should the database engine assume text is coded as UTF-8 or iso8859?
|
||||
#
|
||||
# NAWK = nawk
|
||||
NAWK = awk
|
||||
# ENCODING = UTF8
|
||||
ENCODING = ISO8859
|
||||
|
||||
# You should not have to change anything below this line
|
||||
###############################################################################
|
||||
|
||||
-1512
File diff suppressed because it is too large
Load Diff
@@ -1,671 +0,0 @@
|
||||
#!/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_unix.o mutex_w32.o \
|
||||
notify.o opcodes.o os.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_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_setup.h \
|
||||
$(TOP)/src/os_unix.c \
|
||||
$(TOP)/src/os_win.c \
|
||||
$(TOP)/src/os_win.h \
|
||||
$(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_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/os_setup.h \
|
||||
$(TOP)/src/os_win.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
|
||||
|
||||
fulltestonly: testfixture$(EXE) sqlite3$(EXE)
|
||||
./testfixture$(EXE) $(TOP)/test/full.test
|
||||
|
||||
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 quota2a quota2b quota2c
|
||||
rm -rf tsrc target_source
|
||||
rm -f testloadext.dll libtestloadext.so
|
||||
rm -f sqlite3.c fts?amal.c tclsqlite3.c
|
||||
rm -f sqlite3rc.h
|
||||
rm -f shell.c sqlite3ext.h
|
||||
rm -f $(SHPREFIX)sqlite3.$(SO)
|
||||
@@ -0,0 +1,35 @@
|
||||
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 2.50 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 suite 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 configure script is unmaintained. (You
|
||||
can volunteer to take over maintenance of the configure script, if you want!)
|
||||
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.
|
||||
|
||||
Contacts:
|
||||
|
||||
http://www.sqlite.org/
|
||||
@@ -1,215 +0,0 @@
|
||||
<h1 align="center">SQLite Source Repository</h1>
|
||||
|
||||
This repository contains the complete source code for the SQLite database
|
||||
engine. Some test scripts are also include. However, many other test scripts
|
||||
and most of the documentation are managed separately.
|
||||
|
||||
## 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 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. The
|
||||
makefiles also require AWK.
|
||||
|
||||
## Source Code Tour
|
||||
|
||||
Most of the core source files are in the **src/** subdirectory. But
|
||||
src/ also contains files used to build the "testfixture" test harness;
|
||||
those file all begin with "test". And src/ contains the "shell.c" file
|
||||
which is the main program for the "sqlite3.exe" command-line shell and
|
||||
the "tclsqlite.c" file which implements the bindings to SQLite from the
|
||||
Tcl programming language. (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.
|
||||
There are other test suites for SQLite (see
|
||||
[How SQLite Is Tested](http://www.sqlite.org/testing.html))
|
||||
but those other test suites are
|
||||
in separate source repositories.
|
||||
|
||||
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 at tool/mksqlite3h.tcl does the conversion. The manifest.uuid
|
||||
file contains the SHA1 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 a
|
||||
template for generating its parser. A generic template is in tool/lempar.c,
|
||||
but SQLite uses a slightly modified template found in src/lempar.c.
|
||||
|
||||
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.awk
|
||||
AWK 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
|
||||
AWK script at ./mkopcodeh.awk does this scan and generates opcodes.h.
|
||||
A second AWK script, ./mkopcodec.awk, 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 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 100K 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 five other files
|
||||
named **sqlite3-1.c**, **sqlite3-2.c**, ..., **sqlite3-5.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/vdbe.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).
|
||||
|
||||
Unfortunately, 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 SQLite implementation.
|
||||
|
||||
Key files:
|
||||
|
||||
* **sqlite3.h** - 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.
|
||||
|
||||
* **parse.y** - This file describes the LALR(1) grammer that SQLite uses
|
||||
to parse SQL statements, and the actions that are taken at each stop
|
||||
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 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.
|
||||
|
||||
* **pager.c** - This file contains the "pager" implementation, the
|
||||
module that implements transactions.
|
||||
|
||||
* **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.
|
||||
|
||||
|
||||
## Contacts
|
||||
|
||||
The main SQLite webpage is [http://www.sqlite.org/](http://www.sqlite.org/)
|
||||
with geographically distributed backup servers at
|
||||
[http://www2.sqlite.org/](http://www2.sqlite.org) and
|
||||
[http://www3.sqlite.org/](http://www3.sqlite.org).
|
||||
Vendored
+3703
-5762
File diff suppressed because it is too large
Load Diff
@@ -1,34 +0,0 @@
|
||||
#!/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", "UMINUS", ++max
|
||||
printf "#define TK_%-29s %4d\n", "UPLUS", ++max
|
||||
printf "#define TK_%-29s %4d\n", "REGISTER", ++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.
-5333
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 2.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 79 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.
|
||||
|
||||
@@ -1,19 +0,0 @@
|
||||
|
||||
AM_CFLAGS = @THREADSAFE_FLAGS@ @DYNAMIC_EXTENSION_FLAGS@ -DSQLITE_ENABLE_FTS3 -DSQLITE_ENABLE_RTREE
|
||||
|
||||
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
|
||||
sqlite3_LDADD = $(top_builddir)/libsqlite3.la @READLINE_LIBS@
|
||||
sqlite3_DEPENDENCIES = $(top_builddir)/libsqlite3.la
|
||||
|
||||
include_HEADERS = sqlite3.h sqlite3ext.h
|
||||
|
||||
EXTRA_DIST = sqlite3.1 tea
|
||||
pkgconfigdir = ${libdir}/pkgconfig
|
||||
pkgconfig_DATA = sqlite3.pc
|
||||
|
||||
man_MANS = sqlite3.1
|
||||
@@ -1,32 +0,0 @@
|
||||
|
||||
This package contains:
|
||||
|
||||
* the SQLite library amalgamation (single file) source code distribution,
|
||||
* the shell.c file used to build the sqlite3 shell too, and
|
||||
* the sqlite3.h and sqlite3ext.h header files required to link programs
|
||||
and sqlite extensions against the installed libary.
|
||||
* autoconf/automake installation infrastucture.
|
||||
|
||||
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_OMIT_TRIGGERS" ./configure
|
||||
|
||||
@@ -1,57 +0,0 @@
|
||||
|
||||
This file describes how to use the files in this directory to create a new
|
||||
version of the "autoconf-amalgamation" package.
|
||||
|
||||
1. The following files should have executable permission:
|
||||
|
||||
chmod 755 install-sh
|
||||
chmod 755 missing
|
||||
chmod 755 depcomp
|
||||
chmod 755 config.sub
|
||||
chmod 755 config.guess
|
||||
|
||||
2. Copy new versions of the following SQLite files into this directory:
|
||||
|
||||
sqlite3.c
|
||||
sqlite3.h
|
||||
sqlite3ext.h
|
||||
sqlite3.1
|
||||
sqlite3.pc.in
|
||||
shell.c
|
||||
|
||||
3. Update the SQLite version number in the AC_INIT macro in file
|
||||
configure.ac:
|
||||
|
||||
AC_INIT(sqlite, 3.6.3, http://www.sqlite.org)
|
||||
|
||||
4. Run the following commands to push the version number change through
|
||||
to the generated files.
|
||||
|
||||
aclocal
|
||||
autoconf
|
||||
automake
|
||||
|
||||
5. Create the tclsqlite3.c file in the tea/generic directory. As follows:
|
||||
|
||||
mkdir -p tea/generic
|
||||
echo "#ifdef USE_SYSTEM_SQLITE" > tea/generic/tclsqlite3.c
|
||||
echo "# include <sqlite3.h>" >> tea/generic/tclsqlite3.c
|
||||
echo "#else" >> tea/generic/tclsqlite3.c
|
||||
echo "#include \"../../sqlite3.c\"" >> tea/generic/tclsqlite3.c
|
||||
echo "#endif" >> tea/generic/tclsqlite3.c
|
||||
cat ../src/tclsqlite.c >> tea/generic/tclsqlite3.c
|
||||
|
||||
6. Update the SQLite version in the AC_INIT macro in file tea/configure.in:
|
||||
|
||||
AC_INIT([sqlite], [3.6.3])
|
||||
|
||||
7. From the 'tea' directory, run the following commands:
|
||||
|
||||
autoconf
|
||||
rm -rf autom4te.cache
|
||||
|
||||
8. Run "./configure && make dist". This builds a distribution package
|
||||
named something like "sqlite-3.6.3.tar.gz". Rename to
|
||||
"sqlite-amalgamation-3.6.3.tar.gz" and use.
|
||||
|
||||
|
||||
Vendored
-1530
File diff suppressed because it is too large
Load Diff
Vendored
-1773
File diff suppressed because it is too large
Load Diff
@@ -1,108 +0,0 @@
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Supports the following non-standard switches.
|
||||
#
|
||||
# --enable-threadsafe
|
||||
# --enable-readline
|
||||
# --enable-dynamic-extensions
|
||||
#
|
||||
|
||||
AC_PREREQ(2.61)
|
||||
AC_INIT(sqlite, 3.7.5, http://www.sqlite.org)
|
||||
AC_CONFIG_SRCDIR([sqlite3.c])
|
||||
|
||||
# Use automake.
|
||||
AM_INIT_AUTOMAKE([foreign])
|
||||
|
||||
AC_SYS_LARGEFILE
|
||||
|
||||
# Check for required programs.
|
||||
AC_PROG_CC
|
||||
AC_PROG_RANLIB
|
||||
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])
|
||||
AC_SUBST(BUILD_CFLAGS)
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-readline
|
||||
#
|
||||
AC_ARG_ENABLE(readline, [AS_HELP_STRING(
|
||||
[--enable-readline],
|
||||
[use readline in shell tool (yes, no) [default=yes]])],
|
||||
[], [enable_readline=yes])
|
||||
if test x"$enable_readline" != xno ; then
|
||||
sLIBS=$LIBS
|
||||
LIBS=""
|
||||
AC_SEARCH_LIBS(tgetent, curses ncurses ncursesw, [], [])
|
||||
AC_SEARCH_LIBS(readline, readline, [], [enable_readline=no])
|
||||
AC_CHECK_FUNCS(readline, [], [])
|
||||
READLINE_LIBS=$LIBS
|
||||
LIBS=$sLIBS
|
||||
fi
|
||||
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])
|
||||
THREADSAFE_FLAGS=-DSQLITE_THREADSAFE=0
|
||||
if test x"$enable_threadsafe" != "xno"; then
|
||||
THREADSAFE_FLAGS="-D_REENTRANT=1 -DSQLITE_THREADSAFE=1"
|
||||
AC_SEARCH_LIBS(pthread_create, pthread)
|
||||
fi
|
||||
AC_SUBST(THREADSAFE_FLAGS)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# --enable-dynamic-extensions
|
||||
#
|
||||
AC_ARG_ENABLE(dynamic-extensions, [AS_HELP_STRING(
|
||||
[--enable-dynamic-extensions], [support loadable extensions [default=yes]])],
|
||||
[], [enable_dynamic_extensions=yes])
|
||||
if test x"$enable_dynamic_extensions" != "xno"; then
|
||||
AC_SEARCH_LIBS(dlopen, dl)
|
||||
else
|
||||
DYNAMIC_EXTENSION_FLAGS=-DSQLITE_OMIT_LOAD_EXTENSION=1
|
||||
fi
|
||||
AC_MSG_CHECKING([for whether to support dynamic extensions])
|
||||
AC_MSG_RESULT($enable_dynamic_extensions)
|
||||
AC_SUBST(DYNAMIC_EXTENSION_FLAGS)
|
||||
#-----------------------------------------------------------------------
|
||||
|
||||
AC_CHECK_FUNCS(posix_fallocate)
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# UPDATE: Maybe it's better if users just set CFLAGS before invoking
|
||||
# configure. This option doesn't really add much...
|
||||
#
|
||||
# --enable-tempstore
|
||||
#
|
||||
# AC_ARG_ENABLE(tempstore, [AS_HELP_STRING(
|
||||
# [--enable-tempstore],
|
||||
# [in-memory temporary tables (never, no, yes, always) [default=no]])],
|
||||
# [], [enable_tempstore=no])
|
||||
# AC_MSG_CHECKING([for whether or not to store temp tables in-memory])
|
||||
# case "$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
|
||||
@@ -1,708 +0,0 @@
|
||||
#! /bin/sh
|
||||
# depcomp - compile a program generating dependencies as side-effects
|
||||
|
||||
scriptversion=2012-03-27.16; # UTC
|
||||
|
||||
# Copyright (C) 1999, 2000, 2003, 2004, 2005, 2006, 2007, 2009, 2010,
|
||||
# 2011, 2012 Free Software Foundation, Inc.
|
||||
|
||||
# This program is free software; you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation; either version 2, or (at your option)
|
||||
# any later version.
|
||||
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
# As a special exception to the GNU General Public License, if you
|
||||
# distribute this file as part of a program that contains a
|
||||
# configuration script generated by Autoconf, you may include it under
|
||||
# the same distribution terms that you use for the rest of that program.
|
||||
|
||||
# Originally written by Alexandre Oliva <oliva@dcc.unicamp.br>.
|
||||
|
||||
case $1 in
|
||||
'')
|
||||
echo "$0: No command. Try '$0 --help' for more information." 1>&2
|
||||
exit 1;
|
||||
;;
|
||||
-h | --h*)
|
||||
cat <<\EOF
|
||||
Usage: depcomp [--help] [--version] PROGRAM [ARGS]
|
||||
|
||||
Run PROGRAMS ARGS to compile a file, generating dependencies
|
||||
as side-effects.
|
||||
|
||||
Environment variables:
|
||||
depmode Dependency tracking mode.
|
||||
source Source file read by 'PROGRAMS ARGS'.
|
||||
object Object file output by 'PROGRAMS ARGS'.
|
||||
DEPDIR directory where to store dependencies.
|
||||
depfile Dependency file to output.
|
||||
tmpdepfile Temporary file to use when outputting dependencies.
|
||||
libtool Whether libtool is used (yes/no).
|
||||
|
||||
Report bugs to <bug-automake@gnu.org>.
|
||||
EOF
|
||||
exit $?
|
||||
;;
|
||||
-v | --v*)
|
||||
echo "depcomp $scriptversion"
|
||||
exit $?
|
||||
;;
|
||||
esac
|
||||
|
||||
# A tabulation character.
|
||||
tab=' '
|
||||
# A newline character.
|
||||
nl='
|
||||
'
|
||||
|
||||
if test -z "$depmode" || test -z "$source" || test -z "$object"; then
|
||||
echo "depcomp: Variables source, object and depmode must be set" 1>&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Dependencies for sub/bar.o or sub/bar.obj go into sub/.deps/bar.Po.
|
||||
depfile=${depfile-`echo "$object" |
|
||||
sed 's|[^\\/]*$|'${DEPDIR-.deps}'/&|;s|\.\([^.]*\)$|.P\1|;s|Pobj$|Po|'`}
|
||||
tmpdepfile=${tmpdepfile-`echo "$depfile" | sed 's/\.\([^.]*\)$/.T\1/'`}
|
||||
|
||||
rm -f "$tmpdepfile"
|
||||
|
||||
# Some modes work just like other modes, but use different flags. We
|
||||
# parameterize here, but still list the modes in the big case below,
|
||||
# to make depend.m4 easier to write. Note that we *cannot* use a case
|
||||
# here, because this file can only contain one case statement.
|
||||
if test "$depmode" = hp; then
|
||||
# HP compiler uses -M and no extra arg.
|
||||
gccflag=-M
|
||||
depmode=gcc
|
||||
fi
|
||||
|
||||
if test "$depmode" = dashXmstdout; then
|
||||
# This is just like dashmstdout with a different argument.
|
||||
dashmflag=-xM
|
||||
depmode=dashmstdout
|
||||
fi
|
||||
|
||||
cygpath_u="cygpath -u -f -"
|
||||
if test "$depmode" = msvcmsys; then
|
||||
# This is just like msvisualcpp but w/o cygpath translation.
|
||||
# Just convert the backslash-escaped backslashes to single forward
|
||||
# slashes to satisfy depend.m4
|
||||
cygpath_u='sed s,\\\\,/,g'
|
||||
depmode=msvisualcpp
|
||||
fi
|
||||
|
||||
if test "$depmode" = msvc7msys; then
|
||||
# This is just like msvc7 but w/o cygpath translation.
|
||||
# Just convert the backslash-escaped backslashes to single forward
|
||||
# slashes to satisfy depend.m4
|
||||
cygpath_u='sed s,\\\\,/,g'
|
||||
depmode=msvc7
|
||||
fi
|
||||
|
||||
if test "$depmode" = xlc; then
|
||||
# IBM C/C++ Compilers xlc/xlC can output gcc-like dependency informations.
|
||||
gccflag=-qmakedep=gcc,-MF
|
||||
depmode=gcc
|
||||
fi
|
||||
|
||||
case "$depmode" in
|
||||
gcc3)
|
||||
## gcc 3 implements dependency tracking that does exactly what
|
||||
## we want. Yay! Note: for some reason libtool 1.4 doesn't like
|
||||
## it if -MD -MP comes after the -MF stuff. Hmm.
|
||||
## Unfortunately, FreeBSD c89 acceptance of flags depends upon
|
||||
## the command line argument order; so add the flags where they
|
||||
## appear in depend2.am. Note that the slowdown incurred here
|
||||
## affects only configure: in makefiles, %FASTDEP% shortcuts this.
|
||||
for arg
|
||||
do
|
||||
case $arg in
|
||||
-c) set fnord "$@" -MT "$object" -MD -MP -MF "$tmpdepfile" "$arg" ;;
|
||||
*) set fnord "$@" "$arg" ;;
|
||||
esac
|
||||
shift # fnord
|
||||
shift # $arg
|
||||
done
|
||||
"$@"
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile"
|
||||
exit $stat
|
||||
fi
|
||||
mv "$tmpdepfile" "$depfile"
|
||||
;;
|
||||
|
||||
gcc)
|
||||
## There are various ways to get dependency output from gcc. Here's
|
||||
## why we pick this rather obscure method:
|
||||
## - Don't want to use -MD because we'd like the dependencies to end
|
||||
## up in a subdir. Having to rename by hand is ugly.
|
||||
## (We might end up doing this anyway to support other compilers.)
|
||||
## - The DEPENDENCIES_OUTPUT environment variable makes gcc act like
|
||||
## -MM, not -M (despite what the docs say).
|
||||
## - Using -M directly means running the compiler twice (even worse
|
||||
## than renaming).
|
||||
if test -z "$gccflag"; then
|
||||
gccflag=-MD,
|
||||
fi
|
||||
"$@" -Wp,"$gccflag$tmpdepfile"
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile"
|
||||
exit $stat
|
||||
fi
|
||||
rm -f "$depfile"
|
||||
echo "$object : \\" > "$depfile"
|
||||
alpha=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
|
||||
## The second -e expression handles DOS-style file names with drive letters.
|
||||
sed -e 's/^[^:]*: / /' \
|
||||
-e 's/^['$alpha']:\/[^:]*: / /' < "$tmpdepfile" >> "$depfile"
|
||||
## This next piece of magic avoids the "deleted header file" problem.
|
||||
## The problem is that when a header file which appears in a .P file
|
||||
## is deleted, the dependency causes make to die (because there is
|
||||
## typically no way to rebuild the header). We avoid this by adding
|
||||
## dummy dependencies for each header file. Too bad gcc doesn't do
|
||||
## this for us directly.
|
||||
tr ' ' "$nl" < "$tmpdepfile" |
|
||||
## Some versions of gcc put a space before the ':'. On the theory
|
||||
## that the space means something, we add a space to the output as
|
||||
## well. hp depmode also adds that space, but also prefixes the VPATH
|
||||
## to the object. Take care to not repeat it in the output.
|
||||
## Some versions of the HPUX 10.20 sed can't process this invocation
|
||||
## correctly. Breaking it into two sed invocations is a workaround.
|
||||
sed -e 's/^\\$//' -e '/^$/d' -e "s|.*$object$||" -e '/:$/d' \
|
||||
| sed -e 's/$/ :/' >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
hp)
|
||||
# This case exists only to let depend.m4 do its work. It works by
|
||||
# looking at the text of this script. This case will never be run,
|
||||
# since it is checked for above.
|
||||
exit 1
|
||||
;;
|
||||
|
||||
sgi)
|
||||
if test "$libtool" = yes; then
|
||||
"$@" "-Wp,-MDupdate,$tmpdepfile"
|
||||
else
|
||||
"$@" -MDupdate "$tmpdepfile"
|
||||
fi
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile"
|
||||
exit $stat
|
||||
fi
|
||||
rm -f "$depfile"
|
||||
|
||||
if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files
|
||||
echo "$object : \\" > "$depfile"
|
||||
|
||||
# Clip off the initial element (the dependent). Don't try to be
|
||||
# clever and replace this with sed code, as IRIX sed won't handle
|
||||
# lines with more than a fixed number of characters (4096 in
|
||||
# IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines;
|
||||
# the IRIX cc adds comments like '#:fec' to the end of the
|
||||
# dependency line.
|
||||
tr ' ' "$nl" < "$tmpdepfile" \
|
||||
| sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' | \
|
||||
tr "$nl" ' ' >> "$depfile"
|
||||
echo >> "$depfile"
|
||||
|
||||
# The second pass generates a dummy entry for each header file.
|
||||
tr ' ' "$nl" < "$tmpdepfile" \
|
||||
| sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \
|
||||
>> "$depfile"
|
||||
else
|
||||
# The sourcefile does not contain any dependencies, so just
|
||||
# store a dummy comment line, to avoid errors with the Makefile
|
||||
# "include basename.Plo" scheme.
|
||||
echo "#dummy" > "$depfile"
|
||||
fi
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
xlc)
|
||||
# This case exists only to let depend.m4 do its work. It works by
|
||||
# looking at the text of this script. This case will never be run,
|
||||
# since it is checked for above.
|
||||
exit 1
|
||||
;;
|
||||
|
||||
aix)
|
||||
# The C for AIX Compiler uses -M and outputs the dependencies
|
||||
# in a .u file. In older versions, this file always lives in the
|
||||
# current directory. Also, the AIX compiler puts '$object:' at the
|
||||
# start of each line; $object doesn't have directory information.
|
||||
# Version 6 uses the directory in both cases.
|
||||
dir=`echo "$object" | sed -e 's|/[^/]*$|/|'`
|
||||
test "x$dir" = "x$object" && dir=
|
||||
base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'`
|
||||
if test "$libtool" = yes; then
|
||||
tmpdepfile1=$dir$base.u
|
||||
tmpdepfile2=$base.u
|
||||
tmpdepfile3=$dir.libs/$base.u
|
||||
"$@" -Wc,-M
|
||||
else
|
||||
tmpdepfile1=$dir$base.u
|
||||
tmpdepfile2=$dir$base.u
|
||||
tmpdepfile3=$dir$base.u
|
||||
"$@" -M
|
||||
fi
|
||||
stat=$?
|
||||
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3"
|
||||
exit $stat
|
||||
fi
|
||||
|
||||
for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3"
|
||||
do
|
||||
test -f "$tmpdepfile" && break
|
||||
done
|
||||
if test -f "$tmpdepfile"; then
|
||||
# Each line is of the form 'foo.o: dependent.h'.
|
||||
# Do two passes, one to just change these to
|
||||
# '$object: dependent.h' and one to simply 'dependent.h:'.
|
||||
sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile"
|
||||
sed -e 's,^.*\.[a-z]*:['"$tab"' ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile"
|
||||
else
|
||||
# The sourcefile does not contain any dependencies, so just
|
||||
# store a dummy comment line, to avoid errors with the Makefile
|
||||
# "include basename.Plo" scheme.
|
||||
echo "#dummy" > "$depfile"
|
||||
fi
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
icc)
|
||||
# Intel's C compiler anf tcc (Tiny C Compiler) understand '-MD -MF file'.
|
||||
# However on
|
||||
# $CC -MD -MF foo.d -c -o sub/foo.o sub/foo.c
|
||||
# ICC 7.0 will fill foo.d with something like
|
||||
# foo.o: sub/foo.c
|
||||
# foo.o: sub/foo.h
|
||||
# which is wrong. We want
|
||||
# sub/foo.o: sub/foo.c
|
||||
# sub/foo.o: sub/foo.h
|
||||
# sub/foo.c:
|
||||
# sub/foo.h:
|
||||
# ICC 7.1 will output
|
||||
# foo.o: sub/foo.c sub/foo.h
|
||||
# and will wrap long lines using '\':
|
||||
# foo.o: sub/foo.c ... \
|
||||
# sub/foo.h ... \
|
||||
# ...
|
||||
# tcc 0.9.26 (FIXME still under development at the moment of writing)
|
||||
# will emit a similar output, but also prepend the continuation lines
|
||||
# with horizontal tabulation characters.
|
||||
"$@" -MD -MF "$tmpdepfile"
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile"
|
||||
exit $stat
|
||||
fi
|
||||
rm -f "$depfile"
|
||||
# Each line is of the form 'foo.o: dependent.h',
|
||||
# or 'foo.o: dep1.h dep2.h \', or ' dep3.h dep4.h \'.
|
||||
# Do two passes, one to just change these to
|
||||
# '$object: dependent.h' and one to simply 'dependent.h:'.
|
||||
sed -e "s/^[ $tab][ $tab]*/ /" -e "s,^[^:]*:,$object :," \
|
||||
< "$tmpdepfile" > "$depfile"
|
||||
sed '
|
||||
s/[ '"$tab"'][ '"$tab"']*/ /g
|
||||
s/^ *//
|
||||
s/ *\\*$//
|
||||
s/^[^:]*: *//
|
||||
/^$/d
|
||||
/:$/d
|
||||
s/$/ :/
|
||||
' < "$tmpdepfile" >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
hp2)
|
||||
# The "hp" stanza above does not work with aCC (C++) and HP's ia64
|
||||
# compilers, which have integrated preprocessors. The correct option
|
||||
# to use with these is +Maked; it writes dependencies to a file named
|
||||
# 'foo.d', which lands next to the object file, wherever that
|
||||
# happens to be.
|
||||
# Much of this is similar to the tru64 case; see comments there.
|
||||
dir=`echo "$object" | sed -e 's|/[^/]*$|/|'`
|
||||
test "x$dir" = "x$object" && dir=
|
||||
base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'`
|
||||
if test "$libtool" = yes; then
|
||||
tmpdepfile1=$dir$base.d
|
||||
tmpdepfile2=$dir.libs/$base.d
|
||||
"$@" -Wc,+Maked
|
||||
else
|
||||
tmpdepfile1=$dir$base.d
|
||||
tmpdepfile2=$dir$base.d
|
||||
"$@" +Maked
|
||||
fi
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile1" "$tmpdepfile2"
|
||||
exit $stat
|
||||
fi
|
||||
|
||||
for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2"
|
||||
do
|
||||
test -f "$tmpdepfile" && break
|
||||
done
|
||||
if test -f "$tmpdepfile"; then
|
||||
sed -e "s,^.*\.[a-z]*:,$object:," "$tmpdepfile" > "$depfile"
|
||||
# Add 'dependent.h:' lines.
|
||||
sed -ne '2,${
|
||||
s/^ *//
|
||||
s/ \\*$//
|
||||
s/$/:/
|
||||
p
|
||||
}' "$tmpdepfile" >> "$depfile"
|
||||
else
|
||||
echo "#dummy" > "$depfile"
|
||||
fi
|
||||
rm -f "$tmpdepfile" "$tmpdepfile2"
|
||||
;;
|
||||
|
||||
tru64)
|
||||
# The Tru64 compiler uses -MD to generate dependencies as a side
|
||||
# effect. 'cc -MD -o foo.o ...' puts the dependencies into 'foo.o.d'.
|
||||
# At least on Alpha/Redhat 6.1, Compaq CCC V6.2-504 seems to put
|
||||
# dependencies in 'foo.d' instead, so we check for that too.
|
||||
# Subdirectories are respected.
|
||||
dir=`echo "$object" | sed -e 's|/[^/]*$|/|'`
|
||||
test "x$dir" = "x$object" && dir=
|
||||
base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'`
|
||||
|
||||
if test "$libtool" = yes; then
|
||||
# With Tru64 cc, shared objects can also be used to make a
|
||||
# static library. This mechanism is used in libtool 1.4 series to
|
||||
# handle both shared and static libraries in a single compilation.
|
||||
# With libtool 1.4, dependencies were output in $dir.libs/$base.lo.d.
|
||||
#
|
||||
# With libtool 1.5 this exception was removed, and libtool now
|
||||
# generates 2 separate objects for the 2 libraries. These two
|
||||
# compilations output dependencies in $dir.libs/$base.o.d and
|
||||
# in $dir$base.o.d. We have to check for both files, because
|
||||
# one of the two compilations can be disabled. We should prefer
|
||||
# $dir$base.o.d over $dir.libs/$base.o.d because the latter is
|
||||
# automatically cleaned when .libs/ is deleted, while ignoring
|
||||
# the former would cause a distcleancheck panic.
|
||||
tmpdepfile1=$dir.libs/$base.lo.d # libtool 1.4
|
||||
tmpdepfile2=$dir$base.o.d # libtool 1.5
|
||||
tmpdepfile3=$dir.libs/$base.o.d # libtool 1.5
|
||||
tmpdepfile4=$dir.libs/$base.d # Compaq CCC V6.2-504
|
||||
"$@" -Wc,-MD
|
||||
else
|
||||
tmpdepfile1=$dir$base.o.d
|
||||
tmpdepfile2=$dir$base.d
|
||||
tmpdepfile3=$dir$base.d
|
||||
tmpdepfile4=$dir$base.d
|
||||
"$@" -MD
|
||||
fi
|
||||
|
||||
stat=$?
|
||||
if test $stat -eq 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4"
|
||||
exit $stat
|
||||
fi
|
||||
|
||||
for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4"
|
||||
do
|
||||
test -f "$tmpdepfile" && break
|
||||
done
|
||||
if test -f "$tmpdepfile"; then
|
||||
sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile"
|
||||
sed -e 's,^.*\.[a-z]*:['"$tab"' ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile"
|
||||
else
|
||||
echo "#dummy" > "$depfile"
|
||||
fi
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
msvc7)
|
||||
if test "$libtool" = yes; then
|
||||
showIncludes=-Wc,-showIncludes
|
||||
else
|
||||
showIncludes=-showIncludes
|
||||
fi
|
||||
"$@" $showIncludes > "$tmpdepfile"
|
||||
stat=$?
|
||||
grep -v '^Note: including file: ' "$tmpdepfile"
|
||||
if test "$stat" = 0; then :
|
||||
else
|
||||
rm -f "$tmpdepfile"
|
||||
exit $stat
|
||||
fi
|
||||
rm -f "$depfile"
|
||||
echo "$object : \\" > "$depfile"
|
||||
# The first sed program below extracts the file names and escapes
|
||||
# backslashes for cygpath. The second sed program outputs the file
|
||||
# name when reading, but also accumulates all include files in the
|
||||
# hold buffer in order to output them again at the end. This only
|
||||
# works with sed implementations that can handle large buffers.
|
||||
sed < "$tmpdepfile" -n '
|
||||
/^Note: including file: *\(.*\)/ {
|
||||
s//\1/
|
||||
s/\\/\\\\/g
|
||||
p
|
||||
}' | $cygpath_u | sort -u | sed -n '
|
||||
s/ /\\ /g
|
||||
s/\(.*\)/'"$tab"'\1 \\/p
|
||||
s/.\(.*\) \\/\1:/
|
||||
H
|
||||
$ {
|
||||
s/.*/'"$tab"'/
|
||||
G
|
||||
p
|
||||
}' >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
msvc7msys)
|
||||
# This case exists only to let depend.m4 do its work. It works by
|
||||
# looking at the text of this script. This case will never be run,
|
||||
# since it is checked for above.
|
||||
exit 1
|
||||
;;
|
||||
|
||||
#nosideeffect)
|
||||
# This comment above is used by automake to tell side-effect
|
||||
# dependency tracking mechanisms from slower ones.
|
||||
|
||||
dashmstdout)
|
||||
# Important note: in order to support this mode, a compiler *must*
|
||||
# always write the preprocessed file to stdout, regardless of -o.
|
||||
"$@" || exit $?
|
||||
|
||||
# Remove the call to Libtool.
|
||||
if test "$libtool" = yes; then
|
||||
while test "X$1" != 'X--mode=compile'; do
|
||||
shift
|
||||
done
|
||||
shift
|
||||
fi
|
||||
|
||||
# Remove '-o $object'.
|
||||
IFS=" "
|
||||
for arg
|
||||
do
|
||||
case $arg in
|
||||
-o)
|
||||
shift
|
||||
;;
|
||||
$object)
|
||||
shift
|
||||
;;
|
||||
*)
|
||||
set fnord "$@" "$arg"
|
||||
shift # fnord
|
||||
shift # $arg
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
test -z "$dashmflag" && dashmflag=-M
|
||||
# Require at least two characters before searching for ':'
|
||||
# in the target name. This is to cope with DOS-style filenames:
|
||||
# a dependency such as 'c:/foo/bar' could be seen as target 'c' otherwise.
|
||||
"$@" $dashmflag |
|
||||
sed 's:^['"$tab"' ]*[^:'"$tab"' ][^:][^:]*\:['"$tab"' ]*:'"$object"'\: :' > "$tmpdepfile"
|
||||
rm -f "$depfile"
|
||||
cat < "$tmpdepfile" > "$depfile"
|
||||
tr ' ' "$nl" < "$tmpdepfile" | \
|
||||
## Some versions of the HPUX 10.20 sed can't process this invocation
|
||||
## correctly. Breaking it into two sed invocations is a workaround.
|
||||
sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
dashXmstdout)
|
||||
# This case only exists to satisfy depend.m4. It is never actually
|
||||
# run, as this mode is specially recognized in the preamble.
|
||||
exit 1
|
||||
;;
|
||||
|
||||
makedepend)
|
||||
"$@" || exit $?
|
||||
# Remove any Libtool call
|
||||
if test "$libtool" = yes; then
|
||||
while test "X$1" != 'X--mode=compile'; do
|
||||
shift
|
||||
done
|
||||
shift
|
||||
fi
|
||||
# X makedepend
|
||||
shift
|
||||
cleared=no eat=no
|
||||
for arg
|
||||
do
|
||||
case $cleared in
|
||||
no)
|
||||
set ""; shift
|
||||
cleared=yes ;;
|
||||
esac
|
||||
if test $eat = yes; then
|
||||
eat=no
|
||||
continue
|
||||
fi
|
||||
case "$arg" in
|
||||
-D*|-I*)
|
||||
set fnord "$@" "$arg"; shift ;;
|
||||
# Strip any option that makedepend may not understand. Remove
|
||||
# the object too, otherwise makedepend will parse it as a source file.
|
||||
-arch)
|
||||
eat=yes ;;
|
||||
-*|$object)
|
||||
;;
|
||||
*)
|
||||
set fnord "$@" "$arg"; shift ;;
|
||||
esac
|
||||
done
|
||||
obj_suffix=`echo "$object" | sed 's/^.*\././'`
|
||||
touch "$tmpdepfile"
|
||||
${MAKEDEPEND-makedepend} -o"$obj_suffix" -f"$tmpdepfile" "$@"
|
||||
rm -f "$depfile"
|
||||
# makedepend may prepend the VPATH from the source file name to the object.
|
||||
# No need to regex-escape $object, excess matching of '.' is harmless.
|
||||
sed "s|^.*\($object *:\)|\1|" "$tmpdepfile" > "$depfile"
|
||||
sed '1,2d' "$tmpdepfile" | tr ' ' "$nl" | \
|
||||
## Some versions of the HPUX 10.20 sed can't process this invocation
|
||||
## correctly. Breaking it into two sed invocations is a workaround.
|
||||
sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile"
|
||||
rm -f "$tmpdepfile" "$tmpdepfile".bak
|
||||
;;
|
||||
|
||||
cpp)
|
||||
# Important note: in order to support this mode, a compiler *must*
|
||||
# always write the preprocessed file to stdout.
|
||||
"$@" || exit $?
|
||||
|
||||
# Remove the call to Libtool.
|
||||
if test "$libtool" = yes; then
|
||||
while test "X$1" != 'X--mode=compile'; do
|
||||
shift
|
||||
done
|
||||
shift
|
||||
fi
|
||||
|
||||
# Remove '-o $object'.
|
||||
IFS=" "
|
||||
for arg
|
||||
do
|
||||
case $arg in
|
||||
-o)
|
||||
shift
|
||||
;;
|
||||
$object)
|
||||
shift
|
||||
;;
|
||||
*)
|
||||
set fnord "$@" "$arg"
|
||||
shift # fnord
|
||||
shift # $arg
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
"$@" -E |
|
||||
sed -n -e '/^# [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' \
|
||||
-e '/^#line [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' |
|
||||
sed '$ s: \\$::' > "$tmpdepfile"
|
||||
rm -f "$depfile"
|
||||
echo "$object : \\" > "$depfile"
|
||||
cat < "$tmpdepfile" >> "$depfile"
|
||||
sed < "$tmpdepfile" '/^$/d;s/^ //;s/ \\$//;s/$/ :/' >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
msvisualcpp)
|
||||
# Important note: in order to support this mode, a compiler *must*
|
||||
# always write the preprocessed file to stdout.
|
||||
"$@" || exit $?
|
||||
|
||||
# Remove the call to Libtool.
|
||||
if test "$libtool" = yes; then
|
||||
while test "X$1" != 'X--mode=compile'; do
|
||||
shift
|
||||
done
|
||||
shift
|
||||
fi
|
||||
|
||||
IFS=" "
|
||||
for arg
|
||||
do
|
||||
case "$arg" in
|
||||
-o)
|
||||
shift
|
||||
;;
|
||||
$object)
|
||||
shift
|
||||
;;
|
||||
"-Gm"|"/Gm"|"-Gi"|"/Gi"|"-ZI"|"/ZI")
|
||||
set fnord "$@"
|
||||
shift
|
||||
shift
|
||||
;;
|
||||
*)
|
||||
set fnord "$@" "$arg"
|
||||
shift
|
||||
shift
|
||||
;;
|
||||
esac
|
||||
done
|
||||
"$@" -E 2>/dev/null |
|
||||
sed -n '/^#line [0-9][0-9]* "\([^"]*\)"/ s::\1:p' | $cygpath_u | sort -u > "$tmpdepfile"
|
||||
rm -f "$depfile"
|
||||
echo "$object : \\" > "$depfile"
|
||||
sed < "$tmpdepfile" -n -e 's% %\\ %g' -e '/^\(.*\)$/ s::'"$tab"'\1 \\:p' >> "$depfile"
|
||||
echo "$tab" >> "$depfile"
|
||||
sed < "$tmpdepfile" -n -e 's% %\\ %g' -e '/^\(.*\)$/ s::\1\::p' >> "$depfile"
|
||||
rm -f "$tmpdepfile"
|
||||
;;
|
||||
|
||||
msvcmsys)
|
||||
# This case exists only to let depend.m4 do its work. It works by
|
||||
# looking at the text of this script. This case will never be run,
|
||||
# since it is checked for above.
|
||||
exit 1
|
||||
;;
|
||||
|
||||
none)
|
||||
exec "$@"
|
||||
;;
|
||||
|
||||
*)
|
||||
echo "Unknown depmode $depmode" 1>&2
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
exit 0
|
||||
|
||||
# Local Variables:
|
||||
# mode: shell-script
|
||||
# sh-indentation: 2
|
||||
# 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:
|
||||
@@ -1,527 +0,0 @@
|
||||
#!/bin/sh
|
||||
# install - install a program, script, or datafile
|
||||
|
||||
scriptversion=2011-01-19.21; # 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.
|
||||
-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;;
|
||||
|
||||
-t) dst_arg=$2
|
||||
# Protect names problematic for `test' and other utilities.
|
||||
case $dst_arg in
|
||||
-* | [=\(\)!]) dst_arg=./$dst_arg;;
|
||||
esac
|
||||
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
|
||||
# Protect names problematic for `test' and other utilities.
|
||||
case $dst_arg in
|
||||
-* | [=\(\)!]) dst_arg=./$dst_arg;;
|
||||
esac
|
||||
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 problematic for `test' and other utilities.
|
||||
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
|
||||
|
||||
# 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 X"$d" = X && continue
|
||||
|
||||
prefix=$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:
|
||||
-9655
File diff suppressed because it is too large
Load Diff
@@ -1,331 +0,0 @@
|
||||
#! /bin/sh
|
||||
# Common stub for a few missing GNU programs while installing.
|
||||
|
||||
scriptversion=2012-01-06.13; # UTC
|
||||
|
||||
# Copyright (C) 1996, 1997, 1999, 2000, 2002, 2003, 2004, 2005, 2006,
|
||||
# 2008, 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
# Originally by Fran,cois Pinard <pinard@iro.umontreal.ca>, 1996.
|
||||
|
||||
# This program is free software; you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation; either version 2, or (at your option)
|
||||
# any later version.
|
||||
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
# As a special exception to the GNU General Public License, if you
|
||||
# distribute this file as part of a program that contains a
|
||||
# configuration script generated by Autoconf, you may include it under
|
||||
# the same distribution terms that you use for the rest of that program.
|
||||
|
||||
if test $# -eq 0; then
|
||||
echo 1>&2 "Try \`$0 --help' for more information"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
run=:
|
||||
sed_output='s/.* --output[ =]\([^ ]*\).*/\1/p'
|
||||
sed_minuso='s/.* -o \([^ ]*\).*/\1/p'
|
||||
|
||||
# In the cases where this matters, `missing' is being run in the
|
||||
# srcdir already.
|
||||
if test -f configure.ac; then
|
||||
configure_ac=configure.ac
|
||||
else
|
||||
configure_ac=configure.in
|
||||
fi
|
||||
|
||||
msg="missing on your system"
|
||||
|
||||
case $1 in
|
||||
--run)
|
||||
# Try to run requested program, and just exit if it succeeds.
|
||||
run=
|
||||
shift
|
||||
"$@" && exit 0
|
||||
# Exit code 63 means version mismatch. This often happens
|
||||
# when the user try to use an ancient version of a tool on
|
||||
# a file that requires a minimum version. In this case we
|
||||
# we should proceed has if the program had been absent, or
|
||||
# if --run hadn't been passed.
|
||||
if test $? = 63; then
|
||||
run=:
|
||||
msg="probably too old"
|
||||
fi
|
||||
;;
|
||||
|
||||
-h|--h|--he|--hel|--help)
|
||||
echo "\
|
||||
$0 [OPTION]... PROGRAM [ARGUMENT]...
|
||||
|
||||
Handle \`PROGRAM [ARGUMENT]...' for when PROGRAM is missing, or return an
|
||||
error status if there is no known handling for PROGRAM.
|
||||
|
||||
Options:
|
||||
-h, --help display this help and exit
|
||||
-v, --version output version information and exit
|
||||
--run try to run the given command, and emulate it if it fails
|
||||
|
||||
Supported PROGRAM values:
|
||||
aclocal touch file \`aclocal.m4'
|
||||
autoconf touch file \`configure'
|
||||
autoheader touch file \`config.h.in'
|
||||
autom4te touch the output file, or create a stub one
|
||||
automake touch all \`Makefile.in' files
|
||||
bison create \`y.tab.[ch]', if possible, from existing .[ch]
|
||||
flex create \`lex.yy.c', if possible, from existing .c
|
||||
help2man touch the output file
|
||||
lex create \`lex.yy.c', if possible, from existing .c
|
||||
makeinfo touch the output file
|
||||
yacc create \`y.tab.[ch]', if possible, from existing .[ch]
|
||||
|
||||
Version suffixes to PROGRAM as well as the prefixes \`gnu-', \`gnu', and
|
||||
\`g' are ignored when checking the name.
|
||||
|
||||
Send bug reports to <bug-automake@gnu.org>."
|
||||
exit $?
|
||||
;;
|
||||
|
||||
-v|--v|--ve|--ver|--vers|--versi|--versio|--version)
|
||||
echo "missing $scriptversion (GNU Automake)"
|
||||
exit $?
|
||||
;;
|
||||
|
||||
-*)
|
||||
echo 1>&2 "$0: Unknown \`$1' option"
|
||||
echo 1>&2 "Try \`$0 --help' for more information"
|
||||
exit 1
|
||||
;;
|
||||
|
||||
esac
|
||||
|
||||
# normalize program name to check for.
|
||||
program=`echo "$1" | sed '
|
||||
s/^gnu-//; t
|
||||
s/^gnu//; t
|
||||
s/^g//; t'`
|
||||
|
||||
# Now exit if we have it, but it failed. Also exit now if we
|
||||
# don't have it and --version was passed (most likely to detect
|
||||
# the program). This is about non-GNU programs, so use $1 not
|
||||
# $program.
|
||||
case $1 in
|
||||
lex*|yacc*)
|
||||
# Not GNU programs, they don't have --version.
|
||||
;;
|
||||
|
||||
*)
|
||||
if test -z "$run" && ($1 --version) > /dev/null 2>&1; then
|
||||
# We have it, but it failed.
|
||||
exit 1
|
||||
elif test "x$2" = "x--version" || test "x$2" = "x--help"; then
|
||||
# Could not run --version or --help. This is probably someone
|
||||
# running `$TOOL --version' or `$TOOL --help' to check whether
|
||||
# $TOOL exists and not knowing $TOOL uses missing.
|
||||
exit 1
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
|
||||
# If it does not exist, or fails to run (possibly an outdated version),
|
||||
# try to emulate it.
|
||||
case $program in
|
||||
aclocal*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified \`acinclude.m4' or \`${configure_ac}'. You might want
|
||||
to install the \`Automake' and \`Perl' packages. Grab them from
|
||||
any GNU archive site."
|
||||
touch aclocal.m4
|
||||
;;
|
||||
|
||||
autoconf*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified \`${configure_ac}'. You might want to install the
|
||||
\`Autoconf' and \`GNU m4' packages. Grab them from any GNU
|
||||
archive site."
|
||||
touch configure
|
||||
;;
|
||||
|
||||
autoheader*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified \`acconfig.h' or \`${configure_ac}'. You might want
|
||||
to install the \`Autoconf' and \`GNU m4' packages. Grab them
|
||||
from any GNU archive site."
|
||||
files=`sed -n 's/^[ ]*A[CM]_CONFIG_HEADER(\([^)]*\)).*/\1/p' ${configure_ac}`
|
||||
test -z "$files" && files="config.h"
|
||||
touch_files=
|
||||
for f in $files; do
|
||||
case $f in
|
||||
*:*) touch_files="$touch_files "`echo "$f" |
|
||||
sed -e 's/^[^:]*://' -e 's/:.*//'`;;
|
||||
*) touch_files="$touch_files $f.in";;
|
||||
esac
|
||||
done
|
||||
touch $touch_files
|
||||
;;
|
||||
|
||||
automake*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified \`Makefile.am', \`acinclude.m4' or \`${configure_ac}'.
|
||||
You might want to install the \`Automake' and \`Perl' packages.
|
||||
Grab them from any GNU archive site."
|
||||
find . -type f -name Makefile.am -print |
|
||||
sed 's/\.am$/.in/' |
|
||||
while read f; do touch "$f"; done
|
||||
;;
|
||||
|
||||
autom4te*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is needed, but is $msg.
|
||||
You might have modified some files without having the
|
||||
proper tools for further handling them.
|
||||
You can get \`$1' as part of \`Autoconf' from any GNU
|
||||
archive site."
|
||||
|
||||
file=`echo "$*" | sed -n "$sed_output"`
|
||||
test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"`
|
||||
if test -f "$file"; then
|
||||
touch $file
|
||||
else
|
||||
test -z "$file" || exec >$file
|
||||
echo "#! /bin/sh"
|
||||
echo "# Created by GNU Automake missing as a replacement of"
|
||||
echo "# $ $@"
|
||||
echo "exit 0"
|
||||
chmod +x $file
|
||||
exit 1
|
||||
fi
|
||||
;;
|
||||
|
||||
bison*|yacc*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' $msg. You should only need it if
|
||||
you modified a \`.y' file. You may need the \`Bison' package
|
||||
in order for those modifications to take effect. You can get
|
||||
\`Bison' from any GNU archive site."
|
||||
rm -f y.tab.c y.tab.h
|
||||
if test $# -ne 1; then
|
||||
eval LASTARG=\${$#}
|
||||
case $LASTARG in
|
||||
*.y)
|
||||
SRCFILE=`echo "$LASTARG" | sed 's/y$/c/'`
|
||||
if test -f "$SRCFILE"; then
|
||||
cp "$SRCFILE" y.tab.c
|
||||
fi
|
||||
SRCFILE=`echo "$LASTARG" | sed 's/y$/h/'`
|
||||
if test -f "$SRCFILE"; then
|
||||
cp "$SRCFILE" y.tab.h
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
fi
|
||||
if test ! -f y.tab.h; then
|
||||
echo >y.tab.h
|
||||
fi
|
||||
if test ! -f y.tab.c; then
|
||||
echo 'main() { return 0; }' >y.tab.c
|
||||
fi
|
||||
;;
|
||||
|
||||
lex*|flex*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified a \`.l' file. You may need the \`Flex' package
|
||||
in order for those modifications to take effect. You can get
|
||||
\`Flex' from any GNU archive site."
|
||||
rm -f lex.yy.c
|
||||
if test $# -ne 1; then
|
||||
eval LASTARG=\${$#}
|
||||
case $LASTARG in
|
||||
*.l)
|
||||
SRCFILE=`echo "$LASTARG" | sed 's/l$/c/'`
|
||||
if test -f "$SRCFILE"; then
|
||||
cp "$SRCFILE" lex.yy.c
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
fi
|
||||
if test ! -f lex.yy.c; then
|
||||
echo 'main() { return 0; }' >lex.yy.c
|
||||
fi
|
||||
;;
|
||||
|
||||
help2man*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified a dependency of a manual page. You may need the
|
||||
\`Help2man' package in order for those modifications to take
|
||||
effect. You can get \`Help2man' from any GNU archive site."
|
||||
|
||||
file=`echo "$*" | sed -n "$sed_output"`
|
||||
test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"`
|
||||
if test -f "$file"; then
|
||||
touch $file
|
||||
else
|
||||
test -z "$file" || exec >$file
|
||||
echo ".ab help2man is required to generate this page"
|
||||
exit $?
|
||||
fi
|
||||
;;
|
||||
|
||||
makeinfo*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is $msg. You should only need it if
|
||||
you modified a \`.texi' or \`.texinfo' file, or any other file
|
||||
indirectly affecting the aspect of the manual. The spurious
|
||||
call might also be the consequence of using a buggy \`make' (AIX,
|
||||
DU, IRIX). You might want to install the \`Texinfo' package or
|
||||
the \`GNU make' package. Grab either from any GNU archive site."
|
||||
# The file to touch is that specified with -o ...
|
||||
file=`echo "$*" | sed -n "$sed_output"`
|
||||
test -z "$file" && file=`echo "$*" | sed -n "$sed_minuso"`
|
||||
if test -z "$file"; then
|
||||
# ... or it is the one specified with @setfilename ...
|
||||
infile=`echo "$*" | sed 's/.* \([^ ]*\) *$/\1/'`
|
||||
file=`sed -n '
|
||||
/^@setfilename/{
|
||||
s/.* \([^ ]*\) *$/\1/
|
||||
p
|
||||
q
|
||||
}' $infile`
|
||||
# ... or it is derived from the source name (dir/f.texi becomes f.info)
|
||||
test -z "$file" && file=`echo "$infile" | sed 's,.*/,,;s,.[^.]*$,,'`.info
|
||||
fi
|
||||
# If the file does not exist, the user really needs makeinfo;
|
||||
# let's fail without touching anything.
|
||||
test -f $file || exit 1
|
||||
touch $file
|
||||
;;
|
||||
|
||||
*)
|
||||
echo 1>&2 "\
|
||||
WARNING: \`$1' is needed, and is $msg.
|
||||
You might have modified some files without having the
|
||||
proper tools for further handling them. Check the \`README' file,
|
||||
it often tells you about the needed prerequisites for installing
|
||||
this package. You may also peek at any GNU archive site, in case
|
||||
some other package would contain this missing \`$1' program."
