Issue 3143 - Filter elements with :-abp-has()

chrome/content/elemHideEmulation.js

Index: chrome/content/elemHideEmulation.js
===================================================================
--- a/chrome/content/elemHideEmulation.js
+++ b/chrome/content/elemHideEmulation.js
@@ -1,12 +1,15 @@
 // We are currently limited to ECMAScript 5 in this file, because it is being
 // used in the browser tests. See https://issues.adblockplus.org/ticket/4796
 
-var propertySelectorRegExp = /\[\-abp\-properties=(["'])([^"']+)\1\]/;
+var propertySelectorRegExp = /\[-abp-properties=(["'])([^"']+)\1\]/;
+var abpSelectorRegExp = /\[-abp-selector=(["'])(.+)\1\]/;
+var pseudoClassHasSelectorRegExp = /:has\((.*)\)/;
+var pseudoClassPropsSelectorRegExp = /:-abp-properties\((["'])([^"']+)\1\)/;
 
 function splitSelector(selector)
 {
   if (selector.indexOf(",") == -1)
     return [selector];
 
   var selectors = [];
   var start = 0;
@@ -36,132 +39,332 @@
       }
     }
   }
 
   selectors.push(selector.substring(start));
   return selectors;
 }
 
-function ElemHideEmulation(window, getFiltersFunc, addSelectorsFunc)
+const ABP_ATTR = "abp-0ac791f0-a03b-4f2c-a935-a285bc2e668e";
+const ABP_ATTR_SEL = "[" + ABP_ATTR + "] ";
+
+function matchChildren(e, selector)
+{
+  var subElement;
+  var newSelector = ABP_ATTR_SEL + selector;
+  var parentNode = e.parentNode || document;
+
+  e.setAttribute(ABP_ATTR, "");
+  subElement = parentNode.querySelector(newSelector);
+  e.removeAttribute(ABP_ATTR);
+
+  return subElement != null;
+}
+
+function selectChildren(e, selector)
+{
+  var subElements;
+  var newSelector = ABP_ATTR_SEL + selector;
+  var parentNode = e.parentNode || document;
+
+  e.setAttribute(ABP_ATTR, "");
+  subElements = parentNode.querySelectorAll(newSelector);
+  e.removeAttribute(ABP_ATTR);
+
+  return subElements;
+}
+
+/** Unwrap the pattern out of a [-abp-selector=''] if necessary
+ * @param {object} pattern - The pattern object to unwrap
+ * @return {object} the parsed pattern object or undefined if nothing parse.
+ */
+function unwrapPattern(pattern)
+{
+  var match = abpSelectorRegExp.exec(pattern.selector);
+  if (match)
+  {
+    var prefix = pattern.selector.substr(0, match.index).trim();
+    var suffix = pattern.selector.substr(match.index + match[0].length).trim();
+    var selector = prefix + match[2] + suffix;
+    return parsePattern({selector: selector});
+  }
+
+  return parsePattern(pattern);
+}
+
+function parsePattern(pattern)
+{
+  var selector = pattern.selector;
+
+  var match = pseudoClassHasSelectorRegExp.exec(selector);

[Felix Dahlke, 2017/04/10 10:55:12]

How I understand the code, :has and :-abp-properties would work outside
[-abp-selector]. I think that shouldn't be possible - otherwise filter list
authors might opt for the more convenient approach of leaving [-abp-selector]
out.

[hub, 2017/04/10 12:29:27]

My question is do we still support [-abp-properties=] after this?
OTOH I'll make sure a lonely :has() is rejected.

[Felix Dahlke, 2017/04/10 12:35:41]

Lonely :-abp-properties (pseudo class syntax!) should also not work, same as
:has.

As for [-abp-properties] (attribute syntax): Yeah I think we need to support it
at least until the lists we are aware of stopped using it in favour of
[-abp-selector].

[hub, 2017/04/10 12:41:02]

Ah right. The pseudo class syntax. Good catch.

