|
1
|
<?php
|
|
2
|
|
|
3
|
// $Id: search_convert.php 881 2008-11-22 15:51:23Z thorn $
|
|
4
|
|
|
5
|
/*
|
|
6
|
|
|
7
|
Website Baker Project <http://www.websitebaker.org/>
|
|
8
|
Copyright (C) 2004-2008, Ryan Djurovich
|
|
9
|
|
|
10
|
Website Baker is free software; you can redistribute it and/or modify
|
|
11
|
it under the terms of the GNU General Public License as published by
|
|
12
|
the Free Software Foundation; either version 2 of the License, or
|
|
13
|
(at your option) any later version.
|
|
14
|
|
|
15
|
Website Baker is distributed in the hope that it will be useful,
|
|
16
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
17
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
18
|
GNU General Public License for more details.
|
|
19
|
|
|
20
|
You should have received a copy of the GNU General Public License
|
|
21
|
along with Website Baker; if not, write to the Free Software
|
|
22
|
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
23
|
|
|
24
|
*/
|
|
25
|
|
|
26
|
/*
|
|
27
|
Character Conversion file
|
|
28
|
for search-/highlighting-related character-translations
|
|
29
|
*/
|
|
30
|
|
|
31
|
if(!defined('WB_URL')) {
|
|
32
|
header('Location: ../index.php');
|
|
33
|
exit(0);
|
|
34
|
}
|
|
35
|
if(!isset($search_lang)) $search_lang = LANGUAGE;
|
|
36
|
|
|
37
|
// umlaut to '(upper|lower)' for preg_match()
|
|
38
|
// this is UTF-8-encoded
|
|
39
|
// there is no need for a translation-table anymore since we use u-switch (utf-8) for preg-functions
|
|
40
|
// remember that we use the i-switch, too. [No need for (ae|Ae)]
|
|
41
|
|
|
42
|
$string_ul_umlaut = array();
|
|
43
|
$string_ul_regex = array();
|
|
44
|
|
|
45
|
// but add some national stuff
|
|
46
|
if($search_lang=='DE') { // add special handling for german umlauts (ä==ae, ...)
|
|
47
|
$string_ul_umlaut_add = array(
|
|
48
|
"\xc3\x9f", // german SZ-Ligatur
|
|
49
|
"\xc3\xa4", // german ae
|
|
50
|
"\xc3\xb6", // german oe
|
|
51
|
"\xc3\xbc", // german ue
|
|
52
|
"\xc3\x84", // german Ae
|
|
53
|
"\xc3\x96", // german Oe
|
|
54
|
"\xc3\x9c", // german Ue
|
|
55
|
// these are not that usual
|
|
56
|
"\xEF\xAC\x84", // german ffl-ligatur
|
|
57
|
"ffl", // german ffl-ligatur
|
|
58
|
"\xEF\xAC\x83", // german ffi-ligatur
|
|
59
|
"ffi", // german ffi-ligatur
|
|
60
|
"0xEF\xAC\x80", // german ff-Ligatur
|
|
61
|
"ff", // german ff-Ligatur
|
|
62
|
"\xEF\xAC\x81", // german fi-ligatur
|
|
63
|
"fi", // german fi-ligatur
|
|
64
|
"\xEF\xAC\x82", // german fl-ligatur
|
|
65
|
"fl", // german fl-ligatur
|
|
66
|
"\xEF\xAC\x85", // german st-Ligatur (long s)
|
|
67
|
"st", // german st-Ligatur
|
|
68
|
"\xEF\xAC\x86" // german st-ligatur (round-s)
|
|
69
|
);
|
|
70
|
$string_ul_regex_add = array(
|
|
71
|
"(\xc3\x9f|ss)", // german SZ.Ligatur
|
|
72
|
"(\xc3\xa4|ae)", // german ae
|
|
73
|
"(\xc3\xb6|oe)", // german oe
|
|
74
|
"(\xc3\xbc|ue)", // german ue
|
|
75
|
"(\xc3\x84|Ae)", // german Ae
|
|
76
|
"(\xc3\x96|Oe)", // german Oe
|
|
77
|
"(\xc3\x9c|Ue)", // german Ue
|
|
78
|
// these are not that usual
|
|
79
|
"(\xEF\xAC\x84|ffl)", // german ffl-ligatur
|
|
80
|
"(\xEF\xAC\x84|ffl)", // german ffl-ligatur
|
|
81
|
"(\xEF\xAC\x83|ffi)", // german ffi-ligatur
|
|
82
|
"(\xEF\xAC\x83|ffi)", // german ffi-ligatur
|
|
83
|
"(\xEF\xAC\x80|ff)", // german ff-Ligatur
|
|
84
|
"(\xEF\xAC\x80|ff)", // german ff-Ligatur
|
|
85
|
"(\xEF\xAC\x81|fi)", // german fi-Ligatur
|
|
86
|
"(\xEF\xAC\x81|fi)", // german fi-Ligatur
|
|
87
|
"(\xEF\xAC\x82|fl)", // german fl-ligatur
|
|
88
|
"(\xEF\xAC\x82|fl)", // german fl-ligatur
|
|
89
|
"(\xEF\xAC\x85|st)", // german st-Ligatur (long s)
|
|
90
|
"(\xEF\xAC\x85|st|\xEF\xAC\x86)", // german st-Ligaturs
|
|
91
|
"(\xEF\xAC\x86|st)" // german st-ligatur (round-s)
|
|
92
|
);
|
|
93
|
$string_ul_umlaut = array_merge($string_ul_umlaut_add, $string_ul_umlaut);
|
|
94
|
$string_ul_regex = array_merge($string_ul_regex_add, $string_ul_regex);
|
|
95
|
}
|
|
96
|
|
|
97
|
|
|
98
|
?>
|