mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-02-07 06:53:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add PCRE2 library to third_party

Browse source
This commit is contained in:
Justine Tunney 2023-12-10 05:59:18 -08:00
parent 4f66d7f2dd
commit b27e9fe845
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
47 changed files with 58274 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
Makefile
View file

@ -225,6 +225,7 @@ include third_party/stb/BUILD.mk # │
include third_party/mbedtls/BUILD.mk # │ include third_party/mbedtls/BUILD.mk # │
include third_party/libcxx/BUILD.mk # │ include third_party/libcxx/BUILD.mk # │
include third_party/ggml/BUILD.mk # │ include third_party/ggml/BUILD.mk # │
include third_party/pcre/BUILD.mk # │
include third_party/radpajama/BUILD.mk # │ include third_party/radpajama/BUILD.mk # │
include net/https/BUILD.mk # │ include net/https/BUILD.mk # │
include third_party/regex/BUILD.mk #─┘ include third_party/regex/BUILD.mk #─┘

1
third_party/BUILD.mk vendored
View file

@ -24,6 +24,7 @@ o/$(MODE)/third_party: \
o/$(MODE)/third_party/mbedtls \ o/$(MODE)/third_party/mbedtls \
o/$(MODE)/third_party/musl \ o/$(MODE)/third_party/musl \
o/$(MODE)/third_party/nsync \ o/$(MODE)/third_party/nsync \
o/$(MODE)/third_party/pcre \
o/$(MODE)/third_party/puff \ o/$(MODE)/third_party/puff \
o/$(MODE)/third_party/python \ o/$(MODE)/third_party/python \
o/$(MODE)/third_party/quickjs \ o/$(MODE)/third_party/quickjs \

69
third_party/pcre/BUILD.mk vendored Normal file
View file

@ -0,0 +1,69 @@
#-*-mode:makefile-gmake;indent-tabs-mode:t;tab-width:8;coding:utf-8-*-┐
#───vi: set et ft=make ts=8 tw=8 fenc=utf-8 :vi───────────────────────┘
PKGS += THIRD_PARTY_PCRE
THIRD_PARTY_PCRE_ARTIFACTS += THIRD_PARTY_PCRE_A
THIRD_PARTY_PCRE = $(THIRD_PARTY_PCRE_A_DEPS) $(THIRD_PARTY_PCRE_A)
THIRD_PARTY_PCRE_A = o/$(MODE)/third_party/pcre/pcre.a
THIRD_PARTY_PCRE_A_FILES := $(wildcard third_party/pcre/*)
THIRD_PARTY_PCRE_A_HDRS = $(filter %.h,$(THIRD_PARTY_PCRE_A_FILES))
THIRD_PARTY_PCRE_A_INCS = $(filter %.inc,$(THIRD_PARTY_PCRE_A_FILES))
THIRD_PARTY_PCRE_A_SRCS = $(filter %.c,$(THIRD_PARTY_PCRE_A_FILES))
THIRD_PARTY_PCRE_A_OBJS = $(THIRD_PARTY_PCRE_A_SRCS:%.c=o/$(MODE)/%.o)
THIRD_PARTY_PCRE_A_CHECKS = \
$(THIRD_PARTY_PCRE_A).pkg \
o/$(MODE)/third_party/pcre/pcre2posix_test.com.runs
THIRD_PARTY_PCRE_A_DIRECTDEPS = \
LIBC_CALLS \
LIBC_FMT \
LIBC_INTRIN \
LIBC_MEM \
LIBC_NEXGEN32E \
LIBC_PROC \
LIBC_RUNTIME \
LIBC_STDIO \
LIBC_STR \
LIBC_SYSV
THIRD_PARTY_PCRE_A_DEPS := \
$(call uniq,$(foreach x,$(THIRD_PARTY_PCRE_A_DIRECTDEPS),$($(x))))
$(THIRD_PARTY_PCRE_A): \
third_party/pcre/ \
$(THIRD_PARTY_PCRE_A).pkg \
$(THIRD_PARTY_PCRE_A_OBJS)
$(THIRD_PARTY_PCRE_A).pkg: \
$(THIRD_PARTY_PCRE_A_OBJS) \
$(foreach x,$(THIRD_PARTY_PCRE_A_DIRECTDEPS),$($(x)_A).pkg)
$(THIRD_PARTY_PCRE_A_OBJS): private CPPFLAGS += -DHAVE_CONFIG_H
o/$(MODE)/third_party/pcre/%.com.dbg: \
$(THIRD_PARTY_PCRE) \
o/$(MODE)/third_party/pcre/%.o \
$(CRT) \
$(APE_NO_MODIFY_SELF)
@$(APELINK)
THIRD_PARTY_PCRE_COMS = \
o/$(MODE)/third_party/pcre/pcre2grep.com \
o/$(MODE)/third_party/pcre/pcre2posix_test.com
THIRD_PARTY_PCRE_BINS = $(THIRD_PARTY_PCRE_COMS) $(THIRD_PARTY_PCRE_COMS:%=%.dbg)
THIRD_PARTY_PCRE_LIBS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)))
THIRD_PARTY_PCRE_SRCS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)_SRCS))
THIRD_PARTY_PCRE_HDRS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)_HDRS))
THIRD_PARTY_PCRE_INCS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)_INCS))
THIRD_PARTY_PCRE_CHECKS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)_CHECKS))
THIRD_PARTY_PCRE_OBJS = $(foreach x,$(THIRD_PARTY_PCRE_ARTIFACTS),$($(x)_OBJS))
$(THIRD_PARTY_PCRE_OBJS): $(BUILD_FILES) third_party/pcre/BUILD.mk
.PHONY: o/$(MODE)/third_party/pcre
o/$(MODE)/third_party/pcre: \
$(THIRD_PARTY_PCRE_A) \
$(THIRD_PARTY_PCRE_BINS) \
$(THIRD_PARTY_PCRE_CHECKS)

94
third_party/pcre/LICENCE vendored Normal file
View file

@ -0,0 +1,94 @@
PCRE2 LICENCE
-------------
PCRE2 is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Releases 10.00 and above of PCRE2 are distributed under the terms of the "BSD"
licence, as specified below, with one exemption for certain binary
redistributions. The documentation for PCRE2, supplied in the "doc" directory,
is distributed under the same terms as the software itself. The data in the
testdata directory is not copyrighted and is in the public domain.
The basic library functions are written in C and are freestanding. Also
included in the distribution is a just-in-time compiler that can be used to
optimize pattern matching. This is an optional feature that can be omitted when
the library is built.
THE BASIC LIBRARY FUNCTIONS
---------------------------
Written by: Philip Hazel
Email local part: Philip.Hazel
Email domain: gmail.com
Retired from University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2022 University of Cambridge
All rights reserved.
PCRE2 JUST-IN-TIME COMPILATION SUPPORT
--------------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2010-2022 Zoltan Herczeg
All rights reserved.
STACK-LESS JUST-IN-TIME COMPILER
--------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2009-2022 Zoltan Herczeg
All rights reserved.
THE "BSD" LICENCE
-----------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notices,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notices, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of any
contributors may be used to endorse or promote products derived from this
software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
EXEMPTION FOR BINARY LIBRARY-LIKE PACKAGES
------------------------------------------
The second condition in the BSD licence (covering binary redistributions) does
not apply all the way down a chain of software. If binary package A includes
PCRE2, it must respect the condition, but if package B is software that
includes package A, the condition is not imposed on package B unless it uses
PCRE2 independently.
End

15
third_party/pcre/README.cosmo vendored Normal file
View file

@ -0,0 +1,15 @@
DESCRIPTION
PCRE2 is a regular expression library
LICENSE
PCRE2 License
ORIGIN
https://github.com/PCRE2Project/pcre2/archive/refs/tags/pcre2-10.42.tar.gz
LOCAL CHANGES
Removed JIT code.

446
third_party/pcre/config.h vendored Normal file
View file

@ -0,0 +1,446 @@
/* src/config.h. Generated from config.h.in by configure. */
/* src/config.h.in. Generated from configure.ac by autoheader. */
/* PCRE2 is written in Standard C, but there are a few non-standard things it
can cope with, allowing it to run on SunOS4 and other "close to standard"
systems.
In environments that support the GNU autotools, config.h.in is converted into
config.h by the "configure" script. In environments that use CMake,
config-cmake.in is converted into config.h. If you are going to build PCRE2 "by
hand" without using "configure" or CMake, you should copy the distributed
config.h.generic to config.h, and edit the macro definitions to be the way you
need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
so that config.h is included at the start of every source.
Alternatively, you can avoid editing by using -D on the compiler command line
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
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as 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.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
sure both macros are undefined; an emulation function will then be used. */
/* By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined (to any
value), this is changed so that backslash-R matches only CR, LF, or CRLF.
The build-time default can be overridden by the user of PCRE2 at runtime.
*/
/* #undef BSR_ANYCRLF */
/* Define to any value to disable the use of the z and t modifiers in
formatting settings such as %zu or %td (this is rarely needed). */
/* #undef DISABLE_PERCENT_ZT */
/* If you are compiling for a system that uses EBCDIC instead of ASCII
character codes, define this macro to any value. When EBCDIC is set, PCRE2
assumes that all input strings are in EBCDIC. If you do not define this
macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
is not possible to build a version of PCRE2 that supports both EBCDIC and
UTF-8/16/32. */
/* #undef EBCDIC */
/* In an EBCDIC environment, define this macro to any value to arrange for the
NL character to be 0x25 instead of the default 0x15. NL plays the role that
LF does in an ASCII/Unicode environment. */
/* #undef EBCDIC_NL25 */
/* Define this if your compiler supports __attribute__((uninitialized)) */
#define HAVE_ATTRIBUTE_UNINITIALIZED 1
/* Define to 1 if you have the `bcopy' function. */
#define HAVE_BCOPY 1
/* Define to 1 if you have the <bzlib.h> header file. */
/* #undef HAVE_BZLIB_H */
/* Define to 1 if you have the <dirent.h> header file. */
#define HAVE_DIRENT_H 1
/* Define to 1 if you have the <dlfcn.h> header file. */
#define HAVE_DLFCN_H 1
/* Define to 1 if you have the <editline/readline.h> header file. */
/* #undef HAVE_EDITLINE_READLINE_H */
/* Define to 1 if you have the <edit/readline/readline.h> header file. */
/* #undef HAVE_EDIT_READLINE_READLINE_H */
/* Define to 1 if you have the <inttypes.h> header file. */
#define HAVE_INTTYPES_H 1
/* Define to 1 if you have the <limits.h> header file. */
#define HAVE_LIMITS_H 1
/* Define to 1 if you have the `memfd_create' function. */
#define HAVE_MEMFD_CREATE 1
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE 1
/* Define to 1 if you have the <minix/config.h> header file. */
/* #undef HAVE_MINIX_CONFIG_H */
/* Define to 1 if you have the `mkostemp' function. */
#define HAVE_MKOSTEMP 1
/* Define if you have POSIX threads libraries and header files. */
/* #undef HAVE_PTHREAD */
/* Have PTHREAD_PRIO_INHERIT. */
/* #undef HAVE_PTHREAD_PRIO_INHERIT */
/* Define to 1 if you have the <readline.h> header file. */
/* #undef HAVE_READLINE_H */
/* Define to 1 if you have the <readline/history.h> header file. */
/* #undef HAVE_READLINE_HISTORY_H */
/* Define to 1 if you have the <readline/readline.h> header file. */
/* #undef HAVE_READLINE_READLINE_H */
/* Define to 1 if you have the `realpath' function. */
#define HAVE_REALPATH 1
/* Define to 1 if you have the `secure_getenv' function. */
#define HAVE_SECURE_GETENV 1
/* Define to 1 if you have the <stdint.h> header file. */
#define HAVE_STDINT_H 1
/* Define to 1 if you have the <stdio.h> header file. */
#define HAVE_STDIO_H 1
/* Define to 1 if you have the <stdlib.h> header file. */
#define HAVE_STDLIB_H 1
/* Define to 1 if you have the `strerror' function. */
#define HAVE_STRERROR 1
/* Define to 1 if you have the <strings.h> header file. */
#define HAVE_STRINGS_H 1
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
/* Define to 1 if you have the <sys/stat.h> header file. */
#define HAVE_SYS_STAT_H 1
/* Define to 1 if you have the <sys/types.h> header file. */
#define HAVE_SYS_TYPES_H 1
/* Define to 1 if you have the <sys/wait.h> header file. */
#define HAVE_SYS_WAIT_H 1
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* Define to 1 if the compiler supports simple visibility declarations. */
#define HAVE_VISIBILITY 1
/* Define to 1 if you have the <wchar.h> header file. */
#define HAVE_WCHAR_H 1
/* Define to 1 if you have the <windows.h> header file. */
/* #undef HAVE_WINDOWS_H */
/* Define to 1 if you have the <zlib.h> header file. */
/* #undef HAVE_ZLIB_H */
/* This limits the amount of memory that may be used while matching a pattern.
It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply
to JIT matching. The value is in kibibytes (units of 1024 bytes). */
#define HEAP_LIMIT 20000000
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 65535 code units long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes
instead. This allows for longer patterns in extreme cases. */
#define LINK_SIZE 2
/* Define to the sub-directory where libtool stores uninstalled libraries. */
#define LT_OBJDIR ".libs/"
/* The value of MATCH_LIMIT determines the default number of times the
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases. */
#define MATCH_LIMIT 10000000
/* The above limit applies to all backtracks, whether or not they are nested.
In some environments it is desirable to limit the nesting of backtracking
(that is, the depth of tree that is searched) more strictly, in order to
restrict the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it
must be less than the value of MATCH_LIMIT. The default is to use the same
value as MATCH_LIMIT. There is a runtime method for setting a different
limit. In the case of pcre2_dfa_match(), this limit controls the depth of
the internal nested function calls that are used for pattern recursions,
lookarounds, and atomic groups. */
#define MATCH_LIMIT_DEPTH MATCH_LIMIT
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#define MAX_NAME_COUNT 10000
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#define MAX_NAME_SIZE 32
/* Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns. */
/* #undef NEVER_BACKSLASH_C */
/* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF), and 6 (NUL). */
#define NEWLINE_DEFAULT 2
/* Name of package */
#define PACKAGE "pcre2"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT ""
/* Define to the full name of this package. */
#define PACKAGE_NAME "PCRE2"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE2 10.42"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2"
/* Define to the home page for this package. */
#define PACKAGE_URL ""
/* Define to the version of this package. */
#define PACKAGE_VERSION "10.42"
/* 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
stack that is used while compiling a pattern. */
#define PARENS_NEST_LIMIT 250
/* The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing
very long lines. The actual amount of memory used by pcre2grep is three
times this number, because it allows for the buffering of "before" and
"after" lines. */
#define PCRE2GREP_BUFSIZE 20480
/* The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines. */
#define PCRE2GREP_MAX_BUFSIZE 1048576
/* to make a symbol visible */
#define PCRE2POSIX_EXP_DECL extern __attribute__ ((visibility ("default")))
/* to make a symbol visible */
#define PCRE2POSIX_EXP_DEFN extern __attribute__ ((visibility ("default")))
/* Define to any value to include debugging code. */
/* #undef PCRE2_DEBUG */
/* to make a symbol visible */
#define PCRE2_EXP_DECL extern __attribute__ ((visibility ("default")))
/* If you are compiling for a system other than a Unix-like system or
Win32, and it needs some magic to be inserted before the definition
of a function that is exported by the library, define this macro to
contain the relevant magic. If you do not define this macro, a suitable
__declspec value is used for Windows systems; in other environments
"extern" is used for a C compiler and "extern C" for a C++ compiler.
This macro apears at the start of every exported function that is part
of the external API. It does not appear on functions that are "external"
in the C sense, but which are internal to the library. */
#define PCRE2_EXP_DEFN __attribute__ ((visibility ("default")))
/* Define to any value if linking statically (TODO: make nice with Libtool) */
#define PCRE2_STATIC 1
/* Define to necessary symbol if this constant uses a non-standard name on
your system. */
/* #undef PTHREAD_CREATE_JOINABLE */
/* Define to any non-zero number to enable support for SELinux compatible
executable memory allocator in JIT. Note that this will have no effect
unless SUPPORT_JIT is also defined. */
/* #undef SLJIT_PROT_EXECUTABLE_ALLOCATOR */
/* Define to 1 if all of the C90 standard headers exist (not just the ones
required in a freestanding environment). This macro is provided for
backward compatibility; new code need not use it. */
#define STDC_HEADERS 1
/* Define to any value to enable support for Just-In-Time compiling. */
/* #undef SUPPORT_JIT */
/* Define to any value to allow pcre2grep to be linked with libbz2, so that it
is able to handle .bz2 files. */
/* #undef SUPPORT_LIBBZ2 */
/* Define to any value to allow pcre2test to be linked with libedit. */
/* #undef SUPPORT_LIBEDIT */
/* Define to any value to allow pcre2test to be linked with libreadline. */
/* #undef SUPPORT_LIBREADLINE */
/* Define to any value to allow pcre2grep to be linked with libz, so that it
is able to handle .gz files. */
/* #undef SUPPORT_LIBZ */
/* Define to any value to enable callout script support in pcre2grep. */
#define SUPPORT_PCRE2GREP_CALLOUT /**/
/* Define to any value to enable fork support in pcre2grep callout scripts.
This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also defined.
*/
#define SUPPORT_PCRE2GREP_CALLOUT_FORK /**/
/* Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined. */
/* #undef SUPPORT_PCRE2GREP_JIT */
/* Define to any value to enable the 16 bit PCRE2 library. */
/* #undef SUPPORT_PCRE2_16 */
/* Define to any value to enable the 32 bit PCRE2 library. */
/* #undef SUPPORT_PCRE2_32 */
/* Define to any value to enable the 8 bit PCRE2 library. */
#define SUPPORT_PCRE2_8 /**/
/* Define to any value to enable support for Unicode and UTF encoding. This
will work even in an EBCDIC environment, but it is incompatible with the
EBCDIC macro. That is, PCRE2 can support *either* EBCDIC code *or*
ASCII/Unicode, but not both at once. */
#define SUPPORT_UNICODE /**/
/* Define to any value for valgrind support to find invalid memory reads. */
/* #undef SUPPORT_VALGRIND */
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# define _ALL_SOURCE 1
#endif
/* Enable general extensions on macOS. */
#ifndef _DARWIN_C_SOURCE
# define _DARWIN_C_SOURCE 1
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# define __EXTENSIONS__ 1
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE 1
#endif
/* Enable X/Open compliant socket functions that do not require linking
with -lxnet on HP-UX 11.11. */
#ifndef _HPUX_ALT_XOPEN_SOCKET_API
# define _HPUX_ALT_XOPEN_SOCKET_API 1
#endif
/* Identify the host operating system as Minix.
This macro does not affect the system headers' behavior.
A future release of Autoconf may stop defining this macro. */
#ifndef _MINIX
/* # undef _MINIX */
#endif
/* Enable general extensions on NetBSD.
Enable NetBSD compatibility extensions on Minix. */
#ifndef _NETBSD_SOURCE
# define _NETBSD_SOURCE 1
#endif
/* Enable OpenBSD compatibility extensions on NetBSD.
Oddly enough, this does nothing on OpenBSD. */
#ifndef _OPENBSD_SOURCE
# define _OPENBSD_SOURCE 1
#endif
/* Define to 1 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_SOURCE
/* # undef _POSIX_SOURCE */
#endif
/* Define to 2 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_1_SOURCE
/* # undef _POSIX_1_SOURCE */
#endif
/* Enable POSIX-compatible threading on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# define _POSIX_PTHREAD_SEMANTICS 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-5:2014. */
#ifndef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
# define __STDC_WANT_IEC_60559_ATTRIBS_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-1:2014. */
#ifndef __STDC_WANT_IEC_60559_BFP_EXT__
# define __STDC_WANT_IEC_60559_BFP_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-2:2015. */
#ifndef __STDC_WANT_IEC_60559_DFP_EXT__
# define __STDC_WANT_IEC_60559_DFP_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-4:2015. */
#ifndef __STDC_WANT_IEC_60559_FUNCS_EXT__
# define __STDC_WANT_IEC_60559_FUNCS_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-3:2015. */
#ifndef __STDC_WANT_IEC_60559_TYPES_EXT__
# define __STDC_WANT_IEC_60559_TYPES_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TR 24731-2:2010. */
#ifndef __STDC_WANT_LIB_EXT2__
# define __STDC_WANT_LIB_EXT2__ 1
#endif
/* Enable extensions specified by ISO/IEC 24747:2009. */
#ifndef __STDC_WANT_MATH_SPEC_FUNCS__
# define __STDC_WANT_MATH_SPEC_FUNCS__ 1
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# define _TANDEM_SOURCE 1
#endif
/* Enable X/Open extensions. Define to 500 only if necessary
to make mbstate_t available. */
#ifndef _XOPEN_SOURCE
/* # undef _XOPEN_SOURCE */
#endif
/* Version number of package */
#define VERSION "10.42"
/* Number of bits in a file offset, on hosts where this is settable. */
/* #undef _FILE_OFFSET_BITS */
/* Define for large files, on AIX-style hosts. */
/* #undef _LARGE_FILES */
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
/* Define to the type of a signed integer type of width exactly 64 bits if
such a type exists and the standard includes do not define it. */
/* #undef int64_t */
/* Define to `unsigned int' if <sys/types.h> does not define. */
/* #undef size_t */

997
third_party/pcre/pcre2.h vendored Normal file
View file

@ -0,0 +1,997 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef PCRE2_H_IDEMPOTENT_GUARD
#define PCRE2_H_IDEMPOTENT_GUARD
#ifndef PCRE2_CODE_UNIT_WIDTH
#define PCRE2_CODE_UNIT_WIDTH 8
#endif
/* The current PCRE version information. */
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 42
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2022-12-11
/* 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
export setting is defined in pcre2_internal.h, which includes this file. So we
don't change existing definitions of PCRE2_EXP_DECL. */
#if defined(_WIN32) && !defined(PCRE2_STATIC)
# ifndef PCRE2_EXP_DECL
# define PCRE2_EXP_DECL extern __declspec(dllimport)
# endif
#endif
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE2_EXP_DECL
# ifdef __cplusplus
# define PCRE2_EXP_DECL extern "C"
# else
# define PCRE2_EXP_DECL extern
# endif
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Have to include limits.h, stdlib.h, and inttypes.h to ensure that size_t and
uint8_t, UCHAR_MAX, etc are defined. Some systems that do have inttypes.h do
not have stdint.h, which is why we use inttypes.h, which according to the C
standard is a superset of stdint.h. If inttypes.h is not available the build
will break and the relevant values must be provided by some other means. */
#include <limits.h>
#include <stdlib.h>
#include <inttypes.h>
/* Allow for C++ users compiling this directly. */
#ifdef __cplusplus
extern "C" {
#endif
/* The following option bits can be passed to pcre2_compile(), pcre2_match(),
or pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it
is passed. Put these bits at the most significant end of the options word so
others can be added next to them */
#define PCRE2_ANCHORED 0x80000000u
#define PCRE2_NO_UTF_CHECK 0x40000000u
#define PCRE2_ENDANCHORED 0x20000000u
/* The following option bits can be passed only to pcre2_compile(). However,
they may affect compilation, JIT compilation, and/or interpretive execution.
The following tags indicate which:
C alters what is compiled by pcre2_compile()
J alters what is compiled by pcre2_jit_compile()
M is inspected during pcre2_match() execution
D is inspected during pcre2_dfa_match() execution
*/
#define PCRE2_ALLOW_EMPTY_CLASS 0x00000001u /* C */
#define PCRE2_ALT_BSUX 0x00000002u /* C */
#define PCRE2_AUTO_CALLOUT 0x00000004u /* C */
#define PCRE2_CASELESS 0x00000008u /* C */
#define PCRE2_DOLLAR_ENDONLY 0x00000010u /* J M D */
#define PCRE2_DOTALL 0x00000020u /* C */
#define PCRE2_DUPNAMES 0x00000040u /* C */
#define PCRE2_EXTENDED 0x00000080u /* C */
#define PCRE2_FIRSTLINE 0x00000100u /* J M D */
#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u /* C J M */
#define PCRE2_MULTILINE 0x00000400u /* C */
#define PCRE2_NEVER_UCP 0x00000800u /* C */
#define PCRE2_NEVER_UTF 0x00001000u /* C */
#define PCRE2_NO_AUTO_CAPTURE 0x00002000u /* C */
#define PCRE2_NO_AUTO_POSSESS 0x00004000u /* C */
#define PCRE2_NO_DOTSTAR_ANCHOR 0x00008000u /* C */
#define PCRE2_NO_START_OPTIMIZE 0x00010000u /* J M D */
#define PCRE2_UCP 0x00020000u /* C J M D */
#define PCRE2_UNGREEDY 0x00040000u /* C */
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
#define PCRE2_EXTENDED_MORE 0x01000000u /* C */
#define PCRE2_LITERAL 0x02000000u /* C */
#define PCRE2_MATCH_INVALID_UTF 0x04000000u /* J M D */
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
#define PCRE2_EXTRA_MATCH_WORD 0x00000004u /* C */
#define PCRE2_EXTRA_MATCH_LINE 0x00000008u /* C */
#define PCRE2_EXTRA_ESCAPED_CR_IS_LF 0x00000010u /* C */
#define PCRE2_EXTRA_ALT_BSUX 0x00000020u /* C */
#define PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK 0x00000040u /* C */
/* These are for pcre2_jit_compile(). */
#define PCRE2_JIT_COMPLETE 0x00000001u /* For full matching */
#define PCRE2_JIT_PARTIAL_SOFT 0x00000002u
#define PCRE2_JIT_PARTIAL_HARD 0x00000004u
#define PCRE2_JIT_INVALID_UTF 0x00000100u
/* These are for pcre2_match(), pcre2_dfa_match(), pcre2_jit_match(), and
pcre2_substitute(). Some are allowed only for one of the functions, and in
these cases it is noted below. Note that PCRE2_ANCHORED, PCRE2_ENDANCHORED and
PCRE2_NO_UTF_CHECK can also be passed to these functions (though
pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
#define PCRE2_NOTBOL 0x00000001u
#define PCRE2_NOTEOL 0x00000002u
#define PCRE2_NOTEMPTY 0x00000004u /* ) These two must be kept */
#define PCRE2_NOTEMPTY_ATSTART 0x00000008u /* ) adjacent to each other. */
#define PCRE2_PARTIAL_SOFT 0x00000010u
#define PCRE2_PARTIAL_HARD 0x00000020u
#define PCRE2_DFA_RESTART 0x00000040u /* pcre2_dfa_match() only */
#define PCRE2_DFA_SHORTEST 0x00000080u /* pcre2_dfa_match() only */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u /* pcre2_substitute() only */
#define PCRE2_NO_JIT 0x00002000u /* Not for pcre2_dfa_match() */
#define PCRE2_COPY_MATCHED_SUBJECT 0x00004000u
#define PCRE2_SUBSTITUTE_LITERAL 0x00008000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_MATCHED 0x00010000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_REPLACEMENT_ONLY 0x00020000u /* pcre2_substitute() only */
/* Options for pcre2_pattern_convert(). */
#define PCRE2_CONVERT_UTF 0x00000001u
#define PCRE2_CONVERT_NO_UTF_CHECK 0x00000002u
#define PCRE2_CONVERT_POSIX_BASIC 0x00000004u
#define PCRE2_CONVERT_POSIX_EXTENDED 0x00000008u
#define PCRE2_CONVERT_GLOB 0x00000010u
#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
#define PCRE2_CONVERT_GLOB_NO_STARSTAR 0x00000050u
/* 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
greater than zero. */
#define PCRE2_NEWLINE_CR 1
#define PCRE2_NEWLINE_LF 2
#define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2
/* Error codes for pcre2_compile(). Some of these are also used by
pcre2_pattern_convert(). */
#define PCRE2_ERROR_END_BACKSLASH 101
#define PCRE2_ERROR_END_BACKSLASH_C 102
#define PCRE2_ERROR_UNKNOWN_ESCAPE 103
#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104
#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105
#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106
#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107
#define PCRE2_ERROR_CLASS_RANGE_ORDER 108
#define PCRE2_ERROR_QUANTIFIER_INVALID 109
#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110
#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111
#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112
#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113
#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114
#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115
#define PCRE2_ERROR_NULL_PATTERN 116
#define PCRE2_ERROR_BAD_OPTIONS 117
#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118
#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119
#define PCRE2_ERROR_PATTERN_TOO_LARGE 120
#define PCRE2_ERROR_HEAP_FAILED 121
#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122
#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123
#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124
#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125
#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126
#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127
#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128
#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129
#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130
#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131
#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132
#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133
#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134
#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135
#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137
#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138
#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139
#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140
#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141
#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142
#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143
#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144
#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146
#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147
#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148
#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149
#define PCRE2_ERROR_CLASS_INVALID_RANGE 150
#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151
#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152
#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153
#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154
#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155
#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156
#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157
#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
/* Error 159 is obsolete and should now never occur */
#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159
#define PCRE2_ERROR_VERB_UNKNOWN 160
#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161
#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162
#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163
#define PCRE2_ERROR_INVALID_OCTAL 164
#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165
#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166
#define PCRE2_ERROR_INVALID_HEXADECIMAL 167
#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168
#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169
#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170
#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171
#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172
#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173
#define PCRE2_ERROR_UTF_IS_DISABLED 174
#define PCRE2_ERROR_UCP_IS_DISABLED 175
#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176
#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178
#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179
#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181
#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182
#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183
#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184
#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185
#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186
#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187
#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188
#define PCRE2_ERROR_INTERNAL_BAD_CODE 189
#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190
#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191
#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192
#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
#define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN 195
#define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE 196
#define PCRE2_ERROR_TOO_MANY_CAPTURES 197
#define PCRE2_ERROR_CONDITION_ATOMIC_ASSERTION_EXPECTED 198
#define PCRE2_ERROR_BACKSLASH_K_IN_LOOKAROUND 199
/* "Expected" matching error codes: no match and partial match. */
#define PCRE2_ERROR_NOMATCH (-1)
#define PCRE2_ERROR_PARTIAL (-2)
/* Error codes for UTF-8 validity checks */
#define PCRE2_ERROR_UTF8_ERR1 (-3)
#define PCRE2_ERROR_UTF8_ERR2 (-4)
#define PCRE2_ERROR_UTF8_ERR3 (-5)
#define PCRE2_ERROR_UTF8_ERR4 (-6)
#define PCRE2_ERROR_UTF8_ERR5 (-7)
#define PCRE2_ERROR_UTF8_ERR6 (-8)
#define PCRE2_ERROR_UTF8_ERR7 (-9)
#define PCRE2_ERROR_UTF8_ERR8 (-10)
#define PCRE2_ERROR_UTF8_ERR9 (-11)
#define PCRE2_ERROR_UTF8_ERR10 (-12)
#define PCRE2_ERROR_UTF8_ERR11 (-13)
#define PCRE2_ERROR_UTF8_ERR12 (-14)
#define PCRE2_ERROR_UTF8_ERR13 (-15)
#define PCRE2_ERROR_UTF8_ERR14 (-16)
#define PCRE2_ERROR_UTF8_ERR15 (-17)
#define PCRE2_ERROR_UTF8_ERR16 (-18)
#define PCRE2_ERROR_UTF8_ERR17 (-19)
#define PCRE2_ERROR_UTF8_ERR18 (-20)
#define PCRE2_ERROR_UTF8_ERR19 (-21)
#define PCRE2_ERROR_UTF8_ERR20 (-22)
#define PCRE2_ERROR_UTF8_ERR21 (-23)
/* Error codes for UTF-16 validity checks */
#define PCRE2_ERROR_UTF16_ERR1 (-24)
#define PCRE2_ERROR_UTF16_ERR2 (-25)
#define PCRE2_ERROR_UTF16_ERR3 (-26)
/* Error codes for UTF-32 validity checks */
#define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
functions, context functions, and serializing functions. They are in numerical
order. Originally they were in alphabetical order too, but now that PCRE2 is
released, the numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
#define PCRE2_ERROR_BADMAGIC (-31)
#define PCRE2_ERROR_BADMODE (-32)
#define PCRE2_ERROR_BADOFFSET (-33)
#define PCRE2_ERROR_BADOPTION (-34)
#define PCRE2_ERROR_BADREPLACEMENT (-35)
#define PCRE2_ERROR_BADUTFOFFSET (-36)
#define PCRE2_ERROR_CALLOUT (-37) /* Never used by PCRE2 itself */
#define PCRE2_ERROR_DFA_BADRESTART (-38)
#define PCRE2_ERROR_DFA_RECURSE (-39)
#define PCRE2_ERROR_DFA_UCOND (-40)
#define PCRE2_ERROR_DFA_UFUNC (-41)
#define PCRE2_ERROR_DFA_UITEM (-42)
#define PCRE2_ERROR_DFA_WSSIZE (-43)
#define PCRE2_ERROR_INTERNAL (-44)
#define PCRE2_ERROR_JIT_BADOPTION (-45)
#define PCRE2_ERROR_JIT_STACKLIMIT (-46)
#define PCRE2_ERROR_MATCHLIMIT (-47)
#define PCRE2_ERROR_NOMEMORY (-48)
#define PCRE2_ERROR_NOSUBSTRING (-49)
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
#define PCRE2_ERROR_NULL (-51)
#define PCRE2_ERROR_RECURSELOOP (-52)
#define PCRE2_ERROR_DEPTHLIMIT (-53)
#define PCRE2_ERROR_RECURSIONLIMIT (-53) /* Obsolete synonym */
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
#define PCRE2_ERROR_HEAPLIMIT (-63)
#define PCRE2_ERROR_CONVERT_SYNTAX (-64)
#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
#define PCRE2_ERROR_DFA_UINVALID_UTF (-66)
/* Request types for pcre2_pattern_info() */
#define PCRE2_INFO_ALLOPTIONS 0
#define PCRE2_INFO_ARGOPTIONS 1
#define PCRE2_INFO_BACKREFMAX 2
#define PCRE2_INFO_BSR 3
#define PCRE2_INFO_CAPTURECOUNT 4
#define PCRE2_INFO_FIRSTCODEUNIT 5
#define PCRE2_INFO_FIRSTCODETYPE 6
#define PCRE2_INFO_FIRSTBITMAP 7
#define PCRE2_INFO_HASCRORLF 8
#define PCRE2_INFO_JCHANGED 9
#define PCRE2_INFO_JITSIZE 10
#define PCRE2_INFO_LASTCODEUNIT 11
#define PCRE2_INFO_LASTCODETYPE 12
#define PCRE2_INFO_MATCHEMPTY 13
#define PCRE2_INFO_MATCHLIMIT 14
#define PCRE2_INFO_MAXLOOKBEHIND 15
#define PCRE2_INFO_MINLENGTH 16
#define PCRE2_INFO_NAMECOUNT 17
#define PCRE2_INFO_NAMEENTRYSIZE 18
#define PCRE2_INFO_NAMETABLE 19
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_DEPTHLIMIT 21
#define PCRE2_INFO_RECURSIONLIMIT 21 /* Obsolete synonym */
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
#define PCRE2_INFO_HEAPLIMIT 25
#define PCRE2_INFO_EXTRAOPTIONS 26
/* Request types for pcre2_config(). */
#define PCRE2_CONFIG_BSR 0
#define PCRE2_CONFIG_JIT 1
#define PCRE2_CONFIG_JITTARGET 2
#define PCRE2_CONFIG_LINKSIZE 3
#define PCRE2_CONFIG_MATCHLIMIT 4
#define PCRE2_CONFIG_NEWLINE 5
#define PCRE2_CONFIG_PARENSLIMIT 6
#define PCRE2_CONFIG_DEPTHLIMIT 7
#define PCRE2_CONFIG_RECURSIONLIMIT 7 /* Obsolete synonym */
#define PCRE2_CONFIG_STACKRECURSE 8 /* Obsolete */
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
#define PCRE2_CONFIG_HEAPLIMIT 12
#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13
#define PCRE2_CONFIG_COMPILED_WIDTHS 14
#define PCRE2_CONFIG_TABLES_LENGTH 15
/* Types for code units in patterns and subject strings. */
typedef uint8_t PCRE2_UCHAR8;
typedef uint16_t PCRE2_UCHAR16;
typedef uint32_t PCRE2_UCHAR32;
typedef const PCRE2_UCHAR8 *PCRE2_SPTR8;
typedef const PCRE2_UCHAR16 *PCRE2_SPTR16;
typedef const PCRE2_UCHAR32 *PCRE2_SPTR32;
/* The PCRE2_SIZE type is used for all string lengths and offsets in PCRE2,
including pattern offsets for errors and subject offsets after a match. We
define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
/* Generic types for opaque structures and JIT callback functions. These
declarations are defined in a macro that is expanded for each width later. */
#define PCRE2_TYPES_LIST \
struct pcre2_real_general_context; \
typedef struct pcre2_real_general_context pcre2_general_context; \
\
struct pcre2_real_compile_context; \
typedef struct pcre2_real_compile_context pcre2_compile_context; \
\
struct pcre2_real_match_context; \
typedef struct pcre2_real_match_context pcre2_match_context; \
\
struct pcre2_real_convert_context; \
typedef struct pcre2_real_convert_context pcre2_convert_context; \
\
struct pcre2_real_code; \
typedef struct pcre2_real_code pcre2_code; \
\
struct pcre2_real_match_data; \
typedef struct pcre2_real_match_data pcre2_match_data; \
\
struct pcre2_real_jit_stack; \
typedef struct pcre2_real_jit_stack pcre2_jit_stack; \
\
typedef pcre2_jit_stack *(*pcre2_jit_callback)(void *);
/* The structures for passing out data via callout functions. We use structures
so that new fields can be added on the end in future versions, without changing
the API of the function, thereby allowing old clients to work without
modification. Define the generic versions in a macro; the width-specific
versions are generated from this macro below. */
/* Flags for the callout_flags field. These are cleared after a callout. */
#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */
#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */
#define PCRE2_STRUCTURE_LIST \
typedef struct pcre2_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
uint32_t callout_number; /* Number compiled into pattern */ \
uint32_t capture_top; /* Max current capture */ \
uint32_t capture_last; /* Most recently closed capture */ \
PCRE2_SIZE *offset_vector; /* The offset vector */ \
PCRE2_SPTR mark; /* Pointer to current mark or NULL */ \
PCRE2_SPTR subject; /* The subject being matched */ \
PCRE2_SIZE subject_length; /* The length of the subject */ \
PCRE2_SIZE start_match; /* Offset to start of this match attempt */ \
PCRE2_SIZE current_position; /* Where we currently are in the subject */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
/* ------------------- Added for Version 1 -------------------------- */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------- Added for Version 2 -------------------------- */ \
uint32_t callout_flags; /* See above for list */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_block; \
\
typedef struct pcre2_callout_enumerate_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
uint32_t callout_number; /* Number compiled into pattern */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_enumerate_block; \
\
typedef struct pcre2_substitute_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SPTR input; /* Pointer to input subject string */ \
PCRE2_SPTR output; /* Pointer to output buffer */ \
PCRE2_SIZE output_offsets[2]; /* Changed portion of the output */ \
PCRE2_SIZE *ovector; /* Pointer to current ovector */ \
uint32_t oveccount; /* Count of pairs set in ovector */ \
uint32_t subscount; /* Substitution number */ \
/* ------------------------------------------------------------------ */ \
} pcre2_substitute_callout_block;
/* List the generic forms of all other functions in macros, which will be
expanded for each width below. Start with functions that give general
information. */
#define PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
/* Functions for manipulating contexts. */
#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_general_context_free(pcre2_general_context *);
#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_create(pcre2_general_context *);\
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_character_tables(pcre2_compile_context *, const uint8_t *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
int (*)(uint32_t, void *), void *);
#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_context_free(pcre2_match_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_substitute_callout(pcre2_match_context *, \
int (*)(pcre2_substitute_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_memory_management(pcre2_match_context *, \
void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_copy(pcre2_convert_context *); \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_convert_context_free(pcre2_convert_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
/* Functions concerned with compiling a pattern to PCRE internal code. */
#define PCRE2_COMPILE_FUNCTIONS \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
pcre2_compile_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy(const pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
#define PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), void *);
/* Functions for running a match and inspecting the result. */
#define PCRE2_MATCH_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create(uint32_t, pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create_from_pattern(const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_match_data_size(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE *PCRE2_CALL_CONVENTION \
pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_startchar(pcre2_match_data *);
/* Convenience functions for handling matched substrings. */
#define PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
PCRE2_SIZE *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
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 converting pattern source strings. */
#define PCRE2_CONVERT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *, pcre2_convert_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_converted_pattern_free(PCRE2_UCHAR *);
/* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_jit_stack *PCRE2_CALL_CONVENTION \
pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_free(pcre2_jit_stack *);
/* Other miscellaneous functions. */
#define PCRE2_OTHER_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL const uint8_t *PCRE2_CALL_CONVENTION \
pcre2_maketables(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_maketables_free(pcre2_general_context *, const uint8_t *);
/* Define macros that generate width-specific names from generic versions. The
three-level macro scheme is necessary to get the macros expanded when we want
them to be. First we get the width from PCRE2_LOCAL_WIDTH, which is used for
generating three versions of everything below. After that, PCRE2_SUFFIX will be
re-defined to use PCRE2_CODE_UNIT_WIDTH, for use when macros such as
pcre2_compile are called by application code. */
#define PCRE2_JOIN(a,b) a ## b
#define PCRE2_GLUE(a,b) PCRE2_JOIN(a,b)
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a,PCRE2_LOCAL_WIDTH)
/* Data types */
#define PCRE2_UCHAR PCRE2_SUFFIX(PCRE2_UCHAR)
#define PCRE2_SPTR PCRE2_SUFFIX(PCRE2_SPTR)
#define pcre2_code PCRE2_SUFFIX(pcre2_code_)
#define pcre2_jit_callback PCRE2_SUFFIX(pcre2_jit_callback_)
#define pcre2_jit_stack PCRE2_SUFFIX(pcre2_jit_stack_)
#define pcre2_real_code PCRE2_SUFFIX(pcre2_real_code_)
#define pcre2_real_general_context PCRE2_SUFFIX(pcre2_real_general_context_)
#define pcre2_real_compile_context PCRE2_SUFFIX(pcre2_real_compile_context_)
#define pcre2_real_convert_context PCRE2_SUFFIX(pcre2_real_convert_context_)
#define pcre2_real_match_context PCRE2_SUFFIX(pcre2_real_match_context_)
#define pcre2_real_jit_stack PCRE2_SUFFIX(pcre2_real_jit_stack_)
#define pcre2_real_match_data PCRE2_SUFFIX(pcre2_real_match_data_)
/* Data blocks */
#define pcre2_callout_block PCRE2_SUFFIX(pcre2_callout_block_)
#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
#define pcre2_substitute_callout_block PCRE2_SUFFIX(pcre2_substitute_callout_block_)
#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_)
#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_)
#define pcre2_convert_context PCRE2_SUFFIX(pcre2_convert_context_)
#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_)
#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_)
/* Functions: the complete list in alphabetical order */
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
#define pcre2_compile_context_create PCRE2_SUFFIX(pcre2_compile_context_create_)
#define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_)
#define pcre2_config PCRE2_SUFFIX(pcre2_config_)
#define pcre2_convert_context_copy PCRE2_SUFFIX(pcre2_convert_context_copy_)
#define pcre2_convert_context_create PCRE2_SUFFIX(pcre2_convert_context_create_)
#define pcre2_convert_context_free PCRE2_SUFFIX(pcre2_convert_context_free_)
#define pcre2_converted_pattern_free PCRE2_SUFFIX(pcre2_converted_pattern_free_)
#define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_)
#define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_)
#define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_)
#define pcre2_general_context_free PCRE2_SUFFIX(pcre2_general_context_free_)
#define pcre2_get_error_message PCRE2_SUFFIX(pcre2_get_error_message_)
#define pcre2_get_mark PCRE2_SUFFIX(pcre2_get_mark_)
#define pcre2_get_match_data_size PCRE2_SUFFIX(pcre2_get_match_data_size_)
#define pcre2_get_ovector_pointer PCRE2_SUFFIX(pcre2_get_ovector_pointer_)
#define pcre2_get_ovector_count PCRE2_SUFFIX(pcre2_get_ovector_count_)
#define pcre2_get_startchar PCRE2_SUFFIX(pcre2_get_startchar_)
#define pcre2_jit_compile PCRE2_SUFFIX(pcre2_jit_compile_)
#define pcre2_jit_match PCRE2_SUFFIX(pcre2_jit_match_)
#define pcre2_jit_free_unused_memory PCRE2_SUFFIX(pcre2_jit_free_unused_memory_)
#define pcre2_jit_stack_assign PCRE2_SUFFIX(pcre2_jit_stack_assign_)
#define pcre2_jit_stack_create PCRE2_SUFFIX(pcre2_jit_stack_create_)
#define pcre2_jit_stack_free PCRE2_SUFFIX(pcre2_jit_stack_free_)
#define pcre2_maketables PCRE2_SUFFIX(pcre2_maketables_)
#define pcre2_maketables_free PCRE2_SUFFIX(pcre2_maketables_free_)
#define pcre2_match PCRE2_SUFFIX(pcre2_match_)
#define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_)
#define pcre2_match_context_create PCRE2_SUFFIX(pcre2_match_context_create_)
#define pcre2_match_context_free PCRE2_SUFFIX(pcre2_match_context_free_)
#define pcre2_match_data_create PCRE2_SUFFIX(pcre2_match_data_create_)
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_convert PCRE2_SUFFIX(pcre2_pattern_convert_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
#define pcre2_serialize_free PCRE2_SUFFIX(pcre2_serialize_free_)
#define pcre2_serialize_get_number_of_codes PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_extra_options PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
#define pcre2_set_glob_escape PCRE2_SUFFIX(pcre2_set_glob_escape_)
#define pcre2_set_glob_separator PCRE2_SUFFIX(pcre2_set_glob_separator_)
#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_substitute_callout PCRE2_SUFFIX(pcre2_set_substitute_callout_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)
#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_free PCRE2_SUFFIX(pcre2_substring_free_)
#define pcre2_substring_get_byname PCRE2_SUFFIX(pcre2_substring_get_byname_)
#define pcre2_substring_get_bynumber PCRE2_SUFFIX(pcre2_substring_get_bynumber_)
#define pcre2_substring_length_byname PCRE2_SUFFIX(pcre2_substring_length_byname_)
#define pcre2_substring_length_bynumber PCRE2_SUFFIX(pcre2_substring_length_bynumber_)
#define pcre2_substring_list_get PCRE2_SUFFIX(pcre2_substring_list_get_)
#define pcre2_substring_list_free PCRE2_SUFFIX(pcre2_substring_list_free_)
#define pcre2_substring_nametable_scan PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
#define pcre2_substring_number_from_name PCRE2_SUFFIX(pcre2_substring_number_from_name_)
/* Keep this old function name for backwards compatibility */
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
/* Keep this obsolete function for backwards compatibility: it is now a noop. */
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
/* Now generate all three sets of width-specific structures and function
prototypes. */
#define PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS \
PCRE2_TYPES_LIST \
PCRE2_STRUCTURE_LIST \
PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_FUNCTIONS \
PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS
#define PCRE2_LOCAL_WIDTH 8
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 16
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 32
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
/* Undefine the list macros; they are no longer needed. */
#undef PCRE2_TYPES_LIST
#undef PCRE2_STRUCTURE_LIST
#undef PCRE2_GENERAL_INFO_FUNCTIONS
#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS
#undef PCRE2_MATCH_FUNCTIONS
#undef PCRE2_SUBSTRING_FUNCTIONS
#undef PCRE2_SERIALIZE_FUNCTIONS
#undef PCRE2_SUBSTITUTE_FUNCTION
#undef PCRE2_JIT_FUNCTIONS
#undef PCRE2_OTHER_FUNCTIONS
#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
/* PCRE2_CODE_UNIT_WIDTH must be defined. If it is 8, 16, or 32, redefine
PCRE2_SUFFIX to use it. If it is 0, undefine the other macros and make
PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
#undef PCRE2_SUFFIX
#ifndef PCRE2_CODE_UNIT_WIDTH
#error PCRE2_CODE_UNIT_WIDTH must be defined before including pcre2.h.
#error Use 8, 16, or 32; or 0 for a multi-width application.
#else /* PCRE2_CODE_UNIT_WIDTH is defined */
#if PCRE2_CODE_UNIT_WIDTH == 8 || \
PCRE2_CODE_UNIT_WIDTH == 16 || \
PCRE2_CODE_UNIT_WIDTH == 32
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a, PCRE2_CODE_UNIT_WIDTH)
#elif PCRE2_CODE_UNIT_WIDTH == 0
#undef PCRE2_JOIN
#undef PCRE2_GLUE
#define PCRE2_SUFFIX(a) a
#else
#error PCRE2_CODE_UNIT_WIDTH must be 0, 8, 16, or 32.
#endif
#endif /* PCRE2_CODE_UNIT_WIDTH is defined */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* PCRE2_H_IDEMPOTENT_GUARD */
/* End of pcre2.h */

