fivedev/harbour-core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2007-05-31 15:10 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)

Browse Source 
* harbour/common.mak
  * harbour/makefile.bc
  * harbour/makefile.vc
  * harbour/bin/hb-func.sh
  * harbour/config/bsd/gcc.cf
  * harbour/config/darwin/gcc.cf
  * harbour/config/hpux/gcc.cf
  * harbour/config/linux/gcc.cf
  * harbour/config/sunos/gcc.cf
  * harbour/source/Makefile
  + harbour/source/hbpcre/ChangeLog
  + harbour/source/hbpcre/Makefile
  + harbour/source/hbpcre/chartabs.c
  + harbour/source/hbpcre/config.h
  + harbour/source/hbpcre/dftables.c
  + harbour/source/hbpcre/pcre.h
  + harbour/source/hbpcre/pcrecomp.c
  + harbour/source/hbpcre/pcreconf.c
  + harbour/source/hbpcre/pcredfa.c
  + harbour/source/hbpcre/pcreexec.c
  + harbour/source/hbpcre/pcrefind.c
  + harbour/source/hbpcre/pcrefinf.c
  + harbour/source/hbpcre/pcreget.c
  + harbour/source/hbpcre/pcreglob.c
  + harbour/source/hbpcre/pcreinal.h
  + harbour/source/hbpcre/pcreinfo.c
  + harbour/source/hbpcre/pcremktb.c
  + harbour/source/hbpcre/pcreoutf.c
  + harbour/source/hbpcre/pcreprni.c
  + harbour/source/hbpcre/pcrerefc.c
  + harbour/source/hbpcre/pcrestud.c
  + harbour/source/hbpcre/pcretabs.c
  + harbour/source/hbpcre/pcretryf.c
  + harbour/source/hbpcre/pcrever.c
  + harbour/source/hbpcre/pcrevutf.c
  + harbour/source/hbpcre/pcrexcls.c
  + harbour/source/hbpcre/ucp.h
  + harbour/source/hbpcre/ucpinter.h
  + harbour/source/hbpcre/ucptable.c
    + added HBPCRE library - based on older xHarbour 6.3 version
      filenames changed to 8.3 DOS format

  * harbour/include/hbregex.h
  * harbour/source/rtl/Makefile
  * harbour/source/rtl/hbregex.c
  + harbour/source/rtl/hbregexc.c
    * divided harbour regular expression functions into two files
      Now regular expression low level library is not linked with
      application until user will not use or REQUEST for one of HB_REGEX*
      functions. It also means that also DBOI_SKIPREGEX will not work when
      regex module is not linked.
    + added support for build-in regular expression library
    + added ulLen parameter to hb_regexMatch() to support strings with
      embedded 0

  * harbour/contrib/bmdbfcdx/bmdbfcdx1.c
  * harbour/source/rdd/dbfcdx/dbfcdx1.c
  * harbour/source/rdd/dbfntx/dbfntx1.c
  * harbour/source/rtl/strmatch.c
    * use new hb_regexMatch() format

  * harbour/utils/hbrun/Makefile
    + added hbpcre to linked library list
This commit is contained in:
Przemyslaw Czerpak
2007-05-31 13:12:34 +00:00
parent ad72a62c95
commit 9087dd18ed
49 changed files with 30821 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
harbour/ChangeLog
View File

@@ -8,6 +8,71 @@
2002-12-01 13:30 UTC+0100 Foo Bar <foo.bar@foobar.org>
*/
2007-05-31 15:10 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
* harbour/common.mak
* harbour/makefile.bc
* harbour/makefile.vc
* harbour/bin/hb-func.sh
* harbour/config/bsd/gcc.cf
* harbour/config/darwin/gcc.cf
* harbour/config/hpux/gcc.cf
* harbour/config/linux/gcc.cf
* harbour/config/sunos/gcc.cf
* harbour/source/Makefile
+ harbour/source/hbpcre/ChangeLog
+ harbour/source/hbpcre/Makefile
+ harbour/source/hbpcre/chartabs.c
+ harbour/source/hbpcre/config.h
+ harbour/source/hbpcre/dftables.c
+ harbour/source/hbpcre/pcre.h
+ harbour/source/hbpcre/pcrecomp.c
+ harbour/source/hbpcre/pcreconf.c
+ harbour/source/hbpcre/pcredfa.c
+ harbour/source/hbpcre/pcreexec.c
+ harbour/source/hbpcre/pcrefind.c
+ harbour/source/hbpcre/pcrefinf.c
+ harbour/source/hbpcre/pcreget.c
+ harbour/source/hbpcre/pcreglob.c
+ harbour/source/hbpcre/pcreinal.h
+ harbour/source/hbpcre/pcreinfo.c
+ harbour/source/hbpcre/pcremktb.c
+ harbour/source/hbpcre/pcreoutf.c
+ harbour/source/hbpcre/pcreprni.c
+ harbour/source/hbpcre/pcrerefc.c
+ harbour/source/hbpcre/pcrestud.c
+ harbour/source/hbpcre/pcretabs.c
+ harbour/source/hbpcre/pcretryf.c
+ harbour/source/hbpcre/pcrever.c
+ harbour/source/hbpcre/pcrevutf.c
+ harbour/source/hbpcre/pcrexcls.c
+ harbour/source/hbpcre/ucp.h
+ harbour/source/hbpcre/ucpinter.h
+ harbour/source/hbpcre/ucptable.c
+ added HBPCRE library - based on older xHarbour 6.3 version
filenames changed to 8.3 DOS format
* harbour/include/hbregex.h
* harbour/source/rtl/Makefile
* harbour/source/rtl/hbregex.c
+ harbour/source/rtl/hbregexc.c
* divided harbour regular expression functions into two files
Now regular expression low level library is not linked with
application until user will not use or REQUEST for one of HB_REGEX*
functions. It also means that also DBOI_SKIPREGEX will not work when
regex module is not linked.
+ added support for build-in regular expression library
+ added ulLen parameter to hb_regexMatch() to support strings with
embedded 0
* harbour/contrib/bmdbfcdx/bmdbfcdx1.c
* harbour/source/rdd/dbfcdx/dbfcdx1.c
* harbour/source/rdd/dbfntx/dbfntx1.c
* harbour/source/rtl/strmatch.c
* use new hb_regexMatch() format
* harbour/utils/hbrun/Makefile
+ added hbpcre to linked library list
2007-05-30 01:35 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
* harbour/source/main/harbour.c
- removed unnecessary code for HB_PARANOID_MEM_CHECK macro

7
harbour/bin/hb-func.sh
View File

@@ -64,7 +64,7 @@ mk_hbgetlibs()
{
if [ -z "$@" ]
then
echo -n "vm pp rtl rdd dbffpt dbfcdx dbfntx hsx hbsix usrrdd ${HB_DB_DRVEXT} macro common lang codepage gtcrs gtsln gtxvt gtxwc gtalleg gtcgi gtstd gtpca gtwin gtwvt gtdos gtos2 debug profiler compiler"
echo -n "vm pp rtl rdd dbffpt dbfcdx dbfntx hsx hbsix usrrdd ${HB_DB_DRVEXT} macro common lang codepage gtcrs gtsln gtxvt gtxwc gtalleg gtcgi gtstd gtpca gtwin gtwvt gtdos gtos2 debug profiler compiler hbpcre"
else
echo -n "$@"
fi
@@ -119,7 +119,10 @@ mk_hbtools()
HB_CRS_LIB=""
HB_SLN_LIB=""
if [ "${C_USR//-DHB_PCRE_REGEX/}" != "${C_USR}" ]; then
HB_SYS_LIBS="-lpcreposix -lpcre ${HB_SYS_LIBS}"
HB_SYS_LIBS="-lpcre ${HB_SYS_LIBS}"
hb_libs="${hb_libs//hbpcre/}"
elif [ "${C_USR//-DHB_POSIX_REGEX/}" = "${C_USR}" ]; then
hb_libs="${hb_libs//hbpcre/}"
fi
if [ "${HB_COMPILER}" = "mingw32" ]; then
HB_SYS_LIBS="${HB_SYS_LIBS} -luser32 -lwinspool -lgdi32 -lcomctl32 -lcomdlg32 -lole32 -loleaut32 -luuid -lwsock32 -lws2_32"

25
harbour/common.mak
View File

@@ -388,6 +388,7 @@ RTL_LIB_OBJS = \
$(OBJ_DIR)\hbinet.obj \
$(OBJ_DIR)\hbrandom.obj \
$(OBJ_DIR)\hbregex.obj \
$(OBJ_DIR)\hbregexc.obj \
$(OBJ_DIR)\hbtoken.obj \
$(OBJ_DIR)\idle.obj \
$(OBJ_DIR)\inkey.obj \
@@ -603,6 +604,29 @@ LANG_LIB_OBJS = \
$(OBJ_DIR)\msgzhb5.obj \
$(OBJ_DIR)\msgzhgb.obj \
#**********************************************************
PCRE_LIB_OBJS = \
$(OBJ_DIR)\chartabs.obj \
$(OBJ_DIR)\pcrecomp.obj \
$(OBJ_DIR)\pcreconf.obj \
$(OBJ_DIR)\pcredfa.obj \
$(OBJ_DIR)\pcreexec.obj \
$(OBJ_DIR)\pcrefinf.obj \
$(OBJ_DIR)\pcreget.obj \
$(OBJ_DIR)\pcreglob.obj \
$(OBJ_DIR)\pcreinfo.obj \
$(OBJ_DIR)\pcremktb.obj \
$(OBJ_DIR)\pcreoutf.obj \
$(OBJ_DIR)\pcreprni.obj \
$(OBJ_DIR)\pcrerefc.obj \
$(OBJ_DIR)\pcrestud.obj \
$(OBJ_DIR)\pcretabs.obj \
$(OBJ_DIR)\pcretryf.obj \
$(OBJ_DIR)\pcrefind.obj \
$(OBJ_DIR)\pcrevutf.obj \
$(OBJ_DIR)\pcrever.obj \
$(OBJ_DIR)\pcrexcls.obj \
#**********************************************************
CODEPAGE_LIB_OBJS = \
@@ -899,6 +923,7 @@ TMP_DLL_OBJS = \
$(DEBUG_LIB_OBJS) \
$(LANG_LIB_OBJS) \
$(CODEPAGE_LIB_OBJS) \
$(PCRE_LIB_OBJS) \
$(RDD_LIB_OBJS) \
$(DBFNTX_LIB_OBJS) \
$(DBFCDX_LIB_OBJS) \

2
harbour/config/bsd/gcc.cf
View File

@@ -82,7 +82,7 @@ endif
endif
ifneq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
LINKLIBS += -lpcreposix -lpcre
LINKLIBS += -lpcre
endif
LINKLIBS += -lm -Wl,--end-group

2
harbour/config/darwin/gcc.cf
View File

@@ -106,7 +106,7 @@ endif
endif
ifneq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
LINKLIBS += -lpcreposix -lpcre
LINKLIBS += -lpcre
endif
LINKLIBS += -lm

2
harbour/config/hpux/gcc.cf
View File

@@ -89,7 +89,7 @@ endif
endif
ifneq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
LINKLIBS += -lpcreposix -lpcre
LINKLIBS += -lpcre
endif
LINKLIBS += -lm -lrt

2
harbour/config/linux/gcc.cf
View File

@@ -102,7 +102,7 @@ endif
endif
ifneq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
LINKLIBS += -lpcreposix -lpcre
LINKLIBS += -lpcre
endif
LINKLIBS += -lm -ldl -Wl,--end-group

2
harbour/config/sunos/gcc.cf
View File

@@ -89,7 +89,7 @@ endif
endif
ifneq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
LINKLIBS += -lpcreposix -lpcre
LINKLIBS += -lpcre
endif
LINKLIBS += -lm -lrt

2
harbour/contrib/bmdbfcdx/bmdbfcdx1.c
View File

@@ -5538,7 +5538,7 @@ static BOOL hb_cdxRegexMatch( CDXAREAP pArea, PHB_REGEX pRegEx, LPCDXKEY pKey )
#else
HB_SYMBOL_UNUSED( pArea );
#endif
return hb_regexMatch( pRegEx, szKey, FALSE );
return hb_regexMatch( pRegEx, szKey, pKey->len, FALSE );
}
/*

68
harbour/include/hbregex.h
View File

@@ -57,47 +57,64 @@
#if defined( _HB_REGEX_INTERNAL_ )
#if defined( __BORLANDC__ )
# if __BORLANDC__ >= 0x550 && !defined( HB_PCRE_REGEX_BCC )
# define HB_PCRE_REGEX_BCC
# endif
#elif ( defined( OS_UNIX_COMPATIBLE ) && !defined( __WATCOMC__ ) ) || \
defined( __DJGPP__ )
# if !defined( HB_POSIX_REGEX ) && !defined( HB_PCRE_REGEX )
# define HB_POSIX_REGEX
# endif
#endif
#if defined( HB_PCRE_REGEX_BCC )
# include <pcre.h>
# include <pcreposi.h>
# if !defined( HB_PCRE_REGEX )
# define HB_PCRE_REGEX
# undef HB_PCRE_REGEX
# if !defined( HB_POSIX_REGEX )
# define HB_POSIX_REGEX
# endif
#elif defined( HB_PCRE_REGEX )
# include <pcre.h>
# include <pcreposix.h>
# undef HB_POSIX_REGEX
#elif defined( HB_POSIX_REGEX )
# include <sys/types.h>
# include <regex.h>
#else
# undef _HB_REGEX_INTERNAL_
# define HB_PCRE_REGEX
# if defined(__XCC__) || defined(__LCC__)
# include "source\hbpcre\pcre.h"
# else
# include "../source/hbpcre/pcre.h"
# endif
#endif
#endif /* _HB_REGEX_INTERNAL_ */
#if defined( _HB_REGEX_INTERNAL_ )
typedef struct
{
regex_t reg;
regmatch_t aMatches[1];
BOOL fFree;
int iCFlags;
int iFlags;
int iEFlags;
#if defined( HB_PCRE_REGEX )
pcre * re_pcre;
#elif defined( HB_POSIX_REGEX )
regex_t reg;
#endif
} HB_REGEX;
typedef HB_REGEX * PHB_REGEX;
#if defined( HB_PCRE_REGEX )
#define HB_REGMATCH int
#define HB_REGMATCH_SIZE( n ) ( ( n + 1 ) * 3 )
#define HB_REGMATCH_SO( p, n ) ( p )[ ( n ) * 2 ]
#define HB_REGMATCH_EO( p, n ) ( p )[ ( n ) * 2 + 1 ]
#elif defined( HB_POSIX_REGEX )
#define HB_REGMATCH regmatch_t
#define HB_REGMATCH_SIZE( n ) ( n )
#define HB_REGMATCH_SO( p, n ) ( p )[ n ].rm_so
#define HB_REGMATCH_EO( p, n ) ( p )[ n ].rm_eo
#else
#define HB_REGMATCH int
#define HB_REGMATCH_SIZE( n ) ( ( n ) * 2 )
#define HB_REGMATCH_SO( p, n ) ( p )[ ( n ) * 2 ]
#define HB_REGMATCH_EO( p, n ) ( p )[ ( n ) * 2 + 1 ]
#endif
typedef void ( * HB_REG_FREE )( PHB_REGEX );
typedef int ( * HB_REG_COMP )( PHB_REGEX, const char * );
typedef int ( * HB_REG_EXEC )( PHB_REGEX, const char *, ULONG, int, HB_REGMATCH * );
extern void hb_regexInit( HB_REG_FREE pFree, HB_REG_COMP pComp, HB_REG_EXEC pExec );
extern HB_GARBAGE_FUNC( hb_regexRelease );
#ifndef REG_EXTENDED
# define REG_EXTENDED 0x00
#endif
@@ -117,6 +134,7 @@ typedef void * PHB_REGEX;
#define HBREG_NOTEOL 0x08
#define HBREG_EXTENDED 0x10
#define HBREG_NOSUB 0x20
#define HBREG_DOTALL 0x40
#ifndef REGEX_MAX_GROUPS
# define REGEX_MAX_GROUPS 16
@@ -124,10 +142,10 @@ typedef void * PHB_REGEX;
HB_EXTERN_BEGIN
extern HB_EXPORT PHB_REGEX hb_regexCompile( const char *szRegEx, ULONG ulLen, int iFlags );
extern HB_EXPORT PHB_REGEX hb_regexCompile( const char * szRegEx, ULONG ulLen, int iFlags );
extern HB_EXPORT PHB_REGEX hb_regexGet( PHB_ITEM pRegExItm, int iFlags );
extern HB_EXPORT void hb_regexFree( PHB_REGEX pRegEx );
extern HB_EXPORT BOOL hb_regexMatch( PHB_REGEX pRegEx, const char *szString, BOOL fFull );
extern HB_EXPORT BOOL hb_regexMatch( PHB_REGEX pRegEx, const char * szString, ULONG UlLen, BOOL fFull );
HB_EXTERN_END

7
harbour/makefile.bc
View File

@@ -354,6 +354,13 @@ $(CODEPAGE_LIB) : $(CODEPAGE_LIB_OBJS)
+)
!
#**********************************************************
$(PCRE_LIB) : $(PCRE_LIB_OBJS)
IF EXIST "$(PCRE_LIB)" $(DEL) "$(PCRE_LIB)" > NUL
$(MKLIB) "$(PCRE_LIB)" $(ARFLAGS) @&&!
+$(**: = &^
+)
!
#**********************************************************
$(RDD_LIB) :: BasicExes
$(RDD_LIB) :: $(RDD_LIB_OBJS)
IF EXIST "$(RDD_LIB)" $(DEL) "$(RDD_LIB)" > NUL

