generic-library/poco
1
0
Fork 0
mirror of https://github.com/pocoproject/poco.git synced 2025-10-16 18:56:52 +02:00
Code Issues Projects Releases Wiki Activity

upgraded to PCRE 7.8

Browse Source
This commit is contained in:
Guenter Obiltschnig
2008-09-18 11:08:06 +00:00
parent de1518b091
commit ec1997c2e5
26 changed files with 18119 additions and 16844 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Foundation/Foundation_vs71.vcproj
View File

@@ -1712,7 +1712,7 @@
RelativePath=".\src\pcre_try_flipped.c">
</File>
<File
RelativePath=".\src\pcre_ucp_searchfuncs.c">
RelativePath=".\src\pcre_ucd.c">
</File>
<File
RelativePath=".\src\pcre_valid_utf8.c">
@@ -1750,12 +1750,6 @@
<File
RelativePath=".\src\ucp.h">
</File>
<File
RelativePath=".\src\ucpinternal.h">
</File>
<File
RelativePath=".\src\ucptable.h">
</File>
</Filter>
</Filter>
<Filter

10
Foundation/Foundation_vs80.vcproj
View File

@@ -2193,14 +2193,6 @@
RelativePath=".\src\ucp.h"
>
</File>
<File
RelativePath=".\src\ucpinternal.h"
>
</File>
<File
RelativePath=".\src\ucptable.h"
>
</File>
</Filter>
<Filter
Name="Source Files"
@@ -2266,7 +2258,7 @@
>
</File>
<File
RelativePath=".\src\pcre_ucp_searchfuncs.c"
RelativePath=".\src\pcre_ucd.c"
>
</File>
<File

10
Foundation/Foundation_vs90.vcproj
View File

@@ -2184,14 +2184,6 @@
RelativePath=".\src\ucp.h"
>
</File>
<File
RelativePath=".\src\ucpinternal.h"
>
</File>
<File
RelativePath=".\src\ucptable.h"
>
</File>
</Filter>
<Filter
Name="Source Files"
@@ -2257,7 +2249,7 @@
>
</File>
<File
RelativePath=".\src\pcre_ucp_searchfuncs.c"
RelativePath=".\src\pcre_ucd.c"
>
</File>
<File

15
Foundation/include/Poco/Unicode.h
View File

@@ -1,7 +1,7 @@
//
// Unicode.h
//
// $Id: //poco/svn/Foundation/include/Poco/Unicode.h#2 $
// $Id: //poco/1.3/Foundation/include/Poco/Unicode.h#1 $
//
// Library: Foundation
// Package: Text
@@ -174,7 +174,18 @@ public:
UCP_CUNEIFORM,
UCP_NKO,
UCP_PHAGS_PA,
UCP_PHOENICIAN
UCP_PHOENICIAN,
UCP_CARIAN,
UCP_CHAM,
UCP_KAYAH_LI,
UCP_LEPCHA,
UCP_LYCIAN,
UCP_LYDIAN,
UCP_OL_CHIKI,
UCP_REJANG,
UCP_SAURASHTRA,
UCP_SUNDANESE,
UCP_VAI
};
struct CharacterProperties

17
Foundation/src/Unicode.cpp
View File

@@ -1,7 +1,7 @@
//
// Unicode.cpp
//
// $Id: //poco/svn/Foundation/src/Unicode.cpp#2 $
// $Id: //poco/1.3/Foundation/src/Unicode.cpp#2 $
//
// Library: Foundation
// Package: Text
@@ -39,6 +39,7 @@
extern "C"
{
#include "pcre_config.h"
#include "pcre_internal.h"
}
@@ -48,12 +49,10 @@ namespace Poco {
void Unicode::properties(int ch, CharacterProperties& props)
{
int type;
int script;
int category = _pcre_ucp_findprop(static_cast<unsigned>(ch), &type, &script);
props.category = static_cast<CharacterCategory>(category);
props.type = static_cast<CharacterType>(type);
props.script = static_cast<Script>(script);
const ucd_record* ucd = GET_UCD(ch);
props.category = static_cast<CharacterCategory>(_pcre_ucp_gentype[ucd->chartype]);
props.type = static_cast<CharacterType>(ucd->chartype);
props.script = static_cast<Script>(ucd->script);
}
@@ -76,7 +75,7 @@ bool Unicode::isUpper(int ch)
int Unicode::toLower(int ch)
{
if (isUpper(ch))
return static_cast<int>(_pcre_ucp_othercase(static_cast<unsigned>(ch)));
return static_cast<int>(UCD_OTHERCASE(static_cast<unsigned>(ch)));
else
return ch;
}
@@ -85,7 +84,7 @@ int Unicode::toLower(int ch)
int Unicode::toUpper(int ch)
{
if (isLower(ch))
return static_cast<int>(_pcre_ucp_othercase(static_cast<unsigned>(ch)));
return static_cast<int>(UCD_OTHERCASE(static_cast<unsigned>(ch)));
else
return ch;
}

44
Foundation/src/pcre.h
View File

@@ -5,7 +5,7 @@
/* This is the public header file for the PCRE library, to be #included by
applications that call the PCRE functions.
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -42,19 +42,25 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE_MAJOR 7
#define PCRE_MINOR 1
#define PCRE_MINOR 8
#define PCRE_PRERELEASE
#define PCRE_DATE 2007-04-24
#define PCRE_DATE 2008-09-05
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE, the appropriate
export setting is defined in pcre_internal.h, which includes this file. So we
don't change an existing definition of PCRE_EXP_DECL. */
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllimport)
#if defined(_WIN32) && !defined(PCRE_STATIC)
# ifndef PCRE_EXP_DECL
# define PCRE_EXP_DECL extern __declspec(dllimport)
# endif
# ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern __declspec(dllimport)
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN __declspec(dllimport)
# endif
# endif
#endif
@@ -63,9 +69,18 @@ don't change an existing definition of PCRE_EXP_DECL. */
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DECL extern
# endif
#endif
#ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN
# endif
#endif
@@ -107,6 +122,9 @@ extern "C" {
#define PCRE_NEWLINE_CRLF 0x00300000
#define PCRE_NEWLINE_ANY 0x00400000
#define PCRE_NEWLINE_ANYCRLF 0x00500000
#define PCRE_BSR_ANYCRLF 0x00800000
#define PCRE_BSR_UNICODE 0x01000000
#define PCRE_JAVASCRIPT_COMPAT 0x02000000
/* Exec-time and get/set-time error codes */
@@ -132,7 +150,7 @@ extern "C" {
#define PCRE_ERROR_DFA_WSSIZE (-19)
#define PCRE_ERROR_DFA_RECURSE (-20)
#define PCRE_ERROR_RECURSIONLIMIT (-21)
#define PCRE_ERROR_NULLWSLIMIT (-22)
#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
#define PCRE_ERROR_BADNEWLINE (-23)
/* Request types for pcre_fullinfo() */
@@ -150,6 +168,9 @@ extern "C" {
#define PCRE_INFO_NAMETABLE 9
#define PCRE_INFO_STUDYSIZE 10
#define PCRE_INFO_DEFAULT_TABLES 11
#define PCRE_INFO_OKPARTIAL 12
#define PCRE_INFO_JCHANGED 13
#define PCRE_INFO_HASCRORLF 14
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
@@ -162,6 +183,7 @@ compatible. */
#define PCRE_CONFIG_STACKRECURSE 5
#define PCRE_CONFIG_UNICODE_PROPERTIES 6
#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
#define PCRE_CONFIG_BSR 8
/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
these bits, just add new ones on the end, in order to remain compatible. */

3
Foundation/src/pcre_chartables.c
View File

@@ -14,12 +14,13 @@ example ISO-8859-1. When dftables is run, it creates these tables in the
current locale. If PCRE is configured with --enable-rebuild-chartables, this
happens automatically.
The following #include is present because without it gcc 4.x may remove the
The following #includes are present because without the gcc 4.x may remove the
array definition from the final binary if PCRE is built into a static library
and dead code stripping is activated. This leads to link errors. Pulling in the
header ensures that the array gets flagged as "someone outside this compilation
unit might reference this" and so it will always be supplied to the linker. */
#include "pcre_config.h"
#include "pcre_internal.h"
const unsigned char _pcre_default_tables[] = {

