User:Polygnotus/Scripts/FindArticlesWithDuplicateRefs.js

The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Code that you insert on this page could contain malicious content capable of compromising your account. If you import a script from another page with "importScript", "mw.loader.load", "iusc", or "lusc", take note that this causes you to dynamically load a remote script, which could be changed by others. Editors are responsible for all edits and actions they perform, including by scripts. User scripts are not centrally supported and may malfunction or become inoperable due to software changes. A guide to help you find broken scripts is available. If you are unsure whether code you are adding to this page is safe, you can ask at the appropriate village pump.
This code will be executed when previewing this page.

Documentation for this user script can be added at User:Polygnotus/Scripts/FindArticlesWithDuplicateRefs.

Note: After saving, you have to bypass your browser's cache to see the changes. Google Chrome, Firefox, Microsoft Edge and Safari: Hold down the ⇧ Shift key and click the Reload toolbar button. For details and instructions about other browsers, see Wikipedia:Bypass your cache.

 //needed for testing DeduplicateReferences.js
 // Wikipedia Duplicate Reference Finder for common.js
 // Adds a tool to search for articles with exact duplicate references

 $(document).ready(function(){
 // Only run on Wikipedia
 if(mw.config.get('wgSiteName')!=='Wikipedia')return;

 // Add portlet link to toolbox
 mw.util.addPortletLink(
 'p-tb',
 '#',
 'Find Duplicate Refs',
 'find-duplicate-refs',
 'Search for articles with duplicate references'
 );

 // Add the search interface
 $('#find-duplicate-refs').click(function(e){
 e.preventDefault();
 showDuplicateRefFinder();
 });

 functionshowDuplicateRefFinder(){
 // Remove existing dialog if present
 $('#duplicate-ref-finder').remove();

 // Create the search interface
 constdialog=$(`
  <div id="duplicate-ref-finder" style="
  position: fixed;
  top: 50px;
  right: 20px;
  width: 400px;
  background: white;
  border: 2px solid #0645ad;
  border-radius: 5px;
  padding: 15px;
  box-shadow: 0 4px 8px rgba(0,0,0,0.2);
  z-index: 1000;
  font-family: sans-serif;
  ">
  <h3 style="margin-top: 0; color: #0645ad;">Duplicate Reference Finder</h3>

  <div style="margin-bottom: 10px;">
  <label>Search Method:</label><br>
  <input type="radio" name="searchMethod" value="random" id="method-random" checked>
  <label for="method-random">Random articles</label><br>
  <input type="radio" name="searchMethod" value="category" id="method-category">
  <label for="method-category">From category</label><br>
  <input type="radio" name="searchMethod" value="search" id="method-search">
  <label for="method-search">Search term</label>
  </div>

  <div id="search-input" style="margin-bottom: 10px; display: none;">
  <input type="text" id="search-term" placeholder="Enter search term or category" style="width: 100%; padding: 5px;">
  </div>

  <div style="margin-bottom: 10px;">
  <label>Min references to check: </label>
  <input type="number" id="min-refs" value="10" min="5" max="100" style="width: 60px;">
  </div>

  <div style="margin-bottom: 15px;">
  <button id="start-search" style="background: #0645ad; color: white; padding: 8px 15px; border: none; border-radius: 3px; cursor: pointer;">Start Search</button>
  <button id="stop-search" style="background: #d33; color: white; padding: 8px 15px; border: none; border-radius: 3px; cursor: pointer; margin-left: 5px;" disabled>Stop</button>
  <button id="close-finder" style="float: right; background: #666; color: white; padding: 8px 15px; border: none; border-radius: 3px; cursor: pointer;">Close</button>
  </div>

  <div id="search-status" style="margin-bottom: 10px; font-weight: bold;"></div>
  <div id="search-progress" style="margin-bottom: 10px;"></div>
  <div id="results" style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; background: #f9f9f9;"></div>
  </div>
  `);

 $('body').append(dialog);

 // Event handlers
 $('input[name="searchMethod"]').change(function(){
 if($(this).val()==='random'){
 $('#search-input').hide();
 }else{
 $('#search-input').show();
 $('#search-term').attr('placeholder',
 $(this).val()==='category'?'Enter category name (e.g., "Living people")':'Enter search term'
 );
 }
 });

 $('#close-finder').click(()=>$('#duplicate-ref-finder').remove());

 letsearchActive=false;
 letsearchAborted=false;

 // Make searchAborted accessible to the performSearch function
 window.currentSearchAborted=false;

 $('#start-search').click(asyncfunction(){
 if(searchActive)return;

 searchActive=true;
 window.currentSearchAborted=false;
 $(this).prop('disabled',true);
 $('#stop-search').prop('disabled',false);
 $('#results').empty();
 $('#search-status').text('Starting search...');

 try{
 awaitperformSearch();
 }catch(error){
 $('#search-status').text('Search error: '+error.message);
 }

 searchActive=false;
 $('#start-search').prop('disabled',false);
 $('#stop-search').prop('disabled',true);
 });

