runtime/RegExp.cpp

   1 /*
   2  *  Copyright (C) 1999-2001, 2004 Harri Porten (porten@kde.org)
   3  *  Copyright (c) 2007, 2008 Apple Inc. All rights reserved.
   4  *
   5  *  This library is free software; you can redistribute it and/or
   6  *  modify it under the terms of the GNU Lesser General Public
   7  *  License as published by the Free Software Foundation; either
   8  *  version 2 of the License, or (at your option) any later version.
   9  *
  10  *  This library is distributed in the hope that it will be useful,
  11  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13  *  Lesser General Public License for more details.
  14  *
  15  *  You should have received a copy of the GNU Lesser General Public
  16  *  License along with this library; if not, write to the Free Software
  17  *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  18  *
  19  */
  20
  21 #include "config.h"
  22 #include "RegExp.h"
  23
  24 #include "JIT.h"
  25 #include "Lexer.h"
  26 #include "WRECGenerator.h"
  27 #include <pcre/pcre.h>
  28 #include <stdio.h>
  29 #include <stdlib.h>
  30 #include <string.h>
  31 #include <wtf/Assertions.h>
  32 #include <wtf/OwnArrayPtr.h>
  33
  34 namespace JSC {
  35
  36 #if ENABLE(WREC)
  37 using namespace WREC;
  38 #endif
  39
  40 inline RegExp::RegExp(JSGlobalData* globalData, const UString& pattern)
  41     : m_pattern(pattern)
  42     , m_flagBits(0)
  43     , m_regExp(0)
  44     , m_constructionError(0)
  45     , m_numSubpatterns(0)
  46 {
  47 #if ENABLE(WREC)
  48     m_wrecFunction = Generator::compileRegExp(globalData, pattern, &m_numSubpatterns, &m_constructionError, m_executablePool);
  49     if (m_wrecFunction || m_constructionError)
  50         return;
  51     // Fall through to non-WREC case.
  52 #else
  53     UNUSED_PARAM(globalData);
  54 #endif
  55     m_regExp = jsRegExpCompile(reinterpret_cast<const UChar*>(pattern.data()), pattern.size(),
  56         JSRegExpDoNotIgnoreCase, JSRegExpSingleLine, &m_numSubpatterns, &m_constructionError);
  57 }
  58
  59 PassRefPtr<RegExp> RegExp::create(JSGlobalData* globalData, const UString& pattern)
  60 {
  61     return adoptRef(new RegExp(globalData, pattern));
  62 }
  63
  64 inline RegExp::RegExp(JSGlobalData* globalData, const UString& pattern, const UString& flags)
  65     : m_pattern(pattern)
  66     , m_flags(flags)
  67     , m_flagBits(0)
  68     , m_regExp(0)
  69     , m_constructionError(0)
  70     , m_numSubpatterns(0)
  71 {
  72     // NOTE: The global flag is handled on a case-by-case basis by functions like
  73     // String::match and RegExpObject::match.
  74     if (flags.find('g') != -1)
  75         m_flagBits |= Global;
  76
  77     // FIXME: Eliminate duplication by adding a way ask a JSRegExp what its flags are?
  78     JSRegExpIgnoreCaseOption ignoreCaseOption = JSRegExpDoNotIgnoreCase;
  79     if (flags.find('i') != -1) {
  80         m_flagBits |= IgnoreCase;
  81         ignoreCaseOption = JSRegExpIgnoreCase;
  82     }
  83
  84     JSRegExpMultilineOption multilineOption = JSRegExpSingleLine;
  85     if (flags.find('m') != -1) {
  86         m_flagBits |= Multiline;
  87         multilineOption = JSRegExpMultiline;
  88     }
  89
  90 #if ENABLE(WREC)
  91     m_wrecFunction = Generator::compileRegExp(globalData, pattern, &m_numSubpatterns, &m_constructionError, m_executablePool, (m_flagBits & IgnoreCase), (m_flagBits & Multiline));
  92     if (m_wrecFunction || m_constructionError)
  93         return;
  94     // Fall through to non-WREC case.
  95 #else
  96     UNUSED_PARAM(globalData);
  97 #endif
  98     m_regExp = jsRegExpCompile(reinterpret_cast<const UChar*>(pattern.data()), pattern.size(),
  99         ignoreCaseOption, multilineOption, &m_numSubpatterns, &m_constructionError);
 100 }
 101
 102 PassRefPtr<RegExp> RegExp::create(JSGlobalData* globalData, const UString& pattern, const UString& flags)
 103 {
 104     return adoptRef(new RegExp(globalData, pattern, flags));
 105 }
 106
 107 RegExp::~RegExp()
 108 {
 109     jsRegExpFree(m_regExp);
 110 }
 111
 112 int RegExp::match(const UString& s, int startOffset, OwnArrayPtr<int>* ovector)
 113 {
 114     if (startOffset < 0)
 115         startOffset = 0;
 116     if (ovector)
 117         ovector->clear();
 118
 119     if (startOffset > s.size() || s.isNull())
 120         return -1;
 121
 122 #if ENABLE(WREC)
 123     if (m_wrecFunction) {
 124         int offsetVectorSize = (m_numSubpatterns + 1) * 2;
 125         int* offsetVector = new int [offsetVectorSize];
 126         for (int j = 0; j < offsetVectorSize; ++j)
 127             offsetVector[j] = -1;
 128
 129         OwnArrayPtr<int> nonReturnedOvector;
 130         if (!ovector)
 131             nonReturnedOvector.set(offsetVector);
 132         else
 133             ovector->set(offsetVector);
 134
 135         int result = m_wrecFunction(s.data(), startOffset, s.size(), offsetVector);
 136
 137         if (result < 0) {
 138 #ifndef NDEBUG
 139             // TODO: define up a symbol, rather than magic -1
 140             if (result != -1)
 141                 fprintf(stderr, "jsRegExpExecute failed with result %d\n", result);
 142 #endif
 143             if (ovector)
 144                 ovector->clear();
 145         }
 146         return result;
 147     } else
 148 #endif
 149     if (m_regExp) {
 150         // Set up the offset vector for the result.
 151         // First 2/3 used for result, the last third used by PCRE.
 152         int* offsetVector;
 153         int offsetVectorSize;
 154         int fixedSizeOffsetVector[3];
 155         if (!ovector) {
 156             offsetVectorSize = 3;
 157             offsetVector = fixedSizeOffsetVector;
 158         } else {
 159             offsetVectorSize = (m_numSubpatterns + 1) * 3;
 160             offsetVector = new int [offsetVectorSize];
 161             ovector->set(offsetVector);
 162         }
 163
 164         int numMatches = jsRegExpExecute(m_regExp, reinterpret_cast<const UChar*>(s.data()), s.size(), startOffset, offsetVector, offsetVectorSize);
 165
 166         if (numMatches < 0) {
 167 #ifndef NDEBUG
 168             if (numMatches != JSRegExpErrorNoMatch)
 169                 fprintf(stderr, "jsRegExpExecute failed with result %d\n", numMatches);
 170 #endif
 171             if (ovector)
 172                 ovector->clear();
 173             return -1;
 174         }
 175
 176         return offsetVector[0];
 177     }
 178
 179     return -1;
 180 }
 181
 182 } // namespace JSC