let regexp blank = [ ' ' '\t' '\n' ]
let regexp paren = [ '(' '[' '{' ')' ']' '}' ]
let regexp implicit = '?'
+let regexp placeholder = '%'
let regexp symbol_char =
[^ 'a' - 'z' 'A' - 'Z' '0' - '9'
' ' '\t' '\n'
'\\' '(' '[' '{' ')' ']' '}' '?'
]
-let regexp comment_char = [^ '\n' ]
-let regexp comment = "%%" comment_char*
+let regexp dust = "%%" [^ '\n']* '\n'
+
+let regexp comment_char = [^ ")" ]
+let regexp note = "(*" comment_char* "*)"
+
+let regexp commentbegin = "(**"
+let regexp commentend = "**)"
+
let regexp blanks = blank+
let regexp num = digit+
let regexp tex_token = '\\' alpha+
-let regexp symbol = symbol_char+
+let regexp symbol = symbol_char
let regexp ident_cont = alpha | num | '_' | '\''
let regexp ident_cont' = ident_cont | tex_token
let regexp ident = (alpha ident_cont*) | ('_' ident_cont+)
| paren -> return lexbuf ("PAREN", Ulexing.utf8_lexeme lexbuf)
| meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
| implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
+ | placeholder -> return lexbuf ("PLACEHOLDER", Ulexing.utf8_lexeme lexbuf)
| qstring ->
return lexbuf ("QSTRING", remove_quotes (Ulexing.utf8_lexeme lexbuf))
| symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
return lexbuf ("SYMBOL", Utf8Macro.expand macro)
with Utf8Macro.Macro_not_found _ ->
return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
- | comment ->
- if comments then
+ | dust -> token comments lexbuf
+ | note ->
+ (*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
+ return lexbuf ("NOTE", comment)
+ (*else
+ token comments lexbuf*)
+ | commentbegin -> return lexbuf ("BEGINCOMMENT","")
+ | commentend -> return lexbuf ("ENDCOMMENT","")
| eof -> return lexbuf ("EOI", "")
| _ -> error lexbuf "Invalid character"