1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
namespace AppUtils; |
6
|
|
|
|
7
|
|
|
use ForceUTF8\Encoding; |
8
|
|
|
|
9
|
|
|
class ConvertHelper_String |
10
|
|
|
{ |
11
|
|
|
/** |
12
|
|
|
* Searches for needle in the specified string, and returns a list |
13
|
|
|
* of all occurrences, including the matched string. The matched |
14
|
|
|
* string is useful when doing a case insensitive search, as it |
15
|
|
|
* shows the exact matched case of needle. |
16
|
|
|
* |
17
|
|
|
* @param string $needle |
18
|
|
|
* @param string $haystack |
19
|
|
|
* @param bool $caseInsensitive |
20
|
|
|
* @return ConvertHelper_StringMatch[] |
21
|
|
|
*/ |
22
|
|
|
public static function findString(string $needle, string $haystack, bool $caseInsensitive=false): array |
23
|
|
|
{ |
24
|
|
|
if($needle === '') { |
25
|
|
|
return array(); |
26
|
|
|
} |
27
|
|
|
|
28
|
|
|
$function = 'mb_strpos'; |
29
|
|
|
if($caseInsensitive) { |
30
|
|
|
$function = 'mb_stripos'; |
31
|
|
|
} |
32
|
|
|
|
33
|
|
|
$pos = 0; |
34
|
|
|
$positions = array(); |
35
|
|
|
$length = mb_strlen($needle); |
36
|
|
|
|
37
|
|
|
while( ($pos = $function($haystack, $needle, $pos)) !== false) |
38
|
|
|
{ |
39
|
|
|
$match = mb_substr($haystack, $pos, $length); |
40
|
|
|
$positions[] = new ConvertHelper_StringMatch($pos, $match); |
41
|
|
|
$pos += $length; |
42
|
|
|
} |
43
|
|
|
|
44
|
|
|
return $positions; |
45
|
|
|
} |
46
|
|
|
|
47
|
|
|
/** |
48
|
|
|
* Splits a string into an array of all characters it is composed of. |
49
|
|
|
* Unicode character safe. |
50
|
|
|
* |
51
|
|
|
* NOTE: Spaces and newlines (both \r and \n) are also considered single |
52
|
|
|
* characters. |
53
|
|
|
* |
54
|
|
|
* @param string $string |
55
|
|
|
* @return string[] |
56
|
|
|
*/ |
57
|
|
|
public static function toArray(string $string) : array |
58
|
|
|
{ |
59
|
|
|
$result = preg_split('//u', $string, 0, PREG_SPLIT_NO_EMPTY); |
60
|
|
|
if($result !== false) { |
61
|
|
|
return $result; |
|
|
|
|
62
|
|
|
} |
63
|
|
|
|
64
|
|
|
return array(); |
65
|
|
|
} |
66
|
|
|
|
67
|
|
|
/** |
68
|
|
|
* Calculates the byte length of a string, taking into |
69
|
|
|
* account any unicode characters. |
70
|
|
|
* |
71
|
|
|
* @param string $string |
72
|
|
|
* @return int |
73
|
|
|
* @see https://stackoverflow.com/a/9718273/2298192 |
74
|
|
|
*/ |
75
|
|
|
public static function toBytes(string $string) : int |
76
|
|
|
{ |
77
|
|
|
return mb_strlen($string, '8bit'); |
78
|
|
|
} |
79
|
|
|
|
80
|
|
|
/** |
81
|
|
|
* Converts a string into an MD5 hash. |
82
|
|
|
* |
83
|
|
|
* @param string $string |
84
|
|
|
* @return string |
85
|
|
|
*/ |
86
|
|
|
public static function toHash(string $string): string |
87
|
|
|
{ |
88
|
|
|
return md5($string); |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
/** |
92
|
|
|
* Creates a short, 8-character long hash for the specified string. |
93
|
|
|
* |
94
|
|
|
* WARNING: Not cryptographically safe. |
95
|
|
|
* |
96
|
|
|
* @param string $string |
97
|
|
|
* @return string |
98
|
|
|
*/ |
99
|
|
|
public static function toShortHash(string $string) : string |
100
|
|
|
{ |
101
|
|
|
return hash('crc32', $string, false); |
102
|
|
|
} |
103
|
|
|
|
104
|
|
|
/** |
105
|
|
|
* Converts a string to valid utf8, regardless |
106
|
|
|
* of the string's encoding(s). |
107
|
|
|
* |
108
|
|
|
* @param string $string |
