Changeset 114844 in webkit for trunk/Source/JavaScriptCore/parser/Lexer.cpp

Timestamp:

Apr 21, 2012, 12:46:02 PM (13 years ago)

Author:

Darin Adler

Message:

Change JavaScript lexer to use 0 instead of -1 for sentinel, eliminating the need to put characters into ints
​https://bugs.webkit.org/show_bug.cgi?id=84523

Reviewed by Oliver Hunt.

Separate preparation step of copyright dates, renaming, and other small tweaks.

• parser/Lexer.cpp:

(JSC::Lexer::invalidCharacterMessage): Removed "get" from name to match WebKit naming conventions.
(JSC::Lexer::peek): Removed meaningless comment.
(JSC::Lexer::parseFourDigitUnicodeHex): Renamed from getUnicodeCharacter to be more precise about
what this function does.
(JSC::Lexer::shiftLineTerminator): Renamed local variable that had a data-member-style name.
(JSC::Lexer::parseStringSlowCase): Updated for new name of parseFourDigitUnicodeHex.
(JSC::Lexer::lex): Updated for new name of invalidCharacterMessage.

• parser/Lexer.h: Removed an unneeded forward declaration of the RegExp class.

Renamed getInvalidCharMessage to invalidCharacterMessage and made it const. Renamed
getUnicodeCharacter to parseFourDigitUnicodeHex.

File:

• trunk/Source/JavaScriptCore/parser/Lexer.cpp (modified) (10 diffs)

trunk/Source/JavaScriptCore/parser/Lexer.cpp

@@ -1 +1 @@
 /*
  *  Copyright (C) 1999-2000 Harri Porten ([email protected])
- *  Copyright (C) 2006, 2007, 2008, 2009 Apple Inc. All Rights Reserved.
+ *  Copyright (C) 2006, 2007, 2008, 2009, 2011, 2012 Apple Inc. All Rights Reserved.
  *  Copyright (C) 2007 Cameron Zwarich ([email protected])
  *  Copyright (C) 2010 Zoltan Herczeg ([email protected])
@@ -369 +369 @@
 
 template <typename T>
-UString Lexer<T>::getInvalidCharMessage()
+UString Lexer<T>::invalidCharacterMessage() const
 {
     switch (m_current) {
@@ -451 +451 @@
 ALWAYS_INLINE int Lexer<T>::peek(int offset)
 {
-    // Only use if necessary
     ASSERT(offset > 0 && offset < 5);
     const T* code = m_code + offset;
@@ -458 +457 @@
 
 template <typename T>
-int Lexer<T>::getUnicodeCharacter()
+int Lexer<T>::parseFourDigitUnicodeHex()
 {
     int char1 = peek(1);
@@ -480 +479 @@
     ASSERT(isLineTerminator(static_cast<T>(m_current)));
 
-    int m_prev = m_current;
+    int prev = m_current;
     shift();
 
     // Allow both CRLF and LFCR.
-    if (m_prev + m_current == '\n' + '\r')
+    if (prev + m_current == '\n' + '\r')
         shift();
 
@@ -634 +633 @@
 
 template <>
-    template <bool shouldCreateIdentifier> ALWAYS_INLINE JSTokenType Lexer<LChar>::parseIdentifier(JSTokenData* tokenData, unsigned lexerFlags, bool strictMode)
+template <bool shouldCreateIdentifier> ALWAYS_INLINE JSTokenType Lexer<LChar>::parseIdentifier(JSTokenData* tokenData, unsigned lexerFlags, bool strictMode)
 {
     const ptrdiff_t remaining = m_codeEnd - m_code;
@@ -692 +691 @@
         }
     }
+
     const UChar* identifierStart = currentCharacter();
 
@@ -763 +763 @@
             return ERRORTOK;
         shift();
-        int character = getUnicodeCharacter();
+        int character = parseFourDigitUnicodeHex();
         if (UNLIKELY(character == -1))
             return ERRORTOK;
@@ -911 +911 @@
             } else if (m_current == 'u') {
                 shift();
-                int character = getUnicodeCharacter();
+                int character = parseFourDigitUnicodeHex();
                 if (character != -1) {
                     if (shouldBuildStrings)
@@ -1509 +1509 @@
         goto start;
     case CharacterInvalid:
-        m_lexErrorMessage = getInvalidCharMessage();
+        m_lexErrorMessage = invalidCharacterMessage();
         goto returnError;
     default: