MediaWiki  REL1_31
ParserOutputTest.php
Go to the documentation of this file.
1 <?php
2 
8 
9  public static function provideIsLinkInternal() {
10  return [
11  // Different domains
12  [ false, 'http://example.org', 'http://mediawiki.org' ],
13  // Same domains
14  [ true, 'http://example.org', 'http://example.org' ],
15  [ true, 'https://example.org', 'https://example.org' ],
16  [ true, '//example.org', '//example.org' ],
17  // Same domain different cases
18  [ true, 'http://example.org', 'http://EXAMPLE.ORG' ],
19  // Paths, queries, and fragments are not relevant
20  [ true, 'http://example.org', 'http://example.org/wiki/Main_Page' ],
21  [ true, 'http://example.org', 'http://example.org?my=query' ],
22  [ true, 'http://example.org', 'http://example.org#its-a-fragment' ],
23  // Different protocols
24  [ false, 'http://example.org', 'https://example.org' ],
25  [ false, 'https://example.org', 'http://example.org' ],
26  // Protocol relative servers always match http and https links
27  [ true, '//example.org', 'http://example.org' ],
28  [ true, '//example.org', 'https://example.org' ],
29  // But they don't match strange things like this
30  [ false, '//example.org', 'irc://example.org' ],
31  ];
32  }
33 
39  public function testIsLinkInternal( $shouldMatch, $server, $url ) {
40  $this->assertEquals( $shouldMatch, ParserOutput::isLinkInternal( $server, $url ) );
41  }
42 
47  public function testExtensionData() {
48  $po = new ParserOutput();
49 
50  $po->setExtensionData( "one", "Foo" );
51 
52  $this->assertEquals( "Foo", $po->getExtensionData( "one" ) );
53  $this->assertNull( $po->getExtensionData( "spam" ) );
54 
55  $po->setExtensionData( "two", "Bar" );
56  $this->assertEquals( "Foo", $po->getExtensionData( "one" ) );
57  $this->assertEquals( "Bar", $po->getExtensionData( "two" ) );
58 
59  $po->setExtensionData( "one", null );
60  $this->assertNull( $po->getExtensionData( "one" ) );
61  $this->assertEquals( "Bar", $po->getExtensionData( "two" ) );
62  }
63 
70  public function testProperties() {
71  $po = new ParserOutput();
72 
73  $po->setProperty( 'foo', 'val' );
74 
75  $properties = $po->getProperties();
76  $this->assertEquals( $po->getProperty( 'foo' ), 'val' );
77  $this->assertEquals( $properties['foo'], 'val' );
78 
79  $po->setProperty( 'foo', 'second val' );
80 
81  $properties = $po->getProperties();
82  $this->assertEquals( $po->getProperty( 'foo' ), 'second val' );
83  $this->assertEquals( $properties['foo'], 'second val' );
84 
85  $po->unsetProperty( 'foo' );
86 
87  $properties = $po->getProperties();
88  $this->assertEquals( $po->getProperty( 'foo' ), false );
89  $this->assertArrayNotHasKey( 'foo', $properties );
90  }
91 
99  public function testGetText( $options, $text, $expect ) {
100  $this->setMwGlobals( [
101  'wgArticlePath' => '/wiki/$1',
102  'wgScriptPath' => '/w',
103  'wgScript' => '/w/index.php',
104  ] );
105 
106  $po = new ParserOutput( $text );
107  $actual = $po->getText( $options );
108  $this->assertSame( $expect, $actual );
109  }
110 
111  public static function provideGetText() {
112  // phpcs:disable Generic.Files.LineLength
113  $text = <<<EOF
114 <div class="mw-parser-output"><p>Test document.
