1
|
|
|
<?php |
2
|
|
|
/* |
3
|
|
|
* This file is a part of HDS (HeBIS Discovery System). HDS is an |
4
|
|
|
* extension of the open source library search engine VuFind, that |
5
|
|
|
* allows users to search and browse beyond resources. More |
6
|
|
|
* Information about VuFind you will find on http://www.vufind.org |
7
|
|
|
* |
8
|
|
|
* Copyright (C) 2016 |
9
|
|
|
* HeBIS Verbundzentrale des HeBIS-Verbundes |
10
|
|
|
* Goethe-Universität Frankfurt / Goethe University of Frankfurt |
11
|
|
|
* http://www.hebis.de |
12
|
|
|
* |
13
|
|
|
* This program is free software; you can redistribute it and/or |
14
|
|
|
* modify it under the terms of the GNU General Public License |
15
|
|
|
* as published by the Free Software Foundation; either version 2 |
16
|
|
|
* of the License, or (at your option) any later version. |
17
|
|
|
* |
18
|
|
|
* This program is distributed in the hope that it will be useful, |
19
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
20
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
21
|
|
|
* GNU General Public License for more details. |
22
|
|
|
* |
23
|
|
|
* You should have received a copy of the GNU General Public License |
24
|
|
|
* along with this program; if not, write to the Free Software |
25
|
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
26
|
|
|
*/ |
27
|
|
|
|
28
|
|
|
namespace Seboettg\CiteProc\Util; |
29
|
|
|
|
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* Class StringHelper |
33
|
|
|
* @package Seboettg\CiteProc\Util |
34
|
|
|
* |
35
|
|
|
* @author Sebastian Böttger <[email protected]> |
36
|
|
|
*/ |
37
|
|
|
class StringHelper |
38
|
|
|
{ |
39
|
|
|
|
40
|
|
|
const PREPOSITIONS = [ |
41
|
|
|
'on', 'in', 'at', 'since', 'for', 'ago', 'before', 'to', 'past', 'till', 'until', 'by', 'under', 'below', 'over', |
42
|
|
|
'above', 'across', 'through', 'into', 'towards', 'onto', 'from', 'of', 'off', 'about', 'via' |
43
|
|
|
]; |
44
|
|
|
|
45
|
|
|
const ARTICLES = [ |
46
|
|
|
'a', 'an', 'the' |
47
|
|
|
]; |
48
|
|
|
|
49
|
|
|
const ADVERBS = [ |
50
|
|
|
'yet', 'so', 'just', 'only' |
51
|
|
|
]; |
52
|
|
|
|
53
|
|
|
const CONJUNCTIONS = [ |
54
|
|
|
'nor', 'so', 'and', 'or' |
55
|
|
|
]; |
56
|
|
|
|
57
|
|
|
const ADJECTIVES = [ |
58
|
|
|
'down', 'up' |
59
|
|
|
]; |
60
|
|
|
|
61
|
|
|
|
62
|
|
|
public static function capitalizeAll($text) |
63
|
|
|
{ |
64
|
|
|
$wordArray = explode(" ", $text); |
65
|
|
|
|
66
|
|
|
array_walk($wordArray, function (&$word) { |
67
|
|
|
$word = ucfirst($word); |
68
|
|
|
}); |
69
|
|
|
|
70
|
|
|
return implode(" ", $wordArray); |
71
|
|
|
} |
72
|
|
|
|
73
|
|
|
public static function capitalizeForTitle($titleString) |
74
|
|
|
{ |
75
|
|
|
if (preg_match('/(.+[^\<\>][\.:\/;\?\!]\s?)([a-z])(.+)/', $titleString, $match)) { |
76
|
|
|
$titleString = $match[1].StringHelper::mb_ucfirst($match[2]).$match[3]; |
77
|
|
|
} |
78
|
|
|
|
79
|
|
|
$wordArray = explode(" ", $titleString); |
80
|
|
|
|
81
|
|
|
array_walk($wordArray, function (&$word) { |
82
|
|
|
|
83
|
|
|
$words = explode("-", $word); |
84
|
|
|
if (count($words) > 1) { |
85
|
|
|
array_walk($words, function (&$w) { |
86
|
|
|
$w = StringHelper::keepLowerCase($w) ? $w : StringHelper::mb_ucfirst($w); |
87
|
|
|
}); |
88
|
|
|
$word = implode("-", $words); |
89
|
|
|
} |
90
|
|
|
$word = StringHelper::keepLowerCase($word) ? $word : StringHelper::mb_ucfirst($word); |
91
|
|
|
}); |
92
|
|
|
|
93
|
|
|
return implode(" ", $wordArray); |
94
|
|
|
} |
95
|
|
|
|
96
|
|
|
public static function keepLowerCase($word) |
97
|
|
|
{ |
98
|
|
|
$lowerCase = in_array($word, self::PREPOSITIONS) || |
99
|
|
|
in_array($word, self::ARTICLES) || |
100
|
|
|
in_array($word, self::CONJUNCTIONS) || |
101
|
|
|
in_array($word, self::ADJECTIVES); |
102
|
|
|
return $lowerCase; |
103
|
|
|
|
104
|
|
|
} |
105
|
|
|
|
106
|
|
|
public static function mb_ucfirst($string, $encoding = 'UTF-8') |
107
|
|
|
{ |
108
|
|
|
$strlen = mb_strlen($string, $encoding); |
109
|
|
|
$firstChar = mb_substr($string, 0, 1, $encoding); |
110
|
|
|
$then = mb_substr($string, 1, $strlen - 1, $encoding); |
111
|
|
|
$encodings = ['ISO-8859-7']; |
112
|
|
|
$encoding = mb_detect_encoding($firstChar, $encodings, true); |
113
|
|
|
return in_array($encoding, $encodings) ? $firstChar.$then : mb_strtoupper($firstChar, $encoding) . $then; |
114
|
|
|
} |
115
|
|
|
} |