1berry/MariaDB-server
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

8.44

Browse Source
This commit is contained in:
Oleksandr Byelkin 2020-04-30 18:40:02 +02:00
parent 879f7e85aa
commit c1291d7a6b
47 changed files with 3622 additions and 2766 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
pcre/AUTHORS
View File

@ -8,7 +8,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2019 University of Cambridge
Copyright (c) 1997-2020 University of Cambridge
All rights reserved
@ -19,7 +19,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2019 Zoltan Herczeg
Copyright(c) 2010-2020 Zoltan Herczeg
All rights reserved.
@ -30,7 +30,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2019 Zoltan Herczeg
Copyright(c) 2009-2020 Zoltan Herczeg
All rights reserved.

29
pcre/ChangeLog
View File

@ -5,6 +5,35 @@ Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All
development is happening in the PCRE2 10.xx series.
Version 8.44 12 February-2020
-----------------------------
1. Setting --enable-jit=auto for an out-of-tree build failed because the
source directory wasn't in the search path for AC_TRY_COMPILE always. Patch
from Ross Burton.
2. Applied a patch from Michael Shigorin to fix 8.43 build on e2k arch
with lcc compiler (EDG frontend based); the problem it fixes is:
lcc: "pcrecpp.cc", line 74: error: declaration aliased to undefined entity
"_ZN7pcrecpp2RE6no_argE" [-Werror]
3. Change 2 for 8.43 omitted (*LF) from the list of start-of-pattern items. Now
added.
4. Fix ARMv5 JIT improper handling of labels right after a constant pool.
5. Small patch to pcreposix.c to set the erroroffset field to -1 immediately
after a successful compile, instead of at the start of matching to avoid a
sanitizer complaint (regexec is supposed to be thread safe).
6. Check the size of the number after (?C as it is read, in order to avoid
integer overflow.
7. Tidy up left shifts to avoid sanitize warnings; also fix one NULL deference
in pcretest.
Version 8.43 23-February-2019
-----------------------------

6
pcre/LICENCE
View File

@ -25,7 +25,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2019 University of Cambridge
Copyright (c) 1997-2020 University of Cambridge
All rights reserved.
@ -36,7 +36,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2010-2019 Zoltan Herczeg
Copyright(c) 2010-2020 Zoltan Herczeg
All rights reserved.
@ -47,7 +47,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2009-2019 Zoltan Herczeg
Copyright(c) 2009-2020 Zoltan Herczeg
All rights reserved.

6
pcre/NEWS
View File

@ -5,6 +5,12 @@ Note that this library (now called PCRE1) is now being maintained for bug fixes
only. New projects are advised to use the new PCRE2 libraries.
Release 8.44 12-February-2020
-----------------------------
This is a bug-fix release.
Release 8.43 23-February-2019
-----------------------------

9
pcre/README
View File

@ -13,9 +13,10 @@ libraries.
The latest release of PCRE1 is always available in three alternative formats
from:
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.gz
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.bz2
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.zip
There is a mailing list for discussion about the development of PCRE at
pcre-dev@exim.org. You can access the archives and subscribe or manage your
@ -999,4 +1000,4 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 10 February 2015
Last updated: 12 February 2020

6
pcre/config.h.generic
View File

@ -235,7 +235,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_NAME "PCRE"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE 8.43"
#define PACKAGE_STRING "PCRE 8.44"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre"
@ -244,7 +244,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_URL ""
/* Define to the version of this package. */
#define PACKAGE_VERSION "8.43"
#define PACKAGE_VERSION "8.44"
/* 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
@ -336,7 +336,7 @@ sure both macros are undefined; an emulation function will then be used. */
/* #undef SUPPORT_VALGRIND */
/* Version number of package */
#define VERSION "8.43"
#define VERSION "8.44"
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */

38
pcre/configure vendored
View File

@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.69 for PCRE 8.43.
# Generated by GNU Autoconf 2.69 for PCRE 8.44.
#
#
# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@ -587,8 +587,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='PCRE'
PACKAGE_TARNAME='pcre'
PACKAGE_VERSION='8.43'
PACKAGE_STRING='PCRE 8.43'
PACKAGE_VERSION='8.44'
PACKAGE_STRING='PCRE 8.44'
PACKAGE_BUGREPORT=''
PACKAGE_URL=''
@ -1418,7 +1418,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
\`configure' configures PCRE 8.43 to adapt to many kinds of systems.
\`configure' configures PCRE 8.44 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@ -1488,7 +1488,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of PCRE 8.43:";;
short | recursive ) echo "Configuration of PCRE 8.44:";;
esac
cat <<\_ACEOF
@ -1662,7 +1662,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
PCRE configure 8.43
PCRE configure 8.44
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@ -2419,7 +2419,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
It was created by PCRE $as_me 8.43, which was
It was created by PCRE $as_me 8.44, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@ -3283,7 +3283,7 @@ fi
# Define the identity of the package.
PACKAGE='pcre'
VERSION='8.43'
VERSION='8.44'
cat >>confdefs.h <<_ACEOF
@ -17664,9 +17664,9 @@ _ACEOF
# Versioning
PCRE_MAJOR="8"
PCRE_MINOR="43"
PCRE_MINOR="44"
PCRE_PRERELEASE=""
PCRE_DATE="2019-02-23"
PCRE_DATE="2020-02-12"
if test "$PCRE_MINOR" = "08" -o "$PCRE_MINOR" = "09"
then
@ -17747,6 +17747,8 @@ ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5'
ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5'
ac_compiler_gnu=$ac_cv_c_compiler_gnu
SAVE_CPPFLAGS=$CPPFLAGS
CPPFLAGS=-I$srcdir
cat confdefs.h - <<_ACEOF >conftest.$ac_ext
/* end confdefs.h. */
@ -17762,6 +17764,7 @@ else
enable_jit=no
fi
rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
CPPFLAGS=$SAVE_CPPFLAGS
fi
# Handle --disable-pcregrep-jit (enabled by default)
@ -19714,19 +19717,19 @@ esac
# (Note: The libpcre*_version bits are m4 variables, assigned above)
EXTRA_LIBPCRE_LDFLAGS="$EXTRA_LIBPCRE_LDFLAGS \
$NO_UNDEFINED -version-info 3:11:2"
$NO_UNDEFINED -version-info 3:12:2"
EXTRA_LIBPCRE16_LDFLAGS="$EXTRA_LIBPCRE16_LDFLAGS \
$NO_UNDEFINED -version-info 2:11:2"
$NO_UNDEFINED -version-info 2:12:2"
EXTRA_LIBPCRE32_LDFLAGS="$EXTRA_LIBPCRE32_LDFLAGS \
$NO_UNDEFINED -version-info 0:11:0"
$NO_UNDEFINED -version-info 0:12:0"
EXTRA_LIBPCREPOSIX_LDFLAGS="$EXTRA_LIBPCREPOSIX_LDFLAGS \
$NO_UNDEFINED -version-info 0:6:0"
$NO_UNDEFINED -version-info 0:7:0"
EXTRA_LIBPCRECPP_LDFLAGS="$EXTRA_LIBPCRECPP_LDFLAGS \
$NO_UNDEFINED -version-info 0:1:0 \
$NO_UNDEFINED -version-info 0:2:0 \
$EXPORT_ALL_SYMBOLS"
@ -20775,7 +20778,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
This file was extended by PCRE $as_me 8.43, which was
This file was extended by PCRE $as_me 8.44, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@ -20841,7 +20844,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
PCRE config.status 8.43
PCRE config.status 8.44
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
@ -22072,7 +22075,6 @@ See \`config.log' for more details" "$LINENO" 5; }
cat <<_LT_EOF >> "$cfgfile"
#! $SHELL
# Generated automatically by $as_me ($PACKAGE) $VERSION
# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`:
# NOTE: Changes made to this file will be lost: look at ltmain.sh.
# Provide generalized library-building support services.

17
pcre/configure.ac
View File

@ -9,19 +9,19 @@ dnl The PCRE_PRERELEASE feature is for identifying release candidates. It might
dnl be defined as -RC2, for example. For real releases, it should be empty.
m4_define(pcre_major, [8])
m4_define(pcre_minor, [43])
m4_define(pcre_minor, [44])
m4_define(pcre_prerelease, [])
m4_define(pcre_date, [2019-02-23])
m4_define(pcre_date, [2020-02-12])
# NOTE: The CMakeLists.txt file searches for the above variables in the first
# 50 lines of this file. Please update that if the variables above are moved.
# Libtool shared library interface versions (current:revision:age)
m4_define(libpcre_version, [3:11:2])
m4_define(libpcre16_version, [2:11:2])
m4_define(libpcre32_version, [0:11:0])
m4_define(libpcreposix_version, [0:6:0])
m4_define(libpcrecpp_version, [0:1:0])
m4_define(libpcre_version, [3:12:2])
m4_define(libpcre16_version, [2:12:2])
m4_define(libpcre32_version, [0:12:0])
m4_define(libpcreposix_version, [0:7:0])
m4_define(libpcrecpp_version, [0:2:0])
AC_PREREQ(2.57)
AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre)
@ -159,12 +159,15 @@ AC_ARG_ENABLE(jit,
if test "$enable_jit" = "auto"; then
AC_LANG(C)
SAVE_CPPFLAGS=$CPPFLAGS
CPPFLAGS=-I$srcdir
AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
#define SLJIT_CONFIG_AUTO 1
#include "sljit/sljitConfigInternal.h"
#if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED)
#error unsupported
#endif]])], enable_jit=yes, enable_jit=no)
CPPFLAGS=$SAVE_CPPFLAGS
fi
# Handle --disable-pcregrep-jit (enabled by default)

9
pcre/doc/html/README.txt
View File

@ -13,9 +13,10 @@ libraries.
The latest release of PCRE1 is always available in three alternative formats
from:
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.gz
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.bz2
https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.zip
There is a mailing list for discussion about the development of PCRE at
pcre-dev@exim.org. You can access the archives and subscribe or manage your
@ -999,4 +1000,4 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 10 February 2015
Last updated: 12 February 2020

2
pcre/doc/html/pcre.html
View File

@ -143,7 +143,7 @@ performance.
One way of guarding against this possibility is to use the
<b>pcre_fullinfo()</b> function to check the compiled pattern's options for UTF.
Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at
compile time. This causes an compile time error if a pattern contains a
compile time. This causes a compile time error if a pattern contains a
UTF-setting sequence.
</P>
<P>

6
pcre/doc/html/pcreapi.html
View File

@ -1246,7 +1246,7 @@ the following negative numbers:
PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid
PCRE_ERROR_UNSET the requested field is not set
</pre>
The "magic number" is placed at the start of each compiled pattern as an simple
The "magic number" is placed at the start of each compiled pattern as a simple
check against passing an arbitrary memory pointer. The endianness error can
occur if a compiled pattern is saved and reloaded on a different host. Here is
a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled
@ -1318,7 +1318,7 @@ returned. For anchored patterns, -2 is returned.
</pre>
Return the value of the first data unit (non-UTF character) of any matched
string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
otherwise return 0. The fourth argument should point to an <b>uint_t</b>
otherwise return 0. The fourth argument should point to a <b>uint_t</b>
variable.
</P>
<P>
@ -1577,7 +1577,7 @@ returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
</pre>
Return the value of the rightmost literal data unit that must exist in any
matched string, other than at its start, if such a value has been recorded. The
fourth argument should point to an <b>uint32_t</b> variable. If there is no such
fourth argument should point to a <b>uint32_t</b> variable. If there is no such
value, 0 is returned.
</P>
<br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>

24
pcre/doc/html/pcretest.html
View File

@ -99,23 +99,21 @@ the 16-bit library, or <b>pcre32_xx</b> when using the 32-bit library".
<br><a name="SEC4" href="#TOC1">COMMAND LINE OPTIONS</a><br>
<P>
<b>-8</b>
If both the 8-bit library has been built, this option causes the 8-bit library
to be used (which is the default); if the 8-bit library has not been built,
this option causes an error.
If the 8-bit library has been built, this option causes it to be used (this is
the default). If the 8-bit library has not been built, this option causes an
error.
</P>
<P>
<b>-16</b>
If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this
option causes the 16-bit library to be used. If only the 16-bit library has been
built, this is the default (so has no effect). If only the 8-bit or the 32-bit
library has been built, this option causes an error.
If the 16-bit library has been built, this option causes it to be used. If only
the 16-bit library has been built, this is the default. If the 16-bit library
has not been built, this option causes an error.
</P>
<P>
<b>-32</b>
If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this
option causes the 32-bit library to be used. If only the 32-bit library has been
built, this is the default (so has no effect). If only the 8-bit or the 16-bit
library has been built, this option causes an error.
If the 32-bit library has been built, this option causes it to be used. If only
the 32-bit library has been built, this is the default. If the 32-bit library
has not been built, this option causes an error.
</P>
<P>
<b>-b</b>
@ -1154,9 +1152,9 @@ Cambridge CB2 3QH, England.
</P>
<br><a name="SEC17" href="#TOC1">REVISION</a><br>
<P>
Last updated: 23 February 2017
Last updated: 10 February 2020
<br>
Copyright &copy; 1997-2017 University of Cambridge.
Copyright &copy; 1997-2020 University of Cambridge.
<br>
<p>
Return to the <a href="index.html">PCRE index page</a>.

42
pcre/doc/pcre-config.txt
View File

@ -16,8 +16,8 @@ DESCRIPTION
pcre-config returns the configuration of the installed PCRE libraries
and the options required to compile a program to use them. Some of the
options apply only to the 8-bit, or 16-bit, or 32-bit libraries,
respectively, and are not available if only one of those libraries has
options apply only to the 8-bit, or 16-bit, or 32-bit libraries, re-
spectively, and are not available if only one of those libraries has
been built. If an unavailable option is encountered, the "usage" infor-
mation is output.
@ -36,37 +36,37 @@ OPTIONS
--version Writes the version number of the installed PCRE libraries to
the standard output.
--libs Writes to the standard output the command line options
required to link with the 8-bit PCRE library (-lpcre on many
--libs Writes to the standard output the command line options re-
quired to link with the 8-bit PCRE library (-lpcre on many
systems).
--libs16 Writes to the standard output the command line options
required to link with the 16-bit PCRE library (-lpcre16 on
many systems).
--libs16 Writes to the standard output the command line options re-
quired to link with the 16-bit PCRE library (-lpcre16 on many
systems).
--libs32 Writes to the standard output the command line options
required to link with the 32-bit PCRE library (-lpcre32 on
many systems).
--libs32 Writes to the standard output the command line options re-
quired to link with the 32-bit PCRE library (-lpcre32 on many
systems).
--libs-cpp
Writes to the standard output the command line options
required to link with PCRE's C++ wrapper library (-lpcrecpp
Writes to the standard output the command line options re-
quired to link with PCRE's C++ wrapper library (-lpcrecpp
-lpcre on many systems).
--libs-posix
Writes to the standard output the command line options
required to link with PCRE's POSIX API wrapper library
Writes to the standard output the command line options re-
quired to link with PCRE's POSIX API wrapper library
(-lpcreposix -lpcre on many systems).
--cflags Writes to the standard output the command line options
required to compile files that use PCRE (this may include
some -I options, but is blank on many systems).
--cflags Writes to the standard output the command line options re-
quired to compile files that use PCRE (this may include some
-I options, but is blank on many systems).
--cflags-posix
Writes to the standard output the command line options
required to compile files that use PCRE's POSIX API wrapper
library (this may include some -I options, but is blank on
many systems).
Writes to the standard output the command line options re-
quired to compile files that use PCRE's POSIX API wrapper li-
brary (this may include some -I options, but is blank on many
systems).
SEE ALSO

2
pcre/doc/pcre.3
View File

@ -146,7 +146,7 @@ performance.
One way of guarding against this possibility is to use the
\fBpcre_fullinfo()\fP function to check the compiled pattern's options for UTF.
Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at
compile time. This causes an compile time error if a pattern contains a
compile time. This causes a compile time error if a pattern contains a
UTF-setting sequence.
.P
If your application is one that supports UTF, be aware that validity checking

3893
pcre/doc/pcre.txt
View File

File diff suppressed because it is too large Load Diff

6
pcre/doc/pcreapi.3
View File

@ -1227,7 +1227,7 @@ the following negative numbers:
PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
PCRE_ERROR_UNSET the requested field is not set
.sp
The "magic number" is placed at the start of each compiled pattern as an simple
The "magic number" is placed at the start of each compiled pattern as a simple
check against passing an arbitrary memory pointer. The endianness error can
occur if a compiled pattern is saved and reloaded on a different host. Here is
a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
@ -1294,7 +1294,7 @@ returned. For anchored patterns, -2 is returned.
.sp
Return the value of the first data unit (non-UTF character) of any matched
string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
otherwise return 0. The fourth argument should point to an \fBuint_t\fP
otherwise return 0. The fourth argument should point to a \fBuint_t\fP
variable.
.P
In the 8-bit library, the value is always less than 256. In the 16-bit library
@ -1560,7 +1560,7 @@ returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
.sp
Return the value of the rightmost literal data unit that must exist in any
matched string, other than at its start, if such a value has been recorded. The
fourth argument should point to an \fBuint32_t\fP variable. If there is no such
fourth argument should point to a \fBuint32_t\fP variable. If there is no such
value, 0 is returned.
.
.

232
pcre/doc/pcregrep.txt
View File

@ -26,8 +26,8 @@ DESCRIPTION
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
on the command line because they are interpreted by the shell, and in-
deed quotes are required if a pattern contains white space or shell
metacharacters.
The first argument that follows any option settings is treated as the
@ -37,8 +37,8 @@ DESCRIPTION
or an argument pattern must be provided.
If no files are specified, pcregrep reads the standard input. The stan-
dard input can also be referenced by a name consisting of a single
hyphen. For example:
dard input can also be referenced by a name consisting of a single hy-
phen. For example:
pcregrep some-pattern /file1 - /file3
@ -47,8 +47,8 @@ DESCRIPTION
the start of each line, followed by a colon. However, there are options
that can change how pcregrep behaves. In particular, the -M option
makes it possible to search for patterns that span line boundaries.
What defines a line boundary is controlled by the -N (--newline)
option.
What defines a line boundary is controlled by the -N (--newline) op-
tion.
The amount of memory used for buffering files that are being scanned is
controlled by a parameter that can be set by the --buffer-size option.
@ -66,12 +66,12 @@ DESCRIPTION
By default, as soon as one pattern matches a line, no further patterns
are considered. However, if --colour (or --color) is used to colour the
matching substrings, or if --only-matching, --file-offsets, or --line-
offsets is used to output only the part of the line that matched
(either shown literally, or as an offset), scanning resumes immediately
offsets is used to output only the part of the line that matched (ei-
ther shown literally, or as an offset), scanning resumes immediately
following the match, so that further matches on the same line can be
found. If there are multiple patterns, they are all tried on the
remainder of the line, but patterns that follow the one that matched
are not tried on the earlier part of the line.
found. If there are multiple patterns, they are all tried on the re-
mainder of the line, but patterns that follow the one that matched are
not tried on the earlier part of the line.
This behaviour means that the order in which multiple patterns are
specified can affect the output when one of the above options is used.
@ -80,11 +80,11 @@ DESCRIPTION
overlap).
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.
matches are never recognized. An example is the pattern "(su-
per)?(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.
If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses
the value to set a locale when calling the PCRE library. The --locale
@ -105,9 +105,9 @@ BINARY FILES
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.
(GNU grep also identifies binary files in this manner.) See the
--binary-files option for a means of changing the way binary files are
handled.
(GNU grep also identifies binary files in this manner.) See the --bi-
nary-files option for a means of changing the way binary files are han-
dled.
OPTIONS
@ -151,16 +151,16 @@ OPTIONS
--binary-files=word
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>
"binary" (the default), pattern matching is performed on bi-
nary files, but the only output is "Binary file <name>
matches" when a match succeeds. If the word is "text", which
is equivalent to the -a or --text 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 -I
option, binary files are not processed at all; they are
assumed not to be of interest.
word is "without-match", which is equivalent to the -I op-
tion, binary files are not processed at all; they are assumed
not to be of interest.
--buffer-size=number
Set the parameter that controls how much memory is used for
@ -201,15 +201,15 @@ OPTIONS
ronment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value
of this variable should be a string of two numbers, separated
by a semicolon. They are copied directly into the control
string for setting colour on a terminal, so it is your
responsibility to ensure that they make sense. If neither of
string for setting colour on a terminal, so it is your re-
sponsibility to ensure that they make sense. If neither of
the environment variables is set, the default is "1;31",
which gives red.
-D action, --devices=action
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).
If an input path is not a regular file or a directory, "ac-
tion" specifies how it is to be processed. Valid values are
"read" (the default) or "skip" (silently skip the path).
-d action, --directories=action
If an input path is a directory, "action" specifies how it is
@ -218,8 +218,8 @@ OPTIONS
"recurse" (equivalent to the -r 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
files. In some operating systems the effect of reading a di-
rectory like this is an immediate end-of-file; in others it
may provoke an error.
-e pattern, --regex=pattern, --regexp=pattern
@ -249,8 +249,8 @@ OPTIONS
whether listed on the command line, obtained from --file-
list, or by scanning a directory. The pattern is a PCRE regu-
lar expression, and is matched against the final component of
the file name, not the entire path. The -F, -w, and -x
options do not apply to this pattern. The option may be given
the file name, not the entire path. The -F, -w, and -x op-
tions 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 --include and an --exclude pat-
tern, it is excluded. There is no short form for this option.
@ -264,29 +264,29 @@ OPTIONS
--exclude-dir=pattern
Directories whose names match the pattern are skipped without
being processed, whatever the setting of the --recursive
option. This applies to all directories, whether listed on
the command line, obtained from --file-list, or by scanning a
being processed, whatever the setting of the --recursive op-
tion. This applies to all directories, whether listed on the
command line, obtained from --file-list, or by scanning a
parent directory. The pattern is a PCRE regular expression,
and is matched against the final component of the directory
name, not the entire path. The -F, -w, and -x 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 direc-
tory matches both --include-dir and --exclude-dir, it is
excluded. There is no short form for this option.
tory matches both --include-dir and --exclude-dir, it is ex-
cluded. There is no short form for this option.
-F, --fixed-strings
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 --newline option. The -w (match as a word)
and -x (match whole line) options can be used with -F. They
apply to each of the fixed strings. A line is selected if any
strings, separated by newlines, instead of as a regular ex-
pression. What constitutes a newline for this purpose is con-
trolled by the --newline option. The -w (match as a word) and
-x (match whole line) options can be used with -F. They ap-
ply to each of the fixed strings. A line is selected if any
of the fixed strings are found in it (subject to -w or -x, 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 --include or --exclude
options.
patterns specified by any of the --include or --exclude op-
tions.
-f filename, --file=filename
Read patterns from the file, one per line, and match them
@ -358,16 +358,16 @@ OPTIONS
--include=pattern
If any --include patterns are specified, the only files that
are processed are those that match one of the patterns (and
do not match an --exclude pattern). This option does not
affect directories, but it applies to all files, whether
listed on the command line, obtained from --file-list, or by
scanning a directory. The pattern is a PCRE regular expres-
sion, and is matched against the final component of the file
name, not the entire path. The -F, -w, and -x options do not
apply to this pattern. The option may be given any number of
times. If a file name matches both an --include and an
--exclude pattern, it is excluded. There is no short form
for this option.
do not match an --exclude pattern). This option does not af-
fect directories, but it applies to all files, whether listed
on the command line, obtained from --file-list, or by scan-
ning a directory. The pattern is a PCRE regular expression,
and is matched against the final component of the file name,
not the entire path. The -F, -w, and -x options do not apply
to this pattern. The option may be given any number of times.
If a file name matches both an --include and an --exclude
pattern, it is excluded. There is no short form for this op-
tion.
--include-from=filename
Treat each non-empty line of the file as the data for an
@ -381,8 +381,8 @@ OPTIONS
tories that are processed are those that match one of the
patterns (and do not match an --exclude-dir pattern). This
applies to all directories, whether listed on the command
line, obtained from --file-list, or by scanning a parent
directory. The pattern is a PCRE regular expression, and is
line, obtained from --file-list, or by scanning a parent di-
rectory. The pattern is a PCRE regular expression, and is
matched against the final component of the directory name,
not the entire path. The -F, -w, and -x options do not apply
to this pattern. The option may be given any number of times.
@ -413,9 +413,9 @@ OPTIONS
--line-buffered
When this option is given, 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 pcregrep can
determine that it is reading from a terminal (which is cur-
by line, and the output is flushed after each write. By de-
fault, input is read in large chunks, unless pcregrep can de-
termine that it is reading from a terminal (which is cur-
rently possible only in Unix-like environments). Output to
terminal is normally automatically flushed by the operating
system. This option can be useful when the input or output is
@ -437,9 +437,9 @@ OPTIONS
--locale=locale-name
This option specifies a locale to be used for pattern match-
ing. It overrides the value in the LC_ALL or LC_CTYPE envi-
ronment variables. If no locale is specified, the PCRE
library's default (usually the "C" locale) is used. There is
no short form for this option.
ronment variables. If no locale is specified, the PCRE li-
brary's default (usually the "C" locale) is used. There is no
short form for this option.
--match-limit=number
Processing some regular expression patterns can require a
@ -447,26 +447,26 @@ OPTIONS
gram crash if not enough is available. Other patterns may
take a very long time to search for all possible matching
strings. The pcre_exec() function that is called by pcregrep
to do the matching has two parameters that can limit the
resources that it uses.
to do the matching has two parameters that can limit the re-
sources that it uses.
The --match-limit option provides a means of limiting
resource usage when processing patterns that are not going to
The --match-limit option provides a means of limiting re-
source 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, PCRE uses a func-
tion called match() which it calls repeatedly (sometimes
recursively). The limit set by --match-limit is imposed on
the number of times this function is called during a match,
which has the effect of limiting the amount of backtracking
that can take place.
tion called match() which it calls repeatedly (sometimes re-
cursively). The limit set by --match-limit is imposed on the
number of times this function is called during a match, which
has the effect of limiting the amount of backtracking that
can take place.
The --recursion-limit option is similar to --match-limit, but
instead of limiting the total number of times that match() is
called, it limits the depth of recursive calls, which in turn
limits the amount of memory that can be used. The recursion
depth is a smaller number than the total number of calls,
because not all calls to match() are recursive. This limit is
depth is a smaller number than the total number of calls, be-
cause not all calls to match() are recursive. This limit is
of use only if it is set smaller than --match-limit.
There are no short forms for these options. The default set-
@ -494,30 +494,30 @@ OPTIONS
is read line by line (see --line-buffered.)
-N newline-type, --newline=newline-type
The PCRE library supports five different conventions for
indicating the ends of lines. They are the single-character
sequences CR (carriage return) and LF (linefeed), the two-
character sequence CRLF, an "anycrlf" convention, which rec-
ognizes any of the preceding three types, and an "any" con-
vention, in which any Unicode line ending sequence is assumed
to end a line. The Unicode sequences are the three just men-
The PCRE library supports five different conventions for in-
dicating the ends of lines. They are the single-character se-
quences CR (carriage return) and LF (linefeed), the two-char-
acter sequence CRLF, an "anycrlf" convention, which recog-
nizes any of the preceding three types, and an "any" conven-
tion, in which any Unicode line ending sequence is assumed to
end a line. The Unicode sequences are the three just men-
tioned, 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).
When the PCRE 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, pcregrep uses the library's default. The
possible values for this option are CR, LF, CRLF, ANYCRLF, or
ANY. This makes it possible to use pcregrep to scan files
that have come from other environments without having to mod-
ify their line endings. If the data that is being scanned
does not agree with the convention set by this option, pcre-
grep may behave in strange ways. Note that this option does
not apply to files specified by the -f, --exclude-from, or
--include-from options, which are expected to use the operat-
ing system's standard newline sequence.
When the PCRE library is built, a default line-ending se-
quence is specified. This is normally the standard sequence
for the operating system. Unless otherwise specified by this
option, pcregrep uses the library's default. The possible
values for this option are CR, LF, CRLF, ANYCRLF, or ANY.
This makes it possible to use pcregrep 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, pcregrep
may behave in strange ways. Note that this option does not
apply to files specified by the -f, --exclude-from, or --in-
clude-from options, which are expected to use the operating
system's standard newline sequence.
-n, --line-number
Precede each output line by its line number in the file, fol-
@ -538,12 +538,12 @@ OPTIONS
is, the -A, -B, and -C options are ignored. If there is more
than one match in a line, each of them is shown separately.
If -o is combined with -v (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 --file-offsets and --line-offsets.
find non-matching lines), no output is generated, but the re-
turn 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
--file-offsets and --line-offsets.
-onumber, --only-matching=number
Show only the part of the line that matched the capturing
@ -579,8 +579,8 @@ OPTIONS
it contains, taking note of any --include and --exclude set-
tings. 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 -d option to
"recurse".
This option is a shorthand for setting the -d option to "re-
curse".
--recursion-limit=number
See --match-limit above.
@ -626,10 +626,10 @@ OPTIONS
ENVIRONMENT VARIABLES
The environment variables LC_ALL and LC_CTYPE are examined, in that
order, for a locale. The first one that is set is used. This can be
overridden by the --locale option. If no locale is set, the PCRE
library's default (usually the "C" locale) is used.
The environment variables LC_ALL and LC_CTYPE are examined, in that or-
der, for a locale. The first one that is set is used. This can be over-
ridden by the --locale option. If no locale is set, the PCRE library's
default (usually the "C" locale) is used.
NEWLINES
@ -640,8 +640,8 @@ NEWLINES
ever newline sequences they have in the input. However, the setting of
this option does not affect the interpretation of files specified by
the -f, --exclude-from, or --include-from options, which are assumed to
use the operating system's standard newline sequence, nor does it
affect the way in which pcregrep writes informational messages to the
use the operating system's standard newline sequence, nor does it af-
fect the way in which pcregrep writes informational messages to the
standard error and output streams. For these it uses the string "\n" to
indicate newlines, relying on the C I/O library to convert this to an
appropriate sequence.
@ -687,13 +687,13 @@ OPTIONS WITH DATA
--file /some/file
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
as data in a shell command, and have the shell expand ~ to a home di-
rectory, 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.
The exceptions to the above are the --colour (or --color) and --only-
matching 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
matching options, for which the data is optional. If one of these op-
tions does have data, it must be given in the first form, using an
equals character. Otherwise pcregrep will assume that it has no data.
@ -702,14 +702,14 @@ MATCHING ERRORS
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+)*\d when matched against a
line of a's with no final digit. The PCRE matching function has a
resource limit that causes it to abort in these circumstances. If this
line of a's with no final digit. The PCRE matching function has a re-
source limit that causes it to abort in these circumstances. If this
happens, pcregrep outputs an error message and the line that caused the
problem to the standard error stream. If there are more than 20 such
errors, pcregrep gives up.
The --match-limit option of pcregrep can be used to set the overall
resource limit; there is a second option called --recursion-limit that
The --match-limit option of pcregrep can be used to set the overall re-
source limit; there is a second option called --recursion-limit that
sets a limit on the amount of memory (usually stack) that is used (see
the discussion of these options above).

26
pcre/doc/pcretest.1
View File

@ -1,4 +1,4 @@
.TH PCRETEST 1 "23 February 2017" "PCRE 8.41"
.TH PCRETEST 1 "10 February 2020" "PCRE 8.44"
.SH NAME
pcretest - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS
@ -78,21 +78,19 @@ the 16-bit library, or \fBpcre32_xx\fP when using the 32-bit library".
.rs
.TP 10
\fB-8\fP
If both the 8-bit library has been built, this option causes the 8-bit library
to be used (which is the default); if the 8-bit library has not been built,
this option causes an error.
If the 8-bit library has been built, this option causes it to be used (this is
the default). If the 8-bit library has not been built, this option causes an
error.
.TP 10
\fB-16\fP
If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this
option causes the 16-bit library to be used. If only the 16-bit library has been
built, this is the default (so has no effect). If only the 8-bit or the 32-bit
library has been built, this option causes an error.
If the 16-bit library has been built, this option causes it to be used. If only
the 16-bit library has been built, this is the default. If the 16-bit library
has not been built, this option causes an error.
.TP 10
\fB-32\fP
If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this
option causes the 32-bit library to be used. If only the 32-bit library has been
built, this is the default (so has no effect). If only the 8-bit or the 16-bit
library has been built, this option causes an error.
If the 32-bit library has been built, this option causes it to be used. If only
the 32-bit library has been built, this is the default. If the 32-bit library
has not been built, this option causes an error.
.TP 10
\fB-b\fP
Behave as if each pattern has the \fB/B\fP (show byte code) modifier; the
@ -1155,6 +1153,6 @@ Cambridge CB2 3QH, England.
.rs
.sp
.nf
Last updated: 23 February 2017
Copyright (c) 1997-2017 University of Cambridge.
Last updated: 10 February 2020
Copyright (c) 1997-2020 University of Cambridge.
.fi