109
|
|
|
* @return string |
110
|
|
|
*/ |
111
|
|
|
public static function toUtf8(string $string) : string |
112
|
|
|
{ |
113
|
|
|
if(!self::isASCII($string)) { |
114
|
|
|
return Encoding::toUTF8($string); |
115
|
|
|
} |
116
|
|
|
|
117
|
|
|
return $string; |
118
|
|
|
} |
119
|
|
|
|
120
|
|
|
/** |
121
|
|
|
* Checks whether the specified string is an ASCII |
122
|
|
|
* string, without any special or UTF8 characters. |
123
|
|
|
* Note: empty strings and NULL are considered ASCII. |
124
|
|
|
* Any variable types other than strings are not. |
125
|
|
|
* |
126
|
|
|
* @param mixed $string |
127
|
|
|
* @return boolean |
128
|
|
|
*/ |
129
|
|
|
public static function isASCII(string $string) : bool |
130
|
|
|
{ |
131
|
|
|
if($string === '' || $string === NULL) { |
132
|
|
|
return true; |
133
|
|
|
} |
134
|
|
|
|
135
|
|
|
if(!is_string($string)) { |
|
|
|
|
136
|
|
|
return false; |
137
|
|
|
} |
138
|
|
|
|
139
|
|
|
return !preg_match('/[^\x00-\x7F]/', $string); |
140
|
|
|
} |
141
|
|
|
|
142
|
|
|
/** |
143
|
|
|
* Checks whether the specified string contains HTML code. |
144
|
|
|
* |
145
|
|
|
* @param string $string |
146
|
|
|
* @return boolean |
147
|
|
|
*/ |
148
|
|
|
public static function isHTML(string $string) : bool |
149
|
|
|
{ |
150
|
|
|
if(preg_match('%<[a-z/][\s\S]*>%siU', $string)) { |
151
|
|
|
return true; |
152
|
|
|
} |
153
|
|
|
|
154
|
|
|
$decoded = html_entity_decode($string); |
155
|
|
|
if($decoded !== $string) { |
156
|
|
|
return true; |
157
|
|
|
} |
158
|
|
|
|
159
|
|
|
return false; |
160
|
|
|
} |
161
|
|
|
|
162
|
|
|
/** |
163
|
|
|
* Normalizes tabs in the specified string by indenting everything |
164
|
|
|
* back to the minimum tab distance. With the second parameter, |
165
|
|
|
* tabs can optionally be converted to spaces as well (recommended |
166
|
|
|
* for HTML output). |
167
|
|
|
* |
168
|
|
|
* @param string $string |
169
|
|
|
* @param boolean $tabs2spaces |
170
|
|
|
* @return string |
171
|
|
|
*/ |
172
|
|
|
public static function normalizeTabs(string $string, bool $tabs2spaces = false) : string |
173
|
|
|
{ |
174
|
|
|
$normalizer = new ConvertHelper_TabsNormalizer(); |
175
|
|
|
$normalizer->convertTabsToSpaces($tabs2spaces); |
176
|
|
|
|
177
|
|
|
return $normalizer->normalize($string); |
178
|
|
|
} |
179
|
|
|
|
180
|
|
|
/** |
181
|
|
|
* Converts tabs to spaces in the specified string. |
182
|
|
|
* |
183
|
|
|
* @param string $string |
184
|
|
|
* @param int $tabSize The amount of spaces per tab. |
185
|
|
|
* @return string |
186
|
|
|
*/ |
187
|
|
|
public static function tabs2spaces(string $string, int $tabSize=4) : string |
188
|
|
|
{ |
189
|
|
|
return str_replace("\t", str_repeat(' ', $tabSize), $string); |
190
|
|
|
} |
191
|
|
|
|
192
|
|
|
/** |
193
|
|
|
* Converts spaces to tabs in the specified string. |
194
|
|
|
* |
195
|
|
|
* @param string $string |
196
|
|
|
* @param int $tabSize The amount of spaces per tab in the source string. |
197
|
|
|
* @return string |
198
|
|
|
*/ |
199
|
|
|
public static function spaces2tabs(string $string, int $tabSize=4) : string |
200
|
|
|
{ |
201
|
|
|
return str_replace(str_repeat(' ', $tabSize), "\t", $string); |
202
|
|
|
} |
203
|
|
|
|
204
|
|
|
/** |
205
|
|
|
* Makes all hidden characters visible in the target string, |
206
|
|
|
* from spaces to control characters. |