1586
Foundation/src/pcre_compile.c
View File

File diff suppressed because it is too large Load Diff

1404
Foundation/src/pcre_exec.c
View File

File diff suppressed because it is too large Load Diff

25
Foundation/src/pcre_fullinfo.c
View File

@@ -2,11 +2,11 @@
* Perl-Compatible Regular Expressions *
*************************************************/
/*PCRE is a library of functions to support regular expressions whose syntax
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -42,6 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
information about a compiled pattern. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -61,7 +62,7 @@ Arguments:
Returns: 0 if data returned, negative on error
*/
PCRE_EXP_DEFN int
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what,
void *where)
{
@@ -106,8 +107,8 @@ switch (what)
case PCRE_INFO_FIRSTBYTE:
*((int *)where) =
((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
break;
/* Make sure we pass back the pointer to the bit vector in the external
@@ -121,7 +122,7 @@ switch (what)
case PCRE_INFO_LASTLITERAL:
*((int *)where) =
((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1;
((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1;
break;
case PCRE_INFO_NAMEENTRYSIZE:
@@ -140,6 +141,18 @@ switch (what)
*((const uschar **)where) = (const uschar *)(_pcre_default_tables);
break;
case PCRE_INFO_OKPARTIAL:
*((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0;
break;
case PCRE_INFO_JCHANGED:
*((int *)where) = (re->flags & PCRE_JCHANGED) != 0;
break;
case PCRE_INFO_HASCRORLF:
*((int *)where) = (re->flags & PCRE_HASCRORLF) != 0;
break;
default: return PCRE_ERROR_BADOPTION;
}

3
Foundation/src/pcre_globals.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -46,6 +46,7 @@ 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 "pcre_config.h"
#include "pcre_internal.h"
#ifndef VPCOMPAT

