wikimedia/mediawiki-extensions-TextExtracts
1
0
Fork 0
mirror of https://gerrit.wikimedia.org/r/mediawiki/extensions/TextExtracts synced 2024-11-15 03:35:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge "CodeSniffer fixes"

Browse source
This commit is contained in:
jenkins-bot 2016-09-26 22:27:32 +00:00 committed by Gerrit Code Review
parent 4754b02ecb 754c9e4f19
commit 27c935f66c
4 changed files with 83 additions and 84 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

64
includes/ApiQueryExtracts.php
View file

@ -48,7 +48,7 @@ class ApiQueryExtracts extends ApiQueryBase {
/**
* @var array
*/
private $supportedContentModels = array( 'wikitext' );
private $supportedContentModels = [ 'wikitext' ];
public function __construct( $query, $moduleName, Config $conf ) {
parent::__construct( $query, $moduleName, 'ex' );
@ -91,9 +91,9 @@ class ApiQueryExtracts extends ApiQueryBase {
}
if ( $isXml ) {
$fit = $result->addValue( array( 'query', 'pages', $id ), 'extract', array( '*' => $text ) );
$fit = $result->addValue( [ 'query', 'pages', $id ], 'extract', [ '*' => $text ] );
} else {
$fit = $result->addValue( array( 'query', 'pages', $id ), 'extract', $text );
$fit = $result->addValue( [ 'query', 'pages', $id ], 'extract', $text );
}
if ( !$fit ) {
$this->setContinueEnumParameter( 'continue', $continue + $count - 1 );
@ -196,33 +196,33 @@ class ApiQueryExtracts extends ApiQueryBase {
return $text;
}
}
$request = array(
$request = [
'action' => 'parse',
'page' => $page->getTitle()->getPrefixedText(),
'prop' => 'text'
);
];
if ( $this->params['intro'] ) {
$request['section'] = 0;
}
// in case of cache miss, render just the needed section
$api = new ApiMain( new FauxRequest( $request ) );
$api = new ApiMain( new FauxRequest( $request ) );
try {
$api->execute();
$data = $api->getResult()->getResultData( null, array(
'BC' => array(),
'Types' => array(),
) );
$data = $api->getResult()->getResultData( null, [
'BC' => [],
'Types' => [],
] );
} catch ( UsageException $e ) {
if ( $e->getCodeString() === 'nosuchsection' ) {
// Looks like we tried to get the intro to a page without
// sections! Lets just grab what we can get.
unset( $request['section'] );
$api = new ApiMain( new FauxRequest( $request ) );
$api = new ApiMain( new FauxRequest( $request ) );
$api->execute();
$data = $api->getResult()->getResultData( null, array(
'BC' => array(),
'Types' => array(),
) );
$data = $api->getResult()->getResultData( null, [
'BC' => [],
'Types' => [],
] );
} else {
// Some other unexpected error - lets just report it to the user
// on the off chance that is the right thing.
@ -304,7 +304,7 @@ class ApiQueryExtracts extends ApiQueryBase {
*/
private function tidy( $text ) {
if ( $this->getConfig()->get( 'UseTidy' ) && !$this->params['plaintext'] ) {
$text = trim ( MWTidy::tidy( $text ) );
$text = trim( MWTidy::tidy( $text ) );
}
return $text;
}
@ -312,7 +312,7 @@ class ApiQueryExtracts extends ApiQueryBase {
private function doSections( $text ) {
$text = preg_replace_callback(
"/" . ExtractFormatter::SECTION_MARKER_START . '(\d)'. ExtractFormatter::SECTION_MARKER_END . "(.*?)$/m",
array( $this, 'sectionCallback' ),
[ $this, 'sectionCallback' ],
$text
);
return $text;
@ -336,44 +336,44 @@ class ApiQueryExtracts extends ApiQueryBase {
}
public function getAllowedParams() {
return array(
'chars' => array(
return [
'chars' => [
ApiBase::PARAM_TYPE => 'integer',
ApiBase::PARAM_MIN => 1,
),
'sentences' => array(
],
'sentences' => [
ApiBase::PARAM_TYPE => 'integer',
ApiBase::PARAM_MIN => 1,
ApiBase::PARAM_MAX => 10,
),
'limit' => array(
],
'limit' => [
ApiBase::PARAM_DFLT => 1,
ApiBase::PARAM_TYPE => 'limit',
ApiBase::PARAM_MIN => 1,
ApiBase::PARAM_MAX => 20,
ApiBase::PARAM_MAX2 => 20,
),
],
'intro' => false,
'plaintext' => false,
'sectionformat' => array(
ApiBase::PARAM_TYPE => array( 'plain', 'wiki', 'raw' ),
'sectionformat' => [
ApiBase::PARAM_TYPE => [ 'plain', 'wiki', 'raw' ],
ApiBase::PARAM_DFLT => 'wiki',
),
'continue' => array(
],
'continue' => [
ApiBase::PARAM_TYPE => 'integer',
ApiBase::PARAM_HELP_MSG => 'api-help-param-continue',
),
);
],
];
}
/**
* @see ApiBase::getExamplesMessages()
*/
protected function getExamplesMessages() {
return array(
return [
'action=query&prop=extracts&exchars=175&titles=Therion'
=> 'apihelp-query+extracts-example-1',
);
];
}
public function getHelpUrls() {

