diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
commit | 36d22d82aa202bb199967e9512281e9a53db42c9 (patch) | |
tree | 105e8c98ddea1c1e4784a60a5a6410fa416be2de /toolkit/components/reader/Readability-readerable.js | |
parent | Initial commit. (diff) | |
download | firefox-esr-36d22d82aa202bb199967e9512281e9a53db42c9.tar.xz firefox-esr-36d22d82aa202bb199967e9512281e9a53db42c9.zip |
Adding upstream version 115.7.0esr.upstream/115.7.0esr
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'toolkit/components/reader/Readability-readerable.js')
-rw-r--r-- | toolkit/components/reader/Readability-readerable.js | 116 |
1 files changed, 116 insertions, 0 deletions
diff --git a/toolkit/components/reader/Readability-readerable.js b/toolkit/components/reader/Readability-readerable.js new file mode 100644 index 0000000000..fe9c89d789 --- /dev/null +++ b/toolkit/components/reader/Readability-readerable.js @@ -0,0 +1,116 @@ +/* eslint-env es6:false */ +/* globals exports */ +/* + * DO NOT MODIFY THIS FILE DIRECTLY! + * + * This is a shared library that is maintained in an external repo: + * https://github.com/mozilla/readability + */ + +/* + * 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|footer|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|content|main|shadow/i, +}; + +function isNodeVisible(node) { + // Have to null-check node.style and node.className.indexOf to deal with SVG and MathML nodes. + return (!node.style || node.style.display != "none") + && !node.hasAttribute("hidden") + //check for "fallback-image" so that wikimedia math images are displayed + && (!node.hasAttribute("aria-hidden") || node.getAttribute("aria-hidden") != "true" || (node.className && node.className.indexOf && node.className.indexOf("fallback-image") !== -1)); +} + +/** + * Decides whether or not the document is reader-able without parsing the whole thing. + * @param {Object} options Configuration object. + * @param {number} [options.minContentLength=140] The minimum node content length used to decide if the document is readerable. + * @param {number} [options.minScore=20] The minumum cumulated 'score' used to determine if the document is readerable. + * @param {Function} [options.visibilityChecker=isNodeVisible] The function used to determine if a node is visible. + * @return {boolean} Whether or not we suspect Readability.parse() will suceeed at returning an article object. + */ +function isProbablyReaderable(doc, options = {}) { + // For backward compatibility reasons 'options' can either be a configuration object or the function used + // to determine if a node is visible. + if (typeof options == "function") { + options = { visibilityChecker: options }; + } + + var defaultOptions = { minScore: 20, minContentLength: 140, visibilityChecker: isNodeVisible }; + options = Object.assign(defaultOptions, options); + + var nodes = doc.querySelectorAll("p, pre, article"); + + // 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 (!options.visibilityChecker(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 < options.minContentLength) { + return false; + } + + score += Math.sqrt(textContentLength - options.minContentLength); + + if (score > options.minScore) { + return true; + } + return false; + }); +} + +if (typeof module === "object") { + module.exports = isProbablyReaderable; +} |