walkero
/
pcre2
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Final preparations for 10.00-RC1

This commit is contained in:
Philip.Hazel 2014-11-24 15:31:28 +00:00
parent 91f2e97474
commit 0acc416ed1
20 changed files with 454 additions and 428 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
ChangeLog
View File

@ -1,12 +1,12 @@
Change Log for PCRE2 Change Log for PCRE2
-------------------- --------------------
Version 10.0 xx-xxxx-2014 Version 10.00 24-November-2014
------------------------- ------------------------------
Version 10.0 is the first release of PCRE2, a revised API for the PCRE library. Version 10.00 is the first release of PCRE2, a revised API for the PCRE
Changes prior to 10.0 are logged in the ChangeLog file for the old API, up to library. Changes prior to 10.00 are logged in the ChangeLog file for the old
item 20 for release 8.36. API, up to item 20 for release 8.36.
The code of the library was heavily revised as part of the new API The code of the library was heavily revised as part of the new API
implementation. Details of each and every modification were not individually implementation. Details of each and every modification were not individually
@ -25,7 +25,7 @@ matched by that pattern.
4. For the benefit of those who use PCRE2 via some other application, that is, 4. For the benefit of those who use PCRE2 via some other application, that is,
not writing the function calls themselves, it is possible to check the PCRE2 not writing the function calls themselves, it is possible to check the PCRE2
version by matching a pattern such as /(?(VERSION>=10.0)yes|no)/ against a version by matching a pattern such as /(?(VERSION>=10)yes|no)/ against a
string such as "yesno". string such as "yesno".
5. There are case-equivalent Unicode characters whose encodings use different 5. There are case-equivalent Unicode characters whose encodings use different
@ -46,14 +46,15 @@ characters, for example: /(?:(?=.)|(?<!x))a/.
7. When an (*ACCEPT) is triggered inside capturing parentheses, it arranges for 7. When an (*ACCEPT) is triggered inside capturing parentheses, it arranges for
those parentheses to be closed with whatever has been captured so far. However, those parentheses to be closed with whatever has been captured so far. However,
it was failing to mark any other groups between the hightest capture so far and it was failing to mark any other groups between the highest capture so far and
the currrent group as "unset". Thus, the ovector for those groups contained the currrent group as "unset". Thus, the ovector for those groups contained
whatever was previously there. An example is the pattern /(x)|((*ACCEPT))/ when whatever was previously there. An example is the pattern /(x)|((*ACCEPT))/ when
matched against "abcd". matched against "abcd".
8. The pcre2_substitute() function has been implemented. 8. The pcre2_substitute() function has been implemented.
9. If an assertion condition was quantified with a minimum of zero (an odd 9. If an assertion used as a condition was quantified with a minimum of zero
thing to do, but it happened), SIGSEGV or other misbehaviour could occur. (an odd thing to do, but it happened), SIGSEGV or other misbehaviour could
occur.
**** ****

50
Makefile.am
View File

@ -375,28 +375,34 @@ CLEANFILES += src/pcre2_chartables.c
# when pcre2_jit_compile.c is processed, so they must be distributed. # when pcre2_jit_compile.c is processed, so they must be distributed.
EXTRA_DIST += \ EXTRA_DIST += \
sljit/sljitConfig.h \ src/sljit/sljitConfig.h \
sljit/sljitConfigInternal.h \ src/sljit/sljitConfigInternal.h \
sljit/sljitExecAllocator.c \ src/sljit/sljitExecAllocator.c \
sljit/sljitLir.c \ src/sljit/sljitLir.c \
sljit/sljitLir.h \ src/sljit/sljitLir.h \
sljit/sljitNativeARM_32.c \ src/sljit/sljitNativeARM_32.c \
sljit/sljitNativeARM_64.c \ src/sljit/sljitNativeARM_64.c \
sljit/sljitNativeARM_T2_32.c \ src/sljit/sljitNativeARM_T2_32.c \
sljit/sljitNativeMIPS_32.c \ src/sljit/sljitNativeMIPS_32.c \
sljit/sljitNativeMIPS_64.c \ src/sljit/sljitNativeMIPS_64.c \
sljit/sljitNativeMIPS_common.c \ src/sljit/sljitNativeMIPS_common.c \
sljit/sljitNativePPC_32.c \ src/sljit/sljitNativePPC_32.c \
sljit/sljitNativePPC_64.c \ src/sljit/sljitNativePPC_64.c \
sljit/sljitNativePPC_common.c \ src/sljit/sljitNativePPC_common.c \
sljit/sljitNativeSPARC_32.c \ src/sljit/sljitNativeSPARC_32.c \
sljit/sljitNativeSPARC_common.c \ src/sljit/sljitNativeSPARC_common.c \
sljit/sljitNativeTILEGX-encoder.c \ src/sljit/sljitNativeTILEGX-encoder.c \
sljit/sljitNativeTILEGX_64.c \ src/sljit/sljitNativeTILEGX_64.c \
sljit/sljitNativeX86_32.c \ src/sljit/sljitNativeX86_32.c \
sljit/sljitNativeX86_64.c \ src/sljit/sljitNativeX86_64.c \
sljit/sljitNativeX86_common.c \ src/sljit/sljitNativeX86_common.c \
sljit/sljitUtils.c src/sljit/sljitUtils.c
# Some of the JIT sources are also in separate files that are #included.
EXTRA_DIST += \
src/pcre2_jit_match.c \
src/pcre2_jit_misc.c
if WITH_PCRE2_8 if WITH_PCRE2_8
libpcre2_8_la_LDFLAGS = $(EXTRA_LIBPCRE2_8_LDFLAGS) libpcre2_8_la_LDFLAGS = $(EXTRA_LIBPCRE2_8_LDFLAGS)

12
NEWS
View File

@ -1,11 +1,13 @@
News about PCRE2 releases News about PCRE2 releases
------------------------- -------------------------
Version 10.0 xx-xxxx-2014 Version 10.00 24-November-2014
------------------------- ------------------------------
Version 10.0 is the first release of PCRE2, a revised API for the PCRE library. Version 10.00 is the first release of PCRE2, a revised API for the PCRE
Changes prior to 10.0 are logged in the ChangeLog file for the old API, up to library. Changes prior to 10.00 are logged in the ChangeLog file for the old
item 20 for release 8.36. API, up to item 20 for release 8.36. New programs are recommended to use the
new library. Programs that use the original (PCRE1) API will need changing
before linking with the new library.
**** ****

72
README
View File

@ -5,11 +5,9 @@ PCRE2 is a re-implementation of the original PCRE library with an entirely new
API. The latest release of PCRE2 is always available in three alternative API. The latest release of PCRE2 is always available in three alternative
formats from: formats from:
FIXME: THIS WILL NOT BE THE CASE UNTIL THERE IS A FORMAL RELEASE. ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.gz
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.tar.gz ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.zip
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.zip
There is a mailing list for discussion about the development of PCRE (both the There is a mailing list for discussion about the development of PCRE (both the
original and new APIs) at pcre-dev@exim.org. You can access the archives and original and new APIs) at pcre-dev@exim.org. You can access the archives and
@ -46,7 +44,7 @@ there as yet no C++ wrappers.
The distribution does contain a set of C wrapper functions for the 8-bit The distribution does contain a set of C wrapper functions for the 8-bit
library that are based on the POSIX regular expression API (see the pcre2posix library that are based on the POSIX regular expression API (see the pcre2posix
man page). These end up in the library called libpcre2posix. Note that this man page). These can be found in a library called libpcre2posix. Note that this
just provides a POSIX calling interface to PCRE2; the regular expressions just provides a POSIX calling interface to PCRE2; the regular expressions
themselves still follow Perl syntax and semantics. The POSIX API is restricted, themselves still follow Perl syntax and semantics. The POSIX API is restricted,
and does not give full access to all of PCRE2's facilities. and does not give full access to all of PCRE2's facilities.
@ -72,7 +70,7 @@ new names.
Documentation for PCRE2 Documentation for PCRE2
---------------------- -----------------------
If you install PCRE2 in the normal way on a Unix-like system, you will end up If you install PCRE2 in the normal way on a Unix-like system, you will end up
with a set of man pages whose names all start with "pcre2". The one that is with a set of man pages whose names all start with "pcre2". The one that is
@ -95,7 +93,7 @@ PCRE2 documentation is supplied in two other forms:
Building PCRE2 on non-Unix-like systems Building PCRE2 on non-Unix-like systems
-------------------------------------- ---------------------------------------
For a non-Unix-like system, please read the comments in the file For a non-Unix-like system, please read the comments in the file
NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and
@ -112,7 +110,7 @@ library, because it uses only Standard C functions.
Building PCRE2 without using autotools Building PCRE2 without using autotools
------------------------------------- --------------------------------------
The use of autotools (in particular, libtool) is problematic in some The use of autotools (in particular, libtool) is problematic in some
environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
@ -120,7 +118,7 @@ file for ways of building PCRE2 without using autotools.
Building PCRE2 using autotools Building PCRE2 using autotools
----------------------------- ------------------------------
The following instructions assume the use of the widely used "configure; make; The following instructions assume the use of the widely used "configure; make;
make install" (autotools) process. make install" (autotools) process.
@ -166,15 +164,15 @@ library. They are also documented in the pcre2build man page.
. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to . By default, only the 8-bit library is built. If you add --enable-pcre2-16 to
the "configure" command, the 16-bit library is also built. If you add the "configure" command, the 16-bit library is also built. If you add
--enable-pcre2-32 to the "configure" command, the 32-bit library is also built. --enable-pcre2-32 to the "configure" command, the 32-bit library is also
If you want only the 16-bit or 32-bit library, use --disable-pcre2-8 to disable built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8
building the 8-bit library. to disable building the 8-bit library.
. If you want to include support for just-in-time compiling, which can give . If you want to include support for just-in-time compiling, which can give
large performance improvements on certain platforms, add --enable-jit to the large performance improvements on certain platforms, add --enable-jit to the
"configure" command. This support is available only for certain hardware "configure" command. This support is available only for certain hardware
architectures. If you try to enable it on an unsupported architecture, there architectures. If you try to enable it on an unsupported architecture, there
will be a compile time error. FIXME: NOT YET IMPLEMENTED. will be a compile time error.
. When JIT support is enabled, pcre2grep automatically makes use of it, unless . When JIT support is enabled, pcre2grep automatically makes use of it, unless
you add --disable-pcre2grep-jit to the "configure" command. you add --disable-pcre2grep-jit to the "configure" command.
@ -196,13 +194,13 @@ library. They are also documented in the pcre2build man page.
\P, \p, and \X sequences that recognize Unicode character properties. \P, \p, and \X sequences that recognize Unicode character properties.
However, only the basic two-letter properties such as Lu are supported. However, only the basic two-letter properties such as Lu are supported.
. You can build PCRE2 to recognize either CR or LF or the sequence CRLF or any . You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
of the preceding, or any of the Unicode newline sequences as indicating the of the preceding, or any of the Unicode newline sequences, as indicating the
end of a line. Whatever you specify at build time is the default; the caller end of a line. Whatever you specify at build time is the default; the caller
of PCRE2 can change the selection at run time. The default newline indicator of PCRE2 can change the selection at run time. The default newline indicator
is a single LF character (the Unix standard). You can specify the default is a single LF character (the Unix standard). You can specify the default
newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf newline indicator by adding --enable-newline-is-cr, --enable-newline-is-lf,
or --enable-newline-is-crlf or --enable-newline-is-anycrlf or --enable-newline-is-crlf, --enable-newline-is-anycrlf, or
--enable-newline-is-any to the "configure" command, respectively. --enable-newline-is-any to the "configure" command, respectively.
If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of
@ -251,8 +249,9 @@ library. They are also documented in the pcre2build man page.
command. PCRE2 then uses three bytes instead of two for offsets to different command. PCRE2 then uses three bytes instead of two for offsets to different
parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is
the same as --with-link-size=4, which (in both libraries) uses four-byte the same as --with-link-size=4, which (in both libraries) uses four-byte
offsets. Increasing the internal link size reduces performance. In the 32-bit offsets. Increasing the internal link size reduces performance in the 8-bit
library, the link size setting is ignored, as 4-byte offsets are always used. and 16-bit libraries. In the 32-bit library, the link size setting is
ignored, as 4-byte offsets are always used.
. You can build PCRE2 so that its internal match() function that is called from . You can build PCRE2 so that its internal match() function that is called from
pcre2_match() does not call itself recursively. Instead, it uses memory pcre2_match() does not call itself recursively. Instead, it uses memory
@ -376,12 +375,13 @@ contains compiler output from tests that "configure" runs.
Once "configure" has run, you can run "make". This builds whichever of the Once "configure" has run, you can run "make". This builds whichever of the
libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test
program called pcre2test. If you enabled JIT support with --enable-jit, another program called pcre2test. If you enabled JIT support with --enable-jit, another
test program called pcre2_jit_test is built as well. FIXME: still to be test program called pcre2_jit_test is built as well. If the 8-bit library is
implemented. If the 8-bit library is built, libpcre2-posix and the pcre2grep built, libpcre2-posix and the pcre2grep command are also built. Running
command are also built. "make" with the -j option may speed up compilation on multiprocessor systems.
The command "make check" runs all the appropriate tests. Details of the PCRE2 The command "make check" runs all the appropriate tests. Details of the PCRE2
tests are given below in a separate section of this document. tests are given below in a separate section of this document. The -j option of
"make" can also be used when running the tests.
You can use "make install" to install PCRE2 into live directories on your You can use "make install" to install PCRE2 into live directories on your
system. The following are installed (file names are all relative to the system. The following are installed (file names are all relative to the
@ -528,7 +528,7 @@ Testing PCRE2
To test the basic PCRE2 library on a Unix-like system, run the RunTest script. To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the options of the There is another script called RunGrepTest that tests the options of the
pcre2grep command. When JIT support is enabled, another test program called pcre2grep command. When JIT support is enabled, a third test program called
pcre2_jit_test is built. Both the scripts and all the program tests are run if pcre2_jit_test is built. Both the scripts and all the program tests are run if
you obey "make check". For other environments, see the instructions in you obey "make check". For other environments, see the instructions in
NON-AUTOTOOLS-BUILD. NON-AUTOTOOLS-BUILD.
@ -709,7 +709,6 @@ The distribution should contain the files listed below.
src/pcre2_context.c ) src/pcre2_context.c )
src/pcre2_dfa_match.c ) src/pcre2_dfa_match.c )
src/pcre2_error.c ) src/pcre2_error.c )
src/pcre2_exec.c )
src/pcre2_jit_compile.c ) src/pcre2_jit_compile.c )
src/pcre2_jit_match.c ) sources for the functions in the library, src/pcre2_jit_match.c ) sources for the functions in the library,
src/pcre2_jit_misc.c ) and some internal functions that they use src/pcre2_jit_misc.c ) and some internal functions that they use
@ -721,6 +720,7 @@ The distribution should contain the files listed below.
src/pcre2_pattern_info.c ) src/pcre2_pattern_info.c )
src/pcre2_string_utils.c ) src/pcre2_string_utils.c )
src/pcre2_study.c ) src/pcre2_study.c )
src/pcre2_substitute.c )
src/pcre2_substring.c ) src/pcre2_substring.c )
src/pcre2_tables.c ) src/pcre2_tables.c )
src/pcre2_ucd.c ) src/pcre2_ucd.c )
@ -736,13 +736,15 @@ The distribution should contain the files listed below.
src/pcre2_intmodedep.h a mode-specific internal header src/pcre2_intmodedep.h a mode-specific internal header
src/pcre2_ucp.h header for Unicode property handling src/pcre2_ucp.h header for Unicode property handling
sljit/* 16 files that make up the JIT compiler FIXME sljit/* source files for the JIT compiler
(B) Source files for programs that use PCRE2: (B) Source files for programs that use PCRE2:
src/pcre2demo.c simple demonstration of coding calls to PCRE2 src/pcre2demo.c simple demonstration of coding calls to PCRE2
src/pcre2grep.c source of a grep utility that uses PCRE2 src/pcre2grep.c source of a grep utility that uses PCRE2
src/pcre2test.c comprehensive test program src/pcre2test.c comprehensive test program
src/pcre2_printint.c part of pcre2test
src/pcre2_jit_test.c JIT test program
(C) Auxiliary files: (C) Auxiliary files:
@ -790,7 +792,6 @@ The distribution should contain the files listed below.
mkinstalldirs script for making install directories mkinstalldirs script for making install directories
perltest.sh Script for running a Perl test program perltest.sh Script for running a Perl test program
pcre2-config.in source of script which retains PCRE2 information pcre2-config.in source of script which retains PCRE2 information
pcre2_jit_test.c test program for the JIT compiler
testdata/testinput* test data for main library tests testdata/testinput* test data for main library tests
testdata/testoutput* expected test results testdata/testoutput* expected test results
testdata/grep* input and output for pcre2grep tests testdata/grep* input and output for pcre2grep tests
@ -805,25 +806,14 @@ The distribution should contain the files listed below.
CMakeLists.txt CMakeLists.txt
config-cmake.h.in config-cmake.h.in
(E) Auxiliary files for VPASCAL FIXME FIXME (E) Auxiliary files for building PCRE2 "by hand"
makevp.bat
makevp_c.txt
makevp_l.txt
pcre2gexp.pas
(F) Auxiliary files for building PCRE2 "by hand"
pcre2.h.generic ) a version of the public PCRE2 header file pcre2.h.generic ) a version of the public PCRE2 header file
) for use in non-"configure" environments ) for use in non-"configure" environments
config.h.generic ) a version of config.h for use in non-"configure" config.h.generic ) a version of config.h for use in non-"configure"
) environments ) environments
(F) Miscellaneous
RunTest.bat a script for running tests under Windows FIXME
Philip Hazel Philip Hazel
Email local part: ph10 Email local part: ph10
Email domain: cam.ac.uk Email domain: cam.ac.uk
Last updated: 03 November 2014 Last updated: 24 November 2014

