User:Phlsph7/ListUnreferencedParagraphs.js

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.

This user script seems to have a documentation page at User:Phlsph7/ListUnreferencedParagraphs.

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.

(function(){
	const scriptName = 'List Unreferenced Paragraphs';

	$.when(mw.loader.using('mediawiki.util'), $.ready).then(function(){
		const portletlink = mw.util.addPortletLink('p-tb', '#', scriptName, scriptName + 'Id');
		portletlink.onclick = function(e) {
			e.preventDefault();
			openScript();
		};
	});

	function openScript(){
		const timeout = 50;
		let stopProcessing = false;
		const content = document.getElementById('content');
		const contentContainer = content.parentElement;
		content.style.display = 'none';

		let scriptContainer = document.createElement('div');
		contentContainer.appendChild(scriptContainer);
		scriptContainer.outerHTML = `
	<div id="scriptContainer" style="display:flex; flex-direction: column;">
		<style>
			textarea {
				resize: none;
				padding: 5px;
			}
			button {
				margin: 5px;
			}
		</style>
		<h1>Unreferenced Paragraph Counter</h1>
		<div style="display:flex;">
			<div style="flex: 1; display:flex; flex-direction: column; margin: 5px;  height: 50vh; overflow-y: auto;">
				<label for="taList">Article Titles</label>
				<textarea id="taList" style="height: 100%;"></textarea>
			</div>
			<div style="flex: 2; display:flex; flex-direction: column; margin: 5px; height: 50vh; overflow-y: auto;">
				<label for="tableCounter">Overview table</label>
				<table id="tableCounter" class="wikitable" style="height: 100%; margin: 0px; width: 100%; border-collapse: collapse;">
					<thead>
						<tr>
							<th>Article title</th>
							<th>Paragraphs with references / total paragraphs</th>
						</tr>
					</thead>
					<tbody id="tbodyCounter">
					
					</tbody>
				</table>
			</div>
		</div>
		<div style="display:flex; flex-direction: column">
			<div style="display:flex;">
				<button id="btStart" style="flex: 1;">Start</button>
				<button id="btStop" disabled style="flex: 1;">Stop</button>
				<button id="btCopy" style="flex: 1;">Copy</button>
			</div>
			<div>
				<button id="btClose" style="width: 100%;">Close</button>
			</div>
		</div>
	</div>
	`;
		const btStart = $('#btStart');
		btStart.click(function(){
			stopProcessing = false;
			btStart.prop("disabled", true);
			btStop.prop("disabled", false);
			
			let articleTitles = $('#taList').val().trim()
				.split('\r').join('')
				.split('\n');
				
			// remove duplicates
			articleTitles = [...new Set(articleTitles)];
			
			// populate table
			$("#tbodyCounter").empty();
			for(let i = 0; i < articleTitles.length; i++){
				let row = `<tr><td>${articleTitles[i]}</td><td id="td${i}" style="text-align: center;">-</td></tr>`;
				$("#tbodyCounter").append(row);
			}
				
			recursivelyProcessArticles(articleTitles, 0, timeout);
			
		});
		const btStop = $('#btStop');
		btStop.click(function(){
			stopProcessing = true;
			btStart.prop("disabled", false);
			btStop.prop("disabled", true);
		});
		const btCopy = $('#btCopy');
		btCopy.click(function(){
			const tableText =  getTextViaSelection();
			copyToClipboard(tableText);
			alert("The table was copied to the clipboard.");
			
			function getTextViaSelection(){
				const tbodyCounter = $('#tbodyCounter')[0];
				const range = document.createRange();
				range.selectNodeContents(tbodyCounter);

				const selection = window.getSelection();
				selection.removeAllRanges();
				selection.addRange(range);
				return selection.toString();
			}
			
			function copyToClipboard(text) {
				const textarea = document.createElement('textarea');
				textarea.value = text;
				document.body.appendChild(textarea);
				textarea.select();
				document.execCommand('copy');
				document.body.removeChild(textarea);
			}
		});
		const btClose = $('#btClose');
		btClose.click(function(){
			btStop.trigger('click');
			let scriptContainer = document.getElementById('scriptContainer');
			scriptContainer.parentElement.removeChild(scriptContainer);
			content.style.display = '';
		});

		function recursivelyProcessArticles(articleTitles, index, timeout){
			if(!stopProcessing && index < articleTitles.length){
				btStop.text(`Stop (${index}/${articleTitles.length})`);
				const articleTitle = articleTitles[index];
				processArticle(articleTitles, index);
				
				setTimeout(function(){recursivelyProcessArticles(articleTitles, index + 1, timeout);}, timeout);
			}
			else{
				btStop.text(`Stop`);
				btStop.trigger('click');
			}
		}

		function processArticle(articleTitles, index){
			const articleTitle = articleTitles[index];
			const articleSearchTerm = encodeURIComponent(articleTitle);
			let wikiApiUrl = `https://en.wikipedia.org/w/api.php?action=parse&page=${articleSearchTerm}&format=json`;
			fetch(wikiApiUrl).then(async function(response) {
				const data = await response.json();
				let cellId = `td${index}`;
				if (data && data.parse && data.parse.text && data.parse.text['*']) {
					const articleHTML = data.parse.text['*'];
					let count = getParagraphInfo(articleHTML);
					$('#' + cellId).html(count);
				} else {
					$('#' + cellId).html('error');
				}
			});

			function getParagraphInfo(articleHTML){
				const minimalParagraphLength = 100;
				const parser = new DOMParser();
				const doc = parser.parseFromString(articleHTML, 'text/html');
				const paragraphContainer = $(doc).find('.mw-parser-output').eq(0);
				const releventChildren = paragraphContainer.children("p, h2").toArray();
				const articleObject = convertToObject(releventChildren);
				removeIrrelevantSections(articleObject);
				const paragraphsInRelevantSections = convertToSimpleArray(articleObject);
				const longParagraphs = removeShortParagraphs(paragraphsInRelevantSections);
				const unreferencedParagraphs = getUnreferencedParagraphs(longParagraphs);

				return `${unreferencedParagraphs.length} / ${longParagraphs.length}`;

				function convertToObject(elementArray){
					const articleObject = {};
					let currentSection = "Lead";
					articleObject["Lead"] = []; // jshint ignore:line
					
					for(let element of elementArray){
						if(element.tagName === 'H2'){
							currentSection = element.innerText.split('[edit]').join('');
							articleObject[currentSection] = [];
						}
						else{
							articleObject[currentSection].push(element);
						}
					}
					
					return articleObject;
				}

				function removeIrrelevantSections(articleObject){
					const excludedSections = ['Lead', 'Plot', 'Synopsis', 'Further reading', 'See also', 'External links', 'References', 'Bibliography', 'Notes', 'Selected publications', 'Selected works', 'Cited sources', 'Sources', 'Footnotes'];
					for(let sectionName in articleObject){
						if(excludedSections.indexOf(sectionName) != -1){
							delete articleObject[sectionName];
						}
					}
				}

				function convertToSimpleArray(articleObject){
					let array = [];
					for (let sectionName in articleObject){
						array = array.concat(articleObject[sectionName]);
					}
					
					return array;
				}

				function removeShortParagraphs(paragraphArray){
					const longParagraphs = [];
					for(let paragraph of paragraphArray){
						if(paragraph.innerText.length >= minimalParagraphLength){
							longParagraphs.push(paragraph);
						}
					}
					
					return longParagraphs;
				}

				function getUnreferencedParagraphs(paragraphArray){
					const unreferencedParagraph = [];
					for(let paragraph of paragraphArray){
						if(isUnreferenced(paragraph)){
							unreferencedParagraph.push(paragraph);
						}
					}
					return unreferencedParagraph;
					
					function isUnreferenced(paragraph){
						return $(paragraph).find('.reference').length === 0;
					}
				}
			}
		}
	}
})();