1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the Ivory Lucene Search package. |
5
|
|
|
* |
6
|
|
|
* (c) Eric GELOEN <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please read the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace Ivory\LuceneSearchBundle\Model; |
13
|
|
|
|
14
|
|
|
use ZendSearch\Lucene\Analysis\Analyzer\Analyzer; |
15
|
|
|
use ZendSearch\Lucene\Analysis\Analyzer\Common\TextNum\CaseInsensitive; |
16
|
|
|
use ZendSearch\Lucene\Index; |
17
|
|
|
use ZendSearch\Lucene\Lucene; |
18
|
|
|
use ZendSearch\Lucene\Search\QueryParser; |
19
|
|
|
use ZendSearch\Lucene\Storage\Directory\Filesystem; |
20
|
|
|
|
21
|
|
|
/** |
22
|
|
|
* @author GeLo <[email protected]> |
23
|
|
|
*/ |
24
|
|
|
class LuceneManager |
25
|
|
|
{ |
26
|
|
|
const DEFAULT_ANALYZER = CaseInsensitive::class; |
27
|
|
|
const DEFAULT_MAX_BUFFERED_DOCS = 10; |
28
|
|
|
const DEFAULT_MAX_MERGE_DOCS = PHP_INT_MAX; |
29
|
|
|
const DEFAULT_MERGE_FACTOR = 10; |
30
|
|
|
const DEFAULT_PERMISSIONS = 0777; |
31
|
|
|
const DEFAULT_AUTO_OPTIMIZED = false; |
32
|
|
|
const DEFAULT_QUERY_PARSER_ENCODING = ''; |
33
|
|
|
|
34
|
|
|
/** |
35
|
|
|
* @var Index[] |
36
|
|
|
*/ |
37
|
|
|
private $indexes = []; |
38
|
|
|
|
39
|
|
|
/** |
40
|
|
|
* @var array |
41
|
|
|
*/ |
42
|
|
|
private $configs = []; |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* @return bool |
46
|
|
|
*/ |
47
|
27 |
|
public function hasIndexes() |
48
|
|
|
{ |
49
|
27 |
|
return !empty($this->configs); |
50
|
|
|
} |
51
|
|
|
|
52
|
|
|
/** |
53
|
|
|
* @return string[] |
54
|
|
|
*/ |
55
|
108 |
|
public function getIndexes() |
56
|
7 |
|
{ |
57
|
108 |
|
return array_keys($this->configs); |
58
|
|
|
} |
59
|
|
|
|
60
|
|
|
/** |
61
|
|
|
* @param string $identifier |
62
|
|
|
* |
63
|
|
|
* @return bool |
64
|
|
|
*/ |
65
|
18 |
|
public function hasIndex($identifier) |
66
|
|
|
{ |
67
|
18 |
|
return isset($this->configs[$identifier]); |
68
|
|
|
} |
69
|
|
|
|
70
|
|
|
/** |
71
|
|
|
* @param string $identifier |
72
|
|
|
* |
73
|
|
|
* @return Index |
74
|
|
|
*/ |
75
|
81 |
|
public function getIndex($identifier) |
76
|
|
|
{ |
77
|
81 |
|
$config = $this->getConfig($identifier); |
78
|
72 |
|
$path = $config['path']; |
79
|
|
|
|
80
|
72 |
|
Filesystem::setDefaultFilePermissions($config['permissions']); |
81
|
72 |
|
QueryParser::setDefaultEncoding($config['query_parser_encoding']); |
82
|
72 |
|
Analyzer::setDefault(new $config['analyzer']()); |
83
|
|
|
|
84
|
72 |
|
if (!$this->checkPath($path)) { |
85
|
72 |
|
$this->indexes[$identifier] = Lucene::create($path); |
86
|
56 |
|
} else { |
87
|
63 |
|
$this->indexes[$identifier] = Lucene::open($path); |
88
|
|
|
} |
89
|
|
|
|
90
|
72 |
|
$this->indexes[$identifier]->setMaxBufferedDocs($config['max_buffered_docs']); |
91
|
72 |
|
$this->indexes[$identifier]->setMaxMergeDocs($config['max_merge_docs']); |
92
|
72 |
|
$this->indexes[$identifier]->setMergeFactor($config['merge_factor']); |
93
|
|
|
|
94
|
72 |
|
if ($config['auto_optimized']) { |
95
|
18 |
|
$this->indexes[$identifier]->optimize(); |
96
|
14 |
|
} |
97
|
|
|
|
98
|
72 |
|
return $this->indexes[$identifier]; |
99
|
|
|
} |
100
|
|
|
|
101
|
|
|
/** |
102
|
|
|
* @param array $indexes |
103
|
|
|
* |
104
|
|
|
* @throws \InvalidArgumentException |
105
|
|
|
*/ |
106
|
36 |
|
public function setIndexes(array $indexes) |
107
|
|
|
{ |
108
|
36 |
|
foreach ($indexes as $identifier => $index) { |
109
|
36 |
|
if (!isset($index['path'])) { |
110
|
9 |
|
throw new \InvalidArgumentException('Each lucene index must have a path value.'); |
111
|
|
|
} |
112
|
|
|
|
113
|
27 |
|
$this->setIndex( |
114
|
21 |
|
$identifier, |
115
|
27 |
|
$index['path'], |
116
|
27 |
|
isset($index['analyzer']) ? $index['analyzer'] : self::DEFAULT_ANALYZER, |
117
|
27 |
|
isset($index['max_buffered_docs']) ? $index['max_buffered_docs'] : self::DEFAULT_MAX_BUFFERED_DOCS, |
118
|
27 |
|