1365
third_party/pcre/pcre2_auto_possess.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

202
third_party/pcre/pcre2_chartables.c vendored Normal file
View file

@ -0,0 +1,202 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This file was automatically written by the pcre2_dftables auxiliary
program. It contains character tables that are used when no external
tables are passed to PCRE2 by the application that calls it. The tables
are used only for characters whose code values are less than 256. */
/* This set of tables was written in the C locale. */
/* The pcre2_ftables program (which is distributed with PCRE2) can be used
to build alternative versions of this file. This is necessary if you are
running in an EBCDIC environment, or if you want to default to a different
encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
these tables in the "C" locale by default. This happens automatically if
PCRE2 is configured with --enable-rebuild-chartables. However, you can run
pcre2_dftables manually with the -L option to build tables using the LC_ALL
locale. */
/* The following #include is present because without it gcc 4.x may remove
the array definition from the final binary if PCRE2 is built into a static
library and dead code stripping is activated. This leads to link errors.
Pulling in the header ensures that the array gets flagged as "someone
outside this compilation unit might reference this" and so it will always
be supplied to the linker. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
const uint8_t PRIV(default_tables)[] = {
/* This table is a lower casing table. */
0, 1, 2, 3, 4, 5, 6, 7,
8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63,
64, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122, 91, 92, 93, 94, 95,
96, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
192,193,194,195,196,197,198,199,
200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,215,
216,217,218,219,220,221,222,223,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
/* This table is a case flipping table. */
0, 1, 2, 3, 4, 5, 6, 7,
8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63,
64, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122, 91, 92, 93, 94, 95,
96, 65, 66, 67, 68, 69, 70, 71,
72, 73, 74, 75, 76, 77, 78, 79,
80, 81, 82, 83, 84, 85, 86, 87,
88, 89, 90,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
192,193,194,195,196,197,198,199,
200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,215,
216,217,218,219,220,221,222,223,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
/* This table contains bit maps for various character classes. Each map is 32
bytes long and the bits run from the least significant end of each byte. The
classes that have their own maps are: space, xdigit, digit, upper, lower, word,
graph, print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, /* space */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* xdigit */
0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* digit */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* upper */
0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* lower */
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* word */
0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, /* graph */
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, /* print */
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, /* punct */
0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, /* cntrl */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* This table identifies various classes of character by individual bits:
0x01 white space character
0x02 letter
0x04 lower case letter
0x08 decimal digit
0x10 alphanumeric or '_'
*/
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */
0x18,0x18,0x18,0x18,0x18,0x18,0x18,0x18, /* 0 - 7 */
0x18,0x18,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */
0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* @ - G */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
0x12,0x12,0x12,0x00,0x00,0x00,0x00,0x10, /* X - _ */
0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* ` - g */
0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* h - o */
0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* p - w */
0x16,0x16,0x16,0x00,0x00,0x00,0x00,0x00, /* x -127 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
/* End of pcre2_chartables.c */

10635
third_party/pcre/pcre2_compile.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

252
third_party/pcre/pcre2_config.c vendored Normal file
View file

@ -0,0 +1,252 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
/* Save the configured link size, which is in bytes. In 16-bit and 32-bit modes
its value gets changed by pcre2_intmodedep.h (included by pcre2_internal.h) to
be in code units. */
static int configured_link_size = LINK_SIZE;
#include "pcre2_internal.h"
/* These macros are the standard way of turning unquoted text into C strings.
They allow macros like PCRE2_MAJOR to be defined without quotes, which is
convenient for user programs that want to test their values. */
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/*************************************************
* Return info about what features are configured *
*************************************************/
/* If where is NULL, the length of memory required is returned.
Arguments:
what what information is required
where where to put the information
Returns: 0 if a numerical value is returned
>= 0 if a string value
PCRE2_ERROR_BADOPTION if "where" not recognized
or JIT target requested when JIT not enabled
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_config(uint32_t what, void *where)
{
if (where == NULL) /* Requests a length */
{
switch(what)
{
default:
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
case PCRE2_CONFIG_COMPILED_WIDTHS:
case PCRE2_CONFIG_DEPTHLIMIT:
case PCRE2_CONFIG_HEAPLIMIT:
case PCRE2_CONFIG_JIT:
case PCRE2_CONFIG_LINKSIZE:
case PCRE2_CONFIG_MATCHLIMIT:
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
case PCRE2_CONFIG_NEWLINE:
case PCRE2_CONFIG_PARENSLIMIT:
case PCRE2_CONFIG_STACKRECURSE: /* Obsolete */
case PCRE2_CONFIG_TABLES_LENGTH:
case PCRE2_CONFIG_UNICODE:
return sizeof(uint32_t);
/* These are handled below */
case PCRE2_CONFIG_JITTARGET:
case PCRE2_CONFIG_UNICODE_VERSION:
case PCRE2_CONFIG_VERSION:
break;
}
}
switch (what)
{
default:
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
#ifdef BSR_ANYCRLF
*((uint32_t *)where) = PCRE2_BSR_ANYCRLF;
#else
*((uint32_t *)where) = PCRE2_BSR_UNICODE;
#endif
break;
case PCRE2_CONFIG_COMPILED_WIDTHS:
*((uint32_t *)where) = 0
#ifdef SUPPORT_PCRE2_8
+ 1
#endif
#ifdef SUPPORT_PCRE2_16
+ 2
#endif
#ifdef SUPPORT_PCRE2_32
+ 4
#endif
;
break;
case PCRE2_CONFIG_DEPTHLIMIT:
*((uint32_t *)where) = MATCH_LIMIT_DEPTH;
break;
case PCRE2_CONFIG_HEAPLIMIT:
*((uint32_t *)where) = HEAP_LIMIT;
break;
case PCRE2_CONFIG_JIT:
#ifdef SUPPORT_JIT
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
case PCRE2_CONFIG_JITTARGET:
#ifdef SUPPORT_JIT
{
const char *v = PRIV(jit_get_target)();
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
#else
return PCRE2_ERROR_BADOPTION;
#endif
case PCRE2_CONFIG_LINKSIZE:
*((uint32_t *)where) = (uint32_t)configured_link_size;
break;
case PCRE2_CONFIG_MATCHLIMIT:
*((uint32_t *)where) = MATCH_LIMIT;
break;
case PCRE2_CONFIG_NEWLINE:
*((uint32_t *)where) = NEWLINE_DEFAULT;
break;
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
#ifdef NEVER_BACKSLASH_C
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
case PCRE2_CONFIG_PARENSLIMIT:
*((uint32_t *)where) = PARENS_NEST_LIMIT;
break;
/* This is now obsolete. The stack is no longer used via recursion for
handling backtracking in pcre2_match(). */
case PCRE2_CONFIG_STACKRECURSE:
*((uint32_t *)where) = 0;
break;
case PCRE2_CONFIG_TABLES_LENGTH:
*((uint32_t *)where) = TABLES_LENGTH;
break;
case PCRE2_CONFIG_UNICODE_VERSION:
{
#if defined SUPPORT_UNICODE
const char *v = PRIV(unicode_version);
#else
const char *v = "Unicode not supported";
#endif
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
break;
case PCRE2_CONFIG_UNICODE:
#if defined SUPPORT_UNICODE
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
/* The hackery in setting "v" below is to cope with the case when
PCRE2_PRERELEASE is set to an empty string (which it is for real releases).
If the second alternative is used in this case, it does not leave a space
before the date. On the other hand, if all four macros are put into a single
XSTRING when PCRE2_PRERELEASE is not empty, an unwanted space is inserted.
There are problems using an "obvious" approach like this:
XSTRING(PCRE2_MAJOR) "." XSTRING(PCRE_MINOR)
XSTRING(PCRE2_PRERELEASE) " " XSTRING(PCRE_DATE)
because, when PCRE2_PRERELEASE is empty, this leads to an attempted expansion
of STRING(). The C standard states: "If (before argument substitution) any
argument consists of no preprocessing tokens, the behavior is undefined." It
turns out the gcc treats this case as a single empty string - which is what
we really want - but Visual C grumbles about the lack of an argument for the
macro. Unfortunately, both are within their rights. As there seems to be no
way to test for a macro's value being empty at compile time, we have to
resort to a runtime test. */
case PCRE2_CONFIG_VERSION:
{
const char *v = (XSTRING(Z PCRE2_PRERELEASE)[1] == 0)?
XSTRING(PCRE2_MAJOR.PCRE2_MINOR PCRE2_DATE) :
XSTRING(PCRE2_MAJOR.PCRE2_MINOR) XSTRING(PCRE2_PRERELEASE PCRE2_DATE);
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
}
return 0;
}
/* End of pcre2_config.c */

494
third_party/pcre/pcre2_context.c vendored Normal file
View file

@ -0,0 +1,494 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Default malloc/free functions *
*************************************************/
/* Ignore the "user data" argument in each case. */
static void *default_malloc(size_t size, void *data)
{
(void)data;
return malloc(size);
}
static void default_free(void *block, void *data)
{
(void)data;
free(block);
}
/*************************************************
* Get a block and save memory control *
*************************************************/
/* This internal function is called to get a block of memory in which the
memory control data is to be stored at the start for future use.
Arguments:
size amount of memory required
memctl pointer to a memctl block or NULL
Returns: pointer to memory or NULL on failure
*/
extern void *
PRIV(memctl_malloc)(size_t size, pcre2_memctl *memctl)
{
pcre2_memctl *newmemctl;
void *yield = (memctl == NULL)? malloc(size) :
memctl->malloc(size, memctl->memory_data);
if (yield == NULL) return NULL;
newmemctl = (pcre2_memctl *)yield;
if (memctl == NULL)
{
newmemctl->malloc = default_malloc;
newmemctl->free = default_free;
newmemctl->memory_data = NULL;
}
else *newmemctl = *memctl;
return yield;
}
/*************************************************
* Create and initialize contexts *
*************************************************/
/* Initializing for compile and match contexts is done in separate, private
functions so that these can be called from functions such as pcre2_compile()
when an external context is not supplied. The initializing functions have an
option to set up default memory management. */
PCRE2_EXP_DEFN pcre2_general_context * PCRE2_CALL_CONVENTION
pcre2_general_context_create(void *(*private_malloc)(size_t, void *),
void (*private_free)(void *, void *), void *memory_data)
{
pcre2_general_context *gcontext;
if (private_malloc == NULL) private_malloc = default_malloc;
if (private_free == NULL) private_free = default_free;
gcontext = private_malloc(sizeof(pcre2_real_general_context), memory_data);
if (gcontext == NULL) return NULL;
gcontext->memctl.malloc = private_malloc;
gcontext->memctl.free = private_free;
gcontext->memctl.memory_data = memory_data;
return gcontext;
}
/* A default compile context is set up to save having to initialize at run time
when no context is supplied to the compile function. */
const pcre2_compile_context PRIV(default_compile_context) = {
{ default_malloc, default_free, NULL }, /* Default memory handling */
NULL, /* Stack guard */
NULL, /* Stack guard data */
PRIV(default_tables), /* Character tables */
PCRE2_UNSET, /* Max pattern length */
BSR_DEFAULT, /* Backslash R default */
NEWLINE_DEFAULT, /* Newline convention */
PARENS_NEST_LIMIT, /* As it says */
0 }; /* Extra options */
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_compile_context * PCRE2_CALL_CONVENTION
pcre2_compile_context_create(pcre2_general_context *gcontext)
{
pcre2_compile_context *ccontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_compile_context), (pcre2_memctl *)gcontext);
if (ccontext == NULL) return NULL;
*ccontext = PRIV(default_compile_context);
if (gcontext != NULL)
*((pcre2_memctl *)ccontext) = *((pcre2_memctl *)gcontext);
return ccontext;
}
/* A default match context is set up to save having to initialize at run time
when no context is supplied to a match function. */
const pcre2_match_context PRIV(default_match_context) = {
{ default_malloc, default_free, NULL },
#ifdef SUPPORT_JIT
NULL, /* JIT callback */
NULL, /* JIT callback data */
#endif
NULL, /* Callout function */
NULL, /* Callout data */
NULL, /* Substitute callout function */
NULL, /* Substitute callout data */
PCRE2_UNSET, /* Offset limit */
HEAP_LIMIT,
MATCH_LIMIT,
MATCH_LIMIT_DEPTH };
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_match_context * PCRE2_CALL_CONVENTION
pcre2_match_context_create(pcre2_general_context *gcontext)
{
pcre2_match_context *mcontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_match_context), (pcre2_memctl *)gcontext);
if (mcontext == NULL) return NULL;
*mcontext = PRIV(default_match_context);
if (gcontext != NULL)
*((pcre2_memctl *)mcontext) = *((pcre2_memctl *)gcontext);
return mcontext;
}
/* A default convert context is set up to save having to initialize at run time
when no context is supplied to the convert function. */
const pcre2_convert_context PRIV(default_convert_context) = {
{ default_malloc, default_free, NULL }, /* Default memory handling */
#ifdef _WIN32
CHAR_BACKSLASH, /* Default path separator */
CHAR_GRAVE_ACCENT /* Default escape character */
#else /* Not Windows */
CHAR_SLASH, /* Default path separator */
CHAR_BACKSLASH /* Default escape character */
#endif
};
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_create(pcre2_general_context *gcontext)
{
pcre2_convert_context *ccontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_convert_context), (pcre2_memctl *)gcontext);
if (ccontext == NULL) return NULL;
*ccontext = PRIV(default_convert_context);
if (gcontext != NULL)
*((pcre2_memctl *)ccontext) = *((pcre2_memctl *)gcontext);
return ccontext;
}
/*************************************************
* Context copy functions *
*************************************************/
PCRE2_EXP_DEFN pcre2_general_context * PCRE2_CALL_CONVENTION
pcre2_general_context_copy(pcre2_general_context *gcontext)
{
pcre2_general_context *new =
gcontext->memctl.malloc(sizeof(pcre2_real_general_context),
gcontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, gcontext, sizeof(pcre2_real_general_context));
return new;
}
PCRE2_EXP_DEFN pcre2_compile_context * PCRE2_CALL_CONVENTION
pcre2_compile_context_copy(pcre2_compile_context *ccontext)
{
pcre2_compile_context *new =
ccontext->memctl.malloc(sizeof(pcre2_real_compile_context),
ccontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, ccontext, sizeof(pcre2_real_compile_context));
return new;
}
PCRE2_EXP_DEFN pcre2_match_context * PCRE2_CALL_CONVENTION
pcre2_match_context_copy(pcre2_match_context *mcontext)
{
pcre2_match_context *new =
mcontext->memctl.malloc(sizeof(pcre2_real_match_context),
mcontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, mcontext, sizeof(pcre2_real_match_context));
return new;
}
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_copy(pcre2_convert_context *ccontext)
{
pcre2_convert_context *new =
ccontext->memctl.malloc(sizeof(pcre2_real_convert_context),
ccontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, ccontext, sizeof(pcre2_real_convert_context));
return new;
}
/*************************************************
* Context free functions *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_general_context_free(pcre2_general_context *gcontext)
{
if (gcontext != NULL)
gcontext->memctl.free(gcontext, gcontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_compile_context_free(pcre2_compile_context *ccontext)
{
if (ccontext != NULL)
ccontext->memctl.free(ccontext, ccontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_match_context_free(pcre2_match_context *mcontext)
{
if (mcontext != NULL)
mcontext->memctl.free(mcontext, mcontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_convert_context_free(pcre2_convert_context *ccontext)
{
if (ccontext != NULL)
ccontext->memctl.free(ccontext, ccontext->memctl.memory_data);
}
/*************************************************
* Set values in contexts *
*************************************************/
/* All these functions return 0 for success or PCRE2_ERROR_BADDATA if invalid
data is given. Only some of the functions are able to test the validity of the
data. */
/* ------------ Compile context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_character_tables(pcre2_compile_context *ccontext,
const uint8_t *tables)
{
ccontext->tables = tables;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_bsr(pcre2_compile_context *ccontext, uint32_t value)
{
switch(value)
{
case PCRE2_BSR_ANYCRLF:
case PCRE2_BSR_UNICODE:
ccontext->bsr_convention = value;
return 0;
default:
return PCRE2_ERROR_BADDATA;
}
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_max_pattern_length(pcre2_compile_context *ccontext, PCRE2_SIZE length)
{
ccontext->max_pattern_length = length;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_newline(pcre2_compile_context *ccontext, uint32_t newline)
{
switch(newline)
{
case PCRE2_NEWLINE_CR:
case PCRE2_NEWLINE_LF:
case PCRE2_NEWLINE_CRLF:
case PCRE2_NEWLINE_ANY:
case PCRE2_NEWLINE_ANYCRLF:
case PCRE2_NEWLINE_NUL:
ccontext->newline_convention = newline;
return 0;
default:
return PCRE2_ERROR_BADDATA;
}
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext, uint32_t limit)
{
ccontext->parens_nest_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_extra_options(pcre2_compile_context *ccontext, uint32_t options)
{
ccontext->extra_options = options;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
int (*guard)(uint32_t, void *), void *user_data)
{
ccontext->stack_guard = guard;
ccontext->stack_guard_data = user_data;
return 0;
}
/* ------------ Match context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_callout(pcre2_match_context *mcontext,
int (*callout)(pcre2_callout_block *, void *), void *callout_data)
{
mcontext->callout = callout;
mcontext->callout_data = callout_data;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_substitute_callout(pcre2_match_context *mcontext,
int (*substitute_callout)(pcre2_substitute_callout_block *, void *),
void *substitute_callout_data)
{
mcontext->substitute_callout = substitute_callout;
mcontext->substitute_callout_data = substitute_callout_data;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_heap_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->heap_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_match_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->match_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_depth_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->depth_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_offset_limit(pcre2_match_context *mcontext, PCRE2_SIZE limit)
{
mcontext->offset_limit = limit;
return 0;
}
/* These functions became obsolete at release 10.30. The first is kept as a
synonym for backwards compatibility. The second now does nothing. Exclude both
from coverage reports. */
/* LCOV_EXCL_START */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
{
return pcre2_set_depth_limit(mcontext, limit);
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_memory_management(pcre2_match_context *mcontext,
void *(*mymalloc)(size_t, void *), void (*myfree)(void *, void *),
void *mydata)
{
(void)mcontext;
(void)mymalloc;
(void)myfree;
(void)mydata;
return 0;
}
/* LCOV_EXCL_STOP */
/* ------------ Convert context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_separator(pcre2_convert_context *ccontext, uint32_t separator)
{
if (separator != CHAR_SLASH && separator != CHAR_BACKSLASH &&
separator != CHAR_DOT) return PCRE2_ERROR_BADDATA;
ccontext->glob_separator = separator;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_escape(pcre2_convert_context *ccontext, uint32_t escape)
{
if (escape > 255 || (escape != 0 && !ispunct(escape)))
return PCRE2_ERROR_BADDATA;
ccontext->glob_escape = escape;
return 0;
}
/* End of pcre2_context.c */

1181
third_party/pcre/pcre2_convert.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

4066
third_party/pcre/pcre2_dfa_match.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

341
third_party/pcre/pcre2_error.c vendored Normal file
View file

@ -0,0 +1,341 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/* The texts of compile-time error messages. Compile-time error numbers start
at COMPILE_ERROR_BASE (100).
This used to be a table of strings, but in order to reduce the number of
relocations needed when a shared library is loaded dynamically, it is now one
long string. We cannot use a table of offsets, because the lengths of inserts
such as XSTRING(MAX_NAME_SIZE) are not known. Instead,
pcre2_get_error_message() counts through to the one it wants - this isn't a
performance issue because these strings are used only when there is an error.
Each substring ends with \0 to insert a null character. This includes the final
substring, so that the whole string ends with \0\0, which can be detected when
counting through. */
static const unsigned char compile_error_texts[] =
"no error\0"
"\\ at end of pattern\0"
"\\c at end of pattern\0"
"unrecognized character follows \\\0"
"numbers out of order in {} quantifier\0"
/* 5 */
"number too big in {} quantifier\0"
"missing terminating ] for character class\0"
"escape sequence is invalid in character class\0"
"range out of order in character class\0"
"quantifier does not follow a repeatable item\0"
/* 10 */
"internal error: unexpected repeat\0"
"unrecognized character after (? or (?-\0"
"POSIX named classes are supported only within a class\0"
"POSIX collating elements are not supported\0"
"missing closing parenthesis\0"
/* 15 */
"reference to non-existent subpattern\0"
"pattern passed as NULL\0"
"unrecognised compile-time option bit(s)\0"
"missing ) after (?# comment\0"
"parentheses are too deeply nested\0"
/* 20 */
"regular expression is too large\0"
"failed to allocate heap memory\0"
"unmatched closing parenthesis\0"
"internal error: code overflow\0"
"missing closing parenthesis for condition\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"a relative value of zero is not allowed\0"
"conditional subpattern contains more than two branches\0"
"assertion expected after (?( or (?(?C)\0"
"digit expected after (?+ or (?-\0"
/* 30 */
"unknown POSIX class name\0"
"internal error in pcre2_study(): should not occur\0"
"this version of PCRE2 does not have Unicode support\0"
"parentheses are too deeply nested (stack check)\0"
"character code point value in \\x{} or \\o{} is too large\0"
/* 35 */
"lookbehind is too complicated\0"
"\\C is not allowed in a lookbehind assertion in UTF-" XSTRING(PCRE2_CODE_UNIT_WIDTH) " mode\0"
"PCRE2 does not support \\F, \\L, \\l, \\N{name}, \\U, or \\u\0"
"number after (?C is greater than 255\0"
"closing parenthesis for (?C expected\0"
/* 40 */
"invalid escape sequence in (*VERB) name\0"
"unrecognized character after (?P\0"
"syntax error in subpattern name (missing terminator?)\0"
"two named subpatterns have the same name (PCRE2_DUPNAMES not set)\0"
"subpattern name must start with a non-digit\0"
/* 45 */
"this version of PCRE2 does not have support for \\P, \\p, or \\X\0"
"malformed \\P or \\p sequence\0"
"unknown property after \\P or \\p\0"
"subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " code units)\0"
"too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
/* 50 */
"invalid range in character class\0"
"octal value is greater than \\377 in 8-bit non-UTF-8 mode\0"
"internal error: overran compiling workspace\0"
"internal error: previously-checked referenced subpattern not found\0"
"DEFINE subpattern contains more than one branch\0"
/* 55 */
"missing opening brace after \\o\0"
"internal error: unknown newline setting\0"
"\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0"
"(?R (recursive pattern call) must be followed by a closing parenthesis\0"
/* "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" */
"obsolete error (should not occur)\0" /* Was the above */
/* 60 */
"(*VERB) not recognized or malformed\0"
"subpattern number is too big\0"
"subpattern name expected\0"
"internal error: parsed pattern overflow\0"
"non-octal character in \\o{} (closing brace missing?)\0"
/* 65 */
"different names for subpatterns of the same number are not allowed\0"
"(*MARK) must have an argument\0"
"non-hex character in \\x{} (closing brace missing?)\0"
#ifndef EBCDIC
"\\c must be followed by a printable ASCII character\0"
#else
"\\c must be followed by a letter or one of [\\]^_?\0"
#endif
"\\k is not followed by a braced, angle-bracketed, or quoted name\0"
/* 70 */
"internal error: unknown meta code in check_lookbehinds()\0"
"\\N is not supported in a class\0"
"callout string is too long\0"
"disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
"using UTF is disabled by the application\0"
/* 75 */
"using UCP is disabled by the application\0"
"name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0"
"character code point value in \\u.... sequence is too large\0"
"digits missing in \\x{} or \\o{} or \\N{U+}\0"
"syntax error or number too big in (?(VERSION condition\0"
/* 80 */
"internal error: unknown opcode in auto_possessify()\0"
"missing terminating delimiter for callout with string argument\0"
"unrecognized string delimiter follows (?C\0"
"using \\C is disabled by the application\0"
"(?| and/or (?J: or (?x: parentheses are too deeply nested\0"
/* 85 */
"using \\C is disabled in this PCRE2 library\0"
"regular expression is too complicated\0"
"lookbehind assertion is too long\0"
"pattern string is longer than the limit set by the application\0"
"internal error: unknown code in parsed pattern\0"
/* 90 */
"internal error: bad code value in parsed_skip()\0"
"PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is not allowed in UTF-16 mode\0"
"invalid option bits with PCRE2_LITERAL\0"
"\\N{U+dddd} is supported only in Unicode (UTF) mode\0"
"invalid hyphen in option setting\0"
/* 95 */
"(*alpha_assertion) not recognized\0"
"script runs require Unicode support, which this version of PCRE2 does not have\0"
"too many capturing groups (maximum 65535)\0"
"atomic assertion expected after (?( or (?(?C)\0"
"\\K is not allowed in lookarounds (but see PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK)\0"
;
/* Match-time and UTF error texts are in the same format. */
static const unsigned char match_error_texts[] =
"no error\0"
"no match\0"
"partial match\0"
"UTF-8 error: 1 byte missing at end\0"
"UTF-8 error: 2 bytes missing at end\0"
/* 5 */
"UTF-8 error: 3 bytes missing at end\0"
"UTF-8 error: 4 bytes missing at end\0"
"UTF-8 error: 5 bytes missing at end\0"
"UTF-8 error: byte 2 top bits not 0x80\0"
"UTF-8 error: byte 3 top bits not 0x80\0"
/* 10 */
"UTF-8 error: byte 4 top bits not 0x80\0"
"UTF-8 error: byte 5 top bits not 0x80\0"
"UTF-8 error: byte 6 top bits not 0x80\0"
"UTF-8 error: 5-byte character is not allowed (RFC 3629)\0"
"UTF-8 error: 6-byte character is not allowed (RFC 3629)\0"
/* 15 */
"UTF-8 error: code points greater than 0x10ffff are not defined\0"
"UTF-8 error: code points 0xd800-0xdfff are not defined\0"
"UTF-8 error: overlong 2-byte sequence\0"
"UTF-8 error: overlong 3-byte sequence\0"
"UTF-8 error: overlong 4-byte sequence\0"
/* 20 */
"UTF-8 error: overlong 5-byte sequence\0"
"UTF-8 error: overlong 6-byte sequence\0"
"UTF-8 error: isolated byte with 0x80 bit set\0"
"UTF-8 error: illegal byte (0xfe or 0xff)\0"
"UTF-16 error: missing low surrogate at end\0"
/* 25 */
"UTF-16 error: invalid low surrogate\0"
"UTF-16 error: isolated low surrogate\0"
"UTF-32 error: code points 0xd800-0xdfff are not defined\0"
"UTF-32 error: code points greater than 0x10ffff are not defined\0"
"bad data value\0"
/* 30 */
"patterns do not all use the same character tables\0"
"magic number missing\0"
"pattern compiled in wrong mode: 8/16/32-bit error\0"
"bad offset value\0"
"bad option value\0"
/* 35 */
"invalid replacement string\0"
"bad offset into UTF string\0"
"callout error code\0" /* Never returned by PCRE2 itself */
"invalid data in workspace for DFA restart\0"
"too much recursion for DFA matching\0"
/* 40 */
"backreference condition or recursion test is not supported for DFA matching\0"
"function is not supported for DFA matching\0"
"pattern contains an item that is not supported for DFA matching\0"
"workspace size exceeded in DFA matching\0"
"internal error - pattern overwritten?\0"
/* 45 */
"bad JIT option\0"
"JIT stack limit reached\0"
"match limit exceeded\0"
"no more memory\0"
"unknown substring\0"
/* 50 */
"non-unique substring name\0"
"NULL argument passed with non-zero length\0"
"nested recursion at the same subject position\0"
"matching depth limit exceeded\0"
"requested value is not available\0"
/* 55 */
"requested value is not set\0"
"offset limit set without PCRE2_USE_OFFSET_LIMIT\0"
"bad escape sequence in replacement string\0"
"expected closing curly bracket in replacement string\0"
"bad substitution in replacement string\0"
/* 60 */
"match with end before start or start moved backwards is not supported\0"
"too many replacements (more than INT_MAX)\0"
"bad serialized data\0"
"heap limit exceeded\0"
"invalid syntax\0"
/* 65 */
"internal error - duplicate substitution match\0"
"PCRE2_MATCH_INVALID_UTF is not supported for DFA matching\0"
;
/*************************************************
* Return error message *
*************************************************/
/* This function copies an error message into a buffer whose units are of an
appropriate width. Error numbers are positive for compile-time errors, and
negative for match-time errors (except for UTF errors), but the numbers are all
distinct.
Arguments:
enumber error number
buffer where to put the message (zero terminated)
size size of the buffer in code units
Returns: length of message if all is well
negative on error
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_get_error_message(int enumber, PCRE2_UCHAR *buffer, PCRE2_SIZE size)
{
const unsigned char *message;
PCRE2_SIZE i;
int n;
if (size == 0) return PCRE2_ERROR_NOMEMORY;
if (enumber >= COMPILE_ERROR_BASE) /* Compile error */
{
message = compile_error_texts;
n = enumber - COMPILE_ERROR_BASE;
}
else if (enumber < 0) /* Match or UTF error */
{
message = match_error_texts;
n = -enumber;
}
else /* Invalid error number */
{
message = (unsigned char *)"\0"; /* Empty message list */
n = 1;
}
for (; n > 0; n--)
{
while (*message++ != CHAR_NUL) {};
if (*message == CHAR_NUL) return PCRE2_ERROR_BADDATA;
}
for (i = 0; *message != 0; i++)
{
if (i >= size - 1)
{
buffer[i] = 0; /* Terminate partial message */
return PCRE2_ERROR_NOMEMORY;
}
buffer[i] = *message++;
}
buffer[i] = 0;
return (int)i;
}
/* End of pcre2_error.c */

148
third_party/pcre/pcre2_extuni.c vendored Normal file
View file

@ -0,0 +1,148 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that is used to match a Unicode
extended grapheme sequence. It is used by both pcre2_match() and
pcre2_def_match(). However, it is called only when Unicode support is being
compiled. Nevertheless, we provide a dummy function when there is no Unicode
support, because some compilers do not like functionless source files. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* Dummy function */
#ifndef SUPPORT_UNICODE
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
(void)c;
(void)eptr;
(void)start_subject;
(void)end_subject;
(void)utf;
(void)xcount;
return NULL;
}
#else
/*************************************************
* Match an extended grapheme sequence *
*************************************************/
/*
Arguments:
c the first character
eptr pointer to next character
start_subject pointer to start of subject
end_subject pointer to end of subject
utf TRUE if in UTF mode
xcount pointer to count of additional characters,
or NULL if count not needed
Returns: pointer after the end of the sequence
*/
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
int lgb = UCD_GRAPHBREAK(c);
while (eptr < end_subject)
{
int rgb;
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1u << rgb)) == 0) break;
/* Not breaking between Regional Indicators is allowed only if there
are an even number of preceding RIs. */
if (lgb == ucp_gbRegional_Indicator && rgb == ucp_gbRegional_Indicator)
{
int ricount = 0;
PCRE2_SPTR bptr = eptr - 1;
if (utf) BACKCHAR(bptr);
/* bptr is pointing to the left-hand character */
while (bptr > start_subject)
{
bptr--;
if (utf)
{
BACKCHAR(bptr);
GETCHAR(c, bptr);
}
else
c = *bptr;
if (UCD_GRAPHBREAK(c) != ucp_gbRegional_Indicator) break;
ricount++;
}
if ((ricount & 1) != 0) break; /* Grapheme break required */
}
/* If Extend or ZWJ follows Extended_Pictographic, do not update lgb; this
allows any number of them before a following Extended_Pictographic. */
if ((rgb != ucp_gbExtend && rgb != ucp_gbZWJ) ||
lgb != ucp_gbExtended_Pictographic)
lgb = rgb;
eptr += len;
if (xcount != NULL) *xcount += 1;
}
return eptr;
}
#endif /* SUPPORT_UNICODE */
/* End of pcre2_extuni.c */