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
exit 0
|
||||
|
||||
# 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:
|
||||
@@ -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)/$$p/; \
|
||||
fi; \
|
||||
done
|
||||
|
||||
(cd $(DIST_ROOT); $(COMPRESS);)
|
||||
|
||||
#========================================================================
|
||||
# End of user-definable section
|
||||
#========================================================================
|
||||
|
||||
#========================================================================
|
||||
# Don't modify the file to clean here. Instead, set the "CLEANFILES"
|
||||
# variable in configure.in
|
||||
#========================================================================
|
||||
|
||||
clean:
|
||||
-test -z "$(BINARIES)" || rm -f $(BINARIES)
|
||||
-rm -f *.$(OBJEXT) core *.core
|
||||
-test -z "$(CLEANFILES)" || rm -f $(CLEANFILES)
|
||||
|
||||
distclean: clean
|
||||
-rm -f *.tab.c
|
||||
-rm -f $(CONFIG_CLEAN_FILES)
|
||||
-rm -f config.cache config.log config.status
|
||||
|
||||
#========================================================================
|
||||
# Install binary object libraries. On Windows this includes both .dll and
|
||||
# .lib files. Because the .lib files are not explicitly listed anywhere,
|
||||
# we need to deduce their existence from the .dll file of the same name.
|
||||
# Library files go into the lib directory.
|
||||
# In addition, this will generate the pkgIndex.tcl
|
||||
# file in the install location (assuming it can find a usable tclsh shell)
|
||||
#
|
||||
# You should not have to modify this target.
|
||||
#========================================================================
|
||||
|
||||
install-lib-binaries: binaries
|
||||
@mkdir -p $(DESTDIR)$(pkglibdir)
|
||||
@list='$(lib_BINARIES)'; for p in $$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
|
||||
#
|
||||
@@ -1,202 +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_CFLAGS([-DSQLITE_OMIT_DEPRECATED=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) {
|
||||
char *ks, *ke, *vs, *ve;
|
||||
ks = 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, ks, 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
|
||||
|
||||
Vendored
+311
-414
File diff suppressed because it is too large
Load Diff
-113
@@ -1,113 +0,0 @@
|
||||
/* config.h.in. Generated from configure.ac by autoheader. */
|
||||
|
||||
/* Define to 1 if you have the <dlfcn.h> header file. */
|
||||
#undef HAVE_DLFCN_H
|
||||
|
||||
/* Define to 1 if you have the `fdatasync' function. */
|
||||
#undef HAVE_FDATASYNC
|
||||
|
||||
/* Define to 1 if you have the `gmtime_r' function. */
|
||||
#undef HAVE_GMTIME_R
|
||||
|
||||
/* Define to 1 if the system has the type `int16_t'. */
|
||||
#undef HAVE_INT16_T
|
||||
|
||||
/* Define to 1 if the system has the type `int32_t'. */
|
||||
#undef HAVE_INT32_T
|
||||
|
||||
/* Define to 1 if the system has the type `int64_t'. */
|
||||
#undef HAVE_INT64_T
|
||||
|
||||
/* Define to 1 if the system has the type `int8_t'. */
|
||||
#undef HAVE_INT8_T
|
||||
|
||||
/* Define to 1 if the system has the type `intptr_t'. */
|
||||
#undef HAVE_INTPTR_T
|
||||
|
||||
/* Define to 1 if you have the <inttypes.h> header file. */
|
||||
#undef HAVE_INTTYPES_H
|
||||
|
||||
/* Define to 1 if you have the `localtime_r' function. */
|
||||
#undef HAVE_LOCALTIME_R
|
||||
|
||||
/* Define to 1 if you have the `localtime_s' function. */
|
||||
#undef HAVE_LOCALTIME_S
|
||||
|
||||
/* Define to 1 if you have the <malloc.h> header file. */
|
||||
#undef HAVE_MALLOC_H
|
||||
|
||||
/* Define to 1 if you have the `malloc_usable_size' function. */
|
||||
#undef HAVE_MALLOC_USABLE_SIZE
|
||||
|
||||
/* Define to 1 if you have the <memory.h> header file. */
|
||||
#undef HAVE_MEMORY_H
|
||||
|
||||
/* 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 <strings.h> header file. */
|
||||
#undef HAVE_STRINGS_H
|
||||
|
||||
/* Define to 1 if you have the <string.h> header file. */
|
||||
#undef HAVE_STRING_H
|
||||
|
||||
/* Define to 1 if you have the <sys/stat.h> header file. */
|
||||
#undef HAVE_SYS_STAT_H
|
||||
|
||||
/* Define to 1 if you have the <sys/types.h> header file. */
|
||||
#undef HAVE_SYS_TYPES_H
|
||||
|
||||
/* Define to 1 if the system has the type `uint16_t'. */
|
||||
#undef HAVE_UINT16_T
|
||||
|
||||
/* Define to 1 if the system has the type `uint32_t'. */
|
||||
#undef HAVE_UINT32_T
|
||||
|
||||
/* Define to 1 if the system has the type `uint64_t'. */
|
||||
#undef HAVE_UINT64_T
|
||||
|
||||
/* Define to 1 if the system has the type `uint8_t'. */
|
||||
#undef HAVE_UINT8_T
|
||||
|
||||
/* Define to 1 if the system has the type `uintptr_t'. */
|
||||
#undef HAVE_UINTPTR_T
|
||||
|
||||
/* Define to 1 if you have the <unistd.h> header file. */
|
||||
#undef HAVE_UNISTD_H
|
||||
|
||||
/* Define to 1 if you have the `usleep' function. */
|
||||
#undef HAVE_USLEEP
|
||||
|
||||
/* Define to 1 if you have the utime() library function. */
|
||||
#undef HAVE_UTIME
|
||||
|
||||
/* Define to the sub-directory in which libtool stores uninstalled libraries.
|
||||
*/
|
||||
#undef LT_OBJDIR
|
||||
|
||||
/* Define to the address where bug reports for this package should be sent. */
|
||||
#undef PACKAGE_BUGREPORT
|
||||
|
||||
/* Define to the full name of this package. */
|
||||
#undef PACKAGE_NAME
|
||||
|
||||
/* Define to the full name and version of this package. */
|
||||
#undef PACKAGE_STRING
|
||||
|
||||
/* Define to the one symbol short name of this package. */
|
||||
#undef PACKAGE_TARNAME
|
||||
|
||||
/* Define to the version of this package. */
|
||||
#undef PACKAGE_VERSION
|
||||
|
||||
/* Define to 1 if you have the ANSI C header files. */
|
||||
#undef STDC_HEADERS
|
||||
|
||||
/* Number of bits in a file offset, on hosts where this is settable. */
|
||||
#undef _FILE_OFFSET_BITS
|
||||
|
||||
/* Define for large files, on AIX-style hosts. */
|
||||
#undef _LARGE_FILES
|
||||
Vendored
+58
-165
@@ -1,10 +1,9 @@
|
||||
#! /bin/sh
|
||||
# Configuration validation subroutine script.
|
||||
# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999,
|
||||
# 2000, 2001, 2002, 2003, 2004, 2005, 2006 Free Software Foundation,
|
||||
# Inc.
|
||||
# 2000, 2001, 2002, 2003 Free Software Foundation, Inc.
|
||||
|
||||
timestamp='2007-06-28'
|
||||
timestamp='2004-01-05'
|
||||
|
||||
# This file is (in principle) common to ALL GNU software.
|
||||
# The presence of a machine in this file suggests that SOME GNU software
|
||||
@@ -22,15 +21,14 @@ timestamp='2007-06-28'
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
|
||||
# 02110-1301, USA.
|
||||
#
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330,
|
||||
# Boston, MA 02111-1307, USA.
|
||||
|
||||
# As a special exception to the GNU General Public License, if you
|
||||
# distribute this file as part of a program that contains a
|
||||
# configuration script generated by Autoconf, you may include it under
|
||||
# the same distribution terms that you use for the rest of that program.
|
||||
|
||||
|
||||
# Please send patches to <config-patches@gnu.org>. Submit a context
|
||||
# diff and a properly formatted ChangeLog entry.
|
||||
#
|
||||
@@ -72,7 +70,7 @@ Report bugs and patches to <config-patches@gnu.org>."
|
||||
version="\
|
||||
GNU config.sub ($timestamp)
|
||||
|
||||
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005
|
||||
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001
|
||||
Free Software Foundation, Inc.
|
||||
|
||||
This is free software; see the source for copying conditions. There is NO
|
||||
@@ -85,11 +83,11 @@ Try \`$me --help' for more information."
|
||||
while test $# -gt 0 ; do
|
||||
case $1 in
|
||||
--time-stamp | --time* | -t )
|
||||
echo "$timestamp" ; exit ;;
|
||||
echo "$timestamp" ; exit 0 ;;
|
||||
--version | -v )
|
||||
echo "$version" ; exit ;;
|
||||
echo "$version" ; exit 0 ;;
|
||||
--help | --h* | -h )
|
||||
echo "$usage"; exit ;;
|
||||
echo "$usage"; exit 0 ;;
|
||||
-- ) # Stop option processing
|
||||
shift; break ;;
|
||||
- ) # Use stdin as input.
|
||||
@@ -101,7 +99,7 @@ while test $# -gt 0 ; do
|
||||
*local*)
|
||||
# First pass through any local machine types.
|
||||
echo $1
|
||||
exit ;;
|
||||
exit 0;;
|
||||
|
||||
* )
|
||||
break ;;
|
||||
@@ -120,9 +118,8 @@ esac
|
||||
# Here we must recognize all the valid KERNEL-OS combinations.
|
||||
maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'`
|
||||
case $maybe_os in
|
||||
nto-qnx* | linux-gnu* | linux-dietlibc | linux-newlib* | linux-uclibc* | \
|
||||
uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | knetbsd*-gnu* | netbsd*-gnu* | \
|
||||
storm-chaos* | os2-emx* | rtmk-nova*)
|
||||
nto-qnx* | linux-gnu* | linux-dietlibc | linux-uclibc* | uclinux-uclibc* | uclinux-gnu* | \
|
||||
kfreebsd*-gnu* | knetbsd*-gnu* | netbsd*-gnu* | storm-chaos* | os2-emx* | rtmk-nova*)
|
||||
os=-$maybe_os
|
||||
basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'`
|
||||
;;
|
||||
@@ -148,7 +145,7 @@ case $os in
|
||||
-convergent* | -ncr* | -news | -32* | -3600* | -3100* | -hitachi* |\
|
||||
-c[123]* | -convex* | -sun | -crds | -omron* | -dg | -ultra | -tti* | \
|
||||
-harris | -dolphin | -highlevel | -gould | -cbm | -ns | -masscomp | \
|
||||
-apple | -axis | -knuth | -cray)
|
||||
-apple | -axis)
|
||||
os=
|
||||
basic_machine=$1
|
||||
;;
|
||||
@@ -173,10 +170,6 @@ case $os in
|
||||
-hiux*)
|
||||
os=-hiuxwe2
|
||||
;;
|
||||
-sco6)
|
||||
os=-sco5v6
|
||||
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
|
||||
;;
|
||||
-sco5)
|
||||
os=-sco3.2v5
|
||||
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
|
||||
@@ -193,10 +186,6 @@ case $os in
|
||||
# Don't forget version if it is 3.2v4 or newer.
|
||||
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
|
||||
;;
|
||||
-sco5v6*)
|
||||
# Don't forget version if it is 3.2v4 or newer.
|
||||
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
|
||||
;;
|
||||
-sco*)
|
||||
os=-sco3.2v2
|
||||
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
|
||||
@@ -241,16 +230,14 @@ case $basic_machine in
|
||||
| alpha | alphaev[4-8] | alphaev56 | alphaev6[78] | alphapca5[67] \
|
||||
| alpha64 | alpha64ev[4-8] | alpha64ev56 | alpha64ev6[78] | alpha64pca5[67] \
|
||||
| am33_2.0 \
|
||||
| arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr | avr32 \
|
||||
| bfin \
|
||||
| arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr \
|
||||
| c4x | clipper \
|
||||
| d10v | d30v | dlx | dsp16xx | dvp \
|
||||
| fido | fr30 | frv \
|
||||
| d10v | d30v | dlx | dsp16xx \
|
||||
| fr30 | frv \
|
||||
| h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \
|
||||
| i370 | i860 | i960 | ia64 \
|
||||
| ip2k | iq2000 \
|
||||
| m32c | m32r | m32rle | m68000 | m68k | m88k \
|
||||
| maxq | mb | microblaze | mcore | mep \
|
||||
| m32r | m68000 | m68k | m88k | mcore \
|
||||
| mips | mipsbe | mipseb | mipsel | mipsle \
|
||||
| mips16 \
|
||||
| mips64 | mips64el \
|
||||
@@ -259,7 +246,6 @@ case $basic_machine in
|
||||
| mips64vr4100 | mips64vr4100el \
|
||||
| mips64vr4300 | mips64vr4300el \
|
||||
| mips64vr5000 | mips64vr5000el \
|
||||
| mips64vr5900 | mips64vr5900el \
|
||||
| mipsisa32 | mipsisa32el \
|
||||
| mipsisa32r2 | mipsisa32r2el \
|
||||
| mipsisa64 | mipsisa64el \
|
||||
@@ -268,24 +254,20 @@ case $basic_machine in
|
||||
| mipsisa64sr71k | mipsisa64sr71kel \
|
||||
| mipstx39 | mipstx39el \
|
||||
| mn10200 | mn10300 \
|
||||
| mt \
|
||||
| msp430 \
|
||||
| nios | nios2 \
|
||||
| ns16k | ns32k \
|
||||
| or32 \
|
||||
| openrisc | or32 \
|
||||
| pdp10 | pdp11 | pj | pjl \
|
||||
| powerpc | powerpc64 | powerpc64le | powerpcle | ppcbe \
|
||||
| pyramid \
|
||||
| score \
|
||||
| sh | sh[1234] | sh[24]a | sh[24]a*eb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
|
||||
| sh | sh[1234] | sh[23]e | sh[34]eb | shbe | shle | sh[1234]le | sh3ele \
|
||||
| sh64 | sh64le \
|
||||
| sparc | sparc64 | sparc64b | sparc64v | sparc86x | sparclet | sparclite \
|
||||
| sparcv8 | sparcv9 | sparcv9b | sparcv9v \
|
||||
| spu | strongarm \
|
||||
| sparc | sparc64 | sparc86x | sparclet | sparclite | sparcv9 | sparcv9b \
|
||||
| strongarm \
|
||||
| tahoe | thumb | tic4x | tic80 | tron \
|
||||
| v850 | v850e \
|
||||
| we32k \
|
||||
| x86 | xc16x | xscale | xscalee[bl] | xstormy16 | xtensa \
|
||||
| x86 | xscale | xstormy16 | xtensa \
|
||||
| z8k)
|
||||
basic_machine=$basic_machine-unknown
|
||||
;;
|
||||
@@ -296,9 +278,6 @@ case $basic_machine in
|
||||
;;
|
||||
m88110 | m680[12346]0 | m683?2 | m68360 | m5200 | v70 | w65 | z8k)
|
||||
;;
|
||||
ms1)
|
||||
basic_machine=mt-unknown
|
||||
;;
|
||||
|
||||
# We use `pc' rather than `unknown'
|
||||
# because (1) that's what they normally are, and
|
||||
@@ -318,20 +297,20 @@ case $basic_machine in
|
||||
| alpha64-* | alpha64ev[4-8]-* | alpha64ev56-* | alpha64ev6[78]-* \
|
||||
| alphapca5[67]-* | alpha64pca5[67]-* | arc-* \
|
||||
| arm-* | armbe-* | armle-* | armeb-* | armv*-* \
|
||||
| avr-* | avr32-* \
|
||||
| bfin-* | bs2000-* \
|
||||
| avr-* \
|
||||
| bs2000-* \
|
||||
| c[123]* | c30-* | [cjt]90-* | c4x-* | c54x-* | c55x-* | c6x-* \
|
||||
| clipper-* | craynv-* | cydra-* \
|
||||
| clipper-* | cydra-* \
|
||||
| d10v-* | d30v-* | dlx-* \
|
||||
| elxsi-* \
|
||||
| f30[01]-* | f700-* | fido-* | fr30-* | frv-* | fx80-* \
|
||||
| f30[01]-* | f700-* | fr30-* | frv-* | fx80-* \
|
||||
| h8300-* | h8500-* \
|
||||
| hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \
|
||||
| i*86-* | i860-* | i960-* | ia64-* \
|
||||
| ip2k-* | iq2000-* \
|
||||
| m32c-* | m32r-* | m32rle-* \
|
||||
| m32r-* \
|
||||
| m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \
|
||||
| m88110-* | m88k-* | maxq-* | mcore-* \
|
||||
| m88110-* | m88k-* | mcore-* \
|
||||
| mips-* | mipsbe-* | mipseb-* | mipsel-* | mipsle-* \
|
||||
| mips16-* \
|
||||
| mips64-* | mips64el-* \
|
||||
@@ -340,7 +319,6 @@ case $basic_machine in
|
||||
| mips64vr4100-* | mips64vr4100el-* \
|
||||
| mips64vr4300-* | mips64vr4300el-* \
|
||||
| mips64vr5000-* | mips64vr5000el-* \
|
||||
| mips64vr5900-* | mips64vr5900el-* \
|
||||
| mipsisa32-* | mipsisa32el-* \
|
||||
| mipsisa32r2-* | mipsisa32r2el-* \
|
||||
| mipsisa64-* | mipsisa64el-* \
|
||||
@@ -348,28 +326,24 @@ case $basic_machine in
|
||||
| mipsisa64sb1-* | mipsisa64sb1el-* \
|
||||
| mipsisa64sr71k-* | mipsisa64sr71kel-* \
|
||||
| mipstx39-* | mipstx39el-* \
|
||||
| mmix-* \
|
||||
| mt-* \
|
||||
| msp430-* \
|
||||
| nios-* | nios2-* \
|
||||
| none-* | np1-* | ns16k-* | ns32k-* \
|
||||
| none-* | np1-* | nv1-* | ns16k-* | ns32k-* \
|
||||
| orion-* \
|
||||
| pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \
|
||||
| powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* | ppcbe-* \
|
||||
| pyramid-* \
|
||||
| romp-* | rs6000-* \
|
||||
| sh-* | sh[1234]-* | sh[24]a-* | sh[24]a*eb-* | sh[23]e-* | sh[34]eb-* | sheb-* | shbe-* \
|
||||
| sh-* | sh[1234]-* | sh[23]e-* | sh[34]eb-* | shbe-* \
|
||||
| shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \
|
||||
| sparc-* | sparc64-* | sparc64b-* | sparc64v-* | sparc86x-* | sparclet-* \
|
||||
| sparclite-* \
|
||||
| sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | strongarm-* | sv1-* | sx?-* \
|
||||
| sparc-* | sparc64-* | sparc86x-* | sparclet-* | sparclite-* \
|
||||
| sparcv9-* | sparcv9b-* | strongarm-* | sv1-* | sx?-* \
|
||||
| tahoe-* | thumb-* \
|
||||
| tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \
|
||||
| tron-* \
|
||||
| v850-* | v850e-* | vax-* \
|
||||
| we32k-* \
|
||||
| x86-* | x86_64-* | xc16x-* | xps100-* | xscale-* | xscalee[bl]-* \
|
||||
| xstormy16-* | xtensa-* \
|
||||
| x86-* | x86_64-* | xps100-* | xscale-* | xstormy16-* \
|
||||
| xtensa-* \
|
||||
| ymp-* \
|
||||
| z8k-*)
|
||||
;;
|
||||
@@ -389,9 +363,6 @@ case $basic_machine in
|
||||
basic_machine=a29k-amd
|
||||
os=-udi
|
||||
;;
|
||||
abacus)
|
||||
basic_machine=abacus-unknown
|
||||
;;
|
||||
adobe68k)
|
||||
basic_machine=m68010-adobe
|
||||
os=-scout
|
||||
@@ -471,27 +442,12 @@ case $basic_machine in
|
||||
basic_machine=j90-cray
|
||||
os=-unicos
|
||||
;;
|
||||
craynv)
|
||||
basic_machine=craynv-cray
|
||||
os=-unicosmp
|
||||
;;
|
||||
cr16)
|
||||
basic_machine=cr16-unknown
|
||||
os=-elf
|
||||
;;
|
||||
crds | unos)
|
||||
basic_machine=m68k-crds
|
||||
;;
|
||||
crisv32 | crisv32-* | etraxfs*)
|
||||
basic_machine=crisv32-axis
|
||||
;;
|
||||
cris | cris-* | etrax*)
|
||||
basic_machine=cris-axis
|
||||
;;
|
||||
crx)
|
||||
basic_machine=crx-unknown
|
||||
os=-elf
|
||||
;;
|
||||
da30 | da30-*)
|
||||
basic_machine=m68k-da30
|
||||
;;
|
||||
@@ -514,10 +470,6 @@ case $basic_machine in
|
||||
basic_machine=m88k-motorola
|
||||
os=-sysv3
|
||||
;;
|
||||
djgpp)
|
||||
basic_machine=i586-pc
|
||||
os=-msdosdjgpp
|
||||
;;
|
||||
dpx20 | dpx20-*)
|
||||
basic_machine=rs6000-bull
|
||||
os=-bosx
|
||||
@@ -683,10 +635,6 @@ case $basic_machine in
|
||||
basic_machine=i386-pc
|
||||
os=-mingw32
|
||||
;;
|
||||
mingw32ce)
|
||||
basic_machine=arm-unknown
|
||||
os=-mingw32ce
|
||||
;;
|
||||
miniframe)
|
||||
basic_machine=m68000-convergent
|
||||
;;
|
||||
@@ -694,30 +642,16 @@ case $basic_machine in
|
||||
basic_machine=m68k-atari
|
||||
os=-mint
|
||||
;;
|
||||
mipsEE* | ee | ps2)
|
||||
basic_machine=mips64r5900el-scei
|
||||
case $os in
|
||||
-linux*)
|
||||
;;
|
||||
*)
|
||||
os=-elf
|
||||
;;
|
||||
esac
|
||||
;;
|
||||
iop)
|
||||
basic_machine=mipsel-scei
|
||||
os=-irx
|
||||
;;
|
||||
dvp)
|
||||
basic_machine=dvp-scei
|
||||
os=-elf
|
||||
;;
|
||||
mips3*-*)
|
||||
basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'`
|
||||
;;
|
||||
mips3*)
|
||||
basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'`-unknown
|
||||
;;
|
||||
mmix*)
|
||||
basic_machine=mmix-knuth
|
||||
os=-mmixware
|
||||
;;
|
||||
monitor)
|
||||
basic_machine=m68k-rom68k
|
||||
os=-coff
|
||||
@@ -730,9 +664,6 @@ case $basic_machine in
|
||||
basic_machine=i386-pc
|
||||
os=-msdos
|
||||
;;
|
||||
ms1-*)
|
||||
basic_machine=`echo $basic_machine | sed -e 's/ms1-/mt-/'`
|
||||
;;
|
||||
mvs)
|
||||
basic_machine=i370-ibm
|
||||
os=-mvs
|
||||
@@ -801,6 +732,10 @@ case $basic_machine in
|
||||
np1)
|
||||
basic_machine=np1-gould
|
||||
;;
|
||||
nv1)
|
||||
basic_machine=nv1-cray
|
||||
os=-unicosmp
|
||||
;;
|
||||
nsr-tandem)
|
||||
basic_machine=nsr-tandem
|
||||
;;
|
||||
@@ -808,8 +743,9 @@ case $basic_machine in
|
||||
basic_machine=hppa1.1-oki
|
||||
os=-proelf
|
||||
;;
|
||||
openrisc | openrisc-*)
|
||||
or32 | or32-*)
|
||||
basic_machine=or32-unknown
|
||||
os=-coff
|
||||
;;
|
||||
os400)
|
||||
basic_machine=powerpc-ibm
|
||||
@@ -840,12 +776,6 @@ case $basic_machine in
|
||||
pc532 | pc532-*)
|
||||
basic_machine=ns32k-pc532
|
||||
;;
|
||||
pc98)
|
||||
basic_machine=i386-pc
|
||||
;;
|
||||
pc98-*)
|
||||
basic_machine=i386-`echo $basic_machine | sed 's/^[^-]*-//'`
|
||||
;;
|
||||
pentium | p5 | k5 | k6 | nexgen | viac3)
|
||||
basic_machine=i586-pc
|
||||
;;
|
||||
@@ -902,10 +832,6 @@ case $basic_machine in
|
||||
basic_machine=i586-unknown
|
||||
os=-pw32
|
||||
;;
|
||||
rdos)
|
||||
basic_machine=i386-pc
|
||||
os=-rdos
|
||||
;;
|
||||
rom68k)
|
||||
basic_machine=m68k-rom68k
|
||||
os=-coff
|
||||
@@ -932,10 +858,6 @@ case $basic_machine in
|
||||
sb1el)
|
||||
basic_machine=mipsisa64sb1el-unknown
|
||||
;;
|
||||
sde)
|
||||
basic_machine=mipsisa32-sde
|
||||
os=-elf
|
||||
;;
|
||||
sei)
|
||||
basic_machine=mips-sei
|
||||
os=-seiux
|
||||
@@ -947,9 +869,6 @@ case $basic_machine in
|
||||
basic_machine=sh-hitachi
|
||||
os=-hms
|
||||
;;
|
||||
sh5el)
|
||||
basic_machine=sh5le-unknown
|
||||
;;
|
||||
sh64)
|
||||
basic_machine=sh64-unknown
|
||||
;;
|
||||
@@ -1099,10 +1018,6 @@ case $basic_machine in
|
||||
basic_machine=hppa1.1-winbond
|
||||
os=-proelf
|
||||
;;
|
||||
xbox)
|
||||
basic_machine=i686-pc
|
||||
os=-mingw32
|
||||
;;
|
||||
xps | xps100)
|
||||
basic_machine=xps100-honeywell
|
||||
;;
|
||||
@@ -1133,9 +1048,6 @@ case $basic_machine in
|
||||
romp)
|
||||
basic_machine=romp-ibm
|
||||
;;
|
||||
mmix)
|
||||
basic_machine=mmix-knuth
|
||||
;;
|
||||
rs6000)
|
||||
basic_machine=rs6000-ibm
|
||||
;;
|
||||
@@ -1152,10 +1064,13 @@ case $basic_machine in
|
||||
we32k)
|
||||
basic_machine=we32k-att
|
||||
;;
|
||||
sh[1234] | sh[24]a | sh[34]eb | sh[1234]le | sh[23]ele)
|
||||
sh3 | sh4 | sh[34]eb | sh[1234]le | sh[23]ele)
|
||||
basic_machine=sh-unknown
|
||||
;;
|
||||
sparc | sparcv8 | sparcv9 | sparcv9b | sparcv9v)
|
||||
sh64)
|
||||
basic_machine=sh64-unknown
|
||||
;;
|
||||
sparc | sparcv9 | sparcv9b)
|
||||
basic_machine=sparc-sun
|
||||
;;
|
||||
cydra)
|
||||
@@ -1228,23 +1143,19 @@ case $os in
|
||||
| -aos* \
|
||||
| -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \
|
||||
| -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \
|
||||
| -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* \
|
||||
| -openbsd* | -solidbsd* \
|
||||
| -ekkobsd* | -kfreebsd* | -freebsd* | -riscix* | -lynxos* \
|
||||
| -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \
|
||||
| -hiux* | -386bsd* | -knetbsd* | -netbsd* | -openbsd* | -kfreebsd* | -freebsd* | -riscix* \
|
||||
| -lynxos* | -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \
|
||||
| -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \
|
||||
| -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \
|
||||
| -chorusos* | -chorusrdb* \
|
||||
| -cygwin* | -pe* | -psos* | -moss* | -proelf* | -rtems* \
|
||||
| -mingw32* | -linux-gnu* | -linux-newlib* | -linux-uclibc* \
|
||||
| -uxpv* | -beos* | -mpeix* | -udk* \
|
||||
| -mingw32* | -linux-gnu* | -linux-uclibc* | -uxpv* | -beos* | -mpeix* | -udk* \
|
||||
| -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \
|
||||
| -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \
|
||||
| -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \
|
||||
| -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \
|
||||
| -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \
|
||||
| -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \
|
||||
| -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -irx*)
|
||||
| -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly*)
|
||||
# Remember, each alternative MUST END IN *, to match a version number.
|
||||
;;
|
||||
-qnx*)
|
||||
@@ -1262,7 +1173,7 @@ case $os in
|
||||
os=`echo $os | sed -e 's|nto|nto-qnx|'`
|
||||
;;
|
||||
-sim | -es1800* | -hms* | -xray | -os68k* | -none* | -v88r* \
|
||||
| -windows* | -osx | -abug | -netware* | -os9* | -beos* | -haiku* \
|
||||
| -windows* | -osx | -abug | -netware* | -os9* | -beos* \
|
||||
| -macos* | -mpw* | -magic* | -mmixware* | -mon960* | -lnews*)
|
||||
;;
|
||||
-mac*)
|
||||
@@ -1371,9 +1282,6 @@ case $os in
|
||||
-kaos*)
|
||||
os=-kaos
|
||||
;;
|
||||
-zvmoe)
|
||||
os=-zvmoe
|
||||
;;
|
||||
-none)
|
||||
;;
|
||||
*)
|
||||
@@ -1396,12 +1304,6 @@ else
|
||||
# system, and we'll never get to this point.
|
||||
|
||||
case $basic_machine in
|
||||
score-*)
|
||||
os=-elf
|
||||
;;
|
||||
spu-*)
|
||||
os=-elf
|
||||
;;
|
||||
*-acorn)
|
||||
os=-riscix1.2
|
||||
;;
|
||||
@@ -1411,9 +1313,9 @@ case $basic_machine in
|
||||
arm*-semi)
|
||||
os=-aout
|
||||
;;
|
||||
c4x-* | tic4x-*)
|
||||
os=-coff
|
||||
;;
|
||||
c4x-* | tic4x-*)
|
||||
os=-coff
|
||||
;;
|
||||
# This must come before the *-dec entry.
|
||||
pdp10-*)
|
||||
os=-tops20
|
||||
@@ -1439,9 +1341,6 @@ case $basic_machine in
|
||||
m68*-cisco)
|
||||
os=-aout
|
||||
;;
|
||||
mep-*)
|
||||
os=-elf
|
||||
;;
|
||||
mips*-cisco)
|
||||
os=-elf
|
||||
;;
|
||||
@@ -1460,15 +1359,9 @@ case $basic_machine in
|
||||
*-be)
|
||||
os=-beos
|
||||
;;
|
||||
*-haiku)
|
||||
os=-haiku
|
||||
;;
|
||||
*-ibm)
|
||||
os=-aix
|
||||
;;
|
||||
*-knuth)
|
||||
os=-mmixware
|
||||
;;
|
||||
*-wec)
|
||||
os=-proelf
|
||||
;;
|
||||
@@ -1634,7 +1527,7 @@ case $basic_machine in
|
||||
esac
|
||||
|
||||
echo $basic_machine$os
|
||||
exit
|
||||
exit 0
|
||||
|
||||
# Local variables:
|
||||
# eval: (add-hook 'write-file-hooks 'time-stamp)
|
||||
|
||||
+211
-288
@@ -45,6 +45,18 @@
|
||||
# The filename extension for executables on the build
|
||||
# platform. "" for Unix and ".exe" for Windows.
|
||||
#
|
||||
# TARGET_CC
|
||||
#
|
||||
# The name of a command that runs on the build platform
|
||||
# and converts C source files into *.o files for the
|
||||
# target platform. In other words, the cross-compiler.
|
||||
#
|
||||
# TARGET_CFLAGS
|
||||
#
|
||||
# Switches that the target compiler needs to turn C source files
|
||||
# into *.o files. Do not include TARGET_TCL_INC in this list.
|
||||
# Makefiles might add additional switches such as "-I.".
|
||||
#
|
||||
# TCL_*
|
||||
#
|
||||
# Lots of values are read in from the tclConfig.sh script,
|
||||
@@ -64,6 +76,18 @@
|
||||
# files for the readline library. If the compiler is able
|
||||
# to find <readline.h> on its own, then this can be blank.
|
||||
#
|
||||
# TARGET_LINK
|
||||
#
|
||||
# The name of the linker that combines *.o files generated
|
||||
# by TARGET_CC into executables for the target platform.
|
||||
#
|
||||
# TARGET_LIBS
|
||||
#
|
||||
# Additional libraries or other switch that the target linker needs
|
||||
# to build an executable on the target. Do not include
|
||||
# on this list any libraries in TARGET_TCL_LIBS and
|
||||
# TARGET_READLINE_LIBS, etc.
|
||||
#
|
||||
# TARGET_EXEEXT
|
||||
#
|
||||
# The filename extension for executables on the
|
||||
@@ -87,78 +111,18 @@
|
||||
# you don't need (for example BLT) by erasing or commenting out
|
||||
# the corresponding code.
|
||||
#
|
||||
AC_INIT(sqlite, m4_esyscmd([cat VERSION | tr -d '\n']))
|
||||
|
||||
dnl Make sure the local VERSION file matches this configure script
|
||||
sqlite_version_sanity_check=`cat $srcdir/VERSION | tr -d '\n'`
|
||||
if test "$PACKAGE_VERSION" != "$sqlite_version_sanity_check" ; then
|
||||
AC_MSG_ERROR([configure script is out of date:
|
||||
configure \$PACKAGE_VERSION = $PACKAGE_VERSION
|
||||
top level VERSION file = $sqlite_version_sanity_check
|
||||
please regen with autoconf])
|
||||
fi
|
||||
AC_INIT(src/sqlite.h.in)
|
||||
|
||||
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 $
|
||||
# $Revision: 1.17 $
|
||||
|
||||
#########
|
||||
# Programs needed
|
||||
#
|
||||
AC_PROG_LIBTOOL
|
||||
AC_PROG_INSTALL
|
||||
AC_PROG_AWK
|
||||
|
||||
#########
|
||||
# Enable large file support (if special flags are necessary)
|
||||
#
|
||||
AC_SYS_LARGEFILE
|
||||
|
||||
#########
|
||||
# Check for needed/wanted data types
|
||||
AC_CHECK_TYPES([int8_t, int16_t, int32_t, int64_t, intptr_t, uint8_t,
|
||||
uint16_t, uint32_t, uint64_t, uintptr_t])
|
||||
|
||||
#########
|
||||
# Check for needed/wanted headers
|
||||
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([usleep fdatasync localtime_r gmtime_r localtime_s utime malloc_usable_size])
|
||||
|
||||
#########
|
||||
# By default, we use the amalgamation (this may be changed below...)
|
||||
#
|
||||
USE_AMALGAMATION=1
|
||||
|
||||
#########
|
||||
# See whether we can run specific tclsh versions known to work well;
|
||||
# if not, then we fall back to plain tclsh.
|
||||
# TODO: try other versions before falling back?
|
||||
#
|
||||
AC_CHECK_PROGS(TCLSH_CMD, [tclsh8.6 tclsh8.5 tclsh], none)
|
||||
if test "$TCLSH_CMD" = "none"; then
|
||||
# If we can't find a local tclsh, then building the amalgamation will fail.
|
||||
# We act as though --disable-amalgamation has been used.
|
||||
echo "Warning: can't find tclsh - defaulting to non-amalgamation build."
|
||||
USE_AMALGAMATION=0
|
||||
TCLSH_CMD="tclsh"
|
||||
fi
|
||||
AC_SUBST(TCLSH_CMD)
|
||||
|
||||
AC_ARG_VAR([TCLLIBDIR], [Where to install tcl plugin])
|
||||
if test "x${TCLLIBDIR+set}" != "xset" ; then
|
||||
TCLLIBDIR='$(libdir)'
|
||||
for i in `echo 'puts stdout $auto_path' | ${TCLSH_CMD}` ; do
|
||||
TCLLIBDIR=$i
|
||||
break
|
||||
done
|
||||
TCLLIBDIR="${TCLLIBDIR}/sqlite3"
|
||||
fi
|
||||
|
||||
|
||||
#########
|
||||
# Set up an appropriate program prefix
|
||||
@@ -169,15 +133,15 @@ fi
|
||||
AC_SUBST(program_prefix)
|
||||
|
||||
VERSION=[`cat $srcdir/VERSION | sed 's/^\([0-9]*\.*[0-9]*\).*/\1/'`]
|
||||
AC_MSG_NOTICE(Version set to $VERSION)
|
||||
echo "Version set to $VERSION"
|
||||
AC_SUBST(VERSION)
|
||||
RELEASE=`cat $srcdir/VERSION`
|
||||
AC_MSG_NOTICE(Release set to $RELEASE)
|
||||
echo "Release set to $RELEASE"
|
||||
AC_SUBST(RELEASE)
|
||||
VERSION_NUMBER=[`cat $srcdir/VERSION \
|
||||
VERSION_NUMBER=[`cat $srcdir/VERSION \
|
||||
| sed 's/[^0-9]/ /g' \
|
||||
| awk '{printf "%d%03d%03d",$1,$2,$3}'`]
|
||||
AC_MSG_NOTICE(Version number set to $VERSION_NUMBER)
|
||||
echo "Version number set to $VERSION_NUMBER"
|
||||
AC_SUBST(VERSION_NUMBER)
|
||||
|
||||
#########
|
||||
@@ -188,7 +152,7 @@ AC_SUBST(VERSION_NUMBER)
|
||||
# $system is the result of uname -s.
|
||||
#
|
||||
AC_ARG_WITH(hints,
|
||||
AC_HELP_STRING([--with-hints=FILE],[Read configuration options from FILE]),
|
||||
[ --with-hints=FILE Read configuration options from FILE],
|
||||
hints=$withval)
|
||||
if test "$hints" = ""; then
|
||||
host=`hostname | sed 's/\..*//'`
|
||||
@@ -219,66 +183,133 @@ fi
|
||||
# Locate a compiler for the build machine. This compiler should
|
||||
# generate command-line programs that run on the build machine.
|
||||
#
|
||||
if test x"$cross_compiling" = xno; then
|
||||
BUILD_CC=$CC
|
||||
BUILD_CFLAGS=$CFLAGS
|
||||
default_build_cflags="-g"
|
||||
if test "$config_BUILD_CC" = ""; then
|
||||
AC_PROG_CC
|
||||
if test "$cross_compiling" = "yes"; then
|
||||
AC_MSG_ERROR([unable to find a compiler for building build tools])
|
||||
fi
|
||||
BUILD_CC=$CC
|
||||
default_build_cflags=$CFLAGS
|
||||
else
|
||||
if test "${BUILD_CC+set}" != set; then
|
||||
AC_CHECK_PROGS(BUILD_CC, gcc cc cl)
|
||||
fi
|
||||
if test "${BUILD_CFLAGS+set}" != set; then
|
||||
BUILD_CFLAGS="-g"
|
||||
fi
|
||||
BUILD_CC=$config_BUILD_CC
|
||||
AC_MSG_CHECKING([host compiler])
|
||||
CC=$BUILD_CC
|
||||
AC_MSG_RESULT($BUILD_CC)
|
||||
fi
|
||||
AC_MSG_CHECKING([switches for the host compiler])
|
||||
if test "$config_BUILD_CFLAGS" != ""; then
|
||||
CFLAGS=$config_BUILD_CFLAGS
|
||||
BUILD_CFLAGS=$config_BUILD_CFLAGS
|
||||
else
|
||||
BUILD_CFLAGS=$default_build_cflags
|
||||
fi
|
||||
AC_MSG_RESULT($BUILD_CFLAGS)
|
||||
if test "$config_BUILD_LIBS" != ""; then
|
||||
BUILD_LIBS=$config_BUILD_LIBS
|
||||
fi
|
||||
AC_SUBST(BUILD_CC)
|
||||
AC_SUBST(BUILD_CFLAGS)
|
||||
AC_SUBST(BUILD_LIBS)
|
||||
|
||||
##########
|
||||
# Locate a compiler that converts C code into *.o files that run on
|
||||
# the target machine.
|
||||
#
|
||||
AC_MSG_CHECKING([target compiler])
|
||||
if test "$config_TARGET_CC" != ""; then
|
||||
TARGET_CC=$config_TARGET_CC
|
||||
else
|
||||
TARGET_CC=$BUILD_CC
|
||||
fi
|
||||
AC_MSG_RESULT($TARGET_CC)
|
||||
AC_MSG_CHECKING([switches on the target compiler])
|
||||
if test "$config_TARGET_CFLAGS" != ""; then
|
||||
TARGET_CFLAGS=$config_TARGET_CFLAGS
|
||||
else
|
||||
TARGET_CFLAGS=$BUILD_CFLAGS
|
||||
fi
|
||||
AC_MSG_RESULT($TARGET_CFLAGS)
|
||||
AC_MSG_CHECKING([target linker])
|
||||
if test "$config_TARGET_LINK" = ""; then
|
||||
TARGET_LINK=$TARGET_CC
|
||||
else
|
||||
TARGET_LINK=$config_TARGET_LINK
|
||||
fi
|
||||
AC_MSG_RESULT($TARGET_LINK)
|
||||
AC_MSG_CHECKING([switches on the target compiler])
|
||||
if test "$config_TARGET_TFLAGS" != ""; then
|
||||
TARGET_TFLAGS=$config_TARGET_TFLAGS
|
||||
else
|
||||
TARGET_TFLAGS=$BUILD_CFLAGS
|
||||
fi
|
||||
if test "$config_TARGET_RANLIB" != ""; then
|
||||
TARGET_RANLIB=$config_TARGET_RANLIB
|
||||
else
|
||||
AC_PROG_RANLIB
|
||||
TARGET_RANLIB=$RANLIB
|
||||
fi
|
||||
if test "$config_TARGET_AR" != ""; then
|
||||
TARGET_AR=$config_TARGET_AR
|
||||
else
|
||||
TARGET_AR='ar cr'
|
||||
fi
|
||||
AC_MSG_RESULT($TARGET_TFLAGS)
|
||||
AC_SUBST(TARGET_CC)
|
||||
AC_SUBST(TARGET_CFLAGS)
|
||||
AC_SUBST(TARGET_LINK)
|
||||
AC_SUBST(TARGET_LFLAGS)
|
||||
AC_SUBST(TARGET_RANLIB)
|
||||
AC_SUBST(TARGET_AR)
|
||||
|
||||
# Set the $cross variable if we are cross-compiling. Make
|
||||
# it 0 if we are not.
|
||||
#
|
||||
AC_MSG_CHECKING([if host and target compilers are the same])
|
||||
if test "$BUILD_CC" = "$TARGET_CC"; then
|
||||
cross=0
|
||||
AC_MSG_RESULT(yes)
|
||||
else
|
||||
cross=1
|
||||
AC_MSG_RESULT(no)
|
||||
fi
|
||||
|
||||
##########
|
||||
# Do we want to support multithreaded use of sqlite
|
||||
#
|
||||
AC_ARG_ENABLE(threadsafe,
|
||||
AC_HELP_STRING([--enable-threadsafe],[Support threadsafe operation]),,enable_threadsafe=yes)
|
||||
[ --enable-threadsafe Support threadsafe operation],,enable_threadsafe=no)
|
||||
AC_MSG_CHECKING([whether to support threadsafe operation])
|
||||
if test "$enable_threadsafe" = "no"; then
|
||||
SQLITE_THREADSAFE=0
|
||||
THREADSAFE=0
|
||||
AC_MSG_RESULT([no])
|
||||
else
|
||||
SQLITE_THREADSAFE=1
|
||||
THREADSAFE=1
|
||||
AC_MSG_RESULT([yes])
|
||||
fi
|
||||
AC_SUBST(SQLITE_THREADSAFE)
|
||||
AC_SUBST(THREADSAFE)
|
||||
|
||||
if test "$SQLITE_THREADSAFE" = "1"; then
|
||||
AC_SEARCH_LIBS(pthread_create, pthread)
|
||||
fi
|
||||
|
||||
##########
|
||||
# Do we want to allow a connection created in one thread to be used
|
||||
# in another thread. This does not work on many Linux systems (ex: RedHat 9)
|
||||
# due to bugs in the threading implementations. This is thus off by default.
|
||||
#
|
||||
AC_ARG_ENABLE(cross-thread-connections,
|
||||
AC_HELP_STRING([--enable-cross-thread-connections],[Allow connection sharing across threads]),,enable_xthreadconnect=no)
|
||||
AC_MSG_CHECKING([whether to allow connections to be shared across threads])
|
||||
if test "$enable_xthreadconnect" = "no"; then
|
||||
XTHREADCONNECT=''
|
||||
AC_MSG_RESULT([no])
|
||||
if test "$THREADSAFE" = "1"; then
|
||||
LIBS=""
|
||||
AC_CHECK_LIB(pthread, pthread_create)
|
||||
TARGET_THREAD_LIB="$LIBS"
|
||||
LIBS=""
|
||||
else
|
||||
XTHREADCONNECT='-DSQLITE_ALLOW_XTHREAD_CONNECT=1'
|
||||
AC_MSG_RESULT([yes])
|
||||
TARGET_THREAD_LIB=""
|
||||
fi
|
||||
AC_SUBST(XTHREADCONNECT)
|
||||
AC_SUBST(TARGET_THREAD_LIB)
|
||||
|
||||
##########
|
||||
# Do we want to support release
|
||||
#
|
||||
AC_ARG_ENABLE(releasemode,
|
||||
AC_HELP_STRING([--enable-releasemode],[Support libtool link to release mode]),,enable_releasemode=no)
|
||||
[ --enable-releasemode Support libtool link to release mode],,enable_releasemode=no)
|
||||
AC_MSG_CHECKING([whether to support shared library linked as release mode or not])
|
||||
if test "$enable_releasemode" = "no"; then
|
||||
ALLOWRELEASE=""
|
||||
AC_MSG_RESULT([no])
|
||||
else
|
||||
ALLOWRELEASE="-release `cat $srcdir/VERSION`"
|
||||
ALLOWRELEASE="-release `cat VERSION`"
|
||||
AC_MSG_RESULT([yes])
|
||||
fi
|
||||
AC_SUBST(ALLOWRELEASE)
|
||||
@@ -287,7 +318,7 @@ AC_SUBST(ALLOWRELEASE)
|
||||
# Do we want temporary databases in memory
|
||||
#
|
||||
AC_ARG_ENABLE(tempstore,
|
||||
AC_HELP_STRING([--enable-tempstore],[Use an in-ram database for temporary tables (never,no,yes,always)]),,enable_tempstore=no)
|
||||
[ --enable-tempstore Use an in-ram database for temporary tables (never,no,yes,always)],,enable_tempstore=yes)
|
||||
AC_MSG_CHECKING([whether to use an in-ram database for temporary tables])
|
||||
case "$enable_tempstore" in
|
||||
never )
|
||||
@@ -298,17 +329,13 @@ case "$enable_tempstore" in
|
||||
TEMP_STORE=1
|
||||
AC_MSG_RESULT([no])
|
||||
;;
|
||||
yes )
|
||||
TEMP_STORE=2
|
||||
AC_MSG_RESULT([yes])
|
||||
;;
|
||||
always )
|
||||
TEMP_STORE=3
|
||||
AC_MSG_RESULT([always])
|
||||
;;
|
||||
* )
|
||||
TEMP_STORE=1
|
||||
AC_MSG_RESULT([no])
|
||||
TEMP_STORE=2
|
||||
AC_MSG_RESULT([yes])
|
||||
;;
|
||||
esac
|
||||
|
||||
@@ -334,26 +361,38 @@ if test "$CYGWIN" = "yes"; then
|
||||
else
|
||||
BUILD_EXEEXT=$EXEEXT
|
||||
fi
|
||||
if test x"$cross_compiling" = xno; then
|
||||
if test "$cross" = "0"; then
|
||||
TARGET_EXEEXT=$BUILD_EXEEXT
|
||||
else
|
||||
TARGET_EXEEXT=$config_TARGET_EXEEXT
|
||||
fi
|
||||
if test "$TARGET_EXEEXT" = ".exe"; then
|
||||
SQLITE_OS_UNIX=0
|
||||
SQLITE_OS_WIN=1
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_WIN=1"
|
||||
OS_UNIX=0
|
||||
OS_WIN=1
|
||||
tclsubdir=win
|
||||
TARGET_CFLAGS="$TARGET_CFLAGS -DOS_WIN=1"
|
||||
else
|
||||
SQLITE_OS_UNIX=1
|
||||
SQLITE_OS_WIN=0
|
||||
CFLAGS="$CFLAGS -DSQLITE_OS_UNIX=1"
|
||||
OS_UNIX=1
|
||||
OS_WIN=0
|
||||
tclsubdir=unix
|
||||
TARGET_CFLAGS="$TARGET_CFLAGS -DOS_UNIX=1"
|
||||
fi
|
||||
|
||||
AC_SUBST(BUILD_EXEEXT)
|
||||
AC_SUBST(SQLITE_OS_UNIX)
|
||||
AC_SUBST(SQLITE_OS_WIN)
|
||||
AC_SUBST(OS_UNIX)
|
||||
AC_SUBST(OS_WIN)
|
||||
AC_SUBST(TARGET_EXEEXT)
|
||||
|
||||
##########
|
||||
# Extract generic linker options from the environment.
|
||||
#
|
||||
if test "$config_TARGET_LIBS" != ""; then
|
||||
TARGET_LIBS=$config_TARGET_LIBS
|
||||
else
|
||||
TARGET_LIBS=""
|
||||
fi
|
||||
AC_SUBST(TARGET_LIBS)
|
||||
|
||||
##########
|
||||
# Figure out all the parameters needed to compile against Tcl.
|
||||
#
|
||||
@@ -362,10 +401,10 @@ AC_SUBST(TARGET_EXEEXT)
|
||||
# Those macros could not be used directly since we have to make some
|
||||
# minor changes to accomodate systems that do not have TCL installed.
|
||||
#
|
||||
AC_ARG_ENABLE(tcl, AC_HELP_STRING([--disable-tcl],[do not build TCL extension]),
|
||||
AC_ARG_ENABLE(tcl, [ --disable-tcl do not build TCL extension],
|
||||
[use_tcl=$enableval],[use_tcl=yes])
|
||||
if test "${use_tcl}" = "yes" ; then
|
||||
AC_ARG_WITH(tcl, AC_HELP_STRING([--with-tcl=DIR],[directory containing tcl configuration (tclConfig.sh)]), with_tclconfig=${withval})
|
||||
AC_ARG_WITH(tcl, [ --with-tcl=DIR directory containing tcl configuration (tclConfig.sh)], with_tclconfig=${withval})
|
||||
AC_MSG_CHECKING([for Tcl configuration])
|
||||
AC_CACHE_VAL(ac_cv_c_tclconfig,[
|
||||
# First check to see if --with-tcl was specified.
|
||||
@@ -376,20 +415,6 @@ if test "${use_tcl}" = "yes" ; then
|
||||
AC_MSG_ERROR([${with_tclconfig} directory doesn't contain tclConfig.sh])
|
||||
fi
|
||||
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="$i"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
fi
|
||||
|
||||
# then check for a private Tcl installation
|
||||
if test x"${ac_cv_c_tclconfig}" = x ; then
|
||||
for i in \
|
||||
@@ -470,7 +495,7 @@ if test "${use_tcl}" = "yes" ; then
|
||||
# installed and uninstalled version of Tcl.
|
||||
#
|
||||
|
||||
if test -f $TCL_BIN_DIR/Makefile ; then
|
||||
if test -f $TCL_BIN_DIR/Makefile ; then
|
||||
TCL_LIB_SPEC=${TCL_BUILD_LIB_SPEC}
|
||||
TCL_STUB_LIB_SPEC=${TCL_BUILD_STUB_LIB_SPEC}
|
||||
TCL_STUB_LIB_PATH=${TCL_BUILD_STUB_LIB_PATH}
|
||||
@@ -491,6 +516,7 @@ if test "${use_tcl}" = "yes" ; then
|
||||
AC_SUBST(TCL_VERSION)
|
||||
AC_SUBST(TCL_BIN_DIR)
|
||||
AC_SUBST(TCL_SRC_DIR)
|
||||
AC_SUBST(TCL_LIBS)
|
||||
AC_SUBST(TCL_INCLUDE_SPEC)
|
||||
|
||||
AC_SUBST(TCL_LIB_FILE)
|
||||
@@ -513,180 +539,77 @@ AC_SUBST(HAVE_TCL)
|
||||
# Figure out what C libraries are required to compile programs
|
||||
# that use "readline()" library.
|
||||
#
|
||||
TARGET_READLINE_LIBS=""
|
||||
TARGET_READLINE_INC=""
|
||||
TARGET_HAVE_READLINE=0
|
||||
AC_ARG_ENABLE([readline],
|
||||
[AC_HELP_STRING([--disable-readline],[disable readline support [default=detect]])],
|
||||
[with_readline=$enableval],
|
||||
[with_readline=auto])
|
||||
|
||||
if test x"$with_readline" != xno; then
|
||||
found="yes"
|
||||
|
||||
AC_ARG_WITH([readline-lib],
|
||||
[AC_HELP_STRING([--with-readline-lib],[specify readline library])],
|
||||
[with_readline_lib=$withval],
|
||||
[with_readline_lib="auto"])
|
||||
if test "x$with_readline_lib" = xauto; then
|
||||
save_LIBS="$LIBS"
|
||||
LIBS=""
|
||||
AC_SEARCH_LIBS(tgetent, [readline ncurses curses termcap], [term_LIBS="$LIBS"], [term_LIBS=""])
|
||||
AC_CHECK_LIB([readline], [readline], [TARGET_READLINE_LIBS="-lreadline"], [found="no"])
|
||||
TARGET_READLINE_LIBS="$TARGET_READLINE_LIBS $term_LIBS"
|
||||
LIBS="$save_LIBS"
|
||||
else
|
||||
TARGET_READLINE_LIBS="$with_readline_lib"
|
||||
fi
|
||||
|
||||
AC_ARG_WITH([readline-inc],
|
||||
[AC_HELP_STRING([--with-readline-inc],[specify readline include paths])],
|
||||
[with_readline_inc=$withval],
|
||||
[with_readline_inc="auto"])
|
||||
if test "x$with_readline_inc" = xauto; then
|
||||
AC_CHECK_HEADER(readline.h, [found="yes"], [
|
||||
found="no"
|
||||
if test "$cross_compiling" != yes; then
|
||||
for dir in /usr /usr/local /usr/local/readline /usr/contrib /mingw; do
|
||||
for subdir in include include/readline; do
|
||||
AC_CHECK_FILE($dir/$subdir/readline.h, found=yes)
|
||||
if test "$found" = "yes"; then
|
||||
TARGET_READLINE_INC="-I$dir/$subdir"
|
||||
break
|
||||
fi
|
||||
done
|
||||
test "$found" = "yes" && break
|
||||
done
|
||||
fi
|
||||
])
|
||||
else
|
||||
TARGET_READLINE_INC="$with_readline_inc"
|
||||
fi
|
||||
|
||||
if test x"$found" = xno; then
|
||||
TARGET_READLINE_LIBS=""
|
||||
TARGET_READLINE_INC=""
|
||||
TARGET_HAVE_READLINE=0
|
||||
else
|
||||
TARGET_HAVE_READLINE=1
|
||||
fi
|
||||
if test "$config_TARGET_READLINE_LIBS" != ""; then
|
||||
TARGET_READLINE_LIBS="$config_TARGET_READLINE_LIBS"
|
||||
else
|
||||
CC=$TARGET_CC
|
||||
LIBS=""
|
||||
AC_SEARCH_LIBS(tgetent, [readline ncurses curses termcap])
|
||||
AC_CHECK_LIB([readline], [readline])
|
||||
TARGET_READLINE_LIBS="$LIBS"
|
||||
fi
|
||||
|
||||
AC_SUBST(TARGET_READLINE_LIBS)
|
||||
|
||||
##########
|
||||
# Figure out where to get the READLINE header files.
|
||||
#
|
||||
AC_MSG_CHECKING([readline header files])
|
||||
found=no
|
||||
if test "$config_TARGET_READLINE_INC" != ""; then
|
||||
TARGET_READLINE_INC=$config_TARGET_READLINE_INC
|
||||
found=yes
|
||||
fi
|
||||
if test "$found" = "yes"; then
|
||||
AC_MSG_RESULT($TARGET_READLINE_INC)
|
||||
else
|
||||
AC_MSG_RESULT(not specified: still searching...)
