line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
/* |
2
|
|
|
|
|
|
|
Copyright (C) 2015-2017 Alexander Borisov |
3
|
|
|
|
|
|
|
|
4
|
|
|
|
|
|
|
This library is free software; you can redistribute it and/or |
5
|
|
|
|
|
|
|
modify it under the terms of the GNU Lesser General Public |
6
|
|
|
|
|
|
|
License as published by the Free Software Foundation; either |
7
|
|
|
|
|
|
|
version 2.1 of the License, or (at your option) any later version. |
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
This library is distributed in the hope that it will be useful, |
10
|
|
|
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of |
11
|
|
|
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
12
|
|
|
|
|
|
|
Lesser General Public License for more details. |
13
|
|
|
|
|
|
|
|
14
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public |
15
|
|
|
|
|
|
|
License along with this library; if not, write to the Free Software |
16
|
|
|
|
|
|
|
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
17
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
Author: lex.borisov@gmail.com (Alexander Borisov) |
19
|
|
|
|
|
|
|
*/ |
20
|
|
|
|
|
|
|
|
21
|
|
|
|
|
|
|
#include "myhtml/myhtml.h" |
22
|
|
|
|
|
|
|
|
23
|
115
|
|
|
|
|
|
void myhtml_init_marker(myhtml_t* myhtml) |
24
|
|
|
|
|
|
|
{ |
25
|
115
|
|
|
|
|
|
myhtml->marker = (myhtml_tree_node_t*)mycore_malloc(sizeof(myhtml_tree_node_t)); |
26
|
|
|
|
|
|
|
|
27
|
115
|
50
|
|
|
|
|
if(myhtml->marker) |
28
|
115
|
|
|
|
|
|
myhtml_tree_node_clean(myhtml->marker); |
29
|
115
|
|
|
|
|
|
} |
30
|
|
|
|
|
|
|
|
31
|
115
|
|
|
|
|
|
void myhtml_destroy_marker(myhtml_t* myhtml) |
32
|
|
|
|
|
|
|
{ |
33
|
115
|
50
|
|
|
|
|
if(myhtml->marker) |
34
|
115
|
|
|
|
|
|
mycore_free(myhtml->marker); |
35
|
115
|
|
|
|
|
|
} |
36
|
|
|
|
|
|
|
|
37
|
|
|
|
|
|
|
#ifndef MyCORE_BUILD_WITHOUT_THREADS |
38
|
115
|
|
|
|
|
|
mystatus_t myhtml_stream_create(myhtml_t* myhtml, mystatus_t* status, size_t count, size_t id_increase) |
39
|
|
|
|
|
|
|
{ |
40
|
115
|
100
|
|
|
|
|
if(count == 0) { |
41
|
108
|
|
|
|
|
|
myhtml->thread_stream = NULL; |
42
|
|
|
|
|
|
|
|
43
|
108
|
|
|
|
|
|
*status = MyHTML_STATUS_OK; |
44
|
108
|
|
|
|
|
|
return *status; |
45
|
|
|
|
|
|
|
} |
46
|
|
|
|
|
|
|
|
47
|
7
|
|
|
|
|
|
myhtml->thread_stream = mythread_create(); |
48
|
7
|
50
|
|
|
|
|
if(myhtml->thread_stream == NULL) |
49
|
0
|
|
|
|
|
|
*status = MyCORE_STATUS_THREAD_ERROR_MEMORY_ALLOCATION; |
50
|
|
|
|
|
|
|
|
51
|
7
|
|
|
|
|
|
*status = mythread_init(myhtml->thread_stream, MyTHREAD_TYPE_STREAM, count, id_increase); |
52
|
|
|
|
|
|
|
|
53
|
7
|
50
|
|
|
|
|
if(*status) |
54
|
0
|
|
|
|
|
|
myhtml->thread_stream = mythread_destroy(myhtml->thread_stream, NULL, NULL, true); |
55
|
|
|
|
|
|
|
|
56
|
7
|
|
|
|
|
|
return *status; |
57
|
|
|
|
|
|
|
} |
58
|
|
|
|
|
|
|
|
59
|
115
|
|
|
|
|
|
mystatus_t myhtml_batch_create(myhtml_t* myhtml, mystatus_t* status, size_t count, size_t id_increase) |
60
|
|
|
|
|
|
|
{ |
61
|
115
|
100
|
|
|
|
|
if(count == 0) { |
62
|
108
|
|
|
|
|
|
myhtml->thread_batch = NULL; |
63
|
|
|
|
|
|
|
|
64
|
108
|
|
|
|
|
|
*status = MyHTML_STATUS_OK; |
65
|
108
|
|
|
|
|
|
return *status; |
66
|
|
|
|
|
|
|
} |
67
|
|
|
|
|
|
|
|
68
|
7
|
|
|
|
|
|
myhtml->thread_batch = mythread_create(); |
69
|
7
|
50
|
|
|
|
|
if(myhtml->thread_stream == NULL) { |
70
|
0
|
|
|
|
|
|
myhtml->thread_stream = mythread_destroy(myhtml->thread_stream, NULL, NULL, true); |
71
|
0
|
|
|
|
|
|
*status = MyCORE_STATUS_THREAD_ERROR_MEMORY_ALLOCATION; |
72
|
|
|
|
|
|
|
} |
73
|
|
|
|
|
|
|
|
74
|
7
|
|
|
|
|
|
*status = mythread_init(myhtml->thread_batch, MyTHREAD_TYPE_BATCH, count, id_increase); |
75
|
|
|
|
|
|
|
|
76
|
7
|
50
|
|
|
|
|
if(*status) |
77
|
0
|
|
|
|
|
|
myhtml->thread_batch = mythread_destroy(myhtml->thread_batch , NULL, NULL, true); |
78
|
|
|
|
|
|
|
|
79
|
7
|
|
|
|
|
|
return *status; |
80
|
|
|
|
|
|
|
} |
81
|
|
|
|
|
|
|
|
82
|
115
|
|
|
|
|
|
mystatus_t myhtml_create_stream_and_batch(myhtml_t* myhtml, size_t stream_count, size_t batch_count) |
83
|
|
|
|
|
|
|
{ |
84
|
|
|
|
|
|
|
mystatus_t status; |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
/* stream */ |
87
|
115
|
50
|
|
|
|
|
if(myhtml_stream_create(myhtml, &status, stream_count, 0)) { |
88
|
0
|
|
|
|
|
|
return status; |
89
|
|
|
|
|
|
|
} |
90
|
|
|
|
|
|
|
|
91
|
|
|
|
|
|
|
/* batch */ |
92
|
115
|
50
|
|
|
|
|
if(myhtml_batch_create(myhtml, &status, batch_count, stream_count)) { |
93
|
0
|
|
|
|
|
|
myhtml->thread_stream = mythread_destroy(myhtml->thread_stream, NULL, NULL, true); |
94
|
0
|
|
|
|
|
|
return status; |
95
|
|
|
|
|
|
|
} |
96
|
|
|
|
|
|
|
|
97
|
115
|
|
|
|
|
|
return status; |
98
|
|
|
|
|
|
|
} |
99
|
|
|
|
|
|
|
#endif /* if undef MyCORE_BUILD_WITHOUT_THREADS */ |
100
|
|
|
|
|
|
|
|
101
|
115
|
|
|
|
|
|
myhtml_t * myhtml_create(void) |
102
|
|
|
|
|
|
|
{ |
103
|
115
|
|
|
|
|
|
return (myhtml_t*)mycore_calloc(1, sizeof(myhtml_t)); |
104
|
|
|
|
|
|
|
} |
105
|
|
|
|
|
|
|
|
106
|
115
|
|
|
|
|
|
mystatus_t myhtml_init(myhtml_t* myhtml, enum myhtml_options opt, size_t thread_count, size_t queue_size) |
107
|
|
|
|
|
|
|
{ |
108
|
|
|
|
|
|
|
mystatus_t status; |
109
|
|
|
|
|
|
|
|
110
|
115
|
|
|
|
|
|
myhtml->opt = opt; |
111
|
115
|
|
|
|
|
|
myhtml_init_marker(myhtml); |
112
|
|
|
|
|
|
|
|
113
|
115
|
|
|
|
|
|
status = myhtml_tokenizer_state_init(myhtml); |
114
|
115
|
50
|
|
|
|
|
if(status) |
115
|
0
|
|
|
|
|
|
return status; |
116
|
|
|
|
|
|
|
|
117
|
115
|
|
|
|
|
|
status = myhtml_rules_init(myhtml); |
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
#ifdef MyCORE_BUILD_WITHOUT_THREADS |
120
|
|
|
|
|
|
|
|
121
|
|
|
|
|
|
|
myhtml->thread_stream = NULL; |
122
|
|
|
|
|
|
|
myhtml->thread_batch = NULL; |
123
|
|
|
|
|
|
|
myhtml->thread_total = 0; |
124
|
|
|
|
|
|
|
|
125
|
|
|
|
|
|
|
#else /* if undef MyCORE_BUILD_WITHOUT_THREADS */ |
126
|
115
|
50
|
|
|
|
|
if(status) |
127
|
0
|
|
|
|
|
|
return status; |
128
|
|
|
|
|
|
|
|
129
|
115
|
50
|
|
|
|
|
if(thread_count == 0) { |
130
|
0
|
|
|
|
|
|
thread_count = 1; |
131
|
|
|
|
|
|
|
} |
132
|
|
|
|
|
|
|
|
133
|
115
|
|
|
|
|
|
switch (opt) { |
134
|
|
|
|
|
|
|
case MyHTML_OPTIONS_PARSE_MODE_SINGLE: |
135
|
108
|
50
|
|
|
|
|
if((status = myhtml_create_stream_and_batch(myhtml, 0, 0))) |
136
|
0
|
|
|
|
|
|
return status; |
137
|
|
|
|
|
|
|
|
138
|
108
|
|
|
|
|
|
break; |
139
|
|
|
|
|
|
|
|
140
|
|
|
|
|
|
|
case MyHTML_OPTIONS_PARSE_MODE_ALL_IN_ONE: |
141
|
0
|
0
|
|
|
|
|
if((status = myhtml_create_stream_and_batch(myhtml, 1, 0))) |
142
|
0
|
|
|
|
|
|
return status; |
143
|
|
|
|
|
|
|
|
144
|
0
|
|
|
|
|
|
myhtml->thread_stream->context = mythread_queue_list_create(&status); |
145
|
0
|
|
|
|
|
|
status = myhread_entry_create(myhtml->thread_stream, mythread_function_queue_stream, myhtml_parser_worker_stream, MyTHREAD_OPT_STOP); |
146
|
|
|
|
|
|
|
|
147
|
0
|
|
|
|
|
|
break; |
148
|
|
|
|
|
|
|
|
149
|
|
|
|
|
|
|
default: |
150
|
|
|
|
|
|
|
// default MyHTML_OPTIONS_PARSE_MODE_SEPARATELY |
151
|
7
|
50
|
|
|
|
|
if(thread_count < 2) |
152
|
0
|
|
|
|
|
|
thread_count = 2; |
153
|
|
|
|
|
|
|
|
154
|
7
|
50
|
|
|
|
|
if((status = myhtml_create_stream_and_batch(myhtml, 1, (thread_count - 1)))) |
155
|
0
|
|
|
|
|
|
return status; |
156
|
|
|
|
|
|
|
|
157
|
7
|
|
|
|
|
|
myhtml->thread_stream->context = mythread_queue_list_create(&status); |
158
|
7
|
|
|
|
|
|
myhtml->thread_batch->context = myhtml->thread_stream->context; |
159
|
|
|
|
|
|
|
|
160
|
7
|
|
|
|
|
|
status = myhread_entry_create(myhtml->thread_stream, mythread_function_queue_stream, myhtml_parser_stream, MyTHREAD_OPT_STOP); |
161
|
7
|
50
|
|
|
|
|
if(status) |
162
|
0
|
|
|
|
|
|
return status; |
163
|
|
|
|
|
|
|
|
164
|
14
|
100
|
|
|
|
|
for(size_t i = 0; i < myhtml->thread_batch->entries_size; i++) { |
165
|
7
|
|
|
|
|
|
status = myhread_entry_create(myhtml->thread_batch, mythread_function_queue_batch, myhtml_parser_worker, MyTHREAD_OPT_STOP); |
166
|
|
|
|
|
|
|
|
167
|
7
|
50
|
|
|
|
|
if(status) |
168
|
0
|
|
|
|
|
|
return status; |
169
|
|
|
|
|
|
|
} |
170
|
|
|
|
|
|
|
|
171
|
7
|
|
|
|
|
|
break; |
172
|
|
|
|
|
|
|
} |
173
|
|
|
|
|
|
|
|
174
|
115
|
|
|
|
|
|
myhtml->thread_total = thread_count; |
175
|
|
|
|
|
|
|
|
176
|
115
|
|
|
|
|
|
myhtml->thread_list[0] = myhtml->thread_stream; |
177
|
115
|
|
|
|
|
|
myhtml->thread_list[1] = myhtml->thread_batch; |
178
|
115
|
|
|
|
|
|
myhtml->thread_list[2] = NULL; |
179
|
|
|
|
|
|
|
|
180
|
|
|
|
|
|
|
#endif /* if undef MyCORE_BUILD_WITHOUT_THREADS */ |
181
|
|
|
|
|
|
|
|
182
|
115
|
50
|
|
|
|
|
if(status) |
183
|
0
|
|
|
|
|
|
return status; |
184
|
|
|
|
|
|
|
|
185
|
115
|
|
|
|
|
|
myhtml_clean(myhtml); |
186
|
|
|
|
|
|
|
|
187
|
115
|
|
|
|
|
|
return status; |
188
|
|
|
|
|
|
|
} |
189
|
|
|
|
|
|
|
|
190
|
115
|
|
|
|
|
|
void myhtml_clean(myhtml_t* myhtml) |
191
|
|
|
|
|
|
|
{ |
192
|
|
|
|
|
|
|
/* some code */ |
193
|
115
|
|
|
|
|
|
} |
194
|
|
|
|
|
|
|
|
195
|
115
|
|
|
|
|
|
myhtml_t* myhtml_destroy(myhtml_t* myhtml) |
196
|
|
|
|
|
|
|
{ |
197
|
115
|
50
|
|
|
|
|
if(myhtml == NULL) |
198
|
0
|
|
|
|
|
|
return NULL; |
199
|
|
|
|
|
|
|
|
200
|
115
|
|
|
|
|
|
myhtml_destroy_marker(myhtml); |
201
|
|
|
|
|
|
|
|
202
|
|
|
|
|
|
|
#ifndef MyCORE_BUILD_WITHOUT_THREADS |
203
|
115
|
100
|
|
|
|
|
if(myhtml->thread_stream) { |
204
|
7
|
|
|
|
|
|
mythread_queue_list_t* queue_list = myhtml->thread_stream->context; |
205
|
|
|
|
|
|
|
|
206
|
7
|
50
|
|
|
|
|
if(queue_list) |
207
|
7
|
|
|
|
|
|
mythread_queue_list_wait_for_done(myhtml->thread_stream, queue_list); |
208
|
|
|
|
|
|
|
|
209
|
7
|
|
|
|
|
|
myhtml->thread_stream = mythread_destroy(myhtml->thread_stream, mythread_callback_quit, NULL, true); |
210
|
|
|
|
|
|
|
|
211
|
7
|
50
|
|
|
|
|
if(myhtml->thread_batch) |
212
|
7
|
|
|
|
|
|
myhtml->thread_batch = mythread_destroy(myhtml->thread_batch, mythread_callback_quit, NULL, true); |
213
|
|
|
|
|
|
|
|
214
|
7
|
50
|
