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

chrome/content/elemHideEmulation.js

 // 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 pseudoClassHasSelectorRegExp = /:has\((.*)\)/;
+
+// polyfill. We should deal with this better, but PhantomJS doesn't
+// have matches. At least not in the version we use.
+// Chrome 34, Firefox 34, Opera 21 and Safari 7.1 do have it.
+if (!Element.prototype.matches) {
+  Element.prototype.matches =
+    Element.prototype.matchesSelector ||
+    Element.prototype.mozMatchesSelector ||

[Sebastian Noack, 2017/03/29 07:46:19]

These fallbacks seem unnecessary. We only support Firefox >=38. Chrome >=49 as
well as the respective version of Opera, and Microsoft Edge, with this code.
Safari and Internet Explorer doesn't need to be considered here at all.

[hub, 2017/03/29 14:00:00]

I need at least the webkit one for PhantomJS, otherwise the test will never
pass. This until we fix issue #4796

+    Element.prototype.msMatchesSelector ||
+    Element.prototype.oMatchesSelector ||
+    Element.prototype.webkitMatchesSelector
+}
+
+// return the index were the simple-selector ends
+function findFirstSelector(selector)
+{
+  var sepIndex = selector.indexOf(' ');
+  var nextIndex = selector.indexOf('>');
+  if (nextIndex != -1)
+    sepIndex = sepIndex == -1 ? nextIndex : Math.min(sepIndex, nextIndex);
+  nextIndex = selector.indexOf('+');
+  if (nextIndex != -1)
+    sepIndex = sepIndex == -1 ? nextIndex : Math.min(sepIndex, nextIndex);
+  nextIndex = selector.indexOf('~');
+  if (nextIndex != -1)
+    sepIndex = sepIndex == -1 ? nextIndex : Math.min(sepIndex, nextIndex);
+  return sepIndex;

[Sebastian Noack, 2017/03/29 07:46:19]

There is a lot of duplication above. How about using a loop, or a function, for
the repeated logic? Or just a regular expression (assuming that it doesn't have
too bad performance implications)?

[hub, 2017/03/29 14:00:00]

Done

+}
+
+function extractFirstSelector(selector)
+{
+  var sepIndex = findFirstSelector(selector);
+
+  if (sepIndex == -1)
+    return selector;
+
+  return selector.substr(0, sepIndex);
+}
 
 function splitSelector(selector)
 {
   if (selector.indexOf(",") == -1)
     return [selector];
 
   var selectors = [];
   var start = 0;
   var level = 0;
   var sep = "";
@@ skipping 19 matching lines @@
         selectors.push(selector.substring(start, i));
         start = i + 1;
       }
     }
   }
 
   selectors.push(selector.substring(start));
   return selectors;
 }
 
-function ElemHideEmulation(window, getFiltersFunc, addSelectorsFunc)
+function selectChildren(e, selector)
+{
+  var sel = selector;
+  // XXX we should have a more elegant way
+  // also startsWith isn't available in PhantomJS.
+  var combinator = sel.substr(0, 1);
+  var subElements;
+  var nextEl = e;
+  sel = sel.substr(1).trim();
+  switch (combinator)
+  {
+  case ">":
+    subElements = e.querySelectorAll(sel);
+    break;
+
+  case "+":
+    do
+    {
+      nextEl = nextEl.nextSibling;
+    }
+    while (nextEl && nextEl.nodeType != 1);
+
+    var siblingSel = extractFirstSelector(sel);
+    var idx = findFirstSelector(sel);
+    var childSel = idx != -1 ? sel.substr(idx + 1).trim() : "";
+
+    if (nextEl && nextEl.matches(siblingSel))
+    {
+      if (childSel != "")
+        subElements = selectChildren(nextEl, childSel);
+      else
+        subElements = [ nextEl ];
+    }
+    break;
+
+  case "~":
+    do
+    {
+      nextEl = nextEl.nextSibling;
+      if (nextEl && nextEl.nodeType == 1 && nextEl.matches(sel))
+      {
+        subElements = nextEl.querySelectorAll(sel);
+        break;
+      }
+    }
+    while (nextEl);
+
+    break;
+  }
+  return subElements;
+}
+
+function parsePattern(pattern)
+{
+  // we should catch the :has() pseudo class first.
+  var match = pseudoClassHasSelectorRegExp.exec(pattern.selector);
+  if (match)
+  {
+    return {
+      type: "has",
+      text: pattern.text,
+      elementMatcher: new PseudoHasMatcher(match[1]),
+      prefix: pattern.selector.substr(0, match.index).trim(),
+      suffix: pattern.selector.substr(match.index + match[0].length).trim()
+    };
+  }
+
+  match = propertySelectorRegExp.exec(pattern.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: pattern.selector.substr(0, match.index),
+      suffix: pattern.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);
+    }
+  }
+}
+
+function pseudoClassHasMatch(pattern, node, stylesheets, elements, filters)
+{
+  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, !pattern.suffix);
+    if (matched.length == 0)
+      continue;
+
+    if (pattern.suffix)
+    {
+      matched.forEach(function(e)
+      {
+        var subElements = selectChildren(e, 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, firstOnly)
+  {
+    var matches = [];
+    var selectors = [];
+
+    if (this.parsed)
+    {
+      var filters = []; // don't need this

[Sebastian Noack, 2017/03/29 07:46:19]

These are actually needed for the developer tools panel:
https://adblockplus.org/development-builds/bringing-blockable-items-to-chrome...

Previously the filters where passed as second argument to addSelectorsFunc(),
which then if the respective selector matches, where logged into the the
developer tools panel. While for filters using the :has() selector, we don't
call addSelectorsFunc(), we should make sure to report the applied filters (for
the devtools panel) by other means.

[hub, 2017/03/29 14:00:00]

At that level we might be processing fragments of the filter. Line 356 we'll get
the actual filter match that we want for the complete filter.

+      if (this.parsed.type == "has")
+      {
+        pseudoClassHasMatch(this.parsed, elem, stylesheets, matches, filters)
+        return matches;
+      }
+      if (this.parsed.type == "props")
+      {
+        for (var i = 0; i  < stylesheets.length; i++)
+          findPropsSelectors(stylesheets[i], [this.parsed], selectors, filters);
+      }
+    }
+    else
+    {
+      selectors = [this.hasSelector];
+    }
+
+    // look up for all elements that match the :has().
+    for (var k = 0; k < selectors.length; k++)
+    {
+      try
+      {
+        var hasElem = elem.querySelector(selectors[k]);
+        if (hasElem)
+        {
+          matches.push(hasElem);
+          if (firstOnly)
+            break;
+        }
+      }
+      catch(e)
+      {
+        console.log("Exception with querySelector()", selectors[k]);
+      }
+    }
+    return matches;
+  }
+};
+
+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)
-  {
-    // 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++)
-    {
-      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);
-          }
-        }
-      }
+  findPseudoClassHasElements: function(node, stylesheets, elements, filters)
+  {
+    for (var i = 0; i < this.pseudoHasPatterns.length; i++)
+    {
+      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 = parsePattern(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 (this.patterns.length > 0)
+        if (parsed.type == "props")
+        {
+          this.propSelPatterns.push(parsed);
+        }
+        else if (parsed.type == "has")
+        {
+          this.pseudoHasPatterns.push(parsed);
+        }
+      }
+
+      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));
   }
 };