|
1
|
|
|
<?php |
|
2
|
|
|
/* |
|
3
|
|
|
* Ntentan Framework |
|
4
|
|
|
* Copyright (c) 2008-2015 James Ekow Abaka Ainooson |
|
5
|
|
|
* |
|
6
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining |
|
7
|
|
|
* a copy of this software and associated documentation files (the |
|
8
|
|
|
* "Software"), to deal in the Software without restriction, including |
|
9
|
|
|
* without limitation the rights to use, copy, modify, merge, publish, |
|
10
|
|
|
* distribute, sublicense, and/or sell copies of the Software, and to |
|
11
|
|
|
* permit persons to whom the Software is furnished to do so, subject to |
|
12
|
|
|
* the following conditions: |
|
13
|
|
|
* |
|
14
|
|
|
* The above copyright notice and this permission notice shall be |
|
15
|
|
|
* included in all copies or substantial portions of the Software. |
|
16
|
|
|
* |
|
17
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, |
|
18
|
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF |
|
19
|
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND |
|
20
|
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE |
|
21
|
|
|
* LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION |
|
22
|
|
|
* OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION |
|
23
|
|
|
* WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. |
|
24
|
|
|
* |
|
25
|
|
|
*/ |
|
26
|
|
|
|
|
27
|
|
|
namespace ntentan\utils; |
|
28
|
|
|
|
|
29
|
|
|
/** |
|
30
|
|
|
* A couple of utility functions for manipulating strings. |
|
31
|
|
|
*/ |
|
32
|
|
|
class Text |
|
33
|
|
|
{ |
|
34
|
|
|
/** |
|
35
|
|
|
* Regexes for plurals |
|
36
|
|
|
* @var array |
|
37
|
|
|
*/ |
|
38
|
|
|
private static $pluralRules = [ |
|
39
|
|
|
['/child/', 'ren'], |
|
40
|
|
|
['/^ox$/', 'en'], |
|
41
|
|
|
['/(.*)(a|e|i|o|u)(?<remove>y)$/', 'ys'], |
|
42
|
|
|
['/(.*)(?<remove>y)$/', 'ies'], |
|
43
|
|
|
['/(foc|alumn|fung|nucle|octop|radi|syllab)(?<remove>us)$/', 'i'], |
|
44
|
|
|
['/(.*)(d|r)(?<remove>ex|ix)$/', 'ices'], |
|
45
|
|
|
['/(.*)(s|x)(?<remove>is)$/', 'es'], |
|
46
|
|
|
['/(.*)(?<remove>sh)$/', 'shes'], |
|
47
|
|
|
['/(.*)(?<remove>eau)$/', 'eaux'], |
|
48
|
|
|
['/(.*)(?<remove>um)$/', 'a'], |
|
49
|
|
|
['/(.*)(?<remove>tooth)$/', 'teeth'], |
|
50
|
|
|
['/(.*)(?<remove>h)$/', 'hes'], |
|
51
|
|
|
['/(formul|alumn|nebul)(?<remove>a)$/', 'ae'], |
|
52
|
|
|
['/(.*)(?<remove>x)$/', 'xes'], |
|
53
|
|
|
['/(.+)(?<remove>rion)$/', 'ria'], |
|
54
|
|
|
['/(.*)(?<remove>roof)$/', 'roofs'], |
|
55
|
|
|
['/(.*)[^f](?<remove>f|fe)$/', 'ves'], |
|
56
|
|
|
['/(.*)(m|l)(?<remove>ouse)$/', 'ice'], |
|
57
|
|
|
['/(.*)(?<remove>man)$/', 'men'], |
|
58
|
|
|
['/(.*)(?<remove>foot)$/', 'feet'], |
|
59
|
|
|
['/(.*)(disc|phot|pian)(?<remove>o)$/', 'os'], |
|
60
|
|
|
['/(.*)(?<remove>goose)$/', 'geese'], |
|
61
|
|
|
['/(.*)(?<remove>person)$/', 'people'], |
|
62
|
|
|
['/(.*)(?<remove>quiz)$/', 'quizzes'], |
|
63
|
|
|
['/.*(s|[bcdfghjklmnpqrstvwxyz]o|z)$/', 'es'], |
|
64
|
|
|
['/.*/', 's'] |
|
65
|
|
|
]; |
|
66
|
|
|
|
|
67
|
|
|
/** |
|
68
|
|
|
* Regexes for singulars |
|
69
|
|
|
* @var array |