|
||||
AC_CHECK_HEADER(readline.h, [found=yes])
|
||||
fi
|
||||
if test "$found" = "no"; then
|
||||
for dir in /usr /usr/local /usr/local/readline /usr/contrib /mingw; do
|
||||
AC_CHECK_FILE($dir/include/readline.h, found=yes)
|
||||
if test "$found" = "yes"; then
|
||||
TARGET_READLINE_INC="-I$dir/include"
|
||||
break
|
||||
fi
|
||||
AC_CHECK_FILE($dir/include/readline/readline.h, found=yes)
|
||||
if test "$found" = "yes"; then
|
||||
TARGET_READLINE_INC="-I$dir/include/readline"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
if test "$found" = "yes"; then
|
||||
if test "$TARGET_READLINE_LIBS" = ""; then
|
||||
TARGET_HAVE_READLINE=0
|
||||
else
|
||||
TARGET_HAVE_READLINE=1
|
||||
fi
|
||||
else
|
||||
TARGET_HAVE_READLINE=0
|
||||
fi
|
||||
AC_SUBST(TARGET_READLINE_INC)
|
||||
AC_SUBST(TARGET_HAVE_READLINE)
|
||||
|
||||
##########
|
||||
# Figure out what C libraries are required to compile programs
|
||||
# that use "fdatasync()" function.
|
||||
#
|
||||
AC_SEARCH_LIBS(fdatasync, [rt])
|
||||
|
||||
#########
|
||||
# check for debug enabled
|
||||
AC_ARG_ENABLE(debug, AC_HELP_STRING([--enable-debug],[enable debugging & verbose explain]),
|
||||
AC_ARG_ENABLE(debug, [ --enable-debug enable debugging & verbose explain],
|
||||
[use_debug=$enableval],[use_debug=no])
|
||||
if test "${use_debug}" = "yes" ; then
|
||||
TARGET_DEBUG="-DSQLITE_DEBUG=1"
|
||||
TARGET_DEBUG=""
|
||||
else
|
||||
TARGET_DEBUG="-DNDEBUG"
|
||||
fi
|
||||
AC_SUBST(TARGET_DEBUG)
|
||||
|
||||
#########
|
||||
# See whether we should use the amalgamation to build
|
||||
AC_ARG_ENABLE(amalgamation, AC_HELP_STRING([--disable-amalgamation],
|
||||
[Disable the amalgamation and instead build all files separately]),
|
||||
[use_amalgamation=$enableval],[use_amalgamation=yes])
|
||||
if test "${use_amalgamation}" != "yes" ; then
|
||||
USE_AMALGAMATION=0
|
||||
fi
|
||||
AC_SUBST(USE_AMALGAMATION)
|
||||
|
||||
#########
|
||||
# See whether we should allow loadable extensions
|
||||
AC_ARG_ENABLE(load-extension, AC_HELP_STRING([--enable-load-extension],
|
||||
[Enable loading of external extensions]),
|
||||
[use_loadextension=$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
|
||||
|
||||
#########
|
||||
# attempt to duplicate any OMITS and ENABLES into the $(OPT_FEATURE_FLAGS) parameter
|
||||
for option in $CFLAGS $CPPFLAGS
|
||||
do
|
||||
case $option in
|
||||
-DSQLITE_OMIT*) OPT_FEATURE_FLAGS="$OPT_FEATURE_FLAGS $option";;
|
||||
-DSQLITE_ENABLE*) OPT_FEATURE_FLAGS="$OPT_FEATURE_FLAGS $option";;
|
||||
esac
|
||||
done
|
||||
AC_SUBST(OPT_FEATURE_FLAGS)
|
||||
|
||||
|
||||
# attempt to remove any OMITS and ENABLES from the $(CFLAGS) parameter
|
||||
ac_temp_CFLAGS=""
|
||||
for option in $CFLAGS
|
||||
do
|
||||
case $option in
|
||||
-DSQLITE_OMIT*) ;;
|
||||
-DSQLITE_ENABLE*) ;;
|
||||
*) ac_temp_CFLAGS="$ac_temp_CFLAGS $option";;
|
||||
esac
|
||||
done
|
||||
CFLAGS=$ac_temp_CFLAGS
|
||||
|
||||
|
||||
# attempt to remove any OMITS and ENABLES from the $(CPPFLAGS) parameter
|
||||
ac_temp_CPPFLAGS=""
|
||||
for option in $CPPFLAGS
|
||||
do
|
||||
case $option in
|
||||
-DSQLITE_OMIT*) ;;
|
||||
-DSQLITE_ENABLE*) ;;
|
||||
*) ac_temp_CPPFLAGS="$ac_temp_CPPFLAGS $option";;
|
||||
esac
|
||||
done
|
||||
CPPFLAGS=$ac_temp_CPPFLAGS
|
||||
|
||||
|
||||
# attempt to remove any OMITS and ENABLES from the $(BUILD_CFLAGS) parameter
|
||||
ac_temp_BUILD_CFLAGS=""
|
||||
for option in $BUILD_CFLAGS
|
||||
do
|
||||
case $option in
|
||||
-DSQLITE_OMIT*) ;;
|
||||
-DSQLITE_ENABLE*) ;;
|
||||
*) ac_temp_BUILD_CFLAGS="$ac_temp_BUILD_CFLAGS $option";;
|
||||
esac
|
||||
done
|
||||
BUILD_CFLAGS=$ac_temp_BUILD_CFLAGS
|
||||
|
||||
|
||||
#########
|
||||
# See whether we should use GCOV
|
||||
AC_ARG_ENABLE(gcov, AC_HELP_STRING([--enable-gcov],
|
||||
[Enable coverage testing using gcov]),
|
||||
[use_gcov=$enableval],[use_gcov=no])
|
||||
if test "${use_gcov}" = "yes" ; then
|
||||
USE_GCOV=1
|
||||
else
|
||||
USE_GCOV=0
|
||||
fi
|
||||
AC_SUBST(USE_GCOV)
|
||||
|
||||
|
||||
#########
|
||||
# Output the config header
|
||||
AC_CONFIG_HEADERS(config.h)
|
||||
# Figure out whether or not we have a "usleep()" function.
|
||||
#
|
||||
AC_CHECK_FUNC(usleep, [TARGET_CFLAGS="$TARGET_CFLAGS -DHAVE_USLEEP=1"])
|
||||
|
||||
#########
|
||||
# Generate the output files.
|
||||
#
|
||||
AC_SUBST(BUILD_CFLAGS)
|
||||
AC_OUTPUT([
|
||||
Makefile
|
||||
sqlite3.pc
|
||||
|
||||
+2
-2
@@ -282,7 +282,7 @@ tokens) and it honors the same commenting conventions as C and C++.</p>
|
||||
<p>A terminal symbol (token) is any string of alphanumeric
|
||||
and underscore characters
|
||||
that begins with an upper case letter.
|
||||
A terminal can contain lowercase letters after the first character,
|
||||
A terminal can contain lower class letters after the first character,
|
||||
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 lower case letter.
|
||||
@@ -481,7 +481,7 @@ as follows:
|
||||
<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 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
|
||||
|
||||
@@ -1,76 +0,0 @@
|
||||
*** Throughout this document, a page is deemed to have been synced
|
||||
automatically as soon as it is written when PRAGMA synchronous=OFF.
|
||||
Otherwise, the page is not synced until the xSync method of the VFS
|
||||
is called successfully on the file containing the page.
|
||||
|
||||
*** Definition: A page of the database file is said to be "overwriteable" if
|
||||
one or more of the following are true about the page:
|
||||
|
||||
(a) The original content of the page as it was at the beginning of
|
||||
the transaction has been written into the rollback journal and
|
||||
synced.
|
||||
|
||||
(b) The page was a freelist leaf page at the start of the transaction.
|
||||
|
||||
(c) The page number is greater than the largest page that existed in
|
||||
the database file at the start of the transaction.
|
||||
|
||||
(1) A page of the database file is never overwritten unless one of the
|
||||
following are true:
|
||||
|
||||
(a) The page and all other pages on the same sector are overwriteable.
|
||||
|
||||
(b) The atomic page write optimization is enabled, and the entire
|
||||
transaction other than the update of the transaction sequence
|
||||
number consists of a single page change.
|
||||
|
||||
(2) The content of a page written into the rollback journal exactly matches
|
||||
both the content in the database when the rollback journal was written
|
||||
and the content in the database at the beginning of the current
|
||||
transaction.
|
||||
|
||||
(3) Writes to the database file are an integer multiple of the page size
|
||||
in length and are aligned to a page boundary.
|
||||
|
||||
(4) Reads from the database file are either aligned on a page boundary and
|
||||
an integer multiple of the page size in length or are taken from the
|
||||
first 100 bytes of the database file.
|
||||
|
||||
(5) All writes to the database file are synced prior to the rollback journal
|
||||
being deleted, truncated, or zeroed.
|
||||
|
||||
(6) If a master journal file is used, then all writes to the database file
|
||||
are synced prior to the master journal being deleted.
|
||||
|
||||
*** 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
|
||||
pages can be changed arbitarily without effecting the logical equivalence
|
||||
of the database.
|
||||
|
||||
(7) At any time, if any subset, including the empty set and the total set,
|
||||
of the unsynced changes to a rollback journal are removed and the
|
||||
journal is rolled back, the resulting database file will be logical
|
||||
equivalent to the database file at the beginning of the transaction.
|
||||
|
||||
(8) When a transaction is rolled back, the xTruncate method of the VFS
|
||||
is called to restore the database file to the same size it was at
|
||||
the beginning of the transaction. (In some VFSes, the xTruncate
|
||||
method is a no-op, but that does not change the fact the SQLite will
|
||||
invoke it.)
|
||||
|
||||
(9) Whenever the database file is modified, at least one bit in the range
|
||||
of bytes from 24 through 39 inclusive will be changed prior to releasing
|
||||
the EXCLUSIVE lock.
|
||||
|
||||
(10) The pattern of bits in bytes 24 through 39 shall not repeat in less
|
||||
than one billion transactions.
|
||||
|
||||
(11) A database file is well-formed at the beginning and at the conclusion
|
||||
of every transaction.
|
||||
|
||||
(12) An EXCLUSIVE lock must be held on the database file before making
|
||||
any changes to the database file.
|
||||
|
||||
(13) A SHARED lock must be held on the database file before reading any
|
||||
content out of the database file.
|
||||
+121
@@ -0,0 +1,121 @@
|
||||
An SQLite (version 1.0) database was used in a large military application
|
||||
where the database contained 105 tables and indices. The following is
|
||||
a breakdown on the sizes of keys and data within these tables and indices:
|
||||
|
||||
Entries: 967089
|
||||
Size: 45896104
|
||||
Avg Size: 48
|
||||
Key Size: 11112265
|
||||
Avg Key Size: 12
|
||||
Max Key Size: 99
|
||||
|
||||
0..8 263 0%
|
||||
9..12 5560 0%
|
||||
13..16 71394 7%
|
||||
17..24 180717 26%
|
||||
25..32 215442 48%
|
||||
33..40 151118 64%
|
||||
41..48 77479 72%
|
||||
49..56 13983 74%
|
||||
57..64 14481 75%
|
||||
65..80 41342 79%
|
||||
81..96 127098 92%
|
||||
97..112 38054 96%
|
||||
113..128 14197 98%
|
||||
129..144 8208 99%
|
||||
145..160 3326 99%
|
||||
161..176 1242 99%
|
||||
177..192 604 99%
|
||||
193..208 222 99%
|
||||
209..224 213 99%
|
||||
225..240 132 99%
|
||||
241..256 58 99%
|
||||
257..288 515 99%
|
||||
289..320 64 99%
|
||||
321..352 39 99%
|
||||
353..384 44 99%
|
||||
385..416 25 99%
|
||||
417..448 24 99%
|
||||
449..480 26 99%
|
||||
481..512 27 99%
|
||||
513..1024 470 99%
|
||||
1025..2048 396 99%
|
||||
2049..4096 187 99%
|
||||
4097..8192 78 99%
|
||||
8193..16384 35 99%
|
||||
16385..32768 17 99%
|
||||
32769..65536 6 99%
|
||||
65537..65541 3 100%
|
||||
|
||||
If the indices are omitted, the statistics for the 49 tables
|
||||
become the following:
|
||||
|
||||
Entries: 451103
|
||||
Size: 30930282
|
||||
Avg Size: 69
|
||||
Key Size: 1804412
|
||||
Avg Key Size: 4
|
||||
Max Key Size: 4
|
||||
|
||||
0..24 89 0%
|
||||
25..32 9417 2%
|
||||
33..40 119162 28%
|
||||
41..48 68710 43%
|
||||
49..56 9539 45%
|
||||
57..64 12435 48%
|
||||
65..80 38650 57%
|
||||
81..96 126877 85%
|
||||
97..112 38030 93%
|
||||
113..128 14183 96%
|
||||
129..144 7668 98%
|
||||
145..160 3302 99%
|
||||
161..176 1238 99%
|
||||
177..192 597 99%
|
||||
193..208 217 99%
|
||||
209..224 211 99%
|
||||
225..240 130 99%
|
||||
241..256 57 99%
|
||||
257..288 100 99%
|
||||
289..320 62 99%
|
||||
321..352 34 99%
|
||||
353..384 43 99%
|
||||
385..416 24 99%
|
||||
417..448 24 99%
|
||||
449..480 25 99%
|
||||
481..512 27 99%
|
||||
513..1024 153 99%
|
||||
1025..2048 92 99%
|
||||
2049..4096 7 100%
|
||||
|
||||
The 56 indices have these statistics:
|
||||
|
||||
Entries: 512422
|
||||
Size: 14879828
|
||||
Avg Size: 30
|
||||
Key Size: 9253204
|
||||
Avg Key Size: 19
|
||||
Max Key Size: 99
|
||||
|
||||
0..8 246 0%
|
||||
9..12 5486 1%
|
||||
13..16 70717 14%
|
||||
17..24 178246 49%
|
||||
25..32 205722 89%
|
||||
33..40 31951 96%
|
||||
41..48 8768 97%
|
||||
49..56 4444 98%
|
||||
57..64 2046 99%
|
||||
65..80 2691 99%
|
||||
81..96 202 99%
|
||||
97..112 11 99%
|
||||
113..144 527 99%
|
||||
145..160 20 99%
|
||||
161..288 406 99%
|
||||
289..1024 316 99%
|
||||
1025..2048 304 99%
|
||||
2049..4096 180 99%
|
||||
4097..8192 78 99%
|
||||
8193..16384 35 99%
|
||||
16385..32768 17 99%
|
||||
32769..65536 6 99%
|
||||
65537..65541 3 100%
|
||||
-130
@@ -1,130 +0,0 @@
|
||||
The 5 states of an historical rollback lock as implemented by the
|
||||
xLock, xUnlock, and xCheckReservedLock methods of the sqlite3_io_methods
|
||||
objec are:
|
||||
|
||||
UNLOCKED
|
||||
SHARED
|
||||
RESERVED
|
||||
PENDING
|
||||
EXCLUSIVE
|
||||
|
||||
The wal-index file has a similar locking hierarchy implemented using
|
||||
the xShmLock method of the sqlite3_vfs object, but with 7
|
||||
states. Each connection to a wal-index file must be in one of
|
||||
the following 7 states:
|
||||
|
||||
UNLOCKED
|
||||
READ
|
||||
READ_FULL
|
||||
WRITE
|
||||
PENDING
|
||||
CHECKPOINT
|
||||
RECOVER
|
||||
|
||||
These roughly correspond to the 5 states of a rollback lock except
|
||||
that SHARED is split out into 2 states: READ and READ_FULL and
|
||||
there is an extra RECOVER state used for wal-index reconstruction.
|
||||
|
||||
The meanings of the various wal-index locking states is as follows:
|
||||
|
||||
UNLOCKED - The wal-index is not in use.
|
||||
|
||||
READ - Some prefix of the wal-index is being read. Additional
|
||||
wal-index information can be appended at any time. The
|
||||
newly appended content will be ignored by the holder of
|
||||
the READ lock.
|
||||
|
||||
READ_FULL - The entire wal-index is being read. No new information
|
||||
can be added to the wal-index. The holder of a READ_FULL
|
||||
lock promises never to read pages from the database file
|
||||
that are available anywhere in the wal-index.
|
||||
|
||||
WRITE - It is OK to append to the wal-index file and to adjust
|
||||
the header to indicate the new "last valid frame".
|
||||
|
||||
PENDING - Waiting on all READ locks to clear so that a
|
||||
CHECKPOINT lock can be acquired.
|
||||
|
||||
CHECKPOINT - It is OK to write any WAL data into the database file
|
||||
and zero the last valid frame field of the wal-index
|
||||
header. The wal-index file itself may not be changed
|
||||
other than to zero the last valid frame field in the
|
||||
header.
|
||||
|
||||
RECOVER - Held during wal-index recovery. Used to prevent a
|
||||
race if multiple clients try to recover a wal-index at
|
||||
the same time.
|
||||
|
||||
|
||||
A particular lock manager implementation may coalesce one or more of
|
||||
the wal-index locking states, though with a reduction in concurrency.
|
||||
For example, an implemention might implement only exclusive locking,
|
||||
in which case all states would be equivalent to CHECKPOINT, meaning that
|
||||
only one reader or one writer or one checkpointer could be active at a
|
||||
time. Or, an implementation might combine READ and READ_FULL into
|
||||
a single state equivalent to READ, meaning that a writer could
|
||||
coexist with a reader, but no reader or writers could coexist with a
|
||||
checkpointer.
|
||||
|
||||
The lock manager must obey the following rules:
|
||||
|
||||
(1) A READ cannot coexist with CHECKPOINT.
|
||||
(2) A READ_FULL cannot coexist with WRITE.
|
||||
(3) None of WRITE, PENDING, CHECKPOINT, or RECOVER can coexist.
|
||||
|
||||
The SQLite core will obey the next set of rules. These rules are
|
||||
assertions on the behavior of the SQLite core which might be verified
|
||||
during testing using an instrumented lock manager.
|
||||
|
||||
(5) No part of the wal-index will be read without holding either some
|
||||
kind of SHM lock or an EXCLUSIVE lock on the original database.
|
||||
The original database is the file named in the 2nd parameter to
|
||||
the xShmOpen method.
|
||||
|
||||
(6) A holder of a READ_FULL will never read any page of the database
|
||||
file that is contained anywhere in the wal-index.
|
||||
|
||||
(7) No part of the wal-index other than the header will be written nor
|
||||
will the size of the wal-index grow without holding a WRITE or
|
||||
an EXCLUSIVE on the original database file.
|
||||
|
||||
(8) The wal-index header will not be written without holding one of
|
||||
WRITE, CHECKPOINT, or RECOVER on the wal-index or an EXCLUSIVE on
|
||||
the original database files.
|
||||
|
||||
(9) A CHECKPOINT or RECOVER must be held on the wal-index, or an
|
||||
EXCLUSIVE on the original database file, in order to reset the
|
||||
last valid frame counter in the header of the wal-index back to zero.
|
||||
|
||||
(10) A WRITE can only increase the last valid frame pointer in the header.
|
||||
|
||||
The SQLite core will only ever send requests for UNLOCK, READ, WRITE,
|
||||
CHECKPOINT, or RECOVER to the lock manager. The SQLite core will never
|
||||
request a READ_FULL or PENDING lock though the lock manager may deliver
|
||||
those locking states in response to READ and CHECKPOINT requests,
|
||||
respectively, if and only if the requested READ or CHECKPOINT cannot
|
||||
be delivered.
|
||||
|
||||
The following are the allowed lock transitions:
|
||||
|
||||
Original-State Request New-State
|
||||
-------------- ---------- ----------
|
||||
(11a) UNLOCK READ READ
|
||||
(11b) UNLOCK READ READ_FULL
|
||||
(11c) UNLOCK CHECKPOINT PENDING
|
||||
(11d) UNLOCK CHECKPOINT CHECKPOINT
|
||||
(11e) READ UNLOCK UNLOCK
|
||||
(11f) READ WRITE WRITE
|
||||
(11g) READ RECOVER RECOVER
|
||||
(11h) READ_FULL UNLOCK UNLOCK
|
||||
(11i) READ_FULL WRITE WRITE
|
||||
(11j) READ_FULL RECOVER RECOVER
|
||||
(11k) WRITE READ READ
|
||||
(11l) PENDING UNLOCK UNLOCK
|
||||
(11m) PENDING CHECKPOINT CHECKPOINT
|
||||
(11n) CHECKPOINT UNLOCK UNLOCK
|
||||
(11o) RECOVER READ READ
|
||||
|
||||
These 15 transitions are all that needs to be supported. The lock
|
||||
manager implementation can assert that fact. The other 27 possible
|
||||
transitions among the 7 locking states will never occur.
|
||||
@@ -1,2 +0,0 @@
|
||||
Version loadable extensions to SQLite are found in subfolders
|
||||
of this folder.
|
||||
@@ -1,170 +0,0 @@
|
||||
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.
|
||||
Since writing to the file-system is usually very slow compared with CPU
|
||||
bound operations, this can be a performance bottleneck. This directory
|
||||
contains an extension that causes SQLite to perform all write requests
|
||||
using a separate thread running in the background. Although this does not
|
||||
reduce the overall system resources (CPU, disk bandwidth etc.) at all, it
|
||||
allows SQLite to return control to the caller quickly even when writing to
|
||||
the database, eliminating the bottleneck.
|
||||
|
||||
1. Functionality
|
||||
|
||||
1.1 How it Works
|
||||
1.2 Limitations
|
||||
1.3 Locking and Concurrency
|
||||
|
||||
2. Compilation and Usage
|
||||
|
||||
3. Porting
|
||||
|
||||
|
||||
|
||||
1. FUNCTIONALITY
|
||||
|
||||
With asynchronous I/O, write requests are handled by a separate thread
|
||||
running in the background. This means that the thread that initiates
|
||||
a database write does not have to wait for (sometimes slow) disk I/O
|
||||
to occur. The write seems to happen very quickly, though in reality
|
||||
it is happening at its usual slow pace in the background.
|
||||
|
||||
Asynchronous I/O appears to give better responsiveness, but at a price.
|
||||
You lose the Durable property. With the default I/O backend of SQLite,
|
||||
once a write completes, you know that the information you wrote is
|
||||
safely on disk. With the asynchronous I/O, this is not the case. If
|
||||
your program crashes or if a power loss occurs after the database
|
||||
write but before the asynchronous write thread has completed, then the
|
||||
database change might never make it to disk and the next user of the
|
||||
database might not see your change.
|
||||
|
||||
You lose Durability with asynchronous I/O, but you still retain the
|
||||
other parts of ACID: Atomic, Consistent, and Isolated. Many
|
||||
appliations get along fine without the Durablity.
|
||||
|
||||
1.1 How it Works
|
||||
|
||||
Asynchronous I/O works by creating a special SQLite "vfs" structure
|
||||
and registering it with sqlite3_vfs_register(). When files opened via
|
||||
this vfs are written to (using the vfs xWrite() method), the data is not
|
||||
written directly to disk, but is placed in the "write-queue" to be
|
||||
handled by the background thread.
|
||||
|
||||
When files opened with the asynchronous vfs are read from
|
||||
(using the vfs xRead() method), the data is read from the file on
|
||||
disk and the write-queue, so that from the point of view of
|
||||
the vfs reader the xWrite() appears to have already completed.
|
||||
|
||||
The special vfs is registered (and unregistered) by calls to the
|
||||
API functions sqlite3async_initialize() and sqlite3async_shutdown().
|
||||
See section "Compilation and Usage" below for details.
|
||||
|
||||
1.2 Limitations
|
||||
|
||||
In order to gain experience with the main ideas surrounding asynchronous
|
||||
IO, this implementation is deliberately kept simple. Additional
|
||||
capabilities may be added in the future.
|
||||
|
||||
For example, as currently implemented, if writes are happening at a
|
||||
steady stream that exceeds the I/O capability of the background writer
|
||||
thread, the queue of pending write operations will grow without bound.
|
||||
If this goes on for long enough, the host system could run out of memory.
|
||||
A more sophisticated module could to keep track of the quantity of
|
||||
pending writes and stop accepting new write requests when the queue of
|
||||
pending writes grows too large.
|
||||
|
||||
1.3 Locking and Concurrency
|
||||
|
||||
Multiple connections from within a single process that use this
|
||||
implementation of asynchronous IO may access a single database
|
||||
file concurrently. From the point of view of the user, if all
|
||||
connections are from within a single process, there is no difference
|
||||
between the concurrency offered by "normal" SQLite and SQLite
|
||||
using the asynchronous backend.
|
||||
|
||||
If file-locking is enabled (it is enabled by default), then connections
|
||||
from multiple processes may also read and write the database file.
|
||||
However concurrency is reduced as follows:
|
||||
|
||||
* When a connection using asynchronous IO begins a database
|
||||
transaction, the database is locked immediately. However the
|
||||
lock is not released until after all relevant operations
|
||||
in the write-queue have been flushed to disk. This means
|
||||
(for example) that the database may remain locked for some
|
||||
time after a "COMMIT" or "ROLLBACK" is issued.
|
||||
|
||||
* If an application using asynchronous IO executes transactions
|
||||
in quick succession, other database users may be effectively
|
||||
locked out of the database. This is because when a BEGIN
|
||||
is executed, a database lock is established immediately. But
|
||||
when the corresponding COMMIT or ROLLBACK occurs, the lock
|
||||
is not released until the relevant part of the write-queue
|
||||
has been flushed through. As a result, if a COMMIT is followed
|
||||
by a BEGIN before the write-queue is flushed through, the database
|
||||
is never unlocked,preventing other processes from accessing
|
||||
the database.
|
||||
|
||||
File-locking may be disabled at runtime using the sqlite3async_control()
|
||||
API (see below). This may improve performance when an NFS or other
|
||||
network file-system, as the synchronous round-trips to the server be
|
||||
required to establish file locks are avoided. However, if multiple
|
||||
connections attempt to access the same database file when file-locking
|
||||
is disabled, application crashes and database corruption is a likely
|
||||
outcome.
|
||||
|
||||
|
||||
2. COMPILATION AND USAGE
|
||||
|
||||
The asynchronous IO extension consists of a single file of C code
|
||||
(sqlite3async.c), and a header file (sqlite3async.h) that defines the
|
||||
C API used by applications to activate and control the modules
|
||||
functionality.
|
||||
|
||||
To use the asynchronous IO extension, compile sqlite3async.c as
|
||||
part of the application that uses SQLite. Then use the API defined
|
||||
in sqlite3async.h to initialize and configure the module.
|
||||
|
||||
The asynchronous IO VFS API is described in detail in comments in
|
||||
sqlite3async.h. Using the API usually consists of the following steps:
|
||||
|
||||
1. Register the asynchronous IO VFS with SQLite by calling the
|
||||
sqlite3async_initialize() function.
|
||||
|
||||
2. Create a background thread to perform write operations and call
|
||||
sqlite3async_run().
|
||||
|
||||
3. Use the normal SQLite API to read and write to databases via
|
||||
the asynchronous IO VFS.
|
||||
|
||||
Refer to sqlite3async.h for details.
|
||||
|
||||
|
||||
3. PORTING
|
||||
|
||||
Currently the asynchronous IO extension is compatible with win32 systems
|
||||
and systems that support the pthreads interface, including Mac OSX, Linux,
|
||||
and other varieties of Unix.
|
||||
|
||||
To port the asynchronous IO extension to another platform, the user must
|
||||
implement mutex and condition variable primitives for the new platform.
|
||||
Currently there is no externally available interface to allow this, but
|
||||
modifying the code within sqlite3async.c to include the new platforms
|
||||
concurrency primitives is relatively easy. Search within sqlite3async.c
|
||||
for the comment string "PORTING FUNCTIONS" for details. Then implement
|
||||
new versions of each of the following:
|
||||
|
||||
static void async_mutex_enter(int eMutex);
|
||||
static void async_mutex_leave(int eMutex);
|
||||
static void async_cond_wait(int eCond, int eMutex);
|
||||
static void async_cond_signal(int eCond);
|
||||
static void async_sched_yield(void);
|
||||
|
||||
The functionality required of each of the above functions is described
|
||||
in comments in sqlite3async.c.
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,223 +0,0 @@
|
||||
|
||||
#ifndef __SQLITEASYNC_H_
|
||||
#define __SQLITEASYNC_H_ 1
|
||||
|
||||
/*
|
||||
** Make sure we can call this stuff from C++.
|
||||
*/
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#define SQLITEASYNC_VFSNAME "sqlite3async"
|
||||
|
||||
/*
|
||||
** THREAD SAFETY NOTES:
|
||||
**
|
||||
** Of the four API functions in this file, the following are not threadsafe:
|
||||
**
|
||||
** sqlite3async_initialize()
|
||||
** sqlite3async_shutdown()
|
||||
**
|
||||
** Care must be taken that neither of these functions is called while
|
||||
** another thread may be calling either any sqlite3async_XXX() function
|
||||
** or an sqlite3_XXX() API function related to a database handle that
|
||||
** is using the asynchronous IO VFS.
|
||||
**
|
||||
** These functions:
|
||||
**
|
||||
** sqlite3async_run()
|
||||
** sqlite3async_control()
|
||||
**
|
||||
** are threadsafe. It is quite safe to call either of these functions even
|
||||
** if another thread may also be calling one of them or an sqlite3_XXX()
|
||||
** function related to a database handle that uses the asynchronous IO VFS.
|
||||
*/
|
||||
|
||||
/*
|
||||
** Initialize the asynchronous IO VFS and register it with SQLite using
|
||||
** sqlite3_vfs_register(). If the asynchronous VFS is already initialized
|
||||
** and registered, this function is a no-op. The asynchronous IO VFS
|
||||
** is registered as "sqlite3async".
|
||||
**
|
||||
** The asynchronous IO VFS does not make operating system IO requests
|
||||
** directly. Instead, it uses an existing VFS implementation for all
|
||||
** required file-system operations. If the first parameter to this function
|
||||
** is NULL, then the current default VFS is used for IO. If it is not
|
||||
** NULL, then it must be the name of an existing VFS. In other words, the
|
||||
** first argument to this function is passed to sqlite3_vfs_find() to
|
||||
** locate the VFS to use for all real IO operations. This VFS is known
|
||||
** as the "parent VFS".
|
||||
**
|
||||
** If the second parameter to this function is non-zero, then the
|
||||
** asynchronous IO VFS is registered as the default VFS for all SQLite
|
||||
** database connections within the process. Otherwise, the asynchronous IO
|
||||
** VFS is only used by connections opened using sqlite3_open_v2() that
|
||||
** specifically request VFS "sqlite3async".
|
||||
**
|
||||
** If a parent VFS cannot be located, then SQLITE_ERROR is returned.
|
||||
** In the unlikely event that operating system specific initialization
|
||||
** fails (win32 systems create the required critical section and event
|
||||
** objects within this function), then SQLITE_ERROR is also returned.
|
||||
** Finally, if the call to sqlite3_vfs_register() returns an error, then
|
||||
** the error code is returned to the user by this function. In all three
|
||||
** of these cases, intialization has failed and the asynchronous IO VFS
|
||||
** is not registered with SQLite.
|
||||
**
|
||||
** Otherwise, if no error occurs, SQLITE_OK is returned.
|
||||
*/
|
||||
int sqlite3async_initialize(const char *zParent, int isDefault);
|
||||
|
||||
/*
|
||||
** This function unregisters the asynchronous IO VFS using
|
||||
** sqlite3_vfs_unregister().
|
||||
**
|
||||
** On win32 platforms, this function also releases the small number of
|
||||
** critical section and event objects created by sqlite3async_initialize().
|
||||
*/
|
||||
void sqlite3async_shutdown(void);
|
||||
|
||||
/*
|
||||
** This function may only be called when the asynchronous IO VFS is
|
||||
** installed (after a call to sqlite3async_initialize()). It processes
|
||||
** zero or more queued write operations before returning. It is expected
|
||||
** (but not required) that this function will be called by a different
|
||||
** thread than those threads that use SQLite. The "background thread"
|
||||
** that performs IO.
|
||||
**
|
||||
** How many queued write operations are performed before returning
|
||||
** depends on the global setting configured by passing the SQLITEASYNC_HALT
|
||||
** verb to sqlite3async_control() (see below for details). By default
|
||||
** this function never returns - it processes all pending operations and
|
||||
** then blocks waiting for new ones.
|
||||
**
|
||||
** If multiple simultaneous calls are made to sqlite3async_run() from two
|
||||
** or more threads, then the calls are serialized internally.
|
||||
*/
|
||||
void sqlite3async_run(void);
|
||||
|
||||
/*
|
||||
** This function may only be called when the asynchronous IO VFS is
|
||||
** installed (after a call to sqlite3async_initialize()). It is used
|
||||
** to query or configure various parameters that affect the operation
|
||||
** of the asynchronous IO VFS. At present there are three parameters
|
||||
** supported:
|
||||
**
|
||||
** * The "halt" parameter, which configures the circumstances under
|
||||
** which the sqlite3async_run() parameter is configured.
|
||||
**
|
||||
** * The "delay" parameter. Setting the delay parameter to a non-zero
|
||||
** value causes the sqlite3async_run() function to sleep for the
|
||||
** configured number of milliseconds between each queued write
|
||||
** operation.
|
||||
**
|
||||
** * The "lockfiles" parameter. This parameter determines whether or
|
||||
** not the asynchronous IO VFS locks the database files it operates
|
||||
** on. Disabling file locking can improve throughput.
|
||||
**
|
||||
** This function is always passed two arguments. When setting the value
|
||||
** of a parameter, the first argument must be one of SQLITEASYNC_HALT,
|
||||
** SQLITEASYNC_DELAY or SQLITEASYNC_LOCKFILES. The second argument must
|
||||
** be passed the new value for the parameter as type "int".
|
||||
**
|
||||
** When querying the current value of a paramter, the first argument must
|
||||
** be one of SQLITEASYNC_GET_HALT, GET_DELAY or GET_LOCKFILES. The second
|
||||
** argument to this function must be of type (int *). The current value
|
||||
** of the queried parameter is copied to the memory pointed to by the
|
||||
** second argument. For example:
|
||||
**
|
||||
** int eCurrentHalt;
|
||||
** int eNewHalt = SQLITEASYNC_HALT_IDLE;
|
||||
**
|
||||
** sqlite3async_control(SQLITEASYNC_HALT, eNewHalt);
|
||||
** sqlite3async_control(SQLITEASYNC_GET_HALT, &eCurrentHalt);
|
||||
** assert( eNewHalt==eCurrentHalt );
|
||||
**
|
||||
** See below for more detail on each configuration parameter.
|
||||
**
|
||||
** SQLITEASYNC_HALT:
|
||||
**
|
||||
** This is used to set the value of the "halt" parameter. The second
|
||||
** argument must be one of the SQLITEASYNC_HALT_XXX symbols defined
|
||||
** below (either NEVER, IDLE and NOW).
|
||||
**
|
||||
** If the parameter is set to NEVER, then calls to sqlite3async_run()
|
||||
** never return. This is the default setting. If the parameter is set
|
||||
** to IDLE, then calls to sqlite3async_run() return as soon as the
|
||||
** queue of pending write operations is empty. If the parameter is set
|
||||
** to NOW, then calls to sqlite3async_run() return as quickly as
|
||||
** possible, without processing any pending write requests.
|
||||
**
|
||||
** If an attempt is made to set this parameter to an integer value other
|
||||
** than SQLITEASYNC_HALT_NEVER, IDLE or NOW, then sqlite3async_control()
|
||||
** returns SQLITE_MISUSE and the current value of the parameter is not
|
||||
** modified.
|
||||
**
|
||||
** Modifying the "halt" parameter affects calls to sqlite3async_run()
|
||||
** made by other threads that are currently in progress.
|
||||
**
|
||||
** SQLITEASYNC_DELAY:
|
||||
**
|
||||
** This is used to set the value of the "delay" parameter. If set to
|
||||
** a non-zero value, then after completing a pending write request, the
|
||||
** sqlite3async_run() function sleeps for the configured number of
|
||||
** milliseconds.
|
||||
**
|
||||
** If an attempt is made to set this parameter to a negative value,
|
||||
** sqlite3async_control() returns SQLITE_MISUSE and the current value
|
||||
** of the parameter is not modified.
|
||||
**
|
||||
** Modifying the "delay" parameter affects calls to sqlite3async_run()
|
||||
** made by other threads that are currently in progress.
|
||||
**
|
||||
** SQLITEASYNC_LOCKFILES:
|
||||
**
|
||||
** This is used to set the value of the "lockfiles" parameter. This
|
||||
** parameter must be set to either 0 or 1. If set to 1, then the
|
||||
** asynchronous IO VFS uses the xLock() and xUnlock() methods of the
|
||||
** parent VFS to lock database files being read and/or written. If
|
||||
** the parameter is set to 0, then these locks are omitted.
|
||||
**
|
||||
** This parameter may only be set when there are no open database
|
||||
** connections using the VFS and the queue of pending write requests
|
||||
** is empty. Attempting to set it when this is not true, or to set it
|
||||
** to a value other than 0 or 1 causes sqlite3async_control() to return
|
||||
** SQLITE_MISUSE and the value of the parameter to remain unchanged.
|
||||
**
|
||||
** If this parameter is set to zero, then it is only safe to access the
|
||||
** database via the asynchronous IO VFS from within a single process. If
|
||||
** while writing to the database via the asynchronous IO VFS the database
|
||||
** is also read or written from within another process, or via another
|
||||
** connection that does not use the asynchronous IO VFS within the same
|
||||
** process, the results are undefined (and may include crashes or database
|
||||
** corruption).
|
||||
**
|
||||
** Alternatively, if this parameter is set to 1, then it is safe to access
|
||||
** the database from multiple connections within multiple processes using
|
||||
** either the asynchronous IO VFS or the parent VFS directly.
|
||||
*/
|
||||
int sqlite3async_control(int op, ...);
|
||||
|
||||
/*
|
||||
** Values that can be used as the first argument to sqlite3async_control().
|
||||
*/
|
||||
#define SQLITEASYNC_HALT 1
|
||||
#define SQLITEASYNC_GET_HALT 2
|
||||
#define SQLITEASYNC_DELAY 3
|
||||
#define SQLITEASYNC_GET_DELAY 4
|
||||
#define SQLITEASYNC_LOCKFILES 5
|
||||
#define SQLITEASYNC_GET_LOCKFILES 6
|
||||
|
||||
/*
|
||||
** If the first argument to sqlite3async_control() is SQLITEASYNC_HALT,
|
||||
** the second argument should be one of the following.
|
||||
*/
|
||||
#define SQLITEASYNC_HALT_NEVER 0 /* Never halt (default value) */
|
||||
#define SQLITEASYNC_HALT_NOW 1 /* Halt as soon as possible */
|
||||
#define SQLITEASYNC_HALT_IDLE 2 /* Halt when write-queue is empty */
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* End of the 'extern "C"' block */
|
||||
#endif
|
||||
#endif /* ifndef __SQLITEASYNC_H_ */
|
||||
|
||||
@@ -1,2 +0,0 @@
|
||||
This folder contains source code to the first full-text search
|
||||
extension for SQLite.
|
||||
@@ -1,404 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the implementation of generic hash-tables used in SQLite.
|
||||
** We've modified it slightly to serve as a standalone hash table
|
||||
** implementation for the full-text indexing module.
|
||||
*/
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "ft_hash.h"
|
||||
|
||||
void *malloc_and_zero(int n){
|
||||
void *p = malloc(n);
|
||||
if( p ){
|
||||
memset(p, 0, n);
|
||||
}
|
||||
return p;
|
||||
}
|
||||
|
||||
/* Turn bulk memory into a hash table object by initializing the
|
||||
** fields of the Hash structure.
|
||||
**
|
||||
** "pNew" is a pointer to the hash table that is to be initialized.
|
||||
** keyClass is one of the constants HASH_INT, HASH_POINTER,
|
||||
** HASH_BINARY, or HASH_STRING. The value of keyClass
|
||||
** determines what kind of key the hash table will use. "copyKey" is
|
||||
** true if the hash table should make its own private copy of keys and
|
||||
** false if it should just use the supplied pointer. CopyKey only makes
|
||||
** sense for HASH_STRING and HASH_BINARY and is ignored
|
||||
** for other key classes.
|
||||
*/
|
||||
void HashInit(Hash *pNew, int keyClass, int copyKey){
|
||||
assert( pNew!=0 );
|
||||
assert( keyClass>=HASH_STRING && keyClass<=HASH_BINARY );
|
||||
pNew->keyClass = keyClass;
|
||||
#if 0
|
||||
if( keyClass==HASH_POINTER || keyClass==HASH_INT ) copyKey = 0;
|
||||
#endif
|
||||
pNew->copyKey = copyKey;
|
||||
pNew->first = 0;
|
||||
pNew->count = 0;
|
||||
pNew->htsize = 0;
|
||||
pNew->ht = 0;
|
||||
pNew->xMalloc = malloc_and_zero;
|
||||
pNew->xFree = free;
|
||||
}
|
||||
|
||||
/* Remove all entries from a hash table. Reclaim all memory.
|
||||
** Call this routine to delete a hash table or to reset a hash table
|
||||
** to the empty state.
|
||||
*/
|
||||
void HashClear(Hash *pH){
|
||||
HashElem *elem; /* For looping over all elements of the table */
|
||||
|
||||
assert( pH!=0 );
|
||||
elem = pH->first;
|
||||
pH->first = 0;
|
||||
if( pH->ht ) pH->xFree(pH->ht);
|
||||
pH->ht = 0;
|
||||
pH->htsize = 0;
|
||||
while( elem ){
|
||||
HashElem *next_elem = elem->next;
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
pH->xFree(elem->pKey);
|
||||
}
|
||||
pH->xFree(elem);
|
||||
elem = next_elem;
|
||||
}
|
||||
pH->count = 0;
|
||||
}
|
||||
|
||||
#if 0 /* NOT USED */
|
||||
/*
|
||||
** Hash and comparison functions when the mode is HASH_INT
|
||||
*/
|
||||
static int intHash(const void *pKey, int nKey){
|
||||
return nKey ^ (nKey<<8) ^ (nKey>>8);
|
||||
}
|
||||
static int intCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
return n2 - n1;
|
||||
}
|
||||
#endif
|
||||
|
||||
#if 0 /* NOT USED */
|
||||
/*
|
||||
** Hash and comparison functions when the mode is HASH_POINTER
|
||||
*/
|
||||
static int ptrHash(const void *pKey, int nKey){
|
||||
uptr x = Addr(pKey);
|
||||
return x ^ (x<<8) ^ (x>>8);
|
||||
}
|
||||
static int ptrCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( pKey1==pKey2 ) return 0;
|
||||
if( pKey1<pKey2 ) return -1;
|
||||
return 1;
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is HASH_STRING
|
||||
*/
|
||||
static int strHash(const void *pKey, int nKey){
|
||||
const char *z = (const char *)pKey;
|
||||
int h = 0;
|
||||
if( nKey<=0 ) nKey = (int) strlen(z);
|
||||
while( nKey > 0 ){
|
||||
h = (h<<3) ^ h ^ *z++;
|
||||
nKey--;
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int strCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return strncmp((const char*)pKey1,(const char*)pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is HASH_BINARY
|
||||
*/
|
||||
static int binHash(const void *pKey, int nKey){
|
||||
int h = 0;
|
||||
const char *z = (const char *)pKey;
|
||||
while( nKey-- > 0 ){
|
||||
h = (h<<3) ^ h ^ *(z++);
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int binCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return memcmp(pKey1,pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** The C syntax in this function definition may be unfamilar to some
|
||||
** programmers, so we provide the following additional explanation:
|
||||
**
|
||||
** The name of the function is "hashFunction". The function takes a
|
||||
** single parameter "keyClass". The return value of hashFunction()
|
||||
** is a pointer to another function. Specifically, the return value
|
||||
** of hashFunction() is a pointer to a function that takes two parameters
|
||||
** with types "const void*" and "int" and returns an "int".
|
||||
*/
|
||||
static int (*hashFunction(int keyClass))(const void*,int){
|
||||
#if 0 /* HASH_INT and HASH_POINTER are never used */
|
||||
switch( keyClass ){
|
||||
case HASH_INT: return &intHash;
|
||||
case HASH_POINTER: return &ptrHash;
|
||||
case HASH_STRING: return &strHash;
|
||||
case HASH_BINARY: return &binHash;;
|
||||
default: break;
|
||||
}
|
||||
return 0;
|
||||
#else
|
||||
if( keyClass==HASH_STRING ){
|
||||
return &strHash;
|
||||
}else{
|
||||
assert( keyClass==HASH_BINARY );
|
||||
return &binHash;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** For help in interpreted the obscure C code in the function definition,
|
||||
** see the header comment on the previous function.
|
||||
*/
|
||||
static int (*compareFunction(int keyClass))(const void*,int,const void*,int){
|
||||
#if 0 /* HASH_INT and HASH_POINTER are never used */
|
||||
switch( keyClass ){
|
||||
case HASH_INT: return &intCompare;
|
||||
case HASH_POINTER: return &ptrCompare;
|
||||
case HASH_STRING: return &strCompare;
|
||||
case HASH_BINARY: return &binCompare;
|
||||
default: break;
|
||||
}
|
||||
return 0;
|
||||
#else
|
||||
if( keyClass==HASH_STRING ){
|
||||
return &strCompare;
|
||||
}else{
|
||||
assert( keyClass==HASH_BINARY );
|
||||
return &binCompare;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/* Link an element into the hash table
|
||||
*/
|
||||
static void insertElement(
|
||||
Hash *pH, /* The complete hash table */
|
||||
struct _ht *pEntry, /* The entry into which pNew is inserted */
|
||||
HashElem *pNew /* The element to be inserted */
|
||||
){
|
||||
HashElem *pHead; /* First element already in pEntry */
|
||||
pHead = pEntry->chain;
|
||||
if( pHead ){
|
||||
pNew->next = pHead;
|
||||
pNew->prev = pHead->prev;
|
||||
if( pHead->prev ){ pHead->prev->next = pNew; }
|
||||
else { pH->first = pNew; }
|
||||
pHead->prev = pNew;
|
||||
}else{
|
||||
pNew->next = pH->first;
|
||||
if( pH->first ){ pH->first->prev = pNew; }
|
||||
pNew->prev = 0;
|
||||
pH->first = pNew;
|
||||
}
|
||||
pEntry->count++;
|
||||
pEntry->chain = pNew;
|
||||
}
|
||||
|
||||
|
||||
/* Resize the hash table so that it cantains "new_size" buckets.
|
||||
** "new_size" must be a power of 2. The hash table might fail
|
||||
** to resize if sqliteMalloc() fails.
|
||||
*/
|
||||
static void rehash(Hash *pH, int new_size){
|
||||
struct _ht *new_ht; /* The new hash table */
|
||||
HashElem *elem, *next_elem; /* For looping over existing elements */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( (new_size & (new_size-1))==0 );
|
||||
new_ht = (struct _ht *)pH->xMalloc( new_size*sizeof(struct _ht) );
|
||||
if( new_ht==0 ) return;
|
||||
if( pH->ht ) pH->xFree(pH->ht);
|
||||
pH->ht = new_ht;
|
||||
pH->htsize = new_size;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
for(elem=pH->first, pH->first=0; elem; elem = next_elem){
|
||||
int h = (*xHash)(elem->pKey, elem->nKey) & (new_size-1);
|
||||
next_elem = elem->next;
|
||||
insertElement(pH, &new_ht[h], elem);
|
||||
}
|
||||
}
|
||||
|
||||
/* This function (for internal use only) locates an element in an
|
||||
** hash table that matches the given key. The hash for this key has
|
||||
** already been computed and is passed as the 4th parameter.
|
||||
*/
|
||||
static HashElem *findElementGivenHash(
|
||||
const Hash *pH, /* The pH to be searched */
|
||||
const void *pKey, /* The key we are searching for */
|
||||
int nKey,
|
||||
int h /* The hash for this key. */
|
||||
){
|
||||
HashElem *elem; /* Used to loop thru the element list */
|
||||
int count; /* Number of elements left to test */
|
||||
int (*xCompare)(const void*,int,const void*,int); /* comparison function */
|
||||
|
||||
if( pH->ht ){
|
||||
struct _ht *pEntry = &pH->ht[h];
|
||||
elem = pEntry->chain;
|
||||
count = pEntry->count;
|
||||
xCompare = compareFunction(pH->keyClass);
|
||||
while( count-- && elem ){
|
||||
if( (*xCompare)(elem->pKey,elem->nKey,pKey,nKey)==0 ){
|
||||
return elem;
|
||||
}
|
||||
elem = elem->next;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Remove a single entry from the hash table given a pointer to that
|
||||
** element and a hash on the element's key.
|
||||
*/
|
||||
static void removeElementGivenHash(
|
||||
Hash *pH, /* The pH containing "elem" */
|
||||
HashElem* elem, /* The element to be removed from the pH */
|
||||
int h /* Hash value for the element */
|
||||
){
|
||||
struct _ht *pEntry;
|
||||
if( elem->prev ){
|
||||
elem->prev->next = elem->next;
|
||||
}else{
|
||||
pH->first = elem->next;
|
||||
}
|
||||
if( elem->next ){
|
||||
elem->next->prev = elem->prev;
|
||||
}
|
||||
pEntry = &pH->ht[h];
|
||||
if( pEntry->chain==elem ){
|
||||
pEntry->chain = elem->next;
|
||||
}
|
||||
pEntry->count--;
|
||||
if( pEntry->count<=0 ){
|
||||
pEntry->chain = 0;
|
||||
}
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
pH->xFree(elem->pKey);
|
||||
}
|
||||
pH->xFree( elem );
|
||||
pH->count--;
|
||||
if( pH->count<=0 ){
|
||||
assert( pH->first==0 );
|
||||
assert( pH->count==0 );
|
||||
HashClear(pH);
|
||||
}
|
||||
}
|
||||
|
||||
/* Attempt to locate an element of the hash table pH with a key
|
||||
** that matches pKey,nKey. Return the data for this element if it is
|
||||
** found, or NULL if there is no match.
|
||||
*/
|
||||
void *HashFind(const Hash *pH, const void *pKey, int nKey){
|
||||
int h; /* A hash on key */
|
||||
HashElem *elem; /* The element that matches key */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
if( pH==0 || pH->ht==0 ) return 0;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
h = (*xHash)(pKey,nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
elem = findElementGivenHash(pH,pKey,nKey, h & (pH->htsize-1));
|
||||
return elem ? elem->data : 0;
|
||||
}
|
||||
|
||||
/* Insert an element into the hash table pH. The key is pKey,nKey
|
||||
** and the data is "data".
|
||||
**
|
||||
** If no element exists with a matching key, then a new
|
||||
** element is created. A copy of the key is made if the copyKey
|
||||
** flag is set. NULL is returned.
|
||||
**
|
||||
** If another element already exists with the same key, then the
|
||||
** new data replaces the old data and the old data is returned.
|
||||
** The key is not copied in this instance. If a malloc fails, then
|
||||
** the new data is returned and the hash table is unchanged.
|
||||
**
|
||||
** If the "data" parameter to this function is NULL, then the
|
||||
** element corresponding to "key" is removed from the hash table.
|
||||
*/
|
||||
void *HashInsert(Hash *pH, const void *pKey, int nKey, void *data){
|
||||
int hraw; /* Raw hash value of the key */
|
||||
int h; /* the hash of the key modulo hash table size */
|
||||
HashElem *elem; /* Used to loop thru the element list */
|
||||
HashElem *new_elem; /* New element added to the pH */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( pH!=0 );
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
hraw = (*xHash)(pKey, nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
elem = findElementGivenHash(pH,pKey,nKey,h);
|
||||
if( elem ){
|
||||
void *old_data = elem->data;
|
||||
if( data==0 ){
|
||||
removeElementGivenHash(pH,elem,h);
|
||||
}else{
|
||||
elem->data = data;
|
||||
}
|
||||
return old_data;
|
||||
}
|
||||
if( data==0 ) return 0;
|
||||
new_elem = (HashElem*)pH->xMalloc( sizeof(HashElem) );
|
||||
if( new_elem==0 ) return data;
|
||||
if( pH->copyKey && pKey!=0 ){
|
||||
new_elem->pKey = pH->xMalloc( nKey );
|
||||
if( new_elem->pKey==0 ){
|
||||
pH->xFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
memcpy((void*)new_elem->pKey, pKey, nKey);
|
||||
}else{
|
||||
new_elem->pKey = (void*)pKey;
|
||||
}
|
||||
new_elem->nKey = nKey;
|
||||
pH->count++;
|
||||
if( pH->htsize==0 ){
|
||||
rehash(pH,8);
|
||||
if( pH->htsize==0 ){
|
||||
pH->count = 0;
|
||||
pH->xFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
}
|
||||
if( pH->count > pH->htsize ){
|
||||
rehash(pH,pH->htsize*2);
|
||||
}
|
||||
assert( pH->htsize>0 );
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
insertElement(pH, &pH->ht[h], new_elem);
|
||||
new_elem->data = data;
|
||||
return 0;
|
||||
}
|
||||
@@ -1,111 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the header file for the generic hash-table implementation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
*/
|
||||
#ifndef _HASH_H_
|
||||
#define _HASH_H_
|
||||
|
||||
/* Forward declarations of structures. */
|
||||
typedef struct Hash Hash;
|
||||
typedef struct HashElem HashElem;
|
||||
|
||||
/* A complete hash table is an instance of the following structure.
|
||||
** The internals of this structure are intended to be opaque -- client
|
||||
** code should not attempt to access or modify the fields of this structure
|
||||
** directly. Change this structure only by using the routines below.
|
||||
** However, many of the "procedures" and "functions" for modifying and
|
||||
** accessing this structure are really macros, so we can't really make
|
||||
** this structure opaque.
|
||||
*/
|
||||
struct Hash {
|
||||
char keyClass; /* HASH_INT, _POINTER, _STRING, _BINARY */
|
||||
char copyKey; /* True if copy of key made on insert */
|
||||
int count; /* Number of entries in this table */
|
||||
HashElem *first; /* The first element of the array */
|
||||
void *(*xMalloc)(int); /* malloc() function to use */
|
||||
void (*xFree)(void *); /* free() function to use */
|
||||
int htsize; /* Number of buckets in the hash table */
|
||||
struct _ht { /* the hash table */
|
||||
int count; /* Number of entries with this hash */
|
||||
HashElem *chain; /* Pointer to first entry with this hash */
|
||||
} *ht;
|
||||
};
|
||||
|
||||
/* Each element in the hash table is an instance of the following
|
||||
** structure. All elements are stored on a single doubly-linked list.
|
||||
**
|
||||
** Again, this structure is intended to be opaque, but it can't really
|
||||
** be opaque because it is used by macros.
|
||||
*/
|
||||
struct HashElem {
|
||||
HashElem *next, *prev; /* Next and previous elements in the table */
|
||||
void *data; /* Data associated with this element */
|
||||
void *pKey; int nKey; /* Key associated with this element */
|
||||
};
|
||||
|
||||
/*
|
||||
** There are 4 different modes of operation for a hash table:
|
||||
**
|
||||
** HASH_INT nKey is used as the key and pKey is ignored.
|
||||
**
|
||||
** HASH_POINTER pKey is used as the key and nKey is ignored.
|
||||
**
|
||||
** HASH_STRING pKey points to a string that is nKey bytes long
|
||||
** (including the null-terminator, if any). Case
|
||||
** is respected in comparisons.
|
||||
**
|
||||
** HASH_BINARY pKey points to binary data nKey bytes long.
|
||||
** memcmp() is used to compare keys.
|
||||
**
|
||||
** A copy of the key is made for HASH_STRING and HASH_BINARY
|
||||
** if the copyKey parameter to HashInit is 1.
|
||||
*/
|
||||
/* #define HASH_INT 1 // NOT USED */
|
||||
/* #define HASH_POINTER 2 // NOT USED */
|
||||
#define HASH_STRING 3
|
||||
#define HASH_BINARY 4
|
||||
|
||||
/*
|
||||
** Access routines. To delete, insert a NULL pointer.
|
||||
*/
|
||||
void HashInit(Hash*, int keytype, int copyKey);
|
||||
void *HashInsert(Hash*, const void *pKey, int nKey, void *pData);
|
||||
void *HashFind(const Hash*, const void *pKey, int nKey);
|
||||
void HashClear(Hash*);
|
||||
|
||||
/*
|
||||
** Macros for looping over all elements of a hash table. The idiom is
|
||||
** like this:
|
||||
**
|
||||
** Hash h;
|
||||
** HashElem *p;
|
||||
** ...
|
||||
** for(p=HashFirst(&h); p; p=HashNext(p)){
|
||||
** SomeStructure *pData = HashData(p);
|
||||
** // do something with pData
|
||||
** }
|
||||
*/
|
||||
#define HashFirst(H) ((H)->first)
|
||||
#define HashNext(E) ((E)->next)
|
||||
#define HashData(E) ((E)->data)
|
||||
#define HashKey(E) ((E)->pKey)
|
||||
#define HashKeysize(E) ((E)->nKey)
|
||||
|
||||
/*
|
||||
** Number of entries in a hash table
|
||||
*/
|
||||
#define HashCount(H) ((H)->count)
|
||||
|
||||
#endif /* _HASH_H_ */
|
||||
-3348
File diff suppressed because it is too large
Load Diff
@@ -1,11 +0,0 @@
|
||||
#include "sqlite3.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif /* __cplusplus */
|
||||
|
||||
int sqlite3Fts1Init(sqlite3 *db);
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" */
|
||||
#endif /* __cplusplus */
|
||||
@@ -1,369 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the implementation of generic hash-tables used in SQLite.
|
||||
** We've modified it slightly to serve as a standalone hash table
|
||||
** implementation for the full-text indexing module.
|
||||
*/
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS1 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS1 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS1 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1)
|
||||
|
||||
|
||||
#include "fts1_hash.h"
|
||||
|
||||
static void *malloc_and_zero(int n){
|
||||
void *p = malloc(n);
|
||||
if( p ){
|
||||
memset(p, 0, n);
|
||||
}
|
||||
return p;
|
||||
}
|
||||
|
||||
/* Turn bulk memory into a hash table object by initializing the
|
||||
** fields of the Hash structure.
|
||||
**
|
||||
** "pNew" is a pointer to the hash table that is to be initialized.
|
||||
** keyClass is one of the constants
|
||||
** FTS1_HASH_BINARY or FTS1_HASH_STRING. The value of keyClass
|
||||
** determines what kind of key the hash table will use. "copyKey" is
|
||||
** true if the hash table should make its own private copy of keys and
|
||||
** false if it should just use the supplied pointer.
|
||||
*/
|
||||
void sqlite3Fts1HashInit(fts1Hash *pNew, int keyClass, int copyKey){
|
||||
assert( pNew!=0 );
|
||||
assert( keyClass>=FTS1_HASH_STRING && keyClass<=FTS1_HASH_BINARY );
|
||||
pNew->keyClass = keyClass;
|
||||
pNew->copyKey = copyKey;
|
||||
pNew->first = 0;
|
||||
pNew->count = 0;
|
||||
pNew->htsize = 0;
|
||||
pNew->ht = 0;
|
||||
pNew->xMalloc = malloc_and_zero;
|
||||
pNew->xFree = free;
|
||||
}
|
||||
|
||||
/* Remove all entries from a hash table. Reclaim all memory.
