1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
|
<?php
/**
* Helper class for the --prefetch option of dumpTextPass.php
*
* Copyright © 2005 Brooke Vibber <bvibber@wikimedia.org>
* https://www.mediawiki.org/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
* @ingroup Maintenance
*/
use MediaWiki\Revision\SlotRecord;
/**
* Readahead helper for making large MediaWiki data dumps;
* reads in a previous XML dump to sequentially prefetch text
* records already normalized and decompressed.
*
* This can save load on the external database servers, hopefully.
*
* Assumes that dumps will be recorded in the canonical order:
* - ascending by page_id
* - ascending by rev_id within each page
* - text contents are immutable and should not change once
* recorded, so the previous dump is a reliable source
*
* @ingroup Maintenance
*/
class BaseDump {
/** @var XMLReader|null */
protected $reader = null;
/** @var bool */
protected $atEnd = false;
/** @var bool */
protected $atPageEnd = false;
/** @var int */
protected $lastPage = 0;
/** @var int */
protected $lastRev = 0;
/** @var string[]|null */
protected $infiles = null;
/**
* @param string $infile
*/
public function __construct( $infile ) {
$this->infiles = explode( ';', $infile );
$this->reader = new XMLReader();
$infile = array_shift( $this->infiles );
if ( !$this->reader->open( $infile, null, LIBXML_PARSEHUGE ) ) {
$this->debug( __METHOD__ . ' was unable to open xml' );
$this->atEnd = true;
}
}
/**
* Attempts to fetch the text of a particular page revision
* from the dump stream. May return null if the page is
* unavailable.
*
* @param int $page ID number of page to read
* @param int $rev ID number of revision to read
* @param string $slot Role name of the slot to read
* @return string|null
*/
public function prefetch( $page, $rev, $slot = SlotRecord::MAIN ) {
$page = intval( $page );
$rev = intval( $rev );
while ( $this->lastPage < $page && !$this->atEnd ) {
$this->debug( "BaseDump::prefetch at page $this->lastPage, looking for $page" );
$this->nextPage();
}
if ( $this->lastPage > $page || $this->atEnd ) {
$this->debug( "BaseDump::prefetch already past page $page or failed to open/read input file, "
. "looking for rev $rev [$this->lastPage, $this->lastRev]" );
return null;
}
while ( $this->lastRev < $rev && !$this->atEnd && !$this->atPageEnd ) {
$this->debug( "BaseDump::prefetch at page $this->lastPage, rev $this->lastRev, "
. "looking for $page, $rev" );
$this->nextRev();
}
if ( $this->lastRev == $rev && !$this->atEnd ) {
$this->debug( "BaseDump::prefetch hit on $page, $rev [$this->lastPage, $this->lastRev]" );
if ( $slot !== SlotRecord::MAIN ) {
$lastSlot = SlotRecord::MAIN;
while ( $lastSlot !== $slot ) {
if ( !$this->skipTo( 'content', 'revision' ) ||
!$this->skipTo( 'role', 'revision' )
) {
return null;
}
$lastSlot = $this->nodeContents();
}
}
return $this->nextText();
} else {
$this->debug( "BaseDump::prefetch already past rev $rev on page $page "
. "[$this->lastPage, $this->lastRev]" );
return null;
}
}
/**
* @param string $str
*/
protected function debug( $str ) {
wfDebug( $str );
// global $dumper;
// $dumper->progress( $str );
}
private function nextPage() {
if ( $this->skipTo( 'page', 'mediawiki' ) ) {
if ( $this->skipTo( 'id' ) ) {
$this->lastPage = intval( $this->nodeContents() );
$this->lastRev = 0;
$this->atPageEnd = false;
}
} else {
$this->close();
if ( count( $this->infiles ) ) {
$infile = array_shift( $this->infiles );
if ( !$this->reader->open( $infile, null, LIBXML_PARSEHUGE ) ) {
$this->debug( __METHOD__ . ' was unable to open xml' );
$this->atEnd = true;
} else {
$this->atEnd = false;
}
}
}
}
private function nextRev() {
if ( $this->skipTo( 'revision' ) ) {
if ( $this->skipTo( 'id' ) ) {
$this->lastRev = intval( $this->nodeContents() );
}
} else {
$this->atPageEnd = true;
}
}
/**
* @return string|null
*/
private function nextText() {
if ( !$this->skipTo( 'text', 'revision' ) ) {
return null;
}
return strval( $this->nodeContents() );
}
/**
* @param string $name
* @param string $parent
* @return bool|null
*/
private function skipTo( $name, $parent = 'page' ) {
if ( $this->atEnd ) {
return false;
}
while ( $this->reader->read() ) {
if ( $this->reader->nodeType == XMLReader::ELEMENT
&& $this->reader->name == $name
) {
return true;
}
if ( $this->reader->nodeType == XMLReader::END_ELEMENT
&& $this->reader->name == $parent
) {
$this->debug( "BaseDump::skipTo found </$parent> searching for <$name>" );
return false;
}
}
return $this->close();
}
/**
* Shouldn't something like this be built-in to XMLReader?
* Fetches text contents of the current element, assuming
* no sub-elements or such scary things.
*
* @return string|null
*/
private function nodeContents() {
if ( $this->atEnd ) {
return null;
}
if ( $this->reader->isEmptyElement ) {
return "";
}
$buffer = "";
while ( $this->reader->read() ) {
switch ( $this->reader->nodeType ) {
case XMLReader::TEXT:
// case XMLReader::WHITESPACE:
case XMLReader::SIGNIFICANT_WHITESPACE:
$buffer .= $this->reader->value;
break;
case XMLReader::END_ELEMENT:
return $buffer;
}
}
return $this->close();
}
/**
* @return null
*/
public function close() {
$this->reader->close();
$this->atEnd = true;
return null;
}
}
|