-# $Cambridge: exim/src/OS/Makefile-Base,v 1.12 2007/11/12 13:02:19 nm4 Exp $
+# $Cambridge: exim/src/OS/Makefile-Base,v 1.13 2008/01/16 13:44:45 nm4 Exp $
# This file is the basis of the main makefile for Exim and friends. The
# makefile at the top level arranges to build the main makefile by calling
# therefore always be run, even if the files exist. This shouldn't in fact be a
# problem, but it does no harm. Other make programs will just ignore this.
-.PHONY: all allexim buildauths buildlookups buildpcre buildrouters \
+.PHONY: all allexim buildauths buildlookups buildrouters \
buildtransports checklocalmake clean
# This is the real default target for all the various exim binaries and
# scripts, once the configuring stuff is done.
-allexim: config.h buildpcre $(EXIM_MONITOR) exicyclog exinext exiwhat \
+allexim: config.h $(EXIM_MONITOR) exicyclog exinext exiwhat \
exigrep eximstats exipick exiqgrep exiqsumm \
transport-filter.pl convert4r3 convert4r4 \
exim_checkaccess \
local_scan.o $(EXIM_PERL) $(OBJ_WITH_CONTENT_SCAN) \
$(OBJ_WITH_OLD_DEMIME) $(OBJ_EXPERIMENTAL)
-exim: pcre/libpcre.a lookups/lookups.a auths/auths.a \
+exim: lookups/lookups.a auths/auths.a \
routers/routers.a transports/transports.a \
$(OBJ_EXIM) version.c
@echo " "
rm -f exim
@echo "$(LNCC) -o exim"
$(FE)$(PURIFY) $(LNCC) -o exim $(LFLAGS) $(OBJ_EXIM) version.o \
- pcre/libpcre.a \
routers/routers.a transports/transports.a lookups/lookups.a \
auths/auths.a \
$(LIBRESOLV) $(LIBS) $(LIBS_EXIM) $(IPV6_LIBS) $(EXTRALIBS) \
$(EXTRALIBS_EXIM) $(DBMLIB) $(LOOKUP_LIBS) $(AUTH_LIBS) \
- $(PERL_LIBS) $(TLS_LIBS) $(LDFLAGS)
+ $(PERL_LIBS) $(TLS_LIBS) $(PCRE_LIBS) $(LDFLAGS)
@if [ x"$(STRIP_COMMAND)" != x"" ]; then \
echo $(STRIP_COMMAND) exim; \
$(STRIP_COMMAND) exim; \
OBJ_MONBIN = util-spool_in.o util-store.o util-string.o tod.o tree.o $(MONBIN)
-eximon.bin: $(EXIMON_EDITME) eximon $(OBJ_MONBIN) pcre/libpcre.a \
+eximon.bin: $(EXIMON_EDITME) eximon $(OBJ_MONBIN) \
../exim_monitor/em_version.c
@echo "$(CC) exim_monitor/em_version.c"
$(FE)$(CC) -o em_version.o -c \
$(CFLAGS) $(XINCLUDE) -I. ../exim_monitor/em_version.c
@echo "$(LNCC) -o eximon.bin"
$(FE)$(PURIFY) $(LNCC) -o eximon.bin em_version.o $(LFLAGS) $(XLFLAGS) \
- $(OBJ_MONBIN) -lXaw -lXmu -lXt -lXext -lX11 pcre/libpcre.a \
+ $(OBJ_MONBIN) -lXaw -lXmu -lXt -lXext -lX11 $(PCRE_LIBS) \
$(LIBS) $(LIBS_EXIMON) $(EXTRALIBS) $(EXTRALIBS_EXIMON) -lc
@if [ x"$(STRIP_COMMAND)" != x"" ]; then \
echo $(STRIP_COMMAND) eximon.bin; \
# drtables.o when they rebuild.) To get round this, we forcibly remove the
# binary when it needs to be rebuilt.
-# The PCRE regex library. Move the pcretest program to the util directory. Some
-# "clever" versions of make notice that there are two successive shell
-# commands, and they run them in the same shell. This means that we have to
-# take care to encapsulate change of directory in parentheses, so that it
-# reverts when it should.
-
-buildpcre:
- @(cd pcre; $(MAKE) SHELL=$(SHELL) AR="$(AR)" $(MFLAGS) CC="$(CC)" \
- FE="$(FE)" CFLAGS="$(CFLAGS) $(PCRE_CFLAGS) -DHAVE_CONFIG_H" \
- RANLIB="$(RANLIB)" RM_COMMAND="$(RM_COMMAND)" HDRS="$(PHDRS)" \
- INCLUDE="$(INCLUDE) $(IPV6_INCLUDE) $(TLS_INCLUDE)")
- @if $(SHELL) $(SCRIPTS)/newer pcre/libpcre.a exim; then \
- rm -f exim eximon.bin; fi
- @echo " "
-
# The lookups library.
buildlookups:
-# $Cambridge: exim/src/OS/Makefile-Default,v 1.2 2006/02/10 14:33:26 ph10 Exp $
+# $Cambridge: exim/src/OS/Makefile-Default,v 1.3 2008/01/16 13:44:45 nm4 Exp $
##################################################
# The Exim mail transport agent #
# LFLAGS=
+# PCRE_LIBS contains the library to be linked for PCRE
+
+#PCRE_LIBS=-lpcre
+
+
# LIBS and EXTRALIBS contain library settings that are used on linking
# commands to build binaries. The OS-dependent Makefile may contain a default
# setting for LIBS, leaving EXTRALIBS available for adding further libraries
# EXTRALIBS_EXIMON=
-# PCRE_CFLAGS contains flags to be passed to the CFLAGS parameter of the
-# makefile for building the PCRE regular expression library, in addition
-# to CFLAGS. Typical use is to set -DUSE_BCOPY on legacy systems that lack
-# the memmove() function but do have bcopy().
-
-# PCRE_CFLAGS=
-
-
# The error name for quota exceeded varies among operating systems, and
# even, unfortunately, in different versions of the same operating system.
# EDQUOT was not in Sys V, but is in SPEC 1170, apparently. It was used
-/* $Cambridge: exim/src/exim_monitor/em_hdr.h,v 1.6 2007/01/08 10:50:17 ph10 Exp $ */
+/* $Cambridge: exim/src/exim_monitor/em_hdr.h,v 1.7 2008/01/16 13:44:45 nm4 Exp $ */
/*************************************************
* Exim Monitor *
/* Regular expression include */
-#include "pcre/pcre.h"
+#include <pcre.h>
/* Includes from the main source of Exim. We need to have MAXPACKET defined for
the benefit of structs.h. One of these days I should tidy up this interface so
-# $Cambridge: exim/src/src/EDITME,v 1.20 2007/01/22 16:29:54 ph10 Exp $
+# $Cambridge: exim/src/src/EDITME,v 1.21 2008/01/16 13:44:45 nm4 Exp $
##################################################
# The Exim mail transport agent #
# Michigan (OpenLDAP 1) library.
+#------------------------------------------------------------------------------
+# The PCRE library is required for exim. There is no longer an embedded
+# version of the PCRE library included with the source code, instead you
+# must use a system library or build your own copy of PCRE.
+# In either case you must specify the library link info here. If the
+# PCRE header files are not in the standard search path you must also
+# modify the INCLUDE path (above)
+# The default setting of PCRE_LIBS should work on the vast majority of
+# systems
+
+PCRE_LIBS=-lpcre
+
+
#------------------------------------------------------------------------------
# Additional libraries and include directories may be required for some
# lookup styles (e.g. LDAP, MYSQL or PGSQL). LOOKUP_LIBS is included only on
-/* $Cambridge: exim/src/src/exim.h,v 1.23 2007/09/28 12:21:57 tom Exp $ */
+/* $Cambridge: exim/src/src/exim.h,v 1.24 2008/01/16 13:44:45 nm4 Exp $ */
/*************************************************
* Exim - an Internet mail transport agent *
/* The header from the PCRE regex package */
-#include "pcre/pcre.h"
+#include <pcre.h>
/* Exim includes are in several files. Note that local_scan.h #includes
config.h, mytypes.h, and store.h, so we don't need to mention them explicitly.
+++ /dev/null
-ChangeLog for PCRE
-------------------
-
-Version 7.4 21-Sep-07
----------------------
-
-1. Change 7.3/28 was implemented for classes by looking at the bitmap. This
- means that a class such as [\s] counted as "explicit reference to CR or
- LF". That isn't really right - the whole point of the change was to try to
- help when there was an actual mention of one of the two characters. So now
- the change happens only if \r or \n (or a literal CR or LF) character is
- encountered.
-
-2. The 32-bit options word was also used for 6 internal flags, but the numbers
- of both had grown to the point where there were only 3 bits left.
- Fortunately, there was spare space in the data structure, and so I have
- moved the internal flags into a new 16-bit field to free up more option
- bits.
-
-3. The appearance of (?J) at the start of a pattern set the DUPNAMES option,
- but did not set the internal JCHANGED flag - either of these is enough to
- control the way the "get" function works - but the PCRE_INFO_JCHANGED
- facility is supposed to tell if (?J) was ever used, so now (?J) at the
- start sets both bits.
-
-4. Added options (at build time, compile time, exec time) to change \R from
- matching any Unicode line ending sequence to just matching CR, LF, or CRLF.
-
-5. doc/pcresyntax.html was missing from the distribution.
-
-6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward
- compatibility, even though it is no longer used.
-
-7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and
- strtoull to pcrecpp.cc to select the available functions in WIN32 when the
- windows.h file is present (where different names are used). [This was
- reversed later after testing - see 16 below.]
-
-8. Changed all #include <config.h> to #include "config.h". There were also
- some further <pcre.h> cases that I changed to "pcre.h".
-
-9. When pcregrep was used with the --colour option, it missed the line ending
- sequence off the lines that it output.
-
-10. It was pointed out to me that arrays of string pointers cause lots of
- relocations when a shared library is dynamically loaded. A technique of
- using a single long string with a table of offsets can drastically reduce
- these. I have refactored PCRE in four places to do this. The result is
- dramatic:
-
- Originally: 290
- After changing UCP table: 187
- After changing error message table: 43
- After changing table of "verbs" 36
- After changing table of Posix names 22
-
- Thanks to the folks working on Gregex for glib for this insight.
-
-11. --disable-stack-for-recursion caused compiling to fail unless -enable-
- unicode-properties was also set.
-
-12. Updated the tests so that they work when \R is defaulted to ANYCRLF.
-
-13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously
- checked only for CRLF.
-
-14. Added casts to pcretest.c to avoid compiler warnings.
-
-15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings.
-
-16. Added Craig's patch to remove the WINDOWS_H tests, that were not working,
- and instead check for _strtoi64 explicitly, and avoid the use of snprintf()
- entirely. This removes changes made in 7 above.
-
-17. The CMake files have been updated, and there is now more information about
- building with CMake in the NON-UNIX-USE document.
-
-
-Version 7.3 28-Aug-07
----------------------
-
- 1. In the rejigging of the build system that eventually resulted in 7.1, the
- line "#include <pcre.h>" was included in pcre_internal.h. The use of angle
- brackets there is not right, since it causes compilers to look for an
- installed pcre.h, not the version that is in the source that is being
- compiled (which of course may be different). I have changed it back to:
-
- #include "pcre.h"
-
- I have a vague recollection that the change was concerned with compiling in
- different directories, but in the new build system, that is taken care of
- by the VPATH setting the Makefile.
-
- 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed
- when the subject happened to end in the byte 0x85 (e.g. if the last
- character was \x{1ec5}). *Character* 0x85 is one of the "any" newline
- characters but of course it shouldn't be taken as a newline when it is part
- of another character. The bug was that, for an unlimited repeat of . in
- not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by
- characters when looking for a newline.
-
- 3. A small performance improvement in the DOTALL UTF-8 mode .* case.
-
- 4. Debugging: adjusted the names of opcodes for different kinds of parentheses
- in debug output.
-
- 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for
- long printing in the pcrecpp unittest when running under MinGW.
-
- 6. ESC_K was left out of the EBCDIC table.
-
- 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing
- parentheses; I made it 1000, which seemed large enough. Unfortunately, the
- limit also applies to "virtual nesting" when a pattern is recursive, and in
- this case 1000 isn't so big. I have been able to remove this limit at the
- expense of backing off one optimization in certain circumstances. Normally,
- when pcre_exec() would call its internal match() function recursively and
- immediately return the result unconditionally, it uses a "tail recursion"
- feature to save stack. However, when a subpattern that can match an empty
- string has an unlimited repetition quantifier, it no longer makes this
- optimization. That gives it a stack frame in which to save the data for
- checking that an empty string has been matched. Previously this was taken
- from the 1000-entry workspace that had been reserved. So now there is no
- explicit limit, but more stack is used.
-
- 8. Applied Daniel's patches to solve problems with the import/export magic
- syntax that is required for Windows, and which was going wrong for the
- pcreposix and pcrecpp parts of the library. These were overlooked when this
- problem was solved for the main library.
-
- 9. There were some crude static tests to avoid integer overflow when computing
- the size of patterns that contain repeated groups with explicit upper
- limits. As the maximum quantifier is 65535, the maximum group length was
- set at 30,000 so that the product of these two numbers did not overflow a
- 32-bit integer. However, it turns out that people want to use groups that
- are longer than 30,000 bytes (though not repeat them that many times).
- Change 7.0/17 (the refactoring of the way the pattern size is computed) has
- made it possible to implement the integer overflow checks in a much more
- dynamic way, which I have now done. The artificial limitation on group
- length has been removed - we now have only the limit on the total length of
- the compiled pattern, which depends on the LINK_SIZE setting.
-
-10. Fixed a bug in the documentation for get/copy named substring when
- duplicate names are permitted. If none of the named substrings are set, the
- functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an
- empty string.
-
-11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E
- instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error,
- because the ] is interpreted as the first data character and the
- terminating ] is not found. PCRE has been made compatible with Perl in this
- regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could
- cause memory overwriting.
-
-10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty
- string has been matched (to stop an infinite loop). It was not recognizing
- a conditional subpattern that could match an empty string if that
- subpattern was within another subpattern. For example, it looped when
- trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the
- condition was not nested. This bug has been fixed.
-
-12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack
- past the start of the subject in the presence of bytes with the top bit
- set, for example "\x8aBCD".
-
-13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE),
- (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT).
-
-14. Optimized (?!) to (*FAIL).
-
-15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629.
- This restricts code points to be within the range 0 to 0x10FFFF, excluding
- the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the
- full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still
- does: it's just the validity check that is more restrictive.
-
-16. Inserted checks for integer overflows during escape sequence (backslash)
- processing, and also fixed erroneous offset values for syntax errors during
- backslash processing.
-
-17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above)
- for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80".
-
-18. An unterminated class in a pattern like (?1)\c[ with a "forward reference"
- caused an overrun.
-
-19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with
- something other than just ASCII characters) inside a group that had an
- unlimited repeat caused a loop at compile time (while checking to see
- whether the group could match an empty string).
-
-20. Debugging a pattern containing \p or \P could cause a crash. For example,
- [\P{Any}] did so. (Error in the code for printing property names.)
-
-21. An orphan \E inside a character class could cause a crash.
-
-22. A repeated capturing bracket such as (A)? could cause a wild memory
- reference during compilation.
-
-23. There are several functions in pcre_compile() that scan along a compiled
- expression for various reasons (e.g. to see if it's fixed length for look
- behind). There were bugs in these functions when a repeated \p or \P was
- present in the pattern. These operators have additional parameters compared
- with \d, etc, and these were not being taken into account when moving along
- the compiled data. Specifically:
-
- (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed
- length.
-
- (b) An item such as \pL+ within a repeated group could cause crashes or
- loops.
-
- (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect
- "reference to non-existent subpattern" error.
-
- (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time.
-
-24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte
- characters were involved (for example /\S{2}/8g with "A\x{a3}BC").
-
-25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop.
-
-26. Patterns such as [\P{Yi}A] which include \p or \P and just one other
- character were causing crashes (broken optimization).
-
-27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing
- \p or \P) caused a compile-time loop.
-
-28. More problems have arisen in unanchored patterns when CRLF is a valid line
- break. For example, the unstudied pattern [\r\n]A does not match the string
- "\r\nA" because change 7.0/46 below moves the current point on by two
- characters after failing to match at the start. However, the pattern \nA
- *does* match, because it doesn't start till \n, and if [\r\n]A is studied,
- the same is true. There doesn't seem any very clean way out of this, but
- what I have chosen to do makes the common cases work: PCRE now takes note
- of whether there can be an explicit match for \r or \n anywhere in the
- pattern, and if so, 7.0/46 no longer applies. As part of this change,
- there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled
- pattern has explicit CR or LF references.
-
-29. Added (*CR) etc for changing newline setting at start of pattern.
-
-
-Version 7.2 19-Jun-07
----------------------
-
- 1. If the fr_FR locale cannot be found for test 3, try the "french" locale,
- which is apparently normally available under Windows.
-
- 2. Re-jig the pcregrep tests with different newline settings in an attempt
- to make them independent of the local environment's newline setting.
-
- 3. Add code to configure.ac to remove -g from the CFLAGS default settings.
-
- 4. Some of the "internals" tests were previously cut out when the link size
- was not 2, because the output contained actual offsets. The recent new
- "Z" feature of pcretest means that these can be cut out, making the tests
- usable with all link sizes.
-
- 5. Implemented Stan Switzer's goto replacement for longjmp() when not using
- stack recursion. This gives a massive performance boost under BSD, but just
- a small improvement under Linux. However, it saves one field in the frame
- in all cases.
-
- 6. Added more features from the forthcoming Perl 5.10:
-
- (a) (?-n) (where n is a string of digits) is a relative subroutine or
- recursion call. It refers to the nth most recently opened parentheses.
-
- (b) (?+n) is also a relative subroutine call; it refers to the nth next
- to be opened parentheses.
-
- (c) Conditions that refer to capturing parentheses can be specified
- relatively, for example, (?(-2)... or (?(+3)...
-
- (d) \K resets the start of the current match so that everything before
- is not part of it.
-
- (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible).
-
- (f) \g{name} is another synonym - part of Perl 5.10's unification of
- reference syntax.
-
- (g) (?| introduces a group in which the numbering of parentheses in each
- alternative starts with the same number.
-
- (h) \h, \H, \v, and \V match horizontal and vertical whitespace.
-
- 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and
- PCRE_INFO_JCHANGED.
-
- 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not
- terminating or by crashing. Diagnosed by Viktor Griph; it was in the code
- for detecting groups that can match an empty string.
-
- 9. A pattern with a very large number of alternatives (more than several
- hundred) was running out of internal workspace during the pre-compile
- phase, where pcre_compile() figures out how much memory will be needed. A
- bit of new cunning has reduced the workspace needed for groups with
- alternatives. The 1000-alternative test pattern now uses 12 bytes of
- workspace instead of running out of the 4096 that are available.
-
-10. Inserted some missing (unsigned int) casts to get rid of compiler warnings.
-
-11. Applied patch from Google to remove an optimization that didn't quite work.
- The report of the bug said:
-
- pcrecpp::RE("a*").FullMatch("aaa") matches, while
- pcrecpp::RE("a*?").FullMatch("aaa") does not, and
- pcrecpp::RE("a*?\\z").FullMatch("aaa") does again.
-
-12. If \p or \P was used in non-UTF-8 mode on a character greater than 127
- it matched the wrong number of bytes.
-
-
-Version 7.1 24-Apr-07
----------------------
-
- 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one
- that is more "standard", making use of automake and other Autotools. There
- is some re-arrangement of the files and adjustment of comments consequent
- on this.
-
- 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r
- for recursive directory scanning broke on some systems because the files
- are not scanned in any specific order and on different systems the order
- was different. A call to "sort" has been inserted into RunGrepTest for the
- approprate test as a short-term fix. In the longer term there may be an
- alternative.
-
- 3. I had an email from Eric Raymond about problems translating some of PCRE's
- man pages to HTML (despite the fact that I distribute HTML pages, some
- people do their own conversions for various reasons). The problems
- concerned the use of low-level troff macros .br and .in. I have therefore
- removed all such uses from the man pages (some were redundant, some could
- be replaced by .nf/.fi pairs). The 132html script that I use to generate
- HTML has been updated to handle .nf/.fi and to complain if it encounters
- .br or .in.
-
- 4. Updated comments in configure.ac that get placed in config.h.in and also
- arranged for config.h to be included in the distribution, with the name
- config.h.generic, for the benefit of those who have to compile without
- Autotools (compare pcre.h, which is now distributed as pcre.h.generic).
-
- 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan
- Weber: (1) pcre_internal.h was missing some function renames; (2) updated
- makevp.bat for the current PCRE, using the additional files
- makevp_c.txt, makevp_l.txt, and pcregexp.pas.
-
- 6. A Windows user reported a minor discrepancy with test 2, which turned out
- to be caused by a trailing space on an input line that had got lost in his
- copy. The trailing space was an accident, so I've just removed it.
-
- 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told
- that is needed.
-
- 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c)
- as "const" (a) because they are and (b) because it helps the PHP
- maintainers who have recently made a script to detect big data structures
- in the php code that should be moved to the .rodata section. I remembered
- to update Builducptable as well, so it won't revert if ucptable.h is ever
- re-created.
-
- 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c,
- pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in
- order to be able to cut out the UTF-8 tables in the latter when UTF-8
- support is not required. This saves 1.5-2K of code, which is important in
- some applications.
-
- Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c
- so as not to refer to the tables, even though these functions will never be
- called when UTF-8 support is disabled. Otherwise there are problems with a
- shared library.
-
-10. Fixed two bugs in the emulated memmove() function in pcre_internal.h:
-
- (a) It was defining its arguments as char * instead of void *.
-
- (b) It was assuming that all moves were upwards in memory; this was true
- a long time ago when I wrote it, but is no longer the case.
-
- The emulated memove() is provided for those environments that have neither
- memmove() nor bcopy(). I didn't think anyone used it these days, but that
- is clearly not the case, as these two bugs were recently reported.
-
-11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt,
- and Detrail to create the HTML documentation, the .txt form of the man
- pages, and it removes trailing spaces from listed files. It also creates
- pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter
- case, it wraps all the #defines with #ifndefs. This script should be run
- before "make dist".
-
-12. Fixed two fairly obscure bugs concerned with quantified caseless matching
- with Unicode property support.
-
- (a) For a maximizing quantifier, if the two different cases of the
- character were of different lengths in their UTF-8 codings (there are
- some cases like this - I found 11), and the matching function had to
- back up over a mixture of the two cases, it incorrectly assumed they
- were both the same length.
-
- (b) When PCRE was configured to use the heap rather than the stack for
- recursion during matching, it was not correctly preserving the data for
- the other case of a UTF-8 character when checking ahead for a match
- while processing a minimizing repeat. If the check also involved
- matching a wide character, but failed, corruption could cause an
- erroneous result when trying to check for a repeat of the original
- character.
-
-13. Some tidying changes to the testing mechanism:
-
- (a) The RunTest script now detects the internal link size and whether there
- is UTF-8 and UCP support by running ./pcretest -C instead of relying on
- values substituted by "configure". (The RunGrepTest script already did
- this for UTF-8.) The configure.ac script no longer substitutes the
- relevant variables.
-
- (b) The debugging options /B and /D in pcretest show the compiled bytecode
- with length and offset values. This means that the output is different
- for different internal link sizes. Test 2 is skipped for link sizes
- other than 2 because of this, bypassing the problem. Unfortunately,
- there was also a test in test 3 (the locale tests) that used /B and
- failed for link sizes other than 2. Rather than cut the whole test out,
- I have added a new /Z option to pcretest that replaces the length and
- offset values with spaces. This is now used to make test 3 independent
- of link size. (Test 2 will be tidied up later.)
-
-14. If erroroffset was passed as NULL to pcre_compile, it provoked a
- segmentation fault instead of returning the appropriate error message.
-
-15. In multiline mode when the newline sequence was set to "any", the pattern
- ^$ would give a match between the \r and \n of a subject such as "A\r\nB".
- This doesn't seem right; it now treats the CRLF combination as the line
- ending, and so does not match in that case. It's only a pattern such as ^$
- that would hit this one: something like ^ABC$ would have failed after \r
- and then tried again after \r\n.
-
-16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub"
- in an attempt to make files that differ only in their line terminators
- compare equal. This works on Linux.
-
-17. Under certain error circumstances pcregrep might try to free random memory
- as it exited. This is now fixed, thanks to valgrind.
-
-19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string
- "abc\r\n\r\n", it found an unwanted second match after the second \r. This
- was because its rules for how to advance for /g after matching an empty
- string at the end of a line did not allow for this case. They now check for
- it specially.
-
-20. pcretest is supposed to handle patterns and data of any length, by
- extending its buffers when necessary. It was getting this wrong when the
- buffer for a data line had to be extended.
-
-21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or
- CRLF as a newline sequence.
-
-22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut
- out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but
- I have nevertheless tidied it up.
-
-23. Added some casts to kill warnings from HP-UX ia64 compiler.
-
-24. Added a man page for pcre-config.
-
-
-Version 7.0 19-Dec-06
----------------------
-
- 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by
- moving to gcc 4.1.1.
-
- 2. The -S option for pcretest uses setrlimit(); I had omitted to #include
- sys/time.h, which is documented as needed for this function. It doesn't
- seem to matter on Linux, but it showed up on some releases of OS X.
-
- 3. It seems that there are systems where bytes whose values are greater than
- 127 match isprint() in the "C" locale. The "C" locale should be the
- default when a C program starts up. In most systems, only ASCII printing
- characters match isprint(). This difference caused the output from pcretest
- to vary, making some of the tests fail. I have changed pcretest so that:
-
- (a) When it is outputting text in the compiled version of a pattern, bytes
- other than 32-126 are always shown as hex escapes.
-
- (b) When it is outputting text that is a matched part of a subject string,
- it does the same, unless a different locale has been set for the match
- (using the /L modifier). In this case, it uses isprint() to decide.
-
- 4. Fixed a major bug that caused incorrect computation of the amount of memory
- required for a compiled pattern when options that changed within the
- pattern affected the logic of the preliminary scan that determines the
- length. The relevant options are -x, and -i in UTF-8 mode. The result was
- that the computed length was too small. The symptoms of this bug were
- either the PCRE error "internal error: code overflow" from pcre_compile(),
- or a glibc crash with a message such as "pcretest: free(): invalid next
- size (fast)". Examples of patterns that provoked this bug (shown in
- pcretest format) are:
-
- /(?-x: )/x
- /(?x)(?-x: \s*#\s*)/
- /((?i)[\x{c0}])/8
- /(?i:[\x{c0}])/8
-
- HOWEVER: Change 17 below makes this fix obsolete as the memory computation
- is now done differently.
-
- 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++
- wrapper classes; (b) implement a new function in the C++ scanner that is
- more efficient than the old way of doing things because it avoids levels of
- recursion in the regex matching; (c) add a paragraph to the documentation
- for the FullMatch() function.
-
- 6. The escape sequence \n was being treated as whatever was defined as
- "newline". Not only was this contrary to the documentation, which states
- that \n is character 10 (hex 0A), but it also went horribly wrong when
- "newline" was defined as CRLF. This has been fixed.
-
- 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c)
- was being set to -1 for the "end of line" case (supposedly a value that no
- character can have). Though this value is never used (the check for end of
- line is "zero bytes in current character"), it caused compiler complaints.
- I've changed it to 0xffffffff.
-
- 8. In pcre_version.c, the version string was being built by a sequence of
- C macros that, in the event of PCRE_PRERELEASE being defined as an empty
- string (as it is for production releases) called a macro with an empty
- argument. The C standard says the result of this is undefined. The gcc
- compiler treats it as an empty string (which was what was wanted) but it is
- reported that Visual C gives an error. The source has been hacked around to
- avoid this problem.
-
- 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows
- builds of pcretest, and changed the call to _setmode() to use _O_BINARY
- instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all
- of them did).
-
-10. Originally, pcretest opened its input and output without "b"; then I was
- told that "b" was needed in some environments, so it was added for release
- 5.0 to both the input and output. (It makes no difference on Unix-like
- systems.) Later I was told that it is wrong for the input on Windows. I've
- now abstracted the modes into two macros, to make it easier to fiddle with
- them, and removed "b" from the input mode under Windows.
-
-11. Added pkgconfig support for the C++ wrapper library, libpcrecpp.
-
-12. Added -help and --help to pcretest as an official way of being reminded
- of the options.
-
-13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in
- and pcrecpp.cc because they annoy compilers at high warning levels.
-
-14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop.
-
-15. Fixed an occurrence of == in configure.ac that should have been = (shell
- scripts are not C programs :-) and which was not noticed because it works
- on Linux.
-
-16. pcretest is supposed to handle any length of pattern and data line (as one
- line or as a continued sequence of lines) by extending its input buffer if
- necessary. This feature was broken for very long pattern lines, leading to
- a string of junk being passed to pcre_compile() if the pattern was longer
- than about 50K.
-
-17. I have done a major re-factoring of the way pcre_compile() computes the
- amount of memory needed for a compiled pattern. Previously, there was code
- that made a preliminary scan of the pattern in order to do this. That was
- OK when PCRE was new, but as the facilities have expanded, it has become
- harder and harder to keep it in step with the real compile phase, and there
- have been a number of bugs (see for example, 4 above). I have now found a
- cunning way of running the real compile function in a "fake" mode that
- enables it to compute how much memory it would need, while actually only
- ever using a few hundred bytes of working memory and without too many
- tests of the mode. This should make future maintenance and development
- easier. A side effect of this work is that the limit of 200 on the nesting
- depth of parentheses has been removed (though this was never a serious
- limitation, I suspect). However, there is a downside: pcre_compile() now
- runs more slowly than before (30% or more, depending on the pattern). I
- hope this isn't a big issue. There is no effect on runtime performance.
-
-18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a
- newline (only possible for the last line of a file) and it was a
- pattern that set a locale (followed by /Lsomething), pcretest crashed.
-
-19. Added additional timing features to pcretest. (1) The -tm option now times
- matching only, not compiling. (2) Both -t and -tm can be followed, as a
- separate command line item, by a number that specifies the number of
- repeats to use when timing. The default is 50000; this gives better
- precision, but takes uncomfortably long for very large patterns.
-
-20. Extended pcre_study() to be more clever in cases where a branch of a
- subpattern has no definite first character. For example, (a*|b*)[cd] would
- previously give no result from pcre_study(). Now it recognizes that the
- first character must be a, b, c, or d.
-
-21. There was an incorrect error "recursive call could loop indefinitely" if
- a subpattern (or the entire pattern) that was being tested for matching an
- empty string contained only one non-empty item after a nested subpattern.
- For example, the pattern (?>\x{100}*)\d(?R) provoked this error
- incorrectly, because the \d was being skipped in the check.
-
-22. The pcretest program now has a new pattern option /B and a command line
- option -b, which is equivalent to adding /B to every pattern. This causes
- it to show the compiled bytecode, without the additional information that
- -d shows. The effect of -d is now the same as -b with -i (and similarly, /D
- is the same as /B/I).
-
-23. A new optimization is now able automatically to treat some sequences such
- as a*b as a*+b. More specifically, if something simple (such as a character
- or a simple class like \d) has an unlimited quantifier, and is followed by
- something that cannot possibly match the quantified thing, the quantifier
- is automatically "possessified".
-
-24. A recursive reference to a subpattern whose number was greater than 39
- went wrong under certain circumstances in UTF-8 mode. This bug could also
- have affected the operation of pcre_study().
-
-25. Realized that a little bit of performance could be had by replacing
- (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters.
-
-26. Timing data from pcretest is now shown to 4 decimal places instead of 3.
-
-27. Possessive quantifiers such as a++ were previously implemented by turning
- them into atomic groups such as ($>a+). Now they have their own opcodes,
- which improves performance. This includes the automatically created ones
- from 23 above.
-
-28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a
- lookahead was broken if it was not anchored. PCRE was mistakenly expecting
- the first matched character to be a colon. This applied both to named and
- numbered groups.
-
-29. The ucpinternal.h header file was missing its idempotency #ifdef.
-
-30. I was sent a "project" file called libpcre.a.dev which I understand makes
- building PCRE on Windows easier, so I have included it in the distribution.
-
-31. There is now a check in pcretest against a ridiculously large number being
- returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G
- loop, the loop is abandoned.
-
-32. Forward references to subpatterns in conditions such as (?(2)...) where
- subpattern 2 is defined later cause pcre_compile() to search forwards in
- the pattern for the relevant set of parentheses. This search went wrong
- when there were unescaped parentheses in a character class, parentheses
- escaped with \Q...\E, or parentheses in a #-comment in /x mode.
-
-33. "Subroutine" calls and backreferences were previously restricted to
- referencing subpatterns earlier in the regex. This restriction has now
- been removed.
-
-34. Added a number of extra features that are going to be in Perl 5.10. On the
- whole, these are just syntactic alternatives for features that PCRE had
- previously implemented using the Python syntax or my own invention. The
- other formats are all retained for compatibility.
-
- (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well
- as (?P<name>...). The new forms, as well as being in Perl 5.10, are
- also .NET compatible.
-
- (b) A recursion or subroutine call to a named group can now be defined as
- (?&name) as well as (?P>name).
-
- (c) A backreference to a named group can now be defined as \k<name> or
- \k'name' as well as (?P=name). The new forms, as well as being in Perl
- 5.10, are also .NET compatible.
-
- (d) A conditional reference to a named group can now use the syntax
- (?(<name>) or (?('name') as well as (?(name).
-
- (e) A "conditional group" of the form (?(DEFINE)...) can be used to define
- groups (named and numbered) that are never evaluated inline, but can be
- called as "subroutines" from elsewhere. In effect, the DEFINE condition
- is always false. There may be only one alternative in such a group.
-
- (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well
- as the simple (?(R). The condition is true only if the most recent
- recursion is that of the given number or name. It does not search out
- through the entire recursion stack.
-
- (g) The escape \gN or \g{N} has been added, where N is a positive or
- negative number, specifying an absolute or relative reference.
-
-35. Tidied to get rid of some further signed/unsigned compiler warnings and
- some "unreachable code" warnings.
-
-36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other
- things, this adds five new scripts.
-
-37. Perl ignores orphaned \E escapes completely. PCRE now does the same.
