kjs/regexp.cpp

   1 // -*- c-basic-offset: 2 -*-
   2 /*
   3  *  This file is part of the KDE libraries
   4  *  Copyright (C) 1999-2001, 2004 Harri Porten (porten@kde.org)
   5  *  Copyright (c) 2007, Apple Inc.
   6  *
   7  *  This library is free software; you can redistribute it and/or
   8  *  modify it under the terms of the GNU Lesser General Public
   9  *  License as published by the Free Software Foundation; either
  10  *  version 2 of the License, or (at your option) any later version.
  11  *
  12  *  This library is distributed in the hope that it will be useful,
  13  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15  *  Lesser General Public License for more details.
  16  *
  17  *  You should have received a copy of the GNU Lesser General Public
  18  *  License along with this library; if not, write to the Free Software
  19  *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  20  *
  21  */
  22
  23 #include "config.h"
  24 #include "regexp.h"
  25
  26 #include "lexer.h"
  27 #include <stdio.h>
  28 #include <stdlib.h>
  29 #include <string.h>
  30 #include <wtf/Assertions.h>
  31
  32 namespace KJS {
  33
  34 RegExp::RegExp(const UString& pattern)
  35   : m_pattern(pattern)
  36   , m_flagBits(0)
  37   , m_constructionError(0)
  38   , m_numSubpatterns(0)
  39 {
  40     m_regExp = jsRegExpCompile(reinterpret_cast<const ::UChar*>(pattern.data()), pattern.size(),
  41         JSRegExpDoNotIgnoreCase, JSRegExpSingleLine, &m_numSubpatterns, &m_constructionError);
  42 }
  43
  44 RegExp::RegExp(const UString& pattern, const UString& flags)
  45   : m_pattern(pattern)
  46   , m_flags(flags)
  47   , m_flagBits(0)
  48   , m_constructionError(0)
  49   , m_numSubpatterns(0)
  50 {
  51     // NOTE: The global flag is handled on a case-by-case basis by functions like
  52     // String::match and RegExpImp::match.
  53     if (flags.find('g') != -1)
  54         m_flagBits |= Global;
  55
  56     // FIXME: Eliminate duplication by adding a way ask a JSRegExp what its flags are?
  57     JSRegExpIgnoreCaseOption ignoreCaseOption = JSRegExpDoNotIgnoreCase;
  58     if (flags.find('i') != -1) {
  59         m_flagBits |= IgnoreCase;
  60         ignoreCaseOption = JSRegExpIgnoreCase;
  61     }
  62
  63     JSRegExpMultilineOption multilineOption = JSRegExpSingleLine;
  64     if (flags.find('m') != -1) {
  65         m_flagBits |= Multiline;
  66         multilineOption = JSRegExpMultiline;
  67     }
  68
  69     m_regExp = jsRegExpCompile(reinterpret_cast<const ::UChar*>(pattern.data()), pattern.size(),
  70         ignoreCaseOption, multilineOption, &m_numSubpatterns, &m_constructionError);
  71 }
  72
  73 RegExp::~RegExp()
  74 {
  75     jsRegExpFree(m_regExp);
  76 }
  77
  78 int RegExp::match(const UString& s, int i, OwnArrayPtr<int>* ovector)
  79 {
  80   if (i < 0)
  81     i = 0;
  82   if (ovector)
  83     ovector->clear();
  84
  85   if (i > s.size() || s.isNull())
  86     return -1;
  87
  88   if (!m_regExp)
  89     return -1;
  90
  91   // Set up the offset vector for the result.
  92   // First 2/3 used for result, the last third used by PCRE.
  93   int* offsetVector;
  94   int offsetVectorSize;
  95   int fixedSizeOffsetVector[3];
  96   if (!ovector) {
  97     offsetVectorSize = 3;
  98     offsetVector = fixedSizeOffsetVector;
  99   } else {
 100     offsetVectorSize = (m_numSubpatterns + 1) * 3;
 101     offsetVector = new int [offsetVectorSize];
 102     ovector->set(offsetVector);
 103   }
 104
 105   int numMatches = jsRegExpExecute(m_regExp, reinterpret_cast<const ::UChar*>(s.data()), s.size(), i, offsetVector, offsetVectorSize);
 106
 107   if (numMatches < 0) {
 108 #ifndef NDEBUG
 109     if (numMatches != JSRegExpErrorNoMatch)
 110       fprintf(stderr, "jsRegExpExecute failed with result %d\n", numMatches);
 111 #endif
 112     if (ovector)
 113       ovector->clear();
 114     return -1;
 115   }
 116
 117   return offsetVector[0];
 118 }
 119
 120 } // namespace KJS