| 1 | /*
|
|---|
| 2 | * This file is part of the KDE libraries
|
|---|
| 3 | * Copyright (C) 1999-2000 Harri Porten ([email protected])
|
|---|
| 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., 59 Temple Place - Suite 330,
|
|---|
| 18 | * Boston, MA 02111-1307, USA.
|
|---|
| 19 | */
|
|---|
| 20 |
|
|---|
| 21 | #ifndef _KJSLEXER_H_
|
|---|
| 22 | #define _KJSLEXER_H_
|
|---|
| 23 |
|
|---|
| 24 | #include "ustring.h"
|
|---|
| 25 |
|
|---|
| 26 | namespace KJS {
|
|---|
| 27 |
|
|---|
| 28 | class RegExp;
|
|---|
| 29 |
|
|---|
| 30 | class Lexer {
|
|---|
| 31 | public:
|
|---|
| 32 | Lexer();
|
|---|
| 33 | ~Lexer();
|
|---|
| 34 | static Lexer *curr();
|
|---|
| 35 |
|
|---|
| 36 | void setCode(const UChar *c, unsigned int len);
|
|---|
| 37 | int lex();
|
|---|
| 38 |
|
|---|
| 39 | int lineNo() const { return yylineno + 1; }
|
|---|
| 40 |
|
|---|
| 41 | bool prevTerminator() const { return terminator; }
|
|---|
| 42 |
|
|---|
| 43 | enum State { Start,
|
|---|
| 44 | Identifier,
|
|---|
| 45 | InIdentifier,
|
|---|
| 46 | InSingleLineComment,
|
|---|
| 47 | InMultiLineComment,
|
|---|
| 48 | InNum,
|
|---|
| 49 | InNum0,
|
|---|
| 50 | InHex,
|
|---|
| 51 | InOctal,
|
|---|
| 52 | InDecimal,
|
|---|
| 53 | InExponentIndicator,
|
|---|
| 54 | InExponent,
|
|---|
| 55 | Hex,
|
|---|
| 56 | Octal,
|
|---|
| 57 | Number,
|
|---|
| 58 | String,
|
|---|
| 59 | Eof,
|
|---|
| 60 | InString,
|
|---|
| 61 | InEscapeSequence,
|
|---|
| 62 | InHexEscape,
|
|---|
| 63 | InUnicodeEscape,
|
|---|
| 64 | Other,
|
|---|
| 65 | Bad };
|
|---|
| 66 |
|
|---|
| 67 | bool scanRegExp();
|
|---|
| 68 | UString pattern, flags;
|
|---|
| 69 |
|
|---|
| 70 | private:
|
|---|
| 71 | int yylineno;
|
|---|
| 72 | bool done;
|
|---|
| 73 | char *buffer8;
|
|---|
| 74 | UChar *buffer16;
|
|---|
| 75 | unsigned int size8, size16;
|
|---|
| 76 | unsigned int pos8, pos16;
|
|---|
| 77 | bool terminator;
|
|---|
| 78 | bool restrKeyword;
|
|---|
| 79 | // encountered delimiter like "'" and "}" on last run
|
|---|
| 80 | bool delimited;
|
|---|
| 81 | int stackToken;
|
|---|
| 82 |
|
|---|
| 83 | State state;
|
|---|
| 84 | void setDone(State s);
|
|---|
| 85 | unsigned int pos;
|
|---|
| 86 | void shift(unsigned int p);
|
|---|
| 87 | int lookupKeyword(const char *);
|
|---|
| 88 |
|
|---|
| 89 | bool isWhiteSpace() const;
|
|---|
| 90 | bool isLineTerminator() const;
|
|---|
| 91 | bool isHexDigit(unsigned short c) const;
|
|---|
| 92 | bool isOctalDigit(unsigned short c) const;
|
|---|
| 93 |
|
|---|
| 94 | int matchPunctuator(unsigned short c1, unsigned short c2,
|
|---|
| 95 | unsigned short c3, unsigned short c4);
|
|---|
| 96 | unsigned short singleEscape(unsigned short c) const;
|
|---|
| 97 | unsigned short convertOctal(unsigned short c1, unsigned short c2,
|
|---|
| 98 | unsigned short c3) const;
|
|---|
| 99 | public:
|
|---|
| 100 | static unsigned char convertHex(unsigned short c1);
|
|---|
| 101 | static unsigned char convertHex(unsigned short c1, unsigned short c2);
|
|---|
| 102 | static UChar convertUnicode(unsigned short c1, unsigned short c2,
|
|---|
| 103 | unsigned short c3, unsigned short c4);
|
|---|
| 104 | static bool isIdentLetter(unsigned short c);
|
|---|
| 105 | static bool isDecimalDigit(unsigned short c);
|
|---|
| 106 |
|
|---|
| 107 | private:
|
|---|
| 108 |
|
|---|
| 109 | void record8(unsigned short c);
|
|---|
| 110 | void record16(UChar c);
|
|---|
| 111 |
|
|---|
| 112 | const UChar *code;
|
|---|
| 113 | unsigned int length;
|
|---|
| 114 | int yycolumn;
|
|---|
| 115 | #ifndef KJS_PURE_ECMA
|
|---|
| 116 | int bol; // begin of line
|
|---|
| 117 | #endif
|
|---|
| 118 |
|
|---|
| 119 | // current and following unicode characters
|
|---|
| 120 | unsigned short current, next1, next2, next3;
|
|---|
| 121 |
|
|---|
| 122 | struct keyword {
|
|---|
| 123 | const char *name;
|
|---|
| 124 | int token;
|
|---|
| 125 | };
|
|---|
| 126 |
|
|---|
| 127 | // for future extensions
|
|---|
| 128 | class LexerPrivate;
|
|---|
| 129 | LexerPrivate *priv;
|
|---|
| 130 | };
|
|---|
| 131 |
|
|---|
| 132 | }; // namespace
|
|---|
| 133 |
|
|---|
| 134 | #endif
|
|---|