- There were also incompatibilities regarding the handling of \Q..\E inside
- character classes, for example with patterns like [\Qa\E-\Qz\E] where the
- hyphen was adjacent to \Q or \E. I hope I've cleared all this up now.
-
-38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group
- matches an empty string, and forcibly breaks the loop. There were bugs in
- this code in non-simple cases. For a pattern such as ^(a()*)* matched
- against aaaa the result was just "a" rather than "aaaa", for example. Two
- separate and independent bugs (that affected different cases) have been
- fixed.
-
-39. Refactored the code to abolish the use of different opcodes for small
- capturing bracket numbers. This is a tidy that I avoided doing when I
- removed the limit on the number of capturing brackets for 3.5 back in 2001.
- The new approach is not only tidier, it makes it possible to reduce the
- memory needed to fix the previous bug (38).
-
-40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline
- sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when
- processing dot, circumflex, or dollar metacharacters, or #-comments in /x
- mode.
-
-41. Add \R to match any Unicode newline sequence, as suggested in the Unicode
- report.
-
-42. Applied patch, originally from Ari Pollak, modified by Google, to allow
- copy construction and assignment in the C++ wrapper.
-
-43. Updated pcregrep to support "--newline=any". In the process, I fixed a
- couple of bugs that could have given wrong results in the "--newline=crlf"
- case.
-
-44. Added a number of casts and did some reorganization of signed/unsigned int
- variables following suggestions from Dair Grant. Also renamed the variable
- "this" as "item" because it is a C++ keyword.
-
-45. Arranged for dftables to add
-
- #include "pcre_internal.h"
-
- to pcre_chartables.c because without it, gcc 4.x may remove the array
- definition from the final binary if PCRE is built into a static library and
- dead code stripping is activated.
-
-46. For an unanchored pattern, if a match attempt fails at the start of a
- newline sequence, and the newline setting is CRLF or ANY, and the next two
- characters are CRLF, advance by two characters instead of one.
-
-
-Version 6.7 04-Jul-06
----------------------
-
- 1. In order to handle tests when input lines are enormously long, pcretest has
- been re-factored so that it automatically extends its buffers when
- necessary. The code is crude, but this _is_ just a test program. The
- default size has been increased from 32K to 50K.
-
- 2. The code in pcre_study() was using the value of the re argument before
- testing it for NULL. (Of course, in any sensible call of the function, it
- won't be NULL.)
-
- 3. The memmove() emulation function in pcre_internal.h, which is used on
- systems that lack both memmove() and bcopy() - that is, hardly ever -
- was missing a "static" storage class specifier.
-
- 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns
- containing an extended class (one that cannot be represented by a bitmap
- because it contains high-valued characters or Unicode property items, e.g.
- [\pZ]). Almost always one would set UTF-8 mode when processing such a
- pattern, but PCRE should not loop if you do not (it no longer does).
- [Detail: two cases were found: (a) a repeated subpattern containing an
- extended class; (b) a recursive reference to a subpattern that followed a
- previous extended class. It wasn't skipping over the extended class
- correctly when UTF-8 mode was not set.]
-
- 5. A negated single-character class was not being recognized as fixed-length
- in lookbehind assertions such as (?<=[^f]), leading to an incorrect
- compile error "lookbehind assertion is not fixed length".
-
- 6. The RunPerlTest auxiliary script was showing an unexpected difference
- between PCRE and Perl for UTF-8 tests. It turns out that it is hard to
- write a Perl script that can interpret lines of an input file either as
- byte characters or as UTF-8, which is what "perltest" was being required to
- do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you
- can't do is switch easily at run time between having the "use utf8;" pragma
- or not. In the end, I fudged it by using the RunPerlTest script to insert
- "use utf8;" explicitly for the UTF-8 tests.
-
- 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at
- the end of the subject string, contrary to the documentation and to what
- Perl does. This was true of both matching functions. Now it matches only at
- the start of the subject and immediately after *internal* newlines.
-
- 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing
- a pointer to an int instead of a pointer to an unsigned long int. This
- caused problems on 64-bit systems.
-
- 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another
- instance of the 'standard' template library not being so standard".
-
-10. There was no check on the number of named subpatterns nor the maximum
- length of a subpattern name. The product of these values is used to compute
- the size of the memory block for a compiled pattern. By supplying a very
- long subpattern name and a large number of named subpatterns, the size
- computation could be caused to overflow. This is now prevented by limiting
- the length of names to 32 characters, and the number of named subpatterns
- to 10,000.
-
-11. Subpatterns that are repeated with specific counts have to be replicated in
- the compiled pattern. The size of memory for this was computed from the
- length of the subpattern and the repeat count. The latter is limited to
- 65535, but there was no limit on the former, meaning that integer overflow
- could in principle occur. The compiled length of a repeated subpattern is
- now limited to 30,000 bytes in order to prevent this.
-
-12. Added the optional facility to have named substrings with the same name.
-
-13. Added the ability to use a named substring as a condition, using the
- Python syntax: (?(name)yes|no). This overloads (?(R)... and names that
- are numbers (not recommended). Forward references are permitted.
-
-14. Added forward references in named backreferences (if you see what I mean).
-
-15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the
- pattern could run off the end of the subject. For example, the pattern
- "(?s)(.{1,5})"8 did this with the subject "ab".
-
-16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if
- PCRE_CASELESS was set when matching characters that were quantified with ?
- or *.
-
-17. A character class other than a single negated character that had a minimum
- but no maximum quantifier - for example [ab]{6,} - was not handled
- correctly by pce_dfa_exec(). It would match only one character.
-
-18. A valid (though odd) pattern that looked like a POSIX character
- class but used an invalid character after [ (for example [[,abc,]]) caused
- pcre_compile() to give the error "Failed: internal error: code overflow" or
- in some cases to crash with a glibc free() error. This could even happen if
- the pattern terminated after [[ but there just happened to be a sequence of
- letters, a binary zero, and a closing ] in the memory that followed.
-
-19. Perl's treatment of octal escapes in the range \400 to \777 has changed
- over the years. Originally (before any Unicode support), just the bottom 8
- bits were taken. Thus, for example, \500 really meant \100. Nowadays the
- output from "man perlunicode" includes this:
-
- The regular expression compiler produces polymorphic opcodes. That
- is, the pattern adapts to the data and automatically switches to
- the Unicode character scheme when presented with Unicode data--or
- instead uses a traditional byte scheme when presented with byte
- data.
-
- Sadly, a wide octal escape does not cause a switch, and in a string with
- no other multibyte characters, these octal escapes are treated as before.
- Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern
- /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a
- Unicode string.
-
- I have not perpetrated such confusion in PCRE. Up till now, it took just
- the bottom 8 bits, as in old Perl. I have now made octal escapes with
- values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they
- translate to the appropriate multibyte character.
-
-29. Applied some refactoring to reduce the number of warnings from Microsoft
- and Borland compilers. This has included removing the fudge introduced
- seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused
- a warning about an unused variable.
-
-21. PCRE has not included VT (character 0x0b) in the set of whitespace
- characters since release 4.0, because Perl (from release 5.004) does not.
- [Or at least, is documented not to: some releases seem to be in conflict
- with the documentation.] However, when a pattern was studied with
- pcre_study() and all its branches started with \s, PCRE still included VT
- as a possible starting character. Of course, this did no harm; it just
- caused an unnecessary match attempt.
-
-22. Removed a now-redundant internal flag bit that recorded the fact that case
- dependency changed within the pattern. This was once needed for "required
- byte" processing, but is no longer used. This recovers a now-scarce options
- bit. Also moved the least significant internal flag bit to the most-
- significant bit of the word, which was not previously used (hangover from
- the days when it was an int rather than a uint) to free up another bit for
- the future.
-
-23. Added support for CRLF line endings as well as CR and LF. As well as the
- default being selectable at build time, it can now be changed at runtime
- via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to
- specify that it is scanning data with non-default line endings.
-
-24. Changed the definition of CXXLINK to make it agree with the definition of
- LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS.
-
-25. Applied Ian Taylor's patches to avoid using another stack frame for tail
- recursions. This makes a big different to stack usage for some patterns.
-
-26. If a subpattern containing a named recursion or subroutine reference such
- as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of
- the space required for the compiled pattern went wrong and gave too small a
- value. Depending on the environment, this could lead to "Failed: internal
- error: code overflow at offset 49" or "glibc detected double free or
- corruption" errors.
-
-27. Applied patches from Google (a) to support the new newline modes and (b) to
- advance over multibyte UTF-8 characters in GlobalReplace.
-
-28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a
- difference for some implementation of PCRE in some Windows version.
-
-29. Added some extra testing facilities to pcretest:
-
- \q<number> in a data line sets the "match limit" value
- \Q<number> in a data line sets the "match recursion limt" value
- -S <number> sets the stack size, where <number> is in megabytes
-
- The -S option isn't available for Windows.
-
-
-Version 6.6 06-Feb-06
----------------------
-
- 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined
- in pcreposix.h. I have copied the definition from pcre.h.
-
- 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree
- because pcre.h is no longer a built file.
-
- 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are
- not normally included in the compiled code.
-
-
-Version 6.5 01-Feb-06
----------------------
-
- 1. When using the partial match feature with pcre_dfa_exec(), it was not
- anchoring the second and subsequent partial matches at the new starting
- point. This could lead to incorrect results. For example, with the pattern
- /1234/, partially matching against "123" and then "a4" gave a match.
-
- 2. Changes to pcregrep:
-
- (a) All non-match returns from pcre_exec() were being treated as failures
- to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an
- error message is output. Some extra information is given for the
- PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are
- probably the only errors that are likely to be caused by users (by
- specifying a regex that has nested indefinite repeats, for instance).
- If there are more than 20 of these errors, pcregrep is abandoned.
-
- (b) A binary zero was treated as data while matching, but terminated the
- output line if it was written out. This has been fixed: binary zeroes
- are now no different to any other data bytes.
-
- (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is
- used to set a locale for matching. The --locale=xxxx long option has
- been added (no short equivalent) to specify a locale explicitly on the
- pcregrep command, overriding the environment variables.
-
- (d) When -B was used with -n, some line numbers in the output were one less
- than they should have been.
-
- (e) Added the -o (--only-matching) option.
-
- (f) If -A or -C was used with -c (count only), some lines of context were
- accidentally printed for the final match.
-
- (g) Added the -H (--with-filename) option.
-
- (h) The combination of options -rh failed to suppress file names for files
- that were found from directory arguments.
-
- (i) Added the -D (--devices) and -d (--directories) options.
-
- (j) Added the -F (--fixed-strings) option.
-
- (k) Allow "-" to be used as a file name for -f as well as for a data file.
-
- (l) Added the --colo(u)r option.
-
- (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it
- is not present by default.
-
- 3. A nasty bug was discovered in the handling of recursive patterns, that is,
- items such as (?R) or (?1), when the recursion could match a number of
- alternatives. If it matched one of the alternatives, but subsequently,
- outside the recursion, there was a failure, the code tried to back up into
- the recursion. However, because of the way PCRE is implemented, this is not
- possible, and the result was an incorrect result from the match.
-
- In order to prevent this happening, the specification of recursion has
- been changed so that all such subpatterns are automatically treated as
- atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)).
-
- 4. I had overlooked the fact that, in some locales, there are characters for
- which isalpha() is true but neither isupper() nor islower() are true. In
- the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine
- and ordfeminine) are like this. This affected the treatment of \w and \W
- when they appeared in character classes, but not when they appeared outside
- a character class. The bit map for "word" characters is now created
- separately from the results of isalnum() instead of just taking it from the
- upper, lower, and digit maps. (Plus the underscore character, of course.)
-
- 5. The above bug also affected the handling of POSIX character classes such as
- [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's
- permanent tables. Instead, the bit maps for such a class were previously
- created as the appropriate unions of the upper, lower, and digit bitmaps.
- Now they are created by subtraction from the [[:word:]] class, which has
- its own bitmap.
-
- 6. The [[:blank:]] character class matches horizontal, but not vertical space.
- It is created by subtracting the vertical space characters (\x09, \x0a,
- \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the
- subtraction was done in the overall bitmap for a character class, meaning
- that a class such as [\x0c[:blank:]] was incorrect because \x0c would not
- be recognized. This bug has been fixed.
-
- 7. Patches from the folks at Google:
-
- (a) pcrecpp.cc: "to handle a corner case that may or may not happen in
- real life, but is still worth protecting against".
-
- (b) pcrecpp.cc: "corrects a bug when negative radixes are used with
- regular expressions".
-
- (c) pcre_scanner.cc: avoid use of std::count() because not all systems
- have it.
-
- (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by
- "configure" and the latter not, in order to fix a problem somebody had
- with compiling the Arg class on HP-UX.
-
- (e) Improve the error-handling of the C++ wrapper a little bit.
-
- (f) New tests for checking recursion limiting.
-
- 8. The pcre_memmove() function, which is used only if the environment does not
- have a standard memmove() function (and is therefore rarely compiled),
- contained two bugs: (a) use of int instead of size_t, and (b) it was not
- returning a result (though PCRE never actually uses the result).
-
- 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously
- large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is
- returned instead of calling malloc() with an overflowing number that would
- most likely cause subsequent chaos.
-
-10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag.
-
-11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled
- with this option is matched, the nmatch and pmatch options of regexec() are
- ignored.
-
-12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is
- provided in case anyone wants to the the POSIX interface with UTF-8
- strings.
-
-13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the
- C++ linking (needed for some HP-UX environments).
-
-14. Avoid compiler warnings in get_ucpname() when compiled without UCP support
- (unused parameter) and in the pcre_printint() function (omitted "default"
- switch label when the default is to do nothing).
-
-15. Added some code to make it possible, when PCRE is compiled as a C++
- library, to replace subject pointers for pcre_exec() with a smart pointer
- class, thus making it possible to process discontinuous strings.
-
-16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform
- much the same function. They were added by different people who were trying
- to make PCRE easy to compile on non-Unix systems. It has been suggested
- that PCRE_EXPORT be abolished now that there is more automatic apparatus
- for compiling on Windows systems. I have therefore replaced it with
- PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it
- defaults to "extern" for C or "extern C" for C++, which works fine on
- Unix-like systems. It is now possible to override the value of PCRE_DATA_
- SCOPE with something explicit in config.h. In addition:
-
- (a) pcreposix.h still had just "extern" instead of either of these macros;
- I have replaced it with PCRE_DATA_SCOPE.
-
- (b) Functions such as _pcre_xclass(), which are internal to the library,
- but external in the C sense, all had PCRE_EXPORT in their definitions.
- This is apparently wrong for the Windows case, so I have removed it.
- (It makes no difference on Unix-like systems.)
-
-17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting
- of recursive calls to match(). This is different to MATCH_LIMIT because
- that limits the total number of calls to match(), not all of which increase
- the depth of recursion. Limiting the recursion depth limits the amount of
- stack (or heap if NO_RECURSE is set) that is used. The default can be set
- when PCRE is compiled, and changed at run time. A patch from Google adds
- this functionality to the C++ interface.
-
-18. Changes to the handling of Unicode character properties:
-
- (a) Updated the table to Unicode 4.1.0.
-
- (b) Recognize characters that are not in the table as "Cn" (undefined).
-
- (c) I revised the way the table is implemented to a much improved format
- which includes recognition of ranges. It now supports the ranges that
- are defined in UnicodeData.txt, and it also amalgamates other
- characters into ranges. This has reduced the number of entries in the
- table from around 16,000 to around 3,000, thus reducing its size
- considerably. I realized I did not need to use a tree structure after
- all - a binary chop search is just as efficient. Having reduced the
- number of entries, I extended their size from 6 bytes to 8 bytes to
- allow for more data.
-
- (d) Added support for Unicode script names via properties such as \p{Han}.
-
-19. In UTF-8 mode, a backslash followed by a non-Ascii character was not
- matching that character.
-
-20. When matching a repeated Unicode property with a minimum greater than zero,
- (for example \pL{2,}), PCRE could look past the end of the subject if it
- reached it while seeking the minimum number of characters. This could
- happen only if some of the characters were more than one byte long, because
- there is a check for at least the minimum number of bytes.
-
-21. Refactored the implementation of \p and \P so as to be more general, to
- allow for more different types of property in future. This has changed the
- compiled form incompatibly. Anybody with saved compiled patterns that use
- \p or \P will have to recompile them.
-
-22. Added "Any" and "L&" to the supported property types.
-
-23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode,
- but give a compile time error if the value is greater than 0xff.
-
-24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were
- accidentally not being installed or uninstalled.
-
-25. The pcre.h file was built from pcre.h.in, but the only changes that were
- made were to insert the current release number. This seemed silly, because
- it made things harder for people building PCRE on systems that don't run
- "configure". I have turned pcre.h into a distributed file, no longer built
- by "configure", with the version identification directly included. There is
- no longer a pcre.h.in file.
-
- However, this change necessitated a change to the pcre-config script as
- well. It is built from pcre-config.in, and one of the substitutions was the
- release number. I have updated configure.ac so that ./configure now finds
- the release number by grepping pcre.h.
-
-26. Added the ability to run the tests under valgrind.
-
-
-Version 6.4 05-Sep-05
----------------------
-
- 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines
- "--" to be printed when multiple files were scanned, even when none of the
- -A, -B, or -C options were used. This is not compatible with Gnu grep, so I
- consider it to be a bug, and have restored the previous behaviour.
-
- 2. A couple of code tidies to get rid of compiler warnings.
-
- 3. The pcretest program used to cheat by referring to symbols in the library
- whose names begin with _pcre_. These are internal symbols that are not
- really supposed to be visible externally, and in some environments it is
- possible to suppress them. The cheating is now confined to including
- certain files from the library's source, which is a bit cleaner.
-
- 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the
- file's purpose clearer.
-
- 5. Reorganized pcre_ucp_findchar().
-
-
-Version 6.3 15-Aug-05
----------------------
-
- 1. The file libpcre.pc.in did not have general read permission in the tarball.
-
- 2. There were some problems when building without C++ support:
-
- (a) If C++ support was not built, "make install" and "make test" still
- tried to test it.
-
- (b) There were problems when the value of CXX was explicitly set. Some
- changes have been made to try to fix these, and ...
-
- (c) --disable-cpp can now be used to explicitly disable C++ support.
-
- (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a
- backslash in a target when C++ was disabled. This confuses some
- versions of "make", apparently. Using an intermediate variable solves
- this. (Same for CPP_LOBJ.)
-
- 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK)
- (non-Windows) now includes $(CFLAGS) because these flags are sometimes
- necessary on certain architectures.
-
- 4. Added a setting of -export-symbols-regex to the link command to remove
- those symbols that are exported in the C sense, but actually are local
- within the library, and not documented. Their names all begin with
- "_pcre_". This is not a perfect job, because (a) we have to except some
- symbols that pcretest ("illegally") uses, and (b) the facility isn't always
- available (and never for static libraries). I have made a note to try to
- find a way round (a) in the future.
-
-
-Version 6.2 01-Aug-05
----------------------
-
- 1. There was no test for integer overflow of quantifier values. A construction
- such as {1111111111111111} would give undefined results. What is worse, if
- a minimum quantifier for a parenthesized subpattern overflowed and became
- negative, the calculation of the memory size went wrong. This could have
- led to memory overwriting.
-
- 2. Building PCRE using VPATH was broken. Hopefully it is now fixed.
-
- 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like
- operating environments where this matters.
-
- 4. Applied Giuseppe Maxia's patch to add additional features for controlling
- PCRE options from within the C++ wrapper.
-
- 5. Named capturing subpatterns were not being correctly counted when a pattern
- was compiled. This caused two problems: (a) If there were more than 100
- such subpatterns, the calculation of the memory needed for the whole
- compiled pattern went wrong, leading to an overflow error. (b) Numerical
- back references of the form \12, where the number was greater than 9, were
- not recognized as back references, even though there were sufficient
- previous subpatterns.
-
- 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older
- versions of gcc, e.g. 2.95.4.
-
-
-Version 6.1 21-Jun-05
----------------------
-
- 1. There was one reference to the variable "posix" in pcretest.c that was not
- surrounded by "#if !defined NOPOSIX".
-
- 2. Make it possible to compile pcretest without DFA support, UTF8 support, or
- the cross-check on the old pcre_info() function, for the benefit of the
- cut-down version of PCRE that is currently imported into Exim.
-
- 3. A (silly) pattern starting with (?i)(?-i) caused an internal space
- allocation error. I've done the easy fix, which wastes 2 bytes for sensible
- patterns that start (?i) but I don't think that matters. The use of (?i) is
- just an example; this all applies to the other options as well.
-
- 4. Since libtool seems to echo the compile commands it is issuing, the output
- from "make" can be reduced a bit by putting "@" in front of each libtool
- compile command.
-
- 5. Patch from the folks at Google for configure.in to be a bit more thorough
- in checking for a suitable C++ installation before trying to compile the
- C++ stuff. This should fix a reported problem when a compiler was present,
- but no suitable headers.
-
- 6. The man pages all had just "PCRE" as their title. I have changed them to
- be the relevant file name. I have also arranged that these names are
- retained in the file doc/pcre.txt, which is a concatenation in text format
- of all the man pages except the little individual ones for each function.
-
- 7. The NON-UNIX-USE file had not been updated for the different set of source
- files that come with release 6. I also added a few comments about the C++
- wrapper.
-
-
-Version 6.0 07-Jun-05
----------------------
-
- 1. Some minor internal re-organization to help with my DFA experiments.
-
- 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that
- didn't matter for the library itself when fully configured, but did matter
- when compiling without UCP support, or within Exim, where the ucp files are
- not imported.
-
- 3. Refactoring of the library code to split up the various functions into
- different source modules. The addition of the new DFA matching code (see
- below) to a single monolithic source would have made it really too
- unwieldy, quite apart from causing all the code to be include in a
- statically linked application, when only some functions are used. This is
- relevant even without the DFA addition now that patterns can be compiled in
- one application and matched in another.
-
- The downside of splitting up is that there have to be some external
- functions and data tables that are used internally in different modules of
- the library but which are not part of the API. These have all had their
- names changed to start with "_pcre_" so that they are unlikely to clash
- with other external names.
-
- 4. Added an alternate matching function, pcre_dfa_exec(), which matches using
- a different (DFA) algorithm. Although it is slower than the original
- function, it does have some advantages for certain types of matching
- problem.
-
- 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(),
- including restarting after a partial match.
-
- 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not
- defined when compiling for Windows was sent to me. I have put it into the
- code, though I have no means of testing or verifying it.
-
- 7. Added the pcre_refcount() auxiliary function.
-
- 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to
- match before or at the first newline in the subject string. In pcretest,
- the /f option on a pattern can be used to set this.
-
- 9. A repeated \w when used in UTF-8 mode with characters greater than 256
- would behave wrongly. This has been present in PCRE since release 4.0.
-
-10. A number of changes to the pcregrep command:
-
- (a) Refactored how -x works; insert ^(...)$ instead of setting
- PCRE_ANCHORED and checking the length, in preparation for adding
- something similar for -w.
-
- (b) Added the -w (match as a word) option.
-
- (c) Refactored the way lines are read and buffered so as to have more
- than one at a time available.
-
- (d) Implemented a pcregrep test script.
-
- (e) Added the -M (multiline match) option. This allows patterns to match
- over several lines of the subject. The buffering ensures that at least
- 8K, or the rest of the document (whichever is the shorter) is available
- for matching (and similarly the previous 8K for lookbehind assertions).
-
- (f) Changed the --help output so that it now says
-
- -w, --word-regex(p)
-
- instead of two lines, one with "regex" and the other with "regexp"
- because that confused at least one person since the short forms are the
- same. (This required a bit of code, as the output is generated
- automatically from a table. It wasn't just a text change.)
-
- (g) -- can be used to terminate pcregrep options if the next thing isn't an
- option but starts with a hyphen. Could be a pattern or a path name
- starting with a hyphen, for instance.
-
- (h) "-" can be given as a file name to represent stdin.
-
- (i) When file names are being printed, "(standard input)" is used for
- the standard input, for compatibility with GNU grep. Previously
- "<stdin>" was used.
-
- (j) The option --label=xxx can be used to supply a name to be used for
- stdin when file names are being printed. There is no short form.
-
- (k) Re-factored the options decoding logic because we are going to add
- two more options that take data. Such options can now be given in four
- different ways, e.g. "-fname", "-f name", "--file=name", "--file name".
-
- (l) Added the -A, -B, and -C options for requesting that lines of context
- around matches be printed.
-
- (m) Added the -L option to print the names of files that do not contain
- any matching lines, that is, the complement of -l.
-
- (n) The return code is 2 if any file cannot be opened, but pcregrep does
- continue to scan other files.
-
- (o) The -s option was incorrectly implemented. For compatibility with other
- greps, it now suppresses the error message for a non-existent or non-
- accessible file (but not the return code). There is a new option called
- -q that suppresses the output of matching lines, which was what -s was
- previously doing.
-
- (p) Added --include and --exclude options to specify files for inclusion
- and exclusion when recursing.
-
-11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly.
- Hopefully, it now does.
-
-12. Missing cast in pcre_study().
-
-13. Added an "uninstall" target to the makefile.
-
-14. Replaced "extern" in the function prototypes in Makefile.in with
- "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix
- world, but is set differently for Windows.
-
-15. Added a second compiling function called pcre_compile2(). The only
- difference is that it has an extra argument, which is a pointer to an
- integer error code. When there is a compile-time failure, this is set
- non-zero, in addition to the error test pointer being set to point to an
- error message. The new argument may be NULL if no error number is required
- (but then you may as well call pcre_compile(), which is now just a
- wrapper). This facility is provided because some applications need a
- numeric error indication, but it has also enabled me to tidy up the way
- compile-time errors are handled in the POSIX wrapper.
-
-16. Added VPATH=.libs to the makefile; this should help when building with one
- prefix path and installing with another. (Or so I'm told by someone who
- knows more about this stuff than I do.)
-
-17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This
- passes PCRE_DOTALL to the pcre_compile() function, making the "." character
- match everything, including newlines. This is not POSIX-compatible, but
- somebody wanted the feature. From pcretest it can be activated by using
- both the P and the s flags.
-
-18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one.
-
-19. libpcre.pc was being incorrectly installed as executable.
-
-20. A couple of places in pcretest check for end-of-line by looking for '\n';
- it now also looks for '\r' so that it will work unmodified on Windows.
-
-21. Added Google's contributed C++ wrapper to the distribution.
-
-22. Added some untidy missing memory free() calls in pcretest, to keep
- Electric Fence happy when testing.
-
-
-
-Version 5.0 13-Sep-04
----------------------
-
- 1. Internal change: literal characters are no longer packed up into items
- containing multiple characters in a single byte-string. Each character
- is now matched using a separate opcode. However, there may be more than one
- byte in the character in UTF-8 mode.
-
- 2. The pcre_callout_block structure has two new fields: pattern_position and
- next_item_length. These contain the offset in the pattern to the next match
- item, and its length, respectively.
-
- 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic
- insertion of callouts before each pattern item. Added the /C option to
- pcretest to make use of this.
-
- 4. On the advice of a Windows user, the lines
-
- #if defined(_WIN32) || defined(WIN32)
- _setmode( _fileno( stdout ), 0x8000 );
- #endif /* defined(_WIN32) || defined(WIN32) */
-
- have been added to the source of pcretest. This apparently does useful
- magic in relation to line terminators.
-
- 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb"
- for the benefit of those environments where the "b" makes a difference.
-
- 6. The icc compiler has the same options as gcc, but "configure" doesn't seem
- to know about it. I have put a hack into configure.in that adds in code
- to set GCC=yes if CC=icc. This seems to end up at a point in the
- generated configure script that is early enough to affect the setting of
- compiler options, which is what is needed, but I have no means of testing
- whether it really works. (The user who reported this had patched the
- generated configure script, which of course I cannot do.)
-
- LATER: After change 22 below (new libtool files), the configure script
- seems to know about icc (and also ecc). Therefore, I have commented out
- this hack in configure.in.
-
- 7. Added support for pkg-config (2 patches were sent in).
-
- 8. Negated POSIX character classes that used a combination of internal tables
- were completely broken. These were [[:^alpha:]], [[:^alnum:]], and
- [[:^ascii]]. Typically, they would match almost any characters. The other
- POSIX classes were not broken in this way.
-
- 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed
- to find the match, as PCRE was deluded into thinking that the match had to
- start at the start point or following a newline. The same bug applied to
- patterns with negative forward assertions or any backward assertions
- preceding ".*" at the start, unless the pattern required a fixed first
- character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed.
-
-10. In UTF-8 mode, when moving forwards in the subject after a failed match
- starting at the last subject character, bytes beyond the end of the subject
- string were read.
-
-11. Renamed the variable "class" as "classbits" to make life easier for C++
- users. (Previously there was a macro definition, but it apparently wasn't
- enough.)
-
-12. Added the new field "tables" to the extra data so that tables can be passed
- in at exec time, or the internal tables can be re-selected. This allows
- a compiled regex to be saved and re-used at a later time by a different
- program that might have everything at different addresses.
-
-13. Modified the pcre-config script so that, when run on Solaris, it shows a
- -R library as well as a -L library.
-
-14. The debugging options of pcretest (-d on the command line or D on a
- pattern) showed incorrect output for anything following an extended class
- that contained multibyte characters and which was followed by a quantifier.
-
-15. Added optional support for general category Unicode character properties
- via the \p, \P, and \X escapes. Unicode property support implies UTF-8
- support. It adds about 90K to the size of the library. The meanings of the
- inbuilt class escapes such as \d and \s have NOT been changed.
-
-16. Updated pcredemo.c to include calls to free() to release the memory for the
- compiled pattern.
-
-17. The generated file chartables.c was being created in the source directory
- instead of in the building directory. This caused the build to fail if the
- source directory was different from the building directory, and was
- read-only.
-
-18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE
- file. No doubt somebody will tell me if they don't make sense... Also added
- Dan Mooney's comments about building on OpenVMS.
-
-19. Added support for partial matching via the PCRE_PARTIAL option for
- pcre_exec() and the \P data escape in pcretest.
-
-20. Extended pcretest with 3 new pattern features:
-
- (i) A pattern option of the form ">rest-of-line" causes pcretest to
- write the compiled pattern to the file whose name is "rest-of-line".
- This is a straight binary dump of the data, with the saved pointer to
- the character tables forced to be NULL. The study data, if any, is
- written too. After writing, pcretest reads a new pattern.
-
- (ii) If, instead of a pattern, "<rest-of-line" is given, pcretest reads a
- compiled pattern from the given file. There must not be any
- occurrences of "<" in the file name (pretty unlikely); if there are,
- pcretest will instead treat the initial "<" as a pattern delimiter.
- After reading in the pattern, pcretest goes on to read data lines as
- usual.
-
- (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit
- and 16-bit fields in a compiled pattern, to simulate a pattern that
- was compiled on a host of opposite endianness.
-
-21. The pcre-exec() function can now cope with patterns that were compiled on
- hosts of opposite endianness, with this restriction:
-
- As for any compiled expression that is saved and used later, the tables
- pointer field cannot be preserved; the extra_data field in the arguments
- to pcre_exec() should be used to pass in a tables address if a value
- other than the default internal tables were used at compile time.
-
-22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is
- now diagnosed as an error. Previously, most of the time, a negative number
- would have been treated as zero, but if in addition "ovector" was passed as
- NULL, a crash could occur.
-
-23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with
- new versions from the libtool 1.5 distribution (the last one is a copy of
- a file called libtool.m4). This seems to have fixed the need to patch
- "configure" to support Darwin 1.3 (which I used to do). However, I still
- had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my
- workstation).
-
-24. Changed the PCRE licence to be the more standard "BSD" licence.
-
-
-Version 4.5 01-Dec-03
----------------------
-
- 1. There has been some re-arrangement of the code for the match() function so
- that it can be compiled in a version that does not call itself recursively.
- Instead, it keeps those local variables that need separate instances for
- each "recursion" in a frame on the heap, and gets/frees frames whenever it
- needs to "recurse". Keeping track of where control must go is done by means
- of setjmp/longjmp. The whole thing is implemented by a set of macros that
- hide most of the details from the main code, and operates only if
- NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the
- "configure" mechanism, "--disable-stack-for-recursion" turns on this way of
- operating.
-
- To make it easier for callers to provide specially tailored get/free
- functions for this usage, two new functions, pcre_stack_malloc, and
- pcre_stack_free, are used. They are always called in strict stacking order,
- and the size of block requested is always the same.
-
- The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether
- PCRE has been compiled to use the stack or the heap for recursion. The
- -C option of pcretest uses this to show which version is compiled.
-
- A new data escape \S, is added to pcretest; it causes the amounts of store
- obtained and freed by both kinds of malloc/free at match time to be added
- to the output.
-
- 2. Changed the locale test to use "fr_FR" instead of "fr" because that's
- what's available on my current Linux desktop machine.
-
- 3. When matching a UTF-8 string, the test for a valid string at the start has
- been extended. If start_offset is not zero, PCRE now checks that it points
- to a byte that is the start of a UTF-8 character. If not, it returns
- PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked;
- this is necessary because there may be backward assertions in the pattern.
- When matching the same subject several times, it may save resources to use
- PCRE_NO_UTF8_CHECK on all but the first call if the string is long.
-
- 4. The code for checking the validity of UTF-8 strings has been tightened so
- that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings
- containing "overlong sequences".
-
- 5. Fixed a bug (appearing twice) that I could not find any way of exploiting!
- I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&"
- should have been "&", but it just so happened that all the cases this let
- through by mistake were picked up later in the function.
-
- 6. I had used a variable called "isblank" - this is a C99 function, causing
- some compilers to warn. To avoid this, I renamed it (as "blankclass").
-
- 7. Cosmetic: (a) only output another newline at the end of pcretest if it is
- prompting; (b) run "./pcretest /dev/null" at the start of the test script
- so the version is shown; (c) stop "make test" echoing "./RunTest".
-
- 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems.
-
- 9. The prototype for memmove() for systems that don't have it was using
- size_t, but the inclusion of the header that defines size_t was later. I've
- moved the #includes for the C headers earlier to avoid this.
-
-10. Added some adjustments to the code to make it easier to compiler on certain
- special systems:
-
- (a) Some "const" qualifiers were missing.
- (b) Added the macro EXPORT before all exported functions; by default this
- is defined to be empty.
- (c) Changed the dftables auxiliary program (that builds chartables.c) so
- that it reads its output file name as an argument instead of writing
- to the standard output and assuming this can be redirected.
