1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace Ronanchilvers\Utility; |
4
|
|
|
|
5
|
|
|
/** |
6
|
|
|
* Useful string manipulation methods |
7
|
|
|
* |
8
|
|
|
* NB: This class only handles english strings - it is not aware of other languages |
9
|
|
|
* |
10
|
|
|
* @author Ronan Chilvers <[email protected]> |
11
|
|
|
*/ |
12
|
|
|
class Str |
13
|
|
|
{ |
14
|
|
|
/** |
15
|
|
|
* @var array |
16
|
|
|
*/ |
17
|
|
|
static protected $irregulars = [ |
18
|
|
|
'child' => 'children', |
19
|
|
|
'foot' => 'feet', |
20
|
|
|
'goose' => 'geese', |
21
|
|
|
'man' => 'men', |
22
|
|
|
'mouse' => 'mice', |
23
|
|
|
'person' => 'people', |
24
|
|
|
'sheep' => 'sheep', |
25
|
|
|
'tooth' => 'teeth', |
26
|
|
|
]; |
27
|
|
|
|
28
|
|
|
/** |
29
|
|
|
* @var array |
30
|
|
|
*/ |
31
|
|
|
static protected $uncountable = [ |
32
|
|
|
'sheep', |
33
|
|
|
'fish', |
34
|
|
|
'deer', |
35
|
|
|
'series', |
36
|
|
|
'species', |
37
|
|
|
'money', |
38
|
|
|
'rice', |
39
|
|
|
'information', |
40
|
|
|
'equipment' |
41
|
|
|
]; |
42
|
|
|
|
43
|
|
|
/** |
44
|
|
|
* @var array |
45
|
|
|
*/ |
46
|
|
|
static protected $vowels = [ |
47
|
|
|
'a', |
48
|
|
|
'e', |
49
|
|
|
'i', |
50
|
|
|
'o', |
51
|
|
|
'u' |
52
|
|
|
]; |
53
|
|
|
|
54
|
|
|
/** |
55
|
|
|
* Pluralise a string |
56
|
|
|
* |
57
|
|
|
* [1.0] 'ies' rule (ends in a consonant + y : baby/lady) |
58
|
|
|
* [2.0] 'ves' rule (ends in f or fe : leaf/knife) --- roof : rooves (correct but old english, roofs is ok). |
59
|
|
|
* [3.1] 'es' rule 1 (ends in a consonant + o : volcano/mango) |
60
|
|
|
* [3.2] 'es' rule 2 (ends in ch, sh, s, ss, x, z : match/dish/bus/glass/fox/buzz) |
61
|
|
|
* [4.1] 's' rule 1 (ends in a vowel + y or o : boy/radio) |
62
|
|
|
* [4.2] 's' rule 2 (ends in other than above : cat/ball) |
63
|
|
|
* |
64
|
|
|
* @param string $string The singular noun to pluralise |
65
|
|
|
* @param int $count |
66
|
|
|
* @param string $plural |
67
|
|
|
* @return string |
68
|
|
|
* @author Ronan Chilvers <[email protected]> |
69
|
|
|
*/ |
70
|
132 |
|
static public function plural($string, $count = 2, $plural = false) |
71
|
|
|
{ |
72
|
132 |
|
$string = trim($string); |
73
|
132 |
|
if (in_array($string, static::$uncountable) && false === $plural) { |
74
|
18 |
|
return $string; |
75
|
|
|
} |
76
|
|
|
|
77
|
114 |
|
if (empty($string) || $count == 1) { |
78
|
57 |
|
return $string; |
79
|
|
|
} |
80
|
|
|
|
81
|
57 |
|
if (false !== $plural) { |
82
|
33 |
|
return $plural; |
83
|
|
|
} |
84
|
|
|
|
85
|
24 |
|
$string = mb_strtolower($string); |
86
|
24 |
|
if (isset(static::$irregulars[$string])) { |
87
|
7 |
|
return static::$irregulars[$string]; |
88
|
|
|
} |
89
|
|
|
|
90
|
|
|
// [1.0] |
91
|
17 |
|
if (!in_array(mb_substr($string, -2, 1), static::$vowels) && 'y' == mb_substr($string, -1)) { |
92
|
2 |
|
return mb_substr($string, 0, -1) . 'ies'; |
93
|
|
|
} |
94
|
|
|
|
95
|
|
|
// [2.0] |
96
|
15 |
|
if ('f' == mb_substr($string, -1) || 'fe' == mb_substr($string, -2)) { |
97
|
2 |
|