219
third_party/pcre/pcre2_find_bracket.c vendored Normal file
View file

@ -0,0 +1,219 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains a single function that scans through a compiled pattern
until it finds a capturing bracket with the given number, or, if the number is
negative, an instance of OP_REVERSE for a lookbehind. The function is called
from pcre2_compile.c and also from pcre2_study.c when finding the minimum
matching length. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Scan compiled regex for specific bracket *
*************************************************/
/*
Arguments:
code points to start of expression
utf TRUE in UTF mode
number the required bracket number or negative to find a lookbehind
Returns: pointer to the opcode for the bracket, or NULL if not found
*/
PCRE2_SPTR
PRIV(find_bracket)(PCRE2_SPTR code, BOOL utf, int number)
{
for (;;)
{
PCRE2_UCHAR c = *code;
if (c == OP_END) return NULL;
/* XCLASS is used for classes that cannot be represented just by a bit map.
This includes negated single high-valued characters. CALLOUT_STR is used for
callouts with string arguments. In both cases the length in the table is
zero; the actual length is stored in the compiled code. */
if (c == OP_XCLASS) code += GET(code, 1);
else if (c == OP_CALLOUT_STR) code += GET(code, 1 + 2*LINK_SIZE);
/* Handle lookbehind */
else if (c == OP_REVERSE)
{
if (number < 0) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Handle capturing bracket */
else if (c == OP_CBRA || c == OP_SCBRA ||
c == OP_CBRAPOS || c == OP_SCBRAPOS)
{
int n = (int)GET2(code, 1+LINK_SIZE);
if (n == number) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Otherwise, we can get the item's length from the table, except that for
repeated character types, we have to test for \p and \P, which have an extra
two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we
must add in its length. */
else
{
switch(c)
{
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
case OP_TYPEPOSSTAR:
case OP_TYPEPOSPLUS:
case OP_TYPEPOSQUERY:
if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
break;
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
case OP_TYPEEXACT:
case OP_TYPEPOSUPTO:
if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP)
code += 2;
break;
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
code += code[1];
break;
}
/* Add in the fixed length from the table */
code += PRIV(OP_lengths)[c];
/* In UTF-8 and UTF-16 modes, opcodes that are followed by a character may be
followed by a multi-byte character. The length in the table is a minimum, so
we have to arrange to skip the extra bytes. */
#ifdef MAYBE_UTF_MULTI
if (utf) switch(c)
{
case OP_CHAR:
case OP_CHARI:
case OP_NOT:
case OP_NOTI:
case OP_EXACT:
case OP_EXACTI:
case OP_NOTEXACT:
case OP_NOTEXACTI:
case OP_UPTO:
case OP_UPTOI:
case OP_NOTUPTO:
case OP_NOTUPTOI:
case OP_MINUPTO:
case OP_MINUPTOI:
case OP_NOTMINUPTO:
case OP_NOTMINUPTOI:
case OP_POSUPTO:
case OP_POSUPTOI:
case OP_NOTPOSUPTO:
case OP_NOTPOSUPTOI:
case OP_STAR:
case OP_STARI:
case OP_NOTSTAR:
case OP_NOTSTARI:
case OP_MINSTAR:
case OP_MINSTARI:
case OP_NOTMINSTAR:
case OP_NOTMINSTARI:
case OP_POSSTAR:
case OP_POSSTARI:
case OP_NOTPOSSTAR:
case OP_NOTPOSSTARI:
case OP_PLUS:
case OP_PLUSI:
case OP_NOTPLUS:
case OP_NOTPLUSI:
case OP_MINPLUS:
case OP_MINPLUSI:
case OP_NOTMINPLUS:
case OP_NOTMINPLUSI:
case OP_POSPLUS:
case OP_POSPLUSI:
case OP_NOTPOSPLUS:
case OP_NOTPOSPLUSI:
case OP_QUERY:
case OP_QUERYI:
case OP_NOTQUERY:
case OP_NOTQUERYI:
case OP_MINQUERY:
case OP_MINQUERYI:
case OP_NOTMINQUERY:
case OP_NOTMINQUERYI:
case OP_POSQUERY:
case OP_POSQUERYI:
case OP_NOTPOSQUERY:
case OP_NOTPOSQUERYI:
if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
break;
}
#else
(void)(utf); /* Keep compiler happy by referencing function argument */
#endif /* MAYBE_UTF_MULTI */
}
}
}
/* End of pcre2_find_bracket.c */

2047
third_party/pcre/pcre2_internal.h vendored Normal file
View file

File diff suppressed because it is too large Load diff

934
third_party/pcre/pcre2_intmodedep.h vendored Normal file
View file

@ -0,0 +1,934 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains mode-dependent macro and structure definitions. The
file is #included by pcre2_internal.h if PCRE2_CODE_UNIT_WIDTH is defined.
These mode-dependent items are kept in a separate file so that they can also be
#included multiple times for different code unit widths by pcre2test in order
to have access to the hidden structures at all supported widths.
Some of the mode-dependent macros are required at different widths for
different parts of the pcre2test code (in particular, the included
pcre_printint.c file). We undefine them here so that they can be re-defined for
multiple inclusions. Not all of these are used in pcre2test, but it's easier
just to undefine them all. */
#undef ACROSSCHAR
#undef BACKCHAR
#undef BYTES2CU
#undef CHMAX_255
#undef CU2BYTES
#undef FORWARDCHAR
#undef FORWARDCHARTEST
#undef GET
#undef GET2
#undef GETCHAR
#undef GETCHARINC
#undef GETCHARINCTEST
#undef GETCHARLEN
#undef GETCHARLENTEST
#undef GETCHARTEST
#undef GET_EXTRALEN
#undef HAS_EXTRALEN
#undef IMM2_SIZE
#undef MAX_255
#undef MAX_MARK
#undef MAX_PATTERN_SIZE
#undef MAX_UTF_SINGLE_CU
#undef NOT_FIRSTCU
#undef PUT
#undef PUT2
#undef PUT2INC
#undef PUTCHAR
#undef PUTINC
#undef TABLE_GET
/* -------------------------- MACROS ----------------------------- */
/* PCRE keeps offsets in its compiled code as at least 16-bit quantities
(always stored in big-endian order in 8-bit mode) by default. These are used,
for example, to link from the start of a subpattern to its alternatives and its
end. The use of 16 bits per offset limits the size of an 8-bit compiled regex
to around 64K, which is big enough for almost everybody. However, I received a
request for an even bigger limit. For this reason, and also to make the code
easier to maintain, the storing and loading of offsets from the compiled code
unit string is now handled by the macros that are defined here.
The macros are controlled by the value of LINK_SIZE. This defaults to 2, but
values of 3 or 4 are also supported. */
/* ------------------- 8-bit support ------------------ */
#if PCRE2_CODE_UNIT_WIDTH == 8
#if LINK_SIZE == 2
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 8) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+2] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
#define MAX_PATTERN_SIZE (1 << 24)
#elif LINK_SIZE == 4
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 24)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+2] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+3] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be 2, 3, or 4
#endif
/* ------------------- 16-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 16
#if LINK_SIZE == 2
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)(d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3 || LINK_SIZE == 4
#undef LINK_SIZE
#define LINK_SIZE 2
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) & 65535))
#define GET(a,n) \
(unsigned int)(((a)[n] << 16) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be 2, 3, or 4
#endif
/* ------------------- 32-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 32
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error Unsupported compiling mode
#endif
/* --------------- Other mode-specific macros ----------------- */
/* PCRE uses some other (at least) 16-bit quantities that do not change when
the size of offsets changes. There are used for repeat counts and for other
things such as capturing parenthesis numbers in back references.
Define the number of code units required to hold a 16-bit count/offset, and
macros to load and store such a value. For reasons that I do not understand,
the expression in the 8-bit GET2 macro is treated by gcc as a signed
expression, even when a is declared as unsigned. It seems that any kind of
arithmetic results in a signed value. Hence the cast. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define IMM2_SIZE 2
#define GET2(a,n) (unsigned int)(((a)[n] << 8) | (a)[(n)+1])
#define PUT2(a,n,d) a[n] = (d) >> 8, a[(n)+1] = (d) & 255
#else /* Code units are 16 or 32 bits */
#define IMM2_SIZE 1
#define GET2(a,n) a[n]
#define PUT2(a,n,d) a[n] = d
#endif
/* Other macros that are different for 8-bit mode. The MAX_255 macro checks
whether its argument, which is assumed to be one code unit, is less than 256.
The CHMAX_255 macro does not assume one code unit. The maximum length of a MARK
name must fit in one code unit; currently it is set to 255 or 65535. The
TABLE_GET macro is used to access elements of tables containing exactly 256
items. Its argument is a code unit. When code points can be greater than 255, a
check is needed before accessing these tables. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define MAX_255(c) TRUE
#define MAX_MARK ((1u << 8) - 1)
#define TABLE_GET(c, table, default) ((table)[c])
#ifdef SUPPORT_UNICODE
#define SUPPORT_WIDE_CHARS
#define CHMAX_255(c) ((c) <= 255u)
#else
#define CHMAX_255(c) TRUE
#endif /* SUPPORT_UNICODE */
#else /* Code units are 16 or 32 bits */
#define CHMAX_255(c) ((c) <= 255u)
#define MAX_255(c) ((c) <= 255u)
#define MAX_MARK ((1u << 16) - 1)
#define SUPPORT_WIDE_CHARS
#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default))
#endif
/* ----------------- Character-handling macros ----------------- */
/* There is a proposed future special "UTF-21" mode, in which only the lowest
21 bits of a 32-bit character are interpreted as UTF, with the remaining 11
high-order bits available to the application for other uses. In preparation for
the future implementation of this mode, there are macros that load a data item
and, if in this special mode, mask it to 21 bits. These macros all have names
starting with UCHAR21. In all other modes, including the normal 32-bit
library, the macros all have the same simple definitions. When the new mode is
implemented, it is expected that these definitions will be varied appropriately
using #ifdef when compiling the library that supports the special mode. */
#define UCHAR21(eptr) (*(eptr))
#define UCHAR21TEST(eptr) (*(eptr))
#define UCHAR21INC(eptr) (*(eptr)++)
#define UCHAR21INCTEST(eptr) (*(eptr)++)
/* When UTF encoding is being used, a character is no longer just a single
byte in 8-bit mode or a single short in 16-bit mode. The macros for character
handling generate simple sequences when used in the basic mode, and more
complicated ones for UTF characters. GETCHARLENTEST and other macros are not
used when UTF is not supported. To make sure they can never even appear when
UTF support is omitted, we don't even define them. */
#ifndef SUPPORT_UNICODE
/* #define MAX_UTF_SINGLE_CU */
/* #define HAS_EXTRALEN(c) */
/* #define GET_EXTRALEN(c) */
/* #define NOT_FIRSTCU(c) */
#define GETCHAR(c, eptr) c = *eptr;
#define GETCHARTEST(c, eptr) c = *eptr;
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
#define PUTCHAR(c, p) (*p = c, 1)
/* #define GETCHARLENTEST(c, eptr, len) */
/* #define BACKCHAR(eptr) */
/* #define FORWARDCHAR(eptr) */
/* #define FORWARCCHARTEST(eptr,end) */
/* #define ACROSSCHAR(condition, eptr, action) */
#else /* SUPPORT_UNICODE */
/* ------------------- 8-bit support ------------------ */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
/* The largest UTF code point that can be encoded as a single code unit. */
#define MAX_UTF_SINGLE_CU 127
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) HASUTF8EXTRALEN(c)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3fu])
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCU(c) (((c) & 0xc0u) == 0x80u)
/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if (c >= 0xc0u) GETUTF8(c, eptr);
/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf && c >= 0xc0u) GETUTF8(c, eptr);
/* Get the next UTF-8 character, advancing the pointer. This is called when we
know we are in UTF-8 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if (c >= 0xc0u) GETUTF8INC(c, eptr);
/* Get the next character, testing for UTF-8 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-8 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf && c >= 0xc0u) GETUTF8INC(c, eptr);
/* Get the next UTF-8 character, not advancing the pointer, incrementing length
if there are extra bytes. This is called when we know we are in UTF-8 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if (c >= 0xc0u) GETUTF8LEN(c, eptr, len);
/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
pointer, incrementing length if there are extra bytes. This is called when we
do not know if we are in UTF-8 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf && c >= 0xc0u) GETUTF8LEN(c, eptr, len);
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-8 mode - we don't put a test within the macro
because almost all calls are already within a block of UTF-8 only code. */
#define BACKCHAR(eptr) while((*eptr & 0xc0u) == 0x80u) eptr--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) while((*eptr & 0xc0u) == 0x80u) eptr++
#define FORWARDCHARTEST(eptr,end) while(eptr < end && (*eptr & 0xc0u) == 0x80u) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
while((condition) && ((*eptr) & 0xc0u) == 0x80u) action
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
PRIV(ord2utf)(c,p) : (*p = c, 1))
/* ------------------- 16-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 16
#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
/* The largest UTF code point that can be encoded as a single code unit. */
#define MAX_UTF_SINGLE_CU 65535
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) (((c) & 0xfc00u) == 0xd800u)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) 1
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCU(c) (((c) & 0xfc00u) == 0xdc00u)
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer. */
#define GETUTF16(c, eptr) \
{ c = (((c & 0x3ffu) << 10) | (eptr[1] & 0x3ffu)) + 0x10000u; }
/* Get the next UTF-16 character, not advancing the pointer. This is called when
we know we are in UTF-16 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16(c, eptr);
/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, advancing
the pointer. */
#define GETUTF16INC(c, eptr) \
{ c = (((c & 0x3ffu) << 10) | (*eptr++ & 0x3ffu)) + 0x10000u; }
/* Get the next UTF-16 character, advancing the pointer. This is called when we
know we are in UTF-16 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16INC(c, eptr);
/* Get the next character, testing for UTF-16 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-16 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16INC(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer, incrementing the length. */
#define GETUTF16LEN(c, eptr, len) \
{ c = (((c & 0x3ffu) << 10) | (eptr[1] & 0x3ffu)) + 0x10000u; len++; }
/* Get the next UTF-16 character, not advancing the pointer, incrementing
length if there is a low surrogate. This is called when we know we are in
UTF-16 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16LEN(c, eptr, len);
/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
pointer, incrementing length if there is a low surrogate. This is called when
we do not know if we are in UTF-16 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16LEN(c, eptr, len);
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-16 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-16 only
code. */
#define BACKCHAR(eptr) if ((*eptr & 0xfc00u) == 0xdc00u) eptr--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00u) == 0xdc00u) eptr++
#define FORWARDCHARTEST(eptr,end) if (eptr < end && (*eptr & 0xfc00u) == 0xdc00u) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
if ((condition) && ((*eptr) & 0xfc00u) == 0xdc00u) action
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
PRIV(ord2utf)(c,p) : (*p = c, 1))
/* ------------------- 32-bit support ------------------ */
#else
/* These are trivial for the 32-bit library, since all UTF-32 characters fit
into one PCRE2_UCHAR unit. */
#define MAX_UTF_SINGLE_CU (0x10ffffu)
#define HAS_EXTRALEN(c) (0)
#define GET_EXTRALEN(c) (0)
#define NOT_FIRSTCU(c) (0)
/* Get the next UTF-32 character, not advancing the pointer. This is called when
we know we are in UTF-32 mode. */
#define GETCHAR(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, advancing the pointer. This is called when we
know we are in UTF-32 mode. */
#define GETCHARINC(c, eptr) \
c = *((eptr)++);
/* Get the next character, testing for UTF-32 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-32 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *((eptr)++);
/* Get the next UTF-32 character, not advancing the pointer, not incrementing
length (since all UTF-32 is of length 1). This is called when we know we are in
UTF-32 mode. */
#define GETCHARLEN(c, eptr, len) \
GETCHAR(c, eptr)
/* Get the next UTF-32character, testing for UTF-32 mode, not advancing the
pointer, not incrementing the length (since all UTF-32 is of length 1).
This is called when we do not know if we are in UTF-32 mode. */
#define GETCHARLENTEST(c, eptr, len) \
GETCHARTEST(c, eptr)
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-32 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-32 only
code.
These are all no-ops since all UTF-32 characters fit into one PCRE2_UCHAR. */
#define BACKCHAR(eptr) do { } while (0)
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) do { } while (0)
#define FORWARDCHARTEST(eptr,end) do { } while (0)
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) do { } while (0)
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) (*p = c, 1)
#endif /* UTF-32 character handling */
#endif /* SUPPORT_UNICODE */
/* Mode-dependent macros that have the same definition in all modes. */
#define CU2BYTES(x) ((x)*((PCRE2_CODE_UNIT_WIDTH/8)))
#define BYTES2CU(x) ((x)/((PCRE2_CODE_UNIT_WIDTH/8)))
#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE
#define PUT2INC(a,n,d) PUT2(a,n,d), a += IMM2_SIZE
/* ----------------------- HIDDEN STRUCTURES ----------------------------- */
/* NOTE: All these structures *must* start with a pcre2_memctl structure. The
code that uses them is simpler because it assumes this. */
/* The real general context structure. At present it holds only data for custom
memory control. */
typedef struct pcre2_real_general_context {
pcre2_memctl memctl;
} pcre2_real_general_context;
/* The real compile context structure */
typedef struct pcre2_real_compile_context {
pcre2_memctl memctl;
int (*stack_guard)(uint32_t, void *);
void *stack_guard_data;
const uint8_t *tables;
PCRE2_SIZE max_pattern_length;
uint16_t bsr_convention;
uint16_t newline_convention;
uint32_t parens_nest_limit;
uint32_t extra_options;
} pcre2_real_compile_context;
/* The real match context structure. */
typedef struct pcre2_real_match_context {
pcre2_memctl memctl;
#ifdef SUPPORT_JIT
pcre2_jit_callback jit_callback;
void *jit_callback_data;
#endif
int (*callout)(pcre2_callout_block *, void *);
void *callout_data;
int (*substitute_callout)(pcre2_substitute_callout_block *, void *);
void *substitute_callout_data;
PCRE2_SIZE offset_limit;
uint32_t heap_limit;
uint32_t match_limit;
uint32_t depth_limit;
} pcre2_real_match_context;
/* The real convert context structure. */
typedef struct pcre2_real_convert_context {
pcre2_memctl memctl;
uint32_t glob_separator;
uint32_t glob_escape;
} pcre2_real_convert_context;
/* The real compiled code structure. The type for the blocksize field is
defined specially because it is required in pcre2_serialize_decode() when
copying the size from possibly unaligned memory into a variable of the same
type. Use a macro rather than a typedef to avoid compiler warnings when this
file is included multiple times by pcre2test. LOOKBEHIND_MAX specifies the
largest lookbehind that is supported. (OP_REVERSE in a pattern has a 16-bit
argument in 8-bit and 16-bit modes, so we need no more than a 16-bit field
here.) */
#undef CODE_BLOCKSIZE_TYPE
#define CODE_BLOCKSIZE_TYPE size_t
#undef LOOKBEHIND_MAX
#define LOOKBEHIND_MAX UINT16_MAX
typedef struct pcre2_real_code {
pcre2_memctl memctl; /* Memory control fields */
const uint8_t *tables; /* The character tables */
void *executable_jit; /* Pointer to JIT code */
uint8_t start_bitmap[32]; /* Bitmap for starting code unit < 256 */
CODE_BLOCKSIZE_TYPE blocksize; /* Total (bytes) that was malloc-ed */
uint32_t magic_number; /* Paranoid and endianness check */
uint32_t compile_options; /* Options passed to pcre2_compile() */
uint32_t overall_options; /* Options after processing the pattern */
uint32_t extra_options; /* Taken from compile_context */
uint32_t flags; /* Various state flags */
uint32_t limit_heap; /* Limit set in the pattern */
uint32_t limit_match; /* Limit set in the pattern */
uint32_t limit_depth; /* Limit set in the pattern */
uint32_t first_codeunit; /* Starting code unit */
uint32_t last_codeunit; /* This codeunit must be seen */
uint16_t bsr_convention; /* What \R matches */
uint16_t newline_convention; /* What is a newline? */
uint16_t max_lookbehind; /* Longest lookbehind (characters) */
uint16_t minlength; /* Minimum length of match */
uint16_t top_bracket; /* Highest numbered group */
uint16_t top_backref; /* Highest numbered back reference */
uint16_t name_entry_size; /* Size (code units) of table entries */
uint16_t name_count; /* Number of name entries in the table */
} pcre2_real_code;
/* The real match data structure. Define ovector as large as it can ever
actually be so that array bound checkers don't grumble. Memory for this
structure is obtained by calling pcre2_match_data_create(), which sets the size
as the offset of ovector plus a pair of elements for each capturable string, so
the size varies from call to call. As the maximum number of capturing
subpatterns is 65535 we must allow for 65536 strings to include the overall
match. (See also the heapframe structure below.) */
struct heapframe; /* Forward reference */
typedef struct pcre2_real_match_data {
pcre2_memctl memctl; /* Memory control fields */
const pcre2_real_code *code; /* The pattern used for the match */
PCRE2_SPTR subject; /* The subject that was matched */
PCRE2_SPTR mark; /* Pointer to last mark */
struct heapframe *heapframes; /* Backtracking frames heap memory */
PCRE2_SIZE heapframes_size; /* Malloc-ed size */
PCRE2_SIZE leftchar; /* Offset to leftmost code unit */
PCRE2_SIZE rightchar; /* Offset to rightmost code unit */
PCRE2_SIZE startchar; /* Offset to starting code unit */
uint8_t matchedby; /* Type of match (normal, JIT, DFA) */
uint8_t flags; /* Various flags */
uint16_t oveccount; /* Number of pairs */
int rc; /* The return code from the match */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} pcre2_real_match_data;
/* ----------------------- PRIVATE STRUCTURES ----------------------------- */
/* These structures are not needed for pcre2test. */
#ifndef PCRE2_PCRE2TEST
/* Structures for checking for mutual recursion when scanning compiled or
parsed code. */
typedef struct recurse_check {
struct recurse_check *prev;
PCRE2_SPTR group;
} recurse_check;
typedef struct parsed_recurse_check {
struct parsed_recurse_check *prev;
uint32_t *groupptr;
} parsed_recurse_check;
/* Structure for building a cache when filling in recursion offsets. */
typedef struct recurse_cache {
PCRE2_SPTR group;
int groupnumber;
} recurse_cache;
/* Structure for maintaining a chain of pointers to the currently incomplete
branches, for testing for left recursion while compiling. */
typedef struct branch_chain {
struct branch_chain *outer;
PCRE2_UCHAR *current_branch;
} branch_chain;
/* Structure for building a list of named groups during the first pass of
compiling. */
typedef struct named_group {
PCRE2_SPTR name; /* Points to the name in the pattern */
uint32_t number; /* Group number */
uint16_t length; /* Length of the name */
uint16_t isdup; /* TRUE if a duplicate */
} named_group;
/* Structure for passing "static" information around between the functions
doing the compiling, so that they are thread-safe. */
typedef struct compile_block {
pcre2_real_compile_context *cx; /* Points to the compile context */
const uint8_t *lcc; /* Points to lower casing table */
const uint8_t *fcc; /* Points to case-flipping table */
const uint8_t *cbits; /* Points to character type table */
const uint8_t *ctypes; /* Points to table of type maps */
PCRE2_SPTR start_workspace; /* The start of working space */
PCRE2_SPTR start_code; /* The start of the compiled code */
PCRE2_SPTR start_pattern; /* The start of the pattern */
PCRE2_SPTR end_pattern; /* The end of the pattern */
PCRE2_UCHAR *name_table; /* The name/number table */
PCRE2_SIZE workspace_size; /* Size of workspace */
PCRE2_SIZE small_ref_offset[10]; /* Offsets for \1 to \9 */
PCRE2_SIZE erroroffset; /* Offset of error in pattern */
uint16_t names_found; /* Number of entries so far */
uint16_t name_entry_size; /* Size of each entry */
uint16_t parens_depth; /* Depth of nested parentheses */
uint16_t assert_depth; /* Depth of nested assertions */
open_capitem *open_caps; /* Chain of open capture items */
named_group *named_groups; /* Points to vector in pre-compile */
uint32_t named_group_list_size; /* Number of entries in the list */
uint32_t external_options; /* External (initial) options */
uint32_t external_flags; /* External flag bits to be set */
uint32_t bracount; /* Count of capturing parentheses */
uint32_t lastcapture; /* Last capture encountered */
uint32_t *parsed_pattern; /* Parsed pattern buffer */
uint32_t *parsed_pattern_end; /* Parsed pattern should not get here */
uint32_t *groupinfo; /* Group info vector */
uint32_t top_backref; /* Maximum back reference */
uint32_t backref_map; /* Bitmap of low back refs */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
uint32_t class_range_start; /* Overall class range start */
uint32_t class_range_end; /* Overall class range end */
PCRE2_UCHAR nl[4]; /* Newline string when fixed length */
uint32_t req_varyopt; /* "After variable item" flag for reqbyte */
int max_lookbehind; /* Maximum lookbehind (characters) */
BOOL had_accept; /* (*ACCEPT) encountered */
BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */
BOOL had_recurse; /* Had a recursion or subroutine call */
BOOL dupnames; /* Duplicate names exist */
} compile_block;
/* Structure for keeping the properties of the in-memory stack used
by the JIT matcher. */
typedef struct pcre2_real_jit_stack {
pcre2_memctl memctl;
void* stack;
} pcre2_real_jit_stack;
/* Structure for items in a linked list that represents an explicit recursive
call within the pattern when running pcre2_dfa_match(). */
typedef struct dfa_recursion_info {
struct dfa_recursion_info *prevrec;
PCRE2_SPTR subject_position;
uint32_t group_num;
} dfa_recursion_info;
/* Structure for "stack" frames that are used for remembering backtracking
positions during matching. As these are used in a vector, with the ovector item
being extended, the size of the structure must be a multiple of PCRE2_SIZE. The
only way to check this at compile time is to force an error by generating an
array with a negative size. By putting this in a typedef (which is never used),
we don't generate any code when all is well. */
typedef struct heapframe {
/* The first set of fields are variables that have to be preserved over calls
to RRMATCH(), but which do not need to be copied to new frames. */
PCRE2_SPTR ecode; /* The current position in the pattern */
PCRE2_SPTR temp_sptr[2]; /* Used for short-term PCRE_SPTR values */
PCRE2_SIZE length; /* Used for character, string, or code lengths */
PCRE2_SIZE back_frame; /* Amount to subtract on RRETURN */
PCRE2_SIZE temp_size; /* Used for short-term PCRE2_SIZE values */
uint32_t rdepth; /* "Recursion" depth */
uint32_t group_frame_type; /* Type information for group frames */
uint32_t temp_32[4]; /* Used for short-term 32-bit or BOOL values */
uint8_t return_id; /* Where to go on in internal "return" */
uint8_t op; /* Processing opcode */
/* At this point, the structure is 16-bit aligned. On most architectures
the alignment requirement for a pointer will ensure that the eptr field below
is 32-bit or 64-bit aligned. However, on m68k it is fine to have a pointer
that is 16-bit aligned. We must therefore ensure that what comes between here
and eptr is an odd multiple of 16 bits so as to get back into 32-bit
alignment. This happens naturally when PCRE2_UCHAR is 8 bits wide, but needs
fudges in the other cases. In the 32-bit case the padding comes first so that
the occu field itself is 32-bit aligned. Without the padding, this structure
is no longer a multiple of PCRE2_SIZE on m68k, and the check below fails. */
#if PCRE2_CODE_UNIT_WIDTH == 8
PCRE2_UCHAR occu[6]; /* Used for other case code units */
#elif PCRE2_CODE_UNIT_WIDTH == 16
PCRE2_UCHAR occu[2]; /* Used for other case code units */
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
#else
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
PCRE2_UCHAR occu[1]; /* Used for other case code units */
#endif
/* The rest have to be copied from the previous frame whenever a new frame
becomes current. The final field is specified as a large vector so that
runtime array bound checks don't catch references to it. However, for any
specific call to pcre2_match() the memory allocated for each frame structure
allows for exactly the right size ovector for the number of capturing
parentheses. (See also the comment for pcre2_real_match_data above.) */
PCRE2_SPTR eptr; /* MUST BE FIRST */
PCRE2_SPTR start_match; /* Can be adjusted by \K */
PCRE2_SPTR mark; /* Most recent mark on the success path */
uint32_t current_recurse; /* Current (deepest) recursion number */
uint32_t capture_last; /* Most recent capture */
PCRE2_SIZE last_group_offset; /* Saved offset to most recent group frame */
PCRE2_SIZE offset_top; /* Offset after highest capture */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} heapframe;
/* This typedef is a check that the size of the heapframe structure is a
multiple of PCRE2_SIZE. See various comments above. */
typedef char check_heapframe_size[
((sizeof(heapframe) % sizeof(PCRE2_SIZE)) == 0)? (+1):(-1)];
/* Structure for computing the alignment of heapframe. */
typedef struct heapframe_align {
char unalign; /* Completely unalign the current offset */
heapframe frame; /* Offset is its alignment */
} heapframe_align;
/* This define is the minimum alignment required for a heapframe, in bytes. */
#define HEAPFRAME_ALIGNMENT offsetof(heapframe_align, frame)
/* Structure for passing "static" information around between the functions
doing traditional NFA matching (pcre2_match() and friends). */
typedef struct match_block {
pcre2_memctl memctl; /* For general use */
PCRE2_SIZE heap_limit; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of times a new frame is created */
BOOL hitend; /* Hit the end of the subject at some point */
BOOL hasthen; /* Pattern contains (*THEN) */
BOOL allowemptypartial; /* Allow empty hard partial */
const uint8_t *lcc; /* Points to lower casing table */
const uint8_t *fcc; /* Points to case-flipping table */
const uint8_t *ctypes; /* Points to table of type maps */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE end_offset_top; /* Highwater mark at end of match */
uint16_t partial; /* PARTIAL options */
uint16_t bsr_convention; /* \R interpretation */
uint16_t name_count; /* Number of names in name table */
uint16_t name_entry_size; /* Size of entry in names table */
PCRE2_SPTR name_table; /* Table of group names */
PCRE2_SPTR start_code; /* For use when recursing */
PCRE2_SPTR start_subject; /* Start of the subject string */
PCRE2_SPTR check_subject; /* Where UTF-checked from */
PCRE2_SPTR end_subject; /* End of the subject string */
PCRE2_SPTR end_match_ptr; /* Subject position at end match */
PCRE2_SPTR start_used_ptr; /* Earliest consulted character */
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
PCRE2_SPTR mark; /* Mark pointer to pass back on success */
PCRE2_SPTR nomatch_mark; /* Mark pointer to pass back on failure */
PCRE2_SPTR verb_ecode_ptr; /* For passing back info */
PCRE2_SPTR verb_skip_ptr; /* For passing back a (*SKIP) name */
uint32_t verb_current_recurse; /* Current recurse when (*VERB) happens */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t skip_arg_count; /* For counting SKIP_ARGs */
uint32_t ignore_skip_arg; /* For re-run when SKIP arg name not found */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
} match_block;
/* A similar structure is used for the same purpose by the DFA matching
functions. */
typedef struct dfa_match_block {
pcre2_memctl memctl; /* For general use */
PCRE2_SPTR start_code; /* Start of the compiled pattern */
PCRE2_SPTR start_subject ; /* Start of the subject string */
PCRE2_SPTR end_subject; /* End of subject string */
PCRE2_SPTR start_used_ptr; /* Earliest consulted character */
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
const uint8_t *tables; /* Character tables */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE heap_limit; /* As it says */
PCRE2_SIZE heap_used; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of calls of internal function */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
BOOL allowemptypartial; /* Allow empty hard partial */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
uint16_t bsr_convention; /* \R interpretation */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
dfa_recursion_info *recursive; /* Linked list of recursion data */
} dfa_match_block;
#endif /* PCRE2_PCRE2TEST */
/* End of pcre2_intmodedep.h */

163
third_party/pcre/pcre2_maketables.c vendored Normal file
View file

@ -0,0 +1,163 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains the external function pcre2_maketables(), which builds
character tables for PCRE2 in the current locale. The file is compiled on its
own as part of the PCRE2 library. It is also included in the compilation of
pcre2_dftables.c as a freestanding program, in which case the macro
PCRE2_DFTABLES is defined. */
#ifndef PCRE2_DFTABLES /* Compiling the library */
# ifdef HAVE_CONFIG_H
# include "config.h"
# endif
# include "pcre2_internal.h"
#endif
/*************************************************
* Create PCRE2 character tables *
*************************************************/
/* This function builds a set of character tables for use by PCRE2 and returns
a pointer to them. They are build using the ctype functions, and consequently
their contents will depend upon the current locale setting. When compiled as
part of the library, the store is obtained via a general context malloc, if
supplied, but when PCRE2_DFTABLES is defined (when compiling the pcre2_dftables
freestanding auxiliary program) malloc() is used, and the function has a
different name so as not to clash with the prototype in pcre2.h.
Arguments: none when PCRE2_DFTABLES is defined
else a PCRE2 general context or NULL
Returns: pointer to the contiguous block of data
else NULL if memory allocation failed
*/
#ifdef PCRE2_DFTABLES /* Included in freestanding pcre2_dftables program */
static const uint8_t *maketables(void)
{
uint8_t *yield = (uint8_t *)malloc(TABLES_LENGTH);
#else /* Not PCRE2_DFTABLES, that is, compiling the library */
PCRE2_EXP_DEFN const uint8_t * PCRE2_CALL_CONVENTION
pcre2_maketables(pcre2_general_context *gcontext)
{
uint8_t *yield = (uint8_t *)((gcontext != NULL)?
gcontext->memctl.malloc(TABLES_LENGTH, gcontext->memctl.memory_data) :
malloc(TABLES_LENGTH));
#endif /* PCRE2_DFTABLES */
int i;
uint8_t *p;
if (yield == NULL) return NULL;
p = yield;
/* First comes the lower casing table */
for (i = 0; i < 256; i++) *p++ = tolower(i);
/* Next the case-flipping table */
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i);
/* Then the character class tables. Don't try to be clever and save effort on
exclusive ones - in some locales things may be different.
Note that the table for "space" includes everything "isspace" gives, including
VT in the default locale. This makes it work for the POSIX class [:space:].
From PCRE1 release 8.34 and for all PCRE2 releases it is also correct for Perl
space, because Perl added VT at release 5.18.
Note also that it is possible for a character to be alnum or alpha without
being lower or upper, such as "male and female ordinals" (\xAA and \xBA) in the
fr_FR locale (at least under Debian Linux's locales as of 12/2005). So we must
test for alnum specially. */
memset(p, 0, cbit_length);
for (i = 0; i < 256; i++)
{
if (isdigit(i)) p[cbit_digit + i/8] |= 1u << (i&7);
if (isupper(i)) p[cbit_upper + i/8] |= 1u << (i&7);
if (islower(i)) p[cbit_lower + i/8] |= 1u << (i&7);
if (isalnum(i)) p[cbit_word + i/8] |= 1u << (i&7);
if (i == '_') p[cbit_word + i/8] |= 1u << (i&7);
if (isspace(i)) p[cbit_space + i/8] |= 1u << (i&7);
if (isxdigit(i)) p[cbit_xdigit + i/8] |= 1u << (i&7);
if (isgraph(i)) p[cbit_graph + i/8] |= 1u << (i&7);
if (isprint(i)) p[cbit_print + i/8] |= 1u << (i&7);
if (ispunct(i)) p[cbit_punct + i/8] |= 1u << (i&7);
if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1u << (i&7);
}
p += cbit_length;
/* Finally, the character type table. In this, we used to exclude VT from the
white space chars, because Perl didn't recognize it as such for \s and for
comments within regexes. However, Perl changed at release 5.18, so PCRE1
changed at release 8.34 and it's always been this way for PCRE2. */
for (i = 0; i < 256; i++)
{
int x = 0;
if (isspace(i)) x += ctype_space;
if (isalpha(i)) x += ctype_letter;
if (islower(i)) x += ctype_lcletter;
if (isdigit(i)) x += ctype_digit;
if (isalnum(i) || i == '_') x += ctype_word;
*p++ = x;
}
return yield;
}
#ifndef PCRE2_DFTABLES /* Compiling the library */
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_maketables_free(pcre2_general_context *gcontext, const uint8_t *tables)
{
if (gcontext)
gcontext->memctl.free((void *)tables, gcontext->memctl.memory_data);
else
free((void *)tables);
}
#endif
/* End of pcre2_maketables.c */

7548
third_party/pcre/pcre2_match.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

173
third_party/pcre/pcre2_match_data.c vendored Normal file
View file

@ -0,0 +1,173 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Create a match data block given ovector size *
*************************************************/
/* A minimum of 1 is imposed on the number of ovector pairs. A maximum is also
imposed because the oveccount field in a match data block is uintt6_t. */
PCRE2_EXP_DEFN pcre2_match_data * PCRE2_CALL_CONVENTION
pcre2_match_data_create(uint32_t oveccount, pcre2_general_context *gcontext)
{
pcre2_match_data *yield;
if (oveccount < 1) oveccount = 1;
if (oveccount > UINT16_MAX) oveccount = UINT16_MAX;
yield = PRIV(memctl_malloc)(
offsetof(pcre2_match_data, ovector) + 2*oveccount*sizeof(PCRE2_SIZE),
(pcre2_memctl *)gcontext);
if (yield == NULL) return NULL;
yield->oveccount = oveccount;
yield->flags = 0;
yield->heapframes = NULL;
yield->heapframes_size = 0;
return yield;
}
/*************************************************
* Create a match data block using pattern data *
*************************************************/
/* If no context is supplied, use the memory allocator from the code. */
PCRE2_EXP_DEFN pcre2_match_data * PCRE2_CALL_CONVENTION
pcre2_match_data_create_from_pattern(const pcre2_code *code,
pcre2_general_context *gcontext)
{
if (gcontext == NULL) gcontext = (pcre2_general_context *)code;
return pcre2_match_data_create(((pcre2_real_code *)code)->top_bracket + 1,
gcontext);
}
/*************************************************
* Free a match data block *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_match_data_free(pcre2_match_data *match_data)
{
if (match_data != NULL)
{
if (match_data->heapframes != NULL)
match_data->memctl.free(match_data->heapframes,
match_data->memctl.memory_data);
if ((match_data->flags & PCRE2_MD_COPIED_SUBJECT) != 0)
match_data->memctl.free((void *)match_data->subject,
match_data->memctl.memory_data);
match_data->memctl.free(match_data, match_data->memctl.memory_data);
}
}
/*************************************************
* Get last mark in match *
*************************************************/
PCRE2_EXP_DEFN PCRE2_SPTR PCRE2_CALL_CONVENTION
pcre2_get_mark(pcre2_match_data *match_data)
{
return match_data->mark;
}
/*************************************************
* Get pointer to ovector *
*************************************************/
PCRE2_EXP_DEFN PCRE2_SIZE * PCRE2_CALL_CONVENTION
pcre2_get_ovector_pointer(pcre2_match_data *match_data)
{
return match_data->ovector;
}
/*************************************************
* Get number of ovector slots *
*************************************************/
PCRE2_EXP_DEFN uint32_t PCRE2_CALL_CONVENTION
pcre2_get_ovector_count(pcre2_match_data *match_data)
{
return match_data->oveccount;
}
/*************************************************
* Get starting code unit in match *
*************************************************/
PCRE2_EXP_DEFN PCRE2_SIZE PCRE2_CALL_CONVENTION
pcre2_get_startchar(pcre2_match_data *match_data)
{
return match_data->startchar;
}
/*************************************************
* Get size of match data block *
*************************************************/
PCRE2_EXP_DEFN PCRE2_SIZE PCRE2_CALL_CONVENTION
pcre2_get_match_data_size(pcre2_match_data *match_data)
{
return offsetof(pcre2_match_data, ovector) +
2 * (match_data->oveccount) * sizeof(PCRE2_SIZE);
}
/* End of pcre2_match_data.c */

243
third_party/pcre/pcre2_newline.c vendored Normal file
View file

@ -0,0 +1,243 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains internal functions for testing newlines when more than
one kind of newline is to be recognized. When a newline is found, its length is
returned. In principle, we could implement several newline "types", each
referring to a different set of newline characters. At present, PCRE2 supports
only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF,
and NLTYPE_ANY. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Check for newline at given position *
*************************************************/
/* This function is called only via the IS_NEWLINE macro, which does so only
when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the code unit
pointed to by ptr is less than the end of the string.
Arguments:
ptr pointer to possible newline
type the newline type
endptr pointer to the end of the string
lenptr where to return the length
utf TRUE if in utf mode
Returns: TRUE or FALSE
*/
BOOL
PRIV(is_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR endptr,
uint32_t *lenptr, BOOL utf)
{
uint32_t c;
#ifdef SUPPORT_UNICODE
if (utf) { GETCHAR(c, ptr); } else c = *ptr;
#else
(void)utf;
c = *ptr;
#endif /* SUPPORT_UNICODE */
if (type == NLTYPE_ANYCRLF) switch(c)
{
case CHAR_LF:
*lenptr = 1;
return TRUE;
case CHAR_CR:
*lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
return TRUE;
default:
return FALSE;
}
/* NLTYPE_ANY */
else switch(c)
{
#ifdef EBCDIC
case CHAR_NEL:
#endif
case CHAR_LF:
case CHAR_VT:
case CHAR_FF:
*lenptr = 1;
return TRUE;
case CHAR_CR:
*lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
return TRUE;
#ifndef EBCDIC
#if PCRE2_CODE_UNIT_WIDTH == 8
case CHAR_NEL:
*lenptr = utf? 2 : 1;
return TRUE;
case 0x2028: /* LS */
case 0x2029: /* PS */
*lenptr = 3;
return TRUE;
#else /* 16-bit or 32-bit code units */
case CHAR_NEL:
case 0x2028: /* LS */
case 0x2029: /* PS */
*lenptr = 1;
return TRUE;
#endif
#endif /* Not EBCDIC */
default:
return FALSE;
}
}
/*************************************************
* Check for newline at previous position *
*************************************************/
/* This function is called only via the WAS_NEWLINE macro, which does so only
when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the initial
value of ptr is greater than the start of the string that is being processed.
Arguments:
ptr pointer to possible newline
type the newline type
startptr pointer to the start of the string
lenptr where to return the length
utf TRUE if in utf mode
Returns: TRUE or FALSE
*/
BOOL
PRIV(was_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR startptr,
uint32_t *lenptr, BOOL utf)
{
uint32_t c;
ptr--;
#ifdef SUPPORT_UNICODE
if (utf)
{
BACKCHAR(ptr);
GETCHAR(c, ptr);
}
else c = *ptr;
#else
(void)utf;
c = *ptr;
#endif /* SUPPORT_UNICODE */
if (type == NLTYPE_ANYCRLF) switch(c)
{
case CHAR_LF:
*lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
return TRUE;
case CHAR_CR:
*lenptr = 1;
return TRUE;
default:
return FALSE;
}
/* NLTYPE_ANY */
else switch(c)
{
case CHAR_LF:
*lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
return TRUE;
#ifdef EBCDIC
case CHAR_NEL:
#endif
case CHAR_VT:
case CHAR_FF:
case CHAR_CR:
*lenptr = 1;
return TRUE;
#ifndef EBCDIC
#if PCRE2_CODE_UNIT_WIDTH == 8
case CHAR_NEL:
*lenptr = utf? 2 : 1;
return TRUE;
case 0x2028: /* LS */
case 0x2029: /* PS */
*lenptr = 3;
return TRUE;
#else /* 16-bit or 32-bit code units */
case CHAR_NEL:
case 0x2028: /* LS */
case 0x2029: /* PS */
*lenptr = 1;
return TRUE;
#endif
#endif /* Not EBCDIC */
default:
return FALSE;
}
}
/* End of pcre2_newline.c */