-
-11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character
- class containing characters with values greater than 255, PCRE compilation
- went into a loop.
-
-12. A recursive reference to a subpattern that was within another subpattern
- that had a minimum quantifier of zero caused PCRE to crash. For example,
- (x(y(?2))z)? provoked this bug with a subject that got as far as the
- recursion. If the recursively-called subpattern itself had a zero repeat,
- that was OK.
-
-13. In pcretest, the buffer for reading a data line was set at 30K, but the
- buffer into which it was copied (for escape processing) was still set at
- 1024, so long lines caused crashes.
-
-14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error
- "internal error: code overflow...". This applied to any character class
- that was followed by a possessive quantifier.
-
-15. Modified the Makefile to add libpcre.la as a prerequisite for
- libpcreposix.la because I was told this is needed for a parallel build to
- work.
-
-16. If a pattern that contained .* following optional items at the start was
- studied, the wrong optimizing data was generated, leading to matching
- errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any
- matching string must start with a or b or c. The correct conclusion for
- this pattern is that a match can start with any character.
-
-
-Version 4.4 13-Aug-03
----------------------
-
- 1. In UTF-8 mode, a character class containing characters with values between
- 127 and 255 was not handled correctly if the compiled pattern was studied.
- In fixing this, I have also improved the studying algorithm for such
- classes (slightly).
-
- 2. Three internal functions had redundant arguments passed to them. Removal
- might give a very teeny performance improvement.
-
- 3. Documentation bug: the value of the capture_top field in a callout is *one
- more than* the number of the hightest numbered captured substring.
-
- 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result
- in incorrectly linking with a previously installed version. They now link
- explicitly with libpcre.la.
-
- 5. configure.in no longer needs to recognize Cygwin specially.
-
- 6. A problem in pcre.in for Windows platforms is fixed.
-
- 7. If a pattern was successfully studied, and the -d (or /D) flag was given to
- pcretest, it used to include the size of the study block as part of its
- output. Unfortunately, the structure contains a field that has a different
- size on different hardware architectures. This meant that the tests that
- showed this size failed. As the block is currently always of a fixed size,
- this information isn't actually particularly useful in pcretest output, so
- I have just removed it.
-
- 8. Three pre-processor statements accidentally did not start in column 1.
- Sadly, there are *still* compilers around that complain, even though
- standard C has not required this for well over a decade. Sigh.
-
- 9. In pcretest, the code for checking callouts passed small integers in the
- callout_data field, which is a void * field. However, some picky compilers
- complained about the casts involved for this on 64-bit systems. Now
- pcretest passes the address of the small integer instead, which should get
- rid of the warnings.
-
-10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at
- both compile and run time, and gives an error if an invalid UTF-8 sequence
- is found. There is a option for disabling this check in cases where the
- string is known to be correct and/or the maximum performance is wanted.
-
-11. In response to a bug report, I changed one line in Makefile.in from
-
- -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \
- to
- -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \
-
- to look similar to other lines, but I have no way of telling whether this
- is the right thing to do, as I do not use Windows. No doubt I'll get told
- if it's wrong...
-
-
-Version 4.3 21-May-03
----------------------
-
-1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the
- Makefile.
-
-2. Some refactoring to improve the quality of the code:
-
- (i) The utf8_table... variables are now declared "const".
-
- (ii) The code for \cx, which used the "case flipping" table to upper case
- lower case letters, now just substracts 32. This is ASCII-specific,
- but the whole concept of \cx is ASCII-specific, so it seems
- reasonable.
-
- (iii) PCRE was using its character types table to recognize decimal and
- hexadecimal digits in the pattern. This is silly, because it handles
- only 0-9, a-f, and A-F, but the character types table is locale-
- specific, which means strange things might happen. A private
- table is now used for this - though it costs 256 bytes, a table is
- much faster than multiple explicit tests. Of course, the standard
- character types table is still used for matching digits in subject
- strings against \d.
-
- (iv) Strictly, the identifier ESC_t is reserved by POSIX (all identifiers
- ending in _t are). So I've renamed it as ESC_tee.
-
-3. The first argument for regexec() in the POSIX wrapper should have been
- defined as "const".
-
-4. Changed pcretest to use malloc() for its buffers so that they can be
- Electric Fenced for debugging.
-
-5. There were several places in the code where, in UTF-8 mode, PCRE would try
- to read one or more bytes before the start of the subject string. Often this
- had no effect on PCRE's behaviour, but in some circumstances it could
- provoke a segmentation fault.
-
-6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE
- to try to read one or more bytes before the start of the subject string.
-
-7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with
- UTF-8 support could misbehave in various ways if the subject string
- contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind
- area. (PCRE was not checking for the UTF-8 mode flag, and trying to move
- back over UTF-8 characters.)
-
-
-Version 4.2 14-Apr-03
----------------------
-
-1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed.
-
-2. Changes to the building process, supplied by Ronald Landheer-Cieslak
- [ON_WINDOWS]: new variable, "#" on non-Windows platforms
- [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms
- [WIN_PREFIX]: new variable, "cyg" for Cygwin
- * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT
- and BUILD_EXEEXT
- Note: automatic setting of the BUILD variables is not yet working
- set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at
- compile-time but not at link-time
- [LINK]: use for linking executables only
- make different versions for Windows and non-Windows
- [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking
- libraries
- [LINK_FOR_BUILD]: new variable
- [OBJEXT]: use throughout
- [EXEEXT]: use throughout
- <winshared>: new target
- <wininstall>: new target
- <dftables.o>: use native compiler
- <dftables>: use native linker
- <install>: handle Windows platform correctly
- <clean>: ditto
- <check>: ditto
- copy DLL to top builddir before testing
-
- As part of these changes, -no-undefined was removed again. This was reported
- to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea
- in any case.
-
-3. Some tidies to get rid of compiler warnings:
-
- . In the match_data structure, match_limit was an unsigned long int, whereas
- match_call_count was an int. I've made them both unsigned long ints.
-
- . In pcretest the fact that a const uschar * doesn't automatically cast to
- a void * provoked a warning.
-
- . Turning on some more compiler warnings threw up some "shadow" variables
- and a few more missing casts.
-
-4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8
- option, a class that contained a single character with a value between 128
- and 255 (e.g. /[\xFF]/) caused PCRE to crash.
-
-5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8
- option, a class that contained several characters, but with at least one
- whose value was between 128 and 255 caused PCRE to crash.
-
-
-Version 4.1 12-Mar-03
----------------------
-
-1. Compiling with gcc -pedantic found a couple of places where casts were
-needed, and a string in dftables.c that was longer than standard compilers are
-required to support.
-
-2. Compiling with Sun's compiler found a few more places where the code could
-be tidied up in order to avoid warnings.
-
-3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the
-first of these names is deprecated in the latest Autoconf in favour of the name
-CC_FOR_BUILD, because "host" is typically used to mean the system on which the
-compiled code will be run. I can't find a reference for HOST_CFLAGS, but by
-analogy I have changed it to CFLAGS_FOR_BUILD.
-
-4. Added -no-undefined to the linking command in the Makefile, because this is
-apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the
-linking step for the pcreposix library.
-
-5. PCRE was failing to diagnose the case of two named groups with the same
-name.
-
-6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a
-literal character that is needed in the subject for a match, and scans along to
-ensure that it is present before embarking on the full matching process. This
-saves time in cases of nested unlimited repeats that are never going to match.
-Problem: the scan can take a lot of time if the subject is very long (e.g.
-megabytes), thus penalizing straightforward matches. It is now done only if the
-amount of subject to be scanned is less than 1000 bytes.
-
-7. A lesser problem with the same optimization is that it was recording the
-first character of an anchored pattern as "needed", thus provoking a search
-right along the subject, even when the first match of the pattern was going to
-fail. The "needed" character is now not set for anchored patterns, unless it
-follows something in the pattern that is of non-fixed length. Thus, it still
-fulfils its original purpose of finding quick non-matches in cases of nested
-unlimited repeats, but isn't used for simple anchored patterns such as /^abc/.
-
-
-Version 4.0 17-Feb-03
----------------------
-
-1. If a comment in an extended regex that started immediately after a meta-item
-extended to the end of string, PCRE compiled incorrect data. This could lead to
-all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not.
-
-2. Moved to autoconf 2.53 and libtool 1.4.2.
-
-3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently,
-the special perltest8 script is no longer needed - all the tests can be run
-from a single perltest script.
-
-4. From 5.004, Perl has not included the VT character (0x0b) in the set defined
-by \s. It has now been removed in PCRE. This means it isn't recognized as
-whitespace in /x regexes too, which is the same as Perl. Note that the POSIX
-class [:space:] *does* include VT, thereby creating a mess.
-
-5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only
-space and tab.
-
-6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use
-its new features into the main test script, reducing the number of scripts.
-
-7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions
-were backward compatible, and made the (?i) apply to the whole pattern, as if
-/i were given. Now it behaves more logically, and applies the option setting
-only to what follows. PCRE has been changed to follow suit. However, if it
-finds options settings right at the start of the pattern, it extracts them into
-the global options, as before. Thus, they show up in the info data.
-
-8. Added support for the \Q...\E escape sequence. Characters in between are
-treated as literals. This is slightly different from Perl in that $ and @ are
-also handled as literals inside the quotes. In Perl, they will cause variable
-interpolation. Note the following examples:
-
- Pattern PCRE matches Perl matches
-
- \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz
- \Qabc\$xyz\E abc\$xyz abc\$xyz
- \Qabc\E\$\Qxyz\E abc$xyz abc$xyz
-
-For compatibility with Perl, \Q...\E sequences are recognized inside character
-classes as well as outside them.
-
-9. Re-organized 3 code statements in pcretest to avoid "overflow in
-floating-point constant arithmetic" warnings from a Microsoft compiler. Added a
-(size_t) cast to one statement in pcretest and one in pcreposix to avoid
-signed/unsigned warnings.
-
-10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o
-option for pcretest, so I've replaced it by a simple function that does just
-that job.
-
-11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or
-"pcregrep -".
-
-12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's
-Java package. This provides some syntactic sugar for simple cases of what my
-documentation calls "once-only subpatterns". A pattern such as x*+ is the same
-as (?>x*). In other words, if what is inside (?>...) is just a single repeated
-item, you can use this simplified notation. Note that only makes sense with
-greedy quantifiers. Consequently, the use of the possessive quantifier forces
-greediness, whatever the setting of the PCRE_UNGREEDY option.
-
-13. A change of greediness default within a pattern was not taking effect at
-the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized
-subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option
-was abstracted outside.
-
-14. PCRE now supports the \G assertion. It is true when the current matching
-position is at the start point of the match. This differs from \A when the
-starting offset is non-zero. Used with the /g option of pcretest (or similar
-code), it works in the same way as it does for Perl's /g option. If all
-alternatives of a regex begin with \G, the expression is anchored to the start
-match position, and the "anchored" flag is set in the compiled expression.
-
-15. Some bugs concerning the handling of certain option changes within patterns
-have been fixed. These applied to options other than (?ims). For example,
-"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have
-been the other way round. Some of this was related to change 7 above.
-
-16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX
-features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/
-and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports
-POSIX classes only within a class (e.g. /[[:alpha:]]/).
-
-17. Added support for Perl's \C escape. This matches one byte, even in UTF8
-mode. Unlike ".", it always matches newline, whatever the setting of
-PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind
-assertions. Perl allows it, but it doesn't (in general) work because it can't
-calculate the length of the lookbehind. At least, that's the case for Perl
-5.8.0 - I've been told they are going to document that it doesn't work in
-future.
-
-18. Added an error diagnosis for escapes that PCRE does not support: these are
-\L, \l, \N, \P, \p, \U, \u, and \X.
-
-19. Although correctly diagnosing a missing ']' in a character class, PCRE was
-reading past the end of the pattern in cases such as /[abcd/.
-
-20. PCRE was getting more memory than necessary for patterns with classes that
-contained both POSIX named classes and other characters, e.g. /[[:space:]abc/.
-
-21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for
-compiling PCRE for use with Virtual Pascal.
-
-22. Small fix to the Makefile to make it work properly if the build is done
-outside the source tree.
-
-23. Added a new extension: a condition to go with recursion. If a conditional
-subpattern starts with (?(R) the "true" branch is used if recursion has
-happened, whereas the "false" branch is used only at the top level.
-
-24. When there was a very long string of literal characters (over 255 bytes
-without UTF support, over 250 bytes with UTF support), the computation of how
-much memory was required could be incorrect, leading to segfaults or other
-strange effects.
-
-25. PCRE was incorrectly assuming anchoring (either to start of subject or to
-start of line for a non-DOTALL pattern) when a pattern started with (.*) and
-there was a subsequent back reference to those brackets. This meant that, for
-example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't
-possible to check for precisely this case. All we can do is abandon the
-optimization if .* occurs inside capturing brackets when there are any back
-references whatsoever. (See below for a better fix that came later.)
-
-26. The handling of the optimization for finding the first character of a
-non-anchored pattern, and for finding a character that is required later in the
-match were failing in some cases. This didn't break the matching; it just
-failed to optimize when it could. The way this is done has been re-implemented.
-
-27. Fixed typo in error message for invalid (?R item (it said "(?p").
-
-28. Added a new feature that provides some of the functionality that Perl
-provides with (?{...}). The facility is termed a "callout". The way it is done
-in PCRE is for the caller to provide an optional function, by setting
-pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a
-global variable. By default it is unset, which disables all calling out. To get
-the function called, the regex must include (?C) at appropriate points. This
-is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C).
-This provides a means of identifying different callout points. When PCRE
-reaches such a point in the regex, if pcre_callout has been set, the external
-function is called. It is provided with data in a structure called
-pcre_callout_block, which is defined in pcre.h. If the function returns 0,
-matching continues; if it returns a non-zero value, the match at the current
-point fails. However, backtracking will occur if possible. [This was changed
-later and other features added - see item 49 below.]
-
-29. pcretest is upgraded to test the callout functionality. It provides a
-callout function that displays information. By default, it shows the start of
-the match and the current position in the text. There are some new data escapes
-to vary what happens:
-
- \C+ in addition, show current contents of captured substrings
- \C- do not supply a callout function
- \C!n return 1 when callout number n is reached
- \C!n!m return 1 when callout number n is reached for the mth time
-
-30. If pcregrep was called with the -l option and just a single file name, it
-output "<stdin>" if a match was found, instead of the file name.
-
-31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing
-slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to
-pcre_exec(). This saves a malloc/free per call. The default value of
-POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold
-when configuring.
-
-32. The default maximum size of a compiled pattern is 64K. There have been a
-few cases of people hitting this limit. The code now uses macros to handle the
-storing of links as offsets within the compiled pattern. It defaults to 2-byte
-links, but this can be changed to 3 or 4 bytes by --with-link-size when
-configuring. Tests 2 and 5 work only with 2-byte links because they output
-debugging information about compiled patterns.
-
-33. Internal code re-arrangements:
-
-(a) Moved the debugging function for printing out a compiled regex into
- its own source file (printint.c) and used #include to pull it into
- pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two
- separate copies.
-
-(b) Defined the list of op-code names for debugging as a macro in
- internal.h so that it is next to the definition of the opcodes.
-
-(c) Defined a table of op-code lengths for simpler skipping along compiled
- code. This is again a macro in internal.h so that it is next to the
- definition of the opcodes.
-
-34. Added support for recursive calls to individual subpatterns, along the
-lines of Robin Houston's patch (but implemented somewhat differently).
-
-35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to
-allow it to read and process whole directories in Win32. This code was
-contributed by Lionel Fourquaux; it has not been tested by me.
-
-36. Added support for named subpatterns. The Python syntax (?P<name>...) is
-used to name a group. Names consist of alphanumerics and underscores, and must
-be unique. Back references use the syntax (?P=name) and recursive calls use
-(?P>name) which is a PCRE extension to the Python extension. Groups still have
-numbers. The function pcre_fullinfo() can be used after compilation to extract
-a name/number map. There are three relevant calls:
-
- PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map
- PCRE_INFO_NAMECOUNT yields the number of entries
- PCRE_INFO_NAMETABLE yields a pointer to the map.
-
-The map is a vector of fixed-size entries. The size of each entry depends on
-the length of the longest name used. The first two bytes of each entry are the
-group number, most significant byte first. There follows the corresponding
-name, zero terminated. The names are in alphabetical order.
-
-37. Make the maximum literal string in the compiled code 250 for the non-UTF-8
-case instead of 255. Making it the same both with and without UTF-8 support
-means that the same test output works with both.
-
-38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid
-calling malloc() with a zero argument.
-
-39. Change 25 above had to resort to a heavy-handed test for the .* anchoring
-optimization. I've improved things by keeping a bitmap of backreferences with
-numbers 1-31 so that if .* occurs inside capturing brackets that are not in
-fact referenced, the optimization can be applied. It is unlikely that a
-relevant occurrence of .* (i.e. one which might indicate anchoring or forcing
-the match to follow \n) will appear inside brackets with a number greater than
-31, but if it does, any back reference > 31 suppresses the optimization.
-
-40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect
-of disabling numbered capturing parentheses. Any opening parenthesis that is
-not followed by ? behaves as if it were followed by ?: but named parentheses
-can still be used for capturing (and they will acquire numbers in the usual
-way).
-
-41. Redesigned the return codes from the match() function into yes/no/error so
-that errors can be passed back from deep inside the nested calls. A malloc
-failure while inside a recursive subpattern call now causes the
-PCRE_ERROR_NOMEMORY return instead of quietly going wrong.
-
-42. It is now possible to set a limit on the number of times the match()
-function is called in a call to pcre_exec(). This facility makes it possible to
-limit the amount of recursion and backtracking, though not in a directly
-obvious way, because the match() function is used in a number of different
-circumstances. The count starts from zero for each position in the subject
-string (for non-anchored patterns). The default limit is, for compatibility, a
-large number, namely 10 000 000. You can change this in two ways:
-
-(a) When configuring PCRE before making, you can use --with-match-limit=n
- to set a default value for the compiled library.
-
-(b) For each call to pcre_exec(), you can pass a pcre_extra block in which
- a different value is set. See 45 below.
-
-If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT.
-
-43. Added a new function pcre_config(int, void *) to enable run-time extraction
-of things that can be changed at compile time. The first argument specifies
-what is wanted and the second points to where the information is to be placed.
-The current list of available information is:
-
- PCRE_CONFIG_UTF8
-
-The output is an integer that is set to one if UTF-8 support is available;
-otherwise it is set to zero.
-
- PCRE_CONFIG_NEWLINE
-
-The output is an integer that it set to the value of the code that is used for
-newline. It is either LF (10) or CR (13).
-
- PCRE_CONFIG_LINK_SIZE
-
-The output is an integer that contains the number of bytes used for internal
-linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above.
-
- PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
-
-The output is an integer that contains the threshold above which the POSIX
-interface uses malloc() for output vectors. See item 31 above.
-
- PCRE_CONFIG_MATCH_LIMIT
-
-The output is an unsigned integer that contains the default limit of the number
-of match() calls in a pcre_exec() execution. See 42 above.
-
-44. pcretest has been upgraded by the addition of the -C option. This causes it
-to extract all the available output from the new pcre_config() function, and to
-output it. The program then exits immediately.
-
-45. A need has arisen to pass over additional data with calls to pcre_exec() in
-order to support additional features. One way would have been to define
-pcre_exec2() (for example) with extra arguments, but this would not have been
-extensible, and would also have required all calls to the original function to
-be mapped to the new one. Instead, I have chosen to extend the mechanism that
-is used for passing in "extra" data from pcre_study().
-
-The pcre_extra structure is now exposed and defined in pcre.h. It currently
-contains the following fields:
-
- flags a bitmap indicating which of the following fields are set
- study_data opaque data from pcre_study()
- match_limit a way of specifying a limit on match() calls for a specific
- call to pcre_exec()
- callout_data data for callouts (see 49 below)
-
-The flag bits are also defined in pcre.h, and are
-
- PCRE_EXTRA_STUDY_DATA
- PCRE_EXTRA_MATCH_LIMIT
- PCRE_EXTRA_CALLOUT_DATA
-
-The pcre_study() function now returns one of these new pcre_extra blocks, with
-the actual study data pointed to by the study_data field, and the
-PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as
-before. That is, this change is entirely upwards-compatible and requires no
-change to existing code.
-
-If you want to pass in additional data to pcre_exec(), you can either place it
-in a pcre_extra block provided by pcre_study(), or create your own pcre_extra
-block.
-
-46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a
-data string contains the escape sequence \M, pcretest calls pcre_exec() several
-times with different match limits, until it finds the minimum value needed for
-pcre_exec() to complete. The value is then output. This can be instructive; for
-most simple matches the number is quite small, but for pathological cases it
-gets very large very quickly.
-
-47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It
-returns the size of the data block pointed to by the study_data field in a
-pcre_extra block, that is, the value that was passed as the argument to
-pcre_malloc() when PCRE was getting memory in which to place the information
-created by pcre_study(). The fourth argument should point to a size_t variable.
-pcretest has been extended so that this information is shown after a successful
-pcre_study() call when information about the compiled regex is being displayed.
-
-48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR)
-because what follows is always an absolute path. (Later: it turns out that this
-is more than cosmetic for MinGW, because it doesn't like empty path
-components.)
-
-49. Some changes have been made to the callout feature (see 28 above):
-
-(i) A callout function now has three choices for what it returns:
-
- 0 => success, carry on matching
- > 0 => failure at this point, but backtrack if possible
- < 0 => serious error, return this value from pcre_exec()
-
- Negative values should normally be chosen from the set of PCRE_ERROR_xxx
- values. In particular, returning PCRE_ERROR_NOMATCH forces a standard
- "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for
- use by callout functions. It will never be used by PCRE itself.
-
-(ii) The pcre_extra structure (see 45 above) has a void * field called
- callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The
- pcre_callout_block structure has a field of the same name. The contents of
- the field passed in the pcre_extra structure are passed to the callout
- function in the corresponding field in the callout block. This makes it
- easier to use the same callout-containing regex from multiple threads. For
- testing, the pcretest program has a new data escape
-
- \C*n pass the number n (may be negative) as callout_data
-
- If the callout function in pcretest receives a non-zero value as
- callout_data, it returns that value.
-
-50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also,
-there were some redundant $(CFLAGS) in commands that are now specified as
-$(LINK), which already includes $(CFLAGS).
-
-51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE
-has been compiled with UTF-8 support *and* pcre_compile() has been compiled
-with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume
-one-byte characters throughout. Note that case-insensitive matching applies
-only to characters whose values are less than 256. PCRE doesn't support the
-notion of cases for higher-valued characters.
-
-(i) A character class whose characters are all within 0-255 is handled as
- a bit map, and the map is inverted for negative classes. Previously, a
- character > 255 always failed to match such a class; however it should
- match if the class was a negative one (e.g. [^ab]). This has been fixed.
-
-(ii) A negated character class with a single character < 255 is coded as
- "not this character" (OP_NOT). This wasn't working properly when the test
- character was multibyte, either singly or repeated.
-
-(iii) Repeats of multibyte characters are now handled correctly in UTF-8
- mode, for example: \x{100}{2,3}.
-
-(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either
- singly or repeated) now correctly test multibyte characters. However,
- PCRE doesn't recognize any characters with values greater than 255 as
- digits, spaces, or word characters. Such characters always match \D, \S,
- and \W, and never match \d, \s, or \w.
-
-(v) Classes may now contain characters and character ranges with values
- greater than 255. For example: [ab\x{100}-\x{400}].
-
-(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call
- PCRE in UTF-8 mode.
-
-52. The info request value PCRE_INFO_FIRSTCHAR has been renamed
-PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is
-retained for backwards compatibility. (Note that LASTLITERAL is also a byte
-value.)
-
-53. The single man page has become too large. I have therefore split it up into
-a number of separate man pages. These also give rise to individual HTML pages;
-these are now put in a separate directory, and there is an index.html page that
-lists them all. Some hyperlinking between the pages has been installed.
-
-54. Added convenience functions for handling named capturing parentheses.
-
-55. Unknown escapes inside character classes (e.g. [\M]) and escapes that
-aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also
-true in PCRE, except when the PCRE_EXTENDED option is set, in which case they
-are faulted.
-
-56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when
-calling configure. These values are used when compiling the dftables.c program
-which is run to generate the source of the default character tables. They
-default to the values of CC and CFLAGS. If you are cross-compiling PCRE,
-you will need to set these values.
-
-57. Updated the building process for Windows DLL, as provided by Fred Cox.
-
-
-Version 3.9 02-Jan-02
----------------------
-
-1. A bit of extraneous text had somehow crept into the pcregrep documentation.
-
-2. If --disable-static was given, the building process failed when trying to
-build pcretest and pcregrep. (For some reason it was using libtool to compile
-them, which is not right, as they aren't part of the library.)
-
-
-Version 3.8 18-Dec-01
----------------------
-
-1. The experimental UTF-8 code was completely screwed up. It was packing the
-bytes in the wrong order. How dumb can you get?
-
-
-Version 3.7 29-Oct-01
----------------------
-
-1. In updating pcretest to check change 1 of version 3.6, I screwed up.
-This caused pcretest, when used on the test data, to segfault. Unfortunately,
-this didn't happen under Solaris 8, where I normally test things.
-
-2. The Makefile had to be changed to make it work on BSD systems, where 'make'
-doesn't seem to recognize that ./xxx and xxx are the same file. (This entry
-isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made
-this fix an hour or so after the initial 3.7 release.)
-
-
-Version 3.6 23-Oct-01
----------------------
-
-1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if
-offsets passed as NULL with zero offset count.
-
-2. The config.guess and config.sub files had not been updated when I moved to
-the latest autoconf.
-
-
-Version 3.5 15-Aug-01
----------------------
-
-1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that
-had been forgotten.
-
-2. By using declared but undefined structures, we can avoid using "void"
-definitions in pcre.h while keeping the internal definitions of the structures
-private.
-
-3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a
-user point of view, this means that both static and shared libraries are built
-by default, but this can be individually controlled. More of the work of
-handling this static/shared cases is now inside libtool instead of PCRE's make
-file.
-
-4. The pcretest utility is now installed along with pcregrep because it is
-useful for users (to test regexs) and by doing this, it automatically gets
-relinked by libtool. The documentation has been turned into a man page, so
-there are now .1, .txt, and .html versions in /doc.
-
-5. Upgrades to pcregrep:
- (i) Added long-form option names like gnu grep.
- (ii) Added --help to list all options with an explanatory phrase.
- (iii) Added -r, --recursive to recurse into sub-directories.
- (iv) Added -f, --file to read patterns from a file.
-
-6. pcre_exec() was referring to its "code" argument before testing that
-argument for NULL (and giving an error if it was NULL).
-
-7. Upgraded Makefile.in to allow for compiling in a different directory from
-the source directory.
-
-8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the
-options bits, the pointer it was passed was to an int instead of to an unsigned
-long int. This mattered only on 64-bit systems.
-
-9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is
-generated) instead of pcre.in, which it its source. Also made the same change
-in several of the .c files.
-
-10. A new release of gcc defines printf() as a macro, which broke pcretest
-because it had an ifdef in the middle of a string argument for printf(). Fixed
-by using separate calls to printf().
-
-11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure
-script, to force use of CR or LF instead of \n in the source. On non-Unix
-systems, the value can be set in config.h.
-
-12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an
-absolute limit. Changed the text of the error message to make this clear, and
-likewise updated the man page.
-
-13. The limit of 99 on the number of capturing subpatterns has been removed.
-The new limit is 65535, which I hope will not be a "real" limit.
-
-
-Version 3.4 22-Aug-00
----------------------
-
-1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *.
-
-2. Diagnose condition (?(0) as an error instead of crashing on matching.
-
-
-Version 3.3 01-Aug-00
----------------------
-
-1. If an octal character was given, but the value was greater than \377, it
-was not getting masked to the least significant bits, as documented. This could
-lead to crashes in some systems.
-
-2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats
-the hyphen as a literal. PCRE used to give an error; it now behaves like Perl.
-
-3. Added the functions pcre_free_substring() and pcre_free_substring_list().
-These just pass their arguments on to (pcre_free)(), but they are provided
-because some uses of PCRE bind it to non-C systems that can call its functions,
-but cannot call free() or pcre_free() directly.
-
-4. Add "make test" as a synonym for "make check". Corrected some comments in
-the Makefile.
-
-5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the
-Makefile.
-
-6. Changed the name of pgrep to pcregrep, because Solaris has introduced a
-command called pgrep for grepping around the active processes.
-
-7. Added the beginnings of support for UTF-8 character strings.
-
-8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and
-RANLIB to ./ltconfig so that they are used by libtool. I think these are all
-the relevant ones. (AR is not passed because ./ltconfig does its own figuring
-out for the ar command.)
-
-
-Version 3.2 12-May-00
----------------------
-
-This is purely a bug fixing release.
-
-1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead
-of ZA. This was just one example of several cases that could provoke this bug,
-which was introduced by change 9 of version 2.00. The code for breaking
-infinite loops after an iteration that matches an empty string was't working
-correctly.
-
-2. The pcretest program was not imitating Perl correctly for the pattern /a*/g
-when matched against abbab (for example). After matching an empty string, it
-wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this
-caused it to match further down the string than it should.
-
-3. The code contained an inclusion of sys/types.h. It isn't clear why this
-was there because it doesn't seem to be needed, and it causes trouble on some
-systems, as it is not a Standard C header. It has been removed.
-
-4. Made 4 silly changes to the source to avoid stupid compiler warnings that
-were reported on the Macintosh. The changes were from
-
- while ((c = *(++ptr)) != 0 && c != '\n');
-to
- while ((c = *(++ptr)) != 0 && c != '\n') ;
-
-Totally extraordinary, but if that's what it takes...
-
-5. PCRE is being used in one environment where neither memmove() nor bcopy() is
-available. Added HAVE_BCOPY and an autoconf test for it; if neither
-HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which
-assumes the way PCRE uses memmove() (always moving upwards).
-
-6. PCRE is being used in one environment where strchr() is not available. There
-was only one use in pcre.c, and writing it out to avoid strchr() probably gives
-faster code anyway.
-
-
-Version 3.1 09-Feb-00
----------------------
-
-The only change in this release is the fixing of some bugs in Makefile.in for
-the "install" target:
-
-(1) It was failing to install pcreposix.h.
-
-(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page.
-
-
-Version 3.0 01-Feb-00
----------------------
-
-1. Add support for the /+ modifier to perltest (to output $` like it does in
-pcretest).
-
-2. Add support for the /g modifier to perltest.
-
-3. Fix pcretest so that it behaves even more like Perl for /g when the pattern
-matches null strings.
-
-4. Fix perltest so that it doesn't do unwanted things when fed an empty
-pattern. Perl treats empty patterns specially - it reuses the most recent
-pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this
-effect.
-
-5. The POSIX interface was broken in that it was just handing over the POSIX
-captured string vector to pcre_exec(), but (since release 2.00) PCRE has
-required a bigger vector, with some working space on the end. This means that
-the POSIX wrapper now has to get and free some memory, and copy the results.
-
-6. Added some simple autoconf support, placing the test data and the
-documentation in separate directories, re-organizing some of the
-information files, and making it build pcre-config (a GNU standard). Also added
-libtool support for building PCRE as a shared library, which is now the
-default.
-
-7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and
-09 are not valid octal constants. Single digits will be used for minor values
-less than 10.
-
-8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that
-existing programs that set these in the POSIX interface can use PCRE without
-modification.
-
-9. Added a new function, pcre_fullinfo() with an extensible interface. It can
-return all that pcre_info() returns, plus additional data. The pcre_info()
-function is retained for compatibility, but is considered to be obsolete.
-
-10. Added experimental recursion feature (?R) to handle one common case that
-Perl 5.6 will be able to do with (?p{...}).
-
-11. Added support for POSIX character classes like [:alpha:], which Perl is
-adopting.
-
-
-Version 2.08 31-Aug-99
-----------------------
-
-1. When startoffset was not zero and the pattern began with ".*", PCRE was not
-trying to match at the startoffset position, but instead was moving forward to
-the next newline as if a previous match had failed.
-
-2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G,
-and could get into a loop if a null string was matched other than at the start
-of the subject.
-
-3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can
-be distinguished at compile time, and for completeness also added PCRE_DATE.
-
-5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL
-in GnuWin32 environments.
-
-
-Version 2.07 29-Jul-99
-----------------------
-
-1. The documentation is now supplied in plain text form and HTML as well as in
-the form of man page sources.
-
-2. C++ compilers don't like assigning (void *) values to other pointer types.
-In particular this affects malloc(). Although there is no problem in Standard
-C, I've put in casts to keep C++ compilers happy.
-
-3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call
-should be (const char *).
-
-4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may
-be useful for non-Unix systems who don't want to bother with the POSIX stuff.
-However, I haven't made this a standard facility. The documentation doesn't
-mention it, and the Makefile doesn't support it.
-
-5. The Makefile now contains an "install" target, with editable destinations at
-the top of the file. The pcretest program is not installed.
-
-6. pgrep -V now gives the PCRE version number and date.
-
-7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was
-causing the entire string to be ignored, instead of just the last character.
-
-8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a
-non-matching string, it can take a very, very long time, even for strings of
-quite modest length, because of the nested recursion. PCRE now does better in
-some of these cases. It does this by remembering the last required literal
-character in the pattern, and pre-searching the subject to ensure it is present
-before running the real match. In other words, it applies a heuristic to detect
-some types of certain failure quickly, and in the above example, if presented
-with a string that has no trailing " it gives "no match" very quickly.
-
-9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored;
-other alternatives are tried instead.
-
-
-Version 2.06 09-Jun-99
-----------------------
-
-1. Change pcretest's output for amount of store used to show just the code
-space, because the remainder (the data block) varies in size between 32-bit and
-64-bit systems.
-
-2. Added an extra argument to pcre_exec() to supply an offset in the subject to
-start matching at. This allows lookbehinds to work when searching for multiple
-occurrences in a string.
-
-3. Added additional options to pcretest for testing multiple occurrences:
-
- /+ outputs the rest of the string that follows a match
- /g loops for multiple occurrences, using the new startoffset argument
- /G loops for multiple occurrences by passing an incremented pointer
-
-4. PCRE wasn't doing the "first character" optimization for patterns starting
-with \b or \B, though it was doing it for other lookbehind assertions. That is,
-it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with
-the letter 'x'. On long subject strings, this gives a significant speed-up.
