Cleanup of ScannerConstants, now named UnicodeCache.

src/scanner-base.cc

-// Copyright 2010 the V8 project authors. All rights reserved.
+// Copyright 2011 the V8 project authors. All rights reserved.
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are
 // met:
 //
 //     * Redistributions of source code must retain the above copyright
 //       notice, this list of conditions and the following disclaimer.
 //     * Redistributions in binary form must reproduce the above
 //       copyright notice, this list of conditions and the following
 //       disclaimer in the documentation and/or other materials provided
 //       with the distribution.
@@ skipping 16 matching lines @@
 // Features shared by parsing and pre-parsing scanners.
 
 #include "../include/v8stdint.h"
 #include "scanner-base.h"
 #include "char-predicates-inl.h"
 
 namespace v8 {
 namespace internal {
 
 // ----------------------------------------------------------------------------
-// Compound predicates.
-
-bool ScannerConstants::IsIdentifier(unibrow::CharacterStream* buffer) {
-  // Checks whether the buffer contains an identifier (no escape).
-  if (!buffer->has_more()) return false;
-  if (!kIsIdentifierStart.get(buffer->GetNext())) {
-    return false;
-  }
-  while (buffer->has_more()) {
-    if (!kIsIdentifierPart.get(buffer->GetNext())) {
-      return false;
-    }
-  }
-  return true;
-}
-
-// ----------------------------------------------------------------------------
 // Scanner
 
-Scanner::Scanner(ScannerConstants* scanner_constants)
-    : scanner_constants_(scanner_constants),
+Scanner::Scanner(UnicodeCache* unicode_cache)
+    : unicode_cache_(unicode_cache),
       octal_pos_(kNoOctalLocation) {

[Karl Klose, 2011/04/12 07:55:40]

I think this newline should be removed.

[Lasse Reichstein, 2011/04/12 08:18:47]

Done.

 }
 
 
 uc32 Scanner::ScanHexEscape(uc32 c, int length) {
   ASSERT(length <= 4);  // prevent overflow
 
   uc32 digits[4];
   uc32 x = 0;
   for (int i = 0; i < length; i++) {
     digits[i] = c0_;
@@ skipping 37 matching lines @@
   if (c != '0' || i > 0) {
     octal_pos_ = source_pos() - i - 1;     // Already advanced
   }
   return x;
 }
 
 
 // ----------------------------------------------------------------------------
 // JavaScriptScanner
 
-JavaScriptScanner::JavaScriptScanner(ScannerConstants* scanner_contants)
+JavaScriptScanner::JavaScriptScanner(UnicodeCache* scanner_contants)
     : Scanner(scanner_contants) { }
 
 
 Token::Value JavaScriptScanner::Next() {
   current_ = next_;
   has_line_terminator_before_next_ = false;
   Scan();
   return current_.token;
 }
 
 
 static inline bool IsByteOrderMark(uc32 c) {
   // The Unicode value U+FFFE is guaranteed never to be assigned as a
   // Unicode character; this implies that in a Unicode context the
   // 0xFF, 0xFE byte pattern can only be interpreted as the U+FEFF
   // character expressed in little-endian byte order (since it could
   // not be a U+FFFE character expressed in big-endian byte
   // order). Nevertheless, we check for it to be compatible with
   // Spidermonkey.
   return c == 0xFEFF || c == 0xFFFE;
 }
 
 
 bool JavaScriptScanner::SkipWhiteSpace() {
   int start_position = source_pos();
 
   while (true) {
     // We treat byte-order marks (BOMs) as whitespace for better
     // compatibility with Spidermonkey and other JavaScript engines.
-    while (scanner_constants_->IsWhiteSpace(c0_) || IsByteOrderMark(c0_)) {
+    while (unicode_cache_->IsWhiteSpace(c0_) || IsByteOrderMark(c0_)) {
       // IsWhiteSpace() includes line terminators!
-      if (scanner_constants_->IsLineTerminator(c0_)) {
+      if (unicode_cache_->IsLineTerminator(c0_)) {
         // Ignore line terminators, but remember them. This is necessary
         // for automatic semicolon insertion.
         has_line_terminator_before_next_ = true;
       }
       Advance();
     }
 
     // If there is an HTML comment end '-->' at the beginning of a
     // line (with only whitespace in front of it), we treat the rest
     // of the line as a comment. This is in line with the way
@@ skipping 19 matching lines @@
 
 
 Token::Value JavaScriptScanner::SkipSingleLineComment() {
   Advance();
 
