runtime/LiteralParser.h

   1 /*
   2  * Copyright (C) 2009 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 LiteralParser_h
  27 #define LiteralParser_h
  28
  29 #include "Identifier.h"
  30 #include "JSGlobalObjectFunctions.h"
  31 #include "JSValue.h"
  32 #include "UString.h"
  33
  34 namespace JSC {
  35
  36 typedef enum { StrictJSON, NonStrictJSON, JSONP } ParserMode;
  37
  38 enum JSONPPathEntryType {
  39     JSONPPathEntryTypeDeclare, // var pathEntryName = JSON
  40     JSONPPathEntryTypeDot, // <prior entries>.pathEntryName = JSON
  41     JSONPPathEntryTypeLookup, // <prior entries>[pathIndex] = JSON
  42     JSONPPathEntryTypeCall // <prior entries>(JSON)
  43 };
  44
  45 enum ParserState { StartParseObject, StartParseArray, StartParseExpression,
  46                    StartParseStatement, StartParseStatementEndStatement,
  47                    DoParseObjectStartExpression, DoParseObjectEndExpression,
  48                    DoParseArrayStartExpression, DoParseArrayEndExpression };
  49 enum TokenType { TokLBracket, TokRBracket, TokLBrace, TokRBrace,
  50                  TokString, TokIdentifier, TokNumber, TokColon,
  51                  TokLParen, TokRParen, TokComma, TokTrue, TokFalse,
  52                  TokNull, TokEnd, TokDot, TokAssign, TokSemi, TokError };
  53
  54 struct JSONPPathEntry {
  55     JSONPPathEntryType m_type;
  56     Identifier m_pathEntryName;
  57     int m_pathIndex;
  58 };
  59
  60 struct JSONPData {
  61     Vector<JSONPPathEntry> m_path;
  62     Strong<Unknown> m_value;
  63 };
  64
  65 template <typename CharType>
  66 struct LiteralParserToken {
  67     TokenType type;
  68     const CharType* start;
  69     const CharType* end;
  70     UString stringBuffer;
  71     union {
  72         double numberToken;
  73         struct {
  74             union {
  75                 const LChar* stringToken8;
  76                 const UChar* stringToken16;
  77             };
  78             unsigned stringIs8Bit : 1;
  79             unsigned stringLength : 31;
  80         };
  81     };
  82 };
  83
  84 template <typename CharType>
  85 ALWAYS_INLINE void setParserTokenString(LiteralParserToken<CharType>&, const CharType* string);
  86
  87 template <typename CharType>
  88 class LiteralParser {
  89 public:
  90     LiteralParser(ExecState* exec, const CharType* characters, unsigned length, ParserMode mode)
  91         : m_exec(exec)
  92         , m_lexer(characters, length, mode)
  93         , m_mode(mode)
  94     {
  95     }
  96
  97     UString getErrorMessage()
  98     {
  99         if (!m_lexer.getErrorMessage().isEmpty())
 100             return String::format("JSON Parse error: %s", m_lexer.getErrorMessage().ascii().data()).impl();
 101         if (!m_parseErrorMessage.isEmpty())
 102             return String::format("JSON Parse error: %s", m_parseErrorMessage.ascii().data()).impl();
 103         return "JSON Parse error: Unable to parse JSON string";
 104     }
 105
 106     JSValue tryLiteralParse()
 107     {
 108         m_lexer.next();
 109         JSValue result = parse(m_mode == StrictJSON ? StartParseExpression : StartParseStatement);
 110         if (m_lexer.currentToken().type == TokSemi)
 111             m_lexer.next();
 112         if (m_lexer.currentToken().type != TokEnd)
 113             return JSValue();
 114         return result;
 115     }
 116
 117     bool tryJSONPParse(Vector<JSONPData>&, bool needsFullSourceInfo);
 118
 119 private:
 120     class Lexer {
 121     public:
 122         Lexer(const CharType* characters, unsigned length, ParserMode mode)
 123             : m_mode(mode)
 124             , m_ptr(characters)
 125             , m_end(characters + length)
 126         {
 127         }
 128
 129         TokenType next();
 130
 131         const LiteralParserToken<CharType>& currentToken()
 132         {
 133             return m_currentToken;
 134         }
 135
 136         UString getErrorMessage() { return m_lexErrorMessage; }
 137
 138     private:
 139         UString m_lexErrorMessage;
 140         template <ParserMode mode> TokenType lex(LiteralParserToken<CharType>&);
 141         ALWAYS_INLINE TokenType lexIdentifier(LiteralParserToken<CharType>&);
 142         template <ParserMode mode, char terminator> ALWAYS_INLINE TokenType lexString(LiteralParserToken<CharType>&);
 143         ALWAYS_INLINE TokenType lexNumber(LiteralParserToken<CharType>&);
 144         LiteralParserToken<CharType> m_currentToken;
 145         ParserMode m_mode;
 146         const CharType* m_ptr;
 147         const CharType* m_end;
 148     };
 149
 150     class StackGuard;
 151     JSValue parse(ParserState);
 152
 153     ExecState* m_exec;
 154     typename LiteralParser<CharType>::Lexer m_lexer;
 155     ParserMode m_mode;
 156     UString m_parseErrorMessage;
 157     static unsigned const MaximumCachableCharacter = 128;
 158     FixedArray<Identifier, MaximumCachableCharacter> m_shortIdentifiers;
 159     FixedArray<Identifier, MaximumCachableCharacter> m_recentIdentifiers;
 160     ALWAYS_INLINE const Identifier makeIdentifier(const LChar* characters, size_t length);
 161     ALWAYS_INLINE const Identifier makeIdentifier(const UChar* characters, size_t length);
 162     };
 163
 164 }
 165
 166 #endif