-
-
-Version 2.05 21-Apr-99
-----------------------
-
-1. Changed the type of magic_number from int to long int so that it works
-properly on 16-bit systems.
-
-2. Fixed a bug which caused patterns starting with .* not to work correctly
-when the subject string contained newline characters. PCRE was assuming
-anchoring for such patterns in all cases, which is not correct because .* will
-not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if
-DOTALL is set at top level; otherwise it knows that patterns starting with .*
-must be retried after every newline in the subject.
-
-
-Version 2.04 18-Feb-99
-----------------------
-
-1. For parenthesized subpatterns with repeats whose minimum was zero, the
-computation of the store needed to hold the pattern was incorrect (too large).
-If such patterns were nested a few deep, this could multiply and become a real
-problem.
-
-2. Added /M option to pcretest to show the memory requirement of a specific
-pattern. Made -m a synonym of -s (which does this globally) for compatibility.
-
-3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being
-compiled in such a way that the backtracking after subsequent failure was
-pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of
-((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size.
-
-
-Version 2.03 02-Feb-99
-----------------------
-
-1. Fixed typo and small mistake in man page.
-
-2. Added 4th condition (GPL supersedes if conflict) and created separate
-LICENCE file containing the conditions.
-
-3. Updated pcretest so that patterns such as /abc\/def/ work like they do in
-Perl, that is the internal \ allows the delimiter to be included in the
-pattern. Locked out the use of \ as a delimiter. If \ immediately follows
-the final delimiter, add \ to the end of the pattern (to test the error).
-
-4. Added the convenience functions for extracting substrings after a successful
-match. Updated pcretest to make it able to test these functions.
-
-
-Version 2.02 14-Jan-99
-----------------------
-
-1. Initialized the working variables associated with each extraction so that
-their saving and restoring doesn't refer to uninitialized store.
-
-2. Put dummy code into study.c in order to trick the optimizer of the IBM C
-compiler for OS/2 into generating correct code. Apparently IBM isn't going to
-fix the problem.
-
-3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution
-calls, and wasn't printing the correct value for compiling calls. Increased the
-default value of LOOPREPEAT, and the number of significant figures in the
-times.
-
-4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT.
-
-5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid
-a building problem on Windows NT with a FAT file system.
-
-
-Version 2.01 21-Oct-98
-----------------------
-
-1. Changed the API for pcre_compile() to allow for the provision of a pointer
-to character tables built by pcre_maketables() in the current locale. If NULL
-is passed, the default tables are used.
-
-
-Version 2.00 24-Sep-98
-----------------------
-
-1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable
-it any more.
-
-2. Allow quantification of (?>) groups, and make it work correctly.
-
-3. The first character computation wasn't working for (?>) groups.
-
-4. Correct the implementation of \Z (it is permitted to match on the \n at the
-end of the subject) and add 5.005's \z, which really does match only at the
-very end of the subject.
-
-5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater.
-
-6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and
-DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005
-localized options. All options to pcre_study() were also removed.
-
-7. Add other new features from 5.005:
-
- $(?<= positive lookbehind
- $(?<! negative lookbehind
- (?imsx-imsx) added the unsetting capability
- such a setting is global if at outer level; local otherwise
- (?imsx-imsx:) non-capturing groups with option setting
- (?(cond)re|re) conditional pattern matching
-
- A backreference to itself in a repeated group matches the previous
- captured string.
-
-8. General tidying up of studying (both automatic and via "study")
-consequential on the addition of new assertions.
-
-9. As in 5.005, unlimited repeated groups that could match an empty substring
-are no longer faulted at compile time. Instead, the loop is forcibly broken at
-runtime if any iteration does actually match an empty substring.
-
-10. Include the RunTest script in the distribution.
-
-11. Added tests from the Perl 5.005_02 distribution. This showed up a few
-discrepancies, some of which were old and were also with respect to 5.004. They
-have now been fixed.
-
-
-Version 1.09 28-Apr-98
-----------------------
-
-1. A negated single character class followed by a quantifier with a minimum
-value of one (e.g. [^x]{1,6} ) was not compiled correctly. This could lead to
-program crashes, or just wrong answers. This did not apply to negated classes
-containing more than one character, or to minima other than one.
-
-
-Version 1.08 27-Mar-98
-----------------------
-
-1. Add PCRE_UNGREEDY to invert the greediness of quantifiers.
-
-2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The
-latter must appear before anything that relies on it in the pattern.
-
-
-Version 1.07 16-Feb-98
-----------------------
-
-1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited
-repeat of a potentially empty string).
-
-
-Version 1.06 23-Jan-98
-----------------------
-
-1. Added Markus Oberhumer's little patches for C++.
-
-2. Literal strings longer than 255 characters were broken.
-
-
-Version 1.05 23-Dec-97
-----------------------
-
-1. Negated character classes containing more than one character were failing if
-PCRE_CASELESS was set at run time.
-
-
-Version 1.04 19-Dec-97
-----------------------
-
-1. Corrected the man page, where some "const" qualifiers had been omitted.
-
-2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with
-input syntax.
-
-3. Fixed memory leak which occurred when a regex with back references was
-matched with an offsets vector that wasn't big enough. The temporary memory
-that is used in this case wasn't being freed if the match failed.
-
-4. Tidied pcretest to ensure it frees memory that it gets.
-
-5. Temporary memory was being obtained in the case where the passed offsets
-vector was exactly big enough.
-
-6. Corrected definition of offsetof() from change 5 below.
-
-7. I had screwed up change 6 below and broken the rules for the use of
-setjmp(). Now fixed.
-
-
-Version 1.03 18-Dec-97
-----------------------
-
-1. A erroneous regex with a missing opening parenthesis was correctly
-diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes
-on some systems.
-
-2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because
-it was reported that one broken compiler failed on the former because "code" is
-also an independent variable.
-
-3. The erroneous regex a[]b caused an array overrun reference.
-
-4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not
-fail on data ending with that character. (It was going on too far, and checking
-the next character, typically a binary zero.) This was specific to the
-optimized code for single-character negative classes.
-
-5. Added a contributed patch from the TIN world which does the following:
-
- + Add an undef for memmove, in case the the system defines a macro for it.
-
- + Add a definition of offsetof(), in case there isn't one. (I don't know
- the reason behind this - offsetof() is part of the ANSI standard - but
- it does no harm).
-
- + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating
- most of the places where whitespace preceded '#'. I have given up and
- allowed the remaining 2 cases to be at the margin.
-
- + Rename some variables in pcre to eliminate shadowing. This seems very
- pedantic, but does no harm, of course.
-
-6. Moved the call to setjmp() into its own function, to get rid of warnings
-from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used.
-
-7. Constructs such as \d{8,} were compiling into the equivalent of
-\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the
-outcome, but in this particular case used more store than had been allocated,
-which caused the bug to be discovered because it threw up an internal error.
-
-8. The debugging code in both pcre and pcretest for outputting the compiled
-form of a regex was going wrong in the case of back references followed by
-curly-bracketed repeats.
-
-
-Version 1.02 12-Dec-97
-----------------------
-
-1. Typos in pcre.3 and comments in the source fixed.
-
-2. Applied a contributed patch to get rid of places where it used to remove
-'const' from variables, and fixed some signed/unsigned and uninitialized
-variable warnings.
-
-3. Added the "runtest" target to Makefile.
-
-4. Set default compiler flag to -O2 rather than just -O.
-
-
-Version 1.01 19-Nov-97
-----------------------
-
-1. PCRE was failing to diagnose unlimited repeat of empty string for patterns
-like /([ab]*)*/, that is, for classes with more than one character in them.
-
-2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such
-as /((?>a*))*/ (a PCRE_EXTRA facility).
-
-
-Version 1.00 18-Nov-97
-----------------------
-
-1. Added compile-time macros to support systems such as SunOS4 which don't have
-memmove() or strerror() but have other things that can be used instead.
-
-2. Arranged that "make clean" removes the executables.
-
-
-Version 0.99 27-Oct-97
-----------------------
-
-1. Fixed bug in code for optimizing classes with only one character. It was
-initializing a 32-byte map regardless, which could cause it to run off the end
-of the memory it had got.
-
-2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction.
-
-
-Version 0.98 22-Oct-97
-----------------------
-
-1. Fixed bug in code for handling temporary memory usage when there are more
-back references than supplied space in the ovector. This could cause segfaults.
-
-
-Version 0.97 21-Oct-97
-----------------------
-
-1. Added the \X "cut" facility, conditional on PCRE_EXTRA.
-
-2. Optimized negated single characters not to use a bit map.
-
-3. Brought error texts together as macro definitions; clarified some of them;
-fixed one that was wrong - it said "range out of order" when it meant "invalid
-escape sequence".
-
-4. Changed some char * arguments to const char *.
-
-5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX).
-
-6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in
-pcretest.
-
-
-Version 0.96 16-Oct-97
-----------------------
-
-1. Added a simple "pgrep" utility to the distribution.
-
-2. Fixed an incompatibility with Perl: "{" is now treated as a normal character
-unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}"
-where "ddd" means "one or more decimal digits".
-
-3. Fixed serious bug. If a pattern had a back reference, but the call to
-pcre_exec() didn't supply a large enough ovector to record the related
-identifying subpattern, the match always failed. PCRE now remembers the number
-of the largest back reference, and gets some temporary memory in which to save
-the offsets during matching if necessary, in order to ensure that
-backreferences always work.
-
-4. Increased the compatibility with Perl in a number of ways:
-
- (a) . no longer matches \n by default; an option PCRE_DOTALL is provided
- to request this handling. The option can be set at compile or exec time.
-
- (b) $ matches before a terminating newline by default; an option
- PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline
- mode). The option can be set at compile or exec time.
-
- (c) The handling of \ followed by a digit other than 0 is now supposed to be
- the same as Perl's. If the decimal number it represents is less than 10
- or there aren't that many previous left capturing parentheses, an octal
- escape is read. Inside a character class, it's always an octal escape,
- even if it is a single digit.
-
- (d) An escaped but undefined alphabetic character is taken as a literal,
- unless PCRE_EXTRA is set. Currently this just reserves the remaining
- escapes.
-
- (e) {0} is now permitted. (The previous item is removed from the compiled
- pattern).
-
-5. Changed all the names of code files so that the basic parts are no longer
-than 10 characters, and abolished the teeny "globals.c" file.
-
-6. Changed the handling of character classes; they are now done with a 32-byte
-bit map always.
-
-7. Added the -d and /D options to pcretest to make it possible to look at the
-internals of compilation without having to recompile pcre.
-
-
-Version 0.95 23-Sep-97
-----------------------
-
-1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or
-\x20 at the start of a run of normal characters. These were being treated as
-real characters, instead of the source characters being re-checked.
-
-
-Version 0.94 18-Sep-97
-----------------------
-
-1. The functions are now thread-safe, with the caveat that the global variables
-containing pointers to malloc() and free() or alternative functions are the
-same for all threads.
-
-2. Get pcre_study() to generate a bitmap of initial characters for non-
-anchored patterns when this is possible, and use it if passed to pcre_exec().
-
-
-Version 0.93 15-Sep-97
-----------------------
-
-1. /(b)|(:+)/ was computing an incorrect first character.
-
-2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(),
-but not actually doing anything yet.
-
-3. Treat "-" characters in classes that cannot be part of ranges as literals,
-as Perl does (e.g. [-az] or [az-]).
-
-4. Set the anchored flag if a branch starts with .* or .*? because that tests
-all possible positions.
-
-5. Split up into different modules to avoid including unneeded functions in a
-compiled binary. However, compile and exec are still in one module. The "study"
-function is split off.
-
-6. The character tables are now in a separate module whose source is generated
-by an auxiliary program - but can then be edited by hand if required. There are
-now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or
-toupper() in the code.
-
-7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and
-make them global. Abolish the function for setting them, as the caller can now
-set them directly.
-
-
-Version 0.92 11-Sep-97
-----------------------
-
-1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character
-(e.g. /a{1,3}/) was broken (I mis-optimized it).
-
-2. Caseless matching was not working in character classes if the characters in
-the pattern were in upper case.
-
-3. Make ranges like [W-c] work in the same way as Perl for caseless matching.
-
-4. Make PCRE_ANCHORED public and accept as a compile option.
-
-5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and
-PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to
-pass them.
-
-6. Give an error if bad option bits passed at compile or run time.
-
-7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to
-pcretest to cause it to pass that flag.
-
-8. Add pcre_info(), to get the number of identifying subpatterns, the stored
-options, and the first character, if set.
-
-9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character.
-
-
-Version 0.91 10-Sep-97
-----------------------
-
-1. PCRE was failing to diagnose unlimited repeats of subpatterns that could
-match the empty string as in /(a*)*/. It was looping and ultimately crashing.
-
-2. PCRE was looping on encountering an indefinitely repeated back reference to
-a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what
-Perl does - treats the match as successful.
-
-****
+++ /dev/null
-PCRE LICENCE
-------------
-
-PCRE is a library of functions to support regular expressions whose syntax
-and semantics are as close as possible to those of the Perl 5 language.
-
-Release 7 of PCRE is distributed under the terms of the "BSD" licence, as
-specified below. The documentation for PCRE, supplied in the "doc"
-directory, is distributed under the same terms as the software itself.
-
-The basic library functions are written in C and are freestanding. Also
-included in the distribution is a set of C++ wrapper functions.
-
-
-THE BASIC LIBRARY FUNCTIONS
----------------------------
-
-Written by: Philip Hazel
-Email local part: ph10
-Email domain: cam.ac.uk
-
-University of Cambridge Computing Service,
-Cambridge, England.
-
-Copyright (c) 1997-2007 University of Cambridge
-All rights reserved.
-
-
-THE C++ WRAPPER FUNCTIONS
--------------------------
-
-Contributed by: Google Inc.
-
-Copyright (c) 2007, Google Inc.
-All rights reserved.
-
-
-THE "BSD" LICENCE
------------------
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
-
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
- * Neither the name of the University of Cambridge nor the name of Google
- Inc. nor the names of their contributors may be used to endorse or
- promote products derived from this software without specific prior
- written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
-
-End
+++ /dev/null
-# $Cambridge: exim/src/src/pcre/Makefile,v 1.9 2007/06/29 08:49:17 ph10 Exp $
-
-# Makefile for PCRE (Perl-Compatible Regular Expression) library for use by
-# Exim. This is a tailored Makefile, not the normal one that comes with the
-# PCRE distribution.
-
-# These variables are in practice overridden from the Exim Makefile.
-
-AR = ar cq
-CC = gcc -O2 -Wall
-CFLAGS =
-RANLIB = @true
-
-##############################################################################
-
-OBJ = pcre_maketables.o pcre_chartables.o pcre_fullinfo.o pcre_get.o \
- pcre_globals.o pcre_compile.o pcre_config.o pcre_exec.o pcre_newline.o \
- pcre_study.o pcre_tables.o pcre_try_flipped.o pcre_version.o
-
-all: libpcre.a ../pcretest
-
-../pcretest: libpcre.a pcretest.o
- @echo "$(CC) -o ../pcretest pcretest.o libpcre.a"
- $(FE)$(CC) $(CFLAGS) -o ../pcretest pcretest.o libpcre.a
-
-libpcre.a: $(OBJ)
- -rm -f libpcre.a
- @echo "$(AR) libpcre.a"
- $(FE)$(AR) libpcre.a $(OBJ)
- $(RANLIB) libpcre.a
-
-pcre_chartables.o: pcre_chartables.c pcre_compile.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_chartables.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_chartables.c
-
-pcre_compile.o: pcre_compile.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_compile.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_compile.c
-
-pcre_config.o: pcre_config.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_config.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_config.c
-
-pcre_exec.o: pcre_chartables.c pcre_exec.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_exec.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_exec.c
-
-pcre_maketables.o: pcre_maketables.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_maketables.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_maketables.c
-
-pcre_fullinfo.o: pcre_fullinfo.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_fullinfo.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_fullinfo.c
-
-pcre_get.o: pcre_get.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_get.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_get.c
-
-pcre_globals.o: pcre_globals.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_globals.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_globals.c
-
-pcre_newline.o: pcre_newline.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_newline.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_newline.c
-
-pcre_study.o: pcre_study.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_study.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_study.c
-
-pcre_tables.o: pcre_tables.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_tables.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_tables.c
-
-pcre_try_flipped.o: pcre_try_flipped.c pcre.h config.h pcre_internal.h Makefile
- @echo "$(CC) pcre_try_flipped.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_try_flipped.c
-
-pcre_version.o: pcre_version.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcre_version.c"
- $(FE)$(CC) -c $(CFLAGS) pcre_version.c
-
-pcretest.o: pcretest.c config.h pcre.h pcre_internal.h Makefile
- @echo "$(CC) pcretest.c"
- $(FE)$(CC) -c -DNOPOSIX -DNODFA -DNOUTF8 -DNOINFOCHECK $(CFLAGS) pcretest.c
-
-# End
-$Cambridge: exim/src/src/pcre/README,v 1.1 2004/10/07 13:04:13 ph10 Exp $
+$Cambridge: exim/src/src/pcre/README,v 1.2 2008/01/16 13:44:45 nm4 Exp $
PCRE for use in Exim
--------------------
-This directory contains a subset of the files from the PCRE distribution,
-enough to supply regular expression support for Exim, plus the pcretest test
-program. Do not start from here if you want to install PCRE as a free-standing
-library for use by other programs. Get the full PCRE distribution, which can be
-obtained from
+This directory used to contain a subset of the files from the PCRE distribution.
-ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-x.x.tar.gz
+However carrying our own subset of PCRE, especially when the vast
+majority of systems now have PCRE as a system library, has become a
+liability, requiring exim to be manually updated whenever changes are
+made in PCRE.
-where x.x is the version number. This contains support for a POSIX interface to
-PCRE, a "grep" program that uses PCRE, and the means to build PCRE as a shared
-library. It is configured by autoconf, and has "make install" support in the
-conventional way.
+PCRE can be found at http://www.pcre.org/
-Philip Hazel <ph10@cam.ac.uk>
-February 2000
+Nigel Metheringham
+January 2008
+++ /dev/null
-/* $Cambridge: exim/src/src/pcre/config.h,v 1.4 2007/11/12 13:02:19 nm4 Exp $ */
-
-/*************************************************
-* config.h for PCRE for Exim *
-*************************************************/
-
-/* The PCRE sources include config.h, which for a free-standing PCRE build gets
-set up by autoconf. For the embedded version in Exim, this file, which is
-manually maintained, is used.
-
-The only configuration thing that matters for the PCRE library itself is
-whether the memmove() function exists or not. It should be present in all
-Standard C libraries, but is missing in SunOS4. PCRE expects autoconf to set
-HAVE_MEMMOVE to 1 in config.h when memmove() is present. If that is not set, it
-defines memmove() as a macro for bcopy().
-
-Exim works differently. It handles this case by defining memmove() as a macro
-in its os.h-SunOS4 file. We interface this to PCRE by including the os.h file
-here, and then defining HAVE_MEMOVE so that PCRE's code in internal.h leaves
-things alone. */
-
-#ifndef PCRE_CONFIG_H
-#define PCRE_CONFIG_H
-
-#include "../os.h"
-#define HAVE_MEMMOVE 1
-
-/* We also set up directly a number of parameters that, in the freestanding
-PCRE, can be adjusted by "configure". */
-
-#define NEWLINE '\n'
-#define LINK_SIZE 2
-#define MATCH_LIMIT 10000000
-#define MATCH_LIMIT_RECURSION 10000000
-#define POSIX_MALLOC_THRESHOLD 10
-
-#define MAX_NAME_SIZE 32
-#define MAX_NAME_COUNT 10000
-#define MAX_DUPLENGTH 30000
-
-/* There is some stuff in the PCRE sources for compilation on non-Unix systems
-and non-ASCII systems. For Exim's purposes, just flatten it. */
-
-#undef EBCDIC
-
-#endif // include once
-
-/* End */
+++ /dev/null
-/* $Cambridge: exim/src/src/pcre/dftables.c,v 1.7 2007/11/12 13:02:19 nm4 Exp $ */
-
-/*************************************************
-* Perl-Compatible Regular Expressions *
-*************************************************/
-
-/* PCRE is a library of functions to support regular expressions whose syntax
-and semantics are as close as possible to those of the Perl 5 language.
-
- Written by Philip Hazel
- Copyright (c) 1997-2007 University of Cambridge
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
-
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
- * Neither the name of the University of Cambridge nor the names of its
- contributors may be used to endorse or promote products derived from
- this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This is a freestanding support program to generate a file containing
-character tables for PCRE. The tables are built according to the current
-locale. Now that pcre_maketables is a function visible to the outside world, we
-make use of its code from here in order to be consistent. */
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#include <ctype.h>
-#include <stdio.h>
-#include <string.h>
-#include <locale.h>
-
-#include "pcre_internal.h"
-
-#define DFTABLES /* pcre_maketables.c notices this */
-#include "pcre_maketables.c"
-
-
-int main(int argc, char **argv)
-{
-FILE *f;
-int i = 1;
-const unsigned char *tables;
-const unsigned char *base_of_tables;
-
-/* By default, the default C locale is used rather than what the building user
-happens to have set. However, if the -L option is given, set the locale from
-the LC_xxx environment variables. */
-
-if (argc > 1 && strcmp(argv[1], "-L") == 0)
- {
- setlocale(LC_ALL, ""); /* Set from environment variables */
- i++;
- }
-
-if (argc < i + 1)
- {
- fprintf(stderr, "dftables: one filename argument is required\n");
- return 1;
- }
-
-tables = pcre_maketables();
-base_of_tables = tables;
-
-f = fopen(argv[i], "wb");
-if (f == NULL)
- {
- fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]);
- return 1;
- }
-
-/* There are several fprintf() calls here, because gcc in pedantic mode
-complains about the very long string otherwise. */
-
-fprintf(f,
- "/*************************************************\n"
- "* Perl-Compatible Regular Expressions *\n"
- "*************************************************/\n\n"
- "/* This file was automatically written by the dftables auxiliary\n"
- "program. It contains character tables that are used when no external\n"
- "tables are passed to PCRE by the application that calls it. The tables\n"
- "are used only for characters whose code values are less than 256.\n\n");
-fprintf(f,
- "The following #includes are present because without them gcc 4.x may remove\n"
- "the array definition from the final binary if PCRE is built into a static\n"
- "library and dead code stripping is activated. This leads to link errors.\n"
- "Pulling in the header ensures that the array gets flagged as \"someone\n"
- "outside this compilation unit might reference this\" and so it will always\n"
- "be supplied to the linker. */\n\n"
- "#ifdef HAVE_CONFIG_H\n"
- "#include \"config.h\"\n"
- "#endif\n\n"
- "#include \"pcre_internal.h\"\n\n");
-fprintf(f,
- "const unsigned char _pcre_default_tables[] = {\n\n"
- "/* This table is a lower casing table. */\n\n");
-
-fprintf(f, " ");
-for (i = 0; i < 256; i++)
- {
- if ((i & 7) == 0 && i != 0) fprintf(f, "\n ");
- fprintf(f, "%3d", *tables++);
- if (i != 255) fprintf(f, ",");
- }
-fprintf(f, ",\n\n");
-
-fprintf(f, "/* This table is a case flipping table. */\n\n");
-
-fprintf(f, " ");
-for (i = 0; i < 256; i++)
- {
- if ((i & 7) == 0 && i != 0) fprintf(f, "\n ");
- fprintf(f, "%3d", *tables++);
- if (i != 255) fprintf(f, ",");
- }
-fprintf(f, ",\n\n");
-
-fprintf(f,
- "/* This table contains bit maps for various character classes.\n"
- "Each map is 32 bytes long and the bits run from the least\n"
- "significant end of each byte. The classes that have their own\n"
- "maps are: space, xdigit, digit, upper, lower, word, graph\n"
- "print, punct, and cntrl. Other classes are built from combinations. */\n\n");
-
-fprintf(f, " ");
-for (i = 0; i < cbit_length; i++)
- {
- if ((i & 7) == 0 && i != 0)
- {
- if ((i & 31) == 0) fprintf(f, "\n");
- fprintf(f, "\n ");
- }
- fprintf(f, "0x%02x", *tables++);
- if (i != cbit_length - 1) fprintf(f, ",");
- }
-fprintf(f, ",\n\n");
-
-fprintf(f,
- "/* This table identifies various classes of character by individual bits:\n"
- " 0x%02x white space character\n"
- " 0x%02x letter\n"
- " 0x%02x decimal digit\n"
- " 0x%02x hexadecimal digit\n"
- " 0x%02x alphanumeric or '_'\n"
- " 0x%02x regular expression metacharacter or binary zero\n*/\n\n",
- ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word,
- ctype_meta);
-
-fprintf(f, " ");
-for (i = 0; i < 256; i++)
- {
- if ((i & 7) == 0 && i != 0)
- {
- fprintf(f, " /* ");
- if (isprint(i-8)) fprintf(f, " %c -", i-8);
- else fprintf(f, "%3d-", i-8);
- if (isprint(i-1)) fprintf(f, " %c ", i-1);
- else fprintf(f, "%3d", i-1);
- fprintf(f, " */\n ");
- }
- fprintf(f, "0x%02x", *tables++);
- if (i != 255) fprintf(f, ",");
- }
-
-fprintf(f, "};/* ");
-if (isprint(i-8)) fprintf(f, " %c -", i-8);
- else fprintf(f, "%3d-", i-8);
-if (isprint(i-1)) fprintf(f, " %c ", i-1);
- else fprintf(f, "%3d", i-1);
-fprintf(f, " */\n\n/* End of pcre_chartables.c */\n");
-
-fclose(f);
-free((void *)base_of_tables);
-return 0;
-}
-
-/* End of dftables.c */
+++ /dev/null
-/* $Cambridge: exim/src/src/pcre/pcre.h,v 1.7 2007/11/12 13:02:19 nm4 Exp $ */
-
-/*************************************************
-* Perl-Compatible Regular Expressions *
-*************************************************/
-
-/* This is the public header file for the PCRE library, to be #included by
-applications that call the PCRE functions.
-
- Copyright (c) 1997-2007 University of Cambridge
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
-
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
- * Neither the name of the University of Cambridge nor the names of its
- contributors may be used to endorse or promote products derived from
- this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-#ifndef _PCRE_H
-#define _PCRE_H
-
-/* The current PCRE version information. */
-
-#define PCRE_MAJOR 7
-#define PCRE_MINOR 2
-#define PCRE_PRERELEASE
-#define PCRE_DATE 2007-06-19
-
-/* 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
-export setting is defined in pcre_internal.h, which includes this file. So we
-don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
-
-#if defined(_WIN32) && !defined(PCRE_STATIC)
-# ifndef PCRE_EXP_DECL
-# define PCRE_EXP_DECL extern __declspec(dllimport)
-# endif
-# ifdef __cplusplus
-# ifndef PCRECPP_EXP_DECL
-# define PCRECPP_EXP_DECL extern __declspec(dllimport)
-# endif
-# ifndef PCRECPP_EXP_DEFN
-# define PCRECPP_EXP_DEFN __declspec(dllimport)
-# endif
-# endif
-#endif
-
-/* By default, we use the standard "extern" declarations. */
-
-#ifndef PCRE_EXP_DECL
-# ifdef __cplusplus
-# define PCRE_EXP_DECL extern "C"
-# else
-# define PCRE_EXP_DECL extern
-# endif
-#endif
-
-#ifdef __cplusplus
-# ifndef PCRECPP_EXP_DECL
-# define PCRECPP_EXP_DECL extern
-# endif
-# ifndef PCRECPP_EXP_DEFN
-# define PCRECPP_EXP_DEFN
-# endif
-#endif
-
-/* Have to include stdlib.h in order to ensure that size_t is defined;
-it is needed here for malloc. */
-
-#include <stdlib.h>
-
-/* Allow for C++ users */
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* Options */
-
-#define PCRE_CASELESS 0x00000001
-#define PCRE_MULTILINE 0x00000002
-#define PCRE_DOTALL 0x00000004
-#define PCRE_EXTENDED 0x00000008
-#define PCRE_ANCHORED 0x00000010
-#define PCRE_DOLLAR_ENDONLY 0x00000020
-#define PCRE_EXTRA 0x00000040
-#define PCRE_NOTBOL 0x00000080
-#define PCRE_NOTEOL 0x00000100
-#define PCRE_UNGREEDY 0x00000200
-#define PCRE_NOTEMPTY 0x00000400
-#define PCRE_UTF8 0x00000800
-#define PCRE_NO_AUTO_CAPTURE 0x00001000
-#define PCRE_NO_UTF8_CHECK 0x00002000
-#define PCRE_AUTO_CALLOUT 0x00004000
-#define PCRE_PARTIAL 0x00008000
-#define PCRE_DFA_SHORTEST 0x00010000
-#define PCRE_DFA_RESTART 0x00020000
-#define PCRE_FIRSTLINE 0x00040000
-#define PCRE_DUPNAMES 0x00080000
-#define PCRE_NEWLINE_CR 0x00100000
-#define PCRE_NEWLINE_LF 0x00200000
-#define PCRE_NEWLINE_CRLF 0x00300000
-#define PCRE_NEWLINE_ANY 0x00400000
-#define PCRE_NEWLINE_ANYCRLF 0x00500000
-#define PCRE_BSR_ANYCRLF 0x00800000
-#define PCRE_BSR_UNICODE 0x01000000
-
-/* Exec-time and get/set-time error codes */
-
-#define PCRE_ERROR_NOMATCH (-1)
-#define PCRE_ERROR_NULL (-2)
-#define PCRE_ERROR_BADOPTION (-3)
-#define PCRE_ERROR_BADMAGIC (-4)
-#define PCRE_ERROR_UNKNOWN_OPCODE (-5)
-#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */
-#define PCRE_ERROR_NOMEMORY (-6)
-#define PCRE_ERROR_NOSUBSTRING (-7)
-#define PCRE_ERROR_MATCHLIMIT (-8)
-#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */
-#define PCRE_ERROR_BADUTF8 (-10)
-#define PCRE_ERROR_BADUTF8_OFFSET (-11)
-#define PCRE_ERROR_PARTIAL (-12)
-#define PCRE_ERROR_BADPARTIAL (-13)
-#define PCRE_ERROR_INTERNAL (-14)
-#define PCRE_ERROR_BADCOUNT (-15)
-#define PCRE_ERROR_DFA_UITEM (-16)
-#define PCRE_ERROR_DFA_UCOND (-17)
-#define PCRE_ERROR_DFA_UMLIMIT (-18)
-#define PCRE_ERROR_DFA_WSSIZE (-19)
-#define PCRE_ERROR_DFA_RECURSE (-20)
-#define PCRE_ERROR_RECURSIONLIMIT (-21)
-#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
-#define PCRE_ERROR_BADNEWLINE (-23)
-
-/* Request types for pcre_fullinfo() */
-
-#define PCRE_INFO_OPTIONS 0
-#define PCRE_INFO_SIZE 1
-#define PCRE_INFO_CAPTURECOUNT 2
-#define PCRE_INFO_BACKREFMAX 3
-#define PCRE_INFO_FIRSTBYTE 4
-#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */
-#define PCRE_INFO_FIRSTTABLE 5
-#define PCRE_INFO_LASTLITERAL 6
-#define PCRE_INFO_NAMEENTRYSIZE 7
-#define PCRE_INFO_NAMECOUNT 8
-#define PCRE_INFO_NAMETABLE 9
-#define PCRE_INFO_STUDYSIZE 10
-#define PCRE_INFO_DEFAULT_TABLES 11
-#define PCRE_INFO_OKPARTIAL 12
-#define PCRE_INFO_JCHANGED 13
-#define PCRE_INFO_HASCRORLF 14
-
-/* Request types for pcre_config(). Do not re-arrange, in order to remain
-compatible. */
-
-#define PCRE_CONFIG_UTF8 0
-#define PCRE_CONFIG_NEWLINE 1
-#define PCRE_CONFIG_LINK_SIZE 2
-#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3
-#define PCRE_CONFIG_MATCH_LIMIT 4
-#define PCRE_CONFIG_STACKRECURSE 5
-#define PCRE_CONFIG_UNICODE_PROPERTIES 6
-#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
-#define PCRE_CONFIG_BSR 8
-
-/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
-these bits, just add new ones on the end, in order to remain compatible. */
-
-#define PCRE_EXTRA_STUDY_DATA 0x0001
-#define PCRE_EXTRA_MATCH_LIMIT 0x0002
-#define PCRE_EXTRA_CALLOUT_DATA 0x0004
-#define PCRE_EXTRA_TABLES 0x0008
-#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010
-
-/* Types */
-
-struct real_pcre; /* declaration; the definition is private */
-typedef struct real_pcre pcre;
-
-/* When PCRE is compiled as a C++ library, the subject pointer type can be
-replaced with a custom type. For conventional use, the public interface is a
-const char *. */
-
-#ifndef PCRE_SPTR
-#define PCRE_SPTR const char *
-#endif
-
-/* The structure for passing additional data to pcre_exec(). This is defined in
-such as way as to be extensible. Always add new fields at the end, in order to
-remain compatible. */
-
-typedef struct pcre_extra {
- unsigned long int flags; /* Bits for which fields are set */
- void *study_data; /* Opaque data from pcre_study() */
- unsigned long int match_limit; /* Maximum number of calls to match() */
- void *callout_data; /* Data passed back in callouts */
- const unsigned char *tables; /* Pointer to character tables */
- unsigned long int match_limit_recursion; /* Max recursive calls to match() */
-} pcre_extra;
-
-/* The structure for passing out data via the pcre_callout_function. We use a
-structure so that new fields can be added on the end in future versions,
-without changing the API of the function, thereby allowing old clients to work
-without modification. */
-
-typedef struct pcre_callout_block {
- int version; /* Identifies version of block */
- /* ------------------------ Version 0 ------------------------------- */
- int callout_number; /* Number compiled into pattern */
- int *offset_vector; /* The offset vector */
- PCRE_SPTR subject; /* The subject being matched */
- int subject_length; /* The length of the subject */
- int start_match; /* Offset to start of this match attempt */
- int current_position; /* Where we currently are in the subject */
- int capture_top; /* Max current capture */
- int capture_last; /* Most recently closed capture */
- void *callout_data; /* Data passed in with the call */
- /* ------------------- Added for Version 1 -------------------------- */
- int pattern_position; /* Offset to next item in the pattern */
- int next_item_length; /* Length of next item in the pattern */
- /* ------------------------------------------------------------------ */
-} pcre_callout_block;
-
-/* Indirection for store get and free functions. These can be set to
-alternative malloc/free functions if required. Special ones are used in the
-non-recursive case for "frames". There is also an optional callout function
-that is triggered by the (?) regex item. For Virtual Pascal, these definitions
-have to take another form. */
-
-#ifndef VPCOMPAT
-PCRE_EXP_DECL void *(*pcre_malloc)(size_t);
-PCRE_EXP_DECL void (*pcre_free)(void *);
-PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
-PCRE_EXP_DECL void (*pcre_stack_free)(void *);
-PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *);
-#else /* VPCOMPAT */
-PCRE_EXP_DECL void *pcre_malloc(size_t);
-PCRE_EXP_DECL void pcre_free(void *);
-PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
-PCRE_EXP_DECL void pcre_stack_free(void *);
-PCRE_EXP_DECL int pcre_callout(pcre_callout_block *);
-#endif /* VPCOMPAT */
-
-/* Exported PCRE functions */
-
-PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
- const unsigned char *);
-PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **,
- int *, const unsigned char *);
-PCRE_EXP_DECL int pcre_config(int, void *);
-PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *,
- int *, int, const char *, char *, int);
-PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *,
- int);
-PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *,
- const char *, int, int, int, int *, int , int *, int);
-PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
- int, int, int, int *, int);
-PCRE_EXP_DECL void pcre_free_substring(const char *);
-PCRE_EXP_DECL void pcre_free_substring_list(const char **);
-PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int,
- void *);
-PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *,
- int *, int, const char *, const char **);
-PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *);
-PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *,
- char **, char **);
-PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int,
- const char **);
-PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int,
- const char ***);
-PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *);
-PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
-PCRE_EXP_DECL int pcre_refcount(pcre *, int);
-PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
-PCRE_EXP_DECL const char *pcre_version(void);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif /* End of pcre.h */
+++ /dev/null
-/* $Cambridge: exim/src/src/pcre/pcre_chartables.c,v 1.2 2007/11/12 13:02:19 nm4 Exp $ */
-
-/*************************************************
-* Perl-Compatible Regular Expressions *
-*************************************************/
-
-/* This file contains character tables that are used when no external tables
-are passed to PCRE by the application that calls it. The tables are used only
-for characters whose code values are less than 256.
