|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* This file is part of the League.csv library |
|
4
|
|
|
* |
|
5
|
|
|
* @license http://opensource.org/licenses/MIT |
|
6
|
|
|
* @link https://github.com/thephpleague/csv/ |
|
7
|
|
|
* @version 9.0.0 |
|
8
|
|
|
* @package League.csv |
|
9
|
|
|
* |
|
10
|
|
|
* For the full copyright and license information, please view the LICENSE |
|
11
|
|
|
* file that was distributed with this source code. |
|
12
|
|
|
*/ |
|
13
|
|
|
declare(strict_types=1); |
|
14
|
|
|
|
|
15
|
|
|
namespace League\Csv\Config; |
|
16
|
|
|
|
|
17
|
|
|
use CallbackFilterIterator; |
|
18
|
|
|
use InvalidArgumentException; |
|
19
|
|
|
use League\Csv\AbstractCsv; |
|
20
|
|
|
use LimitIterator; |
|
21
|
|
|
use SplFileObject; |
|
22
|
|
|
|
|
23
|
|
|
/** |
|
24
|
|
|
* An abstract class to enable basic CSV manipulation |
|
25
|
|
|
* |
|
26
|
|
|
* @package League.csv |
|
27
|
|
|
* @since 9.0.0 |
|
28
|
|
|
* @internal |
|
29
|
|
|
*/ |
|
30
|
|
|
trait ControlsTrait |
|
31
|
|
|
{ |
|
32
|
|
|
use ValidatorTrait; |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* the field delimiter (one character only) |
|
36
|
|
|
* |
|
37
|
|
|
* @var string |
|
38
|
|
|
*/ |
|
39
|
|
|
protected $delimiter = ','; |
|
40
|
|
|
|
|
41
|
|
|
/** |
|
42
|
|
|
* the field enclosure character (one character only) |
|
43
|
|
|
* |
|
44
|
|
|
* @var string |
|
45
|
|
|
*/ |
|
46
|
|
|
protected $enclosure = '"'; |
|
47
|
|
|
|
|
48
|
|
|
/** |
|
49
|
|
|
* the field escape character (one character only) |
|
50
|
|
|
* |
|
51
|
|
|
* @var string |
|
52
|
|
|
*/ |
|
53
|
|
|
protected $escape = '\\'; |
|
54
|
|
|
|
|
55
|
|
|
/** |
|
56
|
|
|
* newline character |
|
57
|
|
|
* |
|
58
|
|
|
* @var string |
|
59
|
|
|
*/ |
|
60
|
|
|
protected $newline = "\n"; |
|
61
|
|
|
|
|
62
|
|
|
/** |
|
63
|
|
|
* The Input file BOM character |
|
64
|
|
|
* @var string |
|
65
|
|
|
*/ |
|
66
|
|
|
protected $input_bom; |
|
67
|
|
|
|
|
68
|
|
|
/** |
|
69
|
|
|
* The Output file BOM character |
|
70
|
|
|
* @var string |
|
71
|
|
|
*/ |
|
72
|
|
|
protected $output_bom = ''; |
|
73
|
|
|
|
|
74
|
|
|
/** |
|
75
|
|
|
* CSV Document header offset |
|
76
|
|
|
* |
|
77
|
|
|
* @var int|null |
|
78
|
|
|
*/ |
|
79
|
|
|
protected $header_offset; |
|
80
|
|
|
|
|
81
|
|
|
/** |
|
82
|
|
|
* Buffer flush threshold |
|
83
|
|
|
* |
|
84
|
|
|
* @var int |
|
85
|
|
|
*/ |
|
86
|
|
|
protected $flush_threshold = 500; |
|
87
|
|
|
|
|
88
|
|
|
/** |
|
89
|
|
|
* Returns the inner CSV Document Iterator object |
|
90
|
|
|
* |
|
91
|
|
|
* @return StreamIterator|SplFileObject |
|
92
|
|
|
*/ |
|
93
|
|
|
abstract public function getDocument(); |
|
94
|
|
|
|
|
95
|
|
|
/** |
|
96
|
|
|