640
pcre/doc/pcretest.txt
View File

@ -47,15 +47,15 @@ INPUT DATA FORMAT
PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES
From release 8.30, two separate PCRE libraries can be built. The origi-
nal one supports 8-bit character strings, whereas the newer 16-bit
library supports character strings encoded in 16-bit units. From
release 8.32, a third library can be built, supporting character
strings encoded in 32-bit units. The pcretest program can be used to
test all three libraries. However, it is itself still an 8-bit program,
reading 8-bit input and writing 8-bit output. When testing the 16-bit
or 32-bit library, the patterns and data strings are converted to 16-
or 32-bit format before being passed to the PCRE library functions.
Results are converted to 8-bit for output.
nal one supports 8-bit character strings, whereas the newer 16-bit li-
brary supports character strings encoded in 16-bit units. From release
8.32, a third library can be built, supporting character strings en-
coded in 32-bit units. The pcretest program can be used to test all
three libraries. However, it is itself still an 8-bit program, reading
8-bit input and writing 8-bit output. When testing the 16-bit or
32-bit library, the patterns and data strings are converted to 16- or
32-bit format before being passed to the PCRE library functions. Re-
sults are converted to 8-bit for output.
References to functions and structures of the form pcre[16|32]_xx below
mean "pcre_xx when using the 8-bit library, pcre16_xx when using the
@ -64,34 +64,31 @@ PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES
COMMAND LINE OPTIONS
-8 If both the 8-bit library has been built, this option causes
the 8-bit library to be used (which is the default); if the
8-bit library has not been built, this option causes an
error.
-8 If the 8-bit library has been built, this option causes it to
be used (this is the default). If the 8-bit library has not
been built, this option causes an error.
-16 If both the 8-bit or the 32-bit, and the 16-bit libraries
have been built, this option causes the 16-bit library to be
used. If only the 16-bit library has been built, this is the
default (so has no effect). If only the 8-bit or the 32-bit
library has been built, this option causes an error.
-16 If the 16-bit library has been built, this option causes it
to be used. If only the 16-bit library has been built, this
is the default. If the 16-bit library has not been built,
this option causes an error.
-32 If both the 8-bit or the 16-bit, and the 32-bit libraries
have been built, this option causes the 32-bit library to be
used. If only the 32-bit library has been built, this is the
default (so has no effect). If only the 8-bit or the 16-bit
library has been built, this option causes an error.
-32 If the 32-bit library has been built, this option causes it
to be used. If only the 32-bit library has been built, this
is the default. If the 32-bit library has not been built,
this option causes an error.
-b Behave as if each pattern has the /B (show byte code) modi-
-b Behave as if each pattern has the /B (show byte code) modi-
fier; the internal form is output after compilation.
-C Output the version number of the PCRE library, and all avail-
able information about the optional features that are
included, and then exit with zero exit code. All other
options are ignored.
able information about the optional features that are in-
cluded, and then exit with zero exit code. All other options
are ignored.
-C option Output information about a specific build-time option, then
exit. This functionality is intended for use in scripts such
as RunTest. The following options output the value and set
-C option Output information about a specific build-time option, then
exit. This functionality is intended for use in scripts such
as RunTest. The following options output the value and set
the exit code as indicated:
ebcdic-nl the code for LF (= NL) in an EBCDIC environment:
@ -107,7 +104,7 @@ COMMAND LINE OPTIONS
ANYCRLF or ANY
exit code is always 0
The following options output 1 for true or 0 for false, and
The following options output 1 for true or 0 for false, and
set the exit code to the same value:
ebcdic compiled for an EBCDIC environment
@ -119,61 +116,61 @@ COMMAND LINE OPTIONS
utf UTF-8 and/or UTF-16 and/or UTF-32 support
is available
If an unknown option is given, an error message is output;
If an unknown option is given, an error message is output;
the exit code is 0.
-d Behave as if each pattern has the /D (debug) modifier; the
internal form and information about the compiled pattern is
-d Behave as if each pattern has the /D (debug) modifier; the
internal form and information about the compiled pattern is
output after compilation; -d is equivalent to -b -i.
-dfa Behave as if each data line contains the \D escape sequence;
-dfa Behave as if each data line contains the \D escape sequence;
this causes the alternative matching function,
pcre[16|32]_dfa_exec(), to be used instead of the standard
pcre[16|32]_dfa_exec(), to be used instead of the standard
pcre[16|32]_exec() function (more detail is given below).
-help Output a brief summary these options and then exit.
-i Behave as if each pattern has the /I modifier; information
-i Behave as if each pattern has the /I modifier; information
about the compiled pattern is given after compilation.
-M Behave as if each data line contains the \M escape sequence;
this causes PCRE to discover the minimum MATCH_LIMIT and
MATCH_LIMIT_RECURSION settings by calling pcre[16|32]_exec()
-M Behave as if each data line contains the \M escape sequence;
this causes PCRE to discover the minimum MATCH_LIMIT and
MATCH_LIMIT_RECURSION settings by calling pcre[16|32]_exec()
repeatedly with different limits.
-m Output the size of each compiled pattern after it has been
compiled. This is equivalent to adding /M to each regular
expression. The size is given in bytes for both libraries.
-m Output the size of each compiled pattern after it has been
compiled. This is equivalent to adding /M to each regular ex-
pression. The size is given in bytes for both libraries.
-O Behave as if each pattern has the /O modifier, that is dis-
-O Behave as if each pattern has the /O modifier, that is dis-
able auto-possessification for all patterns.
-o osize Set the number of elements in the output vector that is used
when calling pcre[16|32]_exec() or pcre[16|32]_dfa_exec() to
be osize. The default value is 45, which is enough for 14
-o osize Set the number of elements in the output vector that is used
when calling pcre[16|32]_exec() or pcre[16|32]_dfa_exec() to
be osize. The default value is 45, which is enough for 14
capturing subexpressions for pcre[16|32]_exec() or 22 differ-
ent matches for pcre[16|32]_dfa_exec(). The vector size can
be changed for individual matching calls by including \O in
ent matches for pcre[16|32]_dfa_exec(). The vector size can
be changed for individual matching calls by including \O in
the data line (see below).
-p Behave as if each pattern has the /P modifier; the POSIX
wrapper API is used to call PCRE. None of the other options
has any effect when -p is set. This option can be used only
-p Behave as if each pattern has the /P modifier; the POSIX
wrapper API is used to call PCRE. None of the other options
has any effect when -p is set. This option can be used only
with the 8-bit library.
-q Do not output the version number of pcretest at the start of
-q Do not output the version number of pcretest at the start of
execution.
-S size On Unix-like systems, set the size of the run-time stack to
-S size On Unix-like systems, set the size of the run-time stack to
size megabytes.
-s or -s+ Behave as if each pattern has the /S modifier; in other
words, force each pattern to be studied. If -s+ is used, all
the JIT compile options are passed to pcre[16|32]_study(),
causing just-in-time optimization to be set up if it is
available, for both full and partial matching. Specific JIT
-s or -s+ Behave as if each pattern has the /S modifier; in other
words, force each pattern to be studied. If -s+ is used, all
the JIT compile options are passed to pcre[16|32]_study(),
causing just-in-time optimization to be set up if it is
available, for both full and partial matching. Specific JIT
compile options can be selected by following -s+ with a digit
in the range 1 to 7, which selects the JIT compile modes as
in the range 1 to 7, which selects the JIT compile modes as
follows:
1 normal match only
@ -183,119 +180,119 @@ COMMAND LINE OPTIONS
6 soft and hard partial match
7 all three modes (default)
If -s++ is used instead of -s+ (with or without a following
digit), the text "(JIT)" is added to the first output line
If -s++ is used instead of -s+ (with or without a following
digit), the text "(JIT)" is added to the first output line
after a match or no match when JIT-compiled code was actually
used.
Note that there are pattern options that can override -s,
either specifying no studying at all, or suppressing JIT com-
pilation.
Note that there are pattern options that can override -s, ei-
ther specifying no studying at all, or suppressing JIT compi-
lation.
If the /I or /D option is present on a pattern (requesting
output about the compiled pattern), information about the
result of studying is not included when studying is caused
only by -s and neither -i nor -d is present on the command
line. This behaviour means that the output from tests that
are run with and without -s should be identical, except when
options that output information about the actual running of a
match are set.
If the /I or /D option is present on a pattern (requesting
output about the compiled pattern), information about the re-
sult of studying is not included when studying is caused only
by -s and neither -i nor -d is present on the command line.
This behaviour means that the output from tests that are run
with and without -s should be identical, except when options
that output information about the actual running of a match
are set.
The -M, -t, and -tm options, which give information about
resources used, are likely to produce different output with
and without -s. Output may also differ if the /C option is
The -M, -t, and -tm options, which give information about re-
sources used, are likely to produce different output with and
without -s. Output may also differ if the /C option is
present on an individual pattern. This uses callouts to trace
the the matching process, and this may be different between
studied and non-studied patterns. If the pattern contains
(*MARK) items there may also be differences, for the same
the the matching process, and this may be different between
studied and non-studied patterns. If the pattern contains
(*MARK) items there may also be differences, for the same
reason. The -s command line option can be overridden for spe-
cific patterns that should never be studied (see the /S pat-
cific patterns that should never be studied (see the /S pat-
tern modifier below).
-t Run each compile, study, and match many times with a timer,
and output the resulting times per compile, study, or match
(in milliseconds). Do not set -m with -t, because you will
-t Run each compile, study, and match many times with a timer,
and output the resulting times per compile, study, or match
(in milliseconds). Do not set -m with -t, because you will
then get the size output a zillion times, and the timing will
be distorted. You can control the number of iterations that
be distorted. You can control the number of iterations that
are used for timing by following -t with a number (as a sepa-
rate item on the command line). For example, "-t 1000" iter-
rate item on the command line). For example, "-t 1000" iter-
ates 1000 times. The default is to iterate 500000 times.
-tm This is like -t except that it times only the matching phase,
not the compile or study phases.
-T -TM These behave like -t and -tm, but in addition, at the end of
-T -TM These behave like -t and -tm, but in addition, at the end of
a run, the total times for all compiles, studies, and matches
are output.
DESCRIPTION
If pcretest is given two filename arguments, it reads from the first
If pcretest is given two filename arguments, it reads from the first
and writes to the second. If it is given only one filename argument, it
reads from that file and writes to stdout. Otherwise, it reads from
stdin and writes to stdout, and prompts for each line of input, using
reads from that file and writes to stdout. Otherwise, it reads from
stdin and writes to stdout, and prompts for each line of input, using
"re>" to prompt for regular expressions, and "data>" to prompt for data
lines.
When pcretest is built, a configuration option can specify that it
should be linked with the libreadline library. When this is done, if
When pcretest is built, a configuration option can specify that it
should be linked with the libreadline library. When this is done, if
the input is from a terminal, it is read using the readline() function.
This provides line-editing and history facilities. The output from the
This provides line-editing and history facilities. The output from the
-help option states whether or not readline() will be used.
The program handles any number of sets of input on a single input file.
Each set starts with a regular expression, and continues with any num-
Each set starts with a regular expression, and continues with any num-
ber of data lines to be matched against that pattern.
Each data line is matched separately and independently. If you want to
Each data line is matched separately and independently. If you want to
do multi-line matches, you have to use the \n escape sequence (or \r or
\r\n, etc., depending on the newline setting) in a single line of input
to encode the newline sequences. There is no limit on the length of
data lines; the input buffer is automatically extended if it is too
to encode the newline sequences. There is no limit on the length of
data lines; the input buffer is automatically extended if it is too
small.
An empty line signals the end of the data lines, at which point a new
regular expression is read. The regular expressions are given enclosed
An empty line signals the end of the data lines, at which point a new
regular expression is read. The regular expressions are given enclosed
in any non-alphanumeric delimiters other than backslash, for example:
/(a|bc)x+yz/
White space before the initial delimiter is ignored. A regular expres-
sion may be continued over several input lines, in which case the new-
line characters are included within it. It is possible to include the
White space before the initial delimiter is ignored. A regular expres-
sion may be continued over several input lines, in which case the new-
line characters are included within it. It is possible to include the
delimiter within the pattern by escaping it, for example
/abc\/def/
If you do so, the escape and the delimiter form part of the pattern,
but since delimiters are always non-alphanumeric, this does not affect
its interpretation. If the terminating delimiter is immediately fol-
If you do so, the escape and the delimiter form part of the pattern,
but since delimiters are always non-alphanumeric, this does not affect
its interpretation. If the terminating delimiter is immediately fol-
lowed by a backslash, for example,
/abc/\
then a backslash is added to the end of the pattern. This is done to
provide a way of testing the error condition that arises if a pattern
then a backslash is added to the end of the pattern. This is done to
provide a way of testing the error condition that arises if a pattern
finishes with a backslash, because
/abc\/
is interpreted as the first line of a pattern that starts with "abc/",
is interpreted as the first line of a pattern that starts with "abc/",
causing pcretest to read the next line as a continuation of the regular
expression.
PATTERN MODIFIERS
A pattern may be followed by any number of modifiers, which are mostly
single characters, though some of these can be qualified by further
characters. Following Perl usage, these are referred to below as, for
example, "the /i modifier", even though the delimiter of the pattern
need not always be a slash, and no slash is used when writing modi-
fiers. White space may appear between the final pattern delimiter and
the first modifier, and between the modifiers themselves. For refer-
ence, here is a complete list of modifiers. They fall into several
A pattern may be followed by any number of modifiers, which are mostly
single characters, though some of these can be qualified by further
characters. Following Perl usage, these are referred to below as, for
example, "the /i modifier", even though the delimiter of the pattern
need not always be a slash, and no slash is used when writing modi-
fiers. White space may appear between the final pattern delimiter and
the first modifier, and between the modifiers themselves. For refer-
ence, here is a complete list of modifiers. They fall into several
groups that are described in detail in the following sections.
/8 set UTF mode
@ -347,8 +344,8 @@ PATTERN MODIFIERS
Perl-compatible modifiers
The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, PCRE_MULTILINE,
PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when
pcre[16|32]_compile() is called. These four modifier letters have the
PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when
pcre[16|32]_compile() is called. These four modifier letters have the
same effect as they do in Perl. For example:
/caseless/i
@ -356,7 +353,7 @@ PATTERN MODIFIERS
Modifiers for other PCRE options
The following table shows additional modifiers for setting PCRE com-
The following table shows additional modifiers for setting PCRE com-
pile-time options that do not correspond to anything in Perl:
/8 PCRE_UTF8 ) when using the 8-bit
@ -389,145 +386,145 @@ PATTERN MODIFIERS
/<bsr_unicode> PCRE_BSR_UNICODE
/<JS> PCRE_JAVASCRIPT_COMPAT
The modifiers that are enclosed in angle brackets are literal strings
as shown, including the angle brackets, but the letters within can be
in either case. This example sets multiline matching with CRLF as the
The modifiers that are enclosed in angle brackets are literal strings
as shown, including the angle brackets, but the letters within can be
in either case. This example sets multiline matching with CRLF as the
line ending sequence:
/^abc/m<CRLF>
As well as turning on the PCRE_UTF8/16/32 option, the /8 modifier
causes all non-printing characters in output strings to be printed
using the \x{hh...} notation. Otherwise, those less than 0x100 are out-
put in hex without the curly brackets.
As well as turning on the PCRE_UTF8/16/32 option, the /8 modifier
causes all non-printing characters in output strings to be printed us-
ing the \x{hh...} notation. Otherwise, those less than 0x100 are output
in hex without the curly brackets.
Full details of the PCRE options are given in the pcreapi documenta-
Full details of the PCRE options are given in the pcreapi documenta-
tion.
Finding all matches in a string
Searching for all possible matches within each subject string can be
requested by the /g or /G modifier. After finding a match, PCRE is
Searching for all possible matches within each subject string can be
requested by the /g or /G modifier. After finding a match, PCRE is
called again to search the remainder of the subject string. The differ-
ence between /g and /G is that the former uses the startoffset argument
to pcre[16|32]_exec() to start searching at a new point within the
entire string (which is in effect what Perl does), whereas the latter
passes over a shortened substring. This makes a difference to the
matching process if the pattern begins with a lookbehind assertion
(including \b or \B).
to pcre[16|32]_exec() to start searching at a new point within the en-
tire string (which is in effect what Perl does), whereas the latter
passes over a shortened substring. This makes a difference to the
matching process if the pattern begins with a lookbehind assertion (in-
cluding \b or \B).
If any call to pcre[16|32]_exec() in a /g or /G sequence matches an
empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and
PCRE_ANCHORED flags set in order to search for another, non-empty,
match at the same point. If this second match fails, the start offset
is advanced, and the normal match is retried. This imitates the way
If any call to pcre[16|32]_exec() in a /g or /G sequence matches an
empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and
PCRE_ANCHORED flags set in order to search for another, non-empty,
match at the same point. If this second match fails, the start offset
is advanced, and the normal match is retried. This imitates the way
Perl handles such cases when using the /g modifier or the split() func-
tion. Normally, the start offset is advanced by one character, but if
the newline convention recognizes CRLF as a newline, and the current
tion. Normally, the start offset is advanced by one character, but if
the newline convention recognizes CRLF as a newline, and the current
character is CR followed by LF, an advance of two is used.
Other modifiers
There are yet more modifiers for controlling the way pcretest operates.
The /+ modifier requests that as well as outputting the substring that
matched the entire pattern, pcretest should in addition output the
remainder of the subject string. This is useful for tests where the
subject contains multiple copies of the same substring. If the + modi-
fier appears twice, the same action is taken for captured substrings.
In each case the remainder is output on the following line with a plus
character following the capture number. Note that this modifier must
not immediately follow the /S modifier because /S+ and /S++ have other
The /+ modifier requests that as well as outputting the substring that
matched the entire pattern, pcretest should in addition output the re-
mainder of the subject string. This is useful for tests where the sub-
ject contains multiple copies of the same substring. If the + modifier
appears twice, the same action is taken for captured substrings. In
each case the remainder is output on the following line with a plus
character following the capture number. Note that this modifier must
not immediately follow the /S modifier because /S+ and /S++ have other
meanings.
The /= modifier requests that the values of all potential captured
parentheses be output after a match. By default, only those up to the
The /= modifier requests that the values of all potential captured
parentheses be output after a match. By default, only those up to the
highest one actually used in the match are output (corresponding to the
return code from pcre[16|32]_exec()). Values in the offsets vector cor-
responding to higher numbers should be set to -1, and these are output
as "<unset>". This modifier gives a way of checking that this is hap-
responding to higher numbers should be set to -1, and these are output
as "<unset>". This modifier gives a way of checking that this is hap-
pening.
The /B modifier is a debugging feature. It requests that pcretest out-
put a representation of the compiled code after compilation. Normally
this information contains length and offset values; however, if /Z is
also present, this data is replaced by spaces. This is a special fea-
ture for use in the automatic test scripts; it ensures that the same
The /B modifier is a debugging feature. It requests that pcretest out-
put a representation of the compiled code after compilation. Normally
this information contains length and offset values; however, if /Z is
also present, this data is replaced by spaces. This is a special fea-
ture for use in the automatic test scripts; it ensures that the same
output is generated for different internal link sizes.
The /D modifier is a PCRE debugging feature, and is equivalent to /BI,
The /D modifier is a PCRE debugging feature, and is equivalent to /BI,
that is, both the /B and the /I modifiers.
The /F modifier causes pcretest to flip the byte order of the 2-byte
The /F modifier causes pcretest to flip the byte order of the 2-byte
and 4-byte fields in the compiled pattern. This facility is for testing
the feature in PCRE that allows it to execute patterns that were com-
the feature in PCRE that allows it to execute patterns that were com-
piled on a host with a different endianness. This feature is not avail-
able when the POSIX interface to PCRE is being used, that is, when the
able when the POSIX interface to PCRE is being used, that is, when the
/P pattern modifier is specified. See also the section about saving and
reloading compiled patterns below.
The /I modifier requests that pcretest output information about the
compiled pattern (whether it is anchored, has a fixed first character,
and so on). It does this by calling pcre[16|32]_fullinfo() after com-
piling a pattern. If the pattern is studied, the results of that are
The /I modifier requests that pcretest output information about the
compiled pattern (whether it is anchored, has a fixed first character,
and so on). It does this by calling pcre[16|32]_fullinfo() after com-
piling a pattern. If the pattern is studied, the results of that are
also output. In this output, the word "char" means a non-UTF character,
that is, the value of a single data item (8-bit, 16-bit, or 32-bit,
depending on the library that is being tested).
that is, the value of a single data item (8-bit, 16-bit, or 32-bit, de-
pending on the library that is being tested).
