Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 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 | 1x 1x 1x 2x 1x 2x 46x 46x 19x 19x 21x 8x 21x 4x 4x 2x 2x 2x 17x 17x 5x 5x 5x 12x 12x 4x 4x 2x 2x 9x 9x 9x 9x 9x 9x 9x 4x 9x 4x 5x 9x 9x 9x 9x 9x 7x 7x 7x 3x 9x 5x 39x 39x 39x 39x 38x 38x 38x 39x 1x 39x 5x 1x 1x 1x | const
Thumbnail = require( './Thumbnail' ),
HEADING_SELECTOR = mw.config.get( 'wgMFMobileFormatterHeadings', [ 'h1', 'h2', 'h3', 'h4', 'h5' ] ).join( ',' ),
EXCLUDE_THUMBNAIL_CLASS_SELECTORS = [ 'noviewer', 'metadata' ],
NOT_SELECTORS = EXCLUDE_THUMBNAIL_CLASS_SELECTORS.map( ( excludeSelector ) => `:not(.${excludeSelector})` ).join( '' ),
THUMB_SELECTOR = [ 'a.image', 'a.thumbimage, a.mw-file-description' ].map(
( selector ) => `${selector}${NOT_SELECTORS}`
).join( ',' );
class PageHTMLParser {
/**
* @param {jQuery.Object} $container Used when parsing to find children within
* this container
*/
constructor( $container ) {
this.$el = $container;
// T220751: Cache headings as $el.find is a very expensive call.
/** @private */
this.$headings = this.$el.find( HEADING_SELECTOR );
}
/**
* Find the heading in the page.
* This has the benefit of excluding any additional h2s and h3s that may
* have been added programatically.
*
* @param {number} sectionIndex as defined by the PHP parser.
* It should correspond to the section id
* used in the edit link for the section.
* Note, confusingly, this is different from section "ID" which is
* used in methods
* @return {jQuery.Object}
*/
findSectionHeadingByIndex( sectionIndex ) {
Iif ( sectionIndex < 1 ) {
// negative indexes will search from the end, which is behaviour we do not want.
// return an empty set when this happens.
// eslint-disable-next-line no-undef
return $( [] );
} else {
return this.$headings
// Headings must strictly be a child element of a section element
// or the parser-output.
// Not an ancestor!
.filter( '.mw-parser-output > *, [class^="mf-section-"] > *' ).eq( sectionIndex - 1 );
}
}
/**
* Finds all child elements that match the selector in a given section or subsection.
* Returns any direct child elements that match the selector,
* (i.e. searches only one level deep)
* as well as any elements that match the selector within those children.
* If the Page has no headings (e.g. a stub),
* then the search will target all nodes within the page.
*
* This code should work on desktop (PHP parser HTML)
* as well as mobile formatted HTML (PHP parser + MobileFormatter)
*
* @param {number} sectionIndex as defined by the PHP parser. It should correspond to
* the section id used in the edit link for the section.
* Note, confusingly, this is different from section "ID" which is
* used in methods
* @param {string} selector to match
* @return {jQuery.Object}
*/
findChildInSectionLead( sectionIndex, selector ) {
var $heading, $nextHeading, $el, $lead,
headingSelector = HEADING_SELECTOR;
function withNestedChildren( $matchingNodes ) {
return $matchingNodes.find( selector ).addBack();
}
if ( sectionIndex === 0 ) {
// lead is easy
$lead = this.getLeadSectionElement();
if ( $lead && $lead.length ) {
return withNestedChildren( $lead.children( selector ) );
} else {
$heading = this.findSectionHeadingByIndex( 1 );
return $heading.length ? withNestedChildren( $heading.prevAll( selector ) ) :
// this page is a stub so search entire page
this.$el.find( selector );
}
}
// find heading associated with the section by looking at its
// index position in the article
// section ids relate to the element position in the page and the first heading
// lead has been dealt with above, so first heading corresponds to section 1,
// the first heading in the article.
$heading = this.findSectionHeadingByIndex( sectionIndex );
// If section-heading is present on the heading,
// then we know the page has been MobileFormatted
// and that this is a wrapped section
if ( $heading.hasClass( 'section-heading' ) ) {
// get content of section
$el = $heading.next();
// inside section find the first heading
$nextHeading = $el.find( headingSelector ).eq( 0 );
return $nextHeading.length ?
// find all amboxes before the next heading
withNestedChildren( $nextHeading.prevAll( selector ) ) :
// There is no subheadings inside
// Grab all issues in section
withNestedChildren( $el.children( selector ) );
} else {
// the heading relates to a subsection (or unwrapped desktop section),
// so grab elements between this and the next one
$nextHeading = $heading.eq( 0 ).nextAll( headingSelector ).eq( 0 );
return $heading.nextUntil( $nextHeading, selector );
}
}
/**
* Get the lead section of the page view.