* Returns the current field delimiter |
|
97
|
|
|
* |
|
98
|
|
|
* @return string |
|
99
|
|
|
*/ |
|
100
|
|
|
public function getDelimiter(): string |
|
101
|
|
|
{ |
|
102
|
|
|
return $this->delimiter; |
|
103
|
|
|
} |
|
104
|
|
|
|
|
105
|
|
|
/** |
|
106
|
|
|
* Returns the current field enclosure |
|
107
|
|
|
* |
|
108
|
|
|
* @return string |
|
109
|
|
|
*/ |
|
110
|
|
|
public function getEnclosure(): string |
|
111
|
|
|
{ |
|
112
|
|
|
return $this->enclosure; |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* Returns the current field escape character |
|
117
|
|
|
* |
|
118
|
|
|
* @return string |
|
119
|
|
|
*/ |
|
120
|
|
|
public function getEscape(): string |
|
121
|
|
|
{ |
|
122
|
|
|
return $this->escape; |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
/** |
|
126
|
|
|
* Returns the current newline sequence characters |
|
127
|
|
|
* |
|
128
|
|
|
* @return string |
|
129
|
|
|
*/ |
|
130
|
|
|
public function getNewline(): string |
|
131
|
|
|
{ |
|
132
|
|
|
return $this->newline; |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* Get the flush threshold |
|
137
|
|
|
* |
|
138
|
|
|
* @return int |
|
139
|
|
|
*/ |
|
140
|
|
|
public function getFlushThreshold(): int |
|
141
|
|
|
{ |
|
142
|
|
|
return $this->flush_threshold; |
|
143
|
|
|
} |
|
144
|
|
|
|
|
145
|
|
|
/** |
|
146
|
|
|
* Returns the BOM sequence in use on Output methods |
|
147
|
|
|
* |
|
148
|
|
|
* @return string |
|
149
|
|
|
*/ |
|
150
|
|
|
public function getOutputBOM(): string |
|
151
|
|
|
{ |
|
152
|
|
|
return $this->output_bom; |
|
153
|
|
|
} |
|
154
|
|
|
|
|
155
|
|
|
/** |
|
156
|
|
|
* Returns the record offset used as header |
|
157
|
|
|
* |
|
158
|
|
|
* If no CSV record is used this method MUST return null |
|
159
|
|
|
* |
|
160
|
|
|
* @return int|null |
|
161
|
|
|
*/ |
|
162
|
|
|
public function getHeaderOffset() |
|
163
|
|
|
{ |
|
164
|
|
|
return $this->header_offset; |
|
165
|
|
|
} |
|
166
|
|
|
|
|
167
|
|
|
/** |
|
168
|
|
|
* Returns the BOM sequence of the given CSV |
|
169
|
|
|
* |
|
170
|
|
|
* @return string |
|
171
|
|
|
*/ |
|
172
|
|
|
public function getInputBOM(): string |
|
173
|
|
|
{ |
|
174
|
|
|
if (null === $this->input_bom) { |
|
175
|
|
|
$bom = [ |
|
176
|
|
|
AbstractCsv::BOM_UTF32_BE, AbstractCsv::BOM_UTF32_LE, |
|
177
|
|
|
AbstractCsv::BOM_UTF16_BE, AbstractCsv::BOM_UTF16_LE, AbstractCsv::BOM_UTF8, |
|
178
|
|
|
]; |
|
179
|
|
|
$csv = $this->getDocument(); |
|
180
|
|
|
$csv->setFlags(SplFileObject::READ_CSV); |
|
181
|
|
|
$csv->rewind(); |
|
182
|
|
|
$line = $csv->fgets(); |
|
183
|
|
|
$res = array_filter($bom, function ($sequence) use ($line) { |
|
184
|
|
|
return strpos($line, $sequence) === 0; |
|
185
|
|
|
}); |
|
186
|
|
|
|
|