120
third_party/pcre/pcre2_ord2utf.c vendored Normal file
View file

@ -0,0 +1,120 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This file contains a function that converts a Unicode character code point
into a UTF string. The behaviour is different for each code unit width. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* If SUPPORT_UNICODE is not defined, this function will never be called.
Supply a dummy function because some compilers do not like empty source
modules. */
#ifndef SUPPORT_UNICODE
unsigned int
PRIV(ord2utf)(uint32_t cvalue, PCRE2_UCHAR *buffer)
{
(void)(cvalue);
(void)(buffer);
return 0;
}
#else /* SUPPORT_UNICODE */
/*************************************************
* Convert code point to UTF *
*************************************************/
/*
Arguments:
cvalue the character value
buffer pointer to buffer for result
Returns: number of code units placed in the buffer
*/
unsigned int
PRIV(ord2utf)(uint32_t cvalue, PCRE2_UCHAR *buffer)
{
/* Convert to UTF-8 */
#if PCRE2_CODE_UNIT_WIDTH == 8
int i, j;
for (i = 0; i < PRIV(utf8_table1_size); i++)
if ((int)cvalue <= PRIV(utf8_table1)[i]) break;
buffer += i;
for (j = i; j > 0; j--)
{
*buffer-- = 0x80 | (cvalue & 0x3f);
cvalue >>= 6;
}
*buffer = PRIV(utf8_table2)[i] | cvalue;
return i + 1;
/* Convert to UTF-16 */
#elif PCRE2_CODE_UNIT_WIDTH == 16
if (cvalue <= 0xffff)
{
*buffer = (PCRE2_UCHAR)cvalue;
return 1;
}
cvalue -= 0x10000;
*buffer++ = 0xd800 | (cvalue >> 10);
*buffer = 0xdc00 | (cvalue & 0x3ff);
return 2;
/* Convert to UTF-32 */
#else
*buffer = (PCRE2_UCHAR)cvalue;
return 1;
#endif
}
#endif /* SUPPORT_UNICODE */
/* End of pcre_ord2utf.c */

432
third_party/pcre/pcre2_pattern_info.c vendored Normal file
View file

@ -0,0 +1,432 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Return info about compiled pattern *
*************************************************/
/*
Arguments:
code points to compiled code
what what information is required
where where to put the information; if NULL, return length
Returns: 0 when data returned
> 0 when length requested
< 0 on error or unset value
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_pattern_info(const pcre2_code *code, uint32_t what, void *where)
{
const pcre2_real_code *re = (pcre2_real_code *)code;
if (where == NULL) /* Requests field length */
{
switch(what)
{
case PCRE2_INFO_ALLOPTIONS:
case PCRE2_INFO_ARGOPTIONS:
case PCRE2_INFO_BACKREFMAX:
case PCRE2_INFO_BSR:
case PCRE2_INFO_CAPTURECOUNT:
case PCRE2_INFO_DEPTHLIMIT:
case PCRE2_INFO_EXTRAOPTIONS:
case PCRE2_INFO_FIRSTCODETYPE:
case PCRE2_INFO_FIRSTCODEUNIT:
case PCRE2_INFO_HASBACKSLASHC:
case PCRE2_INFO_HASCRORLF:
case PCRE2_INFO_HEAPLIMIT:
case PCRE2_INFO_JCHANGED:
case PCRE2_INFO_LASTCODETYPE:
case PCRE2_INFO_LASTCODEUNIT:
case PCRE2_INFO_MATCHEMPTY:
case PCRE2_INFO_MATCHLIMIT:
case PCRE2_INFO_MAXLOOKBEHIND:
case PCRE2_INFO_MINLENGTH:
case PCRE2_INFO_NAMEENTRYSIZE:
case PCRE2_INFO_NAMECOUNT:
case PCRE2_INFO_NEWLINE:
return sizeof(uint32_t);
case PCRE2_INFO_FIRSTBITMAP:
return sizeof(const uint8_t *);
case PCRE2_INFO_JITSIZE:
case PCRE2_INFO_SIZE:
case PCRE2_INFO_FRAMESIZE:
return sizeof(size_t);
case PCRE2_INFO_NAMETABLE:
return sizeof(PCRE2_SPTR);
}
}
if (re == NULL) return PCRE2_ERROR_NULL;
/* Check that the first field in the block is the magic number. If it is not,
return with PCRE2_ERROR_BADMAGIC. */
if (re->magic_number != MAGIC_NUMBER) return PCRE2_ERROR_BADMAGIC;
/* Check that this pattern was compiled in the correct bit mode */
if ((re->flags & (PCRE2_CODE_UNIT_WIDTH/8)) == 0) return PCRE2_ERROR_BADMODE;
switch(what)
{
case PCRE2_INFO_ALLOPTIONS:
*((uint32_t *)where) = re->overall_options;
break;
case PCRE2_INFO_ARGOPTIONS:
*((uint32_t *)where) = re->compile_options;
break;
case PCRE2_INFO_BACKREFMAX:
*((uint32_t *)where) = re->top_backref;
break;
case PCRE2_INFO_BSR:
*((uint32_t *)where) = re->bsr_convention;
break;
case PCRE2_INFO_CAPTURECOUNT:
*((uint32_t *)where) = re->top_bracket;
break;
case PCRE2_INFO_DEPTHLIMIT:
*((uint32_t *)where) = re->limit_depth;
if (re->limit_depth == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_EXTRAOPTIONS:
*((uint32_t *)where) = re->extra_options;
break;
case PCRE2_INFO_FIRSTCODETYPE:
*((uint32_t *)where) = ((re->flags & PCRE2_FIRSTSET) != 0)? 1 :
((re->flags & PCRE2_STARTLINE) != 0)? 2 : 0;
break;
case PCRE2_INFO_FIRSTCODEUNIT:
*((uint32_t *)where) = ((re->flags & PCRE2_FIRSTSET) != 0)?
re->first_codeunit : 0;
break;
case PCRE2_INFO_FIRSTBITMAP:
*((const uint8_t **)where) = ((re->flags & PCRE2_FIRSTMAPSET) != 0)?
&(re->start_bitmap[0]) : NULL;
break;
case PCRE2_INFO_FRAMESIZE:
*((size_t *)where) = offsetof(heapframe, ovector) +
re->top_bracket * 2 * sizeof(PCRE2_SIZE);
break;
case PCRE2_INFO_HASBACKSLASHC:
*((uint32_t *)where) = (re->flags & PCRE2_HASBKC) != 0;
break;
case PCRE2_INFO_HASCRORLF:
*((uint32_t *)where) = (re->flags & PCRE2_HASCRORLF) != 0;
break;
case PCRE2_INFO_HEAPLIMIT:
*((uint32_t *)where) = re->limit_heap;
if (re->limit_heap == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_JCHANGED:
*((uint32_t *)where) = (re->flags & PCRE2_JCHANGED) != 0;
break;
case PCRE2_INFO_JITSIZE:
#ifdef SUPPORT_JIT
*((size_t *)where) = (re->executable_jit != NULL)?
PRIV(jit_get_size)(re->executable_jit) : 0;
#else
*((size_t *)where) = 0;
#endif
break;
case PCRE2_INFO_LASTCODETYPE:
*((uint32_t *)where) = ((re->flags & PCRE2_LASTSET) != 0)? 1 : 0;
break;
case PCRE2_INFO_LASTCODEUNIT:
*((uint32_t *)where) = ((re->flags & PCRE2_LASTSET) != 0)?
re->last_codeunit : 0;
break;
case PCRE2_INFO_MATCHEMPTY:
*((uint32_t *)where) = (re->flags & PCRE2_MATCH_EMPTY) != 0;
break;
case PCRE2_INFO_MATCHLIMIT:
*((uint32_t *)where) = re->limit_match;
if (re->limit_match == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_MAXLOOKBEHIND:
*((uint32_t *)where) = re->max_lookbehind;
break;
case PCRE2_INFO_MINLENGTH:
*((uint32_t *)where) = re->minlength;
break;
case PCRE2_INFO_NAMEENTRYSIZE:
*((uint32_t *)where) = re->name_entry_size;
break;
case PCRE2_INFO_NAMECOUNT:
*((uint32_t *)where) = re->name_count;
break;
case PCRE2_INFO_NAMETABLE:
*((PCRE2_SPTR *)where) = (PCRE2_SPTR)((char *)re + sizeof(pcre2_real_code));
break;
case PCRE2_INFO_NEWLINE:
*((uint32_t *)where) = re->newline_convention;
break;
case PCRE2_INFO_SIZE:
*((size_t *)where) = re->blocksize;
break;
default: return PCRE2_ERROR_BADOPTION;
}
return 0;
}
/*************************************************
* Callout enumerator *
*************************************************/
/*
Arguments:
code points to compiled code
callback function called for each callout block
callout_data user data passed to the callback
Returns: 0 when successfully completed
< 0 on local error
!= 0 for callback error
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_callout_enumerate(const pcre2_code *code,
int (*callback)(pcre2_callout_enumerate_block *, void *), void *callout_data)
{
pcre2_real_code *re = (pcre2_real_code *)code;
pcre2_callout_enumerate_block cb;
PCRE2_SPTR cc;
#ifdef SUPPORT_UNICODE
BOOL utf;
#endif
if (re == NULL) return PCRE2_ERROR_NULL;
#ifdef SUPPORT_UNICODE
utf = (re->overall_options & PCRE2_UTF) != 0;
#endif
/* Check that the first field in the block is the magic number. If it is not,
return with PCRE2_ERROR_BADMAGIC. */
if (re->magic_number != MAGIC_NUMBER) return PCRE2_ERROR_BADMAGIC;
/* Check that this pattern was compiled in the correct bit mode */
if ((re->flags & (PCRE2_CODE_UNIT_WIDTH/8)) == 0) return PCRE2_ERROR_BADMODE;
cb.version = 0;
cc = (PCRE2_SPTR)((uint8_t *)re + sizeof(pcre2_real_code))
+ re->name_count * re->name_entry_size;
while (TRUE)
{
int rc;
switch (*cc)
{
case OP_END:
return 0;
case OP_CHAR:
case OP_CHARI:
case OP_NOT:
case OP_NOTI:
case OP_STAR:
case OP_MINSTAR:
case OP_PLUS:
case OP_MINPLUS:
case OP_QUERY:
case OP_MINQUERY:
case OP_UPTO:
case OP_MINUPTO:
case OP_EXACT:
case OP_POSSTAR:
case OP_POSPLUS:
case OP_POSQUERY:
case OP_POSUPTO:
case OP_STARI:
case OP_MINSTARI:
case OP_PLUSI:
case OP_MINPLUSI:
case OP_QUERYI:
case OP_MINQUERYI:
case OP_UPTOI:
case OP_MINUPTOI:
case OP_EXACTI:
case OP_POSSTARI:
case OP_POSPLUSI:
case OP_POSQUERYI:
case OP_POSUPTOI:
case OP_NOTSTAR:
case OP_NOTMINSTAR:
case OP_NOTPLUS:
case OP_NOTMINPLUS:
case OP_NOTQUERY:
case OP_NOTMINQUERY:
case OP_NOTUPTO:
case OP_NOTMINUPTO:
case OP_NOTEXACT:
case OP_NOTPOSSTAR:
case OP_NOTPOSPLUS:
case OP_NOTPOSQUERY:
case OP_NOTPOSUPTO:
case OP_NOTSTARI:
case OP_NOTMINSTARI:
case OP_NOTPLUSI:
case OP_NOTMINPLUSI:
case OP_NOTQUERYI:
case OP_NOTMINQUERYI:
case OP_NOTUPTOI:
case OP_NOTMINUPTOI:
case OP_NOTEXACTI:
case OP_NOTPOSSTARI:
case OP_NOTPOSPLUSI:
case OP_NOTPOSQUERYI:
case OP_NOTPOSUPTOI:
cc += PRIV(OP_lengths)[*cc];
#ifdef SUPPORT_UNICODE
if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
#endif
break;
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
case OP_TYPEEXACT:
case OP_TYPEPOSSTAR:
case OP_TYPEPOSPLUS:
case OP_TYPEPOSQUERY:
case OP_TYPEPOSUPTO:
cc += PRIV(OP_lengths)[*cc];
#ifdef SUPPORT_UNICODE
if (cc[-1] == OP_PROP || cc[-1] == OP_NOTPROP) cc += 2;
#endif
break;
#if defined SUPPORT_UNICODE || PCRE2_CODE_UNIT_WIDTH != 8
case OP_XCLASS:
cc += GET(cc, 1);
break;
#endif
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
cc += PRIV(OP_lengths)[*cc] + cc[1];
break;
case OP_CALLOUT:
cb.pattern_position = GET(cc, 1);
cb.next_item_length = GET(cc, 1 + LINK_SIZE);
cb.callout_number = cc[1 + 2*LINK_SIZE];
cb.callout_string_offset = 0;
cb.callout_string_length = 0;
cb.callout_string = NULL;
rc = callback(&cb, callout_data);
if (rc != 0) return rc;
cc += PRIV(OP_lengths)[*cc];
break;
case OP_CALLOUT_STR:
cb.pattern_position = GET(cc, 1);
cb.next_item_length = GET(cc, 1 + LINK_SIZE);
cb.callout_number = 0;
cb.callout_string_offset = GET(cc, 1 + 3*LINK_SIZE);
cb.callout_string_length =
GET(cc, 1 + 2*LINK_SIZE) - (1 + 4*LINK_SIZE) - 2;
cb.callout_string = cc + (1 + 4*LINK_SIZE) + 1;
rc = callback(&cb, callout_data);
if (rc != 0) return rc;
cc += GET(cc, 1 + 2*LINK_SIZE);
break;
default:
cc += PRIV(OP_lengths)[*cc];
break;
}
}
}
/* End of pcre2_pattern_info.c */

868
third_party/pcre/pcre2_printint.inc vendored Normal file
View file

@ -0,0 +1,868 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains a PCRE private debugging function for printing out the
internal form of a compiled regular expression, along with some supporting
local functions. This source file is #included in pcre2test.c at each supported
code unit width, with PCRE2_SUFFIX set appropriately, just like the functions
that comprise the library. It can also optionally be included in
pcre2_compile.c for detailed debugging in error situations. */
/* Tables of operator names. The same 8-bit table is used for all code unit
widths, so it must be defined only once. The list itself is defined in
pcre2_internal.h, which is #included by pcre2test before this file. */
#ifndef OP_LISTS_DEFINED
static const char *OP_names[] = { OP_NAME_LIST };
#define OP_LISTS_DEFINED
#endif
/* The functions and tables herein must all have mode-dependent names. */
#define OP_lengths PCRE2_SUFFIX(OP_lengths_)
#define get_ucpname PCRE2_SUFFIX(get_ucpname_)
#define pcre2_printint PCRE2_SUFFIX(pcre2_printint_)
#define print_char PCRE2_SUFFIX(print_char_)
#define print_custring PCRE2_SUFFIX(print_custring_)
#define print_custring_bylen PCRE2_SUFFIX(print_custring_bylen_)
#define print_prop PCRE2_SUFFIX(print_prop_)
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
the definition is next to the definition of the opcodes in pcre2_internal.h.
The contents of the table are, however, mode-dependent. */
static const uint8_t OP_lengths[] = { OP_LENGTHS };
/*************************************************
* Print one character from a string *
*************************************************/
/* In UTF mode the character may occupy more than one code unit.
Arguments:
f file to write to
ptr pointer to first code unit of the character
utf TRUE if string is UTF (will be FALSE if UTF is not supported)
Returns: number of additional code units used
*/
static unsigned int
print_char(FILE *f, PCRE2_SPTR ptr, BOOL utf)
{
uint32_t c = *ptr;
BOOL one_code_unit = !utf;
/* If UTF is supported and requested, check for a valid single code unit. */
#ifdef SUPPORT_UNICODE
if (utf)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
one_code_unit = c < 0x80;
#elif PCRE2_CODE_UNIT_WIDTH == 16
one_code_unit = (c & 0xfc00) != 0xd800;
#else
one_code_unit = (c & 0xfffff800u) != 0xd800u;
#endif /* CODE_UNIT_WIDTH */
}
#endif /* SUPPORT_UNICODE */
/* Handle a valid one-code-unit character at any width. */
if (one_code_unit)
{
if (PRINTABLE(c)) fprintf(f, "%c", (char)c);
else if (c < 0x80) fprintf(f, "\\x%02x", c);
else fprintf(f, "\\x{%02x}", c);
return 0;
}
/* Code for invalid UTF code units and multi-unit UTF characters is different
for each width. If UTF is not supported, control should never get here, but we
need a return statement to keep the compiler happy. */
#ifndef SUPPORT_UNICODE
return 0;
#else
/* Malformed UTF-8 should occur only if the sanity check has been turned off.
Rather than swallow random bytes, just stop if we hit a bad one. Print it with
\X instead of \x as an indication. */
#if PCRE2_CODE_UNIT_WIDTH == 8
if ((c & 0xc0) != 0xc0)
{
fprintf(f, "\\X{%x}", c); /* Invalid starting byte */
return 0;
}
else
{
int i;
int a = PRIV(utf8_table4)[c & 0x3f]; /* Number of additional bytes */
int s = 6*a;
c = (c & PRIV(utf8_table3)[a]) << s;
for (i = 1; i <= a; i++)
{
if ((ptr[i] & 0xc0) != 0x80)
{
fprintf(f, "\\X{%x}", c); /* Invalid secondary byte */
return i - 1;
}
s -= 6;
c |= (ptr[i] & 0x3f) << s;
}
fprintf(f, "\\x{%x}", c);
return a;
}
#endif /* PCRE2_CODE_UNIT_WIDTH == 8 */
/* UTF-16: rather than swallow a low surrogate, just stop if we hit a bad one.
Print it with \X instead of \x as an indication. */
#if PCRE2_CODE_UNIT_WIDTH == 16
if ((ptr[1] & 0xfc00) != 0xdc00)
{
fprintf(f, "\\X{%x}", c);
return 0;
}
c = (((c & 0x3ff) << 10) | (ptr[1] & 0x3ff)) + 0x10000;
fprintf(f, "\\x{%x}", c);
return 1;
#endif /* PCRE2_CODE_UNIT_WIDTH == 16 */
/* For UTF-32 we get here only for a malformed code unit, which should only
occur if the sanity check has been turned off. Print it with \X instead of \x
as an indication. */
#if PCRE2_CODE_UNIT_WIDTH == 32
fprintf(f, "\\X{%x}", c);
return 0;
#endif /* PCRE2_CODE_UNIT_WIDTH == 32 */
#endif /* SUPPORT_UNICODE */
}
/*************************************************
* Print string as a list of code units *
*************************************************/
/* These take no account of UTF as they always print each individual code unit.
The string is zero-terminated for print_custring(); the length is given for
print_custring_bylen().
Arguments:
f file to write to
ptr point to the string
len length for print_custring_bylen()
Returns: nothing
*/
static void
print_custring(FILE *f, PCRE2_SPTR ptr)
{
while (*ptr != '\0')
{
uint32_t c = *ptr++;
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c);
}
}
static void
print_custring_bylen(FILE *f, PCRE2_SPTR ptr, PCRE2_UCHAR len)
{
for (; len > 0; len--)
{
uint32_t c = *ptr++;
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c);
}
}
/*************************************************
* Find Unicode property name *
*************************************************/
/* When there is no UTF/UCP support, the table of names does not exist. This
function should not be called in such configurations, because a pattern that
tries to use Unicode properties won't compile. Rather than put lots of #ifdefs
into the main code, however, we just put one into this function.
Now that the table contains both full names and their abbreviations, we do some
fiddling to try to get the full name, which is either the longer of two found
names, or a 3-character script name. */
static const char *
get_ucpname(unsigned int ptype, unsigned int pvalue)
{
#ifdef SUPPORT_UNICODE
int count = 0;
const char *yield = "??";
size_t len = 0;
unsigned int ptypex = (ptype == PT_SC)? PT_SCX : ptype;
for (int i = PRIV(utt_size) - 1; i >= 0; i--)
{
const ucp_type_table *u = PRIV(utt) + i;
if ((ptype == u->type || ptypex == u->type) && pvalue == u->value)
{
const char *s = PRIV(utt_names) + u->name_offset;
size_t sl = strlen(s);
if (sl == 3 && (u->type == PT_SC || u->type == PT_SCX))
{
yield = s;
break;
}
if (sl > len)
{
yield = s;
len = sl;
}
if (++count >= 2) break;
}
}
return yield;
#else /* No UTF support */
(void)ptype;
(void)pvalue;
return "??";
#endif /* SUPPORT_UNICODE */
}
/*************************************************
* Print Unicode property value *
*************************************************/
/* "Normal" properties can be printed from tables. The PT_CLIST property is a
pseudo-property that contains a pointer to a list of case-equivalent
characters.
Arguments:
f file to write to
code pointer in the compiled code
before text to print before
after text to print after
Returns: nothing
*/
static void
print_prop(FILE *f, PCRE2_SPTR code, const char *before, const char *after)
{
if (code[1] != PT_CLIST)
{
const char *sc = (code[1] == PT_SC)? "script:" : "";
const char *s = get_ucpname(code[1], code[2]);
fprintf(f, "%s%s %s%c%s%s", before, OP_names[*code], sc, toupper(s[0]), s+1, after);
}
else
{
const char *not = (*code == OP_PROP)? "" : "not ";
const uint32_t *p = PRIV(ucd_caseless_sets) + code[2];
fprintf (f, "%s%sclist", before, not);
while (*p < NOTACHAR) fprintf(f, " %04x", *p++);
fprintf(f, "%s", after);
}
}
/*************************************************
* Print compiled pattern *
*************************************************/
/* The print_lengths flag controls whether offsets and lengths of items are
printed. Lenths can be turned off from pcre2test so that automatic tests on
bytecode can be written that do not depend on the value of LINK_SIZE.
Arguments:
re a compiled pattern
f the file to write to
print_lengths show various lengths
Returns: nothing
*/
static void
pcre2_printint(pcre2_code *re, FILE *f, BOOL print_lengths)
{
PCRE2_SPTR codestart, nametable, code;
uint32_t nesize = re->name_entry_size;
BOOL utf = (re->overall_options & PCRE2_UTF) != 0;
nametable = (PCRE2_SPTR)((uint8_t *)re + sizeof(pcre2_real_code));
code = codestart = nametable + re->name_count * re->name_entry_size;
for(;;)
{
PCRE2_SPTR ccode;
uint32_t c;
int i;
const char *flag = " ";
unsigned int extra = 0;
if (print_lengths)
fprintf(f, "%3d ", (int)(code - codestart));
else
fprintf(f, " ");
switch(*code)
{
/* ========================================================================== */
/* These cases are never obeyed. This is a fudge that causes a compile-
time error if the vectors OP_names or OP_lengths, which are indexed
by opcode, are not the correct length. It seems to be the only way to do
such a check at compile time, as the sizeof() operator does not work in
the C preprocessor. */
case OP_TABLE_LENGTH:
case OP_TABLE_LENGTH +
((sizeof(OP_names)/sizeof(const char *) == OP_TABLE_LENGTH) &&
(sizeof(OP_lengths) == OP_TABLE_LENGTH)):
return;
/* ========================================================================== */
case OP_END:
fprintf(f, " %s\n", OP_names[*code]);
fprintf(f, "------------------------------------------------------------------\n");
return;
case OP_CHAR:
fprintf(f, " ");
do
{
code++;
code += 1 + print_char(f, code, utf);
}
while (*code == OP_CHAR);
fprintf(f, "\n");
continue;
case OP_CHARI:
fprintf(f, " /i ");
do
{
code++;
code += 1 + print_char(f, code, utf);
}
while (*code == OP_CHARI);
fprintf(f, "\n");
continue;
case OP_CBRA:
case OP_CBRAPOS:
case OP_SCBRA:
case OP_SCBRAPOS:
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE));
break;
case OP_BRA:
case OP_BRAPOS:
case OP_SBRA:
case OP_SBRAPOS:
case OP_KETRMAX:
case OP_KETRMIN:
case OP_KETRPOS:
case OP_ALT:
case OP_KET:
case OP_ASSERT:
case OP_ASSERT_NOT:
case OP_ASSERTBACK:
case OP_ASSERTBACK_NOT:
case OP_ASSERT_NA:
case OP_ASSERTBACK_NA:
case OP_ONCE:
case OP_SCRIPT_RUN:
case OP_COND:
case OP_SCOND:
case OP_REVERSE:
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s", OP_names[*code]);
break;
case OP_CLOSE:
fprintf(f, " %s %d", OP_names[*code], GET2(code, 1));
break;
case OP_CREF:
fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
break;
case OP_DNCREF:
{
PCRE2_SPTR entry = nametable + (GET2(code, 1) * nesize) + IMM2_SIZE;
fprintf(f, " %s Cond ref <", flag);
print_custring(f, entry);
fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE));
}
break;
case OP_RREF:
c = GET2(code, 1);
if (c == RREF_ANY)
fprintf(f, " Cond recurse any");
else
fprintf(f, " Cond recurse %d", c);
break;
case OP_DNRREF:
{
PCRE2_SPTR entry = nametable + (GET2(code, 1) * nesize) + IMM2_SIZE;
fprintf(f, " %s Cond recurse <", flag);
print_custring(f, entry);
fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE));
}
break;
case OP_FALSE:
fprintf(f, " Cond false");
break;
case OP_TRUE:
fprintf(f, " Cond true");
break;
case OP_STARI:
case OP_MINSTARI:
case OP_POSSTARI:
case OP_PLUSI:
case OP_MINPLUSI:
case OP_POSPLUSI:
case OP_QUERYI:
case OP_MINQUERYI:
case OP_POSQUERYI:
flag = "/i";
/* Fall through */
case OP_STAR:
case OP_MINSTAR:
case OP_POSSTAR:
case OP_PLUS:
case OP_MINPLUS:
case OP_POSPLUS:
case OP_QUERY:
case OP_MINQUERY:
case OP_POSQUERY:
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPOSSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEPOSPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
case OP_TYPEPOSQUERY:
fprintf(f, " %s ", flag);
if (*code >= OP_TYPESTAR)
{
if (code[1] == OP_PROP || code[1] == OP_NOTPROP)
{
print_prop(f, code + 1, "", " ");
extra = 2;
}
else fprintf(f, "%s", OP_names[code[1]]);
}
else extra = print_char(f, code+1, utf);
fprintf(f, "%s", OP_names[*code]);
break;
case OP_EXACTI:
case OP_UPTOI:
case OP_MINUPTOI:
case OP_POSUPTOI:
flag = "/i";
/* Fall through */
case OP_EXACT:
case OP_UPTO:
case OP_MINUPTO:
case OP_POSUPTO:
fprintf(f, " %s ", flag);
extra = print_char(f, code + 1 + IMM2_SIZE, utf);
fprintf(f, "{");
if (*code != OP_EXACT && *code != OP_EXACTI) fprintf(f, "0,");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_MINUPTO || *code == OP_MINUPTOI) fprintf(f, "?");
else if (*code == OP_POSUPTO || *code == OP_POSUPTOI) fprintf(f, "+");
break;
case OP_TYPEEXACT:
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
case OP_TYPEPOSUPTO:
if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP)
{
print_prop(f, code + IMM2_SIZE + 1, " ", " ");
extra = 2;
}
else fprintf(f, " %s", OP_names[code[1 + IMM2_SIZE]]);
fprintf(f, "{");
if (*code != OP_TYPEEXACT) fprintf(f, "0,");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+");
break;
case OP_NOTI:
flag = "/i";
/* Fall through */
case OP_NOT:
fprintf(f, " %s [^", flag);
extra = print_char(f, code + 1, utf);
fprintf(f, "]");
break;
case OP_NOTSTARI:
case OP_NOTMINSTARI:
case OP_NOTPOSSTARI:
case OP_NOTPLUSI:
case OP_NOTMINPLUSI:
case OP_NOTPOSPLUSI:
case OP_NOTQUERYI:
case OP_NOTMINQUERYI:
case OP_NOTPOSQUERYI:
flag = "/i";
/* Fall through */
case OP_NOTSTAR:
case OP_NOTMINSTAR:
case OP_NOTPOSSTAR:
case OP_NOTPLUS:
case OP_NOTMINPLUS:
case OP_NOTPOSPLUS:
case OP_NOTQUERY:
case OP_NOTMINQUERY:
case OP_NOTPOSQUERY:
fprintf(f, " %s [^", flag);
extra = print_char(f, code + 1, utf);
fprintf(f, "]%s", OP_names[*code]);
break;
case OP_NOTEXACTI:
case OP_NOTUPTOI:
case OP_NOTMINUPTOI:
case OP_NOTPOSUPTOI:
flag = "/i";
/* Fall through */
case OP_NOTEXACT:
case OP_NOTUPTO:
case OP_NOTMINUPTO:
case OP_NOTPOSUPTO:
fprintf(f, " %s [^", flag);
extra = print_char(f, code + 1 + IMM2_SIZE, utf);
fprintf(f, "]{");
if (*code != OP_NOTEXACT && *code != OP_NOTEXACTI) fprintf(f, "0,");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_NOTMINUPTO || *code == OP_NOTMINUPTOI) fprintf(f, "?");
else
if (*code == OP_NOTPOSUPTO || *code == OP_NOTPOSUPTOI) fprintf(f, "+");
break;
case OP_RECURSE:
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s", OP_names[*code]);
break;
case OP_REFI:
flag = "/i";
/* Fall through */
case OP_REF:
fprintf(f, " %s \\%d", flag, GET2(code,1));
ccode = code + OP_lengths[*code];
goto CLASS_REF_REPEAT;
case OP_DNREFI:
flag = "/i";
/* Fall through */
case OP_DNREF:
{
PCRE2_SPTR entry = nametable + (GET2(code, 1) * nesize) + IMM2_SIZE;
fprintf(f, " %s \\k<", flag);
print_custring(f, entry);
fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE));
}
ccode = code + OP_lengths[*code];
goto CLASS_REF_REPEAT;
case OP_CALLOUT:
fprintf(f, " %s %d %d %d", OP_names[*code], code[1 + 2*LINK_SIZE],
GET(code, 1), GET(code, 1 + LINK_SIZE));
break;
case OP_CALLOUT_STR:
c = code[1 + 4*LINK_SIZE];
fprintf(f, " %s %c", OP_names[*code], c);
extra = GET(code, 1 + 2*LINK_SIZE);
print_custring_bylen(f, code + 2 + 4*LINK_SIZE, extra - 3 - 4*LINK_SIZE);
for (i = 0; PRIV(callout_start_delims)[i] != 0; i++)
if (c == PRIV(callout_start_delims)[i])
{
c = PRIV(callout_end_delims)[i];
break;
}
fprintf(f, "%c %d %d %d", c, GET(code, 1 + 3*LINK_SIZE), GET(code, 1),
GET(code, 1 + LINK_SIZE));
break;
case OP_PROP:
case OP_NOTPROP:
print_prop(f, code, " ", "");
break;
/* OP_XCLASS cannot occur in 8-bit, non-UTF mode. However, there's no harm
in having this code always here, and it makes it less messy without all
those #ifdefs. */
case OP_CLASS:
case OP_NCLASS:
case OP_XCLASS:
{
unsigned int min, max;
BOOL printmap;
BOOL invertmap = FALSE;
uint8_t *map;
uint8_t inverted_map[32];
fprintf(f, " [");
if (*code == OP_XCLASS)
{
extra = GET(code, 1);
ccode = code + LINK_SIZE + 1;
printmap = (*ccode & XCL_MAP) != 0;
if ((*ccode & XCL_NOT) != 0)
{
invertmap = (*ccode & XCL_HASPROP) == 0;
fprintf(f, "^");
}
ccode++;
}
else
{
printmap = TRUE;
ccode = code + 1;
}
/* Print a bit map */
if (printmap)
{
map = (uint8_t *)ccode;
if (invertmap)
{
/* Using 255 ^ instead of ~ avoids clang sanitize warning. */
for (i = 0; i < 32; i++) inverted_map[i] = 255 ^ map[i];
map = inverted_map;
}
for (i = 0; i < 256; i++)
{
if ((map[i/8] & (1u << (i&7))) != 0)
{
int j;
for (j = i+1; j < 256; j++)
if ((map[j/8] & (1u << (j&7))) == 0) break;
if (i == '-' || i == ']') fprintf(f, "\\");
if (PRINTABLE(i)) fprintf(f, "%c", i);
else fprintf(f, "\\x%02x", i);
if (--j > i)
{
if (j != i + 1) fprintf(f, "-");
if (j == '-' || j == ']') fprintf(f, "\\");
if (PRINTABLE(j)) fprintf(f, "%c", j);
else fprintf(f, "\\x%02x", j);
}
i = j;
}
}
ccode += 32 / sizeof(PCRE2_UCHAR);
}
/* For an XCLASS there is always some additional data */
if (*code == OP_XCLASS)
{
PCRE2_UCHAR ch;
while ((ch = *ccode++) != XCL_END)
{
BOOL not = FALSE;
const char *notch = "";
switch(ch)
{
case XCL_NOTPROP:
not = TRUE;
notch = "^";
/* Fall through */
case XCL_PROP:
{
unsigned int ptype = *ccode++;
unsigned int pvalue = *ccode++;
const char *s;
switch(ptype)
{
case PT_PXGRAPH:
fprintf(f, "[:%sgraph:]", notch);
break;
case PT_PXPRINT:
fprintf(f, "[:%sprint:]", notch);
break;
case PT_PXPUNCT:
fprintf(f, "[:%spunct:]", notch);
break;
default:
s = get_ucpname(ptype, pvalue);
fprintf(f, "\\%c{%c%s}", (not? 'P':'p'), toupper(s[0]), s+1);
break;
}
}
break;
default:
ccode += 1 + print_char(f, ccode, utf);
if (ch == XCL_RANGE)
{
fprintf(f, "-");
ccode += 1 + print_char(f, ccode, utf);
}
break;
}
}
}
/* Indicate a non-UTF class which was created by negation */
fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
/* Handle repeats after a class or a back reference */
CLASS_REF_REPEAT:
switch(*ccode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRPLUS:
case OP_CRMINPLUS:
case OP_CRQUERY:
case OP_CRMINQUERY:
case OP_CRPOSSTAR:
case OP_CRPOSPLUS:
case OP_CRPOSQUERY:
fprintf(f, "%s", OP_names[*ccode]);
extra += OP_lengths[*ccode];
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
case OP_CRPOSRANGE:
min = GET2(ccode,1);
max = GET2(ccode,1 + IMM2_SIZE);
if (max == 0) fprintf(f, "{%u,}", min);
else fprintf(f, "{%u,%u}", min, max);
if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
else if (*ccode == OP_CRPOSRANGE) fprintf(f, "+");
extra += OP_lengths[*ccode];
break;
/* Do nothing if it's not a repeat; this code stops picky compilers
warning about the lack of a default code path. */
default:
break;
}
}
break;
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
fprintf(f, " %s ", OP_names[*code]);
print_custring_bylen(f, code + 2, code[1]);
extra += code[1];
break;
case OP_THEN:
fprintf(f, " %s", OP_names[*code]);
break;
case OP_CIRCM:
case OP_DOLLM:
flag = "/m";
/* Fall through */
/* Anything else is just an item with no data, but possibly a flag. */
default:
fprintf(f, " %s %s", flag, OP_names[*code]);
break;
}
code += OP_lengths[*code] + extra;
fprintf(f, "\n");
}
}
/* End of pcre2_printint.c */