isset($index['max_merge_docs']) ? $index['max_merge_docs'] : self::DEFAULT_MAX_MERGE_DOCS, |
119
|
27 |
|
isset($index['merge_factor']) ? $index['merge_factor'] : self::DEFAULT_MERGE_FACTOR, |
120
|
27 |
|
isset($index['permissions']) ? $index['permissions'] : self::DEFAULT_PERMISSIONS, |
121
|
27 |
|
isset($index['auto_optimized']) ? $index['auto_optimized'] : self::DEFAULT_AUTO_OPTIMIZED, |
122
|
27 |
|
isset($index['query_parser_encoding']) ? $index['query_parser_encoding'] : self::DEFAULT_QUERY_PARSER_ENCODING |
123
|
21 |
|
); |
124
|
21 |
|
} |
125
|
27 |
|
} |
126
|
|
|
|
127
|
|
|
/** |
128
|
|
|
* @param string $identifier |
129
|
|
|
* @param string $path |
130
|
|
|
* @param string $analyzer |
131
|
|
|
* @param int $maxBufferedDocs |
132
|
|
|
* @param int $maxMergeDocs |
133
|
|
|
* @param int $mergeFactor |
134
|
|
|
* @param int $permissions |
135
|
|
|
* @param bool $autoOptimized |
136
|
|
|
* @param string $queryParserEncoding |
137
|
|
|
*/ |
138
|
72 |
|
public function setIndex( |
139
|
|
|
$identifier, |
140
|
|
|
$path, |
141
|
|
|
$analyzer = self::DEFAULT_ANALYZER, |
142
|
|
|
$maxBufferedDocs = self::DEFAULT_MAX_BUFFERED_DOCS, |
143
|
|
|
$maxMergeDocs = self::DEFAULT_MAX_MERGE_DOCS, |
144
|
|
|
$mergeFactor = self::DEFAULT_MERGE_FACTOR, |
145
|
|
|
$permissions = self::DEFAULT_PERMISSIONS, |
146
|
|
|
$autoOptimized = self::DEFAULT_AUTO_OPTIMIZED, |
147
|
|
|
$queryParserEncoding = self::DEFAULT_QUERY_PARSER_ENCODING |
148
|
|
|
) { |
149
|
72 |
|
$this->configs[$identifier] = [ |
150
|
72 |
|
'path' => $path, |
151
|
72 |
|
'analyzer' => $analyzer, |
152
|
72 |
|
'max_buffered_docs' => $maxBufferedDocs, |
153
|
72 |
|
'max_merge_docs' => $maxMergeDocs, |
154
|
72 |
|
'merge_factor' => $mergeFactor, |
155
|
72 |
|
'permissions' => $permissions, |
156
|
72 |
|
'auto_optimized' => $autoOptimized, |
157
|
72 |
|
'query_parser_encoding' => $queryParserEncoding, |
158
|
|
|
]; |
159
|
72 |
|
} |
160
|
|
|
|
161
|
|
|
/** |
162
|
|
|
* @param string $identifier |
163
|
|
|
* @param bool $removeDirectory |
164
|
|
|
*/ |
165
|
9 |
|
public function removeIndex($identifier, $removeDirectory = false) |
166
|
|
|
{ |
167
|
9 |
|
if ($removeDirectory) { |
168
|
9 |
|
$this->eraseIndex($identifier); |
169
|
7 |
|
} |
170
|
|
|
|
171
|
9 |
|
unset($this->indexes[$identifier]); |
172
|
9 |
|
unset($this->configs[$identifier]); |
173
|
9 |
|
} |
174
|
|
|
|
175
|
|
|
/** |
176
|
|
|
* @param string $identifier |
177
|
|
|
*/ |
178
|
72 |
|
public function eraseIndex($identifier) |
179
|
|
|
{ |
180
|
72 |
|
$directory = $this->getIndex($identifier)->getDirectory(); |
181
|
72 |
|
unset($this->indexes[$identifier]); |
182
|
|
|
|
183
|
72 |
|
if (!$directory instanceof Filesystem) { |
184
|
|
|
return; |
185
|
|
|
} |
186
|
|
|
|
187
|
72 |
|
foreach ($directory->fileList() as $file) { |
188
|
72 |
|
$directory->deleteFile($file); |
189
|
56 |
|
} |
190
|
|
|
|
191
|
72 |
|
$config = $this->getConfig($identifier); |
192
|
|
|
|
193
|
72 |
|
if (is_dir($config['path'])) { |
194
|
72 |
|
rmdir($config['path']); |
195
|
56 |
|
} |
196
|
72 |
|
} |
197
|
|
|
|
198
|
|
|
/** |
199
|
|
|
* @param string $identifier |
200
|
|
|
* |
201
|
|
|
* @throws \InvalidArgumentException |
202
|
|
|
* |
203
|
|
|
* @return array |
204
|
|
|
*/ |
205
|
81 |
|
private function getConfig($identifier) |
206
|
|
|
{ |
207
|
81 |
|
if (!isset($this->configs[$identifier])) { |
208
|
9 |
|
throw new \InvalidArgumentException(sprintf('The lucene index "%s" does not exist.', $identifier)); |
209
|
|
|
} |
210
|
|
|
|
211
|
72 |
|
return $this->configs[$identifier]; |
212
|
|
|
} |
213
|
|
|
|
214
|
|
|
/** |
215
|
|
|
* @param string $path |
216
|
|
|
* |
217
|
|
|
* @return bool |
218
|
|
|
*/ |
219
|
72 |
|
private function checkPath($path) |
220
|
|
|
{ |
221
|
72 |
|
return file_exists($path) && is_readable($path) && ($resources = scandir($path)) && (count($resources) > 2); |
222
|
|
|
} |
223
|
|
|
} |
224
|
|
|
|