(*
 * bibtex2html - A BibTeX to HTML translator
 * Copyright (C) 1997-2000 Jean-Christophe Filliâtre and Claude Marché
 * 
 * This software is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License version 2, as published by the Free Software Foundation.
 * 
 * This software is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * 
 * See the GNU General Public License version 2 for more details
 * (enclosed in the file GPL).
 *)

(*i $Id: latex_accents.mll,v 1.9 2006/02/22 10:05:44 filliatr Exp $ i*)

(* Normalize both ISO-latin characters and LaTeX accents to HTML entities *)

{

  let string_buf = Buffer.create 79
                     
  let add_string s = Buffer.add_string string_buf s

  let add lexbuf = Buffer.add_string string_buf (Lexing.lexeme lexbuf)

  let produce_regexp = ref false

}

let space = [ '\t']

rule next_char = parse
    '\\'                          { control lexbuf }
  | '{'                           { next_char lexbuf }
  | '}'                           { next_char lexbuf }
  | 'ç' { add_string "ç" ; next_char lexbuf }
  | 'ñ' { add_string "ñ"; next_char lexbuf }
  | 'ä' { add_string "ä"; next_char lexbuf }
  | 'ö' { add_string "ö"; next_char lexbuf }
  | 'ü' { add_string "ü"; next_char lexbuf }
  | 'ë' { add_string "ë"; next_char lexbuf }
  | 'Ä' { add_string "Ä"; next_char lexbuf }
  | 'Ö' { add_string "Ö"; next_char lexbuf }
  | 'Ü' { add_string "Ü"; next_char lexbuf }
  | 'Ë' { add_string "Ë"; next_char lexbuf }
  | 'ï' { add_string "ï"; next_char lexbuf }
  | 'Ï' { add_string "Ï"; next_char lexbuf }
  | 'á' { add_string "á"; next_char lexbuf }
  | 'ó' { add_string "ó"; next_char lexbuf }
  | 'ú' { add_string "ú"; next_char lexbuf }
  | 'é' { add_string "é"; next_char lexbuf }
  | 'Á' { add_string "Á"; next_char lexbuf }
  | 'Ó' { add_string "Ó"; next_char lexbuf }
  | 'Ú' { add_string "Ú"; next_char lexbuf }
  | 'É' { add_string "É"; next_char lexbuf }
  | 'í' { add_string "í"; next_char lexbuf }
  | 'Í' { add_string "Í"; next_char lexbuf }
  | 'à' { add_string "à"; next_char lexbuf }
  | 'ò' { add_string "ò"; next_char lexbuf }
  | 'ù' { add_string "ù"; next_char lexbuf }
  | 'è' { add_string "è"; next_char lexbuf }
  | 'À' { add_string "À"; next_char lexbuf }
  | 'Ò' { add_string "Ò"; next_char lexbuf }
  | 'Ù' { add_string "Ù"; next_char lexbuf }
  | 'È' { add_string "È"; next_char lexbuf }
  | 'ì' { add_string "ì"; next_char lexbuf }
  | 'Ì' { add_string "Ì"; next_char lexbuf }
  | 'â' { add_string "â"; next_char lexbuf }
  | 'ô' { add_string "ô"; next_char lexbuf }
  | 'û' { add_string "û"; next_char lexbuf }
  | 'ê' { add_string "ê"; next_char lexbuf }
  | 'î' { add_string "î"; next_char lexbuf }
  | 'Â' { add_string "Â"; next_char lexbuf }
  | 'Ô' { add_string "Ô"; next_char lexbuf }
  | 'Û' { add_string "Û"; next_char lexbuf }
  | 'Ê' { add_string "Ê"; next_char lexbuf }
  | 'Î' { add_string "Î"; next_char lexbuf }
  | _                             { add lexbuf ; next_char lexbuf }
  | eof                           { () }


(* called when we have seen  "\\"  *)

and control = parse
  '"'                { quote_char lexbuf }
| '\''               { right_accent lexbuf }
| '`'                { left_accent lexbuf }
| '^'                { hat lexbuf }
| "c{c}"             { add_string "ç" ; next_char lexbuf }
| 'v'                { czech lexbuf }
| ("~n"|"~{n}")      { add_string "ñ"; next_char lexbuf  }
|  _                 { add_string "\\" ; add lexbuf ; next_char lexbuf  }
| eof                { add_string "\\" }