   // The line terminator at the end of the line is not considered
   // to be part of the single-line comment; it is recognized
   // separately by the lexical grammar and becomes part of the
   // stream of input elements for the syntactic grammar (see
   // ECMA-262, section 7.4, page 12).
-  while (c0_ >= 0 && !scanner_constants_->IsLineTerminator(c0_)) {
+  while (c0_ >= 0 && !unicode_cache_->IsLineTerminator(c0_)) {
     Advance();
   }
 
   return Token::WHITESPACE;
 }
 
 
 Token::Value JavaScriptScanner::SkipMultiLineComment() {
   ASSERT(c0_ == '*');
   Advance();
@@ skipping 244 matching lines @@
 
       case '?':
         token = Select(Token::CONDITIONAL);
         break;
 
       case '~':
         token = Select(Token::BIT_NOT);
         break;
 
       default:
-        if (scanner_constants_->IsIdentifierStart(c0_)) {
+        if (unicode_cache_->IsIdentifierStart(c0_)) {
           token = ScanIdentifierOrKeyword();
         } else if (IsDecimalDigit(c0_)) {
           token = ScanNumber(false);
         } else if (SkipWhiteSpace()) {
           token = Token::WHITESPACE;
         } else if (c0_ < 0) {
           token = Token::EOS;
         } else {
           token = Select(Token::ILLEGAL);
         }
@@ skipping 27 matching lines @@
   }
   Scan();
 }
 
 
 void JavaScriptScanner::ScanEscape() {
   uc32 c = c0_;
   Advance();
 
   // Skip escaped newlines.
-  if (scanner_constants_->IsLineTerminator(c)) {
+  if (unicode_cache_->IsLineTerminator(c)) {
     // Allow CR+LF newlines in multiline string literals.
     if (IsCarriageReturn(c) && IsLineFeed(c0_)) Advance();
     // Allow LF+CR newlines in multiline string literals.
     if (IsLineFeed(c) && IsCarriageReturn(c0_)) Advance();
     return;
   }
 
   switch (c) {
     case '\'':  // fall through
     case '"' :  // fall through
@@ skipping 22 matching lines @@
   AddLiteralChar(c);
 }
 
 
 Token::Value JavaScriptScanner::ScanString() {
   uc32 quote = c0_;
   Advance();  // consume quote
 
   LiteralScope literal(this);
   while (c0_ != quote && c0_ >= 0
-         && !scanner_constants_->IsLineTerminator(c0_)) {
+         && !unicode_cache_->IsLineTerminator(c0_)) {
     uc32 c = c0_;
     Advance();
     if (c == '\\') {
       if (c0_ < 0) return Token::ILLEGAL;
       ScanEscape();
     } else {
       AddLiteralChar(c);
     }
   }
   if (c0_ != quote) return Token::ILLEGAL;
@@ skipping 78 matching lines @@
       // we must have at least one decimal digit after 'e'/'E'
       return Token::ILLEGAL;
     }
     ScanDecimalDigits();
   }
 
   // The source character immediately following a numeric literal must
   // not be an identifier start or a decimal digit; see ECMA-262
   // section 7.8.3, page 17 (note that we read only one decimal digit
   // if the value is 0).
-  if (IsDecimalDigit(c0_) || scanner_constants_->IsIdentifierStart(c0_))
+  if (IsDecimalDigit(c0_) || unicode_cache_->IsIdentifierStart(c0_))
     return Token::ILLEGAL;
 
   literal.Complete();
 
   return Token::NUMBER;
 }
 
 
 uc32 JavaScriptScanner::ScanIdentifierUnicodeEscape() {
   Advance();
   if (c0_ != 'u') return unibrow::Utf8::kBadChar;
   Advance();
   uc32 c = ScanHexEscape('u', 4);
   // We do not allow a unicode escape sequence to start another
   // unicode escape sequence.
   if (c == '\\') return unibrow::Utf8::kBadChar;
   return c;
 }
 
 
 Token::Value JavaScriptScanner::ScanIdentifierOrKeyword() {
-  ASSERT(scanner_constants_->IsIdentifierStart(c0_));
+  ASSERT(unicode_cache_->IsIdentifierStart(c0_));
   LiteralScope literal(this);
   KeywordMatcher keyword_match;
   // Scan identifier start character.
   if (c0_ == '\\') {
     uc32 c = ScanIdentifierUnicodeEscape();
     // Only allow legal identifier start characters.
-    if (!scanner_constants_->IsIdentifierStart(c)) return Token::ILLEGAL;
+    if (!unicode_cache_->IsIdentifierStart(c)) return Token::ILLEGAL;
     AddLiteralChar(c);
     return ScanIdentifierSuffix(&literal);
   }
 
   uc32 first_char = c0_;
   Advance();
   AddLiteralChar(first_char);
   if (!keyword_match.AddChar(first_char)) {
     return ScanIdentifierSuffix(&literal);
   }
 