407
Foundation/src/pcre_internal.h
View File

@@ -7,7 +7,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -67,10 +67,6 @@ be absolutely sure we get our version. */
#endif
/* Get the definitions provided by running "configure" */
#include "pcre_config.h"
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
@@ -112,7 +108,7 @@ PCRE_EXP_DATA_DEFN only if they are not already set. */
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifdef DLL_EXPORT
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllexport)
# define PCRE_EXP_DEFN __declspec(dllexport)
# define PCRE_EXP_DATA_DEFN __declspec(dllexport)
@@ -121,7 +117,6 @@ PCRE_EXP_DATA_DEFN only if they are not already set. */
# define PCRE_EXP_DEFN
# define PCRE_EXP_DATA_DEFN
# endif
#
# else
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
@@ -137,6 +132,20 @@ PCRE_EXP_DATA_DEFN only if they are not already set. */
# endif
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE_CALL_CONVENTION
#define PCRE_CALL_CONVENTION
#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
@@ -145,16 +154,20 @@ preprocessor time in standard C environments. */
#if USHRT_MAX == 65535
typedef unsigned short pcre_uint16;
typedef short pcre_int16;
#elif UINT_MAX == 65535
typedef unsigned int pcre_uint16;
typedef int pcre_int16;
#else
#error Cannot determine a type for 16-bit unsigned integers
#endif
#if UINT_MAX == 4294967295
typedef unsigned int pcre_uint32;
typedef int pcre_int32;
#elif ULONG_MAX == 4294967295
typedef unsigned long int pcre_uint32;
typedef long int pcre_int32;
#else
#error Cannot determine a type for 32-bit unsigned integers
#endif
@@ -363,7 +376,9 @@ capturing parenthesis numbers in back references. */
/* 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. */
byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should
never be called in byte mode. To make sure it can never even appear when UTF-8
support is omitted, we don't even define it. */
#ifndef SUPPORT_UTF8
#define GETCHAR(c, eptr) c = *eptr;
@@ -371,7 +386,7 @@ byte-mode, and more complicated ones for UTF-8 characters. */
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
#define BACKCHAR(eptr)
/* #define BACKCHAR(eptr) */
#else /* SUPPORT_UTF8 */
@@ -464,9 +479,10 @@ if there are extra bytes. This is called when we know we are in UTF-8 mode. */
}
/* If the pointer is not at the start of a character, move it back until
it is. Called only in UTF-8 mode. */
it is. This is called only in UTF-8 mode - we don't put a test within the macro
because almost all calls are already within a block of UTF-8 only code. */
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--;
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--
#endif
@@ -483,17 +499,16 @@ Standard C system should have one. */
#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
/* Private options flags start at the most significant end of the four bytes.
The public options defined in pcre.h start at the least significant end. Make
sure they don't overlap! The bits are getting a bit scarce now -- when we run
out, there is a dummy word in the structure that could be used for the private
bits. */
/* Private flags containing information about the compiled regex. They used to
live at the top end of the options word, but that got almost full, so now they
are in a 16-bit flags word. */
#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */
#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_JCHANGED 0x08000000 /* j option changes within regex */
#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */
#define PCRE_FIRSTSET 0x0002 /* first_byte is set */
#define PCRE_REQCHSET 0x0004 /* req_byte is set */
#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */
#define PCRE_JCHANGED 0x0010 /* j option used in regex */
#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */
/* Options for the "extra" block produced by pcre_study(). */
@@ -509,15 +524,17 @@ time, run time, or study time, respectively. */
(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| \
PCRE_DUPNAMES|PCRE_NEWLINE_BITS)
PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
PCRE_JAVASCRIPT_COMPAT)
#define PUBLIC_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
PCRE_PARTIAL|PCRE_NEWLINE_BITS)
PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
#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|PCRE_NEWLINE_BITS)
PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \
PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
#define PUBLIC_STUDY_OPTIONS 0 /* None defined */
@@ -542,12 +559,15 @@ 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 */
/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in
environments where these macros are defined elsewhere. */
#ifndef FALSE
typedef int BOOL;
#define FALSE 0
#define TRUE 1
#endif
/* Escape items that are just an encoding of a particular data value. */
@@ -598,26 +618,25 @@ contain UTF-8 characters with values greater than 255. */
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 backreferences (\1, \2, \3, etc).
There 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. */
corresponds to "." rather than an escape sequence, and another for OP_ALLANY
(which is used for [^] in JavaScript compatibility mode).
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_R, ESC_X, ESC_Z, ESC_z,
ESC_E, ESC_Q, ESC_k, ESC_REF };
The final escape must be ESC_REF as subsequent values are used for
backreferences (\1, \2, \3, etc). There 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_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
ESC_W, ESC_w, ESC_dum1, ESC_dum2, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H,
ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_g, ESC_k,
ESC_REF };
/* 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
/* Opcode table: 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.
To keep stored, compiled patterns compatible, new opcodes should be added
immediately before OP_BRA, where (since release 7.0) a gap is left for this
purpose.
*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions
that follow must also be updated to match. There is also a table called
"coptable" in pcre_dfa_exec.c that must be updated. */
@@ -629,133 +648,155 @@ enum {
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_ANYNL, /* 15 \R (any newline sequence) */
OP_EXTUNI, /* 16 \X (extended Unicode sequence */
OP_EODN, /* 17 End of data or \n at end of data: \Z. */
OP_EOD, /* 18 End of data: \z */
OP_SET_SOM, /* 3 Set start of match (\K) */
OP_NOT_WORD_BOUNDARY, /* 4 \B */
OP_WORD_BOUNDARY, /* 5 \b */
OP_NOT_DIGIT, /* 6 \D */
OP_DIGIT, /* 7 \d */
OP_NOT_WHITESPACE, /* 8 \S */
OP_WHITESPACE, /* 9 \s */
OP_NOT_WORDCHAR, /* 10 \W */
OP_WORDCHAR, /* 11 \w */
OP_ANY, /* 12 Match any character (subject to DOTALL) */
OP_ALLANY, /* 13 Match any character (not subject to DOTALL) */
OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */
OP_NOTPROP, /* 15 \P (not Unicode property) */
OP_PROP, /* 16 \p (Unicode property) */
OP_ANYNL, /* 17 \R (any newline sequence) */
OP_NOT_HSPACE, /* 18 \H (not horizontal whitespace) */
OP_HSPACE, /* 19 \h (horizontal whitespace) */
OP_NOT_VSPACE, /* 20 \V (not vertical whitespace) */
OP_VSPACE, /* 21 \v (vertical whitespace) */
OP_EXTUNI, /* 22 \X (extended Unicode sequence */
OP_EODN, /* 23 End of data or \n at end of data: \Z. */
OP_EOD, /* 24 End of data: \z */
OP_OPT, /* 19 Set runtime options */
OP_CIRC, /* 20 Start of line - varies with multiline switch */
OP_DOLL, /* 21 End of line - varies with multiline switch */
OP_CHAR, /* 22 Match one character, casefully */
OP_CHARNC, /* 23 Match one character, caselessly */
OP_NOT, /* 24 Match one character, not the following one */
OP_OPT, /* 25 Set runtime options */
OP_CIRC, /* 26 Start of line - varies with multiline switch */
OP_DOLL, /* 27 End of line - varies with multiline switch */
OP_CHAR, /* 28 Match one character, casefully */
OP_CHARNC, /* 29 Match one character, caselessly */
OP_NOT, /* 30 Match one character, not the following one */
OP_STAR, /* 25 The maximizing and minimizing versions of */
OP_MINSTAR, /* 26 these six opcodes must come in pairs, with */
OP_PLUS, /* 27 the minimizing one second. */
OP_MINPLUS, /* 28 This first set applies to single characters.*/
OP_QUERY, /* 29 */
OP_MINQUERY, /* 30 */
OP_STAR, /* 31 The maximizing and minimizing versions of */
OP_MINSTAR, /* 32 these six opcodes must come in pairs, with */
OP_PLUS, /* 33 the minimizing one second. */
OP_MINPLUS, /* 34 This first set applies to single characters.*/
OP_QUERY, /* 35 */
OP_MINQUERY, /* 36 */
OP_UPTO, /* 31 From 0 to n matches */
OP_MINUPTO, /* 32 */
OP_EXACT, /* 33 Exactly n matches */
OP_UPTO, /* 37 From 0 to n matches */
OP_MINUPTO, /* 38 */
OP_EXACT, /* 39 Exactly n matches */
OP_POSSTAR, /* 34 Possessified star */
OP_POSPLUS, /* 35 Possessified plus */
OP_POSQUERY, /* 36 Posesssified query */
OP_POSUPTO, /* 37 Possessified upto */
OP_POSSTAR, /* 40 Possessified star */
OP_POSPLUS, /* 41 Possessified plus */
OP_POSQUERY, /* 42 Posesssified query */
OP_POSUPTO, /* 43 Possessified upto */
OP_NOTSTAR, /* 38 The maximizing and minimizing versions of */
OP_NOTMINSTAR, /* 39 these six opcodes must come in pairs, with */
OP_NOTPLUS, /* 40 the minimizing one second. They must be in */
OP_NOTMINPLUS, /* 41 exactly the same order as those above. */
OP_NOTQUERY, /* 42 This set applies to "not" single characters. */
OP_NOTMINQUERY, /* 43 */
OP_NOTSTAR, /* 44 The maximizing and minimizing versions of */
OP_NOTMINSTAR, /* 45 these six opcodes must come in pairs, with */
OP_NOTPLUS, /* 46 the minimizing one second. They must be in */
OP_NOTMINPLUS, /* 47 exactly the same order as those above. */
OP_NOTQUERY, /* 48 This set applies to "not" single characters. */
OP_NOTMINQUERY, /* 49 */
OP_NOTUPTO, /* 44 From 0 to n matches */
OP_NOTMINUPTO, /* 45 */
OP_NOTEXACT, /* 46 Exactly n matches */
OP_NOTUPTO, /* 50 From 0 to n matches */
OP_NOTMINUPTO, /* 51 */
OP_NOTEXACT, /* 52 Exactly n matches */
OP_NOTPOSSTAR, /* 47 Possessified versions */
OP_NOTPOSPLUS, /* 48 */
OP_NOTPOSQUERY, /* 49 */
OP_NOTPOSUPTO, /* 50 */
OP_NOTPOSSTAR, /* 53 Possessified versions */
OP_NOTPOSPLUS, /* 54 */
OP_NOTPOSQUERY, /* 55 */
OP_NOTPOSUPTO, /* 56 */
OP_TYPESTAR, /* 51 The maximizing and minimizing versions of */
OP_TYPEMINSTAR, /* 52 these six opcodes must come in pairs, with */
OP_TYPEPLUS, /* 53 the minimizing one second. These codes must */
OP_TYPEMINPLUS, /* 54 be in exactly the same order as those above. */
OP_TYPEQUERY, /* 55 This set applies to character types such as \d */
OP_TYPEMINQUERY, /* 56 */
OP_TYPESTAR, /* 57 The maximizing and minimizing versions of */
OP_TYPEMINSTAR, /* 58 these six opcodes must come in pairs, with */
OP_TYPEPLUS, /* 59 the minimizing one second. These codes must */
OP_TYPEMINPLUS, /* 60 be in exactly the same order as those above. */
OP_TYPEQUERY, /* 61 This set applies to character types such as \d */
OP_TYPEMINQUERY, /* 62 */
OP_TYPEUPTO, /* 57 From 0 to n matches */
OP_TYPEMINUPTO, /* 58 */
OP_TYPEEXACT, /* 59 Exactly n matches */
OP_TYPEUPTO, /* 63 From 0 to n matches */
OP_TYPEMINUPTO, /* 64 */
OP_TYPEEXACT, /* 65 Exactly n matches */
OP_TYPEPOSSTAR, /* 60 Possessified versions */
OP_TYPEPOSPLUS, /* 61 */
OP_TYPEPOSQUERY, /* 62 */
OP_TYPEPOSUPTO, /* 63 */
OP_TYPEPOSSTAR, /* 66 Possessified versions */
OP_TYPEPOSPLUS, /* 67 */
OP_TYPEPOSQUERY, /* 68 */
OP_TYPEPOSUPTO, /* 69 */