|
|
|
|
if(queue_list) |
215
|
7
|
|
|
|
|
|
mythread_queue_list_destroy(queue_list); |
216
|
|
|
|
|
|
|
} |
217
|
|
|
|
|
|
|
#endif /* if undef MyCORE_BUILD_WITHOUT_THREADS */ |
218
|
|
|
|
|
|
|
|
219
|
115
|
|
|
|
|
|
myhtml_tokenizer_state_destroy(myhtml); |
220
|
|
|
|
|
|
|
|
221
|
115
|
50
|
|
|
|
|
if(myhtml->insertion_func) |
222
|
115
|
|
|
|
|
|
mycore_free(myhtml->insertion_func); |
223
|
|
|
|
|
|
|
|
224
|
115
|
|
|
|
|
|
mycore_free(myhtml); |
225
|
|
|
|
|
|
|
|
226
|
115
|
|
|
|
|
|
return NULL; |
227
|
|
|
|
|
|
|
} |
228
|
|
|
|
|
|
|
|
229
|
126
|
|
|
|
|
|
mystatus_t myhtml_parse(myhtml_tree_t* tree, myencoding_t encoding, const char* html, size_t html_size) |
230
|
|
|
|
|
|
|
{ |
231
|
126
|
50
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
232
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
233
|
|
|
|
|
|
|
} |
234
|
|
|
|
|
|
|
|
235
|
126
|
|
|
|
|
|
myhtml_encoding_set(tree, encoding); |
236
|
126
|
|
|
|
|
|
mystatus_t status = myhtml_tokenizer_begin(tree, html, html_size); |
237
|
|
|
|
|
|
|
|
238
|
126
|
50
|
|
|
|
|
if(status) |
239
|
0
|
|
|
|
|
|
return status; |
240
|
|
|
|
|
|
|
|
241
|
126
|
|
|
|
|
|
return myhtml_tokenizer_end(tree); |
242
|
|
|
|
|
|
|
} |
243
|
|
|
|
|
|
|
|
244
|
17
|
|
|
|
|
|
mystatus_t myhtml_parse_fragment(myhtml_tree_t* tree, myencoding_t encoding, const char* html, size_t html_size, myhtml_tag_id_t tag_id, enum myhtml_namespace ns) |
245
|
|
|
|
|
|
|
{ |
246
|
17
|
50
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
247
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
248
|
|
|
|
|
|
|
} |
249
|
|
|
|
|
|
|
|
250
|
17
|
50
|
|
|
|
|
if(tag_id == 0) |
251
|
0
|
|
|
|
|
|
tag_id = MyHTML_TAG_DIV; |
252
|
|
|
|
|
|
|
|
253
|
17
|
50
|
|
|
|
|
if(ns == 0) |
254
|
0
|
|
|
|
|
|
ns = MyHTML_NAMESPACE_HTML; |
255
|
|
|
|
|
|
|
|
256
|
17
|
50
|
|
|
|
|
if(myhtml_tokenizer_fragment_init(tree, tag_id, ns) == NULL) |
257
|
0
|
|
|
|
|
|
return MyHTML_STATUS_TOKENIZER_ERROR_FRAGMENT_INIT; |
258
|
|
|
|
|
|
|
|
259
|
17
|
|
|
|
|
|
myhtml_encoding_set(tree, encoding); |
260
|
17
|
|
|
|
|
|
mystatus_t status = myhtml_tokenizer_begin(tree, html, html_size); |
261
|
|
|
|
|
|
|
|
262
|
17
|
50
|
|
|
|
|
if(status) |
263
|
0
|
|
|
|
|
|
return status; |
264
|
|
|
|
|
|
|
|
265
|
17
|
|
|
|
|
|
return myhtml_tokenizer_end(tree); |
266
|
|
|
|
|
|
|
} |
267
|
|
|
|
|
|
|
|
268
|
0
|
|
|
|
|
|
mystatus_t myhtml_parse_single(myhtml_tree_t* tree, myencoding_t encoding, const char* html, size_t html_size) |
269
|
|
|
|
|
|
|
{ |
270
|
0
|
0
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
271
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
272
|
|
|
|
|
|
|
} |
273
|
|
|
|
|
|
|
|
274
|
0
|
|
|
|
|
|
tree->flags |= MyHTML_TREE_FLAGS_SINGLE_MODE; |
275
|
|
|
|
|
|
|
|
276
|
0
|
|
|
|
|
|
myhtml_encoding_set(tree, encoding); |
277
|
|
|
|
|
|
|
|
278
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_tokenizer_begin(tree, html, html_size); |
279
|
|
|
|
|
|
|
|
280
|
0
|
0
|
|
|
|
|
if(status) |
281
|
0
|
|
|
|
|
|
return status; |
282
|
|
|
|
|
|
|
|
283
|
0
|
|
|
|
|
|
return myhtml_tokenizer_end(tree); |
284
|
|
|
|
|
|
|
} |
285
|
|
|
|
|
|
|
|
286
|
0
|
|
|
|
|
|
mystatus_t myhtml_parse_fragment_single(myhtml_tree_t* tree, myencoding_t encoding, const char* html, size_t html_size, myhtml_tag_id_t tag_id, enum myhtml_namespace ns) |
287
|
|
|
|
|
|
|
{ |
288
|
0
|
0
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
289
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
290
|
|
|
|
|
|
|
} |
291
|
|
|
|
|
|
|
|
292
|
0
|
0
|
|
|
|
|
if(tag_id == 0) |
293
|
0
|
|
|
|
|
|
tag_id = MyHTML_TAG_DIV; |
294
|
|
|
|
|
|
|
|
295
|
0
|
0
|
|
|
|
|
if(ns == 0) |
296
|
0
|
|
|
|
|
|
ns = MyHTML_NAMESPACE_HTML; |
297
|
|
|
|
|
|
|
|
298
|
0
|
|
|
|
|
|
tree->flags |= MyHTML_TREE_FLAGS_SINGLE_MODE; |
299
|
|
|
|
|
|
|
|
300
|
0
|
0
|
|
|
|
|
if(myhtml_tokenizer_fragment_init(tree, tag_id, ns) == NULL) |
301
|
0
|
|
|
|
|
|
return MyHTML_STATUS_TOKENIZER_ERROR_FRAGMENT_INIT; |
302
|
|
|
|
|
|
|
|
303
|
0
|
|
|
|
|
|
myhtml_encoding_set(tree, encoding); |
304
|
|
|
|
|
|
|
|
305
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_tokenizer_begin(tree, html, html_size); |
306
|
|
|
|
|
|
|
|
307
|
0
|
0
|
|
|
|
|
if(status) |
308
|
0
|
|
|
|
|
|
return status; |
309
|
|
|
|
|
|
|
|
310
|
0
|
|
|
|
|
|
return myhtml_tokenizer_end(tree); |
311
|
|
|
|
|
|
|
} |
312
|
|
|
|
|
|
|
|
313
|
5
|
|
|
|
|
|
mystatus_t myhtml_parse_chunk(myhtml_tree_t* tree, const char* html, size_t html_size) |
314
|
|
|
|
|
|
|
{ |
315
|
5
|
50
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
316
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
317
|
|
|
|
|
|
|
} |
318
|
|
|
|
|
|
|
|
319
|
5
|
|
|
|
|
|
return myhtml_tokenizer_chunk(tree, html, html_size); |
320
|
|
|
|
|
|
|
} |
321
|
|
|
|
|
|
|
|
322
|
0
|
|
|
|
|
|
mystatus_t myhtml_parse_chunk_fragment(myhtml_tree_t* tree, const char* html, size_t html_size, myhtml_tag_id_t tag_id, enum myhtml_namespace ns) |
323
|
|
|
|
|
|
|
{ |
324
|
0
|
0
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_PARSE_END) { |
325
|
0
|
|
|
|
|
|
myhtml_tree_clean(tree); |
326
|
|
|
|
|
|
|
} |
327
|
|
|
|
|
|
|
|
328
|
0
|
0
|
|
|
|
|
if(tag_id == 0) |
329
|
0
|
|
|
|
|
|
tag_id = MyHTML_TAG_DIV; |
330
|
|
|
|
|
|
|
|
331
|
0
|
0
|
|
|
|
|
if(ns == 0) |
332
|
0
|
|
|
|
|
|
ns = MyHTML_NAMESPACE_HTML; |
333
|
|
|
|
|
|
|
|
334
|
0
|
0
|
|
|
|
|
if(myhtml_tokenizer_fragment_init(tree, tag_id, ns) == NULL) |
335
|
0
|
|
|
|
|
|
return MyHTML_STATUS_TOKENIZER_ERROR_FRAGMENT_INIT; |
336
|
|
|
|
|
|
|
|
337
|
0
|
|
|
|
|
|
return myhtml_tokenizer_chunk(tree, html, html_size); |
338
|
|
|
|
|
|
|
} |
339
|
|
|
|
|
|
|
|
340
|
0
|
|
|
|
|
|
mystatus_t myhtml_parse_chunk_single(myhtml_tree_t* tree, const char* html, size_t html_size) |
341
|
|
|
|
|
|
|
{ |
342
|
0
|
0
|
|
|
|
|
if((tree->flags & MyHTML_TREE_FLAGS_SINGLE_MODE) == 0) |
343
|
0
|
|
|
|
|
|
tree->flags |= MyHTML_TREE_FLAGS_SINGLE_MODE; |
344
|
|
|
|
|
|
|
|
345
|
0
|
|
|
|
|
|
return myhtml_parse_chunk(tree, html, html_size); |
346
|
|
|
|
|
|
|
} |
347
|
|
|
|
|
|
|
|
348
|
0
|
|
|
|
|
|
mystatus_t myhtml_parse_chunk_fragment_single(myhtml_tree_t* tree, const char* html, size_t html_size, myhtml_tag_id_t tag_id, enum myhtml_namespace ns) |
349
|
|
|
|
|
|
|
{ |
350
|
0
|
0
|
|
|
|
|
if((tree->flags & MyHTML_TREE_FLAGS_SINGLE_MODE) == 0) |
351
|
0
|
|
|
|
|
|
tree->flags |= MyHTML_TREE_FLAGS_SINGLE_MODE; |
352
|
|
|
|
|
|
|
|
353
|
0
|
|
|
|
|
|
return myhtml_parse_chunk_fragment(tree, html, html_size, tag_id, ns); |
354
|
|
|
|
|
|
|
} |
355
|
|
|
|
|
|
|
|
356
|
2
|
|
|
|
|
|
mystatus_t myhtml_parse_chunk_end(myhtml_tree_t* tree) |
357
|
|
|
|
|
|
|
{ |
358
|
2
|
|
|
|
|
|
return myhtml_tokenizer_end(tree); |
359
|
|
|
|
|
|
|
} |
360
|
|
|
|
|
|
|
|
361
|
147
|
|
|
|
|
|
void myhtml_encoding_set(myhtml_tree_t* tree, myencoding_t encoding) |
362
|
|
|
|
|
|
|
{ |
363
|
147
|
50
|
|
|
|
|
if(encoding >= MyENCODING_LAST_ENTRY) |
364
|
0
|
|
|
|
|
|
return; |
365
|
|
|
|
|
|
|
|
366
|
147
|
|
|
|
|
|
tree->encoding_usereq = encoding; |
367
|
147
|
|
|
|
|
|
tree->encoding = encoding; |
368
|
|
|
|
|
|
|
} |
369
|
|
|
|
|
|
|
|
370
|
0
|
|
|
|
|
|
myencoding_t myhtml_encoding_get(myhtml_tree_t* tree) |
371
|
|
|
|
|
|
|
{ |
372
|
0
|
|
|
|
|
|
return tree->encoding; |
373
|
|
|
|
|
|
|
} |
374
|
|
|
|
|
|
|
|
375
|
|
|
|
|
|
|
/* |
376
|
|
|
|
|
|
|
* Nodes |
377
|
|
|
|
|
|
|
*/ |
378
|
|
|
|
|
|
|
|
379
|
64
|
|
|
|
|
|
mystatus_t myhtml_get_nodes_by_tag_id_in_scope_find_recursion(myhtml_tree_node_t *node, myhtml_collection_t *collection, myhtml_tag_id_t tag_id) |
380
|
|
|
|
|
|
|
{ |
381
|
544
|
100
|
|
|
|
|
while(node) { |
382
|
480
|
100
|
|
|
|
|
if(node->tag_id == tag_id) { |
383
|
64
|
|
|
|
|
|
collection->list[ collection->length ] = node; |
384
|
64
|
|
|
|
|
|
collection->length++; |
385
|
|
|
|
|
|
|
|
386
|
64
|
50
|
|
|
|
|
if(collection->length >= collection->size) |
387
|
|
|
|
|
|
|
{ |
388
|
0
|
|
|
|
|
|
mystatus_t mystatus = myhtml_collection_check_size(collection, 1024, 0); |
389
|
|
|
|
|
|
|
|
390
|
0
|
0
|
|
|
|
|
if(mystatus != MyHTML_STATUS_OK) |
391
|
0
|
|
|
|
|
|
return mystatus; |
392
|
|
|
|
|
|
|
} |
393
|
|
|
|
|
|
|
} |
394
|
|
|
|
|
|
|
|
395
|
480
|
100
|
|
|
|
|
if(node->child) |
396
|
48
|
|
|
|
|
|
myhtml_get_nodes_by_tag_id_in_scope_find_recursion(node->child, collection, tag_id); |
397
|
|
|
|
|
|
|
|
398
|
480
|
|
|
|
|
|
node = node->next; |
399
|
|
|
|
|
|
|
} |
400
|
|
|
|
|
|
|
|
401
|
64
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
402
|
|
|
|
|
|
|
} |
403
|
|
|
|
|
|
|
|
404
|
16
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_tag_id_in_scope(myhtml_tree_t* tree, myhtml_collection_t *collection, myhtml_tree_node_t *node, myhtml_tag_id_t tag_id, mystatus_t *status) |
405
|
|
|
|
|
|
|
{ |
406
|
16
|
50
|
|
|
|
|
if(node == NULL) |
407
|
0
|
|
|
|
|
|
return NULL; |
408
|
|
|
|
|
|
|
|
409
|
16
|
|
|
|
|
|
mystatus_t mystatus = MyHTML_STATUS_OK; |
410
|
|
|
|
|
|
|
|
411
|
16
|
50
|
|
|
|
|
if(collection == NULL) { |
412
|
16
|
|
|
|
|
|
collection = myhtml_collection_create(1024, &mystatus); |
413
|
|
|
|
|
|
|
} |
414
|
|
|
|
|
|
|
|
415
|
16
|
50
|
|
|
|
|
if(mystatus) { |
416
|
0
|
0
|
|
|
|
|
if(status) |
417
|
0
|
|
|
|
|
|
*status = mystatus; |
418
|
|
|
|
|
|
|
|
419
|
0
|
|
|
|
|
|
return collection; |
420
|
|
|
|
|
|
|
} |
421
|
|
|
|
|
|
|
|
422
|
16
|
50
|
|
|
|
|
if(node->child) |
423
|
16
|
|
|
|
|
|
mystatus = myhtml_get_nodes_by_tag_id_in_scope_find_recursion(node->child, collection, tag_id); |
424
|
|
|
|
|
|
|
|
425
|
16
|
|
|
|
|
|
collection->list[collection->length] = NULL; |
426
|
|
|
|
|
|
|
|
427
|
16
|
50
|
|
|
|
|
if(status) |
428
|
0
|
|
|
|
|
|
*status = mystatus; |
429
|
|
|
|
|
|
|
|
430
|
16
|
|
|
|
|
|
return collection; |
431
|
|
|
|
|
|
|
} |
432
|
|
|
|
|
|
|
|
433
|
24
