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/tokenizer_script.h" |
22
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
|
24
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
25
|
|
|
|
|
|
|
{ |
26
|
0
|
0
|
|
|
|
|
while (html_offset < html_size) |
27
|
|
|
|
|
|
|
{ |
28
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '<') { |
29
|
0
|
|
|
|
|
|
token_node->element_begin = (tree->global_offset + html_offset); |
30
|
|
|
|
|
|
|
|
31
|
0
|
|
|
|
|
|
html_offset++; |
32
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_LESS_THAN_SIGN; |
33
|
|
|
|
|
|
|
|
34
|
0
|
|
|
|
|
|
break; |
35
|
|
|
|
|
|
|
} |
36
|
|
|
|
|
|
|
|
37
|
0
|
|
|
|
|
|
html_offset++; |
38
|
|
|
|
|
|
|
} |
39
|
|
|
|
|
|
|
|
40
|
0
|
|
|
|
|
|
return html_offset; |
41
|
|
|
|
|
|
|
} |
42
|
|
|
|
|
|
|
|
43
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
44
|
|
|
|
|
|
|
{ |
45
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '/') |
46
|
|
|
|
|
|
|
{ |
47
|
0
|
|
|
|
|
|
html_offset++; |
48
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_END_TAG_OPEN; |
49
|
|
|
|
|
|
|
} |
50
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '!') |
51
|
|
|
|
|
|
|
{ |
52
|
0
|
|
|
|
|
|
html_offset++; |
53
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPE_START; |
54
|
|
|
|
|
|
|
} |
55
|
|
|
|
|
|
|
else { |
56
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
57
|
|
|
|
|
|
|
} |
58
|
|
|
|
|
|
|
|
59
|
0
|
|
|
|
|
|
return html_offset; |
60
|
|
|
|
|
|
|
} |
61
|
|
|
|
|
|
|
|
62
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escape_start(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
63
|
|
|
|
|
|
|
{ |
64
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') { |
65
|
0
|
|
|
|
|
|
html_offset++; |
66
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPE_START_DASH; |
67
|
|
|
|
|
|
|
} |
68
|
|
|
|
|
|
|
else { |
69
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
70
|
|
|
|
|
|
|
} |
71
|
|
|
|
|
|
|
|
72
|
0
|
|
|
|
|
|
return html_offset; |
73
|
|
|
|
|
|
|
} |
74
|
|
|
|
|
|
|
|
75
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escape_start_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
76
|
|
|
|
|
|
|
{ |
77
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') { |
78
|
0
|
|
|
|
|
|
html_offset++; |
79
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_DASH_DASH; |
80
|
|
|
|
|
|
|
} |
81
|
|
|
|
|
|
|
else { |
82
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
83
|
|
|
|
|
|
|
} |
84
|
|
|
|
|
|
|
|
85
|
0
|
|
|
|
|
|
return html_offset; |
86
|
|
|
|
|
|
|
} |
87
|
|
|
|
|
|
|
|
88
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
89
|
|
|
|
|
|
|
{ |
90
|
0
|
0
|
|
|
|
|
if(myhtml_ascii_char_cmp(html[html_offset])) { |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
91
|
0
|
|
|
|
|
|
token_node->str.length = (html_offset + tree->global_offset); |
92
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_END_TAG_NAME; |
93
|
|
|
|
|
|
|
} |
94
|
|
|
|
|
|
|
else { |
95
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
96
|
|
|
|
|
|
|
} |
97
|
|
|
|
|
|
|
|
98
|
0
|
|
|
|
|
|
return html_offset; |
99
|
|
|
|
|
|
|
} |
100
|
|
|
|
|
|
|
|
101
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
102
|
|
|
|
|
|
|
{ |
103
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
104
|
|
|
|
|
|
|
{ |
105
|
0
|
0
|
|
|
|
|
if(myhtml_whithspace(html[html_offset], ==, ||)) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
106
|
|
|
|
|
|
|
{ |
107
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
108
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
109
|
0
|
|
|
|
|
|
html_offset++; |
110
|
0
|
|
|
|
|
|
break; |
111
|
|
|
|
|
|
|
} |
112
|
|
|
|
|
|
|
|
113
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
114
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
115
|
|
|
|
|
|
|
|
116
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
117
|
|
|
|
|
|
|
{ |
118
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
119
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
120