344
third_party/pcre/pcre2_script_run.c vendored Normal file
View file

@ -0,0 +1,344 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains the function for checking a script run. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Check script run *
*************************************************/
/* A script run is conceptually a sequence of characters all in the same
Unicode script. However, it isn't quite that simple. There are special rules
for scripts that are commonly used together, and also special rules for digits.
This function implements the appropriate checks, which is possible only when
PCRE2 is compiled with Unicode support. The function returns TRUE if there is
no Unicode support; however, it should never be called in that circumstance
because an error is given by pcre2_compile() if a script run is called for in a
version of PCRE2 compiled without Unicode support.
Arguments:
pgr point to the first character
endptr point after the last character
utf TRUE if in UTF mode
Returns: TRUE if this is a valid script run
*/
/* These are states in the checking process. */
enum { SCRIPT_UNSET, /* Requirement as yet unknown */
SCRIPT_MAP, /* Bitmap contains acceptable scripts */
SCRIPT_HANPENDING, /* Have had only Han characters */
SCRIPT_HANHIRAKATA, /* Expect Han or Hirikata */
SCRIPT_HANBOPOMOFO, /* Expect Han or Bopomofo */
SCRIPT_HANHANGUL /* Expect Han or Hangul */
};
#define UCD_MAPSIZE (ucp_Unknown/32 + 1)
#define FULL_MAPSIZE (ucp_Script_Count/32 + 1)
BOOL
PRIV(script_run)(PCRE2_SPTR ptr, PCRE2_SPTR endptr, BOOL utf)
{
#ifdef SUPPORT_UNICODE
uint32_t require_state = SCRIPT_UNSET;
uint32_t require_map[FULL_MAPSIZE];
uint32_t map[FULL_MAPSIZE];
uint32_t require_digitset = 0;
uint32_t c;
#if PCRE2_CODE_UNIT_WIDTH == 32
(void)utf; /* Avoid compiler warning */
#endif
/* Any string containing fewer than 2 characters is a valid script run. */
if (ptr >= endptr) return TRUE;
GETCHARINCTEST(c, ptr);
if (ptr >= endptr) return TRUE;
/* Initialize the require map. This is a full-size bitmap that has a bit for
every script, as opposed to the maps in ucd_script_sets, which only have bits
for scripts less than ucp_Unknown - those that appear in script extension
lists. */
for (int i = 0; i < FULL_MAPSIZE; i++) require_map[i] = 0;
/* Scan strings of two or more characters, checking the Unicode characteristics
of each code point. There is special code for scripts that can be combined with
characters from the Han Chinese script. This may be used in conjunction with
four other scripts in these combinations:
. Han with Hiragana and Katakana is allowed (for Japanese).
. Han with Bopomofo is allowed (for Taiwanese Mandarin).
. Han with Hangul is allowed (for Korean).
If the first significant character's script is one of the four, the required
script type is immediately known. However, if the first significant
character's script is Han, we have to keep checking for a non-Han character.
Hence the SCRIPT_HANPENDING state. */
for (;;)
{
const ucd_record *ucd = GET_UCD(c);
uint32_t script = ucd->script;
/* If the script is Unknown, the string is not a valid script run. Such
characters can only form script runs of length one (see test above). */
if (script == ucp_Unknown) return FALSE;
/* A character without any script extensions whose script is Inherited or
Common is always accepted with any script. If there are extensions, the
following processing happens for all scripts. */
if (UCD_SCRIPTX_PROP(ucd) != 0 || (script != ucp_Inherited && script != ucp_Common))
{
BOOL OK;
/* Set up a full-sized map for this character that can include bits for all
scripts. Copy the scriptx map for this character (which covers those
scripts that appear in script extension lists), set the remaining values to
zero, and then, except for Common or Inherited, add this script's bit to
the map. */
memcpy(map, PRIV(ucd_script_sets) + UCD_SCRIPTX_PROP(ucd), UCD_MAPSIZE * sizeof(uint32_t));
memset(map + UCD_MAPSIZE, 0, (FULL_MAPSIZE - UCD_MAPSIZE) * sizeof(uint32_t));
if (script != ucp_Common && script != ucp_Inherited) MAPSET(map, script);
/* Handle the different checking states */
switch(require_state)
{
/* First significant character - it might follow Common or Inherited
characters that do not have any script extensions. */
case SCRIPT_UNSET:
switch(script)
{
case ucp_Han:
require_state = SCRIPT_HANPENDING;
break;
case ucp_Hiragana:
case ucp_Katakana:
require_state = SCRIPT_HANHIRAKATA;
break;
case ucp_Bopomofo:
require_state = SCRIPT_HANBOPOMOFO;
break;
case ucp_Hangul:
require_state = SCRIPT_HANHANGUL;
break;
default:
memcpy(require_map, map, FULL_MAPSIZE * sizeof(uint32_t));
require_state = SCRIPT_MAP;
break;
}
break;
/* The first significant character was Han. An inspection of the Unicode
11.0.0 files shows that there are the following types of Script Extension
list that involve the Han, Bopomofo, Hiragana, Katakana, and Hangul
scripts:
. Bopomofo + Han
. Han + Hiragana + Katakana
. Hiragana + Katakana
. Bopopmofo + Hangul + Han + Hiragana + Katakana
The following code tries to make sense of this. */
#define FOUND_BOPOMOFO 1
#define FOUND_HIRAGANA 2
#define FOUND_KATAKANA 4
#define FOUND_HANGUL 8
case SCRIPT_HANPENDING:
if (script != ucp_Han) /* Another Han does nothing */
{
uint32_t chspecial = 0;
if (MAPBIT(map, ucp_Bopomofo) != 0) chspecial |= FOUND_BOPOMOFO;
if (MAPBIT(map, ucp_Hiragana) != 0) chspecial |= FOUND_HIRAGANA;
if (MAPBIT(map, ucp_Katakana) != 0) chspecial |= FOUND_KATAKANA;
if (MAPBIT(map, ucp_Hangul) != 0) chspecial |= FOUND_HANGUL;
if (chspecial == 0) return FALSE; /* Not allowed with Han */
if (chspecial == FOUND_BOPOMOFO)
require_state = SCRIPT_HANBOPOMOFO;
else if (chspecial == (FOUND_HIRAGANA|FOUND_KATAKANA))
require_state = SCRIPT_HANHIRAKATA;
/* Otherwise this character must be allowed with all of them, so remain
in the pending state. */
}
break;
/* Previously encountered one of the "with Han" scripts. Check that
this character is appropriate. */
case SCRIPT_HANHIRAKATA:
if (MAPBIT(map, ucp_Han) + MAPBIT(map, ucp_Hiragana) +
MAPBIT(map, ucp_Katakana) == 0) return FALSE;
break;
case SCRIPT_HANBOPOMOFO:
if (MAPBIT(map, ucp_Han) + MAPBIT(map, ucp_Bopomofo) == 0) return FALSE;
break;
case SCRIPT_HANHANGUL:
if (MAPBIT(map, ucp_Han) + MAPBIT(map, ucp_Hangul) == 0) return FALSE;
break;
/* Previously encountered one or more characters that are allowed with a
list of scripts. */
case SCRIPT_MAP:
OK = FALSE;
for (int i = 0; i < FULL_MAPSIZE; i++)
{
if ((require_map[i] & map[i]) != 0)
{
OK = TRUE;
break;
}
}
if (!OK) return FALSE;
/* The rest of the string must be in this script, but we have to
allow for the Han complications. */
switch(script)
{
case ucp_Han:
require_state = SCRIPT_HANPENDING;
break;
case ucp_Hiragana:
case ucp_Katakana:
require_state = SCRIPT_HANHIRAKATA;
break;
case ucp_Bopomofo:
require_state = SCRIPT_HANBOPOMOFO;
break;
case ucp_Hangul:
require_state = SCRIPT_HANHANGUL;
break;
/* Compute the intersection of the required list of scripts and the
allowed scripts for this character. */
default:
for (int i = 0; i < FULL_MAPSIZE; i++) require_map[i] &= map[i];
break;
}
break;
}
} /* End checking character's script and extensions. */
/* The character is in an acceptable script. We must now ensure that all
decimal digits in the string come from the same set. Some scripts (e.g.
Common, Arabic) have more than one set of decimal digits. This code does
not allow mixing sets, even within the same script. The vector called
PRIV(ucd_digit_sets)[] contains, in its first element, the number of
following elements, and then, in ascending order, the code points of the
'9' characters in every set of 10 digits. Each set is identified by the
offset in the vector of its '9' character. An initial check of the first
value picks up ASCII digits quickly. Otherwise, a binary chop is used. */
if (ucd->chartype == ucp_Nd)
{
uint32_t digitset;
if (c <= PRIV(ucd_digit_sets)[1]) digitset = 1; else
{
int mid;
int bot = 1;
int top = PRIV(ucd_digit_sets)[0];
for (;;)
{
if (top <= bot + 1) /* <= rather than == is paranoia */
{
digitset = top;
break;
}
mid = (top + bot) / 2;
if (c <= PRIV(ucd_digit_sets)[mid]) top = mid; else bot = mid;
}
}
/* A required value of 0 means "unset". */
if (require_digitset == 0) require_digitset = digitset;
else if (digitset != require_digitset) return FALSE;
} /* End digit handling */
/* If we haven't yet got to the end, pick up the next character. */
if (ptr >= endptr) return TRUE;
GETCHARINCTEST(c, ptr);
} /* End checking loop */
#else /* NOT SUPPORT_UNICODE */
(void)ptr;
(void)endptr;
(void)utf;
return TRUE;
#endif /* SUPPORT_UNICODE */
}
/* End of pcre2_script_run.c */

286
third_party/pcre/pcre2_serialize.c vendored Normal file
View file

@ -0,0 +1,286 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains functions for serializing and deserializing
a sequence of compiled codes. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* Magic number to provide a small check against being handed junk. */
#define SERIALIZED_DATA_MAGIC 0x50523253u
/* Deserialization is limited to the current PCRE version and
character width. */
#define SERIALIZED_DATA_VERSION \
((PCRE2_MAJOR) | ((PCRE2_MINOR) << 16))
#define SERIALIZED_DATA_CONFIG \
(sizeof(PCRE2_UCHAR) | ((sizeof(void*)) << 8) | ((sizeof(PCRE2_SIZE)) << 16))
/*************************************************
* Serialize compiled patterns *
*************************************************/
PCRE2_EXP_DEFN int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_encode(const pcre2_code **codes, int32_t number_of_codes,
uint8_t **serialized_bytes, PCRE2_SIZE *serialized_size,
pcre2_general_context *gcontext)
{
uint8_t *bytes;
uint8_t *dst_bytes;
int32_t i;
PCRE2_SIZE total_size;
const pcre2_real_code *re;
const uint8_t *tables;
pcre2_serialized_data *data;
const pcre2_memctl *memctl = (gcontext != NULL) ?
&gcontext->memctl : &PRIV(default_compile_context).memctl;
if (codes == NULL || serialized_bytes == NULL || serialized_size == NULL)
return PCRE2_ERROR_NULL;
if (number_of_codes <= 0) return PCRE2_ERROR_BADDATA;
/* Compute total size. */
total_size = sizeof(pcre2_serialized_data) + TABLES_LENGTH;
tables = NULL;
for (i = 0; i < number_of_codes; i++)
{
if (codes[i] == NULL) return PCRE2_ERROR_NULL;
re = (const pcre2_real_code *)(codes[i]);
if (re->magic_number != MAGIC_NUMBER) return PCRE2_ERROR_BADMAGIC;
if (tables == NULL)
tables = re->tables;
else if (tables != re->tables)
return PCRE2_ERROR_MIXEDTABLES;
total_size += re->blocksize;
}
/* Initialize the byte stream. */
bytes = memctl->malloc(total_size + sizeof(pcre2_memctl), memctl->memory_data);
if (bytes == NULL) return PCRE2_ERROR_NOMEMORY;
/* The controller is stored as a hidden parameter. */
memcpy(bytes, memctl, sizeof(pcre2_memctl));
bytes += sizeof(pcre2_memctl);
data = (pcre2_serialized_data *)bytes;
data->magic = SERIALIZED_DATA_MAGIC;
data->version = SERIALIZED_DATA_VERSION;
data->config = SERIALIZED_DATA_CONFIG;
data->number_of_codes = number_of_codes;
/* Copy all compiled code data. */
dst_bytes = bytes + sizeof(pcre2_serialized_data);
memcpy(dst_bytes, tables, TABLES_LENGTH);
dst_bytes += TABLES_LENGTH;
for (i = 0; i < number_of_codes; i++)
{
re = (const pcre2_real_code *)(codes[i]);
(void)memcpy(dst_bytes, (char *)re, re->blocksize);
/* Certain fields in the compiled code block are re-set during
deserialization. In order to ensure that the serialized data stream is always
the same for the same pattern, set them to zero here. We can't assume the
copy of the pattern is correctly aligned for accessing the fields as part of
a structure. Note the use of sizeof(void *) in the second of these, to
specify the size of a pointer. If sizeof(uint8_t *) is used (tables is a
pointer to uint8_t), gcc gives a warning because the first argument is also a
pointer to uint8_t. Casting the first argument to (void *) can stop this, but
it didn't stop Coverity giving the same complaint. */
(void)memset(dst_bytes + offsetof(pcre2_real_code, memctl), 0,
sizeof(pcre2_memctl));
(void)memset(dst_bytes + offsetof(pcre2_real_code, tables), 0,
sizeof(void *));
(void)memset(dst_bytes + offsetof(pcre2_real_code, executable_jit), 0,
sizeof(void *));
dst_bytes += re->blocksize;
}
*serialized_bytes = bytes;
*serialized_size = total_size;
return number_of_codes;
}
/*************************************************
* Deserialize compiled patterns *
*************************************************/
PCRE2_EXP_DEFN int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_decode(pcre2_code **codes, int32_t number_of_codes,
const uint8_t *bytes, pcre2_general_context *gcontext)
{
const pcre2_serialized_data *data = (const pcre2_serialized_data *)bytes;
const pcre2_memctl *memctl = (gcontext != NULL) ?
&gcontext->memctl : &PRIV(default_compile_context).memctl;
const uint8_t *src_bytes;
pcre2_real_code *dst_re;
uint8_t *tables;
int32_t i, j;
/* Sanity checks. */
if (data == NULL || codes == NULL) return PCRE2_ERROR_NULL;
if (number_of_codes <= 0) return PCRE2_ERROR_BADDATA;
if (data->number_of_codes <= 0) return PCRE2_ERROR_BADSERIALIZEDDATA;
if (data->magic != SERIALIZED_DATA_MAGIC) return PCRE2_ERROR_BADMAGIC;
if (data->version != SERIALIZED_DATA_VERSION) return PCRE2_ERROR_BADMODE;
if (data->config != SERIALIZED_DATA_CONFIG) return PCRE2_ERROR_BADMODE;
if (number_of_codes > data->number_of_codes)
number_of_codes = data->number_of_codes;
src_bytes = bytes + sizeof(pcre2_serialized_data);
/* Decode tables. The reference count for the tables is stored immediately
following them. */
tables = memctl->malloc(TABLES_LENGTH + sizeof(PCRE2_SIZE), memctl->memory_data);
if (tables == NULL) return PCRE2_ERROR_NOMEMORY;
memcpy(tables, src_bytes, TABLES_LENGTH);
*(PCRE2_SIZE *)(tables + TABLES_LENGTH) = number_of_codes;
src_bytes += TABLES_LENGTH;
/* Decode the byte stream. We must not try to read the size from the compiled
code block in the stream, because it might be unaligned, which causes errors on
hardware such as Sparc-64 that doesn't like unaligned memory accesses. The type
of the blocksize field is given its own name to ensure that it is the same here
as in the block. */
for (i = 0; i < number_of_codes; i++)
{
CODE_BLOCKSIZE_TYPE blocksize;
memcpy(&blocksize, src_bytes + offsetof(pcre2_real_code, blocksize),
sizeof(CODE_BLOCKSIZE_TYPE));
if (blocksize <= sizeof(pcre2_real_code))
return PCRE2_ERROR_BADSERIALIZEDDATA;
/* The allocator provided by gcontext replaces the original one. */
dst_re = (pcre2_real_code *)PRIV(memctl_malloc)(blocksize,
(pcre2_memctl *)gcontext);
if (dst_re == NULL)
{
memctl->free(tables, memctl->memory_data);
for (j = 0; j < i; j++)
{
memctl->free(codes[j], memctl->memory_data);
codes[j] = NULL;
}
return PCRE2_ERROR_NOMEMORY;
}
/* The new allocator must be preserved. */
memcpy(((uint8_t *)dst_re) + sizeof(pcre2_memctl),
src_bytes + sizeof(pcre2_memctl), blocksize - sizeof(pcre2_memctl));
if (dst_re->magic_number != MAGIC_NUMBER ||
dst_re->name_entry_size > MAX_NAME_SIZE + IMM2_SIZE + 1 ||
dst_re->name_count > MAX_NAME_COUNT)
{
memctl->free(dst_re, memctl->memory_data);
return PCRE2_ERROR_BADSERIALIZEDDATA;
}
/* At the moment only one table is supported. */
dst_re->tables = tables;
dst_re->executable_jit = NULL;
dst_re->flags |= PCRE2_DEREF_TABLES;
codes[i] = dst_re;
src_bytes += blocksize;
}
return number_of_codes;
}
/*************************************************
* Get the number of serialized patterns *
*************************************************/
PCRE2_EXP_DEFN int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_get_number_of_codes(const uint8_t *bytes)
{
const pcre2_serialized_data *data = (const pcre2_serialized_data *)bytes;
if (data == NULL) return PCRE2_ERROR_NULL;
if (data->magic != SERIALIZED_DATA_MAGIC) return PCRE2_ERROR_BADMAGIC;
if (data->version != SERIALIZED_DATA_VERSION) return PCRE2_ERROR_BADMODE;
if (data->config != SERIALIZED_DATA_CONFIG) return PCRE2_ERROR_BADMODE;
return data->number_of_codes;
}
/*************************************************
* Free the allocated stream *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_serialize_free(uint8_t *bytes)
{
if (bytes != NULL)
{
pcre2_memctl *memctl = (pcre2_memctl *)(bytes - sizeof(pcre2_memctl));
memctl->free(memctl, memctl->memory_data);
}
}
/* End of pcre2_serialize.c */

237
third_party/pcre/pcre2_string_utils.c vendored Normal file
View file

@ -0,0 +1,237 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2018-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains internal functions for comparing and finding the length
of strings. These are used instead of strcmp() etc because the standard
functions work only on 8-bit data. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Emulated memmove() for systems without it *
*************************************************/
/* This function can make use of bcopy() if it is available. Otherwise do it by
steam, as there some non-Unix environments that lack both memmove() and
bcopy(). */
#if !defined(VPCOMPAT) && !defined(HAVE_MEMMOVE)
void *
PRIV(memmove)(void *d, const void *s, size_t n)
{
#ifdef HAVE_BCOPY
bcopy(s, d, n);
return d;
#else
size_t i;
unsigned char *dest = (unsigned char *)d;
const unsigned char *src = (const unsigned char *)s;
if (dest > src)
{
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return (void *)dest;
}
else
{
for (i = 0; i < n; ++i) *dest++ = *src++;
return (void *)(dest - n);
}
#endif /* not HAVE_BCOPY */
}
#endif /* not VPCOMPAT && not HAVE_MEMMOVE */
/*************************************************
* Compare two zero-terminated PCRE2 strings *
*************************************************/
/*
Arguments:
str1 first string
str2 second string
Returns: 0, 1, or -1
*/
int
PRIV(strcmp)(PCRE2_SPTR str1, PCRE2_SPTR str2)
{
PCRE2_UCHAR c1, c2;
while (*str1 != '\0' || *str2 != '\0')
{
c1 = *str1++;
c2 = *str2++;
if (c1 != c2) return ((c1 > c2) << 1) - 1;
}
return 0;
}
/*************************************************
* Compare zero-terminated PCRE2 & 8-bit strings *
*************************************************/
/* As the 8-bit string is almost always a literal, its type is specified as
const char *.
Arguments:
str1 first string
str2 second string
Returns: 0, 1, or -1
*/
int
PRIV(strcmp_c8)(PCRE2_SPTR str1, const char *str2)
{
PCRE2_UCHAR c1, c2;
while (*str1 != '\0' || *str2 != '\0')
{
c1 = *str1++;
c2 = *str2++;
if (c1 != c2) return ((c1 > c2) << 1) - 1;
}
return 0;
}
/*************************************************
* Compare two PCRE2 strings, given a length *
*************************************************/
/*
Arguments:
str1 first string
str2 second string
len the length
Returns: 0, 1, or -1
*/
int
PRIV(strncmp)(PCRE2_SPTR str1, PCRE2_SPTR str2, size_t len)
{
PCRE2_UCHAR c1, c2;
for (; len > 0; len--)
{
c1 = *str1++;
c2 = *str2++;
if (c1 != c2) return ((c1 > c2) << 1) - 1;
}
return 0;
}
/*************************************************
* Compare PCRE2 string to 8-bit string by length *
*************************************************/
/* As the 8-bit string is almost always a literal, its type is specified as
const char *.
Arguments:
str1 first string
str2 second string
len the length
Returns: 0, 1, or -1
*/
int
PRIV(strncmp_c8)(PCRE2_SPTR str1, const char *str2, size_t len)
{
PCRE2_UCHAR c1, c2;
for (; len > 0; len--)
{
c1 = *str1++;
c2 = *str2++;
if (c1 != c2) return ((c1 > c2) << 1) - 1;
}
return 0;
}
/*************************************************
* Find the length of a PCRE2 string *
*************************************************/
/*
Argument: the string
Returns: the length
*/
PCRE2_SIZE
PRIV(strlen)(PCRE2_SPTR str)
{
PCRE2_SIZE c = 0;
while (*str++ != 0) c++;
return c;
}
/*************************************************
* Copy 8-bit 0-terminated string to PCRE2 string *
*************************************************/
/* Arguments:
str1 buffer to receive the string
str2 8-bit string to be copied
Returns: the number of code units used (excluding trailing zero)
*/
PCRE2_SIZE
PRIV(strcpy_c8)(PCRE2_UCHAR *str1, const char *str2)
{
PCRE2_UCHAR *t = str1;
while (*str2 != 0) *t++ = *str2++;
*t = 0;
return t - str1;
}
/* End of pcre2_string_utils.c */

1825
third_party/pcre/pcre2_study.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

1009
third_party/pcre/pcre2_substitute.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

547
third_party/pcre/pcre2_substring.c vendored Normal file
View file

@ -0,0 +1,547 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Copy named captured string to given buffer *
*************************************************/
/* This function copies a single captured substring into a given buffer,
identifying it by name. If the regex permits duplicate names, the first
substring that is set is chosen.
Arguments:
match_data points to the match data
stringname the name of the required substring
buffer where to put the substring
sizeptr the size of the buffer, updated to the size of the substring
Returns: if successful: zero
if not successful, a negative error code:
(1) an error from nametable_scan()
(2) an error from copy_bynumber()
(3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector
(4) PCRE2_ERROR_UNSET: all named groups in ovector are unset
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_copy_byname(pcre2_match_data *match_data, PCRE2_SPTR stringname,
PCRE2_UCHAR *buffer, PCRE2_SIZE *sizeptr)
{
PCRE2_SPTR first, last, entry;
int failrc, entrysize;
if (match_data->matchedby == PCRE2_MATCHEDBY_DFA_INTERPRETER)
return PCRE2_ERROR_DFA_UFUNC;
entrysize = pcre2_substring_nametable_scan(match_data->code, stringname,
&first, &last);
if (entrysize < 0) return entrysize;
failrc = PCRE2_ERROR_UNAVAILABLE;
for (entry = first; entry <= last; entry += entrysize)
{
uint32_t n = GET2(entry, 0);
if (n < match_data->oveccount)
{
if (match_data->ovector[n*2] != PCRE2_UNSET)
return pcre2_substring_copy_bynumber(match_data, n, buffer, sizeptr);
failrc = PCRE2_ERROR_UNSET;
}
}
return failrc;
}
/*************************************************
* Copy numbered captured string to given buffer *
*************************************************/
/* This function copies a single captured substring into a given buffer,
identifying it by number.
Arguments:
match_data points to the match data
stringnumber the number of the required substring
buffer where to put the substring
sizeptr the size of the buffer, updated to the size of the substring
Returns: if successful: 0
if not successful, a negative error code:
PCRE2_ERROR_NOMEMORY: buffer too small
PCRE2_ERROR_NOSUBSTRING: no such substring
PCRE2_ERROR_UNAVAILABLE: ovector too small
PCRE2_ERROR_UNSET: substring is not set
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_copy_bynumber(pcre2_match_data *match_data,
uint32_t stringnumber, PCRE2_UCHAR *buffer, PCRE2_SIZE *sizeptr)
{
int rc;
PCRE2_SIZE size;
rc = pcre2_substring_length_bynumber(match_data, stringnumber, &size);
if (rc < 0) return rc;
if (size + 1 > *sizeptr) return PCRE2_ERROR_NOMEMORY;
memcpy(buffer, match_data->subject + match_data->ovector[stringnumber*2],
CU2BYTES(size));
buffer[size] = 0;
*sizeptr = size;
return 0;
}
/*************************************************
* Extract named captured string *
*************************************************/
/* This function copies a single captured substring, identified by name, into
new memory. If the regex permits duplicate names, the first substring that is
set is chosen.
Arguments:
match_data pointer to match_data
stringname the name of the required substring
stringptr where to put the pointer to the new memory
sizeptr where to put the length of the substring
Returns: if successful: zero
if not successful, a negative value:
(1) an error from nametable_scan()
(2) an error from get_bynumber()
(3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector
(4) PCRE2_ERROR_UNSET: all named groups in ovector are unset
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_get_byname(pcre2_match_data *match_data,
PCRE2_SPTR stringname, PCRE2_UCHAR **stringptr, PCRE2_SIZE *sizeptr)
{
PCRE2_SPTR first, last, entry;
int failrc, entrysize;
if (match_data->matchedby == PCRE2_MATCHEDBY_DFA_INTERPRETER)
return PCRE2_ERROR_DFA_UFUNC;
entrysize = pcre2_substring_nametable_scan(match_data->code, stringname,
&first, &last);
if (entrysize < 0) return entrysize;
failrc = PCRE2_ERROR_UNAVAILABLE;
for (entry = first; entry <= last; entry += entrysize)
{
uint32_t n = GET2(entry, 0);
if (n < match_data->oveccount)
{
if (match_data->ovector[n*2] != PCRE2_UNSET)
return pcre2_substring_get_bynumber(match_data, n, stringptr, sizeptr);
failrc = PCRE2_ERROR_UNSET;
}
}
return failrc;
}
/*************************************************
* Extract captured string to new memory *
*************************************************/
/* This function copies a single captured substring into a piece of new
memory.
Arguments:
match_data points to match data
stringnumber the number of the required substring
stringptr where to put a pointer to the new memory
sizeptr where to put the size of the substring
Returns: if successful: 0
if not successful, a negative error code:
PCRE2_ERROR_NOMEMORY: failed to get memory
PCRE2_ERROR_NOSUBSTRING: no such substring
PCRE2_ERROR_UNAVAILABLE: ovector too small
PCRE2_ERROR_UNSET: substring is not set
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_get_bynumber(pcre2_match_data *match_data,
uint32_t stringnumber, PCRE2_UCHAR **stringptr, PCRE2_SIZE *sizeptr)
{
int rc;
PCRE2_SIZE size;
PCRE2_UCHAR *yield;
rc = pcre2_substring_length_bynumber(match_data, stringnumber, &size);
if (rc < 0) return rc;
yield = PRIV(memctl_malloc)(sizeof(pcre2_memctl) +
(size + 1)*PCRE2_CODE_UNIT_WIDTH, (pcre2_memctl *)match_data);
if (yield == NULL) return PCRE2_ERROR_NOMEMORY;
yield = (PCRE2_UCHAR *)(((char *)yield) + sizeof(pcre2_memctl));
memcpy(yield, match_data->subject + match_data->ovector[stringnumber*2],
CU2BYTES(size));
yield[size] = 0;
*stringptr = yield;
*sizeptr = size;
return 0;
}
/*************************************************
* Free memory obtained by get_substring *
*************************************************/
/*
Argument: the result of a previous pcre2_substring_get_byxxx()
Returns: nothing
*/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_substring_free(PCRE2_UCHAR *string)
{
if (string != NULL)
{
pcre2_memctl *memctl = (pcre2_memctl *)((char *)string - sizeof(pcre2_memctl));
memctl->free(memctl, memctl->memory_data);
}
}
/*************************************************
* Get length of a named substring *
*************************************************/
/* This function returns the length of a named captured substring. If the regex
permits duplicate names, the first substring that is set is chosen.
Arguments:
match_data pointer to match data
stringname the name of the required substring
sizeptr where to put the length
Returns: 0 if successful, else a negative error number
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_length_byname(pcre2_match_data *match_data,
PCRE2_SPTR stringname, PCRE2_SIZE *sizeptr)
{
PCRE2_SPTR first, last, entry;
int failrc, entrysize;
if (match_data->matchedby == PCRE2_MATCHEDBY_DFA_INTERPRETER)
return PCRE2_ERROR_DFA_UFUNC;
entrysize = pcre2_substring_nametable_scan(match_data->code, stringname,
&first, &last);
if (entrysize < 0) return entrysize;
failrc = PCRE2_ERROR_UNAVAILABLE;
for (entry = first; entry <= last; entry += entrysize)
{
uint32_t n = GET2(entry, 0);
if (n < match_data->oveccount)
{
if (match_data->ovector[n*2] != PCRE2_UNSET)
return pcre2_substring_length_bynumber(match_data, n, sizeptr);
failrc = PCRE2_ERROR_UNSET;
}
}
return failrc;
}
/*************************************************
* Get length of a numbered substring *
*************************************************/
/* This function returns the length of a captured substring. If the start is
beyond the end (which can happen when \K is used in an assertion), it sets the
length to zero.
Arguments:
match_data pointer to match data
stringnumber the number of the required substring
sizeptr where to put the length, if not NULL
Returns: if successful: 0
if not successful, a negative error code:
PCRE2_ERROR_NOSUBSTRING: no such substring
PCRE2_ERROR_UNAVAILABLE: ovector is too small
PCRE2_ERROR_UNSET: substring is not set
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_length_bynumber(pcre2_match_data *match_data,
uint32_t stringnumber, PCRE2_SIZE *sizeptr)
{
PCRE2_SIZE left, right;
int count = match_data->rc;
if (count == PCRE2_ERROR_PARTIAL)
{
if (stringnumber > 0) return PCRE2_ERROR_PARTIAL;
count = 0;
}
else if (count < 0) return count; /* Match failed */
if (match_data->matchedby != PCRE2_MATCHEDBY_DFA_INTERPRETER)
{
if (stringnumber > match_data->code->top_bracket)
return PCRE2_ERROR_NOSUBSTRING;
if (stringnumber >= match_data->oveccount)
return PCRE2_ERROR_UNAVAILABLE;
if (match_data->ovector[stringnumber*2] == PCRE2_UNSET)
return PCRE2_ERROR_UNSET;
}
else /* Matched using pcre2_dfa_match() */
{
if (stringnumber >= match_data->oveccount) return PCRE2_ERROR_UNAVAILABLE;
if (count != 0 && stringnumber >= (uint32_t)count) return PCRE2_ERROR_UNSET;
}
left = match_data->ovector[stringnumber*2];
right = match_data->ovector[stringnumber*2+1];
if (sizeptr != NULL) *sizeptr = (left > right)? 0 : right - left;
return 0;
}
/*************************************************
* Extract all captured strings to new memory *
*************************************************/
/* This function gets one chunk of memory and builds a list of pointers and all
the captured substrings in it. A NULL pointer is put on the end of the list.
The substrings are zero-terminated, but also, if the final argument is
non-NULL, a list of lengths is also returned. This allows binary data to be
handled.
Arguments:
match_data points to the match data
listptr set to point to the list of pointers
lengthsptr set to point to the list of lengths (may be NULL)
Returns: if successful: 0
if not successful, a negative error code:
PCRE2_ERROR_NOMEMORY: failed to get memory,
or a match failure code
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_list_get(pcre2_match_data *match_data, PCRE2_UCHAR ***listptr,
PCRE2_SIZE **lengthsptr)
{
int i, count, count2;
PCRE2_SIZE size;
PCRE2_SIZE *lensp;
pcre2_memctl *memp;
PCRE2_UCHAR **listp;
PCRE2_UCHAR *sp;
PCRE2_SIZE *ovector;
if ((count = match_data->rc) < 0) return count; /* Match failed */
if (count == 0) count = match_data->oveccount; /* Ovector too small */
count2 = 2*count;
ovector = match_data->ovector;
size = sizeof(pcre2_memctl) + sizeof(PCRE2_UCHAR *); /* For final NULL */
if (lengthsptr != NULL) size += sizeof(PCRE2_SIZE) * count; /* For lengths */
for (i = 0; i < count2; i += 2)
{
size += sizeof(PCRE2_UCHAR *) + CU2BYTES(1);
if (ovector[i+1] > ovector[i]) size += CU2BYTES(ovector[i+1] - ovector[i]);
}
memp = PRIV(memctl_malloc)(size, (pcre2_memctl *)match_data);
if (memp == NULL) return PCRE2_ERROR_NOMEMORY;
*listptr = listp = (PCRE2_UCHAR **)((char *)memp + sizeof(pcre2_memctl));
lensp = (PCRE2_SIZE *)((char *)listp + sizeof(PCRE2_UCHAR *) * (count + 1));
if (lengthsptr == NULL)
{
sp = (PCRE2_UCHAR *)lensp;
lensp = NULL;
}
else
{
*lengthsptr = lensp;
sp = (PCRE2_UCHAR *)((char *)lensp + sizeof(PCRE2_SIZE) * count);
}
for (i = 0; i < count2; i += 2)
{
size = (ovector[i+1] > ovector[i])? (ovector[i+1] - ovector[i]) : 0;
/* Size == 0 includes the case when the capture is unset. Avoid adding
PCRE2_UNSET to match_data->subject because it overflows, even though with
zero size calling memcpy() is harmless. */
if (size != 0) memcpy(sp, match_data->subject + ovector[i], CU2BYTES(size));
*listp++ = sp;
if (lensp != NULL) *lensp++ = size;
sp += size;
*sp++ = 0;
}
*listp = NULL;
return 0;
}
/*************************************************
* Free memory obtained by substring_list_get *
*************************************************/
/*
Argument: the result of a previous pcre2_substring_list_get()
Returns: nothing
*/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_substring_list_free(PCRE2_SPTR *list)
{
if (list != NULL)
{
pcre2_memctl *memctl = (pcre2_memctl *)((char *)list - sizeof(pcre2_memctl));
memctl->free(memctl, memctl->memory_data);
}
}
/*************************************************
* Find (multiple) entries for named string *
*************************************************/
/* This function scans the nametable for a given name, using binary chop. It
returns either two pointers to the entries in the table, or, if no pointers are
given, the number of a unique group with the given name. If duplicate names are
permitted, and the name is not unique, an error is generated.
Arguments:
code the compiled regex
stringname the name whose entries required
firstptr where to put the pointer to the first entry
lastptr where to put the pointer to the last entry
Returns: PCRE2_ERROR_NOSUBSTRING if the name is not found
otherwise, if firstptr and lastptr are NULL:
a group number for a unique substring
else PCRE2_ERROR_NOUNIQUESUBSTRING
otherwise:
the length of each entry, having set firstptr and lastptr
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR stringname,
PCRE2_SPTR *firstptr, PCRE2_SPTR *lastptr)
{
uint16_t bot = 0;
uint16_t top = code->name_count;
uint16_t entrysize = code->name_entry_size;
PCRE2_SPTR nametable = (PCRE2_SPTR)((char *)code + sizeof(pcre2_real_code));
while (top > bot)
{
uint16_t mid = (top + bot) / 2;
PCRE2_SPTR entry = nametable + entrysize*mid;
int c = PRIV(strcmp)(stringname, entry + IMM2_SIZE);
if (c == 0)
{
PCRE2_SPTR first;
PCRE2_SPTR last;
PCRE2_SPTR lastentry;
lastentry = nametable + entrysize * (code->name_count - 1);
first = last = entry;
while (first > nametable)
{
if (PRIV(strcmp)(stringname, (first - entrysize + IMM2_SIZE)) != 0) break;
first -= entrysize;
}
while (last < lastentry)
{
if (PRIV(strcmp)(stringname, (last + entrysize + IMM2_SIZE)) != 0) break;
last += entrysize;
}
if (firstptr == NULL) return (first == last)?
(int)GET2(entry, 0) : PCRE2_ERROR_NOUNIQUESUBSTRING;
*firstptr = first;
*lastptr = last;
return entrysize;
}
if (c > 0) bot = mid + 1; else top = mid;
}
return PCRE2_ERROR_NOSUBSTRING;
}
/*************************************************
* Find number for named string *
*************************************************/
/* This function is a convenience wrapper for pcre2_substring_nametable_scan()
when it is known that names are unique. If there are duplicate names, it is not
defined which number is returned.
Arguments:
code the compiled regex
stringname the name whose number is required
Returns: the number of the named parenthesis, or a negative number
PCRE2_ERROR_NOSUBSTRING if not found
PCRE2_ERROR_NOUNIQUESUBSTRING if not unique
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substring_number_from_name(const pcre2_code *code,
PCRE2_SPTR stringname)
{
return pcre2_substring_nametable_scan(code, stringname, NULL, NULL);
}
/* End of pcre2_substring.c */

234
third_party/pcre/pcre2_tables.c vendored Normal file
View file

@ -0,0 +1,234 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains some fixed tables that are used by more than one of the
PCRE2 code modules. The tables are also #included by the pcre2test program,
which uses macros to change their names from _pcre2_xxx to xxxx, thereby
avoiding name clashes with the library. In this case, PCRE2_PCRE2TEST is
defined. */
#ifndef PCRE2_PCRE2TEST /* We're compiling the library */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#endif /* PCRE2_PCRE2TEST */
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
the definition is next to the definition of the opcodes in pcre2_internal.h.
This is mode-dependent, so it is skipped when this file is included by
pcre2test. */
#ifndef PCRE2_PCRE2TEST
const uint8_t PRIV(OP_lengths)[] = { OP_LENGTHS };
#endif
/* Tables of horizontal and vertical whitespace characters, suitable for
adding to classes. */
const uint32_t PRIV(hspace_list)[] = { HSPACE_LIST };
const uint32_t PRIV(vspace_list)[] = { VSPACE_LIST };
/* These tables are the pairs of delimiters that are valid for callout string
arguments. For each starting delimiter there must be a matching ending
delimiter, which in fact is different only for bracket-like delimiters. */
const uint32_t PRIV(callout_start_delims)[] = {
CHAR_GRAVE_ACCENT, CHAR_APOSTROPHE, CHAR_QUOTATION_MARK,
CHAR_CIRCUMFLEX_ACCENT, CHAR_PERCENT_SIGN, CHAR_NUMBER_SIGN,
CHAR_DOLLAR_SIGN, CHAR_LEFT_CURLY_BRACKET, 0 };
const uint32_t PRIV(callout_end_delims[]) = {
CHAR_GRAVE_ACCENT, CHAR_APOSTROPHE, CHAR_QUOTATION_MARK,
CHAR_CIRCUMFLEX_ACCENT, CHAR_PERCENT_SIGN, CHAR_NUMBER_SIGN,
CHAR_DOLLAR_SIGN, CHAR_RIGHT_CURLY_BRACKET, 0 };
/*************************************************
* Tables for UTF-8 support *
*************************************************/
/* These tables are required by pcre2test in 16- or 32-bit mode, as well
as for the library in 8-bit mode, because pcre2test uses UTF-8 internally for
handling wide characters. */
#if defined PCRE2_PCRE2TEST || \
(defined SUPPORT_UNICODE && \
defined PCRE2_CODE_UNIT_WIDTH && \
PCRE2_CODE_UNIT_WIDTH == 8)
/* These are the breakpoints for different numbers of bytes in a UTF-8
character. */
const int PRIV(utf8_table1)[] =
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
/* These are the indicator bits and the mask for the data bits to set in the
first byte of a character, indexed by the number of additional bytes. */
const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
/* Table of the number of extra bytes, indexed by the first byte masked with
0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
const uint8_t PRIV(utf8_table4)[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
#endif /* UTF-8 support needed */
/* Tables concerned with Unicode properties are relevant only when Unicode
support is enabled. See also the pcre2_ucptables.c file, which is generated by
a Python script from Unicode data files. */
#ifdef SUPPORT_UNICODE
/* Table to translate from particular type value to the general value. */
const uint32_t PRIV(ucp_gentype)[] = {
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
ucp_P, ucp_P, /* Ps, Po */
ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
};
/* This table encodes the rules for finding the end of an extended grapheme
cluster. Every code point has a grapheme break property which is one of the
ucp_gbXX values defined in pcre2_ucp.h. These changed between Unicode versions
10 and 11. The 2-dimensional table is indexed by the properties of two adjacent
code points. The left property selects a word from the table, and the right
property selects a bit from that word like this:
PRIV(ucp_gbtable)[left-property] & (1u << right-property)
The value is non-zero if a grapheme break is NOT permitted between the relevant
two code points. The breaking rules are as follows:
1. Break at the start and end of text (pretty obviously).
2. Do not break between a CR and LF; otherwise, break before and after
controls.
3. Do not break Hangul syllable sequences, the rules for which are:
L may be followed by L, V, LV or LVT
LV or V may be followed by V or T
LVT or T may be followed by T
4. Do not break before extending characters or zero-width-joiner (ZWJ).
The following rules are only for extended grapheme clusters (but that's what we
are implementing).
5. Do not break before SpacingMarks.
6. Do not break after Prepend characters.
7. Do not break within emoji modifier sequences or emoji zwj sequences. That
is, do not break between characters with the Extended_Pictographic property.
Extend and ZWJ characters are allowed between the characters; this cannot be
represented in this table, the code has to deal with it.
8. Do not break within emoji flag sequences. That is, do not break between
regional indicator (RI) symbols if there are an odd number of RI characters
before the break point. This table encodes "join RI characters"; the code
has to deal with checking for previous adjoining RIs.
9. Otherwise, break everywhere.
*/
#define ESZ (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbZWJ)
const uint32_t PRIV(ucp_gbtable)[] = {
(1u<<ucp_gbLF), /* 0 CR */
0, /* 1 LF */
0, /* 2 Control */
ESZ, /* 3 Extend */
ESZ|(1u<<ucp_gbPrepend)| /* 4 Prepend */
(1u<<ucp_gbL)|(1u<<ucp_gbV)|(1u<<ucp_gbT)|
(1u<<ucp_gbLV)|(1u<<ucp_gbLVT)|(1u<<ucp_gbOther)|
(1u<<ucp_gbRegional_Indicator),
ESZ, /* 5 SpacingMark */
ESZ|(1u<<ucp_gbL)|(1u<<ucp_gbV)|(1u<<ucp_gbLV)| /* 6 L */
(1u<<ucp_gbLVT),
ESZ|(1u<<ucp_gbV)|(1u<<ucp_gbT), /* 7 V */
ESZ|(1u<<ucp_gbT), /* 8 T */
ESZ|(1u<<ucp_gbV)|(1u<<ucp_gbT), /* 9 LV */
ESZ|(1u<<ucp_gbT), /* 10 LVT */
(1u<<ucp_gbRegional_Indicator), /* 11 Regional Indicator */
ESZ, /* 12 Other */
ESZ, /* 13 ZWJ */
ESZ|(1u<<ucp_gbExtended_Pictographic) /* 14 Extended Pictographic */
};
#undef ESZ
#ifdef SUPPORT_JIT
/* This table reverses PRIV(ucp_gentype). We can save the cost
of a memory load. */
const int PRIV(ucp_typerange)[] = {
ucp_Cc, ucp_Cs,
ucp_Ll, ucp_Lu,
ucp_Mc, ucp_Mn,
ucp_Nd, ucp_No,
ucp_Pc, ucp_Ps,
ucp_Sc, ucp_So,
ucp_Zl, ucp_Zs,
};
#endif /* SUPPORT_JIT */
/* Finally, include the tables that are auto-generated from the Unicode data
files. */
#include "pcre2_ucptables.inc"
#endif /* SUPPORT_UNICODE */
/* End of pcre2_tables.c */