4
configure.ac
View File

@ -10,8 +10,8 @@ dnl be defined as -RC2, for example. For real releases, it should be empty.
m4_define(pcre2_major, [10]) m4_define(pcre2_major, [10])
m4_define(pcre2_minor, [00]) m4_define(pcre2_minor, [00])
m4_define(pcre2_prerelease, [-DEV]) m4_define(pcre2_prerelease, [-RC1])
m4_define(pcre2_date, [2014-99-99]) m4_define(pcre2_date, [2014-11-24])
# NOTE: The CMakeLists.txt file searches for the above variables in the first # NOTE: The CMakeLists.txt file searches for the above variables in the first
# 50 lines of this file. Please update that if the variables above are moved. # 50 lines of this file. Please update that if the variables above are moved.

72
doc/html/README.txt
View File

@ -5,11 +5,9 @@ PCRE2 is a re-implementation of the original PCRE library with an entirely new
API. The latest release of PCRE2 is always available in three alternative API. The latest release of PCRE2 is always available in three alternative
formats from: formats from:
FIXME: THIS WILL NOT BE THE CASE UNTIL THERE IS A FORMAL RELEASE. ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.gz
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.tar.gz ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.zip
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre2/pcre2-xxx.zip
There is a mailing list for discussion about the development of PCRE (both the There is a mailing list for discussion about the development of PCRE (both the
original and new APIs) at pcre-dev@exim.org. You can access the archives and original and new APIs) at pcre-dev@exim.org. You can access the archives and
@ -46,7 +44,7 @@ there as yet no C++ wrappers.
The distribution does contain a set of C wrapper functions for the 8-bit The distribution does contain a set of C wrapper functions for the 8-bit
library that are based on the POSIX regular expression API (see the pcre2posix library that are based on the POSIX regular expression API (see the pcre2posix
man page). These end up in the library called libpcre2posix. Note that this man page). These can be found in a library called libpcre2posix. Note that this
just provides a POSIX calling interface to PCRE2; the regular expressions just provides a POSIX calling interface to PCRE2; the regular expressions
themselves still follow Perl syntax and semantics. The POSIX API is restricted, themselves still follow Perl syntax and semantics. The POSIX API is restricted,
and does not give full access to all of PCRE2's facilities. and does not give full access to all of PCRE2's facilities.
@ -72,7 +70,7 @@ new names.
Documentation for PCRE2 Documentation for PCRE2
---------------------- -----------------------
If you install PCRE2 in the normal way on a Unix-like system, you will end up If you install PCRE2 in the normal way on a Unix-like system, you will end up
with a set of man pages whose names all start with "pcre2". The one that is with a set of man pages whose names all start with "pcre2". The one that is
@ -95,7 +93,7 @@ PCRE2 documentation is supplied in two other forms:
Building PCRE2 on non-Unix-like systems Building PCRE2 on non-Unix-like systems
-------------------------------------- ---------------------------------------
For a non-Unix-like system, please read the comments in the file For a non-Unix-like system, please read the comments in the file
NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and
@ -112,7 +110,7 @@ library, because it uses only Standard C functions.
Building PCRE2 without using autotools Building PCRE2 without using autotools
------------------------------------- --------------------------------------
The use of autotools (in particular, libtool) is problematic in some The use of autotools (in particular, libtool) is problematic in some
environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
@ -120,7 +118,7 @@ file for ways of building PCRE2 without using autotools.
Building PCRE2 using autotools Building PCRE2 using autotools
----------------------------- ------------------------------
The following instructions assume the use of the widely used "configure; make; The following instructions assume the use of the widely used "configure; make;
make install" (autotools) process. make install" (autotools) process.
@ -166,15 +164,15 @@ library. They are also documented in the pcre2build man page.
. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to . By default, only the 8-bit library is built. If you add --enable-pcre2-16 to
the "configure" command, the 16-bit library is also built. If you add the "configure" command, the 16-bit library is also built. If you add
--enable-pcre2-32 to the "configure" command, the 32-bit library is also built. --enable-pcre2-32 to the "configure" command, the 32-bit library is also
If you want only the 16-bit or 32-bit library, use --disable-pcre2-8 to disable built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8
building the 8-bit library. to disable building the 8-bit library.
. If you want to include support for just-in-time compiling, which can give . If you want to include support for just-in-time compiling, which can give
large performance improvements on certain platforms, add --enable-jit to the large performance improvements on certain platforms, add --enable-jit to the
"configure" command. This support is available only for certain hardware "configure" command. This support is available only for certain hardware
architectures. If you try to enable it on an unsupported architecture, there architectures. If you try to enable it on an unsupported architecture, there
will be a compile time error. FIXME: NOT YET IMPLEMENTED. will be a compile time error.
. When JIT support is enabled, pcre2grep automatically makes use of it, unless . When JIT support is enabled, pcre2grep automatically makes use of it, unless
you add --disable-pcre2grep-jit to the "configure" command. you add --disable-pcre2grep-jit to the "configure" command.
@ -196,13 +194,13 @@ library. They are also documented in the pcre2build man page.
\P, \p, and \X sequences that recognize Unicode character properties. \P, \p, and \X sequences that recognize Unicode character properties.
However, only the basic two-letter properties such as Lu are supported. However, only the basic two-letter properties such as Lu are supported.
. You can build PCRE2 to recognize either CR or LF or the sequence CRLF or any . You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
of the preceding, or any of the Unicode newline sequences as indicating the of the preceding, or any of the Unicode newline sequences, as indicating the
end of a line. Whatever you specify at build time is the default; the caller end of a line. Whatever you specify at build time is the default; the caller
of PCRE2 can change the selection at run time. The default newline indicator of PCRE2 can change the selection at run time. The default newline indicator
is a single LF character (the Unix standard). You can specify the default is a single LF character (the Unix standard). You can specify the default
newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf newline indicator by adding --enable-newline-is-cr, --enable-newline-is-lf,
or --enable-newline-is-crlf or --enable-newline-is-anycrlf or --enable-newline-is-crlf, --enable-newline-is-anycrlf, or
--enable-newline-is-any to the "configure" command, respectively. --enable-newline-is-any to the "configure" command, respectively.
If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of
@ -251,8 +249,9 @@ library. They are also documented in the pcre2build man page.
command. PCRE2 then uses three bytes instead of two for offsets to different command. PCRE2 then uses three bytes instead of two for offsets to different
parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is
the same as --with-link-size=4, which (in both libraries) uses four-byte the same as --with-link-size=4, which (in both libraries) uses four-byte
offsets. Increasing the internal link size reduces performance. In the 32-bit offsets. Increasing the internal link size reduces performance in the 8-bit
library, the link size setting is ignored, as 4-byte offsets are always used. and 16-bit libraries. In the 32-bit library, the link size setting is
ignored, as 4-byte offsets are always used.
. You can build PCRE2 so that its internal match() function that is called from . You can build PCRE2 so that its internal match() function that is called from
pcre2_match() does not call itself recursively. Instead, it uses memory pcre2_match() does not call itself recursively. Instead, it uses memory
@ -376,12 +375,13 @@ contains compiler output from tests that "configure" runs.
Once "configure" has run, you can run "make". This builds whichever of the Once "configure" has run, you can run "make". This builds whichever of the
libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test
program called pcre2test. If you enabled JIT support with --enable-jit, another program called pcre2test. If you enabled JIT support with --enable-jit, another
test program called pcre2_jit_test is built as well. FIXME: still to be test program called pcre2_jit_test is built as well. If the 8-bit library is
implemented. If the 8-bit library is built, libpcre2-posix and the pcre2grep built, libpcre2-posix and the pcre2grep command are also built. Running
command are also built. "make" with the -j option may speed up compilation on multiprocessor systems.
The command "make check" runs all the appropriate tests. Details of the PCRE2 The command "make check" runs all the appropriate tests. Details of the PCRE2
tests are given below in a separate section of this document. tests are given below in a separate section of this document. The -j option of
"make" can also be used when running the tests.
You can use "make install" to install PCRE2 into live directories on your You can use "make install" to install PCRE2 into live directories on your
system. The following are installed (file names are all relative to the system. The following are installed (file names are all relative to the
@ -528,7 +528,7 @@ Testing PCRE2
To test the basic PCRE2 library on a Unix-like system, run the RunTest script. To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the options of the There is another script called RunGrepTest that tests the options of the
pcre2grep command. When JIT support is enabled, another test program called pcre2grep command. When JIT support is enabled, a third test program called
pcre2_jit_test is built. Both the scripts and all the program tests are run if pcre2_jit_test is built. Both the scripts and all the program tests are run if
you obey "make check". For other environments, see the instructions in you obey "make check". For other environments, see the instructions in
NON-AUTOTOOLS-BUILD. NON-AUTOTOOLS-BUILD.
@ -709,7 +709,6 @@ The distribution should contain the files listed below.
src/pcre2_context.c ) src/pcre2_context.c )
src/pcre2_dfa_match.c ) src/pcre2_dfa_match.c )
src/pcre2_error.c ) src/pcre2_error.c )
src/pcre2_exec.c )
src/pcre2_jit_compile.c ) src/pcre2_jit_compile.c )
src/pcre2_jit_match.c ) sources for the functions in the library, src/pcre2_jit_match.c ) sources for the functions in the library,
src/pcre2_jit_misc.c ) and some internal functions that they use src/pcre2_jit_misc.c ) and some internal functions that they use
@ -721,6 +720,7 @@ The distribution should contain the files listed below.
src/pcre2_pattern_info.c ) src/pcre2_pattern_info.c )
src/pcre2_string_utils.c ) src/pcre2_string_utils.c )
src/pcre2_study.c ) src/pcre2_study.c )
src/pcre2_substitute.c )
src/pcre2_substring.c ) src/pcre2_substring.c )
src/pcre2_tables.c ) src/pcre2_tables.c )
src/pcre2_ucd.c ) src/pcre2_ucd.c )
@ -736,13 +736,15 @@ The distribution should contain the files listed below.
src/pcre2_intmodedep.h a mode-specific internal header src/pcre2_intmodedep.h a mode-specific internal header
src/pcre2_ucp.h header for Unicode property handling src/pcre2_ucp.h header for Unicode property handling
sljit/* 16 files that make up the JIT compiler FIXME sljit/* source files for the JIT compiler
(B) Source files for programs that use PCRE2: (B) Source files for programs that use PCRE2:
src/pcre2demo.c simple demonstration of coding calls to PCRE2 src/pcre2demo.c simple demonstration of coding calls to PCRE2
src/pcre2grep.c source of a grep utility that uses PCRE2 src/pcre2grep.c source of a grep utility that uses PCRE2
src/pcre2test.c comprehensive test program src/pcre2test.c comprehensive test program
src/pcre2_printint.c part of pcre2test
src/pcre2_jit_test.c JIT test program
(C) Auxiliary files: (C) Auxiliary files:
@ -790,7 +792,6 @@ The distribution should contain the files listed below.
mkinstalldirs script for making install directories mkinstalldirs script for making install directories
perltest.sh Script for running a Perl test program perltest.sh Script for running a Perl test program
pcre2-config.in source of script which retains PCRE2 information pcre2-config.in source of script which retains PCRE2 information
pcre2_jit_test.c test program for the JIT compiler
testdata/testinput* test data for main library tests testdata/testinput* test data for main library tests
testdata/testoutput* expected test results testdata/testoutput* expected test results
testdata/grep* input and output for pcre2grep tests testdata/grep* input and output for pcre2grep tests
@ -805,25 +806,14 @@ The distribution should contain the files listed below.
CMakeLists.txt CMakeLists.txt
config-cmake.h.in config-cmake.h.in
(E) Auxiliary files for VPASCAL FIXME FIXME (E) Auxiliary files for building PCRE2 "by hand"
makevp.bat
makevp_c.txt
makevp_l.txt
pcre2gexp.pas
(F) Auxiliary files for building PCRE2 "by hand"
pcre2.h.generic ) a version of the public PCRE2 header file pcre2.h.generic ) a version of the public PCRE2 header file
) for use in non-"configure" environments ) for use in non-"configure" environments
config.h.generic ) a version of config.h for use in non-"configure" config.h.generic ) a version of config.h for use in non-"configure"
) environments ) environments
(F) Miscellaneous
RunTest.bat a script for running tests under Windows FIXME
Philip Hazel Philip Hazel
Email local part: ph10 Email local part: ph10
Email domain: cam.ac.uk Email domain: cam.ac.uk
Last updated: 03 November 2014 Last updated: 24 November 2014