|
||||
** Call this routine to delete a hash table or to reset a hash table
|
||||
** to the empty state.
|
||||
*/
|
||||
void sqlite3Fts1HashClear(fts1Hash *pH){
|
||||
fts1HashElem *elem; /* For looping over all elements of the table */
|
||||
|
||||
assert( pH!=0 );
|
||||
elem = pH->first;
|
||||
pH->first = 0;
|
||||
if( pH->ht ) pH->xFree(pH->ht);
|
||||
pH->ht = 0;
|
||||
pH->htsize = 0;
|
||||
while( elem ){
|
||||
fts1HashElem *next_elem = elem->next;
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
pH->xFree(elem->pKey);
|
||||
}
|
||||
pH->xFree(elem);
|
||||
elem = next_elem;
|
||||
}
|
||||
pH->count = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS1_HASH_STRING
|
||||
*/
|
||||
static int strHash(const void *pKey, int nKey){
|
||||
const char *z = (const char *)pKey;
|
||||
int h = 0;
|
||||
if( nKey<=0 ) nKey = (int) strlen(z);
|
||||
while( nKey > 0 ){
|
||||
h = (h<<3) ^ h ^ *z++;
|
||||
nKey--;
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int strCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return strncmp((const char*)pKey1,(const char*)pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS1_HASH_BINARY
|
||||
*/
|
||||
static int binHash(const void *pKey, int nKey){
|
||||
int h = 0;
|
||||
const char *z = (const char *)pKey;
|
||||
while( nKey-- > 0 ){
|
||||
h = (h<<3) ^ h ^ *(z++);
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int binCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return memcmp(pKey1,pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** The C syntax in this function definition may be unfamilar to some
|
||||
** programmers, so we provide the following additional explanation:
|
||||
**
|
||||
** The name of the function is "hashFunction". The function takes a
|
||||
** single parameter "keyClass". The return value of hashFunction()
|
||||
** is a pointer to another function. Specifically, the return value
|
||||
** of hashFunction() is a pointer to a function that takes two parameters
|
||||
** with types "const void*" and "int" and returns an "int".
|
||||
*/
|
||||
static int (*hashFunction(int keyClass))(const void*,int){
|
||||
if( keyClass==FTS1_HASH_STRING ){
|
||||
return &strHash;
|
||||
}else{
|
||||
assert( keyClass==FTS1_HASH_BINARY );
|
||||
return &binHash;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** For help in interpreted the obscure C code in the function definition,
|
||||
** see the header comment on the previous function.
|
||||
*/
|
||||
static int (*compareFunction(int keyClass))(const void*,int,const void*,int){
|
||||
if( keyClass==FTS1_HASH_STRING ){
|
||||
return &strCompare;
|
||||
}else{
|
||||
assert( keyClass==FTS1_HASH_BINARY );
|
||||
return &binCompare;
|
||||
}
|
||||
}
|
||||
|
||||
/* Link an element into the hash table
|
||||
*/
|
||||
static void insertElement(
|
||||
fts1Hash *pH, /* The complete hash table */
|
||||
struct _fts1ht *pEntry, /* The entry into which pNew is inserted */
|
||||
fts1HashElem *pNew /* The element to be inserted */
|
||||
){
|
||||
fts1HashElem *pHead; /* First element already in pEntry */
|
||||
pHead = pEntry->chain;
|
||||
if( pHead ){
|
||||
pNew->next = pHead;
|
||||
pNew->prev = pHead->prev;
|
||||
if( pHead->prev ){ pHead->prev->next = pNew; }
|
||||
else { pH->first = pNew; }
|
||||
pHead->prev = pNew;
|
||||
}else{
|
||||
pNew->next = pH->first;
|
||||
if( pH->first ){ pH->first->prev = pNew; }
|
||||
pNew->prev = 0;
|
||||
pH->first = pNew;
|
||||
}
|
||||
pEntry->count++;
|
||||
pEntry->chain = pNew;
|
||||
}
|
||||
|
||||
|
||||
/* Resize the hash table so that it cantains "new_size" buckets.
|
||||
** "new_size" must be a power of 2. The hash table might fail
|
||||
** to resize if sqliteMalloc() fails.
|
||||
*/
|
||||
static void rehash(fts1Hash *pH, int new_size){
|
||||
struct _fts1ht *new_ht; /* The new hash table */
|
||||
fts1HashElem *elem, *next_elem; /* For looping over existing elements */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( (new_size & (new_size-1))==0 );
|
||||
new_ht = (struct _fts1ht *)pH->xMalloc( new_size*sizeof(struct _fts1ht) );
|
||||
if( new_ht==0 ) return;
|
||||
if( pH->ht ) pH->xFree(pH->ht);
|
||||
pH->ht = new_ht;
|
||||
pH->htsize = new_size;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
for(elem=pH->first, pH->first=0; elem; elem = next_elem){
|
||||
int h = (*xHash)(elem->pKey, elem->nKey) & (new_size-1);
|
||||
next_elem = elem->next;
|
||||
insertElement(pH, &new_ht[h], elem);
|
||||
}
|
||||
}
|
||||
|
||||
/* This function (for internal use only) locates an element in an
|
||||
** hash table that matches the given key. The hash for this key has
|
||||
** already been computed and is passed as the 4th parameter.
|
||||
*/
|
||||
static fts1HashElem *findElementGivenHash(
|
||||
const fts1Hash *pH, /* The pH to be searched */
|
||||
const void *pKey, /* The key we are searching for */
|
||||
int nKey,
|
||||
int h /* The hash for this key. */
|
||||
){
|
||||
fts1HashElem *elem; /* Used to loop thru the element list */
|
||||
int count; /* Number of elements left to test */
|
||||
int (*xCompare)(const void*,int,const void*,int); /* comparison function */
|
||||
|
||||
if( pH->ht ){
|
||||
struct _fts1ht *pEntry = &pH->ht[h];
|
||||
elem = pEntry->chain;
|
||||
count = pEntry->count;
|
||||
xCompare = compareFunction(pH->keyClass);
|
||||
while( count-- && elem ){
|
||||
if( (*xCompare)(elem->pKey,elem->nKey,pKey,nKey)==0 ){
|
||||
return elem;
|
||||
}
|
||||
elem = elem->next;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Remove a single entry from the hash table given a pointer to that
|
||||
** element and a hash on the element's key.
|
||||
*/
|
||||
static void removeElementGivenHash(
|
||||
fts1Hash *pH, /* The pH containing "elem" */
|
||||
fts1HashElem* elem, /* The element to be removed from the pH */
|
||||
int h /* Hash value for the element */
|
||||
){
|
||||
struct _fts1ht *pEntry;
|
||||
if( elem->prev ){
|
||||
elem->prev->next = elem->next;
|
||||
}else{
|
||||
pH->first = elem->next;
|
||||
}
|
||||
if( elem->next ){
|
||||
elem->next->prev = elem->prev;
|
||||
}
|
||||
pEntry = &pH->ht[h];
|
||||
if( pEntry->chain==elem ){
|
||||
pEntry->chain = elem->next;
|
||||
}
|
||||
pEntry->count--;
|
||||
if( pEntry->count<=0 ){
|
||||
pEntry->chain = 0;
|
||||
}
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
pH->xFree(elem->pKey);
|
||||
}
|
||||
pH->xFree( elem );
|
||||
pH->count--;
|
||||
if( pH->count<=0 ){
|
||||
assert( pH->first==0 );
|
||||
assert( pH->count==0 );
|
||||
fts1HashClear(pH);
|
||||
}
|
||||
}
|
||||
|
||||
/* Attempt to locate an element of the hash table pH with a key
|
||||
** that matches pKey,nKey. Return the data for this element if it is
|
||||
** found, or NULL if there is no match.
|
||||
*/
|
||||
void *sqlite3Fts1HashFind(const fts1Hash *pH, const void *pKey, int nKey){
|
||||
int h; /* A hash on key */
|
||||
fts1HashElem *elem; /* The element that matches key */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
if( pH==0 || pH->ht==0 ) return 0;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
h = (*xHash)(pKey,nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
elem = findElementGivenHash(pH,pKey,nKey, h & (pH->htsize-1));
|
||||
return elem ? elem->data : 0;
|
||||
}
|
||||
|
||||
/* Insert an element into the hash table pH. The key is pKey,nKey
|
||||
** and the data is "data".
|
||||
**
|
||||
** If no element exists with a matching key, then a new
|
||||
** element is created. A copy of the key is made if the copyKey
|
||||
** flag is set. NULL is returned.
|
||||
**
|
||||
** If another element already exists with the same key, then the
|
||||
** new data replaces the old data and the old data is returned.
|
||||
** The key is not copied in this instance. If a malloc fails, then
|
||||
** the new data is returned and the hash table is unchanged.
|
||||
**
|
||||
** If the "data" parameter to this function is NULL, then the
|
||||
** element corresponding to "key" is removed from the hash table.
|
||||
*/
|
||||
void *sqlite3Fts1HashInsert(
|
||||
fts1Hash *pH, /* The hash table to insert into */
|
||||
const void *pKey, /* The key */
|
||||
int nKey, /* Number of bytes in the key */
|
||||
void *data /* The data */
|
||||
){
|
||||
int hraw; /* Raw hash value of the key */
|
||||
int h; /* the hash of the key modulo hash table size */
|
||||
fts1HashElem *elem; /* Used to loop thru the element list */
|
||||
fts1HashElem *new_elem; /* New element added to the pH */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( pH!=0 );
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
hraw = (*xHash)(pKey, nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
elem = findElementGivenHash(pH,pKey,nKey,h);
|
||||
if( elem ){
|
||||
void *old_data = elem->data;
|
||||
if( data==0 ){
|
||||
removeElementGivenHash(pH,elem,h);
|
||||
}else{
|
||||
elem->data = data;
|
||||
}
|
||||
return old_data;
|
||||
}
|
||||
if( data==0 ) return 0;
|
||||
new_elem = (fts1HashElem*)pH->xMalloc( sizeof(fts1HashElem) );
|
||||
if( new_elem==0 ) return data;
|
||||
if( pH->copyKey && pKey!=0 ){
|
||||
new_elem->pKey = pH->xMalloc( nKey );
|
||||
if( new_elem->pKey==0 ){
|
||||
pH->xFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
memcpy((void*)new_elem->pKey, pKey, nKey);
|
||||
}else{
|
||||
new_elem->pKey = (void*)pKey;
|
||||
}
|
||||
new_elem->nKey = nKey;
|
||||
pH->count++;
|
||||
if( pH->htsize==0 ){
|
||||
rehash(pH,8);
|
||||
if( pH->htsize==0 ){
|
||||
pH->count = 0;
|
||||
pH->xFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
}
|
||||
if( pH->count > pH->htsize ){
|
||||
rehash(pH,pH->htsize*2);
|
||||
}
|
||||
assert( pH->htsize>0 );
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
insertElement(pH, &pH->ht[h], new_elem);
|
||||
new_elem->data = data;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1) */
|
||||
@@ -1,112 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the header file for the generic hash-table implementation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
*/
|
||||
#ifndef _FTS1_HASH_H_
|
||||
#define _FTS1_HASH_H_
|
||||
|
||||
/* Forward declarations of structures. */
|
||||
typedef struct fts1Hash fts1Hash;
|
||||
typedef struct fts1HashElem fts1HashElem;
|
||||
|
||||
/* A complete hash table is an instance of the following structure.
|
||||
** The internals of this structure are intended to be opaque -- client
|
||||
** code should not attempt to access or modify the fields of this structure
|
||||
** directly. Change this structure only by using the routines below.
|
||||
** However, many of the "procedures" and "functions" for modifying and
|
||||
** accessing this structure are really macros, so we can't really make
|
||||
** this structure opaque.
|
||||
*/
|
||||
struct fts1Hash {
|
||||
char keyClass; /* HASH_INT, _POINTER, _STRING, _BINARY */
|
||||
char copyKey; /* True if copy of key made on insert */
|
||||
int count; /* Number of entries in this table */
|
||||
fts1HashElem *first; /* The first element of the array */
|
||||
void *(*xMalloc)(int); /* malloc() function to use */
|
||||
void (*xFree)(void *); /* free() function to use */
|
||||
int htsize; /* Number of buckets in the hash table */
|
||||
struct _fts1ht { /* the hash table */
|
||||
int count; /* Number of entries with this hash */
|
||||
fts1HashElem *chain; /* Pointer to first entry with this hash */
|
||||
} *ht;
|
||||
};
|
||||
|
||||
/* Each element in the hash table is an instance of the following
|
||||
** structure. All elements are stored on a single doubly-linked list.
|
||||
**
|
||||
** Again, this structure is intended to be opaque, but it can't really
|
||||
** be opaque because it is used by macros.
|
||||
*/
|
||||
struct fts1HashElem {
|
||||
fts1HashElem *next, *prev; /* Next and previous elements in the table */
|
||||
void *data; /* Data associated with this element */
|
||||
void *pKey; int nKey; /* Key associated with this element */
|
||||
};
|
||||
|
||||
/*
|
||||
** There are 2 different modes of operation for a hash table:
|
||||
**
|
||||
** FTS1_HASH_STRING pKey points to a string that is nKey bytes long
|
||||
** (including the null-terminator, if any). Case
|
||||
** is respected in comparisons.
|
||||
**
|
||||
** FTS1_HASH_BINARY pKey points to binary data nKey bytes long.
|
||||
** memcmp() is used to compare keys.
|
||||
**
|
||||
** A copy of the key is made if the copyKey parameter to fts1HashInit is 1.
|
||||
*/
|
||||
#define FTS1_HASH_STRING 1
|
||||
#define FTS1_HASH_BINARY 2
|
||||
|
||||
/*
|
||||
** Access routines. To delete, insert a NULL pointer.
|
||||
*/
|
||||
void sqlite3Fts1HashInit(fts1Hash*, int keytype, int copyKey);
|
||||
void *sqlite3Fts1HashInsert(fts1Hash*, const void *pKey, int nKey, void *pData);
|
||||
void *sqlite3Fts1HashFind(const fts1Hash*, const void *pKey, int nKey);
|
||||
void sqlite3Fts1HashClear(fts1Hash*);
|
||||
|
||||
/*
|
||||
** Shorthand for the functions above
|
||||
*/
|
||||
#define fts1HashInit sqlite3Fts1HashInit
|
||||
#define fts1HashInsert sqlite3Fts1HashInsert
|
||||
#define fts1HashFind sqlite3Fts1HashFind
|
||||
#define fts1HashClear sqlite3Fts1HashClear
|
||||
|
||||
/*
|
||||
** Macros for looping over all elements of a hash table. The idiom is
|
||||
** like this:
|
||||
**
|
||||
** fts1Hash h;
|
||||
** fts1HashElem *p;
|
||||
** ...
|
||||
** for(p=fts1HashFirst(&h); p; p=fts1HashNext(p)){
|
||||
** SomeStructure *pData = fts1HashData(p);
|
||||
** // do something with pData
|
||||
** }
|
||||
*/
|
||||
#define fts1HashFirst(H) ((H)->first)
|
||||
#define fts1HashNext(E) ((E)->next)
|
||||
#define fts1HashData(E) ((E)->data)
|
||||
#define fts1HashKey(E) ((E)->pKey)
|
||||
#define fts1HashKeysize(E) ((E)->nKey)
|
||||
|
||||
/*
|
||||
** Number of entries in a hash table
|
||||
*/
|
||||
#define fts1HashCount(H) ((H)->count)
|
||||
|
||||
#endif /* _FTS1_HASH_H_ */
|
||||
@@ -1,643 +0,0 @@
|
||||
/*
|
||||
** 2006 September 30
|
||||
**
|
||||
** 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 full-text-search tokenizer that implements
|
||||
** a Porter stemmer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS1 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS1 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS1 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1)
|
||||
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <ctype.h>
|
||||
|
||||
#include "fts1_tokenizer.h"
|
||||
|
||||
/*
|
||||
** Class derived from sqlite3_tokenizer
|
||||
*/
|
||||
typedef struct porter_tokenizer {
|
||||
sqlite3_tokenizer base; /* Base class */
|
||||
} porter_tokenizer;
|
||||
|
||||
/*
|
||||
** Class derived from sqlit3_tokenizer_cursor
|
||||
*/
|
||||
typedef struct porter_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *zInput; /* input we are tokenizing */
|
||||
int nInput; /* size of the input */
|
||||
int iOffset; /* current position in zInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *zToken; /* storage for current token */
|
||||
int nAllocated; /* space allocated to zToken buffer */
|
||||
} porter_tokenizer_cursor;
|
||||
|
||||
|
||||
/* Forward declaration */
|
||||
static const sqlite3_tokenizer_module porterTokenizerModule;
|
||||
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int porterCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
porter_tokenizer *t;
|
||||
t = (porter_tokenizer *) calloc(sizeof(*t), 1);
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int porterDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Prepare to begin tokenizing a particular string. The input
|
||||
** string to be tokenized is zInput[0..nInput-1]. A cursor
|
||||
** used to incrementally tokenize this string is returned in
|
||||
** *ppCursor.
|
||||
*/
|
||||
static int porterOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *zInput, int nInput, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
porter_tokenizer_cursor *c;
|
||||
|
||||
c = (porter_tokenizer_cursor *) malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->zInput = zInput;
|
||||
if( zInput==0 ){
|
||||
c->nInput = 0;
|
||||
}else if( nInput<0 ){
|
||||
c->nInput = (int)strlen(zInput);
|
||||
}else{
|
||||
c->nInput = nInput;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->zToken = NULL; /* no space allocated, yet. */
|
||||
c->nAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** porterOpen() above.
|
||||
*/
|
||||
static int porterClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
free(c->zToken);
|
||||
free(c);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
/*
|
||||
** Vowel or consonant
|
||||
*/
|
||||
static const char cType[] = {
|
||||
0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0,
|
||||
1, 1, 1, 2, 1
|
||||
};
|
||||
|
||||
/*
|
||||
** isConsonant() and isVowel() determine if their first character in
|
||||
** the string they point to is a consonant or a vowel, according
|
||||
** to Porter ruls.
|
||||
**
|
||||
** A consonate is any letter other than 'a', 'e', 'i', 'o', or 'u'.
|
||||
** 'Y' is a consonant unless it follows another consonant,
|
||||
** in which case it is a vowel.
|
||||
**
|
||||
** In these routine, the letters are in reverse order. So the 'y' rule
|
||||
** is that 'y' is a consonant unless it is followed by another
|
||||
** consonent.
|
||||
*/
|
||||
static int isVowel(const char*);
|
||||
static int isConsonant(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return j;
|
||||
return z[1]==0 || isVowel(z + 1);
|
||||
}
|
||||
static int isVowel(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return 1-j;
|
||||
return isConsonant(z + 1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Let any sequence of one or more vowels be represented by V and let
|
||||
** C be sequence of one or more consonants. Then every word can be
|
||||
** represented as:
|
||||
**
|
||||
** [C] (VC){m} [V]
|
||||
**
|
||||
** In prose: A word is an optional consonant followed by zero or
|
||||
** vowel-consonant pairs followed by an optional vowel. "m" is the
|
||||
** number of vowel consonant pairs. This routine computes the value
|
||||
** of m for the first i bytes of a word.
|
||||
**
|
||||
** Return true if the m-value for z is 1 or more. In other words,
|
||||
** return true if z contains at least one vowel that is followed
|
||||
** by a consonant.
|
||||
**
|
||||
** In this routine z[] is in reverse order. So we are really looking
|
||||
** for an instance of of a consonant followed by a vowel.
|
||||
*/
|
||||
static int m_gt_0(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m which is
|
||||
** exactly 1
|
||||
*/
|
||||
static int m_eq_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 1;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z==0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m>1 instead
|
||||
** or m>0
|
||||
*/
|
||||
static int m_gt_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if there is a vowel anywhere within z[0..n-1]
|
||||
*/
|
||||
static int hasVowel(const char *z){
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends in a double consonant.
|
||||
**
|
||||
** The text is reversed here. So we are really looking at
|
||||
** the first two characters of z[].
|
||||
*/
|
||||
static int doubleConsonant(const char *z){
|
||||
return isConsonant(z) && z[0]==z[1] && isConsonant(z+1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends with three letters which
|
||||
** are consonant-vowel-consonent and where the final consonant
|
||||
** is not 'w', 'x', or 'y'.
|
||||
**
|
||||
** The word is reversed here. So we are really checking the
|
||||
** first three letters and the first one cannot be in [wxy].
|
||||
*/
|
||||
static int star_oh(const char *z){
|
||||
return
|
||||
z[0]!=0 && isConsonant(z) &&
|
||||
z[0]!='w' && z[0]!='x' && z[0]!='y' &&
|
||||
z[1]!=0 && isVowel(z+1) &&
|
||||
z[2]!=0 && isConsonant(z+2);
|
||||
}
|
||||
|
||||
/*
|
||||
** If the word ends with zFrom and xCond() is true for the stem
|
||||
** of the word that preceeds the zFrom ending, then change the
|
||||
** ending to zTo.
|
||||
**
|
||||
** The input word *pz and zFrom are both in reverse order. zTo
|
||||
** is in normal order.
|
||||
**
|
||||
** Return TRUE if zFrom matches. Return FALSE if zFrom does not
|
||||
** match. Not that TRUE is returned even if xCond() fails and
|
||||
** no substitution occurs.
|
||||
*/
|
||||
static int stem(
|
||||
char **pz, /* The word being stemmed (Reversed) */
|
||||
const char *zFrom, /* If the ending matches this... (Reversed) */
|
||||
const char *zTo, /* ... change the ending to this (not reversed) */
|
||||
int (*xCond)(const char*) /* Condition that must be true */
|
||||
){
|
||||
char *z = *pz;
|
||||
while( *zFrom && *zFrom==*z ){ z++; zFrom++; }
|
||||
if( *zFrom!=0 ) return 0;
|
||||
if( xCond && !xCond(z) ) return 1;
|
||||
while( *zTo ){
|
||||
*(--z) = *(zTo++);
|
||||
}
|
||||
*pz = z;
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
** This is the fallback stemmer used when the porter stemmer is
|
||||
** inappropriate. The input word is copied into the output with
|
||||
** US-ASCII case folding. If the input word is too long (more
|
||||
** than 20 bytes if it contains no digits or more than 6 bytes if
|
||||
** it contains digits) then word is truncated to 20 or 6 bytes
|
||||
** by taking 10 or 3 bytes from the beginning and end.
|
||||
*/
|
||||
static void copy_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, mx, j;
|
||||
int hasDigit = 0;
|
||||
for(i=0; i<nIn; i++){
|
||||
int c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zOut[i] = c - 'A' + 'a';
|
||||
}else{
|
||||
if( c>='0' && c<='9' ) hasDigit = 1;
|
||||
zOut[i] = c;
|
||||
}
|
||||
}
|
||||
mx = hasDigit ? 3 : 10;
|
||||
if( nIn>mx*2 ){
|
||||
for(j=mx, i=nIn-mx; i<nIn; i++, j++){
|
||||
zOut[j] = zOut[i];
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
zOut[i] = 0;
|
||||
*pnOut = i;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Stem the input word zIn[0..nIn-1]. Store the output in zOut.
|
||||
** zOut is at least big enough to hold nIn bytes. Write the actual
|
||||
** size of the output word (exclusive of the '\0' terminator) into *pnOut.
|
||||
**
|
||||
** Any upper-case characters in the US-ASCII character set ([A-Z])
|
||||
** are converted to lower case. Upper-case UTF characters are
|
||||
** unchanged.
|
||||
**
|
||||
** Words that are longer than about 20 bytes are stemmed by retaining
|
||||
** a few bytes from the beginning and the end of the word. If the
|
||||
** word contains digits, 3 bytes are taken from the beginning and
|
||||
** 3 bytes from the end. For long words without digits, 10 bytes
|
||||
** are taken from each end. US-ASCII case folding still applies.
|
||||
**
|
||||
** If the input word contains not digits but does characters not
|
||||
** in [a-zA-Z] then no stemming is attempted and this routine just
|
||||
** copies the input into the input into the output with US-ASCII
|
||||
** case folding.
|
||||
**
|
||||
** Stemming never increases the length of the word. So there is
|
||||
** no chance of overflowing the zOut buffer.
|
||||
*/
|
||||
static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, j, c;
|
||||
char zReverse[28];
|
||||
char *z, *z2;
|
||||
if( nIn<3 || nIn>=sizeof(zReverse)-7 ){
|
||||
/* The word is too big or too small for the porter stemmer.
|
||||
** Fallback to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
for(i=0, j=sizeof(zReverse)-6; i<nIn; i++, j--){
|
||||
c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zReverse[j] = c + 'a' - 'A';
|
||||
}else if( c>='a' && c<='z' ){
|
||||
zReverse[j] = c;
|
||||
}else{
|
||||
/* The use of a character not in [a-zA-Z] means that we fallback
|
||||
** to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
}
|
||||
memset(&zReverse[sizeof(zReverse)-5], 0, 5);
|
||||
z = &zReverse[j+1];
|
||||
|
||||
|
||||
/* Step 1a */
|
||||
if( z[0]=='s' ){
|
||||
if(
|
||||
!stem(&z, "sess", "ss", 0) &&
|
||||
!stem(&z, "sei", "i", 0) &&
|
||||
!stem(&z, "ss", "ss", 0)
|
||||
){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1b */
|
||||
z2 = z;
|
||||
if( stem(&z, "dee", "ee", m_gt_0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if(
|
||||
(stem(&z, "gni", "", hasVowel) || stem(&z, "de", "", hasVowel))
|
||||
&& z!=z2
|
||||
){
|
||||
if( stem(&z, "ta", "ate", 0) ||
|
||||
stem(&z, "lb", "ble", 0) ||
|
||||
stem(&z, "zi", "ize", 0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if( doubleConsonant(z) && (*z!='l' && *z!='s' && *z!='z') ){
|
||||
z++;
|
||||
}else if( m_eq_1(z) && star_oh(z) ){
|
||||
*(--z) = 'e';
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1c */
|
||||
if( z[0]=='y' && hasVowel(z+1) ){
|
||||
z[0] = 'i';
|
||||
}
|
||||
|
||||
/* Step 2 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
stem(&z, "lanoita", "ate", m_gt_0) ||
|
||||
stem(&z, "lanoit", "tion", m_gt_0);
|
||||
break;
|
||||
case 'c':
|
||||
stem(&z, "icne", "ence", m_gt_0) ||
|
||||
stem(&z, "icna", "ance", m_gt_0);
|
||||
break;
|
||||
case 'e':
|
||||
stem(&z, "rezi", "ize", m_gt_0);
|
||||
break;
|
||||
case 'g':
|
||||
stem(&z, "igol", "log", m_gt_0);
|
||||
break;
|
||||
case 'l':
|
||||
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':
|
||||
stem(&z, "noitazi", "ize", m_gt_0) ||
|
||||
stem(&z, "noita", "ate", m_gt_0) ||
|
||||
stem(&z, "rota", "ate", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
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':
|
||||
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':
|
||||
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':
|
||||
stem(&z, "laci", "ic", m_gt_0) ||
|
||||
stem(&z, "luf", "", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
stem(&z, "ssen", "", m_gt_0);
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 4 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
if( z[0]=='l' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'c':
|
||||
if( z[0]=='e' && z[2]=='n' && (z[3]=='a' || z[3]=='e') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'e':
|
||||
if( z[0]=='r' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'i':
|
||||
if( z[0]=='c' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'l':
|
||||
if( z[0]=='e' && z[2]=='b' && (z[3]=='a' || z[3]=='i') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'n':
|
||||
if( z[0]=='t' ){
|
||||
if( z[2]=='a' ){
|
||||
if( m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
}else if( z[2]=='e' ){
|
||||
stem(&z, "tneme", "", m_gt_1) ||
|
||||
stem(&z, "tnem", "", m_gt_1) ||
|
||||
stem(&z, "tne", "", m_gt_1);
|
||||
}
|
||||
}
|
||||
break;
|
||||
case 'o':
|
||||
if( z[0]=='u' ){
|
||||
if( m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
}else if( z[3]=='s' || z[3]=='t' ){
|
||||
stem(&z, "noi", "", m_gt_1);
|
||||
}
|
||||
break;
|
||||
case 's':
|
||||
if( z[0]=='m' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 't':
|
||||
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) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 'v':
|
||||
case 'z':
|
||||
if( z[0]=='e' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 5a */
|
||||
if( z[0]=='e' ){
|
||||
if( m_gt_1(z+1) ){
|
||||
z++;
|
||||
}else if( m_eq_1(z+1) && !star_oh(z+1) ){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 5b */
|
||||
if( m_gt_1(z) && z[0]=='l' && z[1]=='l' ){
|
||||
z++;
|
||||
}
|
||||
|
||||
/* z[] is now the stemmed word in reverse order. Flip it back
|
||||
** around into forward order and return.
|
||||
*/
|
||||
*pnOut = i = strlen(z);
|
||||
zOut[i] = 0;
|
||||
while( *z ){
|
||||
zOut[--i] = *(z++);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Characters that can be part of a token. We assume any character
|
||||
** whose value is greater than 0x80 (any UTF character) can be
|
||||
** part of a token. In other words, delimiters all must have
|
||||
** values of 0x7f or lower.
|
||||
*/
|
||||
static const char isIdChar[] = {
|
||||
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, /* 3x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 4x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, /* 5x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 6x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, /* 7x */
|
||||
};
|
||||
#define idChar(C) (((ch=C)&0x80)!=0 || (ch>0x2f && isIdChar[ch-0x30]))
|
||||
#define isDelim(C) (((ch=C)&0x80)==0 && (ch<0x30 || !isIdChar[ch-0x30]))
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor. The cursor must
|
||||
** have been opened by a prior call to porterOpen().
|
||||
*/
|
||||
static int porterNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by porterOpen */
|
||||
const char **pzToken, /* OUT: *pzToken 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 */
|
||||
){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
const char *z = c->zInput;
|
||||
|
||||
while( c->iOffset<c->nInput ){
|
||||
int iStartOffset, ch;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nInput && isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nInput && !isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int n = c->iOffset-iStartOffset;
|
||||
if( n>c->nAllocated ){
|
||||
c->nAllocated = n+20;
|
||||
c->zToken = realloc(c->zToken, c->nAllocated);
|
||||
if( c->zToken==NULL ) return SQLITE_NOMEM;
|
||||
}
|
||||
porter_stemmer(&z[iStartOffset], n, c->zToken, pnBytes);
|
||||
*pzToken = c->zToken;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the porter-stemmer tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module porterTokenizerModule = {
|
||||
0,
|
||||
porterCreate,
|
||||
porterDestroy,
|
||||
porterOpen,
|
||||
porterClose,
|
||||
porterNext,
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new porter tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts1PorterTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &porterTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1) */
|
||||
@@ -1,90 +0,0 @@
|
||||
/*
|
||||
** 2006 July 10
|
||||
**
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Defines the interface to tokenizers used by fulltext-search. There
|
||||
** are three basic components:
|
||||
**
|
||||
** sqlite3_tokenizer_module is a singleton defining the tokenizer
|
||||
** interface functions. This is essentially the class structure for
|
||||
** tokenizers.
|
||||
**
|
||||
** sqlite3_tokenizer is used to define a particular tokenizer, perhaps
|
||||
** including customization information defined at creation time.
|
||||
**
|
||||
** sqlite3_tokenizer_cursor is generated by a tokenizer to generate
|
||||
** tokens from a particular input.
|
||||
*/
|
||||
#ifndef _FTS1_TOKENIZER_H_
|
||||
#define _FTS1_TOKENIZER_H_
|
||||
|
||||
/* TODO(shess) Only used for SQLITE_OK and SQLITE_DONE at this time.
|
||||
** If tokenizers are to be allowed to call sqlite3_*() functions, then
|
||||
** we will need a way to register the API consistently.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
/*
|
||||
** Structures used by the tokenizer interface.
|
||||
*/
|
||||
typedef struct sqlite3_tokenizer sqlite3_tokenizer;
|
||||
typedef struct sqlite3_tokenizer_cursor sqlite3_tokenizer_cursor;
|
||||
typedef struct sqlite3_tokenizer_module sqlite3_tokenizer_module;
|
||||
|
||||
struct sqlite3_tokenizer_module {
|
||||
int iVersion; /* currently 0 */
|
||||
|
||||
/*
|
||||
** Create and destroy a tokenizer. argc/argv are passed down from
|
||||
** the fulltext virtual table creation to allow customization.
|
||||
*/
|
||||
int (*xCreate)(int argc, const char *const*argv,
|
||||
sqlite3_tokenizer **ppTokenizer);
|
||||
int (*xDestroy)(sqlite3_tokenizer *pTokenizer);
|
||||
|
||||
/*
|
||||
** Tokenize a particular input. Call xOpen() to prepare to
|
||||
** tokenize, xNext() repeatedly until it returns SQLITE_DONE, then
|
||||
** xClose() to free any internal state. The pInput passed to
|
||||
** xOpen() must exist until the cursor is closed. The ppToken
|
||||
** result from xNext() is only valid until the next call to xNext()
|
||||
** or until xClose() is called.
|
||||
*/
|
||||
/* TODO(shess) current implementation requires pInput to be
|
||||
** nul-terminated. This should either be fixed, or pInput/nBytes
|
||||
** should be converted to zInput.
|
||||
*/
|
||||
int (*xOpen)(sqlite3_tokenizer *pTokenizer,
|
||||
const char *pInput, int nBytes,
|
||||
sqlite3_tokenizer_cursor **ppCursor);
|
||||
int (*xClose)(sqlite3_tokenizer_cursor *pCursor);
|
||||
int (*xNext)(sqlite3_tokenizer_cursor *pCursor,
|
||||
const char **ppToken, int *pnBytes,
|
||||
int *piStartOffset, int *piEndOffset, int *piPosition);
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer {
|
||||
const sqlite3_tokenizer_module *pModule; /* The module for this tokenizer */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer_cursor {
|
||||
sqlite3_tokenizer *pTokenizer; /* Tokenizer for this cursor. */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
/*
|
||||
** Get the module for a tokenizer which generates tokens based on a
|
||||
** set of non-token characters. The default is to break tokens at any
|
||||
** non-alnum character, though the set of delimiters can also be
|
||||
** specified by the first argv argument to xCreate().
|
||||
*/
|
||||
/* TODO(shess) This doesn't belong here. Need some sort of
|
||||
** registration process.
|
||||
*/
|
||||
void sqlite3Fts1SimpleTokenizerModule(sqlite3_tokenizer_module const**ppModule);
|
||||
void sqlite3Fts1PorterTokenizerModule(sqlite3_tokenizer_module const**ppModule);
|
||||
|
||||
#endif /* _FTS1_TOKENIZER_H_ */
|
||||
@@ -1,221 +0,0 @@
|
||||
/*
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Implementation of the "simple" full-text-search tokenizer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS1 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS1 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS1 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1)
|
||||
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <ctype.h>
|
||||
|
||||
#include "fts1_tokenizer.h"
|
||||
|
||||
typedef struct simple_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
char delim[128]; /* flag ASCII delimiters */
|
||||
} simple_tokenizer;
|
||||
|
||||
typedef struct simple_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *pInput; /* input we are tokenizing */
|
||||
int nBytes; /* size of the input */
|
||||
int iOffset; /* current position in pInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *pToken; /* storage for current token */
|
||||
int nTokenAllocated; /* space allocated to zToken buffer */
|
||||
} simple_tokenizer_cursor;
|
||||
|
||||
|
||||
/* Forward declaration */
|
||||
static const sqlite3_tokenizer_module simpleTokenizerModule;
|
||||
|
||||
static int isDelim(simple_tokenizer *t, unsigned char c){
|
||||
return c<0x80 && t->delim[c];
|
||||
}
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int simpleCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
simple_tokenizer *t;
|
||||
|
||||
t = (simple_tokenizer *) calloc(sizeof(*t), 1);
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
/* TODO(shess) Delimiters need to remain the same from run to run,
|
||||
** else we need to reindex. One solution would be a meta-table to
|
||||
** track such information in the database, then we'd only want this
|
||||
** information on the initial create.
|
||||
*/
|
||||
if( argc>1 ){
|
||||
int i, n = strlen(argv[1]);
|
||||
for(i=0; i<n; i++){
|
||||
unsigned char ch = argv[1][i];
|
||||
/* We explicitly don't support UTF-8 delimiters for now. */
|
||||
if( ch>=0x80 ){
|
||||
free(t);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
t->delim[ch] = 1;
|
||||
}
|
||||
} else {
|
||||
/* Mark non-alphanumeric ASCII characters as delimiters */
|
||||
int i;
|
||||
for(i=1; i<0x80; i++){
|
||||
t->delim[i] = !isalnum(i);
|
||||
}
|
||||
}
|
||||
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 simpleOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *pInput, int nBytes, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
simple_tokenizer_cursor *c;
|
||||
|
||||
c = (simple_tokenizer_cursor *) malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->pInput = pInput;
|
||||
if( pInput==0 ){
|
||||
c->nBytes = 0;
|
||||
}else if( nBytes<0 ){
|
||||
c->nBytes = (int)strlen(pInput);
|
||||
}else{
|
||||
c->nBytes = nBytes;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->pToken = NULL; /* no space allocated, yet. */
|
||||
c->nTokenAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** simpleOpen() above.
|
||||
*/
|
||||
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
free(c->pToken);
|
||||
free(c);
|
||||
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 simpleNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
|
||||
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 */
|
||||
){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
|
||||
unsigned char *p = (unsigned char *)c->pInput;
|
||||
|
||||
while( c->iOffset<c->nBytes ){
|
||||
int iStartOffset;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nBytes && isDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nBytes && !isDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int i, n = c->iOffset-iStartOffset;
|
||||
if( n>c->nTokenAllocated ){
|
||||
c->nTokenAllocated = n+20;
|
||||
c->pToken = realloc(c->pToken, c->nTokenAllocated);
|
||||
if( c->pToken==NULL ) return SQLITE_NOMEM;
|
||||
}
|
||||
for(i=0; i<n; i++){
|
||||
/* TODO(shess) This needs expansion to handle UTF-8
|
||||
** case-insensitivity.
|
||||
*/
|
||||
unsigned char ch = p[iStartOffset+i];
|
||||
c->pToken[i] = ch<0x80 ? tolower(ch) : ch;
|
||||
}
|
||||
*ppToken = c->pToken;
|
||||
*pnBytes = n;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the simple tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module simpleTokenizerModule = {
|
||||
0,
|
||||
simpleCreate,
|
||||
simpleDestroy,
|
||||
simpleOpen,
|
||||
simpleClose,
|
||||
simpleNext,
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new simple tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts1SimpleTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &simpleTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1) */
|
||||
-1511
File diff suppressed because it is too large
Load Diff
@@ -1,11 +0,0 @@
|
||||
#include "sqlite3.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif /* __cplusplus */
|
||||
|
||||
int fulltext_init(sqlite3 *db);
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" */
|
||||
#endif /* __cplusplus */
|
||||
@@ -1,174 +0,0 @@
|
||||
/*
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Implementation of the "simple" full-text-search tokenizer.
|
||||
*/
|
||||
|
||||
#include <assert.h>
|
||||
#if !defined(__APPLE__)
|
||||
#include <malloc.h>
|
||||
#else
|
||||
#include <stdlib.h>
|
||||
#endif
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <ctype.h>
|
||||
|
||||
#include "tokenizer.h"
|
||||
|
||||
/* Duplicate a string; the caller must free() the returned string.
|
||||
* (We don't use strdup() since it's not part of the standard C library and
|
||||
* may not be available everywhere.) */
|
||||
/* TODO(shess) Copied from fulltext.c, consider util.c for such
|
||||
** things. */
|
||||
static char *string_dup(const char *s){
|
||||
char *str = malloc(strlen(s) + 1);
|
||||
strcpy(str, s);
|
||||
return str;
|
||||
}
|
||||
|
||||
typedef struct simple_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
const char *zDelim; /* token delimiters */
|
||||
} simple_tokenizer;
|
||||
|
||||
typedef struct simple_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *pInput; /* input we are tokenizing */
|
||||
int nBytes; /* size of the input */
|
||||
const char *pCurrent; /* current position in pInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *zToken; /* storage for current token */
|
||||
int nTokenBytes; /* actual size of current token */
|
||||
int nTokenAllocated; /* space allocated to zToken buffer */
|
||||
} simple_tokenizer_cursor;
|
||||
|
||||
static sqlite3_tokenizer_module simpleTokenizerModule;/* forward declaration */
|
||||
|
||||
static int simpleCreate(
|
||||
int argc, const char **argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
simple_tokenizer *t;
|
||||
|
||||
t = (simple_tokenizer *) malloc(sizeof(simple_tokenizer));
|
||||
/* TODO(shess) Delimiters need to remain the same from run to run,
|
||||
** else we need to reindex. One solution would be a meta-table to
|
||||
** track such information in the database, then we'd only want this
|
||||
** information on the initial create.
|
||||
*/
|
||||
if( argc>1 ){
|
||||
t->zDelim = string_dup(argv[1]);
|
||||
} else {
|
||||
/* Build a string excluding alphanumeric ASCII characters */
|
||||
char zDelim[0x80]; /* nul-terminated, so nul not a member */
|
||||
int i, j;
|
||||
for(i=1, j=0; i<0x80; i++){
|
||||
if( !isalnum(i) ){
|
||||
zDelim[j++] = i;
|
||||
}
|
||||
}
|
||||
zDelim[j++] = '\0';
|
||||
assert( j<=sizeof(zDelim) );
|
||||
t->zDelim = string_dup(zDelim);
|
||||
}
|
||||
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
simple_tokenizer *t = (simple_tokenizer *) pTokenizer;
|
||||
|
||||
free((void *) t->zDelim);
|
||||
free(t);
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int simpleOpen(
|
||||
sqlite3_tokenizer *pTokenizer,
|
||||
const char *pInput, int nBytes,
|
||||
sqlite3_tokenizer_cursor **ppCursor
|
||||
){
|
||||
simple_tokenizer_cursor *c;
|
||||
|
||||
c = (simple_tokenizer_cursor *) malloc(sizeof(simple_tokenizer_cursor));
|
||||
c->pInput = pInput;
|
||||
c->nBytes = nBytes<0 ? (int) strlen(pInput) : nBytes;
|
||||
c->pCurrent = c->pInput; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->zToken = NULL; /* no space allocated, yet. */
|
||||
c->nTokenBytes = 0;
|
||||
c->nTokenAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
|
||||
if( NULL!=c->zToken ){
|
||||
free(c->zToken);
|
||||
}
|
||||
free(c);
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int simpleNext(
|
||||
sqlite3_tokenizer_cursor *pCursor,
|
||||
const char **ppToken, int *pnBytes,
|
||||
int *piStartOffset, int *piEndOffset, int *piPosition
|
||||
){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
|
||||
int ii;
|
||||
|
||||
while( c->pCurrent-c->pInput<c->nBytes ){
|
||||
int n = (int) strcspn(c->pCurrent, t->zDelim);
|
||||
if( n>0 ){
|
||||
if( n+1>c->nTokenAllocated ){
|
||||
c->zToken = realloc(c->zToken, n+1);
|
||||
}
|
||||
for(ii=0; ii<n; ii++){
|
||||
/* TODO(shess) This needs expansion to handle UTF-8
|
||||
** case-insensitivity.
|
||||
*/
|
||||
char ch = c->pCurrent[ii];
|
||||
c->zToken[ii] = (unsigned char)ch<0x80 ? tolower(ch) : ch;
|
||||
}
|
||||
c->zToken[n] = '\0';
|
||||
*ppToken = c->zToken;
|
||||
*pnBytes = n;
|
||||
*piStartOffset = (int) (c->pCurrent-c->pInput);
|
||||
*piEndOffset = *piStartOffset+n;
|
||||
*piPosition = c->iToken++;
|
||||
c->pCurrent += n + 1;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
c->pCurrent += n + 1;
|
||||
/* TODO(shess) could strspn() to skip delimiters en masse. Needs
|
||||
** to happen in two places, though, which is annoying.
|
||||
*/
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
static sqlite3_tokenizer_module simpleTokenizerModule = {
|
||||
0,
|
||||
simpleCreate,
|
||||
simpleDestroy,
|
||||
simpleOpen,
|
||||
simpleClose,
|
||||
simpleNext,
|
||||
};
|
||||
|
||||
void get_simple_tokenizer_module(
|
||||
sqlite3_tokenizer_module **ppModule
|
||||
){
|
||||
*ppModule = &simpleTokenizerModule;
|
||||
}
|
||||
@@ -1,89 +0,0 @@
|
||||
/*
|
||||
** 2006 July 10
|
||||
**
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Defines the interface to tokenizers used by fulltext-search. There
|
||||
** are three basic components:
|
||||
**
|
||||
** sqlite3_tokenizer_module is a singleton defining the tokenizer
|
||||
** interface functions. This is essentially the class structure for
|
||||
** tokenizers.
|
||||
**
|
||||
** sqlite3_tokenizer is used to define a particular tokenizer, perhaps
|
||||
** including customization information defined at creation time.
|
||||
**
|
||||
** sqlite3_tokenizer_cursor is generated by a tokenizer to generate
|
||||
** tokens from a particular input.
|
||||
*/
|
||||
#ifndef _TOKENIZER_H_
|
||||
#define _TOKENIZER_H_
|
||||
|
||||
/* TODO(shess) Only used for SQLITE_OK and SQLITE_DONE at this time.
|
||||
** If tokenizers are to be allowed to call sqlite3_*() functions, then
|
||||
** we will need a way to register the API consistently.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
/*
|
||||
** Structures used by the tokenizer interface.
|
||||
*/
|
||||
typedef struct sqlite3_tokenizer sqlite3_tokenizer;
|
||||
typedef struct sqlite3_tokenizer_cursor sqlite3_tokenizer_cursor;
|
||||
typedef struct sqlite3_tokenizer_module sqlite3_tokenizer_module;
|
||||
|
||||
struct sqlite3_tokenizer_module {
|
||||
int iVersion; /* currently 0 */
|
||||
|
||||
/*
|
||||
** Create and destroy a tokenizer. argc/argv are passed down from
|
||||
** the fulltext virtual table creation to allow customization.
|
||||
*/
|
||||
int (*xCreate)(int argc, const char **argv,
|
||||
sqlite3_tokenizer **ppTokenizer);
|
||||
int (*xDestroy)(sqlite3_tokenizer *pTokenizer);
|
||||
|
||||
/*
|
||||
** Tokenize a particular input. Call xOpen() to prepare to
|
||||
** tokenize, xNext() repeatedly until it returns SQLITE_DONE, then
|
||||
** xClose() to free any internal state. The pInput passed to
|
||||
** xOpen() must exist until the cursor is closed. The ppToken
|
||||
** result from xNext() is only valid until the next call to xNext()
|
||||
** or until xClose() is called.
|
||||
*/
|
||||
/* TODO(shess) current implementation requires pInput to be
|
||||
** nul-terminated. This should either be fixed, or pInput/nBytes
|
||||
** should be converted to zInput.
|
||||
*/
|
||||
int (*xOpen)(sqlite3_tokenizer *pTokenizer,
|
||||
const char *pInput, int nBytes,
|
||||
sqlite3_tokenizer_cursor **ppCursor);
|
||||
int (*xClose)(sqlite3_tokenizer_cursor *pCursor);
|
||||
int (*xNext)(sqlite3_tokenizer_cursor *pCursor,
|
||||
const char **ppToken, int *pnBytes,
|
||||
int *piStartOffset, int *piEndOffset, int *piPosition);
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer {
|
||||
sqlite3_tokenizer_module *pModule; /* The module for this tokenizer */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer_cursor {
|
||||
sqlite3_tokenizer *pTokenizer; /* Tokenizer for this cursor. */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
/*
|
||||
** Get the module for a tokenizer which generates tokens based on a
|
||||
** set of non-token characters. The default is to break tokens at any
|
||||
** non-alnum character, though the set of delimiters can also be
|
||||
** specified by the first argv argument to xCreate().
|
||||
*/
|
||||
/* TODO(shess) This doesn't belong here. Need some sort of
|
||||
** registration process.
|
||||
*/
|
||||
void get_simple_tokenizer_module(sqlite3_tokenizer_module **ppModule);
|
||||
|
||||
#endif /* _TOKENIZER_H_ */
|
||||
@@ -1,133 +0,0 @@
|
||||
|
||||
1. FTS2 Tokenizers
|
||||
|
||||
When creating a new full-text table, FTS2 allows the user to select
|
||||
the text tokenizer implementation to be used when indexing text
|
||||
by specifying a "tokenizer" clause as part of the CREATE VIRTUAL TABLE
|
||||
statement:
|
||||
|
||||
CREATE VIRTUAL TABLE <table-name> USING fts2(
|
||||
<columns ...> [, tokenizer <tokenizer-name> [<tokenizer-args>]]
|
||||
);
|
||||
|
||||
The built-in tokenizers (valid values to pass as <tokenizer name>) are
|
||||
"simple" and "porter".
|
||||
|
||||
<tokenizer-args> should consist of zero or more white-space separated
|
||||
arguments to pass to the selected tokenizer implementation. The
|
||||
interpretation of the arguments, if any, depends on the individual
|
||||
tokenizer.
|
||||
|
||||
2. Custom Tokenizers
|
||||
|
||||
FTS2 allows users to provide custom tokenizer implementations. The
|
||||
interface used to create a new tokenizer is defined and described in
|
||||
the fts2_tokenizer.h source file.
|
||||
|
||||
Registering a new FTS2 tokenizer is similar to registering a new
|
||||
virtual table module with SQLite. The user passes a pointer to a
|
||||
structure containing pointers to various callback functions that
|
||||
make up the implementation of the new tokenizer type. For tokenizers,
|
||||
the structure (defined in fts2_tokenizer.h) is called
|
||||
"sqlite3_tokenizer_module".
|
||||
|
||||
FTS2 does not expose a C-function that users call to register new
|
||||
tokenizer types with a database handle. Instead, the pointer must
|
||||
be encoded as an SQL blob value and passed to FTS2 through the SQL
|
||||
engine by evaluating a special scalar function, "fts2_tokenizer()".
|
||||
The fts2_tokenizer() function may be called with one or two arguments,
|
||||
as follows:
|
||||
|
||||
SELECT fts2_tokenizer(<tokenizer-name>);
|
||||
SELECT fts2_tokenizer(<tokenizer-name>, <sqlite3_tokenizer_module ptr>);
|
||||
|
||||
Where <tokenizer-name> is a string identifying the tokenizer and
|
||||
<sqlite3_tokenizer_module ptr> is a pointer to an sqlite3_tokenizer_module
|
||||
structure encoded as an SQL blob. If the second argument is present,
|
||||
it is registered as tokenizer <tokenizer-name> and a copy of it
|
||||
returned. If only one argument is passed, a pointer to the tokenizer
|
||||
implementation currently registered as <tokenizer-name> is returned,
|
||||
encoded as a blob. Or, if no such tokenizer exists, an SQL exception
|
||||
(error) is raised.
|
||||
|
||||
SECURITY: If the fts2 extension is used in an environment where potentially
|
||||
malicious users may execute arbitrary SQL (i.e. gears), they should be
|
||||
prevented from invoking the fts2_tokenizer() function, possibly using the
|
||||
authorisation callback.
|
||||
|
||||
See "Sample code" below for an example of calling the fts2_tokenizer()
|
||||
function from C code.
|
||||
|
||||
3. ICU Library Tokenizers
|
||||
|
||||
If this extension is compiled with the SQLITE_ENABLE_ICU pre-processor
|
||||
symbol defined, then there exists a built-in tokenizer named "icu"
|
||||
implemented using the ICU library. The first argument passed to the
|
||||
xCreate() method (see fts2_tokenizer.h) of this tokenizer may be
|
||||
an ICU locale identifier. For example "tr_TR" for Turkish as used
|
||||
in Turkey, or "en_AU" for English as used in Australia. For example:
|
||||
|
||||
"CREATE VIRTUAL TABLE thai_text USING fts2(text, tokenizer icu th_TH)"
|
||||
|
||||
The ICU tokenizer implementation is very simple. It splits the input
|
||||
text according to the ICU rules for finding word boundaries and discards
|
||||
any tokens that consist entirely of white-space. This may be suitable
|
||||
for some applications in some locales, but not all. If more complex
|
||||
processing is required, for example to implement stemming or
|
||||
discard punctuation, this can be done by creating a tokenizer
|
||||
implementation that uses the ICU tokenizer as part of its implementation.
|
||||
|
||||
When using the ICU tokenizer this way, it is safe to overwrite the
|
||||
contents of the strings returned by the xNext() method (see
|
||||
fts2_tokenizer.h).
|
||||
|
||||
4. Sample code.
|
||||
|
||||
The following two code samples illustrate the way C code should invoke
|
||||
the fts2_tokenizer() scalar function:
|
||||
|
||||
int registerTokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module *p
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts2_tokenizer(?, ?)";
|
||||
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
|
||||
sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC);
|
||||
sqlite3_bind_blob(pStmt, 2, &p, sizeof(p), SQLITE_STATIC);
|
||||
sqlite3_step(pStmt);
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
int queryTokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module **pp
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts2_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(pp, sqlite3_column_blob(pStmt, 0), sizeof(*pp));
|
||||
}
|
||||
}
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
@@ -1,4 +0,0 @@
|
||||
This folder contains source code to the second full-text search
|
||||
extension for SQLite. While the API is the same, this version uses a
|
||||
substantially different storage schema from fts1, so tables will need
|
||||
to be rebuilt.
|
||||
-6860
File diff suppressed because it is too large
Load Diff
@@ -1,26 +0,0 @@
|
||||
/*
|
||||
** 2006 Oct 10
|
||||
**
|
||||
** 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 header file is used by programs that want to link against the
|
||||
** FTS2 library. All it does is declare the sqlite3Fts2Init() interface.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif /* __cplusplus */
|
||||
|
||||
int sqlite3Fts2Init(sqlite3 *db);
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" */
|
||||
#endif /* __cplusplus */
|
||||
@@ -1,376 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the implementation of generic hash-tables used in SQLite.
