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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
|
<?php
/**
* Copyright (C) 2005 Brion Vibber <brion@pobox.com>
* http://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
*
* @package MediaWiki
* @subpackage SpecialPage
*/
$originalDir = getcwd();
require_once( 'commandLine.inc' );
require_once( 'SpecialExport.php' );
require_once( 'maintenance/backup.inc' );
/**
* Stream wrapper around 7za filter program.
* Required since we can't pass an open file resource to XMLReader->open()
* which is used for the text prefetch.
*/
class SevenZipStream {
var $stream;
private function stripPath( $path ) {
$prefix = 'mediawiki.compress.7z://';
return substr( $path, strlen( $prefix ) );
}
function stream_open( $path, $mode, $options, &$opened_path ) {
if( $mode{0} == 'r' ) {
$options = 'e -bd -so';
} elseif( $mode{0} == 'w' ) {
$options = 'a -bd -si';
} else {
return false;
}
$arg = wfEscapeShellArg( $this->stripPath( $path ) );
$command = "7za $options $arg";
if( !wfIsWindows() ) {
// Suppress the stupid messages on stderr
$command .= ' 2>/dev/null';
}
$this->stream = popen( $command, $mode );
return ($this->stream !== false);
}
function url_stat( $path, $flags ) {
return stat( $this->stripPath( $path ) );
}
// This is all so lame; there should be a default class we can extend
function stream_close() {
return fclose( $this->stream );
}
function stream_flush() {
return fflush( $this->stream );
}
function stream_read( $count ) {
return fread( $this->stream, $count );
}
function stream_write( $data ) {
return fwrite( $this->stream, $data );
}
function stream_tell() {
return ftell( $this->stream );
}
function stream_eof() {
return feof( $this->stream );
}
function stream_seek( $offset, $whence ) {
return fseek( $this->stream, $offset, $whence );
}
}
stream_wrapper_register( 'mediawiki.compress.7z', 'SevenZipStream' );
class TextPassDumper extends BackupDumper {
var $prefetch = null;
var $input = "php://stdin";
var $history = MW_EXPORT_FULL;
var $fetchCount = 0;
var $prefetchCount = 0;
function dump() {
# This shouldn't happen if on console... ;)
header( 'Content-type: text/html; charset=UTF-8' );
# Notice messages will foul up your XML output even if they're
# relatively harmless.
// ini_set( 'display_errors', false );
$this->initProgress( $this->history );
$this->db =& $this->backupDb();
$this->egress = new ExportProgressFilter( $this->sink, $this );
$input = fopen( $this->input, "rt" );
$result = $this->readDump( $input );
if( WikiError::isError( $result ) ) {
wfDie( $result->getMessage() );
}
$this->report( true );
}
function processOption( $opt, $val, $param ) {
$url = $this->processFileOpt( $val, $param );
switch( $opt ) {
case 'prefetch':
require_once 'maintenance/backupPrefetch.inc';
$this->prefetch = new BaseDump( $url );
break;
case 'stub':
$this->input = $url;
break;
case 'current':
$this->history = MW_EXPORT_CURRENT;
break;
case 'full':
$this->history = MW_EXPORT_FULL;
break;
}
}
function processFileOpt( $val, $param ) {
switch( $val ) {
case "file":
return $param;
case "gzip":
return "compress.zlib://$param";
case "bzip2":
return "compress.bzip2://$param";
case "7zip":
return "mediawiki.compress.7z://$param";
default:
return $val;
}
}
/**
* Overridden to include prefetch ratio if enabled.
