Flummi/amxmodx
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #69 from Arkshine/update-regex

Browse Source 
Update regex module
This commit is contained in:
Vincent Herbet
2014-07-18 18:14:56 +02:00
parent b4359d0f53 5aba776da5
commit 3a5cb29e67
385 changed files with 295012 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
dlls/regex/AMBuilder
View File

@ -10,12 +10,15 @@ elif builder.target_platform == 'mac':
elif builder.target_platform == 'windows':
binary.compiler.postlink += [binary.Dep('lib_win\\pcre.lib')]
binary.compiler.defines += ['PCRE_STATIC']
binary.compiler.defines += [
'PCRE_STATIC',
'HAVE_STDINT_H',
]
binary.sources = [
'sdk/amxxmodule.cpp',
'module.cpp',
'CRegEx.cpp',
'utils.cpp',
]
AMXX.modules += [builder.Add(binary)]

721
dlls/regex/CRegEx.cpp
View File

@ -1,7 +1,41 @@
/* AMX Mod X
* Regular Expressions Module
*
* by the AMX Mod X Development Team
*
* This file is part of AMX Mod X.
*
*
* 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 of the License, 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 program; if not, write to the Free Software Foundation,
* Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* In addition, as a special exception, the author gives permission to
* link the code of this program with the Half-Life Game Engine ("HL
* Engine") and Modified Game Libraries ("MODs") developed by Valve,
* L.L.C ("Valve"). You must obey the GNU General Public License in all
* respects for all of the code used other than the HL Engine and MODs
* from Valve. If you modify this file, you may extend this exception
* to your version of the file, but you are not obligated to do so. If
* you do not wish to do so, delete this exception statement from your
* version.
*/
#include "amxxmodule.h"
#include "pcre.h"
#include "CRegEx.h"
#include <string.h>
#include "amxxmodule.h"
#include <ctype.h>
#include "utils.h"
RegEx::RegEx()
{
@ -10,7 +44,10 @@ RegEx::RegEx()
re = NULL;
mFree = true;
subject = NULL;
mSubStrings = 0;
mSubStrings.clear();
mMatchesSubs.clear();
mSubsNameTable.clear();
mNumSubpatterns = 0;
}
void RegEx::Clear()
@ -22,9 +59,12 @@ void RegEx::Clear()
re = NULL;
mFree = true;
if (subject)
delete [] subject;
delete[] subject;
subject = NULL;
mSubStrings = 0;
mSubStrings.clear();
mMatchesSubs.clear();
mSubsNameTable.clear();
mNumSubpatterns = 0;
}
RegEx::~RegEx()
@ -97,57 +137,198 @@ int RegEx::Compile(const char *pattern, const char* flags)
return 1;
}
int RegEx::Compile(const char *pattern, int iFlags)
{
if (!mFree)
Clear();
re = pcre_compile(pattern, iFlags, &mError, &mErrorOffset, NULL);
if (re == NULL)
{
return 0;
}
mFree = false;
/**
* Retrieve the number of captured groups
* including the full match.
*/
pcre_fullinfo(re, NULL, PCRE_INFO_CAPTURECOUNT, &mNumSubpatterns);
++mNumSubpatterns;
/**
* Build the table with the named groups,
* which contain an index and a name per group.
*/
MakeSubpatternsTable(mNumSubpatterns);
return 1;
}
int RegEx::Match(const char *str)
{
int rc = 0;
if (mFree || re == NULL)
return -1;
this->ClearMatch();
ClearMatch();
//save str
subject = new char[strlen(str)+1];
subject = new char[strlen(str) + 1];
strcpy(subject, str);
rc = pcre_exec(re, NULL, subject, (int)strlen(subject), 0, 0, ovector, 30);
rc = pcre_exec(re, NULL, subject, (int)strlen(subject), 0, 0, ovector, REGEX_MAX_SUBPATTERNS);
if (rc < 0)
{
if (rc == PCRE_ERROR_NOMATCH)
{
return 0;
} else {
}
else {
mErrorOffset = rc;
return -1;
}
}
mSubStrings = rc;
RegExSub res;
mSubStrings.ensure(rc);
for (int s = 0; s < rc; ++s)
{
res.start = ovector[2 * s];
res.end = ovector[2 * s + 1];
mSubStrings.append(res);
}
return 1;
}
int RegEx::MatchAll(const char *str)
{
int rr = 0;
int rc = 0;
int startOffset = 0;
int exoptions = 0;
int notEmpty = 0;
int sizeOffsets = mNumSubpatterns * 3;
int subjectLen = strlen(str);
if (mFree || re == NULL)
{
return -1;
}
ClearMatch();
subject = new char[subjectLen + 1];
strcpy(subject, str);
RegExSub sub;
while (1)
{
rr = pcre_exec(re, NULL, subject, (int)subjectLen, startOffset, exoptions | notEmpty, ovector, REGEX_MAX_SUBPATTERNS);
/**
* The string was already proved to be valid UTF-8
*/
exoptions |= PCRE_NO_UTF8_CHECK;
/**
* Too many substrings
*/
if (rr == 0)
{
rr = sizeOffsets / 3;
}
if (rr > 0)
{
mMatchesSubs.append(rr);
for (int s = 0; s < rr; ++s)
{
sub.start = ovector[2 * s];
sub.end = ovector[2 * s + 1];
mSubStrings.append(sub);
}
}
else if (rr == PCRE_ERROR_NOMATCH)
{
/**
* If we previously set PCRE_NOTEMPTY after a null match,
* this is not necessarily the end. We need to advance
* the start offset, and continue. Fudge the offset values
* to achieve this, unless we're already at the end of the string.
*/
if (notEmpty && startOffset < (int)subjectLen)
{
ovector[0] = startOffset;
ovector[1] = startOffset + 1;
}
else
{
break;
}
}
else
{
mErrorOffset = rr;
if (mMatchesSubs.length())
{
ClearMatch();
}
return -1;
}
/**
* If we have matched an empty string, mimic what Perl's /g options does.
* This turns out to be rather cunning. First we set PCRE_NOTEMPTY and try
* the match again at the same point. If this fails (picked up above) we
* advance to the next character.
*/
notEmpty = (ovector[1] == ovector[0]) ? PCRE_NOTEMPTY | PCRE_ANCHORED : 0;
/**
* Advance to the next piece.
*/
startOffset = ovector[1];
}
if (!mMatchesSubs.length())
{
return 0;
}
return 1;
}
void RegEx::ClearMatch()
{
// Clears match results
mErrorOffset = 0;
mError = NULL;
if (subject)
delete [] subject;
delete[] subject;
subject = NULL;
mSubStrings = 0;
mSubStrings.clear();
mMatchesSubs.clear();
}
const char *RegEx::GetSubstring(int s, char buffer[], int max)
const char *getSubstring(char *subject, size_t start, size_t end, char buffer[], size_t max, size_t *outlen)
{
int i = 0;
if (s >= mSubStrings || s < 0)
return NULL;
size_t i;
char * substr_a = subject + start;
size_t substr_l = end - start;
char *substr_a = subject + ovector[2*s];
int substr_l = ovector[2*s+1] - ovector[2*s];
for (i = 0; i<substr_l; i++)
for (i = 0; i < substr_l; i++)
{
if (i >= max)
break;
@ -156,6 +337,506 @@ const char *RegEx::GetSubstring(int s, char buffer[], int max)
buffer[i] = '\0';
if (outlen)
{
*outlen = i;
}
return buffer;
}
const char *RegEx::GetSubstring(size_t start, char buffer[], size_t max, size_t *outlen)
{
if (start >= mSubStrings.length())
{
return NULL;
}
RegExSub sub = mSubStrings.at(start);
return getSubstring(subject, sub.start, sub.end, buffer, max, outlen);
}
void RegEx::MakeSubpatternsTable(int numSubpatterns)
{
int nameCount = 0;
int rc = pcre_fullinfo(re, NULL, PCRE_INFO_NAMECOUNT, &nameCount);
if (rc < 0)
{
return;
}
if (nameCount > 0)
{
const char *nameTable;
int nameSize = 0;
int i = 0;
int rc1 = pcre_fullinfo(re, NULL, PCRE_INFO_NAMETABLE, &nameTable);
int rc2 = pcre_fullinfo(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameSize);
rc = rc2 ? rc2 : rc1;
if (rc < 0)
{
mSubsNameTable.clear();
return;
}
NamedGroup data;
while (i++ < nameCount)
{
data.index = 0xff * (unsigned char)nameTable[0] + (unsigned char)nameTable[1];
data.name = nameTable + 2;
mSubsNameTable.append(ke::Move(data));
nameTable += nameSize;
}
}
}
int RegEx::Replace(char *text, size_t textMaxLen, const char *replace, size_t replaceLen, int flags)
{
char *output = text;
/**
* Retrieve all matches and store them in
* mSubStrings list.
*/
if (MatchAll(output) == -1)
{
return -1;
}
size_t subjectLen = strlen(subject);
size_t total = 0;
size_t baseIndex = 0;
size_t diffLength = 0;
char *toReplace = new char[textMaxLen + 1];
char *toSearch = NULL;
/**
* All characters which is not matched are not copied when replacing matches.