(* called when we have seen  "\\\""  *)
and quote_char = parse
  ('a'|"{a}")                   { add_string "ä" ; next_char lexbuf }
| ('o'|"{o}")                   { add_string "ö" ; next_char lexbuf }
| ('u'|"{u}")                   { add_string "ü" ; next_char lexbuf }
| ('e'|"{e}")                   { add_string "ë" ; next_char lexbuf }
| ('A'|"{A}")                   { add_string "Ä" ; next_char lexbuf }
| ('O'|"{O}")                   { add_string "Ö" ; next_char lexbuf }
| ('U'|"{U}")                   { add_string "Ü" ; next_char lexbuf }
| ('E'|"{E}")                   { add_string "Ë" ; next_char lexbuf }
| ("\\i" space+|"{\\i}")        { add_string "ï" ; next_char lexbuf }
| ('I'|"\\I" space+|"{\\I}")    { add_string "Ï" ; next_char lexbuf }
| _                             { add_string "\\\"" ; add lexbuf }
| eof                           { add_string "\\\"" }

(* called when we have seen  "\\'"  *)
and right_accent = parse
| ('a'|"{a}")   { add_string "á" ; next_char lexbuf }
| ('o'|"{o}")   { add_string "ó" ; next_char lexbuf }
| ('u'|"{u}")   { add_string "ú" ; next_char lexbuf }
| ('e'|"{e}")   { add_string "é" ; next_char lexbuf }
| ('A'|"{A}")   { add_string "Á" ; next_char lexbuf }
| ('O'|"{O}")   { add_string "Ó" ; next_char lexbuf }
| ('U'|"{U}")   { add_string "Ú" ; next_char lexbuf }
| ('E'|"{E}")   { add_string "É" ; next_char lexbuf }
| ('\'')   { add_string "”" ; next_char lexbuf }
| ('i'|"\\i" space+|"{\\i}") { add_string "í" ; next_char lexbuf }
| ('I'|"\\I" space+|"{\\I}") { add_string "Í" ; next_char lexbuf }
| _             { add_string "\\'" ; add lexbuf ; next_char lexbuf }
| eof           { add_string "\\'" }

(* called when we have seen "\\`"  *)
and left_accent = parse
  ('a'|"{a}")   { add_string "à" ; next_char lexbuf }
| ('o'|"{o}")   { add_string "ò" ; next_char lexbuf }
| ('u'|"{u}")   { add_string "ù" ; next_char lexbuf }
| ('e'|"{e}")   { add_string "è" ; next_char lexbuf }
| ('A'|"{A}")   { add_string "À" ; next_char lexbuf }
| ('O'|"{O}")   { add_string "Ò" ; next_char lexbuf }
| ('U'|"{U}")   { add_string "Ù" ; next_char lexbuf }
| ('E'|"{E}")   { add_string "È" ; next_char lexbuf }
| ('`')   { add_string "“" ; next_char lexbuf }
| ('i'|"\\i" space+ |"{\\i}") { add_string "ì" ; next_char lexbuf }
| ('I'|"\\I" space+ |"{\\I}") { add_string "Ì" ; next_char lexbuf }
| _             { add_string "\\`" ; add lexbuf ; next_char lexbuf }
| eof           { add_string "\\`" }

and hat = parse
  ('a'|"{a}")   { add_string "â" ; next_char lexbuf }
| ('o'|"{o}")   { add_string "ô" ; next_char lexbuf }
| ('u'|"{u}")   { add_string "û" ; next_char lexbuf }
| ('e'|"{e}")   { add_string "ê" ; next_char lexbuf }
| ('A'|"{A}")   { add_string "Â" ; next_char lexbuf }
| ('O'|"{O}")   { add_string "Ô" ; next_char lexbuf }
| ('U'|"{U}")   { add_string "Û" ; next_char lexbuf }
| ('E'|"{E}")   { add_string "Ê" ; next_char lexbuf }
| ('i'|"\\i" space+ |"{\\i}") { add_string "î" ; next_char lexbuf }
| ('I'|"\\I" space+ |"{\\I}") { add_string "Î" ; next_char lexbuf }
| _             { add_string "\\^" ; add lexbuf ; next_char lexbuf }
|  eof          { add_string "\\^" }

and czech = parse
  ('r'|"{r}")   { add_string "ř" ; next_char lexbuf }
| ('R'|"{R}")   { add_string "Ř" ; next_char lexbuf }
| ('s'|"{s}")   { add_string "š" ; next_char lexbuf }
| ('S'|"{S}")   { add_string "Š" ; next_char lexbuf }
| ('i'|"\\i" space+ |"{\\i}") { add_string "ĭ" ; next_char lexbuf }
| ('I'|"\\I" space+ |"{\\I}") { add_string "Ĭ" ; next_char lexbuf }
| _             { add_string "\\^" ; add lexbuf ; next_char lexbuf }
|  eof          { add_string "\\^" }

{

let normalize to_regexp s = 
  Buffer.clear string_buf;
  produce_regexp := to_regexp;
  next_char (Lexing.from_string s);
  Buffer.contents string_buf
;;

}