1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
namespace Palmtree\Csv; |
6
|
|
|
|
7
|
|
|
use Palmtree\Csv\Normalizer\NormalizerInterface; |
8
|
|
|
use Palmtree\Csv\Normalizer\NullNormalizer; |
9
|
|
|
use Palmtree\Csv\Row\Row; |
10
|
|
|
use Palmtree\Csv\Util\StringUtil; |
11
|
|
|
|
12
|
|
|
/** |
13
|
|
|
* Reads a CSV file by loading each line into memory one at a time. |
14
|
|
|
*/ |
15
|
|
|
class Reader extends AbstractCsvDocument implements \Iterator |
16
|
|
|
{ |
17
|
|
|
/** @var class-string<NormalizerInterface> */ |
18
|
|
|
private string $defaultNormalizer = NullNormalizer::class; |
19
|
|
|
private ?NormalizerInterface $headerNormalizer = null; |
20
|
|
|
/** @var array<NormalizerInterface> */ |
21
|
|
|
private array $normalizers = []; |
22
|
|
|
private ?Row $headers = null; |
23
|
|
|
private ?Row $row = null; |
24
|
|
|
private ?string $stripBom = StringUtil::BOM_UTF8; |
25
|
|
|
private int $offset = 0; |
26
|
|
|
private int $headerOffset = 0; |
27
|
|
|
|
28
|
|
|
public static function read(string $filePath, bool $hasHeaders = true): self |
29
|
|
|
{ |
30
|
|
|
return new self($filePath, $hasHeaders); |
31
|
|
|
} |
32
|
|
|
|
33
|
3 |
|
public function getHeaders(): ?Row |
34
|
|
|
{ |
35
|
3 |
|
if ($this->hasHeaders && $this->headers === null) { |
36
|
3 |
|
$this->rewind(); |
37
|
|
|
} |
38
|
|
|
|
39
|
3 |
|
return $this->headers; |
40
|
|
|
} |
41
|
|
|
|
42
|
|
|
/** |
43
|
|
|
* @param string|int $key |
44
|
|
|
* |
45
|
|
|
* @return string|int |
46
|
|
|
*/ |
47
|
12 |
|
public function getHeader($key) |
48
|
|
|
{ |
49
|
12 |
|
return $this->headers[$key] ?? $key; |
50
|
|
|
} |
51
|
|
|
|
52
|
|
|
public function setHeaderNormalizer(NormalizerInterface $headerNormalizer): self |
53
|
|
|
{ |
54
|
|
|
$this->headerNormalizer = $headerNormalizer; |
55
|
|
|
|
56
|
|
|
return $this; |
57
|
|
|
} |
58
|
|
|
|
59
|
10 |
|
public function getHeaderNormalizer(): NormalizerInterface |
60
|
|
|
{ |
61
|
10 |
|
return $this->headerNormalizer ??= new NullNormalizer(); |
62
|
|
|
} |
63
|
|
|
|
64
|
|
|
public function addNormalizer(string $key, NormalizerInterface $normalizer): self |
65
|
|
|
{ |
66
|
|
|
$this->normalizers[$key] = $normalizer; |
67
|
|
|
|
68
|
|
|
return $this; |
69
|
|
|
} |
70
|
|
|
|
71
|
|
|
/** |
72
|
|
|
* @param iterable<NormalizerInterface> $normalizers |
73
|
|
|
*/ |
74
|
|
|
public function addNormalizers(iterable $normalizers): self |
75
|
|
|
{ |
76
|
|
|
foreach ($normalizers as $key => $normalizer) { |
77
|
|
|
$this->addNormalizer($key, $normalizer); |
78
|
|
|
} |
79
|
|
|
|
80
|
|
|
return $this; |
81
|
|
|
} |
82
|
|
|
|
83
|
|
|
/** |
84
|
|
|
* @param string|int $key |
85
|
|
|
*/ |
86
|
12 |
|
public function getNormalizer($key): NormalizerInterface |
87
|
|
|
{ |
88
|
12 |
|
if ($this->hasHeaders && \is_int($key)) { |
89
|
10 |
|
$this->normalizers[$key] = $this->getHeaderNormalizer(); |
90
|
|
|
} |
91
|
|
|
|
92
|
12 |
|
if (!isset($this->normalizers[$key])) { |
93
|
6 |
|
$class = $this->getDefaultNormalizer(); |
94
|
|
|
|
95
|
6 |
|
$this->normalizers[$key] = new $class(); |
96
|
|
|
} |
97
|
|
|
|
98
|
12 |
|
return $this->normalizers[$key]; |
99
|
|
|
} |
100
|
|
|
|
101
|
|
|
/** |
102
|
|
|
* @param class-string<NormalizerInterface> $defaultNormalizer |
103
|
|
|
*/ |
104
|
|
|
public function setDefaultNormalizer(string $defaultNormalizer): self |
105
|
|
|
{ |
106
|
|
|
$this->defaultNormalizer = $defaultNormalizer; |
107
|
|
|
|
108
|
|
|
return $this; |
109
|
|
|
} |
110
|
|
|
|
111
|
|
|
/** |
112
|
|
|