-
-This is a default version of the tables that assumes ASCII encoding. A program
-called dftables (which is distributed with PCRE) can be used to build
-alternative versions of this file. This is necessary if you are running in an
-EBCDIC environment, or if you want to default to a different encoding, for
-example ISO-8859-1. When dftables is run, it creates these tables in the
-current locale. If PCRE is configured with --enable-rebuild-chartables, this
-happens automatically.
-
-The following #includes are present because without the gcc 4.x may remove the
-array definition from the final binary if PCRE is built into a static library
-and dead code stripping is activated. This leads to link errors. Pulling in the
-header ensures that the array gets flagged as "someone outside this compilation
-unit might reference this" and so it will always be supplied to the linker. */
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#include "pcre_internal.h"
-
-const unsigned char _pcre_default_tables[] = {
-
-/* This table is a lower casing table. */
-
- 0, 1, 2, 3, 4, 5, 6, 7,
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 97, 98, 99,100,101,102,103,
- 104,105,106,107,108,109,110,111,
- 112,113,114,115,116,117,118,119,
- 120,121,122, 91, 92, 93, 94, 95,
- 96, 97, 98, 99,100,101,102,103,
- 104,105,106,107,108,109,110,111,
- 112,113,114,115,116,117,118,119,
- 120,121,122,123,124,125,126,127,
- 128,129,130,131,132,133,134,135,
- 136,137,138,139,140,141,142,143,
- 144,145,146,147,148,149,150,151,
- 152,153,154,155,156,157,158,159,
- 160,161,162,163,164,165,166,167,
- 168,169,170,171,172,173,174,175,
- 176,177,178,179,180,181,182,183,
- 184,185,186,187,188,189,190,191,
- 192,193,194,195,196,197,198,199,
- 200,201,202,203,204,205,206,207,
- 208,209,210,211,212,213,214,215,
- 216,217,218,219,220,221,222,223,
- 224,225,226,227,228,229,230,231,
- 232,233,234,235,236,237,238,239,
- 240,241,242,243,244,245,246,247,
- 248,249,250,251,252,253,254,255,
-
-/* This table is a case flipping table. */
-
- 0, 1, 2, 3, 4, 5, 6, 7,
- 8, 9, 10, 11, 12, 13, 14, 15,
- 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 36, 37, 38, 39,
- 40, 41, 42, 43, 44, 45, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55,
- 56, 57, 58, 59, 60, 61, 62, 63,
- 64, 97, 98, 99,100,101,102,103,
- 104,105,106,107,108,109,110,111,
- 112,113,114,115,116,117,118,119,
- 120,121,122, 91, 92, 93, 94, 95,
- 96, 65, 66, 67, 68, 69, 70, 71,
- 72, 73, 74, 75, 76, 77, 78, 79,
- 80, 81, 82, 83, 84, 85, 86, 87,
- 88, 89, 90,123,124,125,126,127,
- 128,129,130,131,132,133,134,135,
- 136,137,138,139,140,141,142,143,
- 144,145,146,147,148,149,150,151,
- 152,153,154,155,156,157,158,159,
- 160,161,162,163,164,165,166,167,
- 168,169,170,171,172,173,174,175,
- 176,177,178,179,180,181,182,183,
- 184,185,186,187,188,189,190,191,
- 192,193,194,195,196,197,198,199,
- 200,201,202,203,204,205,206,207,
- 208,209,210,211,212,213,214,215,
- 216,217,218,219,220,221,222,223,
- 224,225,226,227,228,229,230,231,
- 232,233,234,235,236,237,238,239,
- 240,241,242,243,244,245,246,247,
- 248,249,250,251,252,253,254,255,
-
-/* This table contains bit maps for various character classes. Each map is 32
-bytes long and the bits run from the least significant end of each byte. The
-classes that have their own maps are: space, xdigit, digit, upper, lower, word,
-graph, print, punct, and cntrl. Other classes are built from combinations. */
-
- 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
- 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
- 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,
- 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,
- 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,
- 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
- 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-
-/* This table identifies various classes of character by individual bits:
- 0x01 white space character
- 0x02 letter
- 0x04 decimal digit
- 0x08 hexadecimal digit
- 0x10 alphanumeric or '_'
- 0x80 regular expression metacharacter or binary zero
-*/
-
- 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
- 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
- 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */
- 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */
- 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */
- 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */
- 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */
- 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
- 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
- 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */
- 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */
- 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */
- 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */
- 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
-
-/* End of pcre_chartables.c */
+++ /dev/null
-/* $Cambridge: exim/src/src/pcre/pcre_compile.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */
-
-/*************************************************
-* Perl-Compatible Regular Expressions *
-*************************************************/
-
-/* PCRE is a library of functions to support regular expressions whose syntax
-and semantics are as close as possible to those of the Perl 5 language.
-
- Written by Philip Hazel
- Copyright (c) 1997-2007 University of Cambridge
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
-
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
- * Neither the name of the University of Cambridge nor the names of its
- contributors may be used to endorse or promote products derived from
- this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This module contains the external function pcre_compile(), along with
-supporting internal functions that are not used by other modules. */
-
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#define NLBLOCK cd /* Block containing newline information */
-#define PSSTART start_pattern /* Field containing processed string start */
-#define PSEND end_pattern /* Field containing processed string end */
-
-#include "pcre_internal.h"
-
-
-/* When DEBUG is defined, we need the pcre_printint() function, which is also
-used by pcretest. DEBUG is not defined when building a production library. */
-
-#ifdef DEBUG
-#include "pcre_printint.src"
-#endif
-
-
-/* Macro for setting individual bits in class bitmaps. */
-
-#define SETBIT(a,b) a[b/8] |= (1 << (b%8))
-
-/* 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
-INT_MAX to allow for adding in group terminating bytes, so that we don't have
-to check them every time. */
-
-#define OFLOW_MAX (INT_MAX - 20)
-
-
-/*************************************************
-* Code parameters and static tables *
-*************************************************/
-
-/* This value specifies the size of stack workspace that is used during the
-first pre-compile phase that determines how much memory is required. The regex
-is partly compiled into this space, but the compiled parts are discarded as
-soon as they can be, so that hopefully there will never be an overrun. The code
-does, however, check for an overrun. The largest amount I've seen used is 218,
-so this number is very generous.
-
-The same workspace is used during the second, actual compile phase for
-remembering forward references to groups so that they can be filled in at the
-end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE
-is 4 there is plenty of room. */
-
-#define COMPILE_WORK_SIZE (4096)
-
-
-/* Table for handling escaped characters in the range '0'-'z'. Positive returns
-are simple data values; negative values are for special things like \d and so
-on. Zero means further processing is needed (for things like \x), or the escape
-is invalid. */
-
-#ifndef EBCDIC /* This is the "normal" table for ASCII systems */
-static const short int escapes[] = {
- 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */
- 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */
- '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */
--ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */
--ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */
--ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */
- '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */
--ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */
--ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */
- 0, 0, -ESC_z /* x - z */
-};
-
-#else /* This is the "abnormal" table for EBCDIC systems */
-static const short int escapes[] = {
-/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|',
-/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0,
-/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~',
-/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0,
-/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?',
-/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0,
-/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"',
-/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0,
-/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0,
-/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p,
-/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0,
-/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0,
-/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0,
-/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0,
-/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-',
-/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G,
-/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0,
-/* D0 */ '}', 0, -ESC_K, 0, 0, 0, 0, -ESC_P,
-/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0,
-/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X,
-/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0,
-/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0,
-/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0
-};
-#endif
-
-
-/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
-searched linearly. Put all the names into a single string, in order to reduce
-the number of relocations when a shared library is dynamically linked. */
-
-typedef struct verbitem {
- int len;
- int op;
-} verbitem;
-
-static const char verbnames[] =
- "ACCEPT\0"
- "COMMIT\0"
- "F\0"
- "FAIL\0"
- "PRUNE\0"
- "SKIP\0"
- "THEN";
-
-static verbitem verbs[] = {
- { 6, OP_ACCEPT },
- { 6, OP_COMMIT },
- { 1, OP_FAIL },
- { 4, OP_FAIL },
- { 5, OP_PRUNE },
- { 4, OP_SKIP },
- { 4, OP_THEN }
-};
-
-static int verbcount = sizeof(verbs)/sizeof(verbitem);
-
-
-/* Tables of names of POSIX character classes and their lengths. The names are
-now all in a single string, to reduce the number of relocations when a shared
-library is dynamically loaded. The list of lengths is terminated by a zero
-length entry. The first three must be alpha, lower, upper, as this is assumed
-for handling case independence. */
-
-static const char posix_names[] =
- "alpha\0" "lower\0" "upper\0" "alnum\0" "ascii\0" "blank\0"
- "cntrl\0" "digit\0" "graph\0" "print\0" "punct\0" "space\0"
- "word\0" "xdigit";
-
-static const uschar posix_name_lengths[] = {
- 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
-
-/* Table of class bit maps for each POSIX class. Each class is formed from a
-base map, with an optional addition or removal of another map. Then, for some
-classes, there is some additional tweaking: for [:blank:] the vertical space
-characters are removed, and for [:alpha:] and [:alnum:] the underscore
-character is removed. The triples in the table consist of the base map offset,
-second map offset or -1 if no second map, and a non-negative value for map
-addition or a negative value for map subtraction (if there are two maps). The
-absolute value of the third field has these meanings: 0 => no tweaking, 1 =>
-remove vertical space characters, 2 => remove underscore. */
-
-static const int posix_class_maps[] = {
- cbit_word, cbit_digit, -2, /* alpha */
- cbit_lower, -1, 0, /* lower */
- cbit_upper, -1, 0, /* upper */
- cbit_word, -1, 2, /* alnum - word without underscore */
- cbit_print, cbit_cntrl, 0, /* ascii */
- cbit_space, -1, 1, /* blank - a GNU extension */
- cbit_cntrl, -1, 0, /* cntrl */
- cbit_digit, -1, 0, /* digit */
- cbit_graph, -1, 0, /* graph */
- cbit_print, -1, 0, /* print */
- cbit_punct, -1, 0, /* punct */
- cbit_space, -1, 0, /* space */
- cbit_word, -1, 0, /* word - a Perl extension */
- cbit_xdigit,-1, 0 /* xdigit */
-};
-
-
-#define STRING(a) # a
-#define XSTRING(s) STRING(s)
-
-/* The texts of compile-time error messages. These are "char *" because they
-are passed to the outside world. Do not ever re-use any error number, because
-they are documented. Always add a new error instead. Messages marked DEAD below
-are no longer used. This used to be a table of strings, but in order to reduce
-the number of relocations needed when a shared library is loaded dynamically,
-it is now one long string. We cannot use a table of offsets, because the
-lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we
-simply count through to the one we want - this isn't a performance issue
-because these strings are used only when there is a compilation error. */
-
-static const char error_texts[] =
- "no error\0"
- "\\ at end of pattern\0"
- "\\c at end of pattern\0"
- "unrecognized character follows \\\0"
- "numbers out of order in {} quantifier\0"
- /* 5 */
- "number too big in {} quantifier\0"
- "missing terminating ] for character class\0"
- "invalid escape sequence in character class\0"
- "range out of order in character class\0"
- "nothing to repeat\0"
- /* 10 */
- "operand of unlimited repeat could match the empty string\0" /** DEAD **/
- "internal error: unexpected repeat\0"
- "unrecognized character after (?\0"
- "POSIX named classes are supported only within a class\0"
- "missing )\0"
- /* 15 */
- "reference to non-existent subpattern\0"
- "erroffset passed as NULL\0"
- "unknown option bit(s) set\0"
- "missing ) after comment\0"
- "parentheses nested too deeply\0" /** DEAD **/
- /* 20 */
- "regular expression is too large\0"
- "failed to get memory\0"
- "unmatched parentheses\0"
- "internal error: code overflow\0"
- "unrecognized character after (?<\0"
- /* 25 */
- "lookbehind assertion is not fixed length\0"
- "malformed number or name after (?(\0"
- "conditional group contains more than two branches\0"
- "assertion expected after (?(\0"
- "(?R or (?[+-]digits must be followed by )\0"
- /* 30 */
- "unknown POSIX class name\0"
- "POSIX collating elements are not supported\0"
- "this version of PCRE is not compiled with PCRE_UTF8 support\0"
- "spare error\0" /** DEAD **/
- "character value in \\x{...} sequence is too large\0"
- /* 35 */
- "invalid condition (?(0)\0"
- "\\C not allowed in lookbehind assertion\0"
- "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0"
- "number after (?C is > 255\0"
- "closing ) for (?C expected\0"
- /* 40 */
- "recursive call could loop indefinitely\0"
- "unrecognized character after (?P\0"
- "syntax error in subpattern name (missing terminator)\0"
- "two named subpatterns have the same name\0"
- "invalid UTF-8 string\0"
- /* 45 */
- "support for \\P, \\p, and \\X has not been compiled\0"
- "malformed \\P or \\p sequence\0"
- "unknown property name after \\P or \\p\0"
- "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0"
- "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
- /* 50 */
- "repeated subpattern is too long\0" /** DEAD **/
- "octal value is greater than \\377 (not in UTF-8 mode)\0"
- "internal error: overran compiling workspace\0"
- "internal error: previously-checked referenced subpattern not found\0"
- "DEFINE group contains more than one branch\0"
- /* 55 */
- "repeating a DEFINE group is not allowed\0"
- "inconsistent NEWLINE options\0"
- "\\g is not followed by a braced name or an optionally braced non-zero number\0"
- "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number\0"
- "(*VERB) with an argument is not supported\0"
- /* 60 */
- "(*VERB) not recognized\0"
- "number is too big";
-
-
-/* Table to identify digits and hex digits. This is used when compiling
-patterns. Note that the tables in chartables are dependent on the locale, and
-may mark arbitrary characters as digits - but the PCRE compiling code expects
-to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have
-a private table here. It costs 256 bytes, but it is a lot faster than doing
-character value tests (at least in some simple cases I timed), and in some
-applications one wants PCRE to compile efficiently as well as match
-efficiently.
-
-For convenience, we use the same bit definitions as in chartables:
-
- 0x04 decimal digit
- 0x08 hexadecimal digit
-
-Then we can use ctype_digit and ctype_xdigit in the code. */
-
-#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */
-static const unsigned char digitab[] =
- {
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */
- 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */
- 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */
- 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */
- 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
-
-#else /* This is the "abnormal" case, for EBCDIC systems */
-static const unsigned char digitab[] =
- {
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */
- 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
- 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */
- 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */
- 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */
-
-static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */
- 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */
- 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */
- 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
- 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */
- 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */
- 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */
- 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */
- 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */
- 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */
- 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */
- 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */
- 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */
- 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */
- 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
- 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */
- 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */
- 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */
- 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */
- 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */
- 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */
-#endif
-
-
-/* Definition to allow mutual recursion */
-
-static BOOL
- compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int,
- int *, int *, branch_chain *, compile_data *, int *);
-
-
-
-/*************************************************
-* Find an error text *
-*************************************************/
-
-/* The error texts are now all in one long string, to save on relocations. As
-some of the text is of unknown length, we can't use a table of offsets.
-Instead, just count through the strings. This is not a performance issue
-because it happens only when there has been a compilation error.
-
-Argument: the error number
-Returns: pointer to the error string
-*/
-
-static const char *
-find_error_text(int n)
-{
-const char *s = error_texts;
-for (; n > 0; n--) while (*s++ != 0);
-return s;
-}
-
-
-/*************************************************
-* Handle escapes *
-*************************************************/
-
-/* This function is called when a \ has been encountered. It either returns a
-positive value for a simple escape such as \n, or a negative value which
-encodes one of the more complicated things such as \d. A backreference to group
-n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When
-UTF-8 is enabled, a positive value greater than 255 may be returned. On entry,
-ptr is pointing at the \. On exit, it is on the final character of the escape
-sequence.
-
-Arguments:
- ptrptr points to the pattern position pointer
- errorcodeptr points to the errorcode variable
- bracount number of previous extracting brackets
- options the options bits
- isclass TRUE if inside a character class
-
-Returns: zero or positive => a data character
- negative => a special escape sequence
- on error, errorcodeptr is set
-*/
-
-static int
-check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount,
- int options, BOOL isclass)
-{
-BOOL utf8 = (options & PCRE_UTF8) != 0;
-const uschar *ptr = *ptrptr + 1;
-int c, i;
-
-GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
-ptr--; /* Set pointer back to the last byte */
-
-/* If backslash is at the end of the pattern, it's an error. */
-
-if (c == 0) *errorcodeptr = ERR1;
-
-/* Non-alphamerics are literals. For digits or letters, do an initial lookup in
-a table. A non-zero result is something that can be returned immediately.
-Otherwise further processing may be required. */
-
-#ifndef EBCDIC /* ASCII coding */
-else if (c < '0' || c > 'z') {} /* Not alphameric */
-else if ((i = escapes[c - '0']) != 0) c = i;
-
-#else /* EBCDIC coding */
-else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */
-else if ((i = escapes[c - 0x48]) != 0) c = i;
-#endif
-
-/* Escapes that need further processing, or are illegal. */
-
-else
- {
- const uschar *oldptr;
- BOOL braced, negated;
-
- switch (c)
- {
- /* A number of Perl escapes are not handled by PCRE. We give an explicit
- error. */
-
- case 'l':
- case 'L':
- case 'N':
- case 'u':
- case 'U':
- *errorcodeptr = ERR37;
- break;
-
- /* \g must be followed by a number, either plain or braced. If positive, it
- is an absolute backreference. If negative, it is a relative backreference.
- This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a
- reference to a named group. This is part of Perl's movement towards a
- unified syntax for back references. As this is synonymous with \k{name}, we
- fudge it up by pretending it really was \k. */
-
- case 'g':
- if (ptr[1] == '{')
- {
- const uschar *p;
- for (p = ptr+2; *p != 0 && *p != '}'; p++)
- if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break;
- if (*p != 0 && *p != '}')
- {
- c = -ESC_k;
- break;
- }
- braced = TRUE;
- ptr++;
- }
- else braced = FALSE;
-
- if (ptr[1] == '-')
- {
- negated = TRUE;
- ptr++;
- }
- else negated = FALSE;
-
- c = 0;
- while ((digitab[ptr[1]] & ctype_digit) != 0)
- c = c * 10 + *(++ptr) - '0';
-
- if (c < 0)
- {
- *errorcodeptr = ERR61;
- break;
- }
-
- if (c == 0 || (braced && *(++ptr) != '}'))
- {
- *errorcodeptr = ERR57;
- break;
- }
-
- if (negated)
- {
- if (c > bracount)
- {
- *errorcodeptr = ERR15;
- break;
- }
- c = bracount - (c - 1);
- }
-
- c = -(ESC_REF + c);
- break;
-
- /* The handling of escape sequences consisting of a string of digits
- starting with one that is not zero is not straightforward. By experiment,
- the way Perl works seems to be as follows:
-
- Outside a character class, the digits are read as a decimal number. If the
- number is less than 10, or if there are that many previous extracting
- left brackets, then it is a back reference. Otherwise, up to three octal
- digits are read to form an escaped byte. Thus \123 is likely to be octal
- 123 (cf \0123, which is octal 012 followed by the literal 3). If the octal
- value is greater than 377, the least significant 8 bits are taken. Inside a
- character class, \ followed by a digit is always an octal number. */
-
- case '1': case '2': case '3': case '4': case '5':
- case '6': case '7': case '8': case '9':
-
- if (!isclass)
- {
- oldptr = ptr;
- c -= '0';
- while ((digitab[ptr[1]] & ctype_digit) != 0)
- c = c * 10 + *(++ptr) - '0';
- if (c < 0)
- {
- *errorcodeptr = ERR61;
- break;
- }
- if (c < 10 || c <= bracount)
- {
- c = -(ESC_REF + c);
- break;
- }
- ptr = oldptr; /* Put the pointer back and fall through */
- }
-
- /* Handle an octal number following \. If the first digit is 8 or 9, Perl
- generates a binary zero byte and treats the digit as a following literal.
- Thus we have to pull back the pointer by one. */
-
- if ((c = *ptr) >= '8')
- {
- ptr--;
- c = 0;
- break;
- }
-
- /* \0 always starts an octal number, but we may drop through to here with a
- larger first octal digit. The original code used just to take the least
- significant 8 bits of octal numbers (I think this is what early Perls used
- to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more
- than 3 octal digits. */
-
- case '0':
- c -= '0';
- while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7')
- c = c * 8 + *(++ptr) - '0';
- if (!utf8 && c > 255) *errorcodeptr = ERR51;
- break;
-
- /* \x is complicated. \x{ddd} is a character number which can be greater
- than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is
- treated as a data character. */
-
- case 'x':
- if (ptr[1] == '{')
- {
- const uschar *pt = ptr + 2;
- int count = 0;
-
- c = 0;
- while ((digitab[*pt] & ctype_xdigit) != 0)
- {
- register int cc = *pt++;
- if (c == 0 && cc == '0') continue; /* Leading zeroes */
- count++;
-
-#ifndef EBCDIC /* ASCII coding */
- if (cc >= 'a') cc -= 32; /* Convert to upper case */
- c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10));
-#else /* EBCDIC coding */
- if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */
- c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10));
-#endif
- }
-
- if (*pt == '}')
- {
- if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34;
- ptr = pt;
- break;
- }
-
- /* If the sequence of hex digits does not end with '}', then we don't
- recognize this construct; fall through to the normal \x handling. */
- }
-
- /* Read just a single-byte hex-defined char */
-
- c = 0;
- while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0)
- {
- int cc; /* Some compilers don't like ++ */
- cc = *(++ptr); /* in initializers */
-#ifndef EBCDIC /* ASCII coding */
- if (cc >= 'a') cc -= 32; /* Convert to upper case */
- c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10));
-#else /* EBCDIC coding */
- if (cc <= 'z') cc += 64; /* Convert to upper case */
- c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10));
-#endif
- }
- break;
-
- /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped.
- This coding is ASCII-specific, but then the whole concept of \cx is
- ASCII-specific. (However, an EBCDIC equivalent has now been added.) */
-
- case 'c':
- c = *(++ptr);
- if (c == 0)
- {
- *errorcodeptr = ERR2;
- break;
- }
-
-#ifndef EBCDIC /* ASCII coding */
- if (c >= 'a' && c <= 'z') c -= 32;
- c ^= 0x40;
-#else /* EBCDIC coding */
- if (c >= 'a' && c <= 'z') c += 64;
- c ^= 0xC0;
-#endif
- break;
-
- /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any
- other alphameric following \ is an error if PCRE_EXTRA was set; otherwise,
- for Perl compatibility, it is a literal. This code looks a bit odd, but
- there used to be some cases other than the default, and there may be again
- in future, so I haven't "optimized" it. */
-
- default:
- if ((options & PCRE_EXTRA) != 0) switch(c)
- {
- default:
- *errorcodeptr = ERR3;
- break;
- }
- break;
- }
- }
-
-*ptrptr = ptr;
-return c;
-}
-
-
-
-#ifdef SUPPORT_UCP
-/*************************************************
-* Handle \P and \p *
-*************************************************/
-
-/* This function is called after \P or \p has been encountered, provided that
-PCRE is compiled with support for Unicode properties. On entry, ptrptr is
-pointing at the P or p. On exit, it is pointing at the final character of the
-escape sequence.
-
-Argument:
- ptrptr points to the pattern position pointer
- negptr points to a boolean that is set TRUE for negation else FALSE
- dptr points to an int that is set to the detailed property value
- errorcodeptr points to the error code variable
-
-Returns: type value from ucp_type_table, or -1 for an invalid type
-*/
-
-static int
-get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr)
-{
-int c, i, bot, top;
-const uschar *ptr = *ptrptr;
-char name[32];
-
-c = *(++ptr);
-if (c == 0) goto ERROR_RETURN;
-
-*negptr = FALSE;
-
-/* \P or \p can be followed by a name in {}, optionally preceded by ^ for
-negation. */
-
-if (c == '{')
- {
- if (ptr[1] == '^')
- {
- *negptr = TRUE;
- ptr++;
- }
- for (i = 0; i < (int)sizeof(name) - 1; i++)
- {
- c = *(++ptr);
- if (c == 0) goto ERROR_RETURN;
- if (c == '}') break;
- name[i] = c;
- }
- if (c !='}') goto ERROR_RETURN;
- name[i] = 0;
- }
-
-/* Otherwise there is just one following character */
-
-else
- {
- name[0] = c;
- name[1] = 0;
- }
-
-*ptrptr = ptr;
-
-/* Search for a recognized property name using binary chop */
-
-bot = 0;
-top = _pcre_utt_size;
-
-while (bot < top)
- {
- i = (bot + top) >> 1;
- c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset);
- if (c == 0)
- {
- *dptr = _pcre_utt[i].value;
- return _pcre_utt[i].type;
- }
- if (c > 0) bot = i + 1; else top = i;
- }
-
-*errorcodeptr = ERR47;
-*ptrptr = ptr;
-return -1;
-
-ERROR_RETURN:
-*errorcodeptr = ERR46;
-*ptrptr = ptr;
-return -1;
-}
-#endif
-
-
-
-
-/*************************************************
-* Check for counted repeat *
-*************************************************/
-
-/* This function is called when a '{' is encountered in a place where it might
-start a quantifier. It looks ahead to see if it really is a quantifier or not.
-It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd}
-where the ddds are digits.
-
-Arguments:
- p pointer to the first char after '{'
-
-Returns: TRUE or FALSE
-*/
-
-static BOOL
-is_counted_repeat(const uschar *p)
-{
-if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
-while ((digitab[*p] & ctype_digit) != 0) p++;
-if (*p == '}') return TRUE;
-
-if (*p++ != ',') return FALSE;
-if (*p == '}') return TRUE;
-
-if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
-while ((digitab[*p] & ctype_digit) != 0) p++;
-
-return (*p == '}');
-}
-
-
-
-/*************************************************
-* Read repeat counts *
-*************************************************/
-
-/* Read an item of the form {n,m} and return the values. This is called only
-after is_counted_repeat() has confirmed that a repeat-count quantifier exists,
-so the syntax is guaranteed to be correct, but we need to check the values.
-
-Arguments:
- p pointer to first char after '{'
- minp pointer to int for min
- maxp pointer to int for max
- returned as -1 if no max
- errorcodeptr points to error code variable
-
-Returns: pointer to '}' on success;
- current ptr on error, with errorcodeptr set non-zero
-*/
-
-static const uschar *
-read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr)
-{
-int min = 0;
-int max = -1;
-
-/* Read the minimum value and do a paranoid check: a negative value indicates
-an integer overflow. */
-
-while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0';
-if (min < 0 || min > 65535)
- {
- *errorcodeptr = ERR5;
- return p;
- }
-
-/* Read the maximum value if there is one, and again do a paranoid on its size.
-Also, max must not be less than min. */
-
-if (*p == '}') max = min; else
- {
- if (*(++p) != '}')
- {
- max = 0;
- while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0';
- if (max < 0 || max > 65535)
- {
- *errorcodeptr = ERR5;
- return p;
- }
- if (max < min)
- {
- *errorcodeptr = ERR4;
- return p;
- }
- }
- }
-
-/* Fill in the required variables, and pass back the pointer to the terminating
-'}'. */
-
-*minp = min;
-*maxp = max;
-return p;
-}
-
-
-
-/*************************************************
-* Find forward referenced subpattern *
-*************************************************/
-
-/* This function scans along a pattern's text looking for capturing
-subpatterns, and counting them. If it finds a named pattern that matches the
-name it is given, it returns its number. Alternatively, if the name is NULL, it
-returns when it reaches a given numbered subpattern. This is used for forward
-references to subpatterns. We know that if (?P< is encountered, the name will
-be terminated by '>' because that is checked in the first pass.
-
-Arguments:
- ptr current position in the pattern
- count current count of capturing parens so far encountered
- name name to seek, or NULL if seeking a numbered subpattern
- lorn name length, or subpattern number if name is NULL
- xmode TRUE if we are in /x mode
-
-Returns: the number of the named subpattern, or -1 if not found
-*/
-
-static int
-find_parens(const uschar *ptr, int count, const uschar *name, int lorn,
- BOOL xmode)
-{
-const uschar *thisname;
-
-for (; *ptr != 0; ptr++)
- {
- int term;
-
- /* Skip over backslashed characters and also entire \Q...\E */
-
- if (*ptr == '\\')
- {
- if (*(++ptr) == 0) return -1;
- if (*ptr == 'Q') for (;;)
- {
- while (*(++ptr) != 0 && *ptr != '\\');
- if (*ptr == 0) return -1;
- if (*(++ptr) == 'E') break;
- }
- continue;
- }
-
- /* Skip over character classes */
-
- if (*ptr == '[')
- {
- while (*(++ptr) != ']')
- {
- if (*ptr == 0) return -1;
- if (*ptr == '\\')
- {
- if (*(++ptr) == 0) return -1;
- if (*ptr == 'Q') for (;;)
- {
- while (*(++ptr) != 0 && *ptr != '\\');
- if (*ptr == 0) return -1;
- if (*(++ptr) == 'E') break;
- }
- continue;
- }
- }
- continue;
- }
-
- /* Skip comments in /x mode */
-
- if (xmode && *ptr == '#')
- {
- while (*(++ptr) != 0 && *ptr != '\n');
- if (*ptr == 0) return -1;
- continue;
- }
-
- /* An opening parens must now be a real metacharacter */
-
- if (*ptr != '(') continue;
- if (ptr[1] != '?' && ptr[1] != '*')
- {
- count++;
- if (name == NULL && count == lorn) return count;
- continue;
- }
-
- ptr += 2;
- if (*ptr == 'P') ptr++; /* Allow optional P */
-
- /* We have to disambiguate (?<! and (?<= from (?<name> */
-
- if ((*ptr != '<' || ptr[1] == '!' || ptr[1] == '=') &&
- *ptr != '\'')
- continue;
-
- count++;
-
- if (name == NULL && count == lorn) return count;
- term = *ptr++;
- if (term == '<') term = '>';
- thisname = ptr;
- while (*ptr != term) ptr++;
- if (name != NULL && lorn == ptr - thisname &&
- strncmp((const char *)name, (const char *)thisname, lorn) == 0)
- return count;
- }
-
-return -1;
-}
-
-
-
-/*************************************************
-* Find first significant op code *
-*************************************************/
-
-/* This is called by several functions that scan a compiled expression looking
-for a fixed first character, or an anchoring op code etc. It skips over things
-that do not influence this. For some calls, a change of option is important.
-For some calls, it makes sense to skip negative forward and all backward
-assertions, and also the \b assertion; for others it does not.
-
-Arguments:
- code pointer to the start of the group
- options pointer to external options
- optbit the option bit whose changing is significant, or
- zero if none are
- skipassert TRUE if certain assertions are to be skipped
-
-Returns: pointer to the first significant opcode
-*/
-
-static const uschar*
-first_significant_code(const uschar *code, int *options, int optbit,
- BOOL skipassert)
-{
-for (;;)
- {
- switch ((int)*code)
- {
- case OP_OPT:
- if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit))
- *options = (int)code[1];
- code += 2;
- break;
-
- case OP_ASSERT_NOT:
- case OP_ASSERTBACK:
- case OP_ASSERTBACK_NOT:
- if (!skipassert) return code;
- do code += GET(code, 1); while (*code == OP_ALT);
- code += _pcre_OP_lengths[*code];
- break;
-
- case OP_WORD_BOUNDARY:
- case OP_NOT_WORD_BOUNDARY:
- if (!skipassert) return code;
- /* Fall through */
-
- case OP_CALLOUT:
- case OP_CREF:
- case OP_RREF:
- case OP_DEF:
- code += _pcre_OP_lengths[*code];
- break;
-
- default:
- return code;
- }
- }
-/* Control never reaches here */
-}
-
-
-
-
-/*************************************************
-* Find the fixed length of a pattern *
-*************************************************/
-
-/* Scan a pattern and compute the fixed length of subject that will match it,
-if the length is fixed. This is needed for dealing with backward assertions.
