This fixes several bugs with regards to line breaks and comments:

 - any unicode line break (line feed, vertical tab, form feed, carriage
   return, NEL, LS and PS) is considered to terminate a single-line
   comment. The line break itself is considered to be the next token
   after the comment, leading to a parser error if it is not an
   ascii character (i.e. for NEL, LS and PS).
 - unterminated multiline comments are considered illegal tokens
 - '/** /' is considered an unterminated multiline comment
   (previously, whitespace was allowed before the last '/'

1 files changed, 5 insertions, 2 deletions

diff --git a/libsolidity/parsing/Scanner.h b/libsolidity/parsing/Scanner.h
index 0adaa6fd..602532e4 100644
--- a/libsolidity/parsing/Scanner.h
+++ b/libsolidity/parsing/Scanner.h
@@ -197,8 +197,8 @@ private:
 
 	/// Skips all whitespace and @returns true if something was skipped.
 	bool skipWhitespace();
-	/// Skips all whitespace except Line feeds and returns true if something was skipped
-	bool skipWhitespaceExceptLF();
+	/// Skips all whitespace that are neither '\r' nor '\n'.
+	void skipWhitespaceExceptUnicodeLinebreak();
 	Token::Value skipSingleLineComment();
 	Token::Value skipMultiLineComment();
 
@@ -218,6 +218,9 @@ private:
 	/// is scanned.
 	bool scanEscape();
 
+	/// @returns true iff we are currently positioned at a unicode line break.
+	bool isUnicodeLinebreak();
+
 	/// Return the current source position.
 	int sourcePos() const { return m_source.position(); }
 	bool isSourcePastEndOfInput() const { return m_source.isPastEndOfInput(); }