OP_CRSTAR, /* 64 The maximizing and minimizing versions of */
OP_CRMINSTAR, /* 65 all these opcodes must come in pairs, with */
OP_CRPLUS, /* 66 the minimizing one second. These codes must */
OP_CRMINPLUS, /* 67 be in exactly the same order as those above. */
OP_CRQUERY, /* 68 These are for character classes and back refs */
OP_CRMINQUERY, /* 69 */
OP_CRRANGE, /* 70 These are different to the three sets above. */
OP_CRMINRANGE, /* 71 */
OP_CRSTAR, /* 70 The maximizing and minimizing versions of */
OP_CRMINSTAR, /* 71 all these opcodes must come in pairs, with */
OP_CRPLUS, /* 72 the minimizing one second. These codes must */
OP_CRMINPLUS, /* 73 be in exactly the same order as those above. */
OP_CRQUERY, /* 74 These are for character classes and back refs */
OP_CRMINQUERY, /* 75 */
OP_CRRANGE, /* 76 These are different to the three sets above. */
OP_CRMINRANGE, /* 77 */
OP_CLASS, /* 72 Match a character class, chars < 256 only */
OP_NCLASS, /* 73 Same, but the bitmap was created from a negative
OP_CLASS, /* 78 Match a character class, chars < 256 only */
OP_NCLASS, /* 79 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, /* 74 Extended class for handling UTF-8 chars within the
OP_XCLASS, /* 80 Extended class for handling UTF-8 chars within the
class. This does both positive and negative. */
OP_REF, /* 75 Match a back reference */
OP_RECURSE, /* 76 Match a numbered subpattern (possibly recursive) */
OP_CALLOUT, /* 77 Call out to external function if provided */
OP_REF, /* 81 Match a back reference */
OP_RECURSE, /* 82 Match a numbered subpattern (possibly recursive) */
OP_CALLOUT, /* 83 Call out to external function if provided */
OP_ALT, /* 78 Start of alternation */
OP_KET, /* 79 End of group that doesn't have an unbounded repeat */
OP_KETRMAX, /* 80 These two must remain together and in this */
OP_KETRMIN, /* 81 order. They are for groups the repeat for ever. */
OP_ALT, /* 84 Start of alternation */
OP_KET, /* 85 End of group that doesn't have an unbounded repeat */
OP_KETRMAX, /* 86 These two must remain together and in this */
OP_KETRMIN, /* 87 order. They are for groups the repeat for ever. */
/* The assertions must come before BRA, CBRA, ONCE, and COND.*/
OP_ASSERT, /* 82 Positive lookahead */
OP_ASSERT_NOT, /* 83 Negative lookahead */
OP_ASSERTBACK, /* 84 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 85 Negative lookbehind */
OP_REVERSE, /* 86 Move pointer back - used in lookbehind assertions */
OP_ASSERT, /* 88 Positive lookahead */
OP_ASSERT_NOT, /* 89 Negative lookahead */
OP_ASSERTBACK, /* 90 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 91 Negative lookbehind */
OP_REVERSE, /* 92 Move pointer back - used in lookbehind assertions */
/* ONCE, BRA, CBRA, 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, /* 87 Atomic group */
OP_BRA, /* 88 Start of non-capturing bracket */
OP_CBRA, /* 89 Start of capturing bracket */
OP_COND, /* 90 Conditional group */
OP_ONCE, /* 93 Atomic group */
OP_BRA, /* 94 Start of non-capturing bracket */
OP_CBRA, /* 95 Start of capturing bracket */
OP_COND, /* 96 Conditional group */
/* These three must follow the previous three, in the same order. There's a
check for >= SBRA to distinguish the two sets. */
OP_SBRA, /* 91 Start of non-capturing bracket, check empty */
OP_SCBRA, /* 92 Start of capturing bracket, check empty */
OP_SCOND, /* 93 Conditional group, check empty */
OP_SBRA, /* 97 Start of non-capturing bracket, check empty */
OP_SCBRA, /* 98 Start of capturing bracket, check empty */
OP_SCOND, /* 99 Conditional group, check empty */
OP_CREF, /* 94 Used to hold a capture number as condition */
OP_RREF, /* 95 Used to hold a recursion number as condition */
OP_DEF, /* 96 The DEFINE condition */
OP_CREF, /* 100 Used to hold a capture number as condition */
OP_RREF, /* 101 Used to hold a recursion number as condition */
OP_DEF, /* 102 The DEFINE condition */
OP_BRAZERO, /* 97 These two must remain together and in this */
OP_BRAMINZERO /* 98 order. */
OP_BRAZERO, /* 103 These two must remain together and in this */
OP_BRAMINZERO, /* 104 order. */
/* These are backtracking control verbs */
OP_PRUNE, /* 105 */
OP_SKIP, /* 106 */
OP_THEN, /* 107 */
OP_COMMIT, /* 108 */
/* These are forced failure and success verbs */
OP_FAIL, /* 109 */
OP_ACCEPT, /* 110 */
/* This is used to skip a subpattern with a {0} quantifier */
OP_SKIPZERO /* 111 */
};
@@ -763,10 +804,10 @@ enum {
for debugging. The macro is referenced only in pcre_printint.c. */
#define OP_NAME_LIST \
"End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \
"\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \
"notprop", "prop", "anynl", "extuni", \
"\\Z", "\\z", \
"End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \
"\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte", \
"notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \
"extuni", "\\Z", "\\z", \
"Opt", "^", "$", "char", "charnc", "not", \
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
"*+","++", "?+", "{", \
@@ -778,8 +819,10 @@ for debugging. The macro is referenced only in pcre_printint.c. */
"class", "nclass", "xclass", "Ref", "Recurse", "Callout", \
"Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \
"AssertB", "AssertB not", "Reverse", \
"Once", "Bra 0", "Bra", "Cond", "SBra 0", "SBra", "SCond", \
"Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero"
"Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \
"Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \
"*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT", \
"Skip zero"
/* This macro defines the length of fixed length operations in the compiled
@@ -793,9 +836,11 @@ 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 */ \
3, 3, 1, 1, /* NOTPROP, PROP, EXTUNI, ANYNL */ \
1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \
1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \
1, 1, 1, /* Any, AllAny, Anybyte */ \
3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \
1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \
1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \
2, /* Char - the minimum length */ \
2, /* Charnc - the minimum length */ \
@@ -841,6 +886,8 @@ in UTF-8 mode. The code that uses this table must know about such things. */
3, /* RREF */ \
1, /* DEF */ \
1, 1, /* BRAZERO, BRAMINZERO */ \
1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \
1, 1, 1 /* FAIL, ACCEPT, SKIPZERO */
/* A magic value for OP_RREF to indicate the "any recursion" condition. */
@@ -855,7 +902,8 @@ enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9,
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, ERR48, ERR49,
ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57 };
ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
ERR60, ERR61, ERR62, ERR63, ERR64 };
/* 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
@@ -877,9 +925,9 @@ 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_uint32 options; /* Public options */
pcre_uint16 flags; /* Private flags */
pcre_uint16 dummy1; /* For future use */
pcre_uint16 top_bracket;
pcre_uint16 top_backref;
pcre_uint16 first_byte;
@@ -918,12 +966,14 @@ typedef struct compile_data {
uschar *name_table; /* The name/number table */
int names_found; /* Number of entries so far */
int name_entry_size; /* Size of each entry */
int bracount; /* Count of capturing parens */
int bracount; /* Count of capturing parens as we compile */
int final_bracount; /* Saved value after first pass */
int top_backref; /* Maximum back reference */
unsigned int backref_map; /* Bitmap of low back refs */
int external_options; /* External (initial) options */
int external_flags; /* External flag bits to be set */
int req_varyopt; /* "After variable item" flag for reqbyte */
BOOL nopartial; /* Set TRUE if partial won't work */
BOOL had_accept; /* (*ACCEPT) encountered */
int nltype; /* Newline type */
int nllen; /* Newline string length */
uschar nl[4]; /* Newline string when fixed length */
@@ -944,21 +994,11 @@ 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 */
USPTR save_start; /* Old value of md->start_match */
USPTR save_start; /* Old value of mstart */
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_exec.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 building a chain of data for holding the values of the subject
pointer at the start of each subpattern, so as to detect when an empty string
has been matched by a subpattern - to break infinite loops. */
@@ -988,14 +1028,16 @@ typedef struct match_data {
BOOL notbol; /* NOTBOL flag */
BOOL noteol; /* NOTEOL flag */
BOOL utf8; /* UTF8 flag */
BOOL jscript_compat; /* JAVASCRIPT_COMPAT 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 */
BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */
const uschar *start_code; /* For use when recursing */
USPTR start_subject; /* Start of the subject string */
USPTR end_subject; /* End of the subject string */
USPTR start_match; /* Start of this match attempt */
USPTR start_match_ptr; /* Start of matched string */
USPTR 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 */
@@ -1004,7 +1046,6 @@ typedef struct match_data {
int eptrn; /* Next free eptrblock */
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
@@ -1029,7 +1070,7 @@ typedef struct dfa_match_data {
#define ctype_letter 0x02
#define ctype_digit 0x04
#define ctype_xdigit 0x08
#define ctype_word 0x10 /* alphameric or '_' */
#define ctype_word 0x10 /* alphanumeric 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
@@ -1057,10 +1098,12 @@ total length. */
#define tables_length (ctypes_offset + 256)
/* Layout of the UCP type table that translates property names into types and
codes. */
codes. Each entry used to point directly to a name, but to reduce the number of
relocations in shared libraries, it now has an offset into a single string
instead. */
typedef struct {
const char *name;
pcre_uint16 name_offset;
pcre_uint16 type;
pcre_uint16 value;
} ucp_type_table;
@@ -1078,6 +1121,7 @@ extern const uschar _pcre_utf8_table4[];
extern const int _pcre_utf8_table1_size;
extern const char _pcre_utt_names[];
extern const ucp_type_table _pcre_utt[];
extern const int _pcre_utt_size;
@@ -1095,13 +1139,38 @@ extern BOOL _pcre_is_newline(const uschar *, int, const uschar *,
extern int _pcre_ord2utf8(int, uschar *);
extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *,
const pcre_study_data *, pcre_study_data *);
extern int _pcre_ucp_findprop(const unsigned int, int *, int *);
extern unsigned int _pcre_ucp_othercase(const unsigned int);
extern int _pcre_valid_utf8(const uschar *, int);
extern BOOL _pcre_was_newline(const uschar *, int, const uschar *,
int *, BOOL);
extern BOOL _pcre_xclass(int, const uschar *);
/* Unicode character database (UCD) */
typedef struct {
uschar script;
uschar chartype;
pcre_int32 other_case;
} ucd_record;
extern const ucd_record _pcre_ucd_records[];
extern const uschar _pcre_ucd_stage1[];
extern const pcre_uint16 _pcre_ucd_stage2[];
extern const int _pcre_ucp_gentype[];
/* UCD access macros */
#define UCD_BLOCK_SIZE 128
#define GET_UCD(ch) (_pcre_ucd_records + \
_pcre_ucd_stage2[_pcre_ucd_stage1[(ch) / UCD_BLOCK_SIZE] * \
UCD_BLOCK_SIZE + ch % UCD_BLOCK_SIZE])
#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype
#define UCD_SCRIPT(ch) GET_UCD(ch)->script
#define UCD_CATEGORY(ch) _pcre_ucp_gentype[UCD_CHARTYPE(ch)]
#define UCD_OTHERCASE(ch) (ch + GET_UCD(ch)->other_case)
#endif
/* End of pcre_internal.h */