8
doc/html/pcre2api.html
View File

@ -2074,6 +2074,12 @@ returned by <b>pcre2_get_startchar()</b>. For a non-partial match, this can be
different to the value of <i>ovector[0]</i> if the pattern contains the \K different to the value of <i>ovector[0]</i> if the pattern contains the \K
escape sequence. After a partial match, however, this value is always the same escape sequence. After a partial match, however, this value is always the same
as <i>ovector[0]</i> because \K does not affect the result of a partial match. as <i>ovector[0]</i> because \K does not affect the result of a partial match.
</P>
<P>
The <b>startchar</b> field is also used to return the offset of an invalid
UTF character when UTF checking fails. Details are given in the
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
page.
<a name="errorlist"></a></P> <a name="errorlist"></a></P>
<br><a name="SEC26" href="#TOC1">ERROR RETURNS FROM <b>pcre2_match()</b></a><br> <br><a name="SEC26" href="#TOC1">ERROR RETURNS FROM <b>pcre2_match()</b></a><br>
<P> <P>
@ -2658,7 +2664,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC36" href="#TOC1">REVISION</a><br> <br><a name="SEC36" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 21 November 2014 Last updated: 23 November 2014
<br> <br>
Copyright &copy; 1997-2014 University of Cambridge. Copyright &copy; 1997-2014 University of Cambridge.
<br> <br>

6
doc/html/pcre2partial.html
View File

@ -197,9 +197,9 @@ the string "dog" matched against the ungreedy pattern shown above:
<pre> <pre>
/dog(sbody)??/ /dog(sbody)??/
</pre> </pre>
Whereas the standard functions stop as soon as they find the complete match for Whereas the standard function stops as soon as it finds the complete match for
"dog", the DFA functions also find the partial match for "dogsbody", and so "dog", the DFA function also finds the partial match for "dogsbody", and so
return that when PCRE2_PARTIAL_HARD is set. returns that when PCRE2_PARTIAL_HARD is set.
</P> </P>
<br><a name="SEC4" href="#TOC1">PARTIAL MATCHING AND WORD BOUNDARIES</a><br> <br><a name="SEC4" href="#TOC1">PARTIAL MATCHING AND WORD BOUNDARIES</a><br>
<P> <P>

