kjs/regexp.h

   1 // -*- c-basic-offset: 2 -*-
   2 /*
   3  *  This file is part of the KDE libraries
   4  *  Copyright (C) 1999-2000 Harri Porten (porten@kde.org)
   5  *
   6  *  This library is free software; you can redistribute it and/or
   7  *  modify it under the terms of the GNU Lesser General Public
   8  *  License as published by the Free Software Foundation; either
   9  *  version 2 of the License, or (at your option) any later version.
  10  *
  11  *  This library is distributed in the hope that it will be useful,
  12  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14  *  Lesser General Public License for more details.
  15  *
  16  *  You should have received a copy of the GNU Lesser General Public
  17  *  License along with this library; if not, write to the Free Software
  18  *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  19  *
  20  */
  21
  22 #ifndef _KJS_REGEXP_H_
  23 #define _KJS_REGEXP_H_
  24
  25 #include <sys/types.h>
  26
  27 #include "global.h"
  28
  29 #include <config.h>
  30
  31 #ifdef HAVE_PCREPOSIX
  32 #include <pcre.h>
  33 #else  // POSIX regex - not so good...
  34 extern "C" { // bug with some libc5 distributions
  35 #include <regex.h>
  36 }
  37 #endif //HAVE_PCREPOSIX
  38
  39 #include "ustring.h"
  40
  41 namespace KJS {
  42
  43   class RegExp {
  44   public:
  45     enum { None = 0, Global = 1, IgnoreCase = 2, Multiline = 4 };
  46
  47     explicit RegExp(const UString &pattern, char flags = None);
  48     ~RegExp();
  49
  50     char flags() const { return _flags; }
  51     bool isValid() const { return _valid; }
  52
  53     UString match(const UString &s, bool *error, int i, int *pos = 0, int **ovector = 0);
  54     unsigned subPatterns() const { return _numSubPatterns; }
  55     UString  pattern() const { return _pat; }
  56
  57     //These methods should be called around the match of the same string..
  58     void prepareMatch(const UString &s);
  59     void doneMatch();
  60
  61   private:
  62 #ifdef HAVE_PCREPOSIX
  63     pcre *_regex;
  64 #else
  65     regex_t _regex;
  66 #endif
  67     UString _pat;
  68     char _flags;
  69     bool _valid;
  70     unsigned _numSubPatterns;
  71
  72     // Cached encoding info...
  73     char* _buffer;
  74     int*  _originalPos;
  75     int   _bufferSize;
  76
  77     void prepareUtf8  (const UString& s);
  78     void prepareASCII (const UString& s);
  79 #ifndef NDEBUG
  80     UString _originalS; // the original string, used for sanity-checking
  81 #endif
  82
  83     RegExp(const RegExp &);
  84     RegExp &operator=(const RegExp &);
  85
  86     enum UTF8SupportState {
  87       Unknown,
  88       Supported,
  89       Unsupported
  90     };
  91
  92     static UTF8SupportState utf8Support;
  93   };
  94
  95 } // namespace
  96
  97 #endif