115 </p>
116 <mw:toc><div id="toc" class="toc"><div class="toctitle"><h2>Contents</h2></div>
117 <ul>
118 <li class="toclevel-1 tocsection-1"><a href="#Section_1"><span class="tocnumber">1</span> <span class="toctext">Section 1</span></a></li>
119 <li class="toclevel-1 tocsection-2"><a href="#Section_2"><span class="tocnumber">2</span> <span class="toctext">Section 2</span></a>
120 <ul>
121 <li class="toclevel-2 tocsection-3"><a href="#Section_2.1"><span class="tocnumber">2.1</span> <span class="toctext">Section 2.1</span></a></li>
122 </ul>
123 </li>
124 <li class="toclevel-1 tocsection-4"><a href="#Section_3"><span class="tocnumber">3</span> <span class="toctext">Section 3</span></a></li>
125 </ul>
126 </div>
127 </mw:toc>
128 <h2><span class="mw-headline" id="Section_1">Section 1</span><mw:editsection page="Test Page" section="1">Section 1</mw:editsection></h2>
129 <p>One
130 </p>
131 <h2><span class="mw-headline" id="Section_2">Section 2</span><mw:editsection page="Test Page" section="2">Section 2</mw:editsection></h2>
132 <p>Two
133 </p>
134 <h3><span class="mw-headline" id="Section_2.1">Section 2.1</span><mw:editsection page="Test Page" section="3">Section 2.1</mw:editsection></h3>
135 <p>Two point one
136 </p>
137 <h2><span class="mw-headline" id="Section_3">Section 3</span><mw:editsection page="Test Page" section="4">Section 3</mw:editsection></h2>
138 <p>Three
139 </p></div>
140 EOF;
141 
142  $dedupText = <<<EOF
143 <p>This is a test document.</p>
144 <style data-mw-deduplicate="duplicate1">.Duplicate1 {}</style>
145 <style data-mw-deduplicate="duplicate1">.Duplicate1 {}</style>
146 <style data-mw-deduplicate="duplicate2">.Duplicate2 {}</style>
147 <style data-mw-deduplicate="duplicate1">.Duplicate1 {}</style>
148 <style data-mw-deduplicate="duplicate2">.Duplicate2 {}</style>
149 <style data-mw-not-deduplicate="duplicate1">.Duplicate1 {}</style>
150 <style data-mw-deduplicate="duplicate1">.Same-attribute-different-content {}</style>
151 <style data-mw-deduplicate="duplicate3">.Duplicate1 {}</style>
152 <style>.Duplicate1 {}</style>
153 EOF;
154 
155  return [
156  'No options' => [
157  [], $text, <<<EOF
158 <div class="mw-parser-output"><p>Test document.
159 </p>
160 <div id="toc" class="toc"><div class="toctitle"><h2>Contents</h2></div>
161 <ul>
162 <li class="toclevel-1 tocsection-1"><a href="#Section_1"><span class="tocnumber">1</span> <span class="toctext">Section 1</span></a></li>
163 <li class="toclevel-1 tocsection-2"><a href="#Section_2"><span class="tocnumber">2</span> <span class="toctext">Section 2</span></a>
164 <ul>
165 <li class="toclevel-2 tocsection-3"><a href="#Section_2.1"><span class="tocnumber">2.1</span> <span class="toctext">Section 2.1</span></a></li>
166 </ul>
167 </li>
168 <li class="toclevel-1 tocsection-4"><a href="#Section_3"><span class="tocnumber">3</span> <span class="toctext">Section 3</span></a></li>
169 </ul>
170 </div>
171 
172 <h2><span class="mw-headline" id="Section_1">Section 1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=1" title="Edit section: Section 1">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
173 <p>One
174 </p>
175 <h2><span class="mw-headline" id="Section_2">Section 2</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=2" title="Edit section: Section 2">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
176 <p>Two
177 </p>
178 <h3><span class="mw-headline" id="Section_2.1">Section 2.1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=3" title="Edit section: Section 2.1">edit</a><span class="mw-editsection-bracket">]</span></span></h3>
179 <p>Two point one
180 </p>
181 <h2><span class="mw-headline" id="Section_3">Section 3</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=4" title="Edit section: Section 3">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
182 <p>Three
183 </p></div>
184 EOF
185  ],
186  'Disable section edit links' => [
187  [ 'enableSectionEditLinks' => false ], $text, <<<EOF
188 <div class="mw-parser-output"><p>Test document.
189 </p>
190 <div id="toc" class="toc"><div class="toctitle"><h2>Contents</h2></div>
191 <ul>
192 <li class="toclevel-1 tocsection-1"><a href="#Section_1"><span class="tocnumber">1</span> <span class="toctext">Section 1</span></a></li>
193 <li class="toclevel-1 tocsection-2"><a href="#Section_2"><span class="tocnumber">2</span> <span class="toctext">Section 2</span></a>
194 <ul>
195 <li class="toclevel-2 tocsection-3"><a href="#Section_2.1"><span class="tocnumber">2.1</span> <span class="toctext">Section 2.1</span></a></li>
196 </ul>
197 </li>
198 <li class="toclevel-1 tocsection-4"><a href="#Section_3"><span class="tocnumber">3</span> <span class="toctext">Section 3</span></a></li>
199 </ul>
200 </div>
201 
202 <h2><span class="mw-headline" id="Section_1">Section 1</span></h2>
203 <p>One
204 </p>
205 <h2><span class="mw-headline" id="Section_2">Section 2</span></h2>
206 <p>Two
207 </p>
208 <h3><span class="mw-headline" id="Section_2.1">Section 2.1</span></h3>
209 <p>Two point one
210 </p>
211 <h2><span class="mw-headline" id="Section_3">Section 3</span></h2>
212 <p>Three
213 </p></div>
214 EOF
215  ],
216  'Disable TOC' => [
217  [ 'allowTOC' => false ], $text, <<<EOF
218 <div class="mw-parser-output"><p>Test document.
219 </p>
220 
221 <h2><span class="mw-headline" id="Section_1">Section 1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=1" title="Edit section: Section 1">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
222 <p>One
223 </p>
224 <h2><span class="mw-headline" id="Section_2">Section 2</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=2" title="Edit section: Section 2">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
225 <p>Two
226 </p>
227 <h3><span class="mw-headline" id="Section_2.1">Section 2.1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=3" title="Edit section: Section 2.1">edit</a><span class="mw-editsection-bracket">]</span></span></h3>
228 <p>Two point one
229 </p>
230 <h2><span class="mw-headline" id="Section_3">Section 3</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=4" title="Edit section: Section 3">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
231 <p>Three
232 </p></div>
233 EOF
234  ],
235  'Unwrap text' => [
236  [ 'unwrap' => true ], $text, <<<EOF
237 <p>Test document.
238 </p>
239 <div id="toc" class="toc"><div class="toctitle"><h2>Contents</h2></div>
240 <ul>
241 <li class="toclevel-1 tocsection-1"><a href="#Section_1"><span class="tocnumber">1</span> <span class="toctext">Section 1</span></a></li>
242 <li class="toclevel-1 tocsection-2"><a href="#Section_2"><span class="tocnumber">2</span> <span class="toctext">Section 2</span></a>
243 <ul>
244 <li class="toclevel-2 tocsection-3"><a href="#Section_2.1"><span class="tocnumber">2.1</span> <span class="toctext">Section 2.1</span></a></li>
245 </ul>
246 </li>
247 <li class="toclevel-1 tocsection-4"><a href="#Section_3"><span class="tocnumber">3</span> <span class="toctext">Section 3</span></a></li>
248 </ul>
249 </div>
250 
251 <h2><span class="mw-headline" id="Section_1">Section 1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=1" title="Edit section: Section 1">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
252 <p>One
253 </p>
254 <h2><span class="mw-headline" id="Section_2">Section 2</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=2" title="Edit section: Section 2">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
255 <p>Two
256 </p>
257 <h3><span class="mw-headline" id="Section_2.1">Section 2.1</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=3" title="Edit section: Section 2.1">edit</a><span class="mw-editsection-bracket">]</span></span></h3>
258 <p>Two point one
259 </p>
260 <h2><span class="mw-headline" id="Section_3">Section 3</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Test_Page&amp;action=edit&amp;section=4" title="Edit section: Section 3">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
261 <p>Three
262 </p>
263 EOF
264  ],
265  'Unwrap without a mw-parser-output wrapper' => [
266  [ 'unwrap' => true ], '<div class="foobar">Content</div>', '<div class="foobar">Content</div>'
267  ],
268  'Unwrap with extra comment at end' => [
269  [ 'unwrap' => true ], '<div class="mw-parser-output"><p>Test document.</p></div>
270 <!-- Saved in parser cache... -->', '<p>Test document.</p>
271 <!-- Saved in parser cache... -->'
272  ],
273  'Style deduplication' => [
274  [], $dedupText, <<<EOF