187
|
|
|
$this->input_bom = (string) array_shift($res); |
|
188
|
|
|
} |
|
189
|
|
|
|
|
190
|
|
|
return $this->input_bom; |
|
191
|
|
|
} |
|
192
|
|
|
|
|
193
|
|
|
/** |
|
194
|
|
|
* Detect Delimiters occurences in the CSV |
|
195
|
|
|
* |
|
196
|
|
|
* Returns a associative array where each key represents |
|
197
|
|
|
* a valid delimiter and each value the number of occurences |
|
198
|
|
|
* |
|
199
|
|
|
* @param string[] $delimiters the delimiters to consider |
|
200
|
|
|
* @param int $nb_rows Detection is made using $nb_rows of the CSV |
|
201
|
|
|
* |
|
202
|
|
|
* @return array |
|
203
|
|
|
*/ |
|
204
|
|
|
public function fetchDelimitersOccurrence(array $delimiters, int $nb_rows = 1): array |
|
205
|
|
|
{ |
|
206
|
|
|
$nb_rows = $this->filterInteger($nb_rows, 1, 'The number of rows to consider must be a valid positive integer'); |
|
207
|
|
|
$filter_row = function ($row) { |
|
208
|
|
|
return is_array($row) && count($row) > 1; |
|
209
|
|
|
}; |
|
210
|
|
|
$delimiters = array_unique(array_filter($delimiters, function ($value) { |
|
211
|
|
|
return 1 == strlen($value); |
|
212
|
|
|
})); |
|
213
|
|
|
$csv = $this->getDocument(); |
|
214
|
|
|
$csv->setFlags(SplFileObject::READ_CSV); |
|
215
|
|
|
$res = []; |
|
216
|
|
|
foreach ($delimiters as $delim) { |
|
217
|
|
|
$csv->setCsvControl($delim, $this->enclosure, $this->escape); |
|
218
|
|
|
$iterator = new CallbackFilterIterator(new LimitIterator($csv, 0, $nb_rows), $filter_row); |
|
219
|
|
|
$res[$delim] = count(iterator_to_array($iterator, false), COUNT_RECURSIVE); |
|
220
|
|
|
} |
|
221
|
|
|
arsort($res, SORT_NUMERIC); |
|
222
|
|
|
|
|
223
|
|
|
return $res; |
|
224
|
|
|
} |
|
225
|
|
|
|
|
226
|
|
|
/** |
|
227
|
|
|
* Sets the field delimiter |
|
228
|
|
|
* |
|
229
|
|
|
* @param string $delimiter |
|
230
|
|
|
* |
|
231
|
|
|
* @throws InvalidArgumentException If $delimiter is not a single character |
|
232
|
|
|
* |
|
233
|
|
|
* @return $this |
|
234
|
|
|
*/ |
|
235
|
|
|
public function setDelimiter(string $delimiter): self |
|
236
|
|
|
{ |
|
237
|
|
|
$this->delimiter = $this->filterControl($delimiter, 'delimiter'); |
|
238
|
|
|
|
|
239
|
|
|
return $this; |
|
240
|
|
|
} |
|
241
|
|
|
|
|
242
|
|
|
/** |
|
243
|
|
|
* Sets the field enclosure |
|
244
|
|
|
* |
|
245
|
|
|
* @param string $enclosure |
|
246
|
|
|
* |
|
247
|
|
|
* @throws InvalidArgumentException If $enclosure is not a single character |
|
248
|
|
|
* |
|
249
|
|
|
* @return $this |
|
250
|
|
|
*/ |
|
251
|
|
|
public function setEnclosure(string $enclosure): self |
|
252
|
|
|
{ |
|
253
|
|
|
$this->enclosure = $this->filterControl($enclosure, 'enclosure'); |
|
254
|
|
|
|
|
255
|
|
|
return $this; |
|
256
|
|
|
} |
|
257
|
|
|