117
doc/html/pcre2test.html
View File

@ -244,7 +244,7 @@ input lines. Each set starts with a regular expression pattern, followed by any
number of subject lines to be matched against that pattern. In between sets of number of subject lines to be matched against that pattern. In between sets of
test data, command lines that begin with a hash (#) character may appear. This test data, command lines that begin with a hash (#) character may appear. This
file format, with some restrictions, can also be processed by the file format, with some restrictions, can also be processed by the
<b>perltest.pl</b> script that is distributed with PCRE2 as a means of checking <b>perltest.sh</b> script that is distributed with PCRE2 as a means of checking
that the behaviour of PCRE2 and Perl is the same. that the behaviour of PCRE2 and Perl is the same.
</P> </P>
<P> <P>
@ -287,11 +287,11 @@ patterns. Modifiers on a pattern can change these settings.
#perltest #perltest
</pre> </pre>
The appearance of this line causes all subsequent modifier settings to be The appearance of this line causes all subsequent modifier settings to be
checked for compatibility with the <b>perltest.pl</b> script, which is used to checked for compatibility with the <b>perltest.sh</b> script, which is used to
confirm that Perl gives the same results as PCRE2. Also, apart from comment confirm that Perl gives the same results as PCRE2. Also, apart from comment
lines, none of the other command lines are permitted, because they and many lines, none of the other command lines are permitted, because they and many
of the modifiers are specific to <b>pcre2test</b>, and should not be used in of the modifiers are specific to <b>pcre2test</b>, and should not be used in
test files that are also processed by <b>perltest.pl</b>. The \fP#perltest\fB test files that are also processed by <b>perltest.sh</b>. The \fP#perltest\fB
command helps detect tests that are accidentally put in the wrong file. command helps detect tests that are accidentally put in the wrong file.
<pre> <pre>
#subject &#60;modifier-list&#62; #subject &#60;modifier-list&#62;
@ -307,7 +307,7 @@ for both patterns and subject lines, whereas others are valid for one or the
other only. Each modifier has a long name, for example "anchored", and some of other only. Each modifier has a long name, for example "anchored", and some of
them must be followed by an equals sign and a value, for example, "offset=12". them must be followed by an equals sign and a value, for example, "offset=12".
Modifiers that do not take values may be preceded by a minus sign to turn off a Modifiers that do not take values may be preceded by a minus sign to turn off a
previous default setting. previous setting.
</P> </P>
<P> <P>
A few of the more common modifiers can also be specified as single letters, for A few of the more common modifiers can also be specified as single letters, for
@ -376,7 +376,7 @@ encoding non-printing characters in a visible way:
\xhh hexadecimal byte (up to 2 hex digits) \xhh hexadecimal byte (up to 2 hex digits)
\x{hh...} hexadecimal character (any number of hex digits) \x{hh...} hexadecimal character (any number of hex digits)
</pre> </pre>
The use of \x{hh...} is not dependent on the use of the utf modifier on The use of \x{hh...} is not dependent on the use of the <b>utf</b> modifier on
the pattern. It is recognized always. There may be any number of hexadecimal the pattern. It is recognized always. There may be any number of hexadecimal
digits inside the braces; invalid values provoke error messages. digits inside the braces; invalid values provoke error messages.
</P> </P>
@ -411,7 +411,7 @@ is converted to "abcabcabcabc". This feature does not support nesting. To
include a closing square bracket in the characters, code it as \x5D. include a closing square bracket in the characters, code it as \x5D.
</P> </P>
<P> <P>
A backslash followed by an equals sign marke the end of the subject string and A backslash followed by an equals sign marks the end of the subject string and
the start of a modifier list. For example: the start of a modifier list. For example:
<pre> <pre>
abc\=notbol,notempty abc\=notbol,notempty
@ -503,8 +503,8 @@ is built, with the default default being Unicode.
</P> </P>
<P> <P>
The <b>newline</b> modifier specifies which characters are to be interpreted as The <b>newline</b> modifier specifies which characters are to be interpreted as
newlines, both in the pattern and (by default) in subject lines. The type must newlines, both in the pattern and in subject lines. The type must be one of CR,
be one of CR, LF, CRLF, ANYCRLF, or ANY. LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
</P> </P>
<br><b> <br><b>
Information about a pattern Information about a pattern
@ -522,8 +522,8 @@ regression tests can be used in different environments.
</P> </P>
<P> <P>
The <b>fullbincode</b> modifier, by contrast, <i>does</i> include length and The <b>fullbincode</b> modifier, by contrast, <i>does</i> include length and
offset values. This is used in a few special tests and is also useful for offset values. This is used in a few special tests that run only for specific
one-off tests. code unit widths and link sizes, and is also useful for one-off tests.
</P> </P>
<P> <P>
The <b>info</b> modifier requests information about the compiled pattern The <b>info</b> modifier requests information about the compiled pattern
@ -546,13 +546,14 @@ some typical examples:
Last code unit = 'c' (caseless) Last code unit = 'c' (caseless)
Subject length lower bound = 3 Subject length lower bound = 3
</pre> </pre>
"Compile options" are those specified to the compile function; "overall "Compile options" are those specified by modifiers; "overall options" have
options" have added options that are taken or deduced from the pattern. If both added options that are taken or deduced from the pattern. If both sets of
sets of options are the same, just a single "options" line is output. "First options are the same, just a single "options" line is output; if there are no
code unit" is where any match must start; if there is more than one they are options, the line is omitted. "First code unit" is where any match must start;
listed as "starting code units". "Last code unit" is the last literal code unit if there is more than one they are listed as "starting code units". "Last code
that must be present in any match. This is not necessarily the last character. unit" is the last literal code unit that must be present in any match. This is
These lines are omitted if no starting or ending code units are recorded. not necessarily the last character. These lines are omitted if no starting or
ending code units are recorded.
</P> </P>
<br><b> <br><b>
Specifying a pattern in hex Specifying a pattern in hex
@ -565,16 +566,16 @@ pairs. For example:
/ab 32 59/hex /ab 32 59/hex
</pre> </pre>
This feature is provided as a way of creating patterns that contain binary zero This feature is provided as a way of creating patterns that contain binary zero
characters. By default, <b>pcre2test</b> passes patterns as zero-terminated and other non-printing characters. By default, <b>pcre2test</b> passes patterns
strings to <b>pcre2_compile()</b>, giving the length as PCRE2_ZERO_TERMINATED. as zero-terminated strings to <b>pcre2_compile()</b>, giving the length as
However, for patterns specified in hexadecimal, the actual length of the PCRE2_ZERO_TERMINATED. However, for patterns specified in hexadecimal, the
pattern is passed. actual length of the pattern is passed.
</P> </P>
<br><b> <br><b>
JIT compilation JIT compilation
</b><br> </b><br>
<P> <P>
The <b>/jit</b> modifier may optionally be followed by and equals sign and a The <b>/jit</b> modifier may optionally be followed by an equals sign and a
number in the range 0 to 7: number in the range 0 to 7:
<pre> <pre>
0 disable JIT 0 disable JIT
@ -606,7 +607,7 @@ pattern shows whether JIT compilation was or was not successful. If
<b>jitverify</b> is specified without <b>jit</b>, jit=7 is assumed. If JIT <b>jitverify</b> is specified without <b>jit</b>, jit=7 is assumed. If JIT
compilation is successful when <b>jitverify</b> is set, the text "(JIT)" is compilation is successful when <b>jitverify</b> is set, the text "(JIT)" is
added to the first output line after a match or non match when JIT-compiled added to the first output line after a match or non match when JIT-compiled
code was actually used. code was actually used in the match.
</P> </P>
<br><b> <br><b>
Setting a locale Setting a locale
@ -689,8 +690,8 @@ be aborted.
Using alternative character tables Using alternative character tables
</b><br> </b><br>
<P> <P>
The <b>/tables</b> modifier must be followed by a single digit. It causes a The value specified for the <b>/tables</b> modifier must be one of the digits 0,
specific set of built-in character tables to be passed to 1, or 2. It causes a specific set of built-in character tables to be passed to
<b>pcre2_compile()</b>. This is used in the PCRE2 tests to check behaviour with <b>pcre2_compile()</b>. This is used in the PCRE2 tests to check behaviour with
different character tables. The digit specifies the tables as follows: different character tables. The digit specifies the tables as follows:
<pre> <pre>
@ -800,13 +801,13 @@ The effects of these modifiers are described in the following sections.
Showing more text Showing more text
</b><br> </b><br>
<P> <P>
The <b>aftertext</b> modifier requests that as well as outputting the substring The <b>aftertext</b> modifier requests that as well as outputting the part of
that matched the entire pattern, <b>pcre2test</b> should in addition output the the subject string that matched the entire pattern, <b>pcre2test</b> should in
remainder of the subject string. This is useful for tests where the subject addition output the remainder of the subject string. This is useful for tests
contains multiple copies of the same substring. The <b>allaftertext</b> modifier where the subject contains multiple copies of the same substring. The
requests the same action for captured substrings as well as the main matched <b>allaftertext</b> modifier requests the same action for captured substrings as
substring. In each case the remainder is output on the following line with a well as the main matched substring. In each case the remainder is output on the
plus character following the capture number. following line with a plus character following the capture number.
</P> </P>
<P> <P>
The <b>allusedtext</b> modifier requests that all the text that was consulted The <b>allusedtext</b> modifier requests that all the text that was consulted
@ -824,7 +825,8 @@ underneath them. Here is an example:
&#60;&#60;&#60; &#62;&#62;&#62; &#60;&#60;&#60; &#62;&#62;&#62;
</pre> </pre>
This shows that the matched string is "abc", with the preceding and following This shows that the matched string is "abc", with the preceding and following
strings "pqr" and "xyz" also consulted during the match. strings "pqr" and "xyz" having been consulted during the match (when processing
the assertions).
</P> </P>
<P> <P>
The <b>startchar</b> modifier requests that the starting character for the match The <b>startchar</b> modifier requests that the starting character for the match
@ -881,7 +883,7 @@ function is called again to search the remainder of the subject. The difference
between <b>global</b> and <b>altglobal</b> is that the former uses the between <b>global</b> and <b>altglobal</b> is that the former uses the
<i>start_offset</i> argument to <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b> <i>start_offset</i> argument to <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b>
to start searching at a new point within the entire string (which is what Perl to start searching at a new point within the entire string (which is what Perl
does), whereas the latter passes over a shortened substring. This makes a does), whereas the latter passes over a shortened subject. This makes a
difference to the matching process if the pattern begins with a lookbehind difference to the matching process if the pattern begins with a lookbehind
assertion (including \b or \B). assertion (including \b or \B).
</P> </P>
@ -893,7 +895,7 @@ fails, the start offset is advanced, and the normal match is retried. This
imitates the way Perl handles such cases when using the <b>/g</b> modifier or imitates the way Perl handles such cases when using the <b>/g</b> modifier or
the <b>split()</b> function. Normally, the start offset is advanced by one the <b>split()</b> function. Normally, the start offset is advanced by one
character, but if the newline convention recognizes CRLF as a newline, and the character, but if the newline convention recognizes CRLF as a newline, and the
current character is CR followed by LF, an advance of two is used. current character is CR followed by LF, an advance of two characters occurs.
</P> </P>
<br><b> <br><b>
Testing substring extraction functions Testing substring extraction functions
@ -906,9 +908,9 @@ for example:
<pre> <pre>
abcd\=copy=1,copy=3,get=G1 abcd\=copy=1,copy=3,get=G1
</pre> </pre>
If the <b>#subject</b> command is used to set default copy and get lists, these If the <b>#subject</b> command is used to set default copy and/or get lists,
can be unset by specifying a negative number for numbered groups and an empty these can be unset by specifying a negative number to cancel all numbered
name for named groups. groups and an empty name to cancel all named groups.
</P> </P>
<P> <P>
The <b>getall</b> modifier tests <b>pcre2_substring_list_get()</b>, which The <b>getall</b> modifier tests <b>pcre2_substring_list_get()</b>, which
@ -919,7 +921,8 @@ If the subject line is successfully matched, the substrings extracted by the
convenience functions are output with C, G, or L after the string number convenience functions are output with C, G, or L after the string number
instead of a colon. This is in addition to the normal full list. The string instead of a colon. This is in addition to the normal full list. The string
length (that is, the return from the extraction function) is given in length (that is, the return from the extraction function) is given in
parentheses after each substring. parentheses after each substring, followed by the name when the extraction was
by name.
</P> </P>
<br><b> <br><b>
Testing the substitution function Testing the substitution function
@ -1093,11 +1096,10 @@ characters before the actual match start if a lookbehind assertion, \K, \b,
or \B was involved.) or \B was involved.)
</P> </P>
<P> <P>
For any other return, <b>pcre2test</b> outputs the PCRE2 For any other return, <b>pcre2test</b> outputs the PCRE2 negative error number
negative error number and a short descriptive phrase. If the error is a failed and a short descriptive phrase. If the error is a failed UTF string check, the
UTF string check, the offset of the start of the failing character and the code unit offset of the start of the failing character is also output. Here is
reason code are also output. Here is an example of an interactive an example of an interactive <b>pcre2test</b> run.
<b>pcre2test</b> run.
<pre> <pre>
$ pcre2test $ pcre2test
PCRE2 version 9.00 2014-05-10 PCRE2 version 9.00 2014-05-10
@ -1110,10 +1112,10 @@ reason code are also output. Here is an example of an interactive
No match No match
</pre> </pre>
Unset capturing substrings that are not followed by one that is set are not Unset capturing substrings that are not followed by one that is set are not
returned by <b>pcre2_match()</b>, and are not shown by <b>pcre2test</b>. In the shown by <b>pcre2test</b> unless the <b>allcaptures</b> modifier is specified. In
following example, there are two capturing substrings, but when the first data the following example, there are two capturing substrings, but when the first
line is matched, the second, unset substring is not shown. An "internal" unset data line is matched, the second, unset substring is not shown. An "internal"
substring is shown as "&#60;unset&#62;", as for the second data line. unset substring is shown as "&#60;unset&#62;", as for the second data line.
<pre> <pre>
re&#62; /(a)|(b)/ re&#62; /(a)|(b)/
data&#62; a data&#62; a
@ -1149,8 +1151,8 @@ are output in sequence, like this:
1: pp 1: pp
</pre> </pre>
"No match" is output only if the first match attempt fails. Here is an example "No match" is output only if the first match attempt fails. Here is an example
of a failure message (the offset 4 that is specified by \&#62;4 is past the end of of a failure message (the offset 4 that is specified by the <b>offset</b>
the subject string): modifier is past the end of the subject string):
<pre> <pre>
re&#62; /xyz/ re&#62; /xyz/
data&#62; xyz\=offset=4 data&#62; xyz\=offset=4
@ -1175,12 +1177,13 @@ the subject where there is at least one match. For example:
1: tang 1: tang
2: tan 2: tan
</pre> </pre>
(Using the normal matching function on this data finds only "tang".) The Using the normal matching function on this data finds only "tang". The
longest matching string is always given first (and numbered zero). After a longest matching string is always given first (and numbered zero). After a
PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the
partially matching substring. (Note that this is the entire substring that was partially matching substring. Note that this is the entire substring that was
inspected during the partial match; it may include characters before the actual inspected during the partial match; it may include characters before the actual
match start if a lookbehind assertion, \K, \b, or \B was involved.) match start if a lookbehind assertion, \b, or \B was involved. (\K is not
supported for DFA matching.)
</P> </P>
<P> <P>
If global matching is requested, the search for further matches resumes If global matching is requested, the search for further matches resumes
@ -1217,9 +1220,9 @@ documentation.
</P> </P>
<br><a name="SEC16" href="#TOC1">CALLOUTS</a><br> <br><a name="SEC16" href="#TOC1">CALLOUTS</a><br>
<P> <P>
If the pattern contains any callout requests, <b>pcre2test</b>'s callout function If the pattern contains any callout requests, <b>pcre2test</b>'s callout
is called during matching. This works with both matching functions. By default, function is called during matching. This works with both matching functions. By
the called function displays the callout number, the start and current default, the called function displays the callout number, the start and current
positions in the text at the callout time, and the next pattern item to be positions in the text at the callout time, and the next pattern item to be
tested. For example: tested. For example:
<pre> <pre>
@ -1306,7 +1309,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC20" href="#TOC1">REVISION</a><br> <br><a name="SEC20" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 14 November 2014 Last updated: 23 November 2014
<br> <br>
Copyright &copy; 1997-2014 University of Cambridge. Copyright &copy; 1997-2014 University of Cambridge.
<br> <br>

5
doc/html/pcre2unicode.html
View File

@ -115,7 +115,10 @@ VALIDITY OF UTF STRINGS
<P> <P>
When the PCRE2_UTF option is set, the strings passed as patterns and subjects When the PCRE2_UTF option is set, the strings passed as patterns and subjects
are (by default) checked for validity on entry to the relevant functions. are (by default) checked for validity on entry to the relevant functions.
If an invalid UTF string is passed, an error return is given. If an invalid UTF string is passed, an negative error code is returned. The
code unit offset to the offending character can be extracted from the match
data block by calling <b>pcre2_get_startchar()</b>, which is used for this
purpose after a UTF error.
</P> </P>
<P> <P>
UTF-16 and UTF-32 strings can indicate their endianness by special code knows UTF-16 and UTF-32 strings can indicate their endianness by special code knows

18
doc/pcre2.txt
View File

@ -2057,6 +2057,10 @@ OTHER INFORMATION ABOUT A MATCH
value is always the same as ovector[0] because \K does not affect the value is always the same as ovector[0] because \K does not affect the
result of a partial match. result of a partial match.
The startchar field is also used to return the offset of an invalid UTF
character when UTF checking fails. Details are given in the pcre2uni-
code page.
ERROR RETURNS FROM pcre2_match() ERROR RETURNS FROM pcre2_match()
@ -2601,7 +2605,7 @@ AUTHOR
REVISION REVISION
Last updated: 21 November 2014 Last updated: 23 November 2014
Copyright (c) 1997-2014 University of Cambridge. Copyright (c) 1997-2014 University of Cambridge.
------------------------------------------------------------------------------ ------------------------------------------------------------------------------
@ -4327,9 +4331,9 @@ PARTIAL MATCHING USING pcre2_dfa_match()
/dog(sbody)??/ /dog(sbody)??/
Whereas the standard functions stop as soon as they find the complete Whereas the standard function stops as soon as it finds the complete
match for "dog", the DFA functions also find the partial match for match for "dog", the DFA function also finds the partial match for
"dogsbody", and so return that when PCRE2_PARTIAL_HARD is set. "dogsbody", and so returns that when PCRE2_PARTIAL_HARD is set.
PARTIAL MATCHING AND WORD BOUNDARIES PARTIAL MATCHING AND WORD BOUNDARIES
@ -4681,8 +4685,10 @@ VALIDITY OF UTF STRINGS
When the PCRE2_UTF option is set, the strings passed as patterns and When the PCRE2_UTF option is set, the strings passed as patterns and
subjects are (by default) checked for validity on entry to the relevant subjects are (by default) checked for validity on entry to the relevant
functions. If an invalid UTF string is passed, an error return is functions. If an invalid UTF string is passed, an negative error code
given. is returned. The code unit offset to the offending character can be
extracted from the match data block by calling pcre2_get_startchar(),
which is used for this purpose after a UTF error.
UTF-16 and UTF-32 strings can indicate their endianness by special code UTF-16 and UTF-32 strings can indicate their endianness by special code
knows as a byte-order mark (BOM). The PCRE2 functions do not handle knows as a byte-order mark (BOM). The PCRE2 functions do not handle

4
doc/pcre2api.3
View File

@ -2091,12 +2091,12 @@ different to the value of \fIovector[0]\fP if the pattern contains the \eK
escape sequence. After a partial match, however, this value is always the same escape sequence. After a partial match, however, this value is always the same
as \fIovector[0]\fP because \eK does not affect the result of a partial match. as \fIovector[0]\fP because \eK does not affect the result of a partial match.
.P .P
The \fBstartchar\fP field is also used to return the offset of an invalid The \fBstartchar\fP field is also used to return the offset of an invalid
UTF character when UTF checking fails. Details are given in the UTF character when UTF checking fails. Details are given in the
.\" HREF .\" HREF
\fBpcre2unicode\fP \fBpcre2unicode\fP
.\" .\"
page. page.
. .
. .
.\" HTML <a name="errorlist"></a> .\" HTML <a name="errorlist"></a>