-In UTF8 mode, the result is in characters rather than bytes.
-
-Arguments:
- code points to the start of the pattern (the bracket)
- options the compiling options
-
-Returns: the fixed length, or -1 if there is no fixed length,
- or -2 if \C was encountered
-*/
-
-static int
-find_fixedlength(uschar *code, int options)
-{
-int length = -1;
-
-register int branchlength = 0;
-register uschar *cc = code + 1 + LINK_SIZE;
-
-/* Scan along the opcodes for this branch. If we get to the end of the
-branch, check the length against that of the other branches. */
-
-for (;;)
- {
- int d;
- register int op = *cc;
- switch (op)
- {
- case OP_CBRA:
- case OP_BRA:
- case OP_ONCE:
- case OP_COND:
- d = find_fixedlength(cc + ((op == OP_CBRA)? 2:0), options);
- if (d < 0) return d;
- branchlength += d;
- do cc += GET(cc, 1); while (*cc == OP_ALT);
- cc += 1 + LINK_SIZE;
- break;
-
- /* Reached end of a branch; if it's a ket it is the end of a nested
- call. If it's ALT it is an alternation in a nested call. If it is
- END it's the end of the outer call. All can be handled by the same code. */
-
- case OP_ALT:
- case OP_KET:
- case OP_KETRMAX:
- case OP_KETRMIN:
- case OP_END:
- if (length < 0) length = branchlength;
- else if (length != branchlength) return -1;
- if (*cc != OP_ALT) return length;
- cc += 1 + LINK_SIZE;
- branchlength = 0;
- break;
-
- /* Skip over assertive subpatterns */
-
- case OP_ASSERT:
- case OP_ASSERT_NOT:
- case OP_ASSERTBACK:
- case OP_ASSERTBACK_NOT:
- do cc += GET(cc, 1); while (*cc == OP_ALT);
- /* Fall through */
-
- /* Skip over things that don't match chars */
-
- case OP_REVERSE:
- case OP_CREF:
- case OP_RREF:
- case OP_DEF:
- case OP_OPT:
- case OP_CALLOUT:
- case OP_SOD:
- case OP_SOM:
- case OP_EOD:
- case OP_EODN:
- case OP_CIRC:
- case OP_DOLL:
- case OP_NOT_WORD_BOUNDARY:
- case OP_WORD_BOUNDARY:
- cc += _pcre_OP_lengths[*cc];
- break;
-
- /* Handle literal characters */
-
- case OP_CHAR:
- case OP_CHARNC:
- case OP_NOT:
- branchlength++;
- cc += 2;
-#ifdef SUPPORT_UTF8
- if ((options & PCRE_UTF8) != 0)
- {
- while ((*cc & 0xc0) == 0x80) cc++;
- }
-#endif
- break;
-
- /* Handle exact repetitions. The count is already in characters, but we
- need to skip over a multibyte character in UTF8 mode. */
-
- case OP_EXACT:
- branchlength += GET2(cc,1);
- cc += 4;
-#ifdef SUPPORT_UTF8
- if ((options & PCRE_UTF8) != 0)
- {
- while((*cc & 0x80) == 0x80) cc++;
- }
-#endif
- break;
-
- case OP_TYPEEXACT:
- branchlength += GET2(cc,1);
- if (cc[3] == OP_PROP || cc[3] == OP_NOTPROP) cc += 2;
- cc += 4;
- break;
-
- /* Handle single-char matchers */
-
- case OP_PROP:
- case OP_NOTPROP:
- cc += 2;
- /* Fall through */
-
- case OP_NOT_DIGIT:
- case OP_DIGIT:
- case OP_NOT_WHITESPACE:
- case OP_WHITESPACE:
- case OP_NOT_WORDCHAR:
- case OP_WORDCHAR:
- case OP_ANY:
- branchlength++;
- cc++;
- break;
-
- /* The single-byte matcher isn't allowed */
-
- case OP_ANYBYTE:
- return -2;
-
- /* Check a class for variable quantification */
-
-#ifdef SUPPORT_UTF8
- case OP_XCLASS:
- cc += GET(cc, 1) - 33;
- /* Fall through */
-#endif
-
- case OP_CLASS:
- case OP_NCLASS:
- cc += 33;
-
- switch (*cc)
- {
- case OP_CRSTAR:
- case OP_CRMINSTAR:
- case OP_CRQUERY:
- case OP_CRMINQUERY:
- return -1;
-
- case OP_CRRANGE:
- case OP_CRMINRANGE:
- if (GET2(cc,1) != GET2(cc,3)) return -1;
- branchlength += GET2(cc,1);
- cc += 5;
- break;
-
- default:
- branchlength++;
- }
- break;
-
- /* Anything else is variable length */
-
- default:
- return -1;
- }
- }
-/* Control never gets here */
-}
-
-
-
-
-/*************************************************
-* Scan compiled regex for numbered bracket *
-*************************************************/
-
-/* This little function scans through a compiled pattern until it finds a
-capturing bracket with the given number.
-
-Arguments:
- code points to start of expression
- utf8 TRUE in UTF-8 mode
- number the required bracket number
-
-Returns: pointer to the opcode for the bracket, or NULL if not found
-*/
-
-static const uschar *
-find_bracket(const uschar *code, BOOL utf8, int number)
-{
-for (;;)
- {
- register int c = *code;
- if (c == OP_END) return NULL;
-
- /* XCLASS is used for classes that cannot be represented just by a bit
- map. This includes negated single high-valued characters. The length in
- the table is zero; the actual length is stored in the compiled code. */
-
- if (c == OP_XCLASS) code += GET(code, 1);
-
- /* Handle capturing bracket */
-
- else if (c == OP_CBRA)
- {
- int n = GET2(code, 1+LINK_SIZE);
- if (n == number) return (uschar *)code;
- code += _pcre_OP_lengths[c];
- }
-
- /* Otherwise, we can get the item's length from the table, except that for
- repeated character types, we have to test for \p and \P, which have an extra
- two bytes of parameters. */
-
- else
- {
- switch(c)
- {
- case OP_TYPESTAR:
- case OP_TYPEMINSTAR:
- case OP_TYPEPLUS:
- case OP_TYPEMINPLUS:
- case OP_TYPEQUERY:
- case OP_TYPEMINQUERY:
- case OP_TYPEPOSSTAR:
- case OP_TYPEPOSPLUS:
- case OP_TYPEPOSQUERY:
- if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
- break;
-
- case OP_TYPEUPTO:
- case OP_TYPEMINUPTO:
- case OP_TYPEEXACT:
- case OP_TYPEPOSUPTO:
- if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2;
- break;
- }
-
- /* Add in the fixed length from the table */
-
- code += _pcre_OP_lengths[c];
-
- /* In UTF-8 mode, opcodes that are followed by a character may be followed by
- a multi-byte character. The length in the table is a minimum, so we have to
- arrange to skip the extra bytes. */
-
-#ifdef SUPPORT_UTF8
- if (utf8) switch(c)
- {
- case OP_CHAR:
- case OP_CHARNC:
- case OP_EXACT:
- case OP_UPTO:
- case OP_MINUPTO:
- case OP_POSUPTO:
- case OP_STAR:
- case OP_MINSTAR:
- case OP_POSSTAR:
- case OP_PLUS:
- case OP_MINPLUS:
- case OP_POSPLUS:
- case OP_QUERY:
- case OP_MINQUERY:
- case OP_POSQUERY:
- if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f];
- break;
- }
-#endif
- }
- }
-}
-
-
-
-/*************************************************
-* Scan compiled regex for recursion reference *
-*************************************************/
-
-/* This little function scans through a compiled pattern until it finds an
-instance of OP_RECURSE.
-
-Arguments:
- code points to start of expression
- utf8 TRUE in UTF-8 mode
-
-Returns: pointer to the opcode for OP_RECURSE, or NULL if not found
-*/
-
-static const uschar *
-find_recurse(const uschar *code, BOOL utf8)
-{
-for (;;)
- {
- register int c = *code;
- if (c == OP_END) return NULL;
- if (c == OP_RECURSE) return code;
-
- /* XCLASS is used for classes that cannot be represented just by a bit
- map. This includes negated single high-valued characters. The length in
- the table is zero; the actual length is stored in the compiled code. */
-
- if (c == OP_XCLASS) code += GET(code, 1);
-
- /* Otherwise, we can get the item's length from the table, except that for
- repeated character types, we have to test for \p and \P, which have an extra
- two bytes of parameters. */
-
- else
- {
- switch(c)
- {
- case OP_TYPESTAR:
- case OP_TYPEMINSTAR:
- case OP_TYPEPLUS:
- case OP_TYPEMINPLUS:
- case OP_TYPEQUERY:
- case OP_TYPEMINQUERY:
- case OP_TYPEPOSSTAR:
- case OP_TYPEPOSPLUS:
- case OP_TYPEPOSQUERY:
- if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
- break;
-
- case OP_TYPEPOSUPTO:
- case OP_TYPEUPTO:
- case OP_TYPEMINUPTO:
- case OP_TYPEEXACT:
- if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2;
- break;
- }
-
- /* Add in the fixed length from the table */
-
- code += _pcre_OP_lengths[c];
-
- /* In UTF-8 mode, opcodes that are followed by a character may be followed
- by a multi-byte character. The length in the table is a minimum, so we have
- to arrange to skip the extra bytes. */
-
-#ifdef SUPPORT_UTF8
- if (utf8) switch(c)
- {
- case OP_CHAR:
- case OP_CHARNC:
- case OP_EXACT:
- case OP_UPTO:
- case OP_MINUPTO:
- case OP_POSUPTO:
- case OP_STAR:
- case OP_MINSTAR:
- case OP_POSSTAR:
- case OP_PLUS:
- case OP_MINPLUS:
- case OP_POSPLUS:
- case OP_QUERY:
- case OP_MINQUERY:
- case OP_POSQUERY:
- if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f];
- break;
- }
-#endif
- }
- }
-}
-
-
-
-/*************************************************
-* Scan compiled branch for non-emptiness *
-*************************************************/
-
-/* This function scans through a branch of a compiled pattern to see whether it
-can match the empty string or not. It is called from could_be_empty()
-below and from compile_branch() when checking for an unlimited repeat of a
-group that can match nothing. Note that first_significant_code() skips over
-assertions. If we hit an unclosed bracket, we return "empty" - this means we've
-struck an inner bracket whose current branch will already have been scanned.
-
-Arguments:
- code points to start of search
- endcode points to where to stop
- utf8 TRUE if in UTF8 mode
-
-Returns: TRUE if what is matched could be empty
-*/
-
-static BOOL
-could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8)
-{
-register int c;
-for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE);
- code < endcode;
- code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE))
- {
- const uschar *ccode;
-
- c = *code;
-
- /* Groups with zero repeats can of course be empty; skip them. */
-
- if (c == OP_BRAZERO || c == OP_BRAMINZERO)
- {
- code += _pcre_OP_lengths[c];
- do code += GET(code, 1); while (*code == OP_ALT);
- c = *code;
- continue;
- }
-
- /* For other groups, scan the branches. */
-
- if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE || c == OP_COND)
- {
- BOOL empty_branch;
- if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */
-
- /* Scan a closed bracket */
-
- empty_branch = FALSE;
- do
- {
- if (!empty_branch && could_be_empty_branch(code, endcode, utf8))
- empty_branch = TRUE;
- code += GET(code, 1);
- }
- while (*code == OP_ALT);
- if (!empty_branch) return FALSE; /* All branches are non-empty */
- c = *code;
- continue;
- }
-
- /* Handle the other opcodes */
-
- switch (c)
- {
- /* Check for quantifiers after a class. XCLASS is used for classes that
- cannot be represented just by a bit map. This includes negated single
- high-valued characters. The length in _pcre_OP_lengths[] is zero; the
- actual length is stored in the compiled code, so we must update "code"
- here. */
-
-#ifdef SUPPORT_UTF8
- case OP_XCLASS:
- ccode = code += GET(code, 1);
- goto CHECK_CLASS_REPEAT;
-#endif
-
- case OP_CLASS:
- case OP_NCLASS:
- ccode = code + 33;
-
-#ifdef SUPPORT_UTF8
- CHECK_CLASS_REPEAT:
-#endif
-
- switch (*ccode)
- {
- case OP_CRSTAR: /* These could be empty; continue */
- case OP_CRMINSTAR:
- case OP_CRQUERY:
- case OP_CRMINQUERY:
- break;
-
- default: /* Non-repeat => class must match */
- case OP_CRPLUS: /* These repeats aren't empty */
- case OP_CRMINPLUS:
- return FALSE;
-
- case OP_CRRANGE:
- case OP_CRMINRANGE:
- if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */
- break;
- }
- break;
-
- /* Opcodes that must match a character */
-
- case OP_PROP:
- case OP_NOTPROP:
- case OP_EXTUNI:
- case OP_NOT_DIGIT:
- case OP_DIGIT:
- case OP_NOT_WHITESPACE:
- case OP_WHITESPACE:
- case OP_NOT_WORDCHAR:
- case OP_WORDCHAR:
- case OP_ANY:
- case OP_ANYBYTE:
- case OP_CHAR:
- case OP_CHARNC:
- case OP_NOT:
- case OP_PLUS:
- case OP_MINPLUS:
- case OP_POSPLUS:
- case OP_EXACT:
- case OP_NOTPLUS:
- case OP_NOTMINPLUS:
- case OP_NOTPOSPLUS:
- case OP_NOTEXACT:
- case OP_TYPEPLUS:
- case OP_TYPEMINPLUS:
- case OP_TYPEPOSPLUS:
- case OP_TYPEEXACT:
- return FALSE;
-
- /* These are going to continue, as they may be empty, but we have to
- fudge the length for the \p and \P cases. */
-
- case OP_TYPESTAR:
- case OP_TYPEMINSTAR:
- case OP_TYPEPOSSTAR:
- case OP_TYPEQUERY:
- case OP_TYPEMINQUERY:
- case OP_TYPEPOSQUERY:
- if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
- break;
-
- /* Same for these */
-
- case OP_TYPEUPTO:
- case OP_TYPEMINUPTO:
- case OP_TYPEPOSUPTO:
- if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2;
- break;
-
- /* End of branch */
-
- case OP_KET:
- case OP_KETRMAX:
- case OP_KETRMIN:
- case OP_ALT:
- return TRUE;
-
- /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO,
- MINUPTO, and POSUPTO may be followed by a multibyte character */
-
-#ifdef SUPPORT_UTF8
- case OP_STAR:
- case OP_MINSTAR:
- case OP_POSSTAR:
- case OP_QUERY:
- case OP_MINQUERY:
- case OP_POSQUERY:
- case OP_UPTO:
- case OP_MINUPTO:
- case OP_POSUPTO:
- if (utf8) while ((code[2] & 0xc0) == 0x80) code++;
- break;
-#endif
- }
- }
-
-return TRUE;
-}
-
-
-
-/*************************************************
-* Scan compiled regex for non-emptiness *
-*************************************************/
-
-/* This function is called to check for left recursive calls. We want to check
-the current branch of the current pattern to see if it could match the empty
-string. If it could, we must look outwards for branches at other levels,
-stopping when we pass beyond the bracket which is the subject of the recursion.
-
-Arguments:
- code points to start of the recursion
- endcode points to where to stop (current RECURSE item)
- bcptr points to the chain of current (unclosed) branch starts
- utf8 TRUE if in UTF-8 mode
-
-Returns: TRUE if what is matched could be empty
-*/
-
-static BOOL
-could_be_empty(const uschar *code, const uschar *endcode, branch_chain *bcptr,
- BOOL utf8)
-{
-while (bcptr != NULL && bcptr->current >= code)
- {
- if (!could_be_empty_branch(bcptr->current, endcode, utf8)) return FALSE;
- bcptr = bcptr->outer;
- }
-return TRUE;
-}
-
-
-
-/*************************************************
-* Check for POSIX class syntax *
-*************************************************/
-
-/* This function is called when the sequence "[:" or "[." or "[=" is
-encountered in a character class. It checks whether this is followed by an
-optional ^ and then a sequence of letters, terminated by a matching ":]" or
-".]" or "=]".
-
-Argument:
- ptr pointer to the initial [
- endptr where to return the end pointer
- cd pointer to compile data
-
-Returns: TRUE or FALSE
-*/
-
-static BOOL
-check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd)
-{
-int terminator; /* Don't combine these lines; the Solaris cc */
-terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */
-if (*(++ptr) == '^') ptr++;
-while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++;
-if (*ptr == terminator && ptr[1] == ']')
- {
- *endptr = ptr;
- return TRUE;
- }
-return FALSE;
-}
-
-
-
-
-/*************************************************
-* Check POSIX class name *
-*************************************************/
-
-/* This function is called to check the name given in a POSIX-style class entry
-such as [:alnum:].
-
-Arguments:
- ptr points to the first letter
- len the length of the name
-
-Returns: a value representing the name, or -1 if unknown
-*/
-
-static int
-check_posix_name(const uschar *ptr, int len)
-{
-const char *pn = posix_names;
-register int yield = 0;
-while (posix_name_lengths[yield] != 0)
- {
- if (len == posix_name_lengths[yield] &&
- strncmp((const char *)ptr, pn, len) == 0) return yield;
- pn += posix_name_lengths[yield] + 1;
- yield++;
- }
-return -1;
-}
-
-
-/*************************************************
-* Adjust OP_RECURSE items in repeated group *
-*************************************************/
-
-/* OP_RECURSE items contain an offset from the start of the regex to the group
-that is referenced. This means that groups can be replicated for fixed
-repetition simply by copying (because the recursion is allowed to refer to
-earlier groups that are outside the current group). However, when a group is
-optional (i.e. the minimum quantifier is zero), OP_BRAZERO is inserted before
-it, after it has been compiled. This means that any OP_RECURSE items within it
-that refer to the group itself or any contained groups have to have their
-offsets adjusted. That one of the jobs of this function. Before it is called,
-the partially compiled regex must be temporarily terminated with OP_END.
-
-This function has been extended with the possibility of forward references for
-recursions and subroutine calls. It must also check the list of such references
-for the group we are dealing with. If it finds that one of the recursions in
-the current group is on this list, it adjusts the offset in the list, not the
-value in the reference (which is a group number).
-
-Arguments:
- group points to the start of the group
- adjust the amount by which the group is to be moved
- utf8 TRUE in UTF-8 mode
- cd contains pointers to tables etc.
- save_hwm the hwm forward reference pointer at the start of the group
-
-Returns: nothing
-*/
-
-static void
-adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd,
- uschar *save_hwm)
-{
-uschar *ptr = group;
-
-while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL)
- {
- int offset;
- uschar *hc;
-
- /* See if this recursion is on the forward reference list. If so, adjust the
- reference. */
-
- for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE)
- {
- offset = GET(hc, 0);
- if (cd->start_code + offset == ptr + 1)
- {
- PUT(hc, 0, offset + adjust);
- break;
- }
- }
-
- /* Otherwise, adjust the recursion offset if it's after the start of this
- group. */
-
- if (hc >= cd->hwm)
- {
- offset = GET(ptr, 1);
- if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust);
- }
-
- ptr += 1 + LINK_SIZE;
- }
-}
-
-
-
-/*************************************************
-* Insert an automatic callout point *
-*************************************************/
-
-/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert
-callout points before each pattern item.
-
-Arguments:
- code current code pointer
- ptr current pattern pointer
- cd pointers to tables etc
-
-Returns: new code pointer
-*/
-
-static uschar *
-auto_callout(uschar *code, const uschar *ptr, compile_data *cd)
-{
-*code++ = OP_CALLOUT;
-*code++ = 255;
-PUT(code, 0, ptr - cd->start_pattern); /* Pattern offset */
-PUT(code, LINK_SIZE, 0); /* Default length */
-return code + 2*LINK_SIZE;
-}
-
-
-
-/*************************************************
-* Complete a callout item *
-*************************************************/
-
-/* A callout item contains the length of the next item in the pattern, which
-we can't fill in till after we have reached the relevant point. This is used
-for both automatic and manual callouts.
-
-Arguments:
- previous_callout points to previous callout item
- ptr current pattern pointer
- cd pointers to tables etc
-
-Returns: nothing
-*/
-
-static void
-complete_callout(uschar *previous_callout, const uschar *ptr, compile_data *cd)
-{
-int length = ptr - cd->start_pattern - GET(previous_callout, 2);
-PUT(previous_callout, 2 + LINK_SIZE, length);
-}
-
-
-
-#ifdef SUPPORT_UCP
-/*************************************************
-* Get othercase range *
-*************************************************/
-
-/* This function is passed the start and end of a class range, in UTF-8 mode
-with UCP support. It searches up the characters, looking for internal ranges of
-characters in the "other" case. Each call returns the next one, updating the
-start address.
-
-Arguments:
- cptr points to starting character value; updated
- d end value
- ocptr where to put start of othercase range
- odptr where to put end of othercase range
-
-Yield: TRUE when range returned; FALSE when no more
-*/
-
-static BOOL
-get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr,
- unsigned int *odptr)
-{
-unsigned int c, othercase, next;
-
-for (c = *cptr; c <= d; c++)
- { if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR) break; }
-
-if (c > d) return FALSE;
-
-*ocptr = othercase;
-next = othercase + 1;
-
-for (++c; c <= d; c++)
- {
- if (_pcre_ucp_othercase(c) != next) break;
- next++;
- }
-
-*odptr = next - 1;
-*cptr = c;
-
-return TRUE;
-}
-#endif /* SUPPORT_UCP */
-
-
-
-/*************************************************
-* Check if auto-possessifying is possible *
-*************************************************/
-
-/* This function is called for unlimited repeats of certain items, to see
-whether the next thing could possibly match the repeated item. If not, it makes
-sense to automatically possessify the repeated item.
-
-Arguments:
- op_code the repeated op code
- this data for this item, depends on the opcode
- utf8 TRUE in UTF-8 mode
- utf8_char used for utf8 character bytes, NULL if not relevant
- ptr next character in pattern
- options options bits
- cd contains pointers to tables etc.
-
-Returns: TRUE if possessifying is wanted
-*/
-
-static BOOL
-check_auto_possessive(int op_code, int item, BOOL utf8, uschar *utf8_char,
- const uschar *ptr, int options, compile_data *cd)
-{
-int next;
-
-/* Skip whitespace and comments in extended mode */
-
-if ((options & PCRE_EXTENDED) != 0)
- {
- for (;;)
- {
- while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++;
- if (*ptr == '#')
- {
- while (*(++ptr) != 0)
- if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; }
- }
- else break;
- }
- }
-
-/* If the next item is one that we can handle, get its value. A non-negative
-value is a character, a negative value is an escape value. */
-
-if (*ptr == '\\')
- {
- int temperrorcode = 0;
- next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE);
- if (temperrorcode != 0) return FALSE;
- ptr++; /* Point after the escape sequence */
- }
-
-else if ((cd->ctypes[*ptr] & ctype_meta) == 0)
- {
-#ifdef SUPPORT_UTF8
- if (utf8) { GETCHARINC(next, ptr); } else
-#endif
- next = *ptr++;
- }
-
-else return FALSE;
-
-/* Skip whitespace and comments in extended mode */
-
-if ((options & PCRE_EXTENDED) != 0)
- {
- for (;;)
- {
- while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++;
- if (*ptr == '#')
- {
- while (*(++ptr) != 0)
- if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; }
- }
- else break;
- }
- }
-
-/* If the next thing is itself optional, we have to give up. */
-
-if (*ptr == '*' || *ptr == '?' || strncmp((char *)ptr, "{0,", 3) == 0)
- return FALSE;
-
-/* Now compare the next item with the previous opcode. If the previous is a
-positive single character match, "item" either contains the character or, if
-"item" is greater than 127 in utf8 mode, the character's bytes are in
-utf8_char. */
-
-
-/* Handle cases when the next item is a character. */
-
-if (next >= 0) switch(op_code)
- {
- case OP_CHAR:
-#ifdef SUPPORT_UTF8
- if (utf8 && item > 127) { GETCHAR(item, utf8_char); }
-#endif
- return item != next;
-
- /* For CHARNC (caseless character) we must check the other case. If we have
- Unicode property support, we can use it to test the other case of
- high-valued characters. */
-
- case OP_CHARNC:
-#ifdef SUPPORT_UTF8
- if (utf8 && item > 127) { GETCHAR(item, utf8_char); }
-#endif
- if (item == next) return FALSE;
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- unsigned int othercase;
- if (next < 128) othercase = cd->fcc[next]; else
-#ifdef SUPPORT_UCP
- othercase = _pcre_ucp_othercase((unsigned int)next);
-#else
- othercase = NOTACHAR;
-#endif
- return (unsigned int)item != othercase;
- }
- else
-#endif /* SUPPORT_UTF8 */
- return (item != cd->fcc[next]); /* Non-UTF-8 mode */
-
- /* For OP_NOT, "item" must be a single-byte character. */
-
- case OP_NOT:
- if (next < 0) return FALSE; /* Not a character */
- if (item == next) return TRUE;
- if ((options & PCRE_CASELESS) == 0) return FALSE;
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- unsigned int othercase;
- if (next < 128) othercase = cd->fcc[next]; else
-#ifdef SUPPORT_UCP
- othercase = _pcre_ucp_othercase(next);
-#else
- othercase = NOTACHAR;
-#endif
- return (unsigned int)item == othercase;
- }
- else
-#endif /* SUPPORT_UTF8 */
- return (item == cd->fcc[next]); /* Non-UTF-8 mode */
-
- case OP_DIGIT:
- return next > 127 || (cd->ctypes[next] & ctype_digit) == 0;
-
- case OP_NOT_DIGIT:
- return next <= 127 && (cd->ctypes[next] & ctype_digit) != 0;
-
- case OP_WHITESPACE:
- return next > 127 || (cd->ctypes[next] & ctype_space) == 0;
-
- case OP_NOT_WHITESPACE:
- return next <= 127 && (cd->ctypes[next] & ctype_space) != 0;
-
- case OP_WORDCHAR:
- return next > 127 || (cd->ctypes[next] & ctype_word) == 0;
-
- case OP_NOT_WORDCHAR:
- return next <= 127 && (cd->ctypes[next] & ctype_word) != 0;
-
- case OP_HSPACE:
- case OP_NOT_HSPACE:
- switch(next)
- {
- case 0x09:
- case 0x20:
- case 0xa0:
- case 0x1680:
- case 0x180e:
- case 0x2000:
- case 0x2001:
- case 0x2002:
- case 0x2003:
- case 0x2004:
- case 0x2005:
- case 0x2006:
- case 0x2007:
- case 0x2008:
- case 0x2009:
- case 0x200A:
- case 0x202f:
- case 0x205f:
- case 0x3000:
- return op_code != OP_HSPACE;
- default:
- return op_code == OP_HSPACE;
- }
-
- case OP_VSPACE:
- case OP_NOT_VSPACE:
- switch(next)
- {
- case 0x0a:
- case 0x0b:
- case 0x0c:
- case 0x0d:
- case 0x85:
- case 0x2028:
- case 0x2029:
- return op_code != OP_VSPACE;
- default:
- return op_code == OP_VSPACE;
- }
-
- default:
- return FALSE;
- }
-
-
-/* Handle the case when the next item is \d, \s, etc. */
-
-switch(op_code)
- {
- case OP_CHAR:
- case OP_CHARNC:
-#ifdef SUPPORT_UTF8
- if (utf8 && item > 127) { GETCHAR(item, utf8_char); }
-#endif
- switch(-next)
- {
- case ESC_d:
- return item > 127 || (cd->ctypes[item] & ctype_digit) == 0;
-
- case ESC_D:
- return item <= 127 && (cd->ctypes[item] & ctype_digit) != 0;
-
- case ESC_s:
- return item > 127 || (cd->ctypes[item] & ctype_space) == 0;
-
- case ESC_S:
- return item <= 127 && (cd->ctypes[item] & ctype_space) != 0;
-
- case ESC_w:
- return item > 127 || (cd->ctypes[item] & ctype_word) == 0;
-
- case ESC_W:
- return item <= 127 && (cd->ctypes[item] & ctype_word) != 0;
-
- case ESC_h:
- case ESC_H:
- switch(item)
- {
- case 0x09:
- case 0x20:
- case 0xa0:
- case 0x1680:
- case 0x180e:
- case 0x2000:
- case 0x2001:
- case 0x2002:
- case 0x2003:
- case 0x2004:
- case 0x2005:
- case 0x2006:
- case 0x2007:
- case 0x2008:
- case 0x2009:
- case 0x200A:
- case 0x202f:
- case 0x205f:
- case 0x3000:
- return -next != ESC_h;
- default:
- return -next == ESC_h;
- }
-
- case ESC_v:
- case ESC_V:
- switch(item)
- {
- case 0x0a:
- case 0x0b:
- case 0x0c:
- case 0x0d:
- case 0x85:
- case 0x2028:
- case 0x2029:
- return -next != ESC_v;
- default:
- return -next == ESC_v;
- }
-
- default:
- return FALSE;
- }
-
- case OP_DIGIT:
- return next == -ESC_D || next == -ESC_s || next == -ESC_W ||
- next == -ESC_h || next == -ESC_v;
-
- case OP_NOT_DIGIT:
- return next == -ESC_d;
-
- case OP_WHITESPACE:
- return next == -ESC_S || next == -ESC_d || next == -ESC_w;
-
- case OP_NOT_WHITESPACE:
- return next == -ESC_s || next == -ESC_h || next == -ESC_v;
-
- case OP_HSPACE:
- return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w;
-
- case OP_NOT_HSPACE:
- return next == -ESC_h;
-
- /* Can't have \S in here because VT matches \S (Perl anomaly) */
- case OP_VSPACE:
- return next == -ESC_V || next == -ESC_d || next == -ESC_w;
-
- case OP_NOT_VSPACE:
- return next == -ESC_v;
-
- case OP_WORDCHAR:
- return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v;
-
- case OP_NOT_WORDCHAR:
- return next == -ESC_w || next == -ESC_d;
-
- default:
- return FALSE;
- }
-
-/* Control does not reach here */
-}
-
-
-
-/*************************************************
-* Compile one branch *
-*************************************************/
-
-/* Scan the pattern, compiling it into the a vector. If the options are
-changed during the branch, the pointer is used to change the external options
-bits. This function is used during the pre-compile phase when we are trying
-to find out the amount of memory needed, as well as during the real compile
-phase. The value of lengthptr distinguishes the two phases.
-
-Arguments:
- optionsptr pointer to the option bits
- codeptr points to the pointer to the current code point
- ptrptr points to the current pattern pointer
- errorcodeptr points to error code variable
- firstbyteptr set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE)
- reqbyteptr set to the last literal character required, else < 0
- bcptr points to current branch chain
- cd contains pointers to tables etc.
- lengthptr NULL during the real compile phase
- points to length accumulator during pre-compile phase
-
-Returns: TRUE on success
- FALSE, with *errorcodeptr set non-zero on error
-*/
-
-static BOOL
-compile_branch(int *optionsptr, uschar **codeptr, const uschar **ptrptr,
- int *errorcodeptr, int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr,
- compile_data *cd, int *lengthptr)
-{
-int repeat_type, op_type;
-int repeat_min = 0, repeat_max = 0; /* To please picky compilers */
-int bravalue = 0;
-int greedy_default, greedy_non_default;
-int firstbyte, reqbyte;
-int zeroreqbyte, zerofirstbyte;
-int req_caseopt, reqvary, tempreqvary;
-int options = *optionsptr;
-int after_manual_callout = 0;
-int length_prevgroup = 0;
-register int c;
-register uschar *code = *codeptr;
-uschar *last_code = code;
-uschar *orig_code = code;
-uschar *tempcode;
-BOOL inescq = FALSE;
-BOOL groupsetfirstbyte = FALSE;
-const uschar *ptr = *ptrptr;
-const uschar *tempptr;
-uschar *previous = NULL;
-uschar *previous_callout = NULL;
-uschar *save_hwm = NULL;
-uschar classbits[32];
-
-#ifdef SUPPORT_UTF8
-BOOL class_utf8;
-BOOL utf8 = (options & PCRE_UTF8) != 0;
-uschar *class_utf8data;
-uschar utf8_char[6];
-#else
-BOOL utf8 = FALSE;
-uschar *utf8_char = NULL;
-#endif
-
-#ifdef DEBUG
-if (lengthptr != NULL) DPRINTF((">> start branch\n"));
-#endif
-
-/* Set up the default and non-default settings for greediness */
-
-greedy_default = ((options & PCRE_UNGREEDY) != 0);
-greedy_non_default = greedy_default ^ 1;
-
-/* Initialize no first byte, no required byte. REQ_UNSET means "no char
-matching encountered yet". It gets changed to REQ_NONE if we hit something that
-matches a non-fixed char first char; reqbyte just remains unset if we never
-find one.
-
-When we hit a repeat whose minimum is zero, we may have to adjust these values
-to take the zero repeat into account. This is implemented by setting them to
-zerofirstbyte and zeroreqbyte when such a repeat is encountered. The individual
-item types that can be repeated set these backoff variables appropriately. */
-
-firstbyte = reqbyte = zerofirstbyte = zeroreqbyte = REQ_UNSET;
-
-/* The variable req_caseopt contains either the REQ_CASELESS value or zero,
-according to the current setting of the caseless flag. REQ_CASELESS is a bit
-value > 255. It is added into the firstbyte or reqbyte variables to record the
-case status of the value. This is used only for ASCII characters. */
-
-req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0;
-
-/* Switch on next character until the end of the branch */
-
-for (;; ptr++)
- {
- BOOL negate_class;
- BOOL possessive_quantifier;
- BOOL is_quantifier;
- BOOL is_recurse;
- BOOL reset_bracount;
- int class_charcount;
- int class_lastchar;
- int newoptions;
- int recno;
- int refsign;
- int skipbytes;
- int subreqbyte;
- int subfirstbyte;
- int terminator;
- int mclength;
- uschar mcbuffer[8];
-
- /* Get next byte in the pattern */
-
- c = *ptr;
-
- /* If we are in the pre-compile phase, accumulate the length used for the
- previous cycle of this loop. */
-
- if (lengthptr != NULL)
- {
-#ifdef DEBUG
- if (code > cd->hwm) cd->hwm = code; /* High water info */
-#endif
- if (code > cd->start_workspace + COMPILE_WORK_SIZE) /* Check for overrun */
- {
- *errorcodeptr = ERR52;
- goto FAILED;
- }
-
- /* There is at least one situation where code goes backwards: this is the
- case of a zero quantifier after a class (e.g. [ab]{0}). At compile time,
- the class is simply eliminated. However, it is created first, so we have to
- allow memory for it. Therefore, don't ever reduce the length at this point.
