[project @ 2004-05-22 13:45:20 by joty]

Renamed "this" variable (avoiding C++ keywords); simplified code a little bit.

svn path=/import/netsurf/; revision=886
This commit is contained in:
John Tytgat 2004-05-22 13:45:20 +00:00
parent 9644508737
commit d36e4314be

View File

@ -1,7 +1,7 @@
/*
* This file is part of NetSurf, http://netsurf.sourceforge.net/
* Licensed under the GNU General Public License,
* http://www.opensource.org/licenses/gpl-license
* http://www.opensource.org/licenses/gpl-license
* Copyright 2004 John M Bell <jmb202@ecs.soton.ac.uk>
*/
@ -25,21 +25,21 @@ static FILE *out;
void save_as_text(struct content *c, char *path) {
htmlParserCtxtPtr toSave;
htmlParserCtxtPtr toSave;
if (c->type != CONTENT_HTML) {
return;
}
out = fopen(path, "w");
if (!out) return;
out = fopen(path, "w");
if (!out) return;
toSave = htmlCreateMemoryParserCtxt(c->source_data, c->source_size);
htmlParseDocument(toSave);
extract_text(toSave->myDoc);
fclose(out);
fclose(out);
xmlFreeDoc(toSave->myDoc);
htmlFreeParserCtxt(toSave);
@ -47,71 +47,69 @@ void save_as_text(struct content *c, char *path) {
void extract_text(xmlDoc *doc)
{
xmlNode *html;
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;
}
/* 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);
extract_text_from_tree(html);
}
void extract_text_from_tree(xmlNode *n)
{
xmlNode *this;
char *text;
int len, need_nl = 0;
xmlNode *this_node;
const char *text;
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);
fprintf(out, "%s", text);
xfree(text);
return;
}
else {
return;
}
/* now recurse */
for (this = n->children; this != 0; this = this->next) {
extract_text_from_tree(this);
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) {
if ((text = squash_tolat1(n->content)) != NULL) {
fputs(text, out);
free(text);
}
return;
}
else {
return;
}
if (need_nl) {
for (len = 0; len != need_nl; len++) {
fprintf(out, "\n");
}
/* now recurse */
for (this_node = n->children; this_node != 0; this_node = this_node->next) {
extract_text_from_tree(this_node);
}
while (need_nl--)
fputc('\n', out);
}
#endif