6
doc/pcre2partial.3
View File

@ -169,9 +169,9 @@ the string "dog" matched against the ungreedy pattern shown above:
.sp .sp
/dog(sbody)??/ /dog(sbody)??/
.sp .sp
Whereas the standard functions stop as soon as they find the complete match for Whereas the standard function stops as soon as it finds the complete match for
"dog", the DFA functions also find the partial match for "dogsbody", and so "dog", the DFA function also finds the partial match for "dogsbody", and so
return that when PCRE2_PARTIAL_HARD is set. returns that when PCRE2_PARTIAL_HARD is set.
. .
. .
.SH "PARTIAL MATCHING AND WORD BOUNDARIES" .SH "PARTIAL MATCHING AND WORD BOUNDARIES"

16
doc/pcre2test.1
View File

@ -478,7 +478,7 @@ link sizes and different code unit widths. By using \fBbincode\fP, the same
regression tests can be used in different environments. regression tests can be used in different environments.
.P .P
The \fBfullbincode\fP modifier, by contrast, \fIdoes\fP include length and The \fBfullbincode\fP modifier, by contrast, \fIdoes\fP include length and
offset values. This is used in a few special tests that run only for specific offset values. This is used in a few special tests that run only for specific
code unit widths and link sizes, and is also useful for one-off tests. code unit widths and link sizes, and is also useful for one-off tests.
.P .P
The \fBinfo\fP modifier requests information about the compiled pattern The \fBinfo\fP modifier requests information about the compiled pattern
@ -503,7 +503,7 @@ some typical examples:
.sp .sp
"Compile options" are those specified by modifiers; "overall options" have "Compile options" are those specified by modifiers; "overall options" have
added options that are taken or deduced from the pattern. If both sets of added options that are taken or deduced from the pattern. If both sets of
options are the same, just a single "options" line is output; if there are no options are the same, just a single "options" line is output; if there are no
options, the line is omitted. "First code unit" is where any match must start; options, the line is omitted. "First code unit" is where any match must start;
if there is more than one they are listed as "starting code units". "Last code if there is more than one they are listed as "starting code units". "Last code
unit" is the last literal code unit that must be present in any match. This is unit" is the last literal code unit that must be present in any match. This is
@ -646,7 +646,7 @@ be aborted.
.SS "Using alternative character tables" .SS "Using alternative character tables"
.rs .rs
.sp .sp
The value specified for the \fB/tables\fP modifier must be one of the digits 0, The value specified for the \fB/tables\fP modifier must be one of the digits 0,
1, or 2. It causes a specific set of built-in character tables to be passed to 1, or 2. It causes a specific set of built-in character tables to be passed to
\fBpcre2_compile()\fP. This is used in the PCRE2 tests to check behaviour with \fBpcre2_compile()\fP. This is used in the PCRE2 tests to check behaviour with
different character tables. The digit specifies the tables as follows: different character tables. The digit specifies the tables as follows:
@ -760,7 +760,7 @@ The effects of these modifiers are described in the following sections.
.SS "Showing more text" .SS "Showing more text"
.rs .rs
.sp .sp
The \fBaftertext\fP modifier requests that as well as outputting the part of The \fBaftertext\fP modifier requests that as well as outputting the part of
the subject string that matched the entire pattern, \fBpcre2test\fP should in the subject string that matched the entire pattern, \fBpcre2test\fP should in
addition output the remainder of the subject string. This is useful for tests addition output the remainder of the subject string. This is useful for tests
where the subject contains multiple copies of the same substring. The where the subject contains multiple copies of the same substring. The
@ -783,7 +783,7 @@ underneath them. Here is an example:
<<< >>> <<< >>>
.sp .sp
This shows that the matched string is "abc", with the preceding and following This shows that the matched string is "abc", with the preceding and following
strings "pqr" and "xyz" having been consulted during the match (when processing strings "pqr" and "xyz" having been consulted during the match (when processing
the assertions). the assertions).
.P .P
The \fBstartchar\fP modifier requests that the starting character for the match The \fBstartchar\fP modifier requests that the starting character for the match
@ -873,7 +873,7 @@ If the subject line is successfully matched, the substrings extracted by the
convenience functions are output with C, G, or L after the string number convenience functions are output with C, G, or L after the string number
instead of a colon. This is in addition to the normal full list. The string instead of a colon. This is in addition to the normal full list. The string
length (that is, the return from the extraction function) is given in length (that is, the return from the extraction function) is given in
parentheses after each substring, followed by the name when the extraction was parentheses after each substring, followed by the name when the extraction was
by name. by name.
. .
. .
@ -1102,7 +1102,7 @@ are output in sequence, like this:
1: pp 1: pp
.sp .sp
"No match" is output only if the first match attempt fails. Here is an example "No match" is output only if the first match attempt fails. Here is an example
of a failure message (the offset 4 that is specified by the \fBoffset\fP of a failure message (the offset 4 that is specified by the \fBoffset\fP
modifier is past the end of the subject string): modifier is past the end of the subject string):
.sp .sp
re> /xyz/ re> /xyz/
@ -1134,7 +1134,7 @@ longest matching string is always given first (and numbered zero). After a
PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the
partially matching substring. Note that this is the entire substring that was partially matching substring. Note that this is the entire substring that was
inspected during the partial match; it may include characters before the actual inspected during the partial match; it may include characters before the actual
match start if a lookbehind assertion, \eb, or \eB was involved. (\eK is not match start if a lookbehind assertion, \eb, or \eB was involved. (\eK is not
supported for DFA matching.) supported for DFA matching.)
.P .P
If global matching is requested, the search for further matches resumes If global matching is requested, the search for further matches resumes