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_name_in_scope(myhtml_tree_t* tree, myhtml_collection_t *collection, myhtml_tree_node_t *node, const char* html, size_t length, mystatus_t *status) |
434
|
|
|
|
|
|
|
{ |
435
|
24
|
|
|
|
|
|
const myhtml_tag_context_t *tag_ctx = myhtml_tag_get_by_name(tree->tags, html, length); |
436
|
24
|
100
|
|
|
|
|
if(tag_ctx == NULL) { |
437
|
8
|
|
|
|
|
|
return NULL; |
438
|
|
|
|
|
|
|
} |
439
|
16
|
|
|
|
|
|
return myhtml_get_nodes_by_tag_id_in_scope(tree, collection, node, tag_ctx->id, status); |
440
|
|
|
|
|
|
|
} |
441
|
|
|
|
|
|
|
|
442
|
0
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_tag_id(myhtml_tree_t* tree, myhtml_collection_t *collection, myhtml_tag_id_t tag_id, mystatus_t *status) |
443
|
|
|
|
|
|
|
{ |
444
|
0
|
0
|
|
|
|
|
if(collection == NULL) { |
445
|
0
|
|
|
|
|
|
collection = myhtml_collection_create(1024, NULL); |
446
|
|
|
|
|
|
|
|
447
|
0
|
0
|
|
|
|
|
if(collection == NULL) |
448
|
0
|
|
|
|
|
|
return NULL; |
449
|
|
|
|
|
|
|
} |
450
|
|
|
|
|
|
|
|
451
|
0
|
|
|
|
|
|
myhtml_tree_node_t *node = tree->node_html; |
452
|
|
|
|
|
|
|
|
453
|
0
|
0
|
|
|
|
|
while(node) |
454
|
|
|
|
|
|
|
{ |
455
|
0
|
0
|
|
|
|
|
if(node->tag_id == tag_id) |
456
|
|
|
|
|
|
|
{ |
457
|
0
|
0
|
|
|
|
|
if(myhtml_collection_check_size(collection, 1, 1024) == MyHTML_STATUS_OK) { |
458
|
0
|
|
|
|
|
|
collection->list[ collection->length ] = node; |
459
|
0
|
|
|
|
|
|
collection->length++; |
460
|
|
|
|
|
|
|
} |
461
|
|
|
|
|
|
|
else { |
462
|
0
|
0
|
|
|
|
|
if(status) |
463
|
0
|
|
|
|
|
|
*status = MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
464
|
|
|
|
|
|
|
|
465
|
0
|
|
|
|
|
|
return collection; |
466
|
|
|
|
|
|
|
} |
467
|
|
|
|
|
|
|
} |
468
|
|
|
|
|
|
|
|
469
|
0
|
0
|
|
|
|
|
if(node->child) |
470
|
0
|
|
|
|
|
|
node = node->child; |
471
|
|
|
|
|
|
|
else { |
472
|
0
|
0
|
|
|
|
|
while(node != tree->node_html && node->next == NULL) |
|
|
0
|
|
|
|
|
|
473
|
0
|
|
|
|
|
|
node = node->parent; |
474
|
|
|
|
|
|
|
|
475
|
0
|
0
|
|
|
|
|
if(node == tree->node_html) |
476
|
0
|
|
|
|
|
|
break; |
477
|
|
|
|
|
|
|
|
478
|
0
|
|
|
|
|
|
node = node->next; |
479
|
|
|
|
|
|
|
} |
480
|
|
|
|
|
|
|
} |
481
|
|
|
|
|
|
|
|
482
|
0
|
0
|
|
|
|
|
if(myhtml_collection_check_size(collection, 1, 1024) == MyHTML_STATUS_OK) { |
483
|
0
|
|
|
|
|
|
collection->list[ collection->length ] = NULL; |
484
|
|
|
|
|
|
|
} |
485
|
0
|
0
|
|
|
|
|
else if(status) { |
486
|
0
|
|
|
|
|
|
*status = MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
487
|
|
|
|
|
|
|
} |
488
|
|
|
|
|
|
|
|
489
|
0
|
|
|
|
|
|
return collection; |
490
|
|
|
|
|
|
|
} |
491
|
|
|
|
|
|
|
|
492
|
0
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_name(myhtml_tree_t* tree, myhtml_collection_t *collection, const char* html, size_t length, mystatus_t *status) |
493
|
|
|
|
|
|
|
{ |
494
|
0
|
|
|
|
|
|
const myhtml_tag_context_t *tag_ctx = myhtml_tag_get_by_name(tree->tags, html, length); |
495
|
|
|
|
|
|
|
|
496
|
0
|
0
|
|
|
|
|
if(tag_ctx == NULL) |
497
|
0
|
|
|
|
|
|
return NULL; |
498
|
|
|
|
|
|
|
|
499
|
0
|
|
|
|
|
|
return myhtml_get_nodes_by_tag_id(tree, collection, tag_ctx->id, status); |
500
|
|
|
|
|
|
|
} |
501
|
|
|
|
|
|
|
|
502
|
|
|
|
|
|
|
/* |
503
|
|
|
|
|
|
|
* Manipulate Nodes |
504
|
|
|
|
|
|
|
*/ |
505
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_first(myhtml_tree_t* tree) |
506
|
|
|
|
|
|
|
{ |
507
|
0
|
0
|
|
|
|
|
if(tree->fragment) { |
508
|
|
|
|
|
|
|
// document -> html -> need element |
509
|
0
|
0
|
|
|
|
|
if(tree->document && tree->document->child) |
|
|
0
|
|
|
|
|
|
510
|
0
|
|
|
|
|
|
return tree->document->child->child; |
511
|
|
|
|
|
|
|
} |
512
|
0
|
0
|
|
|
|
|
else if(tree->document) { |
513
|
|
|
|
|
|
|
// document -> html |
514
|
0
|
|
|
|
|
|
return tree->document->child; |
515
|
|
|
|
|
|
|
} |
516
|
|
|
|
|
|
|
|
517
|
0
|
|
|
|
|
|
return NULL; |
518
|
|
|
|
|
|
|
} |
519
|
|
|
|
|
|
|
|
520
|
1117
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_next(myhtml_tree_node_t *node) |
521
|
|
|
|
|
|
|
{ |
522
|
1117
|
|
|
|
|
|
return node->next; |
523
|
|
|
|
|
|
|
} |
524
|
|
|
|
|
|
|
|
525
|
60
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_prev(myhtml_tree_node_t *node) |
526
|
|
|
|
|
|
|
{ |
527
|
60
|
|
|
|
|
|
return node->prev; |
528
|
|
|
|
|
|
|
} |
529
|
|
|
|
|
|
|
|
530
|
1336
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_parent(myhtml_tree_node_t *node) |
531
|
|
|
|
|
|
|
{ |
532
|
1336
|
|
|
|
|
|
return node->parent; |
533
|
|
|
|
|
|
|
} |
534
|
|
|
|
|
|
|
|
535
|
772
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_child(myhtml_tree_node_t *node) |
536
|
|
|
|
|
|
|
{ |
537
|
772
|
|
|
|
|
|
return node->child; |
538
|
|
|
|
|
|
|
} |
539
|
|
|
|
|
|
|
|
540
|
20
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_last_child(myhtml_tree_node_t *node) |
541
|
|
|
|
|
|
|
{ |
542
|
20
|
|
|
|
|
|
return node->last_child; |
543
|
|
|
|
|
|
|
} |
544
|
|
|
|
|
|
|
|
545
|
61
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_create(myhtml_tree_t* tree, myhtml_tag_id_t tag_id, enum myhtml_namespace ns) |
546
|
|
|
|
|
|
|
{ |
547
|
61
|
|
|
|
|
|
myhtml_tree_node_t *node = myhtml_tree_node_create(tree); |
548
|
|
|
|
|
|
|
|
549
|
61
|
|
|
|
|
|
node->tag_id = tag_id; |
550
|
61
|
|
|
|
|
|
node->ns = ns; |
551
|
|
|
|
|
|
|
|
552
|
61
|
|
|
|
|
|
return node; |
553
|
|
|
|
|
|
|
} |
554
|
|
|
|
|
|
|
|
555
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_remove(myhtml_tree_node_t *node) |
556
|
|
|
|
|
|
|
{ |
557
|
0
|
|
|
|
|
|
return myhtml_tree_node_remove(node); |
558
|
|
|
|
|
|
|
} |
559
|
|
|
|
|
|
|
|
560
|
0
|
|
|
|
|
|
void myhtml_node_delete(myhtml_tree_node_t *node) |
561
|
|
|
|
|
|
|
{ |
562
|
0
|
|
|
|
|
|
myhtml_tree_node_delete(node); |
563
|
0
|
|
|
|
|
|
} |
564
|
|
|
|
|
|
|
|
565
|
0
|
|
|
|
|
|
void myhtml_node_delete_recursive(myhtml_tree_node_t *node) |
566
|
|
|
|
|
|
|
{ |
567
|
0
|
|
|
|
|
|
myhtml_tree_node_delete_recursive(node); |
568
|
0
|
|
|
|
|
|
} |
569
|
|
|
|
|
|
|
|
570
|
0
|
|
|
|
|
|
void myhtml_node_free(myhtml_tree_node_t *node) |
571
|
|
|
|
|
|
|
{ |
572
|
0
|
|
|
|
|
|
myhtml_tree_node_free(node); |
573
|
0
|
|
|
|
|
|
} |
574
|
|
|
|
|
|
|
|
575
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_insert_before(myhtml_tree_node_t *target, myhtml_tree_node_t *node) |
576
|
|
|
|
|
|
|
{ |
577
|
0
|
0
|
|
|
|
|
if(target == NULL || node == NULL) |
|
|
0
|
|
|
|
|
|
578
|
0
|
|
|
|
|
|
return NULL; |
579
|
|
|
|
|
|
|
|
580
|
0
|
|
|
|
|
|
myhtml_tree_node_insert_before(target, node); |
581
|
|
|
|
|
|
|
|
582
|
0
|
|
|
|
|
|
return node; |
583
|
|
|
|
|
|
|
} |
584
|
|
|
|
|
|
|
|
585
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_insert_after(myhtml_tree_node_t *target, myhtml_tree_node_t *node) |
586
|
|
|
|
|
|
|
{ |
587
|
0
|
0
|
|
|
|
|
if(target == NULL || node == NULL) |
|
|
0
|
|
|
|
|
|
588
|
0
|
|
|
|
|
|
return NULL; |
589
|
|
|
|
|
|
|
|
590
|
0
|
|
|
|
|
|
myhtml_tree_node_insert_after(target, node); |
591
|
|
|
|
|
|
|
|
592
|
0
|
|
|
|
|
|
return node; |
593
|
|
|
|
|
|
|
} |
594
|
|
|
|
|
|
|
|
595
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_append_child(myhtml_tree_node_t *target, myhtml_tree_node_t *node) |
596
|
|
|
|
|
|
|
{ |
597
|
0
|
0
|
|
|
|
|
if(target == NULL || node == NULL) |
|
|
0
|
|
|
|
|
|
598
|
0
|
|
|
|
|
|
return NULL; |
599
|
|
|
|
|
|
|
|
600
|
0
|
|
|
|
|
|
myhtml_tree_node_add_child(target, node); |
601
|
|
|
|
|
|
|
|
602
|
0
|
|
|
|
|
|
return node; |
603
|
|
|
|
|
|
|
} |
604
|
|
|
|
|
|
|
|
605
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_insert_to_appropriate_place(myhtml_tree_node_t *target, myhtml_tree_node_t *node) |
606
|
|
|
|
|
|
|
{ |
607
|
0
|
0
|
|
|
|
|
if(target == NULL || node == NULL) |
|
|
0
|
|
|
|
|
|
608
|
0
|
|
|
|
|
|
return NULL; |
609
|
|
|
|
|
|
|
|
610
|
|
|
|
|
|
|
enum myhtml_tree_insertion_mode mode; |
611
|
|
|
|
|
|
|
|
612
|
0
|
|
|
|
|
|
target->tree->foster_parenting = true; |
613
|
0
|
|
|
|
|
|
target = myhtml_tree_appropriate_place_inserting_in_tree(target, &mode); |
614
|
0
|
|
|
|
|
|
target->tree->foster_parenting = false; |
615
|
|
|
|
|
|
|
|
616
|
0
|
|
|
|
|
|
myhtml_tree_node_insert_by_mode(target, node, mode); |
617
|
|
|
|
|
|
|
|
618
|
0
|
|
|
|
|
|
return node; |
619
|
|
|
|
|
|
|
} |
620
|
|
|
|
|
|
|
|
621
|
21
|
|
|
|
|
|
mycore_string_t * myhtml_node_text_set(myhtml_tree_node_t *node, const char* text, size_t length, myencoding_t encoding) |
622
|
|
|
|
|
|
|
{ |
623
|
21
|
50
|
|
|
|
|
if(node == NULL) |
624
|
0
|
|
|
|
|
|
return NULL; |
625
|
|
|
|
|
|
|
|
626
|
21
|
50
|
|
|
|
|
if(encoding >= MyENCODING_LAST_ENTRY) |
627
|
0
|
|
|
|
|
|
return NULL; |
628
|
|
|
|
|
|
|
|
629
|
21
|
|
|
|
|
|
myhtml_tree_t* tree = node->tree; |
630
|
|
|
|
|
|
|
|
631
|
21
|
50
|
|
|
|
|
if(node->token == NULL) { |
632
|
21
|
|
|
|
|
|
node->token = myhtml_token_node_create(tree->token, tree->mcasync_rules_token_id); |
633
|
|
|
|
|
|
|
|
634
|
21
|
50
|
|
|
|
|
if(node->token == NULL) |
635
|
0
|
|
|
|
|
|
return NULL; |
636
|
|
|
|
|
|
|
|
637
|
21
|
|
|
|
|
|
node->token->type |= MyHTML_TOKEN_TYPE_DONE; |
638
|
|
|
|
|
|
|
} |
639
|
|
|
|
|
|
|
|
640
|
21
|
50
|
|
|
|
|
if(node->token->str.data == NULL) { |
641
|
21
|
|
|
|
|
|
mycore_string_init(tree->mchar, tree->mchar_node_id, &node->token->str, (length + 2)); |
642
|
|
|
|
|
|
|
} |
643
|
|
|
|
|
|
|
else { |
644
|
0
|
0
|
|
|
|
|
if(node->token->str.size < length) { |
645
|
0
|
|
|
|
|
|
mchar_async_free(tree->mchar, node->token->str.node_idx, node->token->str.data); |
646
|
0
|
|
|
|
|
|
mycore_string_init(tree->mchar, tree->mchar_node_id, &node->token->str, length); |
647
|
|
|
|
|
|
|
} |
648
|
|
|
|
|
|
|
else |
649
|
0
|
|
|
|
|
|
node->token->str.length = 0; |
650
|
|
|
|
|
|
|
} |
651
|
|
|
|
|
|
|
|
652
|
21
|
50
|
|
|
|
|
if(encoding != MyENCODING_UTF_8) { |
653
|
0
|
|
|
|
|
|
myencoding_string_append(&node->token->str, text, length, encoding); |
654
|
|
|
|
|
|
|
} |
655
|
|
|
|
|
|
|
else { |
656
|
21
|
|