$length = ('e' == mb_substr($string, -1)) ? -2 : -1 ; |
98
|
2 |
|
return mb_substr($string, 0, $length) . 'ves'; |
99
|
|
|
} |
100
|
|
|
|
101
|
|
|
// [3.1] |
102
|
13 |
|
if (!in_array(mb_substr($string, -2, 1), static::$vowels) && 'o' == mb_substr($string, -1)) { |
103
|
1 |
|
return $string . 'es'; |
104
|
|
|
} |
105
|
|
|
|
106
|
|
|
// [3.2] |
107
|
12 |
|
if (in_array(mb_substr($string, -2), ['ch', 'sh', 'ss']) || in_array(mb_substr($string, -1), ['s', 'x', 'z'])) { |
108
|
7 |
|
return $string . 'es'; |
109
|
|
|
} |
110
|
|
|
|
111
|
5 |
|
return $string . 's'; |
112
|
|
|
} |
113
|
|
|
|
114
|
|
|
/** |
115
|
|
|
* Singularise a string |
116
|
|
|
* |
117
|
|
|
* [1.0] 'ies' rule (ends in a consonant + y : baby/lady) |
118
|
|
|
* [2.0] 'ves' rule (ends in f or fe : leaf/knife) --- roof : rooves (correct but old english, roofs is ok). |
119
|
|
|
* [3.1] 'es' rule 1 (ends in a consonant + o : volcano/mango) |
120
|
|
|
* [3.2] 'es' rule 2 (ends in ch, sh, s, ss, x, z : match/dish/bus/glass/fox/buzz) |
121
|
|
|
* [4.1] 's' rule 1 (ends in a vowel + y or o : boy/radio) |
122
|
|
|
* [4.2] 's' rule 2 (ends in other than above : cat/ball) |
123
|
|
|
* |
124
|
|
|
* @param string $string The singular noun to singularise |
125
|
|
|
* @param int $count |
126
|
|
|
* @param string $singular |
127
|
|
|
* @return string |
128
|
|
|
* @author Ronan Chilvers <[email protected]> |
129
|
|
|
*/ |
130
|
129 |
|
static public function singular($string, $count = 1, $singular = false) |
131
|
|
|
{ |
132
|
129 |
|
$string = trim($string); |
133
|
129 |
|
if (in_array($string, static::$uncountable) && false === $singular) { |
134
|
18 |
|
return $string; |
135
|
|
|
} |
136
|
|
|
|
137
|
111 |
|
if (empty($string) || $count !== 1) { |
138
|
56 |
|
return $string; |
139
|
|
|
} |
140
|
|
|
|
141
|
55 |
|
if (false !== $singular) { |
142
|
32 |
|
return $singular; |
143
|
|
|
} |
144
|
|
|
|
145
|
23 |
|
$singulars = array_flip(static::$irregulars); |
146
|
23 |
|
$string = mb_strtolower($string); |
147
|
23 |
|
if (isset($singulars[$string])) { |
148
|
7 |
|
return $singulars[$string]; |
149
|
|
|
} |
150
|
|
|
|
151
|
|
|
// [1.0] |
152
|
16 |
|
if ('ies' == mb_substr($string, -3)) { |
153
|
2 |
|
return mb_substr($string, 0, -3) . 'y'; |
154
|
|
|
} |
155
|
|
|
|
156
|
|
|
// [2.0] |
157
|
14 |
|
if ('ves' == mb_substr($string, -3)) { |
158
|
2 |
|
if (in_array(mb_substr($string, -4, 1), static::$vowels)) { |
159
|
1 |
|
return mb_substr($string, 0, -3) . 'f'; |
160
|
|
|
} |
161
|
|
|
} |
162
|
|
|
|
163
|
|
|
// [3.1, 3.2] |
164
|
13 |
|
if ('ves' != mb_substr($string, -3) && 'es' == mb_substr($string, -2)) { |
165
|
8 |
|
return mb_substr($string, 0, -2); |
166
|
|
|
} |
167
|
|
|
|
168
|
5 |
|
return rtrim($string, 's'); |
169
|
|
|
} |
170
|
|
|
|
171
|
|
|
/** |
172
|
|
|
* Convert a string to PascalCase |
173
|
|
|
* |
174
|
|
|
* Pascal case is upper camel case, or camel case with the first |
175
|
|
|
* letter uppercased. |
176
|
|
|
* |
177
|
|
|
* @param string $string |
178
|
|
|