The /K modifier requests pcretest to show names from backtracking con-
trol verbs that are returned from calls to pcre[16|32]_exec(). It
causes pcretest to create a pcre[16|32]_extra block if one has not
already been created by a call to pcre[16|32]_study(), and to set the
PCRE_EXTRA_MARK flag and the mark field within it, every time that
pcre[16|32]_exec() is called. If the variable that the mark field
points to is non-NULL for a match, non-match, or partial match,
pcretest prints the string to which it points. For a match, this is
shown on a line by itself, tagged with "MK:". For a non-match it is
The /K modifier requests pcretest to show names from backtracking con-
trol verbs that are returned from calls to pcre[16|32]_exec(). It
causes pcretest to create a pcre[16|32]_extra block if one has not al-
ready been created by a call to pcre[16|32]_study(), and to set the
PCRE_EXTRA_MARK flag and the mark field within it, every time that
pcre[16|32]_exec() is called. If the variable that the mark field
points to is non-NULL for a match, non-match, or partial match,
pcretest prints the string to which it points. For a match, this is
shown on a line by itself, tagged with "MK:". For a non-match it is
added to the message.
The /L modifier must be followed directly by the name of a locale, for
The /L modifier must be followed directly by the name of a locale, for
example,
/pattern/Lfr_FR
For this reason, it must be the last modifier. The given locale is set,
pcre[16|32]_maketables() is called to build a set of character tables
for the locale, and this is then passed to pcre[16|32]_compile() when
compiling the regular expression. Without an /L (or /T) modifier, NULL
is passed as the tables pointer; that is, /L applies only to the
expression on which it appears.
pcre[16|32]_maketables() is called to build a set of character tables
for the locale, and this is then passed to pcre[16|32]_compile() when
compiling the regular expression. Without an /L (or /T) modifier, NULL
is passed as the tables pointer; that is, /L applies only to the ex-
pression on which it appears.
The /M modifier causes the size in bytes of the memory block used to
hold the compiled pattern to be output. This does not include the size
of the pcre[16|32] block; it is just the actual compiled data. If the
The /M modifier causes the size in bytes of the memory block used to
hold the compiled pattern to be output. This does not include the size
of the pcre[16|32] block; it is just the actual compiled data. If the
pattern is successfully studied with the PCRE_STUDY_JIT_COMPILE option,
the size of the JIT compiled code is also output.
The /Q modifier is used to test the use of pcre_stack_guard. It must be
followed by '0' or '1', specifying the return code to be given from an
external function that is passed to PCRE and used for stack checking
followed by '0' or '1', specifying the return code to be given from an
external function that is passed to PCRE and used for stack checking
during compilation (see the pcreapi documentation for details).
The /S modifier causes pcre[16|32]_study() to be called after the
expression has been compiled, and the results used when the expression
is matched. There are a number of qualifying characters that may follow
The /S modifier causes pcre[16|32]_study() to be called after the ex-
pression has been compiled, and the results used when the expression is
matched. There are a number of qualifying characters that may follow
/S. They may appear in any order.
If /S is followed by an exclamation mark, pcre[16|32]_study() is called
with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a
with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a
pcre_extra block, even when studying discovers no useful information.
If /S is followed by a second S character, it suppresses studying, even
if it was requested externally by the -s command line option. This
makes it possible to specify that certain patterns are always studied,
if it was requested externally by the -s command line option. This
makes it possible to specify that certain patterns are always studied,
and others are never studied, independently of -s. This feature is used
in the test files in a few cases where the output is different when the
pattern is studied.
If the /S modifier is followed by a + character, the call to
pcre[16|32]_study() is made with all the JIT study options, requesting
just-in-time optimization support if it is available, for both normal
and partial matching. If you want to restrict the JIT compiling modes,
If the /S modifier is followed by a + character, the call to
pcre[16|32]_study() is made with all the JIT study options, requesting
just-in-time optimization support if it is available, for both normal
and partial matching. If you want to restrict the JIT compiling modes,
you can follow /S+ with a digit in the range 1 to 7:
1 normal match only
@ -538,40 +535,40 @@ PATTERN MODIFIERS
7 all three modes (default)
If /S++ is used instead of /S+ (with or without a following digit), the
text "(JIT)" is added to the first output line after a match or no
text "(JIT)" is added to the first output line after a match or no
match when JIT-compiled code was actually used.
Note that there is also an independent /+ modifier; it must not be
Note that there is also an independent /+ modifier; it must not be
given immediately after /S or /S+ because this will be misinterpreted.
If JIT studying is successful, the compiled JIT code will automatically
be used when pcre[16|32]_exec() is run, except when incompatible run-
time options are specified. For more details, see the pcrejit documen-
tation. See also the \J escape sequence below for a way of setting the
be used when pcre[16|32]_exec() is run, except when incompatible run-
time options are specified. For more details, see the pcrejit documen-
tation. See also the \J escape sequence below for a way of setting the
size of the JIT stack.
Finally, if /S is followed by a minus character, JIT compilation is
suppressed, even if it was requested externally by the -s command line
option. This makes it possible to specify that JIT is never to be used
Finally, if /S is followed by a minus character, JIT compilation is
suppressed, even if it was requested externally by the -s command line
option. This makes it possible to specify that JIT is never to be used
for certain patterns.
The /T modifier must be followed by a single digit. It causes a spe-
The /T modifier must be followed by a single digit. It causes a spe-
cific set of built-in character tables to be passed to pcre[16|32]_com-
pile(). It is used in the standard PCRE tests to check behaviour with
pile(). It is used in the standard PCRE tests to check behaviour with
different character tables. The digit specifies the tables as follows:
0 the default ASCII tables, as distributed in
pcre_chartables.c.dist
1 a set of tables defining ISO 8859 characters
In table 1, some characters whose codes are greater than 128 are iden-
In table 1, some characters whose codes are greater than 128 are iden-
tified as letters, digits, spaces, etc.
Using the POSIX wrapper API
The /P modifier causes pcretest to call PCRE via the POSIX wrapper API
rather than its native API. This supports only the 8-bit library. When
/P is set, the following modifiers set options for the regcomp() func-
The /P modifier causes pcretest to call PCRE via the POSIX wrapper API
rather than its native API. This supports only the 8-bit library. When
/P is set, the following modifiers set options for the regcomp() func-
tion:
/i REG_ICASE
@ -582,48 +579,48 @@ PATTERN MODIFIERS
/W REG_UCP ) the POSIX standard
/8 REG_UTF8 )
The /+ modifier works as described above. All other modifiers are
ignored.
The /+ modifier works as described above. All other modifiers are ig-
nored.
Locking out certain modifiers
PCRE can be compiled with or without support for certain features such
as UTF-8/16/32 or Unicode properties. Accordingly, the standard tests
are split up into a number of different files that are selected for
running depending on which features are available. When updating the
PCRE can be compiled with or without support for certain features such
as UTF-8/16/32 or Unicode properties. Accordingly, the standard tests
are split up into a number of different files that are selected for
running depending on which features are available. When updating the
tests, it is all too easy to put a new test into the wrong file by mis-
take; for example, to put a test that requires UTF support into a file
that is used when it is not available. To help detect such mistakes as
early as possible, there is a facility for locking out specific modi-
take; for example, to put a test that requires UTF support into a file
that is used when it is not available. To help detect such mistakes as
early as possible, there is a facility for locking out specific modi-
fiers. If an input line for pcretest starts with the string "< forbid "
the following sequence of characters is taken as a list of forbidden
the following sequence of characters is taken as a list of forbidden
modifiers. For example, in the test files that must not use UTF or Uni-
code property support, this line appears:
< forbid 8W
This locks out the /8 and /W modifiers. An immediate error is given if
they are subsequently encountered. If the character string contains <
but not >, all the multi-character modifiers that begin with < are
locked out. Otherwise, such modifiers must be explicitly listed, for
This locks out the /8 and /W modifiers. An immediate error is given if
they are subsequently encountered. If the character string contains <
but not >, all the multi-character modifiers that begin with < are
locked out. Otherwise, such modifiers must be explicitly listed, for
example:
< forbid <JS><cr>
There must be a single space between < and "forbid" for this feature to
be recognised. If there is not, the line is interpreted either as a
request to re-load a pre-compiled pattern (see "SAVING AND RELOADING
COMPILED PATTERNS" below) or, if there is a another < character, as a
pattern that uses < as its delimiter.
be recognised. If there is not, the line is interpreted either as a re-
quest to re-load a pre-compiled pattern (see "SAVING AND RELOADING COM-
PILED PATTERNS" below) or, if there is a another < character, as a pat-
tern that uses < as its delimiter.
DATA LINES
Before each data line is passed to pcre[16|32]_exec(), leading and
trailing white space is removed, and it is then scanned for \ escapes.
Some of these are pretty esoteric features, intended for checking out
some of the more complicated features of PCRE. If you are just testing
"ordinary" regular expressions, you probably don't need any of these.
Before each data line is passed to pcre[16|32]_exec(), leading and
trailing white space is removed, and it is then scanned for \ escapes.
Some of these are pretty esoteric features, intended for checking out
some of the more complicated features of PCRE. If you are just testing
"ordinary" regular expressions, you probably don't need any of these.
The following escapes are recognized:
\a alarm (BEL, \x07)
@ -684,7 +681,7 @@ DATA LINES
(any number of digits)
\R pass the PCRE_DFA_RESTART option to pcre[16|32]_dfa_exec()
\S output details of memory get/free calls during matching
\Y pass the PCRE_NO_START_OPTIMIZE option to
\Y pass the PCRE_NO_START_OPTIMIZE option to
pcre[16|32]_exec()
or pcre[16|32]_dfa_exec()
\Z pass the PCRE_NOTEOL option to pcre[16|32]_exec()
@ -693,7 +690,7 @@ DATA LINES
pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
\>dd start the match at offset dd (optional "-"; then
any number of digits); this sets the startoffset
argument for pcre[16|32]_exec() or
argument for pcre[16|32]_exec() or
pcre[16|32]_dfa_exec()
\<cr> pass the PCRE_NEWLINE_CR option to pcre[16|32]_exec()
or pcre[16|32]_dfa_exec()
@ -706,103 +703,102 @@ DATA LINES
\<any> pass the PCRE_NEWLINE_ANY option to pcre[16|32]_exec()
or pcre[16|32]_dfa_exec()
The use of \x{hh...} is not dependent on the use of the /8 modifier on
the pattern. It is recognized always. There may be any number of hexa-
decimal digits inside the braces; invalid values provoke error mes-
The use of \x{hh...} is not dependent on the use of the /8 modifier on
the pattern. It is recognized always. There may be any number of hexa-
decimal digits inside the braces; invalid values provoke error mes-
sages.
Note that \xhh specifies one byte rather than one character in UTF-8
mode; this makes it possible to construct invalid UTF-8 sequences for
testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
character in UTF-8 mode, generating more than one byte if the value is
greater than 127. When testing the 8-bit library not in UTF-8 mode,
Note that \xhh specifies one byte rather than one character in UTF-8
mode; this makes it possible to construct invalid UTF-8 sequences for
testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
character in UTF-8 mode, generating more than one byte if the value is
greater than 127. When testing the 8-bit library not in UTF-8 mode,
\x{hh} generates one byte for values less than 256, and causes an error
for greater values.
In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
possible to construct invalid UTF-16 sequences for testing purposes.
In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
makes it possible to construct invalid UTF-32 sequences for testing
In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
makes it possible to construct invalid UTF-32 sequences for testing
purposes.
The escapes that specify line ending sequences are literal strings,
exactly as shown. No more than one newline setting should be present in
The escapes that specify line ending sequences are literal strings, ex-
actly as shown. No more than one newline setting should be present in
any data line.
A backslash followed by anything else just escapes the anything else.
If the very last character is a backslash, it is ignored. This gives a
way of passing an empty line as data, since a real empty line termi-
A backslash followed by anything else just escapes the anything else.
If the very last character is a backslash, it is ignored. This gives a
way of passing an empty line as data, since a real empty line termi-
nates the data input.
The \J escape provides a way of setting the maximum stack size that is
used by the just-in-time optimization code. It is ignored if JIT opti-
mization is not being used. Providing a stack that is larger than the
The \J escape provides a way of setting the maximum stack size that is
used by the just-in-time optimization code. It is ignored if JIT opti-
mization is not being used. Providing a stack that is larger than the
default 32K is necessary only for very complicated patterns.
If \M is present, pcretest calls pcre[16|32]_exec() several times, with
different values in the match_limit and match_limit_recursion fields of
the pcre[16|32]_extra data structure, until it finds the minimum num-
the pcre[16|32]_extra data structure, until it finds the minimum num-
bers for each parameter that allow pcre[16|32]_exec() to complete with-
out error. Because this is testing a specific feature of the normal
interpretive pcre[16|32]_exec() execution, the use of any JIT optimiza-
tion that might have been set up by the /S+ qualifier of -s+ option is
out error. Because this is testing a specific feature of the normal in-
terpretive pcre[16|32]_exec() execution, the use of any JIT optimiza-
tion that might have been set up by the /S+ qualifier of -s+ option is
disabled.
The match_limit number is a measure of the amount of backtracking that
takes place, and checking it out can be instructive. For most simple
matches, the number is quite small, but for patterns with very large
numbers of matching possibilities, it can become large very quickly
with increasing length of subject string. The match_limit_recursion
number is a measure of how much stack (or, if PCRE is compiled with
NO_RECURSE, how much heap) memory is needed to complete the match
attempt.
The match_limit number is a measure of the amount of backtracking that
takes place, and checking it out can be instructive. For most simple
matches, the number is quite small, but for patterns with very large
numbers of matching possibilities, it can become large very quickly
with increasing length of subject string. The match_limit_recursion
number is a measure of how much stack (or, if PCRE is compiled with
NO_RECURSE, how much heap) memory is needed to complete the match at-
tempt.
When \O is used, the value specified may be higher or lower than the
When \O is used, the value specified may be higher or lower than the
size set by the -O command line option (or defaulted to 45); \O applies
only to the call of pcre[16|32]_exec() for the line in which it
appears.
only to the call of pcre[16|32]_exec() for the line in which it ap-
pears.
If the /P modifier was present on the pattern, causing the POSIX wrap-
per API to be used, the only option-setting sequences that have any
effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and
REG_NOTEOL, respectively, to be passed to regexec().
If the /P modifier was present on the pattern, causing the POSIX wrap-
per API to be used, the only option-setting sequences that have any ef-
fect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NO-
TEOL, respectively, to be passed to regexec().
THE ALTERNATIVE MATCHING FUNCTION
By default, pcretest uses the standard PCRE matching function,
pcre[16|32]_exec() to match each data line. PCRE also supports an
alternative matching function, pcre[16|32]_dfa_test(), which operates
in a different way, and has some restrictions. The differences between
the two functions are described in the pcrematching documentation.
By default, pcretest uses the standard PCRE matching function,
pcre[16|32]_exec() to match each data line. PCRE also supports an al-
ternative matching function, pcre[16|32]_dfa_test(), which operates in
a different way, and has some restrictions. The differences between the
two functions are described in the pcrematching documentation.
If a data line contains the \D escape sequence, or if the command line
contains the -dfa option, the alternative matching function is used.
If a data line contains the \D escape sequence, or if the command line
contains the -dfa option, the alternative matching function is used.
This function finds all possible matches at a given point. If, however,
the \F escape sequence is present in the data line, it stops after the
the \F escape sequence is present in the data line, it stops after the
first match is found. This is always the shortest possible match.
DEFAULT OUTPUT FROM PCRETEST
This section describes the output when the normal matching function,
This section describes the output when the normal matching function,
pcre[16|32]_exec(), is being used.
When a match succeeds, pcretest outputs the list of captured substrings
that pcre[16|32]_exec() returns, starting with number 0 for the string
that matched the whole pattern. Otherwise, it outputs "No match" when
the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the
partially matching substring when pcre[16|32]_exec() returns
PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was
inspected during the partial match; it may include characters before
the actual match start if a lookbehind assertion, \K, \b, or \B was
involved.) For any other return, pcretest outputs the PCRE negative
error number and a short descriptive phrase. If the error is a failed
UTF string check, the offset of the start of the failing character and
the reason code are also output, provided that the size of the output
vector is at least two. Here is an example of an interactive pcretest
run.
that pcre[16|32]_exec() returns, starting with number 0 for the string
that matched the whole pattern. Otherwise, it outputs "No match" when
the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the
partially matching substring when pcre[16|32]_exec() returns PCRE_ER-
ROR_PARTIAL. (Note that this is the entire substring that was inspected
during the partial match; it may include characters before the actual
match start if a lookbehind assertion, \K, \b, or \B was involved.) For
any other return, pcretest outputs the PCRE negative error number and a
short descriptive phrase. If the error is a failed UTF string check,
the offset of the start of the failing character and the reason code
are also output, provided that the size of the output vector is at
least two. Here is an example of an interactive pcretest run.
$ pcretest
PCRE version 8.13 2011-04-30
@ -892,9 +888,9 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
(Using the normal matching function on this data finds only "tang".)
The longest matching string is always given first (and numbered zero).
After a PCRE_ERROR_PARTIAL return, the output is "Partial match:", fol-
lowed by the partially matching substring. (Note that this is the
entire substring that was inspected during the partial match; it may
include characters before the actual match start if a lookbehind asser-
lowed by the partially matching substring. (Note that this is the en-
tire substring that was inspected during the partial match; it may in-
clude characters before the actual match start if a lookbehind asser-
tion, \K, \b, or \B was involved.)
If /g is present on the pattern, the search for further matches resumes
@ -909,9 +905,9 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
1: tan
0: tan
Since the matching function does not support substring capture, the
escape sequences that are concerned with captured substrings are not
relevant.
Since the matching function does not support substring capture, the es-
cape sequences that are concerned with captured substrings are not rel-
evant.
RESTARTING AFTER A PARTIAL MATCH
@ -942,9 +938,9 @@ CALLOUTS
--->pqrabcdef
0 ^ ^ \d
This output indicates that callout number 0 occurred for a match
attempt starting at the fourth character of the subject string, when
the pointer was at the seventh character of the data, and when the next
This output indicates that callout number 0 occurred for a match at-
tempt starting at the fourth character of the subject string, when the
pointer was at the seventh character of the data, and when the next
pattern item was \d. Just one circumflex is output if the start and
current positions are the same.
@ -963,8 +959,8 @@ CALLOUTS
0: E*
If a pattern contains (*MARK) items, an additional line is output when-
ever a change of latest mark is passed to the callout function. For
example:
ever a change of latest mark is passed to the callout function. For ex-
ample:
re> /a(*MARK:X)bc/C
data> abc
@ -999,8 +995,8 @@ NON-PRINTING CHARACTERS
When pcretest is outputting text that is a matched part of a subject
string, it behaves in the same way, unless a different locale has been
set for the pattern (using the /L modifier). In this case, the
isprint() function to distinguish printing and non-printing characters.
set for the pattern (using the /L modifier). In this case, the is-
print() function to distinguish printing and non-printing characters.
SAVING AND RELOADING COMPILED PATTERNS
@ -1020,14 +1016,14 @@ SAVING AND RELOADING COMPILED PATTERNS
studied with JIT optimization, the JIT data cannot be saved.
The data that is written is binary. The first eight bytes are the
length of the compiled pattern data followed by the length of the
optional study data, each written as four bytes in big-endian order
(most significant byte first). If there is no study data (either the
pattern was not studied, or studying did not return any data), the sec-
ond length is zero. The lengths are followed by an exact copy of the
compiled pattern. If there is additional study data, this (excluding
any JIT data) follows immediately after the compiled pattern. After
writing the file, pcretest expects to read a new pattern.
length of the compiled pattern data followed by the length of the op-
tional study data, each written as four bytes in big-endian order (most
significant byte first). If there is no study data (either the pattern
was not studied, or studying did not return any data), the second
length is zero. The lengths are followed by an exact copy of the com-
piled pattern. If there is additional study data, this (excluding any
JIT data) follows immediately after the compiled pattern. After writing
the file, pcretest expects to read a new pattern.
A saved pattern can be reloaded into pcretest by specifying < and a
file name instead of a pattern. There must be no space between < and
@ -1066,10 +1062,10 @@ SAVING AND RELOADING COMPILED PATTERNS
ing and experimentation. It is not intended for production use because
only a single pattern can be written to a file. Furthermore, there is
no facility for supplying custom character tables for use with a
reloaded pattern. If the original pattern was compiled with custom
tables, an attempt to match a subject string using a reloaded pattern
is likely to cause pcretest to crash. Finally, if you attempt to load
a file that is not in the correct format, the result is undefined.
reloaded pattern. If the original pattern was compiled with custom ta-
bles, an attempt to match a subject string using a reloaded pattern is
likely to cause pcretest to crash. Finally, if you attempt to load a
file that is not in the correct format, the result is undefined.
SEE ALSO
@ -1087,5 +1083,5 @@ AUTHOR
REVISION
Last updated: 23 February 2017
Copyright (c) 1997-2017 University of Cambridge.
Last updated: 10 February 2020
Copyright (c) 1997-2020 University of Cambridge.