* Then original text (output buffer) should be considerated as empty.
*/
if (flags & REGEX_FORMAT_NOCOPY)
{
*output = '\0';
}
else
{
/**
* This is used only when we do replace matches.
*/
toSearch = new char[textMaxLen + 1];
}
/**
* Loop over all matches found.
*/
for (size_t i = 0; i < mMatchesSubs.length(); ++i)
{
char *ptr = toReplace;
size_t browsed = 0;
size_t searchLen = 0;
size_t length = 0;
/**
* Build the replace string as it can contain backreference
* and this needs to be parsed.
*/
for (const char *s = replace, *end = s + replaceLen; s < end && browsed <= textMaxLen; ++s, ++browsed)
{
unsigned int c = *s;
/**
* Supported format specifiers:
*
* $number : Substitutes the substring matched by group number.
* n must be an integer value designating a valid backreference, greater than 0, and of two digits at most.
* ${name} : Substitutes the substring matched by the named group name (a maximum of 32 characters).
* $& : Substitutes a copy of the whole match.
* $` : Substitutes all the text of the input string before the match.
* $' : Substitutes all the text of the input string after the match.
* $+ : Substitutes the last group that was captured.
* $_ : Substitutes the entire input string.
* $$ : Substitutes a literal "$".
*/
if (c == '$' || c == '\\')
{
switch (*++s)
{
case '\0':
{
/**
* End of string.
* Copy one character.
*/
*(ptr + browsed) = c;
break;
}
case '&':
{
/**
* Concatenate retrieved full match sub-string.
* length - 1 to overwrite EOS.
*/
GetSubstring(baseIndex, ptr + browsed, textMaxLen, &length);
browsed += length - 1;
break;
}
case '`':
{
/**
* Concatenate part of original text up to
* first sub-string position.
*/
length = mSubStrings.at(baseIndex).start;
memcpy(ptr + browsed, subject, length);
browsed += length - 1;
break;
}
case '\'':
{
/**
* Concatenate part of original text from
* last sub-string end position to EOS.
*/
length = mSubStrings.at(baseIndex).end;
memcpy(ptr + browsed, subject + length, subjectLen - length);
browsed += (subjectLen - length) - 1;
break;
}
case '+':
{
/**
* Copy the last group that was captured.
*/
GetSubstring(baseIndex + mMatchesSubs.at(i) - 1, ptr + browsed, textMaxLen, &length);
browsed += length - 1;
break;
}
case '_':
{
/**
* Copy the entire input string.
*/
memcpy(ptr + browsed, subject, subjectLen);
browsed += (subjectLen - 1);
break;
}
case '$':
case '\\':
{
/**
* Copy the single character $ or \.
*/
*(ptr + browsed) = c;
break;
}
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case '{':
{
/**
* Checking backreference.
* Which can be either $n, ${n} or ${name}.
*/
int backref = -1;
const char *walk = s;
bool inBrace = false;
bool nameCheck = false;
/**
* ${nn}.
* ^
*/
if (*walk == '{')
{
inBrace = true;
++walk;
}
/**
* Valid number.
* $nn or ${nn}
* ^ ^
*/
if (*walk >= '0' && *walk <= '9')
{
backref = *walk - '0';
++walk;
}
else if (inBrace)
{
nameCheck = true;
/**
* Not a valid number.
* Checking as string.
* ${name}
* ^
*/
if (*walk)
{
const char *pch = strchr(walk, '}');
if (pch != NULL)
{
/**
* A named group maximum character is 32 (PCRE).
*/
char name[32];
size_t nameLength = strncopy(name, walk, pch - walk + 1);
int flags, num = 0;
pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &flags);
/**
* If PCRE_DUPNAMES is set, the pcre_copy_named_substring function should be used
* as pcre_get_stringnumber output order is not defined.
*/
if (flags & PCRE_DUPNAMES)
{
memset(ovector, 0, REGEX_MAX_SUBPATTERNS);
/**
* pcre_copy_named_substring needs a vector containing sub-patterns ranges
* for a given match.
*/
for (size_t j = 0; j < mMatchesSubs.at(i); ++j)
{
ovector[2 * j] = mSubStrings.at(baseIndex + j).start;
ovector[2 * j + 1] = mSubStrings.at(baseIndex + j).end;
}
num = pcre_copy_named_substring(re, subject, ovector, mMatchesSubs.at(i), name, ptr + browsed, (int)textMaxLen);
if (num != PCRE_ERROR_NOSUBSTRING)
{
browsed += num - 1;
s = pch;
break;
}
++pch;
}
else
{
/**
* Retrieve sub-pattern index from a give name.
*/
num = pcre_get_stringnumber(re, name);
if (num != PCRE_ERROR_NOSUBSTRING)
{
backref = num;
walk = ++pch;
}
}
if (num == PCRE_ERROR_NOSUBSTRING || num >= (int)mMatchesSubs.at(i))
{
/**
* If a sub-string for a given match is not found, or if > to
* number of sub-patterns we still need to check if this
* group name is a valid one because if so we want to escape it.
* Looking at the name table.
*/
bool found = false;
for (size_t i = 0; i < mSubsNameTable.length(); ++i)
{
if (!mSubsNameTable.at(i).name.compare(name))
{
--browsed;
s = --pch;
found = true;
break;
}
}
if (found)
{
continue;
}
}
}
}
}
if (!nameCheck)
{
/**
* Valid second number.
* $nn or ${nn}
* ^ ^
*/
if (*walk && *walk >= '0' && *walk <= '9')
{
backref = backref * 10 + *walk - '0';
++walk;
}
if (inBrace)
{
/**
* Invalid specifier
* Either hit EOS or missing }.
* ${n or ${nn or ${nx or ${nnx
* ^ ^ ^ ^
*/
if (*walk == '\0' || *walk != '}')
{
backref = -1;
}
else
{
++walk;
}
}
}
length = walk - s;
s = --walk;
/**
* We can't provide a capture number >= to total that pcre_exec has found.
* 0 is implicitly accepted, same behavior as $&.
*/
if (backref >= 0 && (int)backref < mNumSubpatterns)
{
/**
* Valid available index for a given match.
*/
if (backref < mMatchesSubs.at(i))
{
/**
* Concatenate retrieved sub-string.
* length - 1 to overwrite EOS.
*/
GetSubstring(baseIndex + backref, ptr + browsed, textMaxLen, &length);
browsed += length - 1;
}
else
{
/**
* Valid unavailable index for a given match.
*/
--browsed;
}
}
else
{
/**
* If we here it means the syntax is valid but sub-pattern doesn't exist.
* So, copy as it is, including $.
*/
memcpy(ptr + browsed, s - length, length + 1);
browsed += length;
}
break;
}
default:
{
/**
* Not a valid format modifier.
* So we copy characters as it is.
*/
*(ptr + browsed) = *s;
break;
}
}
}
else
{
/**
* At this point, direct copy.
*/
*(ptr + browsed) = c;
}
}
*(ptr + browsed) = '\0';
/**
* Concatenate only replace string of each match,
* as we don't want to copy unmatched characters.
*/
if (flags & REGEX_FORMAT_NOCOPY)
{
/**
* We want just the first occurrence.
*/
if (total++ && (flags & REGEX_FORMAT_FIRSTONLY))
{
break;
}
strncat(output, toReplace, textMaxLen + 1);
}
else
{
/**
* Retrieves full string of a given match.
*/
const char *search = GetSubstring(baseIndex, toSearch, textMaxLen, &searchLen);
/**
* We get something to replace, but the sub-pattern to search is empty.
* We insert replacement either a the start end or string.
*/
if (*toReplace && !searchLen)
{
if (output - text > 0)
{
strncat(output, toReplace, textMaxLen);
}
else
{
strncat(toReplace, text, textMaxLen);
strncopy(text, toReplace, strlen(toReplace) + 1);
}
++total;
}
else if ((output = UTIL_ReplaceEx(text + mSubStrings.at(baseIndex).start + diffLength, textMaxLen, search, searchLen, toReplace, browsed, false)) != NULL)
{
/**
* Then we simply do a replace.
* Probably not the most efficient, but this should be at least safe.
* To avoid issue where the function could find a string which is not at the expected index,
* We force the input string to start from index of the full match.
*/
++total;
}
if (total && (flags & REGEX_FORMAT_FIRSTONLY))
{
break;
}
}
/**
* mMatchesSubs is a flat list containing all sub-patterns of all matches.
* A number of sub-patterns can vary per match. So we calculate the position in the list,
* from where the first sub-pattern result of current match starts.
*/
baseIndex += mMatchesSubs.at(i);
diffLength += browsed - searchLen;
}
delete[] toReplace;
if (toSearch != NULL)
{
delete[] toSearch;
}
/**
* Return the number of successful replacements.
*/
return total;
}

