1 /***************************************************************************
2 * Copyright (C) 2008-2014 by Andrzej Rybczak *
3 * electricityispower@gmail.com *
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. *
10 * This program is distributed in the hope that it will be useful, *
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of *
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
13 * GNU General Public License for more details. *
15 * You should have received a copy of the GNU General Public License *
16 * along with this program; if not, write to the *
17 * Free Software Foundation, Inc., *
18 * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. *
19 ***************************************************************************/
21 #include <boost/algorithm/string/replace.hpp>
22 #include "utility/html.h"
23 //#include "utility/string.h"
25 std::string
unescapeHtmlUtf8(const std::string
&data
)
28 for (size_t i
= 0, j
; i
< data
.length(); ++i
)
30 if (data
[i
] == '&' && data
[i
+1] == '#' && (j
= data
.find(';', i
)) != std::string::npos
)
32 int n
= atoi(&data
.c_str()[i
+2]);
35 result
+= (0xe0 | ((n
>> 12) & 0x0f));
36 result
+= (0x80 | ((n
>> 6) & 0x3f));
37 result
+= (0x80 | (n
& 0x3f));
41 result
+= (0xc0 | ((n
>> 6) & 0x1f));
42 result
+= (0x80 | (n
& 0x3f));
54 void stripHtmlTags(std::string
&s
)
57 for (size_t i
= s
.find("<"); i
!= std::string::npos
; i
= s
.find("<"))
59 size_t j
= s
.find(">", i
)+1;
60 s
.replace(i
, j
-i
, "");
62 boost::replace_all(s
, "'", "'");
63 boost::replace_all(s
, "&", "&");
64 boost::replace_all(s
, """, "\"");
65 boost::replace_all(s
, " ", " ");
66 for (size_t i
= 0; i
< s
.length(); ++i
)
73 if (s
[i
] == 13) // ascii code for windows line ending, get rid of this shit
78 else if (s
[i
] == '\t')