|
||||
** We've modified it slightly to serve as a standalone hash table
|
||||
** implementation for the full-text indexing module.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS2 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS2 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS2 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2)
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_hash.h"
|
||||
|
||||
/*
|
||||
** Malloc and Free functions
|
||||
*/
|
||||
static void *fts2HashMalloc(int n){
|
||||
void *p = sqlite3_malloc(n);
|
||||
if( p ){
|
||||
memset(p, 0, n);
|
||||
}
|
||||
return p;
|
||||
}
|
||||
static void fts2HashFree(void *p){
|
||||
sqlite3_free(p);
|
||||
}
|
||||
|
||||
/* Turn bulk memory into a hash table object by initializing the
|
||||
** fields of the Hash structure.
|
||||
**
|
||||
** "pNew" is a pointer to the hash table that is to be initialized.
|
||||
** keyClass is one of the constants
|
||||
** FTS2_HASH_BINARY or FTS2_HASH_STRING. The value of keyClass
|
||||
** determines what kind of key the hash table will use. "copyKey" is
|
||||
** true if the hash table should make its own private copy of keys and
|
||||
** false if it should just use the supplied pointer.
|
||||
*/
|
||||
void sqlite3Fts2HashInit(fts2Hash *pNew, int keyClass, int copyKey){
|
||||
assert( pNew!=0 );
|
||||
assert( keyClass>=FTS2_HASH_STRING && keyClass<=FTS2_HASH_BINARY );
|
||||
pNew->keyClass = keyClass;
|
||||
pNew->copyKey = copyKey;
|
||||
pNew->first = 0;
|
||||
pNew->count = 0;
|
||||
pNew->htsize = 0;
|
||||
pNew->ht = 0;
|
||||
}
|
||||
|
||||
/* Remove all entries from a hash table. Reclaim all memory.
|
||||
** Call this routine to delete a hash table or to reset a hash table
|
||||
** to the empty state.
|
||||
*/
|
||||
void sqlite3Fts2HashClear(fts2Hash *pH){
|
||||
fts2HashElem *elem; /* For looping over all elements of the table */
|
||||
|
||||
assert( pH!=0 );
|
||||
elem = pH->first;
|
||||
pH->first = 0;
|
||||
fts2HashFree(pH->ht);
|
||||
pH->ht = 0;
|
||||
pH->htsize = 0;
|
||||
while( elem ){
|
||||
fts2HashElem *next_elem = elem->next;
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
fts2HashFree(elem->pKey);
|
||||
}
|
||||
fts2HashFree(elem);
|
||||
elem = next_elem;
|
||||
}
|
||||
pH->count = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS2_HASH_STRING
|
||||
*/
|
||||
static int strHash(const void *pKey, int nKey){
|
||||
const char *z = (const char *)pKey;
|
||||
int h = 0;
|
||||
if( nKey<=0 ) nKey = (int) strlen(z);
|
||||
while( nKey > 0 ){
|
||||
h = (h<<3) ^ h ^ *z++;
|
||||
nKey--;
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int strCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return strncmp((const char*)pKey1,(const char*)pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS2_HASH_BINARY
|
||||
*/
|
||||
static int binHash(const void *pKey, int nKey){
|
||||
int h = 0;
|
||||
const char *z = (const char *)pKey;
|
||||
while( nKey-- > 0 ){
|
||||
h = (h<<3) ^ h ^ *(z++);
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int binCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return memcmp(pKey1,pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** The C syntax in this function definition may be unfamilar to some
|
||||
** programmers, so we provide the following additional explanation:
|
||||
**
|
||||
** The name of the function is "hashFunction". The function takes a
|
||||
** single parameter "keyClass". The return value of hashFunction()
|
||||
** is a pointer to another function. Specifically, the return value
|
||||
** of hashFunction() is a pointer to a function that takes two parameters
|
||||
** with types "const void*" and "int" and returns an "int".
|
||||
*/
|
||||
static int (*hashFunction(int keyClass))(const void*,int){
|
||||
if( keyClass==FTS2_HASH_STRING ){
|
||||
return &strHash;
|
||||
}else{
|
||||
assert( keyClass==FTS2_HASH_BINARY );
|
||||
return &binHash;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** For help in interpreted the obscure C code in the function definition,
|
||||
** see the header comment on the previous function.
|
||||
*/
|
||||
static int (*compareFunction(int keyClass))(const void*,int,const void*,int){
|
||||
if( keyClass==FTS2_HASH_STRING ){
|
||||
return &strCompare;
|
||||
}else{
|
||||
assert( keyClass==FTS2_HASH_BINARY );
|
||||
return &binCompare;
|
||||
}
|
||||
}
|
||||
|
||||
/* Link an element into the hash table
|
||||
*/
|
||||
static void insertElement(
|
||||
fts2Hash *pH, /* The complete hash table */
|
||||
struct _fts2ht *pEntry, /* The entry into which pNew is inserted */
|
||||
fts2HashElem *pNew /* The element to be inserted */
|
||||
){
|
||||
fts2HashElem *pHead; /* First element already in pEntry */
|
||||
pHead = pEntry->chain;
|
||||
if( pHead ){
|
||||
pNew->next = pHead;
|
||||
pNew->prev = pHead->prev;
|
||||
if( pHead->prev ){ pHead->prev->next = pNew; }
|
||||
else { pH->first = pNew; }
|
||||
pHead->prev = pNew;
|
||||
}else{
|
||||
pNew->next = pH->first;
|
||||
if( pH->first ){ pH->first->prev = pNew; }
|
||||
pNew->prev = 0;
|
||||
pH->first = pNew;
|
||||
}
|
||||
pEntry->count++;
|
||||
pEntry->chain = pNew;
|
||||
}
|
||||
|
||||
|
||||
/* Resize the hash table so that it cantains "new_size" buckets.
|
||||
** "new_size" must be a power of 2. The hash table might fail
|
||||
** to resize if sqliteMalloc() fails.
|
||||
*/
|
||||
static void rehash(fts2Hash *pH, int new_size){
|
||||
struct _fts2ht *new_ht; /* The new hash table */
|
||||
fts2HashElem *elem, *next_elem; /* For looping over existing elements */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( (new_size & (new_size-1))==0 );
|
||||
new_ht = (struct _fts2ht *)fts2HashMalloc( new_size*sizeof(struct _fts2ht) );
|
||||
if( new_ht==0 ) return;
|
||||
fts2HashFree(pH->ht);
|
||||
pH->ht = new_ht;
|
||||
pH->htsize = new_size;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
for(elem=pH->first, pH->first=0; elem; elem = next_elem){
|
||||
int h = (*xHash)(elem->pKey, elem->nKey) & (new_size-1);
|
||||
next_elem = elem->next;
|
||||
insertElement(pH, &new_ht[h], elem);
|
||||
}
|
||||
}
|
||||
|
||||
/* This function (for internal use only) locates an element in an
|
||||
** hash table that matches the given key. The hash for this key has
|
||||
** already been computed and is passed as the 4th parameter.
|
||||
*/
|
||||
static fts2HashElem *findElementGivenHash(
|
||||
const fts2Hash *pH, /* The pH to be searched */
|
||||
const void *pKey, /* The key we are searching for */
|
||||
int nKey,
|
||||
int h /* The hash for this key. */
|
||||
){
|
||||
fts2HashElem *elem; /* Used to loop thru the element list */
|
||||
int count; /* Number of elements left to test */
|
||||
int (*xCompare)(const void*,int,const void*,int); /* comparison function */
|
||||
|
||||
if( pH->ht ){
|
||||
struct _fts2ht *pEntry = &pH->ht[h];
|
||||
elem = pEntry->chain;
|
||||
count = pEntry->count;
|
||||
xCompare = compareFunction(pH->keyClass);
|
||||
while( count-- && elem ){
|
||||
if( (*xCompare)(elem->pKey,elem->nKey,pKey,nKey)==0 ){
|
||||
return elem;
|
||||
}
|
||||
elem = elem->next;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Remove a single entry from the hash table given a pointer to that
|
||||
** element and a hash on the element's key.
|
||||
*/
|
||||
static void removeElementGivenHash(
|
||||
fts2Hash *pH, /* The pH containing "elem" */
|
||||
fts2HashElem* elem, /* The element to be removed from the pH */
|
||||
int h /* Hash value for the element */
|
||||
){
|
||||
struct _fts2ht *pEntry;
|
||||
if( elem->prev ){
|
||||
elem->prev->next = elem->next;
|
||||
}else{
|
||||
pH->first = elem->next;
|
||||
}
|
||||
if( elem->next ){
|
||||
elem->next->prev = elem->prev;
|
||||
}
|
||||
pEntry = &pH->ht[h];
|
||||
if( pEntry->chain==elem ){
|
||||
pEntry->chain = elem->next;
|
||||
}
|
||||
pEntry->count--;
|
||||
if( pEntry->count<=0 ){
|
||||
pEntry->chain = 0;
|
||||
}
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
fts2HashFree(elem->pKey);
|
||||
}
|
||||
fts2HashFree( elem );
|
||||
pH->count--;
|
||||
if( pH->count<=0 ){
|
||||
assert( pH->first==0 );
|
||||
assert( pH->count==0 );
|
||||
fts2HashClear(pH);
|
||||
}
|
||||
}
|
||||
|
||||
/* Attempt to locate an element of the hash table pH with a key
|
||||
** that matches pKey,nKey. Return the data for this element if it is
|
||||
** found, or NULL if there is no match.
|
||||
*/
|
||||
void *sqlite3Fts2HashFind(const fts2Hash *pH, const void *pKey, int nKey){
|
||||
int h; /* A hash on key */
|
||||
fts2HashElem *elem; /* The element that matches key */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
if( pH==0 || pH->ht==0 ) return 0;
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
h = (*xHash)(pKey,nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
elem = findElementGivenHash(pH,pKey,nKey, h & (pH->htsize-1));
|
||||
return elem ? elem->data : 0;
|
||||
}
|
||||
|
||||
/* Insert an element into the hash table pH. The key is pKey,nKey
|
||||
** and the data is "data".
|
||||
**
|
||||
** If no element exists with a matching key, then a new
|
||||
** element is created. A copy of the key is made if the copyKey
|
||||
** flag is set. NULL is returned.
|
||||
**
|
||||
** If another element already exists with the same key, then the
|
||||
** new data replaces the old data and the old data is returned.
|
||||
** The key is not copied in this instance. If a malloc fails, then
|
||||
** the new data is returned and the hash table is unchanged.
|
||||
**
|
||||
** If the "data" parameter to this function is NULL, then the
|
||||
** element corresponding to "key" is removed from the hash table.
|
||||
*/
|
||||
void *sqlite3Fts2HashInsert(
|
||||
fts2Hash *pH, /* The hash table to insert into */
|
||||
const void *pKey, /* The key */
|
||||
int nKey, /* Number of bytes in the key */
|
||||
void *data /* The data */
|
||||
){
|
||||
int hraw; /* Raw hash value of the key */
|
||||
int h; /* the hash of the key modulo hash table size */
|
||||
fts2HashElem *elem; /* Used to loop thru the element list */
|
||||
fts2HashElem *new_elem; /* New element added to the pH */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( pH!=0 );
|
||||
xHash = hashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
hraw = (*xHash)(pKey, nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
elem = findElementGivenHash(pH,pKey,nKey,h);
|
||||
if( elem ){
|
||||
void *old_data = elem->data;
|
||||
if( data==0 ){
|
||||
removeElementGivenHash(pH,elem,h);
|
||||
}else{
|
||||
elem->data = data;
|
||||
}
|
||||
return old_data;
|
||||
}
|
||||
if( data==0 ) return 0;
|
||||
new_elem = (fts2HashElem*)fts2HashMalloc( sizeof(fts2HashElem) );
|
||||
if( new_elem==0 ) return data;
|
||||
if( pH->copyKey && pKey!=0 ){
|
||||
new_elem->pKey = fts2HashMalloc( nKey );
|
||||
if( new_elem->pKey==0 ){
|
||||
fts2HashFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
memcpy((void*)new_elem->pKey, pKey, nKey);
|
||||
}else{
|
||||
new_elem->pKey = (void*)pKey;
|
||||
}
|
||||
new_elem->nKey = nKey;
|
||||
pH->count++;
|
||||
if( pH->htsize==0 ){
|
||||
rehash(pH,8);
|
||||
if( pH->htsize==0 ){
|
||||
pH->count = 0;
|
||||
fts2HashFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
}
|
||||
if( pH->count > pH->htsize ){
|
||||
rehash(pH,pH->htsize*2);
|
||||
}
|
||||
assert( pH->htsize>0 );
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
insertElement(pH, &pH->ht[h], new_elem);
|
||||
new_elem->data = data;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2) */
|
||||
@@ -1,110 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the header file for the generic hash-table implementation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
*/
|
||||
#ifndef _FTS2_HASH_H_
|
||||
#define _FTS2_HASH_H_
|
||||
|
||||
/* Forward declarations of structures. */
|
||||
typedef struct fts2Hash fts2Hash;
|
||||
typedef struct fts2HashElem fts2HashElem;
|
||||
|
||||
/* A complete hash table is an instance of the following structure.
|
||||
** The internals of this structure are intended to be opaque -- client
|
||||
** code should not attempt to access or modify the fields of this structure
|
||||
** directly. Change this structure only by using the routines below.
|
||||
** However, many of the "procedures" and "functions" for modifying and
|
||||
** accessing this structure are really macros, so we can't really make
|
||||
** this structure opaque.
|
||||
*/
|
||||
struct fts2Hash {
|
||||
char keyClass; /* HASH_INT, _POINTER, _STRING, _BINARY */
|
||||
char copyKey; /* True if copy of key made on insert */
|
||||
int count; /* Number of entries in this table */
|
||||
fts2HashElem *first; /* The first element of the array */
|
||||
int htsize; /* Number of buckets in the hash table */
|
||||
struct _fts2ht { /* the hash table */
|
||||
int count; /* Number of entries with this hash */
|
||||
fts2HashElem *chain; /* Pointer to first entry with this hash */
|
||||
} *ht;
|
||||
};
|
||||
|
||||
/* Each element in the hash table is an instance of the following
|
||||
** structure. All elements are stored on a single doubly-linked list.
|
||||
**
|
||||
** Again, this structure is intended to be opaque, but it can't really
|
||||
** be opaque because it is used by macros.
|
||||
*/
|
||||
struct fts2HashElem {
|
||||
fts2HashElem *next, *prev; /* Next and previous elements in the table */
|
||||
void *data; /* Data associated with this element */
|
||||
void *pKey; int nKey; /* Key associated with this element */
|
||||
};
|
||||
|
||||
/*
|
||||
** There are 2 different modes of operation for a hash table:
|
||||
**
|
||||
** FTS2_HASH_STRING pKey points to a string that is nKey bytes long
|
||||
** (including the null-terminator, if any). Case
|
||||
** is respected in comparisons.
|
||||
**
|
||||
** FTS2_HASH_BINARY pKey points to binary data nKey bytes long.
|
||||
** memcmp() is used to compare keys.
|
||||
**
|
||||
** A copy of the key is made if the copyKey parameter to fts2HashInit is 1.
|
||||
*/
|
||||
#define FTS2_HASH_STRING 1
|
||||
#define FTS2_HASH_BINARY 2
|
||||
|
||||
/*
|
||||
** Access routines. To delete, insert a NULL pointer.
|
||||
*/
|
||||
void sqlite3Fts2HashInit(fts2Hash*, int keytype, int copyKey);
|
||||
void *sqlite3Fts2HashInsert(fts2Hash*, const void *pKey, int nKey, void *pData);
|
||||
void *sqlite3Fts2HashFind(const fts2Hash*, const void *pKey, int nKey);
|
||||
void sqlite3Fts2HashClear(fts2Hash*);
|
||||
|
||||
/*
|
||||
** Shorthand for the functions above
|
||||
*/
|
||||
#define fts2HashInit sqlite3Fts2HashInit
|
||||
#define fts2HashInsert sqlite3Fts2HashInsert
|
||||
#define fts2HashFind sqlite3Fts2HashFind
|
||||
#define fts2HashClear sqlite3Fts2HashClear
|
||||
|
||||
/*
|
||||
** Macros for looping over all elements of a hash table. The idiom is
|
||||
** like this:
|
||||
**
|
||||
** fts2Hash h;
|
||||
** fts2HashElem *p;
|
||||
** ...
|
||||
** for(p=fts2HashFirst(&h); p; p=fts2HashNext(p)){
|
||||
** SomeStructure *pData = fts2HashData(p);
|
||||
** // do something with pData
|
||||
** }
|
||||
*/
|
||||
#define fts2HashFirst(H) ((H)->first)
|
||||
#define fts2HashNext(E) ((E)->next)
|
||||
#define fts2HashData(E) ((E)->data)
|
||||
#define fts2HashKey(E) ((E)->pKey)
|
||||
#define fts2HashKeysize(E) ((E)->nKey)
|
||||
|
||||
/*
|
||||
** Number of entries in a hash table
|
||||
*/
|
||||
#define fts2HashCount(H) ((H)->count)
|
||||
|
||||
#endif /* _FTS2_HASH_H_ */
|
||||
@@ -1,260 +0,0 @@
|
||||
/*
|
||||
** 2007 June 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 implements a tokenizer for fts2 based on the ICU library.
|
||||
**
|
||||
** $Id: fts2_icu.c,v 1.3 2008/12/18 05:30:26 danielk1977 Exp $
|
||||
*/
|
||||
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2)
|
||||
#ifdef SQLITE_ENABLE_ICU
|
||||
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
#include "fts2_tokenizer.h"
|
||||
|
||||
#include <unicode/ubrk.h>
|
||||
#include <unicode/ucol.h>
|
||||
#include <unicode/ustring.h>
|
||||
#include <unicode/utf16.h>
|
||||
|
||||
typedef struct IcuTokenizer IcuTokenizer;
|
||||
typedef struct IcuCursor IcuCursor;
|
||||
|
||||
struct IcuTokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
char *zLocale;
|
||||
};
|
||||
|
||||
struct IcuCursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
|
||||
UBreakIterator *pIter; /* ICU break-iterator object */
|
||||
int nChar; /* Number of UChar elements in pInput */
|
||||
UChar *aChar; /* Copy of input using utf-16 encoding */
|
||||
int *aOffset; /* Offsets of each character in utf-8 input */
|
||||
|
||||
int nBuffer;
|
||||
char *zBuffer;
|
||||
|
||||
int iToken;
|
||||
};
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int icuCreate(
|
||||
int argc, /* Number of entries in argv[] */
|
||||
const char * const *argv, /* Tokenizer creation arguments */
|
||||
sqlite3_tokenizer **ppTokenizer /* OUT: Created tokenizer */
|
||||
){
|
||||
IcuTokenizer *p;
|
||||
int n = 0;
|
||||
|
||||
if( argc>0 ){
|
||||
n = strlen(argv[0])+1;
|
||||
}
|
||||
p = (IcuTokenizer *)sqlite3_malloc(sizeof(IcuTokenizer)+n);
|
||||
if( !p ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(p, 0, sizeof(IcuTokenizer));
|
||||
|
||||
if( n ){
|
||||
p->zLocale = (char *)&p[1];
|
||||
memcpy(p->zLocale, argv[0], n);
|
||||
}
|
||||
|
||||
*ppTokenizer = (sqlite3_tokenizer *)p;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int icuDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
|
||||
sqlite3_free(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 icuOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *zInput, /* Input string */
|
||||
int nInput, /* Length of zInput in bytes */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
|
||||
IcuCursor *pCsr;
|
||||
|
||||
const int32_t opt = U_FOLD_CASE_DEFAULT;
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
int nChar;
|
||||
|
||||
UChar32 c;
|
||||
int iInput = 0;
|
||||
int iOut = 0;
|
||||
|
||||
*ppCursor = 0;
|
||||
|
||||
if( nInput<0 ){
|
||||
nInput = strlen(zInput);
|
||||
}
|
||||
nChar = nInput+1;
|
||||
pCsr = (IcuCursor *)sqlite3_malloc(
|
||||
sizeof(IcuCursor) + /* IcuCursor */
|
||||
((nChar+3)&~3) * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
(nChar+1) * sizeof(int) /* IcuCursor.aOffset[] */
|
||||
);
|
||||
if( !pCsr ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(pCsr, 0, sizeof(IcuCursor));
|
||||
pCsr->aChar = (UChar *)&pCsr[1];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[(nChar+3)&~3];
|
||||
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
while( c>0 ){
|
||||
int isError = 0;
|
||||
c = u_foldCase(c, opt);
|
||||
U16_APPEND(pCsr->aChar, iOut, nChar, c, isError);
|
||||
if( isError ){
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
|
||||
if( iInput<nInput ){
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
}else{
|
||||
c = 0;
|
||||
}
|
||||
}
|
||||
|
||||
pCsr->pIter = ubrk_open(UBRK_WORD, p->zLocale, pCsr->aChar, iOut, &status);
|
||||
if( !U_SUCCESS(status) ){
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
pCsr->nChar = iOut;
|
||||
|
||||
ubrk_first(pCsr->pIter);
|
||||
*ppCursor = (sqlite3_tokenizer_cursor *)pCsr;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to icuOpen().
|
||||
*/
|
||||
static int icuClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
IcuCursor *pCsr = (IcuCursor *)pCursor;
|
||||
ubrk_close(pCsr->pIter);
|
||||
sqlite3_free(pCsr->zBuffer);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor.
|
||||
*/
|
||||
static int icuNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
|
||||
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 */
|
||||
){
|
||||
IcuCursor *pCsr = (IcuCursor *)pCursor;
|
||||
|
||||
int iStart = 0;
|
||||
int iEnd = 0;
|
||||
int nByte = 0;
|
||||
|
||||
while( iStart==iEnd ){
|
||||
UChar32 c;
|
||||
|
||||
iStart = ubrk_current(pCsr->pIter);
|
||||
iEnd = ubrk_next(pCsr->pIter);
|
||||
if( iEnd==UBRK_DONE ){
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
while( iStart<iEnd ){
|
||||
int iWhite = iStart;
|
||||
U8_NEXT(pCsr->aChar, iWhite, pCsr->nChar, c);
|
||||
if( u_isspace(c) ){
|
||||
iStart = iWhite;
|
||||
}else{
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert(iStart<=iEnd);
|
||||
}
|
||||
|
||||
do {
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
if( nByte ){
|
||||
char *zNew = sqlite3_realloc(pCsr->zBuffer, nByte);
|
||||
if( !zNew ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
pCsr->zBuffer = zNew;
|
||||
pCsr->nBuffer = nByte;
|
||||
}
|
||||
|
||||
u_strToUTF8(
|
||||
pCsr->zBuffer, pCsr->nBuffer, &nByte, /* Output vars */
|
||||
&pCsr->aChar[iStart], iEnd-iStart, /* Input vars */
|
||||
&status /* Output success/failure */
|
||||
);
|
||||
} while( nByte>pCsr->nBuffer );
|
||||
|
||||
*ppToken = pCsr->zBuffer;
|
||||
*pnBytes = nByte;
|
||||
*piStartOffset = pCsr->aOffset[iStart];
|
||||
*piEndOffset = pCsr->aOffset[iEnd];
|
||||
*piPosition = pCsr->iToken++;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 */
|
||||
};
|
||||
|
||||
/*
|
||||
** Set *ppModule to point at the implementation of the ICU tokenizer.
|
||||
*/
|
||||
void sqlite3Fts2IcuTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &icuTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* defined(SQLITE_ENABLE_ICU) */
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2) */
|
||||
@@ -1,644 +0,0 @@
|
||||
/*
|
||||
** 2006 September 30
|
||||
**
|
||||
** 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 full-text-search tokenizer that implements
|
||||
** a Porter stemmer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS2 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS2 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS2 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2)
|
||||
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_tokenizer.h"
|
||||
|
||||
/*
|
||||
** Class derived from sqlite3_tokenizer
|
||||
*/
|
||||
typedef struct porter_tokenizer {
|
||||
sqlite3_tokenizer base; /* Base class */
|
||||
} porter_tokenizer;
|
||||
|
||||
/*
|
||||
** Class derived from sqlit3_tokenizer_cursor
|
||||
*/
|
||||
typedef struct porter_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *zInput; /* input we are tokenizing */
|
||||
int nInput; /* size of the input */
|
||||
int iOffset; /* current position in zInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *zToken; /* storage for current token */
|
||||
int nAllocated; /* space allocated to zToken buffer */
|
||||
} porter_tokenizer_cursor;
|
||||
|
||||
|
||||
/* Forward declaration */
|
||||
static const sqlite3_tokenizer_module porterTokenizerModule;
|
||||
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int porterCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
porter_tokenizer *t;
|
||||
t = (porter_tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
memset(t, 0, sizeof(*t));
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int porterDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
sqlite3_free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Prepare to begin tokenizing a particular string. The input
|
||||
** string to be tokenized is zInput[0..nInput-1]. A cursor
|
||||
** used to incrementally tokenize this string is returned in
|
||||
** *ppCursor.
|
||||
*/
|
||||
static int porterOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *zInput, int nInput, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
porter_tokenizer_cursor *c;
|
||||
|
||||
c = (porter_tokenizer_cursor *) sqlite3_malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->zInput = zInput;
|
||||
if( zInput==0 ){
|
||||
c->nInput = 0;
|
||||
}else if( nInput<0 ){
|
||||
c->nInput = (int)strlen(zInput);
|
||||
}else{
|
||||
c->nInput = nInput;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->zToken = NULL; /* no space allocated, yet. */
|
||||
c->nAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** porterOpen() above.
|
||||
*/
|
||||
static int porterClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
sqlite3_free(c->zToken);
|
||||
sqlite3_free(c);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
/*
|
||||
** Vowel or consonant
|
||||
*/
|
||||
static const char cType[] = {
|
||||
0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0,
|
||||
1, 1, 1, 2, 1
|
||||
};
|
||||
|
||||
/*
|
||||
** isConsonant() and isVowel() determine if their first character in
|
||||
** the string they point to is a consonant or a vowel, according
|
||||
** to Porter ruls.
|
||||
**
|
||||
** A consonate is any letter other than 'a', 'e', 'i', 'o', or 'u'.
|
||||
** 'Y' is a consonant unless it follows another consonant,
|
||||
** in which case it is a vowel.
|
||||
**
|
||||
** In these routine, the letters are in reverse order. So the 'y' rule
|
||||
** is that 'y' is a consonant unless it is followed by another
|
||||
** consonent.
|
||||
*/
|
||||
static int isVowel(const char*);
|
||||
static int isConsonant(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return j;
|
||||
return z[1]==0 || isVowel(z + 1);
|
||||
}
|
||||
static int isVowel(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return 1-j;
|
||||
return isConsonant(z + 1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Let any sequence of one or more vowels be represented by V and let
|
||||
** C be sequence of one or more consonants. Then every word can be
|
||||
** represented as:
|
||||
**
|
||||
** [C] (VC){m} [V]
|
||||
**
|
||||
** In prose: A word is an optional consonant followed by zero or
|
||||
** vowel-consonant pairs followed by an optional vowel. "m" is the
|
||||
** number of vowel consonant pairs. This routine computes the value
|
||||
** of m for the first i bytes of a word.
|
||||
**
|
||||
** Return true if the m-value for z is 1 or more. In other words,
|
||||
** return true if z contains at least one vowel that is followed
|
||||
** by a consonant.
|
||||
**
|
||||
** In this routine z[] is in reverse order. So we are really looking
|
||||
** for an instance of of a consonant followed by a vowel.
|
||||
*/
|
||||
static int m_gt_0(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m which is
|
||||
** exactly 1
|
||||
*/
|
||||
static int m_eq_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 1;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z==0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m>1 instead
|
||||
** or m>0
|
||||
*/
|
||||
static int m_gt_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if there is a vowel anywhere within z[0..n-1]
|
||||
*/
|
||||
static int hasVowel(const char *z){
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends in a double consonant.
|
||||
**
|
||||
** The text is reversed here. So we are really looking at
|
||||
** the first two characters of z[].
|
||||
*/
|
||||
static int doubleConsonant(const char *z){
|
||||
return isConsonant(z) && z[0]==z[1] && isConsonant(z+1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends with three letters which
|
||||
** are consonant-vowel-consonent and where the final consonant
|
||||
** is not 'w', 'x', or 'y'.
|
||||
**
|
||||
** The word is reversed here. So we are really checking the
|
||||
** first three letters and the first one cannot be in [wxy].
|
||||
*/
|
||||
static int star_oh(const char *z){
|
||||
return
|
||||
z[0]!=0 && isConsonant(z) &&
|
||||
z[0]!='w' && z[0]!='x' && z[0]!='y' &&
|
||||
z[1]!=0 && isVowel(z+1) &&
|
||||
z[2]!=0 && isConsonant(z+2);
|
||||
}
|
||||
|
||||
/*
|
||||
** If the word ends with zFrom and xCond() is true for the stem
|
||||
** of the word that preceeds the zFrom ending, then change the
|
||||
** ending to zTo.
|
||||
**
|
||||
** The input word *pz and zFrom are both in reverse order. zTo
|
||||
** is in normal order.
|
||||
**
|
||||
** Return TRUE if zFrom matches. Return FALSE if zFrom does not
|
||||
** match. Not that TRUE is returned even if xCond() fails and
|
||||
** no substitution occurs.
|
||||
*/
|
||||
static int stem(
|
||||
char **pz, /* The word being stemmed (Reversed) */
|
||||
const char *zFrom, /* If the ending matches this... (Reversed) */
|
||||
const char *zTo, /* ... change the ending to this (not reversed) */
|
||||
int (*xCond)(const char*) /* Condition that must be true */
|
||||
){
|
||||
char *z = *pz;
|
||||
while( *zFrom && *zFrom==*z ){ z++; zFrom++; }
|
||||
if( *zFrom!=0 ) return 0;
|
||||
if( xCond && !xCond(z) ) return 1;
|
||||
while( *zTo ){
|
||||
*(--z) = *(zTo++);
|
||||
}
|
||||
*pz = z;
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
** This is the fallback stemmer used when the porter stemmer is
|
||||
** inappropriate. The input word is copied into the output with
|
||||
** US-ASCII case folding. If the input word is too long (more
|
||||
** than 20 bytes if it contains no digits or more than 6 bytes if
|
||||
** it contains digits) then word is truncated to 20 or 6 bytes
|
||||
** by taking 10 or 3 bytes from the beginning and end.
|
||||
*/
|
||||
static void copy_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, mx, j;
|
||||
int hasDigit = 0;
|
||||
for(i=0; i<nIn; i++){
|
||||
int c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zOut[i] = c - 'A' + 'a';
|
||||
}else{
|
||||
if( c>='0' && c<='9' ) hasDigit = 1;
|
||||
zOut[i] = c;
|
||||
}
|
||||
}
|
||||
mx = hasDigit ? 3 : 10;
|
||||
if( nIn>mx*2 ){
|
||||
for(j=mx, i=nIn-mx; i<nIn; i++, j++){
|
||||
zOut[j] = zOut[i];
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
zOut[i] = 0;
|
||||
*pnOut = i;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Stem the input word zIn[0..nIn-1]. Store the output in zOut.
|
||||
** zOut is at least big enough to hold nIn bytes. Write the actual
|
||||
** size of the output word (exclusive of the '\0' terminator) into *pnOut.
|
||||
**
|
||||
** Any upper-case characters in the US-ASCII character set ([A-Z])
|
||||
** are converted to lower case. Upper-case UTF characters are
|
||||
** unchanged.
|
||||
**
|
||||
** Words that are longer than about 20 bytes are stemmed by retaining
|
||||
** a few bytes from the beginning and the end of the word. If the
|
||||
** word contains digits, 3 bytes are taken from the beginning and
|
||||
** 3 bytes from the end. For long words without digits, 10 bytes
|
||||
** are taken from each end. US-ASCII case folding still applies.
|
||||
**
|
||||
** If the input word contains not digits but does characters not
|
||||
** in [a-zA-Z] then no stemming is attempted and this routine just
|
||||
** copies the input into the input into the output with US-ASCII
|
||||
** case folding.
|
||||
**
|
||||
** Stemming never increases the length of the word. So there is
|
||||
** no chance of overflowing the zOut buffer.
|
||||
*/
|
||||
static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, j, c;
|
||||
char zReverse[28];
|
||||
char *z, *z2;
|
||||
if( nIn<3 || nIn>=sizeof(zReverse)-7 ){
|
||||
/* The word is too big or too small for the porter stemmer.
|
||||
** Fallback to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
for(i=0, j=sizeof(zReverse)-6; i<nIn; i++, j--){
|
||||
c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zReverse[j] = c + 'a' - 'A';
|
||||
}else if( c>='a' && c<='z' ){
|
||||
zReverse[j] = c;
|
||||
}else{
|
||||
/* The use of a character not in [a-zA-Z] means that we fallback
|
||||
** to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
}
|
||||
memset(&zReverse[sizeof(zReverse)-5], 0, 5);
|
||||
z = &zReverse[j+1];
|
||||
|
||||
|
||||
/* Step 1a */
|
||||
if( z[0]=='s' ){
|
||||
if(
|
||||
!stem(&z, "sess", "ss", 0) &&
|
||||
!stem(&z, "sei", "i", 0) &&
|
||||
!stem(&z, "ss", "ss", 0)
|
||||
){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1b */
|
||||
z2 = z;
|
||||
if( stem(&z, "dee", "ee", m_gt_0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if(
|
||||
(stem(&z, "gni", "", hasVowel) || stem(&z, "de", "", hasVowel))
|
||||
&& z!=z2
|
||||
){
|
||||
if( stem(&z, "ta", "ate", 0) ||
|
||||
stem(&z, "lb", "ble", 0) ||
|
||||
stem(&z, "zi", "ize", 0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if( doubleConsonant(z) && (*z!='l' && *z!='s' && *z!='z') ){
|
||||
z++;
|
||||
}else if( m_eq_1(z) && star_oh(z) ){
|
||||
*(--z) = 'e';
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1c */
|
||||
if( z[0]=='y' && hasVowel(z+1) ){
|
||||
z[0] = 'i';
|
||||
}
|
||||
|
||||
/* Step 2 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
stem(&z, "lanoita", "ate", m_gt_0) ||
|
||||
stem(&z, "lanoit", "tion", m_gt_0);
|
||||
break;
|
||||
case 'c':
|
||||
stem(&z, "icne", "ence", m_gt_0) ||
|
||||
stem(&z, "icna", "ance", m_gt_0);
|
||||
break;
|
||||
case 'e':
|
||||
stem(&z, "rezi", "ize", m_gt_0);
|
||||
break;
|
||||
case 'g':
|
||||
stem(&z, "igol", "log", m_gt_0);
|
||||
break;
|
||||
case 'l':
|
||||
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':
|
||||
stem(&z, "noitazi", "ize", m_gt_0) ||
|
||||
stem(&z, "noita", "ate", m_gt_0) ||
|
||||
stem(&z, "rota", "ate", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
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':
|
||||
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':
|
||||
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':
|
||||
stem(&z, "laci", "ic", m_gt_0) ||
|
||||
stem(&z, "luf", "", m_gt_0);
|
||||
break;
|
||||
case 's':
|
||||
stem(&z, "ssen", "", m_gt_0);
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 4 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
if( z[0]=='l' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'c':
|
||||
if( z[0]=='e' && z[2]=='n' && (z[3]=='a' || z[3]=='e') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'e':
|
||||
if( z[0]=='r' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'i':
|
||||
if( z[0]=='c' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'l':
|
||||
if( z[0]=='e' && z[2]=='b' && (z[3]=='a' || z[3]=='i') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'n':
|
||||
if( z[0]=='t' ){
|
||||
if( z[2]=='a' ){
|
||||
if( m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
}else if( z[2]=='e' ){
|
||||
stem(&z, "tneme", "", m_gt_1) ||
|
||||
stem(&z, "tnem", "", m_gt_1) ||
|
||||
stem(&z, "tne", "", m_gt_1);
|
||||
}
|
||||
}
|
||||
break;
|
||||
case 'o':
|
||||
if( z[0]=='u' ){
|
||||
if( m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
}else if( z[3]=='s' || z[3]=='t' ){
|
||||
stem(&z, "noi", "", m_gt_1);
|
||||
}
|
||||
break;
|
||||
case 's':
|
||||
if( z[0]=='m' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 't':
|
||||
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) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 'v':
|
||||
case 'z':
|
||||
if( z[0]=='e' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 5a */
|
||||
if( z[0]=='e' ){
|
||||
if( m_gt_1(z+1) ){
|
||||
z++;
|
||||
}else if( m_eq_1(z+1) && !star_oh(z+1) ){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 5b */
|
||||
if( m_gt_1(z) && z[0]=='l' && z[1]=='l' ){
|
||||
z++;
|
||||
}
|
||||
|
||||
/* z[] is now the stemmed word in reverse order. Flip it back
|
||||
** around into forward order and return.
|
||||
*/
|
||||
*pnOut = i = strlen(z);
|
||||
zOut[i] = 0;
|
||||
while( *z ){
|
||||
zOut[--i] = *(z++);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Characters that can be part of a token. We assume any character
|
||||
** whose value is greater than 0x80 (any UTF character) can be
|
||||
** part of a token. In other words, delimiters all must have
|
||||
** values of 0x7f or lower.
|
||||
*/
|
||||
static const char porterIdChar[] = {
|
||||
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, /* 3x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 4x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, /* 5x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 6x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, /* 7x */
|
||||
};
|
||||
#define isDelim(C) (((ch=C)&0x80)==0 && (ch<0x30 || !porterIdChar[ch-0x30]))
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor. The cursor must
|
||||
** have been opened by a prior call to porterOpen().
|
||||
*/
|
||||
static int porterNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by porterOpen */
|
||||
const char **pzToken, /* OUT: *pzToken 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 */
|
||||
){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
const char *z = c->zInput;
|
||||
|
||||
while( c->iOffset<c->nInput ){
|
||||
int iStartOffset, ch;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nInput && isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nInput && !isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int n = c->iOffset-iStartOffset;
|
||||
if( n>c->nAllocated ){
|
||||
c->nAllocated = n+20;
|
||||
c->zToken = sqlite3_realloc(c->zToken, c->nAllocated);
|
||||
if( c->zToken==NULL ) return SQLITE_NOMEM;
|
||||
}
|
||||
porter_stemmer(&z[iStartOffset], n, c->zToken, pnBytes);
|
||||
*pzToken = c->zToken;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the porter-stemmer tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module porterTokenizerModule = {
|
||||
0,
|
||||
porterCreate,
|
||||
porterDestroy,
|
||||
porterOpen,
|
||||
porterClose,
|
||||
porterNext,
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new porter tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts2PorterTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &porterTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2) */
|
||||
@@ -1,371 +0,0 @@
|
||||
/*
|
||||
** 2007 June 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 is part of an SQLite module implementing full-text search.
|
||||
** This particular file implements the generic tokenizer interface.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS2 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS2 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS2 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2)
|
||||
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
|
||||
#include "fts2_hash.h"
|
||||
#include "fts2_tokenizer.h"
|
||||
#include <assert.h>
|
||||
|
||||
/*
|
||||
** Implementation of the SQL scalar function for accessing the underlying
|
||||
** hash table. This function may be called as follows:
|
||||
**
|
||||
** SELECT <function-name>(<key-name>);
|
||||
** SELECT <function-name>(<key-name>, <pointer>);
|
||||
**
|
||||
** where <function-name> is the name passed as the second argument
|
||||
** to the sqlite3Fts2InitHashTable() function (e.g. 'fts2_tokenizer').
|
||||
**
|
||||
** If the <pointer> argument is specified, it must be a blob value
|
||||
** containing a pointer to be stored as the hash data corresponding
|
||||
** to the string <key-name>. If <pointer> is not specified, then
|
||||
** the string <key-name> must already exist in the has table. Otherwise,
|
||||
** an error is returned.
|
||||
**
|
||||
** Whether or not the <pointer> argument is specified, the value returned
|
||||
** 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 scalarFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
fts2Hash *pHash;
|
||||
void *pPtr = 0;
|
||||
const unsigned char *zName;
|
||||
int nName;
|
||||
|
||||
assert( argc==1 || argc==2 );
|
||||
|
||||
pHash = (fts2Hash *)sqlite3_user_data(context);
|
||||
|
||||
zName = sqlite3_value_text(argv[0]);
|
||||
nName = sqlite3_value_bytes(argv[0])+1;
|
||||
|
||||
if( argc==2 ){
|
||||
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 = sqlite3Fts2HashInsert(pHash, (void *)zName, nName, pPtr);
|
||||
if( pOld==pPtr ){
|
||||
sqlite3_result_error(context, "out of memory", -1);
|
||||
return;
|
||||
}
|
||||
}else{
|
||||
pPtr = sqlite3Fts2HashFind(pHash, zName, nName);
|
||||
if( !pPtr ){
|
||||
char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_result_blob(context, (void *)&pPtr, sizeof(pPtr), SQLITE_TRANSIENT);
|
||||
}
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
#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 arguments:
|
||||
**
|
||||
** 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 sqlite3Fts2InitHashTable() function (e.g. 'fts2_tokenizer')
|
||||
** concatenated with the string '_test' (e.g. 'fts2_tokenizer_test').
|
||||
**
|
||||
** The return value is a string that may be interpreted as a Tcl
|
||||
** list. For each token in the <input-string>, three elements are
|
||||
** added to the returned list. The first is the token position, the
|
||||
** second is the token text (folded, stemmed, etc.) and the third is the
|
||||
** substring of <input-string> associated with the token. For example,
|
||||
** using the built-in "simple" tokenizer:
|
||||
**
|
||||
** SELECT fts_tokenizer_test('simple', 'I don't see how');
|
||||
**
|
||||
** will return the string:
|
||||
**
|
||||
** "{0 i I 1 dont don't 2 see see 3 how how}"
|
||||
**
|
||||
*/
|
||||
static void testFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
fts2Hash *pHash;
|
||||
sqlite3_tokenizer_module *p;
|
||||
sqlite3_tokenizer *pTokenizer = 0;
|
||||
sqlite3_tokenizer_cursor *pCsr = 0;
|
||||
|
||||
const char *zErr = 0;
|
||||
|
||||
const char *zName;
|
||||
int nName;
|
||||
const char *zInput;
|
||||
int nInput;
|
||||
|
||||
const char *zArg = 0;
|
||||
|
||||
const char *zToken;
|
||||
int nToken;
|
||||
int iStart;
|
||||
int iEnd;
|
||||
int iPos;
|
||||
|
||||
Tcl_Obj *pRet;
|
||||
|
||||
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 = (fts2Hash *)sqlite3_user_data(context);
|
||||
p = (sqlite3_tokenizer_module *)sqlite3Fts2HashFind(pHash, zName, nName+1);
|
||||
|
||||
if( !p ){
|
||||
char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
|
||||
pRet = Tcl_NewObj();
|
||||
Tcl_IncrRefCount(pRet);
|
||||
|
||||
if( SQLITE_OK!=p->xCreate(zArg ? 1 : 0, &zArg, &pTokenizer) ){
|
||||
zErr = "error in xCreate()";
|
||||
goto finish;
|
||||
}
|
||||
pTokenizer->pModule = p;
|
||||
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));
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken));
|
||||
zToken = &zInput[iStart];
|
||||
nToken = iEnd-iStart;
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken));
|
||||
}
|
||||
|
||||
if( SQLITE_OK!=p->xClose(pCsr) ){
|
||||
zErr = "error in xClose()";
|
||||
goto finish;
|
||||
}
|
||||
if( SQLITE_OK!=p->xDestroy(pTokenizer) ){
|
||||
zErr = "error in xDestroy()";
|
||||
goto finish;
|
||||
}
|
||||
|
||||
finish:
|
||||
if( zErr ){
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
}else{
|
||||
sqlite3_result_text(context, Tcl_GetString(pRet), -1, SQLITE_TRANSIENT);
|
||||
}
|
||||
Tcl_DecrRefCount(pRet);
|
||||
}
|
||||
|
||||
static
|
||||
int registerTokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module *p
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts2_tokenizer(?, ?)";
|
||||
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
|
||||
sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC);
|
||||
sqlite3_bind_blob(pStmt, 2, &p, sizeof(p), SQLITE_STATIC);
|
||||
sqlite3_step(pStmt);
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
static
|
||||
int queryFts2Tokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module **pp
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts2_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(pp, sqlite3_column_blob(pStmt, 0), sizeof(*pp));
|
||||
}
|
||||
}
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
void sqlite3Fts2SimpleTokenizerModule(sqlite3_tokenizer_module const**ppModule);
|
||||
|
||||
/*
|
||||
** Implementation of the scalar function fts2_tokenizer_internal_test().
|
||||
** This function is used for testing only, it is not included in the
|
||||
** build unless SQLITE_TEST is defined.
|
||||
**
|
||||
** The purpose of this is to test that the fts2_tokenizer() function
|
||||
** can be used as designed by the C-code in the queryFts2Tokenizer and
|
||||
** registerTokenizer() functions above. These two functions are repeated
|
||||
** in the README.tokenizer file as an example, so it is important to
|
||||
** test them.
|
||||
**
|
||||
** To run the tests, evaluate the fts2_tokenizer_internal_test() scalar
|
||||
** function with no arguments. An assert() will fail if a problem is
|
||||
** detected. i.e.:
|
||||
**
|
||||
** SELECT fts2_tokenizer_internal_test();
|
||||
**
|
||||
*/
|
||||
static void intTestFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
int rc;
|
||||
const sqlite3_tokenizer_module *p1;
|
||||
const sqlite3_tokenizer_module *p2;
|
||||
sqlite3 *db = (sqlite3 *)sqlite3_user_data(context);
|
||||
|
||||
/* Test the query function */
|
||||
sqlite3Fts2SimpleTokenizerModule(&p1);
|
||||
rc = queryFts2Tokenizer(db, "simple", &p2);
|
||||
assert( rc==SQLITE_OK );
|
||||
assert( p1==p2 );
|
||||
rc = queryFts2Tokenizer(db, "nosuchtokenizer", &p2);
|
||||
assert( rc==SQLITE_ERROR );
|
||||
assert( p2==0 );
|
||||
assert( 0==strcmp(sqlite3_errmsg(db), "unknown tokenizer: nosuchtokenizer") );
|
||||
|
||||
/* Test the storage function */
|
||||
rc = registerTokenizer(db, "nosuchtokenizer", p1);
|
||||
assert( rc==SQLITE_OK );
|
||||
rc = queryFts2Tokenizer(db, "nosuchtokenizer", &p2);
|
||||
assert( rc==SQLITE_OK );
|
||||
assert( p2==p1 );
|
||||
|
||||
sqlite3_result_text(context, "ok", -1, SQLITE_STATIC);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
/*
|
||||
** 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
|
||||
** of the key when a value is inserted. i.e. by a call similar to:
|
||||
**
|
||||
** sqlite3Fts2HashInit(pHash, FTS2_HASH_STRING, 1);
|
||||
**
|
||||
** This function adds a scalar function (see header comment above
|
||||
** 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.
|
||||
**
|
||||
** The third argument to this function, zName, is used as the name
|
||||
** of both the scalar and, if created, the virtual table.
|
||||
*/
|
||||
int sqlite3Fts2InitHashTable(
|
||||
sqlite3 *db,
|
||||
fts2Hash *pHash,
|
||||
const char *zName
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
void *p = (void *)pHash;
|
||||
const int any = SQLITE_ANY;
|
||||
char *zTest = 0;
|
||||
char *zTest2 = 0;
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
void *pdb = (void *)db;
|
||||
zTest = sqlite3_mprintf("%s_test", zName);
|
||||
zTest2 = sqlite3_mprintf("%s_internal_test", zName);
|
||||
if( !zTest || !zTest2 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}
|
||||
#endif
|
||||
|
||||
if( rc!=SQLITE_OK
|
||||
|| (rc = sqlite3_create_function(db, zName, 1, any, p, scalarFunc, 0, 0))
|
||||
|| (rc = sqlite3_create_function(db, zName, 2, any, p, scalarFunc, 0, 0))
|
||||
#ifdef SQLITE_TEST
|
||||
|| (rc = sqlite3_create_function(db, zTest, 2, any, p, testFunc, 0, 0))
|
||||
|| (rc = sqlite3_create_function(db, zTest, 3, any, p, testFunc, 0, 0))
|
||||
|| (rc = sqlite3_create_function(db, zTest2, 0, any, pdb, intTestFunc, 0, 0))
|
||||
#endif
|
||||
);
|
||||
|
||||
sqlite3_free(zTest);
|
||||
sqlite3_free(zTest2);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2) */
|
||||
@@ -1,145 +0,0 @@
|
||||
/*
|
||||
** 2006 July 10
|
||||
**
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Defines the interface to tokenizers used by fulltext-search. There
|
||||
** are three basic components:
|
||||
**
|
||||
** sqlite3_tokenizer_module is a singleton defining the tokenizer
|
||||
** interface functions. This is essentially the class structure for
|
||||
** tokenizers.
|
||||
**
|
||||
** sqlite3_tokenizer is used to define a particular tokenizer, perhaps
|
||||
** including customization information defined at creation time.
|
||||
**
|
||||
** sqlite3_tokenizer_cursor is generated by a tokenizer to generate
|
||||
** tokens from a particular input.
|
||||
*/
|
||||
#ifndef _FTS2_TOKENIZER_H_
|
||||
#define _FTS2_TOKENIZER_H_
|
||||
|
||||
/* TODO(shess) Only used for SQLITE_OK and SQLITE_DONE at this time.
|
||||
** If tokenizers are to be allowed to call sqlite3_*() functions, then
|
||||
** we will need a way to register the API consistently.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
/*
|
||||
** Structures used by the tokenizer interface. When a new tokenizer
|
||||
** implementation is registered, the caller provides a pointer to
|
||||
** an sqlite3_tokenizer_module containing pointers to the callback
|
||||
** functions that make up an implementation.
|
||||
**
|
||||
** When an fts2 table is created, it passes any arguments passed to
|
||||
** the tokenizer clause of the CREATE VIRTUAL TABLE statement to the
|
||||
** sqlite3_tokenizer_module.xCreate() function of the requested tokenizer
|
||||
** implementation. The xCreate() function in turn returns an
|
||||
** sqlite3_tokenizer structure representing the specific tokenizer to
|
||||
** be used for the fts2 table (customized by the tokenizer clause arguments).
|
||||
**
|
||||
** To tokenize an input buffer, the sqlite3_tokenizer_module.xOpen()
|
||||
** method is called. It returns an sqlite3_tokenizer_cursor object
|
||||
** that may be used to tokenize a specific input buffer based on
|
||||
** the tokenization rules supplied by a specific sqlite3_tokenizer
|
||||
** object.
|
||||
*/
|
||||
typedef struct sqlite3_tokenizer_module sqlite3_tokenizer_module;
|
||||
typedef struct sqlite3_tokenizer sqlite3_tokenizer;
|
||||
typedef struct sqlite3_tokenizer_cursor sqlite3_tokenizer_cursor;
|
||||
|
||||
struct sqlite3_tokenizer_module {
|
||||
|
||||
/*
|
||||
** Structure version. Should always be set to 0.
|
||||
*/
|
||||
int iVersion;
|
||||
|
||||
/*
|
||||
** Create a new tokenizer. The values in the argv[] array are the
|
||||
** arguments passed to the "tokenizer" clause of the CREATE VIRTUAL
|
||||
** TABLE statement that created the fts2 table. For example, if
|
||||
** the following SQL is executed:
|
||||
**
|
||||
** CREATE .. USING fts2( ... , tokenizer <tokenizer-name> arg1 arg2)
|
||||
**
|
||||
** then argc is set to 2, and the argv[] array contains pointers
|
||||
** to the strings "arg1" and "arg2".
|
||||
**
|
||||
** 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
|
||||
** this callback. The caller will do so.
|
||||
*/
|
||||
int (*xCreate)(
|
||||
int argc, /* Size of argv array */
|
||||
const char *const*argv, /* Tokenizer argument strings */
|
||||
sqlite3_tokenizer **ppTokenizer /* OUT: Created tokenizer */
|
||||
);
|
||||
|
||||
/*
|
||||
** Destroy an existing tokenizer. The fts2 module calls this method
|
||||
** exactly once for each successful call to xCreate().
|
||||
*/
|
||||
int (*xDestroy)(sqlite3_tokenizer *pTokenizer);
|
||||
|
||||
/*
|
||||
** Create a tokenizer cursor to tokenize an input buffer. The caller
|
||||
** is responsible for ensuring that the input buffer remains valid
|
||||
** until the cursor is closed (using the xClose() method).
|
||||
*/
|
||||
int (*xOpen)(
|
||||
sqlite3_tokenizer *pTokenizer, /* Tokenizer object */
|
||||
const char *pInput, int nBytes, /* Input buffer */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Created tokenizer cursor */
|
||||
);
|
||||
|
||||
/*
|
||||
** Destroy an existing tokenizer cursor. The fts2 module calls this
|
||||
** method exactly once for each successful call to xOpen().
|
||||
*/
|
||||
int (*xClose)(sqlite3_tokenizer_cursor *pCursor);
|
||||
|
||||
/*
|
||||
** Retrieve the next token from the tokenizer cursor pCursor. This
|
||||
** method should either return SQLITE_OK and set the values of the
|
||||
** "OUT" variables identified below, or SQLITE_DONE to indicate that
|
||||
** the end of the buffer has been reached, or an SQLite error code.
|
||||
**
|
||||
** *ppToken should be set to point at a buffer containing the
|
||||
** normalized version of the token (i.e. after any case-folding and/or
|
||||
** stemming has been performed). *pnBytes should be set to the length
|
||||
** of this buffer in bytes. The input text that generated the token is
|
||||
** identified by the byte offsets returned in *piStartOffset and
|
||||
** *piEndOffset.
|
||||
**
|
||||
** The buffer *ppToken is set to point at is managed by the tokenizer
|
||||
** implementation. It is only required to be valid until the next call
|
||||
** to xNext() or xClose().
|
||||
*/
|
||||
/* TODO(shess) current implementation requires pInput to be
|
||||
** nul-terminated. This should either be fixed, or pInput/nBytes
|
||||
** should be converted to zInput.
|
||||
*/
|
||||
int (*xNext)(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Tokenizer cursor */
|
||||
const char **ppToken, int *pnBytes, /* OUT: Normalized text for token */
|
||||
int *piStartOffset, /* OUT: Byte offset of token in input buffer */
|
||||
int *piEndOffset, /* OUT: Byte offset of end of token in input buffer */
|
||||
int *piPosition /* OUT: Number of tokens returned before this one */
|
||||
);
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer {
|
||||
const sqlite3_tokenizer_module *pModule; /* The module for this tokenizer */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer_cursor {
|
||||
sqlite3_tokenizer *pTokenizer; /* Tokenizer for this cursor. */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
#endif /* _FTS2_TOKENIZER_H_ */
|
||||
@@ -1,233 +0,0 @@
|
||||
/*
|
||||
** 2006 Oct 10
|
||||
**
|
||||
** 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 "simple" full-text-search tokenizer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS2 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS2 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS2 is defined).
|
||||
*/
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2)
|
||||
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "sqlite3.h"
|
||||
#include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#include "fts2_tokenizer.h"
|
||||
|
||||
typedef struct simple_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
char delim[128]; /* flag ASCII delimiters */
|
||||
} simple_tokenizer;
|
||||
|
||||
typedef struct simple_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *pInput; /* input we are tokenizing */
|
||||
int nBytes; /* size of the input */
|
||||
int iOffset; /* current position in pInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *pToken; /* storage for current token */
|
||||
int nTokenAllocated; /* space allocated to zToken buffer */
|
||||
} simple_tokenizer_cursor;
|
||||
|
||||
|
||||
/* Forward declaration */
|
||||
static const sqlite3_tokenizer_module simpleTokenizerModule;
|
||||
|
||||
static int simpleDelim(simple_tokenizer *t, unsigned char c){
|
||||
return c<0x80 && t->delim[c];
|
||||
}
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int simpleCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
simple_tokenizer *t;
|
||||
|
||||
t = (simple_tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
memset(t, 0, sizeof(*t));
|
||||
|
||||
/* TODO(shess) Delimiters need to remain the same from run to run,
|
||||
** else we need to reindex. One solution would be a meta-table to
|
||||
** track such information in the database, then we'd only want this
|
||||
** information on the initial create.
|
||||
*/
|
||||
if( argc>1 ){
|
||||
int i, n = strlen(argv[1]);
|
||||
for(i=0; i<n; i++){
|
||||
unsigned char ch = argv[1][i];
|
||||
/* We explicitly don't support UTF-8 delimiters for now. */
|
||||
if( ch>=0x80 ){
|
||||
sqlite3_free(t);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
t->delim[ch] = 1;
|
||||
}
|
||||
} else {
|
||||
/* Mark non-alphanumeric ASCII characters as delimiters */
|
||||
int i;
|
||||
for(i=1; i<0x80; i++){
|
||||
t->delim[i] = !((i>='0' && i<='9') || (i>='A' && i<='Z') ||
|
||||
(i>='a' && i<='z'));
|
||||
}
|
||||
}
|
||||
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
sqlite3_free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 simpleOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *pInput, int nBytes, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
simple_tokenizer_cursor *c;
|
||||
|
||||
c = (simple_tokenizer_cursor *) sqlite3_malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->pInput = pInput;
|
||||
if( pInput==0 ){
|
||||
c->nBytes = 0;
|
||||
}else if( nBytes<0 ){
|
||||
c->nBytes = (int)strlen(pInput);
|
||||
}else{
|
||||
c->nBytes = nBytes;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->pToken = NULL; /* no space allocated, yet. */
|
||||
c->nTokenAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** simpleOpen() above.
