summaryrefslogtreecommitdiff
path: root/Source/JavaScriptCore/parser/Lexer.h
diff options
context:
space:
mode:
authorLorry Tar Creator <lorry-tar-importer@lorry>2016-04-10 09:28:39 +0000
committerLorry Tar Creator <lorry-tar-importer@lorry>2016-04-10 09:28:39 +0000
commit32761a6cee1d0dee366b885b7b9c777e67885688 (patch)
treed6bec92bebfb216f4126356e55518842c2f476a1 /Source/JavaScriptCore/parser/Lexer.h
parenta4e969f4965059196ca948db781e52f7cfebf19e (diff)
downloadWebKitGtk-tarball-32761a6cee1d0dee366b885b7b9c777e67885688.tar.gz
webkitgtk-2.4.11webkitgtk-2.4.11
Diffstat (limited to 'Source/JavaScriptCore/parser/Lexer.h')
-rw-r--r--Source/JavaScriptCore/parser/Lexer.h147
1 files changed, 72 insertions, 75 deletions
diff --git a/Source/JavaScriptCore/parser/Lexer.h b/Source/JavaScriptCore/parser/Lexer.h
index c7b63b2a6..28c61ba19 100644
--- a/Source/JavaScriptCore/parser/Lexer.h
+++ b/Source/JavaScriptCore/parser/Lexer.h
@@ -30,26 +30,49 @@
#include <wtf/ASCIICType.h>
#include <wtf/SegmentedVector.h>
#include <wtf/Vector.h>
+#include <wtf/unicode/Unicode.h>
namespace JSC {
+class Keywords {
+public:
+ bool isKeyword(const Identifier& ident) const
+ {
+ return m_keywordTable.entry(m_vm, ident);
+ }
+
+ const HashEntry* getKeyword(const Identifier& ident) const
+ {
+ return m_keywordTable.entry(m_vm, ident);
+ }
+
+ ~Keywords()
+ {
+ m_keywordTable.deleteTable();
+ }
+
+private:
+ friend class VM;
+
+ explicit Keywords(VM&);
+
+ VM& m_vm;
+ const HashTable m_keywordTable;
+};
+
enum LexerFlags {
LexerFlagsIgnoreReservedWords = 1,
LexerFlagsDontBuildStrings = 2,
LexexFlagsDontBuildKeywords = 4
};
-struct ParsedUnicodeEscapeValue;
-
-bool isLexerKeyword(const Identifier&);
-
template <typename T>
class Lexer {
WTF_MAKE_NONCOPYABLE(Lexer);
WTF_MAKE_FAST_ALLOCATED;
public:
- Lexer(VM*, JSParserBuiltinMode);
+ Lexer(VM*);
~Lexer();
// Character manipulation functions.
@@ -60,10 +83,9 @@ public:
// Functions to set up parsing.
void setCode(const SourceCode&, ParserArena*);
- void setIsReparsingFunction() { m_isReparsingFunction = true; }
- bool isReparsingFunction() const { return m_isReparsingFunction; }
+ void setIsReparsing() { m_isReparsing = true; }
+ bool isReparsing() const { return m_isReparsing; }
- void setTokenPosition(JSToken* tokenRecord);
JSTokenType lex(JSToken*, unsigned, bool strictMode);
bool nextTokenIsColon();
int lineNumber() const { return m_lineNumber; }
@@ -74,20 +96,15 @@ public:
return JSTextPosition(m_lineNumber, currentOffset(), currentLineStartOffset());
}
JSTextPosition positionBeforeLastNewline() const { return m_positionBeforeLastNewline; }
- JSTokenLocation lastTokenLocation() const { return m_lastTockenLocation; }
void setLastLineNumber(int lastLineNumber) { m_lastLineNumber = lastLineNumber; }
int lastLineNumber() const { return m_lastLineNumber; }
bool prevTerminator() const { return m_terminator; }
bool scanRegExp(const Identifier*& pattern, const Identifier*& flags, UChar patternPrefix = 0);
- enum class RawStringsBuildMode { BuildRawStrings, DontBuildRawStrings };
- JSTokenType scanTrailingTemplateString(JSToken*, RawStringsBuildMode);
bool skipRegExp();
// Functions for use after parsing.