5
Foundation/src/pcre_maketables.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -45,7 +45,8 @@ compilation of dftables.c, in which case the macro DFTABLES is defined. */
#ifndef DFTABLES
#include "pcre_internal.h"
# include "pcre_config.h"
# include "pcre_internal.h"
#endif

7
Foundation/src/pcre_newline.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -47,6 +47,7 @@ and NLTYPE_ANY. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -124,12 +125,16 @@ _pcre_was_newline(const uschar *ptr, int type, const uschar *startptr,
{
int c;
ptr--;
#ifdef SUPPORT_UTF8
if (utf8)
{
BACKCHAR(ptr);
GETCHAR(c, ptr);
}
else c = *ptr;
#else /* no UTF-8 support */
c = *ptr;
#endif /* SUPPORT_UTF8 */
if (type == NLTYPE_ANYCRLF) switch(c)
{

10
Foundation/src/pcre_ord2utf8.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE.
/* This file contains a private PCRE function that converts an ordinal
character value into a UTF8 string. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -75,8 +75,10 @@ for (j = i; j > 0; j--)
*buffer = _pcre_utf8_table2[i] | cvalue;
return i + 1;
#else
return 0; /* Keep compiler happy; this function won't ever be */
#endif /* called when SUPPORT_UTF8 is not defined. */
(void)(cvalue); /* Keep compiler happy; this function won't ever be */
(void)(buffer); /* called when SUPPORT_UTF8 is not defined. */
return 0;
#endif
}
/* End of pcre_ord2utf8.c */

17
Foundation/src/pcre_study.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -42,6 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
supporting functions. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -213,6 +214,14 @@ do
tcode += 1 + LINK_SIZE;
break;
/* SKIPZERO skips the bracket. */
case OP_SKIPZERO:
tcode++;
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:
@@ -337,6 +346,7 @@ do
switch(tcode[1])
{
case OP_ANY:
case OP_ALLANY:
return SSB_FAIL;
case OP_NOT_DIGIT:
@@ -491,7 +501,7 @@ Returns: pointer to a pcre_extra block, with study_data filled in and the
NULL on error or if no optimization possible
*/
PCRE_EXP_DEFN pcre_extra *
PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION
pcre_study(const pcre *external_re, int options, const char **errorptr)
{
uschar start_bits[32];
@@ -523,7 +533,8 @@ code = (uschar *)re + re->name_table_offset +
a multiline pattern that matches only at "line starts", no further processing
at present. */
if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
if ((re->options & PCRE_ANCHORED) != 0 ||
(re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
return NULL;
/* Set the character tables in the block that is passed around */