|
|
|
|
mycore_string_append(&node->token->str, text, length); |
657
|
|
|
|
|
|
|
} |
658
|
|
|
|
|
|
|
|
659
|
21
|
|
|
|
|
|
node->token->raw_begin = 0; |
660
|
21
|
|
|
|
|
|
node->token->raw_length = 0; |
661
|
|
|
|
|
|
|
|
662
|
21
|
|
|
|
|
|
return &node->token->str; |
663
|
|
|
|
|
|
|
} |
664
|
|
|
|
|
|
|
|
665
|
0
|
|
|
|
|
|
mycore_string_t * myhtml_node_text_set_with_charef(myhtml_tree_node_t *node, const char* text, size_t length, myencoding_t encoding) |
666
|
|
|
|
|
|
|
{ |
667
|
0
|
0
|
|
|
|
|
if(node == NULL) |
668
|
0
|
|
|
|
|
|
return NULL; |
669
|
|
|
|
|
|
|
|
670
|
0
|
0
|
|
|
|
|
if(encoding >= MyENCODING_LAST_ENTRY) |
671
|
0
|
|
|
|
|
|
return NULL; |
672
|
|
|
|
|
|
|
|
673
|
0
|
|
|
|
|
|
myhtml_tree_t* tree = node->tree; |
674
|
|
|
|
|
|
|
|
675
|
0
|
0
|
|
|
|
|
if(node->token == NULL) { |
676
|
0
|
|
|
|
|
|
node->token = myhtml_token_node_create(tree->token, tree->mcasync_rules_token_id); |
677
|
|
|
|
|
|
|
|
678
|
0
|
0
|
|
|
|
|
if(node->token == NULL) |
679
|
0
|
|
|
|
|
|
return NULL; |
680
|
|
|
|
|
|
|
|
681
|
0
|
|
|
|
|
|
node->token->type |= MyHTML_TOKEN_TYPE_DONE; |
682
|
|
|
|
|
|
|
} |
683
|
|
|
|
|
|
|
|
684
|
0
|
0
|
|
|
|
|
if(node->token->str.data == NULL) { |
685
|
0
|
|
|
|
|
|
mycore_string_init(tree->mchar, tree->mchar_node_id, &node->token->str, (length + 2)); |
686
|
|
|
|
|
|
|
} |
687
|
|
|
|
|
|
|
else { |
688
|
0
|
0
|
|
|
|
|
if(node->token->str.size < length) { |
689
|
0
|
|
|
|
|
|
mchar_async_free(tree->mchar, node->token->str.node_idx, node->token->str.data); |
690
|
0
|
|
|
|
|
|
mycore_string_init(tree->mchar, tree->mchar_node_id, &node->token->str, length); |
691
|
|
|
|
|
|
|
} |
692
|
|
|
|
|
|
|
else |
693
|
0
|
|
|
|
|
|
node->token->str.length = 0; |
694
|
|
|
|
|
|
|
} |
695
|
|
|
|
|
|
|
|
696
|
|
|
|
|
|
|
myhtml_data_process_entry_t proc_entry; |
697
|
0
|
|
|
|
|
|
myhtml_data_process_entry_clean(&proc_entry); |
698
|
|
|
|
|
|
|
|
699
|
0
|
|
|
|
|
|
proc_entry.encoding = encoding; |
700
|
0
|
|
|
|
|
|
myencoding_result_clean(&proc_entry.res); |
701
|
|
|
|
|
|
|
|
702
|
0
|
|
|
|
|
|
myhtml_data_process(&proc_entry, &node->token->str, text, length); |
703
|
0
|
|
|
|
|
|
myhtml_data_process_end(&proc_entry, &node->token->str); |
704
|
|
|
|
|
|
|
|
705
|
0
|
|
|
|
|
|
node->token->raw_begin = 0; |
706
|
0
|
|
|
|
|
|
node->token->raw_length = 0; |
707
|
|
|
|
|
|
|
|
708
|
0
|
|
|
|
|
|
return &node->token->str; |
709
|
|
|
|
|
|
|
} |
710
|
|
|
|
|
|
|
|
711
|
0
|
|
|
|
|
|
myhtml_token_node_t* myhtml_node_token(myhtml_tree_node_t *node) |
712
|
|
|
|
|
|
|
{ |
713
|
0
|
|
|
|
|
|
return node->token; |
714
|
|
|
|
|
|
|
} |
715
|
|
|
|
|
|
|
|
716
|
24
|
|
|
|
|
|
myhtml_namespace_t myhtml_node_namespace(myhtml_tree_node_t *node) |
717
|
|
|
|
|
|
|
{ |
718
|
24
|
|
|
|
|
|
return node->ns; |
719
|
|
|
|
|
|
|
} |
720
|
|
|
|
|
|
|
|
721
|
2
|
|
|
|
|
|
void myhtml_node_namespace_set(myhtml_tree_node_t *node, myhtml_namespace_t ns) |
722
|
|
|
|
|
|
|
{ |
723
|
2
|
|
|
|
|
|
node->ns = ns; |
724
|
2
|
|
|
|
|
|
} |
725
|
|
|
|
|
|
|
|
726
|
0
|
|
|
|
|
|
myhtml_tag_id_t myhtml_node_tag_id(myhtml_tree_node_t *node) |
727
|
|
|
|
|
|
|
{ |
728
|
0
|
|
|
|
|
|
return node->tag_id; |
729
|
|
|
|
|
|
|
} |
730
|
|
|
|
|
|
|
|
731
|
167
|
|
|
|
|
|
const char * myhtml_tag_name_by_id(myhtml_tree_t* tree, myhtml_tag_id_t tag_id, size_t *length) |
732
|
|
|
|
|
|
|
{ |
733
|
167
|
50
|
|
|
|
|
if(length) |
734
|
167
|
|
|
|
|
|
*length = 0; |
735
|
|
|
|
|
|
|
|
736
|
167
|
50
|
|
|
|
|
if(tree == NULL || tree->tags == NULL) |
|
|
50
|
|
|
|
|
|
737
|
0
|
|
|
|
|
|
return NULL; |
738
|
|
|
|
|
|
|
|
739
|
167
|
|
|
|
|
|
const myhtml_tag_context_t *tag_ctx = myhtml_tag_get_by_id(tree->tags, tag_id); |
740
|
|
|
|
|
|
|
|
741
|
167
|
50
|
|
|
|
|
if(tag_ctx == NULL) |
742
|
0
|
|
|
|
|
|
return NULL; |
743
|
|
|
|
|
|
|
|
744
|
167
|
50
|
|
|
|
|
if(length) |
745
|
167
|
|
|
|
|
|
*length = tag_ctx->name_length; |
746
|
|
|
|
|
|
|
|
747
|
167
|
|
|
|
|
|
return tag_ctx->name; |
748
|
|
|
|
|
|
|
} |
749
|
|
|
|
|
|
|
|
750
|
452
|
|
|
|
|
|
myhtml_tag_id_t myhtml_tag_id_by_name(myhtml_tree_t* tree, const char *tag_name, size_t length) |
751
|
|
|
|
|
|
|
{ |
752
|
452
|
50
|
|
|
|
|
if(tree == NULL || tree->tags == NULL) |
|
|
50
|
|
|
|
|
|
753
|
0
|
|
|
|
|
|
return MyHTML_TAG__UNDEF; |
754
|
|
|
|
|
|
|
|
755
|
452
|
|
|
|
|
|
const myhtml_tag_context_t *ctx = myhtml_tag_get_by_name(tree->tags, tag_name, length); |
756
|
|
|
|
|
|
|
|
757
|
452
|
100
|
|
|
|
|
if(ctx == NULL) |
758
|
60
|
|
|
|
|
|
return MyHTML_TAG__UNDEF; |
759
|
|
|
|
|
|
|
|
760
|
392
|
|
|
|
|
|
return ctx->id; |
761
|
|
|
|
|
|
|
} |
762
|
|
|
|
|
|
|
|
763
|
2
|
|
|
|
|
|
bool myhtml_node_is_close_self(myhtml_tree_node_t *node) |
764
|
|
|
|
|
|
|
{ |
765
|
2
|
50
|
|
|
|
|
if(node->token) |
766
|
2
|
|
|
|
|
|
return (node->token->type & MyHTML_TOKEN_TYPE_CLOSE_SELF); |
767
|
|
|
|
|
|
|
|
768
|
0
|
|
|
|
|
|
return false; |
769
|
|
|
|
|
|
|
} |
770
|
|
|
|
|
|
|
|
771
|
38
|
|
|
|
|
|
bool myhtml_node_is_void_element(myhtml_tree_node_t *node) |
772
|
|
|
|
|
|
|
{ |
773
|
|
|
|
|
|
|
// http://w3c.github.io/html-reference/syntax.html#void-elements |
774
|
38
|
100
|
|
|
|
|
switch (node->tag_id) |
775
|
|
|
|
|
|
|
{ |
776
|
|
|
|
|
|
|
case MyHTML_TAG_AREA: |
777
|
|
|
|
|
|
|
case MyHTML_TAG_BASE: |
778
|
|
|
|
|
|
|
case MyHTML_TAG_BR: |
779
|
|
|
|
|
|
|
case MyHTML_TAG_COL: |
780
|
|
|
|
|
|
|
case MyHTML_TAG_COMMAND: |
781
|
|
|
|
|
|
|
case MyHTML_TAG_EMBED: |
782
|
|
|
|
|
|
|
case MyHTML_TAG_HR: |
783
|
|
|
|
|
|
|
case MyHTML_TAG_IMG: |
784
|
|
|
|
|
|
|
case MyHTML_TAG_INPUT: |
785
|
|
|
|
|
|
|
case MyHTML_TAG_KEYGEN: |
786
|
|
|
|
|
|
|
case MyHTML_TAG_LINK: |
787
|
|
|
|
|
|
|
case MyHTML_TAG_META: |
788
|
|
|
|
|
|
|
case MyHTML_TAG_PARAM: |
789
|
|
|
|
|
|
|
case MyHTML_TAG_SOURCE: |
790
|
|
|
|
|
|
|
case MyHTML_TAG_TRACK: |
791
|
|
|
|
|
|
|
case MyHTML_TAG_WBR: |
792
|
|
|
|
|
|
|
{ |
793
|
2
|
|
|
|
|
|
return true; |
794
|
|
|
|
|
|
|
} |
795
|
|
|
|
|
|
|
default: |
796
|
|
|
|
|
|
|
{ |
797
|
36
|
|
|
|
|
|
return false; |
798
|
|
|
|
|
|
|
} |
799
|
|
|
|
|
|
|
} |
800
|
|
|
|
|
|
|
} |
801
|
|
|
|
|
|
|
|
802
|
2
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_node_attribute_first(myhtml_tree_node_t *node) |
803
|
|
|
|
|
|
|
{ |
804
|
2
|
50
|
|
|
|
|
if(node->token) |
805
|
2
|
|
|
|
|
|
return node->token->attr_first; |
806
|
|
|
|
|
|
|
|
807
|
0
|
|
|
|
|
|
return NULL; |
808
|
|
|
|
|
|
|
} |
809
|
|
|
|
|
|
|
|
810
|
0
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_node_attribute_last(myhtml_tree_node_t *node) |
811
|
|
|
|
|
|
|
{ |
812
|
0
|
0
|
|
|
|
|
if(node->token) |
813
|
0
|
|
|
|
|
|
return node->token->attr_last; |
814
|
|
|
|
|
|
|
|
815
|
0
|
|
|
|
|
|
return NULL; |
816
|
|
|
|
|
|
|
} |
817
|
|
|
|
|
|
|
|
818
|
214
|
|
|
|
|
|
const char * myhtml_node_text(myhtml_tree_node_t *node, size_t *length) |
819
|
|
|
|
|
|
|
{ |
820
|
214
|
50
|
|
|
|
|
if(node->token && node->token->str.length && node->token->str.data) |
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
821
|
|
|
|
|
|
|
{ |
822
|
214
|
50
|
|
|
|
|
if(length) |
823
|
214
|
|
|
|
|
|
*length = node->token->str.length; |
824
|
|
|
|
|
|
|
|
825
|
214
|
|
|
|
|
|
return node->token->str.data; |
826
|
|
|
|
|
|
|
} |
827
|
|
|
|
|
|
|
|
828
|
0
|
0
|
|
|
|
|
if(length) |
829
|
0
|
|
|
|
|
|
*length = 0; |
830
|
|
|
|
|
|
|
|
831
|
0
|
|
|
|
|
|
return NULL; |
832
|
|
|
|
|
|
|
} |
833
|
|
|
|
|
|
|
|
834
|
0
|
|
|
|
|
|
mycore_string_t * myhtml_node_string(myhtml_tree_node_t *node) |
835
|
|
|
|
|
|
|
{ |
836
|
0
|
0
|
|
|
|
|
if(node && node->token) |
|
|
0
|
|
|
|
|
|
837
|
0
|
|
|
|
|
|
return &node->token->str; |
838
|
|
|
|
|
|
|
|
839
|
0
|
|
|
|
|
|
return NULL; |
840
|
|
|
|
|
|
|
} |
841
|
|
|
|
|
|
|
|
842
|
0
|
|
|
|
|
|
myhtml_position_t myhtml_node_raw_position(myhtml_tree_node_t *node) |
843
|
|
|
|
|
|
|
{ |
844
|
0
|
0
|
|
|
|
|
if(node && node->token) |
|
|
0
|
|
|
|
|
|
845
|
0
|
|
|
|
|
|
return (myhtml_position_t){node->token->raw_begin, node->token->raw_length}; |
846
|
|
|
|
|
|
|
|
847
|
0
|
|
|
|
|
|
return (myhtml_position_t){0, 0}; |
848
|
|
|
|
|
|
|
} |
849
|
|
|
|
|
|
|
|
850
|
0
|
|
|
|
|
|
myhtml_position_t myhtml_node_element_position(myhtml_tree_node_t *node) |
851
|
|
|
|
|
|
|
{ |
852
|
0
|
0
|
|
|
|
|
if(node && node->token) |
|
|
0
|
|
|
|
|
|
853
|
0
|
|
|
|
|
|
return (myhtml_position_t){node->token->element_begin, node->token->element_length}; |
854
|
|
|
|
|
|
|
|
855
|
0
|
|
|
|
|
|
return (myhtml_position_t){0, 0}; |
856
|
|
|
|
|
|
|
} |
857
|
|
|
|
|
|
|
|
858
|
2492
|
|
|
|
|
|
void myhtml_node_set_data(myhtml_tree_node_t *node, void* data) |
859
|
|
|
|
|
|
|
{ |
860
|
2492
|
|
|
|
|
|
node->data = data; |
861
|
2492
|
|
|
|
|
|
} |
862
|
|
|
|
|
|
|
|
863
|
2794
|
|
|
|
|
|
void * myhtml_node_get_data(myhtml_tree_node_t *node) |
864
|
|
|
|
|
|
|
{ |
865
|
2794
|
|
|
|
|
|
return node->data; |
866
|
|
|
|
|
|
|
} |
867
|
|
|
|
|
|
|
|
868
|
0
|
|
|
|
|
|
myhtml_tree_t * myhtml_node_tree(myhtml_tree_node_t *node) |
869
|
|
|
|
|
|
|
{ |
870
|
0
|
|
|
|
|
|
return node->tree; |
871
|
|
|
|
|
|
|
} |
872
|
|
|
|
|
|
|
|
873
|
0
|
|
|
|
|
|
mystatus_t myhtml_get_nodes_by_attribute_key_recursion(myhtml_tree_node_t* node, myhtml_collection_t* collection, const char* key, size_t key_len) |
874
|
|
|
|
|
|
|
{ |
875
|
0
|
0
|
|
|
|
|
while(node) |
876
|
|
|
|
|
|
|
{ |
877
|
0
|
0
|
|
|
|
|
if(node->token && node->token->attr_first) { |
|
|
0
|
|
|
|
|
|
878
|
0
|
|
|
|
|
|
myhtml_tree_attr_t* attr = node->token->attr_first; |
879
|
|
|
|
|
|
|
|
880
|
0
|
0
|
|
|
|
|
while(attr) { |
881
|
0
|
|
|
|
|
|
mycore_string_t* str_key = &attr->key; |
882
|
|
|
|
|
|
|
|
883
|
0
|
0
|
|
|
|
|
if(str_key->length == key_len && mycore_strncasecmp(str_key->data, key, key_len) == 0) { |
|
|
0
|
|
|
|
|
|
884
|
0
|
|
|
|
|
|
collection->list[ collection->length ] = node; |
885
|
|
|
|
|
|
|
|
886
|
0
|
|
|