374
doc/pcre2test.txt
View File

@ -188,7 +188,7 @@ DESCRIPTION
followed by any number of subject lines to be matched against that pat- followed by any number of subject lines to be matched against that pat-
tern. In between sets of test data, command lines that begin with a tern. In between sets of test data, command lines that begin with a
hash (#) character may appear. This file format, with some restric- hash (#) character may appear. This file format, with some restric-
tions, can also be processed by the perltest.pl script that is distrib- tions, can also be processed by the perltest.sh script that is distrib-
uted with PCRE2 as a means of checking that the behaviour of PCRE2 and uted with PCRE2 as a means of checking that the behaviour of PCRE2 and
Perl is the same. Perl is the same.
@ -232,11 +232,11 @@ COMMAND LINES
#perltest #perltest
The appearance of this line causes all subsequent modifier settings to The appearance of this line causes all subsequent modifier settings to
be checked for compatibility with the perltest.pl script, which is used be checked for compatibility with the perltest.sh script, which is used
to confirm that Perl gives the same results as PCRE2. Also, apart from to confirm that Perl gives the same results as PCRE2. Also, apart from
comment lines, none of the other command lines are permitted, because comment lines, none of the other command lines are permitted, because
they and many of the modifiers are specific to pcre2test, and should they and many of the modifiers are specific to pcre2test, and should
not be used in test files that are also processed by perltest.pl. The not be used in test files that are also processed by perltest.sh. The
#perltest command helps detect tests that are accidentally put in the #perltest command helps detect tests that are accidentally put in the
wrong file. wrong file.
@ -255,53 +255,52 @@ MODIFIER SYNTAX
valid for one or the other only. Each modifier has a long name, for valid for one or the other only. Each modifier has a long name, for
example "anchored", and some of them must be followed by an equals sign example "anchored", and some of them must be followed by an equals sign
and a value, for example, "offset=12". Modifiers that do not take val- and a value, for example, "offset=12". Modifiers that do not take val-
ues may be preceded by a minus sign to turn off a previous default set- ues may be preceded by a minus sign to turn off a previous setting.
ting.
A few of the more common modifiers can also be specified as single let- A few of the more common modifiers can also be specified as single let-
ters, for example "i" for "caseless". In documentation, following the ters, for example "i" for "caseless". In documentation, following the
Perl convention, these are written with a slash ("the /i modifier") for Perl convention, these are written with a slash ("the /i modifier") for
clarity. Abbreviated modifiers must all be concatenated in the first clarity. Abbreviated modifiers must all be concatenated in the first
item of a modifier list. If the first item is not recognized as a long item of a modifier list. If the first item is not recognized as a long
modifier name, it is interpreted as a sequence of these abbreviations. modifier name, it is interpreted as a sequence of these abbreviations.
For example: For example:
/abc/ig,newline=cr,jit=3 /abc/ig,newline=cr,jit=3
This is a pattern line whose modifier list starts with two one-letter This is a pattern line whose modifier list starts with two one-letter
modifiers (/i and /g). The lower-case abbreviated modifiers are the modifiers (/i and /g). The lower-case abbreviated modifiers are the
same as used in Perl. same as used in Perl.
PATTERN SYNTAX PATTERN SYNTAX
A pattern line must start with one of the following characters (common A pattern line must start with one of the following characters (common
symbols, excluding pattern meta-characters): symbols, excluding pattern meta-characters):
/ ! " ' ` - = _ : ; , % & @ ~ / ! " ' ` - = _ : ; , % & @ ~
This is interpreted as the pattern's delimiter. A regular expression This is interpreted as the pattern's delimiter. A regular expression
may be continued over several input lines, in which case the newline may be continued over several input lines, in which case the newline
characters are included within it. It is possible to include the delim- characters are included within it. It is possible to include the delim-
iter within the pattern by escaping it with a backslash, for example iter within the pattern by escaping it with a backslash, for example
/abc\/def/ /abc\/def/
If you do this, the escape and the delimiter form part of the pattern, If you do this, the escape and the delimiter form part of the pattern,
but since the delimiters are all non-alphanumeric, this does not affect but since the delimiters are all non-alphanumeric, this does not affect
its interpretation. If the terminating delimiter is immediately fol- its interpretation. If the terminating delimiter is immediately fol-
lowed by a backslash, for example, lowed by a backslash, for example,
/abc/\ /abc/\
then a backslash is added to the end of the pattern. This is done to then a backslash is added to the end of the pattern. This is done to
provide a way of testing the error condition that arises if a pattern provide a way of testing the error condition that arises if a pattern
finishes with a backslash, because finishes with a backslash, because
/abc\/ /abc\/
is interpreted as the first line of a pattern that starts with "abc/", is interpreted as the first line of a pattern that starts with "abc/",
causing pcre2test to read the next line as a continuation of the regu- causing pcre2test to read the next line as a continuation of the regu-
lar expression. lar expression.
A pattern can be followed by a modifier list (details below). A pattern can be followed by a modifier list (details below).
@ -309,7 +308,7 @@ PATTERN SYNTAX
SUBJECT LINE SYNTAX SUBJECT LINE SYNTAX
Before each subject line is passed to pcre2_match() or Before each subject line is passed to pcre2_match() or
pcre2_dfa_match(), leading and trailing white space is removed, and the pcre2_dfa_match(), leading and trailing white space is removed, and the
line is scanned for backslash escapes. The following provide a means of line is scanned for backslash escapes. The following provide a means of
encoding non-printing characters in a visible way: encoding non-printing characters in a visible way:
@ -329,23 +328,23 @@ SUBJECT LINE SYNTAX
\x{hh...} hexadecimal character (any number of hex digits) \x{hh...} hexadecimal character (any number of hex digits)
The use of \x{hh...} is not dependent on the use of the utf modifier on The use of \x{hh...} is not dependent on the use of the utf modifier on
the pattern. It is recognized always. There may be any number of hexa- the pattern. It is recognized always. There may be any number of hexa-
decimal digits inside the braces; invalid values provoke error mes- decimal digits inside the braces; invalid values provoke error mes-
sages. sages.
Note that \xhh specifies one byte rather than one character in UTF-8 Note that \xhh specifies one byte rather than one character in UTF-8
mode; this makes it possible to construct invalid UTF-8 sequences for mode; this makes it possible to construct invalid UTF-8 sequences for
testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
character in UTF-8 mode, generating more than one byte if the value is character in UTF-8 mode, generating more than one byte if the value is
greater than 127. When testing the 8-bit library not in UTF-8 mode, greater than 127. When testing the 8-bit library not in UTF-8 mode,
\x{hh} generates one byte for values less than 256, and causes an error \x{hh} generates one byte for values less than 256, and causes an error
for greater values. for greater values.
In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
possible to construct invalid UTF-16 sequences for testing purposes. possible to construct invalid UTF-16 sequences for testing purposes.
In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
makes it possible to construct invalid UTF-32 sequences for testing makes it possible to construct invalid UTF-32 sequences for testing
purposes. purposes.
There is a special backslash sequence that specifies replication of one There is a special backslash sequence that specifies replication of one
@ -353,38 +352,38 @@ SUBJECT LINE SYNTAX
\[<characters>]{<count>} \[<characters>]{<count>}
This makes it possible to test long strings without having to provide This makes it possible to test long strings without having to provide
them as part of the file. For example: them as part of the file. For example:
\[abc]{4} \[abc]{4}
is converted to "abcabcabcabc". This feature does not support nesting. is converted to "abcabcabcabc". This feature does not support nesting.
To include a closing square bracket in the characters, code it as \x5D. To include a closing square bracket in the characters, code it as \x5D.
A backslash followed by an equals sign marke the end of the subject A backslash followed by an equals sign marks the end of the subject
string and the start of a modifier list. For example: string and the start of a modifier list. For example:
abc\=notbol,notempty abc\=notbol,notempty
A backslash followed by any other non-alphanumeric character just A backslash followed by any other non-alphanumeric character just
escapes that character. A backslash followed by anything else causes an escapes that character. A backslash followed by anything else causes an
error. However, if the very last character in the line is a backslash error. However, if the very last character in the line is a backslash
(and there is no modifier list), it is ignored. This gives a way of (and there is no modifier list), it is ignored. This gives a way of
passing an empty line as data, since a real empty line terminates the passing an empty line as data, since a real empty line terminates the
data input. data input.
PATTERN MODIFIERS PATTERN MODIFIERS
There are three types of modifier that can appear in pattern lines, two There are three types of modifier that can appear in pattern lines, two
of which may also be used in a #pattern command. A pattern's modifier of which may also be used in a #pattern command. A pattern's modifier
list can add to or override default modifiers that were set by a previ- list can add to or override default modifiers that were set by a previ-
ous #pattern command. ous #pattern command.
Setting compilation options Setting compilation options
The following modifiers set options for pcre2_compile(). The most com- The following modifiers set options for pcre2_compile(). The most com-
mon ones have single-letter abbreviations. See pcreapi for a descrip- mon ones have single-letter abbreviations. See pcreapi for a descrip-
tion of their effects. tion of their effects.
allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS
@ -410,13 +409,13 @@ PATTERN MODIFIERS
utf set PCRE2_UTF utf set PCRE2_UTF
As well as turning on the PCRE2_UTF option, the utf modifier causes all As well as turning on the PCRE2_UTF option, the utf modifier causes all
non-printing characters in output strings to be printed using the non-printing characters in output strings to be printed using the
\x{hh...} notation. Otherwise, those less than 0x100 are output in hex \x{hh...} notation. Otherwise, those less than 0x100 are output in hex
without the curly brackets. without the curly brackets.
Setting compilation controls Setting compilation controls
The following modifiers affect the compilation process or request The following modifiers affect the compilation process or request
information about the pattern: information about the pattern:
bsr=[anycrlf|unicode] specify \R handling bsr=[anycrlf|unicode] specify \R handling
@ -441,34 +440,34 @@ PATTERN MODIFIERS
Newline and \R handling Newline and \R handling
The bsr modifier specifies what \R in a pattern should match. If it is The bsr modifier specifies what \R in a pattern should match. If it is
set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to
"unicode", \R matches any Unicode newline sequence. The default is "unicode", \R matches any Unicode newline sequence. The default is
specified when PCRE2 is built, with the default default being Unicode. specified when PCRE2 is built, with the default default being Unicode.
The newline modifier specifies which characters are to be interpreted The newline modifier specifies which characters are to be interpreted
as newlines, both in the pattern and (by default) in subject lines. The as newlines, both in the pattern and in subject lines. The type must be
type must be one of CR, LF, CRLF, ANYCRLF, or ANY. one of CR, LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
Information about a pattern Information about a pattern
The debug modifier is a shorthand for info,fullbincode, requesting all The debug modifier is a shorthand for info,fullbincode, requesting all
available information. available information.
The bincode modifier causes a representation of the compiled code to be The bincode modifier causes a representation of the compiled code to be
output after compilation. This information does not contain length and output after compilation. This information does not contain length and
offset values, which ensures that the same output is generated for dif- offset values, which ensures that the same output is generated for dif-
ferent internal link sizes and different code unit widths. By using ferent internal link sizes and different code unit widths. By using
bincode, the same regression tests can be used in different environ- bincode, the same regression tests can be used in different environ-
ments. ments.
The fullbincode modifier, by contrast, does include length and offset The fullbincode modifier, by contrast, does include length and offset
values. This is used in a few special tests and is also useful for one- values. This is used in a few special tests that run only for specific
off tests. code unit widths and link sizes, and is also useful for one-off tests.
The info modifier requests information about the compiled pattern The info modifier requests information about the compiled pattern
(whether it is anchored, has a fixed first character, and so on). The (whether it is anchored, has a fixed first character, and so on). The
information is obtained from the pcre2_pattern_info() function. Here information is obtained from the pcre2_pattern_info() function. Here
are some typical examples: are some typical examples:
re> /(?i)(^a|^b)/m,info re> /(?i)(^a|^b)/m,info
@ -486,14 +485,15 @@ PATTERN MODIFIERS
Last code unit = 'c' (caseless) Last code unit = 'c' (caseless)
Subject length lower bound = 3 Subject length lower bound = 3
"Compile options" are those specified to the compile function; "overall "Compile options" are those specified by modifiers; "overall options"
options" have added options that are taken or deduced from the pattern. have added options that are taken or deduced from the pattern. If both
If both sets of options are the same, just a single "options" line is sets of options are the same, just a single "options" line is output;
output. "First code unit" is where any match must start; if there is if there are no options, the line is omitted. "First code unit" is
more than one they are listed as "starting code units". "Last code where any match must start; if there is more than one they are listed
unit" is the last literal code unit that must be present in any match. as "starting code units". "Last code unit" is the last literal code
This is not necessarily the last character. These lines are omitted if unit that must be present in any match. This is not necessarily the
no starting or ending code units are recorded. last character. These lines are omitted if no starting or ending code
units are recorded.
Specifying a pattern in hex Specifying a pattern in hex
@ -504,14 +504,14 @@ PATTERN MODIFIERS
/ab 32 59/hex /ab 32 59/hex
This feature is provided as a way of creating patterns that contain This feature is provided as a way of creating patterns that contain
binary zero characters. By default, pcre2test passes patterns as zero- binary zero and other non-printing characters. By default, pcre2test
terminated strings to pcre2_compile(), giving the length as passes patterns as zero-terminated strings to pcre2_compile(), giving
PCRE2_ZERO_TERMINATED. However, for patterns specified in hexadecimal, the length as PCRE2_ZERO_TERMINATED. However, for patterns specified in
the actual length of the pattern is passed. hexadecimal, the actual length of the pattern is passed.
JIT compilation JIT compilation
The /jit modifier may optionally be followed by and equals sign and a The /jit modifier may optionally be followed by an equals sign and a
number in the range 0 to 7: number in the range 0 to 7:
0 disable JIT 0 disable JIT
@ -540,7 +540,7 @@ PATTERN MODIFIERS
jitverify is specified without jit, jit=7 is assumed. If JIT compila- jitverify is specified without jit, jit=7 is assumed. If JIT compila-
tion is successful when jitverify is set, the text "(JIT)" is added to tion is successful when jitverify is set, the text "(JIT)" is added to
the first output line after a match or non match when JIT-compiled code the first output line after a match or non match when JIT-compiled code
was actually used. was actually used in the match.
Setting a locale Setting a locale
@ -609,25 +609,26 @@ PATTERN MODIFIERS
Using alternative character tables Using alternative character tables
The /tables modifier must be followed by a single digit. It causes a The value specified for the /tables modifier must be one of the digits
specific set of built-in character tables to be passed to pcre2_com- 0, 1, or 2. It causes a specific set of built-in character tables to be
pile(). This is used in the PCRE2 tests to check behaviour with differ- passed to pcre2_compile(). This is used in the PCRE2 tests to check be-
ent character tables. The digit specifies the tables as follows: haviour with different character tables. The digit specifies the tables
as follows:
0 do not pass any special character tables 0 do not pass any special character tables
1 the default ASCII tables, as distributed in 1 the default ASCII tables, as distributed in
pcre2_chartables.c.dist pcre2_chartables.c.dist
2 a set of tables defining ISO 8859 characters 2 a set of tables defining ISO 8859 characters
In table 2, some characters whose codes are greater than 128 are iden- In table 2, some characters whose codes are greater than 128 are iden-
tified as letters, digits, spaces, etc. Setting alternate character tified as letters, digits, spaces, etc. Setting alternate character
tables and a locale are mutually exclusive. tables and a locale are mutually exclusive.
Setting certain match controls Setting certain match controls
The following modifiers are really subject modifiers, and are described The following modifiers are really subject modifiers, and are described
below. However, they may be included in a pattern's modifier list, in below. However, they may be included in a pattern's modifier list, in
which case they are applied to every subject line that is processed which case they are applied to every subject line that is processed
with that pattern. They do not affect the compilation process. with that pattern. They do not affect the compilation process.
aftertext show text after match aftertext show text after match
@ -639,7 +640,7 @@ PATTERN MODIFIERS
replace=<string> specify a replacement string replace=<string> specify a replacement string
startchar show starting character when relevant startchar show starting character when relevant
These modifiers may not appear in a #pattern command. If you want them These modifiers may not appear in a #pattern command. If you want them
as defaults, set them in a #subject command. as defaults, set them in a #subject command.
@ -650,7 +651,7 @@ SUBJECT MODIFIERS
Setting match options Setting match options
The following modifiers set options for pcre2_match() or The following modifiers set options for pcre2_match() or
pcre2_dfa_match(). See pcreapi for a description of their effects. pcre2_dfa_match(). See pcreapi for a description of their effects.
anchored set PCRE2_ANCHORED anchored set PCRE2_ANCHORED
@ -664,20 +665,20 @@ SUBJECT MODIFIERS
partial_hard (or ph) set PCRE2_PARTIAL_HARD partial_hard (or ph) set PCRE2_PARTIAL_HARD
partial_soft (or ps) set PCRE2_PARTIAL_SOFT partial_soft (or ps) set PCRE2_PARTIAL_SOFT
The partial matching modifiers are provided with abbreviations because The partial matching modifiers are provided with abbreviations because
they appear frequently in tests. they appear frequently in tests.
If the /posix modifier was present on the pattern, causing the POSIX If the /posix modifier was present on the pattern, causing the POSIX
wrapper API to be used, the only option-setting modifiers that have any wrapper API to be used, the only option-setting modifiers that have any
effect are notbol, notempty, and noteol, causing REG_NOTBOL, effect are notbol, notempty, and noteol, causing REG_NOTBOL,
REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec().
Any other modifiers cause an error. Any other modifiers cause an error.
Setting match controls Setting match controls
The following modifiers affect the matching process or request addi- The following modifiers affect the matching process or request addi-
tional information. Some of them may also be specified on a pattern tional information. Some of them may also be specified on a pattern
line (see above), in which case they apply to every subject line that line (see above), in which case they apply to every subject line that
is matched against that pattern. is matched against that pattern.