275 <p>This is a test document.</p>
276 <style data-mw-deduplicate="duplicate1">.Duplicate1 {}</style>
277 <link rel="mw-deduplicated-inline-style" href="mw-data:duplicate1"/>
278 <style data-mw-deduplicate="duplicate2">.Duplicate2 {}</style>
279 <link rel="mw-deduplicated-inline-style" href="mw-data:duplicate1"/>
280 <link rel="mw-deduplicated-inline-style" href="mw-data:duplicate2"/>
281 <style data-mw-not-deduplicate="duplicate1">.Duplicate1 {}</style>
282 <link rel="mw-deduplicated-inline-style" href="mw-data:duplicate1"/>
283 <style data-mw-deduplicate="duplicate3">.Duplicate1 {}</style>
284 <style>.Duplicate1 {}</style>
285 EOF
286  ],
287  'Style deduplication disabled' => [
288  [ 'deduplicateStyles' => false ], $dedupText, $dedupText
289  ],
290  ];
291  // phpcs:enable
292  }
293 
294 }
ParserOutput
Definition: ParserOutput.php:25
content
per default it will return the text for text based content
Definition: contenthandler.txt:104
is
We use the convention $dbr for read and $dbw for write to help you keep track of whether the database object is a the world will explode Or to be a subsequent write query which succeeded on the master may fail when replicated to the slave due to a unique key collision Replication on the slave will stop and it may take hours to repair the database and get it back online Setting read_only in my cnf on the slave will avoid this but given the dire we prefer to have as many checks as possible We provide a but the wrapper functions like please read the documentation for except in special pages derived from QueryPage It s a common pitfall for new developers to submit code containing SQL queries which examine huge numbers of rows Remember that COUNT * is(N), counting rows in atable is like counting beans in a bucket.------------------------------------------------------------------------ Replication------------------------------------------------------------------------The largest installation of MediaWiki, Wikimedia, uses a large set ofslave MySQL servers replicating writes made to a master MySQL server. Itis important to understand the issues associated with this setup if youwant to write code destined for Wikipedia.It 's often the case that the best algorithm to use for a given taskdepends on whether or not replication is in use. Due to our unabashedWikipedia-centrism, we often just use the replication-friendly version, but if you like, you can use wfGetLB() ->getServerCount() > 1 tocheck to see if replication is in use.===Lag===Lag primarily occurs when large write queries are sent to the master.Writes on the master are executed in parallel, but they are executed inserial when they are replicated to the slaves. The master writes thequery to the binlog when the transaction is committed. The slaves pollthe binlog and start executing the query as soon as it appears. They canservice reads while they are performing a write query, but will not readanything more from the binlog and thus will perform no more writes. Thismeans that if the write query runs for a long time, the slaves will lagbehind the master for the time it takes for the write query to complete.Lag can be exacerbated by high read load. MediaWiki 's load balancer willstop sending reads to a slave when it is lagged by more than 30 seconds.If the load ratios are set incorrectly, or if there is too much loadgenerally, this may lead to a slave permanently hovering around 30seconds lag.If all slaves are lagged by more than 30 seconds, MediaWiki will stopwriting to the database. All edits and other write operations will berefused, with an error returned to the user. This gives the slaves achance to catch up. Before we had this mechanism, the slaves wouldregularly lag by several minutes, making review of recent editsdifficult.In addition to this, MediaWiki attempts to ensure that the user seesevents occurring on the wiki in chronological order. A few seconds of lagcan be tolerated, as long as the user sees a consistent picture fromsubsequent requests. This is done by saving the master binlog positionin the session, and then at the start of each request, waiting for theslave to catch up to that position before doing any reads from it. Ifthis wait times out, reads are allowed anyway, but the request isconsidered to be in "lagged slave mode". Lagged slave mode can bechecked by calling wfGetLB() ->getLaggedSlaveMode(). The onlypractical consequence at present is a warning displayed in the pagefooter.