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
121
|
0
|
|
|
|
|
|
return 0; |
122
|
|
|
|
|
|
|
} |
123
|
|
|
|
|
|
|
|
124
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
125
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
126
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
127
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE; |
128
|
|
|
|
|
|
|
|
129
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_BEFORE_ATTRIBUTE_NAME; |
130
|
|
|
|
|
|
|
} |
131
|
|
|
|
|
|
|
else { |
132
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
133
|
|
|
|
|
|
|
} |
134
|
|
|
|
|
|
|
|
135
|
0
|
|
|
|
|
|
html_offset++; |
136
|
0
|
|
|
|
|
|
break; |
137
|
|
|
|
|
|
|
} |
138
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '/') |
139
|
|
|
|
|
|
|
{ |
140
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
141
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
142
|
0
|
|
|
|
|
|
html_offset++; |
143
|
0
|
|
|
|
|
|
break; |
144
|
|
|
|
|
|
|
} |
145
|
|
|
|
|
|
|
|
146
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
147
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
148
|
|
|
|
|
|
|
|
149
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
150
|
|
|
|
|
|
|
{ |
151
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
152
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
153
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
154
|
0
|
|
|
|
|
|
return 0; |
155
|
|
|
|
|
|
|
} |
156
|
|
|
|
|
|
|
|
157
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
158
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
159
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
160
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE|MyHTML_TOKEN_TYPE_CLOSE_SELF; |
161
|
|
|
|
|
|
|
|
162
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_BEFORE_ATTRIBUTE_NAME; |
163
|
|
|
|
|
|
|
} |
164
|
|
|
|
|
|
|
else { |
165
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
166
|
|
|
|
|
|
|
} |
167
|
|
|
|
|
|
|
|
168
|
0
|
|
|
|
|
|
html_offset++; |
169
|
0
|
|
|
|
|
|
break; |
170
|
|
|
|
|
|
|
} |
171
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '>') |
172
|
|
|
|
|
|
|
{ |
173
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
174
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
175
|
0
|
|
|
|
|
|
html_offset++; |
176
|
0
|
|
|
|
|
|
break; |
177
|
|
|
|
|
|
|
} |
178
|
|
|
|
|
|
|
|
179
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
180
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
181
|
|
|
|
|
|
|
|
182
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
183
|
|
|
|
|
|
|
{ |
184
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
185
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
186
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
187
|
0
|
|
|
|
|
|
return 0; |
188
|
|
|
|
|
|
|
} |
189
|
|
|
|
|
|
|
|
190
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
191
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
192
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
193
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE; |
194
|
|
|
|
|
|
|
|
195
|
0
|
|
|
|
|
|
html_offset++; |
196
|
|
|
|
|
|
|
|
197
|
0
|
|
|
|
|
|
token_node->element_length = (tree->global_offset + html_offset) - token_node->element_begin; |
198
|
|
|
|
|
|
|
|
199
|
0
|
0
|
|
|
|
|
if(myhtml_queue_add(tree, html_offset, token_node) != MyHTML_STATUS_OK) { |
200
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
201
|
0
|
|
|
|
|
|
return 0; |
202
|
|
|
|
|
|
|
} |
203
|
|
|
|
|
|
|
|
204
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_DATA; |
205
|
|
|
|
|
|
|
} |
206
|
|
|
|
|
|
|
else { |
207
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
208
|
0
|
|
|
|
|
|
html_offset++; |
209
|
|
|
|
|
|
|
} |
210
|
|
|
|
|
|
|
|
211
|
0
|
|
|
|
|
|
break; |
212
|
|
|
|
|
|
|
} |
213
|
0
|
0
|
|
|
|
|
else if(myhtml_ascii_char_unless_cmp(html[html_offset])) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
214
|
|
|
|
|
|
|
{ |
215
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
216
|
0
|
|
|
|
|
|
break; |
217
|
