kjs/lexer.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  *  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 Library 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  *  Library General Public License for more details.
  16  *
  17  *  You should have received a copy of the GNU Library General Public License
  18  *  along with this library; see the file COPYING.LIB.  If not, write to
  19  *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  20  *  Boston, MA 02110-1301, USA.
  21  *
  22  */
  23
  24 #ifndef Lexer_h
  25 #define Lexer_h
  26
  27 #include "SourceCode.h"
  28 #include "ustring.h"
  29 #include <wtf/Vector.h>
  30
  31 namespace KJS {
  32
  33   class Identifier;
  34   class RegExp;
  35
  36   class Lexer : Noncopyable {
  37   public:
  38     void setCode(const SourceCode&);
  39     int lex();
  40
  41     int lineNo() const { return yylineno; }
  42
  43     bool prevTerminator() const { return terminator; }
  44
  45     enum State { Start,
  46                  IdentifierOrKeyword,
  47                  Identifier,
  48                  InIdentifierOrKeyword,
  49                  InIdentifier,
  50                  InIdentifierStartUnicodeEscapeStart,
  51                  InIdentifierStartUnicodeEscape,
  52                  InIdentifierPartUnicodeEscapeStart,
  53                  InIdentifierPartUnicodeEscape,
  54                  InSingleLineComment,
  55                  InMultiLineComment,
  56                  InNum,
  57                  InNum0,
  58                  InHex,
  59                  InOctal,
  60                  InDecimal,
  61                  InExponentIndicator,
  62                  InExponent,
  63                  Hex,
  64                  Octal,
  65                  Number,
  66                  String,
  67                  Eof,
  68                  InString,
  69                  InEscapeSequence,
  70                  InHexEscape,
  71                  InUnicodeEscape,
  72                  Other,
  73                  Bad };
  74
  75     bool scanRegExp();
  76     const UString& pattern() const { return m_pattern; }
  77     const UString& flags() const { return m_flags; }
  78
  79     static unsigned char convertHex(int);
  80     static unsigned char convertHex(int c1, int c2);
  81     static UChar convertUnicode(int c1, int c2, int c3, int c4);
  82     static bool isIdentStart(int);
  83     static bool isIdentPart(int);
  84     static bool isHexDigit(int);
  85
  86     bool sawError() const { return error; }
  87
  88     void clear();
  89     SourceCode sourceCode(int openBrace, int closeBrace, int firstLine)
  90     {
  91         // The SourceCode constructor adds 1 to the line number to account for
  92         // all of the callers in WebCore that use zero-based line numbers, so
  93         // we regrettably subtract 1 here to deal with that.
  94         return SourceCode(m_source->provider(), m_source->startOffset() + openBrace + 1, m_source->startOffset() + closeBrace, firstLine - 1);
  95     }
  96
  97   private:
  98     friend Lexer& lexer();
  99     Lexer();
 100
 101     int yylineno;
 102     bool done;
 103     Vector<char> m_buffer8;
 104     Vector<UChar> m_buffer16;
 105     bool terminator;
 106     bool restrKeyword;
 107     // encountered delimiter like "'" and "}" on last run
 108     bool delimited;
 109     bool skipLF;
 110     bool skipCR;
 111     bool eatNextIdentifier;
 112     int stackToken;
 113     int lastToken;
 114
 115     State state;
 116     void setDone(State);
 117     unsigned int pos;
 118     void shift(unsigned int p);
 119     void nextLine();
 120     int lookupKeyword(const char *);
 121
 122     bool isWhiteSpace() const;
 123     bool isLineTerminator();
 124     static bool isOctalDigit(int);
 125
 126     int matchPunctuator(int& charPos, int c1, int c2, int c3, int c4);
 127     static unsigned short singleEscape(unsigned short);
 128     static unsigned short convertOctal(int c1, int c2, int c3);
 129
 130     void record8(int);
 131     void record16(int);
 132     void record16(UChar);
 133
 134     KJS::Identifier* makeIdentifier(const Vector<UChar>& buffer);
 135     UString* makeUString(const Vector<UChar>& buffer);
 136
 137     const SourceCode* m_source;
 138     const UChar* code;
 139     unsigned int length;
 140     int yycolumn;
 141     int atLineStart;
 142     bool error;
 143
 144     // current and following unicode characters (int to allow for -1 for end-of-file marker)
 145     int current, next1, next2, next3;
 146
 147     int m_currentOffset;
 148     int m_nextOffset1;
 149     int m_nextOffset2;
 150     int m_nextOffset3;
 151
 152     Vector<UString*> m_strings;
 153     Vector<KJS::Identifier*> m_identifiers;
 154
 155     UString m_pattern;
 156     UString m_flags;
 157   };
 158
 159   Lexer& lexer(); // Returns the singletone JavaScript lexer.
 160
 161 } // namespace KJS
 162
 163 #endif // Lexer_h