3 * Find all revisions by logged out users and copy the rev_id,
4 * rev_timestamp, and a hex representation of rev_user_text to the
5 * new ip_changes table. This table is used to efficiently query for
6 * contributions within an IP range.
8 * This program is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU General Public License as published by
10 * the Free Software Foundation; either version 2 of the License, or
11 * (at your option) any later version.
13 * This program is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 * GNU General Public License for more details.
18 * You should have received a copy of the GNU General Public License along
19 * with this program; if not, write to the Free Software Foundation, Inc.,
20 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
21 * http://www.gnu.org/copyleft/gpl.html
24 * @ingroup Maintenance
27 require_once __DIR__
. '/Maintenance.php';
29 use MediaWiki\MediaWikiServices
;
32 * Maintenance script that will find all rows in the revision table where
33 * rev_user = 0 (user is an IP), and copy relevant fields to ip_changes so
34 * that historical data will be available when querying for IP ranges.
36 * @ingroup Maintenance
38 class PopulateIpChanges
extends LoggedUpdateMaintenance
{
39 public function __construct() {
40 parent
::__construct();
42 $this->addDescription( <<<TEXT
43 This script will find all rows in the revision table where the user is an IP,
44 and copy relevant fields to the ip_changes table. This backfilled data will
45 then be available when querying for IP ranges at Special:Contributions.
48 $this->addOption( 'rev-id', 'The rev_id to start copying from. Default: 0', false, true );
51 'The rev_id to stop at. Default: result of MAX(rev_id)',
57 'Wait this many milliseconds after copying each batch of revisions. Default: 0',
61 $this->addOption( 'force', 'Run regardless of whether the database says it\'s been run already' );
64 public function doDBUpdates() {
65 $lbFactory = MediaWikiServices
::getInstance()->getDBLoadBalancerFactory();
66 $dbr = $this->getDB( DB_REPLICA
, [ 'vslow' ] );
67 $dbw = $this->getDB( DB_MASTER
);
68 $throttle = intval( $this->getOption( 'throttle', 0 ) );
69 $maxRevId = intval( $this->getOption( 'max-rev-id', 0 ) );
70 $start = $this->getOption( 'rev-id', 0 );
73 : $dbw->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__
);
77 $this->output( "Copying IP revisions to ip_changes, from rev_id $start to rev_id $end\n" );
79 while ( $blockStart <= $end ) {
80 $blockEnd = min( $blockStart +
200, $end );
83 [ 'rev_id', 'rev_timestamp', 'rev_user_text' ],
84 [ "rev_id BETWEEN $blockStart AND $blockEnd", 'rev_user' => 0 ],
86 [ 'ORDER BY' => 'rev_id ASC', 'LIMIT' => $this->mBatchSize
]
89 if ( !$rows ||
$rows->numRows() === 0 ) {
93 $this->output( "...checking $this->mBatchSize revisions for IP edits that need copying, " .
94 "between rev_ids $blockStart and $blockEnd\n" );
97 foreach ( $rows as $row ) {
98 // Double-check to make sure this is an IP, e.g. not maintenance user or imported revision.
99 if ( IP
::isValid( $row->rev_user_text
) ) {
101 'ipc_rev_id' => $row->rev_id
,
102 'ipc_rev_timestamp' => $row->rev_timestamp
,
103 'ipc_hex' => IP
::toHex( $row->rev_user_text
),
109 $blockStart = (int)$row->rev_id
;
121 $lbFactory->waitForReplication();
122 usleep( $throttle * 1000 );
125 $this->output( "$revCount IP revisions copied.\n" );
130 protected function getUpdateKey() {
131 return 'populate ip_changes';
135 $maintClass = "PopulateIpChanges";
136 require_once RUN_MAINTENANCE_IF_MAIN
;