|
|
|
|
|
|
} |
218
|
|
|
|
|
|
|
|
219
|
0
|
|
|
|
|
|
html_offset++; |
220
|
|
|
|
|
|
|
} |
221
|
|
|
|
|
|
|
|
222
|
0
|
|
|
|
|
|
return html_offset; |
223
|
|
|
|
|
|
|
} |
224
|
|
|
|
|
|
|
|
225
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped_dash_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
226
|
|
|
|
|
|
|
{ |
227
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') { |
228
|
0
|
|
|
|
|
|
html_offset++; |
229
|
0
|
|
|
|
|
|
return html_offset; |
230
|
|
|
|
|
|
|
} |
231
|
|
|
|
|
|
|
|
232
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '<') { |
233
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; |
234
|
|
|
|
|
|
|
} |
235
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '>') { |
236
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
237
|
|
|
|
|
|
|
} |
238
|
|
|
|
|
|
|
else { |
239
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
240
|
|
|
|
|
|
|
} |
241
|
|
|
|
|
|
|
|
242
|
0
|
|
|
|
|
|
html_offset++; |
243
|
|
|
|
|
|
|
|
244
|
0
|
|
|
|
|
|
return html_offset; |
245
|
|
|
|
|
|
|
} |
246
|
|
|
|
|
|
|
|
247
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
248
|
|
|
|
|
|
|
{ |
249
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '/') { |
250
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_END_TAG_OPEN; |
251
|
0
|
|
|
|
|
|
html_offset++; |
252
|
|
|
|
|
|
|
} |
253
|
0
|
0
|
|
|
|
|
else if(myhtml_ascii_char_cmp(html[html_offset])) { |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
254
|
0
|
|
|
|
|
|
token_node->str.length = (html_offset + tree->global_offset); |
255
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPE_START; |
256
|
|
|
|
|
|
|
} |
257
|
|
|
|
|
|
|
else { |
258
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
259
|
|
|
|
|
|
|
} |
260
|
|
|
|
|
|
|
|
261
|
0
|
|
|
|
|
|
return html_offset; |
262
|
|
|
|
|
|
|
} |
263
|
|
|
|
|
|
|
|
264
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped_end_tag_open(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
265
|
|
|
|
|
|
|
{ |
266
|
0
|
0
|
|
|
|
|
if(myhtml_ascii_char_cmp(html[html_offset])) { |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
267
|
0
|
|
|
|
|
|
token_node->str.length = (html_offset + tree->global_offset); |
268
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_END_TAG_NAME; |
269
|
|
|
|
|
|
|
} |
270
|
|
|
|
|
|
|
else { |
271
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
272
|
|
|
|
|
|
|
} |
273
|
|
|
|
|
|
|
|
274
|
0
|
|
|
|
|
|
return html_offset; |
275
|
|
|
|
|
|
|
} |
276
|
|
|
|
|
|
|
|
277
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped_end_tag_name(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
278
|
|
|
|
|
|
|
{ |
279
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
280
|
|
|
|
|
|
|
{ |
281
|
0
|
0
|
|
|
|
|
if(myhtml_whithspace(html[html_offset], ==, ||)) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
282
|
|
|
|
|
|
|
{ |
283
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
284
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
285
|
0
|
|
|
|
|
|
html_offset++; |
286
|
0
|
|
|
|
|
|
break; |
287
|
|
|
|
|
|
|
} |
288
|
|
|
|
|
|
|
|
289
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
290
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
291
|
|
|
|
|
|
|
|
292
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
293
|
|
|
|
|
|
|
{ |
294
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
295
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
296
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
297
|
0
|
|
|
|
|
|
return 0; |
298
|
|
|
|
|
|
|
} |
299
|
|
|
|
|
|
|
|
300
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
301
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
302
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
303
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE; |
304
|
|
|
|
|
|
|
|
305
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_BEFORE_ATTRIBUTE_NAME; |
306
|
|
|
|
|
|
|
} |
307
|
|
|
|
|
|
|
else { |
308
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
309
|
|
