Issue 66: Multi-line comments

4 files changed, 39 insertions, 3 deletions

diff --git a/doc/rust.texi b/doc/rust.texi
index b8a59a2b..3e6a93b2 100644
--- a/doc/rust.texi
+++ b/doc/rust.texi
@@ -616,11 +616,17 @@ otherwise a free-form language.
 @dfn{Whitespace} is any of the following Unicode characters: U+0020 (space),
 U+0009 (tab, @code{'\t'}), U+000A (LF, @code{'\n'}), U+000D (CR, @code{'\r'}).
 
-@dfn{Comments} are any sequence of Unicode characters beginning with U+002F
-U+002F (@code{"//"}) and extending to the next U+000A character,
+@dfn{Comments} are @emph{single-line comments} or @emph{multi-line comments}.
+
+A @dfn{single-line comment} is any sequence of Unicode characters beginning
+with U+002F U+002F (@code{"//"}) and extending to the next U+000A character,
 @emph{excluding} cases in which such a sequence occurs within a string literal
 token or a syntactic extension token.
 
+A @dfn{multi-line comments} is any sequence of Unicode characters beginning
+with U+002F U+002A (@code{"/*"}) and ending with U+002A U+002F (@code{"*/"}),
+@emph{excluding} cases in which such a sequence occurs within a string literal
+token or a syntactic extension token.  Multi-line comments may be nested.
 
 @node       Ref.Lex.Ident
 @subsection Ref.Lex.Ident
diff --git a/src/boot/fe/lexer.mll b/src/boot/fe/lexer.mll
index 6430821d..090da25f 100644
--- a/src/boot/fe/lexer.mll
+++ b/src/boot/fe/lexer.mll
@@ -139,7 +139,7 @@ rule token = parse
                                      <- (bump_line lexbuf.Lexing.lex_curr_p);
                                  token lexbuf }
 | "//" [^'\n']*                { token lexbuf }
-
+| "/*"                         { comment 1 lexbuf }
 | '+'                          { PLUS       }
 | '-'                          { MINUS      }
 | '*'                          { STAR       }
@@ -362,3 +362,16 @@ and bracequote buf depth = parse
 | [^'\\' '{' '}']+              { let s = Lexing.lexeme lexbuf in
                                     Buffer.add_string buf s;
                                     bracequote buf depth lexbuf        }
+
+
+and comment depth = parse
+
+  '/' '*'                       { comment (depth+1) lexbuf      }
+
+| '*' '/'                       { if depth = 1
+                                  then token lexbuf
+                                  else comment (depth-1) lexbuf }
+
+| '*' [^'{']                   { comment depth lexbuf           }
+| '/' [^'*']                   { comment depth lexbuf           }
+| [^'/' '*']+                  { comment depth lexbuf           }
diff --git a/src/test/compile-fail/unbalanced-comment.rs b/src/test/compile-fail/unbalanced-comment.rs
new file mode 100644
index 00000000..c22df4ec
--- /dev/null
+++ b/src/test/compile-fail/unbalanced-comment.rs
@@ -0,0 +1,9 @@
+// -*- rust -*-
+
+/*
+ * This is an un-balanced /* multi-line comment.
+ */
+
+fn main() {
+  log "hello, world.";
+}
diff --git a/src/test/run-pass/multiline-comment.rs b/src/test/run-pass/multiline-comment.rs
new file mode 100644
index 00000000..3b846433
--- /dev/null
+++ b/src/test/run-pass/multiline-comment.rs
@@ -0,0 +1,8 @@
+// -*- rust -*-
+
+/*
+ * This is a /* depth-balanced */ multi-line comment.
+ */
+
+fn main() {
+}