73
dlls/regex/CRegEx.h
View File

@ -1,27 +1,94 @@
/* AMX Mod X
* Regular Expressions Module
*
* by the AMX Mod X Development Team
*
* This file is part of AMX Mod X.
*
*
* 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 of the License, 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 program; if not, write to the Free Software Foundation,
* Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* In addition, as a special exception, the author gives permission to
* link the code of this program with the Half-Life Game Engine ("HL
* Engine") and Modified Game Libraries ("MODs") developed by Valve,
* L.L.C ("Valve"). You must obey the GNU General Public License in all
* respects for all of the code used other than the HL Engine and MODs
* from Valve. If you modify this file, you may extend this exception
* to your version of the file, but you are not obligated to do so. If
* you do not wish to do so, delete this exception statement from your
* version.
*/
#ifndef _INCLUDE_CREGEX_H
#define _INCLUDE_CREGEX_H
#include <am-vector.h>
#include <am-string.h>
/**
* Maximum number of sub-patterns, here 50 (this should be a multiple of 3).
*/
#define REGEX_MAX_SUBPATTERNS 150
/**
* Flags to used with regex_replace, to control the replacement behavior.
*/
#define REGEX_FORMAT_DEFAULT 0 // Uses the standard formatting rules to replace matches.
#define REGEX_FORMAT_NOCOPY 1 // The sections that do not match the regular expression are not copied when replacing matches.
#define REGEX_FORMAT_FIRSTONLY 2 // Only the first occurrence of a regular expression is replaced.
class RegEx
{
public:
struct RegExSub {
int start, end;
};
struct NamedGroup {
ke::AString name;
size_t index;
};
RegEx();
~RegEx();
bool isFree(bool set=false, bool val=false);
void Clear();
int Compile(const char *pattern, const char* flags = NULL);
int Compile(const char *pattern, int iFlags);
int Match(const char *str);
int MatchAll(const char *str);
int Replace(char *text, size_t text_maxlen, const char *replace, size_t replaceLen, int flags = 0);
void ClearMatch();
const char *GetSubstring(int s, char buffer[], int max);
const char *GetSubstring(size_t start, char buffer[], size_t max, size_t *outlen = NULL);
void MakeSubpatternsTable(int numSubpatterns);
public:
int mErrorOffset;
const char *mError;
int mSubStrings;
int Count() { return mSubStrings.length(); }
private:
pcre *re;
bool mFree;
int ovector[30];
int ovector[REGEX_MAX_SUBPATTERNS];
char *subject;
ke::Vector<RegExSub> mSubStrings;
ke::Vector<size_t> mMatchesSubs;
ke::Vector<NamedGroup> mSubsNameTable;
int mNumSubpatterns;
};
#endif //_INCLUDE_CREGEX_H

BIN
dlls/regex/lib_darwin/libpcre.a
View File

Binary file not shown.

BIN
dlls/regex/lib_linux/libpcre.a
View File

Binary file not shown.

BIN
dlls/regex/lib_linux64/libpcre.a
View File

Binary file not shown.

BIN
dlls/regex/lib_win/pcre.lib
View File

Binary file not shown.