|
70
|
|
|
*/ |
|
71
|
|
|
private static $singularRules = [ |
|
72
|
|
|
['/^axe(?<remove>s)$/', ''], |
|
73
|
|
|
['/(.*)(?<remove>a)$/', 'um'], |
|
74
|
|
|
['/(.*)(dev|v|pr)(?<remove>ices)$/', 'ice'], |
|
75
|
|
|
['/(.*)(?<remove>ices)$/', 'ix'], |
|
76
|
|
|
['/(.*)(?<remove>movies)$/', 'movie'], |
|
77
|
|
|
['/(.*)(?<remove>ies)$/', 'y'], |
|
78
|
|
|
['/(.*)(?<remove>shoes)$/', 'shoe'], |
|
79
|
|
|
['/(.*)(?<remove>oes)$/', 'o'], |
|
80
|
|
|
['/(.*)(?<remove>bases)$/', 'base'], |
|
81
|
|
|
['/(.*)(?<remove>cheeses)$/', 'cheese'], |
|
82
|
|
|
['/(.*)(?<remove>children)$/', 'child'], |
|
83
|
|
|
['/(.*)(?<remove>men)$/', 'man'], |
|
84
|
|
|
['/(.*)(?<remove>feet)$/', 'foot'], |
|
85
|
|
|
['/(.*)(?<remove>geese)$/', 'goose'], |
|
86
|
|
|
['/(.*)(?<remove>atlases)$/', 'atlas'], |
|
87
|
|
|
['/(.*)(?<remove>people)$/', 'person'], |
|
88
|
|
|
['/(.*)(?<remove>teeth)$/', 'tooth'], |
|
89
|
|
|
['/(.*)(iri)(?<remove>ses)$/', 's'], |
|
90
|
|
|
['/(.*)(h|l|p)(ou)(?<remove>ses)$/', 'se'], |
|
91
|
|
|
['/(.*)(ro|po|ca)(?<remove>ses)$/', 'se'], |
|
92
|
|
|
['/(.*)(?<remove>quizzes)$/', 'quiz'], |
|
93
|
|
|
['/(.*)(?<remove>zes)$/', 'z'], |
|
94
|
|
|
['/(.*)(y|i|a|o|e)(?<remove>ses)$/', 'sis'], |
|
95
|
|
|
['/(.*)(?<remove>ses)$/', 's'], |
|
96
|
|
|
['/(.*)(?<remove>ice)$/', 'ouse'], |
|
97
|
|
|
['/(.*)(?<remove>xes)$/', 'x'], |
|
98
|
|
|
['/(.*)(?<remove>eaux)$/', 'eau'], |
|
99
|
|
|
['/(formul|alumn|nebul)(?<remove>ae)$/', 'a'], |
|
100
|
|
|
['/(foc|alumn|fung|nucle|octop|radi|syllab)(?<remove>i)$/', 'us'], |
|
101
|
|
|
['/(.*)(?<remove>hes)$/', 'h'], |
|
102
|
|
|
['/(.*)(ca|mo|lo)(?<remove>ves)$/', 've'], |
|
103
|
|
|
['/(.*)(l|r|o|a|e)(?<remove>ves)$/', 'f'], |
|
104
|
|
|
['/(.*)(li|ni|wi)(?<remove>ves)$/', 'fe'], |
|
105
|
|
|
['/(.*)(?<remove>s)$/', ''], |
|
106
|
|
|
]; |
|
107
|
|
|
|
|
108
|
|
|
private static $noPlurals = [ |
|
109
|
|
|
'cod', 'deer', 'feedback', 'fish', 'moose', 'news', 'species', 'series', 'sheep', 'rice' |
|
110
|
|
|
]; |
|
111
|
|
|
|
|
112
|
|
|
/** |
|
113
|
|
|
* Converts text separated by a specified separator to camel case. |
|
114
|
|
|
* This function converts the entire text into lower case before performing the |
|
115
|
|
|
* camel case conversion. Due to this the first character would be lowercased. |
|
116
|
|
|
* |
|
117
|
|
|
* @param string $string The text to be converted. |
|
118
|
|
|
* @param string $separator The separator to consider for camel casing |
|
119
|
|
|
* @return string |
|
120
|
|
|
*/ |
|
121
|
1 |
|
public static function camelize($string, $separator = '_') : string |
|
122
|
|
|
{ |
|
123
|
1 |
|
if(is_array($separator)) |
|
|
|
|
|
|
124
|
|
|
{ |
|
125
|
1 |
|
$separator = "(\\" . implode("|\\", $separator) . ")"; |
|
126
|
|
|
} |
|
127
|
|
|
else |
|
128
|
|
|
{ |
|
129
|
1 |
|
$separator = '\\' . $separator; |
|
130
|
|
|
} |
|
131
|
1 |
|
return preg_replace_callback( |
|
132
|
1 |
|
"/{$separator}[a-zA-Z]/", |
|
133
|
1 |
|
function ($matches) |
|
134
|
|
|
{ |
|
135
|
1 |
|
return strtoupper($matches[0][1]); |
|
136
|
1 |
|
}, |