|
||||
*/
|
||||
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
sqlite3_free(c->pToken);
|
||||
sqlite3_free(c);
|
||||
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 simpleNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
|
||||
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 */
|
||||
){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
|
||||
unsigned char *p = (unsigned char *)c->pInput;
|
||||
|
||||
while( c->iOffset<c->nBytes ){
|
||||
int iStartOffset;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nBytes && simpleDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nBytes && !simpleDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int i, n = c->iOffset-iStartOffset;
|
||||
if( n>c->nTokenAllocated ){
|
||||
c->nTokenAllocated = n+20;
|
||||
c->pToken = sqlite3_realloc(c->pToken, c->nTokenAllocated);
|
||||
if( c->pToken==NULL ) return SQLITE_NOMEM;
|
||||
}
|
||||
for(i=0; i<n; i++){
|
||||
/* TODO(shess) This needs expansion to handle UTF-8
|
||||
** case-insensitivity.
|
||||
*/
|
||||
unsigned char ch = p[iStartOffset+i];
|
||||
c->pToken[i] = (ch>='A' && ch<='Z') ? (ch - 'A' + 'a') : ch;
|
||||
}
|
||||
*ppToken = c->pToken;
|
||||
*pnBytes = n;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the simple tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module simpleTokenizerModule = {
|
||||
0,
|
||||
simpleCreate,
|
||||
simpleDestroy,
|
||||
simpleOpen,
|
||||
simpleClose,
|
||||
simpleNext,
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new simple tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts2SimpleTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &simpleTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS2) */
|
||||
@@ -1,116 +0,0 @@
|
||||
#!/usr/bin/tclsh
|
||||
#
|
||||
# This script builds a single C code file holding all of FTS2 code.
|
||||
# The name of the output file is fts2amal.c. To build this file,
|
||||
# first do:
|
||||
#
|
||||
# make target_source
|
||||
#
|
||||
# The make target above moves all of the source code files into
|
||||
# a subdirectory named "tsrc". (This script expects to find the files
|
||||
# there and will not work if they are not found.)
|
||||
#
|
||||
# After the "tsrc" directory has been created and populated, run
|
||||
# this script:
|
||||
#
|
||||
# tclsh mkfts2amal.tcl
|
||||
#
|
||||
# The amalgamated FTS2 code will be written into fts2amal.c
|
||||
#
|
||||
|
||||
# Open the output file and write a header comment at the beginning
|
||||
# of the file.
|
||||
#
|
||||
set out [open fts2amal.c w]
|
||||
set today [clock format [clock seconds] -format "%Y-%m-%d %H:%M:%S UTC" -gmt 1]
|
||||
puts $out [subst \
|
||||
{/******************************************************************************
|
||||
** This file is an amalgamation of separate C source files from the SQLite
|
||||
** Full Text Search extension 2 (fts2). By combining all the individual C
|
||||
** code files into this single large file, the entire code can be compiled
|
||||
** as a one translation unit. This allows many compilers to do optimizations
|
||||
** that would not be possible if the files were compiled separately. It also
|
||||
** makes the code easier to import into other projects.
|
||||
**
|
||||
** This amalgamation was generated on $today.
|
||||
*/}]
|
||||
|
||||
# These are the header files used by FTS2. The first time any of these
|
||||
# files are seen in a #include statement in the C code, include the complete
|
||||
# text of the file in-line. The file only needs to be included once.
|
||||
#
|
||||
foreach hdr {
|
||||
fts2.h
|
||||
fts2_hash.h
|
||||
fts2_tokenizer.h
|
||||
sqlite3.h
|
||||
sqlite3ext.h
|
||||
} {
|
||||
set available_hdr($hdr) 1
|
||||
}
|
||||
|
||||
# 78 stars used for comment formatting.
|
||||
set s78 \
|
||||
{*****************************************************************************}
|
||||
|
||||
# Insert a comment into the code
|
||||
#
|
||||
proc section_comment {text} {
|
||||
global out s78
|
||||
set n [string length $text]
|
||||
set nstar [expr {60 - $n}]
|
||||
set stars [string range $s78 0 $nstar]
|
||||
puts $out "/************** $text $stars/"
|
||||
}
|
||||
|
||||
# Read the source file named $filename and write it into the
|
||||
# sqlite3.c output file. If any #include statements are seen,
|
||||
# process them approprately.
|
||||
#
|
||||
proc copy_file {filename} {
|
||||
global seen_hdr available_hdr out
|
||||
set tail [file tail $filename]
|
||||
section_comment "Begin file $tail"
|
||||
set in [open $filename r]
|
||||
while {![eof $in]} {
|
||||
set line [gets $in]
|
||||
if {[regexp {^#\s*include\s+["<]([^">]+)[">]} $line all hdr]} {
|
||||
if {[info exists available_hdr($hdr)]} {
|
||||
if {$available_hdr($hdr)} {
|
||||
section_comment "Include $hdr in the middle of $tail"
|
||||
copy_file tsrc/$hdr
|
||||
section_comment "Continuing where we left off in $tail"
|
||||
}
|
||||
} elseif {![info exists seen_hdr($hdr)]} {
|
||||
set seen_hdr($hdr) 1
|
||||
puts $out $line
|
||||
}
|
||||
} elseif {[regexp {^#ifdef __cplusplus} $line]} {
|
||||
puts $out "#if 0"
|
||||
} elseif {[regexp {^#line} $line]} {
|
||||
# Skip #line directives.
|
||||
} else {
|
||||
puts $out $line
|
||||
}
|
||||
}
|
||||
close $in
|
||||
section_comment "End of $tail"
|
||||
}
|
||||
|
||||
|
||||
# Process the source files. Process files containing commonly
|
||||
# used subroutines first in order to help the compiler find
|
||||
# inlining opportunities.
|
||||
#
|
||||
foreach file {
|
||||
fts2.c
|
||||
fts2_hash.c
|
||||
fts2_porter.c
|
||||
fts2_tokenizer.c
|
||||
fts2_tokenizer1.c
|
||||
fts2_icu.c
|
||||
} {
|
||||
copy_file tsrc/$file
|
||||
}
|
||||
|
||||
close $out
|
||||
@@ -1,178 +0,0 @@
|
||||
|
||||
FTS4 CONTENT OPTION
|
||||
|
||||
Normally, in order to create a full-text index on a dataset, the FTS4
|
||||
module stores a copy of all indexed documents in a specially created
|
||||
database table.
|
||||
|
||||
As of SQLite version 3.7.9, FTS4 supports a new option - "content" -
|
||||
designed to extend FTS4 to support the creation of full-text indexes where:
|
||||
|
||||
* The indexed documents are not stored within the SQLite database
|
||||
at all (a "contentless" FTS4 table), or
|
||||
|
||||
* The indexed documents are stored in a database table created and
|
||||
managed by the user (an "external content" FTS4 table).
|
||||
|
||||
Because the indexed documents themselves are usually much larger than
|
||||
the full-text index, the content option can sometimes be used to achieve
|
||||
significant space savings.
|
||||
|
||||
CONTENTLESS FTS4 TABLES
|
||||
|
||||
In order to create an FTS4 table that does not store a copy of the indexed
|
||||
documents at all, the content option should be set to an empty string.
|
||||
For example, the following SQL creates such an FTS4 table with three
|
||||
columns - "a", "b", and "c":
|
||||
|
||||
CREATE VIRTUAL TABLE t1 USING fts4(content="", a, b, c);
|
||||
|
||||
Data can be inserted into such an FTS4 table using an INSERT statements.
|
||||
However, unlike ordinary FTS4 tables, the user must supply an explicit
|
||||
integer docid value. For example:
|
||||
|
||||
-- This statement is Ok:
|
||||
INSERT INTO t1(docid, a, b, c) VALUES(1, 'a b c', 'd e f', 'g h i');
|
||||
|
||||
-- This statement causes an error, as no docid value has been provided:
|
||||
INSERT INTO t1(a, b, c) VALUES('j k l', 'm n o', 'p q r');
|
||||
|
||||
It is not possible to UPDATE or DELETE a row stored in a contentless FTS4
|
||||
table. Attempting to do so is an error.
|
||||
|
||||
Contentless FTS4 tables also support SELECT statements. However, it is
|
||||
an error to attempt to retrieve the value of any table column other than
|
||||
the docid column. The auxiliary function matchinfo() may be used, but
|
||||
snippet() and offsets() may not. For example:
|
||||
|
||||
-- The following statements are Ok:
|
||||
SELECT docid FROM t1 WHERE t1 MATCH 'xxx';
|
||||
SELECT docid FROM t1 WHERE a MATCH 'xxx';
|
||||
SELECT matchinfo(t1) FROM t1 WHERE t1 MATCH 'xxx';
|
||||
|
||||
-- The following statements all cause errors, as the value of columns
|
||||
-- other than docid are required to evaluate them.
|
||||
SELECT * FROM t1;
|
||||
SELECT a, b FROM t1 WHERE t1 MATCH 'xxx';
|
||||
SELECT docid FROM t1 WHERE a LIKE 'xxx%';
|
||||
SELECT snippet(t1) FROM t1 WHERE t1 MATCH 'xxx';
|
||||
|
||||
Errors related to attempting to retrieve column values other than docid
|
||||
are runtime errors that occur within sqlite3_step(). In some cases, for
|
||||
example if the MATCH expression in a SELECT query matches zero rows, there
|
||||
may be no error at all even if a statement does refer to column values
|
||||
other than docid.
|
||||
|
||||
EXTERNAL CONTENT FTS4 TABLES
|
||||
|
||||
An "external content" FTS4 table is similar to a contentless table, except
|
||||
that if evaluation of a query requires the value of a column other than
|
||||
docid, FTS4 attempts to retrieve that value from a table (or view, or
|
||||
virtual table) nominated by the user (hereafter referred to as the "content
|
||||
table"). The FTS4 module never writes to the content table, and writing
|
||||
to the content table does not affect the full-text index. It is the
|
||||
responsibility of the user to ensure that the content table and the
|
||||
full-text index are consistent.
|
||||
|
||||
An external content FTS4 table is created by setting the content option
|
||||
to the name of a table (or view, or virtual table) that may be queried by
|
||||
FTS4 to retrieve column values when required. If the nominated table does
|
||||
not exist, then an external content table behaves in the same way as
|
||||
a contentless table. For example:
|
||||
|
||||
CREATE TABLE t2(id INTEGER PRIMARY KEY, a, b, c);
|
||||
CREATE VIRTUAL TABLE t3 USING fts4(content="t2", a, c);
|
||||
|
||||
Assuming the nominated table does exist, then its columns must be the same
|
||||
as or a superset of those defined for the FTS table.
|
||||
|
||||
When a users query on the FTS table requires a column value other than
|
||||
docid, FTS attempts to read this value from the corresponding column of
|
||||
the row in the content table with a rowid value equal to the current FTS
|
||||
docid. Or, if such a row cannot be found in the content table, a NULL
|
||||
value is used instead. For example:
|
||||
|
||||
CREATE TABLE t2(id INTEGER PRIMARY KEY, a, b, c, d);
|
||||
CREATE VIRTUAL TABLE t3 USING fts4(content="t2", b, c);
|
||||
|
||||
INSERT INTO t2 VALUES(2, 'a b', 'c d', 'e f');
|
||||
INSERT INTO t2 VALUES(3, 'g h', 'i j', 'k l');
|
||||
INSERT INTO t3(docid, b, c) SELECT id, b, c FROM t2;
|
||||
|
||||
-- The following query returns a single row with two columns containing
|
||||
-- the text values "i j" and "k l".
|
||||
--
|
||||
-- The query uses the full-text index to discover that the MATCH
|
||||
-- term matches the row with docid=3. It then retrieves the values
|
||||
-- of columns b and c from the row with rowid=3 in the content table
|
||||
-- to return.
|
||||
--
|
||||
SELECT * FROM t3 WHERE t3 MATCH 'k';
|
||||
|
||||
-- Following the UPDATE, the query still returns a single row, this
|
||||
-- time containing the text values "xxx" and "yyy". This is because the
|
||||
-- full-text index still indicates that the row with docid=3 matches
|
||||
-- the FTS4 query 'k', even though the documents stored in the content
|
||||
-- table have been modified.
|
||||
--
|
||||
UPDATE t2 SET b = 'xxx', c = 'yyy' WHERE rowid = 3;
|
||||
SELECT * FROM t3 WHERE t3 MATCH 'k';
|
||||
|
||||
-- Following the DELETE below, the query returns one row containing two
|
||||
-- NULL values. NULL values are returned because FTS is unable to find
|
||||
-- a row with rowid=3 within the content table.
|
||||
--
|
||||
DELETE FROM t2;
|
||||
SELECT * FROM t3 WHERE t3 MATCH 'k';
|
||||
|
||||
When a row is deleted from an external content FTS4 table, FTS4 needs to
|
||||
retrieve the column values of the row being deleted from the content table.
|
||||
This is so that FTS4 can update the full-text index entries for each token
|
||||
that occurs within the deleted row to indicate that that row has been
|
||||
deleted. If the content table row cannot be found, or if it contains values
|
||||
inconsistent with the contents of the FTS index, the results can be difficult
|
||||
to predict. The FTS index may be left containing entries corresponding to the
|
||||
deleted row, which can lead to seemingly nonsensical results being returned
|
||||
by subsequent SELECT queries. The same applies when a row is updated, as
|
||||
internally an UPDATE is the same as a DELETE followed by an INSERT.
|
||||
|
||||
Instead of writing separately to the full-text index and the content table,
|
||||
some users may wish to use database triggers to keep the full-text index
|
||||
up to date with respect to the set of documents stored in the content table.
|
||||
For example, using the tables from earlier examples:
|
||||
|
||||
CREATE TRIGGER t2_bu BEFORE UPDATE ON t2 BEGIN
|
||||
DELETE FROM t3 WHERE docid=old.rowid;
|
||||
END;
|
||||
CREATE TRIGGER t2_bd BEFORE DELETE ON t2 BEGIN
|
||||
DELETE FROM t3 WHERE docid=old.rowid;
|
||||
END;
|
||||
|
||||
CREATE TRIGGER t2_bu AFTER UPDATE ON t2 BEGIN
|
||||
INSERT INTO t3(docid, b, c) VALUES(new.rowid, new.b, new.c);
|
||||
END;
|
||||
CREATE TRIGGER t2_bd AFTER INSERT ON t2 BEGIN
|
||||
INSERT INTO t3(docid, b, c) VALUES(new.rowid, new.b, new.c);
|
||||
END;
|
||||
|
||||
The DELETE trigger must be fired before the actual delete takes place
|
||||
on the content table. This is so that FTS4 can still retrieve the original
|
||||
values in order to update the full-text index. And the INSERT trigger must
|
||||
be fired after the new row is inserted, so as to handle the case where the
|
||||
rowid is assigned automatically within the system. The UPDATE trigger must
|
||||
be split into two parts, one fired before and one after the update of the
|
||||
content table, for the same reasons.
|
||||
|
||||
FTS4 features a special command similar to the 'optimize' command that
|
||||
deletes the entire full-text index and rebuilds it based on the current
|
||||
set of documents in the content table. Assuming again that "t3" is the
|
||||
name of the external content FTS4 table, the command is:
|
||||
|
||||
INSERT INTO t3(t3) VALUES('rebuild');
|
||||
|
||||
This command may also be used with ordinary FTS4 tables, although it may
|
||||
only be useful if the full-text index has somehow become corrupt. It is an
|
||||
error to attempt to rebuild the full-text index maintained by a contentless
|
||||
FTS4 table.
|
||||
|
||||
|
||||
@@ -1,209 +0,0 @@
|
||||
|
||||
1. OVERVIEW
|
||||
|
||||
This README file describes the syntax of the arguments that may be passed to
|
||||
the FTS3 MATCH operator used for full-text queries. For example, if table
|
||||
"t1" is an Fts3 virtual table, the following SQL query:
|
||||
|
||||
SELECT * FROM t1 WHERE <col> MATCH <full-text query>
|
||||
|
||||
may be used to retrieve all rows that match a specified for full-text query.
|
||||
The text "<col>" should be replaced by either the name of the fts3 table
|
||||
(in this case "t1"), or by the name of one of the columns of the fts3
|
||||
table. <full-text-query> should be replaced by an SQL expression that
|
||||
computes to a string containing an Fts3 query.
|
||||
|
||||
If the left-hand-side of the MATCH operator is set to the name of the
|
||||
fts3 table, then by default the query may be matched against any column
|
||||
of the table. If it is set to a column name, then by default the query
|
||||
may only match the specified column. In both cases this may be overriden
|
||||
as part of the query text (see sections 2 and 3 below).
|
||||
|
||||
As of SQLite version 3.6.8, Fts3 supports two slightly different query
|
||||
formats; the standard syntax, which is used by default, and the enhanced
|
||||
query syntax which can be selected by compiling with the pre-processor
|
||||
symbol SQLITE_ENABLE_FTS3_PARENTHESIS defined.
|
||||
|
||||
-DSQLITE_ENABLE_FTS3_PARENTHESIS
|
||||
|
||||
2. STANDARD QUERY SYNTAX
|
||||
|
||||
When using the standard Fts3 query syntax, a query usually consists of a
|
||||
list of terms (words) separated by white-space characters. To match a
|
||||
query, a row (or column) of an Fts3 table must contain each of the specified
|
||||
terms. For example, the following query:
|
||||
|
||||
<col> MATCH 'hello world'
|
||||
|
||||
matches rows (or columns, if <col> is the name of a column name) that
|
||||
contain at least one instance of the token "hello", and at least one
|
||||
instance of the token "world". Tokens may be grouped into phrases using
|
||||
quotation marks. In this case, a matching row or column must contain each
|
||||
of the tokens in the phrase in the order specified, with no intervening
|
||||
tokens. For example, the query:
|
||||
|
||||
<col> MATCH '"hello world" joe"
|
||||
|
||||
matches the first of the following two documents, but not the second or
|
||||
third:
|
||||
|
||||
"'Hello world', said Joe."
|
||||
"One should always greet the world with a cheery hello, thought Joe."
|
||||
"How many hello world programs could their be?"
|
||||
|
||||
As well as grouping tokens together by phrase, the binary NEAR operator
|
||||
may be used to search for rows that contain two or more specified tokens
|
||||
or phrases within a specified proximity of each other. The NEAR operator
|
||||
must always be specified in upper case. The word "near" in lower or mixed
|
||||
case is treated as an ordinary token. For example, the following query:
|
||||
|
||||
<col> MATCH 'engineering NEAR consultancy'
|
||||
|
||||
matches rows that contain both the "engineering" and "consultancy" tokens
|
||||
in the same column with not more than 10 other words between them. It does
|
||||
not matter which of the two terms occurs first in the document, only that
|
||||
they be seperated by only 10 tokens or less. The user may also specify
|
||||
a different required proximity by adding "/N" immediately after the NEAR
|
||||
operator, where N is an integer. For example:
|
||||
|
||||
<col> MATCH 'engineering NEAR/5 consultancy'
|
||||
|
||||
searches for a row containing an instance of each specified token seperated
|
||||
by not more than 5 other tokens. More than one NEAR operator can be used
|
||||
in as sequence. For example this query:
|
||||
|
||||
<col> MATCH 'reliable NEAR/2 engineering NEAR/5 consultancy'
|
||||
|
||||
searches for a row that contains an instance of the token "reliable"
|
||||
seperated by not more than two tokens from an instance of "engineering",
|
||||
which is in turn separated by not more than 5 other tokens from an
|
||||
instance of the term "consultancy". Phrases enclosed in quotes may
|
||||
also be used as arguments to the NEAR operator.
|
||||
|
||||
Similar to the NEAR operator, one or more tokens or phrases may be
|
||||
separated by OR operators. In this case, only one of the specified tokens
|
||||
or phrases must appear in the document. For example, the query:
|
||||
|
||||
<col> MATCH 'hello OR world'
|
||||
|
||||
matches rows that contain either the term "hello", or the term "world",
|
||||
or both. Note that unlike in many programming languages, the OR operator
|
||||
has a higher precedence than the AND operators implied between white-space
|
||||
separated tokens. The following query matches documents that contain the
|
||||
term 'sqlite' and at least one of the terms 'fantastic' or 'impressive',
|
||||
not those that contain both 'sqlite' and 'fantastic' or 'impressive':
|
||||
|
||||
<col> MATCH 'sqlite fantastic OR impressive'
|
||||
|
||||
Any token that is part of an Fts3 query expression, whether or not it is
|
||||
part of a phrase enclosed in quotes, may have a '*' character appended to
|
||||
it. In this case, the token matches all terms that begin with the characters
|
||||
of the token, not just those that exactly match it. For example, the
|
||||
following query:
|
||||
|
||||
<col> MATCH 'sql*'
|
||||
|
||||
matches all rows that contain the term "SQLite", as well as those that
|
||||
contain "SQL".
|
||||
|
||||
A token that is not part of a quoted phrase may be preceded by a '-'
|
||||
character, which indicates that matching rows must not contain the
|
||||
specified term. For example, the following:
|
||||
|
||||
<col> MATCH '"database engine" -sqlite'
|
||||
|
||||
matches rows that contain the phrase "database engine" but do not contain
|
||||
the term "sqlite". If the '-' character occurs inside a quoted phrase,
|
||||
it is ignored. It is possible to use both the '-' prefix and the '*' postfix
|
||||
on a single term. At this time, all Fts3 queries must contain at least
|
||||
one term or phrase that is not preceded by the '-' prefix.
|
||||
|
||||
Regardless of whether or not a table name or column name is used on the
|
||||
left hand side of the MATCH operator, a specific column of the fts3 table
|
||||
may be associated with each token in a query by preceding a token with
|
||||
a column name followed by a ':' character. For example, regardless of what
|
||||
is specified for <col>, the following query requires that column "col1"
|
||||
of the table contains the term "hello", and that column "col2" of the
|
||||
table contains the term "world". If the table does not contain columns
|
||||
named "col1" and "col2", then an error is returned and the query is
|
||||
not run.
|
||||
|
||||
<col> MATCH 'col1:hello col2:world'
|
||||
|
||||
It is not possible to associate a specific table column with a quoted
|
||||
phrase or a term preceded by a '-' operator. A '*' character may be
|
||||
appended to a term associated with a specific column for prefix matching.
|
||||
|
||||
3. ENHANCED QUERY SYNTAX
|
||||
|
||||
The enhanced query syntax is quite similar to the standard query syntax,
|
||||
with the following four differences:
|
||||
|
||||
1) Parenthesis are supported. When using the enhanced query syntax,
|
||||
parenthesis may be used to overcome the built-in precedence of the
|
||||
supplied binary operators. For example, the following query:
|
||||
|
||||
<col> MATCH '(hello world) OR (simple example)'
|
||||
|
||||
matches documents that contain both "hello" and "world", and documents
|
||||
that contain both "simple" and "example". It is not possible to forumlate
|
||||
such a query using the standard syntax.
|
||||
|
||||
2) Instead of separating tokens and phrases by whitespace, an AND operator
|
||||
may be explicitly specified. This does not change query processing at
|
||||
all, but may be used to improve readability. For example, the following
|
||||
query is handled identically to the one above:
|
||||
|
||||
<col> MATCH '(hello AND world) OR (simple AND example)'
|
||||
|
||||
As with the OR and NEAR operators, the AND operator must be specified
|
||||
in upper case. The word "and" specified in lower or mixed case is
|
||||
handled as a regular token.
|
||||
|
||||
3) The '-' token prefix is not supported. Instead, a new binary operator,
|
||||
NOT, is included. The NOT operator requires that the query specified
|
||||
as its left-hand operator matches, but that the query specified as the
|
||||
right-hand operator does not. For example, to query for all rows that
|
||||
contain the term "example" but not the term "simple", the following
|
||||
query could be used:
|
||||
|
||||
<col> MATCH 'example NOT simple'
|
||||
|
||||
As for all other operators, the NOT operator must be specified in
|
||||
upper case. Otherwise it will be treated as a regular token.
|
||||
|
||||
4) Unlike in the standard syntax, where the OR operator has a higher
|
||||
precedence than the implicit AND operator, when using the enhanced
|
||||
syntax implicit and explict AND operators have a higher precedence
|
||||
than OR operators. Using the enhanced syntax, the following two
|
||||
queries are equivalent:
|
||||
|
||||
<col> MATCH 'sqlite fantastic OR impressive'
|
||||
<col> MATCH '(sqlite AND fantastic) OR impressive'
|
||||
|
||||
however, when using the standard syntax, the query:
|
||||
|
||||
<col> MATCH 'sqlite fantastic OR impressive'
|
||||
|
||||
is equivalent to the enhanced syntax query:
|
||||
|
||||
<col> MATCH 'sqlite AND (fantastic OR impressive)'
|
||||
|
||||
The precedence of all enhanced syntax operators, in order from highest
|
||||
to lowest, is:
|
||||
|
||||
NEAR (highest precedence, tightest grouping)
|
||||
NOT
|
||||
AND
|
||||
OR (lowest precedence, loosest grouping)
|
||||
|
||||
Using the advanced syntax, it is possible to specify expressions enclosed
|
||||
in parenthesis as operands to the NOT, AND and OR operators. However both
|
||||
the left and right hand side operands of NEAR operators must be either
|
||||
tokens or phrases. Attempting the following query will return an error:
|
||||
|
||||
<col> MATCH 'sqlite NEAR (fantastic OR impressive)'
|
||||
|
||||
Queries of this form must be re-written as:
|
||||
|
||||
<col> MATCH 'sqlite NEAR fantastic OR sqlite NEAR impressive'
|
||||
@@ -1,133 +0,0 @@
|
||||
|
||||
1. FTS3 Tokenizers
|
||||
|
||||
When creating a new full-text table, FTS3 allows the user to select
|
||||
the text tokenizer implementation to be used when indexing text
|
||||
by specifying a "tokenize" clause as part of the CREATE VIRTUAL TABLE
|
||||
statement:
|
||||
|
||||
CREATE VIRTUAL TABLE <table-name> USING fts3(
|
||||
<columns ...> [, tokenize <tokenizer-name> [<tokenizer-args>]]
|
||||
);
|
||||
|
||||
The built-in tokenizers (valid values to pass as <tokenizer name>) are
|
||||
"simple", "porter" and "unicode".
|
||||
|
||||
<tokenizer-args> should consist of zero or more white-space separated
|
||||
arguments to pass to the selected tokenizer implementation. The
|
||||
interpretation of the arguments, if any, depends on the individual
|
||||
tokenizer.
|
||||
|
||||
2. Custom Tokenizers
|
||||
|
||||
FTS3 allows users to provide custom tokenizer implementations. The
|
||||
interface used to create a new tokenizer is defined and described in
|
||||
the fts3_tokenizer.h source file.
|
||||
|
||||
Registering a new FTS3 tokenizer is similar to registering a new
|
||||
virtual table module with SQLite. The user passes a pointer to a
|
||||
structure containing pointers to various callback functions that
|
||||
make up the implementation of the new tokenizer type. For tokenizers,
|
||||
the structure (defined in fts3_tokenizer.h) is called
|
||||
"sqlite3_tokenizer_module".
|
||||
|
||||
FTS3 does not expose a C-function that users call to register new
|
||||
tokenizer types with a database handle. Instead, the pointer must
|
||||
be encoded as an SQL blob value and passed to FTS3 through the SQL
|
||||
engine by evaluating a special scalar function, "fts3_tokenizer()".
|
||||
The fts3_tokenizer() function may be called with one or two arguments,
|
||||
as follows:
|
||||
|
||||
SELECT fts3_tokenizer(<tokenizer-name>);
|
||||
SELECT fts3_tokenizer(<tokenizer-name>, <sqlite3_tokenizer_module ptr>);
|
||||
|
||||
Where <tokenizer-name> is a string identifying the tokenizer and
|
||||
<sqlite3_tokenizer_module ptr> is a pointer to an sqlite3_tokenizer_module
|
||||
structure encoded as an SQL blob. If the second argument is present,
|
||||
it is registered as tokenizer <tokenizer-name> and a copy of it
|
||||
returned. If only one argument is passed, a pointer to the tokenizer
|
||||
implementation currently registered as <tokenizer-name> is returned,
|
||||
encoded as a blob. Or, if no such tokenizer exists, an SQL exception
|
||||
(error) is raised.
|
||||
|
||||
SECURITY: If the fts3 extension is used in an environment where potentially
|
||||
malicious users may execute arbitrary SQL (i.e. gears), they should be
|
||||
prevented from invoking the fts3_tokenizer() function, possibly using the
|
||||
authorisation callback.
|
||||
|
||||
See "Sample code" below for an example of calling the fts3_tokenizer()
|
||||
function from C code.
|
||||
|
||||
3. ICU Library Tokenizers
|
||||
|
||||
If this extension is compiled with the SQLITE_ENABLE_ICU pre-processor
|
||||
symbol defined, then there exists a built-in tokenizer named "icu"
|
||||
implemented using the ICU library. The first argument passed to the
|
||||
xCreate() method (see fts3_tokenizer.h) of this tokenizer may be
|
||||
an ICU locale identifier. For example "tr_TR" for Turkish as used
|
||||
in Turkey, or "en_AU" for English as used in Australia. For example:
|
||||
|
||||
"CREATE VIRTUAL TABLE thai_text USING fts3(text, tokenizer icu th_TH)"
|
||||
|
||||
The ICU tokenizer implementation is very simple. It splits the input
|
||||
text according to the ICU rules for finding word boundaries and discards
|
||||
any tokens that consist entirely of white-space. This may be suitable
|
||||
for some applications in some locales, but not all. If more complex
|
||||
processing is required, for example to implement stemming or
|
||||
discard punctuation, this can be done by creating a tokenizer
|
||||
implementation that uses the ICU tokenizer as part of its implementation.
|
||||
|
||||
When using the ICU tokenizer this way, it is safe to overwrite the
|
||||
contents of the strings returned by the xNext() method (see
|
||||
fts3_tokenizer.h).
|
||||
|
||||
4. Sample code.
|
||||
|
||||
The following two code samples illustrate the way C code should invoke
|
||||
the fts3_tokenizer() scalar function:
|
||||
|
||||
int registerTokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module *p
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts3_tokenizer(?, ?)";
|
||||
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
|
||||
sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC);
|
||||
sqlite3_bind_blob(pStmt, 2, &p, sizeof(p), SQLITE_STATIC);
|
||||
sqlite3_step(pStmt);
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
int queryTokenizer(
|
||||
sqlite3 *db,
|
||||
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(pp, sqlite3_column_blob(pStmt, 0), sizeof(*pp));
|
||||
}
|
||||
}
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
@@ -1,4 +0,0 @@
|
||||
This folder contains source code to the second full-text search
|
||||
extension for SQLite. While the API is the same, this version uses a
|
||||
substantially different storage schema from fts1, so tables will need
|
||||
to be rebuilt.
|
||||
-5799
File diff suppressed because it is too large
Load Diff
@@ -1,26 +0,0 @@
|
||||
/*
|
||||
** 2006 Oct 10
|
||||
**
|
||||
** 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 header file is used by programs that want to link against the
|
||||
** FTS3 library. All it does is declare the sqlite3Fts3Init() interface.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif /* __cplusplus */
|
||||
|
||||
int sqlite3Fts3Init(sqlite3 *db);
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" */
|
||||
#endif /* __cplusplus */
|
||||
@@ -1,595 +0,0 @@
|
||||
/*
|
||||
** 2009 Nov 12
|
||||
**
|
||||
** 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 _FTSINT_H
|
||||
#define _FTSINT_H
|
||||
|
||||
#if !defined(NDEBUG) && !defined(SQLITE_DEBUG)
|
||||
# define NDEBUG 1
|
||||
#endif
|
||||
|
||||
/*
|
||||
** FTS4 is really an extension for FTS3. It is enabled using the
|
||||
** SQLITE_ENABLE_FTS3 macro. But to avoid confusion we also all
|
||||
** the SQLITE_ENABLE_FTS4 macro to serve as an alisse for SQLITE_ENABLE_FTS3.
|
||||
*/
|
||||
#if defined(SQLITE_ENABLE_FTS4) && !defined(SQLITE_ENABLE_FTS3)
|
||||
# define SQLITE_ENABLE_FTS3
|
||||
#endif
|
||||
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
/* If not building as part of the core, include sqlite3ext.h. */
|
||||
#ifndef SQLITE_CORE
|
||||
# include "sqlite3ext.h"
|
||||
SQLITE_EXTENSION_INIT3
|
||||
#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
|
||||
** segment of level N+1.
|
||||
*/
|
||||
#define FTS3_MERGE_COUNT 16
|
||||
|
||||
/*
|
||||
** This is the maximum amount of data (in bytes) to store in the
|
||||
** Fts3Table.pendingTerms hash table. Normally, the hash table is
|
||||
** populated as documents are inserted/updated/deleted in a transaction
|
||||
** and used to create a new segment when the transaction is committed.
|
||||
** However if this limit is reached midway through a transaction, a new
|
||||
** segment is created and the hash table cleared immediately.
|
||||
*/
|
||||
#define FTS3_MAX_PENDING_DATA (1*1024*1024)
|
||||
|
||||
/*
|
||||
** Macro to return the number of elements in an array. SQLite has a
|
||||
** similar macro called ArraySize(). Use a different name to avoid
|
||||
** a collision when building an amalgamation with built-in FTS3.
|
||||
*/
|
||||
#define SizeofArray(X) ((int)(sizeof(X)/sizeof(X[0])))
|
||||
|
||||
|
||||
#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
|
||||
** from that used by SQLite, so the maximum length is 10, not 9.
|
||||
*/
|
||||
#define FTS3_VARINT_MAX 10
|
||||
|
||||
/*
|
||||
** 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
|
||||
** as one or more b+-trees in the %_segments and %_segdir tables.
|
||||
**
|
||||
** It is possible to determine which index a b+-tree belongs to based on the
|
||||
** value stored in the "%_segdir.level" column. Given this value L, the index
|
||||
** that the b+-tree belongs to is (L<<10). In other words, all b+-trees with
|
||||
** level values between 0 and 1023 (inclusive) belong to index 0, all levels
|
||||
** between 1024 and 2047 to index 1, and so on.
|
||||
**
|
||||
** It is considered impossible for an index to use more than 1024 levels. In
|
||||
** theory though this may happen, but only after at least
|
||||
** (FTS3_MERGE_COUNT^1024) separate flushes of the pending-terms tables.
|
||||
*/
|
||||
#define FTS3_SEGDIR_MAXLEVEL 1024
|
||||
#define FTS3_SEGDIR_MAXLEVEL_STR "1024"
|
||||
|
||||
/*
|
||||
** The testcase() macro is only used by the amalgamation. If undefined,
|
||||
** make it a no-op.
|
||||
*/
|
||||
#ifndef testcase
|
||||
# define testcase(X)
|
||||
#endif
|
||||
|
||||
/*
|
||||
** Terminator values for position-lists and column-lists.
|
||||
*/
|
||||
#define POS_COLUMN (1) /* Column-list terminator */
|
||||
#define POS_END (0) /* Position-list terminator */
|
||||
|
||||
/*
|
||||
** This section provides definitions to allow the
|
||||
** FTS3 extension to be compiled outside of the
|
||||
** amalgamation.
|
||||
*/
|
||||
#ifndef SQLITE_AMALGAMATION
|
||||
/*
|
||||
** Macros indicating that conditional expressions are always true or
|
||||
** false.
|
||||
*/
|
||||
#ifdef SQLITE_COVERAGE_TEST
|
||||
# define ALWAYS(x) (1)
|
||||
# define NEVER(X) (0)
|
||||
#else
|
||||
# define ALWAYS(x) (x)
|
||||
# define NEVER(x) (x)
|
||||
#endif
|
||||
|
||||
/*
|
||||
** Internal types used by SQLite.
|
||||
*/
|
||||
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.
|
||||
*/
|
||||
#define UNUSED_PARAMETER(x) (void)(x)
|
||||
|
||||
/*
|
||||
** Activate assert() only if SQLITE_TEST is enabled.
|
||||
*/
|
||||
#if !defined(NDEBUG) && !defined(SQLITE_DEBUG)
|
||||
# define NDEBUG 1
|
||||
#endif
|
||||
|
||||
/*
|
||||
** The TESTONLY macro is used to enclose variable declarations or
|
||||
** other bits of code that are needed to support the arguments
|
||||
** within testcase() and assert() macros.
|
||||
*/
|
||||
#if defined(SQLITE_DEBUG) || defined(SQLITE_COVERAGE_TEST)
|
||||
# define TESTONLY(X) X
|
||||
#else
|
||||
# define TESTONLY(X)
|
||||
#endif
|
||||
|
||||
#endif /* SQLITE_AMALGAMATION */
|
||||
|
||||
#ifdef SQLITE_DEBUG
|
||||
int sqlite3Fts3Corrupt(void);
|
||||
# define FTS_CORRUPT_VTAB sqlite3Fts3Corrupt()
|
||||
#else
|
||||
# define FTS_CORRUPT_VTAB SQLITE_CORRUPT_VTAB
|
||||
#endif
|
||||
|
||||
typedef struct Fts3Table Fts3Table;
|
||||
typedef struct Fts3Cursor Fts3Cursor;
|
||||
typedef struct Fts3Expr Fts3Expr;
|
||||
typedef struct Fts3Phrase Fts3Phrase;
|
||||
typedef struct Fts3PhraseToken Fts3PhraseToken;
|
||||
|
||||
typedef struct Fts3Doclist Fts3Doclist;
|
||||
typedef struct Fts3SegFilter Fts3SegFilter;
|
||||
typedef struct Fts3DeferredToken Fts3DeferredToken;
|
||||
typedef struct Fts3SegReader Fts3SegReader;
|
||||
typedef struct Fts3MultiSegReader Fts3MultiSegReader;
|
||||
|
||||
/*
|
||||
** A connection to a fulltext index is an instance of the following
|
||||
** structure. The xCreate and xConnect methods create an instance
|
||||
** of this structure and xDestroy and xDisconnect free that instance.
|
||||
** All other methods receive a pointer to the structure as one of their
|
||||
** arguments.
|
||||
*/
|
||||
struct Fts3Table {
|
||||
sqlite3_vtab base; /* Base class used by SQLite core */
|
||||
sqlite3 *db; /* The database connection */
|
||||
const char *zDb; /* logical database name */
|
||||
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];
|
||||
|
||||
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 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.
|
||||
**
|
||||
** 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 {
|
||||
int nPrefix; /* Prefix length (0 for main terms index) */
|
||||
Fts3Hash hPending; /* Pending terms table for this index */
|
||||
} *aIndex;
|
||||
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 */
|
||||
|
||||
#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.
|
||||
*/
|
||||
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
|
||||
};
|
||||
|
||||
/*
|
||||
** When the core wants to read from the virtual table, it creates a
|
||||
** virtual table cursor (an instance of the following structure) using
|
||||
** the xOpen method. Cursors are destroyed using the xClose method.
|
||||
*/
|
||||
struct Fts3Cursor {
|
||||
sqlite3_vtab_cursor base; /* Base class used by SQLite core */
|
||||
i16 eSearch; /* Search strategy (see below) */
|
||||
u8 isEof; /* True if at End Of Results */
|
||||
u8 isRequireSeek; /* True if must seek pStmt to %_content row */
|
||||
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 */
|
||||
char *pNextId; /* Pointer into the body of aDoclist */
|
||||
char *aDoclist; /* List of docids for full-text queries */
|
||||
int nDoclist; /* Size of buffer at aDoclist */
|
||||
u8 bDesc; /* True to sort in descending order */
|
||||
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 */
|
||||
u32 *aMatchinfo; /* Information about most recent match */
|
||||
int nMatchinfo; /* Number of elements in aMatchinfo[] */
|
||||
char *zMatchinfo; /* Matchinfo specification */
|
||||
};
|
||||
|
||||
#define FTS3_EVAL_FILTER 0
|
||||
#define FTS3_EVAL_NEXT 1
|
||||
#define FTS3_EVAL_MATCHINFO 2
|
||||
|
||||
/*
|
||||
** The Fts3Cursor.eSearch member is always set to one of the following.
|
||||
** Actualy, Fts3Cursor.eSearch can be greater than or equal to
|
||||
** FTS3_FULLTEXT_SEARCH. If so, then Fts3Cursor.eSearch - 2 is the index
|
||||
** of the column to be searched. For example, in
|
||||
**
|
||||
** CREATE VIRTUAL TABLE ex1 USING fts3(a,b,c,d);
|
||||
** SELECT docid FROM ex1 WHERE b MATCH 'one two three';
|
||||
**
|
||||
** Because the LHS of the MATCH operator is 2nd column "b",
|
||||
** Fts3Cursor.eSearch will be set to FTS3_FULLTEXT_SEARCH+1. (+0 for a,
|
||||
** +1 for b, +2 for c, +3 for d.) If the LHS of MATCH were "ex1"
|
||||
** indicating that all columns should be searched,
|
||||
** then eSearch would be set to FTS3_FULLTEXT_SEARCH+4.
|
||||
*/
|
||||
#define FTS3_FULLSCAN_SEARCH 0 /* Linear scan of %_content table */
|
||||
#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) */
|
||||
int nAll; /* Size of a[] in bytes */
|
||||
char *pNextDocid; /* Pointer to next docid */
|
||||
|
||||
sqlite3_int64 iDocid; /* Current docid (if pList!=0) */
|
||||
int bFreeList; /* True if pList should be sqlite3_free()d */
|
||||
char *pList; /* Pointer to position list following iDocid */
|
||||
int nList; /* Length of position list */
|
||||
};
|
||||
|
||||
/*
|
||||
** A "phrase" is a sequence of one or more tokens that must match in
|
||||
** sequence. A single token is the base case and the most common case.
|
||||
** For a sequence of tokens contained in double-quotes (i.e. "one two three")
|
||||
** nToken will be the number of tokens in the string.
|
||||
*/
|
||||
struct Fts3PhraseToken {
|
||||
char *z; /* Text of the token */
|
||||
int n; /* Number of bytes in buffer z */
|
||||
int isPrefix; /* True if token ends with a "*" character */
|
||||
int bFirst; /* True if token must appear at position 0 */
|
||||
|
||||
/* Variables above this point are populated when the expression is
|
||||
** parsed (by code in fts3_expr.c). Below this point the variables are
|
||||
** used when evaluating the expression. */
|
||||
Fts3DeferredToken *pDeferred; /* Deferred token object for this token */
|
||||
Fts3MultiSegReader *pSegcsr; /* Segment-reader for this token */
|
||||
};
|
||||
|
||||
struct Fts3Phrase {
|
||||
/* Cache of doclist for this phrase. */
|
||||
Fts3Doclist doclist;
|
||||
int bIncr; /* True if doclist is loaded incrementally */
|
||||
int iDoclistToken;
|
||||
|
||||
/* Variables below this point are populated by fts3_expr.c when parsing
|
||||
** a MATCH expression. Everything above is part of the evaluation phase.
|
||||
*/
|
||||
int nToken; /* Number of tokens in the phrase */
|
||||
int iColumn; /* Index of column this phrase must match */
|
||||
Fts3PhraseToken aToken[1]; /* One entry for each token in the phrase */
|
||||
};
|
||||
|
||||
/*
|
||||
** A tree of these objects forms the RHS of a MATCH operator.
|
||||
**
|
||||
** If Fts3Expr.eType is FTSQUERY_PHRASE and isLoaded is true, then aDoclist
|
||||
** points to a malloced buffer, size nDoclist bytes, containing the results
|
||||
** of this phrase query in FTS3 doclist format. As usual, the initial
|
||||
** "Length" field found in doclists stored on disk is omitted from this
|
||||
** buffer.
|
||||
**
|
||||
** Variable aMI is used only for FTSQUERY_NEAR nodes to store the global
|
||||
** matchinfo data. If it is not NULL, it points to an array of size nCol*3,
|
||||
** where nCol is the number of columns in the queried FTS table. The array
|
||||
** is populated as follows:
|
||||
**
|
||||
** aMI[iCol*3 + 0] = Undefined
|
||||
** aMI[iCol*3 + 1] = Number of occurrences
|
||||
** aMI[iCol*3 + 2] = Number of rows containing at least one instance
|
||||
**
|
||||
** The aMI array is allocated using sqlite3_malloc(). It should be freed
|
||||
** when the expression node is.
|
||||
*/
|
||||
struct Fts3Expr {
|
||||
int eType; /* One of the FTSQUERY_XXX values defined below */
|
||||
int nNear; /* Valid if eType==FTSQUERY_NEAR */
|
||||
Fts3Expr *pParent; /* pParent->pLeft==this or pParent->pRight==this */
|
||||
Fts3Expr *pLeft; /* Left operand */
|
||||
Fts3Expr *pRight; /* Right operand */
|
||||
Fts3Phrase *pPhrase; /* Valid if eType==FTSQUERY_PHRASE */
|
||||
|
||||
/* The following are used by the fts3_eval.c module. */
|
||||
sqlite3_int64 iDocid; /* Current docid */
|
||||
u8 bEof; /* True this expression is at EOF already */
|
||||
u8 bStart; /* True if iDocid is valid */
|
||||
u8 bDeferred; /* True if this expression is entirely deferred */
|
||||
|
||||
u32 *aMI;
|
||||
};
|
||||
|
||||
/*
|
||||
** Candidate values for Fts3Query.eType. Note that the order of the first
|
||||
** four values is in order of precedence when parsing expressions. For
|
||||
** example, the following:
|
||||
**
|
||||
** "a OR b AND c NOT d NEAR e"
|
||||
**
|
||||
** is equivalent to:
|
||||
**
|
||||
** "a OR (b AND (c NOT (d NEAR e)))"
|
||||
*/
|
||||
#define FTSQUERY_NEAR 1
|
||||
#define FTSQUERY_NOT 2
|
||||
#define FTSQUERY_AND 3
|
||||
#define FTSQUERY_OR 4
|
||||
#define FTSQUERY_PHRASE 5
|
||||
|
||||
|
||||
/* fts3_write.c */
|
||||
int sqlite3Fts3UpdateMethod(sqlite3_vtab*,int,sqlite3_value**,sqlite3_int64*);
|
||||
int sqlite3Fts3PendingTermsFlush(Fts3Table *);
|
||||
void sqlite3Fts3PendingTermsClear(Fts3Table *);
|
||||
int sqlite3Fts3Optimize(Fts3Table *);
|
||||
int sqlite3Fts3SegReaderNew(int, int, sqlite3_int64,
|
||||
sqlite3_int64, sqlite3_int64, const char *, int, Fts3SegReader**);
|
||||
int sqlite3Fts3SegReaderPending(
|
||||
Fts3Table*,int,const char*,int,int,Fts3SegReader**);
|
||||
void sqlite3Fts3SegReaderFree(Fts3SegReader *);
|
||||
int sqlite3Fts3AllSegdirs(Fts3Table*, int, int, int, sqlite3_stmt **);
|
||||
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
|
||||
#define FTS3_SEGCURSOR_ALL -2
|
||||
|
||||
int sqlite3Fts3SegReaderStart(Fts3Table*, Fts3MultiSegReader*, Fts3SegFilter*);
|
||||
int sqlite3Fts3SegReaderStep(Fts3Table *, Fts3MultiSegReader *);
|
||||
void sqlite3Fts3SegReaderFinish(Fts3MultiSegReader *);
|
||||
|
||||
int sqlite3Fts3SegReaderCursor(Fts3Table *,
|
||||
int, int, int, const char *, int, int, int, Fts3MultiSegReader *);
|
||||
|
||||
/* Flags allowed as part of the 4th argument to SegmentReaderIterate() */
|
||||
#define FTS3_SEGMENT_REQUIRE_POS 0x00000001
|
||||
#define FTS3_SEGMENT_IGNORE_EMPTY 0x00000002
|
||||
#define FTS3_SEGMENT_COLUMN_FILTER 0x00000004
|
||||
#define FTS3_SEGMENT_PREFIX 0x00000008
|
||||
#define FTS3_SEGMENT_SCAN 0x00000010
|
||||
#define FTS3_SEGMENT_FIRST 0x00000020
|
||||
|
||||
/* Type passed as 4th argument to SegmentReaderIterate() */
|
||||
struct Fts3SegFilter {
|
||||
const char *zTerm;
|
||||
int nTerm;
|
||||
int iCol;
|
||||
int flags;
|
||||
};
|
||||
|
||||
struct Fts3MultiSegReader {
|
||||
/* Used internally by sqlite3Fts3SegReaderXXX() calls */
|
||||
Fts3SegReader **apSegment; /* Array of Fts3SegReader objects */
|
||||
int nSegment; /* Size of apSegment array */
|
||||
int nAdvance; /* How many seg-readers to advance */
|
||||
Fts3SegFilter *pFilter; /* Pointer to filter object */
|
||||
char *aBuffer; /* Buffer to merge doclists in */
|
||||
int nBuffer; /* Allocated size of aBuffer[] in bytes */
|
||||
|
||||
int iColFilter; /* If >=0, filter for this column */
|
||||
int bRestart;
|
||||
|
||||
/* Used by fts3.c only. */
|
||||
int nCost; /* Cost of running iterator */
|
||||
int bLookup; /* True if a lookup of a single entry. */
|
||||
|
||||
/* Output values. Valid only after Fts3SegReaderStep() returns SQLITE_ROW. */
|
||||
char *zTerm; /* Pointer to term buffer */
|
||||
int nTerm; /* Size of zTerm in bytes */
|
||||
char *aDoclist; /* Pointer to doclist buffer */
|
||||
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 */
|
||||
int sqlite3Fts3PutVarint(char *, sqlite3_int64);
|
||||
int sqlite3Fts3GetVarint(const char *, sqlite_int64 *);
|
||||
int sqlite3Fts3GetVarint32(const char *, int *);
|
||||
int sqlite3Fts3VarintLen(sqlite3_uint64);
|
||||
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*);
|
||||
|
||||
/* fts3_tokenizer.c */
|
||||
const char *sqlite3Fts3NextToken(const char *, int *);
|
||||
int sqlite3Fts3InitHashTable(sqlite3 *, Fts3Hash *, const char *);
|
||||
int sqlite3Fts3InitTokenizer(Fts3Hash *pHash, const char *,
|
||||
sqlite3_tokenizer **, char **
|
||||
);
|
||||
int sqlite3Fts3IsIdChar(char);
|
||||
|
||||
/* fts3_snippet.c */
|
||||
void sqlite3Fts3Offsets(sqlite3_context*, Fts3Cursor*);
|
||||
void sqlite3Fts3Snippet(sqlite3_context *, Fts3Cursor *, const char *,
|
||||
const char *, const char *, int, int
|
||||
);
|
||||
void sqlite3Fts3Matchinfo(sqlite3_context *, Fts3Cursor *, const char *);
|
||||
|
||||
/* fts3_expr.c */
|
||||
int sqlite3Fts3ExprParse(sqlite3_tokenizer *, int,
|
||||
char **, int, int, int, const char *, int, Fts3Expr **, char **
|
||||
);
|
||||
void sqlite3Fts3ExprFree(Fts3Expr *);
|
||||
#ifdef SQLITE_TEST
|
||||
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);
|
||||
|
||||
void sqlite3Fts3EvalPhraseCleanup(Fts3Phrase *);
|
||||
|
||||
int sqlite3Fts3MsrIncrStart(
|
||||
Fts3Table*, Fts3MultiSegReader*, int, const char*, int);
|
||||
int sqlite3Fts3MsrIncrNext(
|
||||
Fts3Table *, Fts3MultiSegReader *, sqlite3_int64 *, char **, int *);
|
||||
int sqlite3Fts3EvalPhrasePoslist(Fts3Cursor *, Fts3Expr *, int iCol, char **);
|
||||
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
|
||||
|
||||
#endif /* !SQLITE_CORE || SQLITE_ENABLE_FTS3 */
|
||||
#endif /* _FTSINT_H */
|
||||
@@ -1,550 +0,0 @@
|
||||
/*
|
||||
** 2011 Jan 27
|
||||
**
|
||||
** 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 "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
|
||||
typedef struct Fts3auxTable Fts3auxTable;
|
||||
typedef struct Fts3auxCursor Fts3auxCursor;
|
||||
|
||||
struct Fts3auxTable {
|
||||
sqlite3_vtab base; /* Base class used by SQLite core */
|
||||
Fts3Table *pFts3Tab;
|
||||
};
|
||||
|
||||
struct Fts3auxCursor {
|
||||
sqlite3_vtab_cursor base; /* Base class used by SQLite core */
|
||||
Fts3MultiSegReader csr; /* Must be right after "base" */
|
||||
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 */
|
||||
|
||||
int iCol; /* Current value of 'col' column */
|
||||
int nStat; /* Size of aStat[] array */
|
||||
struct Fts3auxColstats {
|
||||
sqlite3_int64 nDoc; /* 'documents' values for current csr row */
|
||||
sqlite3_int64 nOcc; /* 'occurrences' values for current csr row */
|
||||
} *aStat;
|
||||
};
|
||||
|
||||
/*
|
||||
** Schema of the terms table.
|
||||
*/
|
||||
#define FTS3_AUX_SCHEMA \
|
||||
"CREATE TABLE x(term, col, documents, occurrences, languageid HIDDEN)"
|
||||
|
||||
/*
|
||||
** 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.
|
||||
*/
|
||||
static int fts3auxConnectMethod(
|
||||
sqlite3 *db, /* Database connection */
|
||||
void *pUnused, /* Unused */
|
||||
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 */
|
||||
){
|
||||
char const *zDb; /* Name of database (e.g. "main") */
|
||||
char const *zFts3; /* Name of fts3 table */
|
||||
int nDb; /* Result of strlen(zDb) */
|
||||
int nFts3; /* Result of strlen(zFts3) */
|
||||
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;
|
||||
|
||||
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);
|
||||
|
||||
rc = sqlite3_declare_vtab(db, FTS3_AUX_SCHEMA);
|
||||
if( rc!=SQLITE_OK ) return rc;
|
||||
|
||||
nByte = sizeof(Fts3auxTable) + sizeof(Fts3Table) + nDb + nFts3 + 2;
|
||||
p = (Fts3auxTable *)sqlite3_malloc(nByte);
|
||||
if( !p ) return SQLITE_NOMEM;
|
||||
memset(p, 0, nByte);
|
||||
|
||||
p->pFts3Tab = (Fts3Table *)&p[1];
|
||||
p->pFts3Tab->zDb = (char *)&p->pFts3Tab[1];
|
||||
p->pFts3Tab->zName = &p->pFts3Tab->zDb[nDb+1];
|
||||
p->pFts3Tab->db = db;
|
||||
p->pFts3Tab->nIndex = 1;
|
||||
|
||||
memcpy((char *)p->pFts3Tab->zDb, zDb, nDb);
|
||||
memcpy((char *)p->pFts3Tab->zName, zFts3, nFts3);
|
||||
sqlite3Fts3Dequote((char *)p->pFts3Tab->zName);
|
||||
|
||||
*ppVtab = (sqlite3_vtab *)p;
|
||||
return SQLITE_OK;
|
||||
|
||||
bad_args:
|
||||
*pzErr = sqlite3_mprintf("invalid arguments to fts4aux constructor");
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 fts3auxDisconnectMethod(sqlite3_vtab *pVtab){
|
||||
Fts3auxTable *p = (Fts3auxTable *)pVtab;
|
||||
Fts3Table *pFts3 = p->pFts3Tab;
|
||||
int i;
|
||||
|
||||
/* Free any prepared statements held */
|
||||
for(i=0; i<SizeofArray(pFts3->aStmt); i++){
|
||||
sqlite3_finalize(pFts3->aStmt[i]);
|
||||
}
|
||||
sqlite3_free(pFts3->zSegmentsTbl);
|
||||
sqlite3_free(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
#define FTS4AUX_EQ_CONSTRAINT 1
|
||||
#define FTS4AUX_GE_CONSTRAINT 2
|
||||
#define FTS4AUX_LE_CONSTRAINT 4
|
||||
|
||||
/*
|
||||
** xBestIndex - Analyze a WHERE and ORDER BY clause.
|
||||
*/
|
||||
static int fts3auxBestIndexMethod(
|
||||
sqlite3_vtab *pVTab,
|
||||
sqlite3_index_info *pInfo
|
||||
){
|
||||
int i;
|
||||
int iEq = -1;
|
||||
int iGe = -1;
|
||||
int iLe = -1;
|
||||
int iLangid = -1;
|
||||
int iNext = 1; /* Next free argvIndex value */
|
||||
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
/* This vtab delivers always results in "ORDER BY term ASC" order. */
|
||||
if( pInfo->nOrderBy==1
|
||||
&& pInfo->aOrderBy[0].iColumn==0
|
||||
&& pInfo->aOrderBy[0].desc==0
|
||||
){
|
||||
pInfo->orderByConsumed = 1;
|
||||
}
|
||||
|
||||
/* Search for equality and range constraints on the "term" column.