1
pcre/m4/libtool.m4 vendored
View File

@ -728,7 +728,6 @@ _LT_CONFIG_SAVE_COMMANDS([
cat <<_LT_EOF >> "$cfgfile"
#! $SHELL
# Generated automatically by $as_me ($PACKAGE) $VERSION
# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`:
# NOTE: Changes made to this file will be lost: look at ltmain.sh.
# Provide generalized library-building support services.

4
pcre/pcre.h.generic
View File

@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE_MAJOR 8
#define PCRE_MINOR 43
#define PCRE_MINOR 44
#define PCRE_PRERELEASE
#define PCRE_DATE 2019-02-23
#define PCRE_DATE 2020-02-12
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE, the appropriate

30
pcre/pcre_compile.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2018 University of Cambridge
Copyright (c) 1997-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -68,7 +68,7 @@ COMPILE_PCREx macro will already be appropriately set. */
/* Macro for setting individual bits in class bitmaps. */
#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7))
#define SETBIT(a,b) a[(b)/8] |= (1U << ((b)&7))
/* Maximum length value to check against when making sure that the integer that
holds the compiled pattern length does not overflow. We make it a bit less than
@ -129,8 +129,8 @@ overrun before it actually does run off the end of the data block. */
/* Private flags added to firstchar and reqchar. */
#define REQ_CASELESS (1 << 0) /* Indicates caselessness */
#define REQ_VARY (1 << 1) /* Reqchar followed non-literal item */
#define REQ_CASELESS (1U << 0) /* Indicates caselessness */
#define REQ_VARY (1U << 1) /* Reqchar followed non-literal item */
/* Negative values for the firstchar and reqchar flags */
#define REQ_UNSET (-2)
#define REQ_NONE (-1)
@ -3611,7 +3611,7 @@ for(;;)
if (chr > 255) break;
class_bitset = (pcre_uint8 *)
((list_ptr == list ? code : base_end) - list_ptr[2]);
if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE;
if ((class_bitset[chr >> 3] & (1U << (chr & 7))) != 0) return FALSE;
break;
#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
@ -7130,17 +7130,19 @@ for (;; ptr++)
int n = 0;
ptr++;
while(IS_DIGIT(*ptr))
{
n = n * 10 + *ptr++ - CHAR_0;
if (n > 255)
{
*errorcodeptr = ERR38;
goto FAILED;
}
}
if (*ptr != CHAR_RIGHT_PARENTHESIS)
{
*errorcodeptr = ERR39;
goto FAILED;
}
if (n > 255)
{
*errorcodeptr = ERR38;
goto FAILED;
}
*code++ = n;
PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */
PUT(code, LINK_SIZE, 0); /* Default length */
@ -7456,7 +7458,7 @@ for (;; ptr++)
{
open_capitem *oc;
recno = GET2(slot, 0);
cd->backref_map |= (recno < 32)? (1 << recno) : 1;
cd->backref_map |= (recno < 32)? (1U << recno) : 1;
if (recno > cd->top_backref) cd->top_backref = recno;
/* Check to see if this back reference is recursive, that it, it
@ -8067,7 +8069,7 @@ for (;; ptr++)
item_hwm_offset = cd->hwm - cd->start_workspace;
*code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF;
PUT2INC(code, 0, recno);
cd->backref_map |= (recno < 32)? (1 << recno) : 1;
cd->backref_map |= (recno < 32)? (1U << recno) : 1;
if (recno > cd->top_backref) cd->top_backref = recno;
/* Check to see if this back reference is recursive, that it, it
@ -8680,7 +8682,7 @@ do {
op == OP_SCBRA || op == OP_SCBRAPOS)
{
int n = GET2(scode, 1+LINK_SIZE);
int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE;
}
@ -8808,7 +8810,7 @@ do {
op == OP_SCBRA || op == OP_SCBRAPOS)
{
int n = GET2(scode, 1+LINK_SIZE);
int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
if (!is_startline(scode, new_map, cd, atomcount, inassert)) return FALSE;
}

6
pcre/pcre_jit_compile.c
View File

@ -3938,10 +3938,10 @@ static sljit_s32 character_to_int32(pcre_uchar chr)
sljit_s32 value = (sljit_s32)chr;
#if defined COMPILE_PCRE8
#define SSE2_COMPARE_TYPE_INDEX 0
return (value << 24) | (value << 16) | (value << 8) | value;
return ((unsigned int)value << 24) | ((unsigned int)value << 16) | ((unsigned int)value << 8) | (unsigned int)value;
#elif defined COMPILE_PCRE16
#define SSE2_COMPARE_TYPE_INDEX 1
return (value << 16) | value;
return ((unsigned int)value << 16) | value;
#elif defined COMPILE_PCRE32
#define SSE2_COMPARE_TYPE_INDEX 2
return value;
@ -8507,7 +8507,7 @@ if (opcode == OP_ONCE)
/* We temporarily encode the needs_control_head in the lowest bit.
Note: on the target architectures of SLJIT the ((x << 1) >> 1) returns
the same value for small signed numbers (including negative numbers). */
BACKTRACK_AS(bracket_backtrack)->u.framesize = (BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
BACKTRACK_AS(bracket_backtrack)->u.framesize = ((unsigned int)BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
}
return cc + repeat_length;
}

4
pcre/pcrecpp.cc
View File

@ -66,7 +66,8 @@ Arg RE::no_arg((void*)NULL);
// inclusive test if we ever needed it. (Note that not only the
// __attribute__ syntax, but also __USER_LABEL_PREFIX__, are
// gnu-specific.)
#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) && !defined(__INTEL_COMPILER)
#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) \
&& !defined(__INTEL_COMPILER) && !defined(__LCC__)
# define ULP_AS_STRING(x) ULP_AS_STRING_INTERNAL(x)
# define ULP_AS_STRING_INTERNAL(x) #x
# define USER_LABEL_PREFIX_STR ULP_AS_STRING(__USER_LABEL_PREFIX__)
@ -91,6 +92,7 @@ static const char *start_options[] = {
"(*LIMIT_RECURSION=",
"(*LIMIT_MATCH=",
"(*CRLF)",
"(*LF)",
"(*CR)",
"(*BSR_UNICODE)",
"(*BSR_ANYCRLF)",

5
pcre/pcreposix.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2018 University of Cambridge
Copyright (c) 1997-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -298,6 +298,7 @@ if (preg->re_pcre == NULL)
(void)pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT,
&re_nsub);
preg->re_nsub = (size_t)re_nsub;
preg->re_erroffset = (size_t)(-1); /* No meaning after successful compile */
return 0;
}
@ -335,8 +336,6 @@ if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL;
if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL;
if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY;
((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */
/* When no string data is being returned, or no vector has been passed in which
to put it, ensure that nmatch is zero. Otherwise, ensure the vector for holding
the return data is large enough. */

12
pcre/pcretest.c
View File

@ -500,7 +500,7 @@ enum {
#if (defined (SUPPORT_PCRE8) + defined (SUPPORT_PCRE16) + \
defined (SUPPORT_PCRE32)) >= 2
#define CHAR_SIZE (1 << pcre_mode)
#define CHAR_SIZE (1U << pcre_mode)
/* There doesn't seem to be an easy way of writing these macros that can cope
with the 3 pairs of bit sizes plus all three bit sizes. So just handle all the
@ -4443,7 +4443,7 @@ while (!done)
/* If there is study data, write it. */
if (extra != NULL)
if (extra != NULL && (extra->flags & PCRE_EXTRA_STUDY_DATA) != 0)
{
if (fwrite(extra->study_data, 1, true_study_size, f) <
true_study_size)
@ -4735,7 +4735,7 @@ while (!done)
if (isdigit(*p)) /* Set copy string */
{
while(isdigit(*p)) n = n * 10 + *p++ - '0';
copystrings |= 1 << n;
copystrings |= 1U << n;
}
else if (isalnum(*p))
{
@ -4798,7 +4798,7 @@ while (!done)
if (isdigit(*p))
{
while(isdigit(*p)) n = n * 10 + *p++ - '0';
getstrings |= 1 << n;
getstrings |= 1U << n;
}
else if (isalnum(*p))
{
@ -5335,7 +5335,7 @@ while (!done)
for (i = 0; i < 32; i++)
{
if ((copystrings & (1 << i)) != 0)
if ((copystrings & (1U << i)) != 0)
{
int rc;
char copybuffer[256];
@ -5400,7 +5400,7 @@ while (!done)
for (i = 0; i < 32; i++)
{
if ((getstrings & (1 << i)) != 0)
if ((getstrings & (1U << i)) != 0)
{
int rc;
const char *substring;

4
pcre/sljit/sljitConfigInternal.h
View File

@ -214,6 +214,10 @@
#define SLJIT_MEMCPY(dest, src, len) memcpy(dest, src, len)
#endif
#ifndef SLJIT_MEMMOVE
#define SLJIT_MEMMOVE(dest, src, len) memmove(dest, src, len)
#endif
#ifndef SLJIT_ZEROMEM
#define SLJIT_ZEROMEM(dest, len) memset(dest, 0, len)
#endif

28
pcre/sljit/sljitExecAllocator.c
View File

@ -118,10 +118,20 @@ static SLJIT_INLINE int get_map_jit_flag()
if (map_jit_flag == -1) {
struct utsname name;
map_jit_flag = 0;
uname(&name);
/* Kernel version for 10.14.0 (Mojave) */
map_jit_flag = (atoi(name.release) >= 18) ? MAP_JIT : 0;
if (atoi(name.release) >= 18) {
/* Only use MAP_JIT if a hardened runtime is used, because MAP_JIT is incompatible with fork(). */
void *ptr = mmap(NULL, getpagesize(), PROT_WRITE|PROT_EXEC, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
if (ptr == MAP_FAILED) {
map_jit_flag = MAP_JIT;
} else {
munmap(ptr, getpagesize());
}
}
}
return map_jit_flag;
@ -137,6 +147,7 @@ static SLJIT_INLINE int get_map_jit_flag()
static SLJIT_INLINE void* alloc_chunk(sljit_uw size)
{
void *retval;
const int prot = PROT_READ | PROT_WRITE | PROT_EXEC;
#ifdef MAP_ANON
@ -146,16 +157,25 @@ static SLJIT_INLINE void* alloc_chunk(sljit_uw size)
flags |= get_map_jit_flag();
#endif
retval = mmap(NULL, size, PROT_READ | PROT_WRITE | PROT_EXEC, flags, -1, 0);
retval = mmap(NULL, size, prot, flags, -1, 0);
#else /* !MAP_ANON */
if (dev_zero < 0) {
if (open_dev_zero())
return NULL;
}
retval = mmap(NULL, size, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, dev_zero, 0);
retval = mmap(NULL, size, prot, MAP_PRIVATE, dev_zero, 0);
#endif /* MAP_ANON */
return (retval != MAP_FAILED) ? retval : NULL;
if (retval == MAP_FAILED)
retval = NULL;
else {
if (mprotect(retval, size, prot) < 0) {
munmap(retval, size);
retval = NULL;
}
}
return retval;
}
static SLJIT_INLINE void free_chunk(void *chunk, sljit_uw size)

80
pcre/sljit/sljitLir.c
View File

@ -144,6 +144,7 @@
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
# define PATCH_MD 0x10
#endif
# define TYPE_SHIFT 13
#endif
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5) || (defined SLJIT_CONFIG_ARM_V7 && SLJIT_CONFIG_ARM_V7)
@ -201,15 +202,16 @@
# define IS_CALL 0x010
# define IS_BIT26_COND 0x020
# define IS_BIT16_COND 0x040
# define IS_BIT23_COND 0x080
# define IS_COND (IS_BIT26_COND | IS_BIT16_COND)
# define IS_COND (IS_BIT26_COND | IS_BIT16_COND | IS_BIT23_COND)
# define PATCH_B 0x080
# define PATCH_J 0x100
# define PATCH_B 0x100
# define PATCH_J 0x200
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
# define PATCH_ABS32 0x200
# define PATCH_ABS48 0x400
# define PATCH_ABS32 0x400
# define PATCH_ABS48 0x800
#endif
/* instruction types */
@ -520,6 +522,12 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_target(struct sljit_jump *jump, sljit_uw
}
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_put_label(struct sljit_put_label *put_label, struct sljit_label *label)
{
if (SLJIT_LIKELY(!!put_label))
put_label->label = label;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_current_flags(struct sljit_compiler *compiler, sljit_s32 current_flags)
{
SLJIT_UNUSED_ARG(compiler);
@ -619,6 +627,30 @@ static SLJIT_INLINE sljit_s32 get_arg_count(sljit_s32 arg_types)
return arg_count;
}
#if !(defined SLJIT_CONFIG_X86 && SLJIT_CONFIG_X86)
static SLJIT_INLINE sljit_uw compute_next_addr(struct sljit_label *label, struct sljit_jump *jump,
struct sljit_const *const_, struct sljit_put_label *put_label)
{
sljit_uw result = ~(sljit_uw)0;
if (label)
result = label->size;
if (jump && jump->addr < result)
result = jump->addr;
if (const_ && const_->addr < result)
result = const_->addr;
if (put_label && put_label->addr < result)
result = put_label->addr;
return result;
}
#endif /* !SLJIT_CONFIG_X86 */
static SLJIT_INLINE void set_emit_enter(struct sljit_compiler *compiler,
sljit_s32 options, sljit_s32 args, sljit_s32 scratches, sljit_s32 saveds,
sljit_s32 fscratches, sljit_s32 fsaveds, sljit_s32 local_size)
@ -686,6 +718,19 @@ static SLJIT_INLINE void set_const(struct sljit_const *const_, struct sljit_comp
compiler->last_const = const_;
}
static SLJIT_INLINE void set_put_label(struct sljit_put_label *put_label, struct sljit_compiler *compiler, sljit_uw offset)
{
put_label->next = NULL;
put_label->label = NULL;
put_label->addr = compiler->size - offset;
put_label->flags = 0;
if (compiler->last_put_label)
compiler->last_put_label->next = put_label;
else
compiler->put_labels = put_label;
compiler->last_put_label = put_label;
}
#define ADDRESSING_DEPENDS_ON(exp, reg) \
(((exp) & SLJIT_MEM) && (((exp) & REG_MASK) == reg || OFFS_REG(exp) == reg))
@ -1904,6 +1949,21 @@ static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_emit_const(struct sljit_compil
CHECK_RETURN_OK;
}
static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
#if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS)
FUNCTION_CHECK_DST(dst, dstw, 0);
#endif
#if (defined SLJIT_VERBOSE && SLJIT_VERBOSE)
if (SLJIT_UNLIKELY(!!compiler->verbose)) {
fprintf(compiler->verbose, " put_label ");
sljit_verbose_param(compiler, dst, dstw);
fprintf(compiler->verbose, "\n");
}
#endif
CHECK_RETURN_OK;
}
#endif /* SLJIT_ARGUMENT_CHECKS || SLJIT_VERBOSE */
#define SELECT_FOP1_OPERATION_WITH_CHECKS(compiler, op, dst, dstw, src, srcw) \
@ -2580,6 +2640,14 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
return NULL;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
SLJIT_UNUSED_ARG(compiler);
SLJIT_UNUSED_ARG(dst);
SLJIT_UNUSED_ARG(dstw);
return NULL;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_target, sljit_sw executable_offset)
{
SLJIT_UNUSED_ARG(addr);
@ -2596,4 +2664,4 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta
SLJIT_UNREACHABLE();
}
#endif
#endif /* !SLJIT_CONFIG_UNSUPPORTED */

22
pcre/sljit/sljitLir.h
View File

@ -348,13 +348,20 @@ struct sljit_label {
struct sljit_jump {
struct sljit_jump *next;
sljit_uw addr;
sljit_sw flags;
sljit_uw flags;
union {
sljit_uw target;
struct sljit_label* label;
struct sljit_label *label;
} u;
};
struct sljit_put_label {
struct sljit_put_label *next;
struct sljit_label *label;
sljit_uw addr;
sljit_uw flags;
};
struct sljit_const {
struct sljit_const *next;
sljit_uw addr;
@ -366,10 +373,12 @@ struct sljit_compiler {
struct sljit_label *labels;
struct sljit_jump *jumps;
struct sljit_put_label *put_labels;
struct sljit_const *consts;
struct sljit_label *last_label;
struct sljit_jump *last_jump;
struct sljit_const *last_const;
struct sljit_put_label *last_put_label;
void *allocator_data;
struct sljit_memory_fragment *buf;
@ -1314,10 +1323,17 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fmem(struct sljit_compiler *compil
Flags: - (may destroy flags) */
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_get_local_base(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw offset);
/* The constant can be changed runtime (see: sljit_set_const)
/* Store a value that can be changed runtime (see: sljit_get_const_addr / sljit_set_const)
Flags: - (does not modify flags) */
SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw init_value);
/* Store the value of a label (see: sljit_set_put_label)
Flags: - (does not modify flags) */
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw);
/* Set the value stored by put_label to this label. */
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_put_label(struct sljit_put_label *put_label, struct sljit_label *label);
/* After the code generation the address for label, jump and const instructions
are computed. Since these structures are freed by sljit_free_compiler, the
addresses must be preserved by the user program elsewere. */

130
pcre/sljit/sljitNativeARM_32.c
View File

@ -583,8 +583,9 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_uw *buf_end;
sljit_uw size;
sljit_uw word_count;
sljit_uw next_addr;
sljit_sw executable_offset;
sljit_sw jump_addr;
sljit_sw addr;
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
sljit_uw cpool_size;
sljit_uw cpool_skip_alignment;
@ -597,6 +598,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -625,11 +627,13 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
word_count = 0;
next_addr = 1;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
if (label && label->size == 0) {
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code, executable_offset);
@ -662,6 +666,8 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
next_addr = compute_next_addr(label, jump, const_, put_label);
}
}
}
@ -669,35 +675,45 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
else if ((*buf_ptr & 0xff000000) != PUSH_POOL) {
#endif
*code_ptr = *buf_ptr++;
if (next_addr == word_count) {
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
SLJIT_ASSERT(!put_label || put_label->addr >= word_count);
/* These structures are ordered by their address. */
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
if (jump && jump->addr == word_count) {
if (jump && jump->addr == word_count) {
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
if (detect_jump_type(jump, code_ptr, code, executable_offset))
code_ptr--;
jump->addr = (sljit_uw)code_ptr;
if (detect_jump_type(jump, code_ptr, code, executable_offset))
code_ptr--;
jump->addr = (sljit_uw)code_ptr;
#else
jump->addr = (sljit_uw)(code_ptr - 2);
if (detect_jump_type(jump, code_ptr, code, executable_offset))
code_ptr -= 2;
jump->addr = (sljit_uw)(code_ptr - 2);
if (detect_jump_type(jump, code_ptr, code, executable_offset))
code_ptr -= 2;
#endif
jump = jump->next;
}
if (label && label->size == word_count) {
/* code_ptr can be affected above. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr + 1, executable_offset);
label->size = (code_ptr + 1) - code;
label = label->next;
}
if (const_ && const_->addr == word_count) {
jump = jump->next;
}
if (label && label->size == word_count) {
/* code_ptr can be affected above. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr + 1, executable_offset);
label->size = (code_ptr + 1) - code;
label = label->next;
}
if (const_ && const_->addr == word_count) {
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
const_->addr = (sljit_uw)code_ptr;
const_->addr = (sljit_uw)code_ptr;
#else
const_->addr = (sljit_uw)(code_ptr - 1);
const_->addr = (sljit_uw)(code_ptr - 1);
#endif
const_ = const_->next;
const_ = const_->next;
}
if (put_label && put_label->addr == word_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr++;
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
@ -725,6 +741,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
SLJIT_ASSERT(cpool_size == 0);
@ -755,15 +772,15 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
buf_ptr = (sljit_uw *)jump->addr;
if (jump->flags & PATCH_B) {
jump_addr = (sljit_sw)SLJIT_ADD_EXEC_OFFSET(buf_ptr + 2, executable_offset);
addr = (sljit_sw)SLJIT_ADD_EXEC_OFFSET(buf_ptr + 2, executable_offset);
if (!(jump->flags & JUMP_ADDR)) {
SLJIT_ASSERT(jump->flags & JUMP_LABEL);
SLJIT_ASSERT(((sljit_sw)jump->u.label->addr - jump_addr) <= 0x01ffffff && ((sljit_sw)jump->u.label->addr - jump_addr) >= -0x02000000);
*buf_ptr |= (((sljit_sw)jump->u.label->addr - jump_addr) >> 2) & 0x00ffffff;
SLJIT_ASSERT(((sljit_sw)jump->u.label->addr - addr) <= 0x01ffffff && ((sljit_sw)jump->u.label->addr - addr) >= -0x02000000);
*buf_ptr |= (((sljit_sw)jump->u.label->addr - addr) >> 2) & 0x00ffffff;
}
else {
SLJIT_ASSERT(((sljit_sw)jump->u.target - jump_addr) <= 0x01ffffff && ((sljit_sw)jump->u.target - jump_addr) >= -0x02000000);
*buf_ptr |= (((sljit_sw)jump->u.target - jump_addr) >> 2) & 0x00ffffff;
SLJIT_ASSERT(((sljit_sw)jump->u.target - addr) <= 0x01ffffff && ((sljit_sw)jump->u.target - addr) >= -0x02000000);
*buf_ptr |= (((sljit_sw)jump->u.target - addr) >> 2) & 0x00ffffff;
}
}
else if (jump->flags & SLJIT_REWRITABLE_JUMP) {
@ -813,6 +830,22 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
}
#endif
put_label = compiler->put_labels;
while (put_label) {
addr = put_label->label->addr;
buf_ptr = (sljit_uw*)put_label->addr;
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
SLJIT_ASSERT((buf_ptr[0] & 0xffff0000) == 0xe59f0000);
buf_ptr[((buf_ptr[0] & 0xfff) >> 2) + 2] = addr;
#else
SLJIT_ASSERT((buf_ptr[-1] & 0xfff00000) == MOVW && (buf_ptr[0] & 0xfff00000) == MOVT);
buf_ptr[-1] |= ((addr << 4) & 0xf0000) | (addr & 0xfff);
buf_ptr[0] |= ((addr >> 12) & 0xf0000) | ((addr >> 16) & 0xfff);
#endif
put_label = put_label->next;
}
SLJIT_ASSERT(code_ptr - code <= (sljit_s32)size);
compiler->error = SLJIT_ERR_COMPILED;
@ -2639,23 +2672,23 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_mem(struct sljit_compiler *compile
SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw init_value)
{
struct sljit_const *const_;
sljit_s32 reg;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value));
ADJUST_LOCAL_OFFSET(dst, dstw);
const_ = (struct sljit_const*)ensure_abuf(compiler, sizeof(struct sljit_const));
PTR_FAIL_IF(!const_);
reg = SLOW_IS_REG(dst) ? dst : TMP_REG2;
dst_r = SLOW_IS_REG(dst) ? dst : TMP_REG2;
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
PTR_FAIL_IF(push_inst_with_unique_literal(compiler, EMIT_DATA_TRANSFER(WORD_SIZE | LOAD_DATA, 1, reg, TMP_PC, 0), init_value));
PTR_FAIL_IF(push_inst_with_unique_literal(compiler, EMIT_DATA_TRANSFER(WORD_SIZE | LOAD_DATA, 1, dst_r, TMP_PC, 0), init_value));
compiler->patches++;
#else
PTR_FAIL_IF(emit_imm(compiler, reg, init_value));
PTR_FAIL_IF(emit_imm(compiler, dst_r, init_value));
#endif
const_ = (struct sljit_const*)ensure_abuf(compiler, sizeof(struct sljit_const));
PTR_FAIL_IF(!const_);
set_const(const_, compiler);
if (dst & SLJIT_MEM)
@ -2663,6 +2696,33 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
dst_r = SLOW_IS_REG(dst) ? dst : TMP_REG2;
#if (defined SLJIT_CONFIG_ARM_V5 && SLJIT_CONFIG_ARM_V5)
PTR_FAIL_IF(push_inst_with_unique_literal(compiler, EMIT_DATA_TRANSFER(WORD_SIZE | LOAD_DATA, 1, dst_r, TMP_PC, 0), 0));
compiler->patches++;
#else
PTR_FAIL_IF(emit_imm(compiler, dst_r, 0));
#endif
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op_mem(compiler, WORD_SIZE, TMP_REG2, dst, dstw, TMP_REG1));
return put_label;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_target, sljit_sw executable_offset)
{
inline_set_jump_addr(addr, executable_offset, new_target, 1);