*
* @return {jQuery.Object|null}
*/
getLeadSectionElement() {
/*
* The page is formatted as follows:
* <div id="bodyContent">
* <!-- content of the page.. -->
* <div id="mw-content-text">
* <div class="mf-section-0">lead section</div>
* <h2></h2>
* <div class="mf-section-1">second section</div>
* </div>
* </div>
*/
const $leadSection = this.$el.find( '.mf-section-0' );
if ( $leadSection.length ) {
return $leadSection;
}
// no lead section found
return null;
}
/**
* Returns a Thumbnail object from an anchor element containing an image or
* null if not valid.
*
* @param {jQuery} $a Anchor element that contains the image.
* @return {Thumbnail|null}
*/
getThumbnail( $a ) {
var
notSelector = '.' + EXCLUDE_THUMBNAIL_CLASS_SELECTORS.join( ',.' ),
$lazyImage = $a.find( '.lazy-image-placeholder' ),
// Parents need to be checked as well.
valid = $a.parents( notSelector ).length === 0 &&
$a.find( notSelector ).length === 0,
href = $a.attr( 'href' ),
legacyMatch = href && href.match( /title=([^/&]+)/ ),
match = href && href.match( /[^/]+$/ );
// filter out invalid lazy loaded images if so far image is valid
if ( $lazyImage.length && valid ) {
// if the regex matches it means the image has one of the classes
// thus we must invert the result
valid = !new RegExp( '\\b(' + EXCLUDE_THUMBNAIL_CLASS_SELECTORS.join( '|' ) + ')\\b' )
.test( $lazyImage.data( 'class' ) );
}
if ( valid && ( legacyMatch || match ) ) {
return new Thumbnail( {
el: $a,
filename: mw.util.percentDecodeFragment(
legacyMatch ? legacyMatch[1] : match[0]
)
} );
}
return null;
}
/**
* Return all the thumbnails in the article.
* Images which have a class or link container (.image|.thumbimage)
* that matches one of the items of the constant EXCLUDE_THUMBNAIL_CLASS_SELECTORS
* will be excluded.
* A thumbnail nested inside one of these classes will still be returned.
* e.g. `<div class="noviewer"><a class="image"><img></a></div>` is not a valid thumbnail
* `<a class="image noviewer"><img></a>` is not a valid thumbnail
* `<a class="image"><img class="noviewer"></a>` is not a valid thumbnail
*
* @param {jQuery} [$el] Container to search, defaults to this.$el.
* @return {Thumbnail[]}
*/
getThumbnails( $el ) {
var
self = this,
$thumbs,
thumbs = [];
$el = $el || this.$el;
$thumbs = $el.find( THUMB_SELECTOR );
$thumbs.each( function () {
var $a = $el.find( this );
var thumb = self.getThumbnail( $a );
if ( thumb ) {
thumbs.push( thumb );
}
} );
return thumbs;
}
/**
* Returns a jQuery object representing all redlinks on the page.
*
* @return {jQuery.Object}
*/
getRedLinks() {
return this.$el.find( '.new' );
}
/**
* Returns an object consistent with MediaWiki API representing languages
* associated with the page in the user's current language.
*
* @param {string} pageTitle to fallback to if none found
* @return {Object} containing langlinks
* and variant links as defined @ https://en.m.wikipedia.org/w/api.php?action=help&modules=query%2Blanglinks
*/
getLanguages( pageTitle ) {
const mapLinkToLanguageObj = ( node ) => {
const DELIMITER = ' – ';
// Name of language (e.g. עברית for Hebrew)
const autonym = node.textContent;
// The name of the language in the current language
// e.g. for english this would be Hebrew
let langname;
let title = node.getAttribute( 'title' ) || pageTitle;
if ( title.indexOf( DELIMITER ) > -1 ) {
title = title.split( DELIMITER );
langname = title.pop();
title = title.join( DELIMITER );
}
if ( !langname ) {
langname = autonym;
}
return {
lang: node.getAttribute( 'hreflang' ),
autonym,
langname,
title,
url: node.getAttribute( 'href' )
};
};
return {
languages: Array.prototype.map.call(
document.querySelectorAll( '#p-lang .interlanguage-link a' ),
mapLinkToLanguageObj
),
variants: Array.prototype.map.call(
document.querySelectorAll( '#p-variants li a' ),
mapLinkToLanguageObj
)
};
}
}
/**
* Selector for matching headings
*
* @memberof PageHTMLParser
*/
PageHTMLParser.HEADING_SELECTOR = HEADING_SELECTOR;
/**
* Selector for thumbnails.
*
* @memberof PageHTMLParser
*/
PageHTMLParser.THUMB_SELECTOR = THUMB_SELECTOR;
module.exports = PageHTMLParser;
|