|
||||
** And equality constraints on the hidden "languageid" column. */
|
||||
for(i=0; i<pInfo->nConstraint; i++){
|
||||
if( pInfo->aConstraint[i].usable ){
|
||||
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( iEq>=0 ){
|
||||
pInfo->idxNum = FTS4AUX_EQ_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iEq].argvIndex = iNext++;
|
||||
pInfo->estimatedCost = 5;
|
||||
}else{
|
||||
pInfo->idxNum = 0;
|
||||
pInfo->estimatedCost = 20000;
|
||||
if( iGe>=0 ){
|
||||
pInfo->idxNum += FTS4AUX_GE_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iGe].argvIndex = iNext++;
|
||||
pInfo->estimatedCost /= 2;
|
||||
}
|
||||
if( iLe>=0 ){
|
||||
pInfo->idxNum += FTS4AUX_LE_CONSTRAINT;
|
||||
pInfo->aConstraintUsage[iLe].argvIndex = iNext++;
|
||||
pInfo->estimatedCost /= 2;
|
||||
}
|
||||
}
|
||||
if( iLangid>=0 ){
|
||||
pInfo->aConstraintUsage[iLangid].argvIndex = iNext++;
|
||||
pInfo->estimatedCost--;
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xOpen - Open a cursor.
|
||||
*/
|
||||
static int fts3auxOpenMethod(sqlite3_vtab *pVTab, sqlite3_vtab_cursor **ppCsr){
|
||||
Fts3auxCursor *pCsr; /* Pointer to cursor object to return */
|
||||
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
pCsr = (Fts3auxCursor *)sqlite3_malloc(sizeof(Fts3auxCursor));
|
||||
if( !pCsr ) return SQLITE_NOMEM;
|
||||
memset(pCsr, 0, sizeof(Fts3auxCursor));
|
||||
|
||||
*ppCsr = (sqlite3_vtab_cursor *)pCsr;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xClose - Close a cursor.
|
||||
*/
|
||||
static int fts3auxCloseMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3Table *pFts3 = ((Fts3auxTable *)pCursor->pVtab)->pFts3Tab;
|
||||
Fts3auxCursor *pCsr = (Fts3auxCursor *)pCursor;
|
||||
|
||||
sqlite3Fts3SegmentsClose(pFts3);
|
||||
sqlite3Fts3SegReaderFinish(&pCsr->csr);
|
||||
sqlite3_free((void *)pCsr->filter.zTerm);
|
||||
sqlite3_free(pCsr->zStop);
|
||||
sqlite3_free(pCsr->aStat);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
static int fts3auxGrowStatArray(Fts3auxCursor *pCsr, int nSize){
|
||||
if( nSize>pCsr->nStat ){
|
||||
struct Fts3auxColstats *aNew;
|
||||
aNew = (struct Fts3auxColstats *)sqlite3_realloc(pCsr->aStat,
|
||||
sizeof(struct Fts3auxColstats) * nSize
|
||||
);
|
||||
if( aNew==0 ) return SQLITE_NOMEM;
|
||||
memset(&aNew[pCsr->nStat], 0,
|
||||
sizeof(struct Fts3auxColstats) * (nSize - pCsr->nStat)
|
||||
);
|
||||
pCsr->aStat = aNew;
|
||||
pCsr->nStat = nSize;
|
||||
}
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xNext - Advance the cursor to the next row, if any.
|
||||
*/
|
||||
static int fts3auxNextMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3auxCursor *pCsr = (Fts3auxCursor *)pCursor;
|
||||
Fts3Table *pFts3 = ((Fts3auxTable *)pCursor->pVtab)->pFts3Tab;
|
||||
int rc;
|
||||
|
||||
/* Increment our pretend rowid value. */
|
||||
pCsr->iRowid++;
|
||||
|
||||
for(pCsr->iCol++; pCsr->iCol<pCsr->nStat; pCsr->iCol++){
|
||||
if( pCsr->aStat[pCsr->iCol].nDoc>0 ) return SQLITE_OK;
|
||||
}
|
||||
|
||||
rc = sqlite3Fts3SegReaderStep(pFts3, &pCsr->csr);
|
||||
if( rc==SQLITE_ROW ){
|
||||
int i = 0;
|
||||
int nDoclist = pCsr->csr.nDoclist;
|
||||
char *aDoclist = pCsr->csr.aDoclist;
|
||||
int iCol;
|
||||
|
||||
int eState = 0;
|
||||
|
||||
if( pCsr->zStop ){
|
||||
int n = (pCsr->nStop<pCsr->csr.nTerm) ? pCsr->nStop : pCsr->csr.nTerm;
|
||||
int mc = memcmp(pCsr->zStop, pCsr->csr.zTerm, n);
|
||||
if( mc<0 || (mc==0 && pCsr->csr.nTerm>pCsr->nStop) ){
|
||||
pCsr->isEof = 1;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
|
||||
if( fts3auxGrowStatArray(pCsr, 2) ) return SQLITE_NOMEM;
|
||||
memset(pCsr->aStat, 0, sizeof(struct Fts3auxColstats) * pCsr->nStat);
|
||||
iCol = 0;
|
||||
|
||||
while( i<nDoclist ){
|
||||
sqlite3_int64 v = 0;
|
||||
|
||||
i += sqlite3Fts3GetVarint(&aDoclist[i], &v);
|
||||
switch( eState ){
|
||||
/* State 0. In this state the integer just read was a docid. */
|
||||
case 0:
|
||||
pCsr->aStat[0].nDoc++;
|
||||
eState = 1;
|
||||
iCol = 0;
|
||||
break;
|
||||
|
||||
/* State 1. In this state we are expecting either a 1, indicating
|
||||
** that the following integer will be a column number, or the
|
||||
** start of a position list for column 0.
|
||||
**
|
||||
** The only difference between state 1 and state 2 is that if the
|
||||
** integer encountered in state 1 is not 0 or 1, then we need to
|
||||
** increment the column 0 "nDoc" count for this term.
|
||||
*/
|
||||
case 1:
|
||||
assert( iCol==0 );
|
||||
if( v>1 ){
|
||||
pCsr->aStat[1].nDoc++;
|
||||
}
|
||||
eState = 2;
|
||||
/* fall through */
|
||||
|
||||
case 2:
|
||||
if( v==0 ){ /* 0x00. Next integer will be a docid. */
|
||||
eState = 0;
|
||||
}else if( v==1 ){ /* 0x01. Next integer will be a column number. */
|
||||
eState = 3;
|
||||
}else{ /* 2 or greater. A position. */
|
||||
pCsr->aStat[iCol+1].nOcc++;
|
||||
pCsr->aStat[0].nOcc++;
|
||||
}
|
||||
break;
|
||||
|
||||
/* State 3. The integer just read is a column number. */
|
||||
default: assert( eState==3 );
|
||||
iCol = (int)v;
|
||||
if( fts3auxGrowStatArray(pCsr, iCol+2) ) return SQLITE_NOMEM;
|
||||
pCsr->aStat[iCol+1].nDoc++;
|
||||
eState = 2;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
pCsr->iCol = 0;
|
||||
rc = SQLITE_OK;
|
||||
}else{
|
||||
pCsr->isEof = 1;
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** xFilter - Initialize a cursor to point at the start of its data.
|
||||
*/
|
||||
static int fts3auxFilterMethod(
|
||||
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 */
|
||||
){
|
||||
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;
|
||||
|
||||
UNUSED_PARAMETER(nVal);
|
||||
UNUSED_PARAMETER(idxStr);
|
||||
|
||||
assert( idxStr==0 );
|
||||
assert( idxNum==FTS4AUX_EQ_CONSTRAINT || idxNum==0
|
||||
|| 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++;
|
||||
}
|
||||
|
||||
/* In case this cursor is being reused, close and zero it. */
|
||||
testcase(pCsr->filter.zTerm);
|
||||
sqlite3Fts3SegReaderFinish(&pCsr->csr);
|
||||
sqlite3_free((void *)pCsr->filter.zTerm);
|
||||
sqlite3_free(pCsr->aStat);
|
||||
memset(&pCsr->csr, 0, ((u8*)&pCsr[1]) - (u8*)&pCsr->csr);
|
||||
|
||||
pCsr->filter.flags = FTS3_SEGMENT_REQUIRE_POS|FTS3_SEGMENT_IGNORE_EMPTY;
|
||||
if( isScan ) pCsr->filter.flags |= FTS3_SEGMENT_SCAN;
|
||||
|
||||
if( iEq>=0 || iGe>=0 ){
|
||||
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;
|
||||
}
|
||||
}
|
||||
|
||||
if( iLe>=0 ){
|
||||
pCsr->zStop = sqlite3_mprintf("%s", sqlite3_value_text(apVal[iLe]));
|
||||
pCsr->nStop = sqlite3_value_bytes(apVal[iLe]);
|
||||
if( pCsr->zStop==0 ) return SQLITE_NOMEM;
|
||||
}
|
||||
|
||||
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,
|
||||
pCsr->filter.zTerm, pCsr->filter.nTerm, 0, isScan, &pCsr->csr
|
||||
);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = sqlite3Fts3SegReaderStart(pFts3, &pCsr->csr, &pCsr->filter);
|
||||
}
|
||||
|
||||
if( rc==SQLITE_OK ) rc = fts3auxNextMethod(pCursor);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** xEof - Return true if the cursor is at EOF, or false otherwise.
|
||||
*/
|
||||
static int fts3auxEofMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3auxCursor *pCsr = (Fts3auxCursor *)pCursor;
|
||||
return pCsr->isEof;
|
||||
}
|
||||
|
||||
/*
|
||||
** xColumn - Return a column value.
|
||||
*/
|
||||
static int fts3auxColumnMethod(
|
||||
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 */
|
||||
){
|
||||
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;
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xRowid - Return the current rowid for the cursor.
|
||||
*/
|
||||
static int fts3auxRowidMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* Cursor to retrieve value from */
|
||||
sqlite_int64 *pRowid /* OUT: Rowid value */
|
||||
){
|
||||
Fts3auxCursor *pCsr = (Fts3auxCursor *)pCursor;
|
||||
*pRowid = pCsr->iRowid;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Register the fts3aux module with database connection db. Return SQLITE_OK
|
||||
** if successful or an error code if sqlite3_create_module() fails.
|
||||
*/
|
||||
int sqlite3Fts3InitAux(sqlite3 *db){
|
||||
static const sqlite3_module fts3aux_module = {
|
||||
0, /* iVersion */
|
||||
fts3auxConnectMethod, /* xCreate */
|
||||
fts3auxConnectMethod, /* xConnect */
|
||||
fts3auxBestIndexMethod, /* xBestIndex */
|
||||
fts3auxDisconnectMethod, /* xDisconnect */
|
||||
fts3auxDisconnectMethod, /* xDestroy */
|
||||
fts3auxOpenMethod, /* xOpen */
|
||||
fts3auxCloseMethod, /* xClose */
|
||||
fts3auxFilterMethod, /* xFilter */
|
||||
fts3auxNextMethod, /* xNext */
|
||||
fts3auxEofMethod, /* xEof */
|
||||
fts3auxColumnMethod, /* xColumn */
|
||||
fts3auxRowidMethod, /* xRowid */
|
||||
0, /* xUpdate */
|
||||
0, /* xBegin */
|
||||
0, /* xSync */
|
||||
0, /* xCommit */
|
||||
0, /* xRollback */
|
||||
0, /* xFindFunction */
|
||||
0, /* xRename */
|
||||
0, /* xSavepoint */
|
||||
0, /* xRelease */
|
||||
0 /* xRollbackTo */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
rc = sqlite3_create_module(db, "fts4aux", &fts3aux_module, 0);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,383 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the implementation of generic hash-tables used in SQLite.
|
||||
** We've modified it slightly to serve as a standalone hash table
|
||||
** implementation for the full-text indexing module.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS3 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS3 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS3 is defined).
|
||||
*/
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "fts3_hash.h"
|
||||
|
||||
/*
|
||||
** Malloc and Free functions
|
||||
*/
|
||||
static void *fts3HashMalloc(int n){
|
||||
void *p = sqlite3_malloc(n);
|
||||
if( p ){
|
||||
memset(p, 0, n);
|
||||
}
|
||||
return p;
|
||||
}
|
||||
static void fts3HashFree(void *p){
|
||||
sqlite3_free(p);
|
||||
}
|
||||
|
||||
/* Turn bulk memory into a hash table object by initializing the
|
||||
** fields of the Hash structure.
|
||||
**
|
||||
** "pNew" is a pointer to the hash table that is to be initialized.
|
||||
** keyClass is one of the constants
|
||||
** FTS3_HASH_BINARY or FTS3_HASH_STRING. The value of keyClass
|
||||
** determines what kind of key the hash table will use. "copyKey" is
|
||||
** true if the hash table should make its own private copy of keys and
|
||||
** false if it should just use the supplied pointer.
|
||||
*/
|
||||
void sqlite3Fts3HashInit(Fts3Hash *pNew, char keyClass, char copyKey){
|
||||
assert( pNew!=0 );
|
||||
assert( keyClass>=FTS3_HASH_STRING && keyClass<=FTS3_HASH_BINARY );
|
||||
pNew->keyClass = keyClass;
|
||||
pNew->copyKey = copyKey;
|
||||
pNew->first = 0;
|
||||
pNew->count = 0;
|
||||
pNew->htsize = 0;
|
||||
pNew->ht = 0;
|
||||
}
|
||||
|
||||
/* Remove all entries from a hash table. Reclaim all memory.
|
||||
** Call this routine to delete a hash table or to reset a hash table
|
||||
** to the empty state.
|
||||
*/
|
||||
void sqlite3Fts3HashClear(Fts3Hash *pH){
|
||||
Fts3HashElem *elem; /* For looping over all elements of the table */
|
||||
|
||||
assert( pH!=0 );
|
||||
elem = pH->first;
|
||||
pH->first = 0;
|
||||
fts3HashFree(pH->ht);
|
||||
pH->ht = 0;
|
||||
pH->htsize = 0;
|
||||
while( elem ){
|
||||
Fts3HashElem *next_elem = elem->next;
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
fts3HashFree(elem->pKey);
|
||||
}
|
||||
fts3HashFree(elem);
|
||||
elem = next_elem;
|
||||
}
|
||||
pH->count = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS3_HASH_STRING
|
||||
*/
|
||||
static int fts3StrHash(const void *pKey, int nKey){
|
||||
const char *z = (const char *)pKey;
|
||||
unsigned h = 0;
|
||||
if( nKey<=0 ) nKey = (int) strlen(z);
|
||||
while( nKey > 0 ){
|
||||
h = (h<<3) ^ h ^ *z++;
|
||||
nKey--;
|
||||
}
|
||||
return (int)(h & 0x7fffffff);
|
||||
}
|
||||
static int fts3StrCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return strncmp((const char*)pKey1,(const char*)pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Hash and comparison functions when the mode is FTS3_HASH_BINARY
|
||||
*/
|
||||
static int fts3BinHash(const void *pKey, int nKey){
|
||||
int h = 0;
|
||||
const char *z = (const char *)pKey;
|
||||
while( nKey-- > 0 ){
|
||||
h = (h<<3) ^ h ^ *(z++);
|
||||
}
|
||||
return h & 0x7fffffff;
|
||||
}
|
||||
static int fts3BinCompare(const void *pKey1, int n1, const void *pKey2, int n2){
|
||||
if( n1!=n2 ) return 1;
|
||||
return memcmp(pKey1,pKey2,n1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** The C syntax in this function definition may be unfamilar to some
|
||||
** programmers, so we provide the following additional explanation:
|
||||
**
|
||||
** The name of the function is "ftsHashFunction". The function takes a
|
||||
** single parameter "keyClass". The return value of ftsHashFunction()
|
||||
** is a pointer to another function. Specifically, the return value
|
||||
** of ftsHashFunction() is a pointer to a function that takes two parameters
|
||||
** with types "const void*" and "int" and returns an "int".
|
||||
*/
|
||||
static int (*ftsHashFunction(int keyClass))(const void*,int){
|
||||
if( keyClass==FTS3_HASH_STRING ){
|
||||
return &fts3StrHash;
|
||||
}else{
|
||||
assert( keyClass==FTS3_HASH_BINARY );
|
||||
return &fts3BinHash;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Return a pointer to the appropriate hash function given the key class.
|
||||
**
|
||||
** For help in interpreted the obscure C code in the function definition,
|
||||
** see the header comment on the previous function.
|
||||
*/
|
||||
static int (*ftsCompareFunction(int keyClass))(const void*,int,const void*,int){
|
||||
if( keyClass==FTS3_HASH_STRING ){
|
||||
return &fts3StrCompare;
|
||||
}else{
|
||||
assert( keyClass==FTS3_HASH_BINARY );
|
||||
return &fts3BinCompare;
|
||||
}
|
||||
}
|
||||
|
||||
/* Link an element into the hash table
|
||||
*/
|
||||
static void fts3HashInsertElement(
|
||||
Fts3Hash *pH, /* The complete hash table */
|
||||
struct _fts3ht *pEntry, /* The entry into which pNew is inserted */
|
||||
Fts3HashElem *pNew /* The element to be inserted */
|
||||
){
|
||||
Fts3HashElem *pHead; /* First element already in pEntry */
|
||||
pHead = pEntry->chain;
|
||||
if( pHead ){
|
||||
pNew->next = pHead;
|
||||
pNew->prev = pHead->prev;
|
||||
if( pHead->prev ){ pHead->prev->next = pNew; }
|
||||
else { pH->first = pNew; }
|
||||
pHead->prev = pNew;
|
||||
}else{
|
||||
pNew->next = pH->first;
|
||||
if( pH->first ){ pH->first->prev = pNew; }
|
||||
pNew->prev = 0;
|
||||
pH->first = pNew;
|
||||
}
|
||||
pEntry->count++;
|
||||
pEntry->chain = pNew;
|
||||
}
|
||||
|
||||
|
||||
/* Resize the hash table so that it cantains "new_size" buckets.
|
||||
** "new_size" must be a power of 2. The hash table might fail
|
||||
** to resize if sqliteMalloc() fails.
|
||||
**
|
||||
** Return non-zero if a memory allocation error occurs.
|
||||
*/
|
||||
static int fts3Rehash(Fts3Hash *pH, int new_size){
|
||||
struct _fts3ht *new_ht; /* The new hash table */
|
||||
Fts3HashElem *elem, *next_elem; /* For looping over existing elements */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( (new_size & (new_size-1))==0 );
|
||||
new_ht = (struct _fts3ht *)fts3HashMalloc( new_size*sizeof(struct _fts3ht) );
|
||||
if( new_ht==0 ) return 1;
|
||||
fts3HashFree(pH->ht);
|
||||
pH->ht = new_ht;
|
||||
pH->htsize = new_size;
|
||||
xHash = ftsHashFunction(pH->keyClass);
|
||||
for(elem=pH->first, pH->first=0; elem; elem = next_elem){
|
||||
int h = (*xHash)(elem->pKey, elem->nKey) & (new_size-1);
|
||||
next_elem = elem->next;
|
||||
fts3HashInsertElement(pH, &new_ht[h], elem);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* This function (for internal use only) locates an element in an
|
||||
** hash table that matches the given key. The hash for this key has
|
||||
** already been computed and is passed as the 4th parameter.
|
||||
*/
|
||||
static Fts3HashElem *fts3FindElementByHash(
|
||||
const Fts3Hash *pH, /* The pH to be searched */
|
||||
const void *pKey, /* The key we are searching for */
|
||||
int nKey,
|
||||
int h /* The hash for this key. */
|
||||
){
|
||||
Fts3HashElem *elem; /* Used to loop thru the element list */
|
||||
int count; /* Number of elements left to test */
|
||||
int (*xCompare)(const void*,int,const void*,int); /* comparison function */
|
||||
|
||||
if( pH->ht ){
|
||||
struct _fts3ht *pEntry = &pH->ht[h];
|
||||
elem = pEntry->chain;
|
||||
count = pEntry->count;
|
||||
xCompare = ftsCompareFunction(pH->keyClass);
|
||||
while( count-- && elem ){
|
||||
if( (*xCompare)(elem->pKey,elem->nKey,pKey,nKey)==0 ){
|
||||
return elem;
|
||||
}
|
||||
elem = elem->next;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Remove a single entry from the hash table given a pointer to that
|
||||
** element and a hash on the element's key.
|
||||
*/
|
||||
static void fts3RemoveElementByHash(
|
||||
Fts3Hash *pH, /* The pH containing "elem" */
|
||||
Fts3HashElem* elem, /* The element to be removed from the pH */
|
||||
int h /* Hash value for the element */
|
||||
){
|
||||
struct _fts3ht *pEntry;
|
||||
if( elem->prev ){
|
||||
elem->prev->next = elem->next;
|
||||
}else{
|
||||
pH->first = elem->next;
|
||||
}
|
||||
if( elem->next ){
|
||||
elem->next->prev = elem->prev;
|
||||
}
|
||||
pEntry = &pH->ht[h];
|
||||
if( pEntry->chain==elem ){
|
||||
pEntry->chain = elem->next;
|
||||
}
|
||||
pEntry->count--;
|
||||
if( pEntry->count<=0 ){
|
||||
pEntry->chain = 0;
|
||||
}
|
||||
if( pH->copyKey && elem->pKey ){
|
||||
fts3HashFree(elem->pKey);
|
||||
}
|
||||
fts3HashFree( elem );
|
||||
pH->count--;
|
||||
if( pH->count<=0 ){
|
||||
assert( pH->first==0 );
|
||||
assert( pH->count==0 );
|
||||
fts3HashClear(pH);
|
||||
}
|
||||
}
|
||||
|
||||
Fts3HashElem *sqlite3Fts3HashFindElem(
|
||||
const Fts3Hash *pH,
|
||||
const void *pKey,
|
||||
int nKey
|
||||
){
|
||||
int h; /* A hash on key */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
if( pH==0 || pH->ht==0 ) return 0;
|
||||
xHash = ftsHashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
h = (*xHash)(pKey,nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
return fts3FindElementByHash(pH,pKey,nKey, h & (pH->htsize-1));
|
||||
}
|
||||
|
||||
/*
|
||||
** Attempt to locate an element of the hash table pH with a key
|
||||
** that matches pKey,nKey. Return the data for this element if it is
|
||||
** found, or NULL if there is no match.
|
||||
*/
|
||||
void *sqlite3Fts3HashFind(const Fts3Hash *pH, const void *pKey, int nKey){
|
||||
Fts3HashElem *pElem; /* The element that matches key (if any) */
|
||||
|
||||
pElem = sqlite3Fts3HashFindElem(pH, pKey, nKey);
|
||||
return pElem ? pElem->data : 0;
|
||||
}
|
||||
|
||||
/* Insert an element into the hash table pH. The key is pKey,nKey
|
||||
** and the data is "data".
|
||||
**
|
||||
** If no element exists with a matching key, then a new
|
||||
** element is created. A copy of the key is made if the copyKey
|
||||
** flag is set. NULL is returned.
|
||||
**
|
||||
** If another element already exists with the same key, then the
|
||||
** new data replaces the old data and the old data is returned.
|
||||
** The key is not copied in this instance. If a malloc fails, then
|
||||
** the new data is returned and the hash table is unchanged.
|
||||
**
|
||||
** If the "data" parameter to this function is NULL, then the
|
||||
** element corresponding to "key" is removed from the hash table.
|
||||
*/
|
||||
void *sqlite3Fts3HashInsert(
|
||||
Fts3Hash *pH, /* The hash table to insert into */
|
||||
const void *pKey, /* The key */
|
||||
int nKey, /* Number of bytes in the key */
|
||||
void *data /* The data */
|
||||
){
|
||||
int hraw; /* Raw hash value of the key */
|
||||
int h; /* the hash of the key modulo hash table size */
|
||||
Fts3HashElem *elem; /* Used to loop thru the element list */
|
||||
Fts3HashElem *new_elem; /* New element added to the pH */
|
||||
int (*xHash)(const void*,int); /* The hash function */
|
||||
|
||||
assert( pH!=0 );
|
||||
xHash = ftsHashFunction(pH->keyClass);
|
||||
assert( xHash!=0 );
|
||||
hraw = (*xHash)(pKey, nKey);
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
elem = fts3FindElementByHash(pH,pKey,nKey,h);
|
||||
if( elem ){
|
||||
void *old_data = elem->data;
|
||||
if( data==0 ){
|
||||
fts3RemoveElementByHash(pH,elem,h);
|
||||
}else{
|
||||
elem->data = data;
|
||||
}
|
||||
return old_data;
|
||||
}
|
||||
if( data==0 ) return 0;
|
||||
if( (pH->htsize==0 && fts3Rehash(pH,8))
|
||||
|| (pH->count>=pH->htsize && fts3Rehash(pH, pH->htsize*2))
|
||||
){
|
||||
pH->count = 0;
|
||||
return data;
|
||||
}
|
||||
assert( pH->htsize>0 );
|
||||
new_elem = (Fts3HashElem*)fts3HashMalloc( sizeof(Fts3HashElem) );
|
||||
if( new_elem==0 ) return data;
|
||||
if( pH->copyKey && pKey!=0 ){
|
||||
new_elem->pKey = fts3HashMalloc( nKey );
|
||||
if( new_elem->pKey==0 ){
|
||||
fts3HashFree(new_elem);
|
||||
return data;
|
||||
}
|
||||
memcpy((void*)new_elem->pKey, pKey, nKey);
|
||||
}else{
|
||||
new_elem->pKey = (void*)pKey;
|
||||
}
|
||||
new_elem->nKey = nKey;
|
||||
pH->count++;
|
||||
assert( pH->htsize>0 );
|
||||
assert( (pH->htsize & (pH->htsize-1))==0 );
|
||||
h = hraw & (pH->htsize-1);
|
||||
fts3HashInsertElement(pH, &pH->ht[h], new_elem);
|
||||
new_elem->data = data;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,112 +0,0 @@
|
||||
/*
|
||||
** 2001 September 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 is the header file for the generic hash-table implementation
|
||||
** used in SQLite. We've modified it slightly to serve as a standalone
|
||||
** hash table implementation for the full-text indexing module.
|
||||
**
|
||||
*/
|
||||
#ifndef _FTS3_HASH_H_
|
||||
#define _FTS3_HASH_H_
|
||||
|
||||
/* Forward declarations of structures. */
|
||||
typedef struct Fts3Hash Fts3Hash;
|
||||
typedef struct Fts3HashElem Fts3HashElem;
|
||||
|
||||
/* A complete hash table is an instance of the following structure.
|
||||
** The internals of this structure are intended to be opaque -- client
|
||||
** code should not attempt to access or modify the fields of this structure
|
||||
** directly. Change this structure only by using the routines below.
|
||||
** However, many of the "procedures" and "functions" for modifying and
|
||||
** accessing this structure are really macros, so we can't really make
|
||||
** this structure opaque.
|
||||
*/
|
||||
struct Fts3Hash {
|
||||
char keyClass; /* HASH_INT, _POINTER, _STRING, _BINARY */
|
||||
char copyKey; /* True if copy of key made on insert */
|
||||
int count; /* Number of entries in this table */
|
||||
Fts3HashElem *first; /* The first element of the array */
|
||||
int htsize; /* Number of buckets in the hash table */
|
||||
struct _fts3ht { /* the hash table */
|
||||
int count; /* Number of entries with this hash */
|
||||
Fts3HashElem *chain; /* Pointer to first entry with this hash */
|
||||
} *ht;
|
||||
};
|
||||
|
||||
/* Each element in the hash table is an instance of the following
|
||||
** structure. All elements are stored on a single doubly-linked list.
|
||||
**
|
||||
** Again, this structure is intended to be opaque, but it can't really
|
||||
** be opaque because it is used by macros.
|
||||
*/
|
||||
struct Fts3HashElem {
|
||||
Fts3HashElem *next, *prev; /* Next and previous elements in the table */
|
||||
void *data; /* Data associated with this element */
|
||||
void *pKey; int nKey; /* Key associated with this element */
|
||||
};
|
||||
|
||||
/*
|
||||
** There are 2 different modes of operation for a hash table:
|
||||
**
|
||||
** FTS3_HASH_STRING pKey points to a string that is nKey bytes long
|
||||
** (including the null-terminator, if any). Case
|
||||
** is respected in comparisons.
|
||||
**
|
||||
** FTS3_HASH_BINARY pKey points to binary data nKey bytes long.
|
||||
** memcmp() is used to compare keys.
|
||||
**
|
||||
** A copy of the key is made if the copyKey parameter to fts3HashInit is 1.
|
||||
*/
|
||||
#define FTS3_HASH_STRING 1
|
||||
#define FTS3_HASH_BINARY 2
|
||||
|
||||
/*
|
||||
** Access routines. To delete, insert a NULL pointer.
|
||||
*/
|
||||
void sqlite3Fts3HashInit(Fts3Hash *pNew, char keyClass, char copyKey);
|
||||
void *sqlite3Fts3HashInsert(Fts3Hash*, const void *pKey, int nKey, void *pData);
|
||||
void *sqlite3Fts3HashFind(const Fts3Hash*, const void *pKey, int nKey);
|
||||
void sqlite3Fts3HashClear(Fts3Hash*);
|
||||
Fts3HashElem *sqlite3Fts3HashFindElem(const Fts3Hash *, const void *, int);
|
||||
|
||||
/*
|
||||
** Shorthand for the functions above
|
||||
*/
|
||||
#define fts3HashInit sqlite3Fts3HashInit
|
||||
#define fts3HashInsert sqlite3Fts3HashInsert
|
||||
#define fts3HashFind sqlite3Fts3HashFind
|
||||
#define fts3HashClear sqlite3Fts3HashClear
|
||||
#define fts3HashFindElem sqlite3Fts3HashFindElem
|
||||
|
||||
/*
|
||||
** Macros for looping over all elements of a hash table. The idiom is
|
||||
** like this:
|
||||
**
|
||||
** Fts3Hash h;
|
||||
** Fts3HashElem *p;
|
||||
** ...
|
||||
** for(p=fts3HashFirst(&h); p; p=fts3HashNext(p)){
|
||||
** SomeStructure *pData = fts3HashData(p);
|
||||
** // do something with pData
|
||||
** }
|
||||
*/
|
||||
#define fts3HashFirst(H) ((H)->first)
|
||||
#define fts3HashNext(E) ((E)->next)
|
||||
#define fts3HashData(E) ((E)->data)
|
||||
#define fts3HashKey(E) ((E)->pKey)
|
||||
#define fts3HashKeysize(E) ((E)->nKey)
|
||||
|
||||
/*
|
||||
** Number of entries in a hash table
|
||||
*/
|
||||
#define fts3HashCount(H) ((H)->count)
|
||||
|
||||
#endif /* _FTS3_HASH_H_ */
|
||||
@@ -1,261 +0,0 @@
|
||||
/*
|
||||
** 2007 June 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 implements a tokenizer for fts3 based on the ICU library.
|
||||
*/
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
#ifdef SQLITE_ENABLE_ICU
|
||||
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
#include "fts3_tokenizer.h"
|
||||
|
||||
#include <unicode/ubrk.h>
|
||||
#include <unicode/ucol.h>
|
||||
#include <unicode/ustring.h>
|
||||
#include <unicode/utf16.h>
|
||||
|
||||
typedef struct IcuTokenizer IcuTokenizer;
|
||||
typedef struct IcuCursor IcuCursor;
|
||||
|
||||
struct IcuTokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
char *zLocale;
|
||||
};
|
||||
|
||||
struct IcuCursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
|
||||
UBreakIterator *pIter; /* ICU break-iterator object */
|
||||
int nChar; /* Number of UChar elements in pInput */
|
||||
UChar *aChar; /* Copy of input using utf-16 encoding */
|
||||
int *aOffset; /* Offsets of each character in utf-8 input */
|
||||
|
||||
int nBuffer;
|
||||
char *zBuffer;
|
||||
|
||||
int iToken;
|
||||
};
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int icuCreate(
|
||||
int argc, /* Number of entries in argv[] */
|
||||
const char * const *argv, /* Tokenizer creation arguments */
|
||||
sqlite3_tokenizer **ppTokenizer /* OUT: Created tokenizer */
|
||||
){
|
||||
IcuTokenizer *p;
|
||||
int n = 0;
|
||||
|
||||
if( argc>0 ){
|
||||
n = strlen(argv[0])+1;
|
||||
}
|
||||
p = (IcuTokenizer *)sqlite3_malloc(sizeof(IcuTokenizer)+n);
|
||||
if( !p ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(p, 0, sizeof(IcuTokenizer));
|
||||
|
||||
if( n ){
|
||||
p->zLocale = (char *)&p[1];
|
||||
memcpy(p->zLocale, argv[0], n);
|
||||
}
|
||||
|
||||
*ppTokenizer = (sqlite3_tokenizer *)p;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int icuDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
|
||||
sqlite3_free(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 icuOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *zInput, /* Input string */
|
||||
int nInput, /* Length of zInput in bytes */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
|
||||
IcuCursor *pCsr;
|
||||
|
||||
const int32_t opt = U_FOLD_CASE_DEFAULT;
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
int nChar;
|
||||
|
||||
UChar32 c;
|
||||
int iInput = 0;
|
||||
int iOut = 0;
|
||||
|
||||
*ppCursor = 0;
|
||||
|
||||
if( zInput==0 ){
|
||||
nInput = 0;
|
||||
zInput = "";
|
||||
}else if( nInput<0 ){
|
||||
nInput = strlen(zInput);
|
||||
}
|
||||
nChar = nInput+1;
|
||||
pCsr = (IcuCursor *)sqlite3_malloc(
|
||||
sizeof(IcuCursor) + /* IcuCursor */
|
||||
((nChar+3)&~3) * sizeof(UChar) + /* IcuCursor.aChar[] */
|
||||
(nChar+1) * sizeof(int) /* IcuCursor.aOffset[] */
|
||||
);
|
||||
if( !pCsr ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
memset(pCsr, 0, sizeof(IcuCursor));
|
||||
pCsr->aChar = (UChar *)&pCsr[1];
|
||||
pCsr->aOffset = (int *)&pCsr->aChar[(nChar+3)&~3];
|
||||
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
while( c>0 ){
|
||||
int isError = 0;
|
||||
c = u_foldCase(c, opt);
|
||||
U16_APPEND(pCsr->aChar, iOut, nChar, c, isError);
|
||||
if( isError ){
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
pCsr->aOffset[iOut] = iInput;
|
||||
|
||||
if( iInput<nInput ){
|
||||
U8_NEXT(zInput, iInput, nInput, c);
|
||||
}else{
|
||||
c = 0;
|
||||
}
|
||||
}
|
||||
|
||||
pCsr->pIter = ubrk_open(UBRK_WORD, p->zLocale, pCsr->aChar, iOut, &status);
|
||||
if( !U_SUCCESS(status) ){
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
pCsr->nChar = iOut;
|
||||
|
||||
ubrk_first(pCsr->pIter);
|
||||
*ppCursor = (sqlite3_tokenizer_cursor *)pCsr;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to icuOpen().
|
||||
*/
|
||||
static int icuClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
IcuCursor *pCsr = (IcuCursor *)pCursor;
|
||||
ubrk_close(pCsr->pIter);
|
||||
sqlite3_free(pCsr->zBuffer);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor.
|
||||
*/
|
||||
static int icuNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
|
||||
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 */
|
||||
){
|
||||
IcuCursor *pCsr = (IcuCursor *)pCursor;
|
||||
|
||||
int iStart = 0;
|
||||
int iEnd = 0;
|
||||
int nByte = 0;
|
||||
|
||||
while( iStart==iEnd ){
|
||||
UChar32 c;
|
||||
|
||||
iStart = ubrk_current(pCsr->pIter);
|
||||
iEnd = ubrk_next(pCsr->pIter);
|
||||
if( iEnd==UBRK_DONE ){
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
while( iStart<iEnd ){
|
||||
int iWhite = iStart;
|
||||
U16_NEXT(pCsr->aChar, iWhite, pCsr->nChar, c);
|
||||
if( u_isspace(c) ){
|
||||
iStart = iWhite;
|
||||
}else{
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert(iStart<=iEnd);
|
||||
}
|
||||
|
||||
do {
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
if( nByte ){
|
||||
char *zNew = sqlite3_realloc(pCsr->zBuffer, nByte);
|
||||
if( !zNew ){
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
pCsr->zBuffer = zNew;
|
||||
pCsr->nBuffer = nByte;
|
||||
}
|
||||
|
||||
u_strToUTF8(
|
||||
pCsr->zBuffer, pCsr->nBuffer, &nByte, /* Output vars */
|
||||
&pCsr->aChar[iStart], iEnd-iStart, /* Input vars */
|
||||
&status /* Output success/failure */
|
||||
);
|
||||
} while( nByte>pCsr->nBuffer );
|
||||
|
||||
*ppToken = pCsr->zBuffer;
|
||||
*pnBytes = nByte;
|
||||
*piStartOffset = pCsr->aOffset[iStart];
|
||||
*piEndOffset = pCsr->aOffset[iEnd];
|
||||
*piPosition = pCsr->iToken++;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 */
|
||||
};
|
||||
|
||||
/*
|
||||
** Set *ppModule to point at the implementation of the ICU tokenizer.
|
||||
*/
|
||||
void sqlite3Fts3IcuTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &icuTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* defined(SQLITE_ENABLE_ICU) */
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,662 +0,0 @@
|
||||
/*
|
||||
** 2006 September 30
|
||||
**
|
||||
** 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 full-text-search tokenizer that implements
|
||||
** a Porter stemmer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS3 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS3 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS3 is defined).
|
||||
*/
|
||||
#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"
|
||||
|
||||
/*
|
||||
** Class derived from sqlite3_tokenizer
|
||||
*/
|
||||
typedef struct porter_tokenizer {
|
||||
sqlite3_tokenizer base; /* Base class */
|
||||
} porter_tokenizer;
|
||||
|
||||
/*
|
||||
** Class derived from sqlite3_tokenizer_cursor
|
||||
*/
|
||||
typedef struct porter_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *zInput; /* input we are tokenizing */
|
||||
int nInput; /* size of the input */
|
||||
int iOffset; /* current position in zInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *zToken; /* storage for current token */
|
||||
int nAllocated; /* space allocated to zToken buffer */
|
||||
} porter_tokenizer_cursor;
|
||||
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int porterCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
porter_tokenizer *t;
|
||||
|
||||
UNUSED_PARAMETER(argc);
|
||||
UNUSED_PARAMETER(argv);
|
||||
|
||||
t = (porter_tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
memset(t, 0, sizeof(*t));
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int porterDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
sqlite3_free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Prepare to begin tokenizing a particular string. The input
|
||||
** string to be tokenized is zInput[0..nInput-1]. A cursor
|
||||
** used to incrementally tokenize this string is returned in
|
||||
** *ppCursor.
|
||||
*/
|
||||
static int porterOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *zInput, int nInput, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
porter_tokenizer_cursor *c;
|
||||
|
||||
UNUSED_PARAMETER(pTokenizer);
|
||||
|
||||
c = (porter_tokenizer_cursor *) sqlite3_malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->zInput = zInput;
|
||||
if( zInput==0 ){
|
||||
c->nInput = 0;
|
||||
}else if( nInput<0 ){
|
||||
c->nInput = (int)strlen(zInput);
|
||||
}else{
|
||||
c->nInput = nInput;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->zToken = NULL; /* no space allocated, yet. */
|
||||
c->nAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** porterOpen() above.
|
||||
*/
|
||||
static int porterClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
sqlite3_free(c->zToken);
|
||||
sqlite3_free(c);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
/*
|
||||
** Vowel or consonant
|
||||
*/
|
||||
static const char cType[] = {
|
||||
0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0,
|
||||
1, 1, 1, 2, 1
|
||||
};
|
||||
|
||||
/*
|
||||
** isConsonant() and isVowel() determine if their first character in
|
||||
** the string they point to is a consonant or a vowel, according
|
||||
** to Porter ruls.
|
||||
**
|
||||
** A consonate is any letter other than 'a', 'e', 'i', 'o', or 'u'.
|
||||
** 'Y' is a consonant unless it follows another consonant,
|
||||
** in which case it is a vowel.
|
||||
**
|
||||
** In these routine, the letters are in reverse order. So the 'y' rule
|
||||
** is that 'y' is a consonant unless it is followed by another
|
||||
** consonent.
|
||||
*/
|
||||
static int isVowel(const char*);
|
||||
static int isConsonant(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return j;
|
||||
return z[1]==0 || isVowel(z + 1);
|
||||
}
|
||||
static int isVowel(const char *z){
|
||||
int j;
|
||||
char x = *z;
|
||||
if( x==0 ) return 0;
|
||||
assert( x>='a' && x<='z' );
|
||||
j = cType[x-'a'];
|
||||
if( j<2 ) return 1-j;
|
||||
return isConsonant(z + 1);
|
||||
}
|
||||
|
||||
/*
|
||||
** Let any sequence of one or more vowels be represented by V and let
|
||||
** C be sequence of one or more consonants. Then every word can be
|
||||
** represented as:
|
||||
**
|
||||
** [C] (VC){m} [V]
|
||||
**
|
||||
** In prose: A word is an optional consonant followed by zero or
|
||||
** vowel-consonant pairs followed by an optional vowel. "m" is the
|
||||
** number of vowel consonant pairs. This routine computes the value
|
||||
** of m for the first i bytes of a word.
|
||||
**
|
||||
** Return true if the m-value for z is 1 or more. In other words,
|
||||
** return true if z contains at least one vowel that is followed
|
||||
** by a consonant.
|
||||
**
|
||||
** In this routine z[] is in reverse order. So we are really looking
|
||||
** for an instance of of a consonant followed by a vowel.
|
||||
*/
|
||||
static int m_gt_0(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m which is
|
||||
** exactly 1
|
||||
*/
|
||||
static int m_eq_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 1;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z==0;
|
||||
}
|
||||
|
||||
/* Like mgt0 above except we are looking for a value of m>1 instead
|
||||
** or m>0
|
||||
*/
|
||||
static int m_gt_1(const char *z){
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isVowel(z) ){ z++; }
|
||||
if( *z==0 ) return 0;
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if there is a vowel anywhere within z[0..n-1]
|
||||
*/
|
||||
static int hasVowel(const char *z){
|
||||
while( isConsonant(z) ){ z++; }
|
||||
return *z!=0;
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends in a double consonant.
|
||||
**
|
||||
** The text is reversed here. So we are really looking at
|
||||
** the first two characters of z[].
|
||||
*/
|
||||
static int doubleConsonant(const char *z){
|
||||
return isConsonant(z) && z[0]==z[1];
|
||||
}
|
||||
|
||||
/*
|
||||
** Return TRUE if the word ends with three letters which
|
||||
** are consonant-vowel-consonent and where the final consonant
|
||||
** is not 'w', 'x', or 'y'.
|
||||
**
|
||||
** The word is reversed here. So we are really checking the
|
||||
** first three letters and the first one cannot be in [wxy].
|
||||
*/
|
||||
static int star_oh(const char *z){
|
||||
return
|
||||
isConsonant(z) &&
|
||||
z[0]!='w' && z[0]!='x' && z[0]!='y' &&
|
||||
isVowel(z+1) &&
|
||||
isConsonant(z+2);
|
||||
}
|
||||
|
||||
/*
|
||||
** If the word ends with zFrom and xCond() is true for the stem
|
||||
** of the word that preceeds the zFrom ending, then change the
|
||||
** ending to zTo.
|
||||
**
|
||||
** The input word *pz and zFrom are both in reverse order. zTo
|
||||
** is in normal order.
|
||||
**
|
||||
** Return TRUE if zFrom matches. Return FALSE if zFrom does not
|
||||
** match. Not that TRUE is returned even if xCond() fails and
|
||||
** no substitution occurs.
|
||||
*/
|
||||
static int stem(
|
||||
char **pz, /* The word being stemmed (Reversed) */
|
||||
const char *zFrom, /* If the ending matches this... (Reversed) */
|
||||
const char *zTo, /* ... change the ending to this (not reversed) */
|
||||
int (*xCond)(const char*) /* Condition that must be true */
|
||||
){
|
||||
char *z = *pz;
|
||||
while( *zFrom && *zFrom==*z ){ z++; zFrom++; }
|
||||
if( *zFrom!=0 ) return 0;
|
||||
if( xCond && !xCond(z) ) return 1;
|
||||
while( *zTo ){
|
||||
*(--z) = *(zTo++);
|
||||
}
|
||||
*pz = z;
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
** This is the fallback stemmer used when the porter stemmer is
|
||||
** inappropriate. The input word is copied into the output with
|
||||
** US-ASCII case folding. If the input word is too long (more
|
||||
** than 20 bytes if it contains no digits or more than 6 bytes if
|
||||
** it contains digits) then word is truncated to 20 or 6 bytes
|
||||
** by taking 10 or 3 bytes from the beginning and end.
|
||||
*/
|
||||
static void copy_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, mx, j;
|
||||
int hasDigit = 0;
|
||||
for(i=0; i<nIn; i++){
|
||||
char c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zOut[i] = c - 'A' + 'a';
|
||||
}else{
|
||||
if( c>='0' && c<='9' ) hasDigit = 1;
|
||||
zOut[i] = c;
|
||||
}
|
||||
}
|
||||
mx = hasDigit ? 3 : 10;
|
||||
if( nIn>mx*2 ){
|
||||
for(j=mx, i=nIn-mx; i<nIn; i++, j++){
|
||||
zOut[j] = zOut[i];
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
zOut[i] = 0;
|
||||
*pnOut = i;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
** Stem the input word zIn[0..nIn-1]. Store the output in zOut.
|
||||
** zOut is at least big enough to hold nIn bytes. Write the actual
|
||||
** size of the output word (exclusive of the '\0' terminator) into *pnOut.
|
||||
**
|
||||
** Any upper-case characters in the US-ASCII character set ([A-Z])
|
||||
** are converted to lower case. Upper-case UTF characters are
|
||||
** unchanged.
|
||||
**
|
||||
** Words that are longer than about 20 bytes are stemmed by retaining
|
||||
** a few bytes from the beginning and the end of the word. If the
|
||||
** word contains digits, 3 bytes are taken from the beginning and
|
||||
** 3 bytes from the end. For long words without digits, 10 bytes
|
||||
** are taken from each end. US-ASCII case folding still applies.
|
||||
**
|
||||
** If the input word contains not digits but does characters not
|
||||
** in [a-zA-Z] then no stemming is attempted and this routine just
|
||||
** copies the input into the input into the output with US-ASCII
|
||||
** case folding.
|
||||
**
|
||||
** Stemming never increases the length of the word. So there is
|
||||
** no chance of overflowing the zOut buffer.
|
||||
*/
|
||||
static void porter_stemmer(const char *zIn, int nIn, char *zOut, int *pnOut){
|
||||
int i, j;
|
||||
char zReverse[28];
|
||||
char *z, *z2;
|
||||
if( nIn<3 || nIn>=(int)sizeof(zReverse)-7 ){
|
||||
/* The word is too big or too small for the porter stemmer.
|
||||
** Fallback to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
for(i=0, j=sizeof(zReverse)-6; i<nIn; i++, j--){
|
||||
char c = zIn[i];
|
||||
if( c>='A' && c<='Z' ){
|
||||
zReverse[j] = c + 'a' - 'A';
|
||||
}else if( c>='a' && c<='z' ){
|
||||
zReverse[j] = c;
|
||||
}else{
|
||||
/* The use of a character not in [a-zA-Z] means that we fallback
|
||||
** to the copy stemmer */
|
||||
copy_stemmer(zIn, nIn, zOut, pnOut);
|
||||
return;
|
||||
}
|
||||
}
|
||||
memset(&zReverse[sizeof(zReverse)-5], 0, 5);
|
||||
z = &zReverse[j+1];
|
||||
|
||||
|
||||
/* Step 1a */
|
||||
if( z[0]=='s' ){
|
||||
if(
|
||||
!stem(&z, "sess", "ss", 0) &&
|
||||
!stem(&z, "sei", "i", 0) &&
|
||||
!stem(&z, "ss", "ss", 0)
|
||||
){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1b */
|
||||
z2 = z;
|
||||
if( stem(&z, "dee", "ee", m_gt_0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if(
|
||||
(stem(&z, "gni", "", hasVowel) || stem(&z, "de", "", hasVowel))
|
||||
&& z!=z2
|
||||
){
|
||||
if( stem(&z, "ta", "ate", 0) ||
|
||||
stem(&z, "lb", "ble", 0) ||
|
||||
stem(&z, "zi", "ize", 0) ){
|
||||
/* Do nothing. The work was all in the test */
|
||||
}else if( doubleConsonant(z) && (*z!='l' && *z!='s' && *z!='z') ){
|
||||
z++;
|
||||
}else if( m_eq_1(z) && star_oh(z) ){
|
||||
*(--z) = 'e';
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 1c */
|
||||
if( z[0]=='y' && hasVowel(z+1) ){
|
||||
z[0] = 'i';
|
||||
}
|
||||
|
||||
/* Step 2 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
if( !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);
|
||||
}
|
||||
break;
|
||||
case 'e':
|
||||
stem(&z, "rezi", "ize", m_gt_0);
|
||||
break;
|
||||
case 'g':
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
break;
|
||||
case 's':
|
||||
stem(&z, "ssen", "", m_gt_0);
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 4 */
|
||||
switch( z[1] ){
|
||||
case 'a':
|
||||
if( z[0]=='l' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'c':
|
||||
if( z[0]=='e' && z[2]=='n' && (z[3]=='a' || z[3]=='e') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'e':
|
||||
if( z[0]=='r' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'i':
|
||||
if( z[0]=='c' && m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
break;
|
||||
case 'l':
|
||||
if( z[0]=='e' && z[2]=='b' && (z[3]=='a' || z[3]=='i') && m_gt_1(z+4) ){
|
||||
z += 4;
|
||||
}
|
||||
break;
|
||||
case 'n':
|
||||
if( z[0]=='t' ){
|
||||
if( z[2]=='a' ){
|
||||
if( m_gt_1(z+3) ){
|
||||
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);
|
||||
}
|
||||
}
|
||||
}
|
||||
break;
|
||||
case 'o':
|
||||
if( z[0]=='u' ){
|
||||
if( m_gt_1(z+2) ){
|
||||
z += 2;
|
||||
}
|
||||
}else if( z[3]=='s' || z[3]=='t' ){
|
||||
stem(&z, "noi", "", m_gt_1);
|
||||
}
|
||||
break;
|
||||
case 's':
|
||||
if( z[0]=='m' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 't':
|
||||
if( !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) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
case 'v':
|
||||
case 'z':
|
||||
if( z[0]=='e' && z[2]=='i' && m_gt_1(z+3) ){
|
||||
z += 3;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
/* Step 5a */
|
||||
if( z[0]=='e' ){
|
||||
if( m_gt_1(z+1) ){
|
||||
z++;
|
||||
}else if( m_eq_1(z+1) && !star_oh(z+1) ){
|
||||
z++;
|
||||
}
|
||||
}
|
||||
|
||||
/* Step 5b */
|
||||
if( m_gt_1(z) && z[0]=='l' && z[1]=='l' ){
|
||||
z++;
|
||||
}
|
||||
|
||||
/* z[] is now the stemmed word in reverse order. Flip it back
|
||||
** around into forward order and return.
|
||||
*/
|
||||
*pnOut = i = (int)strlen(z);
|
||||
zOut[i] = 0;
|
||||
while( *z ){
|
||||
zOut[--i] = *(z++);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
** Characters that can be part of a token. We assume any character
|
||||
** whose value is greater than 0x80 (any UTF character) can be
|
||||
** part of a token. In other words, delimiters all must have
|
||||
** values of 0x7f or lower.
|
||||
*/
|
||||
static const char porterIdChar[] = {
|
||||
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, /* 3x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 4x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, /* 5x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 6x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, /* 7x */
|
||||
};
|
||||
#define isDelim(C) (((ch=C)&0x80)==0 && (ch<0x30 || !porterIdChar[ch-0x30]))
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor. The cursor must
|
||||
** have been opened by a prior call to porterOpen().
|
||||
*/
|
||||
static int porterNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by porterOpen */
|
||||
const char **pzToken, /* OUT: *pzToken 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 */
|
||||
){
|
||||
porter_tokenizer_cursor *c = (porter_tokenizer_cursor *) pCursor;
|
||||
const char *z = c->zInput;
|
||||
|
||||
while( c->iOffset<c->nInput ){
|
||||
int iStartOffset, ch;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nInput && isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nInput && !isDelim(z[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int n = c->iOffset-iStartOffset;
|
||||
if( n>c->nAllocated ){
|
||||
char *pNew;
|
||||
c->nAllocated = n+20;
|
||||
pNew = sqlite3_realloc(c->zToken, c->nAllocated);
|
||||
if( !pNew ) return SQLITE_NOMEM;
|
||||
c->zToken = pNew;
|
||||
}
|
||||
porter_stemmer(&z[iStartOffset], n, c->zToken, pnBytes);
|
||||
*pzToken = c->zToken;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the porter-stemmer tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module porterTokenizerModule = {
|
||||
0,
|
||||
porterCreate,
|
||||
porterDestroy,
|
||||
porterOpen,
|
||||
porterClose,
|
||||
porterNext,
|
||||
0
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new porter tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts3PorterTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &porterTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,373 +0,0 @@
|
||||
/*
|
||||
** 2011 Jan 27
|
||||
**
|
||||
** 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 is not part of the production FTS code. It is only used for
|
||||
** testing. It contains a virtual table implementation that provides direct
|
||||
** access to the full-text index of an FTS table.
|
||||
*/
|
||||
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
typedef struct Fts3termTable Fts3termTable;
|
||||
typedef struct Fts3termCursor Fts3termCursor;
|
||||
|
||||
struct Fts3termTable {
|
||||
sqlite3_vtab base; /* Base class used by SQLite core */
|
||||
int iIndex; /* Index for Fts3Table.aIndex[] */
|
||||
Fts3Table *pFts3Tab;
|
||||
};
|
||||
|
||||
struct Fts3termCursor {
|
||||
sqlite3_vtab_cursor base; /* Base class used by SQLite core */
|
||||
Fts3MultiSegReader csr; /* Must be right after "base" */
|
||||
Fts3SegFilter filter;
|
||||
|
||||
int isEof; /* True if cursor is at EOF */
|
||||
char *pNext;
|
||||
|
||||
sqlite3_int64 iRowid; /* Current 'rowid' value */
|
||||
sqlite3_int64 iDocid; /* Current 'docid' value */
|
||||
int iCol; /* Current 'col' value */
|
||||
int iPos; /* Current 'pos' value */
|
||||
};
|
||||
|
||||
/*
|
||||
** Schema of the terms table.
|
||||
*/
|
||||
#define FTS3_TERMS_SCHEMA "CREATE TABLE x(term, docid, col, pos)"
|
||||
|
||||
/*
|
||||
** 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.
|
||||
*/
|
||||
static int fts3termConnectMethod(
|
||||
sqlite3 *db, /* Database connection */
|
||||
void *pCtx, /* Non-zero for an fts4prefix table */
|
||||
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 */
|
||||
){
|
||||
char const *zDb; /* Name of database (e.g. "main") */
|
||||
char const *zFts3; /* Name of fts3 table */
|
||||
int nDb; /* Result of strlen(zDb) */
|
||||
int nFts3; /* Result of strlen(zFts3) */
|
||||
int nByte; /* Bytes of space to allocate here */
|
||||
int rc; /* value returned by declare_vtab() */
|
||||
Fts3termTable *p; /* Virtual table object to return */
|
||||
int iIndex = 0;
|
||||
|
||||
UNUSED_PARAMETER(pCtx);
|
||||
if( argc==5 ){
|
||||
iIndex = atoi(argv[4]);
|
||||
argc--;
|
||||
}
|
||||
|
||||
/* The user should specify a single argument - the name of an fts3 table. */
|
||||
if( argc!=4 ){
|
||||
*pzErr = sqlite3_mprintf(
|
||||
"wrong number of arguments to fts4term constructor"
|
||||
);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
zDb = argv[1];
|
||||
nDb = (int)strlen(zDb);
|
||||
zFts3 = argv[3];
|
||||
nFts3 = (int)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_malloc(nByte);
|
||||
if( !p ) return SQLITE_NOMEM;
|
||||
memset(p, 0, nByte);
|
||||
|
||||
p->pFts3Tab = (Fts3Table *)&p[1];
|
||||
p->pFts3Tab->zDb = (char *)&p->pFts3Tab[1];
|
||||
p->pFts3Tab->zName = &p->pFts3Tab->zDb[nDb+1];
|
||||
p->pFts3Tab->db = db;
|
||||
p->pFts3Tab->nIndex = iIndex+1;
|
||||
p->iIndex = iIndex;
|
||||
|
||||
memcpy((char *)p->pFts3Tab->zDb, zDb, nDb);
|
||||
memcpy((char *)p->pFts3Tab->zName, zFts3, nFts3);
|
||||
sqlite3Fts3Dequote((char *)p->pFts3Tab->zName);
|
||||
|
||||
*ppVtab = (sqlite3_vtab *)p;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 fts3termDisconnectMethod(sqlite3_vtab *pVtab){
|
||||
Fts3termTable *p = (Fts3termTable *)pVtab;
|
||||
Fts3Table *pFts3 = p->pFts3Tab;
|
||||
int i;
|
||||
|
||||
/* Free any prepared statements held */
|
||||
for(i=0; i<SizeofArray(pFts3->aStmt); i++){
|
||||
sqlite3_finalize(pFts3->aStmt[i]);
|
||||
}
|
||||
sqlite3_free(pFts3->zSegmentsTbl);
|
||||
sqlite3_free(p);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
#define FTS4AUX_EQ_CONSTRAINT 1
|
||||
#define FTS4AUX_GE_CONSTRAINT 2
|
||||
#define FTS4AUX_LE_CONSTRAINT 4
|
||||
|
||||
/*
|
||||
** xBestIndex - Analyze a WHERE and ORDER BY clause.
|
||||
*/
|
||||
static int fts3termBestIndexMethod(
|
||||
sqlite3_vtab *pVTab,
|
||||
sqlite3_index_info *pInfo
|
||||
){
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
/* This vtab naturally does "ORDER BY term, docid, col, pos". */
|
||||
if( pInfo->nOrderBy ){
|
||||
int i;
|
||||
for(i=0; i<pInfo->nOrderBy; i++){
|
||||
if( pInfo->aOrderBy[i].iColumn!=i || pInfo->aOrderBy[i].desc ) break;
|
||||
}
|
||||
if( i==pInfo->nOrderBy ){
|
||||
pInfo->orderByConsumed = 1;
|
||||
}
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xOpen - Open a cursor.