|
|
|
|
|
} |
310
|
|
|
|
|
|
|
|
311
|
0
|
|
|
|
|
|
html_offset++; |
312
|
0
|
|
|
|
|
|
break; |
313
|
|
|
|
|
|
|
} |
314
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '/') |
315
|
|
|
|
|
|
|
{ |
316
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
317
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
318
|
0
|
|
|
|
|
|
html_offset++; |
319
|
0
|
|
|
|
|
|
break; |
320
|
|
|
|
|
|
|
} |
321
|
|
|
|
|
|
|
|
322
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
323
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
324
|
|
|
|
|
|
|
|
325
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
326
|
|
|
|
|
|
|
{ |
327
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
328
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
329
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
330
|
0
|
|
|
|
|
|
return 0; |
331
|
|
|
|
|
|
|
} |
332
|
|
|
|
|
|
|
|
333
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
334
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
335
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
336
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE|MyHTML_TOKEN_TYPE_CLOSE_SELF; |
337
|
|
|
|
|
|
|
|
338
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_BEFORE_ATTRIBUTE_NAME; |
339
|
|
|
|
|
|
|
} |
340
|
|
|
|
|
|
|
else { |
341
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
342
|
|
|
|
|
|
|
} |
343
|
|
|
|
|
|
|
|
344
|
0
|
|
|
|
|
|
html_offset++; |
345
|
0
|
|
|
|
|
|
break; |
346
|
|
|
|
|
|
|
} |
347
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '>') |
348
|
|
|
|
|
|
|
{ |
349
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
350
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
351
|
0
|
|
|
|
|
|
html_offset++; |
352
|
0
|
|
|
|
|
|
break; |
353
|
|
|
|
|
|
|
} |
354
|
|
|
|
|
|
|
|
355
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
356
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
357
|
|
|
|
|
|
|
|
358
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) |
359
|
|
|
|
|
|
|
{ |
360
|
0
|
|
|
|
|
|
token_node = myhtml_tokenizer_queue_create_text_node_if_need(tree, token_node, html, ((html_offset + tree->global_offset) - 8), MyHTML_TOKEN_TYPE_SCRIPT); |
361
|
0
|
0
|
|
|
|
|
if(token_node == NULL) { |
362
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
363
|
0
|
|
|
|
|
|
return 0; |
364
|
|
|
|
|
|
|
} |
365
|
|
|
|
|
|
|
|
366
|
0
|
|
|
|
|
|
token_node->raw_begin = tmp_size; |
367
|
0
|
|
|
|
|
|
token_node->raw_length = 6; |
368
|
0
|
|
|
|
|
|
token_node->tag_id = MyHTML_TAG_SCRIPT; |
369
|
0
|
|
|
|
|
|
token_node->type = MyHTML_TOKEN_TYPE_CLOSE; |
370
|
|
|
|
|
|
|
|
371
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_DATA; |
372
|
|
|
|
|
|
|
|
373
|
0
|
|
|
|
|
|
html_offset++; |
374
|
|
|
|
|
|
|
|
375
|
0
|
|
|
|
|
|
token_node->element_length = (tree->global_offset + html_offset) - token_node->element_begin; |
376
|
|
|
|
|
|
|
|
377
|
0
|
0
|
|
|
|
|
if(myhtml_queue_add(tree, html_offset, token_node) != MyHTML_STATUS_OK) { |
378
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_PARSE_ERROR_STOP; |
379
|
0
|
|
|
|
|
|
return 0; |
380
|
|
|
|
|
|
|
} |
381
|
|
|
|
|
|
|
} |
382
|
|
|
|
|
|
|
else { |
383
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
384
|
0
|
|
|
|
|
|
html_offset++; |
385
|
|
|
|
|
|
|
} |
386
|
0
|
|
|
|
|
|
break; |
387
|
|
|
|
|
|
|
} |
388
|
0
|
0
|
|
|
|
|
else if(myhtml_ascii_char_unless_cmp(html[html_offset])) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
389
|
|
|
|
|
|
|
{ |
390
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
391
|
0
|
|
|
|
|
|
break; |
392
|
|
|
|
|
|
|
} |
393
|
|
|
|
|
|
|
|
394
|
0
|
|
|
|
|
|
html_offset++; |
395
|
|
|
|
|
|
|
} |
396
|
|
|
|
|
|
|
|
397
|
0
|
|
|
|
|
|
return html_offset; |
398
|
|
|
|
|
|
|
} |
399
|
|
|
|
|
|
|
|
400
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
401
|
|
|
|
|
|
|
{ |
402
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
403
|
|
|
|
|
|
|
{ |
404
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') |
405
|
|
|
|
|
|
|
{ |
406