aftertext show text after match aftertext show text after match
@ -710,23 +711,23 @@ SUBJECT MODIFIERS
Showing more text Showing more text
The aftertext modifier requests that as well as outputting the sub- The aftertext modifier requests that as well as outputting the part of
string that matched the entire pattern, pcre2test should in addition the subject string that matched the entire pattern, pcre2test should in
output the remainder of the subject string. This is useful for tests addition output the remainder of the subject string. This is useful for
where the subject contains multiple copies of the same substring. The tests where the subject contains multiple copies of the same substring.
allaftertext modifier requests the same action for captured substrings The allaftertext modifier requests the same action for captured sub-
as well as the main matched substring. In each case the remainder is strings as well as the main matched substring. In each case the remain-
output on the following line with a plus character following the cap- der is output on the following line with a plus character following the
ture number. capture number.
The allusedtext modifier requests that all the text that was consulted The allusedtext modifier requests that all the text that was consulted
during a successful pattern match by the interpreter should be shown. during a successful pattern match by the interpreter should be shown.
This feature is not supported for JIT matching, and if requested with This feature is not supported for JIT matching, and if requested with
JIT it is ignored (with a warning message). Setting this modifier JIT it is ignored (with a warning message). Setting this modifier
affects the output if there is a lookbehind at the start of a match, or affects the output if there is a lookbehind at the start of a match, or
a lookahead at the end, or if \K is used in the pattern. Characters a lookahead at the end, or if \K is used in the pattern. Characters
that precede or follow the start and end of the actual match are indi- that precede or follow the start and end of the actual match are indi-
cated in the output by '<' or '>' characters underneath them. Here is cated in the output by '<' or '>' characters underneath them. Here is
an example: an example:
re> /(?<=pqr)abc(?=xyz)/ re> /(?<=pqr)abc(?=xyz)/
@ -734,8 +735,9 @@ SUBJECT MODIFIERS
0: pqrabcxyz 0: pqrabcxyz
<<< >>> <<< >>>
This shows that the matched string is "abc", with the preceding and This shows that the matched string is "abc", with the preceding and
following strings "pqr" and "xyz" also consulted during the match. following strings "pqr" and "xyz" having been consulted during the
match (when processing the assertions).
The startchar modifier requests that the starting character for the The startchar modifier requests that the starting character for the
match be indicated, if it is different to the start of the matched match be indicated, if it is different to the start of the matched
@ -784,9 +786,9 @@ SUBJECT MODIFIERS
difference between global and altglobal is that the former uses the difference between global and altglobal is that the former uses the
start_offset argument to pcre2_match() or pcre2_dfa_match() to start start_offset argument to pcre2_match() or pcre2_dfa_match() to start
searching at a new point within the entire string (which is what Perl searching at a new point within the entire string (which is what Perl
does), whereas the latter passes over a shortened substring. This makes does), whereas the latter passes over a shortened subject. This makes a
a difference to the matching process if the pattern begins with a look- difference to the matching process if the pattern begins with a lookbe-
behind assertion (including \b or \B). hind assertion (including \b or \B).
If an empty string is matched, the next match is done with the If an empty string is matched, the next match is done with the
PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search
@ -796,7 +798,7 @@ SUBJECT MODIFIERS
/g modifier or the split() function. Normally, the start offset is /g modifier or the split() function. Normally, the start offset is
advanced by one character, but if the newline convention recognizes advanced by one character, but if the newline convention recognizes
CRLF as a newline, and the current character is CR followed by LF, an CRLF as a newline, and the current character is CR followed by LF, an
advance of two is used. advance of two characters occurs.
Testing substring extraction functions Testing substring extraction functions
@ -807,9 +809,9 @@ SUBJECT MODIFIERS
abcd\=copy=1,copy=3,get=G1 abcd\=copy=1,copy=3,get=G1
If the #subject command is used to set default copy and get lists, If the #subject command is used to set default copy and/or get lists,
these can be unset by specifying a negative number for numbered groups these can be unset by specifying a negative number to cancel all num-
and an empty name for named groups. bered groups and an empty name to cancel all named groups.
The getall modifier tests pcre2_substring_list_get(), which extracts The getall modifier tests pcre2_substring_list_get(), which extracts
all captured substrings. all captured substrings.
@ -818,23 +820,24 @@ SUBJECT MODIFIERS
by the convenience functions are output with C, G, or L after the by the convenience functions are output with C, G, or L after the
string number instead of a colon. This is in addition to the normal string number instead of a colon. This is in addition to the normal
full list. The string length (that is, the return from the extraction full list. The string length (that is, the return from the extraction
function) is given in parentheses after each substring. function) is given in parentheses after each substring, followed by the
name when the extraction was by name.
Testing the substitution function Testing the substitution function
If the replace modifier is set, the pcre2_substitute() function is If the replace modifier is set, the pcre2_substitute() function is
called instead of one of the matching functions. Unlike subject called instead of one of the matching functions. Unlike subject
strings, pcre2test does not process replacement strings for escape strings, pcre2test does not process replacement strings for escape
sequences. In UTF mode, a replacement string is checked to see if it is sequences. In UTF mode, a replacement string is checked to see if it is
a valid UTF-8 string. If so, it is correctly converted to a UTF string a valid UTF-8 string. If so, it is correctly converted to a UTF string
of the appropriate code unit width. If it is not a valid UTF-8 string, of the appropriate code unit width. If it is not a valid UTF-8 string,
the individual code units are copied directly. This provides a means of the individual code units are copied directly. This provides a means of
passing an invalid UTF-8 string for testing purposes. passing an invalid UTF-8 string for testing purposes.
If the global modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to If the global modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to
pcre2_substitute(). After a successful substitution, the modified pcre2_substitute(). After a successful substitution, the modified
string is output, preceded by the number of replacements. This may be string is output, preceded by the number of replacements. This may be
zero if there were no matches. Here is a simple example of a substitu- zero if there were no matches. Here is a simple example of a substitu-
tion test: tion test:
/abc/replace=xxx /abc/replace=xxx
@ -843,11 +846,11 @@ SUBJECT MODIFIERS
=abc=abc=\=global =abc=abc=\=global
2: =xxx=xxx= 2: =xxx=xxx=
Subject and replacement strings should be kept relatively short for Subject and replacement strings should be kept relatively short for
substitution tests, as fixed-size buffers are used. To make it easy to substitution tests, as fixed-size buffers are used. To make it easy to
test for buffer overflow, if the replacement string starts with a num- test for buffer overflow, if the replacement string starts with a num-
ber in square brackets, that number is passed to pcre2_substitute() as ber in square brackets, that number is passed to pcre2_substitute() as
the size of the output buffer, with the replacement string starting at the size of the output buffer, with the replacement string starting at
the next character. Here is an example that tests the edge case: the next character. Here is an example that tests the edge case:
/abc/ /abc/
@ -857,125 +860,124 @@ SUBJECT MODIFIERS
Failed: error -47: no more memory Failed: error -47: no more memory
A replacement string is ignored with POSIX and DFA matching. Specifying A replacement string is ignored with POSIX and DFA matching. Specifying
partial matching provokes an error return ("bad option value") from partial matching provokes an error return ("bad option value") from
pcre2_substitute(). pcre2_substitute().
Setting the JIT stack size Setting the JIT stack size
The jitstack modifier provides a way of setting the maximum stack size The jitstack modifier provides a way of setting the maximum stack size
that is used by the just-in-time optimization code. It is ignored if that is used by the just-in-time optimization code. It is ignored if
JIT optimization is not being used. The value is a number of kilobytes. JIT optimization is not being used. The value is a number of kilobytes.
Providing a stack that is larger than the default 32K is necessary only Providing a stack that is larger than the default 32K is necessary only
for very complicated patterns. for very complicated patterns.
Setting match and recursion limits Setting match and recursion limits
The match_limit and recursion_limit modifiers set the appropriate lim- The match_limit and recursion_limit modifiers set the appropriate lim-
its in the match context. These values are ignored when the find_limits its in the match context. These values are ignored when the find_limits
modifier is specified. modifier is specified.
Finding minimum limits Finding minimum limits
If the find_limits modifier is present, pcre2test calls pcre2_match() If the find_limits modifier is present, pcre2test calls pcre2_match()
several times, setting different values in the match context via several times, setting different values in the match context via
pcre2_set_match_limit() and pcre2_set_recursion_limit() until it finds pcre2_set_match_limit() and pcre2_set_recursion_limit() until it finds
the minimum values for each parameter that allow pcre2_match() to com- the minimum values for each parameter that allow pcre2_match() to com-
plete without error. plete without error.
If JIT is being used, only the match limit is relevant. If DFA matching If JIT is being used, only the match limit is relevant. If DFA matching
is being used, neither limit is relevant, and this modifier is ignored is being used, neither limit is relevant, and this modifier is ignored
(with a warning message). (with a warning message).
The match_limit number is a measure of the amount of backtracking that The match_limit number is a measure of the amount of backtracking that
takes place, and learning the minimum value can be instructive. For takes place, and learning the minimum value can be instructive. For
most simple matches, the number is quite small, but for patterns with most simple matches, the number is quite small, but for patterns with
very large numbers of matching possibilities, it can become large very very large numbers of matching possibilities, it can become large very
quickly with increasing length of subject string. The quickly with increasing length of subject string. The
match_limit_recursion number is a measure of how much stack (or, if match_limit_recursion number is a measure of how much stack (or, if
PCRE2 is compiled with NO_RECURSE, how much heap) memory is needed to PCRE2 is compiled with NO_RECURSE, how much heap) memory is needed to
complete the match attempt. complete the match attempt.
Showing MARK names Showing MARK names
The mark modifier causes the names from backtracking control verbs that The mark modifier causes the names from backtracking control verbs that
are returned from calls to pcre2_match() to be displayed. If a mark is are returned from calls to pcre2_match() to be displayed. If a mark is
returned for a match, non-match, or partial match, pcre2test shows it. returned for a match, non-match, or partial match, pcre2test shows it.
For a match, it is on a line by itself, tagged with "MK:". Otherwise, For a match, it is on a line by itself, tagged with "MK:". Otherwise,
it is added to the non-match message. it is added to the non-match message.
Showing memory usage Showing memory usage
The memory modifier causes pcre2test to log all memory allocation and The memory modifier causes pcre2test to log all memory allocation and
freeing calls that occur during a match operation. freeing calls that occur during a match operation.
Setting a starting offset Setting a starting offset
The offset modifier sets an offset in the subject string at which The offset modifier sets an offset in the subject string at which
matching starts. Its value is a number of code units, not characters. matching starts. Its value is a number of code units, not characters.
Setting the size of the output vector Setting the size of the output vector
The ovector modifier applies only to the subject line in which it The ovector modifier applies only to the subject line in which it
appears, though of course it can also be used to set a default in a appears, though of course it can also be used to set a default in a
#subject command. It specifies the number of pairs of offsets that are #subject command. It specifies the number of pairs of offsets that are
available for storing matching information. The default is 15. available for storing matching information. The default is 15.
A value of zero is useful when testing the POSIX API because it causes A value of zero is useful when testing the POSIX API because it causes
regexec() to be called with a NULL capture vector. When not testing the regexec() to be called with a NULL capture vector. When not testing the
POSIX API, a value of zero is used to cause pcre2_match_data_cre- POSIX API, a value of zero is used to cause pcre2_match_data_cre-
ate_from_pattern() to be called, in order to create a match block of ate_from_pattern() to be called, in order to create a match block of
exactly the right size for the pattern. (It is not possible to create a exactly the right size for the pattern. (It is not possible to create a
match block with a zero-length ovector; there is always at least one match block with a zero-length ovector; there is always at least one
pair of offsets.) pair of offsets.)
Passing the subject as zero-terminated Passing the subject as zero-terminated
By default, the subject string is passed to a native API matching func- By default, the subject string is passed to a native API matching func-
tion with its correct length. In order to test the facility for passing tion with its correct length. In order to test the facility for passing
a zero-terminated string, the zero_terminate modifier is provided. It a zero-terminated string, the zero_terminate modifier is provided. It
causes the length to be passed as PCRE2_ZERO_TERMINATED. (When matching causes the length to be passed as PCRE2_ZERO_TERMINATED. (When matching
via the POSIX interface, this modifier has no effect, as there is no via the POSIX interface, this modifier has no effect, as there is no
facility for passing a length.) facility for passing a length.)
When testing pcre2_substitute(), this modifier also has the effect of When testing pcre2_substitute(), this modifier also has the effect of
passing the replacement string as zero-terminated. passing the replacement string as zero-terminated.
THE ALTERNATIVE MATCHING FUNCTION THE ALTERNATIVE MATCHING FUNCTION
By default, pcre2test uses the standard PCRE2 matching function, By default, pcre2test uses the standard PCRE2 matching function,
pcre2_match() to match each subject line. PCRE2 also supports an alter- pcre2_match() to match each subject line. PCRE2 also supports an alter-
native matching function, pcre2_dfa_match(), which operates in a dif- native matching function, pcre2_dfa_match(), which operates in a dif-
ferent way, and has some restrictions. The differences between the two ferent way, and has some restrictions. The differences between the two
functions are described in the pcre2matching documentation. functions are described in the pcre2matching documentation.
If the dfa modifier is set, the alternative matching function is used. If the dfa modifier is set, the alternative matching function is used.
This function finds all possible matches at a given point in the sub- This function finds all possible matches at a given point in the sub-
ject. If, however, the dfa_shortest modifier is set, processing stops ject. If, however, the dfa_shortest modifier is set, processing stops
after the first match is found. This is always the shortest possible after the first match is found. This is always the shortest possible
match. match.
DEFAULT OUTPUT FROM pcre2test DEFAULT OUTPUT FROM pcre2test
This section describes the output when the normal matching function, This section describes the output when the normal matching function,
pcre2_match(), is being used. pcre2_match(), is being used.
When a match succeeds, pcre2test outputs the list of captured sub- When a match succeeds, pcre2test outputs the list of captured sub-
strings, starting with number 0 for the string that matched the whole strings, starting with number 0 for the string that matched the whole
pattern. Otherwise, it outputs "No match" when the return is pattern. Otherwise, it outputs "No match" when the return is
PCRE2_ERROR_NOMATCH, or "Partial match:" followed by the partially PCRE2_ERROR_NOMATCH, or "Partial match:" followed by the partially
matching substring when the return is PCRE2_ERROR_PARTIAL. (Note that matching substring when the return is PCRE2_ERROR_PARTIAL. (Note that
this is the entire substring that was inspected during the partial this is the entire substring that was inspected during the partial
match; it may include characters before the actual match start if a match; it may include characters before the actual match start if a
lookbehind assertion, \K, \b, or \B was involved.) lookbehind assertion, \K, \b, or \B was involved.)
For any other return, pcre2test outputs the PCRE2 negative error number For any other return, pcre2test outputs the PCRE2 negative error number
and a short descriptive phrase. If the error is a failed UTF string and a short descriptive phrase. If the error is a failed UTF string
check, the offset of the start of the failing character and the reason check, the code unit offset of the start of the failing character is
code are also output. Here is an example of an interactive pcre2test also output. Here is an example of an interactive pcre2test run.
run.
$ pcre2test $ pcre2test
PCRE2 version 9.00 2014-05-10 PCRE2 version 9.00 2014-05-10
@ -988,8 +990,8 @@ DEFAULT OUTPUT FROM pcre2test
No match No match
Unset capturing substrings that are not followed by one that is set are Unset capturing substrings that are not followed by one that is set are
not returned by pcre2_match(), and are not shown by pcre2test. In the not shown by pcre2test unless the allcaptures modifier is specified. In
following example, there are two capturing substrings, but when the the following example, there are two capturing substrings, but when the
first data line is matched, the second, unset substring is not shown. first data line is matched, the second, unset substring is not shown.
An "internal" unset substring is shown as "<unset>", as for the second An "internal" unset substring is shown as "<unset>", as for the second
data line. data line.
@ -1028,8 +1030,8 @@ DEFAULT OUTPUT FROM pcre2test
1: pp 1: pp
"No match" is output only if the first match attempt fails. Here is an "No match" is output only if the first match attempt fails. Here is an
example of a failure message (the offset 4 that is specified by \>4 is example of a failure message (the offset 4 that is specified by the
past the end of the subject string): offset modifier is past the end of the subject string):
re> /xyz/ re> /xyz/
data> xyz\=offset=4 data> xyz\=offset=4
@ -1053,13 +1055,13 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
1: tang 1: tang
2: tan 2: tan
(Using the normal matching function on this data finds only "tang".) Using the normal matching function on this data finds only "tang". The
The longest matching string is always given first (and numbered zero). longest matching string is always given first (and numbered zero).
After a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", After a PCRE2_ERROR_PARTIAL return, the output is "Partial match:",
followed by the partially matching substring. (Note that this is the followed by the partially matching substring. Note that this is the
entire substring that was inspected during the partial match; it may entire substring that was inspected during the partial match; it may
include characters before the actual match start if a lookbehind asser- include characters before the actual match start if a lookbehind asser-
tion, \K, \b, or \B was involved.) tion, \b, or \B was involved. (\K is not supported for DFA matching.)
If global matching is requested, the search for further matches resumes If global matching is requested, the search for further matches resumes
at the end of the longest match. For example: at the end of the longest match. For example:
@ -1183,5 +1185,5 @@ AUTHOR
REVISION REVISION
Last updated: 14 November 2014 Last updated: 23 November 2014
Copyright (c) 1997-2014 University of Cambridge. Copyright (c) 1997-2014 University of Cambridge.