3
harbour/makefile.vc
View File

@@ -754,6 +754,9 @@ $(LANG_LIB) : $(LANG_LIB_OBJS)
$(CODEPAGE_LIB) : $(CODEPAGE_LIB_OBJS)
$(MKLIB) /out:$@ $**
#**********************************************************
$(PCRE_LIB) : $(PCRE_LIB_OBJS)
$(MKLIB) /out:$@ $**
#**********************************************************
$(RDD_LIB) : $(RDD_LIB_OBJS)
$(MKLIB) /out:$@ $**
#**********************************************************

1
harbour/source/Makefile
View File

@@ -34,6 +34,7 @@ DIRS=\
codepage \
lang \
rdd \
hbpcre \
debug \
endif

43
harbour/source/hbpcre/ChangeLog Normal file
View File

@@ -0,0 +1,43 @@
/*
* $Id$
*/
/*
* Harbour Project - http://www.harbour-project.org
* xHarbour Project - http://www.xharbour.org
*
* Please left here information about any modifications to original
* PCRE files. It will make upgrading PCRE library much more easier
* and safer in the future.
*
*
* Use this format for the entry headers:
* YYYY-MM-DD HH:MM UTC[-|+]hhmm Your Full Name <your_email@address>
* For example:
* 2002-12-01 23:12 UTC+0100 Foo Bar <foo.bar@foobar.org>
*
*/
2007-05-31 15:10 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
* initial upload to Harbour CVS
* filenames changed to keep 8.3 DOS format
2006-01-31 22:00 UTC+0100 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
* Makefile
* config.h
* moved SUPPORT_UCP and SUPPORT_UTF8 setting to reduce command line
overhead in DOS builds
2005-09-27 10:50 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
* pcreglob.c
* minor modification to avoid G++ warning messages
2005-09-01 12:30 UTC+0200 Przemyslaw Czerpak (druzus/at/priv.onet.pl)
+ ChangeLog
+ added change log for PCRE files
* pcredfa.c
* removed unused variables: is_repeated, endcode
* chartabs.c
* dftables.c
* add extern declaration for _pcre_default_tables - some C++ compilers
may need it

31
harbour/source/hbpcre/Makefile Normal file
View File

@@ -0,0 +1,31 @@
#
# $Id$
#
ROOT = ../../
C_SOURCES=\
chartabs.c \
pcrecomp.c \
pcreconf.c \
pcredfa.c \
pcreexec.c \
pcrefinf.c \
pcreget.c \
pcreglob.c \
pcreinfo.c \
pcremktb.c \
pcreoutf.c \
pcreprni.c \
pcrerefc.c \
pcrestud.c \
pcretabs.c \
pcretryf.c \
pcrefind.c \
pcrevutf.c \
pcrever.c \
pcrexcls.c \
LIBNAME=hbpcre
include $(TOP)$(ROOT)config/lib.cf

184
harbour/source/hbpcre/chartabs.c Normal file
View File

@@ -0,0 +1,184 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This file is automatically written by the dftables auxiliary
program. If you edit it by hand, you might like to edit the Makefile to
prevent its ever being regenerated.
This file contains the default tables for characters with codes less than
128 (ASCII characters). These tables are used when no external tables are
passed to PCRE. */
extern const unsigned char _pcre_default_tables[];
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 */
0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* 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 chartables.c */

116
harbour/source/hbpcre/config.h Normal file
View File

@@ -0,0 +1,116 @@
/* On Unix systems config.in is converted by configure into config.h. PCRE is
written in Standard C, but there are a few non-standard things it can cope
with, allowing it to run on SunOS4 and other "close to standard" systems.
On a non-Unix system you should just copy this file into config.h, and set up
the macros the way you need them. You should normally change the definitions of
HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way autoconf
works, these cannot be made the defaults. If your system has bcopy() and not
memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE. If your
system has neither bcopy() nor memmove(), leave them both as 0; an emulation
function will be used. */
/* If you are compiling for a system that uses EBCDIC instead of ASCII
character codes, define this macro as 1. On systems that can use "configure",
this can be done via --enable-ebcdic. */
#ifndef EBCDIC
#define EBCDIC 0
#endif
/* If you are compiling for a system that needs some magic to be inserted
before the definition of an exported function, define this macro to contain the
relevant magic. It apears at the start of every exported function. */
#define EXPORT
/* Define to empty if the "const" keyword does not work. */
#undef const
/* Define to "unsigned" if <stddef.h> doesn't define size_t. */
#undef size_t
/* The following two definitions are mainly for the benefit of SunOS4, which
doesn't have the strerror() or memmove() functions that should be present in
all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should
normally be defined with the value 1 for other systems, but unfortunately we
can't make this the default because "configure" files generated by autoconf
will only change 0 to 1; they won't change 1 to 0 if the functions are not
found. */
#define HAVE_STRERROR 1
#define HAVE_MEMMOVE 1
/* There are some non-Unix systems that don't even have bcopy(). If this macro
is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of
HAVE_BCOPY is not relevant. */
#define HAVE_BCOPY 0
/* The value of NEWLINE determines the newline character. The default is to
leave it up to the compiler, but some sites want to force a particular value.
On Unix systems, "configure" can be used to override this default. */
#ifndef NEWLINE
#define NEWLINE '\n'
#endif
/* The value of LINK_SIZE determines the number of bytes used to store
links as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 64K long. This covers the vast majority of cases.
However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows for
longer patterns in extreme cases. On Unix systems, "configure" can be used to
override this default. */
#ifndef LINK_SIZE
#define LINK_SIZE 2
#endif
/* The value of MATCH_LIMIT determines the default number of times the match()
function can be called during a single execution of pcre_exec(). (There is a
runtime method of setting a different limit.) The limit exists in order to
catch runaway regular expressions that take for ever to determine that they do
not match. The default is set very large so that it does not accidentally catch
legitimate cases. On Unix systems, "configure" can be used to override this
default default. */
#ifndef MATCH_LIMIT
#define MATCH_LIMIT 10000000
#endif
/* When calling PCRE via the POSIX interface, additional working storage is
required for holding the pointers to capturing substrings because PCRE requires
three integers per substring, whereas the POSIX interface provides only two. If
the number of expected substrings is small, the wrapper function uses space on
the stack, because this is faster than using malloc() for each call. The
threshold above which the stack is no longer use is defined by POSIX_MALLOC_
THRESHOLD. On Unix systems, "configure" can be used to override this default.
*/
#ifndef POSIX_MALLOC_THRESHOLD
#define POSIX_MALLOC_THRESHOLD 10
#endif
/* PCRE uses recursive function calls to handle backtracking while matching.
This can sometimes be a problem on systems that have stacks of limited size.
Define NO_RECURSE to get a version that doesn't use recursion in the match()
function; instead it creates its own stack by steam using pcre_recurse_malloc
to get memory. For more detail, see comments and other stuff just above the
match() function. On Unix systems, "configure" can be used to set this in the
Makefile (use --disable-stack-for-recursion). */
/* #define NO_RECURSE */
/* xHarbour stuff - default definitions */
#ifndef SUPPORT_UTF8
#define SUPPORT_UTF8
#endif
#ifndef SUPPORT_UCP
#define SUPPORT_UCP
#endif
/* End */

173
harbour/source/hbpcre/dftables.c Normal file
View File

@@ -0,0 +1,173 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2005 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 default
character tables for PCRE. The tables are built according to the default C
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. */
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include "pcreinal.h"
#define DFTABLES /* pcremktb.c notices this */
#include "pcremktb.c"
int main(int argc, char **argv)
{
int i;
FILE *f;
const unsigned char *tables = pcre_maketables();
const unsigned char *base_of_tables = tables;
if (argc != 2)
{
fprintf(stderr, "dftables: one filename argument is required\n");
return 1;
}
f = fopen(argv[1], "wb");
if (f == NULL)
{
fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]);
return 1;
}
/* There are two 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 is automatically written by the dftables auxiliary \n"
"program. If you edit it by hand, you might like to edit the Makefile to \n"
"prevent its ever being regenerated.\n\n");
fprintf(f,
"This file contains the default tables for characters with codes less than\n"
"128 (ASCII characters). These tables are used when no external tables are\n"
"passed to PCRE. */\n\n"
"extern const unsigned char _pcre_default_tables[];\n"
"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 chartabs.c */\n");
fclose(f);
free((void *)base_of_tables);
return 0;
}
/* End of dftables.c */

258
harbour/source/hbpcre/pcre.h Normal file
View File

@@ -0,0 +1,258 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* In its original form, this is the .in file that is transformed by
"configure" into pcre.h.
Copyright (c) 1997-2005 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 file pcre.h is build by "configure". Do not edit it; instead
make changes to pcre.in. */
#define PCRE_MAJOR 6
#define PCRE_MINOR 3
#define PCRE_DATE 15-Aug-2005
/* Win32 uses DLL by default; it needs special stuff for exported functions. */
#ifdef _WIN32
# ifdef PCRE_DEFINITION
# ifdef DLL_EXPORT
# define PCRE_DATA_SCOPE __declspec(dllexport)
# endif
# else
# ifndef PCRE_STATIC
# define PCRE_DATA_SCOPE extern __declspec(dllimport)
# endif
# endif
#endif
/* For other operating systems, we use the standard "extern". */
#ifndef PCRE_DATA_SCOPE
# ifdef __cplusplus
# define PCRE_DATA_SCOPE extern "C"
# else
# define PCRE_DATA_SCOPE extern
# 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
/* 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_NODE (-5)
#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)
/* 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
/* Request types for pcre_config() */
#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
/* Bit flags for the pcre_extra structure */
#define PCRE_EXTRA_STUDY_DATA 0x0001
#define PCRE_EXTRA_MATCH_LIMIT 0x0002
#define PCRE_EXTRA_CALLOUT_DATA 0x0004
#define PCRE_EXTRA_TABLES 0x0008
/* Types */
struct real_pcre; /* declaration; the definition is private */
typedef struct real_pcre pcre;
/* 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 */
} 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 */
const char *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_DATA_SCOPE void *(*pcre_malloc)(size_t);
PCRE_DATA_SCOPE void (*pcre_free)(void *);
PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t);
PCRE_DATA_SCOPE void (*pcre_stack_free)(void *);
PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *);
#else /* VPCOMPAT */
PCRE_DATA_SCOPE void *pcre_malloc(size_t);
PCRE_DATA_SCOPE void pcre_free(void *);
PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t);
PCRE_DATA_SCOPE void pcre_stack_free(void *);
PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *);
#endif /* VPCOMPAT */
/* Exported PCRE functions */
PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *,
const unsigned char *);
PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **,
int *, const unsigned char *);
PCRE_DATA_SCOPE int pcre_config(int, void *);
PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *,
int *, int, const char *, char *, int);
PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *,
int);
PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *,
const char *, int, int, int, int *, int , int *, int);
PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, const char *,
int, int, int, int *, int);
PCRE_DATA_SCOPE void pcre_free_substring(const char *);
PCRE_DATA_SCOPE void pcre_free_substring_list(const char **);
PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int,
void *);
PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *,
int *, int, const char *, const char **);
PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *);
PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int,
const char **);
PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int,
const char ***);
PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *);
PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void);
PCRE_DATA_SCOPE int pcre_refcount(pcre *, int);
PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **);
PCRE_DATA_SCOPE const char *pcre_version(void);
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* End of pcre.h */

5059
harbour/source/hbpcre/pcrecomp.c Normal file
View File

File diff suppressed because it is too large Load Diff

112
harbour/source/hbpcre/pcreconf.c Normal file
View File

@@ -0,0 +1,112 @@
/*************************************************
* 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) 1997-2005 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_config(). */
#include "pcreinal.h"
/*************************************************
* Return info about what features are configured *
*************************************************/
/* This function has an extensible interface so that additional items can be
added compatibly.
Arguments:
what what information is required
where where to put the information
Returns: 0 if data returned, negative on error
*/
EXPORT int
pcre_config(int what, void *where)
{
switch (what)
{
case PCRE_CONFIG_UTF8:
#ifdef SUPPORT_UTF8
*((int *)where) = 1;
#else
*((int *)where) = 0;
#endif
break;
case PCRE_CONFIG_UNICODE_PROPERTIES:
#ifdef SUPPORT_UCP
*((int *)where) = 1;
#else
*((int *)where) = 0;
#endif
break;
case PCRE_CONFIG_NEWLINE:
*((int *)where) = NEWLINE;
break;
case PCRE_CONFIG_LINK_SIZE:
*((int *)where) = LINK_SIZE;
break;
case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD:
*((int *)where) = POSIX_MALLOC_THRESHOLD;
break;
case PCRE_CONFIG_MATCH_LIMIT:
*((unsigned int *)where) = MATCH_LIMIT;
break;
case PCRE_CONFIG_STACKRECURSE:
#ifdef NO_RECURSE
*((int *)where) = 0;
#else
*((int *)where) = 1;
#endif
break;
default: return PCRE_ERROR_BADOPTION;
}
return 0;
}
/* End of pcreconf.c */

1924
harbour/source/hbpcre/pcredfa.c Normal file
View File

File diff suppressed because it is too large Load Diff

3632
harbour/source/hbpcre/pcreexec.c Normal file
View File

File diff suppressed because it is too large Load Diff

161
harbour/source/hbpcre/pcrefind.c Normal file
View File

@@ -0,0 +1,161 @@
/*************************************************
* libucp - Unicode Property Table handler *
*************************************************/
/* Copyright (c) University of Cambridge 2004 */
/* This little library provides a fast way of obtaining the basic Unicode
properties of a character, using a compact binary tree that occupies less than
100K bytes.
-----------------------------------------------------------------------------
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.
-----------------------------------------------------------------------------
*/
#include "pcreinal.h"
#include "ucp.h" /* Exported interface */
#include "ucpinter.h" /* Internal table details */
#include "ucptable.c" /* The table itself */
/* In some environments, external functions have to be preceded by some magic.
In my world (Unix), they do not. Use a macro to deal with this. */
#ifndef EXPORT
#define EXPORT
#endif
/*************************************************
* Search table and return data *
*************************************************/
/* Two values are returned: the category is ucp_C, ucp_L, etc. The detailed
character type is ucp_Lu, ucp_Nd, etc.
Arguments:
c the character value
type_ptr the detailed character type is returned here
case_ptr for letters, the opposite case is returned here, if there
is one, else zero
Returns: the character type category or -1 if not found
*/
EXPORT int
ucp_findchar(const int c, int *type_ptr, int *case_ptr)
{
cnode *node = ucp_table;
register int cc = c;
int case_offset;
for (;;)
{
register int d = node->f1 | ((node->f0 & f0_chhmask) << 16);
if (cc == d) break;
if (cc < d)
{
if ((node->f0 & f0_leftexists) == 0) return -1;
node ++;
}
else
{
register int roffset = (node->f2 & f2_rightmask) >> f2_rightshift;
if (roffset == 0) return -1;
node += 1 << (roffset - 1);
}
}
switch ((*type_ptr = ((node->f0 & f0_typemask) >> f0_typeshift)))
{
case ucp_Cc:
case ucp_Cf:
case ucp_Cn:
case ucp_Co:
case ucp_Cs:
return ucp_C;
break;
case ucp_Ll:
case ucp_Lu:
case_offset = node->f2 & f2_casemask;
if ((case_offset & 0x0100) != 0) case_offset |= 0xfffff000;
*case_ptr = (case_offset == 0)? 0 : cc + case_offset;
return ucp_L;
case ucp_Lm:
case ucp_Lo:
case ucp_Lt:
*case_ptr = 0;
return ucp_L;
break;
case ucp_Mc:
case ucp_Me:
case ucp_Mn:
return ucp_M;
break;
case ucp_Nd:
case ucp_Nl:
case ucp_No:
return ucp_N;
break;
case ucp_Pc:
case ucp_Pd:
case ucp_Pe:
case ucp_Pf:
case ucp_Pi:
case ucp_Ps:
case ucp_Po:
return ucp_P;
break;
case ucp_Sc:
case ucp_Sk:
case ucp_Sm:
case ucp_So:
return ucp_S;
break;
case ucp_Zl:
case ucp_Zp:
case ucp_Zs:
return ucp_Z;
break;
default: /* "Should never happen" */
return -1;
break;
}
}
/* End of pcrefind.c */