bool sawError() const { return m_error; }
String getErrorMessage() const { return m_lexErrorMessage; }
- String sourceURL() const { return m_sourceURLDirective; }
- String sourceMappingURL() const { return m_sourceMappingURLDirective; }
void clear();
void setOffset(int offset, int lineStartOffset)
{
@@ -109,10 +126,8 @@ public:
{
m_lineNumber = line;
}
- void setTerminator(bool terminator)
- {
- m_terminator = terminator;
- }
+
+ SourceProvider* sourceProvider() const { return m_source->provider(); }
JSTokenType lexExpectIdentifier(JSToken*, unsigned, bool strictMode);
@@ -121,15 +136,42 @@ private:
void append8(const T*, size_t);
void record16(int);
void record16(T);
- void recordUnicodeCodePoint(UChar32);
void append16(const LChar*, size_t);
void append16(const UChar* characters, size_t length) { m_buffer16.append(characters, length); }
ALWAYS_INLINE void shift();
ALWAYS_INLINE bool atEnd() const;
ALWAYS_INLINE T peek(int offset) const;
-
- ParsedUnicodeEscapeValue parseUnicodeEscape();
+ struct UnicodeHexValue {
+
+ enum ValueType { ValidHex, IncompleteHex, InvalidHex };
+
+ explicit UnicodeHexValue(int value)
+ : m_value(value)
+ {
+ }
+ explicit UnicodeHexValue(ValueType type)
+ : m_value(type == IncompleteHex ? -2 : -1)
+ {
+ }
+
+ ValueType valueType() const
+ {
+ if (m_value >= 0)
+ return ValidHex;
+ return m_value == -2 ? IncompleteHex : InvalidHex;
+ }
+ bool isValid() const { return m_value >= 0; }
+ int value() const
+ {
+ ASSERT(m_value >= 0);
+ return m_value;
+ }
+
+ private:
+ int m_value;
+ };
+ UnicodeHexValue parseFourDigitUnicodeHex();
void shiftLineTerminator();
ALWAYS_INLINE int offsetFromSourcePtr(const T* ptr) const { return ptr - m_codeStart; }
@@ -139,7 +181,7 @@ private:
ALWAYS_INLINE const T* currentSourcePtr() const;
ALWAYS_INLINE void setOffsetFromSourcePtr(const T* sourcePtr, unsigned lineStartOffset) { setOffset(offsetFromSourcePtr(sourcePtr), lineStartOffset); }
- ALWAYS_INLINE void setCodeStart(const StringView&);
+ ALWAYS_INLINE void setCodeStart(const StringImpl*);
ALWAYS_INLINE const Identifier* makeIdentifier(const LChar* characters, size_t length);
ALWAYS_INLINE const Identifier* makeIdentifier(const UChar* characters, size_t length);
@@ -147,11 +189,8 @@ private:
ALWAYS_INLINE const Identifier* makeLCharIdentifier(const UChar* characters, size_t length);
ALWAYS_INLINE const Identifier* makeRightSizedIdentifier(const UChar* characters, size_t length, UChar orAllChars);
ALWAYS_INLINE const Identifier* makeIdentifierLCharFromUChar(const UChar* characters, size_t length);
- ALWAYS_INLINE const Identifier* makeEmptyIdentifier();
ALWAYS_INLINE bool lastTokenWasRestrKeyword() const;
-
- ALWAYS_INLINE void skipWhitespace();
template <int shiftAmount> void internalShift();
template <bool shouldCreateIdentifier> ALWAYS_INLINE JSTokenType parseKeyword(JSTokenData*);
@@ -164,24 +203,13 @@ private:
};
template <bool shouldBuildStrings> ALWAYS_INLINE StringParseResult parseString(JSTokenData*, bool strictMode);
template <bool shouldBuildStrings> NEVER_INLINE StringParseResult parseStringSlowCase(JSTokenData*, bool strictMode);
-
- enum class EscapeParseMode { Template, String };
- template <bool shouldBuildStrings> ALWAYS_INLINE StringParseResult parseComplexEscape(EscapeParseMode, bool strictMode, T stringQuoteCharacter);
- template <bool shouldBuildStrings> ALWAYS_INLINE StringParseResult parseTemplateLiteral(JSTokenData*, RawStringsBuildMode);
ALWAYS_INLINE void parseHex(double& returnValue);
- ALWAYS_INLINE bool parseBinary(double& returnValue);
ALWAYS_INLINE bool parseOctal(double& returnValue);
ALWAYS_INLINE bool parseDecimal(double& returnValue);
ALWAYS_INLINE void parseNumberAfterDecimalPoint();
ALWAYS_INLINE bool parseNumberAfterExponentIndicator();
ALWAYS_INLINE bool parseMultilineComment();
- ALWAYS_INLINE void parseCommentDirective();
- ALWAYS_INLINE String parseCommentDirectiveValue();
-
- template <unsigned length>
- ALWAYS_INLINE bool consume(const char (&input)[length]);
-
static const size_t initialReadBufferCapacity = 32;
int m_lineNumber;
@@ -189,7 +217,6 @@ private:
Vector<LChar> m_buffer8;
Vector<UChar> m_buffer16;
- Vector<UChar> m_bufferForRawTemplateString16;
bool m_terminator;
int m_lastToken;
@@ -201,21 +228,16 @@ private:
const T* m_codeStartPlusOffset;
const T* m_lineStart;
JSTextPosition m_positionBeforeLastNewline;
- JSTokenLocation m_lastTockenLocation;
- bool m_isReparsingFunction;
+ bool m_isReparsing;
bool m_atLineStart;
bool m_error;
String m_lexErrorMessage;
- String m_sourceURLDirective;
- String m_sourceMappingURLDirective;
-
T m_current;
IdentifierArena* m_arena;
VM* m_vm;
- bool m_parsingBuiltinFunction;
};
template <>
@@ -227,8 +249,7 @@ ALWAYS_INLINE bool Lexer<LChar>::isWhiteSpace(LChar ch)
template <>
ALWAYS_INLINE bool Lexer<UChar>::isWhiteSpace(UChar ch)
{
- // 0x180E used to be in Zs category before Unicode 6.3, and EcmaScript says that we should keep treating it as such.