* @param array $allowed Allowed characters that won't be compressed |
179
|
|
|
* @return string |
180
|
|
|
* @author Ronan Chilvers <[email protected]> |
181
|
|
|
*/ |
182
|
4 |
|
static public function pascal($string, $allowed = []) |
183
|
|
|
{ |
184
|
4 |
|
$string = mb_strtolower($string); |
185
|
4 |
|
$string = preg_replace('#[^a-z0-9' . implode('', $allowed) . ']+#', ' ', $string); |
186
|
4 |
|
$string = str_replace(' ', '', ucwords($string)); |
187
|
|
|
|
188
|
4 |
|
return $string; |
189
|
|
|
} |
190
|
|
|
|
191
|
|
|
/** |
192
|
|
|
* Convert a string to camelCase |
193
|
|
|
* |
194
|
|
|
* We're taking camel case here to mean lower camel case, ie: the first |
195
|
|
|
* letter is lower case. |
196
|
|
|
* |
197
|
|
|
* @param string $string |
198
|
|
|
* @param array $allowed Allowed characters that won't be compressed |
199
|
|
|
* @return string |
200
|
|
|
* @author Ronan Chilvers <[email protected]> |
201
|
|
|
*/ |
202
|
2 |
|
static public function camel($string, $allowed = []) |
203
|
|
|
{ |
204
|
2 |
|
return lcfirst( |
205
|
2 |
|
static::pascal($string, $allowed) |
206
|
|
|
); |
207
|
|
|
} |
208
|
|
|
|
209
|
|
|
/** |
210
|
|
|
* Snake case a string |
211
|
|
|
* |
212
|
|
|
* This method snake cases phrases and can also convert camelCase |
213
|
|
|
* and PascalCase strings to snake case. |
214
|
|
|
* |
215
|
|
|
* @param string $string |
216
|
|
|
* @param array $allowed Allowed characters that won't be compressed |
217
|
|
|
* @return string |
218
|
|
|
* @author Ronan Chilvers <[email protected]> |
219
|
|
|
*/ |
220
|
4 |
|
static public function snake($string, $allowed = []) |
221
|
|
|
{ |
222
|
|
|
// $string = mb_strtolower($string); |
223
|
4 |
|
$string = preg_replace('#([A-Z]{1})#', ' $1', $string); |
224
|
4 |
|
$string = mb_strtolower(trim($string)); |
225
|
4 |
|
$string = preg_replace('#[^a-z0-9' . implode('', $allowed) . ']{1,}#', ' ', $string); |
226
|
4 |
|
$string = str_replace(' ', '_', $string); |
227
|
|
|
|
228
|
4 |
|
return $string; |
229
|
|
|
} |
230
|
|
|
|
231
|
|
|
/** |
232
|
|
|
* Truncate a string to a given length, optionally respecting word |
233
|
|
|
* boundaries |
234
|
|
|
* |
235
|
|
|
* @param string $string The string to truncate |
236
|
|
|
* @param int $length The length to truncate to |
237
|
|
|
* @param string $suffix Suffix to tag on the end of the string |
238
|
|
|
* @param boolean $words Respect word boundaries |
239
|
|
|
* @return string |
240
|
|
|
* @author Ronan Chilvers <[email protected]> |
241
|
|
|
*/ |
242
|
5 |
|
static public function truncate($string, $length, $suffix = '...', $words = false) |
243
|
|
|
{ |
244
|
5 |
|
if ($length > mb_strlen($string)) { |
245
|
1 |
|
return $string; |
246
|
|
|
} |
247
|
4 |
|
if (false === $words) { |
248
|
2 |
|
return mb_substr($string, 0, $length - mb_strlen($suffix)) . $suffix; |
249
|
|
|
} |
250
|
2 |
|
$matches = []; |
251
|
2 |
|
preg_match( |
252
|
2 |
|
"/(^.{1," . ($length - mb_strlen($suffix)) . "})(?=\s|$).*/u", |
253
|
|
|
$string, |
254
|
|
|
$matches |
255