274
dlls/regex/module.cpp
View File

@ -1,24 +1,59 @@
/* AMX Mod X
* Regular Expressions Module
*
* by the AMX Mod X Development Team
*
* This file is part of AMX Mod X.
*
*
* 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 of the License, 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 program; if not, write to the Free Software Foundation,
* Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* In addition, as a special exception, the author gives permission to
* link the code of this program with the Half-Life Game Engine ("HL
* Engine") and Modified Game Libraries ("MODs") developed by Valve,
* L.L.C ("Valve"). You must obey the GNU General Public License in all
* respects for all of the code used other than the HL Engine and MODs
* from Valve. If you modify this file, you may extend this exception
* to your version of the file, but you are not obligated to do so. If
* you do not wish to do so, delete this exception statement from your
* version.
*/
#include <string.h>
#include "pcre.h"
#include "amxxmodule.h"
#include "CVector.h"
#include <am-vector.h>
#include <am-utility.h>
#include "CRegEx.h"
#include "utils.h"
CVector<RegEx *> PEL;
ke::Vector<RegEx *> PEL;
int GetPEL()
{
for (int i=0; i<(int)PEL.size(); i++)
for (int i=0; i<(int)PEL.length(); i++)
{
if (PEL[i]->isFree())
return i;
}
RegEx *x = new RegEx();
PEL.push_back(x);
PEL.append(x);
return (int)PEL.size() - 1;
return (int)PEL.length() - 1;
}
// native Regex:regex_compile(const pattern[], &ret, error[], maxLen, const flags[]="");
static cell AMX_NATIVE_CALL regex_compile(AMX *amx, cell *params)
{
@ -31,17 +66,36 @@ static cell AMX_NATIVE_CALL regex_compile(AMX *amx, cell *params)
if (x->Compile(regex, flags) == 0)
{
cell *eOff = MF_GetAmxAddr(amx, params[2]);
const char *err = x->mError;
*eOff = x->mErrorOffset;
*MF_GetAmxAddr(amx, params[2]) = x->mErrorOffset;
MF_SetAmxString(amx, params[3], err?err:"unknown", params[4]);
return -1;
}
return id+1;
}// 1.8 includes the last parameter
// Regex:regex_match(const string[], const pattern[], &ret, error[], maxLen, const flags[] = "");
static cell AMX_NATIVE_CALL regex_match(AMX *amx, cell *params)
}
// native Regex:regex_compile_ex(const pattern[], flags = 0, error[] = "", maxLen = 0, &errcode = 0);
static cell AMX_NATIVE_CALL regex_compile_ex(AMX *amx, cell *params)
{
int len;
const char *regex = MF_GetAmxString(amx, params[1], 0, &len);
int id = GetPEL();
RegEx *x = PEL[id];
if (x->Compile(regex, params[2]) == 0)
{
const char *err = x->mError;
*MF_GetAmxAddr(amx, params[5]) = x->mErrorOffset;
MF_SetAmxString(amx, params[3], err ? err : "unknown", params[4]);
return -1;
}
return id + 1;
}
cell match(AMX *amx, cell *params, bool all)
{
int len;
const char *str = MF_GetAmxString(amx, params[1], 0, &len);
@ -49,101 +103,166 @@ static cell AMX_NATIVE_CALL regex_match(AMX *amx, cell *params)
int id = GetPEL();
RegEx *x = PEL[id];
char* flags = NULL;
if ((params[0] / sizeof(cell)) >= 6) // compiled with 1.8's extra parameter
char *flags = NULL;
cell *errorCode;
int result = 0;
if (!all)
{
flags = MF_GetAmxString(amx, params[6], 2, &len);
if (*params / sizeof(cell) >= 6) // compiled with 1.8's extra parameter
{
flags = MF_GetAmxString(amx, params[6], 2, &len);
}
result = x->Compile(regex, flags);
errorCode = MF_GetAmxAddr(amx, params[3]);
}
if (x->Compile(regex, flags) == 0)
else
{
result = x->Compile(regex, params[3]);
errorCode = MF_GetAmxAddr(amx, params[6]);
}
if (!result)
{
cell *eOff = MF_GetAmxAddr(amx, params[3]);
const char *err = x->mError;
*eOff = x->mErrorOffset;
MF_SetAmxString(amx, params[4], err?err:"unknown", params[5]);
*errorCode = x->mErrorOffset;
MF_SetAmxString(amx, params[4], err ? err : "unknown", params[5]);
return -1;
}
int e = x->Match(str);
int e;
if (all)
e = x->MatchAll(str);
else
e = x->Match(str);
if (e == -1)
{
/* there was a match error. destroy this and move on. */
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = x->mErrorOffset;
*errorCode = x->mErrorOffset;
x->Clear();
return -2;
} else if (e == 0) {
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = 0;
}
else if (e == 0)
{
*errorCode = 0;
x->Clear();
return 0;
} else {
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = x->mSubStrings;
}
else
{
*errorCode = x->Count();
if (all)
return x->Count();
}
return id+1;
return id + 1;
}
// native regex_match_c(const string[], Regex:id, &ret);
static cell AMX_NATIVE_CALL regex_match_c(AMX *amx, cell *params)
{
int len;
int id = params[2]-1;
const char *str = MF_GetAmxString(amx, params[1], 0, &len);
if (id >= (int)PEL.size() || id < 0 || PEL[id]->isFree())
// native Regex:regex_match(const string[], const pattern[], &ret, error[], maxLen, const flags[] = "");
static cell AMX_NATIVE_CALL regex_match(AMX *amx, cell *params)
{
return match(amx, params, false);
}
// native Regex:regex_match_all(const string[], const pattern[], flags = 0, error[] = "", maxLen = 0, &errcode = 0);
static cell AMX_NATIVE_CALL regex_match_all(AMX *amx, cell *params)
{
return match(amx, params, true);
}
cell match_c(AMX *amx, cell *params, bool all)
{
int id = params[2] - 1;
if (id >= (int)PEL.length() || id < 0 || PEL[id]->isFree())
{
MF_LogError(amx, AMX_ERR_NATIVE, "Invalid regex handle %d", id);
return 0;
}
int len;
const char *str = MF_GetAmxString(amx, params[1], 0, &len);
cell *errorCode = MF_GetAmxAddr(amx, params[3]);
RegEx *x = PEL[id];
int e = x->Match(str);
int e;
if (all)
e = x->MatchAll(str);
else
e = x->Match(str);
if (e == -1)
{
/* there was a match error. move on. */
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = x->mErrorOffset;
*errorCode = x->mErrorOffset;
/* only clear the match results, since the regex object
may still be referenced later */
may still be referenced later */
x->ClearMatch();
return -2;
} else if (e == 0) {
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = 0;
}
else if (e == 0)
{
*errorCode = 0;
/* only clear the match results, since the regex object
may still be referenced later */
may still be referenced later */
x->ClearMatch();
return 0;
} else {
cell *res = MF_GetAmxAddr(amx, params[3]);
*res = x->mSubStrings;
return x->mSubStrings;
}
else
{
*errorCode = x->Count();
return x->Count();
}
}
// native regex_match_c(const string[], Regex:id, &ret);
static cell AMX_NATIVE_CALL regex_match_c(AMX *amx, cell *params)
{
return match_c(amx, params, false);
}
// native regex_match_all_c(const string[], Regex:id, &ret);
static cell AMX_NATIVE_CALL regex_match_all_c(AMX *amx, cell *params)
{
return match_c(amx, params, true);
}
// native regex_substr(Regex:id, str_id, buffer[], maxLen);
static cell AMX_NATIVE_CALL regex_substr(AMX *amx, cell *params)
{
int id = params[1]-1;
if (id >= (int)PEL.size() || id < 0 || PEL[id]->isFree())
if (id >= (int)PEL.length() || id < 0 || PEL[id]->isFree())
{
MF_LogError(amx, AMX_ERR_NATIVE, "Invalid regex handle %d", id);
return 0;
}
RegEx *x = PEL[id];
//good idea? probably not.
static char buffer[4096];
static char buffer[16384]; // Same as AMXX buffer.
const char *ret = x->GetSubstring(params[2], buffer, 4095);
size_t length;
size_t maxLength = ke::Min<size_t>(params[4], sizeof(buffer) - 1);
const char *ret = x->GetSubstring(params[2], buffer, maxLength, &length);
if (ret == NULL)
{
return 0;
}
MF_SetAmxString(amx, params[3], ret, params[4]);
if (length >= maxLength && ret[length - 1] & 1 << 7)
{
maxLength -= UTIL_CheckValidChar((char *)ret + length - 1);
}
MF_SetAmxString(amx, params[3], ret, maxLength);
return 1;
}
@ -154,7 +273,7 @@ static cell AMX_NATIVE_CALL regex_free(AMX *amx, cell *params)
int id = *c;
*c = 0;
id -= 1;
if (id >= (int)PEL.size() || id < 0 || PEL[id]->isFree())
if (id >= (int)PEL.length() || id < 0 || PEL[id]->isFree())
{
MF_LogError(amx, AMX_ERR_NATIVE, "Invalid regex handle %d", id);
return 0;
@ -166,11 +285,52 @@ static cell AMX_NATIVE_CALL regex_free(AMX *amx, cell *params)
return 1;
}
//native regex_replace(Regex:pattern, string[], maxLen, const replace[], flags = REGEX_FORMAT_DEFAULT, &errcode = 0);
static cell AMX_NATIVE_CALL regex_replace(AMX *amx, cell *params)
{
int id = params[1] - 1;
if (id >= (int)PEL.length() || id < 0 || PEL[id]->isFree())
{
MF_LogError(amx, AMX_ERR_NATIVE, "Invalid regex handle %d", id);
return 0;
}
int textLen, replaceLen;
char *text = MF_GetAmxString(amx, params[2], 0, &textLen);
const char *replace = MF_GetAmxString(amx, params[4], 1, &replaceLen);
cell *erroCode = MF_GetAmxAddr(amx, params[6]);
RegEx *x = PEL[id];
int e = x->Replace(text, params[3] + 1, replace, replaceLen, params[5]);
if (e == -1)
{
*erroCode = x->mErrorOffset;
x->ClearMatch();
return -2;
}
else if (e == 0)
{
*erroCode = 0;
x->ClearMatch();
return 0;
}
MF_SetAmxString(amx, params[2], text, params[3]);
return e;
}
AMX_NATIVE_INFO regex_Natives[] = {
{"regex_compile", regex_compile},
{"regex_compile_ex", regex_compile_ex},
{"regex_match", regex_match},
{"regex_match_c", regex_match_c},
{"regex_match_all", regex_match_all},
{"regex_match_all_c", regex_match_all_c},
{"regex_substr", regex_substr},
{"regex_replace", regex_replace},
{"regex_free", regex_free},
{NULL, NULL},
};
@ -182,7 +342,7 @@ void OnAmxxAttach()
void OnAmxxDetach()
{
for (int i = 0; i<(int)PEL.size(); i++)
for (int i = 0; i<(int)PEL.length(); i++)
{
if (PEL[i])
{

10
dlls/regex/msvc10/regex.vcxproj
View File

@ -52,8 +52,8 @@
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<ClCompile>
<Optimization>Disabled</Optimization>
<AdditionalIncludeDirectories>..\;..\sdk;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
<PreprocessorDefinitions>WIN32;_DEBUG;_WINDOWS;_USRDLL;REGEX_EXPORTS;PCRE_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>..\;..\..\..\public\amtl;..\sdk;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
<PreprocessorDefinitions>WIN32;_DEBUG;_WINDOWS;_USRDLL;REGEX_EXPORTS;HAVE_STDINT_H;PCRE_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<MinimalRebuild>true</MinimalRebuild>
<BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
@ -75,8 +75,8 @@
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<ClCompile>
<AdditionalIncludeDirectories>..\;..\sdk;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
<PreprocessorDefinitions>WIN32;NDEBUG;_WINDOWS;_USRDLL;REGEX_EXPORTS;PCRE_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>..\;..\..\..\public\amtl;..\sdk;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
<PreprocessorDefinitions>WIN32;NDEBUG;_WINDOWS;_USRDLL;REGEX_EXPORTS;HAVE_STDINT_H;PCRE_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
<RuntimeTypeInfo>false</RuntimeTypeInfo>
<PrecompiledHeader>
@ -99,6 +99,7 @@
<ClCompile Include="..\CRegEx.cpp" />
<ClCompile Include="..\module.cpp" />
<ClCompile Include="..\sdk\amxxmodule.cpp" />
<ClCompile Include="..\utils.cpp" />
</ItemGroup>
<ItemGroup>
<ClInclude Include="..\CRegEx.h" />
@ -107,6 +108,7 @@
<ClInclude Include="..\sdk\moduleconfig.h" />
<ClInclude Include="..\sdk\CVector.h" />
<ClInclude Include="..\sdk\amxxmodule.h" />
<ClInclude Include="..\utils.h" />
</ItemGroup>
<ItemGroup>
<None Include="..\..\..\plugins\include\regex.inc" />