- */
-
- if (code < last_code) code = last_code;
-
- /* Paranoid check for integer overflow */
-
- if (OFLOW_MAX - *lengthptr < code - last_code)
- {
- *errorcodeptr = ERR20;
- goto FAILED;
- }
-
- *lengthptr += code - last_code;
- DPRINTF(("length=%d added %d c=%c\n", *lengthptr, code - last_code, c));
-
- /* If "previous" is set and it is not at the start of the work space, move
- it back to there, in order to avoid filling up the work space. Otherwise,
- if "previous" is NULL, reset the current code pointer to the start. */
-
- if (previous != NULL)
- {
- if (previous > orig_code)
- {
- memmove(orig_code, previous, code - previous);
- code -= previous - orig_code;
- previous = orig_code;
- }
- }
- else code = orig_code;
-
- /* Remember where this code item starts so we can pick up the length
- next time round. */
-
- last_code = code;
- }
-
- /* In the real compile phase, just check the workspace used by the forward
- reference list. */
-
- else if (cd->hwm > cd->start_workspace + COMPILE_WORK_SIZE)
- {
- *errorcodeptr = ERR52;
- goto FAILED;
- }
-
- /* If in \Q...\E, check for the end; if not, we have a literal */
-
- if (inescq && c != 0)
- {
- if (c == '\\' && ptr[1] == 'E')
- {
- inescq = FALSE;
- ptr++;
- continue;
- }
- else
- {
- if (previous_callout != NULL)
- {
- if (lengthptr == NULL) /* Don't attempt in pre-compile phase */
- complete_callout(previous_callout, ptr, cd);
- previous_callout = NULL;
- }
- if ((options & PCRE_AUTO_CALLOUT) != 0)
- {
- previous_callout = code;
- code = auto_callout(code, ptr, cd);
- }
- goto NORMAL_CHAR;
- }
- }
-
- /* Fill in length of a previous callout, except when the next thing is
- a quantifier. */
-
- is_quantifier = c == '*' || c == '+' || c == '?' ||
- (c == '{' && is_counted_repeat(ptr+1));
-
- if (!is_quantifier && previous_callout != NULL &&
- after_manual_callout-- <= 0)
- {
- if (lengthptr == NULL) /* Don't attempt in pre-compile phase */
- complete_callout(previous_callout, ptr, cd);
- previous_callout = NULL;
- }
-
- /* In extended mode, skip white space and comments */
-
- if ((options & PCRE_EXTENDED) != 0)
- {
- if ((cd->ctypes[c] & ctype_space) != 0) continue;
- if (c == '#')
- {
- while (*(++ptr) != 0)
- {
- if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; }
- }
- if (*ptr != 0) continue;
-
- /* Else fall through to handle end of string */
- c = 0;
- }
- }
-
- /* No auto callout for quantifiers. */
-
- if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier)
- {
- previous_callout = code;
- code = auto_callout(code, ptr, cd);
- }
-
- switch(c)
- {
- /* ===================================================================*/
- case 0: /* The branch terminates at string end */
- case '|': /* or | or ) */
- case ')':
- *firstbyteptr = firstbyte;
- *reqbyteptr = reqbyte;
- *codeptr = code;
- *ptrptr = ptr;
- if (lengthptr != NULL)
- {
- if (OFLOW_MAX - *lengthptr < code - last_code)
- {
- *errorcodeptr = ERR20;
- goto FAILED;
- }
- *lengthptr += code - last_code; /* To include callout length */
- DPRINTF((">> end branch\n"));
- }
- return TRUE;
-
-
- /* ===================================================================*/
- /* Handle single-character metacharacters. In multiline mode, ^ disables
- the setting of any following char as a first character. */
-
- case '^':
- if ((options & PCRE_MULTILINE) != 0)
- {
- if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE;
- }
- previous = NULL;
- *code++ = OP_CIRC;
- break;
-
- case '$':
- previous = NULL;
- *code++ = OP_DOLL;
- break;
-
- /* There can never be a first char if '.' is first, whatever happens about
- repeats. The value of reqbyte doesn't change either. */
-
- case '.':
- if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE;
- zerofirstbyte = firstbyte;
- zeroreqbyte = reqbyte;
- previous = code;
- *code++ = OP_ANY;
- break;
-
-
- /* ===================================================================*/
- /* Character classes. If the included characters are all < 256, we build a
- 32-byte bitmap of the permitted characters, except in the special case
- where there is only one such character. For negated classes, we build the
- map as usual, then invert it at the end. However, we use a different opcode
- so that data characters > 255 can be handled correctly.
-
- If the class contains characters outside the 0-255 range, a different
- opcode is compiled. It may optionally have a bit map for characters < 256,
- but those above are are explicitly listed afterwards. A flag byte tells
- whether the bitmap is present, and whether this is a negated class or not.
- */
-
- case '[':
- previous = code;
-
- /* PCRE supports POSIX class stuff inside a class. Perl gives an error if
- they are encountered at the top level, so we'll do that too. */
-
- if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') &&
- check_posix_syntax(ptr, &tempptr, cd))
- {
- *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31;
- goto FAILED;
- }
-
- /* If the first character is '^', set the negation flag and skip it. Also,
- if the first few characters (either before or after ^) are \Q\E or \E we
- skip them too. This makes for compatibility with Perl. */
-
- negate_class = FALSE;
- for (;;)
- {
- c = *(++ptr);
- if (c == '\\')
- {
- if (ptr[1] == 'E') ptr++;
- else if (strncmp((const char *)ptr+1, "Q\\E", 3) == 0) ptr += 3;
- else break;
- }
- else if (!negate_class && c == '^')
- negate_class = TRUE;
- else break;
- }
-
- /* Keep a count of chars with values < 256 so that we can optimize the case
- of just a single character (as long as it's < 256). However, For higher
- valued UTF-8 characters, we don't yet do any optimization. */
-
- class_charcount = 0;
- class_lastchar = -1;
-
- /* Initialize the 32-char bit map to all zeros. We build the map in a
- temporary bit of memory, in case the class contains only 1 character (less
- than 256), because in that case the compiled code doesn't use the bit map.
- */
-
- memset(classbits, 0, 32 * sizeof(uschar));
-
-#ifdef SUPPORT_UTF8
- class_utf8 = FALSE; /* No chars >= 256 */
- class_utf8data = code + LINK_SIZE + 2; /* For UTF-8 items */
-#endif
-
- /* Process characters until ] is reached. By writing this as a "do" it
- means that an initial ] is taken as a data character. At the start of the
- loop, c contains the first byte of the character. */
-
- if (c != 0) do
- {
- const uschar *oldptr;
-
-#ifdef SUPPORT_UTF8
- if (utf8 && c > 127)
- { /* Braces are required because the */
- GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */
- }
-#endif
-
- /* Inside \Q...\E everything is literal except \E */
-
- if (inescq)
- {
- if (c == '\\' && ptr[1] == 'E') /* If we are at \E */
- {
- inescq = FALSE; /* Reset literal state */
- ptr++; /* Skip the 'E' */
- continue; /* Carry on with next */
- }
- goto CHECK_RANGE; /* Could be range if \E follows */
- }
-
- /* Handle POSIX class names. Perl allows a negation extension of the
- form [:^name:]. A square bracket that doesn't match the syntax is
- treated as a literal. We also recognize the POSIX constructions
- [.ch.] and [=ch=] ("collating elements") and fault them, as Perl
- 5.6 and 5.8 do. */
-
- if (c == '[' &&
- (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') &&
- check_posix_syntax(ptr, &tempptr, cd))
- {
- BOOL local_negate = FALSE;
- int posix_class, taboffset, tabopt;
- register const uschar *cbits = cd->cbits;
- uschar pbits[32];
-
- if (ptr[1] != ':')
- {
- *errorcodeptr = ERR31;
- goto FAILED;
- }
-
- ptr += 2;
- if (*ptr == '^')
- {
- local_negate = TRUE;
- ptr++;
- }
-
- posix_class = check_posix_name(ptr, tempptr - ptr);
- if (posix_class < 0)
- {
- *errorcodeptr = ERR30;
- goto FAILED;
- }
-
- /* If matching is caseless, upper and lower are converted to
- alpha. This relies on the fact that the class table starts with
- alpha, lower, upper as the first 3 entries. */
-
- if ((options & PCRE_CASELESS) != 0 && posix_class <= 2)
- posix_class = 0;
-
- /* We build the bit map for the POSIX class in a chunk of local store
- because we may be adding and subtracting from it, and we don't want to
- subtract bits that may be in the main map already. At the end we or the
- result into the bit map that is being built. */
-
- posix_class *= 3;
-
- /* Copy in the first table (always present) */
-
- memcpy(pbits, cbits + posix_class_maps[posix_class],
- 32 * sizeof(uschar));
-
- /* If there is a second table, add or remove it as required. */
-
- taboffset = posix_class_maps[posix_class + 1];
- tabopt = posix_class_maps[posix_class + 2];
-
- if (taboffset >= 0)
- {
- if (tabopt >= 0)
- for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset];
- else
- for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset];
- }
-
- /* Not see if we need to remove any special characters. An option
- value of 1 removes vertical space and 2 removes underscore. */
-
- if (tabopt < 0) tabopt = -tabopt;
- if (tabopt == 1) pbits[1] &= ~0x3c;
- else if (tabopt == 2) pbits[11] &= 0x7f;
-
- /* Add the POSIX table or its complement into the main table that is
- being built and we are done. */
-
- if (local_negate)
- for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c];
- else
- for (c = 0; c < 32; c++) classbits[c] |= pbits[c];
-
- ptr = tempptr + 1;
- class_charcount = 10; /* Set > 1; assumes more than 1 per class */
- continue; /* End of POSIX syntax handling */
- }
-
- /* Backslash may introduce a single character, or it may introduce one
- of the specials, which just set a flag. The sequence \b is a special
- case. Inside a class (and only there) it is treated as backspace.
- Elsewhere it marks a word boundary. Other escapes have preset maps ready
- to 'or' into the one we are building. We assume they have more than one
- character in them, so set class_charcount bigger than one. */
-
- if (c == '\\')
- {
- c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
- if (*errorcodeptr != 0) goto FAILED;
-
- if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */
- else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */
- else if (-c == ESC_R) c = 'R'; /* \R is literal R in a class */
- else if (-c == ESC_Q) /* Handle start of quoted string */
- {
- if (ptr[1] == '\\' && ptr[2] == 'E')
- {
- ptr += 2; /* avoid empty string */
- }
- else inescq = TRUE;
- continue;
- }
- else if (-c == ESC_E) continue; /* Ignore orphan \E */
-
- if (c < 0)
- {
- register const uschar *cbits = cd->cbits;
- class_charcount += 2; /* Greater than 1 is what matters */
-
- /* Save time by not doing this in the pre-compile phase. */
-
- if (lengthptr == NULL) switch (-c)
- {
- case ESC_d:
- for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit];
- continue;
-
- case ESC_D:
- for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit];
- continue;
-
- case ESC_w:
- for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word];
- continue;
-
- case ESC_W:
- for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word];
- continue;
-
- case ESC_s:
- for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space];
- classbits[1] &= ~0x08; /* Perl 5.004 onwards omits VT from \s */
- continue;
-
- case ESC_S:
- for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space];
- classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */
- continue;
-
- case ESC_E: /* Perl ignores an orphan \E */
- continue;
-
- default: /* Not recognized; fall through */
- break; /* Need "default" setting to stop compiler warning. */
- }
-
- /* In the pre-compile phase, just do the recognition. */
-
- else if (c == -ESC_d || c == -ESC_D || c == -ESC_w ||
- c == -ESC_W || c == -ESC_s || c == -ESC_S) continue;
-
- /* We need to deal with \H, \h, \V, and \v in both phases because
- they use extra memory. */
-
- if (-c == ESC_h)
- {
- SETBIT(classbits, 0x09); /* VT */
- SETBIT(classbits, 0x20); /* SPACE */
- SETBIT(classbits, 0xa0); /* NSBP */
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- class_utf8 = TRUE;
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data);
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data);
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data);
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data);
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data);
- }
-#endif
- continue;
- }
-
- if (-c == ESC_H)
- {
- for (c = 0; c < 32; c++)
- {
- int x = 0xff;
- switch (c)
- {
- case 0x09/8: x ^= 1 << (0x09%8); break;
- case 0x20/8: x ^= 1 << (0x20%8); break;
- case 0xa0/8: x ^= 1 << (0xa0%8); break;
- default: break;
- }
- classbits[c] |= x;
- }
-
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- class_utf8 = TRUE;
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data);
- }
-#endif
- continue;
- }
-
- if (-c == ESC_v)
- {
- SETBIT(classbits, 0x0a); /* LF */
- SETBIT(classbits, 0x0b); /* VT */
- SETBIT(classbits, 0x0c); /* FF */
- SETBIT(classbits, 0x0d); /* CR */
- SETBIT(classbits, 0x85); /* NEL */
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- class_utf8 = TRUE;
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data);
- }
-#endif
- continue;
- }
-
- if (-c == ESC_V)
- {
- for (c = 0; c < 32; c++)
- {
- int x = 0xff;
- switch (c)
- {
- case 0x0a/8: x ^= 1 << (0x0a%8);
- x ^= 1 << (0x0b%8);
- x ^= 1 << (0x0c%8);
- x ^= 1 << (0x0d%8);
- break;
- case 0x85/8: x ^= 1 << (0x85%8); break;
- default: break;
- }
- classbits[c] |= x;
- }
-
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- class_utf8 = TRUE;
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data);
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data);
- class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data);
- }
-#endif
- continue;
- }
-
- /* We need to deal with \P and \p in both phases. */
-
-#ifdef SUPPORT_UCP
- if (-c == ESC_p || -c == ESC_P)
- {
- BOOL negated;
- int pdata;
- int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr);
- if (ptype < 0) goto FAILED;
- class_utf8 = TRUE;
- *class_utf8data++ = ((-c == ESC_p) != negated)?
- XCL_PROP : XCL_NOTPROP;
- *class_utf8data++ = ptype;
- *class_utf8data++ = pdata;
- class_charcount -= 2; /* Not a < 256 character */
- continue;
- }
-#endif
- /* Unrecognized escapes are faulted if PCRE is running in its
- strict mode. By default, for compatibility with Perl, they are
- treated as literals. */
-
- if ((options & PCRE_EXTRA) != 0)
- {
- *errorcodeptr = ERR7;
- goto FAILED;
- }
-
- class_charcount -= 2; /* Undo the default count from above */
- c = *ptr; /* Get the final character and fall through */
- }
-
- /* Fall through if we have a single character (c >= 0). This may be
- greater than 256 in UTF-8 mode. */
-
- } /* End of backslash handling */
-
- /* A single character may be followed by '-' to form a range. However,
- Perl does not permit ']' to be the end of the range. A '-' character
- at the end is treated as a literal. Perl ignores orphaned \E sequences
- entirely. The code for handling \Q and \E is messy. */
-
- CHECK_RANGE:
- while (ptr[1] == '\\' && ptr[2] == 'E')
- {
- inescq = FALSE;
- ptr += 2;
- }
-
- oldptr = ptr;
-
- /* Remember \r or \n */
-
- if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF;
-
- /* Check for range */
-
- if (!inescq && ptr[1] == '-')
- {
- int d;
- ptr += 2;
- while (*ptr == '\\' && ptr[1] == 'E') ptr += 2;
-
- /* If we hit \Q (not followed by \E) at this point, go into escaped
- mode. */
-
- while (*ptr == '\\' && ptr[1] == 'Q')
- {
- ptr += 2;
- if (*ptr == '\\' && ptr[1] == 'E') { ptr += 2; continue; }
- inescq = TRUE;
- break;
- }
-
- if (*ptr == 0 || (!inescq && *ptr == ']'))
- {
- ptr = oldptr;
- goto LONE_SINGLE_CHARACTER;
- }
-
-#ifdef SUPPORT_UTF8
- if (utf8)
- { /* Braces are required because the */
- GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */
- }
- else
-#endif
- d = *ptr; /* Not UTF-8 mode */
-
- /* The second part of a range can be a single-character escape, but
- not any of the other escapes. Perl 5.6 treats a hyphen as a literal
- in such circumstances. */
-
- if (!inescq && d == '\\')
- {
- d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
- if (*errorcodeptr != 0) goto FAILED;
-
- /* \b is backslash; \X is literal X; \R is literal R; any other
- special means the '-' was literal */
-
- if (d < 0)
- {
- if (d == -ESC_b) d = '\b';
- else if (d == -ESC_X) d = 'X';
- else if (d == -ESC_R) d = 'R'; else
- {
- ptr = oldptr;
- goto LONE_SINGLE_CHARACTER; /* A few lines below */
- }
- }
- }
-
- /* Check that the two values are in the correct order. Optimize
- one-character ranges */
-
- if (d < c)
- {
- *errorcodeptr = ERR8;
- goto FAILED;
- }
-
- if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */
-
- /* Remember \r or \n */
-
- if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF;
-
- /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless
- matching, we have to use an XCLASS with extra data items. Caseless
- matching for characters > 127 is available only if UCP support is
- available. */
-
-#ifdef SUPPORT_UTF8
- if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127)))
- {
- class_utf8 = TRUE;
-
- /* With UCP support, we can find the other case equivalents of
- the relevant characters. There may be several ranges. Optimize how
- they fit with the basic range. */
-
-#ifdef SUPPORT_UCP
- if ((options & PCRE_CASELESS) != 0)
- {
- unsigned int occ, ocd;
- unsigned int cc = c;
- unsigned int origd = d;
- while (get_othercase_range(&cc, origd, &occ, &ocd))
- {
- if (occ >= (unsigned int)c &&
- ocd <= (unsigned int)d)
- continue; /* Skip embedded ranges */
-
- if (occ < (unsigned int)c &&
- ocd >= (unsigned int)c - 1) /* Extend the basic range */
- { /* if there is overlap, */
- c = occ; /* noting that if occ < c */
- continue; /* we can't have ocd > d */
- } /* because a subrange is */
- if (ocd > (unsigned int)d &&
- occ <= (unsigned int)d + 1) /* always shorter than */
- { /* the basic range. */
- d = ocd;
- continue;
- }
-
- if (occ == ocd)
- {
- *class_utf8data++ = XCL_SINGLE;
- }
- else
- {
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(occ, class_utf8data);
- }
- class_utf8data += _pcre_ord2utf8(ocd, class_utf8data);
- }
- }
-#endif /* SUPPORT_UCP */
-
- /* Now record the original range, possibly modified for UCP caseless
- overlapping ranges. */
-
- *class_utf8data++ = XCL_RANGE;
- class_utf8data += _pcre_ord2utf8(c, class_utf8data);
- class_utf8data += _pcre_ord2utf8(d, class_utf8data);
-
- /* With UCP support, we are done. Without UCP support, there is no
- caseless matching for UTF-8 characters > 127; we can use the bit map
- for the smaller ones. */
-
-#ifdef SUPPORT_UCP
- continue; /* With next character in the class */
-#else
- if ((options & PCRE_CASELESS) == 0 || c > 127) continue;
-
- /* Adjust upper limit and fall through to set up the map */
-
- d = 127;
-
-#endif /* SUPPORT_UCP */
- }
-#endif /* SUPPORT_UTF8 */
-
- /* We use the bit map for all cases when not in UTF-8 mode; else
- ranges that lie entirely within 0-127 when there is UCP support; else
- for partial ranges without UCP support. */
-
- class_charcount += d - c + 1;
- class_lastchar = d;
-
- /* We can save a bit of time by skipping this in the pre-compile. */
-
- if (lengthptr == NULL) for (; c <= d; c++)
- {
- classbits[c/8] |= (1 << (c&7));
- if ((options & PCRE_CASELESS) != 0)
- {
- int uc = cd->fcc[c]; /* flip case */
- classbits[uc/8] |= (1 << (uc&7));
- }
- }
-
- continue; /* Go get the next char in the class */
- }
-
- /* Handle a lone single character - we can get here for a normal
- non-escape char, or after \ that introduces a single character or for an
- apparent range that isn't. */
-
- LONE_SINGLE_CHARACTER:
-
- /* Handle a character that cannot go in the bit map */
-
-#ifdef SUPPORT_UTF8
- if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127)))
- {
- class_utf8 = TRUE;
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(c, class_utf8data);
-
-#ifdef SUPPORT_UCP
- if ((options & PCRE_CASELESS) != 0)
- {
- unsigned int othercase;
- if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR)
- {
- *class_utf8data++ = XCL_SINGLE;
- class_utf8data += _pcre_ord2utf8(othercase, class_utf8data);
- }
- }
-#endif /* SUPPORT_UCP */
-
- }
- else
-#endif /* SUPPORT_UTF8 */
-
- /* Handle a single-byte character */
- {
- classbits[c/8] |= (1 << (c&7));
- if ((options & PCRE_CASELESS) != 0)
- {
- c = cd->fcc[c]; /* flip case */
- classbits[c/8] |= (1 << (c&7));
- }
- class_charcount++;
- class_lastchar = c;
- }
- }
-
- /* Loop until ']' reached. This "while" is the end of the "do" above. */
-
- while ((c = *(++ptr)) != 0 && (c != ']' || inescq));
-
- if (c == 0) /* Missing terminating ']' */
- {
- *errorcodeptr = ERR6;
- goto FAILED;
- }
-
-
-/* This code has been disabled because it would mean that \s counts as
-an explicit \r or \n reference, and that's not really what is wanted. Now
-we set the flag only if there is a literal "\r" or "\n" in the class. */
-
-#if 0
- /* Remember whether \r or \n are in this class */
-
- if (negate_class)
- {
- if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF;
- }
- else
- {
- if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF;
- }
-#endif
-
-
- /* If class_charcount is 1, we saw precisely one character whose value is
- less than 256. As long as there were no characters >= 128 and there was no
- use of \p or \P, in other words, no use of any XCLASS features, we can
- optimize.
-
- In UTF-8 mode, we can optimize the negative case only if there were no
- characters >= 128 because OP_NOT and the related opcodes like OP_NOTSTAR
- operate on single-bytes only. This is an historical hangover. Maybe one day
- we can tidy these opcodes to handle multi-byte characters.
-
- The optimization throws away the bit map. We turn the item into a
- 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note
- that OP_NOT does not support multibyte characters. In the positive case, it
- can cause firstbyte to be set. Otherwise, there can be no first char if
- this item is first, whatever repeat count may follow. In the case of
- reqbyte, save the previous value for reinstating. */
-
-#ifdef SUPPORT_UTF8
- if (class_charcount == 1 && !class_utf8 &&
- (!utf8 || !negate_class || class_lastchar < 128))
-#else
- if (class_charcount == 1)
-#endif
- {
- zeroreqbyte = reqbyte;
-
- /* The OP_NOT opcode works on one-byte characters only. */
-
- if (negate_class)
- {
- if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE;
- zerofirstbyte = firstbyte;
- *code++ = OP_NOT;
- *code++ = class_lastchar;
- break;
- }
-
- /* For a single, positive character, get the value into mcbuffer, and
- then we can handle this with the normal one-character code. */
-
-#ifdef SUPPORT_UTF8
- if (utf8 && class_lastchar > 127)
- mclength = _pcre_ord2utf8(class_lastchar, mcbuffer);
- else
-#endif
- {
- mcbuffer[0] = class_lastchar;
- mclength = 1;
- }
- goto ONE_CHAR;
- } /* End of 1-char optimization */
-
- /* The general case - not the one-char optimization. If this is the first
- thing in the branch, there can be no first char setting, whatever the
- repeat count. Any reqbyte setting must remain unchanged after any kind of
- repeat. */
-
- if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE;
- zerofirstbyte = firstbyte;
- zeroreqbyte = reqbyte;
-
- /* If there are characters with values > 255, we have to compile an
- extended class, with its own opcode. If there are no characters < 256,
- we can omit the bitmap in the actual compiled code. */
-
-#ifdef SUPPORT_UTF8
- if (class_utf8)
- {
- *class_utf8data++ = XCL_END; /* Marks the end of extra data */
- *code++ = OP_XCLASS;
- code += LINK_SIZE;
- *code = negate_class? XCL_NOT : 0;
-
- /* If the map is required, move up the extra data to make room for it;
- otherwise just move the code pointer to the end of the extra data. */
-
- if (class_charcount > 0)
- {
- *code++ |= XCL_MAP;
- memmove(code + 32, code, class_utf8data - code);
- memcpy(code, classbits, 32);
- code = class_utf8data + 32;
- }
- else code = class_utf8data;
-
- /* Now fill in the complete length of the item */
-
- PUT(previous, 1, code - previous);
- break; /* End of class handling */
- }
-#endif
-
- /* If there are no characters > 255, negate the 32-byte map if necessary,
- and copy it into the code vector. If this is the first thing in the branch,
- there can be no first char setting, whatever the repeat count. Any reqbyte
- setting must remain unchanged after any kind of repeat. */
-
- if (negate_class)
- {
- *code++ = OP_NCLASS;
- if (lengthptr == NULL) /* Save time in the pre-compile phase */
- for (c = 0; c < 32; c++) code[c] = ~classbits[c];
- }
- else
- {
- *code++ = OP_CLASS;
- memcpy(code, classbits, 32);
- }
- code += 32;
- break;
-
-
- /* ===================================================================*/
- /* Various kinds of repeat; '{' is not necessarily a quantifier, but this
- has been tested above. */
-
- case '{':
- if (!is_quantifier) goto NORMAL_CHAR;
- ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr);
- if (*errorcodeptr != 0) goto FAILED;
- goto REPEAT;
-
- case '*':
- repeat_min = 0;
- repeat_max = -1;
- goto REPEAT;
-
- case '+':
- repeat_min = 1;
- repeat_max = -1;
- goto REPEAT;
-
- case '?':
- repeat_min = 0;
- repeat_max = 1;
-
- REPEAT:
- if (previous == NULL)
- {
- *errorcodeptr = ERR9;
- goto FAILED;
- }
-
- if (repeat_min == 0)
- {
- firstbyte = zerofirstbyte; /* Adjust for zero repeat */
- reqbyte = zeroreqbyte; /* Ditto */
- }
-
- /* Remember whether this is a variable length repeat */
-
- reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY;
-
- op_type = 0; /* Default single-char op codes */
- possessive_quantifier = FALSE; /* Default not possessive quantifier */
-
- /* Save start of previous item, in case we have to move it up to make space
- for an inserted OP_ONCE for the additional '+' extension. */
-
- tempcode = previous;
-
- /* If the next character is '+', we have a possessive quantifier. This
- implies greediness, whatever the setting of the PCRE_UNGREEDY option.
- If the next character is '?' this is a minimizing repeat, by default,
- but if PCRE_UNGREEDY is set, it works the other way round. We change the
- repeat type to the non-default. */
-
- if (ptr[1] == '+')
- {
- repeat_type = 0; /* Force greedy */
- possessive_quantifier = TRUE;
- ptr++;
- }
- else if (ptr[1] == '?')
- {
- repeat_type = greedy_non_default;
- ptr++;
- }
- else repeat_type = greedy_default;
-
- /* If previous was a character match, abolish the item and generate a
- repeat item instead. If a char item has a minumum of more than one, ensure
- that it is set in reqbyte - it might not be if a sequence such as x{3} is
- the first thing in a branch because the x will have gone into firstbyte
- instead. */
-
- if (*previous == OP_CHAR || *previous == OP_CHARNC)
- {
- /* Deal with UTF-8 characters that take up more than one byte. It's
- easier to write this out separately than try to macrify it. Use c to
- hold the length of the character in bytes, plus 0x80 to flag that it's a
- length rather than a small character. */
-
-#ifdef SUPPORT_UTF8
- if (utf8 && (code[-1] & 0x80) != 0)
- {
- uschar *lastchar = code - 1;
- while((*lastchar & 0xc0) == 0x80) lastchar--;
- c = code - lastchar; /* Length of UTF-8 character */
- memcpy(utf8_char, lastchar, c); /* Save the char */
- c |= 0x80; /* Flag c as a length */
- }
- else
-#endif
-
- /* Handle the case of a single byte - either with no UTF8 support, or
- with UTF-8 disabled, or for a UTF-8 character < 128. */
-
- {
- c = code[-1];
- if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt;
- }
-
- /* If the repetition is unlimited, it pays to see if the next thing on
- the line is something that cannot possibly match this character. If so,
- automatically possessifying this item gains some performance in the case
- where the match fails. */
-
- if (!possessive_quantifier &&
- repeat_max < 0 &&
- check_auto_possessive(*previous, c, utf8, utf8_char, ptr + 1,
- options, cd))
- {
- repeat_type = 0; /* Force greedy */
- possessive_quantifier = TRUE;
- }
-
- goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */
- }
-
- /* If previous was a single negated character ([^a] or similar), we use
- one of the special opcodes, replacing it. The code is shared with single-
- character repeats by setting opt_type to add a suitable offset into
- repeat_type. We can also test for auto-possessification. OP_NOT is
- currently used only for single-byte chars. */
-
- else if (*previous == OP_NOT)
- {
- op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */
- c = previous[1];
- if (!possessive_quantifier &&
- repeat_max < 0 &&
- check_auto_possessive(OP_NOT, c, utf8, NULL, ptr + 1, options, cd))
- {
- repeat_type = 0; /* Force greedy */
- possessive_quantifier = TRUE;
- }
- goto OUTPUT_SINGLE_REPEAT;
- }
-
- /* If previous was a character type match (\d or similar), abolish it and
- create a suitable repeat item. The code is shared with single-character
- repeats by setting op_type to add a suitable offset into repeat_type. Note
- the the Unicode property types will be present only when SUPPORT_UCP is
- defined, but we don't wrap the little bits of code here because it just
- makes it horribly messy. */
-
- else if (*previous < OP_EODN)
- {
- uschar *oldcode;
- int prop_type, prop_value;
- op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */
- c = *previous;
-
- if (!possessive_quantifier &&
- repeat_max < 0 &&
- check_auto_possessive(c, 0, utf8, NULL, ptr + 1, options, cd))
- {
- repeat_type = 0; /* Force greedy */
- possessive_quantifier = TRUE;
- }
-
- OUTPUT_SINGLE_REPEAT:
- if (*previous == OP_PROP || *previous == OP_NOTPROP)
- {
- prop_type = previous[1];
- prop_value = previous[2];
- }
- else prop_type = prop_value = -1;
-
- oldcode = code;
- code = previous; /* Usually overwrite previous item */
-
- /* If the maximum is zero then the minimum must also be zero; Perl allows
- this case, so we do too - by simply omitting the item altogether. */
-
- if (repeat_max == 0) goto END_REPEAT;
-
- /* All real repeats make it impossible to handle partial matching (maybe
- one day we will be able to remove this restriction). */
-
- if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL;
-
- /* Combine the op_type with the repeat_type */
-
- repeat_type += op_type;
-
- /* A minimum of zero is handled either as the special case * or ?, or as
- an UPTO, with the maximum given. */
-
- if (repeat_min == 0)
- {
- if (repeat_max == -1) *code++ = OP_STAR + repeat_type;
- else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type;
- else
- {
- *code++ = OP_UPTO + repeat_type;
- PUT2INC(code, 0, repeat_max);
- }
- }
-
- /* A repeat minimum of 1 is optimized into some special cases. If the
- maximum is unlimited, we use OP_PLUS. Otherwise, the original item is
- left in place and, if the maximum is greater than 1, we use OP_UPTO with
- one less than the maximum. */
-
- else if (repeat_min == 1)
- {
- if (repeat_max == -1)
- *code++ = OP_PLUS + repeat_type;
- else
- {
- code = oldcode; /* leave previous item in place */
- if (repeat_max == 1) goto END_REPEAT;
- *code++ = OP_UPTO + repeat_type;
- PUT2INC(code, 0, repeat_max - 1);
- }
- }
-
- /* The case {n,n} is just an EXACT, while the general case {n,m} is
- handled as an EXACT followed by an UPTO. */
-
- else
- {
- *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */
- PUT2INC(code, 0, repeat_min);
-
- /* If the maximum is unlimited, insert an OP_STAR. Before doing so,
- we have to insert the character for the previous code. For a repeated
- Unicode property match, there are two extra bytes that define the
- required property. In UTF-8 mode, long characters have their length in
- c, with the 0x80 bit as a flag. */
-
- if (repeat_max < 0)
- {
-#ifdef SUPPORT_UTF8
- if (utf8 && c >= 128)
- {
- memcpy(code, utf8_char, c & 7);
- code += c & 7;
- }
- else
-#endif
- {
- *code++ = c;
- if (prop_type >= 0)
- {
- *code++ = prop_type;
- *code++ = prop_value;
- }
- }
- *code++ = OP_STAR + repeat_type;
- }
-
- /* Else insert an UPTO if the max is greater than the min, again
- preceded by the character, for the previously inserted code. If the
- UPTO is just for 1 instance, we can use QUERY instead. */
-
- else if (repeat_max != repeat_min)
- {
-#ifdef SUPPORT_UTF8
- if (utf8 && c >= 128)
- {
- memcpy(code, utf8_char, c & 7);
- code += c & 7;
- }
- else
-#endif
- *code++ = c;
- if (prop_type >= 0)
- {
- *code++ = prop_type;
- *code++ = prop_value;
- }
- repeat_max -= repeat_min;
-
- if (repeat_max == 1)
- {
- *code++ = OP_QUERY + repeat_type;
- }
- else
- {
- *code++ = OP_UPTO + repeat_type;
- PUT2INC(code, 0, repeat_max);
- }
- }
- }
-
- /* The character or character type itself comes last in all cases. */
-
-#ifdef SUPPORT_UTF8
- if (utf8 && c >= 128)
- {
- memcpy(code, utf8_char, c & 7);
- code += c & 7;
- }
- else
-#endif
- *code++ = c;
-
- /* For a repeated Unicode property match, there are two extra bytes that
- define the required property. */
-
-#ifdef SUPPORT_UCP
- if (prop_type >= 0)
- {
- *code++ = prop_type;
- *code++ = prop_value;
- }
-#endif
- }
-
- /* If previous was a character class or a back reference, we put the repeat
- stuff after it, but just skip the item if the repeat was {0,0}. */
-
- else if (*previous == OP_CLASS ||
- *previous == OP_NCLASS ||
-#ifdef SUPPORT_UTF8
- *previous == OP_XCLASS ||
-#endif
- *previous == OP_REF)
- {
- if (repeat_max == 0)
- {
- code = previous;
- goto END_REPEAT;
- }
-
- /* All real repeats make it impossible to handle partial matching (maybe
- one day we will be able to remove this restriction). */
-
- if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL;
-
- if (repeat_min == 0 && repeat_max == -1)
- *code++ = OP_CRSTAR + repeat_type;
- else if (repeat_min == 1 && repeat_max == -1)
- *code++ = OP_CRPLUS + repeat_type;
- else if (repeat_min == 0 && repeat_max == 1)
- *code++ = OP_CRQUERY + repeat_type;
- else
- {
- *code++ = OP_CRRANGE + repeat_type;
- PUT2INC(code, 0, repeat_min);
- if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */
- PUT2INC(code, 0, repeat_max);
- }
- }
-
- /* If previous was a bracket group, we may have to replicate it in certain
- cases. */
-
- else if (*previous == OP_BRA || *previous == OP_CBRA ||
- *previous == OP_ONCE || *previous == OP_COND)
- {
- register int i;
- int ketoffset = 0;
- int len = code - previous;
- uschar *bralink = NULL;
-
- /* Repeating a DEFINE group is pointless */
-
- if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF)
- {
- *errorcodeptr = ERR55;
- goto FAILED;
- }
-
- /* If the maximum repeat count is unlimited, find the end of the bracket
- by scanning through from the start, and compute the offset back to it
- from the current code pointer. There may be an OP_OPT setting following
- the final KET, so we can't find the end just by going back from the code
- pointer. */
-
- if (repeat_max == -1)
- {
- register uschar *ket = previous;
- do ket += GET(ket, 1); while (*ket != OP_KET);
- ketoffset = code - ket;
- }
-
- /* The case of a zero minimum is special because of the need to stick
- OP_BRAZERO in front of it, and because the group appears once in the
- data, whereas in other cases it appears the minimum number of times. For
- this reason, it is simplest to treat this case separately, as otherwise
- the code gets far too messy. There are several special subcases when the
- minimum is zero. */
-
- if (repeat_min == 0)
- {
- /* If the maximum is also zero, we just omit the group from the output
- altogether. */
-
- if (repeat_max == 0)
- {
- code = previous;
- goto END_REPEAT;
- }
-
- /* If the maximum is 1 or unlimited, we just have to stick in the
- BRAZERO and do no more at this point. However, we do need to adjust
- any OP_RECURSE calls inside the group that refer to the group itself or
- any internal or forward referenced group, because the offset is from
- the start of the whole regex. Temporarily terminate the pattern while
- doing this. */
-
- if (repeat_max <= 1)
- {
- *code = OP_END;
- adjust_recurse(previous, 1, utf8, cd, save_hwm);
- memmove(previous+1, previous, len);
- code++;
- *previous++ = OP_BRAZERO + repeat_type;
- }
-
- /* If the maximum is greater than 1 and limited, we have to replicate
- in a nested fashion, sticking OP_BRAZERO before each set of brackets.
