Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 57 |
|
0.00% |
0 / 5 |
CRAP | |
0.00% |
0 / 1 |
| IndexBase | |
0.00% |
0 / 56 |
|
0.00% |
0 / 5 |
56 | |
0.00% |
0 / 1 |
| __construct | |
0.00% |
0 / 11 |
|
0.00% |
0 / 1 |
2 | |||
| generateIndexString | n/a |
0 / 0 |
n/a |
0 / 0 |
0 | |||||
| wFile | |
0.00% |
0 / 12 |
|
0.00% |
0 / 1 |
6 | |||
| execute | |
0.00% |
0 / 31 |
|
0.00% |
0 / 1 |
6 | |||
| getHead | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| getFooter | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * Generates harvest files for the MathWebSearch Daemon. |
| 4 | * Example: php CreateMathIndex.php ~/mws_harvest_files |
| 5 | * |
| 6 | * This program is free software; you can redistribute it and/or modify |
| 7 | * it under the terms of the GNU General Public License as published by |
| 8 | * the Free Software Foundation; either version 2 of the License, or |
| 9 | * (at your option) any later version. |
| 10 | * |
| 11 | * This program is distributed in the hope that it will be useful, |
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 14 | * GNU General Public License for more details. |
| 15 | * |
| 16 | * You should have received a copy of the GNU General Public License along |
| 17 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 18 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 19 | * http://www.gnu.org/copyleft/gpl.html |
| 20 | * |
| 21 | * @ingroup Maintenance |
| 22 | */ |
| 23 | |
| 24 | require_once __DIR__ . '/../../../maintenance/Maintenance.php'; |
| 25 | |
| 26 | use MediaWiki\MediaWikiServices; |
| 27 | use Wikimedia\Rdbms\IResultWrapper; |
| 28 | |
| 29 | /** |
| 30 | * @author Moritz Schubotz |
| 31 | */ |
| 32 | abstract class IndexBase extends Maintenance { |
| 33 | /** @var IResultWrapper */ |
| 34 | protected $res; |
| 35 | |
| 36 | public function __construct() { |
| 37 | parent::__construct(); |
| 38 | $this->addDescription( 'Exports data' ); |
| 39 | $this->addArg( 'dir', 'The directory where the harvest files go to.' ); |
| 40 | $this->addArg( 'ffmax', 'The maximal number of formula per file.', false ); |
| 41 | $this->addArg( 'min', 'If set processing is started at the page with rank(pageID)>min', |
| 42 | false ); |
| 43 | $this->addArg( 'max', 'If set processing is stopped at the page with rank(pageID)<=max', |
| 44 | false ); |
| 45 | $this->addOption( 'limit', 'The maximal number of database entries to be considered', false, |
| 46 | true, "L" ); |
| 47 | $this->requireExtension( 'MathSearch' ); |
| 48 | } |
| 49 | |
| 50 | /** |
| 51 | * @param stdClass $row |
| 52 | * |
| 53 | * @return string |
| 54 | */ |
| 55 | abstract protected function generateIndexString( $row ); |
| 56 | |
| 57 | /** |
| 58 | * @param string $fn |
| 59 | * @param int $min |
| 60 | * @param int $inc |
| 61 | * |
| 62 | * @return bool |
| 63 | */ |
| 64 | protected function wFile( $fn, $min, $inc ) { |
| 65 | $out = $this->getHead(); |
| 66 | $max = min( $min + $inc, $this->res->numRows() ); |
| 67 | for ( $i = $min; $i < $max; $i++ ) { |
| 68 | $this->res->seek( $i ); |
| 69 | $out .= $this->generateIndexString( $this->res->fetchObject() ); |
| 70 | restore_error_handler(); |
| 71 | } |
| 72 | $out .= "\n" . $this->getFooter(); |
| 73 | $fh = fopen( $fn, 'w' ); |
| 74 | // echo $out; |
| 75 | // die ("test"); |
| 76 | fwrite( $fh, $out ); |
| 77 | fclose( $fh ); |
| 78 | echo "written file $fn with entries($min ... $max)\n"; |
| 79 | |
| 80 | return $max < $this->res->numRows() - 1; |
| 81 | } |
| 82 | |
| 83 | public function execute() { |
| 84 | libxml_use_internal_errors( true ); |
| 85 | $i = 0; |
| 86 | $inc = $this->getArg( 1, 100 ); |
| 87 | $db = MediaWikiServices::getInstance() |
| 88 | ->getConnectionProvider() |
| 89 | ->getReplicaDatabase(); |
| 90 | echo "getting list of all equations from the database\n"; |
| 91 | $this->res = |
| 92 | $db->select( [ 'mathindex', 'mathlog' ], [ |
| 93 | 'mathindex_revision_id', |
| 94 | 'mathindex_anchor', |
| 95 | 'math_mathml', |
| 96 | 'math_inputhash', |
| 97 | 'mathindex_inputhash' |
| 98 | ], [ |
| 99 | 'math_inputhash = mathindex_inputhash', |
| 100 | 'mathindex_revision_id >= ' . $this->getArg( 2, 0 ), |
| 101 | 'mathindex_revision_id <= ' . $this->getArg( 3, PHP_INT_MAX ) |
| 102 | ], __METHOD__, [ |
| 103 | 'LIMIT' => $this->getOption( 'limit', PHP_INT_MAX ), |
| 104 | 'ORDER BY' => 'mathindex_revision_id' |
| 105 | ] ); |
| 106 | echo "write " . $this->res->numRows() . " results to index\n"; |
| 107 | $dir = $this->getArg( 0 ); |
| 108 | if ( !file_exists( $dir ) ) { |
| 109 | mkdir( $dir, '0755', true ); |
| 110 | } |
| 111 | do { |
| 112 | $fn = $dir . '/math' . sprintf( '%012d', $i ) . '.xml'; |
| 113 | $res = $this->wFile( $fn, $i, $inc ); |
| 114 | $i += $inc; |
| 115 | } while ( $res ); |
| 116 | echo ( 'done' ); |
| 117 | } |
| 118 | |
| 119 | /** |
| 120 | * @return string |
| 121 | */ |
| 122 | protected function getHead() { |
| 123 | return ''; |
| 124 | } |
| 125 | |
| 126 | /** |
| 127 | * @return string |
| 128 | */ |
| 129 | protected function getFooter() { |
| 130 | return ''; |
| 131 | } |
| 132 | } |