1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
/*
* This file is part of NetSurf, http://netsurf.sourceforge.net/
* Licensed under the GNU General Public License,
* http://www.opensource.org/licenses/gpl-license
* Copyright 2004 John M Bell <jmb202@ecs.soton.ac.uk>
*/
#include <stdbool.h>
#include <string.h>
#include "libxml/HTMLtree.h"
#include "oslib/osfile.h"
#include "netsurf/utils/config.h"
#include "netsurf/content/content.h"
#include "netsurf/riscos/save_text.h"
#include "netsurf/utils/log.h"
#include "netsurf/utils/utils.h"
#ifdef WITH_TEXT_EXPORT
static void extract_text(xmlDoc *doc);
static void extract_text_from_tree(xmlNode *n);
static char *buffer = 0;
static int output_size = 0;
void save_as_text(struct content *c, char *path) {
htmlParserCtxtPtr toSave;
if (c->type != CONTENT_HTML) {
return;
}
/* allocate a buffer the same size as the source
* the output is guaranteed to be less than this
*/
buffer = xcalloc(c->source_size, sizeof(char));
toSave = htmlCreateMemoryParserCtxt(c->source_data, c->source_size);
htmlParseDocument(toSave);
extract_text(toSave->myDoc);
if (output_size > 0) {
xosfile_save_stamped(path, 0xfff, (byte*)buffer,
(byte*)buffer+output_size);
}
xmlFreeDoc(toSave->myDoc);
htmlFreeParserCtxt(toSave);
xfree(buffer);
}
void extract_text(xmlDoc *doc)
{
xmlNode *html;
/* find the html element */
for (html = doc->children;
html!=0 && html->type != XML_ELEMENT_NODE;
html = html->next)
;
if (html == 0 || strcmp((const char*)html->name, "html") != 0) {
return;
}
extract_text_from_tree(html);
}
void extract_text_from_tree(xmlNode *n)
{
xmlNode *this;
char *text;
int len = 0;
int need_nl = 0;
if (n->type == XML_ELEMENT_NODE) {
if (strcmp(n->name, "dl") == 0 ||
strcmp(n->name, "h1") == 0 ||
strcmp(n->name, "h2") == 0 ||
strcmp(n->name, "h3") == 0 ||
strcmp(n->name, "ol") == 0 ||
strcmp(n->name, "title") == 0 ||
strcmp(n->name, "ul") == 0) {
need_nl = 2;
}
else if (strcmp(n->name, "applet") == 0 ||
strcmp(n->name, "br") == 0 ||
strcmp(n->name, "div") == 0 ||
strcmp(n->name, "dt") == 0 ||
strcmp(n->name, "h4") == 0 ||
strcmp(n->name, "h5") == 0 ||
strcmp(n->name, "h6") == 0 ||
strcmp(n->name, "li") == 0 ||
strcmp(n->name, "object") == 0 ||
strcmp(n->name, "p") == 0 ||
strcmp(n->name, "tr") == 0) {
need_nl = 1;
}
/* do nothing, we just recurse through these nodes */
}
else if (n->type == XML_TEXT_NODE) {
text = squash_tolat1(n->content);
len = strlen(text);
strcat(buffer, text);
output_size += len;
xfree(text);
return;
}
else {
return;
}
/* now recurse */
for (this = n->children; this != 0; this = this->next) {
extract_text_from_tree(this);
}
if (need_nl) {
for (len = 0; len != need_nl; len++) {
strcat(buffer, "\n");
output_size += 1;
}
}
}
#endif
|
