| 1 | // -*- c-basic-offset: 2 -*-
|
|---|
| 2 | /*
|
|---|
| 3 | * This file is part of the KDE libraries
|
|---|
| 4 | * Copyright (C) 1999-2000 Harri Porten ([email protected])
|
|---|
| 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 "lookup.h"
|
|---|
| 28 | #include "ustring.h"
|
|---|
| 29 | #include <wtf/Vector.h>
|
|---|
| 30 | #include "SourceRange.h"
|
|---|
| 31 |
|
|---|
| 32 | namespace KJS {
|
|---|
| 33 |
|
|---|
| 34 | class Identifier;
|
|---|
| 35 | class RegExp;
|
|---|
| 36 |
|
|---|
| 37 | class Lexer : Noncopyable {
|
|---|
| 38 | public:
|
|---|
| 39 | void setCode(int startingLineNumber, PassRefPtr<SourceProvider> source);
|
|---|
| 40 | int lex(void* lvalp, void* llocp);
|
|---|
| 41 |
|
|---|
| 42 | int lineNo() const { return yylineno; }
|
|---|
| 43 |
|
|---|
| 44 | bool prevTerminator() const { return terminator; }
|
|---|
| 45 |
|
|---|
| 46 | enum State { 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 | bool scanRegExp();
|
|---|
| 77 | const UString& pattern() const { return m_pattern; }
|
|---|
| 78 | const UString& flags() const { return m_flags; }
|
|---|
| 79 |
|
|---|
| 80 | static unsigned char convertHex(int);
|
|---|
| 81 | static unsigned char convertHex(int c1, int c2);
|
|---|
| 82 | static UChar convertUnicode(int c1, int c2, int c3, int c4);
|
|---|
| 83 | static bool isIdentStart(int);
|
|---|
| 84 | static bool isIdentPart(int);
|
|---|
| 85 | static bool isHexDigit(int);
|
|---|
| 86 |
|
|---|
| 87 | bool sawError() const { return error; }
|
|---|
| 88 |
|
|---|
| 89 | void clear();
|
|---|
| 90 | SourceRange sourceRange(int openBrace, int closeBrace) { return SourceRange(m_source, openBrace + 1, closeBrace); }
|
|---|
| 91 |
|
|---|
| 92 | private:
|
|---|
| 93 | friend struct JSGlobalData;
|
|---|
| 94 | Lexer(JSGlobalData*);
|
|---|
| 95 | ~Lexer();
|
|---|
| 96 |
|
|---|
| 97 | int yylineno;
|
|---|
| 98 | bool done;
|
|---|
| 99 | Vector<char> m_buffer8;
|
|---|
| 100 | Vector<UChar> m_buffer16;
|
|---|
| 101 | bool terminator;
|
|---|
| 102 | bool restrKeyword;
|
|---|
| 103 | // encountered delimiter like "'" and "}" on last run
|
|---|
| 104 | bool delimited;
|
|---|
| 105 | bool skipLF;
|
|---|
| 106 | bool skipCR;
|
|---|
| 107 | bool eatNextIdentifier;
|
|---|
| 108 | int stackToken;
|
|---|
| 109 | int lastToken;
|
|---|
| 110 |
|
|---|
| 111 | State state;
|
|---|
| 112 | void setDone(State);
|
|---|
| 113 | unsigned int pos;
|
|---|
| 114 | void shift(unsigned int p);
|
|---|
| 115 | void nextLine();
|
|---|
| 116 | int lookupKeyword(const char *);
|
|---|
| 117 |
|
|---|
| 118 | bool isWhiteSpace() const;
|
|---|
| 119 | bool isLineTerminator();
|
|---|
| 120 | static bool isOctalDigit(int);
|
|---|
| 121 |
|
|---|
| 122 | int matchPunctuator(int& charPos, int c1, int c2, int c3, int c4);
|
|---|
| 123 | static unsigned short singleEscape(unsigned short);
|
|---|
| 124 | static unsigned short convertOctal(int c1, int c2, int c3);
|
|---|
| 125 |
|
|---|
| 126 | void record8(int);
|
|---|
| 127 | void record16(int);
|
|---|
| 128 | void record16(UChar);
|
|---|
| 129 |
|
|---|
| 130 | KJS::Identifier* makeIdentifier(const Vector<UChar>& buffer);
|
|---|
| 131 | UString* makeUString(const Vector<UChar>& buffer);
|
|---|
| 132 |
|
|---|
| 133 | RefPtr<SourceProvider> m_source;
|
|---|
| 134 | const UChar* code;
|
|---|
| 135 | unsigned int length;
|
|---|
| 136 | int yycolumn;
|
|---|
| 137 | int atLineStart;
|
|---|
| 138 | bool error;
|
|---|
| 139 |
|
|---|
| 140 | // current and following unicode characters (int to allow for -1 for end-of-file marker)
|
|---|
| 141 | int current, next1, next2, next3;
|
|---|
| 142 |
|
|---|
| 143 | Vector<UString*> m_strings;
|
|---|
| 144 | Vector<KJS::Identifier*> m_identifiers;
|
|---|
| 145 |
|
|---|
| 146 | JSGlobalData* m_globalData;
|
|---|
| 147 |
|
|---|
| 148 | UString m_pattern;
|
|---|
| 149 | UString m_flags;
|
|---|
| 150 |
|
|---|
| 151 | const HashTable mainTable;
|
|---|
| 152 | };
|
|---|
| 153 |
|
|---|
| 154 | } // namespace KJS
|
|---|
| 155 |
|
|---|
| 156 | #endif // Lexer_h
|
|---|