4
doc/pcre2unicode.3
View File

@ -108,8 +108,8 @@ case-equivalent, and these are treated as such.
.sp .sp
When the PCRE2_UTF option is set, the strings passed as patterns and subjects When the PCRE2_UTF option is set, the strings passed as patterns and subjects
are (by default) checked for validity on entry to the relevant functions. are (by default) checked for validity on entry to the relevant functions.
If an invalid UTF string is passed, an negative error code is returned. The If an invalid UTF string is passed, an negative error code is returned. The
code unit offset to the offending character can be extracted from the match code unit offset to the offending character can be extracted from the match
data block by calling \fBpcre2_get_startchar()\fP, which is used for this data block by calling \fBpcre2_get_startchar()\fP, which is used for this
purpose after a UTF error. purpose after a UTF error.
.P .P

14
src/config.h.generic
View File

@ -18,10 +18,10 @@ to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line. macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be defined
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All (conventionally to 1) for TRUE, and not defined at all for FALSE. All such
such macros are listed as a commented #undef in config.h.generic. Macros such macros are listed as a commented #undef in config.h.generic. Macros such as
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D. surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
@ -201,7 +201,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_NAME "PCRE2" #define PACKAGE_NAME "PCRE2"
/* Define to the full name and version of this package. */ /* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE2 10.00-DEV" #define PACKAGE_STRING "PCRE2 10.00-RC1"
/* Define to the one symbol short name of this package. */ /* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2" #define PACKAGE_TARNAME "pcre2"
@ -210,7 +210,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_URL "" #define PACKAGE_URL ""
/* Define to the version of this package. */ /* Define to the version of this package. */
#define PACKAGE_VERSION "10.00-DEV" #define PACKAGE_VERSION "10.00-RC1"
/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
parentheses (of any kind) in a pattern. This limits the amount of system parentheses (of any kind) in a pattern. This limits the amount of system
@ -288,7 +288,7 @@ sure both macros are undefined; an emulation function will then be used. */
/* #undef SUPPORT_VALGRIND */ /* #undef SUPPORT_VALGRIND */
/* Version number of package */ /* Version number of package */
#define VERSION "10.00-DEV" #define VERSION "10.00-RC1"
/* Define to empty if `const' does not conform to ANSI C. */ /* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */ /* #undef const */

71
src/pcre2.h.generic
View File

@ -43,8 +43,8 @@ POSSIBILITY OF SUCH DAMAGE.
#define PCRE2_MAJOR 10 #define PCRE2_MAJOR 10
#define PCRE2_MINOR 00 #define PCRE2_MINOR 00
#define PCRE2_PRERELEASE -DEV #define PCRE2_PRERELEASE -RC1
#define PCRE2_DATE 2014-99-99 #define PCRE2_DATE 2014-11-24
/* When an application links to a PCRE DLL in Windows, the symbols that are /* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate imported have to be identified as such. When building PCRE2, the appropriate
@ -125,8 +125,8 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_JIT_PARTIAL_HARD 0x00000004u #define PCRE2_JIT_PARTIAL_HARD 0x00000004u
/* These are for pcre2_match() and pcre2_dfa_match(). Note that PCRE2_ANCHORED, /* These are for pcre2_match() and pcre2_dfa_match(). Note that PCRE2_ANCHORED,
PCRE2_NO_START_OPTIMIZE, and PCRE2_NO_UTF_CHECK can also be passed to these and PCRE2_NO_UTF_CHECK can also be passed to these functions, so take care not
functions, so take care not to define synonyms by mistake. */ to define synonyms by mistake. */
#define PCRE2_NOTBOL 0x00000001u #define PCRE2_NOTBOL 0x00000001u
#define PCRE2_NOTEOL 0x00000002u #define PCRE2_NOTEOL 0x00000002u
@ -140,6 +140,10 @@ functions, so take care not to define synonyms by mistake. */
#define PCRE2_DFA_RESTART 0x00000040u #define PCRE2_DFA_RESTART 0x00000040u
#define PCRE2_DFA_SHORTEST 0x00000080u #define PCRE2_DFA_SHORTEST 0x00000080u
/* This is an additional option for pcre2_substitute(). */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
/* Newline and \R settings, for use in compile contexts. The newline values /* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be must be kept in step with values set in config.h and both sets must all be
greater than zero. */ greater than zero. */
@ -202,24 +206,25 @@ context functions. */
#define PCRE2_ERROR_BADMODE (-32) #define PCRE2_ERROR_BADMODE (-32)
#define PCRE2_ERROR_BADOFFSET (-33) #define PCRE2_ERROR_BADOFFSET (-33)
#define PCRE2_ERROR_BADOPTION (-34) #define PCRE2_ERROR_BADOPTION (-34)
#define PCRE2_ERROR_BADUTFOFFSET (-35) #define PCRE2_ERROR_BADREPLACEMENT (-35)
#define PCRE2_ERROR_CALLOUT (-36) /* Never used by PCRE2 itself */ #define PCRE2_ERROR_BADUTFOFFSET (-36)
#define PCRE2_ERROR_DFA_BADRESTART (-37) #define PCRE2_ERROR_CALLOUT (-37) /* Never used by PCRE2 itself */
#define PCRE2_ERROR_DFA_RECURSE (-38) #define PCRE2_ERROR_DFA_BADRESTART (-38)
#define PCRE2_ERROR_DFA_UCOND (-39) #define PCRE2_ERROR_DFA_RECURSE (-39)
#define PCRE2_ERROR_DFA_UITEM (-40) #define PCRE2_ERROR_DFA_UCOND (-40)
#define PCRE2_ERROR_DFA_WSSIZE (-41) #define PCRE2_ERROR_DFA_UITEM (-41)
#define PCRE2_ERROR_INTERNAL (-42) #define PCRE2_ERROR_DFA_WSSIZE (-42)
#define PCRE2_ERROR_JIT_BADOPTION (-43) #define PCRE2_ERROR_INTERNAL (-43)
#define PCRE2_ERROR_JIT_STACKLIMIT (-44) #define PCRE2_ERROR_JIT_BADOPTION (-44)
#define PCRE2_ERROR_MATCHLIMIT (-45) #define PCRE2_ERROR_JIT_STACKLIMIT (-45)
#define PCRE2_ERROR_NOMEMORY (-46) #define PCRE2_ERROR_MATCHLIMIT (-46)
#define PCRE2_ERROR_NOSUBSTRING (-47) #define PCRE2_ERROR_NOMEMORY (-47)
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-48) #define PCRE2_ERROR_NOSUBSTRING (-48)
#define PCRE2_ERROR_NULL (-49) #define PCRE2_ERROR_NOUNIQUESUBSTRING (-49)
#define PCRE2_ERROR_RECURSELOOP (-50) #define PCRE2_ERROR_NULL (-50)
#define PCRE2_ERROR_RECURSIONLIMIT (-51) #define PCRE2_ERROR_RECURSELOOP (-51)
#define PCRE2_ERROR_UNSET (-52) #define PCRE2_ERROR_RECURSIONLIMIT (-52)
#define PCRE2_ERROR_UNSET (-53)
/* Request types for pcre2_pattern_info() */ /* Request types for pcre2_pattern_info() */
@ -406,7 +411,8 @@ PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create(uint32_t, \ pcre2_match_data *pcre2_match_data_create(uint32_t, \
pcre2_general_context *); \ pcre2_general_context *); \
PCRE2_EXP_DECL \ PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create_from_pattern(pcre2_code *, \ pcre2_match_data *pcre2_match_data_create_from_pattern(\
const pcre2_code *, \
pcre2_general_context *); \ pcre2_general_context *); \
PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, \ PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_SIZE, uint32_t, \ PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
@ -447,19 +453,28 @@ PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \
PCRE2_UCHAR ***, PCRE2_SIZE **); PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int pcre2_substitute(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_UCHAR *, \
PCRE2_SIZE *);
/* Functions for JIT processing */ /* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \ #define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t); \ PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \ PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \ PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, \ pcre2_match_data *, pcre2_match_context *); \
pcre2_jit_stack *); \ PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *);\
PCRE2_EXP_DECL \ PCRE2_EXP_DECL \
pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *, \ pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *, \
PCRE2_SIZE, PCRE2_SIZE); \ PCRE2_SIZE, PCRE2_SIZE); \
PCRE2_EXP_DECL void pcre2_jit_stack_assign(const pcre2_code *, \ PCRE2_EXP_DECL void pcre2_jit_stack_assign(pcre2_match_context *, \
pcre2_jit_callback, void *); \ pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *); PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *);
@ -551,6 +566,7 @@ pcre2_compile are called by application code. */
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_) #define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_) #define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_) #define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)
#define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_) #define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_)
#define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_) #define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
#define pcre2_substring_free PCRE2_SUFFIX(pcre2_substring_free_) #define pcre2_substring_free PCRE2_SUFFIX(pcre2_substring_free_)
@ -577,6 +593,7 @@ PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \ PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \ PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \ PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_SUBSTRING_FUNCTIONS \ PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_JIT_FUNCTIONS \ PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS PCRE2_OTHER_FUNCTIONS

6
src/pcre2_internal.h
View File

@ -1570,13 +1570,13 @@ enum {
/* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro /* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro
definitions that follow must also be updated to match. There are also tables definitions that follow must also be updated to match. There are also tables
called "opcode_possessify" in pcre_compile.c and "coptable" and "poptable" in called "opcode_possessify" in pcre2_compile.c and "coptable" and "poptable" in
pcre_dfa_exec.c that must be updated. */ pcre2_dfa_exec.c that must be updated. */
/* This macro defines textual names for all the opcodes. These are used only /* This macro defines textual names for all the opcodes. These are used only
for debugging, and some of them are only partial names. The macro is referenced for debugging, and some of them are only partial names. The macro is referenced
only in pcre_printint.c, which fills out the full names in many cases (and in only in pcre2_printint.c, which fills out the full names in many cases (and in
some cases doesn't actually use these names at all). */ some cases doesn't actually use these names at all). */
#define OP_NAME_LIST \ #define OP_NAME_LIST \

4
src/pcre2test.c
View File

@ -5570,13 +5570,13 @@ else for (gmatched = 0;; gmatched++)
fprintf(outfile, "Failed: error %d: ", capcount); fprintf(outfile, "Failed: error %d: ", capcount);
PCRE2_GET_ERROR_MESSAGE(mlen, capcount, pbuffer); PCRE2_GET_ERROR_MESSAGE(mlen, capcount, pbuffer);
PCHARSV(CASTVAR(void *, pbuffer), 0, mlen, FALSE, outfile); PCHARSV(CASTVAR(void *, pbuffer), 0, mlen, FALSE, outfile);
if (capcount <= PCRE2_ERROR_UTF8_ERR1 && if (capcount <= PCRE2_ERROR_UTF8_ERR1 &&
capcount >= PCRE2_ERROR_UTF32_ERR2) capcount >= PCRE2_ERROR_UTF32_ERR2)
{ {
PCRE2_SIZE startchar; PCRE2_SIZE startchar;
PCRE2_GET_STARTCHAR(startchar, match_data); PCRE2_GET_STARTCHAR(startchar, match_data);
fprintf(outfile, " at offset %ld", startchar); fprintf(outfile, " at offset %ld", startchar);
} }
fprintf(outfile, "\n"); fprintf(outfile, "\n");
break; break;
} }