- return (ch < 256) ? Lexer<LChar>::isWhiteSpace(static_cast<LChar>(ch)) : (u_charType(ch) == U_SPACE_SEPARATOR || ch == 0x180E || ch == 0xFEFF);
+ return (ch < 256) ? Lexer<LChar>::isWhiteSpace(static_cast<LChar>(ch)) : (u_charType(ch) == U_SPACE_SEPARATOR || ch == 0xFEFF);
}
template <>
@@ -282,24 +303,18 @@ ALWAYS_INLINE const Identifier* Lexer<UChar>::makeRightSizedIdentifier(const UCh
return &m_arena->makeIdentifier(m_vm, characters, length);
}
-template <typename T>
-ALWAYS_INLINE const Identifier* Lexer<T>::makeEmptyIdentifier()
-{
- return &m_arena->makeEmptyIdentifier(m_vm);
-}
-
template <>
-ALWAYS_INLINE void Lexer<LChar>::setCodeStart(const StringView& sourceString)
+ALWAYS_INLINE void Lexer<LChar>::setCodeStart(const StringImpl* sourceString)
{
- ASSERT(sourceString.is8Bit());
- m_codeStart = sourceString.characters8();
+ ASSERT(sourceString->is8Bit());
+ m_codeStart = sourceString->characters8();
}
template <>
-ALWAYS_INLINE void Lexer<UChar>::setCodeStart(const StringView& sourceString)
+ALWAYS_INLINE void Lexer<UChar>::setCodeStart(const StringImpl* sourceString)
{
- ASSERT(!sourceString.is8Bit());
- m_codeStart = sourceString.characters16();
+ ASSERT(!sourceString->is8Bit());
+ m_codeStart = sourceString->characters16();
}
template <typename T>
@@ -320,12 +335,6 @@ ALWAYS_INLINE const Identifier* Lexer<T>::makeLCharIdentifier(const UChar* chara
return &m_arena->makeIdentifierLCharFromUChar(m_vm, characters, length);
}
-#if ASSERT_DISABLED
-ALWAYS_INLINE bool isSafeBuiltinIdentifier(VM&, const Identifier*) { return true; }
-#else
-bool isSafeBuiltinIdentifier(VM&, const Identifier*);
-#endif
-
template <typename T>
ALWAYS_INLINE JSTokenType Lexer<T>::lexExpectIdentifier(JSToken* tokenRecord, unsigned lexerFlags, bool strictMode)
{
@@ -361,15 +370,10 @@ ALWAYS_INLINE JSTokenType Lexer<T>::lexExpectIdentifier(JSToken* tokenRecord, un
ASSERT(currentOffset() >= currentLineStartOffset());
// Create the identifier if needed
- if (lexerFlags & LexexFlagsDontBuildKeywords
-#if !ASSERT_DISABLED
- && !m_parsingBuiltinFunction
-#endif
- )
+ if (lexerFlags & LexexFlagsDontBuildKeywords)
tokenData->ident = 0;
else
tokenData->ident = makeLCharIdentifier(start, ptr - start);
-
tokenLocation->line = m_lineNumber;
tokenLocation->lineStartOffset = currentLineStartOffset();
tokenLocation->startOffset = offsetFromSourcePtr(start);
@@ -377,13 +381,6 @@ ALWAYS_INLINE JSTokenType Lexer<T>::lexExpectIdentifier(JSToken* tokenRecord, un
ASSERT(tokenLocation->startOffset >= tokenLocation->lineStartOffset);
tokenRecord->m_startPosition = startPosition;
tokenRecord->m_endPosition = currentPosition();
-#if !ASSERT_DISABLED
- if (m_parsingBuiltinFunction) {
- if (!isSafeBuiltinIdentifier(*m_vm, tokenData->ident))
- return ERRORTOK;
- }
-#endif
-
m_lastToken = IDENT;
return IDENT;