* @return class-string<NormalizerInterface> |
113
|
|
|
*/ |
114
|
6 |
|
public function getDefaultNormalizer(): string |
115
|
|
|
{ |
116
|
6 |
|
return $this->defaultNormalizer; |
117
|
|
|
} |
118
|
|
|
|
119
|
1 |
|
public function setStripBom(?string $stripBom): self |
120
|
|
|
{ |
121
|
1 |
|
$this->stripBom = $stripBom; |
122
|
|
|
|
123
|
1 |
|
return $this; |
124
|
|
|
} |
125
|
|
|
|
126
|
1 |
|
public function setOffset(int $offset): self |
127
|
|
|
{ |
128
|
1 |
|
$this->offset = $offset; |
129
|
|
|
|
130
|
1 |
|
return $this; |
131
|
|
|
} |
132
|
|
|
|
133
|
|
|
public function getOffset(): int |
134
|
|
|
{ |
135
|
|
|
return $this->offset; |
136
|
|
|
} |
137
|
|
|
|
138
|
1 |
|
public function setHeaderOffset(int $headerOffset): self |
139
|
|
|
{ |
140
|
1 |
|
$this->headerOffset = $headerOffset; |
141
|
|
|
|
142
|
1 |
|
return $this; |
143
|
|
|
} |
144
|
|
|
|
145
|
|
|
public function getHeaderOffset(): int |
146
|
|
|
{ |
147
|
|
|
return $this->headerOffset; |
148
|
|
|
} |
149
|
|
|
|
150
|
6 |
|
public function current(): Row |
151
|
|
|
{ |
152
|
6 |
|
\assert($this->row instanceof Row); |
153
|
|
|
|
154
|
6 |
|
return $this->row; |
155
|
|
|
} |
156
|
|
|
|
157
|
6 |
|
public function next(): void |
158
|
|
|
{ |
159
|
6 |
|
$this->getDocument()->next(); |
160
|
6 |
|
} |
161
|
|
|
|
162
|
8 |
|
public function key(): int |
163
|
|
|
{ |
164
|
8 |
|
return $this->getDocument()->key(); |
165
|
|
|
} |
166
|
|
|
|
167
|
6 |
|
public function valid(): bool |
168
|
|
|
{ |
169
|
6 |
|
$this->row = $this->getCurrentRow(); |
170
|
|
|
|
171
|
6 |
|
return $this->row instanceof Row; |
172
|
|
|
} |
173
|
|
|
|
174
|
8 |
|
public function rewind(): void |
175
|
|
|
{ |
176
|
8 |
|
$this->getDocument()->rewind(); |
177
|
|
|
|
178
|
8 |
|
$dataOffset = $this->offset + $this->headerOffset; |
179
|
8 |
|
if ($this->hasHeaders) { |
180
|
6 |
|
if ($this->headerOffset) { |
181
|
1 |
|
$this->getDocument()->seek($this->headerOffset); |
182
|
|
|
} |
183
|
|
|
|
184
|
|
|
// Set headers to null first so the header row is a zero-based array and can be used |
185
|
|
|
// to set the array keys of all other rows. |
186
|
6 |
|
$this->headers = null; |
187
|
6 |
|
$this->headers = $this->getCurrentRow(); |
188
|
|
|
|
189
|
6 |
|
++$dataOffset; |
190
|
|
|
} |
191
|
|
|
|
192
|
8 |
|
if ($dataOffset > 0) { |
193
|
6 |
|
$this->getDocument()->seek($dataOffset); |
194
|
|
|
} |
195
|
8 |
|
} |
196
|
|
|
|
197
|
4 |
|
public function toArray(): array |
198
|
|
|
{ |
199
|
4 |
|
$result = []; |
200
|
4 |
|
foreach ($this as $row) { |
201
|
4 |
|
$result[] = $row->toArray(); |
202
|
|
|
} |
203
|
|
|
|
204
|
4 |
|
return $result; |
205
|
|
|
} |
206
|
|
|
|
207
|
7 |
|
protected function getOpenMode(): string |
208
|
|
|
{ |
209
|
7 |
|
return 'r'; |
210
|
|
|
} |
211
|
|
|
|
212
|
|
|
/** |
213
|
|
|
* Reads the next line in the CSV file and returns a Row object from it. |
214
|
|
|
*/ |
215
|
8 |
|
private function getCurrentRow(): ?Row |
216
|
|
|
{ |
217
|
8 |
|
$cells = $this->getDocument()->current(); |
218
|
|
|
|
219
|
8 |
|
if (!\is_array($cells) || $cells == [null]) { |
220
|
6 |
|
return null; |
221
|
|
|
} |
222
|
|
|
|
223
|
8 |
|
if ($this->key() === 0 && $this->stripBom) { |
224
|
6 |
|
$stripped = StringUtil::stripBom($cells[0], $this->stripBom); |
225
|
|
|
|
226
|
6 |
|
if ($stripped !== $cells[0]) { |
227
|
1 |
|
$cells[0] = trim($stripped, $this->enclosure); |
228
|
|
|
} |
229
|
|
|
} |
230
|
|
|
|
231
|
8 |
|
return new Row($cells, $this); |
232
|
|
|
} |
233
|
|
|
} |
234
|
|
|
|