+  if (match)
+    return {
+      type: "has",
+      text: pattern.text,
+      elementMatcher: new PseudoHasMatcher(match[1]),
+      prefix: selector.substr(0, match.index).trim(),
+      suffix: selector.substr(match.index + match[0].length).trim()
+    };
+
+  match = pseudoClassPropsSelectorRegExp.exec(selector);
+  if (!match)
+    match = propertySelectorRegExp.exec(selector);
+  if (match)
+  {
+    var regexpString;
+    var propertyExpression = match[2];
+    if (propertyExpression.length >= 2 && propertyExpression[0] == "/" &&
+        propertyExpression[propertyExpression.length - 1] == "/")
+      regexpString = propertyExpression.slice(1, -1)
+      .replace("\\x7B ", "{").replace("\\x7D ", "}");
+    else
+      regexpString = filterToRegExp(propertyExpression);
+    return {
+      type: "props",
+      text: pattern.text,
+      regexp: new RegExp(regexpString, "i"),
+      prefix: selector.substr(0, match.index),
+      suffix: selector.substr(match.index + match[0].length)
+    };
+  }
+}
+
+function matchStyleProps(style, rule, pattern, selectors, filters)
+{
+  if (pattern.regexp.test(style))
+  {
+    var subSelectors = splitSelector(rule.selectorText);
+    for (var i = 0; i < subSelectors.length; i++)
+    {
+      var subSelector = subSelectors[i];
+      selectors.push(pattern.prefix + subSelector + pattern.suffix);
+      filters.push(pattern.text);
+    }
+  }
+}
+
+function findPropsSelectors(stylesheet, patterns, selectors, filters)
+{
+  var rules = stylesheet.cssRules;
+  if (!rules)
+    return;
+
+  for (var i = 0; i < rules.length; i++)
+  {
+    var rule = rules[i];
+    if (rule.type != rule.STYLE_RULE)
+      continue;
+
+    var style = stringifyStyle(rule.style);
+    for (var j = 0; j < patterns.length; j++)
+    {
+      matchStyleProps(style, rule, patterns[j], selectors, filters);
+    }
+  }
+}
+
+/**
+ * Match the selector @pattern containing :has() starting from @node.
+ * @param {string} pattern - the pattern to match
+ * @param {object} node - the top level node.
+ */
+function pseudoClassHasMatch(pattern, node, stylesheets, elements, filters)
+{
+  // select element for the prefix pattern. Or just use node.
+  var haveEl = pattern.prefix ? node.querySelectorAll(pattern.prefix) : [ node ];
+  for (var j = 0; j < haveEl.length; j++)
+  {
+    var matched = pattern.elementMatcher.match(haveEl[j], stylesheets);
+    if (!matched)
+      continue;
+
+    if (pattern.suffix)
+    {
+      var subElements = selectChildren(haveEl[j], pattern.suffix);
+      if (subElements)
+      {
+        for (var k = 0; k < subElements.length; k++)
+        {
+          elements.push(subElements[k]);
+          filters.push(pattern.text);
+        }
+      }
+    }
+    else
+    {
+      elements.push(haveEl[j]);
+      filters.push(pattern.text);
+    }
+  }
+}
+
+function stringifyStyle(style)
+{
+  var styles = [];
+  for (var i = 0; i < style.length; i++)
+  {
+    var property = style.item(i);
+    var value = style.getPropertyValue(property);
+    var priority = style.getPropertyPriority(property);
+    styles.push(property + ": " + value + (priority ? " !" + priority : "") + ";");
+  }
+  styles.sort();
+  return styles.join(" ");
+}
+
+/** matcher for the pseudo CSS4 class :has()
+ * For those browser that don't have it yet.
+ */
+function PseudoHasMatcher(selector)
+{
+  this.hasSelector = selector;
+  this.parsed = parsePattern({selector: this.hasSelector});
+}
+
+PseudoHasMatcher.prototype = {
+  match: function(elem, stylesheets)
+  {
+    var selectors = [];
+
+    if (this.parsed)
+    {
+      var filters = []; // don't need this, we have a partial filter.
+      if (this.parsed.type == "has")
+      {
+        var child = elem.firstChild;
+        while (child)
+        {
+          if (child.nodeType === Node.ELEMENT_NODE)
+          {
+            var matches = [];
+            pseudoClassHasMatch(this.parsed, child, stylesheets, matches, filters);
+            if (matches.length > 0)
+              return true;
+          }
+          child = child.nextSibling;
+        }
+        return false;
+      }
+      if (this.parsed.type == "props")
+      {
+        for (var i = 0; i < stylesheets.length; i++)
+          findPropsSelectors(stylesheets[i], [this.parsed], selectors, filters);
+      }
+    }
+    else
+    {
+      selectors = [this.hasSelector];
+    }
+
+    var matched = false;
+    // look up for all elements that match the :has().
+    for (var k = 0; k < selectors.length; k++)
+    {
+      try
+      {
+        matched = matchChildren(elem, selectors[k]);
+        if (matched)
+          break;
+      }
+      catch (e)
+      {
+        console.error("Exception with querySelector()", selectors[k], e);
+      }
+    }
+    return matched;
+  }
+};
+
+function ElemHideEmulation(window, getFiltersFunc, addSelectorsFunc, hideElementsFunc)
 {
   this.window = window;
   this.getFiltersFunc = getFiltersFunc;
   this.addSelectorsFunc = addSelectorsFunc;
+  this.hideElementsFunc = hideElementsFunc;
 }
 
