Changeset 38632 in webkit for trunk/JavaScriptCore/parser

Timestamp:

Nov 20, 2008, 2:27:34 PM (17 years ago)

Author:

[email protected]

Message:

2008-11-20 Sam Weinig <​[email protected]>

Reviewed by Geoffrey Garen.

Speedup the lexer to offset coming re-parsing patch.

• .6% progression on Sunspider.

• bytecompiler/SegmentedVector.h: (JSC::SegmentedVector::shrink): Fixed bug where m_size would not be set when shrinking to 0.

• parser/Lexer.cpp: (JSC::Lexer::Lexer): (JSC::Lexer::isIdentStart): Use isASCIIAlpha and isASCII to avoid going into ICU in the common cases. (JSC::Lexer::isIdentPart): Use isASCIIAlphanumeric and isASCII to avoid going into ICU in the common cases (JSC::isDecimalDigit): Use version in ASCIICType.h. Inlining it was a regression. (JSC::Lexer::isHexDigit): Ditto. (JSC::Lexer::isOctalDigit): Ditto. (JSC::Lexer::clear): Resize the m_identifiers SegmentedVector to initial capacity
• parser/Lexer.h: Remove unused m_strings vector. Make m_identifiers a SegmentedVector<Identifier> to avoid allocating a new Identifier* for each identifier found. The SegmentedVector is need so we can passes references to the Identifier to the parser, which remain valid even when the vector is resized. (JSC::Lexer::makeIdentifier): Inline and return a reference to the added Identifier.

Location:

trunk/JavaScriptCore/parser

Files:

• Lexer.cpp (modified) (5 diffs)
• Lexer.h (modified) (3 diffs)

trunk/JavaScriptCore/parser/Lexer.cpp

@@ -58 +58 @@
 static bool isDecimalDigit(int);
 
-static const size_t initialReadBufferCapacity = 32;
-static const size_t initialStringTableCapacity = 64;
-
 Lexer::Lexer(JSGlobalData* globalData)
     : yylineno(1)
@@ -84 +81 @@
     m_buffer8.reserveCapacity(initialReadBufferCapacity);
     m_buffer16.reserveCapacity(initialReadBufferCapacity);
-    m_strings.reserveCapacity(initialStringTableCapacity);
-    m_identifiers.reserveCapacity(initialStringTableCapacity);
 }
 
@@ -609 +604 @@
 bool Lexer::isIdentStart(int c)
 {
-    return (category(c) & (Letter_Uppercase | Letter_Lowercase | Letter_Titlecase | Letter_Modifier | Letter_Other))
-        || c == '$' || c == '_';
+    return isASCIIAlpha(c) || c == '$' || c == '_' || (!isASCII(c) && (category(c) & (Letter_Uppercase | Letter_Lowercase | Letter_Titlecase | Letter_Modifier | Letter_Other)));
 }
 
 bool Lexer::isIdentPart(int c)
 {
-    return (category(c) & (Letter_Uppercase | Letter_Lowercase | Letter_Titlecase | Letter_Modifier | Letter_Other
-                            | Mark_NonSpacing | Mark_SpacingCombining | Number_DecimalDigit | Punctuation_Connector))
-        || c == '$' || c == '_';
+    return isASCIIAlphanumeric(c) || c == '$' || c == '_' || (!isASCII(c) && (category(c) & (Letter_Uppercase | Letter_Lowercase | Letter_Titlecase | Letter_Modifier | Letter_Other
+                            | Mark_NonSpacing | Mark_SpacingCombining | Number_DecimalDigit | Punctuation_Connector)));
 }
 
 static bool isDecimalDigit(int c)
 {
-    return (c >= '0' && c <= '9');
+    return isASCIIDigit(c);
 }
 
 bool Lexer::isHexDigit(int c)
 {
-    return (c >= '0' && c <= '9'
-        || c >= 'a' && c <= 'f'
-        || c >= 'A' && c <= 'F');
+    return isASCIIHexDigit(c); 
 }
 
 bool Lexer::isOctalDigit(int c)
 {
-    return (c >= '0' && c <= '7');
+    return isASCIIOctalDigit(c);
 }
 
@@ -889 +880 @@
 void Lexer::clear()
 {
-    deleteAllValues(m_strings);
-    Vector<UString*> newStrings;
-    newStrings.reserveCapacity(initialStringTableCapacity);
-    m_strings.swap(newStrings);
-
-    deleteAllValues(m_identifiers);
-    Vector<JSC::Identifier*> newIdentifiers;
-    newIdentifiers.reserveCapacity(initialStringTableCapacity);
-    m_identifiers.swap(newIdentifiers);
+    m_identifiers.resize(0);
 
     Vector<char> newBuffer8;
@@ -911 +894 @@
 }
 
-Identifier* Lexer::makeIdentifier(const Vector<UChar>& buffer)
-{
-    JSC::Identifier* identifier = new JSC::Identifier(m_globalData, buffer.data(), buffer.size());
-    m_identifiers.append(identifier);
-    return identifier;
-}
-
 } // namespace JSC

trunk/JavaScriptCore/parser/Lexer.h

@@ -24 +24 @@
 #define Lexer_h
 
+#include "Identifier.h"
 #include "Lookup.h"
-#include "UString.h"
+#include "SegmentedVector.h"
+#include "SourceCode.h"
 #include <wtf/Vector.h>
-#include "SourceCode.h"
 
 namespace JSC {
 
-    class Identifier;
     class RegExp;
 
@@ -113 +113 @@
         void record16(UChar);
 
-        JSC::Identifier* makeIdentifier(const Vector<UChar>& buffer);
+        JSC::Identifier* makeIdentifier(const Vector<UChar>& buffer)
+        {
+            m_identifiers.append(JSC::Identifier(m_globalData, buffer.data(), buffer.size()));
+            return &m_identifiers.last();
+        }
+
+        static const size_t initialReadBufferCapacity = 32;
+        static const size_t initialIdentifierTableCapacity = 64;
 
         int yylineno;
@@ -149 +156 @@
         int m_nextOffset3;
         
-        Vector<UString*> m_strings;
-        Vector<JSC::Identifier*> m_identifiers;
+        SegmentedVector<JSC::Identifier, initialIdentifierTableCapacity> m_identifiers;
 
         JSGlobalData* m_globalData;