|
|
|
); |
256
|
2 |
|
if (!isset($matches[1])) { |
257
|
1 |
|
return mb_substr($string, 0, $length - mb_strlen($suffix)) . $suffix; |
258
|
|
|
} |
259
|
|
|
|
260
|
1 |
|
return $matches[1] . $suffix; |
261
|
|
|
} |
262
|
|
|
|
263
|
|
|
/** |
264
|
|
|
* Generate a long random string suitable for use as a token |
265
|
|
|
* |
266
|
|
|
* @param int $length |
267
|
|
|
* @return string |
268
|
|
|
* @author Ronan Chilvers <[email protected]> |
269
|
|
|
*/ |
270
|
1 |
|
static public function token($length = 64) |
271
|
|
|
{ |
272
|
1 |
|
return substr(bin2hex( |
273
|
1 |
|
random_bytes($length) |
274
|
|
|
), 0, $length); |
275
|
|
|
} |
276
|
|
|
|
277
|
|
|
/** |
278
|
|
|
* Create a string by joining an arbitrary number of other strings with a separator |
279
|
|
|
* |
280
|
|
|
* @param string $seperator |
281
|
|
|
* @param string $piece... |
282
|
|
|
* @author Ronan Chilvers <[email protected]> |
283
|
|
|
*/ |
284
|
2 |
|
static public function join($seperator, ...$pieces) |
285
|
|
|
{ |
286
|
2 |
|
foreach ($pieces as &$piece) { |
287
|
2 |
|
$piece = trim($piece, $seperator); |
288
|
|
|
} |
289
|
|
|
|
290
|
2 |
|
return implode($seperator, $pieces); |
291
|
|
|
} |
292
|
|
|
|
293
|
|
|
/** |
294
|
|
|
* Convert a string to a boolean value |
295
|
|
|
* |
296
|
|
|
* @param string |
297
|
|
|
* @return boolean |
298
|
|
|
* @author Ronan Chilvers <[email protected]> |
299
|
|
|
*/ |
300
|
6 |
|
static public function bool($string) |
301
|
|
|
{ |
302
|
6 |
|
if (true === $string) { |
303
|
|
|
return true; |
304
|
|
|
} |
305
|
|
|
switch ($string) { |
306
|
|
|
|
307
|
6 |
|
case '1': |
308
|
5 |
|
case 'yes': |
309
|
4 |
|
case 'true': |
310
|
3 |
|
return true; |
311
|
|
|
|
312
|
|
|
default: |
313
|
3 |
|
return false; |
314
|
|
|
|
315
|
|
|
} |
316
|
|
|
} |
317
|
|
|
|
318
|
|
|
/** |
319
|
|
|
* Simple moustaches templating |
320
|
|
|
* |
321
|
|
|
* @param string $template |
322
|
|
|
* @param array $params |
323
|
|
|
* @return string |
324
|
|
|
* @author Ronan Chilvers <[email protected]> |
325
|
|
|
*/ |
326
|
|
|
static public function moustaches(string $template, array $params) |
327
|
|
|
{ |
328
|
|
|
$keys = array_map(function ($value) { |
329
|
|
|
return '{'.$value.'}'; |
330
|
|
|
}, array_keys($params)); |
331
|
|
|
$values = array_values($params); |
332
|
|
|
|
333
|
|
|
return str_replace($keys, $values, $template); |
334
|
|
|
} |
335
|
|
|
|
336
|
|
|
/** |
337
|
|
|
* Normalise a string into a key with only hyphens and lowercase alphanumeric characters |
338
|
|
|
* |
339
|
|
|
* @param string $string |
340
|
|
|
* @return string |
341
|
|
|
* @author Ronan Chilvers <[email protected]> |
342
|
|
|
*/ |
343
|
3 |
|
static public function normalise($string): string |
344
|
|
|
{ |
345
|
3 |
|
$string = strtolower($string); |
346
|
3 |
|
$string = preg_replace('/[^A-z0-9\s-]+/', '', $string); |
347
|
3 |
|
$string = preg_replace('/[\s-]{1,}/', '-', $string); |
348
|
|
|
|
349
|
3 |
|
return $string; |
350
|
|
|
} |
351
|
|
|
} |
352
|
|
|
|