added comments

[helm.git] / helm / ocaml / cic_disambiguation / cicTextualLexer2.ml

diff --git a/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml b/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml
index 6f179505d749c8782e7a83b2ff58edc1bde3b964..4cf0e4270a2fe29e53fdacac1aa017f83e055799 100644 (file)
--- a/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml
+++ b/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml
@@ -37,8 +37,11 @@ let regexp symbol_char =
      ' ' '\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+
@@ -106,6 +109,9 @@ let rec token' = lexer
 
 and token = lexer
 *)
+
+let remove_quotes s = String.sub s 1 (String.length s - 2)
+
 let rec token comments = lexer
   | blanks -> token comments lexbuf
   | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
@@ -119,9 +125,7 @@ let rec token comments = lexer
   | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
   | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
   | qstring ->
-      let lexeme = Ulexing.utf8_lexeme lexbuf in
-      let s = String.sub lexeme 1 (String.length lexeme - 2) in
-      return lexbuf ("QSTRING", s)
+      return lexbuf ("QSTRING", remove_quotes (Ulexing.utf8_lexeme lexbuf))
   | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
   | tex_token ->
       let macro =
@@ -131,14 +135,17 @@ let rec token comments = lexer
         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"