-
Notifications
You must be signed in to change notification settings - Fork 6
/
Copy pathlex-html.c
275 lines (247 loc) · 9.75 KB
/
lex-html.c
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
/* A lexer will special features for handling HTML. */
/* Copyright (C) 1997, 1999 Andrew McCallum
Written by: Andrew Kachites McCallum <mccallum@cs.cmu.edu>
This file is part of the Bag-Of-Words Library, `libbow'.
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License
as published by the Free Software Foundation, version 2.
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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA */
#include <bow/libbow.h>
#include <ctype.h> /* for tolower() */
static const struct
{
char *entityName;
unsigned char entityChar;
} htmlEntities[] = {
{ "nbsp", 32 }, /* non-breaking whitespace */
{ "quot", 34 }, /* double quote */
{ "amp", 38 }, /* ampersand */
{ "lt", 60 }, /* less than */
{ "gt", 62 }, /* greater than */
{ "iexcl", 161 }, /* inverted exclamation mark */
{ "cent", 161 }, /* cent sign */
{ "pound", 163 }, /* pound sign */
{ "yen", 165 }, /* yen sign */
{ "brvbar", 166 }, /* broken vertical bar */
{ "sect", 167 }, /* section sign */
{ "copy", 169 }, /* copyright sign */
{ "laquo", 171 }, /* angle quotation mark, left */
{ "raquo", 187 }, /* angle quotation mark, right */
{ "not", 172 }, /* negation sign */
{ "reg", 174 }, /* circled r registered sign */
{ "deg", 176 }, /* degree sign */
{ "plusmn", 177 }, /* plus or minus sign */
{ "sup2", 178 }, /* superscript 2 */
{ "sup3", 179 }, /* superscript 3 */
{ "micro", 181 }, /* micro sign */
{ "para", 182 }, /* paragraph sign */
{ "sup1", 185 }, /* superscript 1 */
{ "middot", 183 }, /* center dot */
{ "frac14", 188 }, /* fraction 1/4 */
{ "frac12", 189 }, /* fraction 1/2 */
{ "iquest", 191 }, /* inverted question mark */
{ "frac34", 190 }, /* fraction 3/4 */
{ "aelig", 198 }, /* capital ae diphthong (ligature) */
{ "aacute", 193 }, /* capital a, acute accent */
{ "acirc", 194 }, /* capital a, circumflex accent */
{ "agrave", 192 }, /* capital a, grave accent */
{ "aring", 197 }, /* capital a, ring */
{ "atilde", 195 }, /* capital a, tilde */
{ "auml", 196 }, /* capital a, dieresis or umlaut mark */
{ "ccedil", 199 }, /* capital c, cedilla */
{ "eth", 208 }, /* capital eth, icelandic */
{ "eacute", 201 }, /* capital e, acute accent */
{ "ecirc", 202 }, /* capital e, circumflex accent */
{ "egrave", 200 }, /* capital e, grave accent */
{ "euml", 203 }, /* capital e, dieresis or umlaut mark */
{ "iacute", 205 }, /* capital i, acute accent */
{ "icirc", 206 }, /* capital i, circumflex accent */
{ "igrave", 204 }, /* capital i, grave accent */
{ "iuml", 207 }, /* capital i, dieresis or umlaut mark */
{ "ntilde", 209 }, /* capital n, tilde */
{ "oacute", 211 }, /* capital o, acute accent */
{ "ocirc", 212 }, /* capital o, circumflex accent */
{ "ograve", 210 }, /* capital o, grave accent */
{ "oslash", 216 }, /* capital o, slash */
{ "otilde", 213 }, /* capital o, tilde */
{ "ouml", 214 }, /* capital o, dieresis or umlaut mark */
{ "thorn", 222 }, /* capital thorn, icelandic */
{ "uacute", 218 }, /* capital u, acute accent */
{ "ucirc", 219 }, /* capital u, circumflex accent */
{ "ugrave", 217 }, /* capital u, grave accent */
{ "uuml", 220 }, /* capital u, dieresis or umlaut mark */
{ "yacute", 221 }, /* capital y, acute accent */
{ "aacute", 225 }, /* small a, acute accent */
{ "acirc", 226 }, /* small a, circumflex accent */
{ "aelig", 230 }, /* small ae diphthong (ligature) */
{ "agrave", 224 }, /* small a, grave accent */
{ "aring", 229 }, /* small a, ring */
{ "atilde", 227 }, /* small a, tilde */
{ "auml", 228 }, /* small a, dieresis or umlaut mark */
{ "ccedil", 231 }, /* small c, cedilla */
{ "eacute", 233 }, /* small e, acute accent */
{ "ecirc", 234 }, /* small e, circumflex accent */
{ "egrave", 232 }, /* small e, grave accent */
{ "eth", 240 }, /* small eth, icelandic */
{ "euml", 235 }, /* small e, dieresis or umlaut mark */
{ "iacute", 237 }, /* small i, acute accent */
{ "icirc", 238 }, /* small i, circumflex accent */
{ "igrave", 236 }, /* small i, grave accent */
{ "iuml", 239 }, /* small i, dieresis or umlaut mark */