6
dlls/regex/msvc10/regex.vcxproj.filters
View File

@ -32,6 +32,9 @@
<ClCompile Include="..\sdk\amxxmodule.cpp">
<Filter>Module SDK\SDK Base</Filter>
</ClCompile>
<ClCompile Include="..\utils.cpp">
<Filter>Source Files</Filter>
</ClCompile>
</ItemGroup>
<ItemGroup>
<ClInclude Include="..\CRegEx.h">
@ -52,6 +55,9 @@
<ClInclude Include="..\sdk\amxxmodule.h">
<Filter>Module SDK\SDK Base</Filter>
</ClInclude>
<ClInclude Include="..\utils.h">
<Filter>Header Files</Filter>
</ClInclude>
</ItemGroup>
<ItemGroup>
<None Include="..\..\..\plugins\include\regex.inc">

613
dlls/regex/pcre.h
View File

@ -2,10 +2,10 @@
* Perl-Compatible Regular Expressions *
*************************************************/
/* In its original form, this is the .in file that is transformed by
"configure" into pcre.h.
/* This is the public header file for the PCRE library, to be #included by
applications that call the PCRE functions.
Copyright (c) 1997-2005 University of Cambridge
Copyright (c) 1997-2014 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -39,34 +39,48 @@ 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. */
/* The current PCRE version information. */
#define PCRE_MAJOR 6
#define PCRE_MINOR 4
#define PCRE_DATE 05-Sep-2005
#define PCRE_MAJOR 8
#define PCRE_MINOR 35
#define PCRE_PRERELEASE
#define PCRE_DATE 2014-04-04
/* Win32 uses DLL by default; it needs special stuff for exported functions. */
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE, the appropriate
export setting is defined in pcre_internal.h, which includes this file. So we
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
#ifdef _WIN32
# ifdef PCRE_DEFINITION
# ifdef DLL_EXPORT
# define PCRE_DATA_SCOPE __declspec(dllexport)
#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
# else
# ifndef PCRE_STATIC
# define PCRE_DATA_SCOPE extern __declspec(dllimport)
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN __declspec(dllimport)
# endif
# endif
#endif
/* For other operating systems, we use the standard "extern". */
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE_DATA_SCOPE
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_DATA_SCOPE extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_DATA_SCOPE 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
@ -81,50 +95,162 @@ it is needed here for malloc. */
extern "C" {
#endif
/* Options */
/* Public options. Some are compile-time only, some are run-time only, and some
are both. Most of the compile-time options are saved with the compiled regex so
that they can be inspected during studying (and therefore JIT compiling). Note
that pcre_study() has its own set of options. Originally, all the options
defined here used distinct bits. However, almost all the bits in a 32-bit word
are now used, so in order to conserve them, option bits that were previously
only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may
also be used for compile-time options that affect only compiling and are not
relevant for studying or JIT compiling.
#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
Some options for pcre_compile() change its behaviour but do not affect the
behaviour of the execution functions. Other options are passed through to the
execution functions and affect their behaviour, with or without affecting the
behaviour of pcre_compile().
Options that can be passed to pcre_compile() are tagged Cx below, with these
variants:
C1 Affects compile only
C2 Does not affect compile; affects exec, dfa_exec
C3 Affects compile, exec, dfa_exec
C4 Affects compile, exec, dfa_exec, study
C5 Affects compile, exec, study
Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with
E and D, respectively. They take precedence over C3, C4, and C5 settings passed
from pcre_compile(). Those that are compatible with JIT execution are flagged
with J. */
#define PCRE_CASELESS 0x00000001 /* C1 */
#define PCRE_MULTILINE 0x00000002 /* C1 */
#define PCRE_DOTALL 0x00000004 /* C1 */
#define PCRE_EXTENDED 0x00000008 /* C1 */
#define PCRE_ANCHORED 0x00000010 /* C4 E D */
#define PCRE_DOLLAR_ENDONLY 0x00000020 /* C2 */
#define PCRE_EXTRA 0x00000040 /* C1 */
#define PCRE_NOTBOL 0x00000080 /* E D J */
#define PCRE_NOTEOL 0x00000100 /* E D J */
#define PCRE_UNGREEDY 0x00000200 /* C1 */
#define PCRE_NOTEMPTY 0x00000400 /* E D J */
#define PCRE_UTF8 0x00000800 /* C4 ) */
#define PCRE_UTF16 0x00000800 /* C4 ) Synonyms */
#define PCRE_UTF32 0x00000800 /* C4 ) */
#define PCRE_NO_AUTO_CAPTURE 0x00001000 /* C1 */
#define PCRE_NO_UTF8_CHECK 0x00002000 /* C1 E D J ) */
#define PCRE_NO_UTF16_CHECK 0x00002000 /* C1 E D J ) Synonyms */
#define PCRE_NO_UTF32_CHECK 0x00002000 /* C1 E D J ) */
#define PCRE_AUTO_CALLOUT 0x00004000 /* C1 */
#define PCRE_PARTIAL_SOFT 0x00008000 /* E D J ) Synonyms */
#define PCRE_PARTIAL 0x00008000 /* E D J ) */
/* This pair use the same bit. */
#define PCRE_NEVER_UTF 0x00010000 /* C1 ) Overlaid */
#define PCRE_DFA_SHORTEST 0x00010000 /* D ) Overlaid */
/* This pair use the same bit. */
#define PCRE_NO_AUTO_POSSESS 0x00020000 /* C1 ) Overlaid */
#define PCRE_DFA_RESTART 0x00020000 /* D ) Overlaid */
#define PCRE_FIRSTLINE 0x00040000 /* C3 */
#define PCRE_DUPNAMES 0x00080000 /* C1 */
#define PCRE_NEWLINE_CR 0x00100000 /* C3 E D */
#define PCRE_NEWLINE_LF 0x00200000 /* C3 E D */
#define PCRE_NEWLINE_CRLF 0x00300000 /* C3 E D */
#define PCRE_NEWLINE_ANY 0x00400000 /* C3 E D */
#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* C3 E D */
#define PCRE_BSR_ANYCRLF 0x00800000 /* C3 E D */
#define PCRE_BSR_UNICODE 0x01000000 /* C3 E D */
#define PCRE_JAVASCRIPT_COMPAT 0x02000000 /* C5 */
#define PCRE_NO_START_OPTIMIZE 0x04000000 /* C2 E D ) Synonyms */
#define PCRE_NO_START_OPTIMISE 0x04000000 /* C2 E D ) */
#define PCRE_PARTIAL_HARD 0x08000000 /* E D J */
#define PCRE_NOTEMPTY_ATSTART 0x10000000 /* E D J */
#define PCRE_UCP 0x20000000 /* C3 */
/* 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)
#define PCRE_ERROR_NOMATCH (-1)
#define PCRE_ERROR_NULL (-2)
#define PCRE_ERROR_BADOPTION (-3)
#define PCRE_ERROR_BADMAGIC (-4)
#define PCRE_ERROR_UNKNOWN_OPCODE (-5)
#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */
#define PCRE_ERROR_NOMEMORY (-6)
#define PCRE_ERROR_NOSUBSTRING (-7)
#define PCRE_ERROR_MATCHLIMIT (-8)
#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */
#define PCRE_ERROR_BADUTF8 (-10) /* Same for 8/16/32 */
#define PCRE_ERROR_BADUTF16 (-10) /* Same for 8/16/32 */
#define PCRE_ERROR_BADUTF32 (-10) /* Same for 8/16/32 */
#define PCRE_ERROR_BADUTF8_OFFSET (-11) /* Same for 8/16 */
#define PCRE_ERROR_BADUTF16_OFFSET (-11) /* Same for 8/16 */
#define PCRE_ERROR_PARTIAL (-12)
#define PCRE_ERROR_BADPARTIAL (-13)
#define PCRE_ERROR_INTERNAL (-14)
#define PCRE_ERROR_BADCOUNT (-15)
#define PCRE_ERROR_DFA_UITEM (-16)
#define PCRE_ERROR_DFA_UCOND (-17)
#define PCRE_ERROR_DFA_UMLIMIT (-18)
#define PCRE_ERROR_DFA_WSSIZE (-19)
#define PCRE_ERROR_DFA_RECURSE (-20)
#define PCRE_ERROR_RECURSIONLIMIT (-21)
#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
#define PCRE_ERROR_BADNEWLINE (-23)
#define PCRE_ERROR_BADOFFSET (-24)
#define PCRE_ERROR_SHORTUTF8 (-25)
#define PCRE_ERROR_SHORTUTF16 (-25) /* Same for 8/16 */
#define PCRE_ERROR_RECURSELOOP (-26)
#define PCRE_ERROR_JIT_STACKLIMIT (-27)
#define PCRE_ERROR_BADMODE (-28)
#define PCRE_ERROR_BADENDIANNESS (-29)
#define PCRE_ERROR_DFA_BADRESTART (-30)
#define PCRE_ERROR_JIT_BADOPTION (-31)
#define PCRE_ERROR_BADLENGTH (-32)
#define PCRE_ERROR_UNSET (-33)
/* Specific error codes for UTF-8 validity checks */
#define PCRE_UTF8_ERR0 0
#define PCRE_UTF8_ERR1 1
#define PCRE_UTF8_ERR2 2
#define PCRE_UTF8_ERR3 3
#define PCRE_UTF8_ERR4 4
#define PCRE_UTF8_ERR5 5
#define PCRE_UTF8_ERR6 6
#define PCRE_UTF8_ERR7 7
#define PCRE_UTF8_ERR8 8
#define PCRE_UTF8_ERR9 9
#define PCRE_UTF8_ERR10 10
#define PCRE_UTF8_ERR11 11
#define PCRE_UTF8_ERR12 12
#define PCRE_UTF8_ERR13 13
#define PCRE_UTF8_ERR14 14
#define PCRE_UTF8_ERR15 15
#define PCRE_UTF8_ERR16 16
#define PCRE_UTF8_ERR17 17
#define PCRE_UTF8_ERR18 18
#define PCRE_UTF8_ERR19 19
#define PCRE_UTF8_ERR20 20
#define PCRE_UTF8_ERR21 21
#define PCRE_UTF8_ERR22 22 /* Unused (was non-character) */
/* Specific error codes for UTF-16 validity checks */
#define PCRE_UTF16_ERR0 0
#define PCRE_UTF16_ERR1 1
#define PCRE_UTF16_ERR2 2
