summaryrefslogtreecommitdiff
path: root/includes/content/WikitextContent.php
blob: 26337db947dea7fd64fbcab39e7b0433fc940e01 (plain)
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
<?php
/**
 * Content object for wiki text pages.
 *
 * 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
 *
 * @since 1.21
 *
 * @file
 * @ingroup Content
 *
 * @author Daniel Kinzler
 */

/**
 * Content object for wiki text pages.
 *
 * @ingroup Content
 */
class WikitextContent extends TextContent {

	public function __construct( $text ) {
		parent::__construct( $text, CONTENT_MODEL_WIKITEXT );
	}

	/**
	 * @see Content::getSection()
	 */
	public function getSection( $section ) {
		global $wgParser;

		$text = $this->getNativeData();
		$sect = $wgParser->getSection( $text, $section, false );

		if ( $sect === false ) {
			return false;
		} else {
			return new WikitextContent( $sect );
		}
	}

	/**
	 * @see Content::replaceSection()
	 */
	public function replaceSection( $section, Content $with, $sectionTitle = '' ) {
		wfProfileIn( __METHOD__ );

		$myModelId = $this->getModel();
		$sectionModelId = $with->getModel();

		if ( $sectionModelId != $myModelId ) {
			wfProfileOut( __METHOD__ );
			throw new MWException( "Incompatible content model for section: " .
				"document uses $myModelId but " .
				"section uses $sectionModelId." );
		}

		$oldtext = $this->getNativeData();
		$text = $with->getNativeData();

		if ( $section === '' ) {
			wfProfileOut( __METHOD__ );
			return $with; # XXX: copy first?
		} if ( $section == 'new' ) {
			# Inserting a new section
			$subject = $sectionTitle ? wfMessage( 'newsectionheaderdefaultlevel' )
				->rawParams( $sectionTitle )->inContentLanguage()->text() . "\n\n" : '';
			if ( wfRunHooks( 'PlaceNewSection', array( $this, $oldtext, $subject, &$text ) ) ) {
				$text = strlen( trim( $oldtext ) ) > 0
					? "{$oldtext}\n\n{$subject}{$text}"
					: "{$subject}{$text}";
			}
		} else {
			# Replacing an existing section; roll out the big guns
			global $wgParser;

			$text = $wgParser->replaceSection( $oldtext, $section, $text );
		}

		$newContent = new WikitextContent( $text );

		wfProfileOut( __METHOD__ );
		return $newContent;
	}

	/**
	 * Returns a new WikitextContent object with the given section heading
	 * prepended.
	 *
	 * @param $header string
	 * @return Content
	 */
	public function addSectionHeader( $header ) {
		$text = wfMessage( 'newsectionheaderdefaultlevel' )
			->rawParams( $header )->inContentLanguage()->text();
		$text .= "\n\n";
		$text .= $this->getNativeData();

		return new WikitextContent( $text );
	}

	/**
	 * Returns a Content object with pre-save transformations applied using
	 * Parser::preSaveTransform().
	 *
	 * @param $title Title
	 * @param $user User
	 * @param $popts ParserOptions
	 * @return Content
	 */
	public function preSaveTransform( Title $title, User $user, ParserOptions $popts ) {
		global $wgParser;

		$text = $this->getNativeData();
		$pst = $wgParser->preSaveTransform( $text, $title, $user, $popts );
		rtrim( $pst );

		return ( $text === $pst ) ? $this : new WikitextContent( $pst );
	}

	/**
	 * Returns a Content object with preload transformations applied (or this
	 * object if no transformations apply).
	 *
	 * @param $title Title
	 * @param $popts ParserOptions
	 * @return Content
	 */
	public function preloadTransform( Title $title, ParserOptions $popts ) {
		global $wgParser;

		$text = $this->getNativeData();
		$plt = $wgParser->getPreloadText( $text, $title, $popts );