 $('#stop-search').click(function(){
 window.currentSearchAborted=true;
 $('#search-status').text('Search stopped by user.');
 });
 }

 asyncfunctionperformSearch(){
 constmethod=$('input[name="searchMethod"]:checked').val();
 constminRefs=parseInt($('#min-refs').val())||10;
 constsearchTerm=$('#search-term').val();

 letarticles=[];

 // Get list of articles to check
 if(method==='random'){
 articles=awaitgetRandomArticles(50);
 }elseif(method==='category'&&searchTerm){
 articles=awaitgetCategoryArticles(searchTerm,50);
 }elseif(method==='search'&&searchTerm){
 articles=awaitgetSearchResults(searchTerm,50);
 }else{
 $('#search-status').text('Please enter a search term or category.');
 return;
 }

 if(articles.length===0){
 $('#search-status').text('No articles found to check.');
 return;
 }

 $('#search-status').text(`Checking ${articles.length} articles...`);

 letcheckedCount=0;
 letfoundCount=0;

 for(constarticleofarticles){
 if(window.currentSearchAborted)break;

 checkedCount++;
 $('#search-progress').text(`Checked: ${checkedCount}/${articles.length} | Found: ${foundCount}`);

 try{
 constduplicateCount=awaitcheckArticleForDuplicates(article.title,minRefs);
 if(duplicateCount>0){
 foundCount++;
 addResult(article.title,duplicateCount);
 }
 }catch(error){
 console.log(`Error checking ${article.title}:`,error);
 }

 // Small delay to avoid overwhelming the API
 awaitnewPromise(resolve=>setTimeout(resolve,200));
 }

 $('#search-status').text(`Search complete! Checked ${checkedCount} articles, found ${foundCount} with duplicates.`);
 }

 asyncfunctiongetRandomArticles(count){
 constapi=newmw.Api();
 constresult=awaitapi.get({
 action:'query',
 list:'random',
 rnnamespace:0,// Main namespace only
 rnlimit:count,
 format:'json'
 });
 returnresult.query.random;
 }

 asyncfunctiongetCategoryArticles(category,count){
 constapi=newmw.Api();
 // Remove "Category:" prefix if present
 category=category.replace(/^Category:/,'');

 constresult=awaitapi.get({
 action:'query',
 list:'categorymembers',
 cmtitle:'Category:'+category,
 cmnamespace:0,// Main namespace only
 cmlimit:count,
 format:'json'
 });
 returnresult.query.categorymembers;
 }

 asyncfunctiongetSearchResults(term,count){
 constapi=newmw.Api();
 constresult=awaitapi.get({
 action:'query',
 list:'search',
 srsearch:term,
 srnamespace:0,// Main namespace only
 srlimit:count,
 format:'json'
 });
 returnresult.query.search;
 }

 asyncfunctioncheckArticleForDuplicates(title,minRefs){
 constapi=newmw.Api();

 // Get the article content
 constresult=awaitapi.get({
 action:'query',
 titles:title,
 prop:'revisions',
 rvprop:'content',
 rvslots:'main',
 format:'json'
 });

 constpages=result.query.pages;
 constpageId=Object.keys(pages)[0];
 constpage=pages[pageId];

 if(!page.revisions||!page.revisions[0]){
 return0;
 }

 constcontent=page.revisions[0].slots.main['*'];

 // Extract all <ref> tags
 constrefRegex=/<ref[^>]*>[\s\S]*?<\/ref>/gi;
 constrefs=content.match(refRegex)||[];

 if(refs.length<minRefs){
 return0;
 }

 // Count duplicates
 constrefCounts={};
 letduplicateCount=0;

 refs.forEach(ref=>{
 // Normalize whitespace for comparison
 constnormalizedRef=ref.replace(/\s+/g,' ').trim();
 if(refCounts[normalizedRef]){
 refCounts[normalizedRef]++;
 if(refCounts[normalizedRef]===2){
 duplicateCount++;// First time we see a duplicate
 }
 }else{
 refCounts[normalizedRef]=1;
 }
 });

 returnduplicateCount;
 }

 functionaddResult(title,duplicateCount){
 consteditUrl=`/w/index.php?title=${encodeURIComponent(title)}&action=edit`;
 constviewUrl=`/wiki/${encodeURIComponent(title)}`;

 constresultHtml=`
  <div style="margin-bottom: 10px; padding: 8px; border: 1px solid #ddd; border-radius: 3px; background: white;">
  <strong><a href="${viewUrl}" target="_blank">${mw.html.escape(title)}</a></strong><br>
  <span style="color: #d33;">${duplicateCount} duplicate reference${duplicateCount>1?'s':''}</span><br>
  <a href="${editUrl}" target="_blank" style="color: #0645ad;">Edit article</a>
  </div>
  `;

 $('#results').append(resultHtml);

 // Auto-scroll to bottom
 constresultsDiv=$('#results')[0];
 resultsDiv.scrollTop=resultsDiv.scrollHeight;
 }
 });

Retrieved from "https://en.wikipedia.org/w/index.php?title=User:Polygnotus/Scripts/FindArticlesWithDuplicateRefs.js&oldid=1295036553"