Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 88 |
|
0.00% |
0 / 4 |
CRAP | |
0.00% |
0 / 1 |
| ExtractFeatures | |
0.00% |
0 / 85 |
|
0.00% |
0 / 4 |
132 | |
0.00% |
0 / 1 |
| __construct | |
0.00% |
0 / 10 |
|
0.00% |
0 / 1 |
2 | |||
| populateSearchIndex | |
0.00% |
0 / 55 |
|
0.00% |
0 / 1 |
42 | |||
| doUpdate | |
0.00% |
0 / 11 |
|
0.00% |
0 / 1 |
12 | |||
| execute | |
0.00% |
0 / 9 |
|
0.00% |
0 / 1 |
2 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * This program is free software; you can redistribute it and/or modify |
| 4 | * it under the terms of the GNU General Public License as published by |
| 5 | * the Free Software Foundation; either version 2 of the License, or |
| 6 | * (at your option) any later version. |
| 7 | * |
| 8 | * This program is distributed in the hope that it will be useful, |
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | * GNU General Public License for more details. |
| 12 | * |
| 13 | * You should have received a copy of the GNU General Public License along |
| 14 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 15 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 16 | * http://www.gnu.org/copyleft/gpl.html |
| 17 | * |
| 18 | * @ingroup Maintenance |
| 19 | */ |
| 20 | |
| 21 | use MediaWiki\MediaWikiServices; |
| 22 | |
| 23 | require_once __DIR__ . '/../../../maintenance/Maintenance.php'; |
| 24 | |
| 25 | class ExtractFeatures extends Maintenance { |
| 26 | |
| 27 | private const RTI_CHUNK_SIZE = 100; |
| 28 | |
| 29 | /** @var bool */ |
| 30 | private $purge = false; |
| 31 | /** @var \Wikimedia\Rdbms\IDatabase */ |
| 32 | private $dbw = null; |
| 33 | |
| 34 | /** |
| 35 | * @var \Wikimedia\Rdbms\IDatabase |
| 36 | */ |
| 37 | private $db; |
| 38 | |
| 39 | public function __construct() { |
| 40 | parent::__construct(); |
| 41 | $this->addDescription( 'Outputs page text to stdout' ); |
| 42 | $this->addOption( 'purge', |
| 43 | 'If set all formulae are rendered again from strech. (Very time consuming!)', false, |
| 44 | false, 'f' ); |
| 45 | $this->addArg( 'min', 'If set processing is started at the page with rank(pageID)>min', |
| 46 | false ); |
| 47 | $this->addArg( 'max', 'If set processing is stopped at the page with rank(pageID)<=max', |
| 48 | false ); |
| 49 | $this->requireExtension( 'MathSearch' ); |
| 50 | } |
| 51 | |
| 52 | /** |
| 53 | * Populates the search index with content from all pages |
| 54 | * |
| 55 | * @param int $n |
| 56 | * @param int $cmax |
| 57 | */ |
| 58 | protected function populateSearchIndex( $n = 0, $cmax = -1 ) { |
| 59 | $s = $this->db->selectRow( 'page', 'MAX(page_id) AS count' ); |
| 60 | $count = $s->count; |
| 61 | if ( $cmax > 0 && $count > $cmax ) { |
| 62 | $count = $cmax; |
| 63 | } |
| 64 | $this->output( "Rebuilding index fields for {$count} pages with option {$this->purge}...\n" ); |
| 65 | $fcount = 0; |
| 66 | $revisionStore = MediaWikiServices::getInstance()->getRevisionStore(); |
| 67 | |
| 68 | while ( $n < $count ) { |
| 69 | if ( $n ) { |
| 70 | $this->output( $n . " of $count \n" ); |
| 71 | } |
| 72 | $end = $n + self::RTI_CHUNK_SIZE - 1; |
| 73 | |
| 74 | $res = |
| 75 | $this->db->select( [ 'page', 'revision', 'text' ], |
| 76 | [ 'page_id', 'page_namespace', 'page_title', 'old_flags', 'old_text' ], |
| 77 | [ |
| 78 | "page_id BETWEEN $n AND $end", |
| 79 | 'page_latest = rev_id', |
| 80 | 'rev_text_id = old_id' |
| 81 | ], __METHOD__ ); |
| 82 | $this->dbw->begin( __METHOD__ ); |
| 83 | // echo "before" +$this->dbw->selectField('mathindex', 'count(*)')."\n"; |
| 84 | foreach ( $res as $s ) { |
| 85 | $revtext = $revisionStore->newRevisionFromRow( $s ); |