12
includes/ExtractFormatter.php
View file

@ -45,7 +45,7 @@ class ExtractFormatter extends HtmlFormatter {
if ( $plainText ) {
$this->flattenAllTags();
} else {
$this->flatten( array( 'a' ) );
$this->flatten( [ 'a' ] );
}
}
@ -64,7 +64,7 @@ class ExtractFormatter extends HtmlFormatter {
public function onHtmlReady( $html ) {
if ( $this->plainText ) {
$html = preg_replace( '/\s*(<h([1-6])\b)/i',
"\n\n" . self::SECTION_MARKER_START . '$2' . self::SECTION_MARKER_END . '$1' ,
"\n\n" . self::SECTION_MARKER_START . '$2' . self::SECTION_MARKER_END . '$1',
$html
);
}
@ -80,21 +80,21 @@ class ExtractFormatter extends HtmlFormatter {
*/
public static function getFirstSentences( $text, $requestedSentenceCount ) {
// Based on code from OpenSearchXml by Brion Vibber
$endchars = array(
$endchars = [
'[^\p{Lu}]\.(?:[ \n]|$)', '[\!\?](?:[ \n]|$)', // regular ASCII
'。', // full-width ideographic full-stop
'．', '！', '？', // double-width roman forms
'｡', // half-width ideographic full stop
);
];
$endgroup = implode( '|', $endchars );
$end = "(?:$endgroup)";
$sentence = ".+?$end+";
$requestedSentenceCount = intval( $requestedSentenceCount );
$regexp = "/^($sentence){1,{$requestedSentenceCount}}/u";
$matches = array();
$matches = [];
$res = preg_match( $regexp, $text, $matches );
if( $res ) {
if ( $res ) {
$text = trim( $matches[0] );
} else {
if ( $res === false ) {

7
includes/Hooks.php
View file

@ -2,7 +2,6 @@
namespace TextExtracts;
use ApiMain;
use ApiResult;
use ConfigFactory;
@ -22,17 +21,17 @@ class Hooks {
}
$pageIds = array_keys( $results );
$api = new ApiMain( new FauxRequest(
array(
[
'action' => 'query',
'prop' => 'extracts',
'explaintext' => true,
'exintro' => true,
'exlimit' => count( $results ),
'pageids' => implode( '|', $pageIds ),
) )
] )
);
$api->execute();
$data = $api->getResult()->getResultData( array( 'query', 'pages' ) );
$data = $api->getResult()->getResultData( [ 'query', 'pages' ] );
foreach ( $pageIds as $id ) {
$contentKey = isset( $data[$id]['extract'][ApiResult::META_CONTENT] )
? $data[$id]['extract'][ApiResult::META_CONTENT]