111
pcre/sljit/sljitNativeARM_64.c
View File

@ -161,7 +161,7 @@ static SLJIT_INLINE void modify_imm64_const(sljit_ins* inst, sljit_uw new_imm)
inst[3] = MOVK | dst | ((new_imm >> 48) << 5) | (3 << 21);
}
static SLJIT_INLINE sljit_s32 detect_jump_type(struct sljit_jump *jump, sljit_ins *code_ptr, sljit_ins *code, sljit_sw executable_offset)
static SLJIT_INLINE sljit_sw detect_jump_type(struct sljit_jump *jump, sljit_ins *code_ptr, sljit_ins *code, sljit_sw executable_offset)
{
sljit_sw diff;
sljit_uw target_addr;
@ -196,14 +196,14 @@ static SLJIT_INLINE sljit_s32 detect_jump_type(struct sljit_jump *jump, sljit_in
return 4;
}
if (target_addr <= 0xffffffffl) {
if (target_addr < 0x100000000l) {
if (jump->flags & IS_COND)
code_ptr[-5] -= (2 << 5);
code_ptr[-2] = code_ptr[0];
return 2;
}
if (target_addr <= 0xffffffffffffl) {
if (target_addr < 0x1000000000000l) {
if (jump->flags & IS_COND)
code_ptr[-5] -= (1 << 5);
jump->flags |= PATCH_ABS48;
@ -215,6 +215,22 @@ static SLJIT_INLINE sljit_s32 detect_jump_type(struct sljit_jump *jump, sljit_in
return 0;
}
static SLJIT_INLINE sljit_sw put_label_get_length(struct sljit_put_label *put_label, sljit_uw max_label)
{
if (max_label < 0x100000000l) {
put_label->flags = 0;
return 2;
}
if (max_label < 0x1000000000000l) {
put_label->flags = 1;
return 1;
}
put_label->flags = 2;
return 0;
}
SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compiler)
{
struct sljit_memory_fragment *buf;
@ -223,6 +239,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_ins *buf_ptr;
sljit_ins *buf_end;
sljit_uw word_count;
sljit_uw next_addr;
sljit_sw executable_offset;
sljit_uw addr;
sljit_s32 dst;
@ -230,6 +247,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -241,34 +259,47 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
word_count = 0;
next_addr = 0;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
do {
buf_ptr = (sljit_ins*)buf->memory;
buf_end = buf_ptr + (buf->used_size >> 2);
do {
*code_ptr = *buf_ptr++;
/* These structures are ordered by their address. */
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
if (label && label->size == word_count) {
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
jump->addr = (sljit_uw)(code_ptr - 4);
code_ptr -= detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
if (next_addr == word_count) {
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
SLJIT_ASSERT(!put_label || put_label->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
jump->addr = (sljit_uw)(code_ptr - 4);
code_ptr -= detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
}
if (put_label && put_label->addr == word_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)(code_ptr - 3);
code_ptr -= put_label_get_length(put_label, (sljit_uw)(SLJIT_ADD_EXEC_OFFSET(code, executable_offset) + put_label->label->size));
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr ++;
word_count ++;
@ -286,6 +317,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
SLJIT_ASSERT(code_ptr - code <= (sljit_sw)compiler->size);
jump = compiler->jumps;
@ -323,6 +355,23 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
put_label = compiler->put_labels;
while (put_label) {
addr = put_label->label->addr;
buf_ptr = (sljit_ins *)put_label->addr;
buf_ptr[0] |= (addr & 0xffff) << 5;
buf_ptr[1] |= ((addr >> 16) & 0xffff) << 5;
if (put_label->flags >= 1)
buf_ptr[2] |= ((addr >> 32) & 0xffff) << 5;
if (put_label->flags >= 2)
buf_ptr[3] |= ((addr >> 48) & 0xffff) << 5;
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins);
@ -1947,6 +1996,28 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG1;
PTR_FAIL_IF(emit_imm64_const(compiler, dst_r, 0));
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 1);
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op_mem(compiler, WORD_SIZE | STORE, dst_r, dst, dstw, TMP_REG2));
return put_label;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_target, sljit_sw executable_offset)
{
sljit_ins* inst = (sljit_ins*)addr;

76
pcre/sljit/sljitNativeARM_T2_32.c
View File

@ -365,11 +365,13 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_u16 *buf_ptr;
sljit_u16 *buf_end;
sljit_uw half_count;
sljit_uw next_addr;
sljit_sw executable_offset;
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -381,34 +383,46 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
half_count = 0;
next_addr = 0;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
do {
buf_ptr = (sljit_u16*)buf->memory;
buf_end = buf_ptr + (buf->used_size >> 1);
do {
*code_ptr = *buf_ptr++;
/* These structures are ordered by their address. */
SLJIT_ASSERT(!label || label->size >= half_count);
SLJIT_ASSERT(!jump || jump->addr >= half_count);
SLJIT_ASSERT(!const_ || const_->addr >= half_count);
if (label && label->size == half_count) {
label->addr = ((sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset)) | 0x1;
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == half_count) {
jump->addr = (sljit_uw)code_ptr - ((jump->flags & IS_COND) ? 10 : 8);
code_ptr -= detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == half_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
if (next_addr == half_count) {
SLJIT_ASSERT(!label || label->size >= half_count);
SLJIT_ASSERT(!jump || jump->addr >= half_count);
SLJIT_ASSERT(!const_ || const_->addr >= half_count);
SLJIT_ASSERT(!put_label || put_label->addr >= half_count);
/* These structures are ordered by their address. */
if (label && label->size == half_count) {
label->addr = ((sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset)) | 0x1;
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == half_count) {
jump->addr = (sljit_uw)code_ptr - ((jump->flags & IS_COND) ? 10 : 8);
code_ptr -= detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == half_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
}
if (put_label && put_label->addr == half_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr ++;
half_count ++;
@ -426,6 +440,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
SLJIT_ASSERT(code_ptr - code <= (sljit_sw)compiler->size);
jump = compiler->jumps;
@ -434,6 +449,12 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
put_label = compiler->put_labels;
while (put_label) {
modify_imm32_const((sljit_u16 *)put_label->addr, put_label->label->addr);
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
compiler->executable_size = (code_ptr - code) * sizeof(sljit_u16);
@ -2311,6 +2332,27 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG1;
PTR_FAIL_IF(emit_imm32_const(compiler, dst_r, 0));
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op_mem(compiler, WORD_SIZE | STORE, dst_r, dst, dstw, TMP_REG2));
return put_label;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_target, sljit_sw executable_offset)
{
sljit_u16 *inst = (sljit_u16*)addr;

13
pcre/sljit/sljitNativeMIPS_32.c
View File

@ -368,16 +368,21 @@ static SLJIT_INLINE sljit_s32 emit_single_op(struct sljit_compiler *compiler, sl
SLJIT_ASSERT(!(flags & SRC2_IMM));
if (GET_FLAG_TYPE(op) != SLJIT_MUL_OVERFLOW) {
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1) || (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
return push_inst(compiler, MUL | S(src1) | T(src2) | D(dst), DR(dst));
#else
#else /* !SLJIT_MIPS_R1 && !SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, MULT | S(src1) | T(src2), MOVABLE_INS));
return push_inst(compiler, MFLO | D(dst), DR(dst));
#endif
#endif /* SLJIT_MIPS_R1 || SLJIT_MIPS_R6 */
}
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
FAIL_IF(push_inst(compiler, MUL | S(src1) | T(src2) | D(dst), DR(dst)));
FAIL_IF(push_inst(compiler, MUH | S(src1) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG));
#else /* !SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, MULT | S(src1) | T(src2), MOVABLE_INS));
FAIL_IF(push_inst(compiler, MFHI | DA(EQUAL_FLAG), EQUAL_FLAG));
FAIL_IF(push_inst(compiler, MFLO | D(dst), DR(dst)));
#endif /* SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, SRA | T(dst) | DA(OTHER_FLAG) | SH_IMM(31), OTHER_FLAG));
return push_inst(compiler, SUBU | SA(EQUAL_FLAG) | TA(OTHER_FLAG) | DA(OTHER_FLAG), OTHER_FLAG);
@ -420,6 +425,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_ta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT((inst[0] & 0xffe00000) == LUI && (inst[1] & 0xfc000000) == ORI);
inst[0] = (inst[0] & 0xffff0000) | ((new_target >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_target & 0xffff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);
@ -430,6 +436,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT((inst[0] & 0xffe00000) == LUI && (inst[1] & 0xfc000000) == ORI);
inst[0] = (inst[0] & 0xffff0000) | ((new_constant >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_constant & 0xffff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);

13
pcre/sljit/sljitNativeMIPS_64.c
View File

@ -459,19 +459,26 @@ static SLJIT_INLINE sljit_s32 emit_single_op(struct sljit_compiler *compiler, sl
SLJIT_ASSERT(!(flags & SRC2_IMM));
if (GET_FLAG_TYPE(op) != SLJIT_MUL_OVERFLOW) {
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
return push_inst(compiler, SELECT_OP(DMUL, MUL) | S(src1) | T(src2) | D(dst), DR(dst));
#elif (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
if (op & SLJIT_I32_OP)
return push_inst(compiler, MUL | S(src1) | T(src2) | D(dst), DR(dst));
FAIL_IF(push_inst(compiler, DMULT | S(src1) | T(src2), MOVABLE_INS));
return push_inst(compiler, MFLO | D(dst), DR(dst));
#else
#else /* !SLJIT_MIPS_R6 && !SLJIT_MIPS_R1 */
FAIL_IF(push_inst(compiler, SELECT_OP(DMULT, MULT) | S(src1) | T(src2), MOVABLE_INS));
return push_inst(compiler, MFLO | D(dst), DR(dst));
#endif
#endif /* SLJIT_MIPS_R6 */
}
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
FAIL_IF(push_inst(compiler, SELECT_OP(DMUL, MUL) | S(src1) | T(src2) | D(dst), DR(dst)));
FAIL_IF(push_inst(compiler, SELECT_OP(DMUH, MUH) | S(src1) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG));
#else /* !SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, SELECT_OP(DMULT, MULT) | S(src1) | T(src2), MOVABLE_INS));
FAIL_IF(push_inst(compiler, MFHI | DA(EQUAL_FLAG), EQUAL_FLAG));
FAIL_IF(push_inst(compiler, MFLO | D(dst), DR(dst)));
#endif /* SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, SELECT_OP(DSRA32, SRA) | T(dst) | DA(OTHER_FLAG) | SH_IMM(31), OTHER_FLAG));
return push_inst(compiler, SELECT_OP(DSUBU, SUBU) | SA(EQUAL_FLAG) | TA(OTHER_FLAG) | DA(OTHER_FLAG), OTHER_FLAG);