|
||||
*/
|
||||
static int fts3termOpenMethod(sqlite3_vtab *pVTab, sqlite3_vtab_cursor **ppCsr){
|
||||
Fts3termCursor *pCsr; /* Pointer to cursor object to return */
|
||||
|
||||
UNUSED_PARAMETER(pVTab);
|
||||
|
||||
pCsr = (Fts3termCursor *)sqlite3_malloc(sizeof(Fts3termCursor));
|
||||
if( !pCsr ) return SQLITE_NOMEM;
|
||||
memset(pCsr, 0, sizeof(Fts3termCursor));
|
||||
|
||||
*ppCsr = (sqlite3_vtab_cursor *)pCsr;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xClose - Close a cursor.
|
||||
*/
|
||||
static int fts3termCloseMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3Table *pFts3 = ((Fts3termTable *)pCursor->pVtab)->pFts3Tab;
|
||||
Fts3termCursor *pCsr = (Fts3termCursor *)pCursor;
|
||||
|
||||
sqlite3Fts3SegmentsClose(pFts3);
|
||||
sqlite3Fts3SegReaderFinish(&pCsr->csr);
|
||||
sqlite3_free(pCsr);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xNext - Advance the cursor to the next row, if any.
|
||||
*/
|
||||
static int fts3termNextMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3termCursor *pCsr = (Fts3termCursor *)pCursor;
|
||||
Fts3Table *pFts3 = ((Fts3termTable *)pCursor->pVtab)->pFts3Tab;
|
||||
int rc;
|
||||
sqlite3_int64 v;
|
||||
|
||||
/* Increment our pretend rowid value. */
|
||||
pCsr->iRowid++;
|
||||
|
||||
/* Advance to the next term in the full-text index. */
|
||||
if( pCsr->csr.aDoclist==0
|
||||
|| pCsr->pNext>=&pCsr->csr.aDoclist[pCsr->csr.nDoclist-1]
|
||||
){
|
||||
rc = sqlite3Fts3SegReaderStep(pFts3, &pCsr->csr);
|
||||
if( rc!=SQLITE_ROW ){
|
||||
pCsr->isEof = 1;
|
||||
return rc;
|
||||
}
|
||||
|
||||
pCsr->iCol = 0;
|
||||
pCsr->iPos = 0;
|
||||
pCsr->iDocid = 0;
|
||||
pCsr->pNext = pCsr->csr.aDoclist;
|
||||
|
||||
/* Read docid */
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &pCsr->iDocid);
|
||||
}
|
||||
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
if( v==0 ){
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
pCsr->iDocid += v;
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
pCsr->iCol = 0;
|
||||
pCsr->iPos = 0;
|
||||
}
|
||||
|
||||
if( v==1 ){
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
pCsr->iCol += (int)v;
|
||||
pCsr->iPos = 0;
|
||||
pCsr->pNext += sqlite3Fts3GetVarint(pCsr->pNext, &v);
|
||||
}
|
||||
|
||||
pCsr->iPos += (int)(v - 2);
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xFilter - Initialize a cursor to point at the start of its data.
|
||||
*/
|
||||
static int fts3termFilterMethod(
|
||||
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 */
|
||||
){
|
||||
Fts3termCursor *pCsr = (Fts3termCursor *)pCursor;
|
||||
Fts3termTable *p = (Fts3termTable *)pCursor->pVtab;
|
||||
Fts3Table *pFts3 = p->pFts3Tab;
|
||||
int rc;
|
||||
|
||||
UNUSED_PARAMETER(nVal);
|
||||
UNUSED_PARAMETER(idxNum);
|
||||
UNUSED_PARAMETER(idxStr);
|
||||
UNUSED_PARAMETER(apVal);
|
||||
|
||||
assert( idxStr==0 && idxNum==0 );
|
||||
|
||||
/* In case this cursor is being reused, close and zero it. */
|
||||
testcase(pCsr->filter.zTerm);
|
||||
sqlite3Fts3SegReaderFinish(&pCsr->csr);
|
||||
memset(&pCsr->csr, 0, ((u8*)&pCsr[1]) - (u8*)&pCsr->csr);
|
||||
|
||||
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,
|
||||
pCsr->filter.zTerm, pCsr->filter.nTerm, 0, 1, &pCsr->csr
|
||||
);
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = sqlite3Fts3SegReaderStart(pFts3, &pCsr->csr, &pCsr->filter);
|
||||
}
|
||||
if( rc==SQLITE_OK ){
|
||||
rc = fts3termNextMethod(pCursor);
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** xEof - Return true if the cursor is at EOF, or false otherwise.
|
||||
*/
|
||||
static int fts3termEofMethod(sqlite3_vtab_cursor *pCursor){
|
||||
Fts3termCursor *pCsr = (Fts3termCursor *)pCursor;
|
||||
return pCsr->isEof;
|
||||
}
|
||||
|
||||
/*
|
||||
** xColumn - Return a column value.
|
||||
*/
|
||||
static int fts3termColumnMethod(
|
||||
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 */
|
||||
){
|
||||
Fts3termCursor *p = (Fts3termCursor *)pCursor;
|
||||
|
||||
assert( iCol>=0 && iCol<=3 );
|
||||
switch( iCol ){
|
||||
case 0:
|
||||
sqlite3_result_text(pCtx, p->csr.zTerm, p->csr.nTerm, SQLITE_TRANSIENT);
|
||||
break;
|
||||
case 1:
|
||||
sqlite3_result_int64(pCtx, p->iDocid);
|
||||
break;
|
||||
case 2:
|
||||
sqlite3_result_int64(pCtx, p->iCol);
|
||||
break;
|
||||
default:
|
||||
sqlite3_result_int64(pCtx, p->iPos);
|
||||
break;
|
||||
}
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** xRowid - Return the current rowid for the cursor.
|
||||
*/
|
||||
static int fts3termRowidMethod(
|
||||
sqlite3_vtab_cursor *pCursor, /* Cursor to retrieve value from */
|
||||
sqlite_int64 *pRowid /* OUT: Rowid value */
|
||||
){
|
||||
Fts3termCursor *pCsr = (Fts3termCursor *)pCursor;
|
||||
*pRowid = pCsr->iRowid;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Register the fts3term module with database connection db. Return SQLITE_OK
|
||||
** if successful or an error code if sqlite3_create_module() fails.
|
||||
*/
|
||||
int sqlite3Fts3InitTerm(sqlite3 *db){
|
||||
static const sqlite3_module fts3term_module = {
|
||||
0, /* iVersion */
|
||||
fts3termConnectMethod, /* xCreate */
|
||||
fts3termConnectMethod, /* xConnect */
|
||||
fts3termBestIndexMethod, /* xBestIndex */
|
||||
fts3termDisconnectMethod, /* xDisconnect */
|
||||
fts3termDisconnectMethod, /* xDestroy */
|
||||
fts3termOpenMethod, /* xOpen */
|
||||
fts3termCloseMethod, /* xClose */
|
||||
fts3termFilterMethod, /* xFilter */
|
||||
fts3termNextMethod, /* xNext */
|
||||
fts3termEofMethod, /* xEof */
|
||||
fts3termColumnMethod, /* xColumn */
|
||||
fts3termRowidMethod, /* xRowid */
|
||||
0, /* xUpdate */
|
||||
0, /* xBegin */
|
||||
0, /* xSync */
|
||||
0, /* xCommit */
|
||||
0, /* xRollback */
|
||||
0, /* xFindFunction */
|
||||
0, /* xRename */
|
||||
0, /* xSavepoint */
|
||||
0, /* xRelease */
|
||||
0 /* xRollbackTo */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
rc = sqlite3_create_module(db, "fts4term", &fts3term_module, 0);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,584 +0,0 @@
|
||||
/*
|
||||
** 2011 Jun 13
|
||||
**
|
||||
** 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 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.
|
||||
*/
|
||||
|
||||
#include <tcl.h>
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
|
||||
#if defined(SQLITE_TEST)
|
||||
#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)
|
||||
|
||||
/* Required so that the "ifdef SQLITE_ENABLE_FTS3" below works */
|
||||
#include "fts3Int.h"
|
||||
|
||||
#define NM_MAX_TOKEN 12
|
||||
|
||||
typedef struct NearPhrase NearPhrase;
|
||||
typedef struct NearDocument NearDocument;
|
||||
typedef struct NearToken NearToken;
|
||||
|
||||
struct NearDocument {
|
||||
int nToken; /* Length of token in bytes */
|
||||
NearToken *aToken; /* Token array */
|
||||
};
|
||||
|
||||
struct NearToken {
|
||||
int n; /* Length of token in bytes */
|
||||
const char *z; /* Pointer to token string */
|
||||
};
|
||||
|
||||
struct NearPhrase {
|
||||
int nNear; /* Preceding NEAR value */
|
||||
int nToken; /* Number of tokens in this phrase */
|
||||
NearToken aToken[NM_MAX_TOKEN]; /* Array of tokens in this phrase */
|
||||
};
|
||||
|
||||
static int nm_phrase_match(
|
||||
NearPhrase *p,
|
||||
NearToken *aToken
|
||||
){
|
||||
int ii;
|
||||
|
||||
for(ii=0; ii<p->nToken; ii++){
|
||||
NearToken *pToken = &p->aToken[ii];
|
||||
if( pToken->n>0 && pToken->z[pToken->n-1]=='*' ){
|
||||
if( aToken[ii].n<(pToken->n-1) ) return 0;
|
||||
if( memcmp(aToken[ii].z, pToken->z, pToken->n-1) ) return 0;
|
||||
}else{
|
||||
if( aToken[ii].n!=pToken->n ) return 0;
|
||||
if( memcmp(aToken[ii].z, pToken->z, pToken->n) ) return 0;
|
||||
}
|
||||
}
|
||||
|
||||
return 1;
|
||||
}
|
||||
|
||||
static int nm_near_chain(
|
||||
int iDir, /* Direction to iterate through aPhrase[] */
|
||||
NearDocument *pDoc, /* Document to match against */
|
||||
int iPos, /* Position at which iPhrase was found */
|
||||
int nPhrase, /* Size of phrase array */
|
||||
NearPhrase *aPhrase, /* Phrase array */
|
||||
int iPhrase /* Index of phrase found */
|
||||
){
|
||||
int iStart;
|
||||
int iStop;
|
||||
int ii;
|
||||
int nNear;
|
||||
int iPhrase2;
|
||||
NearPhrase *p;
|
||||
NearPhrase *pPrev;
|
||||
|
||||
assert( iDir==1 || iDir==-1 );
|
||||
|
||||
if( iDir==1 ){
|
||||
if( (iPhrase+1)==nPhrase ) return 1;
|
||||
nNear = aPhrase[iPhrase+1].nNear;
|
||||
}else{
|
||||
if( iPhrase==0 ) return 1;
|
||||
nNear = aPhrase[iPhrase].nNear;
|
||||
}
|
||||
pPrev = &aPhrase[iPhrase];
|
||||
iPhrase2 = iPhrase+iDir;
|
||||
p = &aPhrase[iPhrase2];
|
||||
|
||||
iStart = iPos - nNear - p->nToken;
|
||||
iStop = iPos + nNear + pPrev->nToken;
|
||||
|
||||
if( iStart<0 ) iStart = 0;
|
||||
if( iStop > pDoc->nToken - p->nToken ) iStop = pDoc->nToken - p->nToken;
|
||||
|
||||
for(ii=iStart; ii<=iStop; ii++){
|
||||
if( nm_phrase_match(p, &pDoc->aToken[ii]) ){
|
||||
if( nm_near_chain(iDir, pDoc, ii, nPhrase, aPhrase, iPhrase2) ) return 1;
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int nm_match_count(
|
||||
NearDocument *pDoc, /* Document to match against */
|
||||
int nPhrase, /* Size of phrase array */
|
||||
NearPhrase *aPhrase, /* Phrase array */
|
||||
int iPhrase /* Index of phrase to count matches for */
|
||||
){
|
||||
int nOcc = 0;
|
||||
int ii;
|
||||
NearPhrase *p = &aPhrase[iPhrase];
|
||||
|
||||
for(ii=0; ii<(pDoc->nToken + 1 - p->nToken); ii++){
|
||||
if( nm_phrase_match(p, &pDoc->aToken[ii]) ){
|
||||
/* Test forward NEAR chain (i>iPhrase) */
|
||||
if( 0==nm_near_chain(1, pDoc, ii, nPhrase, aPhrase, iPhrase) ) continue;
|
||||
|
||||
/* Test reverse NEAR chain (i<iPhrase) */
|
||||
if( 0==nm_near_chain(-1, pDoc, ii, nPhrase, aPhrase, iPhrase) ) continue;
|
||||
|
||||
/* This is a real match. Increment the counter. */
|
||||
nOcc++;
|
||||
}
|
||||
}
|
||||
|
||||
return nOcc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Tclcmd: fts3_near_match DOCUMENT EXPR ?OPTIONS?
|
||||
*/
|
||||
static int fts3_near_match_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
int nTotal = 0;
|
||||
int rc;
|
||||
int ii;
|
||||
int nPhrase;
|
||||
NearPhrase *aPhrase = 0;
|
||||
NearDocument doc = {0, 0};
|
||||
Tcl_Obj **apDocToken;
|
||||
Tcl_Obj *pRet;
|
||||
Tcl_Obj *pPhrasecount = 0;
|
||||
|
||||
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?...");
|
||||
rc = TCL_ERROR;
|
||||
goto near_match_out;
|
||||
}
|
||||
|
||||
for(ii=3; ii<objc; ii+=2){
|
||||
enum NM_enum { NM_PHRASECOUNTS };
|
||||
struct TestnmSubcmd {
|
||||
char *zName;
|
||||
enum NM_enum eOpt;
|
||||
} aOpt[] = {
|
||||
{ "-phrasecountvar", NM_PHRASECOUNTS },
|
||||
{ 0, 0 }
|
||||
};
|
||||
int iOpt;
|
||||
if( Tcl_GetIndexFromObjStruct(
|
||||
interp, objv[ii], aOpt, sizeof(aOpt[0]), "option", 0, &iOpt)
|
||||
){
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
switch( aOpt[iOpt].eOpt ){
|
||||
case NM_PHRASECOUNTS:
|
||||
pPhrasecount = objv[ii+1];
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
rc = Tcl_ListObjGetElements(interp, objv[1], &doc.nToken, &apDocToken);
|
||||
if( rc!=TCL_OK ) goto near_match_out;
|
||||
doc.aToken = (NearToken *)ckalloc(doc.nToken*sizeof(NearToken));
|
||||
for(ii=0; ii<doc.nToken; ii++){
|
||||
doc.aToken[ii].z = Tcl_GetStringFromObj(apDocToken[ii], &doc.aToken[ii].n);
|
||||
}
|
||||
|
||||
rc = Tcl_ListObjGetElements(interp, objv[2], &nExprToken, &apExprToken);
|
||||
if( rc!=TCL_OK ) goto near_match_out;
|
||||
|
||||
nPhrase = (nExprToken + 1) / 2;
|
||||
aPhrase = (NearPhrase *)ckalloc(nPhrase * sizeof(NearPhrase));
|
||||
memset(aPhrase, 0, nPhrase * sizeof(NearPhrase));
|
||||
for(ii=0; ii<nPhrase; ii++){
|
||||
Tcl_Obj *pPhrase = apExprToken[ii*2];
|
||||
Tcl_Obj **apToken;
|
||||
int nToken;
|
||||
int jj;
|
||||
|
||||
rc = Tcl_ListObjGetElements(interp, pPhrase, &nToken, &apToken);
|
||||
if( rc!=TCL_OK ) goto near_match_out;
|
||||
if( nToken>NM_MAX_TOKEN ){
|
||||
Tcl_AppendResult(interp, "Too many tokens in phrase", 0);
|
||||
rc = TCL_ERROR;
|
||||
goto near_match_out;
|
||||
}
|
||||
for(jj=0; jj<nToken; jj++){
|
||||
NearToken *pT = &aPhrase[ii].aToken[jj];
|
||||
pT->z = Tcl_GetStringFromObj(apToken[jj], &pT->n);
|
||||
}
|
||||
aPhrase[ii].nToken = nToken;
|
||||
}
|
||||
for(ii=1; ii<nPhrase; ii++){
|
||||
Tcl_Obj *pNear = apExprToken[2*ii-1];
|
||||
int nNear;
|
||||
rc = Tcl_GetIntFromObj(interp, pNear, &nNear);
|
||||
if( rc!=TCL_OK ) goto near_match_out;
|
||||
aPhrase[ii].nNear = nNear;
|
||||
}
|
||||
|
||||
pRet = Tcl_NewObj();
|
||||
Tcl_IncrRefCount(pRet);
|
||||
for(ii=0; ii<nPhrase; ii++){
|
||||
int nOcc = nm_match_count(&doc, nPhrase, aPhrase, ii);
|
||||
Tcl_ListObjAppendElement(interp, pRet, Tcl_NewIntObj(nOcc));
|
||||
nTotal += nOcc;
|
||||
}
|
||||
if( pPhrasecount ){
|
||||
Tcl_ObjSetVar2(interp, pPhrasecount, 0, pRet, 0);
|
||||
}
|
||||
Tcl_DecrRefCount(pRet);
|
||||
Tcl_SetObjResult(interp, Tcl_NewBooleanObj(nTotal>0));
|
||||
|
||||
near_match_out:
|
||||
ckfree((char *)aPhrase);
|
||||
ckfree((char *)doc.aToken);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
** Tclcmd: fts3_configure_incr_load ?CHUNKSIZE THRESHOLD?
|
||||
**
|
||||
** Normally, FTS uses hard-coded values to determine the minimum doclist
|
||||
** size eligible for incremental loading, and the size of the chunks loaded
|
||||
** when a doclist is incrementally loaded. This command allows the built-in
|
||||
** values to be overridden for testing purposes.
|
||||
**
|
||||
** If present, the first argument is the chunksize in bytes to load doclists
|
||||
** in. The second argument is the minimum doclist size in bytes to use
|
||||
** incremental loading with.
|
||||
**
|
||||
** 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
|
||||
** tests. For example:
|
||||
**
|
||||
** # Override incr-load settings for testing:
|
||||
** set cfg [fts3_configure_incr_load $new_chunksize $new_threshold]
|
||||
**
|
||||
** .... run tests ....
|
||||
**
|
||||
** # Restore initial incr-load settings:
|
||||
** eval fts3_configure_incr_load $cfg
|
||||
*/
|
||||
static int fts3_configure_incr_load_cmd(
|
||||
ClientData clientData,
|
||||
Tcl_Interp *interp,
|
||||
int objc,
|
||||
Tcl_Obj *CONST objv[]
|
||||
){
|
||||
#ifdef SQLITE_ENABLE_FTS3
|
||||
extern int test_fts3_node_chunksize;
|
||||
extern int test_fts3_node_chunk_threshold;
|
||||
Tcl_Obj *pRet;
|
||||
|
||||
if( objc!=1 && objc!=3 ){
|
||||
Tcl_WrongNumArgs(interp, 1, objv, "?CHUNKSIZE THRESHOLD?");
|
||||
return TCL_ERROR;
|
||||
}
|
||||
|
||||
pRet = Tcl_NewObj();
|
||||
Tcl_IncrRefCount(pRet);
|
||||
Tcl_ListObjAppendElement(
|
||||
interp, pRet, Tcl_NewIntObj(test_fts3_node_chunksize));
|
||||
Tcl_ListObjAppendElement(
|
||||
interp, pRet, Tcl_NewIntObj(test_fts3_node_chunk_threshold));
|
||||
|
||||
if( objc==3 ){
|
||||
int iArg1;
|
||||
int iArg2;
|
||||
if( Tcl_GetIntFromObj(interp, objv[1], &iArg1)
|
||||
|| Tcl_GetIntFromObj(interp, objv[2], &iArg2)
|
||||
){
|
||||
Tcl_DecrRefCount(pRet);
|
||||
return TCL_ERROR;
|
||||
}
|
||||
test_fts3_node_chunksize = iArg1;
|
||||
test_fts3_node_chunk_threshold = iArg2;
|
||||
}
|
||||
|
||||
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] = 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 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 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, 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.
|
||||
**************************************************************************/
|
||||
|
||||
int Sqlitetestfts3_Init(Tcl_Interp *interp){
|
||||
Tcl_CreateObjCommand(interp, "fts3_near_match", fts3_near_match_cmd, 0, 0);
|
||||
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
|
||||
);
|
||||
return TCL_OK;
|
||||
}
|
||||
#endif /* SQLITE_ENABLE_FTS3 || SQLITE_ENABLE_FTS4 */
|
||||
#endif /* ifdef SQLITE_TEST */
|
||||
@@ -1,454 +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 ){
|
||||
*pzErr = sqlite3_mprintf("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_malloc(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;
|
||||
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 */
|
||||
};
|
||||
int rc; /* Return code */
|
||||
|
||||
rc = sqlite3_create_module(db, "fts3tokenize", &fts3tok_module, (void*)pHash);
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,488 +0,0 @@
|
||||
/*
|
||||
** 2007 June 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 is part of an SQLite module implementing full-text search.
|
||||
** This particular file implements the generic tokenizer interface.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS3 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS3 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS3 is defined).
|
||||
*/
|
||||
#include "fts3Int.h"
|
||||
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
|
||||
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
|
||||
/*
|
||||
** Implementation of the SQL scalar function for accessing the underlying
|
||||
** hash table. This function may be called as follows:
|
||||
**
|
||||
** SELECT <function-name>(<key-name>);
|
||||
** 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').
|
||||
**
|
||||
** If the <pointer> argument is specified, it must be a blob value
|
||||
** containing a pointer to be stored as the hash data corresponding
|
||||
** to the string <key-name>. If <pointer> is not specified, then
|
||||
** the string <key-name> must already exist in the has table. Otherwise,
|
||||
** an error is returned.
|
||||
**
|
||||
** Whether or not the <pointer> argument is specified, the value returned
|
||||
** 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 scalarFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
Fts3Hash *pHash;
|
||||
void *pPtr = 0;
|
||||
const unsigned char *zName;
|
||||
int nName;
|
||||
|
||||
assert( argc==1 || argc==2 );
|
||||
|
||||
pHash = (Fts3Hash *)sqlite3_user_data(context);
|
||||
|
||||
zName = sqlite3_value_text(argv[0]);
|
||||
nName = sqlite3_value_bytes(argv[0])+1;
|
||||
|
||||
if( argc==2 ){
|
||||
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{
|
||||
pPtr = sqlite3Fts3HashFind(pHash, zName, nName);
|
||||
if( !pPtr ){
|
||||
char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName);
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
sqlite3_free(zErr);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
sqlite3_result_blob(context, (void *)&pPtr, sizeof(pPtr), SQLITE_TRANSIENT);
|
||||
}
|
||||
|
||||
int sqlite3Fts3IsIdChar(char c){
|
||||
static const char isFtsIdChar[] = {
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1x */
|
||||
0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 2x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, /* 3x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 4x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, /* 5x */
|
||||
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 6x */
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, /* 7x */
|
||||
};
|
||||
return (c&0x80 || isFtsIdChar[(int)(c)]);
|
||||
}
|
||||
|
||||
const char *sqlite3Fts3NextToken(const char *zStr, int *pn){
|
||||
const char *z1;
|
||||
const char *z2 = 0;
|
||||
|
||||
/* Find the start of the next token. */
|
||||
z1 = zStr;
|
||||
while( z2==0 ){
|
||||
char c = *z1;
|
||||
switch( c ){
|
||||
case '\0': return 0; /* No more tokens here */
|
||||
case '\'':
|
||||
case '"':
|
||||
case '`': {
|
||||
z2 = z1;
|
||||
while( *++z2 && (*z2!=c || *++z2==c) );
|
||||
break;
|
||||
}
|
||||
case '[':
|
||||
z2 = &z1[1];
|
||||
while( *z2 && z2[0]!=']' ) z2++;
|
||||
if( *z2 ) z2++;
|
||||
break;
|
||||
|
||||
default:
|
||||
if( sqlite3Fts3IsIdChar(*z1) ){
|
||||
z2 = &z1[1];
|
||||
while( sqlite3Fts3IsIdChar(*z2) ) z2++;
|
||||
}else{
|
||||
z1++;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
*pn = (int)(z2-z1);
|
||||
return z1;
|
||||
}
|
||||
|
||||
int sqlite3Fts3InitTokenizer(
|
||||
Fts3Hash *pHash, /* Tokenizer hash table */
|
||||
const char *zArg, /* Tokenizer name */
|
||||
sqlite3_tokenizer **ppTok, /* OUT: Tokenizer (if applicable) */
|
||||
char **pzErr /* OUT: Set to malloced error message */
|
||||
){
|
||||
int rc;
|
||||
char *z = (char *)zArg;
|
||||
int n = 0;
|
||||
char *zCopy;
|
||||
char *zEnd; /* Pointer to nul-term of zCopy */
|
||||
sqlite3_tokenizer_module *m;
|
||||
|
||||
zCopy = sqlite3_mprintf("%s", zArg);
|
||||
if( !zCopy ) return SQLITE_NOMEM;
|
||||
zEnd = &zCopy[strlen(zCopy)];
|
||||
|
||||
z = (char *)sqlite3Fts3NextToken(zCopy, &n);
|
||||
z[n] = '\0';
|
||||
sqlite3Fts3Dequote(z);
|
||||
|
||||
m = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash,z,(int)strlen(z)+1);
|
||||
if( !m ){
|
||||
*pzErr = sqlite3_mprintf("unknown tokenizer: %s", z);
|
||||
rc = SQLITE_ERROR;
|
||||
}else{
|
||||
char const **aArg = 0;
|
||||
int iArg = 0;
|
||||
z = &z[n+1];
|
||||
while( z<zEnd && (NULL!=(z = (char *)sqlite3Fts3NextToken(z, &n))) ){
|
||||
int nNew = sizeof(char *)*(iArg+1);
|
||||
char const **aNew = (const char **)sqlite3_realloc((void *)aArg, nNew);
|
||||
if( !aNew ){
|
||||
sqlite3_free(zCopy);
|
||||
sqlite3_free((void *)aArg);
|
||||
return SQLITE_NOMEM;
|
||||
}
|
||||
aArg = aNew;
|
||||
aArg[iArg++] = z;
|
||||
z[n] = '\0';
|
||||
sqlite3Fts3Dequote(z);
|
||||
z = &z[n+1];
|
||||
}
|
||||
rc = m->xCreate(iArg, aArg, ppTok);
|
||||
assert( rc!=SQLITE_OK || *ppTok );
|
||||
if( rc!=SQLITE_OK ){
|
||||
*pzErr = sqlite3_mprintf("unknown tokenizer");
|
||||
}else{
|
||||
(*ppTok)->pModule = m;
|
||||
}
|
||||
sqlite3_free((void *)aArg);
|
||||
}
|
||||
|
||||
sqlite3_free(zCopy);
|
||||
return rc;
|
||||
}
|
||||
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
|
||||
#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:
|
||||
**
|
||||
** SELECT <function-name>(<key-name>, ..., <input-string>);
|
||||
**
|
||||
** where <function-name> is the name passed as the second argument
|
||||
** to the sqlite3Fts3InitHashTable() function (e.g. 'fts3_tokenizer')
|
||||
** concatenated with the string '_test' (e.g. 'fts3_tokenizer_test').
|
||||
**
|
||||
** The return value is a string that may be interpreted as a Tcl
|
||||
** list. For each token in the <input-string>, three elements are
|
||||
** added to the returned list. The first is the token position, the
|
||||
** second is the token text (folded, stemmed, etc.) and the third is the
|
||||
** substring of <input-string> associated with the token. For example,
|
||||
** using the built-in "simple" tokenizer:
|
||||
**
|
||||
** SELECT fts_tokenizer_test('simple', 'I don't see how');
|
||||
**
|
||||
** will return the string:
|
||||
**
|
||||
** "{0 i I 1 dont don't 2 see see 3 how how}"
|
||||
**
|
||||
*/
|
||||
static void testFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
Fts3Hash *pHash;
|
||||
sqlite3_tokenizer_module *p;
|
||||
sqlite3_tokenizer *pTokenizer = 0;
|
||||
sqlite3_tokenizer_cursor *pCsr = 0;
|
||||
|
||||
const char *zErr = 0;
|
||||
|
||||
const char *zName;
|
||||
int nName;
|
||||
const char *zInput;
|
||||
int nInput;
|
||||
|
||||
const char *azArg[64];
|
||||
|
||||
const char *zToken;
|
||||
int nToken = 0;
|
||||
int iStart = 0;
|
||||
int iEnd = 0;
|
||||
int iPos = 0;
|
||||
int i;
|
||||
|
||||
Tcl_Obj *pRet;
|
||||
|
||||
if( argc<2 ){
|
||||
sqlite3_result_error(context, "insufficient arguments", -1);
|
||||
return;
|
||||
}
|
||||
|
||||
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]);
|
||||
|
||||
pHash = (Fts3Hash *)sqlite3_user_data(context);
|
||||
p = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash, zName, nName+1);
|
||||
|
||||
if( !p ){
|
||||
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) ){
|
||||
zErr = "error in xCreate()";
|
||||
goto finish;
|
||||
}
|
||||
pTokenizer->pModule = p;
|
||||
if( sqlite3Fts3OpenTokenizer(pTokenizer, 0, zInput, nInput, &pCsr) ){
|
||||
zErr = "error in xOpen()";
|
||||
goto finish;
|
||||
}
|
||||
|
||||
while( SQLITE_OK==p->xNext(pCsr, &zToken, &nToken, &iStart, &iEnd, &iPos) ){
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewIntObj(iPos));
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken));
|
||||
zToken = &zInput[iStart];
|
||||
nToken = iEnd-iStart;
|
||||
Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken));
|
||||
}
|
||||
|
||||
if( SQLITE_OK!=p->xClose(pCsr) ){
|
||||
zErr = "error in xClose()";
|
||||
goto finish;
|
||||
}
|
||||
if( SQLITE_OK!=p->xDestroy(pTokenizer) ){
|
||||
zErr = "error in xDestroy()";
|
||||
goto finish;
|
||||
}
|
||||
|
||||
finish:
|
||||
if( zErr ){
|
||||
sqlite3_result_error(context, zErr, -1);
|
||||
}else{
|
||||
sqlite3_result_text(context, Tcl_GetString(pRet), -1, SQLITE_TRANSIENT);
|
||||
}
|
||||
Tcl_DecrRefCount(pRet);
|
||||
}
|
||||
|
||||
static
|
||||
int registerTokenizer(
|
||||
sqlite3 *db,
|
||||
char *zName,
|
||||
const sqlite3_tokenizer_module *p
|
||||
){
|
||||
int rc;
|
||||
sqlite3_stmt *pStmt;
|
||||
const char zSql[] = "SELECT fts3_tokenizer(?, ?)";
|
||||
|
||||
rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0);
|
||||
if( rc!=SQLITE_OK ){
|
||||
return rc;
|
||||
}
|
||||
|
||||
sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC);
|
||||
sqlite3_bind_blob(pStmt, 2, &p, sizeof(p), SQLITE_STATIC);
|
||||
sqlite3_step(pStmt);
|
||||
|
||||
return sqlite3_finalize(pStmt);
|
||||
}
|
||||
|
||||
static
|
||||
int queryTokenizer(
|
||||
sqlite3 *db,
|
||||
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);
|
||||
}
|
||||
|
||||
void sqlite3Fts3SimpleTokenizerModule(sqlite3_tokenizer_module const**ppModule);
|
||||
|
||||
/*
|
||||
** Implementation of the scalar function fts3_tokenizer_internal_test().
|
||||
** This function is used for testing only, it is not included in the
|
||||
** build unless SQLITE_TEST is defined.
|
||||
**
|
||||
** The purpose of this is to test that the fts3_tokenizer() function
|
||||
** can be used as designed by the C-code in the queryTokenizer and
|
||||
** registerTokenizer() functions above. These two functions are repeated
|
||||
** in the README.tokenizer file as an example, so it is important to
|
||||
** test them.
|
||||
**
|
||||
** To run the tests, evaluate the fts3_tokenizer_internal_test() scalar
|
||||
** function with no arguments. An assert() will fail if a problem is
|
||||
** detected. i.e.:
|
||||
**
|
||||
** SELECT fts3_tokenizer_internal_test();
|
||||
**
|
||||
*/
|
||||
static void intTestFunc(
|
||||
sqlite3_context *context,
|
||||
int argc,
|
||||
sqlite3_value **argv
|
||||
){
|
||||
int rc;
|
||||
const sqlite3_tokenizer_module *p1;
|
||||
const sqlite3_tokenizer_module *p2;
|
||||
sqlite3 *db = (sqlite3 *)sqlite3_user_data(context);
|
||||
|
||||
UNUSED_PARAMETER(argc);
|
||||
UNUSED_PARAMETER(argv);
|
||||
|
||||
/* Test the query function */
|
||||
sqlite3Fts3SimpleTokenizerModule(&p1);
|
||||
rc = queryTokenizer(db, "simple", &p2);
|
||||
assert( rc==SQLITE_OK );
|
||||
assert( p1==p2 );
|
||||
rc = queryTokenizer(db, "nosuchtokenizer", &p2);
|
||||
assert( rc==SQLITE_ERROR );
|
||||
assert( p2==0 );
|
||||
assert( 0==strcmp(sqlite3_errmsg(db), "unknown tokenizer: nosuchtokenizer") );
|
||||
|
||||
/* Test the storage function */
|
||||
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);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
/*
|
||||
** 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
|
||||
** 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
|
||||
** 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.
|
||||
**
|
||||
** The third argument to this function, zName, is used as the name
|
||||
** of both the scalar and, if created, the virtual table.
|
||||
*/
|
||||
int sqlite3Fts3InitHashTable(
|
||||
sqlite3 *db,
|
||||
Fts3Hash *pHash,
|
||||
const char *zName
|
||||
){
|
||||
int rc = SQLITE_OK;
|
||||
void *p = (void *)pHash;
|
||||
const int any = SQLITE_ANY;
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
char *zTest = 0;
|
||||
char *zTest2 = 0;
|
||||
void *pdb = (void *)db;
|
||||
zTest = sqlite3_mprintf("%s_test", zName);
|
||||
zTest2 = sqlite3_mprintf("%s_internal_test", zName);
|
||||
if( !zTest || !zTest2 ){
|
||||
rc = SQLITE_NOMEM;
|
||||
}
|
||||
#endif
|
||||
|
||||
if( SQLITE_OK==rc ){
|
||||
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, scalarFunc, 0, 0);
|
||||
}
|
||||
#ifdef SQLITE_TEST
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zTest, -1, any, p, testFunc, 0, 0);
|
||||
}
|
||||
if( SQLITE_OK==rc ){
|
||||
rc = sqlite3_create_function(db, zTest2, 0, any, pdb, intTestFunc, 0, 0);
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef SQLITE_TEST
|
||||
sqlite3_free(zTest);
|
||||
sqlite3_free(zTest2);
|
||||
#endif
|
||||
|
||||
return rc;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,161 +0,0 @@
|
||||
/*
|
||||
** 2006 July 10
|
||||
**
|
||||
** The author disclaims copyright to this source code.
|
||||
**
|
||||
*************************************************************************
|
||||
** Defines the interface to tokenizers used by fulltext-search. There
|
||||
** are three basic components:
|
||||
**
|
||||
** sqlite3_tokenizer_module is a singleton defining the tokenizer
|
||||
** interface functions. This is essentially the class structure for
|
||||
** tokenizers.
|
||||
**
|
||||
** sqlite3_tokenizer is used to define a particular tokenizer, perhaps
|
||||
** including customization information defined at creation time.
|
||||
**
|
||||
** sqlite3_tokenizer_cursor is generated by a tokenizer to generate
|
||||
** tokens from a particular input.
|
||||
*/
|
||||
#ifndef _FTS3_TOKENIZER_H_
|
||||
#define _FTS3_TOKENIZER_H_
|
||||
|
||||
/* TODO(shess) Only used for SQLITE_OK and SQLITE_DONE at this time.
|
||||
** If tokenizers are to be allowed to call sqlite3_*() functions, then
|
||||
** we will need a way to register the API consistently.
|
||||
*/
|
||||
#include "sqlite3.h"
|
||||
|
||||
/*
|
||||
** Structures used by the tokenizer interface. When a new tokenizer
|
||||
** implementation is registered, the caller provides a pointer to
|
||||
** an sqlite3_tokenizer_module containing pointers to the callback
|
||||
** functions that make up an implementation.
|
||||
**
|
||||
** When an fts3 table is created, it passes any arguments passed to
|
||||
** the tokenizer clause of the CREATE VIRTUAL TABLE statement to the
|
||||
** sqlite3_tokenizer_module.xCreate() function of the requested tokenizer
|
||||
** implementation. The xCreate() function in turn returns an
|
||||
** sqlite3_tokenizer structure representing the specific tokenizer to
|
||||
** be used for the fts3 table (customized by the tokenizer clause arguments).
|
||||
**
|
||||
** To tokenize an input buffer, the sqlite3_tokenizer_module.xOpen()
|
||||
** method is called. It returns an sqlite3_tokenizer_cursor object
|
||||
** that may be used to tokenize a specific input buffer based on
|
||||
** the tokenization rules supplied by a specific sqlite3_tokenizer
|
||||
** object.
|
||||
*/
|
||||
typedef struct sqlite3_tokenizer_module sqlite3_tokenizer_module;
|
||||
typedef struct sqlite3_tokenizer sqlite3_tokenizer;
|
||||
typedef struct sqlite3_tokenizer_cursor sqlite3_tokenizer_cursor;
|
||||
|
||||
struct sqlite3_tokenizer_module {
|
||||
|
||||
/*
|
||||
** Structure version. Should always be set to 0 or 1.
|
||||
*/
|
||||
int iVersion;
|
||||
|
||||
/*
|
||||
** Create a new tokenizer. The values in the argv[] array are the
|
||||
** arguments passed to the "tokenizer" clause of the CREATE VIRTUAL
|
||||
** TABLE statement that created the fts3 table. For example, if
|
||||
** the following SQL is executed:
|
||||
**
|
||||
** CREATE .. USING fts3( ... , tokenizer <tokenizer-name> arg1 arg2)
|
||||
**
|
||||
** then argc is set to 2, and the argv[] array contains pointers
|
||||
** to the strings "arg1" and "arg2".
|
||||
**
|
||||
** 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
|
||||
** this callback. The caller will do so.
|
||||
*/
|
||||
int (*xCreate)(
|
||||
int argc, /* Size of argv array */
|
||||
const char *const*argv, /* Tokenizer argument strings */
|
||||
sqlite3_tokenizer **ppTokenizer /* OUT: Created tokenizer */
|
||||
);
|
||||
|
||||
/*
|
||||
** Destroy an existing tokenizer. The fts3 module calls this method
|
||||
** exactly once for each successful call to xCreate().
|
||||
*/
|
||||
int (*xDestroy)(sqlite3_tokenizer *pTokenizer);
|
||||
|
||||
/*
|
||||
** Create a tokenizer cursor to tokenize an input buffer. The caller
|
||||
** is responsible for ensuring that the input buffer remains valid
|
||||
** until the cursor is closed (using the xClose() method).
|
||||
*/
|
||||
int (*xOpen)(
|
||||
sqlite3_tokenizer *pTokenizer, /* Tokenizer object */
|
||||
const char *pInput, int nBytes, /* Input buffer */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Created tokenizer cursor */
|
||||
);
|
||||
|
||||
/*
|
||||
** Destroy an existing tokenizer cursor. The fts3 module calls this
|
||||
** method exactly once for each successful call to xOpen().
|
||||
*/
|
||||
int (*xClose)(sqlite3_tokenizer_cursor *pCursor);
|
||||
|
||||
/*
|
||||
** Retrieve the next token from the tokenizer cursor pCursor. This
|
||||
** method should either return SQLITE_OK and set the values of the
|
||||
** "OUT" variables identified below, or SQLITE_DONE to indicate that
|
||||
** the end of the buffer has been reached, or an SQLite error code.
|
||||
**
|
||||
** *ppToken should be set to point at a buffer containing the
|
||||
** normalized version of the token (i.e. after any case-folding and/or
|
||||
** stemming has been performed). *pnBytes should be set to the length
|
||||
** of this buffer in bytes. The input text that generated the token is
|
||||
** identified by the byte offsets returned in *piStartOffset and
|
||||
** *piEndOffset. *piStartOffset should be set to the index of the first
|
||||
** byte of the token in the input buffer. *piEndOffset should be set
|
||||
** to the index of the first byte just past the end of the token in
|
||||
** the input buffer.
|
||||
**
|
||||
** The buffer *ppToken is set to point at is managed by the tokenizer
|
||||
** implementation. It is only required to be valid until the next call
|
||||
** to xNext() or xClose().
|
||||
*/
|
||||
/* TODO(shess) current implementation requires pInput to be
|
||||
** nul-terminated. This should either be fixed, or pInput/nBytes
|
||||
** should be converted to zInput.
|
||||
*/
|
||||
int (*xNext)(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Tokenizer cursor */
|
||||
const char **ppToken, int *pnBytes, /* OUT: Normalized text for token */
|
||||
int *piStartOffset, /* OUT: Byte offset of token in input buffer */
|
||||
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 {
|
||||
const sqlite3_tokenizer_module *pModule; /* The module for this tokenizer */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
struct sqlite3_tokenizer_cursor {
|
||||
sqlite3_tokenizer *pTokenizer; /* Tokenizer for this cursor. */
|
||||
/* Tokenizer implementations will typically add additional fields */
|
||||
};
|
||||
|
||||
int fts3_global_term_cnt(int iTerm, int iCol);
|
||||
int fts3_term_cnt(int iTerm, int iCol);
|
||||
|
||||
|
||||
#endif /* _FTS3_TOKENIZER_H_ */
|
||||
@@ -1,234 +0,0 @@
|
||||
/*
|
||||
** 2006 Oct 10
|
||||
**
|
||||
** 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 "simple" full-text-search tokenizer.
|
||||
*/
|
||||
|
||||
/*
|
||||
** The code in this file is only compiled if:
|
||||
**
|
||||
** * The FTS3 module is being built as an extension
|
||||
** (in which case SQLITE_CORE is not defined), or
|
||||
**
|
||||
** * The FTS3 module is being built into the core of
|
||||
** SQLite (in which case SQLITE_ENABLE_FTS3 is defined).
|
||||
*/
|
||||
#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"
|
||||
|
||||
typedef struct simple_tokenizer {
|
||||
sqlite3_tokenizer base;
|
||||
char delim[128]; /* flag ASCII delimiters */
|
||||
} simple_tokenizer;
|
||||
|
||||
typedef struct simple_tokenizer_cursor {
|
||||
sqlite3_tokenizer_cursor base;
|
||||
const char *pInput; /* input we are tokenizing */
|
||||
int nBytes; /* size of the input */
|
||||
int iOffset; /* current position in pInput */
|
||||
int iToken; /* index of next token to be returned */
|
||||
char *pToken; /* storage for current token */
|
||||
int nTokenAllocated; /* space allocated to zToken buffer */
|
||||
} simple_tokenizer_cursor;
|
||||
|
||||
|
||||
static int simpleDelim(simple_tokenizer *t, unsigned char c){
|
||||
return c<0x80 && t->delim[c];
|
||||
}
|
||||
static int fts3_isalnum(int x){
|
||||
return (x>='0' && x<='9') || (x>='A' && x<='Z') || (x>='a' && x<='z');
|
||||
}
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
*/
|
||||
static int simpleCreate(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
){
|
||||
simple_tokenizer *t;
|
||||
|
||||
t = (simple_tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
memset(t, 0, sizeof(*t));
|
||||
|
||||
/* TODO(shess) Delimiters need to remain the same from run to run,
|
||||
** else we need to reindex. One solution would be a meta-table to
|
||||
** track such information in the database, then we'd only want this
|
||||
** information on the initial create.
|
||||
*/
|
||||
if( argc>1 ){
|
||||
int i, n = (int)strlen(argv[1]);
|
||||
for(i=0; i<n; i++){
|
||||
unsigned char ch = argv[1][i];
|
||||
/* We explicitly don't support UTF-8 delimiters for now. */
|
||||
if( ch>=0x80 ){
|
||||
sqlite3_free(t);
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
t->delim[ch] = 1;
|
||||
}
|
||||
} else {
|
||||
/* Mark non-alphanumeric ASCII characters as delimiters */
|
||||
int i;
|
||||
for(i=1; i<0x80; i++){
|
||||
t->delim[i] = !fts3_isalnum(i) ? -1 : 0;
|
||||
}
|
||||
}
|
||||
|
||||
*ppTokenizer = &t->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
|
||||
sqlite3_free(pTokenizer);
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** 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 simpleOpen(
|
||||
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
|
||||
const char *pInput, int nBytes, /* String to be tokenized */
|
||||
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
|
||||
){
|
||||
simple_tokenizer_cursor *c;
|
||||
|
||||
UNUSED_PARAMETER(pTokenizer);
|
||||
|
||||
c = (simple_tokenizer_cursor *) sqlite3_malloc(sizeof(*c));
|
||||
if( c==NULL ) return SQLITE_NOMEM;
|
||||
|
||||
c->pInput = pInput;
|
||||
if( pInput==0 ){
|
||||
c->nBytes = 0;
|
||||
}else if( nBytes<0 ){
|
||||
c->nBytes = (int)strlen(pInput);
|
||||
}else{
|
||||
c->nBytes = nBytes;
|
||||
}
|
||||
c->iOffset = 0; /* start tokenizing at the beginning */
|
||||
c->iToken = 0;
|
||||
c->pToken = NULL; /* no space allocated, yet. */
|
||||
c->nTokenAllocated = 0;
|
||||
|
||||
*ppCursor = &c->base;
|
||||
return SQLITE_OK;
|
||||
}
|
||||
|
||||
/*
|
||||
** Close a tokenization cursor previously opened by a call to
|
||||
** simpleOpen() above.
|
||||
*/
|
||||
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
sqlite3_free(c->pToken);
|
||||
sqlite3_free(c);
|
||||
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 simpleNext(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
|
||||
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 */
|
||||
){
|
||||
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
|
||||
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
|
||||
unsigned char *p = (unsigned char *)c->pInput;
|
||||
|
||||
while( c->iOffset<c->nBytes ){
|
||||
int iStartOffset;
|
||||
|
||||
/* Scan past delimiter characters */
|
||||
while( c->iOffset<c->nBytes && simpleDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
/* Count non-delimiter characters. */
|
||||
iStartOffset = c->iOffset;
|
||||
while( c->iOffset<c->nBytes && !simpleDelim(t, p[c->iOffset]) ){
|
||||
c->iOffset++;
|
||||
}
|
||||
|
||||
if( c->iOffset>iStartOffset ){
|
||||
int i, n = c->iOffset-iStartOffset;
|
||||
if( n>c->nTokenAllocated ){
|
||||
char *pNew;
|
||||
c->nTokenAllocated = n+20;
|
||||
pNew = sqlite3_realloc(c->pToken, c->nTokenAllocated);
|
||||
if( !pNew ) return SQLITE_NOMEM;
|
||||
c->pToken = pNew;
|
||||
}
|
||||
for(i=0; i<n; i++){
|
||||
/* TODO(shess) This needs expansion to handle UTF-8
|
||||
** case-insensitivity.
|
||||
*/
|
||||
unsigned char ch = p[iStartOffset+i];
|
||||
c->pToken[i] = (char)((ch>='A' && ch<='Z') ? ch-'A'+'a' : ch);
|
||||
}
|
||||
*ppToken = c->pToken;
|
||||
*pnBytes = n;
|
||||
*piStartOffset = iStartOffset;
|
||||
*piEndOffset = c->iOffset;
|
||||
*piPosition = c->iToken++;
|
||||
|
||||
return SQLITE_OK;
|
||||
}
|
||||
}
|
||||
return SQLITE_DONE;
|
||||
}
|
||||
|
||||
/*
|
||||
** The set of routines that implement the simple tokenizer
|
||||
*/
|
||||
static const sqlite3_tokenizer_module simpleTokenizerModule = {
|
||||
0,
|
||||
simpleCreate,
|
||||
simpleDestroy,
|
||||
simpleOpen,
|
||||
simpleClose,
|
||||
simpleNext,
|
||||
0,
|
||||
};
|
||||
|
||||
/*
|
||||
** Allocate a new simple tokenizer. Return a pointer to the new
|
||||
** tokenizer in *ppModule
|
||||
*/
|
||||
void sqlite3Fts3SimpleTokenizerModule(
|
||||
sqlite3_tokenizer_module const**ppModule
|
||||
){
|
||||
*ppModule = &simpleTokenizerModule;
|
||||
}
|
||||
|
||||
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|
||||
@@ -1,393 +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 bRemoveDiacritic;
|
||||
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];
|
||||
int iCode;
|
||||
int nEntry = 0;
|
||||
|
||||
assert( bAlnum==0 || bAlnum==1 );
|
||||
|
||||
while( z<zTerm ){
|
||||
READ_UTF8(z, zTerm, iCode);
|
||||
assert( (sqlite3FtsUnicodeIsalnum(iCode) & 0xFFFFFFFE)==0 );
|
||||
if( sqlite3FtsUnicodeIsalnum(iCode)!=bAlnum
|
||||
&& sqlite3FtsUnicodeIsdiacritic(iCode)==0
|
||||
){
|
||||
nEntry++;
|
||||
}
|
||||
}
|
||||
|
||||
if( nEntry ){
|
||||
int *aNew; /* New aiException[] array */
|
||||
int nNew; /* Number of valid entries in array aNew[] */
|
||||
|
||||
aNew = sqlite3_realloc(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(iCode)!=bAlnum
|
||||
&& sqlite3FtsUnicodeIsdiacritic(iCode)==0
|
||||
){
|
||||
int i, j;
|
||||
for(i=0; i<nNew && aNew[i]<iCode; i++);
|
||||
for(j=nNew; j>i; j--) aNew[j] = aNew[j-1];
|
||||
aNew[i] = 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->bRemoveDiacritic = 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->bRemoveDiacritic = 1;
|
||||
}
|
||||
else if( n==19 && memcmp("remove_diacritics=0", z, 19)==0 ){
|
||||
pNew->bRemoveDiacritic = 0;
|
||||
}
|
||||
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);
|
||||
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, 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_realloc(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(iCode, p->bRemoveDiacritic);
|
||||
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, iCode)
|
||||
|| sqlite3FtsUnicodeIsdiacritic(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 */
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user