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_DASH; |
407
|
0
|
|
|
|
|
|
html_offset++; |
408
|
0
|
|
|
|
|
|
break; |
409
|
|
|
|
|
|
|
} |
410
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '<') |
411
|
|
|
|
|
|
|
{ |
412
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; |
413
|
0
|
|
|
|
|
|
html_offset++; |
414
|
0
|
|
|
|
|
|
break; |
415
|
|
|
|
|
|
|
} |
416
|
|
|
|
|
|
|
|
417
|
0
|
|
|
|
|
|
html_offset++; |
418
|
|
|
|
|
|
|
} |
419
|
|
|
|
|
|
|
|
420
|
0
|
|
|
|
|
|
return html_offset; |
421
|
|
|
|
|
|
|
} |
422
|
|
|
|
|
|
|
|
423
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_escaped_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
424
|
|
|
|
|
|
|
{ |
425
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') { |
426
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_DASH_DASH; |
427
|
0
|
|
|
|
|
|
html_offset++; |
428
|
|
|
|
|
|
|
} |
429
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '<') { |
430
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; |
431
|
|
|
|
|
|
|
} |
432
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '\0') { |
433
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
434
|
|
|
|
|
|
|
} |
435
|
|
|
|
|
|
|
else { |
436
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
437
|
0
|
|
|
|
|
|
html_offset++; |
438
|
|
|
|
|
|
|
} |
439
|
|
|
|
|
|
|
|
440
|
0
|
|
|
|
|
|
return html_offset; |
441
|
|
|
|
|
|
|
} |
442
|
|
|
|
|
|
|
|
443
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escape_start(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
444
|
|
|
|
|
|
|
{ |
445
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
446
|
|
|
|
|
|
|
{ |
447
|
0
|
0
|
|
|
|
|
if(myhtml_whithspace(html[html_offset], ==, ||) || html[html_offset] == '/' || html[html_offset] == '>') |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
448
|
|
|
|
|
|
|
{ |
449
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
450
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
451
|
0
|
|
|
|
|
|
html_offset++; |
452
|
0
|
|
|
|
|
|
break; |
453
|
|
|
|
|
|
|
} |
454
|
|
|
|
|
|
|
|
455
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
456
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
457
|
|
|
|
|
|
|
|
458
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) { |
459
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
460
|
|
|
|
|
|
|
} |
461
|
|
|
|
|
|
|
else { |
462
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
463
|
|
|
|
|
|
|
} |
464
|
|
|
|
|
|
|
|
465
|
0
|
|
|
|
|
|
html_offset++; |
466
|
0
|
|
|
|
|
|
break; |
467
|
|
|
|
|
|
|
} |
468
|
0
|
0
|
|
|
|
|
else if(myhtml_ascii_char_unless_cmp(html[html_offset])) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
469
|
|
|
|
|
|
|
{ |
470
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
471
|
0
|
|
|
|
|
|
break; |
472
|
|
|
|
|
|
|
} |
473
|
|
|
|
|
|
|
|
474
|
0
|
|
|
|
|
|
html_offset++; |
475
|
|
|
|
|
|
|
} |
476
|
|
|
|
|
|
|
|
477
|
0
|
|
|
|
|
|
return html_offset; |
478
|
|
|
|
|
|
|
} |
479
|
|
|
|
|
|
|
|
480
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escaped(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
481
|
|
|
|
|
|
|
{ |
482
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
483
|
|
|
|
|
|
|
{ |
484
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') |
485
|
|
|
|
|
|
|
{ |
486
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH; |
487
|
0
|
|
|
|
|
|
html_offset++; |
488
|
0
|
|
|
|
|
|
break; |
489
|
|
|
|
|
|
|
} |
490
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '<') |
491
|
|
|
|
|
|
|
{ |
492
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; |
493
|
0
|
|
|
|
|
|
html_offset++; |
494
|
0
|
|
|
|
|
|
break; |
495
|
|
|
|
|
|
|
} |
496
|
|
|
|
|
|
|
|
497
|
0
|
|
|
|
|
|
html_offset++; |
498
|
|
|
|
|
|
|
} |
499
|
|
|
|
|
|
|
|
500
|
0
|
|
|
|
|
|
return html_offset; |
501
|
|
|
|
|
|
|
} |
502
|
|
|
|
|
|
|
|
503
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escaped_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
504
|
|
|
|
|
|
|
{ |
505
