Make multi-line comments not count when checking whether --> is first on a line.

src/scanner-base.h

 // 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
@@ skipping 456 matching lines @@
    private:
     JavaScriptScanner* scanner_;
     bool complete_;
   };
 
   explicit JavaScriptScanner(UnicodeCache* scanner_contants);
 
   // Returns the next token.
   Token::Value Next();
 
-  // Returns true if there was a line terminator before the peek'ed token.
+  // Returns true if there was a line terminator before the peek'ed token,
+  // possibly inside a multi-line comment.
   bool has_line_terminator_before_next() const {

[William Hesse, 2011/06/21 12:38:54]

You can't have a getter which does not get the actual variable with the same
name, but the value of an expression.
I would call this "should_insert_implicit_semicolon"

[Lasse Reichstein, 2011/06/21 13:05:37]

That would be using parser-level terminology in the scanner.

I'll rename the function to not look like a getter, and rename the variable.

-    return has_line_terminator_before_next_;
+    // The distinction between newlines as whitespace and newlines inside
+    // multi-line comments only matter inside the scanner.

[William Hesse, 2011/06/21 12:38:54]

I don't think this sentence makes sense or adds anything.  I think you mean that
"newlines inside multi-line comments only affect semicolon insertion."

[Lasse Reichstein, 2011/06/21 13:05:37]

Again, semicolon-insertion is a parser-level concept, so it I won't refer to it
in the scanner (unless absolutely necessary).
I'll drop the explanation now that the names are different.

+    return has_line_terminator_before_next_ ||
+           has_multiline_comment_before_next_;
   }
 
   // Scans the input as a regular expression pattern, previous
   // character(s) must be /(=). Returns true if a pattern is scanned.
   bool ScanRegExpPattern(bool seen_equal);
   // Returns true if regexp flags are scanned (always since flags can
   // be empty).
   bool ScanRegExpFlags();
 
   // Tells whether the buffer contains an identifier (no escapes).
@@ skipping 32 matching lines @@
   // Scans a possible HTML comment -- begins with '<!'.
   Token::Value ScanHtmlComment();
 
   // Decodes a unicode escape-sequence which is part of an identifier.
   // If the escape sequence cannot be decoded the result is kBadChar.
   uc32 ScanIdentifierUnicodeEscape();
 
   // Start position of the octal literal last scanned.
   Location octal_pos_;
 
+  // Whether there is a line terminator whitespace character after
+  // the current token, and  before the next. Does not count newlines
+  // inside multiline comments.
   bool has_line_terminator_before_next_;
+  // Whether there is a multi-line comment (actually containing a

[William Hesse, 2011/06/21 12:38:54]

... comment that actually contains a newline ...

(restrictive "that" clause rather than non-restrictive "which" clause or
parenthetical clause)

[Lasse Reichstein, 2011/06/21 13:05:37]

Done.

+  // line-terminator) after the current token, and before the next.
+  bool has_multiline_comment_before_next_;
 };
 
 
 // ----------------------------------------------------------------------------
 // Keyword matching state machine.
 
 class KeywordMatcher {
 //  Incrementally recognize keywords.
 //
 //  Recognized keywords:
@@ skipping 118 matching lines @@
   // keyword with the current prefix).
   const char* keyword_;
   int counter_;
   Token::Value keyword_token_;
 };
 
 
 } }  // namespace v8::internal
 
 #endif  // V8_SCANNER_BASE_H_