*/
function showReport() {
if( !$this->prefetch ) {
return parent::showReport();
}
if( $this->reporting ) {
$delta = wfTime() - $this->startTime;
$now = wfTimestamp( TS_DB );
if( $delta ) {
$rate = $this->pageCount / $delta;
$revrate = $this->revCount / $delta;
$portion = $this->revCount / $this->maxCount;
$eta = $this->startTime + $delta / $portion;
$etats = wfTimestamp( TS_DB, intval( $eta ) );
$fetchrate = 100.0 * $this->prefetchCount / $this->fetchCount;
} else {
$rate = '-';
$revrate = '-';
$etats = '-';
$fetchrate = '-';
}
global $wgDBname;
$this->progress( sprintf( "%s: %s %d pages (%0.3f/sec), %d revs (%0.3f/sec), %0.1f%% prefetched, ETA %s [max %d]",
$now, $wgDBname, $this->pageCount, $rate, $this->revCount, $revrate, $fetchrate, $etats, $this->maxCount ) );
}
}
function readDump( $input ) {
$this->buffer = "";
$this->openElement = false;
$this->atStart = true;
$this->state = "";
$this->lastName = "";
$this->thisPage = 0;
$this->thisRev = 0;
$parser = xml_parser_create( "UTF-8" );
xml_parser_set_option( $parser, XML_OPTION_CASE_FOLDING, false );
xml_set_element_handler( $parser, array( &$this, 'startElement' ), array( &$this, 'endElement' ) );
xml_set_character_data_handler( $parser, array( &$this, 'characterData' ) );
$offset = 0; // for context extraction on error reporting
$bufferSize = 512 * 1024;
do {
$chunk = fread( $input, $bufferSize );
if( !xml_parse( $parser, $chunk, feof( $input ) ) ) {
wfDebug( "TextDumpPass::readDump encountered XML parsing error\n" );
return new WikiXmlError( $parser, 'XML import parse failure', $chunk, $offset );
}
$offset += strlen( $chunk );
} while( $chunk !== false && !feof( $input ) );
xml_parser_free( $parser );
return true;
}
function getText( $id ) {
$this->fetchCount++;
if( isset( $this->prefetch ) ) {
$text = $this->prefetch->prefetch( $this->thisPage, $this->thisRev );
if( $text === null ) {
// Entry missing from prefetch dump
} elseif( $text === "" ) {
// Blank entries may indicate that the prior dump was broken.
// To be safe, reload it.
} else {
$this->prefetchCount++;
return $text;
}
}
$id = intval( $id );
$row = $this->db->selectRow( 'text',
array( 'old_text', 'old_flags' ),
array( 'old_id' => $id ),
'TextPassDumper::getText' );
$text = Revision::getRevisionText( $row );
$stripped = str_replace( "\r", "", $text );
$normalized = UtfNormal::cleanUp( $stripped );
return $normalized;
}
function startElement( $parser, $name, $attribs ) {
$this->clearOpenElement( null );
$this->lastName = $name;
if( $name == 'revision' ) {
$this->state = $name;
$this->egress->writeOpenPage( null, $this->buffer );
$this->buffer = "";
} elseif( $name == 'page' ) {
$this->state = $name;
if( $this->atStart ) {
$this->egress->writeOpenStream( $this->buffer );
$this->buffer = "";
$this->atStart = false;
}
}
if( $name == "text" && isset( $attribs['id'] ) ) {
$text = $this->getText( $attribs['id'] );
$this->openElement = array( $name, array( 'xml:space' => 'preserve' ) );
if( strlen( $text ) > 0 ) {
$this->characterData( $parser, $text );
}
} else {
$this->openElement = array( $name, $attribs );
}
}
function endElement( $parser, $name ) {
if( $this->openElement ) {
$this->clearOpenElement( "" );
} else {
$this->buffer .= "</$name>";
}
if( $name == 'revision' ) {
$this->egress->writeRevision( null, $this->buffer );
$this->buffer = "";
$this->thisRev = "";
} elseif( $name == 'page' ) {
$this->egress->writeClosePage( $this->buffer );
$this->buffer = "";
$this->thisPage = "";
} elseif( $name == 'mediawiki' ) {
$this->egress->writeCloseStream( $this->buffer );
$this->buffer = "";
}
}
function characterData( $parser, $data ) {
$this->clearOpenElement( null );
if( $this->lastName == "id" ) {
if( $this->state == "revision" ) {
$this->thisRev .= $data;
} elseif( $this->state == "page" ) {
$this->thisPage .= $data;
}
}
$this->buffer .= htmlspecialchars( $data );
}
function clearOpenElement( $style ) {
if( $this->openElement ) {
$this->buffer .= wfElement( $this->openElement[0], $this->openElement[1], $style );
$this->openElement = false;
}
}
}
$dumper = new TextPassDumper( $argv );
if( true ) {
$dumper->dump();
} else {
$dumper->progress( <<<END
This script postprocesses XML dumps from dumpBackup.php to add
page text which was stubbed out (using --stub).
XML input is accepted on stdin.
XML output is sent to stdout; progress reports are sent to stderr.
Usage: php dumpTextPass.php [<options>]
Options:
--stub=<type>:<file> To load a compressed stub dump instead of stdin
--prefetch=<type>:<file> Use a prior dump file as a text source, to save
pressure on the database.
(Requires PHP 5.0+ and the XMLReader PECL extension)
--quiet Don't dump status reports to stderr.
--report=n Report position and speed after every n pages processed.
(Default: 100)
--server=h Force reading from MySQL server h
--current Base ETA on number of pages in database instead of all revisions
END
);
}
?>
|