and token = lexer
*)
-let rec token = lexer
- | blanks -> token lexbuf
+let rec token comments = lexer
+ | blanks -> token comments lexbuf
| uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
| ident ->
let lexeme = Ulexing.utf8_lexeme lexbuf in
with Utf8Macro.Macro_not_found _ ->
return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
| comment ->
- let comment =
- Ulexing.utf8_sub_lexeme lexbuf 2 (Ulexing.lexeme_length lexbuf - 2)
- in
- return lexbuf ("COMMENT", comment)
+ if comments then
+ let comment =
+ Ulexing.utf8_sub_lexeme lexbuf 2 (Ulexing.lexeme_length lexbuf - 2)
+ in
+ return lexbuf ("COMMENT", comment)
+ else
+ token comments lexbuf
| eof -> return lexbuf ("EOI", "")
| _ -> error lexbuf "Invalid character"
-let tok_func stream =
+let tok_func comments stream =
let lexbuf = Ulexing.from_utf8_stream stream in
Token.make_stream_and_flocation
(fun () ->
try
- token lexbuf
+ token comments lexbuf
with
| Ulexing.Error -> error_at_end lexbuf "Unexpected character"
| Ulexing.InvalidCodepoint i -> error_at_end lexbuf "Invalid code point")
-let cic_lexer =
- {
- Token.tok_func = tok_func;
+let cic_lexer ?(comments = false) () =
+ {
+ Token.tok_func = tok_func comments;
Token.tok_using = (fun _ -> ());
Token.tok_removing = (fun _ -> ());
Token.tok_match = Token.default_match;