Prevent double reporting on hex, strings, and multiline comments.

sdk/lib/_internal/compiler/implementation/scanner/scanner.dart

 // Copyright (c) 2012, the Dart project authors.  Please see the AUTHORS file
 // for details. All rights reserved. Use of this source code is governed by a
 // BSD-style license that can be found in the LICENSE file.
 
 part of scanner;
 
 abstract class Scanner {
   Token tokenize();
 
   factory Scanner(SourceFile file, {bool includeComments: false}) {
@@ skipping 610 matching lines @@
     next = advance(); // Advance past the $x or $X.
     bool hasDigits = false;
     while (true) {
       next = advance();
       if (($0 <= next && next <= $9)
           || ($A <= next && next <= $F)
           || ($a <= next && next <= $f)) {
         hasDigits = true;
       } else {
         if (!hasDigits) {
-          return unterminated('0x');
+          unterminated('0x', shouldAdvance: false);
+          return next;
         }
         appendSubstringToken(HEXADECIMAL_INFO, start, true);
         return next;
       }
     }
     return null;
   }
 
   int tokenizeDotsOrNumber(int next) {
     int start = scanOffset;
@@ skipping 203 matching lines @@
     return advance();
   }
 
   int tokenizeString(int next, int start, bool raw) {
     int quoteChar = next;
     next = advance();
     if (identical(quoteChar, next)) {
       next = advance();
       if (identical(quoteChar, next)) {
         // Multiline string.
-        return tokenizeMultiLineString(quoteChar, start, raw);
+        return tokenizeMultiLineString(next, quoteChar, start, raw);
       } else {
         // Empty string.
         appendSubstringToken(STRING_INFO, start, true);
         return next;
       }
     }
     if (raw) {
       return tokenizeSingleLineRawString(next, quoteChar, start);
     } else {
       return tokenizeSingleLineString(next, quoteChar, start);
@@ skipping 76 matching lines @@
       next = tokenizeIdentifier(next, scanOffset, false);
     } else {
       unterminated(r'$', shouldAdvance: false);
     }
     beginToken(); // The string interpolation suffix starts here.
     return next;
   }
 
   int tokenizeSingleLineRawString(int next, int quoteChar, int start) {
     bool asciiOnly = true;
-    next = advance(); // Advance past the quote.

[ahe, 2014/06/23 14:28:49]

This line caused dart2js to incorrectly compile this program:

main() {
  print(r'
');
}

I suggest that you create a test case for this. Exceptionally, this will have to
be a "naive" negative test (which we otherwise try to avoid). For example:

tests/language/bad_raw_string_negative_test.dart:
main() {
  print(r'
');
}

[srawlins, 2014/07/15 20:07:07]

I disagree. In this example, I get the correct error:

$ cat issue-18574-222.dart
main() {
  print(r'
');
}
$ xcodebuild/ReleaseIA32/dart-sdk/bin/dart2js issue-18574-222.dart
issue-18574-222.dart:2:9:
Error: String must end with r'.
  print(r'
        ^^
Error: Compilation failed.

I see that when tokenizeSingleLineRawString() is entered in this case, next is
$LF and peek() returns the single-quote character. Since next is correctly $LF,
this will be caught on line 960.

[ahe, 2014/07/16 07:54:18]

What I'm trying to say is:

You removed this line. That is good. It is good because, before your change,
dart2js would accept a broken program:

$ cat foo.dart
main() {
  print(r'
');
}

$ ./sdk/bin/dart2js foo.dart
Dart file (foo.dart) compiled to JavaScript: out.js
$

So your change is good. You fixed a bug. But you should add a regression test to
ensure this bug isn't reintroduced.

On 2014/07/15 20:07:07, srawlins wrote:

[srawlins, 2014/08/12 04:32:58]

Oh, I see! OK thank you. I've added your test as
tests/language/bad_raw_string_negative_test.dart

     while (next != $EOF) {
       if (identical(next, quoteChar)) {
         if (!asciiOnly) handleUnicode(start);
         next = advance();
         appendSubstringToken(STRING_INFO, start, asciiOnly);
         return next;
       } else if (identical(next, $LF) || identical(next, $CR)) {
         if (!asciiOnly) handleUnicode(start);
         return unterminatedRawString(quoteChar);
       } else if (next > 127) {
         asciiOnly = false;
       }
       next = advance();
     }
     if (!asciiOnly) handleUnicode(start);
     return unterminatedRawString(quoteChar);
   }
 
-  int tokenizeMultiLineRawString(int quoteChar, int start) {
+  int tokenizeMultiLineRawString(int next, int quoteChar, int start) {
     bool asciiOnlyString = true;
     bool asciiOnlyLine = true;
     int unicodeStart = start;
     int next = advance(); // Advance past the (last) quote (of three).
     outer: while (!identical(next, $EOF)) {
       while (!identical(next, quoteChar)) {
         if (identical(next, $LF)) {
           if (!asciiOnlyLine) {
             // Synchronize the string offset in the utf8 scanner.
             handleUnicode(unicodeStart);
@@ skipping 16 matching lines @@
           next = advance();
           appendSubstringToken(STRING_INFO, start, asciiOnlyString);
           return next;
         }
       }
     }
     if (!asciiOnlyLine) handleUnicode(unicodeStart);
     return unterminatedRawMultiLineString(quoteChar);
   }
 
-  int tokenizeMultiLineString(int quoteChar, int start, bool raw) {
-    if (raw) return tokenizeMultiLineRawString(quoteChar, start);
+  int tokenizeMultiLineString(int next, int quoteChar, int start, bool raw) {

[ahe, 2014/06/23 14:28:49]

I don't understand this change.

[srawlins, 2014/07/15 20:07:08]

Done. Sorry, I think from a previous fix.

+    if (raw) return tokenizeMultiLineRawString(next, quoteChar, start);
     bool asciiOnlyString = true;
     bool asciiOnlyLine = true;
     int unicodeStart = start;
-    int next = advance(); // Advance past the (last) quote (of three).
+    next = advance(); // Advance past the (last) quote (of three).
     while (!identical(next, $EOF)) {
       if (identical(next, $$)) {
         if (!asciiOnlyLine) handleUnicode(unicodeStart);
         next = tokenizeStringInterpolation(start, asciiOnlyString);
         start = scanOffset;
         unicodeStart = start;
         asciiOnlyString = true; // A new string token is created for the rest.
         asciiOnlyLine = true;
         continue;
       }
@@ skipping 47 matching lines @@
   }
 
   int unterminatedRawString(int quoteChar) {
     return unterminated('r${new String.fromCharCodes([quoteChar])}');
   }
 
   int unterminatedMultiLineString(int quoteChar) {
     return unterminated(
         new String.fromCharCodes([quoteChar, quoteChar, quoteChar]));
   }
+
   int unterminatedRawMultiLineString(int quoteChar) {
     return unterminated(
         'r${new String.fromCharCodes([quoteChar, quoteChar, quoteChar])}');
   }
 
   int advanceAfterError(bool shouldAdvance) {
     if (atEndOfFile()) return $EOF;
     if (shouldAdvance) {
       return advance(); // Ensure progress.
     } else {
@@ skipping 55 matching lines @@
 
 PrecedenceInfo closeBraceInfoFor(BeginGroupToken begin) {
   return const {
     '(': CLOSE_PAREN_INFO,
     '[': CLOSE_SQUARE_BRACKET_INFO,
     '{': CLOSE_CURLY_BRACKET_INFO,
     '<': GT_INFO,
     r'${': CLOSE_CURLY_BRACKET_INFO,
   }[begin.value];
 }