1
|
|
|
<?php /** @noinspection PhpInternalEntityUsedInspection */ |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* citeproc-php |
5
|
|
|
* |
6
|
|
|
* @link http://github.com/seboettg/citeproc-php for the source repository |
7
|
|
|
* @copyright Copyright (c) 2016 Sebastian Böttger. |
8
|
|
|
* @license https://opensource.org/licenses/MIT |
9
|
|
|
*/ |
10
|
|
|
|
11
|
|
|
namespace Seboettg\CiteProc\Util; |
12
|
|
|
|
13
|
|
|
use Seboettg\CiteProc\CiteProc; |
14
|
|
|
use Symfony\Polyfill\Mbstring\Mbstring; |
15
|
|
|
|
16
|
|
|
/** |
17
|
|
|
* Class StringHelper |
18
|
|
|
* @package Seboettg\CiteProc\Util |
19
|
|
|
* |
20
|
|
|
* @author Sebastian Böttger <[email protected]> |
21
|
|
|
*/ |
22
|
|
|
class StringHelper |
23
|
|
|
{ |
24
|
|
|
|
25
|
|
|
const PREPOSITIONS = [ |
26
|
|
|
'on', 'in', 'at', 'since', 'for', 'ago', 'before', 'to', 'past', 'till', 'until', 'by', 'under', 'below', |
27
|
|
|
'over', 'above', 'across', 'through', 'into', 'towards', 'onto', 'from', 'of', 'off', 'about', 'via' |
28
|
|
|
]; |
29
|
|
|
|
30
|
|
|
const ARTICLES = [ |
31
|
|
|
'a', 'an', 'the' |
32
|
|
|
]; |
33
|
|
|
|
34
|
|
|
const ADVERBS = [ |
35
|
|
|
'yet', 'so', 'just', 'only' |
36
|
|
|
]; |
37
|
|
|
|
38
|
|
|
const CONJUNCTIONS = [ |
39
|
|
|
'nor', 'so', 'and', 'or' |
40
|
|
|
]; |
41
|
|
|
|
42
|
|
|
const ADJECTIVES = [ |
43
|
|
|
'down', 'up' |
44
|
|
|
]; |
45
|
|
|
|
46
|
|
|
const ISO_ENCODINGS = [ |
47
|
|
|
'ISO-8859-1', |
48
|
|
|
'ISO-8859-2', |
49
|
|
|
'ISO-8859-3', |
50
|
|
|
'ISO-8859-4', |
51
|
|
|
'ISO-8859-5', |
52
|
|
|
'ISO-8859-6', |
53
|
|
|
'ISO-8859-7', |
54
|
|
|
'ISO-8859-8', |
55
|
|
|
'ISO-8859-9', |
56
|
|
|
'ISO-8859-10', |
57
|
|
|
'ISO-8859-11', |
58
|
|
|
'ISO-8859-13', |
59
|
|
|
'ISO-8859-14', |
60
|
|
|
'ISO-8859-15', |
61
|
|
|
'ISO-8859-16' |
62
|
|
|
]; |
63
|
|
|
|
64
|
|
|
/** |
65
|
|
|
* opening quote sign |
66
|
|
|
*/ |
67
|
|
|
const OPENING_QUOTE = "“"; |
68
|
|
|
|
69
|
|
|
/** |
70
|
|
|
* closing quote sign |
71
|
|
|
*/ |
72
|
|
|
const CLOSING_QUOTE = "”"; |
73
|
|
|
|
74
|
|
|
/** |
75
|
|
|
* @param $text |
76
|
|
|
* @return string |
77
|
|
|
*/ |
78
|
1 |
|
public static function capitalizeAll($text) |
79
|
|
|
{ |
80
|
1 |
|
$wordArray = explode(" ", $text); |
81
|
|
|
|
82
|
|
|
array_walk($wordArray, function (&$word) { |
83
|
1 |
|
$word = ucfirst($word); |
84
|
1 |
|
}); |
85
|
|
|
|
86
|
1 |
|
return implode(" ", $wordArray); |
87
|
|
|
} |
88
|
|
|
|
89
|
|
|
/** |
90
|
|
|
* @param $titleString |
91
|
|
|
* @return string |
92
|
|
|
*/ |
93
|
10 |
|
public static function capitalizeForTitle($titleString) |
94
|
|
|
{ |
95
|
10 |
|
if (preg_match('/(.+[^\<\>][\.:\/;\?\!]\s?)([a-z])(.+)/', $titleString, $match)) { |
96
|
|
|
$titleString = $match[1] . StringHelper::mb_ucfirst($match[2]) . $match[3]; |
97
|
|
|
} |
98
|
|
|
|
99
|
10 |
|
$wordArray = explode(" ", $titleString); |
100
|
|
|
|
101
|
|
|
array_walk($wordArray, function (&$word) { |
102
|
|
|
|
103
|
10 |
|
$words = explode("-", $word); |
104
|
10 |
|
if (count($words) > 1) { |
105
|
|
|
array_walk($words, function (&$w) { |
106
|
3 |
|
$w = StringHelper::keepLowerCase($w) ? $w : StringHelper::mb_ucfirst($w); |
107
|
3 |
|
}); |
108
|
3 |
|
$word = implode("-", $words); |
109
|
|
|
} |
110
|
10 |
|