{ "ntilde", 241 }, /* small n, tilde */
{ "oacute", 243 }, /* small o, acute accent */
{ "ocirc", 244 }, /* small o, circumflex accent */
{ "ograve", 242 }, /* small o, grave accent */
{ "oslash", 248 }, /* small o, slash */
{ "otilde", 245 }, /* small o, tilde */
{ "ouml", 246 }, /* small o, dieresis or umlaut mark */
{ "szlig", 223 }, /* small sharp s, german (sz ligature) */
{ "thorn", 254 }, /* small thorn, icelandic */
{ "uacute", 250 }, /* small u, acute accent */
{ "ucirc", 251 }, /* small u, circumflex accent */
{ "ugrave", 249 }, /* small u, grave accent */
{ "uuml", 252 }, /* small u, dieresis or umlaut mark */
{ "yacute", 253 }, /* small y, acute accent */
{ "yuml", 255 } /* small y, dieresis or umlaut mark */
};
int entityMaxLen;
static bow_int4str *entityMap;
#define PARAMS (bow_default_lexer_parameters)
static void initEntityMap()
{
int i;
if (entityMap != NULL)
return;
entityMap = bow_int4str_new(255);
/* the below must be done from 0-N or logic in get_word below breaks */
for (i = 0; i < sizeof(htmlEntities)/sizeof(htmlEntities[0]); i++) {
bow_str2int (entityMap, htmlEntities[i].entityName);
if (entityMaxLen < strlen(htmlEntities[i].entityName))
entityMaxLen = strlen(htmlEntities[i].entityName);
}
}
int
bow_lexer_html_get_raw_word (bow_lexer *self, bow_lex *lex,
char *buf, int buflen)
{
int byte; /* characters read from the FP */
int wordlen; /* number of characters in the word so far */
int html_bracket_nestings = 0;
assert (lex->document_position <= lex->document_length);
if (entityMap == NULL)
initEntityMap();
/* Ignore characters until we get an beginning character. */
do
{
byte = lex->document[lex->document_position++];
if (byte == 0)
{
if (html_bracket_nestings)
bow_verbosify (bow_verbose,
"Found unterminated `<' in HTML\n");
lex->document_position--;
return 0;
}
if (byte == '&')
{
char *begEntity = &lex->document[lex->document_position];
char *s = strchr(begEntity, ';');
int hashCode;
if (s != NULL)
if ((s - begEntity) <= entityMaxLen) { /* can it be an entity */
*s = '\0';
if (begEntity[0] == '#') {
byte = atoi(&begEntity[1]);
lex->document_position++;
do
{
byte = lex->document[lex->document_position++];
} while (isdigit(byte));
}
else {
hashCode = bow_str2int_no_add(entityMap, begEntity);
if (hashCode != -1) {
byte = htmlEntities[hashCode].entityChar;
lex->document_position += s - begEntity + 1;
}
}
*s = ';';
}
}
if (byte == '<')
{
if (html_bracket_nestings)
bow_verbosify (bow_verbose,
"Found nested '<' in HTML\n");
html_bracket_nestings = 1;
}
else if (byte == '>')
{
if (html_bracket_nestings == 0)
bow_verbosify (bow_verbose,
"Found `>' outside HTML token\n");
html_bracket_nestings = 0;
}
}
while (html_bracket_nestings || !PARAMS->true_to_start (byte));
/* Add the first alphabetic character to the word. */
buf[0] = (bow_lexer_case_sensitive) ? byte : tolower (byte);
/* Add all the satisfying characters to the word - stripping out all HTML
markup. "<FONT SIZE=+2>R</FONT>ainbow " becomes "Rainbow" */
for (wordlen = 1; wordlen < buflen; wordlen++)
{
byte = lex->document[lex->document_position++];
if (byte == 0)
{
lex->document_position--;
break;
}
if (!PARAMS->false_to_end (byte) && html_bracket_nestings == 0)
{
lex->document_position--;
break;
}
if (byte == '<')
{
if (html_bracket_nestings)
bow_verbosify (bow_verbose,
"Found nested '<' in HTML\n");
html_bracket_nestings = 1;
}
if (byte == '>')
{
if (html_bracket_nestings == 0)
bow_verbosify (bow_verbose,
"Found `>' outside HTML token\n");
html_bracket_nestings = 0;
}
if (html_bracket_nestings == 0)
buf[wordlen] = tolower (byte);
}
assert (lex->document_position <= lex->document_length);
if (wordlen >= buflen)
bow_error ("Encountered word longer than buffer length=%d", buflen);
/* Terminate it. */
buf[wordlen] = '\0';
return wordlen;
}
/* A lexer that ignores all HTML directives, ignoring all characters
between angled brackets: < and >. */
const bow_lexer _bow_html_lexer =
{
sizeof (bow_lex),
NULL,
bow_lexer_simple_open_text_fp,
bow_lexer_simple_open_str,
bow_lexer_simple_get_word,
bow_lexer_html_get_raw_word,
bow_lexer_simple_postprocess_word,
bow_lexer_simple_close
};
const bow_lexer *bow_html_lexer = &_bow_html_lexer;