|
|
258
|
|
|
/** |
|
259
|
|
|
* Sets the field escape character |
|
260
|
|
|
* |
|
261
|
|
|
* @param string $escape |
|
262
|
|
|
* |
|
263
|
|
|
* @throws InvalidArgumentException If $escape is not a single character |
|
264
|
|
|
* |
|
265
|
|
|
* @return $this |
|
266
|
|
|
*/ |
|
267
|
|
|
public function setEscape(string $escape): self |
|
268
|
|
|
{ |
|
269
|
|
|
$this->escape = $this->filterControl($escape, 'escape'); |
|
270
|
|
|
|
|
271
|
|
|
return $this; |
|
272
|
|
|
} |
|
273
|
|
|
|
|
274
|
|
|
/** |
|
275
|
|
|
* Sets the newline sequence characters |
|
276
|
|
|
* |
|
277
|
|
|
* @param string $newline |
|
278
|
|
|
* |
|
279
|
|
|
* @return static |
|
280
|
|
|
*/ |
|
281
|
|
|
public function setNewline(string $newline): self |
|
282
|
|
|
{ |
|
283
|
|
|
$this->newline = (string) $newline; |
|
284
|
|
|
|
|
285
|
|
|
return $this; |
|
286
|
|
|
} |
|
287
|
|
|
|
|
288
|
|
|
/** |
|
289
|
|
|
* Set the automatic flush threshold on write |
|
290
|
|
|
* |
|
291
|
|
|
* @param int $threshold |
|
292
|
|
|
*/ |
|
293
|
|
|
public function setFlushThreshold(int $threshold): self |
|
294
|
|
|
{ |
|
295
|
|
|
$this->flush_threshold = $this->filterInteger($threshold, 0, 'The flush threshold must be a valid positive integer or 0'); |
|
296
|
|
|
|
|
297
|
|
|
return $this; |
|
298
|
|
|
} |
|
299
|
|
|
|
|
300
|
|
|
/** |
|
301
|
|
|
* Sets the BOM sequence to prepend the CSV on output |
|
302
|
|
|
* |
|
303
|
|
|
* @param string $str The BOM sequence |
|
304
|
|
|
* |
|
305
|
|
|
* @return static |
|
306
|
|
|
*/ |
|
307
|
|
|
public function setOutputBOM(string $str): self |
|
308
|
|
|
{ |
|
309
|
|
|
if (empty($str)) { |
|
310
|
|
|
$this->output_bom = ''; |
|
311
|
|
|
|
|
312
|
|
|
return $this; |
|
313
|
|
|
} |
|
314
|
|
|
|
|
315
|
|
|
$this->output_bom = (string) $str; |
|
316
|
|
|
|
|
317
|
|
|
return $this; |
|
318
|
|
|
} |
|
319
|
|
|
|
|
320
|
|
|
/** |
|
321
|
|
|
* Selects the record to be used as the CSV header |
|
322
|
|
|
* |
|
323
|
|
|
* Because of the header is represented as an array, to be valid |
|
324
|
|
|
* a header MUST contain only unique string value. |
|
325
|
|
|
* |
|
326
|
|
|
* @param int|null $offset the header row offset |
|
327
|
|
|
* |
|
328
|
|
|
* @return $this |
|
329
|
|
|
*/ |
|
330
|
|
|
public function setHeaderOffset(int $offset = null): self |
|
331
|
|
|
{ |
|
332
|
|
|
$this->header_offset = null; |
|
333
|
|
|
if (null !== $offset) { |
|
334
|
|
|
$this->header_offset = $this->filterInteger( |
|
335
|
|
|
$offset, |
|
336
|
|
|
0, |
|
337
|
|
|
'the header offset index must be a positive integer or 0' |
|
338
|
|
|
); |
|
339
|
|
|
} |
|
340
|
|
|
|
|
341
|
|
|
return $this; |
|
342
|
|
|
} |
|
343
|
|
|
} |
|
344
|
|
|
|