|
|
|
collection->length++; |
887
|
0
|
0
|
|
|
|
|
if(collection->length >= collection->size) { |
888
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_collection_check_size(collection, 1024, 0); |
889
|
|
|
|
|
|
|
|
890
|
0
|
0
|
|
|
|
|
if(status) |
891
|
0
|
|
|
|
|
|
return status; |
892
|
|
|
|
|
|
|
} |
893
|
|
|
|
|
|
|
} |
894
|
|
|
|
|
|
|
|
895
|
0
|
|
|
|
|
|
attr = attr->next; |
896
|
|
|
|
|
|
|
} |
897
|
|
|
|
|
|
|
} |
898
|
|
|
|
|
|
|
|
899
|
0
|
0
|
|
|
|
|
if(node->child) { |
900
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_get_nodes_by_attribute_key_recursion(node->child, collection, key, key_len); |
901
|
|
|
|
|
|
|
|
902
|
0
|
0
|
|
|
|
|
if(status) |
903
|
0
|
|
|
|
|
|
return status; |
904
|
|
|
|
|
|
|
} |
905
|
|
|
|
|
|
|
|
906
|
0
|
|
|
|
|
|
node = node->next; |
907
|
|
|
|
|
|
|
} |
908
|
|
|
|
|
|
|
|
909
|
0
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
910
|
|
|
|
|
|
|
} |
911
|
|
|
|
|
|
|
|
912
|
0
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_key(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* scope_node, const char* key, size_t key_len, mystatus_t* status) |
913
|
|
|
|
|
|
|
{ |
914
|
0
|
0
|
|
|
|
|
if(collection == NULL) { |
915
|
0
|
|
|
|
|
|
collection = myhtml_collection_create(1024, status); |
916
|
|
|
|
|
|
|
|
917
|
0
|
0
|
|
|
|
|
if((status && *status) || collection == NULL) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
918
|
0
|
|
|
|
|
|
return NULL; |
919
|
|
|
|
|
|
|
} |
920
|
|
|
|
|
|
|
|
921
|
0
|
0
|
|
|
|
|
if(scope_node == NULL) |
922
|
0
|
|
|
|
|
|
scope_node = tree->node_html; |
923
|
|
|
|
|
|
|
|
924
|
0
|
|
|
|
|
|
mystatus_t rec_status = myhtml_get_nodes_by_attribute_key_recursion(scope_node, collection, key, key_len); |
925
|
|
|
|
|
|
|
|
926
|
0
|
0
|
|
|
|
|
if(rec_status && status) |
|
|
0
|
|
|
|
|
|
927
|
0
|
|
|
|
|
|
*status = rec_status; |
928
|
|
|
|
|
|
|
|
929
|
0
|
|
|
|
|
|
return collection; |
930
|
|
|
|
|
|
|
} |
931
|
|
|
|
|
|
|
|
932
|
|
|
|
|
|
|
/* find by attribute value; case-sensitivity */ |
933
|
64
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_eq(mycore_string_t* str, const char* value, size_t value_len) |
934
|
|
|
|
|
|
|
{ |
935
|
64
|
100
|
|
|
|
|
return str->length == value_len && mycore_strncmp(str->data, value, value_len) == 0; |
|
|
100
|
|
|
|
|
|
936
|
|
|
|
|
|
|
} |
937
|
|
|
|
|
|
|
|
938
|
128
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_whitespace_separated(mycore_string_t* str, const char* value, size_t value_len) |
939
|
|
|
|
|
|
|
{ |
940
|
128
|
100
|
|
|
|
|
if(str->length < value_len) |
941
|
36
|
|
|
|
|
|
return false; |
942
|
|
|
|
|
|
|
|
943
|
92
|
|
|
|
|
|
const char *data = str->data; |
944
|
|
|
|
|
|
|
|
945
|
92
|
100
|
|
|
|
|
if(mycore_strncmp(data, value, value_len) == 0) { |
946
|
20
|
100
|
|
|
|
|
if((str->length > value_len && mycore_utils_whithspace(data[value_len], ==, ||)) || str->length == value_len) |
|
|
50
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
947
|
20
|
|
|
|
|
|
return true; |
948
|
|
|
|
|
|
|
} |
949
|
|
|
|
|
|
|
|
950
|
428
|
100
|
|
|
|
|
for(size_t i = 1; (str->length - i) >= value_len; i++) |
951
|
|
|
|
|
|
|
{ |
952
|
368
|
100
|
|
|
|
|
if(mycore_utils_whithspace(data[(i - 1)], ==, ||)) { |
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
953
|
64
|
100
|
|
|
|
|
if(mycore_strncmp(&data[i], value, value_len) == 0) { |
954
|
16
|
100
|
|
|
|
|
if((i > value_len && mycore_utils_whithspace(data[(i + value_len)], ==, ||)) || (str->length - i) == value_len) |
|
|
100
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
955
|
12
|
|
|
|
|
|
return true; |
956
|
|
|
|
|
|
|
} |
957
|
|
|
|
|
|
|
} |
958
|
|
|
|
|
|
|
} |
959
|
|
|
|
|
|
|
|
960
|
60
|
|
|
|
|
|
return false; |
961
|
|
|
|
|
|
|
} |
962
|
|
|
|
|
|
|
|
963
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_begin(mycore_string_t* str, const char* value, size_t value_len) |
964
|
|
|
|
|
|
|
{ |
965
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
966
|
0
|
|
|
|
|
|
return false; |
967
|
|
|
|
|
|
|
|
968
|
8
|
|
|
|
|
|
return mycore_strncmp(str->data, value, value_len) == 0; |
969
|
|
|
|
|
|
|
} |
970
|
|
|
|
|
|
|
|
971
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_end(mycore_string_t* str, const char* value, size_t value_len) |
972
|
|
|
|
|
|
|
{ |
973
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
974
|
0
|
|
|
|
|
|
return false; |
975
|
|
|
|
|
|
|
|
976
|
8
|
|
|
|
|
|
return mycore_strncmp(&str->data[ (str->length - value_len) ], value, value_len) == 0; |
977
|
|
|
|
|
|
|
} |
978
|
|
|
|
|
|
|
|
979
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_contain(mycore_string_t* str, const char* value, size_t value_len) |
980
|
|
|
|
|
|
|
{ |
981
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
982
|
0
|
|
|
|
|
|
return false; |
983
|
|
|
|
|
|
|
|
984
|
8
|
|
|
|
|
|
const char *data = str->data; |
985
|
|
|
|
|
|
|
|
986
|
116
|
100
|
|
|
|
|
for(size_t i = 0; (str->length - i) >= value_len; i++) |
987
|
|
|
|
|
|
|
{ |
988
|
112
|
100
|
|
|
|
|
if(mycore_strncmp(&data[i], value, value_len) == 0) { |
989
|
4
|
|
|
|
|
|
return true; |
990
|
|
|
|
|
|
|
} |
991
|
|
|
|
|
|
|
} |
992
|
|
|
|
|
|
|
|
993
|
4
|
|
|
|
|
|
return false; |
994
|
|
|
|
|
|
|
} |
995
|
|
|
|
|
|
|
|
996
|
16
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_hyphen_separated(mycore_string_t* str, const char* value, size_t value_len) |
997
|
|
|
|
|
|
|
{ |
998
|
16
|
|
|
|
|
|
const char *data = str->data; |
999
|
|
|
|
|
|
|
|
1000
|
16
|
50
|
|
|
|
|
if(str->length < value_len) |
1001
|
0
|
|
|
|
|
|
return false; |
1002
|
16
|
50
|
|
|
|
|
else if(str->length == value_len && mycore_strncmp(data, value, value_len) == 0) { |
|
|
0
|
|
|
|
|
|
1003
|
0
|
|
|
|
|
|
return true; |
1004
|
|
|
|
|
|
|
} |
1005
|
16
|
100
|
|
|
|
|
else if(mycore_strncmp(data, value, value_len) == 0 && data[value_len] == '-') { |
|
|
100
|
|
|
|
|
|
1006
|
4
|
|
|
|
|
|
return true; |
1007
|
|
|
|
|
|
|
} |
1008
|
|
|
|
|
|
|
|
1009
|
12
|
|
|
|
|
|
return false; |
1010
|
|
|
|
|
|
|
} |
1011
|
|
|
|
|
|
|
|
1012
|
|
|
|
|
|
|
/* find by attribute value; case-insensitive */ |
1013
|
16
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_eq_i(mycore_string_t* str, const char* value, size_t value_len) |
1014
|
|
|
|
|
|
|
{ |
1015
|
16
|
100
|
|
|
|
|
return str->length == value_len && mycore_strncasecmp(str->data, value, value_len) == 0; |
|
|
100
|
|
|
|
|
|
1016
|
|
|
|
|
|
|
} |
1017
|
|
|
|
|
|
|
|
1018
|
16
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_whitespace_separated_i(mycore_string_t* str, const char* value, size_t value_len) |
1019
|
|
|
|
|
|
|
{ |
1020
|
16
|
50
|
|
|
|
|
if(str->length < value_len) |
1021
|
0
|
|
|
|
|
|
return false; |
1022
|
|
|
|
|
|
|
|
1023
|
16
|
|
|
|
|
|
const char *data = str->data; |
1024
|
|
|
|
|
|
|
|
1025
|
16
|
50
|
|
|
|
|
if(mycore_strncasecmp(data, value, value_len) == 0) { |
1026
|
0
|
0
|
|
|
|
|
if((str->length > value_len && mycore_utils_whithspace(data[value_len], ==, ||)) || str->length == value_len) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
1027
|
0
|
|
|
|
|
|
return true; |
1028
|
|
|
|
|
|
|
} |
1029
|
|
|
|
|
|
|
|
1030
|
240
|
100
|
|
|
|
|
for(size_t i = 1; (str->length - i) >= value_len; i++) |
1031
|
|
|
|
|
|
|
{ |
1032
|
228
|
100
|
|
|
|
|
if(mycore_utils_whithspace(data[(i - 1)], ==, ||)) { |
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
1033
|
48
|
100
|
|
|
|
|
if(mycore_strncasecmp(&data[i], value, value_len) == 0) { |
1034
|
8
|
50
|
|
|
|
|
if((i > value_len && mycore_utils_whithspace(data[(i + value_len)], ==, ||)) || (str->length - i) == value_len) |
|
|
100
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
1035
|
4
|
|
|
|
|
|
return true; |
1036
|
|
|
|
|
|
|
} |
1037
|
|
|
|
|
|
|
} |
1038
|
|
|
|
|
|
|
} |
1039
|
|
|
|
|
|
|
|
1040
|
12
|
|
|
|
|
|
return false; |
1041
|
|
|
|
|
|
|
} |
1042
|
|
|
|
|
|
|
|
1043
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_begin_i(mycore_string_t* str, const char* value, size_t value_len) |
1044
|
|
|
|
|
|
|
{ |
1045
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
1046
|
0
|
|
|
|
|
|
return false; |
1047
|
|
|
|
|
|
|
|
1048
|
8
|
|
|
|
|
|
return mycore_strncasecmp(str->data, value, value_len) == 0; |
1049
|
|
|
|
|
|
|
} |
1050
|
|
|
|
|
|
|
|
1051
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_end_i(mycore_string_t* str, const char* value, size_t value_len) |
1052
|
|
|
|
|
|
|
{ |
1053
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
1054
|
0
|
|
|
|
|
|
return false; |
1055
|
|
|
|
|
|
|
|
1056
|
8
|
|
|
|
|
|
return mycore_strncasecmp(&str->data[ (str->length - value_len) ], value, value_len) == 0; |
1057
|
|
|
|
|
|
|
} |
1058
|
|
|
|
|
|
|
|
1059
|
8
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_contain_i(mycore_string_t* str, const char* value, size_t value_len) |
1060
|
|
|
|
|
|
|
{ |
1061
|
8
|
50
|
|
|
|
|
if(str->length < value_len) |
1062
|
0
|
|
|
|
|
|
return false; |
1063
|
|
|
|
|
|
|
|
1064
|
8
|
|
|
|
|
|
const char *data = str->data; |
1065
|
|
|
|
|
|
|
|
1066
|
112
|
100
|
|
|
|
|
for(size_t i = 0; (str->length - i) >= value_len; i++) |
1067
|
|
|
|
|
|
|
{ |
1068
|
108
|
100
|
|
|
|
|
if(mycore_strncasecmp(&data[i], value, value_len) == 0) { |
1069
|
4
|
|
|
|
|
|
return true; |
1070
|
|
|
|
|
|
|
} |
1071
|
|
|
|
|
|
|
} |
1072
|
|
|
|
|
|
|
|
1073
|
4
|
|
|
|
|
|
return false; |
1074
|
|
|
|
|
|
|
} |
1075
|
|
|
|
|
|
|
|
1076
|
16
|
|
|
|
|
|
bool myhtml_get_nodes_by_attribute_value_recursion_hyphen_separated_i(mycore_string_t* str, const char* value, size_t value_len) |
1077
|
|
|
|
|
|
|
{ |
1078
|
16
|
|
|
|
|
|
const char *data = str->data; |
1079
|
|
|
|
|
|
|
|
1080
|
16
|
50
|
|
|
|
|
if(str->length < value_len) |
1081
|
0
|
|
|
|
|
|
return false; |
1082
|
16
|
50
|
|
|
|
|
else if(str->length == value_len && mycore_strncasecmp(data, value, value_len) == 0) { |
|
|
0
|
|
|
|
|
|
1083
|
0
|
|
|
|
|
|