368
Foundation/src/pcre_tables.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -44,6 +44,7 @@ uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
clashes with the library. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -83,115 +84,266 @@ const uschar _pcre_utf8_table4[] = {
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 type and code values. It
is searched by binary chop, so must be in collating sequence of name. */
/* Table to translate from particular type value to the general value. */
const int _pcre_ucp_gentype[] = {
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
ucp_P, ucp_P, /* Ps, Po */
ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
};
/* The pcre_utt[] table below translates Unicode property names into type and
code values. It is searched by binary chop, so must be in collating sequence of
name. Originally, the table contained pointers to the name strings in the first
field of each entry. However, that leads to a large number of relocations when
a shared library is dynamically loaded. A significant reduction is made by
putting all the names into a single, large string and then using offsets in the
table itself. Maintenance is more error-prone, but frequent changes to this
data are unlikely.
July 2008: There is now a script called maint/GenerateUtt.py which can be used
to generate this data instead of maintaining it entirely by hand. */
const char _pcre_utt_names[] =
"Any\0"
"Arabic\0"
"Armenian\0"
"Balinese\0"
"Bengali\0"
"Bopomofo\0"
"Braille\0"
"Buginese\0"
"Buhid\0"
"C\0"
"Canadian_Aboriginal\0"
"Carian\0"
"Cc\0"
"Cf\0"
"Cham\0"
"Cherokee\0"
"Cn\0"
"Co\0"
"Common\0"
"Coptic\0"
"Cs\0"
"Cuneiform\0"
"Cypriot\0"
"Cyrillic\0"
"Deseret\0"
"Devanagari\0"
"Ethiopic\0"
"Georgian\0"
"Glagolitic\0"
"Gothic\0"
"Greek\0"
"Gujarati\0"
"Gurmukhi\0"
"Han\0"
"Hangul\0"
"Hanunoo\0"
"Hebrew\0"
"Hiragana\0"
"Inherited\0"
"Kannada\0"
"Katakana\0"
"Kayah_Li\0"
"Kharoshthi\0"
"Khmer\0"
"L\0"
"L&\0"
"Lao\0"
"Latin\0"
"Lepcha\0"
"Limbu\0"
"Linear_B\0"
"Ll\0"
"Lm\0"
"Lo\0"
"Lt\0"
"Lu\0"
"Lycian\0"
"Lydian\0"
"M\0"
"Malayalam\0"
"Mc\0"
"Me\0"
"Mn\0"
"Mongolian\0"
"Myanmar\0"
"N\0"
"Nd\0"
"New_Tai_Lue\0"
"Nko\0"
"Nl\0"
"No\0"
"Ogham\0"
"Ol_Chiki\0"
"Old_Italic\0"
"Old_Persian\0"
"Oriya\0"
"Osmanya\0"
"P\0"
"Pc\0"
"Pd\0"
"Pe\0"
"Pf\0"
"Phags_Pa\0"
"Phoenician\0"
"Pi\0"
"Po\0"
"Ps\0"
"Rejang\0"
"Runic\0"
"S\0"
"Saurashtra\0"
"Sc\0"
"Shavian\0"
"Sinhala\0"
"Sk\0"
"Sm\0"
"So\0"
"Sundanese\0"
"Syloti_Nagri\0"
"Syriac\0"
"Tagalog\0"
"Tagbanwa\0"
"Tai_Le\0"
"Tamil\0"
"Telugu\0"
"Thaana\0"
"Thai\0"
"Tibetan\0"
"Tifinagh\0"
"Ugaritic\0"
"Vai\0"
"Yi\0"
"Z\0"
"Zl\0"
"Zp\0"
"Zs\0";
const ucp_type_table _pcre_utt[] = {
{ "Any", PT_ANY, 0 },
{ "Arabic", PT_SC, ucp_Arabic },
{ "Armenian", PT_SC, ucp_Armenian },
{ "Balinese", PT_SC, ucp_Balinese },
{ "Bengali", PT_SC, ucp_Bengali },
{ "Bopomofo", PT_SC, ucp_Bopomofo },
{ "Braille", PT_SC, ucp_Braille },
{ "Buginese", PT_SC, ucp_Buginese },
{ "Buhid", PT_SC, ucp_Buhid },
{ "C", PT_GC, ucp_C },
{ "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal },
{ "Cc", PT_PC, ucp_Cc },
{ "Cf", PT_PC, ucp_Cf },
{ "Cherokee", PT_SC, ucp_Cherokee },
{ "Cn", PT_PC, ucp_Cn },
{ "Co", PT_PC, ucp_Co },
{ "Common", PT_SC, ucp_Common },
{ "Coptic", PT_SC, ucp_Coptic },
{ "Cs", PT_PC, ucp_Cs },
{ "Cuneiform", PT_SC, ucp_Cuneiform },
{ "Cypriot", PT_SC, ucp_Cypriot },
{ "Cyrillic", PT_SC, ucp_Cyrillic },
{ "Deseret", PT_SC, ucp_Deseret },
{ "Devanagari", PT_SC, ucp_Devanagari },
{ "Ethiopic", PT_SC, ucp_Ethiopic },
{ "Georgian", PT_SC, ucp_Georgian },
{ "Glagolitic", PT_SC, ucp_Glagolitic },
{ "Gothic", PT_SC, ucp_Gothic },
{ "Greek", PT_SC, ucp_Greek },
{ "Gujarati", PT_SC, ucp_Gujarati },
{ "Gurmukhi", PT_SC, ucp_Gurmukhi },
{ "Han", PT_SC, ucp_Han },
{ "Hangul", PT_SC, ucp_Hangul },
{ "Hanunoo", PT_SC, ucp_Hanunoo },
{ "Hebrew", PT_SC, ucp_Hebrew },
{ "Hiragana", PT_SC, ucp_Hiragana },
{ "Inherited", PT_SC, ucp_Inherited },
{ "Kannada", PT_SC, ucp_Kannada },
{ "Katakana", PT_SC, ucp_Katakana },
{ "Kharoshthi", PT_SC, ucp_Kharoshthi },
{ "Khmer", PT_SC, ucp_Khmer },
{ "L", PT_GC, ucp_L },
{ "L&", PT_LAMP, 0 },
{ "Lao", PT_SC, ucp_Lao },
{ "Latin", PT_SC, ucp_Latin },
{ "Limbu", PT_SC, ucp_Limbu },
{ "Linear_B", PT_SC, ucp_Linear_B },
{ "Ll", PT_PC, ucp_Ll },
{ "Lm", PT_PC, ucp_Lm },
{ "Lo", PT_PC, ucp_Lo },
{ "Lt", PT_PC, ucp_Lt },
{ "Lu", PT_PC, ucp_Lu },
{ "M", PT_GC, ucp_M },
{ "Malayalam", PT_SC, ucp_Malayalam },
{ "Mc", PT_PC, ucp_Mc },
{ "Me", PT_PC, ucp_Me },
{ "Mn", PT_PC, ucp_Mn },
{ "Mongolian", PT_SC, ucp_Mongolian },
{ "Myanmar", PT_SC, ucp_Myanmar },
{ "N", PT_GC, ucp_N },
{ "Nd", PT_PC, ucp_Nd },
{ "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue },
{ "Nko", PT_SC, ucp_Nko },
{ "Nl", PT_PC, ucp_Nl },
{ "No", PT_PC, ucp_No },
{ "Ogham", PT_SC, ucp_Ogham },
{ "Old_Italic", PT_SC, ucp_Old_Italic },
{ "Old_Persian", PT_SC, ucp_Old_Persian },
{ "Oriya", PT_SC, ucp_Oriya },
{ "Osmanya", PT_SC, ucp_Osmanya },
{ "P", PT_GC, ucp_P },
{ "Pc", PT_PC, ucp_Pc },
{ "Pd", PT_PC, ucp_Pd },
{ "Pe", PT_PC, ucp_Pe },
{ "Pf", PT_PC, ucp_Pf },
{ "Phags_Pa", PT_SC, ucp_Phags_Pa },
{ "Phoenician", PT_SC, ucp_Phoenician },
{ "Pi", PT_PC, ucp_Pi },
{ "Po", PT_PC, ucp_Po },
{ "Ps", PT_PC, ucp_Ps },
{ "Runic", PT_SC, ucp_Runic },
{ "S", PT_GC, ucp_S },
{ "Sc", PT_PC, ucp_Sc },
{ "Shavian", PT_SC, ucp_Shavian },
{ "Sinhala", PT_SC, ucp_Sinhala },
{ "Sk", PT_PC, ucp_Sk },
{ "Sm", PT_PC, ucp_Sm },
{ "So", PT_PC, ucp_So },
{ "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri },
{ "Syriac", PT_SC, ucp_Syriac },
{ "Tagalog", PT_SC, ucp_Tagalog },
{ "Tagbanwa", PT_SC, ucp_Tagbanwa },
{ "Tai_Le", PT_SC, ucp_Tai_Le },
{ "Tamil", PT_SC, ucp_Tamil },
{ "Telugu", PT_SC, ucp_Telugu },
{ "Thaana", PT_SC, ucp_Thaana },
{ "Thai", PT_SC, ucp_Thai },
{ "Tibetan", PT_SC, ucp_Tibetan },
{ "Tifinagh", PT_SC, ucp_Tifinagh },
{ "Ugaritic", PT_SC, ucp_Ugaritic },
{ "Yi", PT_SC, ucp_Yi },
{ "Z", PT_GC, ucp_Z },
{ "Zl", PT_PC, ucp_Zl },
{ "Zp", PT_PC, ucp_Zp },
{ "Zs", PT_PC, ucp_Zs }
{ 0, PT_ANY, 0 },
{ 4, PT_SC, ucp_Arabic },
{ 11, PT_SC, ucp_Armenian },
{ 20, PT_SC, ucp_Balinese },
{ 29, PT_SC, ucp_Bengali },
{ 37, PT_SC, ucp_Bopomofo },
{ 46, PT_SC, ucp_Braille },
{ 54, PT_SC, ucp_Buginese },
{ 63, PT_SC, ucp_Buhid },
{ 69, PT_GC, ucp_C },
{ 71, PT_SC, ucp_Canadian_Aboriginal },
{ 91, PT_SC, ucp_Carian },
{ 98, PT_PC, ucp_Cc },
{ 101, PT_PC, ucp_Cf },
{ 104, PT_SC, ucp_Cham },
{ 109, PT_SC, ucp_Cherokee },
{ 118, PT_PC, ucp_Cn },
{ 121, PT_PC, ucp_Co },
{ 124, PT_SC, ucp_Common },
{ 131, PT_SC, ucp_Coptic },
{ 138, PT_PC, ucp_Cs },
{ 141, PT_SC, ucp_Cuneiform },
{ 151, PT_SC, ucp_Cypriot },
{ 159, PT_SC, ucp_Cyrillic },
{ 168, PT_SC, ucp_Deseret },
{ 176, PT_SC, ucp_Devanagari },
{ 187, PT_SC, ucp_Ethiopic },
{ 196, PT_SC, ucp_Georgian },
{ 205, PT_SC, ucp_Glagolitic },
{ 216, PT_SC, ucp_Gothic },
{ 223, PT_SC, ucp_Greek },
{ 229, PT_SC, ucp_Gujarati },
{ 238, PT_SC, ucp_Gurmukhi },
{ 247, PT_SC, ucp_Han },
{ 251, PT_SC, ucp_Hangul },
{ 258, PT_SC, ucp_Hanunoo },
{ 266, PT_SC, ucp_Hebrew },
{ 273, PT_SC, ucp_Hiragana },
{ 282, PT_SC, ucp_Inherited },
{ 292, PT_SC, ucp_Kannada },
{ 300, PT_SC, ucp_Katakana },
{ 309, PT_SC, ucp_Kayah_Li },
{ 318, PT_SC, ucp_Kharoshthi },
{ 329, PT_SC, ucp_Khmer },
{ 335, PT_GC, ucp_L },
{ 337, PT_LAMP, 0 },
{ 340, PT_SC, ucp_Lao },
{ 344, PT_SC, ucp_Latin },
{ 350, PT_SC, ucp_Lepcha },
{ 357, PT_SC, ucp_Limbu },
{ 363, PT_SC, ucp_Linear_B },
{ 372, PT_PC, ucp_Ll },
{ 375, PT_PC, ucp_Lm },
{ 378, PT_PC, ucp_Lo },
{ 381, PT_PC, ucp_Lt },
{ 384, PT_PC, ucp_Lu },
{ 387, PT_SC, ucp_Lycian },
{ 394, PT_SC, ucp_Lydian },
{ 401, PT_GC, ucp_M },
{ 403, PT_SC, ucp_Malayalam },
{ 413, PT_PC, ucp_Mc },
{ 416, PT_PC, ucp_Me },
{ 419, PT_PC, ucp_Mn },
{ 422, PT_SC, ucp_Mongolian },
{ 432, PT_SC, ucp_Myanmar },
{ 440, PT_GC, ucp_N },
{ 442, PT_PC, ucp_Nd },
{ 445, PT_SC, ucp_New_Tai_Lue },
{ 457, PT_SC, ucp_Nko },
{ 461, PT_PC, ucp_Nl },
{ 464, PT_PC, ucp_No },
{ 467, PT_SC, ucp_Ogham },
{ 473, PT_SC, ucp_Ol_Chiki },
{ 482, PT_SC, ucp_Old_Italic },
{ 493, PT_SC, ucp_Old_Persian },
{ 505, PT_SC, ucp_Oriya },
{ 511, PT_SC, ucp_Osmanya },
{ 519, PT_GC, ucp_P },
{ 521, PT_PC, ucp_Pc },
{ 524, PT_PC, ucp_Pd },
{ 527, PT_PC, ucp_Pe },
{ 530, PT_PC, ucp_Pf },
{ 533, PT_SC, ucp_Phags_Pa },
{ 542, PT_SC, ucp_Phoenician },
{ 553, PT_PC, ucp_Pi },
{ 556, PT_PC, ucp_Po },
{ 559, PT_PC, ucp_Ps },
{ 562, PT_SC, ucp_Rejang },
{ 569, PT_SC, ucp_Runic },
{ 575, PT_GC, ucp_S },
{ 577, PT_SC, ucp_Saurashtra },
{ 588, PT_PC, ucp_Sc },
{ 591, PT_SC, ucp_Shavian },
{ 599, PT_SC, ucp_Sinhala },
{ 607, PT_PC, ucp_Sk },
{ 610, PT_PC, ucp_Sm },
{ 613, PT_PC, ucp_So },
{ 616, PT_SC, ucp_Sundanese },
{ 626, PT_SC, ucp_Syloti_Nagri },
{ 639, PT_SC, ucp_Syriac },
{ 646, PT_SC, ucp_Tagalog },
{ 654, PT_SC, ucp_Tagbanwa },
{ 663, PT_SC, ucp_Tai_Le },
{ 670, PT_SC, ucp_Tamil },
{ 676, PT_SC, ucp_Telugu },
{ 683, PT_SC, ucp_Thaana },
{ 690, PT_SC, ucp_Thai },
{ 695, PT_SC, ucp_Tibetan },
{ 703, PT_SC, ucp_Tifinagh },
{ 712, PT_SC, ucp_Ugaritic },
{ 721, PT_SC, ucp_Vai },
{ 725, PT_SC, ucp_Yi },
{ 728, PT_GC, ucp_Z },
{ 730, PT_PC, ucp_Zl },
{ 733, PT_PC, ucp_Zp },
{ 736, PT_PC, ucp_Zs }
};
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);

