The API for PCRE2 seems to have changed a lot. According to https://redmine.openinfosecfoundation.org/issues/3194
- pcre_free_substring replaced straight by pcre2_substring_free - pcre_get_substring seems replaced by pcre2_substring_get_bynumber which does not have the same arguments... - pcre_exec replaced by pcre2_match - pcre_copy_substring replaced by pcre2_substring_copy_bynumber - pcre_free - pcre_compile replaced by pcre2_compile - pcre_study obsolete in pcre2 : The new API is more extensible, and it was simplified by abolishing the separate "study" optimizing function - pare jit stuff present in pcre2 There seems to be some rationale on the decisions of the new API at http://washitake.com/mail/exim/mirror/pcre/Testing/PCRE2_proposal.pdf Upstream hasn't ported the code yet. I'm attaching my 1st draft of a patch. It builds, but I need to check it carefully. As I don't have much experience with pcre2, comments and suggestions are welcome. Thanks, Miry
# See: https://github.com/wch/r-source/blob/af9a038e277d14b038ef877366652b6e5400c399/src/main/grep.c # See: https://github.com/Sigil-Ebook/Sigil/issues/630 # See: https://github.com/PCRE2Project/pcre2/issues/51 # See: https://github.com/HaxeFoundation/haxe/issues/10491 # See: https://github.com/SWI-Prolog/packages-pcre/issues/2 # See: https://github.com/SWI-Prolog/packages-pcre/pull/3/files # See: https://pcre.org/current/doc/html/ # See: https://github.com/luvit/pcre2/blob/master/src/pcre2demo.c # See: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=999923 # See: http://washitake.com/mail/exim/mirror/pcre/Testing/PCRE2_proposal.pdf # See: https://redmine.openinfosecfoundation.org/issues/3194 # See: https://pcre.org/current/doc/html/pcre2api.html Index: xmlcopyeditor-1.3.0.0/configure.ac =================================================================== --- xmlcopyeditor-1.3.0.0.orig/configure.ac +++ xmlcopyeditor-1.3.0.0/configure.ac @@ -71,9 +71,15 @@ AC_ARG_ENABLE(debug, CXXFLAGS="${CXXFLAGS} -DNDEBUG -DwxDEBUG_LEVEL=0" ]) -# Check pcre is available -AC_CHECK_HEADER(pcre.h, , - AC_MSG_ERROR([PCRE headers not found])) +# Check pcre2 is available +AC_CHECK_HEADER([pcre2.h], [], + [AC_MSG_ERROR([PCRE2 headers not found])], + [#define PCRE2_CODE_UNIT_WIDTH 8 + #include <pcre2.h> + ]) + +PCRE2_LIBS="-lpcre2-8" +AC_SUBST(PCRE2_LIBS) # Check boost::shared_ptr is available AC_LANG(C++) Index: xmlcopyeditor-1.3.0.0/src/wrapregex.h =================================================================== --- xmlcopyeditor-1.3.0.0.orig/src/wrapregex.h +++ xmlcopyeditor-1.3.0.0/src/wrapregex.h @@ -21,10 +21,14 @@ #ifndef WRAPREGEX_H #define WRAPREGEX_H +#ifndef PCRE2_CODE_UNIT_WIDTH +#define PCRE2_CODE_UNIT_WIDTH 8 +#endif + #include <iostream> #include <string> #include <vector> -#include <pcre.h> +#include <pcre2.h> #include <boost/utility.hpp> #include "contexthandler.h" @@ -53,8 +57,11 @@ class WrapRegex : private boost::noncopy int returnValue; bool disabled; - pcre *patternStructure; - pcre_extra *patternExtraStructure; + //~ pcre *patternStructure; + //~ pcre_extra *patternExtraStructure; + pcre2_code *patternCode; + pcre2_match_data *patternMatchData; + pcre2_match_context *patternMatchContext; int *matchArray; string getInterpolatedString_ ( const char *buffer, Index: xmlcopyeditor-1.3.0.0/src/wrapregex.cpp =================================================================== --- xmlcopyeditor-1.3.0.0.orig/src/wrapregex.cpp +++ xmlcopyeditor-1.3.0.0/src/wrapregex.cpp @@ -41,8 +41,11 @@ WrapRegex::WrapRegex ( { disabled = true; matchArray = NULL; - patternStructure = NULL; - patternExtraStructure = NULL; + //~ patternStructure = NULL; + //~ patternExtraStructure = NULL; + patternCode = NULL; + patternMatchData = NULL; + patternMatchContext = NULL; return; } disabled = false; @@ -50,21 +53,25 @@ WrapRegex::WrapRegex ( matchArray = new