#define PCRE_UTF16_ERR3 3
#define PCRE_UTF16_ERR4 4 /* Unused (was non-character) */
/* Specific error codes for UTF-32 validity checks */
#define PCRE_UTF32_ERR0 0
#define PCRE_UTF32_ERR1 1
#define PCRE_UTF32_ERR2 2 /* Unused (was non-character) */
#define PCRE_UTF32_ERR3 3
/* Request types for pcre_fullinfo() */
@ -141,8 +267,23 @@ 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
#define PCRE_INFO_MINLENGTH 15
#define PCRE_INFO_JIT 16
#define PCRE_INFO_JITSIZE 17
#define PCRE_INFO_MAXLOOKBEHIND 18
#define PCRE_INFO_FIRSTCHARACTER 19
#define PCRE_INFO_FIRSTCHARACTERFLAGS 20
#define PCRE_INFO_REQUIREDCHAR 21
#define PCRE_INFO_REQUIREDCHARFLAGS 22
#define PCRE_INFO_MATCHLIMIT 23
#define PCRE_INFO_RECURSIONLIMIT 24
#define PCRE_INFO_MATCH_EMPTY 25
/* Request types for pcre_config() */
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
#define PCRE_CONFIG_UTF8 0
#define PCRE_CONFIG_NEWLINE 1
@ -151,19 +292,83 @@ extern "C" {
#define PCRE_CONFIG_MATCH_LIMIT 4
#define PCRE_CONFIG_STACKRECURSE 5
#define PCRE_CONFIG_UNICODE_PROPERTIES 6
#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
#define PCRE_CONFIG_BSR 8
#define PCRE_CONFIG_JIT 9
#define PCRE_CONFIG_UTF16 10
#define PCRE_CONFIG_JITTARGET 11
#define PCRE_CONFIG_UTF32 12
#define PCRE_CONFIG_PARENS_LIMIT 13
/* Bit flags for the pcre_extra structure */
/* Request types for pcre_study(). Do not re-arrange, in order to remain
compatible. */
#define PCRE_EXTRA_STUDY_DATA 0x0001
#define PCRE_EXTRA_MATCH_LIMIT 0x0002
#define PCRE_EXTRA_CALLOUT_DATA 0x0004
#define PCRE_EXTRA_TABLES 0x0008
#define PCRE_STUDY_JIT_COMPILE 0x0001
#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE 0x0002
#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE 0x0004
#define PCRE_STUDY_EXTRA_NEEDED 0x0008
/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine
these bits, just add new ones on the end, in order to remain compatible. */
#define PCRE_EXTRA_STUDY_DATA 0x0001
#define PCRE_EXTRA_MATCH_LIMIT 0x0002
#define PCRE_EXTRA_CALLOUT_DATA 0x0004
#define PCRE_EXTRA_TABLES 0x0008
#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010
#define PCRE_EXTRA_MARK 0x0020
#define PCRE_EXTRA_EXECUTABLE_JIT 0x0040
/* Types */
struct real_pcre; /* declaration; the definition is private */
typedef struct real_pcre pcre;
struct real_pcre16; /* declaration; the definition is private */
typedef struct real_pcre16 pcre16;
struct real_pcre32; /* declaration; the definition is private */
typedef struct real_pcre32 pcre32;
struct real_pcre_jit_stack; /* declaration; the definition is private */
typedef struct real_pcre_jit_stack pcre_jit_stack;
struct real_pcre16_jit_stack; /* declaration; the definition is private */
typedef struct real_pcre16_jit_stack pcre16_jit_stack;
struct real_pcre32_jit_stack; /* declaration; the definition is private */
typedef struct real_pcre32_jit_stack pcre32_jit_stack;
/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain
a 16 bit wide signed data type. Otherwise it can be a dummy data type since
pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */
#ifndef PCRE_UCHAR16
#define PCRE_UCHAR16 unsigned short
#endif
#ifndef PCRE_SPTR16
#define PCRE_SPTR16 const PCRE_UCHAR16 *
#endif
/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain
a 32 bit wide signed data type. Otherwise it can be a dummy data type since
pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */
#ifndef PCRE_UCHAR32
#define PCRE_UCHAR32 unsigned int
#endif
#ifndef PCRE_SPTR32
#define PCRE_SPTR32 const PCRE_UCHAR32 *
#endif
/* When PCRE is compiled as a C++ library, the subject pointer type can be
replaced with a custom type. For conventional use, the public interface is a
const char *. */
#ifndef PCRE_SPTR
#define PCRE_SPTR const char *
#endif
/* The structure for passing additional data to pcre_exec(). This is defined in
such as way as to be extensible. Always add new fields at the end, in order to
remain compatible. */
@ -174,8 +379,37 @@ typedef struct pcre_extra {
unsigned long int match_limit; /* Maximum number of calls to match() */
void *callout_data; /* Data passed back in callouts */
const unsigned char *tables; /* Pointer to character tables */
unsigned long int match_limit_recursion; /* Max recursive calls to match() */
unsigned char **mark; /* For passing back a mark pointer */
void *executable_jit; /* Contains a pointer to a compiled jit code */
} pcre_extra;
/* Same structure as above, but with 16 bit char pointers. */
typedef struct pcre16_extra {
unsigned long int flags; /* Bits for which fields are set */
void *study_data; /* Opaque data from pcre_study() */
unsigned long int match_limit; /* Maximum number of calls to match() */
void *callout_data; /* Data passed back in callouts */
const unsigned char *tables; /* Pointer to character tables */
unsigned long int match_limit_recursion; /* Max recursive calls to match() */
PCRE_UCHAR16 **mark; /* For passing back a mark pointer */
void *executable_jit; /* Contains a pointer to a compiled jit code */
} pcre16_extra;
/* Same structure as above, but with 32 bit char pointers. */
typedef struct pcre32_extra {
unsigned long int flags; /* Bits for which fields are set */
void *study_data; /* Opaque data from pcre_study() */
unsigned long int match_limit; /* Maximum number of calls to match() */
void *callout_data; /* Data passed back in callouts */
const unsigned char *tables; /* Pointer to character tables */
unsigned long int match_limit_recursion; /* Max recursive calls to match() */
PCRE_UCHAR32 **mark; /* For passing back a mark pointer */
void *executable_jit; /* Contains a pointer to a compiled jit code */
} pcre32_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
@ -186,7 +420,7 @@ typedef struct pcre_callout_block {
/* ------------------------ Version 0 ------------------------------- */
int callout_number; /* Number compiled into pattern */
int *offset_vector; /* The offset vector */
const char *subject; /* The subject being matched */
PCRE_SPTR subject; /* The subject being matched */
int subject_length; /* The length of the subject */
int start_match; /* Offset to start of this match attempt */
int current_position; /* Where we currently are in the subject */
@ -196,9 +430,55 @@ typedef struct pcre_callout_block {
/* ------------------- 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 */
/* ------------------- Added for Version 2 -------------------------- */
const unsigned char *mark; /* Pointer to current mark or NULL */
/* ------------------------------------------------------------------ */
} pcre_callout_block;
/* Same structure as above, but with 16 bit char pointers. */
typedef struct pcre16_callout_block {
int version; /* Identifies version of block */
/* ------------------------ Version 0 ------------------------------- */
int callout_number; /* Number compiled into pattern */
int *offset_vector; /* The offset vector */
PCRE_SPTR16 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 */
/* ------------------- Added for Version 2 -------------------------- */
const PCRE_UCHAR16 *mark; /* Pointer to current mark or NULL */
/* ------------------------------------------------------------------ */
} pcre16_callout_block;
/* Same structure as above, but with 32 bit char pointers. */
typedef struct pcre32_callout_block {
int version; /* Identifies version of block */
/* ------------------------ Version 0 ------------------------------- */
int callout_number; /* Number compiled into pattern */
int *offset_vector; /* The offset vector */
PCRE_SPTR32 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 */
/* ------------------- Added for Version 2 -------------------------- */
const PCRE_UCHAR32 *mark; /* Pointer to current mark or NULL */
/* ------------------------------------------------------------------ */
} pcre32_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
@ -206,50 +486,189 @@ 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 *);
PCRE_EXP_DECL void *(*pcre_malloc)(size_t);
PCRE_EXP_DECL void (*pcre_free)(void *);
PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
PCRE_EXP_DECL void (*pcre_stack_free)(void *);
PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *);
PCRE_EXP_DECL int (*pcre_stack_guard)(void);
PCRE_EXP_DECL void *(*pcre16_malloc)(size_t);
PCRE_EXP_DECL void (*pcre16_free)(void *);
PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t);
PCRE_EXP_DECL void (*pcre16_stack_free)(void *);
PCRE_EXP_DECL int (*pcre16_callout)(pcre16_callout_block *);
PCRE_EXP_DECL int (*pcre16_stack_guard)(void);
PCRE_EXP_DECL void *(*pcre32_malloc)(size_t);
PCRE_EXP_DECL void (*pcre32_free)(void *);
PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t);
PCRE_EXP_DECL void (*pcre32_stack_free)(void *);
PCRE_EXP_DECL int (*pcre32_callout)(pcre32_callout_block *);
PCRE_EXP_DECL int (*pcre32_stack_guard)(void);
#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 *);
PCRE_EXP_DECL void *pcre_malloc(size_t);
PCRE_EXP_DECL void pcre_free(void *);
PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
PCRE_EXP_DECL void pcre_stack_free(void *);
PCRE_EXP_DECL int pcre_callout(pcre_callout_block *);
PCRE_EXP_DECL int pcre_stack_guard(void);
PCRE_EXP_DECL void *pcre16_malloc(size_t);
PCRE_EXP_DECL void pcre16_free(void *);
PCRE_EXP_DECL void *pcre16_stack_malloc(size_t);
PCRE_EXP_DECL void pcre16_stack_free(void *);
PCRE_EXP_DECL int pcre16_callout(pcre16_callout_block *);
PCRE_EXP_DECL int pcre16_stack_guard(void);
PCRE_EXP_DECL void *pcre32_malloc(size_t);
PCRE_EXP_DECL void pcre32_free(void *);
PCRE_EXP_DECL void *pcre32_stack_malloc(size_t);
PCRE_EXP_DECL void pcre32_stack_free(void *);
PCRE_EXP_DECL int pcre32_callout(pcre32_callout_block *);
PCRE_EXP_DECL int pcre32_stack_guard(void);
#endif /* VPCOMPAT */
/* User defined callback which provides a stack just before the match starts. */
typedef pcre_jit_stack *(*pcre_jit_callback)(void *);
typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *);
typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *);
/* Exported PCRE functions */
PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *,
PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
const unsigned char *);
PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **,
PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *,
const unsigned char *);
PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *,
const unsigned char *);
PCRE_EXP_DECL 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 *,
PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **,
int *, const unsigned char *);
PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **,
int *, const unsigned char *);
PCRE_EXP_DECL int pcre_config(int, void *);
PCRE_EXP_DECL int pcre16_config(int, void *);
PCRE_EXP_DECL int pcre32_config(int, void *);
PCRE_EXP_DECL 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 *,
PCRE_EXP_DECL int pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16,
int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int);
PCRE_EXP_DECL int pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32,
int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int);
PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int,
char *, int);
PCRE_EXP_DECL int pcre16_copy_substring(PCRE_SPTR16, int *, int, int,
PCRE_UCHAR16 *, int);
PCRE_EXP_DECL int pcre32_copy_substring(PCRE_SPTR32, int *, int, int,
PCRE_UCHAR32 *, int);
PCRE_EXP_DECL 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 *,
PCRE_EXP_DECL int pcre16_dfa_exec(const pcre16 *, const pcre16_extra *,
PCRE_SPTR16, int, int, int, int *, int , int *, int);
PCRE_EXP_DECL int pcre32_dfa_exec(const pcre32 *, const pcre32_extra *,
PCRE_SPTR32, int, int, int, int *, int , int *, int);
PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
int, int, int, int *, int);
PCRE_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,
PCRE_EXP_DECL int pcre16_exec(const pcre16 *, const pcre16_extra *,
PCRE_SPTR16, int, int, int, int *, int);
PCRE_EXP_DECL int pcre32_exec(const pcre32 *, const pcre32_extra *,
PCRE_SPTR32, int, int, int, int *, int);
PCRE_EXP_DECL int pcre_jit_exec(const pcre *, const pcre_extra *,
PCRE_SPTR, int, int, int, int *, int,
pcre_jit_stack *);
PCRE_EXP_DECL int pcre16_jit_exec(const pcre16 *, const pcre16_extra *,
PCRE_SPTR16, int, int, int, int *, int,
pcre16_jit_stack *);
PCRE_EXP_DECL int pcre32_jit_exec(const pcre32 *, const pcre32_extra *,
PCRE_SPTR32, int, int, int, int *, int,
pcre32_jit_stack *);
PCRE_EXP_DECL void pcre_free_substring(const char *);
PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16);
PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32);
PCRE_EXP_DECL void pcre_free_substring_list(const char **);
PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *);
PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *);
PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int,
void *);
PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *,
PCRE_EXP_DECL int pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int,
void *);
PCRE_EXP_DECL int pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int,
void *);
PCRE_EXP_DECL 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,
PCRE_EXP_DECL int pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16,
int *, int, PCRE_SPTR16, PCRE_SPTR16 *);
PCRE_EXP_DECL int pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32,
int *, int, PCRE_SPTR32, PCRE_SPTR32 *);
PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *);
PCRE_EXP_DECL int pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16);
PCRE_EXP_DECL int pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32);
PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *,
char **, char **);
PCRE_EXP_DECL int pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16,
PCRE_UCHAR16 **, PCRE_UCHAR16 **);
PCRE_EXP_DECL int pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32,
PCRE_UCHAR32 **, PCRE_UCHAR32 **);
PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int,
const char **);
PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int,
PCRE_EXP_DECL int pcre16_get_substring(PCRE_SPTR16, int *, int, int,
PCRE_SPTR16 *);
PCRE_EXP_DECL int pcre32_get_substring(PCRE_SPTR32, int *, int, int,
PCRE_SPTR32 *);
PCRE_EXP_DECL 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);
PCRE_EXP_DECL int pcre16_get_substring_list(PCRE_SPTR16, int *, int,
PCRE_SPTR16 **);
PCRE_EXP_DECL int pcre32_get_substring_list(PCRE_SPTR32, int *, int,
PCRE_SPTR32 **);
PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
PCRE_EXP_DECL const unsigned char *pcre16_maketables(void);
PCRE_EXP_DECL const unsigned char *pcre32_maketables(void);
PCRE_EXP_DECL int pcre_refcount(pcre *, int);
PCRE_EXP_DECL int pcre16_refcount(pcre16 *, int);
PCRE_EXP_DECL int pcre32_refcount(pcre32 *, int);
PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **);
PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **);
PCRE_EXP_DECL void pcre_free_study(pcre_extra *);
PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *);
PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *);
PCRE_EXP_DECL const char *pcre_version(void);
PCRE_EXP_DECL const char *pcre16_version(void);
PCRE_EXP_DECL const char *pcre32_version(void);
/* Utility functions for byte order swaps. */
PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *, pcre_extra *,
const unsigned char *);
PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *,
const unsigned char *);
PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *,
const unsigned char *);
PCRE_EXP_DECL int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *,
PCRE_SPTR16, int, int *, int);
PCRE_EXP_DECL int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *,
PCRE_SPTR32, int, int *, int);
/* JIT compiler related functions. */
PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int);
PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int);
PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int);
PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *);
PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *);
PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *);
PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *,
pcre_jit_callback, void *);
PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *,
pcre16_jit_callback, void *);
PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *,
pcre32_jit_callback, void *);
PCRE_EXP_DECL void pcre_jit_free_unused_memory(void);
PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void);
PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void);
#ifdef __cplusplus
} /* extern "C" */