149
harbour/source/hbpcre/pcrefinf.c Normal file
View File

@@ -0,0 +1,149 @@
/*************************************************
* 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) 1997-2005 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_fullinfo(), which returns
information about a compiled pattern. */
#include "pcreinal.h"
/*************************************************
* Return info about compiled pattern *
*************************************************/
/* This is a newer "info" function which has an extensible interface so
that additional items can be added compatibly.
Arguments:
argument_re points to compiled code
extra_data points extra data, or NULL
what what information is required
where where to put the information
Returns: 0 if data returned, negative on error
*/
EXPORT int
pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what,
void *where)
{
real_pcre internal_re;
pcre_study_data internal_study;
const real_pcre *re = (const real_pcre *)argument_re;
const pcre_study_data *study = NULL;
if (re == NULL || where == NULL) return PCRE_ERROR_NULL;
if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0)
study = (const pcre_study_data *)extra_data->study_data;
if (re->magic_number != MAGIC_NUMBER)
{
re = _pcre_try_flipped(re, &internal_re, study, &internal_study);
if (re == NULL) return PCRE_ERROR_BADMAGIC;
if (study != NULL) study = &internal_study;
}
switch (what)
{
case PCRE_INFO_OPTIONS:
*((unsigned long int *)where) = re->options & PUBLIC_OPTIONS;
break;
case PCRE_INFO_SIZE:
*((size_t *)where) = re->size;
break;
case PCRE_INFO_STUDYSIZE:
*((size_t *)where) = (study == NULL)? 0 : study->size;
break;
case PCRE_INFO_CAPTURECOUNT:
*((int *)where) = re->top_bracket;
break;
case PCRE_INFO_BACKREFMAX:
*((int *)where) = re->top_backref;
break;
case PCRE_INFO_FIRSTBYTE:
*((int *)where) =
((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
break;
/* Make sure we pass back the pointer to the bit vector in the external
block, not the internal copy (with flipped integer fields). */
case PCRE_INFO_FIRSTTABLE:
*((const uschar **)where) =
(study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)?
((const pcre_study_data *)extra_data->study_data)->start_bits : NULL;
break;
case PCRE_INFO_LASTLITERAL:
*((int *)where) =
((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1;
break;
case PCRE_INFO_NAMEENTRYSIZE:
*((int *)where) = re->name_entry_size;
break;
case PCRE_INFO_NAMECOUNT:
*((int *)where) = re->name_count;
break;
case PCRE_INFO_NAMETABLE:
*((const uschar **)where) = (const uschar *)re + re->name_table_offset;
break;
case PCRE_INFO_DEFAULT_TABLES:
*((const uschar **)where) = (const uschar *)(_pcre_default_tables);
break;
default: return PCRE_ERROR_BADOPTION;
}
return 0;
}
/* End of pcrefinf.c */

352
harbour/source/hbpcre/pcreget.c Normal file
View File

@@ -0,0 +1,352 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains some convenience functions for extracting substrings
from the subject string after a regex match has succeeded. The original idea
for these functions came from Scott Wimer. */
#include "pcreinal.h"
/*************************************************
* Find number for named string *
*************************************************/
/* This function is used by the two extraction functions below, as well
as being generally available.
Arguments:
code the compiled regex
stringname the name whose number is required
Returns: the number of the named parentheses, or a negative number
(PCRE_ERROR_NOSUBSTRING) if not found
*/
int
pcre_get_stringnumber(const pcre *code, const char *stringname)
{
int rc;
int entrysize;
int top, bot;
uschar *nametable;
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
return rc;
if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
return rc;
if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
return rc;
bot = 0;
while (top > bot)
{
int mid = (top + bot) / 2;
uschar *entry = nametable + entrysize*mid;
int c = strcmp(stringname, (char *)(entry + 2));
if (c == 0) return (entry[0] << 8) + entry[1];
if (c > 0) bot = mid + 1; else top = mid;
}
return PCRE_ERROR_NOSUBSTRING;
}
/*************************************************
* Copy captured string to given buffer *
*************************************************/
/* This function copies a single captured substring into a given buffer.
Note that we use memcpy() rather than strncpy() in case there are binary zeros
in the string.
Arguments:
subject the subject string that was matched
ovector pointer to the offsets table
stringcount the number of substrings that were captured
(i.e. the yield of the pcre_exec call, unless
that was zero, in which case it should be 1/3
of the offset table size)
stringnumber the number of the required substring
buffer where to put the substring
size the size of the buffer
Returns: if successful:
the length of the copied string, not including the zero
that is put on the end; can be zero
if not successful:
PCRE_ERROR_NOMEMORY (-6) buffer too small
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
*/
int
pcre_copy_substring(const char *subject, int *ovector, int stringcount,
int stringnumber, char *buffer, int size)
{
int yield;
if (stringnumber < 0 || stringnumber >= stringcount)
return PCRE_ERROR_NOSUBSTRING;
stringnumber *= 2;
yield = ovector[stringnumber+1] - ovector[stringnumber];
if (size < yield + 1) return PCRE_ERROR_NOMEMORY;
memcpy(buffer, subject + ovector[stringnumber], yield);
buffer[yield] = 0;
return yield;
}
/*************************************************
* Copy named captured string to given buffer *
*************************************************/
/* This function copies a single captured substring into a given buffer,
identifying it by name.
Arguments:
code the compiled regex
subject the subject string that was matched
ovector pointer to the offsets table
stringcount the number of substrings that were captured
(i.e. the yield of the pcre_exec call, unless
that was zero, in which case it should be 1/3
of the offset table size)
stringname the name of the required substring
buffer where to put the substring
size the size of the buffer
Returns: if successful:
the length of the copied string, not including the zero
that is put on the end; can be zero
if not successful:
PCRE_ERROR_NOMEMORY (-6) buffer too small
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
*/
int
pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector,
int stringcount, const char *stringname, char *buffer, int size)
{
int n = pcre_get_stringnumber(code, stringname);
if (n <= 0) return n;
return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size);
}
/*************************************************
* Copy all captured strings to new store *
*************************************************/
/* This function gets one chunk of store and builds a list of pointers and all
of the captured substrings in it. A NULL pointer is put on the end of the list.
Arguments:
subject the subject string that was matched
ovector pointer to the offsets table
stringcount the number of substrings that were captured
(i.e. the yield of the pcre_exec call, unless
that was zero, in which case it should be 1/3
of the offset table size)
listptr set to point to the list of pointers
Returns: if successful: 0
if not successful:
PCRE_ERROR_NOMEMORY (-6) failed to get store
*/
int
pcre_get_substring_list(const char *subject, int *ovector, int stringcount,
const char ***listptr)
{
int i;
int size = sizeof(char *);
int double_count = stringcount * 2;
char **stringlist;
char *p;
for (i = 0; i < double_count; i += 2)
size += sizeof(char *) + ovector[i+1] - ovector[i] + 1;
stringlist = (char **)(pcre_malloc)(size);
if (stringlist == NULL) return PCRE_ERROR_NOMEMORY;
*listptr = (const char **)stringlist;
p = (char *)(stringlist + stringcount + 1);
for (i = 0; i < double_count; i += 2)
{
int len = ovector[i+1] - ovector[i];
memcpy(p, subject + ovector[i], len);
*stringlist++ = p;
p += len;
*p++ = 0;
}
*stringlist = NULL;
return 0;
}
/*************************************************
* Free store obtained by get_substring_list *
*************************************************/
/* This function exists for the benefit of people calling PCRE from non-C
programs that can call its functions, but not free() or (pcre_free)() directly.
Argument: the result of a previous pcre_get_substring_list()
Returns: nothing
*/
void
pcre_free_substring_list(const char **pointer)
{
(pcre_free)((void *)pointer);
}
/*************************************************
* Copy captured string to new store *
*************************************************/
/* This function copies a single captured substring into a piece of new
store
Arguments:
subject the subject string that was matched
ovector pointer to the offsets table
stringcount the number of substrings that were captured
(i.e. the yield of the pcre_exec call, unless
that was zero, in which case it should be 1/3
of the offset table size)
stringnumber the number of the required substring
stringptr where to put a pointer to the substring
Returns: if successful:
the length of the string, not including the zero that
is put on the end; can be zero
if not successful:
PCRE_ERROR_NOMEMORY (-6) failed to get store
PCRE_ERROR_NOSUBSTRING (-7) substring not present
*/
int
pcre_get_substring(const char *subject, int *ovector, int stringcount,
int stringnumber, const char **stringptr)
{
int yield;
char *substring;
if (stringnumber < 0 || stringnumber >= stringcount)
return PCRE_ERROR_NOSUBSTRING;
stringnumber *= 2;
yield = ovector[stringnumber+1] - ovector[stringnumber];
substring = (char *)(pcre_malloc)(yield + 1);
if (substring == NULL) return PCRE_ERROR_NOMEMORY;
memcpy(substring, subject + ovector[stringnumber], yield);
substring[yield] = 0;
*stringptr = substring;
return yield;
}
/*************************************************
* Copy named captured string to new store *
*************************************************/
/* This function copies a single captured substring, identified by name, into
new store.
Arguments:
code the compiled regex
subject the subject string that was matched
ovector pointer to the offsets table
stringcount the number of substrings that were captured
(i.e. the yield of the pcre_exec call, unless
that was zero, in which case it should be 1/3
of the offset table size)
stringname the name of the required substring
stringptr where to put the pointer
Returns: if successful:
the length of the copied string, not including the zero
that is put on the end; can be zero
if not successful:
PCRE_ERROR_NOMEMORY (-6) couldn't get memory
PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
*/
int
pcre_get_named_substring(const pcre *code, const char *subject, int *ovector,
int stringcount, const char *stringname, const char **stringptr)
{
int n = pcre_get_stringnumber(code, stringname);
if (n <= 0) return n;
return pcre_get_substring(subject, ovector, stringcount, n, stringptr);
}
/*************************************************
* Free store obtained by get_substring *
*************************************************/
/* This function exists for the benefit of people calling PCRE from non-C
programs that can call its functions, but not free() or (pcre_free)() directly.
Argument: the result of a previous pcre_get_substring()
Returns: nothing
*/
void
pcre_free_substring(const char *pointer)
{
(pcre_free)((void *)pointer);
}
/* End of pcreget.c */

72
harbour/source/hbpcre/pcreglob.c Normal file
View File

@@ -0,0 +1,72 @@
/*************************************************
* 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) 1997-2005 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 global variables that are exported by the PCRE library.
PCRE is thread-clean and doesn't use any global variables in the normal sense.
However, it calls memory allocation and freeing functions via the four
indirections below, and it can optionally do callouts, using the fifth
indirection. These values can be changed by the caller, but are shared between
all threads. However, when compiling for Virtual Pascal, things are done
differently, and global variables are not used (see pcre.in). */
#include "pcreinal.h"
#ifndef VPCOMPAT
#ifdef __cplusplus
extern "C"
{
void *(*pcre_malloc)(size_t) = malloc;
void (*pcre_free)(void *) = free;
void *(*pcre_stack_malloc)(size_t) = malloc;
void (*pcre_stack_free)(void *) = free;
int (*pcre_callout)(pcre_callout_block *) = NULL;
}
#else
void *(*pcre_malloc)(size_t) = malloc;
void (*pcre_free)(void *) = free;
void *(*pcre_stack_malloc)(size_t) = malloc;
void (*pcre_stack_free)(void *) = free;
int (*pcre_callout)(pcre_callout_block *) = NULL;
#endif
#endif
/* End of pcreglob.c */