4
Foundation/src/pcre_try_flipped.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -43,6 +43,7 @@ see if it was compiled with the opposite endianness. If so, it uses an
auxiliary local function to flip the appropriate bytes. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -104,6 +105,7 @@ if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER)
*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->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags));
internal_re->top_bracket =
(pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket));
internal_re->top_backref =

2608
Foundation/src/pcre_ucd.c Normal file
View File

File diff suppressed because it is too large Load Diff

175
Foundation/src/pcre_ucp_searchfuncs.c
View File

@@ -1,175 +0,0 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains code for searching the table of Unicode character
properties. */
#include "pcre_internal.h"
#include "ucp.h" /* Category definitions */
#include "ucpinternal.h" /* Internal table details */
#include "ucptable.h" /* The table itself */
/* Table to translate from particular type value to the general value. */
static const int ucp_gentype[] = {
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
ucp_P, ucp_P, /* Ps, Po */
ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
};
/*************************************************
* Search table and return type *
*************************************************/
/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed
character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc.
Arguments:
c the character value
type_ptr the detailed character type is returned here
script_ptr the script is returned here
Returns: the character type category
*/
int
_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr)
{
int bot = 0;
int top = sizeof(ucp_table)/sizeof(cnode);
int mid;
/* The table is searched using a binary chop. You might think that using
intermediate variables to hold some of the common expressions would speed
things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
makes things a lot slower. */
for (;;)
{
if (top <= bot)
{
*type_ptr = ucp_Cn;
*script_ptr = ucp_Common;
return ucp_C;
}
mid = (bot + top) >> 1;
if (c == (ucp_table[mid].f0 & f0_charmask)) break;
if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
else
{
if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
c <= (ucp_table[mid].f0 & f0_charmask) +
(ucp_table[mid].f1 & f1_rangemask)) break;
bot = mid + 1;
}
}
/* Found an entry in the table. Set the script and detailed type values, and
return the general type. */
*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift;
*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift;
return ucp_gentype[*type_ptr];
}
/*************************************************
* Search table and return other case *
*************************************************/
/* If the given character is a letter, and there is another case for the
letter, return the other case. Otherwise, return -1.
Arguments:
c the character value
Returns: the other case or NOTACHAR if none
*/
unsigned int
_pcre_ucp_othercase(const unsigned int c)
{
int bot = 0;
int top = sizeof(ucp_table)/sizeof(cnode);
int mid, offset;
/* The table is searched using a binary chop. You might think that using
intermediate variables to hold some of the common expressions would speed
things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
makes things a lot slower. */
for (;;)
{
if (top <= bot) return -1;
mid = (bot + top) >> 1;
if (c == (ucp_table[mid].f0 & f0_charmask)) break;
if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
else
{
if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
c <= (ucp_table[mid].f0 & f0_charmask) +
(ucp_table[mid].f1 & f1_rangemask)) break;
bot = mid + 1;
}
}
/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise
return the other case if there is one, else NOTACHAR. */
if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR;
offset = ucp_table[mid].f1 & f1_casemask;
if ((offset & f1_caseneg) != 0) offset |= f1_caseneg;
return (offset == 0)? NOTACHAR : c + offset;
}
/* End of pcre_ucp_searchfuncs.c */