   // Scan the rest of the identifier characters.
-  while (scanner_constants_->IsIdentifierPart(c0_)) {
+  while (unicode_cache_->IsIdentifierPart(c0_)) {
     if (c0_ != '\\') {
       uc32 next_char = c0_;
       Advance();
       AddLiteralChar(next_char);
       if (keyword_match.AddChar(next_char)) continue;
     }
     // Fallthrough if no loner able to complete keyword.
     return ScanIdentifierSuffix(&literal);
   }
   literal.Complete();
 
   return keyword_match.token();
 }
 
 
 Token::Value JavaScriptScanner::ScanIdentifierSuffix(LiteralScope* literal) {
   // Scan the rest of the identifier characters.
-  while (scanner_constants_->IsIdentifierPart(c0_)) {
+  while (unicode_cache_->IsIdentifierPart(c0_)) {
     if (c0_ == '\\') {
       uc32 c = ScanIdentifierUnicodeEscape();
       // Only allow legal identifier part characters.
-      if (!scanner_constants_->IsIdentifierPart(c)) return Token::ILLEGAL;
+      if (!unicode_cache_->IsIdentifierPart(c)) return Token::ILLEGAL;
       AddLiteralChar(c);
     } else {
       AddLiteralChar(c0_);
       Advance();
     }
   }
   literal->Complete();
 
   return Token::IDENTIFIER;
 }
 
 
 bool JavaScriptScanner::ScanRegExpPattern(bool seen_equal) {
   // Scan: ('/' | '/=') RegularExpressionBody '/' RegularExpressionFlags
   bool in_character_class = false;
 
   // Previous token is either '/' or '/=', in the second case, the
   // pattern starts at =.
   next_.location.beg_pos = source_pos() - (seen_equal ? 2 : 1);
   next_.location.end_pos = source_pos() - (seen_equal ? 1 : 0);
 
   // Scan regular expression body: According to ECMA-262, 3rd, 7.8.5,
   // the scanner should pass uninterpreted bodies to the RegExp
   // constructor.
   LiteralScope literal(this);
   if (seen_equal)
     AddLiteralChar('=');
 
   while (c0_ != '/' || in_character_class) {
-    if (scanner_constants_->IsLineTerminator(c0_) || c0_ < 0) return false;
+    if (unicode_cache_->IsLineTerminator(c0_) || c0_ < 0) return false;
     if (c0_ == '\\') {  // Escape sequence.
       AddLiteralCharAdvance();
-      if (scanner_constants_->IsLineTerminator(c0_) || c0_ < 0) return false;
+      if (unicode_cache_->IsLineTerminator(c0_) || c0_ < 0) return false;
       AddLiteralCharAdvance();
       // If the escape allows more characters, i.e., \x??, \u????, or \c?,
       // only "safe" characters are allowed (letters, digits, underscore),
       // otherwise the escape isn't valid and the invalid character has
       // its normal meaning. I.e., we can just continue scanning without
       // worrying whether the following characters are part of the escape
       // or not, since any '/', '\\' or '[' is guaranteed to not be part
       // of the escape sequence.
     } else {  // Unescaped character.
       if (c0_ == '[') in_character_class = true;
       if (c0_ == ']') in_character_class = false;
       AddLiteralCharAdvance();
     }
   }
   Advance();  // consume '/'
 
   literal.Complete();
 
   return true;
 }
 
 
 bool JavaScriptScanner::ScanRegExpFlags() {
   // Scan regular expression flags.
   LiteralScope literal(this);
-  while (scanner_constants_->IsIdentifierPart(c0_)) {
+  while (unicode_cache_->IsIdentifierPart(c0_)) {
     if (c0_ == '\\') {
       uc32 c = ScanIdentifierUnicodeEscape();
       if (c != static_cast<uc32>(unibrow::Utf8::kBadChar)) {
         // We allow any escaped character, unlike the restriction on
         // IdentifierPart when it is used to build an IdentifierName.
         AddLiteralChar(c);
         continue;
       }
     }
     AddLiteralCharAdvance();
@@ skipping 177 matching lines @@
       if (MatchKeywordStart(input, "with", 1, Token::WITH)) return;
       break;
     case UNMATCHABLE:
       break;
   }
   // On fallthrough, it's a failure.
   state_ = UNMATCHABLE;
 }
 
 } }  // namespace v8::internal