912
harbour/source/hbpcre/pcreinal.h Normal file
View File

@@ -0,0 +1,912 @@
/*************************************************
* 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) 1997-2005 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 header contains definitions that are shared between the different
modules, but which are not relevant to the exported API. This includes some
functions whose names all begin with "_pcre_". */
/* Define DEBUG to get debugging output on stdout. */
/****
#define DEBUG
****/
/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef
inline, and there are *still* stupid compilers about that don't like indented
pre-processor statements, or at least there were when I first wrote this. After
all, it had only been about 10 years then... */
#ifdef DEBUG
#define DPRINTF(p) printf p
#else
#define DPRINTF(p) /*nothing*/
#endif
/* Get the definitions provided by running "configure" */
#include "config.h"
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
#include <ctype.h>
#include <limits.h>
#include <setjmp.h>
#include <stdarg.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#ifndef PCRE_SPY
#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */
#endif
/* We need to have types that specify unsigned 16-bit and 32-bit integers. We
cannot determine these outside the compilation (e.g. by running a program as
part of "configure") because PCRE is often cross-compiled for use on other
systems. Instead we make use of the maximum sizes that are available at
preprocessor time in standard C environments. */
#if USHRT_MAX == 65535
typedef unsigned short pcre_uint16;
#elif UINT_MAX == 65535
typedef unsigned int pcre_uint16;
#else
#error Cannot determine a type for 16-bit unsigned integers
#endif
#if UINT_MAX == 4294967295
typedef unsigned int pcre_uint32;
#elif ULONG_MAX == 4294967295
typedef unsigned long int pcre_uint32;
#else
#error Cannot determine a type for 32-bit unsigned integers
#endif
/* All character handling must be done as unsigned characters. Otherwise there
are problems with top-bit-set characters and functions such as isspace().
However, we leave the interface to the outside world as char *, because that
should make things easier for callers. We define a short type for unsigned char
to save lots of typing. I tried "uchar", but it causes problems on Digital
Unix, where it is defined in sys/types, so use "uschar" instead. */
typedef unsigned char uschar;
/* Include the public PCRE header */
#include "pcre.h"
/* Include the (copy of) the public ucp header, changing the external name into
a private one. This does no harm, even if we aren't compiling UCP support. */
#define ucp_findchar _pcre_ucp_findchar
#include "ucp.h"
/* When compiling for use with the Virtual Pascal compiler, these functions
need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
option on the command line. */
#ifdef VPCOMPAT
#define strncmp(s1,s2,m) _strncmp(s1,s2,m)
#define memcpy(d,s,n) _memcpy(d,s,n)
#define memmove(d,s,n) _memmove(d,s,n)
#define memset(s,c,n) _memset(s,c,n)
#else /* VPCOMPAT */
/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
is set. Otherwise, include an emulating function for those systems that have
neither (there some non-Unix environments where this is the case). This assumes
that all calls to memmove are moving strings upwards in store, which is the
case in PCRE. */
#if ! HAVE_MEMMOVE
#undef memmove /* some systems may have a macro */
#if HAVE_BCOPY
#define memmove(a, b, c) bcopy(b, a, c)
#else /* HAVE_BCOPY */
void *
pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n)
{
int i;
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
}
#define memmove(a, b, c) pcre_memmove(a, b, c)
#endif /* not HAVE_BCOPY */
#endif /* not HAVE_MEMMOVE */
#endif /* not VPCOMPAT */
/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored
in big-endian order) by default. These are used, for example, to link from the
start of a subpattern to its alternatives and its end. The use of 2 bytes per
offset limits the size of the compiled regex to around 64K, which is big enough
for almost everybody. However, I received a request for an even bigger limit.
For this reason, and also to make the code easier to maintain, the storing and
loading of offsets from the byte string is now handled by the macros that are
defined here.
The macros are controlled by the value of LINK_SIZE. This defaults to 2 in
the config.h file, but can be overridden by using -D on the command line. This
is automated on Unix systems via the "configure" command. */
#if LINK_SIZE == 2
#define PUT(a,n,d) \
(a[n] = (d) >> 8), \
(a[(n)+1] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 8) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3
#define PUT(a,n,d) \
(a[n] = (d) >> 16), \
(a[(n)+1] = (d) >> 8), \
(a[(n)+2] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
#define MAX_PATTERN_SIZE (1 << 24)
#elif LINK_SIZE == 4
#define PUT(a,n,d) \
(a[n] = (d) >> 24), \
(a[(n)+1] = (d) >> 16), \
(a[(n)+2] = (d) >> 8), \
(a[(n)+3] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be either 2, 3, or 4
#endif
/* Convenience macro defined in terms of the others */
#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE
/* PCRE uses some other 2-byte quantities that do not change when the size of
offsets changes. There are used for repeat counts and for other things such as
capturing parenthesis numbers in back references. */
#define PUT2(a,n,d) \
a[n] = (d) >> 8; \
a[(n)+1] = (d) & 255
#define GET2(a,n) \
(((a)[n] << 8) | (a)[(n)+1])
#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2
/* When UTF-8 encoding is being used, a character is no longer just a single
byte. The macros for character handling generate simple sequences when used in
byte-mode, and more complicated ones for UTF-8 characters. */
#ifndef SUPPORT_UTF8
#define GETCHAR(c, eptr) c = *eptr;
#define GETCHARTEST(c, eptr) c = *eptr;
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
#define BACKCHAR(eptr)
#else /* SUPPORT_UTF8 */
/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if ((c & 0xc0) == 0xc0) \
{ \
int gcii; \
int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \
int gcss = 6*gcaa; \
c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
for (gcii = 1; gcii <= gcaa; gcii++) \
{ \
gcss -= 6; \
c |= (eptr[gcii] & 0x3f) << gcss; \
} \
}
/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf8 && (c & 0xc0) == 0xc0) \
{ \
int gcii; \
int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \
int gcss = 6*gcaa; \
c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
for (gcii = 1; gcii <= gcaa; gcii++) \
{ \
gcss -= 6; \
c |= (eptr[gcii] & 0x3f) << gcss; \
} \
}
/* Get the next UTF-8 character, advancing the pointer. This is called when we
know we are in UTF-8 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if ((c & 0xc0) == 0xc0) \
{ \
int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \
int gcss = 6*gcaa; \
c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
while (gcaa-- > 0) \
{ \
gcss -= 6; \
c |= (*eptr++ & 0x3f) << gcss; \
} \
}
/* Get the next character, testing for UTF-8 mode, and advancing the pointer */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf8 && (c & 0xc0) == 0xc0) \
{ \
int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \
int gcss = 6*gcaa; \
c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
while (gcaa-- > 0) \
{ \
gcss -= 6; \
c |= (*eptr++ & 0x3f) << gcss; \
} \
}
/* Get the next UTF-8 character, not advancing the pointer, incrementing length
if there are extra bytes. This is called when we know we are in UTF-8 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if ((c & 0xc0) == 0xc0) \
{ \
int gcii; \
int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \
int gcss = 6*gcaa; \
c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
for (gcii = 1; gcii <= gcaa; gcii++) \
{ \
gcss -= 6; \
c |= (eptr[gcii] & 0x3f) << gcss; \
} \
len += gcaa; \
}
/* If the pointer is not at the start of a character, move it back until
it is. Called only in UTF-8 mode. */
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--;
#endif
/* In case there is no definition of offsetof() provided - though any proper
Standard C system should have one. */
#ifndef offsetof
#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
#endif
/* These are the public options that can change during matching. */
#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
/* Private options flags start at the most significant end of the four bytes,
but skip the top bit so we can use ints for convenience without getting tangled
with negative values. The public options defined in pcre.h start at the least
significant end. Make sure they don't overlap! */
#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */
#define PCRE_REQCHSET 0x20000000 /* req_byte is set */
#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */
#define PCRE_ICHANGED 0x08000000 /* i option changes within regex */
#define PCRE_NOPARTIAL 0x04000000 /* can't use partial with this regex */
/* Options for the "extra" block produced by pcre_study(). */
#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */
/* Masks for identifying the public options that are permitted at compile
time, run time, or study time, respectively. */
#define PUBLIC_OPTIONS \
(PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE)
#define PUBLIC_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
PCRE_PARTIAL)
#define PUBLIC_DFA_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART)
#define PUBLIC_STUDY_OPTIONS 0 /* None defined */
/* Magic number to provide a small check against being handed junk. Also used
to detect whether a pattern was compiled on a host of different endianness. */
#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */
/* Negative values for the firstchar and reqchar variables */
#define REQ_UNSET (-2)
#define REQ_NONE (-1)
/* The maximum remaining length of subject we are prepared to search for a
req_byte match. */
#define REQ_BYTE_MAX 1000
/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a
variable-length repeat, or a anything other than literal characters. */
#define REQ_CASELESS 0x0100 /* indicates caselessness */
#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */
/* Miscellaneous definitions */
/* 30/08/2005 - <maurilio.longo@libero.it>
Use xharbour typedefs if they exist, ie, this file
has been included after xharbour ones
*/
#ifndef FALSE
typedef int BOOL;
#define FALSE 0
#define TRUE 1
#endif
/* Escape items that are just an encoding of a particular data value. Note that
ESC_n is defined as yet another macro, which is set in config.h to either \n
(the default) or \r (which some people want). */
#ifndef ESC_e
#define ESC_e 27
#endif
#ifndef ESC_f
#define ESC_f '\f'
#endif
#ifndef ESC_n
#define ESC_n NEWLINE
#endif
#ifndef ESC_r
#define ESC_r '\r'
#endif
/* We can't officially use ESC_t because it is a POSIX reserved identifier
(presumably because of all the others like size_t). */
#ifndef ESC_tee
#define ESC_tee '\t'
#endif
/* These are escaped items that aren't just an encoding of a particular data
value such as \n. They must have non-zero values, as check_escape() returns
their negation. Also, they must appear in the same order as in the opcode
definitions below, up to ESC_z. There's a dummy for OP_ANY because it
corresponds to "." rather than an escape sequence. The final one must be
ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two
tests in the code for an escape greater than ESC_b and less than ESC_Z to
detect the types that may be repeated. These are the types that consume
characters. If any new escapes are put in between that don't consume a
character, that code will have to change. */
enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W,
ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E,
ESC_Q, ESC_REF };
/* Flag bits and data types for the extended class (OP_XCLASS) for classes that
contain UTF-8 characters with values greater than 255. */
#define XCL_NOT 0x01 /* Flag: this is a negative class */
#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */
#define XCL_END 0 /* Marks end of individual items */
#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */
#define XCL_RANGE 2 /* A range (two multibyte chars) follows */
#define XCL_PROP 3 /* Unicode property (one property code) follows */
#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */
/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets
that extract substrings. Starting from 1 (i.e. after OP_END), the values up to
OP_EOD must correspond in order to the list of escapes immediately above.
Note that whenever this list is updated, the two macro definitions that follow
must also be updated to match. */
enum {
OP_END, /* 0 End of pattern */
/* Values corresponding to backslashed metacharacters */
OP_SOD, /* 1 Start of data: \A */
OP_SOM, /* 2 Start of match (subject + offset): \G */
OP_NOT_WORD_BOUNDARY, /* 3 \B */
OP_WORD_BOUNDARY, /* 4 \b */
OP_NOT_DIGIT, /* 5 \D */
OP_DIGIT, /* 6 \d */
OP_NOT_WHITESPACE, /* 7 \S */
OP_WHITESPACE, /* 8 \s */
OP_NOT_WORDCHAR, /* 9 \W */
OP_WORDCHAR, /* 10 \w */
OP_ANY, /* 11 Match any character */
OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */
OP_NOTPROP, /* 13 \P (not Unicode property) */
OP_PROP, /* 14 \p (Unicode property) */
OP_EXTUNI, /* 15 \X (extended Unicode sequence */
OP_EODN, /* 16 End of data or \n at end of data: \Z. */
OP_EOD, /* 17 End of data: \z */
OP_OPT, /* 18 Set runtime options */
OP_CIRC, /* 19 Start of line - varies with multiline switch */
OP_DOLL, /* 20 End of line - varies with multiline switch */
OP_CHAR, /* 21 Match one character, casefully */
OP_CHARNC, /* 22 Match one character, caselessly */
OP_NOT, /* 23 Match anything but the following char */
OP_STAR, /* 24 The maximizing and minimizing versions of */
OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */
OP_PLUS, /* 26 the minimizing one second. */
OP_MINPLUS, /* 27 This first set applies to single characters */
OP_QUERY, /* 28 */
OP_MINQUERY, /* 29 */
OP_UPTO, /* 30 From 0 to n matches */
OP_MINUPTO, /* 31 */
OP_EXACT, /* 32 Exactly n matches */
OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */
OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */
OP_NOTPLUS, /* 35 the minimizing one second. */
OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */
OP_NOTQUERY, /* 37 */
OP_NOTMINQUERY, /* 38 */
OP_NOTUPTO, /* 39 From 0 to n matches */
OP_NOTMINUPTO, /* 40 */
OP_NOTEXACT, /* 41 Exactly n matches */
OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */
OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */
OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */
OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */
OP_TYPEQUERY, /* 46 This set applies to character types such as \d */
OP_TYPEMINQUERY, /* 47 */
OP_TYPEUPTO, /* 48 From 0 to n matches */
OP_TYPEMINUPTO, /* 49 */
OP_TYPEEXACT, /* 50 Exactly n matches */
OP_CRSTAR, /* 51 The maximizing and minimizing versions of */
OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */
OP_CRPLUS, /* 53 the minimizing one second. These codes must */
OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */
OP_CRQUERY, /* 55 These are for character classes and back refs */
OP_CRMINQUERY, /* 56 */
OP_CRRANGE, /* 57 These are different to the three sets above. */
OP_CRMINRANGE, /* 58 */
OP_CLASS, /* 59 Match a character class, chars < 256 only */
OP_NCLASS, /* 60 Same, but the bitmap was created from a negative
class - the difference is relevant only when a UTF-8
character > 255 is encountered. */
OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the
class. This does both positive and negative. */
OP_REF, /* 62 Match a back reference */
OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */
OP_CALLOUT, /* 64 Call out to external function if provided */
OP_ALT, /* 65 Start of alternation */
OP_KET, /* 66 End of group that doesn't have an unbounded repeat */
OP_KETRMAX, /* 67 These two must remain together and in this */
OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */
/* The assertions must come before ONCE and COND */
OP_ASSERT, /* 69 Positive lookahead */
OP_ASSERT_NOT, /* 70 Negative lookahead */
OP_ASSERTBACK, /* 71 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */
OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */
/* ONCE and COND must come after the assertions, with ONCE first, as there's
a test for >= ONCE for a subpattern that isn't an assertion. */
OP_ONCE, /* 74 Once matched, don't back up into the subpattern */
OP_COND, /* 75 Conditional group */
OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */
OP_BRAZERO, /* 77 These two must remain together and in this */
OP_BRAMINZERO, /* 78 order. */
OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater
than can fit into an opcode. */
OP_BRA /* 80 This and greater values are used for brackets that
extract substrings up to EXTRACT_BASIC_MAX. After
that, use is made of OP_BRANUMBER. */
};
/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and
study.c that all opcodes are less than 128 in value. This makes handling UTF-8
character sequences easier. */
/* The highest extraction number before we have to start using additional
bytes. (Originally PCRE didn't have support for extraction counts highter than
this number.) The value is limited by the number of opcodes left after OP_BRA,
i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional
opcodes. */
#define EXTRACT_BASIC_MAX 100
/* This macro defines textual names for all the opcodes. These are used only
for debugging. The macro is referenced only in pcreprni.c. */
#define OP_NAME_LIST \
"End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \
"\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \
"notprop", "prop", "extuni", \
"\\Z", "\\z", \
"Opt", "^", "$", "char", "charnc", "not", \
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
"*", "*?", "+", "+?", "?", "??", "{", "{", \
"class", "nclass", "xclass", "Ref", "Recurse", "Callout", \
"Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \
"AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\
"Brazero", "Braminzero", "Branumber", "Bra"
/* This macro defines the length of fixed length operations in the compiled
regex. The lengths are used when searching for specific things, and also in the
debugging printing of a compiled regex. We use a macro so that it can be
defined close to the definitions of the opcodes themselves.
As things have been extended, some of these are no longer fixed lenths, but are
minima instead. For example, the length of a single-character repeat may vary
in UTF-8 mode. The code that uses this table must know about such things. */
#define OP_LENGTHS \
1, /* End */ \
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \
1, 1, /* Any, Anybyte */ \
2, 2, 1, /* NOTPROP, PROP, EXTUNI */ \
1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \
2, /* Char - the minimum length */ \
2, /* Charnc - the minimum length */ \
2, /* not */ \
/* Positive single-char repeats ** These are */ \
2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \
4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \
/* Negative single-char repeats - only for chars < 256 */ \
2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \
4, 4, 4, /* NOT upto, minupto, exact */ \
/* Positive type repeats */ \
2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \
4, 4, 4, /* Type upto, minupto, exact */ \
/* Character class & ref repeats */ \
1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \
5, 5, /* CRRANGE, CRMINRANGE */ \
33, /* CLASS */ \
33, /* NCLASS */ \
0, /* XCLASS - variable length */ \
3, /* REF */ \
1+LINK_SIZE, /* RECURSE */ \
2+2*LINK_SIZE, /* CALLOUT */ \
1+LINK_SIZE, /* Alt */ \
1+LINK_SIZE, /* Ket */ \
1+LINK_SIZE, /* KetRmax */ \
1+LINK_SIZE, /* KetRmin */ \
1+LINK_SIZE, /* Assert */ \
1+LINK_SIZE, /* Assert not */ \
1+LINK_SIZE, /* Assert behind */ \
1+LINK_SIZE, /* Assert behind not */ \
1+LINK_SIZE, /* Reverse */ \
1+LINK_SIZE, /* Once */ \
1+LINK_SIZE, /* COND */ \
3, /* CREF */ \
1, 1, /* BRAZERO, BRAMINZERO */ \
3, /* BRANUMBER */ \
1+LINK_SIZE /* BRA */ \
/* A magic value for OP_CREF to indicate the "in recursion" condition. */
#define CREF_RECURSE 0xffff
/* Error code numbers. They are given names so that they can more easily be
tracked. */
enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9,
ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19,
ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29,
ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47 };
/* The real format of the start of the pcre block; the index of names and the
code vector run on as long as necessary after the end. We store an explicit
offset to the name table so that if a regex is compiled on one host, saved, and
then run on another where the size of pointers is different, all might still
be well. For the case of compiled-on-4 and run-on-8, we include an extra
pointer that is always NULL. For future-proofing, a few dummy fields were
originally included - even though you can never get this planning right - but
there is only one left now.
NOTE NOTE NOTE:
Because people can now save and re-use compiled patterns, any additions to this
structure should be made at the end, and something earlier (e.g. a new
flag in the options or one of the dummy fields) should indicate that the new
fields are present. Currently PCRE always sets the dummy fields to zero.
NOTE NOTE NOTE:
*/
typedef struct real_pcre {
pcre_uint32 magic_number;
pcre_uint32 size; /* Total that was malloced */
pcre_uint32 options;
pcre_uint32 dummy1; /* For future use, maybe */
pcre_uint16 top_bracket;
pcre_uint16 top_backref;
pcre_uint16 first_byte;
pcre_uint16 req_byte;
pcre_uint16 name_table_offset; /* Offset to name table that follows */
pcre_uint16 name_entry_size; /* Size of any name items */
pcre_uint16 name_count; /* Number of name items */
pcre_uint16 ref_count; /* Reference count */
const unsigned char *tables; /* Pointer to tables or NULL for std */
const unsigned char *nullpad; /* NULL padding */
} real_pcre;
/* The format of the block used to store data from pcre_study(). The same
remark (see NOTE above) about extending this structure applies. */
typedef struct pcre_study_data {
pcre_uint32 size; /* Total that was malloced */
pcre_uint32 options;
uschar start_bits[32];
} pcre_study_data;
/* Structure for passing "static" information around between the functions
doing the compiling, so that they are thread-safe. */
typedef struct compile_data {
const uschar *lcc; /* Points to lower casing table */
const uschar *fcc; /* Points to case-flipping table */
const uschar *cbits; /* Points to character type table */
const uschar *ctypes; /* Points to table of type maps */
const uschar *start_code; /* The start of the compiled code */
const uschar *start_pattern; /* The start of the pattern */
uschar *name_table; /* The name/number table */
int names_found; /* Number of entries so far */
int name_entry_size; /* Size of each entry */
int top_backref; /* Maximum back reference */
unsigned int backref_map; /* Bitmap of low back refs */
int req_varyopt; /* "After variable item" flag for reqbyte */
BOOL nopartial; /* Set TRUE if partial won't work */
} compile_data;
/* Structure for maintaining a chain of pointers to the currently incomplete
branches, for testing for left recursion. */
typedef struct branch_chain {
struct branch_chain *outer;
uschar *current;
} branch_chain;
/* Structure for items in a linked list that represents an explicit recursive
call within the pattern. */
typedef struct recursion_info {
struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
int group_num; /* Number of group that was called */
const uschar *after_call; /* "Return value": points after the call in the expr */
const uschar *save_start; /* Old value of md->start_match */
int *offset_save; /* Pointer to start of saved offsets */
int saved_max; /* Number of saved offsets */
} recursion_info;
/* When compiling in a mode that doesn't use recursive calls to match(),
a structure is used to remember local variables on the heap. It is defined in
pcre.c, close to the match() function, so that it is easy to keep it in step
with any changes of local variable. However, the pointer to the current frame
must be saved in some "static" place over a longjmp(). We declare the
structure here so that we can put a pointer in the match_data structure.
NOTE: This isn't used for a "normal" compilation of pcre. */
struct heapframe;
/* Structure for passing "static" information around between the functions
doing traditional NFA matching, so that they are thread-safe. */
typedef struct match_data {
unsigned long int match_call_count; /* As it says */
unsigned long int match_limit;/* As it says */
int *offset_vector; /* Offset vector */
int offset_end; /* One past the end */
int offset_max; /* The maximum usable for return data */
const uschar *lcc; /* Points to lower casing table */
const uschar *ctypes; /* Points to table of type maps */
BOOL offset_overflow; /* Set if too many extractions */
BOOL notbol; /* NOTBOL flag */
BOOL noteol; /* NOTEOL flag */
BOOL utf8; /* UTF8 flag */
BOOL endonly; /* Dollar not before final \n */
BOOL notempty; /* Empty string match not wanted */
BOOL partial; /* PARTIAL flag */
BOOL hitend; /* Hit the end of the subject at some point */
const uschar *start_code; /* For use when recursing */
const uschar *start_subject; /* Start of the subject string */
const uschar *end_subject; /* End of the subject string */
const uschar *start_match; /* Start of this match attempt */
const uschar *end_match_ptr; /* Subject position at end match */
int end_offset_top; /* Highwater mark at end of match */
int capture_last; /* Most recent capture number */
int start_offset; /* The start offset value */
recursion_info *recursive; /* Linked list of recursion data */
void *callout_data; /* To pass back to callouts */
struct heapframe *thisframe; /* Used only when compiling for no recursion */
} match_data;
/* A similar structure is used for the same purpose by the DFA matching
functions. */
typedef struct dfa_match_data {
const uschar *start_code; /* Start of the compiled pattern */
const uschar *start_subject; /* Start of the subject string */
const uschar *end_subject; /* End of subject string */
const uschar *tables; /* Character tables */
int moptions; /* Match options */
int poptions; /* Pattern options */
void *callout_data; /* To pass back to callouts */
} dfa_match_data;
/* Bit definitions for entries in the pcre_ctypes table. */
#define ctype_space 0x01
#define ctype_letter 0x02
#define ctype_digit 0x04
#define ctype_xdigit 0x08
#define ctype_word 0x10 /* alphameric or '_' */
#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */
/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set
of bits for a class map. Some classes are built by combining these tables. */
#define cbit_space 0 /* [:space:] or \s */
#define cbit_xdigit 32 /* [:xdigit:] */
#define cbit_digit 64 /* [:digit:] or \d */
#define cbit_upper 96 /* [:upper:] */
#define cbit_lower 128 /* [:lower:] */
#define cbit_word 160 /* [:word:] or \w */
#define cbit_graph 192 /* [:graph:] */
#define cbit_print 224 /* [:print:] */
#define cbit_punct 256 /* [:punct:] */
#define cbit_cntrl 288 /* [:cntrl:] */
#define cbit_length 320 /* Length of the cbits table */
/* Offsets of the various tables from the base tables pointer, and
total length. */
#define lcc_offset 0
#define fcc_offset 256
#define cbits_offset 512
#define ctypes_offset (cbits_offset + cbit_length)
#define tables_length (ctypes_offset + 256)
/* Layout of the UCP type table that translates property names into codes for
ucp_findchar(). */
typedef struct {
const char *name;
int value;
} ucp_type_table;
/* Internal shared data tables. These are tables that are used by more than one
of the exported public functions. They have to be "external" in the C sense,
but are not part of the PCRE public API. The data for these tables is in the
pcretabs.c module. */
extern const int _pcre_utf8_table1[];
extern const int _pcre_utf8_table2[];
extern const int _pcre_utf8_table3[];
extern const uschar _pcre_utf8_table4[];
extern const int _pcre_utf8_table1_size;
extern const ucp_type_table _pcre_utt[];
extern const int _pcre_utt_size;
extern const uschar _pcre_default_tables[];
extern const uschar _pcre_OP_lengths[];
/* Internal shared functions. These are functions that are used by more than
one of the exported public functions. They have to be "external" in the C
sense, but are not part of the PCRE public API. */
extern int _pcre_ord2utf8(int, uschar *);
extern void _pcre_printint(pcre *, FILE *);
extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *,
const pcre_study_data *, pcre_study_data *);
extern int _pcre_ucp_findchar(const int, int *, int *);
extern int _pcre_valid_utf8(const uschar *, int);
extern BOOL _pcre_xclass(int, const uschar *);
/* End of pcreinal.h */