319
pcre/sljit/sljitNativeMIPS_common.c
View File

@ -27,17 +27,31 @@
/* Latest MIPS architecture. */
/* Automatically detect SLJIT_MIPS_R1 */
#if (defined __mips_isa_rev) && (__mips_isa_rev >= 6)
#define SLJIT_MIPS_R6 1
#endif
SLJIT_API_FUNC_ATTRIBUTE const char* sljit_get_platform_name(void)
{
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
return "MIPS32-R6" SLJIT_CPUINFO;
#else /* !SLJIT_CONFIG_MIPS_32 */
return "MIPS64-R6" SLJIT_CPUINFO;
#endif /* SLJIT_CONFIG_MIPS_32 */
#elif (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
return "MIPS32-R1" SLJIT_CPUINFO;
#else
#else /* !SLJIT_CONFIG_MIPS_32 */
return "MIPS64-R1" SLJIT_CPUINFO;
#endif
#endif /* SLJIT_CONFIG_MIPS_32 */
#else /* SLJIT_MIPS_R1 */
return "MIPS III" SLJIT_CPUINFO;
#endif
#endif /* SLJIT_MIPS_R6 */
}
/* Length of an instruction word
@ -62,6 +76,7 @@ typedef sljit_u32 sljit_ins;
#define TMP_FREG1 (SLJIT_NUMBER_OF_FLOAT_REGISTERS + 1)
#define TMP_FREG2 (SLJIT_NUMBER_OF_FLOAT_REGISTERS + 2)
#define TMP_FREG3 (SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3)
static const sljit_u8 reg_map[SLJIT_NUMBER_OF_REGISTERS + 5] = {
0, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 24, 23, 22, 21, 20, 19, 18, 17, 16, 29, 4, 25, 31
@ -69,14 +84,14 @@ static const sljit_u8 reg_map[SLJIT_NUMBER_OF_REGISTERS + 5] = {
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
0, 0, 14, 2, 4, 6, 8, 12, 10
static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 4] = {
0, 0, 14, 2, 4, 6, 8, 12, 10, 16
};
#else
static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
0, 0, 13, 14, 15, 16, 17, 12, 18
static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 4] = {
0, 0, 13, 14, 15, 16, 17, 12, 18, 10
};
#endif
@ -102,6 +117,11 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define FR(dr) (freg_map[dr])
#define HI(opcode) ((opcode) << 26)
#define LO(opcode) (opcode)
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
/* CMP.cond.fmt */
/* S = (20 << 21) D = (21 << 21) */
#define CMP_FMT_S (20 << 21)
#endif /* SLJIT_MIPS_R6 */
/* S = (16 << 21) D = (17 << 21) */
#define FMT_S (16 << 21)
#define FMT_D (17 << 21)
@ -114,8 +134,13 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define ANDI (HI(12))
#define B (HI(4))
#define BAL (HI(1) | (17 << 16))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define BC1EQZ (HI(17) | (9 << 21) | FT(TMP_FREG3))
#define BC1NEZ (HI(17) | (13 << 21) | FT(TMP_FREG3))
#else /* !SLJIT_MIPS_R6 */
#define BC1F (HI(17) | (8 << 21))
#define BC1T (HI(17) | (8 << 21) | (1 << 16))
#endif /* SLJIT_MIPS_R6 */
#define BEQ (HI(4))
#define BGEZ (HI(1) | (1 << 16))
#define BGTZ (HI(7))
@ -124,20 +149,42 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define BNE (HI(5))
#define BREAK (HI(0) | LO(13))
#define CFC1 (HI(17) | (2 << 21))
#define C_UN_S (HI(17) | FMT_S | LO(49))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define C_UEQ_S (HI(17) | CMP_FMT_S | LO(3))
#define C_ULE_S (HI(17) | CMP_FMT_S | LO(7))
#define C_ULT_S (HI(17) | CMP_FMT_S | LO(5))
#define C_UN_S (HI(17) | CMP_FMT_S | LO(1))
#define C_FD (FD(TMP_FREG3))
#else /* !SLJIT_MIPS_R6 */
#define C_UEQ_S (HI(17) | FMT_S | LO(51))
#define C_ULE_S (HI(17) | FMT_S | LO(55))
#define C_ULT_S (HI(17) | FMT_S | LO(53))
#define C_UN_S (HI(17) | FMT_S | LO(49))
#define C_FD (0)
#endif /* SLJIT_MIPS_R6 */
#define CVT_S_S (HI(17) | FMT_S | LO(32))
#define DADDIU (HI(25))
#define DADDU (HI(0) | LO(45))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define DDIV (HI(0) | (2 << 6) | LO(30))
#define DDIVU (HI(0) | (2 << 6) | LO(31))
#define DMOD (HI(0) | (3 << 6) | LO(30))
#define DMODU (HI(0) | (3 << 6) | LO(31))
#define DIV (HI(0) | (2 << 6) | LO(26))
#define DIVU (HI(0) | (2 << 6) | LO(27))
#define DMUH (HI(0) | (3 << 6) | LO(28))
#define DMUHU (HI(0) | (3 << 6) | LO(29))
#define DMUL (HI(0) | (2 << 6) | LO(28))
#define DMULU (HI(0) | (2 << 6) | LO(29))
#else /* !SLJIT_MIPS_R6 */
#define DDIV (HI(0) | LO(30))
#define DDIVU (HI(0) | LO(31))
#define DIV (HI(0) | LO(26))
#define DIVU (HI(0) | LO(27))
#define DIV_S (HI(17) | FMT_S | LO(3))
#define DMULT (HI(0) | LO(28))
#define DMULTU (HI(0) | LO(29))
#endif /* SLJIT_MIPS_R6 */
#define DIV_S (HI(17) | FMT_S | LO(3))
#define DSLL (HI(0) | LO(56))
#define DSLL32 (HI(0) | LO(60))
#define DSLLV (HI(0) | LO(20))
@ -151,18 +198,34 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define J (HI(2))
#define JAL (HI(3))
#define JALR (HI(0) | LO(9))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define JR (HI(0) | LO(9))
#else /* !SLJIT_MIPS_R6 */
#define JR (HI(0) | LO(8))
#endif /* SLJIT_MIPS_R6 */
#define LD (HI(55))
#define LUI (HI(15))
#define LW (HI(35))
#define MFC1 (HI(17))
#if !(defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define MFHI (HI(0) | LO(16))
#define MFLO (HI(0) | LO(18))
#else /* SLJIT_MIPS_R6 */
#define MOD (HI(0) | (3 << 6) | LO(26))
#define MODU (HI(0) | (3 << 6) | LO(27))
#endif /* !SLJIT_MIPS_R6 */
#define MOV_S (HI(17) | FMT_S | LO(6))
#define MTC1 (HI(17) | (4 << 21))
#define MUL_S (HI(17) | FMT_S | LO(2))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define MUH (HI(0) | (3 << 6) | LO(24))
#define MUHU (HI(0) | (3 << 6) | LO(25))
#define MUL (HI(0) | (2 << 6) | LO(24))
#define MULU (HI(0) | (2 << 6) | LO(25))
#else /* !SLJIT_MIPS_R6 */
#define MULT (HI(0) | LO(24))
#define MULTU (HI(0) | LO(25))
#endif /* SLJIT_MIPS_R6 */
#define MUL_S (HI(17) | FMT_S | LO(2))
#define NEG_S (HI(17) | FMT_S | LO(7))
#define NOP (HI(0) | LO(0))
#define NOR (HI(0) | LO(39))
@ -188,14 +251,18 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define XOR (HI(0) | LO(38))
#define XORI (HI(14))
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1) || (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define CLZ (HI(28) | LO(32))
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define DCLZ (LO(18))
#else /* !SLJIT_MIPS_R6 */
#define DCLZ (HI(28) | LO(36))
#define MOVF (HI(0) | (0 << 16) | LO(1))
#define MOVN (HI(0) | LO(11))
#define MOVT (HI(0) | (1 << 16) | LO(1))
#define MOVZ (HI(0) | LO(10))
#define MUL (HI(28) | LO(2))
#endif /* SLJIT_MIPS_R6 */
#define PREF (HI(51))
#define PREFX (HI(19) | LO(15))
#define SEB (HI(31) | (16 << 6) | LO(32))
@ -234,7 +301,13 @@ static sljit_s32 push_inst(struct sljit_compiler *compiler, sljit_ins ins, sljit
static SLJIT_INLINE sljit_ins invert_branch(sljit_s32 flags)
{
return (flags & IS_BIT26_COND) ? (1 << 26) : (1 << 16);
if (flags & IS_BIT26_COND)
return (1 << 26);
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
if (flags & IS_BIT23_COND)
return (1 << 23);
#endif /* SLJIT_MIPS_R6 */
return (1 << 16);
}
static SLJIT_INLINE sljit_ins* detect_jump_type(struct sljit_jump *jump, sljit_ins *code_ptr, sljit_ins *code, sljit_sw executable_offset)
@ -376,6 +449,55 @@ static __attribute__ ((noinline)) void sljit_cache_flush(void* code, void* code_
}
#endif
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
static SLJIT_INLINE sljit_sw put_label_get_length(struct sljit_put_label *put_label, sljit_uw max_label)
{
if (max_label < 0x80000000l) {
put_label->flags = 0;
return 1;
}
if (max_label < 0x800000000000l) {
put_label->flags = 1;
return 3;
}
put_label->flags = 2;
return 5;
}
static SLJIT_INLINE void put_label_set(struct sljit_put_label *put_label)
{
sljit_uw addr = put_label->label->addr;
sljit_ins *inst = (sljit_ins *)put_label->addr;
sljit_s32 reg = *inst;
if (put_label->flags == 0) {
SLJIT_ASSERT(addr < 0x80000000l);
inst[0] = LUI | T(reg) | IMM(addr >> 16);
}
else if (put_label->flags == 1) {
SLJIT_ASSERT(addr < 0x800000000000l);
inst[0] = LUI | T(reg) | IMM(addr >> 32);
inst[1] = ORI | S(reg) | T(reg) | IMM((addr >> 16) & 0xffff);
inst[2] = DSLL | T(reg) | D(reg) | SH_IMM(16);
inst += 2;
}
else {
inst[0] = LUI | T(reg) | IMM(addr >> 48);
inst[1] = ORI | S(reg) | T(reg) | IMM((addr >> 32) & 0xffff);
inst[2] = DSLL | T(reg) | D(reg) | SH_IMM(16);
inst[3] = ORI | S(reg) | T(reg) | IMM((addr >> 16) & 0xffff);
inst[4] = DSLL | T(reg) | D(reg) | SH_IMM(16);
inst += 4;
}
inst[1] = ORI | S(reg) | T(reg) | IMM(addr & 0xffff);
}
#endif
SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compiler)
{
struct sljit_memory_fragment *buf;
@ -384,12 +506,14 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_ins *buf_ptr;
sljit_ins *buf_end;
sljit_uw word_count;
sljit_uw next_addr;
sljit_sw executable_offset;
sljit_uw addr;
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -401,39 +525,54 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
word_count = 0;
next_addr = 0;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
do {
buf_ptr = (sljit_ins*)buf->memory;
buf_end = buf_ptr + (buf->used_size >> 2);
do {
*code_ptr = *buf_ptr++;
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
if (next_addr == word_count) {
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
SLJIT_ASSERT(!put_label || put_label->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
jump->addr = (sljit_uw)(code_ptr - 3);
jump->addr = (sljit_uw)(code_ptr - 3);
#else
jump->addr = (sljit_uw)(code_ptr - 7);
jump->addr = (sljit_uw)(code_ptr - 7);
#endif
code_ptr = detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
/* Just recording the address. */
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
code_ptr = detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
}
if (put_label && put_label->addr == word_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
code_ptr += put_label_get_length(put_label, (sljit_uw)(SLJIT_ADD_EXEC_OFFSET(code, executable_offset) + put_label->label->size));
word_count += 5;
#endif
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr ++;
word_count ++;
@ -451,6 +590,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
SLJIT_ASSERT(code_ptr - code <= (sljit_sw)compiler->size);
jump = compiler->jumps;
@ -498,6 +638,21 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
put_label = compiler->put_labels;
while (put_label) {
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
addr = put_label->label->addr;
buf_ptr = (sljit_ins *)put_label->addr;
SLJIT_ASSERT((buf_ptr[0] & 0xffe00000) == LUI && (buf_ptr[1] & 0xfc000000) == ORI);
buf_ptr[0] |= (addr >> 16) & 0xffff;
buf_ptr[1] |= addr & 0xffff;
#else
put_label_set(put_label);
#endif
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins);
@ -1075,34 +1230,62 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_op0(struct sljit_compiler *compile
return push_inst(compiler, NOP, UNMOVABLE_INS);
case SLJIT_LMUL_UW:
case SLJIT_LMUL_SW:
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? DMULU : DMUL) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG3), DR(TMP_REG3)));
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? DMUHU : DMUH) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG1), DR(TMP_REG1)));
#else /* !SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? MULU : MUL) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG3), DR(TMP_REG3)));
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? MUHU : MUH) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG1), DR(TMP_REG1)));
#endif /* SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, ADDU_W | S(TMP_REG3) | TA(0) | D(SLJIT_R0), DR(SLJIT_R0)));
return push_inst(compiler, ADDU_W | S(TMP_REG1) | TA(0) | D(SLJIT_R1), DR(SLJIT_R1));
#else /* !SLJIT_MIPS_R6 */
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? DMULTU : DMULT) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS));
#else
#else /* !SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, (op == SLJIT_LMUL_UW ? MULTU : MULT) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS));
#endif
#endif /* SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, MFLO | D(SLJIT_R0), DR(SLJIT_R0)));
return push_inst(compiler, MFHI | D(SLJIT_R1), DR(SLJIT_R1));
#endif /* SLJIT_MIPS_R6 */
case SLJIT_DIVMOD_UW:
case SLJIT_DIVMOD_SW:
case SLJIT_DIV_UW:
case SLJIT_DIV_SW:
SLJIT_COMPILE_ASSERT((SLJIT_DIVMOD_UW & 0x2) == 0 && SLJIT_DIV_UW - 0x2 == SLJIT_DIVMOD_UW, bad_div_opcode_assignments);
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
if (int_op) {
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG3), DR(TMP_REG3)));
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? MODU : MOD) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG1), DR(TMP_REG1)));
}
else {
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DDIVU : DDIV) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG3), DR(TMP_REG3)));
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DMODU : DMOD) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG1), DR(TMP_REG1)));
}
#else /* !SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG3), DR(TMP_REG3)));
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? MODU : MOD) | S(SLJIT_R0) | T(SLJIT_R1) | D(TMP_REG1), DR(TMP_REG1)));
#endif /* SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, ADDU_W | S(TMP_REG3) | TA(0) | D(SLJIT_R0), DR(SLJIT_R0)));
return (op >= SLJIT_DIV_UW) ? SLJIT_SUCCESS : push_inst(compiler, ADDU_W | S(TMP_REG1) | TA(0) | D(SLJIT_R1), DR(SLJIT_R1));
#else /* !SLJIT_MIPS_R6 */
#if !(defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
FAIL_IF(push_inst(compiler, NOP, UNMOVABLE_INS));
FAIL_IF(push_inst(compiler, NOP, UNMOVABLE_INS));
#endif
#endif /* !SLJIT_MIPS_R1 */
#if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64)
if (int_op)
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS));
else
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DDIVU : DDIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS));
#else
#else /* !SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_DIV_UW ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS));
#endif
#endif /* SLJIT_CONFIG_MIPS_64 */
FAIL_IF(push_inst(compiler, MFLO | D(SLJIT_R0), DR(SLJIT_R0)));
return (op >= SLJIT_DIV_UW) ? SLJIT_SUCCESS : push_inst(compiler, MFHI | D(SLJIT_R1), DR(SLJIT_R1));
#endif /* SLJIT_MIPS_R6 */
}
return SLJIT_SUCCESS;
@ -1408,8 +1591,7 @@ static SLJIT_INLINE sljit_s32 sljit_emit_fop1_cmp(struct sljit_compiler *compile
inst = C_UN_S;
break;
}
return push_inst(compiler, inst | FMT(op) | FT(src2) | FS(src1), UNMOVABLE_INS);
return push_inst(compiler, inst | FMT(op) | FT(src2) | FS(src1) | C_FD, UNMOVABLE_INS);
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fop1(struct sljit_compiler *compiler, sljit_s32 op,
@ -1608,16 +1790,30 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_label* sljit_emit_label(struct sljit_compi
flags = IS_BIT26_COND; \
delay_check = src;
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
#define BR_T() \
inst = BC1NEZ; \
flags = IS_BIT23_COND; \
delay_check = FCSR_FCC;
#define BR_F() \
inst = BC1EQZ; \
flags = IS_BIT23_COND; \
delay_check = FCSR_FCC;
#else /* !SLJIT_MIPS_R6 */
#define BR_T() \
inst = BC1T | JUMP_LENGTH; \
flags = IS_BIT16_COND; \
delay_check = FCSR_FCC;
#define BR_F() \
inst = BC1F | JUMP_LENGTH; \
flags = IS_BIT16_COND; \
delay_check = FCSR_FCC;
#endif /* SLJIT_MIPS_R6 */
SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compiler *compiler, sljit_s32 type)
{
struct sljit_jump *jump;
@ -1927,7 +2123,11 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_op_flags(struct sljit_compiler *co
case SLJIT_GREATER_EQUAL_F64:
case SLJIT_UNORDERED_F64:
case SLJIT_ORDERED_F64:
#if (defined SLJIT_MIPS_R6 && SLJIT_MIPS_R6)
FAIL_IF(push_inst(compiler, MFC1 | TA(dst_ar) | FS(TMP_FREG3), dst_ar));
#else /* !SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, CFC1 | TA(dst_ar) | DA(FCSR_REG), dst_ar));
#endif /* SLJIT_MIPS_R6 */
FAIL_IF(push_inst(compiler, SRL | TA(dst_ar) | DA(dst_ar) | SH_IMM(23), dst_ar));
FAIL_IF(push_inst(compiler, ANDI | SA(dst_ar) | TA(dst_ar) | IMM(1), dst_ar));
src_ar = dst_ar;
@ -2039,7 +2239,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_cmov(struct sljit_compiler *compil
SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw init_value)
{
struct sljit_const *const_;
sljit_s32 reg;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value));
@ -2049,11 +2249,38 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
PTR_FAIL_IF(!const_);
set_const(const_, compiler);
reg = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, reg, init_value));
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, dst_r, init_value));
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op(compiler, SLJIT_MOV, WORD_DATA, dst, dstw, TMP_REG1, 0, TMP_REG2, 0));
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
#if (defined SLJIT_CONFIG_MIPS_32 && SLJIT_CONFIG_MIPS_32)
PTR_FAIL_IF(emit_const(compiler, dst_r, 0));
#else
PTR_FAIL_IF(push_inst(compiler, dst_r, UNMOVABLE_INS));
compiler->size += 5;
#endif
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op(compiler, SLJIT_MOV, WORD_DATA, dst, dstw, TMP_REG1, 0, TMP_REG2, 0));
return put_label;
}

2
pcre/sljit/sljitNativePPC_32.c
View File

@ -259,6 +259,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_ta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT((inst[0] & 0xfc1f0000) == ADDIS && (inst[1] & 0xfc000000) == ORI);
inst[0] = (inst[0] & 0xffff0000) | ((new_target >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_target & 0xffff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);
@ -269,6 +270,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT((inst[0] & 0xfc1f0000) == ADDIS && (inst[1] & 0xfc000000) == ORI);
inst[0] = (inst[0] & 0xffff0000) | ((new_constant >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_constant & 0xffff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);

3
pcre/sljit/sljitNativePPC_64.c
View File

@ -35,9 +35,6 @@
#error "Must implement count leading zeroes"
#endif
#define RLDI(dst, src, sh, mb, type) \
(HI(30) | S(src) | A(dst) | ((type) << 2) | (((sh) & 0x1f) << 11) | (((sh) & 0x20) >> 4) | (((mb) & 0x1f) << 6) | ((mb) & 0x20))
#define PUSH_RLDICR(reg, shift) \
push_inst(compiler, RLDI(reg, reg, 63 - shift, shift, 1))

228
pcre/sljit/sljitNativePPC_common.c
View File

@ -231,6 +231,9 @@ static const sljit_u8 freg_map[SLJIT_NUMBER_OF_FLOAT_REGISTERS + 3] = {
#define SIMM_MIN (-0x8000)
#define UIMM_MAX (0xffff)
#define RLDI(dst, src, sh, mb, type) \
(HI(30) | S(src) | A(dst) | ((type) << 2) | (((sh) & 0x1f) << 11) | (((sh) & 0x20) >> 4) | (((mb) & 0x1f) << 6) | ((mb) & 0x20))
#if (defined SLJIT_INDIRECT_CALL && SLJIT_INDIRECT_CALL)
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_function_context(void** func_ptr, struct sljit_function_context* context, sljit_sw addr, void* func)
{
@ -324,6 +327,55 @@ keep_address:
return 0;
}
#if (defined SLJIT_CONFIG_PPC_64 && SLJIT_CONFIG_PPC_64)
static SLJIT_INLINE sljit_sw put_label_get_length(struct sljit_put_label *put_label, sljit_uw max_label)
{
if (max_label < 0x100000000l) {
put_label->flags = 0;
return 1;
}
if (max_label < 0x1000000000000l) {
put_label->flags = 1;
return 3;
}
put_label->flags = 2;
return 4;
}
static SLJIT_INLINE void put_label_set(struct sljit_put_label *put_label)
{
sljit_uw addr = put_label->label->addr;
sljit_ins *inst = (sljit_ins *)put_label->addr;
sljit_s32 reg = *inst;
if (put_label->flags == 0) {
SLJIT_ASSERT(addr < 0x100000000l);
inst[0] = ORIS | S(TMP_ZERO) | A(reg) | IMM(addr >> 16);
}
else {
if (put_label->flags == 1) {
SLJIT_ASSERT(addr < 0x1000000000000l);
inst[0] = ORI | S(TMP_ZERO) | A(reg) | IMM(addr >> 32);
}
else {
inst[0] = ORIS | S(TMP_ZERO) | A(reg) | IMM(addr >> 48);
inst[1] = ORI | S(reg) | A(reg) | IMM((addr >> 32) & 0xffff);
inst ++;
}
inst[1] = RLDI(reg, reg, 32, 31, 1);
inst[2] = ORIS | S(reg) | A(reg) | IMM((addr >> 16) & 0xffff);
inst += 2;
}
inst[1] = ORI | S(reg) | A(reg) | IMM(addr & 0xffff);
}
#endif
SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compiler)
{
struct sljit_memory_fragment *buf;
@ -332,12 +384,14 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_ins *buf_ptr;
sljit_ins *buf_end;
sljit_uw word_count;
sljit_uw next_addr;
sljit_sw executable_offset;
sljit_uw addr;
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -356,71 +410,87 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
word_count = 0;
next_addr = 0;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
do {
buf_ptr = (sljit_ins*)buf->memory;
buf_end = buf_ptr + (buf->used_size >> 2);
do {
*code_ptr = *buf_ptr++;
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
/* Just recording the address. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
jump->addr = (sljit_uw)(code_ptr - 3);
#else
jump->addr = (sljit_uw)(code_ptr - 6);
#endif
if (detect_jump_type(jump, code_ptr, code, executable_offset)) {
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
code_ptr[-3] = code_ptr[0];
code_ptr -= 3;
#else
if (jump->flags & PATCH_ABS32) {
code_ptr -= 3;
code_ptr[-1] = code_ptr[2];
code_ptr[0] = code_ptr[3];
}
else if (jump->flags & PATCH_ABS48) {
code_ptr--;
code_ptr[-1] = code_ptr[0];
code_ptr[0] = code_ptr[1];
/* rldicr rX,rX,32,31 -> rX,rX,16,47 */
SLJIT_ASSERT((code_ptr[-3] & 0xfc00ffff) == 0x780007c6);
code_ptr[-3] ^= 0x8422;
/* oris -> ori */
code_ptr[-2] ^= 0x4000000;
}
else {
code_ptr[-6] = code_ptr[0];
code_ptr -= 6;
}
#endif
if (jump->flags & REMOVE_COND) {
code_ptr[0] = BCx | (2 << 2) | ((code_ptr[0] ^ (8 << 21)) & 0x03ff0001);
code_ptr++;
jump->addr += sizeof(sljit_ins);
code_ptr[0] = Bx;
jump->flags -= IS_COND;
}
if (next_addr == word_count) {
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
SLJIT_ASSERT(!put_label || put_label->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
/* Just recording the address. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
if (jump && jump->addr == word_count) {
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
jump->addr = (sljit_uw)(code_ptr - 3);
#else
jump->addr = (sljit_uw)(code_ptr - 6);
#endif
if (detect_jump_type(jump, code_ptr, code, executable_offset)) {
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
code_ptr[-3] = code_ptr[0];
code_ptr -= 3;
#else
if (jump->flags & PATCH_ABS32) {
code_ptr -= 3;
code_ptr[-1] = code_ptr[2];
code_ptr[0] = code_ptr[3];
}
else if (jump->flags & PATCH_ABS48) {
code_ptr--;
code_ptr[-1] = code_ptr[0];
code_ptr[0] = code_ptr[1];
/* rldicr rX,rX,32,31 -> rX,rX,16,47 */
SLJIT_ASSERT((code_ptr[-3] & 0xfc00ffff) == 0x780007c6);
code_ptr[-3] ^= 0x8422;
/* oris -> ori */
code_ptr[-2] ^= 0x4000000;
}
else {
code_ptr[-6] = code_ptr[0];
code_ptr -= 6;
}
#endif
if (jump->flags & REMOVE_COND) {
code_ptr[0] = BCx | (2 << 2) | ((code_ptr[0] ^ (8 << 21)) & 0x03ff0001);
code_ptr++;
jump->addr += sizeof(sljit_ins);
code_ptr[0] = Bx;
jump->flags -= IS_COND;
}
}
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
}
if (put_label && put_label->addr == word_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
#if (defined SLJIT_CONFIG_PPC_64 && SLJIT_CONFIG_PPC_64)
code_ptr += put_label_get_length(put_label, (sljit_uw)(SLJIT_ADD_EXEC_OFFSET(code, executable_offset) + put_label->label->size));
word_count += 4;
#endif
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr ++;
word_count ++;
@ -438,6 +508,8 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
#if (defined SLJIT_INDIRECT_CALL && SLJIT_INDIRECT_CALL)
SLJIT_ASSERT(code_ptr - code <= (sljit_sw)compiler->size - (sizeof(struct sljit_function_context) / sizeof(sljit_ins)));
#else
@ -503,6 +575,21 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
put_label = compiler->put_labels;
while (put_label) {
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
addr = put_label->label->addr;
buf_ptr = (sljit_ins *)put_label->addr;
SLJIT_ASSERT((buf_ptr[0] & 0xfc1f0000) == ADDIS && (buf_ptr[1] & 0xfc000000) == ORI);
buf_ptr[0] |= (addr >> 16) & 0xffff;
buf_ptr[1] |= addr & 0xffff;
#else
put_label_set(put_label);
#endif
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins);
@ -2261,7 +2348,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fmem(struct sljit_compiler *compil
SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw init_value)
{
struct sljit_const *const_;
sljit_s32 reg;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value));
@ -2271,11 +2358,38 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
PTR_FAIL_IF(!const_);
set_const(const_, compiler);
reg = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, reg, init_value));
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, dst_r, init_value));
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op(compiler, SLJIT_MOV, WORD_DATA, dst, dstw, TMP_REG1, 0, TMP_REG2, 0));
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
#if (defined SLJIT_CONFIG_PPC_32 && SLJIT_CONFIG_PPC_32)
PTR_FAIL_IF(emit_const(compiler, dst_r, 0));
#else
PTR_FAIL_IF(push_inst(compiler, dst_r));
compiler->size += 4;
#endif
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op(compiler, SLJIT_MOV, WORD_DATA, dst, dstw, TMP_REG1, 0, TMP_REG2, 0));
return put_label;
}

