Remove aria-hidden="true" nodes (fixes #541) (#555)

Remove aria-hidden="true" nodes (fixes #541)
5 years ago · 60f470c4bb
parent 2982216913
commit 60f470c4bb
5 changed files with 37 additions and 2 deletions
--- a/Readability-readerable.js
+++ b/Readability-readerable.js
@ -30,7 +30,8 @@ var REGEXPS = {

 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");
+  return (!node.style || node.style.display != "none") && !node.hasAttribute("hidden")
+    && (!node.hasAttribute("aria-hidden") || node.getAttribute("aria-hidden") != "true");
 }

 /**
--- a/Readability.js
+++ b/Readability.js
@ -1786,7 +1786,9 @@ Readability.prototype = {
  },

  _isProbablyVisible: function(node) {
-    return (!node.style || node.style.display != "none") && !node.hasAttribute("hidden");
+    return (!node.style || node.style.display != "none")
+      && !node.hasAttribute("hidden")
+      && (!node.hasAttribute("aria-hidden") || node.getAttribute("aria-hidden") != "true");
  },

  /**
--- a/test/test-pages/remove-aria-hidden/expected-metadata.json
+++ b/test/test-pages/remove-aria-hidden/expected-metadata.json
@ -0,0 +1,7 @@
+{
+  "title": "Remove aria-hidden elements test",
+  "byline": null,
+  "excerpt": "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n        tempor incididunt ut labore et dolore magna aliqua.",
+  "readerable": false,
+  "siteName": null
+}
--- a/test/test-pages/remove-aria-hidden/expected.html
+++ b/test/test-pages/remove-aria-hidden/expected.html
@ -0,0 +1,6 @@
+<div id="readability-page-1" class="page">
+    <div>
+        <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.</p>
+        <p>Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.</p>
+    </div>    
+</div>
--- a/test/test-pages/remove-aria-hidden/source.html
+++ b/test/test-pages/remove-aria-hidden/source.html
@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html>
+<head>
+  <meta charset="utf-8"/>
+  <title>Remove aria-hidden elements test</title>
+</head>
+<body>  
+  <article>
+    <h1>Lorem</h1>
+    <div>      
+      <p><span aria-hidden="true">**WRONG**</span>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+        tempor incididunt ut labore et dolore magna aliqua.</p>
+      <p>Ut enim ad minim veniam,
+      quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+      consequat.</p>      
+    </div>    
+  </article>
+</body>
+</html>