wrec/CharacterClassConstructor.h

   1 /*
   2  * Copyright (C) 2008 Apple Inc. All rights reserved.
   3  *
   4  * Redistribution and use in source and binary forms, with or without
   5  * modification, are permitted provided that the following conditions
   6  * are met:
   7  * 1. Redistributions of source code must retain the above copyright
   8  *    notice, this list of conditions and the following disclaimer.
   9  * 2. Redistributions in binary form must reproduce the above copyright
  10  *    notice, this list of conditions and the following disclaimer in the
  11  *    documentation and/or other materials provided with the distribution.
  12  *
  13  * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
  14  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  15  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  16  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
  17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  19  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  20  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  21  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  22  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  23  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  24  */
  25
  26 #ifndef CharacterClassConstructor_h
  27 #define CharacterClassConstructor_h
  28
  29 #include <wtf/Platform.h>
  30
  31 #if ENABLE(WREC)
  32
  33 #include "CharacterClass.h"
  34 #include <wtf/AlwaysInline.h>
  35 #include <wtf/Vector.h>
  36 #include <wtf/unicode/Unicode.h>
  37
  38 namespace JSC { namespace WREC {
  39
  40     class CharacterClassConstructor {
  41     public:
  42         CharacterClassConstructor(bool isCaseInsensitive)
  43             : m_charBuffer(-1)
  44             , m_isPendingDash(false)
  45             , m_isCaseInsensitive(isCaseInsensitive)
  46             , m_isUpsideDown(false)
  47         {
  48         }
  49
  50         void flush();
  51
  52         // We need to flush prior to an escaped hyphen to prevent it as being treated as indicating
  53         // a range, e.g. [a\-c] we flush prior to adding the hyphen so that this is not treated as
  54         // [a-c].  However, we do not want to flush if we have already seen a non escaped hyphen -
  55         // e.g. [+-\-] should be treated the same as [+--], producing a range that will also match
  56         // a comma.
  57         void flushBeforeEscapedHyphen()
  58         {
  59             if (!m_isPendingDash)
  60                 flush();
  61         }
  62
  63         void put(UChar ch);
  64         void append(const CharacterClass& other);
  65
  66         bool isUpsideDown() { return m_isUpsideDown; }
  67
  68         ALWAYS_INLINE CharacterClass charClass()
  69         {
  70             CharacterClass newCharClass = {
  71                 m_matches.begin(), m_matches.size(),
  72                 m_ranges.begin(), m_ranges.size(),
  73                 m_matchesUnicode.begin(), m_matchesUnicode.size(),
  74                 m_rangesUnicode.begin(), m_rangesUnicode.size(),
  75             };
  76
  77             return newCharClass;
  78         }
  79
  80     private:
  81         void addSorted(Vector<UChar>& matches, UChar ch);
  82         void addSortedRange(Vector<CharacterRange>& ranges, UChar lo, UChar hi);
  83
  84         int m_charBuffer;
  85         bool m_isPendingDash;
  86         bool m_isCaseInsensitive;
  87         bool m_isUpsideDown;
  88
  89         Vector<UChar> m_matches;
  90         Vector<CharacterRange> m_ranges;
  91         Vector<UChar> m_matchesUnicode;
  92         Vector<CharacterRange> m_rangesUnicode;
  93     };
  94
  95 } } // namespace JSC::WREC
  96
  97 #endif // ENABLE(WREC)
  98
  99 #endif // CharacterClassConstructor_h