89
harbour/source/hbpcre/pcreinfo.c Normal file
View File

@@ -0,0 +1,89 @@
/*************************************************
* 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) 1997-2005 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_info(), which gives some
information about a compiled pattern. However, use of this function is now
deprecated, as it has been superseded by pcre_fullinfo(). */
#include "pcreinal.h"
/*************************************************
* (Obsolete) Return info about compiled pattern *
*************************************************/
/* This is the original "info" function. It picks potentially useful data out
of the private structure, but its interface was too rigid. It remains for
backwards compatibility. The public options are passed back in an int - though
the re->options field has been expanded to a long int, all the public options
at the low end of it, and so even on 16-bit systems this will still be OK.
Therefore, I haven't changed the API for pcre_info().
Arguments:
argument_re points to compiled code
optptr where to pass back the options
first_byte where to pass back the first character,
or -1 if multiline and all branches start ^,
or -2 otherwise
Returns: number of capturing subpatterns
or negative values on error
*/
EXPORT int
pcre_info(const pcre *argument_re, int *optptr, int *first_byte)
{
real_pcre internal_re;
const real_pcre *re = (const real_pcre *)argument_re;
if (re == NULL) return PCRE_ERROR_NULL;
if (re->magic_number != MAGIC_NUMBER)
{
re = _pcre_try_flipped(re, &internal_re, NULL, NULL);
if (re == NULL) return PCRE_ERROR_BADMAGIC;
}
if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS);
if (first_byte != NULL)
*first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
return re->top_bracket;
}
/* End of pcreinfo.c */

145
harbour/source/hbpcre/pcremktb.c Normal file
View File

@@ -0,0 +1,145 @@
/*************************************************
* 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) 1997-2005 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_maketables(), which builds
character tables for PCRE in the current locale. The file is compiled on its
own as part of the PCRE library. However, it is also included in the
compilation of dftables.c, in which case the macro DFTABLES is defined. */
#ifndef DFTABLES
#include "pcreinal.h"
#endif
/*************************************************
* Create PCRE character tables *
*************************************************/
/* This function builds a set of character tables for use by PCRE and returns
a pointer to them. They are build using the ctype functions, and consequently
their contents will depend upon the current locale setting. When compiled as
part of the library, the store is obtained via pcre_malloc(), but when compiled
inside dftables, use malloc().
Arguments: none
Returns: pointer to the contiguous block of data
*/
const unsigned char *
pcre_maketables(void)
{
unsigned char *yield, *p;
int i;
#ifndef DFTABLES
yield = (unsigned char*)(pcre_malloc)(tables_length);
#else
yield = (unsigned char*)malloc(tables_length);
#endif
if (yield == NULL) return NULL;
p = yield;
/* First comes the lower casing table */
for (i = 0; i < 256; i++) *p++ = tolower(i);
/* Next the case-flipping table */
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i);
/* Then the character class tables. Don't try to be clever and save effort
on exclusive ones - in some locales things may be different. Note that the
table for "space" includes everything "isspace" gives, including VT in the
default locale. This makes it work for the POSIX class [:space:]. */
memset(p, 0, cbit_length);
for (i = 0; i < 256; i++)
{
if (isdigit(i))
{
p[cbit_digit + i/8] |= 1 << (i&7);
p[cbit_word + i/8] |= 1 << (i&7);
}
if (isupper(i))
{
p[cbit_upper + i/8] |= 1 << (i&7);
p[cbit_word + i/8] |= 1 << (i&7);
}
if (islower(i))
{
p[cbit_lower + i/8] |= 1 << (i&7);
p[cbit_word + i/8] |= 1 << (i&7);
}
if (i == '_') p[cbit_word + i/8] |= 1 << (i&7);
if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7);
if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7);
if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7);
if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7);
if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7);
if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7);
}
p += cbit_length;
/* Finally, the character type table. In this, we exclude VT from the white
space chars, because Perl doesn't recognize it as such for \s and for comments
within regexes. */
for (i = 0; i < 256; i++)
{
int x = 0;
if (i != 0x0b && isspace(i)) x += ctype_space;
if (isalpha(i)) x += ctype_letter;
if (isdigit(i)) x += ctype_digit;
if (isxdigit(i)) x += ctype_xdigit;
if (isalnum(i) || i == '_') x += ctype_word;
/* Note: strchr includes the terminating zero in the characters it considers.
In this instance, that is ok because we want binary zero to be flagged as a
meta-character, which in this sense is any character that terminates a run
of data characters. */
if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; *p++ = x; }
return yield;
}
/* End of pcremktb.c */

78
harbour/source/hbpcre/pcreoutf.c Normal file
View File

@@ -0,0 +1,78 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This file contains a private PCRE function that converts an ordinal
character value into a UTF8 string. */
#include "pcreinal.h"
/*************************************************
* Convert character value to UTF-8 *
*************************************************/
/* This function takes an integer value in the range 0 - 0x7fffffff
and encodes it as a UTF-8 character in 0 to 6 bytes.
Arguments:
cvalue the character value
buffer pointer to buffer for result - at least 6 bytes long
Returns: number of characters placed in the buffer
*/
EXPORT int
_pcre_ord2utf8(int cvalue, uschar *buffer)
{
register int i, j;
for (i = 0; i < _pcre_utf8_table1_size; i++)
if (cvalue <= _pcre_utf8_table1[i]) break;
buffer += i;
for (j = i; j > 0; j--)
{
*buffer-- = 0x80 | (cvalue & 0x3f);
cvalue >>= 6;
}
*buffer = _pcre_utf8_table2[i] | cvalue;
return i + 1;
}
/* End of pcreoutf.c */

451
harbour/source/hbpcre/pcreprni.c Normal file
View File

@@ -0,0 +1,451 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an PCRE private debugging function for printing out the
internal form of a compiled regular expression, along with some supporting
local functions. */
#include "pcreinal.h"
static const char *OP_names[] = { OP_NAME_LIST };
/*************************************************
* Print single- or multi-byte character *
*************************************************/
static int
print_char(FILE *f, uschar *ptr, BOOL utf8)
{
int c = *ptr;
if (!utf8 || (c & 0xc0) != 0xc0)
{
if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
return 0;
}
else
{
int i;
int a = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
int s = 6*a;
c = (c & _pcre_utf8_table3[a]) << s;
for (i = 1; i <= a; i++)
{
/* This is a check for malformed UTF-8; it should only occur if the sanity
check has been turned off. Rather than swallow random bytes, just stop if
we hit a bad one. Print it with \X instead of \x as an indication. */
if ((ptr[i] & 0xc0) != 0x80)
{
fprintf(f, "\\X{%x}", c);
return i - 1;
}
/* The byte is OK */
s -= 6;
c |= (ptr[i] & 0x3f) << s;
}
if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
return a;
}
}
/*************************************************
* Find Unicode property name *
*************************************************/
static const char *
get_ucpname(int property)
{
#ifdef SUPPORT_UCP
int i;
for (i = _pcre_utt_size; i >= 0; i--)
{
if (property == _pcre_utt[i].value) break;
}
return (i >= 0)? _pcre_utt[i].name : "??";
#else
return "??";
#endif
}
/*************************************************
* Print compiled regex *
*************************************************/
/* Make this function work for a regex with integers either byte order.
However, we assume that what we are passed is a compiled regex. */
EXPORT void
_pcre_printint(pcre *external_re, FILE *f)
{
real_pcre *re = (real_pcre *)external_re;
uschar *codestart, *code;
BOOL utf8;
unsigned int options = re->options;
int offset = re->name_table_offset;
int count = re->name_count;
int size = re->name_entry_size;
if (re->magic_number != MAGIC_NUMBER)
{
offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff);
count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff);
size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff);
options = ((options << 24) & 0xff000000) |
((options << 8) & 0x00ff0000) |
((options >> 8) & 0x0000ff00) |
((options >> 24) & 0x000000ff);
}
code = codestart = (uschar *)re + offset + count * size;
utf8 = (options & PCRE_UTF8) != 0;
for(;;)
{
uschar *ccode;
int c;
int extra = 0;
fprintf(f, "%3d ", (int)(code - codestart));
if (*code >= OP_BRA)
{
if (*code - OP_BRA > EXTRACT_BASIC_MAX)
fprintf(f, "%3d Bra extra\n", GET(code, 1));
else
fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA);
code += _pcre_OP_lengths[OP_BRA];
continue;
}
switch(*code)
{
case OP_END:
fprintf(f, " %s\n", OP_names[*code]);
fprintf(f, "------------------------------------------------------------------\n");
return;
case OP_OPT:
fprintf(f, " %.2x %s", code[1], OP_names[*code]);
break;
case OP_CHAR:
{
fprintf(f, " ");
do
{
code++;
code += 1 + print_char(f, code, utf8);
}
while (*code == OP_CHAR);
fprintf(f, "\n");
continue;
}
break;
case OP_CHARNC:
{
fprintf(f, " NC ");
do
{
code++;
code += 1 + print_char(f, code, utf8);
}
while (*code == OP_CHARNC);
fprintf(f, "\n");
continue;
}
break;
case OP_KETRMAX:
case OP_KETRMIN:
case OP_ALT:
case OP_KET:
case OP_ASSERT:
case OP_ASSERT_NOT:
case OP_ASSERTBACK:
case OP_ASSERTBACK_NOT:
case OP_ONCE:
case OP_COND:
case OP_REVERSE:
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
break;
case OP_BRANUMBER:
printf("%3d %s", GET2(code, 1), OP_names[*code]);
break;
case OP_CREF:
if (GET2(code, 1) == CREF_RECURSE)
fprintf(f, " Cond recurse");
else
fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
break;
case OP_STAR:
case OP_MINSTAR:
case OP_PLUS:
case OP_MINPLUS:
case OP_QUERY:
case OP_MINQUERY:
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
fprintf(f, " ");
if (*code >= OP_TYPESTAR)
{
fprintf(f, "%s", OP_names[code[1]]);
if (code[1] == OP_PROP || code[1] == OP_NOTPROP)
{
fprintf(f, " %s ", get_ucpname(code[2]));
extra = 1;
}
}
else extra = print_char(f, code+1, utf8);
fprintf(f, "%s", OP_names[*code]);
break;
case OP_EXACT:
case OP_UPTO:
case OP_MINUPTO:
fprintf(f, " ");
extra = print_char(f, code+3, utf8);
fprintf(f, "{");
if (*code != OP_EXACT) fprintf(f, ",");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_MINUPTO) fprintf(f, "?");
break;
case OP_TYPEEXACT:
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
fprintf(f, " %s", OP_names[code[3]]);
if (code[3] == OP_PROP || code[3] == OP_NOTPROP)
{
fprintf(f, " %s ", get_ucpname(code[4]));
extra = 1;
}
fprintf(f, "{");
if (*code != OP_TYPEEXACT) fprintf(f, "0,");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
break;
case OP_NOT:
if (isprint(c = code[1])) fprintf(f, " [^%c]", c);
else fprintf(f, " [^\\x%02x]", c);
break;
case OP_NOTSTAR:
case OP_NOTMINSTAR:
case OP_NOTPLUS:
case OP_NOTMINPLUS:
case OP_NOTQUERY:
case OP_NOTMINQUERY:
if (isprint(c = code[1])) fprintf(f, " [^%c]", c);
else fprintf(f, " [^\\x%02x]", c);
fprintf(f, "%s", OP_names[*code]);
break;
case OP_NOTEXACT:
case OP_NOTUPTO:
case OP_NOTMINUPTO:
if (isprint(c = code[3])) fprintf(f, " [^%c]{", c);
else fprintf(f, " [^\\x%02x]{", c);
if (*code != OP_NOTEXACT) fprintf(f, "0,");
fprintf(f, "%d}", GET2(code,1));
if (*code == OP_NOTMINUPTO) fprintf(f, "?");
break;
case OP_RECURSE:
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
break;
case OP_REF:
fprintf(f, " \\%d", GET2(code,1));
ccode = code + _pcre_OP_lengths[*code];
goto CLASS_REF_REPEAT;
case OP_CALLOUT:
fprintf(f, " %s %d %d %d", OP_names[*code], code[1], GET(code,2),
GET(code, 2 + LINK_SIZE));
break;
case OP_PROP:
case OP_NOTPROP:
fprintf(f, " %s %s", OP_names[*code], get_ucpname(code[1]));
break;
/* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in
having this code always here, and it makes it less messy without all those
#ifdefs. */
case OP_CLASS:
case OP_NCLASS:
case OP_XCLASS:
{
int i, min, max;
BOOL printmap;
fprintf(f, " [");
if (*code == OP_XCLASS)
{
extra = GET(code, 1);
ccode = code + LINK_SIZE + 1;
printmap = (*ccode & XCL_MAP) != 0;
if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^");
}
else
{
printmap = TRUE;
ccode = code + 1;
}
/* Print a bit map */
if (printmap)
{
for (i = 0; i < 256; i++)
{
if ((ccode[i/8] & (1 << (i&7))) != 0)
{
int j;
for (j = i+1; j < 256; j++)
if ((ccode[j/8] & (1 << (j&7))) == 0) break;
if (i == '-' || i == ']') fprintf(f, "\\");
if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i);
if (--j > i)
{
if (j != i + 1) fprintf(f, "-");
if (j == '-' || j == ']') fprintf(f, "\\");
if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j);
}
i = j;
}
}
ccode += 32;
}
/* For an XCLASS there is always some additional data */
if (*code == OP_XCLASS)
{
int ch;
while ((ch = *ccode++) != XCL_END)
{
if (ch == XCL_PROP)
{
fprintf(f, "\\p{%s}", get_ucpname(*ccode++));
}
else if (ch == XCL_NOTPROP)
{
fprintf(f, "\\P{%s}", get_ucpname(*ccode++));
}
else
{
ccode += 1 + print_char(f, ccode, TRUE);
if (ch == XCL_RANGE)
{
fprintf(f, "-");
ccode += 1 + print_char(f, ccode, TRUE);
}
}
}
}
/* Indicate a non-UTF8 class which was created by negation */
fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
/* Handle repeats after a class or a back reference */
CLASS_REF_REPEAT:
switch(*ccode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRPLUS:
case OP_CRMINPLUS:
case OP_CRQUERY:
case OP_CRMINQUERY:
fprintf(f, "%s", OP_names[*ccode]);
extra += _pcre_OP_lengths[*ccode];
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
min = GET2(ccode,1);
max = GET2(ccode,3);
if (max == 0) fprintf(f, "{%d,}", min);
else fprintf(f, "{%d,%d}", min, max);
if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
extra += _pcre_OP_lengths[*ccode];
break;
}
}
break;
/* Anything else is just an item with no data*/
default:
fprintf(f, " %s", OP_names[*code]);
break;
}
code += _pcre_OP_lengths[*code] + extra;
fprintf(f, "\n");
}
}
/* End of pcreprni.c */

77
harbour/source/hbpcre/pcrerefc.c Normal file
View File

@@ -0,0 +1,77 @@
/*************************************************
* 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) 1997-2005 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_refcount(), which is an
auxiliary function that can be used to maintain a reference count in a compiled
pattern data block. This might be helpful in applications where the block is
shared by different users. */
#include "pcreinal.h"
/*************************************************
* Maintain reference count *
*************************************************/
/* The reference count is a 16-bit field, initialized to zero. It is not
possible to transfer a non-zero count from one host to a different host that
has a different byte order - though I can't see why anyone in their right mind
would ever want to do that!
Arguments:
argument_re points to compiled code
adjust value to add to the count
Returns: the (possibly updated) count value (a non-negative number), or
a negative error number
*/
EXPORT int
pcre_refcount(pcre *argument_re, int adjust)
{
real_pcre *re = (real_pcre *)argument_re;
if (re == NULL) return PCRE_ERROR_NULL;
re->ref_count = (-adjust > re->ref_count)? 0 :
(adjust + re->ref_count > 65535)? 65535 :
re->ref_count + adjust;
return re->ref_count;
}
/* End of pcrerefc.c */