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') |
506
|
|
|
|
|
|
|
{ |
507
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH; |
508
|
|
|
|
|
|
|
} |
509
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '<') |
510
|
|
|
|
|
|
|
{ |
511
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; |
512
|
|
|
|
|
|
|
} |
513
|
|
|
|
|
|
|
else { |
514
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
515
|
|
|
|
|
|
|
} |
516
|
|
|
|
|
|
|
|
517
|
0
|
|
|
|
|
|
html_offset++; |
518
|
|
|
|
|
|
|
|
519
|
0
|
|
|
|
|
|
return html_offset; |
520
|
|
|
|
|
|
|
} |
521
|
|
|
|
|
|
|
|
522
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escaped_dash_dash(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
523
|
|
|
|
|
|
|
{ |
524
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '-') { |
525
|
0
|
|
|
|
|
|
html_offset++; |
526
|
0
|
|
|
|
|
|
return html_offset; |
527
|
|
|
|
|
|
|
} |
528
|
|
|
|
|
|
|
|
529
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '<') |
530
|
|
|
|
|
|
|
{ |
531
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; |
532
|
|
|
|
|
|
|
} |
533
|
0
|
0
|
|
|
|
|
else if(html[html_offset] == '>') |
534
|
|
|
|
|
|
|
{ |
535
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA; |
536
|
|
|
|
|
|
|
} |
537
|
|
|
|
|
|
|
else { |
538
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
539
|
|
|
|
|
|
|
} |
540
|
|
|
|
|
|
|
|
541
|
0
|
|
|
|
|
|
html_offset++; |
542
|
|
|
|
|
|
|
|
543
|
0
|
|
|
|
|
|
return html_offset; |
544
|
|
|
|
|
|
|
} |
545
|
|
|
|
|
|
|
|
546
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escaped_less_than_sign(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
547
|
|
|
|
|
|
|
{ |
548
|
0
|
0
|
|
|
|
|
if(html[html_offset] == '/') { |
549
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END; |
550
|
0
|
|
|
|
|
|
html_offset++; |
551
|
|
|
|
|
|
|
|
552
|
0
|
|
|
|
|
|
token_node->str.length = (html_offset + tree->global_offset); |
553
|
|
|
|
|
|
|
} |
554
|
|
|
|
|
|
|
else { |
555
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
556
|
|
|
|
|
|
|
} |
557
|
|
|
|
|
|
|
|
558
|
0
|
|
|
|
|
|
return html_offset; |
559
|
|
|
|
|
|
|
} |
560
|
|
|
|
|
|
|
|
561
|
0
|
|
|
|
|
|
size_t myhtml_tokenizer_state_script_data_double_escape_end(myhtml_tree_t* tree, myhtml_token_node_t* token_node, const char* html, size_t html_offset, size_t html_size) |
562
|
|
|
|
|
|
|
{ |
563
|
0
|
0
|
|
|
|
|
while(html_offset < html_size) |
564
|
|
|
|
|
|
|
{ |
565
|
0
|
0
|
|
|
|
|
if(myhtml_whithspace(html[html_offset], ==, ||) || html[html_offset] == '/' || html[html_offset] == '>') |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
566
|
|
|
|
|
|
|
{ |
567
|
0
|
0
|
|
|
|
|
if(((html_offset + tree->global_offset) - token_node->str.length) != 6) { |
568
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
569
|
0
|
|
|
|
|
|
html_offset++; |
570
|
0
|
|
|
|
|
|
break; |
571
|
|
|
|
|
|
|
} |
572
|
|
|
|
|
|
|
|
573
|
0
|
|
|
|
|
|
size_t tmp_size = token_node->str.length; |
574
|
0
|
|
|
|
|
|
const char *tem_name = myhtml_tree_incomming_buffer_make_data(tree, tmp_size, 6); |
575
|
|
|
|
|
|
|
|
576
|
0
|
0
|
|
|
|
|
if(mycore_strncasecmp(tem_name, "script", 6) == 0) { |
577
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_ESCAPED; |
578
|
|
|
|
|
|
|
} |
579
|
|
|
|
|
|
|
else { |
580
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
581
|
|
|
|
|
|
|
} |
582
|
|
|
|
|
|
|
|
583
|
0
|
|
|
|
|
|
html_offset++; |
584
|
0
|
|
|
|
|
|
break; |
585
|
|
|
|
|
|
|
} |
586
|
0
|
0
|
|
|
|
|
else if(myhtml_ascii_char_unless_cmp(html[html_offset])) |
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
587
|
|
|
|
|
|
|
{ |
588
|
0
|
|
|
|
|
|
myhtml_tokenizer_state_set(tree) = MyHTML_TOKENIZER_STATE_SCRIPT_DATA_DOUBLE_ESCAPED; |
589
|
0
|
|
|
|
|
|
break; |
590
|
|
|
|
|
|
|
} |
591
|
|
|
|
|
|
|
|
592
|
0
|
|
|
|
|
|
html_offset++; |
593
|
|
|
|
|
|
|
} |
594
|
|
|
|
|
|
|
|
595
|
0
|
|
|
|
|
|
return html_offset; |
596
|
|
|
|
|
|
|
} |
597
|
|
|
|
|
|
|
|
598
|
|
|
|
|
|
|
|
599
|
|
|
|
|
|
|
|
600
|
|
|
|
|
|
|
|