File: read_html.mll

package info (click to toggle)
hlins 0.40-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 484 kB
  • sloc: ml: 1,215; makefile: 148; sh: 4
file content (190 lines) | stat: -rw-r--r-- 6,920 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
(***************************************************************************)
(*  HLins: insert http-links into HTML documents.                          *)
(*  See http://www.lri.fr/~treinen/hlins                                   *)
(*                                                                         *)
(*  Copyright (C) 1999-2024 Ralf Treinen <treinen@irif.fr>                 *)
(*                                                                         *)
(*  This program is free software; you can redistribute it and/or modify   *)
(*  it under the terms of the GNU General Public License as published by   *)
(*  the Free Software Foundation; either version 2 of the License, or (at  *)
(*  your option) any later version.                                        *)
(*                                                                         *)
(*  This program 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 for more details.                               *)
(*                                                                         *)
(*  You should have received a copy of the GNU General Public License      *)
(*  along with this program; if not, write to the Free Software            *)
(*  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307    *)
(*  USA                                                                    *)
(*                                                                         *)
(***************************************************************************)

(*
    HLins: insert http-links into HTML documents.
    See http://www.lri.fr/~treinen/hlins

    Copyright (C) 1999 Ralf Treinen <treinen@lri.fr>

    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    This program 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 for more details.

    You should have received a copy of the GNU General Public License
    along with this program; if not, write to the Free Software
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

*)

{
open Lexing;;
open Buffer;;

(* translates an html character representation "&#nnn;" to the 
   corresponding 8-bit char.
*)
let special_to_char s = Char.chr (int_of_string (String.sub s 2 3))
;;

type token =
    CHAR of char
  | VERB of string;;

let b = create 1024;;

}

let space = [' ''\n''\t''\r']


rule next_html = parse
  | "&Agrave;"	{ CHAR '' }
  | "&Aacute;"	{ CHAR '' }
  | "&Acirc;"	{ CHAR '' }
  | "&Atilde;"	{ CHAR '' }
  | "&Auml;"	{ CHAR '' }
  | "&Aring;"	{ CHAR '' }
  | "&AElig;"	{ CHAR '' }
  | "&Egrave;"	{ CHAR '' }
  | "&Eacute;"	{ CHAR '' }
  | "&Ecirc;"	{ CHAR '' }
  | "&Euml;"	{ CHAR '' }
  | "&Igrave;"	{ CHAR '' }
  | "&Iacute;"	{ CHAR '' }
  | "&Icirc;"	{ CHAR '' }
  | "&Iuml;"	{ CHAR '' }
  | "&ETH;"	{ CHAR '' }
  | "&Ntilde;"	{ CHAR '' }
  | "&Ograve;"	{ CHAR '' }
  | "&Oacute;"	{ CHAR '' }
  | "&Ocirc;"	{ CHAR '' }
  | "&Otilde;"	{ CHAR '' }
  | "&Ouml;"	{ CHAR '' }
  | "&Oslash;"	{ CHAR '' }
  | "&Ugrave;"	{ CHAR '' }
  | "&Uacute;"	{ CHAR '' }
  | "&Ucirc;"	{ CHAR '' }
  | "&Uuml;"	{ CHAR '' }
  | "&Yacute;"	{ CHAR '' }
  | "&THORN;"	{ CHAR '' }
  | "&szlig;"	{ CHAR '' }
  | "&agrave;"	{ CHAR '' }
  | "&aacute;"	{ CHAR '' }
  | "&acirc;"	{ CHAR '' }
  | "&atilde;"	{ CHAR '' }
  | "&auml;"	{ CHAR '' }
  | "&aring;"	{ CHAR '' }
  | "&aelig;"	{ CHAR '' }
  | "&ccdil;"	{ CHAR '' }
  | "&egrave;"	{ CHAR '' }
  | "&eacute;"	{ CHAR '' }
  | "&ecirc;"	{ CHAR '' }
  | "&euml;"	{ CHAR '' }
  | "&igrave;"	{ CHAR '' }
  | "&iacute;"	{ CHAR '' }
  | "&icirc;"	{ CHAR '' }
  | "&iuml;"	{ CHAR '' }
  | "&eth;"	{ CHAR '' }
  | "&ntilde;"	{ CHAR '' }
  | "&ograve;"	{ CHAR '' }
  | "&oacute;"	{ CHAR '' }
  | "&ocirc;"	{ CHAR '' }
  | "&otilde;"	{ CHAR '' }
  | "&ugrave;"	{ CHAR '' }
  | "&uacute;"	{ CHAR '' }
  | "&ucirc;"	{ CHAR '' }
  | "&uuml;"	{ CHAR '' }
  | "&yacute;"	{ CHAR '' }
  | "&thorn;"	{ CHAR '' }
      (* special characters between 192 and 255 *)
  | "&#" ( "19"['2'-'9'] | '2'['0'-'4']['0'-'9'] | "25"['0'-'5'] ) ";"
      { CHAR (special_to_char (lexeme lexbuf)) }
  | '<'('H'|'h')('E'|'e')('A'|'a')('D'|'d')'>'
      { add_string b (lexeme lexbuf); skip_head lexbuf }
  | '<'('C'|'c')('O'|'o')('D'|'d')('E'|'e')'>'
      { add_string b (lexeme lexbuf); skip_code lexbuf }
  | '<'('S'|'s')('A'|'a')('M'|'m')('P'|'p')'>'
      { add_string b (lexeme lexbuf); skip_samp lexbuf }
  | '<'('K'|'k')('B'|'b')('D'|'d')'>'
      { add_string b (lexeme lexbuf); skip_kbd lexbuf }
  | '<'('D'|'d')('I'|'i')('V'|'v') space+ "nohlins>"
      { add_string b (lexeme lexbuf); skip_div lexbuf }
  | '<'('A'|'a') space+ ([^'>']*space)?
      ('H'|'h')('R'|'r')('E'|'e')('F'|'f') '=' [^'>']* '>'
     { add_string b (lexeme lexbuf); skip_a lexbuf } 
  | '<' [^'>']* '>'   { VERB(lexeme lexbuf)}
  | eof               { raise End_of_file }
  | _                 { CHAR(lexeme_char lexbuf 0)}

and skip_head = parse
  |  "</"('H'|'h')('E'|'e')('A'|'a')('D'|'d')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c)}
  | _ { add_char b (lexeme_char lexbuf 0); skip_head lexbuf }

and skip_code = parse
  |  "</"('C'|'c')('O'|'o')('D'|'d')('E'|'e')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_code lexbuf }

and skip_samp = parse
  |  "</"('S'|'s')('A'|'a')('M'|'m')('P'|'p')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_samp lexbuf }

and skip_kbd = parse
  |  "</"('K'|'k')('B'|'b')('D'|'d')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_kbd lexbuf }

and skip_pre = parse
  |  "</"('P'|'p')('R'|'r')('E'|'e')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_pre lexbuf }

and skip_div = parse
  |  "</"('D'|'d')('I'|'i')('V'|'v')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_div lexbuf }

and skip_a = parse
  |  "</"('A'|'a')'>'
      { add_string b (lexeme lexbuf);
	let c = contents b in reset b; VERB(c) }
  | _ { add_char b (lexeme_char lexbuf 0); skip_a lexbuf }