$word = StringHelper::keepLowerCase($word) ? $word : StringHelper::mb_ucfirst($word); |
111
|
10 |
|
}); |
112
|
|
|
|
113
|
10 |
|
return implode(" ", $wordArray); |
114
|
|
|
} |
115
|
|
|
|
116
|
|
|
/** |
117
|
|
|
* @param $word |
118
|
|
|
* @return bool |
119
|
|
|
*/ |
120
|
10 |
|
public static function keepLowerCase($word) |
121
|
|
|
{ |
122
|
|
|
// keep lower case if the first char is not an utf-8 letter |
123
|
10 |
|
return in_array($word, self::PREPOSITIONS) || |
124
|
10 |
|
in_array($word, self::ARTICLES) || |
125
|
10 |
|
in_array($word, self::CONJUNCTIONS) || |
126
|
10 |
|
in_array($word, self::ADJECTIVES) || |
127
|
10 |
|
(bool) preg_match("/[^\p{L}].+/", $word); |
128
|
|
|
} |
129
|
|
|
|
130
|
|
|
/** |
131
|
|
|
* @param $string |
132
|
|
|
* @param string $encoding |
133
|
|
|
* @return string |
134
|
|
|
*/ |
135
|
23 |
|
public static function mb_ucfirst($string, $encoding = 'UTF-8') |
|
|
|
|
136
|
|
|
{ |
137
|
23 |
|
$strlen = mb_strlen($string, $encoding); |
138
|
23 |
|
$firstChar = mb_substr($string, 0, 1, $encoding); |
139
|
23 |
|
$then = mb_substr($string, 1, $strlen - 1, $encoding); |
140
|
|
|
|
141
|
|
|
/** @noinspection PhpInternalEntityUsedInspection */ |
142
|
23 |
|
$encoding = Mbstring::mb_detect_encoding($firstChar, self::ISO_ENCODINGS, true); |
143
|
23 |
|
return in_array($encoding, self::ISO_ENCODINGS) ? |
144
|
23 |
|
Mbstring::mb_strtoupper($firstChar, $encoding) . $then : $firstChar . $then; |
145
|
|
|
} |
146
|
|
|
|
147
|
39 |
|
public static function mb_strrev($string) |
|
|
|
|
148
|
|
|
{ |
149
|
39 |
|
$result = ''; |
150
|
39 |
|
for ($i = mb_strlen($string); $i >= 0; --$i) { |
151
|
39 |
|
$result .= mb_substr($string, $i, 1); |
152
|
|
|
} |
153
|
39 |
|
return $result; |
154
|
|
|
} |
155
|
|
|
|
156
|
|
|
/** |
157
|
|
|
* @param string $delimiter |
158
|
|
|
* @param string[] $arrayOfStrings |
159
|
|
|
* @return string; |
160
|
|
|
*/ |
161
|
72 |
|
public static function implodeAndPreventConsecutiveChars($delimiter, $arrayOfStrings) |
162
|
|
|
{ |
163
|
72 |
|
$delim = trim($delimiter); |
164
|
72 |
|
if (!empty($delim)) { |
165
|
39 |
|
foreach ($arrayOfStrings as $key => $textPart) { |
166
|
39 |
|
$pos = mb_strpos(StringHelper::mb_strrev($textPart), StringHelper::mb_strrev($delim)); |
167
|
39 |
|
if ($pos === 0) { |
168
|
3 |
|
$length = mb_strlen($textPart) - mb_strlen($delim); |
169
|
3 |
|
$textPart = mb_substr($textPart, 0, $length); |
170
|
3 |
|
$arrayOfStrings[$key] = $textPart; |
171
|
|
|
} |
172
|
|
|
} |
173
|
|
|
} |
174
|
72 |
|
return implode($delimiter, $arrayOfStrings); |
175
|
|
|
} |
176
|
|
|
|
177
|
|
|
/** |
178
|
|
|
* @param $string |
179
|
|
|
* @param $initializeSign |
180
|
|
|
* @return string |
181
|
|
|
*/ |
182
|
28 |
|
public static function initializeBySpaceOrHyphen($string, $initializeSign) |
183
|
|
|
{ |
184
|
28 |
|
$initializeWithHyphen = CiteProc::getContext()->getGlobalOptions()->isInitializeWithHyphen(); |
185
|
28 |
|
$res = ""; |
186
|
28 |
|
$exploded = explode("-", $string); |
187
|
28 |
|
$i = 0; |
188
|
28 |
|
foreach ($exploded as $explode) { |
189
|
28 |
|
$spaceExploded = explode(" ", $explode); |
190
|
28 |
|
foreach ($spaceExploded as $givenPart) { |
191
|
28 |
|
$firstLetter = mb_substr($givenPart, 0, 1, "UTF-8"); |
192
|
28 |
|
if (StringHelper::isLatinString($firstLetter)) { |
