|
a/src/internfile/mh_html.cpp |
|
b/src/internfile/mh_html.cpp |
| 1 |
/* htmlparse.cc: simple HTML parser for omega indexer
|
1 |
#ifndef lint
|
|
|
2 |
static char rcsid[] = "@(#$Id: mh_html.cpp,v 1.26 2008-10-03 06:17:46 dockes Exp $ (C) 2005 J.F.Dockes";
|
|
|
3 |
#endif
|
|
|
4 |
/*
|
|
|
5 |
* This program is free software; you can redistribute it and/or modify
|
|
|
6 |
* it under the terms of the GNU General Public License as published by
|
|
|
7 |
* the Free Software Foundation; either version 2 of the License, or
|
|
|
8 |
* (at your option) any later version.
|
| 2 |
*
|
9 |
*
|
| 3 |
* ----START-LICENCE----
|
10 |
* This program is distributed in the hope that it will be useful,
|
| 4 |
* Copyright 1999,2000,2001 BrightStation PLC
|
11 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
| 5 |
* Copyright 2001 Ananova Ltd
|
12 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
| 6 |
* Copyright 2002 Olly Betts
|
13 |
* GNU General Public License for more details.
|
| 7 |
*
|
14 |
*
|
| 8 |
* This program is free software; you can redistribute it and/or
|
|
|
| 9 |
* modify it under the terms of the GNU General Public License as
|
|
|
| 10 |
* published by the Free Software Foundation; either version 2 of the
|
|
|
| 11 |
* License, or (at your option) any later version.
|
|
|
| 12 |
*
|
|
|
| 13 |
* This program is distributed in the hope that it will be useful,
|
|
|
| 14 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
| 15 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
| 16 |
* GNU General Public License for more details.
|
|
|
| 17 |
*
|
|
|
| 18 |
* You should have received a copy of the GNU General Public License
|
15 |
* You should have received a copy of the GNU General Public License
|
| 19 |
* along with this program; if not, write to the Free Software
|
16 |
* along with this program; if not, write to the
|
|
|
17 |
* Free Software Foundation, Inc.,
|
| 20 |
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
|
18 |
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
| 21 |
* USA
|
|
|
| 22 |
* -----END-LICENCE-----
|
|
|
| 23 |
*/
|
19 |
*/
|
| 24 |
|
20 |
|
| 25 |
// This file has code from omindex + an adaptor function for recoll at the end
|
|
|
| 26 |
|
21 |
|
| 27 |
#include "mimehandler.h"
|
22 |
#include "mimehandler.h"
|
| 28 |
#include "debuglog.h"
|
23 |
#include "debuglog.h"
|
| 29 |
#include "csguess.h"
|
24 |
#include "csguess.h"
|
| 30 |
#include "readfile.h"
|
25 |
#include "readfile.h"
|
|
... |
|
... |
| 34 |
#include "indextext.h"
|
29 |
#include "indextext.h"
|
| 35 |
#include "mh_html.h"
|
30 |
#include "mh_html.h"
|
| 36 |
#include "smallut.h"
|
31 |
#include "smallut.h"
|
| 37 |
|
32 |
|
| 38 |
#include <iostream>
|
33 |
#include <iostream>
|
|
|
34 |
|
| 39 |
#ifndef NO_NAMESPACES
|
35 |
#ifndef NO_NAMESPACES
|
| 40 |
using namespace std;
|
36 |
using namespace std;
|
| 41 |
#endif /* NO_NAMESPACES */
|
37 |
#endif /* NO_NAMESPACES */
|
| 42 |
|
38 |
|
| 43 |
|
39 |
|
| 44 |
bool MimeHandlerHtml::set_document_file(const string &fn)
|
40 |
bool MimeHandlerHtml::set_document_file(const string &fn)
|
| 45 |
{
|
41 |
{
|
| 46 |
LOGDEB(("textHtmlToDoc: %s\n", fn.c_str()));
|
42 |
LOGDEB0(("textHtmlToDoc: %s\n", fn.c_str()));
|
| 47 |
string otext;
|
43 |
string otext;
|
| 48 |
if (!file_to_string(fn, otext)) {
|
44 |
if (!file_to_string(fn, otext)) {
|
| 49 |
LOGINFO(("textHtmlToDoc: cant read: %s\n", fn.c_str()));
|
45 |
LOGINFO(("textHtmlToDoc: cant read: %s\n", fn.c_str()));
|
| 50 |
return false;
|
46 |
return false;
|
| 51 |
}
|
47 |
}
|
|
... |
|
... |
| 117 |
break;
|
113 |
break;
|
| 118 |
} catch (bool diag) {
|
114 |
} catch (bool diag) {
|
| 119 |
result = p;
|
115 |
result = p;
|
| 120 |
if (diag == true) {
|
116 |
if (diag == true) {
|
| 121 |
// Parser throws true at end of text. ok
|
117 |
// Parser throws true at end of text. ok
|
|
|
118 |
|
|
|
119 |
if (m_forPreview) {
|
|
|
120 |
// Save the html text
|
|
|
121 |
m_html = transcoded;
|
|
|
122 |
// In many cases, we need to change the charset decl,
|
|
|
123 |
// because the file was transcoded. It seems that just
|
|
|
124 |
// inserting one is enough (only the 1st one seems to
|
|
|
125 |
// be used by browsers/qtextedit).
|
|
|
126 |
unsigned int idx = m_html.find("<head>");
|
|
|
127 |
if (idx == string::npos)
|
|
|
128 |
idx = m_html.find("<HEAD>");
|
|
|
129 |
if (idx != string::npos)
|
|
|
130 |
m_html.replace(idx+6, 0,
|
|
|
131 |
"<meta http-equiv=\"content-type\" "
|
|
|
132 |
"content=\"text/html; charset=utf-8\">");
|
|
|
133 |
}
|
|
|
134 |
|
| 122 |
break;
|
135 |
break;
|
| 123 |
}
|
136 |
}
|
| 124 |
|
137 |
|
| 125 |
LOGDEB(("textHtmlToDoc: charset [%s] doc charset [%s]\n",
|
138 |
LOGDEB(("textHtmlToDoc: charset [%s] doc charset [%s]\n",
|
| 126 |
charset.c_str(), result.get_charset().c_str()));
|
139 |
charset.c_str(), result.get_charset().c_str()));
|