234
third_party/pcre/pcre2_tables.inc vendored Normal file
View file

@ -0,0 +1,234 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains some fixed tables that are used by more than one of the
PCRE2 code modules. The tables are also #included by the pcre2test program,
which uses macros to change their names from _pcre2_xxx to xxxx, thereby
avoiding name clashes with the library. In this case, PCRE2_PCRE2TEST is
defined. */
#ifndef PCRE2_PCRE2TEST /* We're compiling the library */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#endif /* PCRE2_PCRE2TEST */
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
the definition is next to the definition of the opcodes in pcre2_internal.h.
This is mode-dependent, so it is skipped when this file is included by
pcre2test. */
#ifndef PCRE2_PCRE2TEST
const uint8_t PRIV(OP_lengths)[] = { OP_LENGTHS };
#endif
/* Tables of horizontal and vertical whitespace characters, suitable for
adding to classes. */
const uint32_t PRIV(hspace_list)[] = { HSPACE_LIST };
const uint32_t PRIV(vspace_list)[] = { VSPACE_LIST };
/* These tables are the pairs of delimiters that are valid for callout string
arguments. For each starting delimiter there must be a matching ending
delimiter, which in fact is different only for bracket-like delimiters. */
const uint32_t PRIV(callout_start_delims)[] = {
CHAR_GRAVE_ACCENT, CHAR_APOSTROPHE, CHAR_QUOTATION_MARK,
CHAR_CIRCUMFLEX_ACCENT, CHAR_PERCENT_SIGN, CHAR_NUMBER_SIGN,
CHAR_DOLLAR_SIGN, CHAR_LEFT_CURLY_BRACKET, 0 };
const uint32_t PRIV(callout_end_delims[]) = {
CHAR_GRAVE_ACCENT, CHAR_APOSTROPHE, CHAR_QUOTATION_MARK,
CHAR_CIRCUMFLEX_ACCENT, CHAR_PERCENT_SIGN, CHAR_NUMBER_SIGN,
CHAR_DOLLAR_SIGN, CHAR_RIGHT_CURLY_BRACKET, 0 };
/*************************************************
* Tables for UTF-8 support *
*************************************************/
/* These tables are required by pcre2test in 16- or 32-bit mode, as well
as for the library in 8-bit mode, because pcre2test uses UTF-8 internally for
handling wide characters. */
#if defined PCRE2_PCRE2TEST || \
(defined SUPPORT_UNICODE && \
defined PCRE2_CODE_UNIT_WIDTH && \
PCRE2_CODE_UNIT_WIDTH == 8)
/* These are the breakpoints for different numbers of bytes in a UTF-8
character. */
const int PRIV(utf8_table1)[] =
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
/* These are the indicator bits and the mask for the data bits to set in the
first byte of a character, indexed by the number of additional bytes. */
const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
/* Table of the number of extra bytes, indexed by the first byte masked with
0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
const uint8_t PRIV(utf8_table4)[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
#endif /* UTF-8 support needed */
/* Tables concerned with Unicode properties are relevant only when Unicode
support is enabled. See also the pcre2_ucptables.c file, which is generated by
a Python script from Unicode data files. */
#ifdef SUPPORT_UNICODE
/* Table to translate from particular type value to the general value. */
const uint32_t PRIV(ucp_gentype)[] = {
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
ucp_P, ucp_P, /* Ps, Po */
ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
};
/* This table encodes the rules for finding the end of an extended grapheme
cluster. Every code point has a grapheme break property which is one of the
ucp_gbXX values defined in pcre2_ucp.h. These changed between Unicode versions
10 and 11. The 2-dimensional table is indexed by the properties of two adjacent
code points. The left property selects a word from the table, and the right
property selects a bit from that word like this:
PRIV(ucp_gbtable)[left-property] & (1u << right-property)
The value is non-zero if a grapheme break is NOT permitted between the relevant
two code points. The breaking rules are as follows:
1. Break at the start and end of text (pretty obviously).
2. Do not break between a CR and LF; otherwise, break before and after
controls.
3. Do not break Hangul syllable sequences, the rules for which are:
L may be followed by L, V, LV or LVT
LV or V may be followed by V or T
LVT or T may be followed by T
4. Do not break before extending characters or zero-width-joiner (ZWJ).
The following rules are only for extended grapheme clusters (but that's what we
are implementing).
5. Do not break before SpacingMarks.
6. Do not break after Prepend characters.
7. Do not break within emoji modifier sequences or emoji zwj sequences. That
is, do not break between characters with the Extended_Pictographic property.
Extend and ZWJ characters are allowed between the characters; this cannot be
represented in this table, the code has to deal with it.
8. Do not break within emoji flag sequences. That is, do not break between
regional indicator (RI) symbols if there are an odd number of RI characters
before the break point. This table encodes "join RI characters"; the code
has to deal with checking for previous adjoining RIs.
9. Otherwise, break everywhere.
*/
#define ESZ (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbZWJ)
const uint32_t PRIV(ucp_gbtable)[] = {
(1u<<ucp_gbLF), /* 0 CR */
0, /* 1 LF */
0, /* 2 Control */
ESZ, /* 3 Extend */
ESZ|(1u<<ucp_gbPrepend)| /* 4 Prepend */
(1u<<ucp_gbL)|(1u<<ucp_gbV)|(1u<<ucp_gbT)|
(1u<<ucp_gbLV)|(1u<<ucp_gbLVT)|(1u<<ucp_gbOther)|
(1u<<ucp_gbRegional_Indicator),
ESZ, /* 5 SpacingMark */
ESZ|(1u<<ucp_gbL)|(1u<<ucp_gbV)|(1u<<ucp_gbLV)| /* 6 L */
(1u<<ucp_gbLVT),
ESZ|(1u<<ucp_gbV)|(1u<<ucp_gbT), /* 7 V */
ESZ|(1u<<ucp_gbT), /* 8 T */
ESZ|(1u<<ucp_gbV)|(1u<<ucp_gbT), /* 9 LV */
ESZ|(1u<<ucp_gbT), /* 10 LVT */
(1u<<ucp_gbRegional_Indicator), /* 11 Regional Indicator */
ESZ, /* 12 Other */
ESZ, /* 13 ZWJ */
ESZ|(1u<<ucp_gbExtended_Pictographic) /* 14 Extended Pictographic */
};
#undef ESZ
#ifdef SUPPORT_JIT
/* This table reverses PRIV(ucp_gentype). We can save the cost
of a memory load. */
const int PRIV(ucp_typerange)[] = {
ucp_Cc, ucp_Cs,
ucp_Ll, ucp_Lu,
ucp_Mc, ucp_Mn,
ucp_Nd, ucp_No,
ucp_Pc, ucp_Ps,
ucp_Sc, ucp_So,
ucp_Zl, ucp_Zs,
};
#endif /* SUPPORT_JIT */
/* Finally, include the tables that are auto-generated from the Unicode data
files. */
#include "pcre2_ucptables.inc"
#endif /* SUPPORT_UNICODE */
/* End of pcre2_tables.c */

5396
third_party/pcre/pcre2_ucd.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

5396
third_party/pcre/pcre2_ucd.inc vendored Normal file
View file

File diff suppressed because it is too large Load diff

394
third_party/pcre/pcre2_ucp.h vendored Normal file
View file

@ -0,0 +1,394 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
This module is auto-generated from Unicode data files. DO NOT EDIT MANUALLY!
Instead, modify the maint/GenerateUcpHeader.py script and run it to generate
a new version of this code.
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef PCRE2_UCP_H_IDEMPOTENT_GUARD
#define PCRE2_UCP_H_IDEMPOTENT_GUARD
/* This file contains definitions of the Unicode property values that are
returned by the UCD access macros and used throughout PCRE2.
IMPORTANT: The specific values of the first two enums (general and particular
character categories) are assumed by the table called catposstab in the file
pcre2_auto_possess.c. They are unlikely to change, but should be checked after
an update. */
/* These are the general character categories. */
enum {
ucp_C,
ucp_L,
ucp_M,
ucp_N,
ucp_P,
ucp_S,
ucp_Z,
};
/* These are the particular character categories. */
enum {
ucp_Cc, /* Control */
ucp_Cf, /* Format */
ucp_Cn, /* Unassigned */
ucp_Co, /* Private use */
ucp_Cs, /* Surrogate */
ucp_Ll, /* Lower case letter */
ucp_Lm, /* Modifier letter */
ucp_Lo, /* Other letter */
ucp_Lt, /* Title case letter */
ucp_Lu, /* Upper case letter */
ucp_Mc, /* Spacing mark */
ucp_Me, /* Enclosing mark */
ucp_Mn, /* Non-spacing mark */
ucp_Nd, /* Decimal number */
ucp_Nl, /* Letter number */
ucp_No, /* Other number */
ucp_Pc, /* Connector punctuation */
ucp_Pd, /* Dash punctuation */
ucp_Pe, /* Close punctuation */
ucp_Pf, /* Final punctuation */
ucp_Pi, /* Initial punctuation */
ucp_Po, /* Other punctuation */
ucp_Ps, /* Open punctuation */
ucp_Sc, /* Currency symbol */
ucp_Sk, /* Modifier symbol */
ucp_Sm, /* Mathematical symbol */
ucp_So, /* Other symbol */
ucp_Zl, /* Line separator */
ucp_Zp, /* Paragraph separator */
ucp_Zs, /* Space separator */
};
/* These are Boolean properties. */
enum {
ucp_ASCII,
ucp_ASCII_Hex_Digit,
ucp_Alphabetic,
ucp_Bidi_Control,
ucp_Bidi_Mirrored,
ucp_Case_Ignorable,
ucp_Cased,
ucp_Changes_When_Casefolded,
ucp_Changes_When_Casemapped,
ucp_Changes_When_Lowercased,
ucp_Changes_When_Titlecased,
ucp_Changes_When_Uppercased,
ucp_Dash,
ucp_Default_Ignorable_Code_Point,
ucp_Deprecated,
ucp_Diacritic,
ucp_Emoji,
ucp_Emoji_Component,
ucp_Emoji_Modifier,
ucp_Emoji_Modifier_Base,
ucp_Emoji_Presentation,
ucp_Extended_Pictographic,
ucp_Extender,
ucp_Grapheme_Base,
ucp_Grapheme_Extend,
ucp_Grapheme_Link,
ucp_Hex_Digit,
ucp_IDS_Binary_Operator,
ucp_IDS_Trinary_Operator,
ucp_ID_Continue,
ucp_ID_Start,
ucp_Ideographic,
ucp_Join_Control,
ucp_Logical_Order_Exception,
ucp_Lowercase,
ucp_Math,
ucp_Noncharacter_Code_Point,
ucp_Pattern_Syntax,
ucp_Pattern_White_Space,
ucp_Prepended_Concatenation_Mark,
ucp_Quotation_Mark,
ucp_Radical,
ucp_Regional_Indicator,
ucp_Sentence_Terminal,
ucp_Soft_Dotted,
ucp_Terminal_Punctuation,
ucp_Unified_Ideograph,
ucp_Uppercase,
ucp_Variation_Selector,
ucp_White_Space,
ucp_XID_Continue,
ucp_XID_Start,
/* This must be last */
ucp_Bprop_Count
};
/* Size of entries in ucd_boolprop_sets[] */
#define ucd_boolprop_sets_item_size 2
/* These are the bidi class values. */
enum {
ucp_bidiAL, /* Arabic letter */
ucp_bidiAN, /* Arabic number */
ucp_bidiB, /* Paragraph separator */
ucp_bidiBN, /* Boundary neutral */
ucp_bidiCS, /* Common separator */
ucp_bidiEN, /* European number */
ucp_bidiES, /* European separator */
ucp_bidiET, /* European terminator */
ucp_bidiFSI, /* First strong isolate */
ucp_bidiL, /* Left to right */
ucp_bidiLRE, /* Left to right embedding */
ucp_bidiLRI, /* Left to right isolate */
ucp_bidiLRO, /* Left to right override */
ucp_bidiNSM, /* Non-spacing mark */
ucp_bidiON, /* Other neutral */
ucp_bidiPDF, /* Pop directional format */
ucp_bidiPDI, /* Pop directional isolate */
ucp_bidiR, /* Right to left */
ucp_bidiRLE, /* Right to left embedding */
ucp_bidiRLI, /* Right to left isolate */
ucp_bidiRLO, /* Right to left override */
ucp_bidiS, /* Segment separator */
ucp_bidiWS, /* White space */
};
/* These are grapheme break properties. The Extended Pictographic property
comes from the emoji-data.txt file. */
enum {
ucp_gbCR, /* 0 */
ucp_gbLF, /* 1 */
ucp_gbControl, /* 2 */
ucp_gbExtend, /* 3 */
ucp_gbPrepend, /* 4 */
ucp_gbSpacingMark, /* 5 */
ucp_gbL, /* 6 Hangul syllable type L */
ucp_gbV, /* 7 Hangul syllable type V */
ucp_gbT, /* 8 Hangul syllable type T */
ucp_gbLV, /* 9 Hangul syllable type LV */
ucp_gbLVT, /* 10 Hangul syllable type LVT */
ucp_gbRegional_Indicator, /* 11 */
ucp_gbOther, /* 12 */
ucp_gbZWJ, /* 13 */
ucp_gbExtended_Pictographic, /* 14 */
};
/* These are the script identifications. */
enum {
/* Scripts which has characters in other scripts. */
ucp_Latin,
ucp_Greek,
ucp_Cyrillic,
ucp_Arabic,
ucp_Syriac,
ucp_Thaana,
ucp_Devanagari,
ucp_Bengali,
ucp_Gurmukhi,
ucp_Gujarati,
ucp_Oriya,
ucp_Tamil,
ucp_Telugu,
ucp_Kannada,
ucp_Malayalam,
ucp_Sinhala,
ucp_Myanmar,
ucp_Georgian,
ucp_Hangul,
ucp_Mongolian,
ucp_Hiragana,
ucp_Katakana,
ucp_Bopomofo,
ucp_Han,
ucp_Yi,
ucp_Tagalog,
ucp_Hanunoo,
ucp_Buhid,
ucp_Tagbanwa,
ucp_Limbu,
ucp_Tai_Le,
ucp_Linear_B,
ucp_Cypriot,
ucp_Buginese,
ucp_Coptic,
ucp_Glagolitic,
ucp_Syloti_Nagri,
ucp_Phags_Pa,
ucp_Nko,
ucp_Kayah_Li,
ucp_Javanese,
ucp_Kaithi,
ucp_Mandaic,
ucp_Chakma,
ucp_Sharada,
ucp_Takri,
ucp_Duployan,
ucp_Grantha,
ucp_Khojki,
ucp_Linear_A,
ucp_Mahajani,
ucp_Manichaean,
ucp_Modi,
ucp_Old_Permic,
ucp_Psalter_Pahlavi,
ucp_Khudawadi,
ucp_Tirhuta,
ucp_Multani,
ucp_Adlam,
ucp_Masaram_Gondi,
ucp_Dogra,
ucp_Gunjala_Gondi,
ucp_Hanifi_Rohingya,
ucp_Sogdian,
ucp_Nandinagari,
ucp_Yezidi,
ucp_Cypro_Minoan,
ucp_Old_Uyghur,
/* Scripts which has no characters in other scripts. */
ucp_Unknown,
ucp_Common,
ucp_Armenian,
ucp_Hebrew,
ucp_Thai,
ucp_Lao,
ucp_Tibetan,
ucp_Ethiopic,
ucp_Cherokee,
ucp_Canadian_Aboriginal,
ucp_Ogham,
ucp_Runic,
ucp_Khmer,
ucp_Old_Italic,
ucp_Gothic,
ucp_Deseret,
ucp_Inherited,
ucp_Ugaritic,
ucp_Shavian,
ucp_Osmanya,
ucp_Braille,
ucp_New_Tai_Lue,
ucp_Tifinagh,
ucp_Old_Persian,
ucp_Kharoshthi,
ucp_Balinese,
ucp_Cuneiform,
ucp_Phoenician,
ucp_Sundanese,
ucp_Lepcha,
ucp_Ol_Chiki,
ucp_Vai,
ucp_Saurashtra,
ucp_Rejang,
ucp_Lycian,
ucp_Carian,
ucp_Lydian,
ucp_Cham,
ucp_Tai_Tham,
ucp_Tai_Viet,
ucp_Avestan,
ucp_Egyptian_Hieroglyphs,
ucp_Samaritan,
ucp_Lisu,
ucp_Bamum,
ucp_Meetei_Mayek,
ucp_Imperial_Aramaic,
ucp_Old_South_Arabian,
ucp_Inscriptional_Parthian,
ucp_Inscriptional_Pahlavi,
ucp_Old_Turkic,
ucp_Batak,
ucp_Brahmi,
ucp_Meroitic_Cursive,
ucp_Meroitic_Hieroglyphs,
ucp_Miao,
ucp_Sora_Sompeng,
ucp_Caucasian_Albanian,
ucp_Bassa_Vah,
ucp_Elbasan,
ucp_Pahawh_Hmong,
ucp_Mende_Kikakui,
ucp_Mro,
ucp_Old_North_Arabian,
ucp_Nabataean,
ucp_Palmyrene,
ucp_Pau_Cin_Hau,
ucp_Siddham,
ucp_Warang_Citi,
ucp_Ahom,
ucp_Anatolian_Hieroglyphs,
ucp_Hatran,
ucp_Old_Hungarian,
ucp_SignWriting,
ucp_Bhaiksuki,
ucp_Marchen,
ucp_Newa,
ucp_Osage,
ucp_Tangut,
ucp_Nushu,
ucp_Soyombo,
ucp_Zanabazar_Square,
ucp_Makasar,
ucp_Medefaidrin,
ucp_Old_Sogdian,
ucp_Elymaic,
ucp_Nyiakeng_Puachue_Hmong,
ucp_Wancho,
ucp_Chorasmian,
ucp_Dives_Akuru,
ucp_Khitan_Small_Script,
ucp_Tangsa,
ucp_Toto,
ucp_Vithkuqi,
/* This must be last */
ucp_Script_Count
};
/* Size of entries in ucd_script_sets[] */
#define ucd_script_sets_item_size 3
#endif /* PCRE2_UCP_H_IDEMPOTENT_GUARD */
/* End of pcre2_ucp.h */

1524
third_party/pcre/pcre2_ucptables.inc vendored Normal file
View file

File diff suppressed because it is too large Load diff

398
third_party/pcre/pcre2_valid_utf.c vendored Normal file
View file

@ -0,0 +1,398 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function for validating UTF character
strings. This file is also #included by the pcre2test program, which uses
macros to change names from _pcre2_xxx to xxxx, thereby avoiding name clashes
with the library. In this case, PCRE2_PCRE2TEST is defined. */
#ifndef PCRE2_PCRE2TEST /* We're compiling the library */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#endif /* PCRE2_PCRE2TEST */
#ifndef SUPPORT_UNICODE
/*************************************************
* Dummy function when Unicode is not supported *
*************************************************/
/* This function should never be called when Unicode is not supported. */
int
PRIV(valid_utf)(PCRE2_SPTR string, PCRE2_SIZE length, PCRE2_SIZE *erroroffset)
{
(void)string;
(void)length;
(void)erroroffset;
return 0;
}
#else /* UTF is supported */
/*************************************************
* Validate a UTF string *
*************************************************/
/* This function is called (optionally) at the start of compile or match, to
check that a supposed UTF string is actually valid. The early check means
that subsequent code can assume it is dealing with a valid string. The check
can be turned off for maximum performance, but the consequences of supplying an
invalid string are then undefined.
Arguments:
string points to the string
length length of string
errp pointer to an error position offset variable
Returns: == 0 if the string is a valid UTF string
!= 0 otherwise, setting the offset of the bad character
*/
int
PRIV(valid_utf)(PCRE2_SPTR string, PCRE2_SIZE length, PCRE2_SIZE *erroroffset)
{
PCRE2_SPTR p;
uint32_t c;
/* ----------------- Check a UTF-8 string ----------------- */
#if PCRE2_CODE_UNIT_WIDTH == 8
/* Originally, this function checked according to RFC 2279, allowing for values
in the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were
in the canonical format. Once somebody had pointed out RFC 3629 to me (it
obsoletes 2279), additional restrictions were applied. The values are now
limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte
characters is still checked. Error returns are as follows:
PCRE2_ERROR_UTF8_ERR1 Missing 1 byte at the end of the string
PCRE2_ERROR_UTF8_ERR2 Missing 2 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR3 Missing 3 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR4 Missing 4 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR5 Missing 5 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR6 2nd-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR7 3rd-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR8 4th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR9 5th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR10 6th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR11 5-byte character is not permitted by RFC 3629
PCRE2_ERROR_UTF8_ERR12 6-byte character is not permitted by RFC 3629
PCRE2_ERROR_UTF8_ERR13 4-byte character with value > 0x10ffff is not permitted
PCRE2_ERROR_UTF8_ERR14 3-byte character with value 0xd800-0xdfff is not permitted
PCRE2_ERROR_UTF8_ERR15 Overlong 2-byte sequence
PCRE2_ERROR_UTF8_ERR16 Overlong 3-byte sequence
PCRE2_ERROR_UTF8_ERR17 Overlong 4-byte sequence
PCRE2_ERROR_UTF8_ERR18 Overlong 5-byte sequence (won't ever occur)
PCRE2_ERROR_UTF8_ERR19 Overlong 6-byte sequence (won't ever occur)
PCRE2_ERROR_UTF8_ERR20 Isolated 0x80 byte (not within UTF-8 character)
PCRE2_ERROR_UTF8_ERR21 Byte with the illegal value 0xfe or 0xff
*/
for (p = string; length > 0; p++)
{
uint32_t ab, d;
c = *p;
length--;
if (c < 128) continue; /* ASCII character */
if (c < 0xc0) /* Isolated 10xx xxxx byte */
{
*erroroffset = (PCRE2_SIZE)(p - string);
return PCRE2_ERROR_UTF8_ERR20;
}
if (c >= 0xfe) /* Invalid 0xfe or 0xff bytes */
{
*erroroffset = (PCRE2_SIZE)(p - string);
return PCRE2_ERROR_UTF8_ERR21;
}
ab = PRIV(utf8_table4)[c & 0x3f]; /* Number of additional bytes (1-5) */
if (length < ab) /* Missing bytes */
{
*erroroffset = (PCRE2_SIZE)(p - string);
switch(ab - length)
{
case 1: return PCRE2_ERROR_UTF8_ERR1;
case 2: return PCRE2_ERROR_UTF8_ERR2;
case 3: return PCRE2_ERROR_UTF8_ERR3;
case 4: return PCRE2_ERROR_UTF8_ERR4;
case 5: return PCRE2_ERROR_UTF8_ERR5;
}
}
length -= ab; /* Length remaining */
/* Check top bits in the second byte */
if (((d = *(++p)) & 0xc0) != 0x80)
{
*erroroffset = (int)(p - string) - 1;
return PCRE2_ERROR_UTF8_ERR6;
}
/* For each length, check that the remaining bytes start with the 0x80 bit
set and not the 0x40 bit. Then check for an overlong sequence, and for the
excluded range 0xd800 to 0xdfff. */
switch (ab)
{
/* 2-byte character. No further bytes to check for 0x80. Check first byte
for for xx00 000x (overlong sequence). */
case 1: if ((c & 0x3e) == 0)
{
*erroroffset = (int)(p - string) - 1;
return PCRE2_ERROR_UTF8_ERR15;
}
break;
/* 3-byte character. Check third byte for 0x80. Then check first 2 bytes
for 1110 0000, xx0x xxxx (overlong sequence) or
1110 1101, 1010 xxxx (0xd800 - 0xdfff) */
case 2:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if (c == 0xe0 && (d & 0x20) == 0)
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR16;
}
if (c == 0xed && d >= 0xa0)
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR14;
}
break;
/* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2
bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a
character greater than 0x0010ffff (f4 8f bf bf) */
case 3:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if (c == 0xf0 && (d & 0x30) == 0)
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR17;
}
if (c > 0xf4 || (c == 0xf4 && d > 0x8f))
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR13;
}
break;
/* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be
rejected by the length test below. However, we do the appropriate tests
here so that overlong sequences get diagnosed, and also in case there is
ever an option for handling these larger code points. */
/* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for
1111 1000, xx00 0xxx */
case 4:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR9;
}
if (c == 0xf8 && (d & 0x38) == 0)
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR18;
}
break;
/* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for
1111 1100, xx00 00xx. */
case 5:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR9;
}
if ((*(++p) & 0xc0) != 0x80) /* Sixth byte */
{
*erroroffset = (int)(p - string) - 5;
return PCRE2_ERROR_UTF8_ERR10;
}
if (c == 0xfc && (d & 0x3c) == 0)
{
*erroroffset = (int)(p - string) - 5;
return PCRE2_ERROR_UTF8_ERR19;
}
break;
}
/* Character is valid under RFC 2279, but 4-byte and 5-byte characters are
excluded by RFC 3629. The pointer p is currently at the last byte of the
character. */
if (ab > 3)
{
*erroroffset = (int)(p - string) - ab;
return (ab == 4)? PCRE2_ERROR_UTF8_ERR11 : PCRE2_ERROR_UTF8_ERR12;
}
}
return 0;
/* ----------------- Check a UTF-16 string ----------------- */
#elif PCRE2_CODE_UNIT_WIDTH == 16
/* There's not so much work, nor so many errors, for UTF-16.
PCRE2_ERROR_UTF16_ERR1 Missing low surrogate at the end of the string
PCRE2_ERROR_UTF16_ERR2 Invalid low surrogate
PCRE2_ERROR_UTF16_ERR3 Isolated low surrogate
*/
for (p = string; length > 0; p++)
{
c = *p;
length--;
if ((c & 0xf800) != 0xd800)
{
/* Normal UTF-16 code point. Neither high nor low surrogate. */
}
else if ((c & 0x0400) == 0)
{
/* High surrogate. Must be a followed by a low surrogate. */
if (length == 0)
{
*erroroffset = p - string;
return PCRE2_ERROR_UTF16_ERR1;
}
p++;
length--;
if ((*p & 0xfc00) != 0xdc00)
{
*erroroffset = p - string - 1;
return PCRE2_ERROR_UTF16_ERR2;
}
}
else
{
/* Isolated low surrogate. Always an error. */
*erroroffset = p - string;
return PCRE2_ERROR_UTF16_ERR3;
}
}
return 0;
/* ----------------- Check a UTF-32 string ----------------- */
#else
/* There is very little to do for a UTF-32 string.
PCRE2_ERROR_UTF32_ERR1 Surrogate character
PCRE2_ERROR_UTF32_ERR2 Character > 0x10ffff
*/
for (p = string; length > 0; length--, p++)
{
c = *p;
if ((c & 0xfffff800u) != 0xd800u)
{
/* Normal UTF-32 code point. Neither high nor low surrogate. */
if (c > 0x10ffffu)
{
*erroroffset = p - string;
return PCRE2_ERROR_UTF32_ERR2;
}
}
else
{
/* A surrogate */
*erroroffset = p - string;
return PCRE2_ERROR_UTF32_ERR1;
}
}
return 0;
#endif /* CODE_UNIT_WIDTH */
}
#endif /* SUPPORT_UNICODE */
/* End of pcre2_valid_utf.c */

398
third_party/pcre/pcre2_valid_utf.inc vendored Normal file
View file

@ -0,0 +1,398 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function for validating UTF character
strings. This file is also #included by the pcre2test program, which uses
macros to change names from _pcre2_xxx to xxxx, thereby avoiding name clashes
with the library. In this case, PCRE2_PCRE2TEST is defined. */
#ifndef PCRE2_PCRE2TEST /* We're compiling the library */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#endif /* PCRE2_PCRE2TEST */
#ifndef SUPPORT_UNICODE
/*************************************************
* Dummy function when Unicode is not supported *
*************************************************/
/* This function should never be called when Unicode is not supported. */
int
PRIV(valid_utf)(PCRE2_SPTR string, PCRE2_SIZE length, PCRE2_SIZE *erroroffset)
{
(void)string;
(void)length;
(void)erroroffset;
return 0;
}
#else /* UTF is supported */
/*************************************************
* Validate a UTF string *
*************************************************/
/* This function is called (optionally) at the start of compile or match, to
check that a supposed UTF string is actually valid. The early check means
that subsequent code can assume it is dealing with a valid string. The check
can be turned off for maximum performance, but the consequences of supplying an
invalid string are then undefined.
Arguments:
string points to the string
length length of string
errp pointer to an error position offset variable
Returns: == 0 if the string is a valid UTF string
!= 0 otherwise, setting the offset of the bad character
*/
int
PRIV(valid_utf)(PCRE2_SPTR string, PCRE2_SIZE length, PCRE2_SIZE *erroroffset)
{
PCRE2_SPTR p;
uint32_t c;
/* ----------------- Check a UTF-8 string ----------------- */
#if PCRE2_CODE_UNIT_WIDTH == 8
/* Originally, this function checked according to RFC 2279, allowing for values
in the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were
in the canonical format. Once somebody had pointed out RFC 3629 to me (it
obsoletes 2279), additional restrictions were applied. The values are now
limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte
characters is still checked. Error returns are as follows:
PCRE2_ERROR_UTF8_ERR1 Missing 1 byte at the end of the string
PCRE2_ERROR_UTF8_ERR2 Missing 2 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR3 Missing 3 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR4 Missing 4 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR5 Missing 5 bytes at the end of the string
PCRE2_ERROR_UTF8_ERR6 2nd-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR7 3rd-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR8 4th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR9 5th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR10 6th-byte's two top bits are not 0x80
PCRE2_ERROR_UTF8_ERR11 5-byte character is not permitted by RFC 3629
PCRE2_ERROR_UTF8_ERR12 6-byte character is not permitted by RFC 3629
PCRE2_ERROR_UTF8_ERR13 4-byte character with value > 0x10ffff is not permitted
PCRE2_ERROR_UTF8_ERR14 3-byte character with value 0xd800-0xdfff is not permitted
PCRE2_ERROR_UTF8_ERR15 Overlong 2-byte sequence
PCRE2_ERROR_UTF8_ERR16 Overlong 3-byte sequence
PCRE2_ERROR_UTF8_ERR17 Overlong 4-byte sequence
PCRE2_ERROR_UTF8_ERR18 Overlong 5-byte sequence (won't ever occur)
PCRE2_ERROR_UTF8_ERR19 Overlong 6-byte sequence (won't ever occur)
PCRE2_ERROR_UTF8_ERR20 Isolated 0x80 byte (not within UTF-8 character)
PCRE2_ERROR_UTF8_ERR21 Byte with the illegal value 0xfe or 0xff
*/
for (p = string; length > 0; p++)
{
uint32_t ab, d;
c = *p;
length--;
if (c < 128) continue; /* ASCII character */
if (c < 0xc0) /* Isolated 10xx xxxx byte */
{
*erroroffset = (PCRE2_SIZE)(p - string);
return PCRE2_ERROR_UTF8_ERR20;
}
if (c >= 0xfe) /* Invalid 0xfe or 0xff bytes */
{
*erroroffset = (PCRE2_SIZE)(p - string);
return PCRE2_ERROR_UTF8_ERR21;
}
ab = PRIV(utf8_table4)[c & 0x3f]; /* Number of additional bytes (1-5) */
if (length < ab) /* Missing bytes */
{
*erroroffset = (PCRE2_SIZE)(p - string);
switch(ab - length)
{
case 1: return PCRE2_ERROR_UTF8_ERR1;
case 2: return PCRE2_ERROR_UTF8_ERR2;
case 3: return PCRE2_ERROR_UTF8_ERR3;
case 4: return PCRE2_ERROR_UTF8_ERR4;
case 5: return PCRE2_ERROR_UTF8_ERR5;
}
}
length -= ab; /* Length remaining */
/* Check top bits in the second byte */
if (((d = *(++p)) & 0xc0) != 0x80)
{
*erroroffset = (int)(p - string) - 1;
return PCRE2_ERROR_UTF8_ERR6;
}
/* For each length, check that the remaining bytes start with the 0x80 bit
set and not the 0x40 bit. Then check for an overlong sequence, and for the
excluded range 0xd800 to 0xdfff. */
switch (ab)
{
/* 2-byte character. No further bytes to check for 0x80. Check first byte
for for xx00 000x (overlong sequence). */
case 1: if ((c & 0x3e) == 0)
{
*erroroffset = (int)(p - string) - 1;
return PCRE2_ERROR_UTF8_ERR15;
}
break;
/* 3-byte character. Check third byte for 0x80. Then check first 2 bytes
for 1110 0000, xx0x xxxx (overlong sequence) or
1110 1101, 1010 xxxx (0xd800 - 0xdfff) */
case 2:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if (c == 0xe0 && (d & 0x20) == 0)
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR16;
}
if (c == 0xed && d >= 0xa0)
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR14;
}
break;
/* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2
bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a
character greater than 0x0010ffff (f4 8f bf bf) */
case 3:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if (c == 0xf0 && (d & 0x30) == 0)
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR17;
}
if (c > 0xf4 || (c == 0xf4 && d > 0x8f))
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR13;
}
break;
/* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be
rejected by the length test below. However, we do the appropriate tests
here so that overlong sequences get diagnosed, and also in case there is
ever an option for handling these larger code points. */
/* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for
1111 1000, xx00 0xxx */
case 4:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR9;
}
if (c == 0xf8 && (d & 0x38) == 0)
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR18;
}
break;
/* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for
1111 1100, xx00 00xx. */
case 5:
if ((*(++p) & 0xc0) != 0x80) /* Third byte */
{
*erroroffset = (int)(p - string) - 2;
return PCRE2_ERROR_UTF8_ERR7;
}
if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */
{
*erroroffset = (int)(p - string) - 3;
return PCRE2_ERROR_UTF8_ERR8;
}
if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */
{
*erroroffset = (int)(p - string) - 4;
return PCRE2_ERROR_UTF8_ERR9;
}
if ((*(++p) & 0xc0) != 0x80) /* Sixth byte */
{
*erroroffset = (int)(p - string) - 5;
return PCRE2_ERROR_UTF8_ERR10;
}
if (c == 0xfc && (d & 0x3c) == 0)
{
*erroroffset = (int)(p - string) - 5;
return PCRE2_ERROR_UTF8_ERR19;
}
break;
}
/* Character is valid under RFC 2279, but 4-byte and 5-byte characters are
excluded by RFC 3629. The pointer p is currently at the last byte of the
character. */
if (ab > 3)
{
*erroroffset = (int)(p - string) - ab;
return (ab == 4)? PCRE2_ERROR_UTF8_ERR11 : PCRE2_ERROR_UTF8_ERR12;
}
}
return 0;
/* ----------------- Check a UTF-16 string ----------------- */
#elif PCRE2_CODE_UNIT_WIDTH == 16
/* There's not so much work, nor so many errors, for UTF-16.
PCRE2_ERROR_UTF16_ERR1 Missing low surrogate at the end of the string
PCRE2_ERROR_UTF16_ERR2 Invalid low surrogate
PCRE2_ERROR_UTF16_ERR3 Isolated low surrogate
*/
for (p = string; length > 0; p++)
{
c = *p;
length--;
if ((c & 0xf800) != 0xd800)
{
/* Normal UTF-16 code point. Neither high nor low surrogate. */
}
else if ((c & 0x0400) == 0)
{
/* High surrogate. Must be a followed by a low surrogate. */
if (length == 0)
{
*erroroffset = p - string;
return PCRE2_ERROR_UTF16_ERR1;
}
p++;
length--;
if ((*p & 0xfc00) != 0xdc00)
{
*erroroffset = p - string - 1;
return PCRE2_ERROR_UTF16_ERR2;
}
}
else
{
/* Isolated low surrogate. Always an error. */
*erroroffset = p - string;
return PCRE2_ERROR_UTF16_ERR3;
}
}
return 0;
/* ----------------- Check a UTF-32 string ----------------- */
#else
/* There is very little to do for a UTF-32 string.
PCRE2_ERROR_UTF32_ERR1 Surrogate character
PCRE2_ERROR_UTF32_ERR2 Character > 0x10ffff
*/
for (p = string; length > 0; length--, p++)
{
c = *p;
if ((c & 0xfffff800u) != 0xd800u)
{
/* Normal UTF-32 code point. Neither high nor low surrogate. */
if (c > 0x10ffffu)
{
*erroroffset = p - string;
return PCRE2_ERROR_UTF32_ERR2;
}
}
else
{
/* A surrogate */
*erroroffset = p - string;
return PCRE2_ERROR_UTF32_ERR1;
}
}
return 0;
#endif /* CODE_UNIT_WIDTH */
}
#endif /* SUPPORT_UNICODE */
/* End of pcre2_valid_utf.c */

289
third_party/pcre/pcre2_xclass.c vendored Normal file
View file

@ -0,0 +1,289 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that is used to match an extended
class. It is used by pcre2_auto_possessify() and by both pcre2_match() and
pcre2_def_match(). */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Match character against an XCLASS *
*************************************************/
/* This function is called to match a character against an extended class that
might contain codepoints above 255 and/or Unicode properties.
Arguments:
c the character
data points to the flag code unit of the XCLASS data
utf TRUE if in UTF mode
Returns: TRUE if character matches, else FALSE
*/
BOOL
PRIV(xclass)(uint32_t c, PCRE2_SPTR data, BOOL utf)
{
PCRE2_UCHAR t;
BOOL negated = (*data & XCL_NOT) != 0;
#if PCRE2_CODE_UNIT_WIDTH == 8
/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */
utf = TRUE;
#endif
/* Code points < 256 are matched against a bitmap, if one is present. If not,
we still carry on, because there may be ranges that start below 256 in the
additional data. */
if (c < 256)
{
if ((*data & XCL_HASPROP) == 0)
{
if ((*data & XCL_MAP) == 0) return negated;
return (((uint8_t *)(data + 1))[c/8] & (1u << (c&7))) != 0;
}
if ((*data & XCL_MAP) != 0 &&
(((uint8_t *)(data + 1))[c/8] & (1u << (c&7))) != 0)
return !negated; /* char found */
}
/* First skip the bit map if present. Then match against the list of Unicode
properties or large chars or ranges that end with a large char. We won't ever
encounter XCL_PROP or XCL_NOTPROP when UTF support is not compiled. */
if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(PCRE2_UCHAR);
while ((t = *data++) != XCL_END)
{
uint32_t x, y;
if (t == XCL_SINGLE)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
GETCHARINC(x, data); /* macro generates multiple statements */
}
else
#endif
x = *data++;
if (c == x) return !negated;
}
else if (t == XCL_RANGE)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
GETCHARINC(x, data); /* macro generates multiple statements */
GETCHARINC(y, data); /* macro generates multiple statements */
}
else
#endif
{
x = *data++;
y = *data++;
}
if (c >= x && c <= y) return !negated;
}
#ifdef SUPPORT_UNICODE
else /* XCL_PROP & XCL_NOTPROP */
{
const ucd_record *prop = GET_UCD(c);
BOOL isprop = t == XCL_PROP;
BOOL ok;
switch(*data)
{
case PT_ANY:
if (isprop) return !negated;
break;
case PT_LAMP:
if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll ||
prop->chartype == ucp_Lt) == isprop) return !negated;
break;
case PT_GC:
if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop)
return !negated;
break;
case PT_PC:
if ((data[1] == prop->chartype) == isprop) return !negated;
break;
case PT_SC:
if ((data[1] == prop->script) == isprop) return !negated;
break;
case PT_SCX:
ok = (data[1] == prop->script ||
MAPBIT(PRIV(ucd_script_sets) + UCD_SCRIPTX_PROP(prop), data[1]) != 0);
if (ok == isprop) return !negated;
break;
case PT_ALNUM:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop)
return !negated;
break;
/* Perl space used to exclude VT, but from Perl 5.18 it is included,
which means that Perl space and POSIX space are now identical. PCRE
was changed at release 8.34. */
case PT_SPACE: /* Perl space */
case PT_PXSPACE: /* POSIX space */
switch(c)
{
HSPACE_CASES:
VSPACE_CASES:
if (isprop) return !negated;
break;
default:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop)
return !negated;
break;
}
break;
case PT_WORD:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE)
== isprop)
return !negated;
break;
case PT_UCNC:
if (c < 0xa0)
{
if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
c == CHAR_GRAVE_ACCENT) == isprop)
return !negated;
}
else
{
if ((c < 0xd800 || c > 0xdfff) == isprop)
return !negated;
}
break;
case PT_BIDICL:
if ((UCD_BIDICLASS_PROP(prop) == data[1]) == isprop)
return !negated;
break;
case PT_BOOL:
ok = MAPBIT(PRIV(ucd_boolprop_sets) +
UCD_BPROPS_PROP(prop), data[1]) != 0;
if (ok == isprop) return !negated;
break;
/* The following three properties can occur only in an XCLASS, as there
is no \p or \P coding for them. */
/* Graphic character. Implement this as not Z (space or separator) and
not C (other), except for Cf (format) with a few exceptions. This seems
to be what Perl does. The exceptional characters are:
U+061C Arabic Letter Mark
U+180E Mongolian Vowel Separator
U+2066 - U+2069 Various "isolate"s
*/
case PT_PXGRAPH:
if ((PRIV(ucp_gentype)[prop->chartype] != ucp_Z &&
(PRIV(ucp_gentype)[prop->chartype] != ucp_C ||
(prop->chartype == ucp_Cf &&
c != 0x061c && c != 0x180e && (c < 0x2066 || c > 0x2069))
)) == isprop)
return !negated;
break;
/* Printable character: same as graphic, with the addition of Zs, i.e.
not Zl and not Zp, and U+180E. */
case PT_PXPRINT:
if ((prop->chartype != ucp_Zl &&
prop->chartype != ucp_Zp &&
(PRIV(ucp_gentype)[prop->chartype] != ucp_C ||
(prop->chartype == ucp_Cf &&
c != 0x061c && (c < 0x2066 || c > 0x2069))
)) == isprop)
return !negated;
break;
/* Punctuation: all Unicode punctuation, plus ASCII characters that
Unicode treats as symbols rather than punctuation, for Perl
compatibility (these are $+<=>^`|~). */
case PT_PXPUNCT:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P ||
(c < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop)
return !negated;
break;
/* This should never occur, but compilers may mutter if there is no
default. */
default:
return FALSE;
}
data += 2;
}
#else
(void)utf; /* Avoid compiler warning */
#endif /* SUPPORT_UNICODE */
}
return negated; /* char did not match */
}
/* End of pcre2_xclass.c */

