Hi Miry,
After your patch is applied, I just set matchArray to
pcre2_get_ovector_pointer(patternMatchData) each time when pcre2_match is
called, then regex searching/replacing works.
The source code has been updated:
https://sourceforge.net/p/xml-copy-editor/code/ci/3d17bca4196670183ad45c0af369acf4acdc7d7e/
Regards,
Zane
diff --git a/configure.ac b/configure.ac
index d0ab3af..1c1f0dd 100755
--- a/configure.ac
+++ b/configure.ac
@@ -72,8 +72,7 @@ AC_ARG_ENABLE(debug,
])
# Check pcre is available
-AC_CHECK_HEADER(pcre.h, ,
- AC_MSG_ERROR([PCRE headers not found]))
+PKG_CHECK_MODULES([PCRE2], [libpcre2-8])
# Check boost::shared_ptr is available
AC_LANG(C++)
diff --git a/src/Makefile.am b/src/Makefile.am
index 7b0c81c..15bf572 100644
--- a/src/Makefile.am
+++ b/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/*.* \
@@ -133,5 +134,5 @@ EXTRA_DIST = \
$(srcdir)/xmlcopyeditor.rc \
$(srcdir)/xmlschemaparser.cpp
-AM_CPPFLAGS = $(XML2_CFLAGS) $(ENCHANT_CFLAGS) $(GTK_CFLAGS)
+AM_CPPFLAGS = $(XML2_CFLAGS) $(ENCHANT_CFLAGS) $(GTK_CFLAGS) $(PCRE2_CFLAGS)
diff --git a/src/rule.cpp b/src/rule.cpp
index 487a364..37bfe3c 100644
--- a/src/rule.cpp
+++ b/src/rule.cpp
@@ -26,12 +26,11 @@ using namespace std;
Rule::Rule (
const string& pattern,
bool matchCase,
- const string& replace,
- const int arrayLength ) : WrapRegex (
+ const string& replace
+ ) : WrapRegex (
pattern,
matchCase,
- replace,
- arrayLength )
+ replace )
{
adjustCaseAttribute = tentativeAttribute = false;
}
diff --git a/src/rule.h b/src/rule.h
index a89289e..1abfbab 100644
--- a/src/rule.h
+++ b/src/rule.h
@@ -32,8 +32,7 @@ class Rule : public WrapRegex
Rule (
const string& pattern,
bool matchCase,
- const string& replace = "",
- const int arrayLength = 60 );
+ const string& replace = "");
bool getAdjustCaseAttribute();
bool getTentativeAttribute();
string getReport();
diff --git a/src/wrapregex.cpp b/src/wrapregex.cpp
index ff8d622..99d2a7c 100644
--- a/src/wrapregex.cpp
+++ b/src/wrapregex.cpp
@@ -31,40 +31,39 @@ using namespace std;
WrapRegex::WrapRegex (
const string& pattern,
bool matchCase,
- const string& replaceParameter,
- const int arrayLengthParameter ) :
+ const string& replaceParameter ) :
replace ( replaceParameter ),
- arrayLength ( arrayLengthParameter ),
returnValue ( 0 )
{
if ( pattern.empty() || pattern == ".*" )
{
disabled = true;
- matchArray = NULL;
- patternStructure = NULL;
- patternExtraStructure = NULL;
+ patternCode = NULL;
+ patternMatchData = NULL;
+ patternMatchContext = NULL;
return;
}
disabled = false;
- 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 ? 0 : 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()
@@ -72,9 +71,9 @@ WrapRegex::~WrapRegex()
if ( disabled )
return;
- pcre_free ( patternStructure );
- pcre_free ( patternExtraStructure );
- delete[] matchArray;
+ pcre2_match_data_free ( patternMatchData );
+ pcre2_code_free ( patternCode );
+ pcre2_match_context_free ( patternMatchContext );
}
int WrapRegex::matchPatternGlobal (
@@ -108,18 +107,18 @@ 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 );
+ PCRE2_SIZE *matchArray = pcre2_get_ovector_pointer ( patternMatchData );
output.append ( s, matchArray[0] );
match.clear();
@@ -150,18 +149,18 @@ 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;
+ PCRE2_SIZE *matchArray = pcre2_get_ovector_pointer ( patternMatchData );
if ( context )
{
match = ContextHandler::getContext (
@@ -255,11 +254,17 @@ string WrapRegex::getSubpattern_ ( const char *s, unsigned subpattern )
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 = 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;
}
diff --git a/src/wrapregex.h b/src/wrapregex.h
index 3046dcc..b59b7c6 100644
--- a/src/wrapregex.h
+++ b/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"
@@ -36,8 +40,7 @@ class WrapRegex : private boost::noncopyable
WrapRegex (
const string& pattern,
bool matchCase,
- const string& replaceParameter = "",
- const int arrayLengthParameter = 60 );
+ const string& replaceParameter = "" );
virtual ~WrapRegex();
string replaceGlobal (
const string& buffer,
@@ -49,13 +52,12 @@ class WrapRegex : private boost::noncopyable
int context = 0 );
private:
string replace;
- const int arrayLength;
int returnValue;
bool disabled;
- pcre *patternStructure;
- pcre_extra *patternExtraStructure;
- int *matchArray;
+ pcre2_code *patternCode;
+ pcre2_match_data *patternMatchData;
+ pcre2_match_context *patternMatchContext;
string getInterpolatedString_ ( const char *buffer,
const char *source );