84
tests/phpunit/ExtractFormatterTest.php
View file

@ -22,29 +22,29 @@ class ExtractFormatterTest extends MediaWikiTestCase {
public function provideExtracts() {
$dutch = '<b>Dutch</b> (<span class="unicode haudio" style="white-space:nowrap;"><span class="fn"><a href="/wiki/File:Nl-Nederlands.ogg" title="About this sound"><img alt="About this sound" src="https://upload.wikimedia.org/wikipedia/commons/thumb/8/8a/Loudspeaker.svg/11px-Loudspeaker.svg.png" width="11" height="11" srcset="https://upload.wikimedia.org/wikipedia/commons/thumb/8/8a/Loudspeaker.svg/17px-Loudspeaker.svg.png 1.5x, https://upload.wikimedia.org/wikipedia/commons/thumb/8/8a/Loudspeaker.svg/22px-Loudspeaker.svg.png 2x" /></a>&#160;<a href="https://upload.wikimedia.org/wikipedia/commons/d/db/Nl-Nederlands.ogg" class="internal" title="Nl-Nederlands.ogg"><i>Nederlands</i></a></span>&#160;<small class="metadata audiolinkinfo" style="cursor:help;">(<a href="/w/index.php?title=Wikipedia:Media_help&amp;action=edit&amp;redlink=1" class="new" title="Wikipedia:Media help (page does not exist)"><span style="cursor:help;">help</span></a>·<a href="/wiki/File:Nl-Nederlands.ogg" title="File:Nl-Nederlands.ogg"><span style="cursor:help;">info</span></a>)</small></span>) is a <a href="/w/index.php?title=West_Germanic_languages&amp;action=edit&amp;redlink=1" class="new" title="West Germanic languages (page does not exist)">West Germanic language</a> and the native language of most of the population of the <a href="/w/index.php?title=Netherlands&amp;action=edit&amp;redlink=1" class="new" title="Netherlands (page does not exist)">Netherlands</a>';
return array(
array(
return [
[
"Dutch ( Nederlands ) is a West Germanic language and the native language of most of the population of the Netherlands",
$dutch,
true,
),
],
array(
[
"<span><span lang=\"baz\">qux</span></span>",
'<span class="foo"><span lang="baz">qux</span></span>',
false,
),
array(
],
[
"<span><span lang=\"baz\">qux</span></span>",
'<span style="foo: bar;"><span lang="baz">qux</span></span>',
false,
),
array(
],
[
"<span><span lang=\"qux\">quux</span></span>",
'<span class="foo"><span style="bar: baz;" lang="qux">quux</span></span>',
false,
),
);
],
];
}
/**
@ -58,68 +58,68 @@ class ExtractFormatterTest extends MediaWikiTestCase {
}
public function provideGetFirstSentences() {
return array(
array(
return [
[
'Foo is a bar. Such a smart boy. But completely useless.',
2,
'Foo is a bar. Such a smart boy.',
),
array(
],
[
'Foo is a bar. Such a smart boy. But completely useless.',
1,
'Foo is a bar.',
),
array(
],
[
'Foo is a bar. Such a smart boy.',
2,
'Foo is a bar. Such a smart boy.',
),
array(
],
[
'Foo is a bar.',
1,
'Foo is a bar.',
),
array(
],
[
'Foo is a bar.',
2,
'Foo is a bar.',
),
array(
],
[
'',
1,
'',
),
],
// Exclamation points too!!!
array(
[
'Foo is a bar! Such a smart boy! But completely useless!',
1,
'Foo is a bar!',
),
],
// A tricky one
array(
[
"Acid phosphatase (EC 3.1.3.2) is a chemical you don't want to mess with. Polyvinyl acetate, however, is another story.",
1,
"Acid phosphatase (EC 3.1.3.2) is a chemical you don't want to mess with.",
),
],
// Bug T118621
array(
[
'Foo was born in 1977. He enjoys listening to Siouxsie and the Banshees.',
1,
'Foo was born in 1977.',
),
],
// Bug T115795 - Test no cropping after initials
array(
[
'P.J. Harvey is a singer. She is awesome!',
1,
'P.J. Harvey is a singer.',
),
],
// Bug T115817 - Non-breaking space is not a delimiter
array(
[
html_entity_decode( 'Pigeons (lat.&nbsp;Columbidae) are birds. They primarily feed on seeds.' ),
1,
html_entity_decode( 'Pigeons (lat.&nbsp;Columbidae) are birds.' ),
),
);
],
];
}
/**
@ -134,13 +134,13 @@ class ExtractFormatterTest extends MediaWikiTestCase {
public function provideGetFirstChars() {
$text = 'Lullzy lulz are lullzy!';
return array(
//array( $text, 0, '' ),
array( $text, 100, $text ),
array( $text, 1, 'Lullzy' ),
array( $text, 6, 'Lullzy' ),
//array( $text, 7, 'Lullzy' ),
array( $text, 8, 'Lullzy lulz' ),
);
return [
// [ $text, 0, '' ],
[ $text, 100, $text ],
[ $text, 1, 'Lullzy' ],
[ $text, 6, 'Lullzy' ],
// [ $text, 7, 'Lullzy' ],
[ $text, 8, 'Lullzy lulz' ],
];
}
}