- The first one has to be handled carefully because it's the original
- copy, which has to be moved up. The remainder can be handled by code
- that is common with the non-zero minimum case below. We have to
- adjust the value or repeat_max, since one less copy is required. Once
- again, we may have to adjust any OP_RECURSE calls inside the group. */
-
- else
- {
- int offset;
- *code = OP_END;
- adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd, save_hwm);
- memmove(previous + 2 + LINK_SIZE, previous, len);
- code += 2 + LINK_SIZE;
- *previous++ = OP_BRAZERO + repeat_type;
- *previous++ = OP_BRA;
-
- /* We chain together the bracket offset fields that have to be
- filled in later when the ends of the brackets are reached. */
-
- offset = (bralink == NULL)? 0 : previous - bralink;
- bralink = previous;
- PUTINC(previous, 0, offset);
- }
-
- repeat_max--;
- }
-
- /* If the minimum is greater than zero, replicate the group as many
- times as necessary, and adjust the maximum to the number of subsequent
- copies that we need. If we set a first char from the group, and didn't
- set a required char, copy the latter from the former. If there are any
- forward reference subroutine calls in the group, there will be entries on
- the workspace list; replicate these with an appropriate increment. */
-
- else
- {
- if (repeat_min > 1)
- {
- /* In the pre-compile phase, we don't actually do the replication. We
- just adjust the length as if we had. Do some paranoid checks for
- potential integer overflow. */
-
- if (lengthptr != NULL)
- {
- int delta = (repeat_min - 1)*length_prevgroup;
- if ((double)(repeat_min - 1)*(double)length_prevgroup >
- (double)INT_MAX ||
- OFLOW_MAX - *lengthptr < delta)
- {
- *errorcodeptr = ERR20;
- goto FAILED;
- }
- *lengthptr += delta;
- }
-
- /* This is compiling for real */
-
- else
- {
- if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte;
- for (i = 1; i < repeat_min; i++)
- {
- uschar *hc;
- uschar *this_hwm = cd->hwm;
- memcpy(code, previous, len);
- for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE)
- {
- PUT(cd->hwm, 0, GET(hc, 0) + len);
- cd->hwm += LINK_SIZE;
- }
- save_hwm = this_hwm;
- code += len;
- }
- }
- }
-
- if (repeat_max > 0) repeat_max -= repeat_min;
- }
-
- /* This code is common to both the zero and non-zero minimum cases. If
- the maximum is limited, it replicates the group in a nested fashion,
- remembering the bracket starts on a stack. In the case of a zero minimum,
- the first one was set up above. In all cases the repeat_max now specifies
- the number of additional copies needed. Again, we must remember to
- replicate entries on the forward reference list. */
-
- if (repeat_max >= 0)
- {
- /* In the pre-compile phase, we don't actually do the replication. We
- just adjust the length as if we had. For each repetition we must add 1
- to the length for BRAZERO and for all but the last repetition we must
- add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some
- paranoid checks to avoid integer overflow. */
-
- if (lengthptr != NULL && repeat_max > 0)
- {
- int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) -
- 2 - 2*LINK_SIZE; /* Last one doesn't nest */
- if ((double)repeat_max *
- (double)(length_prevgroup + 1 + 2 + 2*LINK_SIZE)
- > (double)INT_MAX ||
- OFLOW_MAX - *lengthptr < delta)
- {
- *errorcodeptr = ERR20;
- goto FAILED;
- }
- *lengthptr += delta;
- }
-
- /* This is compiling for real */
-
- else for (i = repeat_max - 1; i >= 0; i--)
- {
- uschar *hc;
- uschar *this_hwm = cd->hwm;
-
- *code++ = OP_BRAZERO + repeat_type;
-
- /* All but the final copy start a new nesting, maintaining the
- chain of brackets outstanding. */
-
- if (i != 0)
- {
- int offset;
- *code++ = OP_BRA;
- offset = (bralink == NULL)? 0 : code - bralink;
- bralink = code;
- PUTINC(code, 0, offset);
- }
-
- memcpy(code, previous, len);
- for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE)
- {
- PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1));
- cd->hwm += LINK_SIZE;
- }
- save_hwm = this_hwm;
- code += len;
- }
-
- /* Now chain through the pending brackets, and fill in their length
- fields (which are holding the chain links pro tem). */
-
- while (bralink != NULL)
- {
- int oldlinkoffset;
- int offset = code - bralink + 1;
- uschar *bra = code - offset;
- oldlinkoffset = GET(bra, 1);
- bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset;
- *code++ = OP_KET;
- PUTINC(code, 0, offset);
- PUT(bra, 1, offset);
- }
- }
-
- /* If the maximum is unlimited, set a repeater in the final copy. We
- can't just offset backwards from the current code point, because we
- don't know if there's been an options resetting after the ket. The
- correct offset was computed above.
-
- Then, when we are doing the actual compile phase, check to see whether
- this group is a non-atomic one that could match an empty string. If so,
- convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so
- that runtime checking can be done. [This check is also applied to
- atomic groups at runtime, but in a different way.] */
-
- else
- {
- uschar *ketcode = code - ketoffset;
- uschar *bracode = ketcode - GET(ketcode, 1);
- *ketcode = OP_KETRMAX + repeat_type;
- if (lengthptr == NULL && *bracode != OP_ONCE)
- {
- uschar *scode = bracode;
- do
- {
- if (could_be_empty_branch(scode, ketcode, utf8))
- {
- *bracode += OP_SBRA - OP_BRA;
- break;
- }
- scode += GET(scode, 1);
- }
- while (*scode == OP_ALT);
- }
- }
- }
-
- /* Else there's some kind of shambles */
-
- else
- {
- *errorcodeptr = ERR11;
- goto FAILED;
- }
-
- /* If the character following a repeat is '+', or if certain optimization
- tests above succeeded, possessive_quantifier is TRUE. For some of the
- simpler opcodes, there is an special alternative opcode for this. For
- anything else, we wrap the entire repeated item inside OP_ONCE brackets.
- The '+' notation is just syntactic sugar, taken from Sun's Java package,
- but the special opcodes can optimize it a bit. The repeated item starts at
- tempcode, not at previous, which might be the first part of a string whose
- (former) last char we repeated.
-
- Possessifying an 'exact' quantifier has no effect, so we can ignore it. But
- an 'upto' may follow. We skip over an 'exact' item, and then test the
- length of what remains before proceeding. */
-
- if (possessive_quantifier)
- {
- int len;
- if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT ||
- *tempcode == OP_NOTEXACT)
- tempcode += _pcre_OP_lengths[*tempcode];
- len = code - tempcode;
- if (len > 0) switch (*tempcode)
- {
- case OP_STAR: *tempcode = OP_POSSTAR; break;
- case OP_PLUS: *tempcode = OP_POSPLUS; break;
- case OP_QUERY: *tempcode = OP_POSQUERY; break;
- case OP_UPTO: *tempcode = OP_POSUPTO; break;
-
- case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break;
- case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break;
- case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break;
- case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break;
-
- case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break;
- case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break;
- case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break;
- case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break;
-
- default:
- memmove(tempcode + 1+LINK_SIZE, tempcode, len);
- code += 1 + LINK_SIZE;
- len += 1 + LINK_SIZE;
- tempcode[0] = OP_ONCE;
- *code++ = OP_KET;
- PUTINC(code, 0, len);
- PUT(tempcode, 1, len);
- break;
- }
- }
-
- /* In all case we no longer have a previous item. We also set the
- "follows varying string" flag for subsequently encountered reqbytes if
- it isn't already set and we have just passed a varying length item. */
-
- END_REPEAT:
- previous = NULL;
- cd->req_varyopt |= reqvary;
- break;
-
-
- /* ===================================================================*/
- /* Start of nested parenthesized sub-expression, or comment or lookahead or
- lookbehind or option setting or condition or all the other extended
- parenthesis forms. */
-
- case '(':
- newoptions = options;
- skipbytes = 0;
- bravalue = OP_CBRA;
- save_hwm = cd->hwm;
- reset_bracount = FALSE;
-
- /* First deal with various "verbs" that can be introduced by '*'. */
-
- if (*(++ptr) == '*' && (cd->ctypes[ptr[1]] & ctype_letter) != 0)
- {
- int i, namelen;
- const char *vn = verbnames;
- const uschar *name = ++ptr;
- previous = NULL;
- while ((cd->ctypes[*++ptr] & ctype_letter) != 0);
- if (*ptr == ':')
- {
- *errorcodeptr = ERR59; /* Not supported */
- goto FAILED;
- }
- if (*ptr != ')')
- {
- *errorcodeptr = ERR60;
- goto FAILED;
- }
- namelen = ptr - name;
- for (i = 0; i < verbcount; i++)
- {
- if (namelen == verbs[i].len &&
- strncmp((char *)name, vn, namelen) == 0)
- {
- *code = verbs[i].op;
- if (*code++ == OP_ACCEPT) cd->had_accept = TRUE;
- break;
- }
- vn += verbs[i].len + 1;
- }
- if (i < verbcount) continue;
- *errorcodeptr = ERR60;
- goto FAILED;
- }
-
- /* Deal with the extended parentheses; all are introduced by '?', and the
- appearance of any of them means that this is not a capturing group. */
-
- else if (*ptr == '?')
- {
- int i, set, unset, namelen;
- int *optset;
- const uschar *name;
- uschar *slot;
-
- switch (*(++ptr))
- {
- case '#': /* Comment; skip to ket */
- ptr++;
- while (*ptr != 0 && *ptr != ')') ptr++;
- if (*ptr == 0)
- {
- *errorcodeptr = ERR18;
- goto FAILED;
- }
- continue;
-
-
- /* ------------------------------------------------------------ */
- case '|': /* Reset capture count for each branch */
- reset_bracount = TRUE;
- /* Fall through */
-
- /* ------------------------------------------------------------ */
- case ':': /* Non-capturing bracket */
- bravalue = OP_BRA;
- ptr++;
- break;
-
-
- /* ------------------------------------------------------------ */
- case '(':
- bravalue = OP_COND; /* Conditional group */
-
- /* A condition can be an assertion, a number (referring to a numbered
- group), a name (referring to a named group), or 'R', referring to
- recursion. R<digits> and R&name are also permitted for recursion tests.
-
- There are several syntaxes for testing a named group: (?(name)) is used
- by Python; Perl 5.10 onwards uses (?(<name>) or (?('name')).
-
- There are two unfortunate ambiguities, caused by history. (a) 'R' can
- be the recursive thing or the name 'R' (and similarly for 'R' followed
- by digits), and (b) a number could be a name that consists of digits.
- In both cases, we look for a name first; if not found, we try the other
- cases. */
-
- /* For conditions that are assertions, check the syntax, and then exit
- the switch. This will take control down to where bracketed groups,
- including assertions, are processed. */
-
- if (ptr[1] == '?' && (ptr[2] == '=' || ptr[2] == '!' || ptr[2] == '<'))
- break;
-
- /* Most other conditions use OP_CREF (a couple change to OP_RREF
- below), and all need to skip 3 bytes at the start of the group. */
-
- code[1+LINK_SIZE] = OP_CREF;
- skipbytes = 3;
- refsign = -1;
-
- /* Check for a test for recursion in a named group. */
-
- if (ptr[1] == 'R' && ptr[2] == '&')
- {
- terminator = -1;
- ptr += 2;
- code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */
- }
-
- /* Check for a test for a named group's having been set, using the Perl
- syntax (?(<name>) or (?('name') */
-
- else if (ptr[1] == '<')
- {
- terminator = '>';
- ptr++;
- }
- else if (ptr[1] == '\'')
- {
- terminator = '\'';
- ptr++;
- }
- else
- {
- terminator = 0;
- if (ptr[1] == '-' || ptr[1] == '+') refsign = *(++ptr);
- }
-
- /* We now expect to read a name; any thing else is an error */
-
- if ((cd->ctypes[ptr[1]] & ctype_word) == 0)
- {
- ptr += 1; /* To get the right offset */
- *errorcodeptr = ERR28;
- goto FAILED;
- }
-
- /* Read the name, but also get it as a number if it's all digits */
-
- recno = 0;
- name = ++ptr;
- while ((cd->ctypes[*ptr] & ctype_word) != 0)
- {
- if (recno >= 0)
- recno = ((digitab[*ptr] & ctype_digit) != 0)?
- recno * 10 + *ptr - '0' : -1;
- ptr++;
- }
- namelen = ptr - name;
-
- if ((terminator > 0 && *ptr++ != terminator) || *ptr++ != ')')
- {
- ptr--; /* Error offset */
- *errorcodeptr = ERR26;
- goto FAILED;
- }
-
- /* Do no further checking in the pre-compile phase. */
-
- if (lengthptr != NULL) break;
-
- /* In the real compile we do the work of looking for the actual
- reference. If the string started with "+" or "-" we require the rest to
- be digits, in which case recno will be set. */
-
- if (refsign > 0)
- {
- if (recno <= 0)
- {
- *errorcodeptr = ERR58;
- goto FAILED;
- }
- if (refsign == '-')
- {
- recno = cd->bracount - recno + 1;
- if (recno <= 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
- }
- else recno += cd->bracount;
- PUT2(code, 2+LINK_SIZE, recno);
- break;
- }
-
- /* Otherwise (did not start with "+" or "-"), start by looking for the
- name. */
-
- slot = cd->name_table;
- for (i = 0; i < cd->names_found; i++)
- {
- if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break;
- slot += cd->name_entry_size;
- }
-
- /* Found a previous named subpattern */
-
- if (i < cd->names_found)
- {
- recno = GET2(slot, 0);
- PUT2(code, 2+LINK_SIZE, recno);
- }
-
- /* Search the pattern for a forward reference */
-
- else if ((i = find_parens(ptr, cd->bracount, name, namelen,
- (options & PCRE_EXTENDED) != 0)) > 0)
- {
- PUT2(code, 2+LINK_SIZE, i);
- }
-
- /* If terminator == 0 it means that the name followed directly after
- the opening parenthesis [e.g. (?(abc)...] and in this case there are
- some further alternatives to try. For the cases where terminator != 0
- [things like (?(<name>... or (?('name')... or (?(R&name)... ] we have
- now checked all the possibilities, so give an error. */
-
- else if (terminator != 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
-
- /* Check for (?(R) for recursion. Allow digits after R to specify a
- specific group number. */
-
- else if (*name == 'R')
- {
- recno = 0;
- for (i = 1; i < namelen; i++)
- {
- if ((digitab[name[i]] & ctype_digit) == 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
- recno = recno * 10 + name[i] - '0';
- }
- if (recno == 0) recno = RREF_ANY;
- code[1+LINK_SIZE] = OP_RREF; /* Change test type */
- PUT2(code, 2+LINK_SIZE, recno);
- }
-
- /* Similarly, check for the (?(DEFINE) "condition", which is always
- false. */
-
- else if (namelen == 6 && strncmp((char *)name, "DEFINE", 6) == 0)
- {
- code[1+LINK_SIZE] = OP_DEF;
- skipbytes = 1;
- }
-
- /* Check for the "name" actually being a subpattern number. */
-
- else if (recno > 0)
- {
- PUT2(code, 2+LINK_SIZE, recno);
- }
-
- /* Either an unidentified subpattern, or a reference to (?(0) */
-
- else
- {
- *errorcodeptr = (recno == 0)? ERR35: ERR15;
- goto FAILED;
- }
- break;
-
-
- /* ------------------------------------------------------------ */
- case '=': /* Positive lookahead */
- bravalue = OP_ASSERT;
- ptr++;
- break;
-
-
- /* ------------------------------------------------------------ */
- case '!': /* Negative lookahead */
- ptr++;
- if (*ptr == ')') /* Optimize (?!) */
- {
- *code++ = OP_FAIL;
- previous = NULL;
- continue;
- }
- bravalue = OP_ASSERT_NOT;
- break;
-
-
- /* ------------------------------------------------------------ */
- case '<': /* Lookbehind or named define */
- switch (ptr[1])
- {
- case '=': /* Positive lookbehind */
- bravalue = OP_ASSERTBACK;
- ptr += 2;
- break;
-
- case '!': /* Negative lookbehind */
- bravalue = OP_ASSERTBACK_NOT;
- ptr += 2;
- break;
-
- default: /* Could be name define, else bad */
- if ((cd->ctypes[ptr[1]] & ctype_word) != 0) goto DEFINE_NAME;
- ptr++; /* Correct offset for error */
- *errorcodeptr = ERR24;
- goto FAILED;
- }
- break;
-
-
- /* ------------------------------------------------------------ */
- case '>': /* One-time brackets */
- bravalue = OP_ONCE;
- ptr++;
- break;
-
-
- /* ------------------------------------------------------------ */
- case 'C': /* Callout - may be followed by digits; */
- previous_callout = code; /* Save for later completion */
- after_manual_callout = 1; /* Skip one item before completing */
- *code++ = OP_CALLOUT;
- {
- int n = 0;
- while ((digitab[*(++ptr)] & ctype_digit) != 0)
- n = n * 10 + *ptr - '0';
- if (*ptr != ')')
- {
- *errorcodeptr = ERR39;
- goto FAILED;
- }
- if (n > 255)
- {
- *errorcodeptr = ERR38;
- goto FAILED;
- }
- *code++ = n;
- PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */
- PUT(code, LINK_SIZE, 0); /* Default length */
- code += 2 * LINK_SIZE;
- }
- previous = NULL;
- continue;
-
-
- /* ------------------------------------------------------------ */
- case 'P': /* Python-style named subpattern handling */
- if (*(++ptr) == '=' || *ptr == '>') /* Reference or recursion */
- {
- is_recurse = *ptr == '>';
- terminator = ')';
- goto NAMED_REF_OR_RECURSE;
- }
- else if (*ptr != '<') /* Test for Python-style definition */
- {
- *errorcodeptr = ERR41;
- goto FAILED;
- }
- /* Fall through to handle (?P< as (?< is handled */
-
-
- /* ------------------------------------------------------------ */
- DEFINE_NAME: /* Come here from (?< handling */
- case '\'':
- {
- terminator = (*ptr == '<')? '>' : '\'';
- name = ++ptr;
-
- while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++;
- namelen = ptr - name;
-
- /* In the pre-compile phase, just do a syntax check. */
-
- if (lengthptr != NULL)
- {
- if (*ptr != terminator)
- {
- *errorcodeptr = ERR42;
- goto FAILED;
- }
- if (cd->names_found >= MAX_NAME_COUNT)
- {
- *errorcodeptr = ERR49;
- goto FAILED;
- }
- if (namelen + 3 > cd->name_entry_size)
- {
- cd->name_entry_size = namelen + 3;
- if (namelen > MAX_NAME_SIZE)
- {
- *errorcodeptr = ERR48;
- goto FAILED;
- }
- }
- }
-
- /* In the real compile, create the entry in the table */
-
- else
- {
- slot = cd->name_table;
- for (i = 0; i < cd->names_found; i++)
- {
- int crc = memcmp(name, slot+2, namelen);
- if (crc == 0)
- {
- if (slot[2+namelen] == 0)
- {
- if ((options & PCRE_DUPNAMES) == 0)
- {
- *errorcodeptr = ERR43;
- goto FAILED;
- }
- }
- else crc = -1; /* Current name is substring */
- }
- if (crc < 0)
- {
- memmove(slot + cd->name_entry_size, slot,
- (cd->names_found - i) * cd->name_entry_size);
- break;
- }
- slot += cd->name_entry_size;
- }
-
- PUT2(slot, 0, cd->bracount + 1);
- memcpy(slot + 2, name, namelen);
- slot[2+namelen] = 0;
- }
- }
-
- /* In both cases, count the number of names we've encountered. */
-
- ptr++; /* Move past > or ' */
- cd->names_found++;
- goto NUMBERED_GROUP;
-
-
- /* ------------------------------------------------------------ */
- case '&': /* Perl recursion/subroutine syntax */
- terminator = ')';
- is_recurse = TRUE;
- /* Fall through */
-
- /* We come here from the Python syntax above that handles both
- references (?P=name) and recursion (?P>name), as well as falling
- through from the Perl recursion syntax (?&name). */
-
- NAMED_REF_OR_RECURSE:
- name = ++ptr;
- while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++;
- namelen = ptr - name;
-
- /* In the pre-compile phase, do a syntax check and set a dummy
- reference number. */
-
- if (lengthptr != NULL)
- {
- if (*ptr != terminator)
- {
- *errorcodeptr = ERR42;
- goto FAILED;
- }
- if (namelen > MAX_NAME_SIZE)
- {
- *errorcodeptr = ERR48;
- goto FAILED;
- }
- recno = 0;
- }
-
- /* In the real compile, seek the name in the table */
-
- else
- {
- slot = cd->name_table;
- for (i = 0; i < cd->names_found; i++)
- {
- if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break;
- slot += cd->name_entry_size;
- }
-
- if (i < cd->names_found) /* Back reference */
- {
- recno = GET2(slot, 0);
- }
- else if ((recno = /* Forward back reference */
- find_parens(ptr, cd->bracount, name, namelen,
- (options & PCRE_EXTENDED) != 0)) <= 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
- }
-
- /* In both phases, we can now go to the code than handles numerical
- recursion or backreferences. */
-
- if (is_recurse) goto HANDLE_RECURSION;
- else goto HANDLE_REFERENCE;
-
-
- /* ------------------------------------------------------------ */
- case 'R': /* Recursion */
- ptr++; /* Same as (?0) */
- /* Fall through */
-
-
- /* ------------------------------------------------------------ */
- case '-': case '+':
- case '0': case '1': case '2': case '3': case '4': /* Recursion or */
- case '5': case '6': case '7': case '8': case '9': /* subroutine */
- {
- const uschar *called;
-
- if ((refsign = *ptr) == '+') ptr++;
- else if (refsign == '-')
- {
- if ((digitab[ptr[1]] & ctype_digit) == 0)
- goto OTHER_CHAR_AFTER_QUERY;
- ptr++;
- }
-
- recno = 0;
- while((digitab[*ptr] & ctype_digit) != 0)
- recno = recno * 10 + *ptr++ - '0';
-
- if (*ptr != ')')
- {
- *errorcodeptr = ERR29;
- goto FAILED;
- }
-
- if (refsign == '-')
- {
- if (recno == 0)
- {
- *errorcodeptr = ERR58;
- goto FAILED;
- }
- recno = cd->bracount - recno + 1;
- if (recno <= 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
- }
- else if (refsign == '+')
- {
- if (recno == 0)
- {
- *errorcodeptr = ERR58;
- goto FAILED;
- }
- recno += cd->bracount;
- }
-
- /* Come here from code above that handles a named recursion */
-
- HANDLE_RECURSION:
-
- previous = code;
- called = cd->start_code;
-
- /* When we are actually compiling, find the bracket that is being
- referenced. Temporarily end the regex in case it doesn't exist before
- this point. If we end up with a forward reference, first check that
- the bracket does occur later so we can give the error (and position)
- now. Then remember this forward reference in the workspace so it can
- be filled in at the end. */
-
- if (lengthptr == NULL)
- {
- *code = OP_END;
- if (recno != 0) called = find_bracket(cd->start_code, utf8, recno);
-
- /* Forward reference */
-
- if (called == NULL)
- {
- if (find_parens(ptr, cd->bracount, NULL, recno,
- (options & PCRE_EXTENDED) != 0) < 0)
- {
- *errorcodeptr = ERR15;
- goto FAILED;
- }
- called = cd->start_code + recno;
- PUTINC(cd->hwm, 0, code + 2 + LINK_SIZE - cd->start_code);
- }
-
- /* If not a forward reference, and the subpattern is still open,
- this is a recursive call. We check to see if this is a left
- recursion that could loop for ever, and diagnose that case. */
-
- else if (GET(called, 1) == 0 &&
- could_be_empty(called, code, bcptr, utf8))
- {
- *errorcodeptr = ERR40;
- goto FAILED;
- }
- }
-
- /* Insert the recursion/subroutine item, automatically wrapped inside
- "once" brackets. Set up a "previous group" length so that a
- subsequent quantifier will work. */
-
- *code = OP_ONCE;
- PUT(code, 1, 2 + 2*LINK_SIZE);
- code += 1 + LINK_SIZE;
-
- *code = OP_RECURSE;
- PUT(code, 1, called - cd->start_code);
- code += 1 + LINK_SIZE;
-
- *code = OP_KET;
- PUT(code, 1, 2 + 2*LINK_SIZE);
- code += 1 + LINK_SIZE;
-
- length_prevgroup = 3 + 3*LINK_SIZE;
- }
-
- /* Can't determine a first byte now */
-
- if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE;
- continue;
-
-
- /* ------------------------------------------------------------ */
- default: /* Other characters: check option setting */
- OTHER_CHAR_AFTER_QUERY:
- set = unset = 0;
- optset = &set;
-
- while (*ptr != ')' && *ptr != ':')
- {
- switch (*ptr++)
- {
- case '-': optset = &unset; break;
-
- case 'J': /* Record that it changed in the external options */
- *optset |= PCRE_DUPNAMES;
- cd->external_flags |= PCRE_JCHANGED;
- break;
-
- case 'i': *optset |= PCRE_CASELESS; break;
- case 'm': *optset |= PCRE_MULTILINE; break;
- case 's': *optset |= PCRE_DOTALL; break;
- case 'x': *optset |= PCRE_EXTENDED; break;
- case 'U': *optset |= PCRE_UNGREEDY; break;
- case 'X': *optset |= PCRE_EXTRA; break;
-
- default: *errorcodeptr = ERR12;
- ptr--; /* Correct the offset */
- goto FAILED;
- }
- }
-
- /* Set up the changed option bits, but don't change anything yet. */
-
- newoptions = (options | set) & (~unset);
-
- /* If the options ended with ')' this is not the start of a nested
- group with option changes, so the options change at this level. If this
- item is right at the start of the pattern, the options can be
- abstracted and made external in the pre-compile phase, and ignored in
- the compile phase. This can be helpful when matching -- for instance in
- caseless checking of required bytes.
-
- If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are
- definitely *not* at the start of the pattern because something has been
- compiled. In the pre-compile phase, however, the code pointer can have
- that value after the start, because it gets reset as code is discarded
- during the pre-compile. However, this can happen only at top level - if
- we are within parentheses, the starting BRA will still be present. At
- any parenthesis level, the length value can be used to test if anything
- has been compiled at that level. Thus, a test for both these conditions
- is necessary to ensure we correctly detect the start of the pattern in
- both phases.
-
- If we are not at the pattern start, compile code to change the ims
- options if this setting actually changes any of them. We also pass the
- new setting back so that it can be put at the start of any following
- branches, and when this group ends (if we are in a group), a resetting
- item can be compiled. */
-
- if (*ptr == ')')
- {
- if (code == cd->start_code + 1 + LINK_SIZE &&
- (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE))
- {
- cd->external_options = newoptions;
- options = newoptions;
- }
- else
- {
- if ((options & PCRE_IMS) != (newoptions & PCRE_IMS))
- {
- *code++ = OP_OPT;
- *code++ = newoptions & PCRE_IMS;
- }
-
- /* Change options at this level, and pass them back for use
- in subsequent branches. Reset the greedy defaults and the case
- value for firstbyte and reqbyte. */
-
- *optionsptr = options = newoptions;
- greedy_default = ((newoptions & PCRE_UNGREEDY) != 0);
- greedy_non_default = greedy_default ^ 1;
- req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0;
- }
-
- previous = NULL; /* This item can't be repeated */
- continue; /* It is complete */
- }
-
- /* If the options ended with ':' we are heading into a nested group
- with possible change of options. Such groups are non-capturing and are
- not assertions of any kind. All we need to do is skip over the ':';
- the newoptions value is handled below. */
-
- bravalue = OP_BRA;
- ptr++;
- } /* End of switch for character following (? */
- } /* End of (? handling */
-
- /* Opening parenthesis not followed by '?'. If PCRE_NO_AUTO_CAPTURE is set,
- all unadorned brackets become non-capturing and behave like (?:...)
- brackets. */
-
- else if ((options & PCRE_NO_AUTO_CAPTURE) != 0)
- {
- bravalue = OP_BRA;
- }
-
- /* Else we have a capturing group. */
-
- else
- {
- NUMBERED_GROUP:
- cd->bracount += 1;
- PUT2(code, 1+LINK_SIZE, cd->bracount);
- skipbytes = 2;
- }
-
- /* Process nested bracketed regex. Assertions may not be repeated, but
- other kinds can be. All their opcodes are >= OP_ONCE. We copy code into a
- non-register variable in order to be able to pass its address because some
- compilers complain otherwise. Pass in a new setting for the ims options if
- they have changed. */
-
- previous = (bravalue >= OP_ONCE)? code : NULL;
- *code = bravalue;
- tempcode = code;
- tempreqvary = cd->req_varyopt; /* Save value before bracket */
- length_prevgroup = 0; /* Initialize for pre-compile phase */
-
- if (!compile_regex(
- newoptions, /* The complete new option state */
- options & PCRE_IMS, /* The previous ims option state */
- &tempcode, /* Where to put code (updated) */
- &ptr, /* Input pointer (updated) */
- errorcodeptr, /* Where to put an error message */
- (bravalue == OP_ASSERTBACK ||
- bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */
- reset_bracount, /* True if (?| group */
- skipbytes, /* Skip over bracket number */
- &subfirstbyte, /* For possible first char */
- &subreqbyte, /* For possible last char */
- bcptr, /* Current branch chain */
- cd, /* Tables block */
- (lengthptr == NULL)? NULL : /* Actual compile phase */
- &length_prevgroup /* Pre-compile phase */
- ))
- goto FAILED;
-
- /* At the end of compiling, code is still pointing to the start of the
- group, while tempcode has been updated to point past the end of the group
- and any option resetting that may follow it. The pattern pointer (ptr)
- is on the bracket. */
-
- /* If this is a conditional bracket, check that there are no more than
- two branches in the group, or just one if it's a DEFINE group. We do this
- in the real compile phase, not in the pre-pass, where the whole group may
- not be available. */
-
- if (bravalue == OP_COND && lengthptr == NULL)
- {
- uschar *tc = code;
- int condcount = 0;
-
- do {
- condcount++;
- tc += GET(tc,1);
- }
- while (*tc != OP_KET);
-
- /* A DEFINE group is never obeyed inline (the "condition" is always
- false). It must have only one branch. */
-
- if (code[LINK_SIZE+1] == OP_DEF)
- {
- if (condcount > 1)
- {
- *errorcodeptr = ERR54;
- goto FAILED;
- }
- bravalue = OP_DEF; /* Just a flag to suppress char handling below */
- }
-
- /* A "normal" conditional group. If there is just one branch, we must not
- make use of its firstbyte or reqbyte, because this is equivalent to an
- empty second branch. */
-
- else
- {
- if (condcount > 2)
- {
- *errorcodeptr = ERR27;
- goto FAILED;
- }
- if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE;
- }
- }
-
- /* Error if hit end of pattern */
-
- if (*ptr != ')')
- {
- *errorcodeptr = ERR14;
- goto FAILED;
- }
-
- /* In the pre-compile phase, update the length by the length of the group,
- less the brackets at either end. Then reduce the compiled code to just a
- set of non-capturing brackets so that it doesn't use much memory if it is
- duplicated by a quantifier.*/
-
- if (lengthptr != NULL)
- {
- if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE)
- {
- *errorcodeptr = ERR20;
- goto FAILED;
- }
-
projects / exim.git / commitdiff