int[arrayLength]; // compile - int optionsFlag = ( matchCase ) ? PCRE_UTF8 : PCRE_CASELESS | PCRE_UTF8; - const char *errorPointer; - int errorOffset; - - if ( ( patternStructure = pcre_compile ( - pattern.c_str(), - optionsFlag, - &errorPointer, - &errorOffset, - NULL ) ) == NULL ) + uint32_t optionsFlag = ( matchCase ) ? PCRE2_UTF | PCRE2_NO_UTF_CHECK : PCRE2_CASELESS | PCRE2_UTF | PCRE2_NO_UTF_CHECK; + int errorCode; + PCRE2_SIZE errorOffset; + + if ( ( patternCode = pcre2_compile ( + (PCRE2_SPTR)pattern.c_str(), // pattern + PCRE2_ZERO_TERMINATED, // pattern is zero-terminated + optionsFlag, // options + &errorCode, // error number + &errorOffset, // error offset + NULL ) ) == NULL ) // default compile context { - throw runtime_error ( errorPointer ); + char buf[256]; + pcre2_get_error_message ( errorCode, (PCRE2_UCHAR *)buf, sizeof(buf) ); + throw runtime_error ( string(buf) ); } - patternExtraStructure = pcre_study ( patternStructure, 0, &errorPointer ); + patternMatchData = pcre2_match_data_create_from_pattern ( patternCode, NULL ); + patternMatchContext = pcre2_match_context_create ( NULL ); } WrapRegex::~WrapRegex() @@ -72,8 +79,11 @@ WrapRegex::~WrapRegex() if ( disabled ) return; - pcre_free ( patternStructure ); - pcre_free ( patternExtraStructure ); + //~ pcre_free ( patternStructure ); + //~ pcre_free ( patternExtraStructure ); + pcre2_match_data_free ( patternMatchData ); + pcre2_code_free ( patternCode ); + pcre2_match_context_free ( patternMatchContext ); delete[] matchArray; } @@ -108,15 +118,14 @@ string WrapRegex::replaceGlobal ( string output, match; output.reserve ( buffer.size() ); - while ( ( returnValue = pcre_exec ( - patternStructure, - patternExtraStructure, - s, - strlen ( s ), - 0, - 0, - matchArray, - arrayLength ) ) >= 0 ) + while ( ( returnValue = pcre2_match ( + patternCode, // compiled pattern + (PCRE2_SPTR)s, // subject string + strlen ( s ), // length of the subject + 0, // start at offset 0 in the subject + 0, // default options + patternMatchData, // block where results will be stored + patternMatchContext ) ) >= 0 ) // match context { ++ ( *matchCount ); @@ -150,15 +159,14 @@ int WrapRegex::matchPatternGlobal_ ( matchcount = 0; offset = 0; - while ( ( returnValue = pcre_exec ( - patternStructure, - patternExtraStructure, - s, - buflen, - offset, - 0, - matchArray, - arrayLength ) ) >= 0 ) + while ( ( returnValue = pcre2_match ( + patternCode, // compiled pattern + (PCRE2_SPTR)s, // subject string + buflen, // length of the subject + offset, // start at this offset in the subject + 0, // default options + patternMatchData, // block where results will be stored + patternMatchContext ) ) >= 0 ) // match context { ++matchcount; @@ -255,11 +263,18 @@ string WrapRegex::getSubpattern_ ( const if ( disabled ) return ""; - const char *sub; - int ret = pcre_get_substring ( s, matchArray, returnValue, subpattern, &sub ); - if ( ret == PCRE_ERROR_NOSUBSTRING || ret == PCRE_ERROR_NOMEMORY ) + char *sub = NULL; + size_t sublen; + //~ int ret = pcre_get_substring ( s, matchArray, returnValue, subpattern, &sub ); + int ret = pcre2_substring_get_bynumber ( + patternMatchData, + subpattern, + (PCRE2_UCHAR **)sub, + &sublen + ); + if ( ret == PCRE2_ERROR_NOMATCH || ret == PCRE2_ERROR_BADDATA ) return ""; string subString ( sub ); - pcre_free_substring ( sub ); + pcre2_substring_free ( (PCRE2_UCHAR *)sub ); return subString; } Index: xmlcopyeditor-1.3.0.0/src/Makefile.am =================================================================== --- xmlcopyeditor-1.3.0.0.orig/src/Makefile.am +++ xmlcopyeditor-1.3.0.0/src/Makefile.am @@ -83,7 +83,8 @@ xmlcopyeditor_LDADD = $(WX_LIBS) \ $(ENCHANT_LIBS) \ $(GTK_LIBS) \ $(XSLT_LIBS) \ - -lexpat -lpcre -lxerces-c + $(PCRE2_LIBS) \ + -lexpat -lxerces-c nobase_dist_xmlcopyeditor_DATA = $(srcdir)/catalog/catalog \ $(srcdir)/dtd/*.* \