207
|
|
|
* |
208
|
|
|
* @param string $string |
209
|
|
|
* @return string |
210
|
|
|
*/ |
211
|
|
|
public static function hidden2visible(string $string) : string |
212
|
|
|
{ |
213
|
|
|
$converter = new ConvertHelper_HiddenConverter(); |
214
|
|
|
|
215
|
|
|
return $converter->convert($string); |
216
|
|
|
} |
217
|
|
|
|
218
|
|
|
/** |
219
|
|
|
* UTF8-safe wordwrap method: works like the regular wordwrap |
220
|
|
|
* PHP function but compatible with UTF8. Otherwise the lengths |
221
|
|
|
* are not calculated correctly. |
222
|
|
|
* |
223
|
|
|
* @param string $str |
224
|
|
|
* @param int $width |
225
|
|
|
* @param string $break |
226
|
|
|
* @param bool $cut |
227
|
|
|
* @return string |
228
|
|
|
*/ |
229
|
|
|
public static function wordwrap(string $str, int $width = 75, string $break = "\n", bool $cut = false) : string |
230
|
|
|
{ |
231
|
|
|
$wrapper = new ConvertHelper_WordWrapper(); |
232
|
|
|
|
233
|
|
|
return $wrapper |
234
|
|
|
->setLineWidth($width) |
235
|
|
|
->setBreakCharacter($break) |
236
|
|
|
->setCuttingEnabled($cut) |
237
|
|
|
->wrapText($str); |
238
|
|
|
} |
239
|
|
|
|
240
|
|
|
/** |
241
|
|
|
* Transliterates a string. |
242
|
|
|
* |
243
|
|
|
* @param string $string |
244
|
|
|
* @param string $spaceChar |
245
|
|
|
* @param bool $lowercase |
246
|
|
|
* @return string |
247
|
|
|
*/ |
248
|
|
|
public static function transliterate(string $string, string $spaceChar = '-', bool $lowercase = true) : string |
249
|
|
|
{ |
250
|
|
|
$translit = new Transliteration(); |
251
|
|
|
$translit->setSpaceReplacement($spaceChar); |
252
|
|
|
if ($lowercase) { |
253
|
|
|
$translit->setLowercase(); |
254
|
|
|
} |
255
|
|
|
|
256
|
|
|
return $translit->convert($string); |
257
|
|
|
} |
258
|
|
|
|
259
|
|
|
/** |
260
|
|
|
* Cuts a text to the specified length if it is longer than the |
261
|
|
|
* target length. Appends a text to signify it has been cut at |
262
|
|
|
* the end of the string. |
263
|
|
|
* |
264
|
|
|
* @param string $text |
265
|
|
|
* @param int $targetLength |
266
|
|
|
* @param string $append |
267
|
|
|
* @return string |
268
|
|
|
*/ |
269
|
|
|
public static function cutText(string $text, int $targetLength, string $append = '...') : string |
270
|
|
|
{ |
271
|
|
|
$length = mb_strlen($text); |
272
|
|
|
if ($length <= $targetLength) { |
273
|
|
|
return $text; |
274
|
|
|
} |
275
|
|
|
|
276
|
|
|
$text = trim(mb_substr($text, 0, $targetLength)) . $append; |
277
|
|
|
|
278
|
|
|
return $text; |
279
|
|
|
} |
280
|
|
|
|
281
|
|
|
/** |
282
|
|
|
* Like explode, but trims all entries, and removes |
283
|
|
|
* empty entries from the resulting array. |
284
|
|
|
* |
285
|
|
|
* @param string $delimiter |
286
|
|
|
* @param string $string |
287
|
|
|
* @return string[] |
288
|
|
|
*/ |
289
|
|
|
public static function explodeTrim(string $delimiter, string $string) : array |
290
|
|
|
{ |
291
|
|
|
if(empty($string) || empty($delimiter)) { |
292
|
|
|
return array(); |
293
|
|
|
} |
294
|
|
|
|
295
|
|
|
$tokens = explode($delimiter, $string); |
296
|
|
|
$tokens = array_map('trim', $tokens); |
297
|
|
|
|
298
|
|
|
$keep = array(); |
299
|
|
|
foreach($tokens as $token) { |
300
|
|
|
if($token !== '') { |
301
|
|
|
$keep[] = $token; |
302
|
|
|
} |
303
|
|
|
} |
304
|
|
|
|
305
|
|
|
return $keep; |
306
|
|
|
} |
307
|
|
|
} |
308
|
|
|
|