return true; |
1084
|
|
|
|
|
|
|
} |
1085
|
16
|
100
|
|
|
|
|
else if(mycore_strncasecmp(data, value, value_len) == 0 && data[value_len] == '-') { |
|
|
100
|
|
|
|
|
|
1086
|
4
|
|
|
|
|
|
return true; |
1087
|
|
|
|
|
|
|
} |
1088
|
|
|
|
|
|
|
|
1089
|
12
|
|
|
|
|
|
return false; |
1090
|
|
|
|
|
|
|
} |
1091
|
|
|
|
|
|
|
|
1092
|
|
|
|
|
|
|
/* find by attribute value; basic functions */ |
1093
|
0
|
|
|
|
|
|
mystatus_t myhtml_get_nodes_by_attribute_value_recursion(myhtml_tree_node_t* node, myhtml_collection_t* collection, |
1094
|
|
|
|
|
|
|
myhtml_attribute_value_find_f func_eq, |
1095
|
|
|
|
|
|
|
const char* value, size_t value_len) |
1096
|
|
|
|
|
|
|
{ |
1097
|
0
|
0
|
|
|
|
|
while(node) |
1098
|
|
|
|
|
|
|
{ |
1099
|
0
|
0
|
|
|
|
|
if(node->token && node->token->attr_first) { |
|
|
0
|
|
|
|
|
|
1100
|
0
|
|
|
|
|
|
myhtml_tree_attr_t* attr = node->token->attr_first; |
1101
|
|
|
|
|
|
|
|
1102
|
0
|
0
|
|
|
|
|
while(attr) { |
1103
|
0
|
|
|
|
|
|
mycore_string_t* str = &attr->value; |
1104
|
|
|
|
|
|
|
|
1105
|
0
|
0
|
|
|
|
|
if(func_eq(str, value, value_len)) { |
1106
|
0
|
|
|
|
|
|
collection->list[ collection->length ] = node; |
1107
|
|
|
|
|
|
|
|
1108
|
0
|
|
|
|
|
|
collection->length++; |
1109
|
0
|
0
|
|
|
|
|
if(collection->length >= collection->size) { |
1110
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_collection_check_size(collection, 1024, 0); |
1111
|
|
|
|
|
|
|
|
1112
|
0
|
0
|
|
|
|
|
if(status) |
1113
|
0
|
|
|
|
|
|
return status; |
1114
|
|
|
|
|
|
|
} |
1115
|
|
|
|
|
|
|
} |
1116
|
|
|
|
|
|
|
|
1117
|
0
|
|
|
|
|
|
attr = attr->next; |
1118
|
|
|
|
|
|
|
} |
1119
|
|
|
|
|
|
|
} |
1120
|
|
|
|
|
|
|
|
1121
|
0
|
0
|
|
|
|
|
if(node->child) { |
1122
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_get_nodes_by_attribute_value_recursion(node->child, collection, func_eq, value, value_len); |
1123
|
|
|
|
|
|
|
|
1124
|
0
|
0
|
|
|
|
|
if(status) |
1125
|
0
|
|
|
|
|
|
return status; |
1126
|
|
|
|
|
|
|
} |
1127
|
|
|
|
|
|
|
|
1128
|
0
|
|
|
|
|
|
node = node->next; |
1129
|
|
|
|
|
|
|
} |
1130
|
|
|
|
|
|
|
|
1131
|
0
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
1132
|
|
|
|
|
|
|
} |
1133
|
|
|
|
|
|
|
|
1134
|
680
|
|
|
|
|
|
mystatus_t myhtml_get_nodes_by_attribute_value_recursion_by_key(myhtml_tree_node_t* node, myhtml_collection_t* collection, |
1135
|
|
|
|
|
|
|
myhtml_attribute_value_find_f func_eq, |
1136
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1137
|
|
|
|
|
|
|
const char* value, size_t value_len) |
1138
|
|
|
|
|
|
|
{ |
1139
|
4896
|
100
|
|
|
|
|
while(node) |
1140
|
|
|
|
|
|
|
{ |
1141
|
4216
|
100
|
|
|
|
|
if(node->token && node->token->attr_first) { |
|
|
100
|
|
|
|
|
|
1142
|
1836
|
|
|
|
|
|
myhtml_tree_attr_t* attr = node->token->attr_first; |
1143
|
|
|
|
|
|
|
|
1144
|
4488
|
100
|
|
|
|
|
while(attr) { |
1145
|
2652
|
|
|
|
|
|
mycore_string_t* str_key = &attr->key; |
1146
|
2652
|
|
|
|
|
|
mycore_string_t* str = &attr->value; |
1147
|
|
|
|
|
|
|
|
1148
|
2652
|
100
|
|
|
|
|
if(str_key->length == key_len && mycore_strncasecmp(str_key->data, key, key_len) == 0) |
|
|
100
|
|
|
|
|
|
1149
|
|
|
|
|
|
|
{ |
1150
|
304
|
100
|
|
|
|
|
if(func_eq(str, value, value_len)) { |
1151
|
84
|
|
|
|
|
|
collection->list[ collection->length ] = node; |
1152
|
|
|
|
|
|
|
|
1153
|
84
|
|
|
|
|
|
collection->length++; |
1154
|
84
|
50
|
|
|
|
|
if(collection->length >= collection->size) { |
1155
|
0
|
|
|
|
|
|
mystatus_t status = myhtml_collection_check_size(collection, 1024, 0); |
1156
|
|
|
|
|
|
|
|
1157
|
0
|
0
|
|
|
|
|
if(status) |
1158
|
0
|
|
|
|
|
|
return status; |
1159
|
|
|
|
|
|
|
} |
1160
|
|
|
|
|
|
|
} |
1161
|
|
|
|
|
|
|
} |
1162
|
|
|
|
|
|
|
|
1163
|
2652
|
|
|
|
|
|
attr = attr->next; |
1164
|
|
|
|
|
|
|
} |
1165
|
|
|
|
|
|
|
} |
1166
|
|
|
|
|
|
|
|
1167
|
4216
|
100
|
|
|
|
|
if(node->child) { |
1168
|
544
|
|
|
|
|
|
mystatus_t status = myhtml_get_nodes_by_attribute_value_recursion_by_key(node->child, collection, func_eq, |
1169
|
|
|
|
|
|
|
key, key_len, value, value_len); |
1170
|
|
|
|
|
|
|
|
1171
|
544
|
50
|
|
|
|
|
if(status) |
1172
|
0
|
|
|
|
|
|
return status; |
1173
|
|
|
|
|
|
|
} |
1174
|
|
|
|
|
|
|
|
1175
|
4216
|
|
|
|
|
|
node = node->next; |
1176
|
|
|
|
|
|
|
} |
1177
|
|
|
|
|
|
|
|
1178
|
680
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
1179
|
|
|
|
|
|
|
} |
1180
|
|
|
|
|
|
|
|
1181
|
136
|
|
|
|
|
|
myhtml_collection_t * _myhtml_get_nodes_by_attribute_value(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1182
|
|
|
|
|
|
|
myhtml_attribute_value_find_f func_eq, |
1183
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1184
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1185
|
|
|
|
|
|
|
mystatus_t* status) |
1186
|
|
|
|
|
|
|
{ |
1187
|
136
|
50
|
|
|
|
|
if(collection == NULL) { |
1188
|
136
|
|
|
|
|
|
collection = myhtml_collection_create(1024, status); |
1189
|
|
|
|
|
|
|
|
1190
|
136
|
50
|
|
|
|
|
if((status && *status) || collection == NULL) |
|
|
0
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
1191
|
0
|
|
|
|
|
|
return NULL; |
1192
|
|
|
|
|
|
|
} |
1193
|
|
|
|
|
|
|
|
1194
|
136
|
50
|
|
|
|
|
if(node == NULL) |
1195
|
0
|
|
|
|
|
|
node = tree->node_html; |
1196
|
|
|
|
|
|
|
|
1197
|
|
|
|
|
|
|
mystatus_t rec_status; |
1198
|
|
|
|
|
|
|
|
1199
|
136
|
50
|
|
|
|
|
if(key && key_len) |
|
|
50
|
|
|
|
|
|
1200
|
136
|
|
|
|
|
|
rec_status = myhtml_get_nodes_by_attribute_value_recursion_by_key(node, collection, func_eq, key, key_len, value, value_len); |
1201
|
|
|
|
|
|
|
else |
1202
|
0
|
|
|
|
|
|
rec_status = myhtml_get_nodes_by_attribute_value_recursion(node, collection, func_eq, value, value_len); |
1203
|
|
|
|
|
|
|
|
1204
|
136
|
50
|
|
|
|
|
if(rec_status && status) |
|
|
0
|
|
|
|
|
|
1205
|
0
|
|
|
|
|
|
*status = rec_status; |
1206
|
|
|
|
|
|
|
|
1207
|
136
|
|
|
|
|
|
return collection; |
1208
|
|
|
|
|
|
|
} |
1209
|
|
|
|
|
|
|
|
1210
|
28
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1211
|
|
|
|
|
|
|
bool case_insensitive, |
1212
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1213
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1214
|
|
|
|
|
|
|
mystatus_t* status) |
1215
|
|
|
|
|
|
|
{ |
1216
|
28
|
100
|
|
|
|
|
if(case_insensitive) { |
1217
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1218
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_eq_i, |
1219
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1220
|
|
|
|
|
|
|
} |
1221
|
|
|
|
|
|
|
|
1222
|
20
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1223
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_eq, |
1224
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1225
|
|
|
|
|
|
|
} |
1226
|
|
|
|
|
|
|
|
1227
|
44
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value_whitespace_separated(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1228
|
|
|
|
|
|
|
bool case_insensitive, |
1229
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1230
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1231
|
|
|
|
|
|
|
mystatus_t* status) |
1232
|
|
|
|
|
|
|
{ |
1233
|
44
|
100
|
|
|
|
|
if(case_insensitive) { |
1234
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1235
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_whitespace_separated_i, |
1236
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1237
|
|
|
|
|
|
|
} |
1238
|
|
|
|
|
|
|
|
1239
|
36
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1240
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_whitespace_separated, |
1241
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1242
|
|
|
|
|
|
|
} |
1243
|
|
|
|
|
|
|
|
1244
|
16
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value_begin(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1245
|
|
|
|
|
|
|
bool case_insensitive, |
1246
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1247
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1248
|
|
|
|
|
|
|
mystatus_t* status) |
1249
|
|
|
|
|
|
|
{ |
1250
|
16
|
100
|
|
|
|
|
if(case_insensitive) { |
1251
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1252
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_begin_i, |
1253
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1254
|
|
|
|
|
|
|
} |
1255
|
|
|
|
|
|
|
|
1256
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1257
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_begin, |
1258
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1259
|
|
|
|
|
|
|
} |
1260
|
|
|
|
|
|
|
|
1261
|
16
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value_end(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1262
|
|
|
|
|
|
|
bool case_insensitive, |
1263
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1264
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1265
|
|
|
|
|
|
|
mystatus_t* status) |
1266
|
|
|
|
|
|
|
{ |
1267
|
16
|
100
|
|
|
|
|
if(case_insensitive) { |
1268
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1269
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_end_i, |
1270
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1271
|
|
|
|
|
|
|
} |
1272
|
|
|
|
|
|
|
|
1273
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1274
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_end, |
1275
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1276
|
|
|
|
|
|
|
} |
1277
|
|
|
|
|
|
|
|
1278
|
16
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value_contain(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1279
|
|
|
|
|
|
|
bool case_insensitive, |
1280
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1281
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1282
|
|
|
|
|
|
|
mystatus_t* status) |
1283
|
|
|
|
|
|
|
{ |
1284
|
16
|
100
|
|
|
|
|
if(case_insensitive) { |
1285
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1286
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_contain_i, |
1287
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1288
|
|
|
|
|
|
|
} |
1289
|
|
|