482
harbour/source/hbpcre/pcrestud.c Normal file
View File

@@ -0,0 +1,482 @@
/*************************************************
* 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) 1997-2005 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_study(), along with local
supporting functions. */
#include "pcreinal.h"
/*************************************************
* Set a bit and maybe its alternate case *
*************************************************/
/* Given a character, set its bit in the table, and also the bit for the other
version of a letter if we are caseless.
Arguments:
start_bits points to the bit map
c is the character
caseless the caseless flag
cd the block with char table pointers
Returns: nothing
*/
static void
set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd)
{
start_bits[c/8] |= (1 << (c&7));
if (caseless && (cd->ctypes[c] & ctype_letter) != 0)
start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7));
}
/*************************************************
* Create bitmap of starting chars *
*************************************************/
/* This function scans a compiled unanchored expression and attempts to build a
bitmap of the set of initial characters. If it can't, it returns FALSE. As time
goes by, we may be able to get more clever at doing this.
Arguments:
code points to an expression
start_bits points to a 32-byte table, initialized to 0
caseless the current state of the caseless flag
utf8 TRUE if in UTF-8 mode
cd the block with char table pointers
Returns: TRUE if table built, FALSE otherwise
*/
static BOOL
set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless,
BOOL utf8, compile_data *cd)
{
register int c;
/* This next statement and the later reference to dummy are here 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, and we would rather not
disable optimization (in this module it actually makes a big difference, and
the pcre module can use all the optimization it can get). */
volatile int dummy;
do
{
const uschar *tcode = code + 1 + LINK_SIZE;
BOOL try_next = TRUE;
while (try_next)
{
/* If a branch starts with a bracket or a positive lookahead assertion,
recurse to set bits from within them. That's all for this branch. */
if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT)
{
if (!set_start_bits(tcode, start_bits, caseless, utf8, cd))
return FALSE;
try_next = FALSE;
}
else switch(*tcode)
{
default:
return FALSE;
/* Skip over callout */
case OP_CALLOUT:
tcode += 2 + 2*LINK_SIZE;
break;
/* Skip over extended extraction bracket number */
case OP_BRANUMBER:
tcode += 3;
break;
/* Skip over lookbehind and negative lookahead assertions */
case OP_ASSERT_NOT:
case OP_ASSERTBACK:
case OP_ASSERTBACK_NOT:
do tcode += GET(tcode, 1); while (*tcode == OP_ALT);
tcode += 1+LINK_SIZE;
break;
/* Skip over an option setting, changing the caseless flag */
case OP_OPT:
caseless = (tcode[1] & PCRE_CASELESS) != 0;
tcode += 2;
break;
/* BRAZERO does the bracket, but carries on. */
case OP_BRAZERO:
case OP_BRAMINZERO:
if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd))
return FALSE;
dummy = 1;
do tcode += GET(tcode,1); while (*tcode == OP_ALT);
tcode += 1+LINK_SIZE;
break;
/* Single-char * or ? sets the bit and tries the next item */
case OP_STAR:
case OP_MINSTAR:
case OP_QUERY:
case OP_MINQUERY:
set_bit(start_bits, tcode[1], caseless, cd);
tcode += 2;
#ifdef SUPPORT_UTF8
if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++;
#endif
break;
/* Single-char upto sets the bit and tries the next */
case OP_UPTO:
case OP_MINUPTO:
set_bit(start_bits, tcode[3], caseless, cd);
tcode += 4;
#ifdef SUPPORT_UTF8
if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++;
#endif
break;
/* At least one single char sets the bit and stops */
case OP_EXACT: /* Fall through */
tcode += 2;
case OP_CHAR:
case OP_CHARNC:
case OP_PLUS:
case OP_MINPLUS:
set_bit(start_bits, tcode[1], caseless, cd);
try_next = FALSE;
break;
/* Single character type sets the bits and stops */
case OP_NOT_DIGIT:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_digit];
try_next = FALSE;
break;
case OP_DIGIT:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_digit];
try_next = FALSE;
break;
case OP_NOT_WHITESPACE:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_space];
try_next = FALSE;
break;
case OP_WHITESPACE:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_space];
try_next = FALSE;
break;
case OP_NOT_WORDCHAR:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_word];
try_next = FALSE;
break;
case OP_WORDCHAR:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_word];
try_next = FALSE;
break;
/* One or more character type fudges the pointer and restarts, knowing
it will hit a single character type and stop there. */
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
tcode++;
break;
case OP_TYPEEXACT:
tcode += 3;
break;
/* Zero or more repeats of character types set the bits and then
try again. */
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
tcode += 2; /* Fall through */
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
switch(tcode[1])
{
case OP_ANY:
return FALSE;
case OP_NOT_DIGIT:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_digit];
break;
case OP_DIGIT:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_digit];
break;
case OP_NOT_WHITESPACE:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_space];
break;
case OP_WHITESPACE:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_space];
break;
case OP_NOT_WORDCHAR:
for (c = 0; c < 32; c++)
start_bits[c] |= ~cd->cbits[c+cbit_word];
break;
case OP_WORDCHAR:
for (c = 0; c < 32; c++)
start_bits[c] |= cd->cbits[c+cbit_word];
break;
}
tcode += 2;
break;
/* Character class where all the information is in a bit map: set the
bits and either carry on or not, according to the repeat count. If it was
a negative class, and we are operating with UTF-8 characters, any byte
with a value >= 0xc4 is a potentially valid starter because it starts a
character with a value > 255. */
case OP_NCLASS:
if (utf8)
{
start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */
memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */
}
/* Fall through */
case OP_CLASS:
{
tcode++;
/* In UTF-8 mode, the bits in a bit map correspond to character
values, not to byte values. However, the bit map we are constructing is
for byte values. So we have to do a conversion for characters whose
value is > 127. In fact, there are only two possible starting bytes for
characters in the range 128 - 255. */
if (utf8)
{
for (c = 0; c < 16; c++) start_bits[c] |= tcode[c];
for (c = 128; c < 256; c++)
{
if ((tcode[c/8] && (1 << (c&7))) != 0)
{
int d = (c >> 6) | 0xc0; /* Set bit for this starter */
start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */
c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */
}
}
}
/* In non-UTF-8 mode, the two bit maps are completely compatible. */
else
{
for (c = 0; c < 32; c++) start_bits[c] |= tcode[c];
}
/* Advance past the bit map, and act on what follows */
tcode += 32;
switch (*tcode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRQUERY:
case OP_CRMINQUERY:
tcode++;
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5;
else try_next = FALSE;
break;
default:
try_next = FALSE;
break;
}
}
break; /* End of bitmap class handling */
} /* End of switch */
} /* End of try_next loop */
code += GET(code, 1); /* Advance to next branch */
}
while (*code == OP_ALT);
return TRUE;
}
/*************************************************
* Study a compiled expression *
*************************************************/
/* This function is handed a compiled expression that it must study to produce
information that will speed up the matching. It returns a pcre_extra block
which then gets handed back to pcre_exec().
Arguments:
re points to the compiled expression
options contains option bits
errorptr points to where to place error messages;
set NULL unless error
Returns: pointer to a pcre_extra block, with study_data filled in and the
appropriate flag set;
NULL on error or if no optimization possible
*/
EXPORT pcre_extra *
pcre_study(const pcre *external_re, int options, const char **errorptr)
{
uschar start_bits[32];
pcre_extra *extra;
pcre_study_data *study;
const uschar *tables;
const real_pcre *re = (const real_pcre *)external_re;
uschar *code = (uschar *)re + re->name_table_offset +
(re->name_count * re->name_entry_size);
compile_data compile_block;
*errorptr = NULL;
if (re == NULL || re->magic_number != MAGIC_NUMBER)
{
*errorptr = "argument is not a compiled regular expression";
return NULL;
}
if ((options & ~PUBLIC_STUDY_OPTIONS) != 0)
{
*errorptr = "unknown or incorrect option bit(s) set";
return NULL;
}
/* For an anchored pattern, or an unanchored pattern that has a first char, or
a multiline pattern that matches only at "line starts", no further processing
at present. */
if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
return NULL;
/* Set the character tables in the block that is passed around */
tables = re->tables;
if (tables == NULL)
(void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES,
(void *)(&tables));
compile_block.lcc = tables + lcc_offset;
compile_block.fcc = tables + fcc_offset;
compile_block.cbits = tables + cbits_offset;
compile_block.ctypes = tables + ctypes_offset;
/* See if we can find a fixed set of initial characters for the pattern. */
memset(start_bits, 0, 32 * sizeof(uschar));
if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0,
(re->options & PCRE_UTF8) != 0, &compile_block)) return NULL;
/* Get a pcre_extra block and a pcre_study_data block. The study data is put in
the latter, which is pointed to by the former, which may also get additional
data set later by the calling program. At the moment, the size of
pcre_study_data is fixed. We nevertheless save it in a field for returning via
the pcre_fullinfo() function so that if it becomes variable in the future, we
don't have to change that code. */
extra = (pcre_extra *)(pcre_malloc)
(sizeof(pcre_extra) + sizeof(pcre_study_data));
if (extra == NULL)
{
*errorptr = "failed to get memory";
return NULL;
}
study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra));
extra->flags = PCRE_EXTRA_STUDY_DATA;
extra->study_data = study;
study->size = sizeof(pcre_study_data);
study->options = PCRE_STUDY_MAPPED;
memcpy(study->start_bits, start_bits, sizeof(start_bits));
return extra;
}
/* End of pcrestud.c */

129
harbour/source/hbpcre/pcretabs.c Normal file
View File

@@ -0,0 +1,129 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains some fixed tables that are used by more than one of the
PCRE code modules. */
#include "pcreinal.h"
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
the definition is next to the definition of the opcodes in internal.h. */
const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
/*************************************************
* Tables for UTF-8 support *
*************************************************/
/* These are the breakpoints for different numbers of bytes in a UTF-8
character. */
const int _pcre_utf8_table1[] =
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);
/* These are the indicator bits and the mask for the data bits to set in the
first byte of a character, indexed by the number of additional bytes. */
const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
/* Table of the number of extra characters, indexed by the first character
masked with 0x3f. The highest number for a valid UTF-8 character is in fact
0x3d. */
const uschar _pcre_utf8_table4[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
/* This table translates Unicode property names into code values for the
ucp_findchar() function. It is used by pcretest as well as by the library
functions. */
const ucp_type_table _pcre_utt[] = {
{ "C", 128 + ucp_C },
{ "Cc", ucp_Cc },
{ "Cf", ucp_Cf },
{ "Cn", ucp_Cn },
{ "Co", ucp_Co },
{ "Cs", ucp_Cs },
{ "L", 128 + ucp_L },
{ "Ll", ucp_Ll },
{ "Lm", ucp_Lm },
{ "Lo", ucp_Lo },
{ "Lt", ucp_Lt },
{ "Lu", ucp_Lu },
{ "M", 128 + ucp_M },
{ "Mc", ucp_Mc },
{ "Me", ucp_Me },
{ "Mn", ucp_Mn },
{ "N", 128 + ucp_N },
{ "Nd", ucp_Nd },
{ "Nl", ucp_Nl },
{ "No", ucp_No },
{ "P", 128 + ucp_P },
{ "Pc", ucp_Pc },
{ "Pd", ucp_Pd },
{ "Pe", ucp_Pe },
{ "Pf", ucp_Pf },
{ "Pi", ucp_Pi },
{ "Po", ucp_Po },
{ "Ps", ucp_Ps },
{ "S", 128 + ucp_S },
{ "Sc", ucp_Sc },
{ "Sk", ucp_Sk },
{ "Sm", ucp_Sm },
{ "So", ucp_So },
{ "Z", 128 + ucp_Z },
{ "Zl", ucp_Zl },
{ "Zp", ucp_Zp },
{ "Zs", ucp_Zs }
};
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
/* End of pcretabs.c */

132
harbour/source/hbpcre/pcretryf.c Normal file
View File

@@ -0,0 +1,132 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that tests a compiled pattern to
see if it was compiled with the opposite endianness. If so, it uses an
auxiliary local function to flip the appropriate bytes. */
#include "pcreinal.h"
/*************************************************
* Flip bytes in an integer *
*************************************************/
/* This function is called when the magic number in a regex doesn't match, in
order to flip its bytes to see if we are dealing with a pattern that was
compiled on a host of different endianness. If so, this function is used to
flip other byte values.
Arguments:
value the number to flip
n the number of bytes to flip (assumed to be 2 or 4)
Returns: the flipped value
*/
static long int
byteflip(long int value, int n)
{
if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8);
return ((value & 0x000000ff) << 24) |
((value & 0x0000ff00) << 8) |
((value & 0x00ff0000) >> 8) |
((value & 0xff000000) >> 24);
}
/*************************************************
* Test for a byte-flipped compiled regex *
*************************************************/
/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from
pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that
is, it was compiled on a system of opposite endianness. The function is called
only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped,
we flip all the relevant values into a different data block, and return it.
Arguments:
re points to the regex
study points to study data, or NULL
internal_re points to a new regex block
internal_study points to a new study block
Returns: the new block if is is indeed a byte-flipped regex
NULL if it is not
*/
EXPORT real_pcre *
_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re,
const pcre_study_data *study, pcre_study_data *internal_study)
{
if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER)
return NULL;
*internal_re = *re; /* To copy other fields */
internal_re->size = byteflip(re->size, sizeof(re->size));
internal_re->options = byteflip(re->options, sizeof(re->options));
internal_re->top_bracket =
(pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket));
internal_re->top_backref =
(pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref));
internal_re->first_byte =
(pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte));
internal_re->req_byte =
(pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte));
internal_re->name_table_offset =
(pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset));
internal_re->name_entry_size =
(pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size));
internal_re->name_count =
(pcre_uint16)byteflip(re->name_count, sizeof(re->name_count));
if (study != NULL)
{
*internal_study = *study; /* To copy other fields */
internal_study->size = byteflip(study->size, sizeof(study->size));
internal_study->options = byteflip(study->options, sizeof(study->options));
}
return internal_re;
}
/* End of pcretryf.c */

61
harbour/source/hbpcre/pcrever.c Normal file
View File

@@ -0,0 +1,61 @@
/*************************************************
* 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) 1997-2005 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_version(), which returns a
string that identifies the PCRE version that is in use. */
#include "pcreinal.h"
/*************************************************
* Return version string *
*************************************************/
#define STRING(a) # a
#define XSTRING(s) STRING(s)
EXPORT const char *
pcre_version(void)
{
return XSTRING(PCRE_MAJOR) "." XSTRING(PCRE_MINOR) " " XSTRING(PCRE_DATE);
}
/* End of pcrevers.c */

130
harbour/source/hbpcre/pcrevutf.c Normal file
View File

@@ -0,0 +1,130 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function for validating UTF-8 character
strings. */
#include "pcreinal.h"
/*************************************************
* Validate a UTF-8 string *
*************************************************/
/* This function is called (optionally) at the start of compile or match, to
validate that a supposed UTF-8 string is actually valid. The early check means
that subsequent code can assume it is dealing with a valid string. The check
can be turned off for maximum performance, but the consequences of supplying
an invalid string are then undefined.
Arguments:
string points to the string
length length of string, or -1 if the string is zero-terminated
Returns: < 0 if the string is a valid UTF-8 string
>= 0 otherwise; the value is the offset of the bad byte
*/
EXPORT int
_pcre_valid_utf8(const uschar *string, int length)
{
register const uschar *p;
if (length < 0)
{
for (p = string; *p != 0; p++);
length = p - string;
}
for (p = string; length-- > 0; p++)
{
register int ab;
register int c = *p;
if (c < 128) continue;
if ((c & 0xc0) != 0xc0) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab) return p - string;
length -= ab;
/* Check top bits in the second byte */
if ((*(++p) & 0xc0) != 0x80) return p - string;
/* Check for overlong sequences for each different length */
switch (ab)
{
/* Check for xx00 000x */
case 1:
if ((c & 0x3e) == 0) return p - string;
continue; /* We know there aren't any more bytes to check */
/* Check for 1110 0000, xx0x xxxx */
case 2:
if (c == 0xe0 && (*p & 0x20) == 0) return p - string;
break;
/* Check for 1111 0000, xx00 xxxx */
case 3:
if (c == 0xf0 && (*p & 0x30) == 0) return p - string;
break;
/* Check for 1111 1000, xx00 0xxx */
case 4:
if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
break;
/* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */
case 5:
if (c == 0xfe || c == 0xff ||
(c == 0xfc && (*p & 0x3c) == 0)) return p - string;
break;
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */
while (--ab > 0)
{
if ((*(++p) & 0xc0) != 0x80) return p - string;
}
}
return -1;
}
/* End of pcrevutf.c */

