parser/Lexer.h

   1 /*
   2  *  Copyright (C) 1999-2000 Harri Porten (porten@kde.org)
   3  *  Copyright (C) 2002, 2003, 2004, 2005, 2006, 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 Library 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  *  Library General Public License for more details.
  14  *
  15  *  You should have received a copy of the GNU Library General Public License
  16  *  along with this library; see the file COPYING.LIB.  If not, write to
  17  *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  18  *  Boston, MA 02110-1301, USA.
  19  *
  20  */
  21
  22 #ifndef Lexer_h
  23 #define Lexer_h
  24
  25 #include "Identifier.h"
  26 #include "Lookup.h"
  27 #include "SegmentedVector.h"
  28 #include "SourceCode.h"
  29 #include <wtf/Vector.h>
  30
  31 namespace JSC {
  32
  33     class RegExp;
  34
  35     class Lexer : Noncopyable {
  36     public:
  37         void setCode(const SourceCode&);
  38         void setIsReparsing() { m_isReparsing = true; }
  39         int lex(void* lvalp, void* llocp);
  40
  41         int lineNo() const { return yylineno; }
  42
  43         bool prevTerminator() const { return m_terminator; }
  44
  45         enum State {
  46             Start,
  47             IdentifierOrKeyword,
  48             Identifier,
  49             InIdentifierOrKeyword,
  50             InIdentifier,
  51             InIdentifierStartUnicodeEscapeStart,
  52             InIdentifierStartUnicodeEscape,
  53             InIdentifierPartUnicodeEscapeStart,
  54             InIdentifierPartUnicodeEscape,
  55             InSingleLineComment,
  56             InMultiLineComment,
  57             InNum,
  58             InNum0,
  59             InHex,
  60             InOctal,
  61             InDecimal,
  62             InExponentIndicator,
  63             InExponent,
  64             Hex,
  65             Octal,
  66             Number,
  67             String,
  68             Eof,
  69             InString,
  70             InEscapeSequence,
  71             InHexEscape,
  72             InUnicodeEscape,
  73             Other,
  74             Bad
  75         };
  76
  77         bool scanRegExp();
  78         const UString& pattern() const { return m_pattern; }
  79         const UString& flags() const { return m_flags; }
  80
  81         static unsigned char convertHex(int);
  82         static unsigned char convertHex(int c1, int c2);
  83         static UChar convertUnicode(int c1, int c2, int c3, int c4);
  84         static bool isIdentStart(int);
  85         static bool isIdentPart(int);
  86         static bool isHexDigit(int);
  87
  88         bool sawError() const { return m_error; }
  89
  90         void clear();
  91         SourceCode sourceCode(int openBrace, int closeBrace, int firstLine) { return SourceCode(m_source->provider(), openBrace, closeBrace + 1, firstLine); }
  92
  93     private:
  94         friend class JSGlobalData;
  95         Lexer(JSGlobalData*);
  96         ~Lexer();
  97
  98         void setDone(State);
  99         void shift(unsigned int p);
 100         void nextLine();
 101         int lookupKeyword(const char *);
 102
 103         bool isWhiteSpace() const;
 104         bool isLineTerminator();
 105         static bool isOctalDigit(int);
 106
 107         ALWAYS_INLINE int matchPunctuator(int& charPos, int c1, int c2, int c3, int c4);
 108         static unsigned short singleEscape(unsigned short);
 109         static unsigned short convertOctal(int c1, int c2, int c3);
 110
 111         void record8(int);
 112         void record16(int);
 113         void record16(UChar);
 114
 115         JSC::Identifier* makeIdentifier(const Vector<UChar>& buffer)
 116         {
 117             m_identifiers.append(JSC::Identifier(m_globalData, buffer.data(), buffer.size()));
 118             return &m_identifiers.last();
 119         }
 120
 121         static const size_t initialReadBufferCapacity = 32;
 122         static const size_t initialIdentifierTableCapacity = 64;
 123
 124         int yylineno;
 125         int yycolumn;
 126
 127         bool m_done;
 128         Vector<char> m_buffer8;
 129         Vector<UChar> m_buffer16;
 130         bool m_terminator;
 131         bool m_restrKeyword;
 132         bool m_delimited; // encountered delimiter like "'" and "}" on last run
 133         bool m_skipLF;
 134         bool m_skipCR;
 135         bool m_eatNextIdentifier;
 136         int m_stackToken;
 137         int m_lastToken;
 138
 139         State m_state;
 140         unsigned int m_position;
 141         const SourceCode* m_source;
 142         const UChar* m_code;
 143         unsigned int m_length;
 144         bool m_isReparsing;
 145         int m_atLineStart;
 146         bool m_error;
 147
 148         // current and following unicode characters (int to allow for -1 for end-of-file marker)
 149         int m_current;
 150         int m_next1;
 151         int m_next2;
 152         int m_next3;
 153
 154         int m_currentOffset;
 155         int m_nextOffset1;
 156         int m_nextOffset2;
 157         int m_nextOffset3;
 158
 159         SegmentedVector<JSC::Identifier, initialIdentifierTableCapacity> m_identifiers;
 160
 161         JSGlobalData* m_globalData;
 162
 163         UString m_pattern;
 164         UString m_flags;
 165
 166         const HashTable m_mainTable;
 167     };
 168
 169 } // namespace JSC
 170
 171 #endif // Lexer_h