===Lag avoidance===To avoid excessive lag, queries which write large numbers of rows shouldbe split up, generally to write one row at a time. Multi-row INSERT ...SELECT queries are the worst offenders should be avoided altogether.Instead do the select first and then the insert.===Working with lag===Despite our best efforts, it 's not practical to guarantee a low-lagenvironment. Lag will usually be less than one second, but mayoccasionally be up to 30 seconds. For scalability, it 's very importantto keep load on the master low, so simply sending all your queries tothe master is not the answer. So when you have a genuine need forup-to-date data, the following approach is advised:1) Do a quick query to the master for a sequence number or timestamp 2) Run the full query on the slave and check if it matches the data you gotfrom the master 3) If it doesn 't, run the full query on the masterTo avoid swamping the master every time the slaves lag, use of thisapproach should be kept to a minimum. In most cases you should just readfrom the slave and let the user deal with the delay.------------------------------------------------------------------------ Lock contention------------------------------------------------------------------------Due to the high write rate on Wikipedia(and some other wikis), MediaWiki developers need to be very careful to structure their writesto avoid long-lasting locks. By default, MediaWiki opens a transactionat the first query, and commits it before the output is sent. Locks willbe held from the time when the query is done until the commit. So youcan reduce lock time by doing as much processing as possible before youdo your write queries.Often this approach is not good enough, and it becomes necessary toenclose small groups of queries in their own transaction. Use thefollowing syntax:$dbw=wfGetDB(DB_MASTER
page
target page
Definition: All_system_messages.txt:1267
ParserOutputTest\testProperties
testProperties()
ParserOutput::setProperty ParserOutput::getProperty ParserOutput::unsetProperty ParserOutput::getProp...
Definition: ParserOutputTest.php:70
true
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped noclasses just before the function returns a value If you return true
Definition: hooks.txt:2006
php
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:37
ParserOutput\isLinkInternal
static isLinkInternal( $internal, $url)
Checks, if a url is pointing to the own server.
Definition: ParserOutput.php:623
MediaWikiTestCase\setMwGlobals
setMwGlobals( $pairs, $value=null)
Sets a global, maintaining a stashed version of the previous global to be restored in tearDown.
Definition: MediaWikiTestCase.php:678
MediaWikiTestCase
Definition: MediaWikiTestCase.php:17
title
title
Definition: parserTests.txt:219
ParserOutputTest\testGetText
testGetText( $options, $text, $expect)
ParserOutput::getText provideGetText.
Definition: ParserOutputTest.php:99
div
div
Definition: parserTests.txt:6593
$options
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped & $options
Definition: hooks.txt:2001
style
Bar style
Definition: parserTests.txt:192
ParserOutputTest\provideGetText
static provideGetText()
Definition: ParserOutputTest.php:111
ParserOutputTest
Database ^— trigger DB shadowing because we are using Title magic.
Definition: ParserOutputTest.php:7
ParserOutputTest\provideIsLinkInternal
static provideIsLinkInternal()
Definition: ParserOutputTest.php:9
ParserOutputTest\testIsLinkInternal
testIsLinkInternal( $shouldMatch, $server, $url)
Test to make sure ParserOutput::isLinkInternal behaves properly provideIsLinkInternal ParserOutput::i...
Definition: ParserOutputTest.php:39
link
usually copyright or history_copyright This message must be in HTML not wikitext if the section is included from a template to be included in the link
Definition: hooks.txt:3023
ParserOutputTest\testExtensionData
testExtensionData()
ParserOutput::setExtensionData ParserOutput::getExtensionData.
Definition: ParserOutputTest.php:47
href
shown</td >< td > a href
Definition: All_system_messages.txt:2667
false
processing should stop and the error should be shown to the user * false
Definition: hooks.txt:187
data
and how to run hooks for an and one after Each event has a preferably in CamelCase For ArticleDelete hook A clump of code and data that should be run when an event happens This can be either a function and a chunk of data
Definition: hooks.txt:18