48
Foundation/src/pcre_valid_utf8.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -42,6 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
strings. */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -55,6 +56,13 @@ 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.
Originally, this function checked according to RFC 2279, allowing for values in
the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in
the canonical format. Once somebody had pointed out RFC 3629 to me (it
obsoletes 2279), additional restrictions were applied. The values are now
limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
subrange 0xd000 to 0xdfff is excluded.
Arguments:
string points to the string
length length of string, or -1 if the string is zero-terminated
@@ -81,31 +89,48 @@ for (p = string; length-- > 0; p++)
register int c = *p;
if (c < 128) continue;
if (c < 0xc0) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab || ab > 3) 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 */
/* Check for overlong sequences for each different length, and for the
excluded range 0xd000 to 0xdfff. */
switch (ab)
{
/* Check for xx00 000x */
/* Check for xx00 000x (overlong sequence) */
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 */
/* Check for 1110 0000, xx0x xxxx (overlong sequence) or
1110 1101, 1010 xxxx (0xd000 - 0xdfff) */
case 2:
if (c == 0xe0 && (*p & 0x20) == 0) return p - string;
if ((c == 0xe0 && (*p & 0x20) == 0) ||
(c == 0xed && *p >= 0xa0))
return p - string;
break;
/* Check for 1111 0000, xx00 xxxx */
/* Check for 1111 0000, xx00 xxxx (overlong sequence) or
greater than 0x0010ffff (f4 8f bf bf) */
case 3:
if (c == 0xf0 && (*p & 0x30) == 0) return p - string;
if ((c == 0xf0 && (*p & 0x30) == 0) ||
(c > 0xf4 ) ||
(c == 0xf4 && *p > 0x8f))
return p - string;
break;
#if 0
/* These cases can no longer occur, as we restrict to a maximum of four
bytes nowadays. Leave the code here in case we ever want to add an option
for longer sequences. */
/* Check for 1111 1000, xx00 0xxx */
case 4:
if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
@@ -116,6 +141,8 @@ for (p = string; length-- > 0; p++)
if (c == 0xfe || c == 0xff ||
(c == 0xfc && (*p & 0x3c) == 0)) return p - string;
break;
#endif
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */
@@ -124,6 +151,9 @@ for (p = string; length-- > 0; p++)
if ((*(++p) & 0xc0) != 0x80) return p - string;
}
}
#else
(void)(string); /* Keep picky compilers happy */
(void)(length);
#endif
return -1;

14
Foundation/src/pcre_xclass.c
View File

@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2007 University of Cambridge
Copyright (c) 1997-2008 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -43,6 +43,7 @@ class (one that contains characters whose values are > 255). It is used by both
pcre_exec() and pcre_def_exec(). */
#include "pcre_config.h"
#include "pcre_internal.h"
@@ -100,8 +101,7 @@ while ((t = *data++) != XCL_END)
#ifdef SUPPORT_UCP
else /* XCL_PROP & XCL_NOTPROP */
{
int chartype, script;
int category = _pcre_ucp_findprop(c, &chartype, &script);
const ucd_record * prop = GET_UCD(c);
switch(*data)
{
@@ -110,20 +110,20 @@ while ((t = *data++) != XCL_END)
break;
case PT_LAMP:
if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) ==
if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt) ==
(t == XCL_PROP)) return !negated;
break;
case PT_GC:
if ((data[1] == category) == (t == XCL_PROP)) return !negated;
if ((data[1] == _pcre_ucp_gentype[prop->chartype]) == (t == XCL_PROP)) return !negated;
break;
case PT_PC:
if ((data[1] == chartype) == (t == XCL_PROP)) return !negated;
if ((data[1] == prop->chartype) == (t == XCL_PROP)) return !negated;
break;
case PT_SC:
if ((data[1] == script) == (t == XCL_PROP)) return !negated;
if ((data[1] == prop->script) == (t == XCL_PROP)) return !negated;
break;
/* This should never occur, but compilers may mutter if there is no

23
Foundation/src/ucp.h
View File

@@ -121,11 +121,24 @@ enum {
ucp_Tifinagh,
ucp_Ugaritic,
ucp_Yi,
ucp_Balinese, /* New for Unicode 5.0.0 */
ucp_Cuneiform, /* New for Unicode 5.0.0 */
ucp_Nko, /* New for Unicode 5.0.0 */
ucp_Phags_Pa, /* New for Unicode 5.0.0 */
ucp_Phoenician /* New for Unicode 5.0.0 */
/* New for Unicode 5.0: */
ucp_Balinese,
ucp_Cuneiform,
ucp_Nko,
ucp_Phags_Pa,
ucp_Phoenician,
/* New for Unicode 5.1: */
ucp_Carian,
ucp_Cham,
ucp_Kayah_Li,
ucp_Lepcha,
ucp_Lycian,
ucp_Lydian,
ucp_Ol_Chiki,
ucp_Rejang,
ucp_Saurashtra,
ucp_Sundanese,
ucp_Vai
};
#endif

92
Foundation/src/ucpinternal.h
View File

@@ -1,92 +0,0 @@
/*************************************************
* Unicode Property Table handler *
*************************************************/
#ifndef _UCPINTERNAL_H
#define _UCPINTERNAL_H
/* Internal header file defining the layout of the bits in each pair of 32-bit
words that form a data item in the table. */
typedef struct cnode {
pcre_uint32 f0;
pcre_uint32 f1;
} cnode;
/* Things for the f0 field */
#define f0_scriptmask 0xff000000 /* Mask for script field */
#define f0_scriptshift 24 /* Shift for script value */
#define f0_rangeflag 0x00f00000 /* Flag for a range item */
#define f0_charmask 0x001fffff /* Mask for code point value */
/* Things for the f1 field */
#define f1_typemask 0xfc000000 /* Mask for char type field */
#define f1_typeshift 26 /* Shift for the type field */
#define f1_rangemask 0x0000ffff /* Mask for a range offset */
#define f1_casemask 0x0000ffff /* Mask for a case offset */
#define f1_caseneg 0xffff8000 /* Bits for negation */
/* The data consists of a vector of structures of type cnode. The two unsigned
32-bit integers are used as follows:
(f0) (1) The most significant byte holds the script number. The numbers are
defined by the enum in ucp.h.
(2) The 0x00800000 bit is set if this entry defines a range of characters.
It is not set if this entry defines a single character
(3) The 0x00600000 bits are spare.
(4) The 0x001fffff bits contain the code point. No Unicode code point will
ever be greater than 0x0010ffff, so this should be OK for ever.
(f1) (1) The 0xfc000000 bits contain the character type number. The numbers are
defined by an enum in ucp.h.
(2) The 0x03ff0000 bits are spare.
(3) The 0x0000ffff bits contain EITHER the unsigned offset to the top of
range if this entry defines a range, OR the *signed* offset to the
character's "other case" partner if this entry defines a single
character. There is no partner if the value is zero.
-------------------------------------------------------------------------------
| script (8) |.|.|.| codepoint (21) || type (6) |.|.| spare (8) | offset (16) |
-------------------------------------------------------------------------------
| | | | |
| | |-> spare | |-> spare
| | |
| |-> spare |-> spare
|
|-> range flag
The upper/lower casing information is set only for characters that come in
pairs. The non-one-to-one mappings in the Unicode data are ignored.
When searching the data, proceed as follows:
(1) Set up for a binary chop search.
(2) If the top is not greater than the bottom, the character is not in the
table. Its type must therefore be "Cn" ("Undefined").
(3) Find the middle vector element.
(4) Extract the code point and compare. If equal, we are done.
(5) If the test character is smaller, set the top to the current point, and
goto (2).
(6) If the current entry defines a range, compute the last character by adding
the offset, and see if the test character is within the range. If it is,
we are done.
(7) Otherwise, set the bottom to one element past the current point and goto
(2).
*/
#endif /* _UCPINTERNAL_H */
/* End of ucpinternal.h */

3068
Foundation/src/ucptable.h
View File

File diff suppressed because it is too large Load Diff