121
harbour/source/hbpcre/pcrexcls.c Normal file
View File

@@ -0,0 +1,121 @@
/*************************************************
* 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) 1997-2005 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that is used to match an extended
class (one that contains characters whose values are > 255). It is used by both
pcre_exec() and pcre_def_exec(). */
#include "pcreinal.h"
/*************************************************
* Match character against an XCLASS *
*************************************************/
/* This function is called to match a character against an extended class that
might contain values > 255.
Arguments:
c the character
data points to the flag byte of the XCLASS data
Returns: TRUE if character matches, else FALSE
*/
EXPORT BOOL
_pcre_xclass(int c, const uschar *data)
{
int t;
BOOL negated = (*data & XCL_NOT) != 0;
/* Character values < 256 are matched against a bitmap, if one is present. If
not, we still carry on, because there may be ranges that start below 256 in the
additional data. */
if (c < 256)
{
if ((*data & XCL_MAP) != 0 && (data[1 + c/8] & (1 << (c&7))) != 0)
return !negated; /* char found */
}
/* First skip the bit map if present. Then match against the list of Unicode
properties or large chars or ranges that end with a large char. We won't ever
encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */
if ((*data++ & XCL_MAP) != 0) data += 32;
while ((t = *data++) != XCL_END)
{
int x, y;
if (t == XCL_SINGLE)
{
GETCHARINC(x, data);
if (c == x) return !negated;
}
else if (t == XCL_RANGE)
{
GETCHARINC(x, data);
GETCHARINC(y, data);
if (c >= x && c <= y) return !negated;
}
#ifdef SUPPORT_UCP
else /* XCL_PROP & XCL_NOTPROP */
{
int chartype, othercase;
int rqdtype = *data++;
int category = ucp_findchar(c, &chartype, &othercase);
if (rqdtype >= 128)
{
if ((rqdtype - 128 == category) == (t == XCL_PROP)) return !negated;
}
else
{
if ((rqdtype == chartype) == (t == XCL_PROP)) return !negated;
}
}
#endif /* SUPPORT_UCP */
}
return negated; /* char did not match */
}
/* End of pcrexcls.c */

60
harbour/source/hbpcre/ucp.h Normal file
View File

@@ -0,0 +1,60 @@
/*************************************************
* libucp - Unicode Property Table handler *
*************************************************/
#ifndef _UCP_H
#define _UCP_H
/* These are the character categories that are returned by ucp_findchar */
enum {
ucp_C, /* Other */
ucp_L, /* Letter */
ucp_M, /* Mark */
ucp_N, /* Number */
ucp_P, /* Punctuation */
ucp_S, /* Symbol */
ucp_Z /* Separator */
};
/* These are the detailed character types that are returned by ucp_findchar */
enum {
ucp_Cc, /* Control */
ucp_Cf, /* Format */
ucp_Cn, /* Unassigned */
ucp_Co, /* Private use */
ucp_Cs, /* Surrogate */
ucp_Ll, /* Lower case letter */
ucp_Lm, /* Modifier letter */
ucp_Lo, /* Other letter */
ucp_Lt, /* Title case letter */
ucp_Lu, /* Upper case letter */
ucp_Mc, /* Spacing mark */
ucp_Me, /* Enclosing mark */
ucp_Mn, /* Non-spacing mark */
ucp_Nd, /* Decimal number */
ucp_Nl, /* Letter number */
ucp_No, /* Other number */
ucp_Pc, /* Connector punctuation */
ucp_Pd, /* Dash punctuation */
ucp_Pe, /* Close punctuation */
ucp_Pf, /* Final punctuation */
ucp_Pi, /* Initial punctuation */
ucp_Po, /* Other punctuation */
ucp_Ps, /* Open punctuation */
ucp_Sc, /* Currency symbol */
ucp_Sk, /* Modifier symbol */
ucp_Sm, /* Mathematical symbol */
ucp_So, /* Other symbol */
ucp_Zl, /* Line separator */
ucp_Zp, /* Paragraph separator */
ucp_Zs /* Space separator */
};
extern int ucp_findchar(const int, int *, int *);
#endif
/* End of ucp.h */

91
harbour/source/hbpcre/ucpinter.h Normal file
View File

@@ -0,0 +1,91 @@
/*************************************************
* libucp - Unicode Property Table handler *
*************************************************/
/* Internal header file defining the layout of compact nodes in the tree. */
typedef struct cnode {
unsigned short int f0;
unsigned short int f1;
unsigned short int f2;
} cnode;
/* Things for the f0 field */
#define f0_leftexists 0x8000 /* Left child exists */
#define f0_typemask 0x3f00 /* Type bits */
#define f0_typeshift 8 /* Type shift */
#define f0_chhmask 0x00ff /* Character high bits */
/* Things for the f2 field */
#define f2_rightmask 0xf000 /* Mask for right offset bits */
#define f2_rightshift 12 /* Shift for right offset */
#define f2_casemask 0x0fff /* Mask for case offset */
/* The tree consists of a vector of structures of type cnode, with the root
node as the first element. The three short ints (16-bits) are used as follows:
(f0) (1) The 0x8000 bit of f0 is set if a left child exists. The child's node
is the next node in the vector.
(2) The 0x4000 bits of f0 is spare.
(3) The 0x3f00 bits of f0 contain the character type; this is a number
defined by the enumeration in ucp.h (e.g. ucp_Lu).
(4) The bottom 8 bits of f0 contain the most significant byte of the
character's 24-bit codepoint.
(f1) (1) The f1 field contains the two least significant bytes of the
codepoint.
(f2) (1) The 0xf000 bits of f2 contain zero if there is no right child of this
node. Otherwise, they contain one plus the exponent of the power of
two of the offset to the right node (e.g. a value of 3 means 8). The
units of the offset are node items.
(2) The 0x0fff bits of f2 contain the signed offset from this character to
its alternate cased value. They are zero if there is no such
character.
-----------------------------------------------------------------------------
||.|.| type (6) | ms char (8) || ls char (16) ||....| case offset (12) ||
-----------------------------------------------------------------------------
| | |
| |-> spare |
| exponent of right
|-> left child exists child offset
The upper/lower casing information is set only for characters that come in
pairs. There are (at present) four non-one-to-one mappings in the Unicode data.
These are ignored. They are:
1FBE Greek Prosgegrammeni (lower, with upper -> capital iota)
2126 Ohm
212A Kelvin
212B Angstrom
Certainly for the last three, having an alternate case would seem to be a
mistake. I don't know any Greek, so cannot comment on the first one.
When searching the tree, proceed as follows:
(1) Start at the first node.
(2) Extract the character value from f1 and the bottom 8 bits of f0;
(3) Compare with the character being sought. If equal, we are done.
(4) If the test character is smaller, inspect the f0_leftexists flag. If it is
not set, the character is not in the tree. If it is set, move to the next
node, and go to (2).
(5) If the test character is bigger, extract the f2_rightmask bits from f2, and
shift them right by f2_rightshift. If the result is zero, the character is
not in the tree. Otherwise, calculate the number of nodes to skip by
shifting the value 1 left by this number minus one. Go to (2).
*/
/* End of internal.h */

15105
harbour/source/hbpcre/ucptable.c Normal file
View File

File diff suppressed because it is too large Load Diff

2
harbour/source/rdd/dbfcdx/dbfcdx1.c
View File

@@ -5521,7 +5521,7 @@ static BOOL hb_cdxRegexMatch( CDXAREAP pArea, PHB_REGEX pRegEx, LPCDXKEY pKey )
#else
HB_SYMBOL_UNUSED( pArea );
#endif
return hb_regexMatch( pRegEx, szKey, FALSE );
return hb_regexMatch( pRegEx, szKey, pKey->len, FALSE );
}
/*

2
harbour/source/rdd/dbfntx/dbfntx1.c
View File

@@ -4289,7 +4289,7 @@ static BOOL hb_ntxRegexMatch( LPTAGINFO pTag, PHB_REGEX pRegEx, char * szKey )
#else
HB_SYMBOL_UNUSED( pTag );
#endif
return hb_regexMatch( pRegEx, szKey, FALSE );
return hb_regexMatch( pRegEx, szKey, pTag->KeyLength, FALSE );
}
/*

1
harbour/source/rtl/Makefile
View File

@@ -56,6 +56,7 @@ C_SOURCES=\
hbinet.c \
hbrandom.c \
hbregex.c \
hbregexc.c \
hbtoken.c \
idle.c \
inkey.c \

