Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 59 |
|
0.00% |
0 / 3 |
CRAP | |
0.00% |
0 / 1 |
| CalculateDistances | |
0.00% |
0 / 56 |
|
0.00% |
0 / 3 |
110 | |
0.00% |
0 / 1 |
| __construct | |
0.00% |
0 / 7 |
|
0.00% |
0 / 1 |
2 | |||
| execute | |
0.00% |
0 / 24 |
|
0.00% |
0 / 1 |
20 | |||
| populateSearchIndex | |
0.00% |
0 / 25 |
|
0.00% |
0 / 1 |
30 | |||
| 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 CalculateDistances extends Maintenance { |
| 26 | |
| 27 | private const RTI_CHUNK_SIZE = 100; |
| 28 | |
| 29 | /** @var \Wikimedia\Rdbms\IDatabase */ |
| 30 | private $dbw = null; |
| 31 | |
| 32 | /** |
| 33 | * @var \Wikimedia\Rdbms\IDatabase |
| 34 | */ |
| 35 | private $db; |
| 36 | /** @var int[] List of revision ids */ |
| 37 | private $pagelist = []; |
| 38 | |
| 39 | public function __construct() { |
| 40 | parent::__construct(); |
| 41 | $this->addDescription( 'Outputs page text to stdout' ); |
| 42 | $this->addOption( 'page9', 'Ignore pages with only 9 equations or less.', false, false, |
| 43 | '9' ); |
| 44 | $this->addArg( 'min', 'If set processing is started at the page with curid>min', false ); |
| 45 | $this->addArg( 'max', 'If set processing is stopped at the page with curid<=max', false ); |
| 46 | $this->requireExtension( 'MathSearch' ); |
| 47 | } |
| 48 | |
| 49 | public function execute() { |
| 50 | $this->dbw = MediaWikiServices::getInstance() |
| 51 | ->getConnectionProvider() |
| 52 | ->getPrimaryDatabase(); |
| 53 | $this->db = MediaWikiServices::getInstance() |
| 54 | ->getConnectionProvider() |
| 55 | ->getPrimaryDatabase(); |
| 56 | $this->pagelist = []; |
| 57 | $min = $this->getArg( 0, 0 ); |
| 58 | $max = $this->getArg( 1, PHP_INT_MAX ); |
| 59 | $conds = "revstat_revid >= $min"; |
| 60 | if ( $max < PHP_INT_MAX ) { |
| 61 | $conds .= " AND revstat_revid <= $max"; |
| 62 | } |
| 63 | if ( $this->getOption( 'page9', false ) ) { |
| 64 | // TODO: Can use selectField() |
| 65 | $res = |
| 66 | $this->db->select( [ 'mathpage9', 'mathrevisionstat' ], |
| 67 | 'revstat_revid', |
| 68 | // FIXME: Should be an array, not a string |
| 69 | $conds . ' AND revstat_revid = page_id', __METHOD__, [ 'DISTINCT' ] ); |
| 70 | } else { |
| 71 | // TODO: Can use selectField() |
| 72 | $res = |
| 73 | $this->db->select( 'mathrevisionstat', 'revstat_revid', $conds, __METHOD__, |
| 74 | [ 'DISTINCT' ] ); |
| 75 | } |
| 76 | foreach ( $res as $row ) { |
| 77 | $this->pagelist[] = $row->revstat_revid; |
| 78 | } |
| 79 | $this->populateSearchIndex(); |
| 80 | $this->output( "Done.\n" ); |
| 81 | } |
| 82 | |
| 83 | /** |
| 84 | * Populates the search index with content from all pages |
| 85 | */ |
| 86 | protected function populateSearchIndex() { |
| 87 | $n = 0; |
| 88 | $count = count( $this->pagelist ); |
| 89 | $this->output( "Rebuilding index fields for $count pages...\n" ); |
| 90 | while ( $n < $count ) { |
| 91 | if ( $n ) { |
| 92 | $this->output( $n . " of $count \n" ); |
| 93 | } |
| 94 | $this->dbw->begin( __METHOD__ ); |
| 95 | for ( $j = 0; $j < self::RTI_CHUNK_SIZE; $j++ ) { |
| 96 | // TODO: USE PREPARED STATEMENTS |
| 97 | $pid = $this->pagelist[$n]; |
| 98 | $sql = |
| 99 | "INSERT IGNORE INTO mathpagesimilarity(pagesimilarity_A,pagesimilarity_B,pagesimilarity_Value) " . |
| 100 | "SELECT DISTINCT $pid,`revstat_revid`, " . |
| 101 | "CosProd( $pid,`revstat_revid`) FROM `mathrevisionstat` m "; |
| 102 | if ( $this->getOption( 'page9', false ) ) { |
| 103 | $sql .= " JOIN (SELECT page_id from mathpage9) as r WHERE m.revstat_revid=r.page_id AND "; |
| 104 | } else { |
| 105 | $sql .= " WHERE "; |
| 106 | } |
| 107 | $sql .= "m.revstat_revid < $pid "; |
| 108 | echo "writing entries for page $pid..."; |
| 109 | $start = microtime( true ); |
| 110 | $this->dbw->query( $sql ); |
| 111 | echo 'done in ' . ( microtime( true ) - $start ) . "\n"; |
| 112 | $n++; |
| 113 | } |
| 114 | $start = microtime( true ); |
| 115 | $this->dbw->commit( __METHOD__ ); |
| 116 | echo ' committed in ' . ( microtime( true ) - $start ) . "s\n\n"; |
| 117 | } |
| 118 | } |
| 119 | } |
| 120 | |
| 121 | $maintClass = CalculateDistances::class; |
| 122 | /** @noinspection PhpIncludeInspection */ |
| 123 | require_once RUN_MAINTENANCE_IF_MAIN; |