|
|
|
|
|
1290
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1291
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_contain, |
1292
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1293
|
|
|
|
|
|
|
} |
1294
|
|
|
|
|
|
|
|
1295
|
16
|
|
|
|
|
|
myhtml_collection_t * myhtml_get_nodes_by_attribute_value_hyphen_separated(myhtml_tree_t *tree, myhtml_collection_t* collection, myhtml_tree_node_t* node, |
1296
|
|
|
|
|
|
|
bool case_insensitive, |
1297
|
|
|
|
|
|
|
const char* key, size_t key_len, |
1298
|
|
|
|
|
|
|
const char* value, size_t value_len, |
1299
|
|
|
|
|
|
|
mystatus_t* status) |
1300
|
|
|
|
|
|
|
{ |
1301
|
16
|
100
|
|
|
|
|
if(case_insensitive) { |
1302
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1303
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_hyphen_separated_i, |
1304
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1305
|
|
|
|
|
|
|
} |
1306
|
|
|
|
|
|
|
|
1307
|
8
|
|
|
|
|
|
return _myhtml_get_nodes_by_attribute_value(tree, collection, node, |
1308
|
|
|
|
|
|
|
myhtml_get_nodes_by_attribute_value_recursion_hyphen_separated, |
1309
|
|
|
|
|
|
|
key, key_len, value, value_len, status); |
1310
|
|
|
|
|
|
|
} |
1311
|
|
|
|
|
|
|
|
1312
|
|
|
|
|
|
|
/* |
1313
|
|
|
|
|
|
|
* Attributes |
1314
|
|
|
|
|
|
|
*/ |
1315
|
10
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_next(myhtml_tree_attr_t *attr) |
1316
|
|
|
|
|
|
|
{ |
1317
|
10
|
|
|
|
|
|
return attr->next; |
1318
|
|
|
|
|
|
|
} |
1319
|
|
|
|
|
|
|
|
1320
|
0
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_prev(myhtml_tree_attr_t *attr) |
1321
|
|
|
|
|
|
|
{ |
1322
|
0
|
|
|
|
|
|
return attr->prev; |
1323
|
|
|
|
|
|
|
} |
1324
|
|
|
|
|
|
|
|
1325
|
5
|
|
|
|
|
|
enum myhtml_namespace myhtml_attribute_namespace(myhtml_tree_attr_t *attr) |
1326
|
|
|
|
|
|
|
{ |
1327
|
5
|
|
|
|
|
|
return attr->ns; |
1328
|
|
|
|
|
|
|
} |
1329
|
|
|
|
|
|
|
|
1330
|
0
|
|
|
|
|
|
void myhtml_attribute_namespace_set(myhtml_tree_attr_t *attr, myhtml_namespace_t ns) |
1331
|
|
|
|
|
|
|
{ |
1332
|
0
|
|
|
|
|
|
attr->ns = ns; |
1333
|
0
|
|
|
|
|
|
} |
1334
|
|
|
|
|
|
|
|
1335
|
46
|
|
|
|
|
|
const char * myhtml_attribute_key(myhtml_tree_attr_t *attr, size_t *length) |
1336
|
|
|
|
|
|
|
{ |
1337
|
46
|
50
|
|
|
|
|
if(attr->key.data && attr->key.length) |
|
|
50
|
|
|
|
|
|
1338
|
|
|
|
|
|
|
{ |
1339
|
46
|
50
|
|
|
|
|
if(length) |
1340
|
46
|
|
|
|
|
|
*length = attr->key.length; |
1341
|
|
|
|
|
|
|
|
1342
|
46
|
|
|
|
|
|
return attr->key.data; |
1343
|
|
|
|
|
|
|
} |
1344
|
|
|
|
|
|
|
|
1345
|
0
|
0
|
|
|
|
|
if(length) |
1346
|
0
|
|
|
|
|
|
*length = 0; |
1347
|
|
|
|
|
|
|
|
1348
|
0
|
|
|
|
|
|
return NULL; |
1349
|
|
|
|
|
|
|
} |
1350
|
|
|
|
|
|
|
|
1351
|
123
|
|
|
|
|
|
const char * myhtml_attribute_value(myhtml_tree_attr_t *attr, size_t *length) |
1352
|
|
|
|
|
|
|
{ |
1353
|
123
|
100
|
|
|
|
|
if(attr->value.data && attr->value.length) |
|
|
100
|
|
|
|
|
|
1354
|
|
|
|
|
|
|
{ |
1355
|
106
|
50
|
|
|
|
|
if(length) |
1356
|
106
|
|
|
|
|
|
*length = attr->value.length; |
1357
|
|
|
|
|
|
|
|
1358
|
106
|
|
|
|
|
|
return attr->value.data; |
1359
|
|
|
|
|
|
|
} |
1360
|
|
|
|
|
|
|
|
1361
|
17
|
50
|
|
|
|
|
if(length) |
1362
|
17
|
|
|
|
|
|
*length = 0; |
1363
|
|
|
|
|
|
|
|
1364
|
17
|
|
|
|
|
|
return NULL; |
1365
|
|
|
|
|
|
|
} |
1366
|
|
|
|
|
|
|
|
1367
|
0
|
|
|
|
|
|
mycore_string_t * myhtml_attribute_key_string(myhtml_tree_attr_t* attr) |
1368
|
|
|
|
|
|
|
{ |
1369
|
0
|
0
|
|
|
|
|
if(attr) |
1370
|
0
|
|
|
|
|
|
return &attr->key; |
1371
|
|
|
|
|
|
|
|
1372
|
0
|
|
|
|
|
|
return NULL; |
1373
|
|
|
|
|
|
|
} |
1374
|
|
|
|
|
|
|
|
1375
|
0
|
|
|
|
|
|
mycore_string_t * myhtml_attribute_value_string(myhtml_tree_attr_t* attr) |
1376
|
|
|
|
|
|
|
{ |
1377
|
0
|
0
|
|
|
|
|
if(attr) |
1378
|
0
|
|
|
|
|
|
return &attr->value; |
1379
|
|
|
|
|
|
|
|
1380
|
0
|
|
|
|
|
|
return NULL; |
1381
|
|
|
|
|
|
|
} |
1382
|
|
|
|
|
|
|
|
1383
|
120
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_by_key(myhtml_tree_node_t *node, const char *key, size_t key_len) |
1384
|
|
|
|
|
|
|
{ |
1385
|
120
|
50
|
|
|
|
|
if(node == NULL || node->token == NULL) |
|
|
50
|
|
|
|
|
|
1386
|
0
|
|
|
|
|
|
return NULL; |
1387
|
|
|
|
|
|
|
|
1388
|
120
|
|
|
|
|
|
return myhtml_token_attr_by_name(node->token, key, key_len); |
1389
|
|
|
|
|
|
|
} |
1390
|
|
|
|
|
|
|
|
1391
|
63
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_add(myhtml_tree_node_t *node, const char *key, size_t key_len, const char *value, size_t value_len, myencoding_t encoding) |
1392
|
|
|
|
|
|
|
{ |
1393
|
63
|
50
|
|
|
|
|
if(node == NULL) |
1394
|
0
|
|
|
|
|
|
return NULL; |
1395
|
|
|
|
|
|
|
|
1396
|
63
|
|
|
|
|
|
myhtml_tree_t *tree = node->tree; |
1397
|
|
|
|
|
|
|
|
1398
|
63
|
50
|
|
|
|
|
if(node->token == NULL) { |
1399
|
0
|
|
|
|
|
|
node->token = myhtml_token_node_create(tree->token, tree->mcasync_rules_token_id); |
1400
|
|
|
|
|
|
|
|
1401
|
0
|
0
|
|
|
|
|
if(node->token == NULL) |
1402
|
0
|
|
|
|
|
|
return NULL; |
1403
|
|
|
|
|
|
|
|
1404
|
0
|
|
|
|
|
|
node->token->type |= MyHTML_TOKEN_TYPE_DONE; |
1405
|
|
|
|
|
|
|
} |
1406
|
|
|
|
|
|
|
|
1407
|
63
|
|
|
|
|
|
return myhtml_token_node_attr_append_with_convert_encoding(tree->token, node->token, key, key_len, |
1408
|
|
|
|
|
|
|
value, value_len, tree->mcasync_rules_token_id, encoding); |
1409
|
|
|
|
|
|
|
} |
1410
|
|
|
|
|
|
|
|
1411
|
0
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_remove(myhtml_tree_node_t *node, myhtml_tree_attr_t *attr) |
1412
|
|
|
|
|
|
|
{ |
1413
|
0
|
0
|
|
|
|
|
if(node == NULL || node->token == NULL) |
|
|
0
|
|
|
|
|
|
1414
|
0
|
|
|
|
|
|
return NULL; |
1415
|
|
|
|
|
|
|
|
1416
|
0
|
|
|
|
|
|
return myhtml_token_attr_remove(node->token, attr); |
1417
|
|
|
|
|
|
|
} |
1418
|
|
|
|
|
|
|
|
1419
|
20
|
|
|
|
|
|
myhtml_tree_attr_t * myhtml_attribute_remove_by_key(myhtml_tree_node_t *node, const char *key, size_t key_len) |
1420
|
|
|
|
|
|
|
{ |
1421
|
20
|
50
|
|
|
|
|
if(node == NULL || node->token == NULL) |
|
|
50
|
|
|
|
|
|
1422
|
0
|
|
|
|
|
|
return NULL; |
1423
|
|
|
|
|
|
|
|
1424
|
20
|
|
|
|
|
|
return myhtml_token_attr_remove_by_name(node->token, key, key_len); |
1425
|
|
|
|
|
|
|
} |
1426
|
|
|
|
|
|
|
|
1427
|
33
|
|
|
|
|
|
void myhtml_attribute_delete(myhtml_tree_t *tree, myhtml_tree_node_t *node, myhtml_tree_attr_t *attr) |
1428
|
|
|
|
|
|
|
{ |
1429
|
33
|
50
|
|
|
|
|
if(node == NULL || node->token == NULL) |
|
|
50
|
|
|
|
|
|
1430
|
0
|
|
|
|
|
|
return; |
1431
|
|
|
|
|
|
|
|
1432
|
33
|
|
|
|
|
|
myhtml_token_attr_remove(node->token, attr); |
1433
|
33
|
|
|
|
|
|
myhtml_attribute_free(tree, attr); |
1434
|
|
|
|
|
|
|
} |
1435
|
|
|
|
|
|
|
|
1436
|
33
|
|
|
|
|
|
void myhtml_attribute_free(myhtml_tree_t *tree, myhtml_tree_attr_t *attr) |
1437
|
|
|
|
|
|
|
{ |
1438
|
33
|
100
|
|
|
|
|
if(attr->key.data) |
1439
|
12
|
|
|
|
|
|
mchar_async_free(attr->key.mchar, attr->key.node_idx, attr->key.data); |
1440
|
33
|
100
|
|
|
|
|
if(attr->value.data) |
1441
|
21
|
|
|
|
|
|
mchar_async_free(attr->value.mchar, attr->value.node_idx, attr->value.data); |
1442
|
|
|
|
|
|
|
|
1443
|
33
|
|
|
|
|
|
mcobject_async_free(tree->token->attr_obj, attr); |
1444
|
33
|
|
|
|
|
|
} |
1445
|
|
|
|
|
|
|
|
1446
|
0
|
|
|
|
|
|
myhtml_position_t myhtml_attribute_key_raw_position(myhtml_tree_attr_t *attr) |
1447
|
|
|
|
|
|
|
{ |
1448
|
0
|
0
|
|
|
|
|
if(attr) |
1449
|
0
|
|
|
|
|
|
return (myhtml_position_t){attr->raw_key_begin, attr->raw_key_length}; |
1450
|
|
|
|
|
|
|
|
1451
|
0
|
|
|
|
|
|
return (myhtml_position_t){0, 0}; |
1452
|
|
|
|
|
|
|
} |
1453
|
|
|
|
|
|
|
|
1454
|
0
|
|
|
|
|
|
myhtml_position_t myhtml_attribute_value_raw_position(myhtml_tree_attr_t *attr) |
1455
|
|
|
|
|
|
|
{ |
1456
|
0
|
0
|
|
|
|
|
if(attr) |
1457
|
0
|
|
|
|
|
|
return (myhtml_position_t){attr->raw_value_begin, attr->raw_value_length}; |
1458
|
|
|
|
|
|
|
|
1459
|
0
|
|
|
|
|
|
return (myhtml_position_t){0, 0}; |
1460
|
|
|
|
|
|
|
} |
1461
|
|
|
|
|
|
|
|
1462
|
|
|
|
|
|
|
/* |
1463
|
|
|
|
|
|
|
* Collections |
1464
|
|
|
|
|
|
|
*/ |
1465
|
189
|
|
|
|
|
|
myhtml_collection_t * myhtml_collection_create(size_t size, mystatus_t *status) |
1466
|
|
|
|
|
|
|
{ |
1467
|
189
|
|
|
|
|
|
myhtml_collection_t *collection = (myhtml_collection_t*)mycore_malloc(sizeof(myhtml_collection_t)); |
1468
|
|
|
|
|
|
|
|
1469
|
189
|
50
|
|
|
|
|
if(collection == NULL) { |
1470
|
0
|
0
|
|
|
|
|
if(status) |
1471
|
0
|
|
|
|
|
|
*status = MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
1472
|
|
|
|
|
|
|
|
1473
|
0
|
|
|
|
|
|
return NULL; |
1474
|
|
|
|
|
|
|
} |
1475
|
|
|
|
|
|
|
|
1476
|
189
|
|
|
|
|
|
collection->size = size; |
1477
|
189
|
|
|
|
|
|
collection->length = 0; |
1478
|
189
|
|
|
|
|
|
collection->list = (myhtml_tree_node_t **)mycore_malloc(sizeof(myhtml_tree_node_t*) * size); |
1479
|
|
|
|
|
|
|
|
1480
|
189
|
50
|
|
|
|
|
if(collection->list == NULL) { |
1481
|
0
|
|
|
|
|
|
mycore_free(collection); |
1482
|
|
|
|
|
|
|
|
1483
|
0
|
0
|
|
|
|
|
if(status) |
1484
|
0
|
|
|
|
|
|
*status = MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
1485
|
|
|
|
|
|
|
|
1486
|
0
|
|
|
|
|
|
return NULL; |
1487
|
|
|
|
|
|
|
} |
1488
|
|
|
|
|
|
|
|
1489
|
189
|
100
|
|
|
|
|
if(status) |
1490
|
53
|
|
|
|
|
|
*status = MyHTML_STATUS_OK; |
1491
|
|
|
|
|
|
|
|
1492
|
189
|
|
|
|
|
|
return collection; |
1493
|
|
|
|
|
|
|
} |
1494
|
|
|
|
|
|
|
|
1495
|
89
|
|
|
|
|
|
mystatus_t myhtml_collection_check_size(myhtml_collection_t *collection, size_t need, size_t upto_length) |
1496
|
|
|
|
|
|
|
{ |
1497
|
89
|
50
|
|
|
|
|
if((collection->length + need) >= collection->size) |
1498
|
|
|
|
|
|
|
{ |
1499
|
0
|
|
|
|
|
|
size_t tmp_size = collection->length + need + upto_length + 1; |
1500
|
0
|
|
|
|
|
|
myhtml_tree_node_t **tmp = (myhtml_tree_node_t **)mycore_realloc(collection->list, sizeof(myhtml_tree_node_t*) * tmp_size); |
1501
|
|
|
|
|
|
|
|
1502
|
0
|
0
|
|
|
|
|
if(tmp) { |