975
third_party/pcre/pcre2grep.1 vendored Normal file
View file

@ -0,0 +1,975 @@
.TH PCRE2GREP 1 "21 November 2022" "PCRE2 10.41"
.SH NAME
pcre2grep - a grep with Perl-compatible regular expressions.
.SH SYNOPSIS
.B pcre2grep [options] [long options] [pattern] [path1 path2 ...]
.
.SH DESCRIPTION
.rs
.sp
\fBpcre2grep\fP searches files for character patterns, in the same way as other
grep commands do, but it uses the PCRE2 regular expression library to support
patterns that are compatible with the regular expressions of Perl 5. See
.\" HREF
\fBpcre2syntax\fP(3)
.\"
for a quick-reference summary of pattern syntax, or
.\" HREF
\fBpcre2pattern\fP(3)
.\"
for a full description of the syntax and semantics of the regular expressions
that PCRE2 supports.
.P
Patterns, whether supplied on the command line or in a separate file, are given
without delimiters. For example:
.sp
pcre2grep Thursday /etc/motd
.sp
If you attempt to use delimiters (for example, by surrounding a pattern with
slashes, as is common in Perl scripts), they are interpreted as part of the
pattern. Quotes can of course be used to delimit patterns on the command line
because they are interpreted by the shell, and indeed quotes are required if a
pattern contains white space or shell metacharacters.
.P
The first argument that follows any option settings is treated as the single
pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present.
Conversely, when one or both of these options are used to specify patterns, all
arguments are treated as path names. At least one of \fB-e\fP, \fB-f\fP, or an
argument pattern must be provided.
.P
If no files are specified, \fBpcre2grep\fP reads the standard input. The
standard input can also be referenced by a name consisting of a single hyphen.
For example:
.sp
pcre2grep some-pattern file1 - file3
.sp
By default, input files are searched line by line. Each line that matches a
pattern is copied to the standard output, and if there is more than one file,
the file name is output at the start of each line, followed by a colon.
However, there are options that can change how \fBpcre2grep\fP behaves. For
example, the \fB-M\fP option makes it possible to search for strings that span
line boundaries. What defines a line boundary is controlled by the \fB-N\fP
(\fB--newline\fP) option. The \fB-h\fP and \fB-H\fP options control whether or
not file names are shown, and the \fB-Z\fP option changes the file name
terminator to a zero byte.
.P
The amount of memory used for buffering files that are being scanned is
controlled by parameters that can be set by the \fB--buffer-size\fP and
\fB--max-buffer-size\fP options. The first of these sets the size of buffer
that is obtained at the start of processing. If an input file contains very
long lines, a larger buffer may be needed; this is handled by automatically
extending the buffer, up to the limit specified by \fB--max-buffer-size\fP. The
default values for these parameters can be set when \fBpcre2grep\fP is
built; if nothing is specified, the defaults are set to 20KiB and 1MiB
respectively. An error occurs if a line is too long and the buffer can no
longer be expanded.
.P
The block of memory that is actually used is three times the "buffer size", to
allow for buffering "before" and "after" lines. If the buffer size is too
small, fewer than requested "before" and "after" lines may be output.
.P
Patterns can be no longer than 8KiB or BUFSIZ bytes, whichever is the greater.
BUFSIZ is defined in \fB<stdio.h>\fP. When there is more than one pattern
(specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to
each line in the order in which they are defined, except that all the \fB-e\fP
patterns are tried before the \fB-f\fP patterns.
.P
By default, as soon as one pattern matches a line, no further patterns are
considered. However, if \fB--colour\fP (or \fB--color\fP) is used to colour the
matching substrings, or if \fB--only-matching\fP, \fB--file-offsets\fP,
\fB--line-offsets\fP, or \fB--output\fP is used to output only the part of the
line that matched (either shown literally, or as an offset), the behaviour is
different. In this situation, all the patterns are applied to the line. If
there is more than one match, the one that begins nearest to the start of the
subject is processed; if there is more than one match at that position, the one
with the longest matching substring is processed; if the matching substrings
are equal, the first match found is processed.
.P
Scanning with all the patterns resumes immediately following the match, so that
later matches on the same line can be found. Note, however, that an overlapping
match that starts in the middle of another match will not be processed.
.P
The above behaviour was changed at release 10.41 to be more compatible with GNU
grep. In earlier releases, \fBpcre2grep\fP did not recognize matches from
later patterns that were earlier in the subject.
.P
Patterns that can match an empty string are accepted, but empty string
matches are never recognized. An example is the pattern "(super)?(man)?", in
which all components are optional. This pattern finds all occurrences of both
"super" and "man"; the output differs from matching with "super|man" when only
the matching substrings are being shown.
.P
If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set,
\fBpcre2grep\fP uses the value to set a locale when calling the PCRE2 library.
The \fB--locale\fP option can be used to override this.
.
.
.SH "SUPPORT FOR COMPRESSED FILES"
.rs
.sp
Compile-time options for \fBpcre2grep\fP can set it up to use \fBlibz\fP or
\fBlibbz2\fP for reading compressed files whose names end in \fB.gz\fP or
\fB.bz2\fP, respectively. You can find out whether your \fBpcre2grep\fP binary
has support for one or both of these file types by running it with the
\fB--help\fP option. If the appropriate support is not present, all files are
treated as plain text. The standard input is always so treated. If a file with
a \fB.gz\fP or \fB.bz2\fP extension is not in fact compressed, it is read as a
plain text file. When input is from a compressed .gz or .bz2 file, the
\fB--line-buffered\fP option is ignored.
.
.
.SH "BINARY FILES"
.rs
.sp
By default, a file that contains a binary zero byte within the first 1024 bytes
is identified as a binary file, and is processed specially. However, if the
newline type is specified as NUL, that is, the line terminator is a binary
zero, the test for a binary file is not applied. See the \fB--binary-files\fP
option for a means of changing the way binary files are handled.
.
.
.SH "BINARY ZEROS IN PATTERNS"
.rs
.sp
Patterns passed from the command line are strings that are terminated by a
binary zero, so cannot contain internal zeros. However, patterns that are read
from a file via the \fB-f\fP option may contain binary zeros.
.
.
.SH OPTIONS
.rs
.sp
The order in which some of the options appear can affect the output. For
example, both the \fB-H\fP and \fB-l\fP options affect the printing of file
names. Whichever comes later in the command line will be the one that takes
effect. Similarly, except where noted below, if an option is given twice, the
later setting is used. Numerical values for options may be followed by K or M,
to signify multiplication by 1024 or 1024*1024 respectively.
.TP 10
\fB--\fP
This terminates the list of options. It is useful if the next item on the
command line starts with a hyphen but is not an option. This allows for the
processing of patterns and file names that start with hyphens.
.TP
\fB-A\fP \fInumber\fP, \fB--after-context=\fP\fInumber\fP
Output up to \fInumber\fP lines of context after each matching line. Fewer
lines are output if the next match or the end of the file is reached, or if the
processing buffer size has been set too small. If file names and/or line
numbers are being output, a hyphen separator is used instead of a colon for the
context lines (the \fB-Z\fP option can be used to change the file name
terminator to a zero byte). A line containing "--" is output between each group
of lines, unless they are in fact contiguous in the input file. The value of
\fInumber\fP is expected to be relatively small. When \fB-c\fP is used,
\fB-A\fP is ignored.
.TP
\fB-a\fP, \fB--text\fP
Treat binary files as text. This is equivalent to
\fB--binary-files\fP=\fItext\fP.
.TP
\fB--allow-lookaround-bsk\fP
PCRE2 now forbids the use of \eK in lookarounds by default, in line with Perl.
This option causes \fBpcre2grep\fP to set the PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK
option, which enables this somewhat dangerous usage.
.TP
\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP
Output up to \fInumber\fP lines of context before each matching line. Fewer
lines are output if the previous match or the start of the file is within
\fInumber\fP lines, or if the processing buffer size has been set too small. If
file names and/or line numbers are being output, a hyphen separator is used
instead of a colon for the context lines (the \fB-Z\fP option can be used to
change the file name terminator to a zero byte). A line containing "--" is
output between each group of lines, unless they are in fact contiguous in the
input file. The value of \fInumber\fP is expected to be relatively small. When
\fB-c\fP is used, \fB-B\fP is ignored.
.TP
\fB--binary-files=\fP\fIword\fP
Specify how binary files are to be processed. If the word is "binary" (the
default), pattern matching is performed on binary files, but the only output is
"Binary file <name> matches" when a match succeeds. If the word is "text",
which is equivalent to the \fB-a\fP or \fB--text\fP option, binary files are
processed in the same way as any other file. In this case, when a match
succeeds, the output may be binary garbage, which can have nasty effects if
sent to a terminal. If the word is "without-match", which is equivalent to the
\fB-I\fP option, binary files are not processed at all; they are assumed not to
be of interest and are skipped without causing any output or affecting the
return code.
.TP
\fB--buffer-size=\fP\fInumber\fP
Set the parameter that controls how much memory is obtained at the start of
processing for buffering files that are being scanned. See also
\fB--max-buffer-size\fP below.
.TP
\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP
Output \fInumber\fP lines of context both before and after each matching line.
This is equivalent to setting both \fB-A\fP and \fB-B\fP to the same value.
.TP
\fB-c\fP, \fB--count\fP
Do not output lines from the files that are being scanned; instead output the
number of lines that would have been shown, either because they matched, or, if
\fB-v\fP is set, because they failed to match. By default, this count is
exactly the same as the number of lines that would have been output, but if the
\fB-M\fP (multiline) option is used (without \fB-v\fP), there may be more
suppressed lines than the count (that is, the number of matches).
.sp
If no lines are selected, the number zero is output. If several files are are
being scanned, a count is output for each of them and the \fB-t\fP option can
be used to cause a total to be output at the end. However, if the
\fB--files-with-matches\fP option is also used, only those files whose counts
are greater than zero are listed. When \fB-c\fP is used, the \fB-A\fP,
\fB-B\fP, and \fB-C\fP options are ignored.
.TP
\fB--colour\fP, \fB--color\fP
If this option is given without any data, it is equivalent to "--colour=auto".
If data is required, it must be given in the same shell item, separated by an
equals sign.
.TP
\fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP
This option specifies under what circumstances the parts of a line that matched
a pattern should be coloured in the output. It is ignored if
\fB--file-offsets\fP, \fB--line-offsets\fP, or \fB--output\fP is set. By
default, output is not coloured. The value for the \fB--colour\fP option (which
is optional, see above) may be "never", "always", or "auto". In the latter
case, colouring happens only if the standard output is connected to a terminal.
More resources are used when colouring is enabled, because \fBpcre2grep\fP has
to search for all possible matches in a line, not just one, in order to colour
them all.
.sp
The colour that is used can be specified by setting one of the environment
variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, PCREGREP_COLOUR, or
PCREGREP_COLOR, which are checked in that order. If none of these are set,
\fBpcre2grep\fP looks for GREP_COLORS or GREP_COLOR (in that order). The value
of the variable should be a string of two numbers, separated by a semicolon,
except in the case of GREP_COLORS, which must start with "ms=" or "mt="
followed by two semicolon-separated colours, terminated by the end of the
string or by a colon. If GREP_COLORS does not start with "ms=" or "mt=" it is
ignored, and GREP_COLOR is checked.
.sp
If the string obtained from one of the above variables contains any characters
other than semicolon or digits, the setting is ignored and the default colour
is used. The string is copied directly into the control string for setting
colour on a terminal, so it is your responsibility to ensure that the values
make sense. If no relevant environment variable is set, the default is "1;31",
which gives red.
.TP
\fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP
If an input path is not a regular file or a directory, "action" specifies how
it is to be processed. Valid values are "read" (the default) or "skip"
(silently skip the path).
.TP
\fB-d\fP \fIaction\fP, \fB--directories=\fP\fIaction\fP
If an input path is a directory, "action" specifies how it is to be processed.
Valid values are "read" (the default in non-Windows environments, for
compatibility with GNU grep), "recurse" (equivalent to the \fB-r\fP option), or
"skip" (silently skip the path, the default in Windows environments). In the
"read" case, directories are read as if they were ordinary files. In some
operating systems the effect of reading a directory like this is an immediate
end-of-file; in others it may provoke an error.
.TP
\fB--depth-limit\fP=\fInumber\fP
See \fB--match-limit\fP below.
.TP
\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP
Specify a pattern to be matched. This option can be used multiple times in
order to specify several patterns. It can also be used as a way of specifying a
single pattern that starts with a hyphen. When \fB-e\fP is used, no argument
pattern is taken from the command line; all arguments are treated as file
names. There is no limit to the number of patterns. They are applied to each
line in the order in which they are defined.
.sp
If \fB-f\fP is used with \fB-e\fP, the command line patterns are matched first,
followed by the patterns from the file(s), independent of the order in which
these options are specified.
.TP
\fB--exclude\fP=\fIpattern\fP
Files (but not directories) whose names match the pattern are skipped without
being processed. This applies to all files, whether listed on the command line,
obtained from \fB--file-list\fP, or by scanning a directory. The pattern is a
PCRE2 regular expression, and is matched against the final component of the
file name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do
not apply to this pattern. The option may be given any number of times in order
to specify multiple patterns. If a file name matches both an \fB--include\fP
and an \fB--exclude\fP pattern, it is excluded. There is no short form for this
option.
.TP
\fB--exclude-from=\fP\fIfilename\fP
Treat each non-empty line of the file as the data for an \fB--exclude\fP
option. What constitutes a newline when reading the file is the operating
system's default. The \fB--newline\fP option has no effect on this option. This
option may be given more than once in order to specify a number of files to
read.
.TP
\fB--exclude-dir\fP=\fIpattern\fP
Directories whose names match the pattern are skipped without being processed,
whatever the setting of the \fB--recursive\fP option. This applies to all
directories, whether listed on the command line, obtained from
\fB--file-list\fP, or by scanning a parent directory. The pattern is a PCRE2
regular expression, and is matched against the final component of the directory
name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not
apply to this pattern. The option may be given any number of times in order to
specify more than one pattern. If a directory matches both \fB--include-dir\fP
and \fB--exclude-dir\fP, it is excluded. There is no short form for this
option.
.TP
\fB-F\fP, \fB--fixed-strings\fP
Interpret each data-matching pattern as a list of fixed strings, separated by
newlines, instead of as a regular expression. What constitutes a newline for
this purpose is controlled by the \fB--newline\fP option. The \fB-w\fP (match
as a word) and \fB-x\fP (match whole line) options can be used with \fB-F\fP.
They apply to each of the fixed strings. A line is selected if any of the fixed
strings are found in it (subject to \fB-w\fP or \fB-x\fP, if present). This
option applies only to the patterns that are matched against the contents of
files; it does not apply to patterns specified by any of the \fB--include\fP or
\fB--exclude\fP options.
.TP
\fB-f\fP \fIfilename\fP, \fB--file=\fP\fIfilename\fP
Read patterns from the file, one per line. As is the case with patterns on the
command line, no delimiters should be used. What constitutes a newline when
reading the file is the operating system's default interpretation of \en. The
\fB--newline\fP option has no effect on this option. Trailing white space is
removed from each line, and blank lines are ignored. An empty file contains no
patterns and therefore matches nothing. Patterns read from a file in this way
may contain binary zeros, which are treated as ordinary data characters.
.sp
If this option is given more than once, all the specified files are read. A
data line is output if any of the patterns match it. A file name can be given
as "-" to refer to the standard input. When \fB-f\fP is used, patterns
specified on the command line using \fB-e\fP may also be present; they are
matched before the file's patterns. However, no pattern is taken from the
command line; all arguments are treated as the names of paths to be searched.
.TP
\fB--file-list\fP=\fIfilename\fP
Read a list of files and/or directories that are to be scanned from the given
file, one per line. What constitutes a newline when reading the file is the
operating system's default. Trailing white space is removed from each line, and
blank lines are ignored. These paths are processed before any that are listed
on the command line. The file name can be given as "-" to refer to the standard
input. If \fB--file\fP and \fB--file-list\fP are both specified as "-",
patterns are read first. This is useful only when the standard input is a
terminal, from which further lines (the list of files) can be read after an
end-of-file indication. If this option is given more than once, all the
specified files are read.
.TP
\fB--file-offsets\fP
Instead of showing lines or parts of lines that match, show each match as an
offset from the start of the file and a length, separated by a comma. In this
mode, \fB--colour\fP has no effect, and no context is shown. That is, the
\fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is more than one
match in a line, each of them is shown separately. This option is mutually
exclusive with \fB--output\fP, \fB--line-offsets\fP, and \fB--only-matching\fP.
.TP
\fB-H\fP, \fB--with-filename\fP
Force the inclusion of the file name at the start of output lines when
searching a single file. The file name is not normally shown in this case.
By default, for matching lines, the file name is followed by a colon; for
context lines, a hyphen separator is used. The \fB-Z\fP option can be used to
change the terminator to a zero byte. If a line number is also being output,
it follows the file name. When the \fB-M\fP option causes a pattern to match
more than one line, only the first is preceded by the file name. This option
overrides any previous \fB-h\fP, \fB-l\fP, or \fB-L\fP options.
.TP
\fB-h\fP, \fB--no-filename\fP
Suppress the output file names when searching multiple files. File names are
normally shown when multiple files are searched. By default, for matching
lines, the file name is followed by a colon; for context lines, a hyphen
separator is used. The \fB-Z\fP option can be used to change the terminator to
a zero byte. If a line number is also being output, it follows the file name.
This option overrides any previous \fB-H\fP, \fB-L\fP, or \fB-l\fP options.
.TP
\fB--heap-limit\fP=\fInumber\fP
See \fB--match-limit\fP below.
.TP
\fB--help\fP
Output a help message, giving brief details of the command options and file
type support, and then exit. Anything else on the command line is
ignored.
.TP
\fB-I\fP
Ignore binary files. This is equivalent to
\fB--binary-files\fP=\fIwithout-match\fP.
.TP
\fB-i\fP, \fB--ignore-case\fP
Ignore upper/lower case distinctions during comparisons.
.TP
\fB--include\fP=\fIpattern\fP
If any \fB--include\fP patterns are specified, the only files that are
processed are those whose names match one of the patterns and do not match an
\fB--exclude\fP pattern. This option does not affect directories, but it
applies to all files, whether listed on the command line, obtained from
\fB--file-list\fP, or by scanning a directory. The pattern is a PCRE2 regular
expression, and is matched against the final component of the file name, not
the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not apply to
this pattern. The option may be given any number of times. If a file name
matches both an \fB--include\fP and an \fB--exclude\fP pattern, it is excluded.
There is no short form for this option.
.TP
\fB--include-from=\fP\fIfilename\fP
Treat each non-empty line of the file as the data for an \fB--include\fP
option. What constitutes a newline for this purpose is the operating system's
default. The \fB--newline\fP option has no effect on this option. This option
may be given any number of times; all the files are read.
.TP
\fB--include-dir\fP=\fIpattern\fP
If any \fB--include-dir\fP patterns are specified, the only directories that
are processed are those whose names match one of the patterns and do not match
an \fB--exclude-dir\fP pattern. This applies to all directories, whether listed
on the command line, obtained from \fB--file-list\fP, or by scanning a parent
directory. The pattern is a PCRE2 regular expression, and is matched against
the final component of the directory name, not the entire path. The \fB-F\fP,
\fB-w\fP, and \fB-x\fP options do not apply to this pattern. The option may be
given any number of times. If a directory matches both \fB--include-dir\fP and
\fB--exclude-dir\fP, it is excluded. There is no short form for this option.
.TP
\fB-L\fP, \fB--files-without-match\fP
Instead of outputting lines from the files, just output the names of the files
that do not contain any lines that would have been output. Each file name is
output once, on a separate line by default, but if the \fB-Z\fP option is set,
they are separated by zero bytes instead of newlines. This option overrides any
previous \fB-H\fP, \fB-h\fP, or \fB-l\fP options.
.TP
\fB-l\fP, \fB--files-with-matches\fP
Instead of outputting lines from the files, just output the names of the files
containing lines that would have been output. Each file name is output once, on
a separate line, but if the \fB-Z\fP option is set, they are separated by zero
bytes instead of newlines. Searching normally stops as soon as a matching line
is found in a file. However, if the \fB-c\fP (count) option is also used,
matching continues in order to obtain the correct count, and those files that
have at least one match are listed along with their counts. Using this option
with \fB-c\fP is a way of suppressing the listing of files with no matches that
occurs with \fB-c\fP on its own. This option overrides any previous \fB-H\fP,
\fB-h\fP, or \fB-L\fP options.
.TP
\fB--label\fP=\fIname\fP
This option supplies a name to be used for the standard input when file names
are being output. If not supplied, "(standard input)" is used. There is no
short form for this option.
.TP
\fB--line-buffered\fP
When this option is given, non-compressed input is read and processed line by
line, and the output is flushed after each write. By default, input is read in
large chunks, unless \fBpcre2grep\fP can determine that it is reading from a
terminal, which is currently possible only in Unix-like environments or
Windows. Output to terminal is normally automatically flushed by the operating
system. This option can be useful when the input or output is attached to a
pipe and you do not want \fBpcre2grep\fP to buffer up large amounts of data.
However, its use will affect performance, and the \fB-M\fP (multiline) option
ceases to work. When input is from a compressed .gz or .bz2 file,
\fB--line-buffered\fP is ignored.
.TP
\fB--line-offsets\fP
Instead of showing lines or parts of lines that match, show each match as a
line number, the offset from the start of the line, and a length. The line
number is terminated by a colon (as usual; see the \fB-n\fP option), and the
offset and length are separated by a comma. In this mode, \fB--colour\fP has no
effect, and no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP
options are ignored. If there is more than one match in a line, each of them is
shown separately. This option is mutually exclusive with \fB--output\fP,
\fB--file-offsets\fP, and \fB--only-matching\fP.
.TP
\fB--locale\fP=\fIlocale-name\fP
This option specifies a locale to be used for pattern matching. It overrides
the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no
locale is specified, the PCRE2 library's default (usually the "C" locale) is
used. There is no short form for this option.
.TP
\fB-M\fP, \fB--multiline\fP
Allow patterns to match more than one line. When this option is set, the PCRE2
library is called in "multiline" mode. This allows a matched string to extend
past the end of a line and continue on one or more subsequent lines. Patterns
used with \fB-M\fP may usefully contain literal newline characters and internal
occurrences of ^ and $ characters. The output for a successful match may
consist of more than one line. The first line is the line in which the match
started, and the last line is the line in which the match ended. If the matched
string ends with a newline sequence, the output ends at the end of that line.
If \fB-v\fP is set, none of the lines in a multi-line match are output. Once a
match has been handled, scanning restarts at the beginning of the line after
the one in which the match ended.
.sp
The newline sequence that separates multiple lines must be matched as part of
the pattern. For example, to find the phrase "regular expression" in a file
where "regular" might be at the end of a line and "expression" at the start of
the next line, you could use this command:
.sp
pcre2grep -M 'regular\es+expression' <file>
.sp
The \es escape sequence matches any white space character, including newlines,
and is followed by + so as to match trailing white space on the first line as
well as possibly handling a two-character newline sequence.
.sp
There is a limit to the number of lines that can be matched, imposed by the way
that \fBpcre2grep\fP buffers the input file as it scans it. With a sufficiently
large processing buffer, this should not be a problem, but the \fB-M\fP option
does not work when input is read line by line (see \fB--line-buffered\fP.)
.TP
\fB-m\fP \fInumber\fP, \fB--max-count\fP=\fInumber\fP
Stop processing after finding \fInumber\fP matching lines, or non-matching
lines if \fB-v\fP is also set. Any trailing context lines are output after the
final match. In multiline mode, each multiline match counts as just one line
for this purpose. If this limit is reached when reading the standard input from
a regular file, the file is left positioned just after the last matching line.
If \fB-c\fP is also set, the count that is output is never greater than
\fInumber\fP. This option has no effect if used with \fB-L\fP, \fB-l\fP, or
\fB-q\fP, or when just checking for a match in a binary file.
.TP
\fB--match-limit\fP=\fInumber\fP
Processing some regular expression patterns may take a very long time to search
for all possible matching strings. Others may require a very large amount of
memory. There are three options that set resource limits for matching.
.sp
The \fB--match-limit\fP option provides a means of limiting computing resource
usage when processing patterns that are not going to match, but which have a
very large number of possibilities in their search trees. The classic example
is a pattern that uses nested unlimited repeats. Internally, PCRE2 has a
counter that is incremented each time around its main processing loop. If the
value set by \fB--match-limit\fP is reached, an error occurs.
.sp
The \fB--heap-limit\fP option specifies, as a number of kibibytes (units of
1024 bytes), the maximum amount of heap memory that may be used for matching.
.sp
The \fB--depth-limit\fP option limits the depth of nested backtracking points,
which indirectly limits the amount of memory that is used. The amount of memory
needed for each backtracking point depends on the number of capturing
parentheses in the pattern, so the amount of memory that is used before this
limit acts varies from pattern to pattern. This limit is of use only if it is
set smaller than \fB--match-limit\fP.
.sp
There are no short forms for these options. The default limits can be set
when the PCRE2 library is compiled; if they are not specified, the defaults
are very large and so effectively unlimited.
.TP
\fB--max-buffer-size\fP=\fInumber\fP
This limits the expansion of the processing buffer, whose initial size can be
set by \fB--buffer-size\fP. The maximum buffer size is silently forced to be no
smaller than the starting buffer size.
.TP
\fB-N\fP \fInewline-type\fP, \fB--newline\fP=\fInewline-type\fP
Six different conventions for indicating the ends of lines in scanned files are
supported. For example:
.sp
pcre2grep -N CRLF 'some pattern' <file>
.sp
The newline type may be specified in upper, lower, or mixed case. If the
newline type is NUL, lines are separated by binary zero characters. The other
types are the single-character sequences CR (carriage return) and LF
(linefeed), the two-character sequence CRLF, an "anycrlf" type, which
recognizes any of the preceding three types, and an "any" type, for which any
Unicode line ending sequence is assumed to end a line. The Unicode sequences
are the three just mentioned, plus VT (vertical tab, U+000B), FF (form feed,
U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
(paragraph separator, U+2029).
.sp
When the PCRE2 library is built, a default line-ending sequence is specified.
This is normally the standard sequence for the operating system. Unless
otherwise specified by this option, \fBpcre2grep\fP uses the library's default.
.sp
This option makes it possible to use \fBpcre2grep\fP to scan files that have
come from other environments without having to modify their line endings. If
the data that is being scanned does not agree with the convention set by this
option, \fBpcre2grep\fP may behave in strange ways. Note that this option does
not apply to files specified by the \fB-f\fP, \fB--exclude-from\fP, or
\fB--include-from\fP options, which are expected to use the operating system's
standard newline sequence.
.TP
\fB-n\fP, \fB--line-number\fP
Precede each output line by its line number in the file, followed by a colon
for matching lines or a hyphen for context lines. If the file name is also
being output, it precedes the line number. When the \fB-M\fP option causes a
pattern to match more than one line, only the first is preceded by its line
number. This option is forced if \fB--line-offsets\fP is used.
.TP
\fB--no-jit\fP
If the PCRE2 library is built with support for just-in-time compiling (which
speeds up matching), \fBpcre2grep\fP automatically makes use of this, unless it
was explicitly disabled at build time. This option can be used to disable the
use of JIT at run time. It is provided for testing and working round problems.
It should never be needed in normal use.
.TP
\fB-O\fP \fItext\fP, \fB--output\fP=\fItext\fP
When there is a match, instead of outputting the line that matched, output just
the text specified in this option, followed by an operating-system standard
newline. In this mode, \fB--colour\fP has no effect, and no context is shown.
That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. The
\fB--newline\fP option has no effect on this option, which is mutually
exclusive with \fB--only-matching\fP, \fB--file-offsets\fP, and
\fB--line-offsets\fP. However, like \fB--only-matching\fP, if there is more
than one match in a line, each of them causes a line of output.
.sp
Escape sequences starting with a dollar character may be used to insert the
contents of the matched part of the line and/or captured substrings into the
text.
.sp
$<digits> or ${<digits>} is replaced by the captured substring of the given
decimal number; zero substitutes the whole match. If the number is greater than
the number of capturing substrings, or if the capture is unset, the replacement
is empty.
.sp
$a is replaced by bell; $b by backspace; $e by escape; $f by form feed; $n by
newline; $r by carriage return; $t by tab; $v by vertical tab.
.sp
$o<digits> or $o{<digits>} is replaced by the character whose code point is the
given octal number. In the first form, up to three octal digits are processed.
When more digits are needed in Unicode mode to specify a wide character, the
second form must be used.
.sp
$x<digits> or $x{<digits>} is replaced by the character represented by the
given hexadecimal number. In the first form, up to two hexadecimal digits are
processed. When more digits are needed in Unicode mode to specify a wide
character, the second form must be used.
.sp
Any other character is substituted by itself. In particular, $$ is replaced by
a single dollar.
.TP
\fB-o\fP, \fB--only-matching\fP
Show only the part of the line that matched a pattern instead of the whole
line. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and
\fB-C\fP options are ignored. If there is more than one match in a line, each
of them is shown separately, on a separate line of output. If \fB-o\fP is
combined with \fB-v\fP (invert the sense of the match to find non-matching
lines), no output is generated, but the return code is set appropriately. If
the matched portion of the line is empty, nothing is output unless the file
name or line number are being printed, in which case they are shown on an
otherwise empty line. This option is mutually exclusive with \fB--output\fP,
\fB--file-offsets\fP and \fB--line-offsets\fP.
.TP
\fB-o\fP\fInumber\fP, \fB--only-matching\fP=\fInumber\fP
Show only the part of the line that matched the capturing parentheses of the
given number. Up to 50 capturing parentheses are supported by default. This
limit can be changed via the \fB--om-capture\fP option. A pattern may contain
any number of capturing parentheses, but only those whose number is within the
limit can be accessed by \fB-o\fP. An error occurs if the number specified by
\fB-o\fP is greater than the limit.
.sp
-o0 is the same as \fB-o\fP without a number. Because these options can be
given without an argument (see above), if an argument is present, it must be
given in the same shell item, for example, -o3 or --only-matching=2. The
comments given for the non-argument case above also apply to this option. If
the specified capturing parentheses do not exist in the pattern, or were not
set in the match, nothing is output unless the file name or line number are
being output.
.sp
If this option is given multiple times, multiple substrings are output for each
match, in the order the options are given, and all on one line. For example,
-o3 -o1 -o3 causes the substrings matched by capturing parentheses 3 and 1 and
then 3 again to be output. By default, there is no separator (but see the next
but one option).
.TP
\fB--om-capture\fP=\fInumber\fP
Set the number of capturing parentheses that can be accessed by \fB-o\fP. The
default is 50.
.TP
\fB--om-separator\fP=\fItext\fP
Specify a separating string for multiple occurrences of \fB-o\fP. The default
is an empty string. Separating strings are never coloured.
.TP
\fB-q\fP, \fB--quiet\fP
Work quietly, that is, display nothing except error messages. The exit
status indicates whether or not any matches were found.
.TP
\fB-r\fP, \fB--recursive\fP
If any given path is a directory, recursively scan the files it contains,
taking note of any \fB--include\fP and \fB--exclude\fP settings. By default, a
directory is read as a normal file; in some operating systems this gives an
immediate end-of-file. This option is a shorthand for setting the \fB-d\fP
option to "recurse".
.TP
\fB--recursion-limit\fP=\fInumber\fP
This is an obsolete synonym for \fB--depth-limit\fP. See \fB--match-limit\fP
above for details.
.TP
\fB-s\fP, \fB--no-messages\fP
Suppress error messages about non-existent or unreadable files. Such files are
quietly skipped. However, the return code is still 2, even if matches were
found in other files.
.TP
\fB-t\fP, \fB--total-count\fP
This option is useful when scanning more than one file. If used on its own,
\fB-t\fP suppresses all output except for a grand total number of matching
lines (or non-matching lines if \fB-v\fP is used) in all the files. If \fB-t\fP
is used with \fB-c\fP, a grand total is output except when the previous output
is just one line. In other words, it is not output when just one file's count
is listed. If file names are being output, the grand total is preceded by
"TOTAL:". Otherwise, it appears as just another number. The \fB-t\fP option is
ignored when used with \fB-L\fP (list files without matches), because the grand
total would always be zero.
.TP
\fB-u\fP, \fB--utf\fP
Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
with UTF-8 support. All patterns (including those for any \fB--exclude\fP and
\fB--include\fP options) and all lines that are scanned must be valid strings
of UTF-8 characters. If an invalid UTF-8 string is encountered, an error
occurs.
.TP
\fB-U\fP, \fB--utf-allow-invalid\fP
As \fB--utf\fP, but in addition subject lines may contain invalid UTF-8 code
unit sequences. These can never form part of any pattern match. Patterns
themselves, however, must still be valid UTF-8 strings. This facility allows
valid UTF-8 strings to be sought within arbitrary byte sequences in executable
or other binary files. For more details about matching in non-valid UTF-8
strings, see the
.\" HREF
\fBpcre2unicode\fP(3)
.\"
documentation.
.TP
\fB-V\fP, \fB--version\fP
Write the version numbers of \fBpcre2grep\fP and the PCRE2 library to the
standard output and then exit. Anything else on the command line is
ignored.
.TP
\fB-v\fP, \fB--invert-match\fP
Invert the sense of the match, so that lines which do \fInot\fP match any of
the patterns are the ones that are found. When this option is set, options such
as \fB--only-matching\fP and \fB--output\fP, which specify parts of a match
that are to be output, are ignored.
.TP
\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP
Force the patterns only to match "words". That is, there must be a word
boundary at the start and end of each matched string. This is equivalent to
having "\eb(?:" at the start of each pattern, and ")\eb" at the end. This
option applies only to the patterns that are matched against the contents of
files; it does not apply to patterns specified by any of the \fB--include\fP or
\fB--exclude\fP options.
.TP
\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP
Force the patterns to start matching only at the beginnings of lines, and in
addition, require them to match entire lines. In multiline mode the match may
be more than one line. This is equivalent to having "^(?:" at the start of each
pattern and ")$" at the end. This option applies only to the patterns that are
matched against the contents of files; it does not apply to patterns specified
by any of the \fB--include\fP or \fB--exclude\fP options.
.TP
\fB-Z\fP, \fB--null\fP
Terminate files names in the regular output with a zero byte (the NUL
character) instead of what would normally appear. This is useful when file
names contain unusual characters such as colons, hyphens, or even newlines. The
option does not apply to file names in error messages.
.
.
.SH "ENVIRONMENT VARIABLES"
.rs
.sp
The environment variables \fBLC_ALL\fP and \fBLC_CTYPE\fP are examined, in that
order, for a locale. The first one that is set is used. This can be overridden
by the \fB--locale\fP option. If no locale is set, the PCRE2 library's default
(usually the "C" locale) is used.
.
.
.SH "NEWLINES"
.rs
.sp
The \fB-N\fP (\fB--newline\fP) option allows \fBpcre2grep\fP to scan files with
newline conventions that differ from the default. This option affects only the
way scanned files are processed. It does not affect the interpretation of files
specified by the \fB-f\fP, \fB--file-list\fP, \fB--exclude-from\fP, or
\fB--include-from\fP options.
.P
Any parts of the scanned input files that are written to the standard output
are copied with whatever newline sequences they have in the input. However, if
the final line of a file is output, and it does not end with a newline
sequence, a newline sequence is added. If the newline setting is CR, LF, CRLF
or NUL, that line ending is output; for the other settings (ANYCRLF or ANY) a
single NL is used.
.P
The newline setting does not affect the way in which \fBpcre2grep\fP writes
newlines in informational messages to the standard output and error streams.
Under Windows, the standard output is set to be binary, so that "\er\en" at the
ends of output lines that are copied from the input is not converted to
"\er\er\en" by the C I/O library. This means that any messages written to the
standard output must end with "\er\en". For all other operating systems, and
for all messages to the standard error stream, "\en" is used.
.
.
.SH "OPTIONS COMPATIBILITY"
.rs
.sp
Many of the short and long forms of \fBpcre2grep\fP's options are the same
as in the GNU \fBgrep\fP program. Any long option of the form
\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP
(PCRE2 terminology). However, the \fB--depth-limit\fP, \fB--file-list\fP,
\fB--file-offsets\fP, \fB--heap-limit\fP, \fB--include-dir\fP,
\fB--line-offsets\fP, \fB--locale\fP, \fB--match-limit\fP, \fB-M\fP,
\fB--multiline\fP, \fB-N\fP, \fB--newline\fP, \fB--om-separator\fP,
\fB--output\fP, \fB-u\fP, \fB--utf\fP, \fB-U\fP, and \fB--utf-allow-invalid\fP
options are specific to \fBpcre2grep\fP, as is the use of the
\fB--only-matching\fP option with a capturing parentheses number.
.P
Although most of the common options work the same way, a few are different in
\fBpcre2grep\fP. For example, the \fB--include\fP option's argument is a glob
for GNU \fBgrep\fP, but a regular expression for \fBpcre2grep\fP. If both the
\fB-c\fP and \fB-l\fP options are given, GNU grep lists only file names,
without counts, but \fBpcre2grep\fP gives the counts as well.
.
.
.SH "OPTIONS WITH DATA"
.rs
.sp
There are four different ways in which an option with data can be specified.
If a short form option is used, the data may follow immediately, or (with one
exception) in the next command line item. For example:
.sp
-f/some/file
-f /some/file
.sp
The exception is the \fB-o\fP option, which may appear with or without data.
Because of this, if data is present, it must follow immediately in the same
item, for example -o3.
.P
If a long form option is used, the data may appear in the same command line
item, separated by an equals character, or (with two exceptions) it may appear
in the next command line item. For example:
.sp
--file=/some/file
--file /some/file
.sp
Note, however, that if you want to supply a file name beginning with ~ as data
in a shell command, and have the shell expand ~ to a home directory, you must
separate the file name from the option, because the shell does not treat ~
specially unless it is at the start of an item.
.P
The exceptions to the above are the \fB--colour\fP (or \fB--color\fP) and
\fB--only-matching\fP options, for which the data is optional. If one of these
options does have data, it must be given in the first form, using an equals
character. Otherwise \fBpcre2grep\fP will assume that it has no data.
.
.
.SH "USING PCRE2'S CALLOUT FACILITY"
.rs
.sp
\fBpcre2grep\fP has, by default, support for calling external programs or
scripts or echoing specific strings during matching by making use of PCRE2's
callout facility. However, this support can be completely or partially disabled
when \fBpcre2grep\fP is built. You can find out whether your binary has support
for callouts by running it with the \fB--help\fP option. If callout support is
completely disabled, all callouts in patterns are ignored by \fBpcre2grep\fP.
If the facility is partially disabled, calling external programs is not
supported, and callouts that request it are ignored.
.P
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argument is
either a number or a quoted string (see the
.\" HREF
\fBpcre2callout\fP
.\"
documentation for details). Numbered callouts are ignored by \fBpcre2grep\fP;
only callouts with string arguments are useful.
.
.
.SS "Echoing a specific string"
.rs
.sp
Starting the callout string with a pipe character invokes an echoing facility
that avoids calling an external program or script. This facility is always
available, provided that callouts were not completely disabled when
\fBpcre2grep\fP was built. The rest of the callout string is processed as a
zero-terminated string, which means it should not contain any internal binary
zeros. It is written to the output, having first been passed through the same
escape processing as text from the \fB--output\fP (\fB-O\fP) option (see
above). However, $0 cannot be used to insert a matched substring because the
match is still in progress. Instead, the single character '0' is inserted. Any
syntax errors in the string (for example, a dollar not followed by another
character) causes the callout to be ignored. No terminator is added to the
output string, so if you want a newline, you must include it explicitly using
the escape $n. For example:
.sp
pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' <some file>
.sp
Matching continues normally after the string is output. If you want to see only
the callout output but not any output from an actual match, you should end the
pattern with (*FAIL).
.
.
.SS "Calling external programs or scripts"
.rs
.sp
This facility can be independently disabled when \fBpcre2grep\fP is built. It
is supported for Windows, where a call to \fB_spawnvp()\fP is used, for VMS,
where \fBlib$spawn()\fP is used, and for any Unix-like environment where
\fBfork()\fP and \fBexecv()\fP are available.
.P
If the callout string does not start with a pipe (vertical bar) character, it
is parsed into a list of substrings separated by pipe characters. The first
substring must be an executable name, with the following substrings specifying
arguments:
.sp
executable_name|arg1|arg2|...
.sp
Any substring (including the executable name) may contain escape sequences
started by a dollar character. These are the same as for the \fB--output\fP
(\fB-O\fP) option documented above, except that $0 cannot insert the matched
string because the match is still in progress. Instead, the character '0'
is inserted. If you need a literal dollar or pipe character in any
substring, use $$ or $| respectively. Here is an example:
.sp
echo -e "abcde\en12345" | pcre2grep \e
'(?x)(.)(..(.))
(?C"/bin/echo|Arg1: [$1] [$2] [$3]|Arg2: $|${1}$| ($4)")()' -
.sp
Output:
.sp
Arg1: [a] [bcd] [d] Arg2: |a| ()
abcde
Arg1: [1] [234] [4] Arg2: |1| ()
12345
.sp
The parameters for the system call that is used to run the program or script
are zero-terminated strings. This means that binary zero characters in the
callout argument will cause premature termination of their substrings, and
therefore should not be present. Any syntax errors in the string (for example,
a dollar not followed by another character) causes the callout to be ignored.
If running the program fails for any reason (including the non-existence of the
executable), a local matching failure occurs and the matcher backtracks in the
normal way.
.
.
.SH "MATCHING ERRORS"
.rs
.sp
It is possible to supply a regular expression that takes a very long time to
fail to match certain lines. Such patterns normally involve nested indefinite
repeats, for example: (a+)*\ed when matched against a line of a's with no final
digit. The PCRE2 matching function has a resource limit that causes it to abort
in these circumstances. If this happens, \fBpcre2grep\fP outputs an error
message and the line that caused the problem to the standard error stream. If
there are more than 20 such errors, \fBpcre2grep\fP gives up.
.P
The \fB--match-limit\fP option of \fBpcre2grep\fP can be used to set the
overall resource limit. There are also other limits that affect the amount of
memory used during matching; see the discussion of \fB--heap-limit\fP and
\fB--depth-limit\fP above.
.
.
.SH DIAGNOSTICS
.rs
.sp
Exit status is 0 if any matches were found, 1 if no matches were found, and 2
for syntax errors, overlong lines, non-existent or inaccessible files (even if
matches were found in other files) or too many matching errors. Using the
\fB-s\fP option to suppress error messages about inaccessible files does not
affect the return code.
.P
When run under VMS, the return code is placed in the symbol PCRE2GREP_RC
because VMS does not distinguish between exit(0) and exit(1).
.
.
.SH "SEE ALSO"
.rs
.sp
\fBpcre2pattern\fP(3), \fBpcre2syntax\fP(3), \fBpcre2callout\fP(3),
\fBpcre2unicode\fP(3).
.
.
.SH AUTHOR
.rs
.sp
.nf
Philip Hazel
Retired from University Computing Service
Cambridge, England.
.fi
.
.
.SH REVISION
.rs
.sp
.nf
Last updated: 21 November 2022
Copyright (c) 1997-2022 University of Cambridge.
.fi