| 86 | $fcount += self::doUpdate( $revtext, $s->page_title, $this->purge, |
| 87 | $this->dbw ); |
| 88 | } |
| 89 | // echo "before" +$this->dbw->selectField('mathindex', 'count(*)')."\n"; |
| 90 | $start = microtime( true ); |
| 91 | $this->dbw->commit( __METHOD__ ); |
| 92 | echo " committed in " . ( microtime( true ) - $start ) . "s\n\n"; |
| 93 | // echo "after" +$this->dbw->selectField('mathindex', 'count(*)')."\n"; |
| 94 | $n += self::RTI_CHUNK_SIZE; |
| 95 | } |
| 96 | $this->output( "Clear mathvarstat\n" ); |
| 97 | $sql = 'DELETE FROM `mathvarstat`'; |
| 98 | $this->dbw->query( $sql ); |
| 99 | $this->output( "Generate mathvarstat\n" ); |
| 100 | $sql = |
| 101 | 'INSERT INTO `mathvarstat` (`varstat_featurename` , `varstat_featuretype`, `varstat_featurecount`)' . |
| 102 | 'SELECT `mathobservation_featurename` , `mathobservation_featuretype` , count( * ) AS CNT ' . |
| 103 | 'FROM `mathobservation` ' . |
| 104 | 'JOIN mathindex ON `mathobservation_inputhash` = mathindex_inputhash ' . |
| 105 | 'GROUP BY `mathobservation_featurename` , `mathobservation_featuretype` ' . |
| 106 | 'ORDER BY CNT DESC'; |
| 107 | $this->dbw->query( $sql ); |
| 108 | $this->output( "Clear mathrevisionstat\n" ); |
| 109 | $sql = 'DELETE FROM `mathrevisionstat`'; |
| 110 | $this->dbw->query( $sql ); |
| 111 | $this->output( "Generate mathrevisionstat\n" ); |
| 112 | $sql = |
| 113 | 'INSERT INTO `mathrevisionstat`(`revstat_featureid`,`revstat_revid`,`revstat_featurecount`) ' . |
| 114 | 'SELECT varstat_id, mathindex_revision_id, count(*) AS CNT FROM `mathobservation` ' |
| 115 | . 'JOIN mathindex ON `mathobservation_inputhash` =mathindex_inputhash ' . |
| 116 | 'JOIN mathvarstat ON varstat_featurename = `mathobservation_featurename` ' |
| 117 | . 'AND varstat_featuretype = `mathobservation_featuretype` ' . |
| 118 | ' GROUP BY `mathobservation_featurename`, `mathobservation_featuretype`, ' |
| 119 | . 'mathindex_revision_id ORDER BY CNT DESC'; |
| 120 | $this->dbw->query( $sql ); |
| 121 | $this->output( "Updated {$fcount} formulae!\n" ); |
| 122 | } |
| 123 | |
| 124 | /** |
| 125 | * @param string $pText |
| 126 | * @param string $pTitle |
| 127 | * @param bool|string $purge |
| 128 | * @param \Wikimedia\Rdbms\IDatabase $dbw |
| 129 | * |
| 130 | * @return number |
| 131 | */ |
| 132 | private static function doUpdate( $pText, $pTitle, $purge, $dbw ) { |
| 133 | // TODO: fix link id problem |
| 134 | $anchorID = 0; |
| 135 | $math = MathObject::extractMathTagsFromWikiText( $pText ); |
| 136 | $matches = count( $math ); |
| 137 | if ( $matches ) { |
| 138 | echo ( "\t processing $matches math fields for {$pTitle} page\n" ); |
| 139 | foreach ( $math as $formula ) { |
| 140 | $mo = new MathObject( $formula[1] ); |
| 141 | $mo->updateObservations( $dbw ); |
| 142 | // Enable indexing of math formula |
| 143 | $anchorID++; |
| 144 | } |
| 145 | return $matches; |
| 146 | } |
| 147 | return 0; |
| 148 | } |
| 149 | |
| 150 | public function execute() { |
| 151 | $this->dbw = MediaWikiServices::getInstance() |
| 152 | ->getConnectionProvider() |
| 153 | ->getPrimaryDatabase(); |
| 154 | $this->purge = $this->getOption( 'purge', false ); |
| 155 | $this->db = MediaWikiServices::getInstance() |
| 156 | ->getConnectionProvider() |
| 157 | ->getPrimaryDatabase(); |
| 158 | $this->output( "Done.\n" ); |
| 159 | $this->populateSearchIndex( $this->getArg( 0, 0 ), $this->getArg( 1, -1 ) ); |
| 160 | } |
| 161 | } |
| 162 | |
| 163 | $maintClass = ExtractFeatures::class; |
| 164 | /** @noinspection PhpIncludeInspection */ |
| 165 | require_once RUN_MAINTENANCE_IF_MAIN; |