|
137
|
1 |
|
strtolower($string) |
|
138
|
|
|
); |
|
139
|
|
|
} |
|
140
|
|
|
|
|
141
|
|
|
/** |
|
142
|
|
|
* Converts text separated by a specified separator to camel case. |
|
143
|
|
|
* This method works just as the Text::camelize method except that it converts |
|
144
|
|
|
* the first character to uppercase. |
|
145
|
|
|
* |
|
146
|
|
|
* @param string $string The text to be converted. |
|
147
|
|
|
* @param string $separator The separator to consider for camel casing |
|
148
|
|
|
* @return string |
|
149
|
|
|
*/ |
|
150
|
1 |
|
public static function ucamelize($string, $separator = '_') : string |
|
151
|
|
|
{ |
|
152
|
1 |
|
return ucfirst(self::camelize($string, $separator)); |
|
153
|
|
|
} |
|
154
|
|
|
|
|
155
|
|
|
/** |
|
156
|
|
|
* Converts camel case text into regular text separated with an arbitrary separator. |
|
157
|
|
|
* By default the seperator is an underscore. A space can also be used as the |
|
158
|
|
|
* seperator in cases where the conversion is to an English sentence. |
|
159
|
|
|
* |
|
160
|
|
|
* @param string $string The text to be converted. |
|
161
|
|
|
* @param string $separator The separator to be used. |
|
162
|
|
|
* @return string |
|
163
|
|
|
*/ |
|
164
|
1 |
|
public static function deCamelize($string, $separator = '_') : string |
|
165
|
|
|
{ |
|
166
|
1 |
|
return preg_replace_callback( |
|
167
|
1 |
|
"/[A-Z][a-z]/", |
|
168
|
1 |
|
function ($matches) use($separator) |
|
169
|
|
|
{ |
|
170
|
1 |
|
return $separator . strtolower($matches[0]); |
|
171
|
1 |
|
}, |
|
172
|
1 |
|
lcfirst($string) |
|
173
|
|
|
); |
|
174
|
|
|
} |
|
175
|
|
|
|
|
176
|
|
|
/** |
|
177
|
|
|
* Run through the rules and generate a text transformation. |
|
178
|
|
|
* |
|
179
|
|
|
* @param string $text |
|
180
|
|
|
* @param array $rules |
|
181
|
|
|
* @return string|null |
|
182
|
|
|
*/ |
|
183
|
320 |
|
private static function runInflection($text, $rules) |
|
184
|
|
|
{ |
|
185
|
320 |
|
if(in_array($text, self::$noPlurals)) { |
|
186
|
18 |
|
return $text; |
|
187
|
|
|
} |
|
188
|
302 |
|
foreach($rules as $rule) { |
|
189
|
302 |
|
if(preg_match($rule[0], $text, $matches)) { |
|
190
|
302 |
|
return substr($text, 0, strlen($text) - strlen($matches['remove'] ?? '')) . $rule[1]; |
|
191
|
|
|
} |
|
192
|
|
|
} |
|
193
|
|
|
} |
|
194
|
|
|
|
|
195
|
|
|
/** |
|
196
|
|
|
* Generates the english plural of a given word. |
|
197
|
|
|
* |
|
198
|
|
|
* @param string $text |
|
199
|
|
|
* @return string |
|
200
|
|
|
*/ |
|
201
|
166 |
|
public static function pluralize($text) : string |
|
202
|
|
|
{ |
|
203
|
166 |
|
return self::runInflection($text, self::$pluralRules); |
|
204
|
|
|
} |
|
205
|
|
|
|
|
206
|
|
|
/** |
|
207
|
|
|
* Generates the english singular of a given word. |
|
208
|
|
|
* |
|
209
|
|
|
* @param string $text |
|
210
|
|
|
* @return string |
|
211
|
|
|
*/ |
|
212
|
154 |
|
public static function singularize($text) : string |
|
213
|
|
|
{ |
|
214
|
154 |
|
return self::runInflection($text, self::$singularRules) ?? $text; |
|
215
|
|
|
} |
|
216
|
|
|
} |
|
217
|
|
|
|