193
|
26 |
|
$res .= ctype_upper($firstLetter) ? $firstLetter . $initializeSign : " " . $givenPart . " "; |
194
|
|
|
} else { |
195
|
2 |
|
$res .= $firstLetter . $initializeSign; |
196
|
|
|
} |
197
|
|
|
} |
198
|
28 |
|
if ($i < count($exploded) - 1 && $initializeWithHyphen) { |
199
|
2 |
|
$res = rtrim($res) . "-"; |
200
|
|
|
} |
201
|
28 |
|
++$i; |
202
|
|
|
} |
203
|
28 |
|
return $res; |
204
|
|
|
} |
205
|
|
|
|
206
|
|
|
/** |
207
|
|
|
* @param $string |
208
|
|
|
* @return mixed|string |
209
|
|
|
*/ |
210
|
1 |
|
public static function camelCase2Hyphen($string) |
211
|
|
|
{ |
212
|
1 |
|
$hyphenated = preg_replace("/([A-Z])/", "-$1", $string); |
213
|
1 |
|
$hyphenated = substr($hyphenated, 0, 1) === "-" ? substr($hyphenated, 1) : $hyphenated; |
214
|
1 |
|
return mb_strtolower($hyphenated); |
215
|
|
|
} |
216
|
|
|
|
217
|
|
|
/** |
218
|
|
|
* @param $string |
219
|
|
|
* @return bool |
220
|
|
|
*/ |
221
|
1 |
|
public static function checkLowerCaseString($string) |
222
|
|
|
{ |
223
|
1 |
|
return ($string === mb_strtolower($string)); |
224
|
|
|
} |
225
|
|
|
|
226
|
|
|
/** |
227
|
|
|
* @param $string |
228
|
|
|
* @return bool |
229
|
|
|
*/ |
230
|
2 |
|
public static function checkUpperCaseString($string) |
231
|
|
|
{ |
232
|
2 |
|
return ($string === mb_strtoupper($string)); |
233
|
|
|
} |
234
|
|
|
|
235
|
|
|
/** |
236
|
|
|
* @param $string |
237
|
|
|
* @return mixed |
238
|
|
|
*/ |
239
|
154 |
|
public static function clearApostrophes($string) |
240
|
|
|
{ |
241
|
154 |
|
return preg_replace("/\'/", "’", $string); |
242
|
|
|
} |
243
|
|
|
|
244
|
|
|
/** |
245
|
|
|
* replaces outer quotes of $text by given inner quotes |
246
|
|
|
* |
247
|
|
|
* @param $text |
248
|
|
|
* @param $outerOpenQuote |
249
|
|
|
* @param $outerCloseQuote |
250
|
|
|
* @param $innerOpenQuote |
251
|
|
|
* @param $innerCloseQuote |
252
|
|
|
* @return string |
253
|
|
|
*/ |
254
|
7 |
|
public static function replaceOuterQuotes( |
255
|
|
|
$text, |
256
|
|
|
$outerOpenQuote, |
257
|
|
|
$outerCloseQuote, |
258
|
|
|
$innerOpenQuote, |
259
|
|
|
$innerCloseQuote |
260
|
|
|
) { |
261
|
7 |
|
if (preg_match("/(.*)$outerOpenQuote(.+)$outerCloseQuote(.*)/u", $text, $match)) { |
262
|
3 |
|
return $match[1] . $innerOpenQuote . $match[2] . $innerCloseQuote . $match[3]; |
263
|
|
|
} |
264
|
6 |
|
return $text; |
265
|
|
|
} |
266
|
|
|
|
267
|
|
|
/** |
268
|
|
|
* @param $string |
269
|
|
|
* @return bool |
270
|
|
|
*/ |
271
|
98 |
|
public static function isLatinString($string) |
272
|
|
|
{ |
273
|
98 |
|
return boolval(preg_match_all("/^[\p{Latin}\p{Common}]+$/u", $string)); |
274
|
|
|
//return !$noLatin; |
275
|
|
|
} |
276
|
|
|
|
277
|
|
|
/** |
278
|
|
|
* @param $string |
279
|
|
|
* @return bool |
280
|
|
|
*/ |
281
|
4 |
|
public static function isCyrillicString($string) |
282
|
|
|
{ |
283
|
4 |
|
return boolval(preg_match("/^[\p{Cyrillic}\p{Common}]+$/u", $string)); |
284
|
|
|
} |
285
|
|
|
|
286
|
|
|
/** |
287
|
|
|
* removes all kind of brackets from a given string |
288
|
|
|
* @param $datePart |
289
|
|
|
* @return mixed |
290
|
|
|
*/ |
291
|
55 |
|
public static function removeBrackets($datePart) |
292
|
|
|
{ |
293
|
55 |
|
return str_replace(["[","]", "(", ")", "{", "}"], "", $datePart); |
294
|
|
|
} |
295
|
|
|
} |
296
|
|
|
|