336
harbour/source/rtl/hbregex.c
View File

@@ -56,113 +56,100 @@
#include "hbregex.h"
#include "hbapiitm.h"
#include "hbapierr.h"
#include "hbinit.h"
/* This releases regex when called from the garbage collector */
static HB_GARBAGE_FUNC( hb_regexRelease )
static void hb_regfree( PHB_REGEX pRegEx )
{
#ifdef _HB_REGEX_INTERNAL_
PHB_REGEX pRegEx = ( PHB_REGEX ) Cargo;
#if defined( HB_PCRE_REGEX )
( pcre_free )( pRegEx->re_pcre );
#elif defined( HB_POSIX_REGEX )
regfree( &pRegEx->reg );
#else
HB_SYMBOL_UNUSED( Cargo );
#endif
}
PHB_REGEX hb_regexCompile( const char *szRegEx, ULONG ulLen, int iFlags )
{
#ifdef _HB_REGEX_INTERNAL_
PHB_REGEX pRegEx;
HB_SYMBOL_UNUSED( ulLen );
pRegEx = ( PHB_REGEX ) hb_gcAlloc( sizeof( HB_REGEX ), hb_regexRelease );
hb_gcLock( pRegEx );
memset( pRegEx, 0, sizeof( HB_REGEX ) );
pRegEx->fFree = TRUE;
pRegEx->iCFlags = REG_EXTENDED |
( ( iFlags & HBREG_ICASE ) ? REG_ICASE : 0 ) |
( ( iFlags & HBREG_NEWLINE ) ? REG_NEWLINE : 0 ) |
( ( iFlags & HBREG_NOSUB ) ? REG_NOSUB : 0 );
pRegEx->iEFlags = ( ( iFlags & HBREG_NOTBOL ) ? REG_NOTBOL : 0 ) |
( ( iFlags & HBREG_NOTEOL ) ? REG_NOTBOL : 0 );
if( regcomp( &pRegEx->reg, szRegEx, pRegEx->iCFlags ) != 0 )
{
hb_gcFree( pRegEx );
pRegEx = NULL;
}
return pRegEx;
#else
HB_SYMBOL_UNUSED( szRegEx );
HB_SYMBOL_UNUSED( ulLen );
HB_SYMBOL_UNUSED( iFlags );
return NULL;
#endif
}
PHB_REGEX hb_regexGet( PHB_ITEM pRegExItm, int iFlags )
{
PHB_REGEX pRegEx = NULL;
if( pRegExItm )
{
if( HB_IS_POINTER( pRegExItm ) )
{
pRegEx = ( PHB_REGEX ) hb_itemGetPtrGC( pRegExItm, hb_regexRelease );
}
else if( HB_IS_STRING( pRegExItm ) )
{
ULONG ulLen = hb_itemGetCLen( pRegExItm );
char * szRegEx = hb_itemGetCPtr( pRegExItm );
if( ulLen > 0 )
pRegEx = hb_regexCompile( szRegEx, ulLen, iFlags );
}
}
if( !pRegEx )
hb_errRT_BASE_SubstR( EG_ARG, 3012, "Invalid Regular expression", &hb_errFuncName, 1, pRegExItm );
return pRegEx;
}
void hb_regexFree( PHB_REGEX pRegEx )
{
#ifdef _HB_REGEX_INTERNAL_
if( pRegEx && pRegEx->fFree )
{
regfree( &pRegEx->reg );
hb_gcFree( pRegEx );
}
#else
HB_SYMBOL_UNUSED( pRegEx );
#endif
}
BOOL hb_regexMatch( PHB_REGEX pRegEx, const char *szString, BOOL fFull )
static int hb_regcomp( PHB_REGEX pRegEx, const char * szRegEx )
{
#ifdef _HB_REGEX_INTERNAL_
BOOL fMatch;
#if defined( HB_PCRE_REGEX )
const unsigned char * pCharTable = NULL;
const char *szError = NULL;
int iErrOffset = 0;
int iCFlags = ( ( pRegEx->iFlags & HBREG_ICASE ) ? PCRE_CASELESS : 0 ) |
( ( pRegEx->iFlags & HBREG_NEWLINE ) ? PCRE_MULTILINE : 0 ) |
( ( pRegEx->iFlags & HBREG_DOTALL ) ? PCRE_DOTALL : 0 );
fMatch = regexec( &pRegEx->reg, szString, 1, pRegEx->aMatches, pRegEx->iEFlags ) == 0;
pRegEx->iEFlags = ( ( pRegEx->iFlags & HBREG_NOTBOL ) ? PCRE_NOTBOL : 0 ) |
( ( pRegEx->iFlags & HBREG_NOTEOL ) ? PCRE_NOTEOL : 0 );
return fMatch && ( !fFull ||
( pRegEx->aMatches[0].rm_so == 0 &&
pRegEx->aMatches[0].rm_eo == (int) strlen( szString ) ) );
pRegEx->re_pcre = pcre_compile( szRegEx, iCFlags, &szError,
&iErrOffset, pCharTable );
return pRegEx->re_pcre ? 0 : -1;
#elif defined( HB_POSIX_REGEX )
int iCFlags = REG_EXTENDED |
( ( pRegEx->iFlags & HBREG_ICASE ) ? REG_ICASE : 0 ) |
( ( pRegEx->iFlags & HBREG_NEWLINE ) ? REG_NEWLINE : 0 ) |
( ( pRegEx->iFlags & HBREG_NOSUB ) ? REG_NOSUB : 0 );
pRegEx->iEFlags = ( ( pRegEx->iFlags & HBREG_NOTBOL ) ? REG_NOTBOL : 0 ) |
( ( pRegEx->iFlags & HBREG_NOTEOL ) ? REG_NOTEOL : 0 );
return regcomp( &pRegEx->reg, szRegEx, iCFlags );
#else
HB_SYMBOL_UNUSED( pRegEx );
HB_SYMBOL_UNUSED( szRegEx );
return -1;
#endif
}
static int hb_regexec( PHB_REGEX pRegEx, const char * szString, ULONG ulLen,
int iMatches, HB_REGMATCH * aMatches )
{
#if defined( HB_PCRE_REGEX )
int iResult;
iResult = pcre_exec( pRegEx->re_pcre, NULL /* pcre_extra */,
szString, ulLen, 0 /* startoffset */,
pRegEx->iEFlags, aMatches, iMatches + 1 );
if( iResult == 0 )
iResult = iMatches;
return iResult;
#elif defined( HB_POSIX_REGEX )
char * szBuffer = NULL;
int iResult, i;
if( szString[ ulLen ] != 0 )
{
szBuffer = hb_strndup( szString, ulLen );
szString = szBuffer;
}
for( i = 0; i < iMatches; i++ )
HB_REGMATCH_EO( aMatches, i ) = -1;
iResult = regexec( &pRegEx->reg, szString, iMatches, aMatches, pRegEx->iEFlags );
if( iResult == 0 )
{
for( i = 0; i < iMatches; i++ )
{
if( HB_REGMATCH_EO( aMatches, i ) != -1 )
iResult = i + 1;
}
}
else
iResult = -1;
if( szBuffer )
hb_xfree( szBuffer );
return iResult;
#else
HB_SYMBOL_UNUSED( pRegEx );
HB_SYMBOL_UNUSED( szString );
HB_SYMBOL_UNUSED( fFull );
return FALSE;
HB_SYMBOL_UNUSED( ulLen );
HB_SYMBOL_UNUSED( iMatches );
HB_SYMBOL_UNUSED( aMatches );
return -1;
#endif
}
HB_FUNC( HB_REGEXCOMP )
{
#ifdef _HB_REGEX_INTERNAL_
ULONG ulLen = hb_parclen( 1 );
if( ulLen == 0 )
@@ -186,7 +173,6 @@ HB_FUNC( HB_REGEXCOMP )
hb_gcUnlock( pRegEx );
}
}
#endif
}
HB_FUNC( HB_ISREGEX )
@@ -196,10 +182,8 @@ HB_FUNC( HB_ISREGEX )
HB_FUNC( HB_ATX )
{
#ifdef _HB_REGEX_INTERNAL_
char * pszString, * pszCopy = NULL;
char * pszString;
ULONG ulLen, ulStart, ulEnd;
regmatch_t aMatches[ 1 ];
PHB_REGEX pRegEx;
PHB_ITEM pString;
int iPCount = hb_pcount();
@@ -223,24 +207,20 @@ HB_FUNC( HB_ATX )
if( ulLen && ulStart <= ulLen && ulStart <= ulEnd )
{
if( ulEnd > 0 && ulEnd < ulLen && pszString[ ulEnd ] != 0 )
{
if( ulStart > 1 )
{
pszString += ulStart - 1;
ulEnd -= ulStart - 1;
}
pszCopy = ( char * ) hb_xgrab( ulEnd + 1 );
memcpy( pszCopy, pszString, ulEnd );
pszCopy[ ulEnd ] = '\0';
pszString = pszCopy;
}
HB_REGMATCH aMatches[ HB_REGMATCH_SIZE( 1 ) ];
if( regexec( &pRegEx->reg, pszString, 1, aMatches, 0 ) == 0 )
if( ulEnd < ulLen )
ulLen = ulEnd;
if( ulStart )
{
ulStart = aMatches[0].rm_so + 1;
ulLen = aMatches[0].rm_eo - aMatches[0].rm_so;
hb_retclen( pszString + aMatches[0].rm_so, ulLen );
--ulStart;
ulLen -= ulStart;
}
if( hb_regexec( pRegEx, pszString + ulStart, ulLen, 1, aMatches ) > 0 )
{
ulStart += HB_REGMATCH_SO( aMatches, 0 ) + 1;
ulLen = HB_REGMATCH_EO( aMatches, 0 ) - HB_REGMATCH_SO( aMatches, 0 );
hb_retclen( pszString + ulStart - 1, ulLen );
}
else
ulStart = ulLen = 0;
@@ -249,22 +229,17 @@ HB_FUNC( HB_ATX )
ulStart = ulLen = 0;
hb_regexFree( pRegEx );
if( pszCopy )
hb_xfree( pszCopy );
if( iPCount > 3 )
{
hb_stornl( ulStart, 4 );
if( iPCount > 4 )
hb_stornl( ulLen, 5 );
}
#endif
}
static BOOL hb_regex( int iRequest )
{
#ifdef _HB_REGEX_INTERNAL_
regmatch_t aMatches[ REGEX_MAX_GROUPS ];
HB_REGMATCH aMatches[ HB_REGMATCH_SIZE( REGEX_MAX_GROUPS ) ];
PHB_ITEM pRetArray, pMatch, pString;
int i, iMatches, iMaxMatch;
BOOL fResult = FALSE;
@@ -287,30 +262,22 @@ static BOOL hb_regex( int iRequest )
pszString = hb_itemGetCPtr( pString );
ulLen = hb_itemGetCLen( pString );
iMatches = 0;
iMaxMatch = iRequest == 0 || iRequest == 4 || iRequest == 5 ?
REGEX_MAX_GROUPS : 1;
aMatches[0].rm_so = 0;
aMatches[0].rm_eo = ulLen;
if( regexec( &pRegEx->reg, pszString, iMaxMatch, aMatches, 0 ) == 0 )
iMatches = hb_regexec( pRegEx, pszString, ulLen, iMaxMatch, aMatches );
if( iMatches > 0 )
{
switch ( iRequest )
{
case 0:
/* Count sucessful matches */
for( i = 0; i < iMaxMatch; i++ )
{
if( aMatches[i].rm_eo != -1 )
iMatches = i;
}
iMatches++;
pRetArray = hb_itemArrayNew( iMatches );
for( i = 0; i < iMatches; i++ )
{
if( aMatches[i].rm_eo > -1 )
if( HB_REGMATCH_EO( aMatches, i ) > -1 )
hb_itemPutCL( hb_arrayGetItemPtr( pRetArray, i + 1 ),
pszString + aMatches[i].rm_so,
aMatches[i].rm_eo - aMatches[i].rm_so );
pszString + HB_REGMATCH_SO( aMatches, i ),
HB_REGMATCH_EO( aMatches, i ) -
HB_REGMATCH_SO( aMatches, i ) );
else
hb_itemPutCL( hb_arrayGetItemPtr( pRetArray, i + 1 ), "", 0 );
}
@@ -319,8 +286,8 @@ static BOOL hb_regex( int iRequest )
break;
case 1: /* LIKE */
fResult = aMatches[0].rm_so == 0 &&
( ULONG ) aMatches[0].rm_eo == ulLen;
fResult = HB_REGMATCH_SO( aMatches, 0 ) == 0 &&
( ULONG ) HB_REGMATCH_EO( aMatches, 0 ) == ulLen;
break;
case 2: /* MATCH ( HAS ) */
@@ -331,16 +298,18 @@ static BOOL hb_regex( int iRequest )
iMaxMatch = hb_parni( 5 );
pRetArray = hb_itemArrayNew( 0 );
pMatch = hb_itemNew( NULL );
iMatches = 0;
do
{
hb_itemPutCL( pMatch, pszString, aMatches[0].rm_so );
hb_itemPutCL( pMatch, pszString, HB_REGMATCH_SO( aMatches, 0 ) );
hb_arrayAddForward( pRetArray, pMatch );
ulLen -= aMatches[0].rm_eo;
pszString += aMatches[ 0 ].rm_eo;
ulLen -= HB_REGMATCH_EO( aMatches, 0 );
pszString += HB_REGMATCH_EO( aMatches, 0 );
iMatches++;
}
while( aMatches[0].rm_eo && ulLen && ( iMaxMatch == 0 || iMatches < iMaxMatch ) &&
regexec( &pRegEx->reg, pszString, 1, aMatches, 0 ) == 0 );
while( HB_REGMATCH_EO( aMatches, 0 ) > 0 && ulLen &&
( iMaxMatch == 0 || iMatches < iMaxMatch ) &&
hb_regexec( pRegEx, pszString, ulLen, 1, aMatches ) > 0 );
/* last match must be done also in case that pszString is empty;
this would mean an empty split field at the end of the string */
@@ -356,27 +325,22 @@ static BOOL hb_regex( int iRequest )
break;
case 4: /* results AND positions */
/* Count sucessful matches */
for( i = 0; i < iMaxMatch; i++ )
{
if( aMatches[i].rm_eo != -1 )
iMatches = i;
}
iMatches++;
pRetArray = hb_itemArrayNew( iMatches );
for( i = 0; i < iMatches; i++ )
{
int iSO = HB_REGMATCH_SO( aMatches, i ),
iEO = HB_REGMATCH_EO( aMatches, i );
pMatch = hb_arrayGetItemPtr( pRetArray, i + 1 );
hb_arrayNew( pMatch, 3 );
if ( aMatches[i].rm_eo != -1 )
if( iEO != -1 )
{
/* matched string */
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + aMatches[i].rm_so, aMatches[i].rm_eo - aMatches[i].rm_so );
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + iSO, iEO - iSO );
/* begin of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), aMatches[i].rm_so + 1 );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), iSO + 1 );
/* End of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), aMatches[i].rm_eo );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), iEO );
}
else
{
@@ -397,19 +361,12 @@ static BOOL hb_regex( int iRequest )
BOOL fOnlyMatch = !ISLOG( 7 ) || hb_parl( 7 ); /* if TRUE returns only matches and sub-matches, not positions */
ULONG ulOffSet = 0;
int iCount = 0;
int iSO, iEO;
/* Set new array */
pRetArray = hb_itemArrayNew( 0 );
do
{
/* Count sucessful matches */
for( i = 0; i < iMaxMatch; i++ )
{
if( aMatches[i].rm_eo != -1 )
iMatches = i;
}
iMatches++;
/* If I want all matches */
if( iGetMatch == 0 || // Check boundaries
( iGetMatch < 0 || iGetMatch > iMatches ) )
@@ -417,18 +374,20 @@ static BOOL hb_regex( int iRequest )
pAtxArray = hb_itemArrayNew( iMatches );
for( i = 0; i < iMatches; i++ )
{
iSO = HB_REGMATCH_SO( aMatches, i );
iEO = HB_REGMATCH_EO( aMatches, i );
pMatch = hb_arrayGetItemPtr( pAtxArray, i + 1 );
if( !fOnlyMatch )
{
hb_arrayNew( pMatch, 3 );
if ( aMatches[i].rm_eo != -1 )
if ( iEO != -1 )
{
/* matched string */
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + aMatches[i].rm_so, aMatches[i].rm_eo - aMatches[i].rm_so );
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + iSO, iEO - iSO );
/* begin of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), ulOffSet + aMatches[i].rm_so + 1 );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), ulOffSet + iSO + 1 );
/* End of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), ulOffSet + aMatches[i].rm_eo );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), ulOffSet + iEO );
}
else
{
@@ -439,9 +398,9 @@ static BOOL hb_regex( int iRequest )
}
else
{
if( aMatches[i].rm_eo != -1 )
if( iEO != -1 )
/* matched string */
hb_itemPutCL( pMatch, pszString + aMatches[i].rm_so, aMatches[i].rm_eo - aMatches[i].rm_so );
hb_itemPutCL( pMatch, pszString + iSO, iEO - iSO );
else
hb_itemPutCL( pMatch, "", 0 );
}
@@ -452,18 +411,20 @@ static BOOL hb_regex( int iRequest )
else /* Here I get only single matches */
{
i = iGetMatch - 1;
iSO = HB_REGMATCH_SO( aMatches, i );
iEO = HB_REGMATCH_EO( aMatches, i );
pMatch = hb_itemNew( NULL );
if( !fOnlyMatch )
{
hb_arrayNew( pMatch, 3 );
if( aMatches[i].rm_eo != -1 )
if( iEO != -1 )
{
/* matched string */
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + aMatches[i].rm_so, aMatches[i].rm_eo - aMatches[i].rm_so );
hb_itemPutCL( hb_arrayGetItemPtr( pMatch, 1 ), pszString + iSO, iEO - iSO );
/* begin of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), ulOffSet + aMatches[i].rm_so + 1 );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 2 ), ulOffSet + iSO + 1 );
/* End of match */
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), ulOffSet + aMatches[i].rm_eo );
hb_itemPutNI( hb_arrayGetItemPtr( pMatch, 3 ), ulOffSet + iEO );
}
else
{
@@ -474,9 +435,9 @@ static BOOL hb_regex( int iRequest )
}
else
{
if( aMatches[i].rm_eo != -1 )
if( iEO != -1 )
/* matched string */
hb_itemPutCL( pMatch, pszString + aMatches[i].rm_so, aMatches[i].rm_eo - aMatches[i].rm_so );
hb_itemPutCL( pMatch, pszString + iSO, iEO - iSO );
else
hb_itemPutCL( pMatch, "", 0 );
}
@@ -484,13 +445,16 @@ static BOOL hb_regex( int iRequest )
hb_itemRelease( pMatch );
}
ulLen -= aMatches[0].rm_eo;
pszString += aMatches[ 0 ].rm_eo;
ulOffSet += aMatches[0].rm_eo;
iEO = HB_REGMATCH_EO( aMatches, 0 );
if( iEO == -1 )
break;
ulLen -= iEO;
pszString += iEO;
ulOffSet += iEO;
iCount++;
}
while( aMatches[0].rm_eo && ulLen && ( iMax == 0 || iCount < iMax ) &&
regexec( &pRegEx->reg, pszString, iMaxMatch, aMatches, 0 ) == 0 );
while( iEO && ulLen && ( iMax == 0 || iCount < iMax ) &&
( iMatches = hb_regexec( pRegEx, pszString, ulLen, iMaxMatch, aMatches ) ) > 0 );
hb_itemRelease( hb_itemReturnForward( pRetArray ) );
fResult = TRUE;
break;
@@ -507,10 +471,6 @@ static BOOL hb_regex( int iRequest )
hb_regexFree( pRegEx );
return fResult;
#else
HB_SYMBOL_UNUSED( iRequest );
return FALSE;
#endif
}
/* Returns array of Match + Sub-Matches. */
@@ -567,3 +527,31 @@ HB_FUNC( HB_REGEXALL )
{
hb_regex( 5 );
}
#if defined( HB_PCRE_REGEX )
static void * hb_pcre_grab( size_t size )
{
return hb_xgrab( size );
}
#endif
HB_CALL_ON_STARTUP_BEGIN( _hb_regex_init_ )
#if defined( HB_PCRE_REGEX )
pcre_malloc = hb_pcre_grab;
pcre_free = hb_xfree;
#endif
hb_regexInit( hb_regfree, hb_regcomp, hb_regexec );
HB_CALL_ON_STARTUP_END( _hb_regex_init_ )
#if defined(HB_PRAGMA_STARTUP)
#pragma startup _hb_regex_init_
#elif defined(HB_MSC_STARTUP)
#if _MSC_VER >= 1010
#pragma data_seg( ".CRT$XIY" )
#pragma comment( linker, "/Merge:.CRT=.data" )
#else
#pragma data_seg( "XIY" )
#endif
static HB_$INITSYM hb_vm_auto_regex_init_ = _hb_regex_init_;
#pragma data_seg()
#endif

164
harbour/source/rtl/hbregexc.c Normal file
View File

@@ -0,0 +1,164 @@
/*
* $Id$
*/
/*
* Harbour Project source code:
*
*
* Copyright 2007 Przemyslaw Czerpak <druzus / at / priv.onet.pl>
* www - http://www.harbour-project.org
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this software; see the file COPYING. If not, write to
* the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
* Boston, MA 02111-1307 USA (or visit the web site http://www.gnu.org/).
*
* As a special exception, the Harbour Project gives permission for
* additional uses of the text contained in its release of Harbour.
*
* The exception is that, if you link the Harbour libraries with other
* files to produce an executable, this does not by itself cause the
* resulting executable to be covered by the GNU General Public License.
* Your use of that executable is in no way restricted on account of
* linking the Harbour library code into it.
*
* This exception does not however invalidate any other reasons why
* the executable file might be covered by the GNU General Public License.
*
* This exception applies only to the code released by the Harbour
* Project under the name Harbour. If you copy code from other
* Harbour Project or Free Software Foundation releases into a copy of
* Harbour, as the General Public License permits, the exception does
* not apply to the code that you add in this way. To avoid misleading
* anyone as to the status of such modified files, you must delete
* this exception notice from them.
*
* If you write modifications of your own for Harbour, it is your choice
* whether to permit this exception to apply to your modifications.
* If you do not wish that, delete this exception notice.
*
*/
/* #define HB_PCRE_REGEX */
#define _HB_REGEX_INTERNAL_
#include "hbregex.h"
#include "hbapiitm.h"
#include "hbapierr.h"
static void hb_regfree( PHB_REGEX pRegEx )
{
HB_SYMBOL_UNUSED( pRegEx );
}
static int hb_regcomp( PHB_REGEX pRegEx, const char * szRegEx )
{
HB_SYMBOL_UNUSED( pRegEx );
HB_SYMBOL_UNUSED( szRegEx );
return -1;
}
static int hb_regexec( PHB_REGEX pRegEx, const char * szString, ULONG ulLen,
int iMatches, HB_REGMATCH * aMatches )
{
HB_SYMBOL_UNUSED( pRegEx );
HB_SYMBOL_UNUSED( szString );
HB_SYMBOL_UNUSED( ulLen );
HB_SYMBOL_UNUSED( iMatches );
HB_SYMBOL_UNUSED( aMatches );
return -1;
}
static HB_REG_FREE s_reg_free = hb_regfree;
static HB_REG_COMP s_reg_comp = hb_regcomp;
static HB_REG_EXEC s_reg_exec = hb_regexec;
void hb_regexInit( HB_REG_FREE pFree, HB_REG_COMP pComp, HB_REG_EXEC pExec )
{
s_reg_free = pFree;
s_reg_comp = pComp;
s_reg_exec = pExec;
}
/* This releases regex when called from the garbage collector */
HB_GARBAGE_FUNC( hb_regexRelease )
{
( s_reg_free )( ( PHB_REGEX ) Cargo );
}
PHB_REGEX hb_regexCompile( const char *szRegEx, ULONG ulLen, int iFlags )
{
PHB_REGEX pRegEx;
HB_SYMBOL_UNUSED( ulLen );
pRegEx = ( PHB_REGEX ) hb_gcAlloc( sizeof( HB_REGEX ), hb_regexRelease );
hb_gcLock( pRegEx );
memset( pRegEx, 0, sizeof( HB_REGEX ) );
pRegEx->fFree = TRUE;
pRegEx->iFlags = iFlags;
if( ( s_reg_comp )( pRegEx, szRegEx ) != 0 )
{
hb_gcFree( pRegEx );
pRegEx = NULL;
}
return pRegEx;
}
PHB_REGEX hb_regexGet( PHB_ITEM pRegExItm, int iFlags )
{
PHB_REGEX pRegEx = NULL;
if( pRegExItm )
{
if( HB_IS_POINTER( pRegExItm ) )
{
pRegEx = ( PHB_REGEX ) hb_itemGetPtrGC( pRegExItm, hb_regexRelease );
}
else if( HB_IS_STRING( pRegExItm ) )
{
ULONG ulLen = hb_itemGetCLen( pRegExItm );
char * szRegEx = hb_itemGetCPtr( pRegExItm );
if( ulLen > 0 )
pRegEx = hb_regexCompile( szRegEx, ulLen, iFlags );
}
}
if( !pRegEx )
hb_errRT_BASE_SubstR( EG_ARG, 3012, "Invalid Regular expression", &hb_errFuncName, 1, pRegExItm );
return pRegEx;
}
void hb_regexFree( PHB_REGEX pRegEx )
{
if( pRegEx && pRegEx->fFree )
{
( s_reg_free )( pRegEx );
hb_gcFree( pRegEx );
}
}
BOOL hb_regexMatch( PHB_REGEX pRegEx, const char *szString, ULONG ulLen, BOOL fFull )
{
HB_REGMATCH aMatches[ HB_REGMATCH_SIZE( 1 ) ];
BOOL fMatch;
fMatch = ( s_reg_exec )( pRegEx, szString, ulLen, 1, aMatches ) > 0;
return fMatch && ( !fFull ||
( HB_REGMATCH_SO( aMatches, 0 ) == 0 &&
HB_REGMATCH_EO( aMatches, 0 ) == ( int ) ulLen ) );
}

2
harbour/source/rtl/strmatch.c
View File

@@ -282,7 +282,7 @@ BOOL hb_strMatchRegExp( const char * szString, const char * szPattern )
if( pRegEx )
{
BOOL fMatch;
fMatch = hb_regexMatch( pRegEx, szString, TRUE );
fMatch = hb_regexMatch( pRegEx, szString, strlen( szString ), TRUE );
hb_regexFree( pRegEx );
return fMatch;
}

7
harbour/utils/hbrun/Makefile
View File

@@ -26,5 +26,12 @@ LIBS=\
pp \
compiler \
common \
hbpcre \
ifeq ($(findstring -DHB_PCRE_REGEX, $(C_USR)),)
ifeq ($(findstring -DHB_POSIX_REGEX, $(C_USR)),)
LIBS += hbpcre
endif
endif
include $(TOP)$(ROOT)config/bin.cf