1503
|
0
|
|
|
|
|
|
collection->size = tmp_size; |
1504
|
0
|
|
|
|
|
|
collection->list = tmp; |
1505
|
|
|
|
|
|
|
} |
1506
|
|
|
|
|
|
|
else |
1507
|
0
|
|
|
|
|
|
return MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
1508
|
|
|
|
|
|
|
} |
1509
|
|
|
|
|
|
|
|
1510
|
89
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
1511
|
|
|
|
|
|
|
} |
1512
|
|
|
|
|
|
|
|
1513
|
0
|
|
|
|
|
|
void myhtml_collection_clean(myhtml_collection_t *collection) |
1514
|
|
|
|
|
|
|
{ |
1515
|
0
|
0
|
|
|
|
|
if(collection) |
1516
|
0
|
|
|
|
|
|
collection->length = 0; |
1517
|
0
|
|
|
|
|
|
} |
1518
|
|
|
|
|
|
|
|
1519
|
189
|
|
|
|
|
|
myhtml_collection_t * myhtml_collection_destroy(myhtml_collection_t *collection) |
1520
|
|
|
|
|
|
|
{ |
1521
|
189
|
50
|
|
|
|
|
if(collection == NULL) |
1522
|
0
|
|
|
|
|
|
return NULL; |
1523
|
|
|
|
|
|
|
|
1524
|
189
|
50
|
|
|
|
|
if(collection->list) |
1525
|
189
|
|
|
|
|
|
mycore_free(collection->list); |
1526
|
|
|
|
|
|
|
|
1527
|
189
|
|
|
|
|
|
mycore_free(collection); |
1528
|
|
|
|
|
|
|
|
1529
|
189
|
|
|
|
|
|
return NULL; |
1530
|
|
|
|
|
|
|
} |
1531
|
|
|
|
|
|
|
|
1532
|
|
|
|
|
|
|
/* queue */ |
1533
|
1685
|
|
|
|
|
|
mystatus_t myhtml_queue_add(myhtml_tree_t *tree, size_t begin, myhtml_token_node_t* token) |
1534
|
|
|
|
|
|
|
{ |
1535
|
|
|
|
|
|
|
// TODO: need refactoring this code |
1536
|
|
|
|
|
|
|
// too many conditions |
1537
|
1685
|
|
|
|
|
|
mythread_queue_node_t *qnode = tree->current_qnode; |
1538
|
|
|
|
|
|
|
|
1539
|
1685
|
50
|
|
|
|
|
if(tree->parse_flags & MyHTML_TREE_PARSE_FLAGS_SKIP_WHITESPACE_TOKEN) { |
1540
|
0
|
0
|
|
|
|
|
if(token && token->tag_id == MyHTML_TAG__TEXT && token->type & MyHTML_TOKEN_TYPE_WHITESPACE) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
1541
|
|
|
|
|
|
|
{ |
1542
|
0
|
|
|
|
|
|
myhtml_token_node_clean(token); |
1543
|
0
|
|
|
|
|
|
token->raw_begin = token->element_begin = (tree->global_offset + begin); |
1544
|
|
|
|
|
|
|
|
1545
|
0
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
1546
|
|
|
|
|
|
|
} |
1547
|
|
|
|
|
|
|
} |
1548
|
|
|
|
|
|
|
|
1549
|
|
|
|
|
|
|
#ifndef MyCORE_BUILD_WITHOUT_THREADS |
1550
|
|
|
|
|
|
|
|
1551
|
1685
|
100
|
|
|
|
|
if(tree->flags & MyHTML_TREE_FLAGS_SINGLE_MODE) { |
1552
|
1663
|
50
|
|
|
|
|
if(qnode && token) { |
|
|
50
|
|
|
|
|
|
1553
|
1663
|
|
|
|
|
|
qnode->args = token; |
1554
|
|
|
|
|
|
|
|
1555
|
1663
|
|
|
|
|
|
myhtml_parser_worker(0, qnode); |
1556
|
1663
|
|
|
|
|
|
myhtml_parser_stream(0, qnode); |
1557
|
|
|
|
|
|
|
} |
1558
|
|
|
|
|
|
|
|
1559
|
1663
|
|
|
|
|
|
tree->current_qnode = mythread_queue_node_malloc_limit(tree->myhtml->thread_stream, tree->queue, 4, NULL); |
1560
|
|
|
|
|
|
|
} |
1561
|
|
|
|
|
|
|
else { |
1562
|
22
|
50
|
|
|
|
|
if(qnode) |
1563
|
22
|
|
|
|
|
|
qnode->args = token; |
1564
|
|
|
|
|
|
|
|
1565
|
22
|
|
|
|
|
|
tree->current_qnode = mythread_queue_node_malloc_round(tree->myhtml->thread_stream, tree->queue_entry); |
1566
|
|
|
|
|
|
|
|
1567
|
|
|
|
|
|
|
/* we have a clean queue list */ |
1568
|
22
|
50
|
|
|
|
|
if(tree->queue_entry->queue->nodes_length == 0) { |
1569
|
0
|
|
|
|
|
|
mythread_queue_list_entry_make_batch(tree->myhtml->thread_batch, tree->queue_entry); |
1570
|
0
|
|
|
|
|
|
mythread_queue_list_entry_make_stream(tree->myhtml->thread_stream, tree->queue_entry); |
1571
|
|
|
|
|
|
|
} |
1572
|
|
|
|
|
|
|
} |
1573
|
|
|
|
|
|
|
|
1574
|
|
|
|
|
|
|
#else |
1575
|
|
|
|
|
|
|
|
1576
|
|
|
|
|
|
|
if(qnode && token) { |
1577
|
|
|
|
|
|
|
qnode->args = token; |
1578
|
|
|
|
|
|
|
|
1579
|
|
|
|
|
|
|
myhtml_parser_worker(0, qnode); |
1580
|
|
|
|
|
|
|
myhtml_parser_stream(0, qnode); |
1581
|
|
|
|
|
|
|
} |
1582
|
|
|
|
|
|
|
|
1583
|
|
|
|
|
|
|
tree->current_qnode = mythread_queue_node_malloc_limit(tree->myhtml->thread_stream, tree->queue, 4, NULL); |
1584
|
|
|
|
|
|
|
|
1585
|
|
|
|
|
|
|
#endif /* MyCORE_BUILD_WITHOUT_THREADS */ |
1586
|
|
|
|
|
|
|
|
1587
|
1685
|
50
|
|
|
|
|
if(tree->current_qnode == NULL) |
1588
|
0
|
|
|
|
|
|
return MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
1589
|
|
|
|
|
|
|
|
1590
|
1685
|
|
|
|
|
|
tree->current_qnode->context = tree; |
1591
|
1685
|
|
|
|
|
|
tree->current_qnode->prev = qnode; |
1592
|
|
|
|
|
|
|
|
1593
|
1685
|
50
|
|
|
|
|
if(qnode && token) |
|
|
50
|
|
|
|
|
|
1594
|
1685
|
|
|
|
|
|
myhtml_tokenizer_calc_current_namespace(tree, token); |
1595
|
|
|
|
|
|
|
|
1596
|
1685
|
|
|
|
|
|
tree->current_token_node = myhtml_token_node_create(tree->token, tree->token->mcasync_token_id); |
1597
|
1685
|
50
|
|
|
|
|
if(tree->current_token_node == NULL) |
1598
|
0
|
|
|
|
|
|
return MyHTML_STATUS_ERROR_MEMORY_ALLOCATION; |
1599
|
|
|
|
|
|
|
|
1600
|
1685
|
|
|
|
|
|
tree->current_token_node->raw_begin = tree->current_token_node->element_begin = (tree->global_offset + begin); |
1601
|
|
|
|
|
|
|
|
1602
|
1685
|
|
|
|
|
|
return MyHTML_STATUS_OK; |
1603
|
|
|
|
|
|
|
} |
1604
|
|
|
|
|
|
|
|
1605
|
0
|
|
|
|
|
|
bool myhtml_utils_strcmp(const char* ab, const char* to_lowercase, size_t size) |
1606
|
|
|
|
|
|
|
{ |
1607
|
0
|
|
|
|
|
|
size_t i = 0; |
1608
|
|
|
|
|
|
|
|
1609
|
|
|
|
|
|
|
for(;;) { |
1610
|
0
|
0
|
|
|
|
|
if(i == size) |
1611
|
0
|
|
|
|
|
|
return true; |
1612
|
|
|
|
|
|
|
|
1613
|
0
|
0
|
|
|
|
|
if((const unsigned char)(to_lowercase[i] > 0x40 && to_lowercase[i] < 0x5b ? |
|
|
0
|
|
|
|
|
|
1614
|
0
|
0
|
|
|
|
|
(to_lowercase[i]|0x60) : to_lowercase[i]) != (const unsigned char)ab[i]) |
1615
|
|
|
|
|
|
|
{ |
1616
|
0
|
|
|
|
|
|
return false; |
1617
|
|
|
|
|
|
|
} |
1618
|
|
|
|
|
|
|
|
1619
|
0
|
|
|
|
|
|
i++; |
1620
|
0
|
|
|
|
|
|
} |
1621
|
|
|
|
|
|
|
|
1622
|
|
|
|
|
|
|
return false; |
1623
|
|
|
|
|
|
|
} |
1624
|
|
|
|
|
|
|
|
1625
|
501
|
|
|
|
|
|
bool myhtml_is_html_node(myhtml_tree_node_t *node, myhtml_tag_id_t tag_id) |
1626
|
|
|
|
|
|
|
{ |
1627
|
501
|
50
|
|
|
|
|
if(node == NULL) |
1628
|
0
|
|
|
|
|
|
return false; |
1629
|
|
|
|
|
|
|
|
1630
|
501
|
100
|
|
|
|
|
return node->tag_id == tag_id && node->ns == MyHTML_NAMESPACE_HTML; |
|
|
50
|
|
|
|
|
|
1631
|
|
|
|
|
|
|
} |
1632
|
|
|
|
|
|
|
|
1633
|
|
|
|
|
|
|
/* version */ |
1634
|
0
|
|
|
|
|
|
myhtml_version_t myhtml_version(void) |
1635
|
|
|
|
|
|
|
{ |
1636
|
0
|
|
|
|
|
|
return (myhtml_version_t){MyHTML_VERSION_MAJOR, MyHTML_VERSION_MINOR, MyHTML_VERSION_PATCH}; |
1637
|
|
|
|
|
|
|
} |
1638
|
|
|
|
|
|
|
|
1639
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_clone(myhtml_tree_t* dest_tree, myhtml_tree_node_t* src) |
1640
|
|
|
|
|
|
|
{ |
1641
|
|
|
|
|
|
|
myhtml_tag_id_t tag_id; |
1642
|
|
|
|
|
|
|
const myhtml_tag_context_t* tag_to, * tag_from; |
1643
|
0
|
|
|
|
|
|
myhtml_tree_node_t* new_node = myhtml_tree_node_create(dest_tree); |
1644
|
|
|
|
|
|
|
|
1645
|
0
|
|
|
|
|
|
tag_id = src->tag_id; |
1646
|
|
|
|
|
|
|
|
1647
|
0
|
0
|
|
|
|
|
if (tag_id >= MyHTML_TAG_LAST_ENTRY) { |
1648
|
0
|
|
|
|
|
|
tag_to = myhtml_tag_get_by_id(dest_tree->tags, src->tag_id); |
1649
|
0
|
|
|
|
|
|
tag_from = myhtml_tag_get_by_id(src->tree->tags, src->tag_id); |
1650
|
|
|
|
|
|
|
|
1651
|
0
|
0
|
|
|
|
|
if (tag_to == NULL |
1652
|
0
|
0
|
|
|
|
|
|| tag_to->name_length != tag_from->name_length |
1653
|
0
|
0
|
|
|
|
|
|| mycore_strncmp(tag_to->name, tag_from->name, tag_from->name_length) != 0) |
1654
|
|
|
|
|
|
|
{ |
1655
|
0
|
|
|
|
|
|
tag_id = myhtml_tag_add(dest_tree->tags, tag_from->name, tag_from->name_length, |
1656
|
|
|
|
|
|
|
MyHTML_TOKENIZER_STATE_DATA, true); |
1657
|
|
|
|
|
|
|
} |
1658
|
|
|
|
|
|
|
} |
1659
|
|
|
|
|
|
|
|
1660
|
0
|
|
|
|
|
|
new_node->token = myhtml_token_node_clone(dest_tree->token, src->token, |
1661
|
|
|
|
|
|
|
dest_tree->mcasync_rules_token_id, |
1662
|
|
|
|
|
|
|
dest_tree->mcasync_rules_attr_id); |
1663
|
0
|
|
|
|
|
|
new_node->tag_id = tag_id; |
1664
|
0
|
|
|
|
|
|
new_node->ns = src->ns; |
1665
|
|
|
|
|
|
|
|
1666
|
0
|
0
|
|
|
|
|
if(new_node->token) { |
1667
|
0
|
|
|
|
|
|
new_node->token->tag_id = tag_id; |
1668
|
0
|
|
|
|
|
|
new_node->token->type |= MyHTML_TOKEN_TYPE_DONE; |
1669
|
|
|
|
|
|
|
} |
1670
|
|
|
|
|
|
|
|
1671
|
0
|
|
|
|
|
|
return new_node; |
1672
|
|
|
|
|
|
|
} |
1673
|
|
|
|
|
|
|
|
1674
|
0
|
|
|
|
|
|
myhtml_tree_node_t * myhtml_node_clone_deep(myhtml_tree_t* dest_tree, myhtml_tree_node_t* src) |
1675
|
|
|
|
|
|
|
{ |
1676
|
|
|
|
|
|
|
myhtml_tree_node_t* cloned, *root, *node; |
1677
|
0
|
|
|
|
|
|
myhtml_tree_node_t* scope_node = src; |
1678
|
|
|
|
|
|
|
|
1679
|
0
|
0
|
|
|
|
|
if(scope_node && scope_node->tree && scope_node->tree->document == scope_node) { |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
1680
|
0
|
|
|
|
|
|
src = scope_node->child; |
1681
|
|
|
|
|
|
|
} |
1682
|
|
|
|
|
|
|
|
1683
|
0
|
|
|
|
|
|
root = node = myhtml_node_clone(dest_tree, src); |
1684
|
0
|
0
|
|
|
|
|
if (root == NULL) { |
1685
|
0
|
|
|
|
|
|
return NULL; |
1686
|
|
|
|
|
|
|
} |
1687
|
|
|
|
|
|
|
|
1688
|
0
|
|
|
|
|
|
src = src->child; |
1689
|
|
|
|
|
|
|
|
1690
|
0
|
0
|
|
|
|
|
while(src != NULL) { |
1691
|
0
|
|
|
|
|
|
cloned = myhtml_node_clone(dest_tree, src); |
1692
|
0
|
0
|
|
|
|
|
if (cloned == NULL) { |
1693
|
0
|
|
|
|
|
|
return NULL; |
1694
|
|
|
|
|
|
|
} |
1695
|
|
|
|
|
|
|
|
1696
|
0
|
|
|
|
|
|
myhtml_tree_node_add_child(node, cloned); |
1697
|
|
|
|
|
|
|
|
1698
|
0
|
0
|
|
|
|
|
if(src->child) { |
1699
|
0
|
|
|
|
|
|
src = src->child; |
1700
|
0
|
|
|
|
|
|
node = cloned; |
1701
|
|
|
|
|
|
|
} |
1702
|
|
|
|
|
|
|
else { |
1703
|
0
|
0
|
|
|
|
|
while(src != scope_node && src->next == NULL) { |
|
|
0
|
|
|
|
|
|
1704
|
0
|
|
|
|
|
|
node = node->parent; |
1705
|
0
|
|
|
|
|
|
src = src->parent; |
1706
|
|
|
|
|
|
|
} |
1707
|
|
|
|
|
|
|
|
1708
|
0
|
0
|
|
|
|
|
if(src == scope_node) { |
1709
|
0
|
|
|
|
|
|
break; |
1710
|
|
|
|
|
|
|
} |
1711
|
|
|
|
|
|
|
|
1712
|
0
|
|
|
|
|
|
src = src->next; |
1713
|
|
|
|
|
|
|
} |
1714
|
|
|
|
|
|
|
} |
1715
|
|
|
|
|
|
|
|
1716
|
0
|
|
|
|
|
|
return root; |
1717
|
|
|
|
|
|
|
} |