joplin/Clipper/joplin-webclipper/content_scripts/Readability-readerable.js

// https://github.com/mozilla/readability/tree/814f0a3884350b6f1adfdebb79ca3599e9806605

/* eslint-env es6:false */
/* globals exports */
/*
 * Copyright (c) 2010 Arc90 Inc
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

/*
 * This code is heavily based on Arc90's readability.js (1.7.1) script
 * available at: http://code.google.com/p/arc90labs-readability
 */

var REGEXPS = {
	// NOTE: These two regular expressions are duplicated in
	// Readability.js. Please keep both copies in sync.
	unlikelyCandidates: /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i,
	okMaybeItsACandidate: /and|article|body|column|main|shadow/i,
};

function isNodeVisible(node) {
	// Have to null-check node.style to deal with SVG and MathML nodes.
	return (!node.style || node.style.display != 'none') && !node.hasAttribute('hidden');
}

/**
 * Decides whether or not the document is reader-able without parsing the whole thing.
 *
 * @return boolean Whether or not we suspect Readability.parse() will suceeed at returning an article object.
 */
function isProbablyReaderable(doc, isVisible) {
	if (!isVisible) {
		isVisible = isNodeVisible;
	}

	var nodes = doc.querySelectorAll('p, pre');

	// Get <div> nodes which have <br> node(s) and append them into the `nodes` variable.
	// Some articles' DOM structures might look like
	// <div>
	//   Sentences<br>
	//   <br>
	//   Sentences<br>
	// </div>
	var brNodes = doc.querySelectorAll('div > br');
	if (brNodes.length) {
		var set = new Set(nodes);
		[].forEach.call(brNodes, function(node) {
			set.add(node.parentNode);
		});
		nodes = Array.from(set);
	}

	var score = 0;
	// This is a little cheeky, we use the accumulator 'score' to decide what to return from
	// this callback:
	return [].some.call(nodes, function(node) {
		if (!isVisible(node))
			return false;

		var matchString = node.className + ' ' + node.id;
		if (REGEXPS.unlikelyCandidates.test(matchString) &&
        !REGEXPS.okMaybeItsACandidate.test(matchString)) {
			return false;
		}

		if (node.matches('li p')) {
			return false;
		}

		var textContentLength = node.textContent.trim().length;
		if (textContentLength < 140) {
			return false;
		}

		score += Math.sqrt(textContentLength - 140);

		if (score > 20) {
			return true;
		}
		return false;
	});
}

if (typeof exports === 'object') {
	exports.isProbablyReaderable = isProbablyReaderable;
}