		return new WikitextContent( $plt );
	}

	/**
	 * Implement redirect extraction for wikitext.
	 *
	 * @return null|Title
	 *
	 * @note: migrated here from Title::newFromRedirectInternal()
	 *
	 * @see Content::getRedirectTarget
	 * @see AbstractContent::getRedirectTarget
	 */
	public function getRedirectTarget() {
		global $wgMaxRedirects;
		if ( $wgMaxRedirects < 1 ) {
			// redirects are disabled, so quit early
			return null;
		}
		$redir = MagicWord::get( 'redirect' );
		$text = trim( $this->getNativeData() );
		if ( $redir->matchStartAndRemove( $text ) ) {
			// Extract the first link and see if it's usable
			// Ensure that it really does come directly after #REDIRECT
			// Some older redirects included a colon, so don't freak about that!
			$m = array();
			if ( preg_match( '!^\s*:?\s*\[{2}(.*?)(?:\|.*?)?\]{2}!', $text, $m ) ) {
				// Strip preceding colon used to "escape" categories, etc.
				// and URL-decode links
				if ( strpos( $m[1], '%' ) !== false ) {
					// Match behavior of inline link parsing here;
					$m[1] = rawurldecode( ltrim( $m[1], ':' ) );
				}
				$title = Title::newFromText( $m[1] );
				// If the title is a redirect to bad special pages or is invalid, return null
				if ( !$title instanceof Title || !$title->isValidRedirectTarget() ) {
					return null;
				}
				return $title;
			}
		}
		return null;
	}

	/**
	 * @see   Content::updateRedirect()
	 *
	 * This implementation replaces the first link on the page with the given new target
	 * if this Content object is a redirect. Otherwise, this method returns $this.
	 *
	 * @since 1.21
	 *
	 * @param Title $target
	 *
	 * @return Content a new Content object with the updated redirect (or $this if this Content object isn't a redirect)
	 */
	public function updateRedirect( Title $target ) {
		if ( !$this->isRedirect() ) {
			return $this;
		}

		# Fix the text
		# Remember that redirect pages can have categories, templates, etc.,
		# so the regex has to be fairly general
		$newText = preg_replace( '/ \[ \[  [^\]]*  \] \] /x',
			'[[' . $target->getFullText() . ']]',
			$this->getNativeData(), 1 );

		return new WikitextContent( $newText );
	}

	/**
	 * Returns true if this content is not a redirect, and this content's text
	 * is countable according to the criteria defined by $wgArticleCountMethod.
	 *
	 * @param bool $hasLinks  if it is known whether this content contains
	 *    links, provide this information here, to avoid redundant parsing to
	 *    find out (default: null).
	 * @param $title Title: (default: null)
	 *
	 * @internal param \IContextSource $context context for parsing if necessary
	 *
	 * @return bool True if the content is countable
	 */
	public function isCountable( $hasLinks = null, Title $title = null ) {
		global $wgArticleCountMethod;

		if ( $this->isRedirect() ) {
			return false;
		}

		$text = $this->getNativeData();

		switch ( $wgArticleCountMethod ) {
			case 'any':
				return true;
			case 'comma':
				return strpos( $text, ',' ) !== false;
			case 'link':
				if ( $hasLinks === null ) { # not known, find out
					if ( !$title ) {
						$context = RequestContext::getMain();
						$title = $context->getTitle();
					}

					$po = $this->getParserOutput( $title, null, null, false );
					$links = $po->getLinks();
					$hasLinks = !empty( $links );
				}

				return $hasLinks;
		}

		return false;
	}

	public function getTextForSummary( $maxlength = 250 ) {
		$truncatedtext = parent::getTextForSummary( $maxlength );

		# clean up unfinished links
		# XXX: make this optional? wasn't there in autosummary, but required for
		# deletion summary.
		$truncatedtext = preg_replace( '/\[\[([^\]]*)\]?$/', '$1', $truncatedtext );

		return $truncatedtext;
	}

	/**
	 * Returns a ParserOutput object resulting from parsing the content's text
	 * using $wgParser.
	 *
	 * @since    1.21
	 *
	 * @param $title Title
	 * @param int $revId Revision to pass to the parser (default: null)
	 * @param $options ParserOptions (default: null)
	 * @param bool $generateHtml (default: false)
	 *
	 * @internal param \IContextSource|null $context
	 * @return ParserOutput representing the HTML form of the text
	 */
	public function getParserOutput( Title $title,
		$revId = null,
		ParserOptions $options = null, $generateHtml = true
	) {
		global $wgParser;

		if ( !$options ) {
			//NOTE: use canonical options per default to produce cacheable output
			$options = $this->getContentHandler()->makeParserOptions( 'canonical' );
		}

		$po = $wgParser->parse( $this->getNativeData(), $title, $options, true, true, $revId );
		return $po;
	}

	protected function getHtml() {
		throw new MWException(
			"getHtml() not implemented for wikitext. "
				. "Use getParserOutput()->getText()."
		);
	}

	/**
	 * @see  Content::matchMagicWord()
	 *
	 * This implementation calls $word->match() on the this TextContent object's text.
	 *
	 * @param MagicWord $word
	 *
	 * @return bool whether this Content object matches the given magic word.
	 */
	public function matchMagicWord( MagicWord $word ) {
		return $word->match( $this->getNativeData() );
	}
}