241
dlls/regex/utils.cpp Normal file
View File

@ -0,0 +1,241 @@
#include "amxxmodule.h"
#include <string.h>
#include "utils.h"
#if defined(WIN32)
#define strcasecmp stricmp
#define strncasecmp _strnicmp
#endif
int UTIL_CheckValidChar(char *c)
{
int count;
int bytecount = 0;
for (count = 1; (*c & 0xC0) == 0x80; count++)
{
c--;
}
switch (*c & 0xF0)
{
case 0xC0:
case 0xD0:
{
bytecount = 2;
break;
}
case 0xE0:
{
bytecount = 3;
break;
}
case 0xF0:
{
bytecount = 4;
break;
}
}
if (bytecount != count)
{
return count;
}
return 0;
}
unsigned int strncopy(char *dest, const char *src, size_t count)
{
if (!count)
{
return 0;
}
char *start = dest;
while ((*src) && (--count))
{
*dest++ = *src++;
}
*dest = '\0';
return (dest - start);
}
/**
* NOTE: Do not edit this for the love of god unless you have
* read the test cases and understand the code behind each one.
* While I don't guarantee there aren't mistakes, I do guarantee
* that plugins will end up relying on tiny idiosyncrasies of this
* function, just like they did with AMX Mod X.
*
* There are explicitly more cases than the AMX Mod X version because
* we're not doing a blind copy. Each case is specifically optimized
* for what needs to be done. Even better, we don't have to error on
* bad buffer sizes. Instead, this function will smartly cut off the
* string in a way that pushes old data out.
*/
char *UTIL_ReplaceEx(char *subject, size_t maxLen, const char *search, size_t searchLen, const char *replace, size_t replaceLen, bool caseSensitive)
{
char *ptr = subject;
size_t browsed = 0;
size_t textLen = strlen(subject);
/* It's not possible to search or replace */
if (searchLen > textLen)
{
return NULL;
}
/* Handle the case of one byte replacement.
* It's only valid in one case.
*/
if (maxLen == 1)
{
/* If the search matches and the replace length is 0,
* we can just terminate the string and be done.
*/
if ((caseSensitive ? strcmp(subject, search) : strcasecmp(subject, search)) == 0 && replaceLen == 0)
{
*subject = '\0';
return subject;
}
else
{
return NULL;
}
}
/* Subtract one off the maxlength so we can include the null terminator */
maxLen--;
while (*ptr != '\0' && (browsed <= textLen - searchLen))
{
/* See if we get a comparison */
if ((caseSensitive ? strncmp(ptr, search, searchLen) : strncasecmp(ptr, search, searchLen)) == 0)
{
if (replaceLen > searchLen)
{
/* First, see if we have enough space to do this operation */
if (maxLen - textLen < replaceLen - searchLen)
{
/* First, see if the replacement length goes out of bounds. */
if (browsed + replaceLen >= maxLen)
{
/* EXAMPLE CASE:
* Subject: AABBBCCC
* Buffer : 12 bytes
* Search : BBB
* Replace: DDDDDDDDDD
* OUTPUT : AADDDDDDDDD
* POSITION: ^
*/
/* If it does, we'll just bound the length and do a strcpy. */
replaceLen = maxLen - browsed;
/* Note, we add one to the final result for the null terminator */
strncopy(ptr, replace, replaceLen + 1);
/* Don't truncate a multi-byte character */
if (*(ptr + replaceLen - 1) & 1 << 7)
{
replaceLen -= UTIL_CheckValidChar(ptr + replaceLen - 1);
*(ptr + replaceLen) = '\0';
}
}
else
{
/* EXAMPLE CASE:
* Subject: AABBBCCC
* Buffer : 12 bytes
* Search : BBB
* Replace: DDDDDDD
* OUTPUT : AADDDDDDDCC
* POSITION: ^
*/
/* We're going to have some bytes left over... */
size_t origBytesToCopy = (textLen - (browsed + searchLen)) + 1;
size_t realBytesToCopy = (maxLen - (browsed + replaceLen)) + 1;
char *moveFrom = ptr + searchLen + (origBytesToCopy - realBytesToCopy);
char *moveTo = ptr + replaceLen;
/* First, move our old data out of the way. */
memmove(moveTo, moveFrom, realBytesToCopy);
/* Now, do our replacement. */
memcpy(ptr, replace, replaceLen);
}
}
else
{
/* EXAMPLE CASE:
* Subject: AABBBCCC
* Buffer : 12 bytes
* Search : BBB
* Replace: DDDD
* OUTPUT : AADDDDCCC
* POSITION: ^
*/
/* Yes, we have enough space. Do a normal move operation. */
char *moveFrom = ptr + searchLen;
char *moveTo = ptr + replaceLen;
/* First move our old data out of the way. */
size_t bytesToCopy = (textLen - (browsed + searchLen)) + 1;
memmove(moveTo, moveFrom, bytesToCopy);
/* Now do our replacement. */
memcpy(ptr, replace, replaceLen);
}
}
else if (replaceLen < searchLen)
{
/* EXAMPLE CASE:
* Subject: AABBBCCC
* Buffer : 12 bytes
* Search : BBB
* Replace: D
* OUTPUT : AADCCC
* POSITION: ^
*/
/* If the replacement does not grow the string length, we do not
* need to do any fancy checking at all. Yay!
*/
char *moveFrom = ptr + searchLen; /* Start after the search pointer */
char *moveTo = ptr + replaceLen; /* Copy to where the replacement ends */
/* Copy our replacement in, if any */
if (replaceLen)
{
memcpy(ptr, replace, replaceLen);
}
/* Figure out how many bytes to move down, including null terminator */
size_t bytesToCopy = (textLen - (browsed + searchLen)) + 1;
/* Move the rest of the string down */
memmove(moveTo, moveFrom, bytesToCopy);
}
else
{
/* EXAMPLE CASE:
* Subject: AABBBCCC
* Buffer : 12 bytes
* Search : BBB
* Replace: DDD
* OUTPUT : AADDDCCC
* POSITION: ^
*/
/* We don't have to move anything around, just do a straight copy */
memcpy(ptr, replace, replaceLen);
}
return ptr + replaceLen;
}
ptr++;
browsed++;
}
return NULL;
}

8
dlls/regex/utils.h Normal file
View File

@ -0,0 +1,8 @@
#ifndef UTILS_H
#define UTILS_H
int UTIL_CheckValidChar(char *c);
char *UTIL_ReplaceEx(char *subject, size_t maxLen, const char *search, size_t searchLen, const char *replace, size_t replaceLen, bool caseSensitive);
unsigned int strncopy(char *dest, const char *src, size_t count);
#endif // UTILS_H