2
pcre/sljit/sljitNativeSPARC_32.c
View File

@ -267,6 +267,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_ta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT(((inst[0] & 0xc1c00000) == 0x01000000) && ((inst[1] & 0xc1f82000) == 0x80102000));
inst[0] = (inst[0] & 0xffc00000) | ((new_target >> 10) & 0x3fffff);
inst[1] = (inst[1] & 0xfffffc00) | (new_target & 0x3ff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);
@ -277,6 +278,7 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta
{
sljit_ins *inst = (sljit_ins *)addr;
SLJIT_ASSERT(((inst[0] & 0xc1c00000) == 0x01000000) && ((inst[1] & 0xc1f82000) == 0x80102000));
inst[0] = (inst[0] & 0xffc00000) | ((new_constant >> 10) & 0x3fffff);
inst[1] = (inst[1] & 0xfffffc00) | (new_constant & 0x3ff);
inst = (sljit_ins *)SLJIT_ADD_EXEC_OFFSET(inst, executable_offset);

102
pcre/sljit/sljitNativeSPARC_common.c
View File

@ -298,12 +298,14 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
sljit_ins *buf_ptr;
sljit_ins *buf_end;
sljit_uw word_count;
sljit_uw next_addr;
sljit_sw executable_offset;
sljit_uw addr;
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -315,40 +317,52 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
code_ptr = code;
word_count = 0;
next_addr = 0;
executable_offset = SLJIT_EXEC_OFFSET(code);
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
do {
buf_ptr = (sljit_ins*)buf->memory;
buf_end = buf_ptr + (buf->used_size >> 2);
do {
*code_ptr = *buf_ptr++;
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
/* Just recording the address. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
if (next_addr == word_count) {
SLJIT_ASSERT(!label || label->size >= word_count);
SLJIT_ASSERT(!jump || jump->addr >= word_count);
SLJIT_ASSERT(!const_ || const_->addr >= word_count);
SLJIT_ASSERT(!put_label || put_label->addr >= word_count);
/* These structures are ordered by their address. */
if (label && label->size == word_count) {
/* Just recording the address. */
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
}
if (jump && jump->addr == word_count) {
#if (defined SLJIT_CONFIG_SPARC_32 && SLJIT_CONFIG_SPARC_32)
jump->addr = (sljit_uw)(code_ptr - 3);
jump->addr = (sljit_uw)(code_ptr - 3);
#else
jump->addr = (sljit_uw)(code_ptr - 6);
jump->addr = (sljit_uw)(code_ptr - 6);
#endif
code_ptr = detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
/* Just recording the address. */
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
code_ptr = detect_jump_type(jump, code_ptr, code, executable_offset);
jump = jump->next;
}
if (const_ && const_->addr == word_count) {
/* Just recording the address. */
const_->addr = (sljit_uw)code_ptr;
const_ = const_->next;
}
if (put_label && put_label->addr == word_count) {
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
put_label = put_label->next;
}
next_addr = compute_next_addr(label, jump, const_, put_label);
}
code_ptr ++;
word_count ++;
@ -366,6 +380,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
SLJIT_ASSERT(code_ptr - code <= (sljit_s32)compiler->size);
jump = compiler->jumps;
@ -389,8 +404,9 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
/* Set the fields of immediate loads. */
#if (defined SLJIT_CONFIG_SPARC_32 && SLJIT_CONFIG_SPARC_32)
buf_ptr[0] = (buf_ptr[0] & 0xffc00000) | ((addr >> 10) & 0x3fffff);
buf_ptr[1] = (buf_ptr[1] & 0xfffffc00) | (addr & 0x3ff);
SLJIT_ASSERT(((buf_ptr[0] & 0xc1cfffff) == 0x01000000) && ((buf_ptr[1] & 0xc1f83fff) == 0x80102000));
buf_ptr[0] |= (addr >> 10) & 0x3fffff;
buf_ptr[1] |= addr & 0x3ff;
#else
#error "Implementation required"
#endif
@ -398,6 +414,20 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
put_label = compiler->put_labels;
while (put_label) {
addr = put_label->label->addr;
buf_ptr = (sljit_ins *)put_label->addr;
#if (defined SLJIT_CONFIG_SPARC_32 && SLJIT_CONFIG_SPARC_32)
SLJIT_ASSERT(((buf_ptr[0] & 0xc1cfffff) == 0x01000000) && ((buf_ptr[1] & 0xc1f83fff) == 0x80102000));
buf_ptr[0] |= (addr >> 10) & 0x3fffff;
buf_ptr[1] |= addr & 0x3ff;
#else
#error "Implementation required"
#endif
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
@ -1465,8 +1495,8 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_cmov(struct sljit_compiler *compil
SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw, sljit_sw init_value)
{
sljit_s32 reg;
struct sljit_const *const_;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value));
@ -1476,11 +1506,31 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
PTR_FAIL_IF(!const_);
set_const(const_, compiler);
reg = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, reg, init_value));
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, dst_r, init_value));
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op_mem(compiler, WORD_DATA, TMP_REG2, dst, dstw));
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_s32 dst_r;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
dst_r = FAST_IS_REG(dst) ? dst : TMP_REG2;
PTR_FAIL_IF(emit_const(compiler, dst_r, 0));
if (dst & SLJIT_MEM)
PTR_FAIL_IF(emit_op_mem(compiler, WORD_DATA, TMP_REG2, dst, dstw));
return put_label;
}

4
pcre/sljit/sljitNativeX86_32.c
View File

@ -38,8 +38,10 @@ static sljit_s32 emit_do_imm(struct sljit_compiler *compiler, sljit_u8 opcode, s
return SLJIT_SUCCESS;
}
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_s32 type, sljit_sw executable_offset)
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_sw executable_offset)
{
sljit_s32 type = jump->flags >> TYPE_SHIFT;
if (type == SLJIT_JUMP) {
*code_ptr++ = JMP_i32;
jump->addr++;

54
pcre/sljit/sljitNativeX86_64.c
View File

@ -39,8 +39,10 @@ static sljit_s32 emit_load_imm64(struct sljit_compiler *compiler, sljit_s32 reg,
return SLJIT_SUCCESS;
}
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_s32 type)
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr)
{
sljit_s32 type = jump->flags >> TYPE_SHIFT;
int short_addr = !(jump->flags & SLJIT_REWRITABLE_JUMP) && !(jump->flags & JUMP_LABEL) && (jump->u.target <= 0xffffffff);
/* The relative jump below specialized for this case. */
@ -72,6 +74,56 @@ static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_
return code_ptr;
}
static sljit_u8* generate_put_label_code(struct sljit_put_label *put_label, sljit_u8 *code_ptr, sljit_uw max_label)
{
if (max_label > HALFWORD_MAX) {
put_label->addr -= put_label->flags;
put_label->flags = PATCH_MD;
return code_ptr;
}
if (put_label->flags == 0) {
/* Destination is register. */
code_ptr = (sljit_u8*)put_label->addr - 2 - sizeof(sljit_uw);
SLJIT_ASSERT((code_ptr[0] & 0xf8) == REX_W);
SLJIT_ASSERT((code_ptr[1] & 0xf8) == MOV_r_i32);
if ((code_ptr[0] & 0x07) != 0) {
code_ptr[0] = (sljit_u8)(code_ptr[0] & ~0x08);
code_ptr += 2 + sizeof(sljit_s32);
}
else {
code_ptr[0] = code_ptr[1];
code_ptr += 1 + sizeof(sljit_s32);
}
put_label->addr = (sljit_uw)code_ptr;
return code_ptr;
}
code_ptr -= put_label->flags + (2 + sizeof(sljit_uw));
SLJIT_MEMMOVE(code_ptr, code_ptr + (2 + sizeof(sljit_uw)), put_label->flags);
SLJIT_ASSERT((code_ptr[0] & 0xf8) == REX_W);
if ((code_ptr[1] & 0xf8) == MOV_r_i32) {
code_ptr += 2 + sizeof(sljit_uw);
SLJIT_ASSERT((code_ptr[0] & 0xf8) == REX_W);
}
SLJIT_ASSERT(code_ptr[1] == MOV_rm_r);
code_ptr[0] = (sljit_u8)(code_ptr[0] & ~0x4);
code_ptr[1] = MOV_rm_i32;
code_ptr[2] = (sljit_u8)(code_ptr[2] & ~(0x7 << 3));
code_ptr = (sljit_u8*)(put_label->addr - (2 + sizeof(sljit_uw)) + sizeof(sljit_s32));
put_label->addr = (sljit_uw)code_ptr;
put_label->flags = 0;
return code_ptr;
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compiler,
sljit_s32 options, sljit_s32 arg_types, sljit_s32 scratches, sljit_s32 saveds,
sljit_s32 fscratches, sljit_s32 fsaveds, sljit_s32 local_size)

125
pcre/sljit/sljitNativeX86_common.c
View File

@ -428,13 +428,15 @@ static sljit_u8 get_jump_code(sljit_s32 type)
}
#if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32)
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_s32 type, sljit_sw executable_offset);
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_sw executable_offset);
#else
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_s32 type);
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr);
static sljit_u8* generate_put_label_code(struct sljit_put_label *put_label, sljit_u8 *code_ptr, sljit_uw max_label);
#endif
static sljit_u8* generate_near_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_u8 *code, sljit_s32 type, sljit_sw executable_offset)
static sljit_u8* generate_near_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_u8 *code, sljit_sw executable_offset)
{
sljit_s32 type = jump->flags >> TYPE_SHIFT;
sljit_s32 short_jump;
sljit_uw label_addr;
@ -447,7 +449,7 @@ static sljit_u8* generate_near_jump_code(struct sljit_jump *jump, sljit_u8 *code
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
if ((sljit_sw)(label_addr - (jump->addr + 1)) > HALFWORD_MAX || (sljit_sw)(label_addr - (jump->addr + 1)) < HALFWORD_MIN)
return generate_far_jump_code(jump, code_ptr, type);
return generate_far_jump_code(jump, code_ptr);
#endif
if (type == SLJIT_JUMP) {
@ -497,6 +499,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
struct sljit_label *label;
struct sljit_jump *jump;
struct sljit_const *const_;
struct sljit_put_label *put_label;
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_generate_code(compiler));
@ -511,6 +514,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
label = compiler->labels;
jump = compiler->jumps;
const_ = compiler->consts;
put_label = compiler->put_labels;
executable_offset = SLJIT_EXEC_OFFSET(code);
do {
@ -525,27 +529,38 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
buf_ptr += len;
}
else {
if (*buf_ptr >= 2) {
switch (*buf_ptr) {
case 0:
label->addr = (sljit_uw)SLJIT_ADD_EXEC_OFFSET(code_ptr, executable_offset);
label->size = code_ptr - code;
label = label->next;
break;
case 1:
jump->addr = (sljit_uw)code_ptr;
if (!(jump->flags & SLJIT_REWRITABLE_JUMP))
code_ptr = generate_near_jump_code(jump, code_ptr, code, *buf_ptr - 2, executable_offset);
code_ptr = generate_near_jump_code(jump, code_ptr, code, executable_offset);
else {
#if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32)
code_ptr = generate_far_jump_code(jump, code_ptr, *buf_ptr - 2, executable_offset);
code_ptr = generate_far_jump_code(jump, code_ptr, executable_offset);
#else
code_ptr = generate_far_jump_code(jump, code_ptr, *buf_ptr - 2);
code_ptr = generate_far_jump_code(jump, code_ptr);
#endif
}
jump = jump->next;
}
else if (*buf_ptr == 0) {
label->addr = ((sljit_uw)code_ptr) + executable_offset;
label->size = code_ptr - code;
label = label->next;
}
else { /* *buf_ptr is 1 */
break;
case 2:
const_->addr = ((sljit_uw)code_ptr) - sizeof(sljit_sw);
const_ = const_->next;
break;
default:
SLJIT_ASSERT(*buf_ptr == 3);
SLJIT_ASSERT(put_label->label);
put_label->addr = (sljit_uw)code_ptr;
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
code_ptr = generate_put_label_code(put_label, code_ptr, (sljit_uw)(SLJIT_ADD_EXEC_OFFSET(code, executable_offset) + put_label->label->size));
#endif
put_label = put_label->next;
break;
}
buf_ptr++;
}
@ -557,6 +572,8 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
SLJIT_ASSERT(!label);
SLJIT_ASSERT(!jump);
SLJIT_ASSERT(!const_);
SLJIT_ASSERT(!put_label);
SLJIT_ASSERT(code_ptr <= code + compiler->size);
jump = compiler->jumps;
while (jump) {
@ -591,8 +608,24 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil
jump = jump->next;
}
/* Some space may be wasted because of short jumps. */
SLJIT_ASSERT(code_ptr <= code + compiler->size);
put_label = compiler->put_labels;
while (put_label) {
#if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32)
sljit_unaligned_store_sw((void*)(put_label->addr - sizeof(sljit_sw)), (sljit_sw)put_label->label->addr);
#else
if (put_label->flags & PATCH_MD) {
SLJIT_ASSERT(put_label->label->addr > HALFWORD_MAX);
sljit_unaligned_store_sw((void*)(put_label->addr - sizeof(sljit_sw)), (sljit_sw)put_label->label->addr);
}
else {
SLJIT_ASSERT(put_label->label->addr <= HALFWORD_MAX);
sljit_unaligned_store_s32((void*)(put_label->addr - sizeof(sljit_s32)), (sljit_s32)put_label->label->addr);
}
#endif
put_label = put_label->next;
}
compiler->error = SLJIT_ERR_COMPILED;
compiler->executable_offset = executable_offset;
compiler->executable_size = code_ptr - code;
@ -2481,7 +2514,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile
jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump));
PTR_FAIL_IF_NULL(jump);
set_jump(jump, compiler, type & SLJIT_REWRITABLE_JUMP);
set_jump(jump, compiler, (type & SLJIT_REWRITABLE_JUMP) | ((type & 0xff) << TYPE_SHIFT));
type &= 0xff;
/* Worst case size. */
@ -2495,7 +2528,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile
PTR_FAIL_IF_NULL(inst);
*inst++ = 0;
*inst++ = type + 2;
*inst++ = 1;
return jump;
}
@ -2513,7 +2546,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_ijump(struct sljit_compiler *compi
if (src == SLJIT_IMM) {
jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump));
FAIL_IF_NULL(jump);
set_jump(jump, compiler, JUMP_ADDR);
set_jump(jump, compiler, JUMP_ADDR | (type << TYPE_SHIFT));
jump->u.target = srcw;
/* Worst case size. */
@ -2527,7 +2560,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_ijump(struct sljit_compiler *compi
FAIL_IF_NULL(inst);
*inst++ = 0;
*inst++ = type + 2;
*inst++ = 1;
}
else {
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
@ -2831,7 +2864,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
PTR_FAIL_IF(!inst);
*inst++ = 0;
*inst++ = 1;
*inst++ = 2;
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
if (dst & SLJIT_MEM)
@ -2842,6 +2875,54 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi
return const_;
}
SLJIT_API_FUNC_ATTRIBUTE struct sljit_put_label* sljit_emit_put_label(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
struct sljit_put_label *put_label;
sljit_u8 *inst;
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
sljit_s32 reg;
sljit_uw start_size;
#endif
CHECK_ERROR_PTR();
CHECK_PTR(check_sljit_emit_put_label(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
CHECK_EXTRA_REGS(dst, dstw, (void)0);
put_label = (struct sljit_put_label*)ensure_abuf(compiler, sizeof(struct sljit_put_label));
PTR_FAIL_IF(!put_label);
set_put_label(put_label, compiler, 0);
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
compiler->mode32 = 0;
reg = FAST_IS_REG(dst) ? dst : TMP_REG1;
if (emit_load_imm64(compiler, reg, 0))
return NULL;
#else
if (emit_mov(compiler, dst, dstw, SLJIT_IMM, 0))
return NULL;
#endif
#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64)
if (dst & SLJIT_MEM) {
start_size = compiler->size;
if (emit_mov(compiler, dst, dstw, TMP_REG1, 0))
return NULL;
put_label->flags = compiler->size - start_size;
}
#endif
inst = (sljit_u8*)ensure_buf(compiler, 2);
PTR_FAIL_IF(!inst);
*inst++ = 0;
*inst++ = 3;
return put_label;
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_target, sljit_sw executable_offset)
{
SLJIT_UNUSED_ARG(executable_offset);

6
pcre/sljit/sljitUtils.c
View File

@ -154,7 +154,13 @@ SLJIT_API_FUNC_ATTRIBUTE void SLJIT_FUNC sljit_release_lock(void)
#include "windows.h"
#else
/* Provides mmap function. */
#include <sys/types.h>
#include <sys/mman.h>
#ifndef MAP_ANON
#ifdef MAP_ANONYMOUS
#define MAP_ANON MAP_ANONYMOUS
#endif
#endif
/* For detecting the page size. */
#include <unistd.h>

2
pcre/testdata/testinput2 vendored
View File

@ -1380,7 +1380,7 @@
1X
123456\P
//KF>testsavedregex
//S-KF>testsavedregex
/abc/IS>testsavedregex
<testsavedregex

3
pcre/testdata/testoutput2 vendored
View File

@ -5614,9 +5614,8 @@ No match
123456\P
No match
//KF>testsavedregex
//S-KF>testsavedregex
Compiled pattern written to testsavedregex
Study data written to testsavedregex
/abc/IS>testsavedregex
Capturing subpattern count = 0