4577
third_party/pcre/pcre2grep.c vendored Normal file
View file

File diff suppressed because it is too large Load diff

329
third_party/pcre/pcre2posix.3 vendored Normal file
View file

@ -0,0 +1,329 @@
.TH PCRE2POSIX 3 "26 April 2021" "PCRE2 10.37"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "SYNOPSIS"
.rs
.sp
.B #include <pcre2posix.h>
.PP
.nf
.B int pcre2_regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP,
.B " int \fIcflags\fP);"
.sp
.B int pcre2_regexec(const regex_t *\fIpreg\fP, const char *\fIstring\fP,
.B " size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP);"
.sp
.B "size_t pcre2_regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP,"
.B " char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP);"
.sp
.B void pcre2_regfree(regex_t *\fIpreg\fP);
.fi
.
.SH DESCRIPTION
.rs
.sp
This set of functions provides a POSIX-style API for the PCRE2 regular
expression 8-bit library. There are no POSIX-style wrappers for PCRE2's 16-bit
and 32-bit libraries. See the
.\" HREF
\fBpcre2api\fP
.\"
documentation for a description of PCRE2's native API, which contains much
additional functionality.
.P
The functions described here are wrapper functions that ultimately call the
PCRE2 native API. Their prototypes are defined in the \fBpcre2posix.h\fP header
file, and they all have unique names starting with \fBpcre2_\fP. However, the
\fBpcre2posix.h\fP header also contains macro definitions that convert the
standard POSIX names such \fBregcomp()\fP into \fBpcre2_regcomp()\fP etc. This
means that a program can use the usual POSIX names without running the risk of
accidentally linking with POSIX functions from a different library.
.P
On Unix-like systems the PCRE2 POSIX library is called \fBlibpcre2-posix\fP, so
can be accessed by adding \fB-lpcre2-posix\fP to the command for linking an
application. Because the POSIX functions call the native ones, it is also
necessary to add \fB-lpcre2-8\fP.
.P
Although they were not defined as protypes in \fBpcre2posix.h\fP, releases
10.33 to 10.36 of the library contained functions with the POSIX names
\fBregcomp()\fP etc. These simply passed their arguments to the PCRE2
functions. These functions were provided for backwards compatibility with
earlier versions of PCRE2, which had only POSIX names. However, this has proved
troublesome in situations where a program links with several libraries, some of
which use PCRE2's POSIX interface while others use the real POSIX functions.
For this reason, the POSIX names have been removed since release 10.37.
.P
Calling the header file \fBpcre2posix.h\fP avoids any conflict with other POSIX
libraries. It can, of course, be renamed or aliased as \fBregex.h\fP, which is
the "correct" name, if there is no clash. It provides two structure types,
\fIregex_t\fP for compiled internal forms, and \fIregmatch_t\fP for returning
captured substrings. It also defines some constants whose names start with
"REG_"; these are used for setting options and identifying error codes.
.
.
.SH "USING THE POSIX FUNCTIONS"
.rs
.sp
Those POSIX option bits that can reasonably be mapped to PCRE2 native options
have been implemented. In addition, the option REG_EXTENDED is defined with the
value zero. This has no effect, but since programs that are written to the
POSIX interface often use it, this makes it easier to slot in PCRE2 as a
replacement library. Other POSIX options are not even defined.
.P
There are also some options that are not defined by POSIX. These have been
added at the request of users who want to make use of certain PCRE2-specific
features via the POSIX calling interface or to add BSD or GNU functionality.
.P
When PCRE2 is called via these functions, it is only the API that is POSIX-like
in style. The syntax and semantics of the regular expressions themselves are
still those of Perl, subject to the setting of various PCRE2 options, as
described below. "POSIX-like in style" means that the API approximates to the
POSIX definition; it is not fully POSIX-compatible, and in multi-unit encoding
domains it is probably even less compatible.
.P
The descriptions below use the actual names of the functions, but, as described
above, the standard POSIX names (without the \fBpcre2_\fP prefix) may also be
used.
.
.
.SH "COMPILING A PATTERN"
.rs
.sp
The function \fBpcre2_regcomp()\fP is called to compile a pattern into an
internal form. By default, the pattern is a C string terminated by a binary
zero (but see REG_PEND below). The \fIpreg\fP argument is a pointer to a
\fBregex_t\fP structure that is used as a base for storing information about
the compiled regular expression. (It is also used for input when REG_PEND is
set.)
.P
The argument \fIcflags\fP is either zero, or contains one or more of the bits
defined by the following macros:
.sp
REG_DOTALL
.sp
The PCRE2_DOTALL option is set when the regular expression is passed for
compilation to the native function. Note that REG_DOTALL is not part of the
POSIX standard.
.sp
REG_ICASE
.sp
The PCRE2_CASELESS option is set when the regular expression is passed for
compilation to the native function.
.sp
REG_NEWLINE
.sp
The PCRE2_MULTILINE option is set when the regular expression is passed for
compilation to the native function. Note that this does \fInot\fP mimic the
defined POSIX behaviour for REG_NEWLINE (see the following section).
.sp
REG_NOSPEC
.sp
The PCRE2_LITERAL option is set when the regular expression is passed for
compilation to the native function. This disables all meta characters in the
pattern, causing it to be treated as a literal string. The only other options
that are allowed with REG_NOSPEC are REG_ICASE, REG_NOSUB, REG_PEND, and
REG_UTF. Note that REG_NOSPEC is not part of the POSIX standard.
.sp
REG_NOSUB
.sp
When a pattern that is compiled with this flag is passed to
\fBpcre2_regexec()\fP for matching, the \fInmatch\fP and \fIpmatch\fP arguments
are ignored, and no captured strings are returned. Versions of the PCRE library
prior to 10.22 used to set the PCRE2_NO_AUTO_CAPTURE compile option, but this
no longer happens because it disables the use of backreferences.
.sp
REG_PEND
.sp
If this option is set, the \fBreg_endp\fP field in the \fIpreg\fP structure
(which has the type const char *) must be set to point to the character beyond
the end of the pattern before calling \fBpcre2_regcomp()\fP. The pattern itself
may now contain binary zeros, which are treated as data characters. Without
REG_PEND, a binary zero terminates the pattern and the \fBre_endp\fP field is
ignored. This is a GNU extension to the POSIX standard and should be used with
caution in software intended to be portable to other systems.
.sp
REG_UCP
.sp
The PCRE2_UCP option is set when the regular expression is passed for
compilation to the native function. This causes PCRE2 to use Unicode properties
when matchine \ed, \ew, etc., instead of just recognizing ASCII values. Note
that REG_UCP is not part of the POSIX standard.
.sp
REG_UNGREEDY
.sp
The PCRE2_UNGREEDY option is set when the regular expression is passed for
compilation to the native function. Note that REG_UNGREEDY is not part of the
POSIX standard.
.sp
REG_UTF
.sp
The PCRE2_UTF option is set when the regular expression is passed for
compilation to the native function. This causes the pattern itself and all data
strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF
is not part of the POSIX standard.
.P
In the absence of these flags, no options are passed to the native function.
This means the the regex is compiled with PCRE2 default semantics. In
particular, the way it handles newline characters in the subject string is the
Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only
\fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way
newlines are matched by the dot metacharacter (they are not) or by a negative
class such as [^a] (they are).
.P
The yield of \fBpcre2_regcomp()\fP is zero on success, and non-zero otherwise.
The \fIpreg\fP structure is filled in on success, and one other member of the
structure (as well as \fIre_endp\fP) is public: \fIre_nsub\fP contains the
number of capturing subpatterns in the regular expression. Various error codes
are defined in the header file.
.P
NOTE: If the yield of \fBpcre2_regcomp()\fP is non-zero, you must not attempt
to use the contents of the \fIpreg\fP structure. If, for example, you pass it
to \fBpcre2_regexec()\fP, the result is undefined and your program is likely to
crash.
.
.
.SH "MATCHING NEWLINE CHARACTERS"
.rs
.sp
This area is not simple, because POSIX and Perl take different views of things.
It is not possible to get PCRE2 to obey POSIX semantics, but then PCRE2 was
never intended to be a POSIX engine. The following table lists the different
possibilities for matching newline characters in Perl and PCRE2:
.sp
Default Change with
.sp
. matches newline no PCRE2_DOTALL
newline matches [^a] yes not changeable
$ matches \en at end yes PCRE2_DOLLAR_ENDONLY
$ matches \en in middle no PCRE2_MULTILINE
^ matches \en in middle no PCRE2_MULTILINE
.sp
This is the equivalent table for a POSIX-compatible pattern matcher:
.sp
Default Change with
.sp
. matches newline yes REG_NEWLINE
newline matches [^a] yes REG_NEWLINE
$ matches \en at end no REG_NEWLINE
$ matches \en in middle no REG_NEWLINE
^ matches \en in middle no REG_NEWLINE
.sp
This behaviour is not what happens when PCRE2 is called via its POSIX
API. By default, PCRE2's behaviour is the same as Perl's, except that there is
no equivalent for PCRE2_DOLLAR_ENDONLY in Perl. In both PCRE2 and Perl, there
is no way to stop newline from matching [^a].
.P
Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and
PCRE2_DOLLAR_ENDONLY when calling \fBpcre2_compile()\fP directly, but there is
no way to make PCRE2 behave exactly as for the REG_NEWLINE action. When using
the POSIX API, passing REG_NEWLINE to PCRE2's \fBpcre2_regcomp()\fP function
causes PCRE2_MULTILINE to be passed to \fBpcre2_compile()\fP, and REG_DOTALL
passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY.
.
.
.SH "MATCHING A PATTERN"
.rs
.sp
The function \fBpcre2_regexec()\fP is called to match a compiled pattern
\fIpreg\fP against a given \fIstring\fP, which is by default terminated by a
zero byte (but see REG_STARTEND below), subject to the options in \fIeflags\fP.
These can be:
.sp
REG_NOTBOL
.sp
The PCRE2_NOTBOL option is set when calling the underlying PCRE2 matching
function.
.sp
REG_NOTEMPTY
.sp
The PCRE2_NOTEMPTY option is set when calling the underlying PCRE2 matching
function. Note that REG_NOTEMPTY is not part of the POSIX standard. However,
setting this option can give more POSIX-like behaviour in some situations.
.sp
REG_NOTEOL
.sp
The PCRE2_NOTEOL option is set when calling the underlying PCRE2 matching
function.
.sp
REG_STARTEND
.sp
When this option is set, the subject string starts at \fIstring\fP +
\fIpmatch[0].rm_so\fP and ends at \fIstring\fP + \fIpmatch[0].rm_eo\fP, which
should point to the first character beyond the string. There may be binary
zeros within the subject string, and indeed, using REG_STARTEND is the only
way to pass a subject string that contains a binary zero.
.P
Whatever the value of \fIpmatch[0].rm_so\fP, the offsets of the matched string
and any captured substrings are still given relative to the start of
\fIstring\fP itself. (Before PCRE2 release 10.30 these were given relative to
\fIstring\fP + \fIpmatch[0].rm_so\fP, but this differs from other
implementations.)
.P
This is a BSD extension, compatible with but not specified by IEEE Standard
1003.2 (POSIX.2), and should be used with caution in software intended to be
portable to other systems. Note that a non-zero \fIrm_so\fP does not imply
REG_NOTBOL; REG_STARTEND affects only the location and length of the string,
not how it is matched. Setting REG_STARTEND and passing \fIpmatch\fP as NULL
are mutually exclusive; the error REG_INVARG is returned.
.P
If the pattern was compiled with the REG_NOSUB flag, no data about any matched
strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of
\fBpcre2_regexec()\fP are ignored (except possibly as input for REG_STARTEND).
.P
The value of \fInmatch\fP may be zero, and the value \fIpmatch\fP may be NULL
(unless REG_STARTEND is set); in both these cases no data about any matched
strings is returned.
.P
Otherwise, the portion of the string that was matched, and also any captured
substrings, are returned via the \fIpmatch\fP argument, which points to an
array of \fInmatch\fP structures of type \fIregmatch_t\fP, containing the
members \fIrm_so\fP and \fIrm_eo\fP. These contain the byte offset to the first
character of each substring and the offset to the first character after the end
of each substring, respectively. The 0th element of the vector relates to the
entire portion of \fIstring\fP that was matched; subsequent elements relate to
the capturing subpatterns of the regular expression. Unused entries in the
array have both structure members set to -1.
.P
A successful match yields a zero return; various error codes are defined in the
header file, of which REG_NOMATCH is the "expected" failure code.
.
.
.SH "ERROR MESSAGES"
.rs
.sp
The \fBpcre2_regerror()\fP function maps a non-zero errorcode from either
\fBpcre2_regcomp()\fP or \fBpcre2_regexec()\fP to a printable message. If
\fIpreg\fP is not NULL, the error should have arisen from the use of that
structure. A message terminated by a binary zero is placed in \fIerrbuf\fP. If
the buffer is too short, only the first \fIerrbuf_size\fP - 1 characters of the
error message are used. The yield of the function is the size of buffer needed
to hold the whole message, including the terminating zero. This value is
greater than \fIerrbuf_size\fP if the message was truncated.
.
.
.SH MEMORY USAGE
.rs
.sp
Compiling a regular expression causes memory to be allocated and associated
with the \fIpreg\fP structure. The function \fBpcre2_regfree()\fP frees all
such memory, after which \fIpreg\fP may no longer be used as a compiled
expression.
.
.
.SH AUTHOR
.rs
.sp
.nf
Philip Hazel
University Computing Service
Cambridge, England.
.fi
.
.
.SH REVISION
.rs
.sp
.nf
Last updated: 26 April 2021
Copyright (c) 1997-2021 University of Cambridge.
.fi

435
third_party/pcre/pcre2posix.c vendored Normal file
View file

@ -0,0 +1,435 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module is a wrapper that provides a POSIX API to the underlying PCRE2
functions. The operative functions are called pcre2_regcomp(), etc., with
wrappers that use the plain POSIX names. In addition, pcre2posix.h defines the
POSIX names as macros for the pcre2_xxx functions, so any program that includes
it and uses the POSIX names will call the base functions directly. This makes
it easier for an application to be sure it gets the PCRE2 versions in the
presence of other POSIX regex libraries. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
/* Ensure that the PCRE2POSIX_EXP_xxx macros are set appropriately for
compiling these functions. This must come before including pcre2posix.h, where
they are set for an application (using these functions) if they have not
previously been set. */
#if defined(_WIN32) && !defined(PCRE2_STATIC)
# define PCRE2POSIX_EXP_DECL extern __declspec(dllexport)
# define PCRE2POSIX_EXP_DEFN __declspec(dllexport)
#endif
/* Older versions of MSVC lack snprintf(). This define allows for
warning/error-free compilation and testing with MSVC compilers back to at least
MSVC 10/2010. Except for VC6 (which is missing some fundamentals and fails). */
#if defined(_MSC_VER) && (_MSC_VER < 1900)
#define snprintf _snprintf
#endif
/* Compile-time error numbers start at this value. It should probably never be
changed. This #define is a copy of the one in pcre2_internal.h. */
#define COMPILE_ERROR_BASE 100
/* Standard C headers */
#include <ctype.h>
#include <limits.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/* PCRE2 headers */
#include "pcre2.h"
#include "pcre2posix.h"
/* Table to translate PCRE2 compile time error codes into POSIX error codes.
Only a few PCRE2 errors with a value greater than 23 turn into special POSIX
codes: most go to REG_BADPAT. The second table lists, in pairs, those that
don't. */
static const int eint1[] = {
0, /* No error */
REG_EESCAPE, /* \ at end of pattern */
REG_EESCAPE, /* \c at end of pattern */
REG_EESCAPE, /* unrecognized character follows \ */
REG_BADBR, /* numbers out of order in {} quantifier */
/* 5 */
REG_BADBR, /* number too big in {} quantifier */
REG_EBRACK, /* missing terminating ] for character class */
REG_ECTYPE, /* invalid escape sequence in character class */
REG_ERANGE, /* range out of order in character class */
REG_BADRPT, /* nothing to repeat */
/* 10 */
REG_ASSERT, /* internal error: unexpected repeat */
REG_BADPAT, /* unrecognized character after (? or (?- */
REG_BADPAT, /* POSIX named classes are supported only within a class */
REG_BADPAT, /* POSIX collating elements are not supported */
REG_EPAREN, /* missing ) */
/* 15 */
REG_ESUBREG, /* reference to non-existent subpattern */
REG_INVARG, /* pattern passed as NULL */
REG_INVARG, /* unknown compile-time option bit(s) */
REG_EPAREN, /* missing ) after (?# comment */
REG_ESIZE, /* parentheses nested too deeply */
/* 20 */
REG_ESIZE, /* regular expression too large */
REG_ESPACE, /* failed to get memory */
REG_EPAREN, /* unmatched closing parenthesis */
REG_ASSERT /* internal error: code overflow */
};
static const int eint2[] = {
30, REG_ECTYPE, /* unknown POSIX class name */
32, REG_INVARG, /* this version of PCRE2 does not have Unicode support */
37, REG_EESCAPE, /* PCRE2 does not support \L, \l, \N{name}, \U, or \u */
56, REG_INVARG, /* internal error: unknown newline setting */
92, REG_INVARG, /* invalid option bits with PCRE2_LITERAL */
99, REG_EESCAPE /* \K in lookaround */
};
/* Table of texts corresponding to POSIX error codes */
static const char *const pstring[] = {
"", /* Dummy for value 0 */
"internal error", /* REG_ASSERT */
"invalid repeat counts in {}", /* BADBR */
"pattern error", /* BADPAT */
"? * + invalid", /* BADRPT */
"unbalanced {}", /* EBRACE */
"unbalanced []", /* EBRACK */
"collation error - not relevant", /* ECOLLATE */
"bad class", /* ECTYPE */
"bad escape sequence", /* EESCAPE */
"empty expression", /* EMPTY */
"unbalanced ()", /* EPAREN */
"bad range inside []", /* ERANGE */
"expression too big", /* ESIZE */
"failed to get memory", /* ESPACE */
"bad back reference", /* ESUBREG */
"bad argument", /* INVARG */
"match failed" /* NOMATCH */
};
#if 0 /* REMOVE THIS CODE */
The code below was created for 10.33 (see ChangeLog 10.33 #4) when the
POSIX functions were given pcre2_... names instead of the traditional POSIX
names. However, it has proved to be more troublesome than useful. There have
been at least two cases where a program links with two others, one of which
uses the POSIX library and the other uses the PCRE2 POSIX functions, thus
causing two instances of the POSIX runctions to exist, leading to trouble. For
10.37 this code is commented out. In due course it can be removed if there are
no issues. The only small worry is the comment below about languages that do
not include pcre2posix.h. If there are any such cases, they will have to use
the PCRE2 names.
/*************************************************
* Wrappers with traditional POSIX names *
*************************************************/
/* Keep defining them to preseve the ABI for applications linked to the pcre2
POSIX library before these names were changed into macros in pcre2posix.h.
This also ensures that the POSIX names are callable from languages that do not
include pcre2posix.h. It is vital to #undef the macro definitions from
pcre2posix.h! */
#undef regerror
PCRE2POSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t);
PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION
regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
{
return pcre2_regerror(errcode, preg, errbuf, errbuf_size);
}
#undef regfree
PCRE2POSIX_EXP_DECL void regfree(regex_t *);
PCRE2POSIX_EXP_DEFN void PCRE2_CALL_CONVENTION
regfree(regex_t *preg)
{
pcre2_regfree(preg);
}
#undef regcomp
PCRE2POSIX_EXP_DECL int regcomp(regex_t *, const char *, int);
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
regcomp(regex_t *preg, const char *pattern, int cflags)
{
return pcre2_regcomp(preg, pattern, cflags);
}
#undef regexec
PCRE2POSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t,
regmatch_t *, int);
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
regexec(const regex_t *preg, const char *string, size_t nmatch,
regmatch_t pmatch[], int eflags)
{
return pcre2_regexec(preg, string, nmatch, pmatch, eflags);
}
#endif
/*************************************************
* Translate error code to string *
*************************************************/
PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION
pcre2_regerror(int errcode, const regex_t *preg, char *errbuf,
size_t errbuf_size)
{
int used;
const char *message;
message = (errcode <= 0 || errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
"unknown error code" : pstring[errcode];
if (preg != NULL && (int)preg->re_erroffset != -1)
{
used = snprintf(errbuf, errbuf_size, "%s at offset %-6d", message,
(int)preg->re_erroffset);
}
else
{
used = snprintf(errbuf, errbuf_size, "%s", message);
}
return used + 1;
}
/*************************************************
* Free store held by a regex *
*************************************************/
PCRE2POSIX_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_regfree(regex_t *preg)
{
pcre2_match_data_free(preg->re_match_data);
pcre2_code_free(preg->re_pcre2_code);
}
/*************************************************
* Compile a regular expression *
*************************************************/
/*
Arguments:
preg points to a structure for recording the compiled expression
pattern the pattern to compile
cflags compilation flags
Returns: 0 on success
various non-zero codes on failure
*/
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_regcomp(regex_t *preg, const char *pattern, int cflags)
{
PCRE2_SIZE erroffset;
PCRE2_SIZE patlen;
int errorcode;
int options = 0;
int re_nsub = 0;
patlen = ((cflags & REG_PEND) != 0)? (PCRE2_SIZE)(preg->re_endp - pattern) :
PCRE2_ZERO_TERMINATED;
if ((cflags & REG_ICASE) != 0) options |= PCRE2_CASELESS;
if ((cflags & REG_NEWLINE) != 0) options |= PCRE2_MULTILINE;
if ((cflags & REG_DOTALL) != 0) options |= PCRE2_DOTALL;
if ((cflags & REG_NOSPEC) != 0) options |= PCRE2_LITERAL;
if ((cflags & REG_UTF) != 0) options |= PCRE2_UTF;
if ((cflags & REG_UCP) != 0) options |= PCRE2_UCP;
if ((cflags & REG_UNGREEDY) != 0) options |= PCRE2_UNGREEDY;
preg->re_cflags = cflags;
preg->re_pcre2_code = pcre2_compile((PCRE2_SPTR)pattern, patlen, options,
&errorcode, &erroffset, NULL);
preg->re_erroffset = erroffset;
if (preg->re_pcre2_code == NULL)
{
unsigned int i;
/* A negative value is a UTF error; otherwise all error codes are greater
than COMPILE_ERROR_BASE, but check, just in case. */
if (errorcode < COMPILE_ERROR_BASE) return REG_BADPAT;
errorcode -= COMPILE_ERROR_BASE;
if (errorcode < (int)(sizeof(eint1)/sizeof(const int)))
return eint1[errorcode];
for (i = 0; i < sizeof(eint2)/sizeof(const int); i += 2)
if (errorcode == eint2[i]) return eint2[i+1];
return REG_BADPAT;
}
(void)pcre2_pattern_info((const pcre2_code *)preg->re_pcre2_code,
PCRE2_INFO_CAPTURECOUNT, &re_nsub);
preg->re_nsub = (size_t)re_nsub;
preg->re_match_data = pcre2_match_data_create(re_nsub + 1, NULL);
preg->re_erroffset = (size_t)(-1); /* No meaning after successful compile */
if (preg->re_match_data == NULL)
{
/* LCOV_EXCL_START */
pcre2_code_free(preg->re_pcre2_code);
return REG_ESPACE;
/* LCOV_EXCL_STOP */
}
return 0;
}
/*************************************************
* Match a regular expression *
*************************************************/
/* A suitable match_data block, large enough to hold all possible captures, was
obtained when the pattern was compiled, to save having to allocate and free it
for each match. If REG_NOSUB was specified at compile time, the nmatch and
pmatch arguments are ignored, and the only result is yes/no/error. */
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_regexec(const regex_t *preg, const char *string, size_t nmatch,
regmatch_t pmatch[], int eflags)
{
int rc, so, eo;
int options = 0;
pcre2_match_data *md = (pcre2_match_data *)preg->re_match_data;
if (string == NULL) return REG_INVARG;
if ((eflags & REG_NOTBOL) != 0) options |= PCRE2_NOTBOL;
if ((eflags & REG_NOTEOL) != 0) options |= PCRE2_NOTEOL;
if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE2_NOTEMPTY;
/* When REG_NOSUB was specified, or if no vector has been passed in which to
put captured strings, ensure that nmatch is zero. This will stop any attempt to
write to pmatch. */
if ((preg->re_cflags & REG_NOSUB) != 0 || pmatch == NULL) nmatch = 0;
/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings.
The man page from OS X says "REG_STARTEND affects only the location of the
string, not how it is matched". That is why the "so" value is used to bump the
start location rather than being passed as a PCRE2 "starting offset". */
if ((eflags & REG_STARTEND) != 0)
{
if (pmatch == NULL) return REG_INVARG;
so = pmatch[0].rm_so;
eo = pmatch[0].rm_eo;
}
else
{
so = 0;
eo = (int)strlen(string);
}
rc = pcre2_match((const pcre2_code *)preg->re_pcre2_code,
(PCRE2_SPTR)string + so, (eo - so), 0, options, md, NULL);
/* Successful match */
if (rc >= 0)
{
size_t i;
PCRE2_SIZE *ovector = pcre2_get_ovector_pointer(md);
if ((size_t)rc > nmatch) rc = (int)nmatch;
for (i = 0; i < (size_t)rc; i++)
{
pmatch[i].rm_so = (ovector[i*2] == PCRE2_UNSET)? -1 :
(int)(ovector[i*2] + so);
pmatch[i].rm_eo = (ovector[i*2+1] == PCRE2_UNSET)? -1 :
(int)(ovector[i*2+1] + so);
}
for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1;
return 0;
}
/* Unsuccessful match */
if (rc <= PCRE2_ERROR_UTF8_ERR1 && rc >= PCRE2_ERROR_UTF8_ERR21)
return REG_INVARG;
/* Most of these are events that won't occur during testing, so exclude them
from coverage. */
switch(rc)
{
case PCRE2_ERROR_HEAPLIMIT: return REG_ESPACE;
case PCRE2_ERROR_NOMATCH: return REG_NOMATCH;
/* LCOV_EXCL_START */
case PCRE2_ERROR_BADMODE: return REG_INVARG;
case PCRE2_ERROR_BADMAGIC: return REG_INVARG;
case PCRE2_ERROR_BADOPTION: return REG_INVARG;
case PCRE2_ERROR_BADUTFOFFSET: return REG_INVARG;
case PCRE2_ERROR_MATCHLIMIT: return REG_ESPACE;
case PCRE2_ERROR_NOMEMORY: return REG_ESPACE;
case PCRE2_ERROR_NULL: return REG_INVARG;
default: return REG_ASSERT;
/* LCOV_EXCL_STOP */
}
}
/* End of pcre2posix.c */

184
third_party/pcre/pcre2posix.h vendored Normal file
View file

@ -0,0 +1,184 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE2 is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language. This is
the public header file to be #included by applications that call PCRE2 via the
POSIX wrapper interface.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* Have to include stdlib.h in order to ensure that size_t is defined. */
#include <stdlib.h>
/* Allow for C++ users */
#ifdef __cplusplus
extern "C" {
#endif
/* Options, mostly defined by POSIX, but with some extras. */
#define REG_ICASE 0x0001 /* Maps to PCRE2_CASELESS */
#define REG_NEWLINE 0x0002 /* Maps to PCRE2_MULTILINE */
#define REG_NOTBOL 0x0004 /* Maps to PCRE2_NOTBOL */
#define REG_NOTEOL 0x0008 /* Maps to PCRE2_NOTEOL */
#define REG_DOTALL 0x0010 /* NOT defined by POSIX; maps to PCRE2_DOTALL */
#define REG_NOSUB 0x0020 /* Do not report what was matched */
#define REG_UTF 0x0040 /* NOT defined by POSIX; maps to PCRE2_UTF */
#define REG_STARTEND 0x0080 /* BSD feature: pass subject string by so,eo */
#define REG_NOTEMPTY 0x0100 /* NOT defined by POSIX; maps to PCRE2_NOTEMPTY */
#define REG_UNGREEDY 0x0200 /* NOT defined by POSIX; maps to PCRE2_UNGREEDY */
#define REG_UCP 0x0400 /* NOT defined by POSIX; maps to PCRE2_UCP */
#define REG_PEND 0x0800 /* GNU feature: pass end pattern by re_endp */
#define REG_NOSPEC 0x1000 /* Maps to PCRE2_LITERAL */
/* This is not used by PCRE2, but by defining it we make it easier
to slot PCRE2 into existing programs that make POSIX calls. */
#define REG_EXTENDED 0
/* Error values. Not all these are relevant or used by the wrapper. */
enum {
REG_ASSERT = 1, /* internal error ? */
REG_BADBR, /* invalid repeat counts in {} */
REG_BADPAT, /* pattern error */
REG_BADRPT, /* ? * + invalid */
REG_EBRACE, /* unbalanced {} */
REG_EBRACK, /* unbalanced [] */
REG_ECOLLATE, /* collation error - not relevant */
REG_ECTYPE, /* bad class */
REG_EESCAPE, /* bad escape sequence */
REG_EMPTY, /* empty expression */
REG_EPAREN, /* unbalanced () */
REG_ERANGE, /* bad range inside [] */
REG_ESIZE, /* expression too big */
REG_ESPACE, /* failed to get memory */
REG_ESUBREG, /* bad back reference */
REG_INVARG, /* bad argument */
REG_NOMATCH /* match failed */
};
/* The structure representing a compiled regular expression. It is also used
for passing the pattern end pointer when REG_PEND is set. */
typedef struct {
void *re_pcre2_code;
void *re_match_data;
const char *re_endp;
size_t re_nsub;
size_t re_erroffset;
int re_cflags;
} regex_t;
/* The structure in which a captured offset is returned. */
typedef int regoff_t;
typedef struct {
regoff_t rm_so;
regoff_t rm_eo;
} regmatch_t;
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order to make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* When an application links to a PCRE2 DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
export settings are needed, and are set in pcre2posix.c before including this
file. */
#if defined(_WIN32) && !defined(PCRE2_STATIC) && !defined(PCRE2POSIX_EXP_DECL)
# define PCRE2POSIX_EXP_DECL extern __declspec(dllimport)
# define PCRE2POSIX_EXP_DEFN __declspec(dllimport)
#endif
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE2POSIX_EXP_DECL
# ifdef __cplusplus
# define PCRE2POSIX_EXP_DECL extern "C"
# define PCRE2POSIX_EXP_DEFN extern "C"
# else
# define PCRE2POSIX_EXP_DECL extern
# define PCRE2POSIX_EXP_DEFN extern
# endif
#endif
/* The functions. The actual code is in functions with pcre2_xxx names for
uniqueness. POSIX names are provided as macros for API compatibility with POSIX
regex functions. It's done this way to ensure to they are always linked from
the PCRE2 library and not by accident from elsewhere (regex_t differs in size
elsewhere). */
PCRE2POSIX_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_regcomp(regex_t *, const char *, int);
PCRE2POSIX_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_regexec(const regex_t *, const char *, size_t,
regmatch_t *, int);
PCRE2POSIX_EXP_DECL size_t PCRE2_CALL_CONVENTION pcre2_regerror(int, const regex_t *, char *, size_t);
PCRE2POSIX_EXP_DECL void PCRE2_CALL_CONVENTION pcre2_regfree(regex_t *);
#define regcomp pcre2_regcomp
#define regexec pcre2_regexec
#define regerror pcre2_regerror
#define regfree pcre2_regfree
/* Debian had a patch that used different names. These are now here to save
them having to maintain their own patch, but are not documented by PCRE2. */
#define PCRE2regcomp pcre2_regcomp
#define PCRE2regexec pcre2_regexec
#define PCRE2regerror pcre2_regerror
#define PCRE2regfree pcre2_regfree
#ifdef __cplusplus
} /* extern "C" */
#endif
/* End of pcre2posix.h */

209
third_party/pcre/pcre2posix_test.c vendored Normal file
View file

@ -0,0 +1,209 @@
/*************************************************
* PCRE2 POSIX interface test program *
*************************************************/
/*
Written by Philip Hazel, December 2022
Copyright (c) 2022
File last edited: December 2022
This program tests the POSIX wrapper to the PCRE2 regular expression library.
The main PCRE2 test program is pcre2test, which also tests these function
calls. This little program is needed to test the case where the client includes
pcre2posix.h but not pcre2.h, mainly to make sure that it builds successfully.
However, the code is written as a flexible test program to which extra tests
can be added.
Compile with -lpcre2-posix -lpcre2-8
If run with no options, there is no output on success, and the return code is
zero. If any test fails there is output to stderr, and the return code is 1.
For testing purposes, the "-v" option causes verification output to be written
to stdout. */
#include <stdio.h>
#include <string.h>
#include "pcre2posix.h"
#define CAPCOUNT 5 /* Number of captures supported */
#define PRINTF if (v) printf /* Shorthand for testing output */
/* This vector contains compiler flags for each pattern that is tested. */
static int cflags[] = {
0, /* Test 0 */
REG_ICASE, /* Test 1 */
0, /* Test 2 */
REG_NEWLINE, /* Test 3 */
0 /* Test 4 */
};
/* This vector contains match flags for each pattern that is tested. */
static int mflags[] = {
0, /* Test 0 */
0, /* Test 1 */
0, /* Test 2 */
REG_NOTBOL, /* Test 3 */
0 /* Test 4 */
};
/* Automate the number of patterns */
#define count (int)(sizeof(cflags)/sizeof(int))
/* The data for each pattern consists of a pattern string, followed by any
number of subject strings, terminated by NULL. Some tests share data, but use
different flags. */
static const char *data0_1[] = { "posix", "lower posix", "upper POSIX", NULL };
static const char *data2_3[] = { "^(cat|dog)", "catastrophic\ncataclysm",
"dogfight", "no animals", NULL };
static const char *data4[] = { "*badpattern", NULL };
/* Index the data strings */
static char **data[] = {
(char **)(&data0_1),
(char **)(&data0_1),
(char **)(&data2_3),
(char **)(&data2_3),
(char **)(&data4)
};
/* The expected results for each pattern consist of a compiler return code,
optionally followed, for each subject string, by a match return code and, for a
successful match, up to CAPCOUNT pairs of returned match data. */
static int results0[] = {
0, /* Compiler rc */
0, 6, 11, /* 1st match */
REG_NOMATCH /* 2nd match */
};
static int results1[] = {
0, /* Compiler rc */
0, 6, 11, /* 1st match */
0, 6, 11 /* 2nd match */
};
static int results2[] = {
0, /* Compiler rc */
0, 0, 3, 0, 3, /* 1st match */
0, 0, 3, 0, 3, /* 2nd match */
REG_NOMATCH /* 3rd match */
};
static int results3[] = {
0, /* Compiler rc */
0, 13, 16, 13, 16, /* 1st match */
REG_NOMATCH, /* 2nd match */
REG_NOMATCH /* 3rd match */
};
static int results4[] = {
REG_BADRPT /* Compiler rc */
};
/* Index the result vectors */
static int *results[] = {
(int *)(&results0),
(int *)(&results1),
(int *)(&results2),
(int *)(&results3),
(int *)(&results4)
};
/* And here is the program */
int main(int argc, char **argv)
{
regex_t re;
regmatch_t match[CAPCOUNT];
int v = argc > 1 && strcmp(argv[1], "-v") == 0;
PRINTF("Test of pcre2posix.h without pcre2.h\n");
for (int i = 0; i < count; i++)
{
char *pattern = data[i][0];
char **subjects = data[i] + 1;
int *rd = results[i];
int rc = regcomp(&re, pattern, cflags[i]);
PRINTF("Pattern: %s flags=0x%02x\n", pattern, cflags[i]);
if (rc != *rd)
{
fprintf(stderr, "Unexpected compile error %d (expected %d)\n", rc, *rd);
fprintf(stderr, "Pattern is: %s\n", pattern);
return 1;
}
if (rc != 0)
{
if (v)
{
char buffer[256];
(void)regerror(rc, &re, buffer, sizeof(buffer));
PRINTF("Compile error %d: %s (expected)\n", rc, buffer);
}
continue;
}
for (; *subjects != NULL; subjects++)
{
rc = regexec(&re, *subjects, CAPCOUNT, match, mflags[i]);
PRINTF("Subject: %s\n", *subjects);
PRINTF("Return: %d", rc);
if (rc != *(++rd))
{
PRINTF("\n");
fprintf(stderr, "Unexpected match error %d (expected %d)\n", rc, *rd);
fprintf(stderr, "Pattern is: %s\n", pattern);
fprintf(stderr, "Subject is: %s\n", *subjects);
return 1;
}
if (rc == 0)
{
for (int j = 0; j < CAPCOUNT; j++)
{
regmatch_t *m = match + j;
if (m->rm_so < 0) continue;
if (m->rm_so != *(++rd) || m->rm_eo != *(++rd))
{
PRINTF("\n");
fprintf(stderr, "Mismatched results for successful match\n");
fprintf(stderr, "Pattern is: %s\n", pattern);
fprintf(stderr, "Subject is: %s\n", *subjects);
fprintf(stderr, "Result %d: expected %d %d received %d %d\n",
j, rd[-1], rd[0], m->rm_so, m->rm_eo);
return 1;
}
PRINTF(" (%d %d %d)", j, m->rm_so, m->rm_eo);
}
}
else if (v)
{
char buffer[256];
(void)regerror(rc, &re, buffer, sizeof(buffer));
PRINTF(": %s (expected)", buffer);
}
PRINTF("\n");
}
regfree(&re);
}
PRINTF("End of test\n");
return 0;
}
/* End of pcre2posix_test.c */