aboutsummaryrefslogtreecommitdiffhomepage
path: root/lib/xml_lexer.mll
blob: 5b06e720a9e27896a0006d9e19a73849a131833e (plain)
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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
{(*
 * Xml Light, an small Xml parser/printer with DTD support.
 * Copyright (C) 2003 Nicolas Cannasse (ncannasse@motion-twin.com)
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *)

open Lexing

type error =
	| EUnterminatedComment
	| EUnterminatedString
	| EIdentExpected
	| ECloseExpected
	| ENodeExpected
	| EAttributeNameExpected
	| EAttributeValueExpected
	| EUnterminatedEntity

exception Error of error

type pos = int * int * int * int

type token =
	| Tag of string * (string * string) list * bool
	| PCData of string
	| Endtag of string
	| Eof

let last_pos = ref 0
and current_line = ref 0
and current_line_start = ref 0

let tmp = Buffer.create 200

let idents = Hashtbl.create 0

let _ = begin
	Hashtbl.add idents "gt;" ">";
	Hashtbl.add idents "lt;" "<";
	Hashtbl.add idents "amp;" "&";
	Hashtbl.add idents "apos;" "'";
	Hashtbl.add idents "quot;" "\"";
end

let init lexbuf =
	current_line := 1;
	current_line_start := lexeme_start lexbuf;
	last_pos := !current_line_start

let close lexbuf =
	Buffer.reset tmp

let pos lexbuf =
	!current_line ,	!current_line_start ,
	!last_pos ,
	lexeme_start lexbuf

let restore (cl,cls,lp,_) =
	current_line := cl;
	current_line_start := cls;
	last_pos := lp

let newline lexbuf =
	incr current_line;
	last_pos := lexeme_end lexbuf;
	current_line_start := !last_pos

let error lexbuf e =
	last_pos := lexeme_start lexbuf;
	raise (Error e)

}

let newline = ['\n']
let break = ['\r']
let space = [' ' '\t']
let identchar =  ['A'-'Z' 'a'-'z' '_' '0'-'9' ':' '-']
let entitychar = ['A'-'Z' 'a'-'z']
let pcchar = [^ '\r' '\n' '<' '>' '&']

rule token = parse
	| newline | (newline break) | break
		{
			newline lexbuf;
                        PCData "\n"
		}
	| "<!--"
		{
			last_pos := lexeme_start lexbuf;
			comment lexbuf;
			token lexbuf
		}
	| "<?"
		{
			last_pos := lexeme_start lexbuf;
			header lexbuf;
			token lexbuf;
		}
	| '<' space* '/' space*
		{
			last_pos := lexeme_start lexbuf;
			let tag = ident_name lexbuf in
			ignore_spaces lexbuf;
			close_tag lexbuf;
			Endtag tag
		}
	| '<' space*
		{
			last_pos := lexeme_start lexbuf;
			let tag = ident_name lexbuf in
			ignore_spaces lexbuf;
			let attribs, closed = attributes lexbuf in
			Tag(tag, attribs, closed)
		}
	| "&#"
		{
			last_pos := lexeme_start lexbuf;
			Buffer.reset tmp;
			Buffer.add_string tmp (lexeme lexbuf);
			PCData (pcdata lexbuf)
		}
	| '&'
		{
			last_pos := lexeme_start lexbuf;
			Buffer.reset tmp;
			Buffer.add_string tmp (entity lexbuf);
			PCData (pcdata lexbuf)
		}
	| pcchar+
		{
			last_pos := lexeme_start lexbuf;
			Buffer.reset tmp;
			Buffer.add_string tmp (lexeme lexbuf);
			PCData (pcdata lexbuf)
		}
	| eof { Eof }
	| _
		{ error lexbuf ENodeExpected }

and ignore_spaces = parse
        | newline | (newline break) | break
		{
			newline lexbuf;
			ignore_spaces lexbuf
		}
	| space +
		{ ignore_spaces lexbuf }
	| ""
		{ () }

and comment = parse
        | newline | (newline break) | break
		{
			newline lexbuf;
			comment lexbuf
		}
	| "-->"
		{ () }
	| eof
		{ raise (Error EUnterminatedComment) }
	| _
		{ comment lexbuf }

and header = parse
        | newline | (newline break) | break
		{
			newline lexbuf;
			header lexbuf
		}
	| "?>"
		{ () }
	| eof
		{ error lexbuf ECloseExpected }
	| _
		{ header lexbuf }

and pcdata = parse
        | newline | (newline break) | break
                {
                        Buffer.add_char tmp '\n';
                        newline lexbuf;
                        pcdata lexbuf
                }
	| pcchar+
		{
			Buffer.add_string tmp (lexeme lexbuf);
			pcdata lexbuf
		}
	| "&#"
		{
			Buffer.add_string tmp (lexeme lexbuf);
			pcdata lexbuf;
		}
	| '&'
		{
			Buffer.add_string tmp (entity lexbuf);
			pcdata lexbuf
		}
	| ""
		{ Buffer.contents tmp }

and entity = parse
	| entitychar+ ';'
		{
			let ident = lexeme lexbuf in
			try
				Hashtbl.find idents (String.lowercase ident)
			with
				Not_found -> "&" ^ ident
		}
	| _ | eof
		{ raise (Error EUnterminatedEntity) }

and ident_name = parse
	| identchar+
		{ lexeme lexbuf }
	| _ | eof
		{ error lexbuf EIdentExpected }

and close_tag = parse
	| '>'
		{ () }
	| _ | eof
		{ error lexbuf ECloseExpected }

and attributes = parse
	| '>'
		{ [], false }
	| "/>"
		{ [], true }
	| "" (* do not read a char ! *)
		{
			let key = attribute lexbuf in
			let data = attribute_data lexbuf in
			ignore_spaces lexbuf;
			let others, closed = attributes lexbuf in
			(key, data) :: others, closed
		}

and attribute = parse
	| identchar+
		{ lexeme lexbuf }
	| _ | eof
		{ error lexbuf EAttributeNameExpected }

and attribute_data = parse
	| space* '=' space* '"'
		{
			Buffer.reset tmp;
			last_pos := lexeme_end lexbuf;
			dq_string lexbuf
		}
	| space* '=' space* '\''
		{
			Buffer.reset tmp;
			last_pos := lexeme_end lexbuf;
			q_string lexbuf
		}
	| _ | eof
		{ error lexbuf EAttributeValueExpected }

and dq_string = parse
	| '"'
		{ Buffer.contents tmp }
	| '\\' [ '"' '\\' ]
		{
			Buffer.add_char tmp (lexeme_char lexbuf 1);
			dq_string lexbuf
		}
	| eof
		{ raise (Error EUnterminatedString) }
	| _
		{ 
			Buffer.add_char tmp (lexeme_char lexbuf 0);
			dq_string lexbuf
		}

and q_string = parse
	| '\''
		{ Buffer.contents tmp }
	| '\\' [ '\'' '\\' ]
		{
			Buffer.add_char tmp (lexeme_char lexbuf 1);
			q_string lexbuf
		}
	| eof
		{ raise (Error EUnterminatedString) }
	| _
		{ 
			Buffer.add_char tmp (lexeme_char lexbuf 0);
			q_string lexbuf
		}