 ElemHideEmulation.prototype = {
-  stringifyStyle: function(style)
-  {
-    var styles = [];
-    for (var i = 0; i < style.length; i++)
-    {
-      var property = style.item(i);
-      var value    = style.getPropertyValue(property);
-      var priority = style.getPropertyPriority(property);
-      styles.push(property + ": " + value + (priority ? " !" + priority : "") + ";");
-    }
-    styles.sort();
-    return styles.join(" ");
-  },
 
   isSameOrigin: function(stylesheet)
   {
     try
     {
       return new URL(stylesheet.href).origin == this.window.location.origin;
     }
     catch (e)
     {
       // Invalid URL, assume that it is first-party.
       return true;
     }
   },
 
-  findSelectors: function(stylesheet, selectors, filters)
+  findPseudoClassHasElements: function(node, stylesheets, elements, filters)
   {
-    // Explicitly ignore third-party stylesheets to ensure consistent behavior
-    // between Firefox and Chrome.
-    if (!this.isSameOrigin(stylesheet))
-      return;
-
-    var rules = stylesheet.cssRules;
-    if (!rules)
-      return;
-
-    for (var i = 0; i < rules.length; i++)
+    for (var i = 0; i < this.pseudoHasPatterns.length; i++)
     {
-      var rule = rules[i];
-      if (rule.type != rule.STYLE_RULE)
-        continue;
-
-      var style = this.stringifyStyle(rule.style);
-      for (var j = 0; j < this.patterns.length; j++)
-      {
-        var pattern = this.patterns[j];
-        if (pattern.regexp.test(style))
-        {
-          var subSelectors = splitSelector(rule.selectorText);
-          for (var k = 0; k < subSelectors.length; k++)
-          {
-            var subSelector = subSelectors[k];
-            selectors.push(pattern.prefix + subSelector + pattern.suffix);
-            filters.push(pattern.text);
-          }
-        }
-      }
+      pseudoClassHasMatch(this.pseudoHasPatterns[i], node, stylesheets, elements, filters);
     }
   },
 
   addSelectors: function(stylesheets)
   {
     var selectors = [];
     var filters = [];
     for (var i = 0; i < stylesheets.length; i++)
-      this.findSelectors(stylesheets[i], selectors, filters);
+    {
+      // Explicitly ignore third-party stylesheets to ensure consistent behavior
+      // between Firefox and Chrome.
+      if (!this.isSameOrigin(stylesheets[i]))
+        continue;
+      findPropsSelectors(stylesheets[i], this.propSelPatterns, selectors, filters);
+    }
     this.addSelectorsFunc(selectors, filters);
   },
 
+  hideElements: function(stylesheets)
+  {
+    var elements = [];
+    var filters = [];
+    this.findPseudoClassHasElements(document, stylesheets, elements, filters);
+    this.hideElementsFunc(elements, filters);
+  },
+
   onLoad: function(event)
   {
     var stylesheet = event.target.sheet;
     if (stylesheet)
       this.addSelectors([stylesheet]);
+    this.hideElements([stylesheet]);
   },
 
   apply: function()
   {
     this.getFiltersFunc(function(patterns)
     {
-      this.patterns = [];
+      this.propSelPatterns = [];
+      this.pseudoHasPatterns = [];
       for (var i = 0; i < patterns.length; i++)
       {
         var pattern = patterns[i];
-        var match = propertySelectorRegExp.exec(pattern.selector);
-        if (!match)
+        var parsed = unwrapPattern(pattern);
+        if (parsed == undefined)
           continue;
-
-        var propertyExpression = match[2];
-        var regexpString;
-        if (propertyExpression.length >= 2 && propertyExpression[0] == "/" &&
-            propertyExpression[propertyExpression.length - 1] == "/")
-          regexpString = propertyExpression.slice(1, -1)
-              .replace("\\x7B ", "{").replace("\\x7D ", "}");
-        else
-          regexpString = filterToRegExp(propertyExpression);
-
-        this.patterns.push({
-          text: pattern.text,
-          regexp: new RegExp(regexpString, "i"),
-          prefix: pattern.selector.substr(0, match.index),
-          suffix: pattern.selector.substr(match.index + match[0].length)
-        });
+        if (parsed.type == "props")
+        {
+          this.propSelPatterns.push(parsed);
+        }
+        else if (parsed.type == "has")
+        {
+          this.pseudoHasPatterns.push(parsed);
+        }
       }
 
-      if (this.patterns.length > 0)
+      if (this.pseudoHasPatterns.length > 0 || this.propSelPatterns.length > 0)
       {
         var document = this.window.document;
         this.addSelectors(document.styleSheets);
+        this.hideElements(document.styleSheets);
         document.addEventListener("load", this.onLoad.bind(this), true);
       }
     }.bind(this));
   }
 };