|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace MediaWiki\Search; |
|
4
|
|
|
|
|
5
|
|
|
use Category; |
|
6
|
|
|
use ParserOutput; |
|
7
|
|
|
use Title; |
|
8
|
|
|
|
|
9
|
|
|
/** |
|
10
|
|
|
* Extracts data from ParserOutput for indexing in the search engine. |
|
11
|
|
|
* |
|
12
|
|
|
* This program is free software; you can redistribute it and/or modify |
|
13
|
|
|
* it under the terms of the GNU General Public License as published by |
|
14
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
|
15
|
|
|
* (at your option) any later version. |
|
16
|
|
|
* |
|
17
|
|
|
* This program is distributed in the hope that it will be useful, |
|
18
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
19
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
20
|
|
|
* GNU General Public License for more details. |
|
21
|
|
|
* |
|
22
|
|
|
* You should have received a copy of the GNU General Public License along |
|
23
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
|
24
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
|
25
|
|
|
* http://www.gnu.org/copyleft/gpl.html |
|
26
|
|
|
* |
|
27
|
|
|
* @since 1.28 |
|
28
|
|
|
*/ |
|
29
|
|
|
class ParserOutputSearchDataExtractor { |
|
30
|
|
|
|
|
31
|
|
|
/** |
|
32
|
|
|
* Get a list of categories, as an array with title text strings. |
|
33
|
|
|
* |
|
34
|
|
|
* @return string[] |
|
35
|
|
|
*/ |
|
36
|
|
|
public function getCategories( ParserOutput $parserOutput ) { |
|
37
|
|
|
$categories = []; |
|
38
|
|
|
|
|
39
|
|
|
foreach ( $parserOutput->getCategoryLinks() as $key ) { |
|
40
|
|
|
$categories[] = Category::newFromName( $key )->getTitle()->getText(); |
|
41
|
|
|
} |
|
42
|
|
|
|
|
43
|
|
|
return $categories; |
|
44
|
|
|
} |
|
45
|
|
|
|
|
46
|
|
|
/** |
|
47
|
|
|
* Get a list of external links from ParserOutput, as an array of strings. |
|
48
|
|
|
* |
|
49
|
|
|
* @return string[] |
|
50
|
|
|
*/ |
|
51
|
|
|
public function getExternalLinks( ParserOutput $parserOutput ) { |
|
52
|
|
|
return array_keys( $parserOutput->getExternalLinks() ); |
|
53
|
|
|
} |
|
54
|
|
|
|
|
55
|
|
|
/** |
|
56
|
|
|
* Get a list of outgoing wiki links (including interwiki links), as |
|
57
|
|
|
* an array of prefixed title strings. |
|
58
|
|
|
* |
|
59
|
|
|
* @return string[] |
|
60
|
|
|
*/ |
|
61
|
|
View Code Duplication |
public function getOutgoingLinks( ParserOutput $parserOutput ) { |
|
62
|
|
|
$outgoingLinks = []; |
|
63
|
|
|
|
|
64
|
|
|
foreach ( $parserOutput->getLinks() as $linkedNamespace => $namespaceLinks ) { |
|
65
|
|
|
foreach ( array_keys( $namespaceLinks ) as $linkedDbKey ) { |
|
66
|
|
|
$outgoingLinks[] = |
|
67
|
|
|
Title::makeTitle( $linkedNamespace, $linkedDbKey )->getPrefixedDBkey(); |
|
68
|
|
|
} |
|
69
|
|
|
} |
|
70
|
|
|
|
|
71
|
|
|
return $outgoingLinks; |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
/** |
|
75
|
|
|
* Get a list of templates used in the ParserOutput content, as prefixed title strings |
|
76
|
|
|
* |
|
77
|
|
|
* @return string[] |
|
78
|
|
|
*/ |
|
79
|
|
View Code Duplication |
public function getTemplates( ParserOutput $parserOutput ) { |
|
80
|
|
|
$templates = []; |
|
81
|
|
|
|
|
82
|
|
|
foreach ( $parserOutput->getTemplates() as $tNS => $templatesInNS ) { |
|
83
|
|
|
foreach ( array_keys( $templatesInNS ) as $tDbKey ) { |
|
84
|
|
|
$templateTitle = Title::makeTitle( $tNS, $tDbKey ); |
|
85
|
|
|
$templates[] = $templateTitle->getPrefixedText(); |
|
86
|
|
|
} |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
|
|
return $templates; |
|
90
|
|
|
} |
|
91
|
|
|
|
|
92
|
|
|
} |
|
93
|
|
|
|
wikimedia /
mediawiki
