Use FrameIsAd to decide whether to isolate a frame in TopDocumentIsolation mode.

chrome/browser/page_load_metrics/observers/ads_page_load_metrics_observer.cc

 // Copyright 2017 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "chrome/browser/page_load_metrics/observers/ads_page_load_metrics_observer.h"
 
 #include <string>
 #include <utility>
 
 #include "base/feature_list.h"
 #include "base/logging.h"
 #include "base/memory/ptr_util.h"
 #include "base/strings/string_util.h"
+#include "chrome/browser/page_load_metrics/observers/ads_detection.h"
 #include "chrome/browser/page_load_metrics/page_load_metrics_util.h"
 #include "content/public/browser/navigation_handle.h"
 #include "content/public/browser/render_frame_host.h"
 #include "content/public/browser/web_contents.h"
 #include "url/gurl.h"
 
 namespace {
 
 const base::Feature kAdsFeature{"AdsMetrics", base::FEATURE_ENABLED_BY_DEFAULT};
 
-bool FrameIsAd(content::NavigationHandle* navigation_handle) {
-  // Because sub-resource filtering isn't always enabled, and doesn't work
-  // well in monitoring mode (no CSS enforcement), it's difficult to identify
-  // ads. Google ads are prevalent and easy to track, so we'll start by
-  // tracking those. Note that the frame name can be very large, so be careful
-  // to avoid full string searches if possible.
-  // TODO(jkarlin): Track other ad networks that are easy to identify.
-
+bool IsAdFrame(content::NavigationHandle* navigation_handle) {
   // In case the navigation aborted, look up the RFH by the Frame Tree Node
   // ID. It returns the committed frame host or the initial frame host for the
   // frame if no committed host exists. Using a previous host is fine because
   // once a frame has an ad we always consider it to have an ad.
   // We use the unsafe method of FindFrameByFrameTreeNodeId because we're not
   // concerned with which process the frame lives on (we're just measuring
   // bytes and not granting security priveleges).
   content::RenderFrameHost* current_frame_host =
       navigation_handle->GetWebContents()->UnsafeFindFrameByFrameTreeNodeId(
           navigation_handle->GetFrameTreeNodeId());
-  if (current_frame_host) {
-    const std::string& frame_name = current_frame_host->GetFrameName();
-    if (base::StartsWith(frame_name, "google_ads_iframe",
-                         base::CompareCase::SENSITIVE) ||
-        base::StartsWith(frame_name, "google_ads_frame",
-                         base::CompareCase::SENSITIVE)) {
-      return true;
-    }
-  }
 
-  const GURL& url = navigation_handle->GetURL();
-  return url.host_piece() == "tpc.googlesyndication.com" &&
-         base::StartsWith(url.path_piece(), "/safeframe",
-                          base::CompareCase::SENSITIVE);
+  return IsAdFrame(current_frame_host ? current_frame_host->GetFrameName() : "",
+                   navigation_handle->GetURL());
 }
 
 void RecordParentExistsForSubFrame(bool parent_exists) {
   UMA_HISTOGRAM_BOOLEAN("PageLoad.Clients.Ads.Google.ParentExistsForSubFrame",
                         parent_exists);
 }
 
 }  // namespace
 
 AdsPageLoadMetricsObserver::AdFrameData::AdFrameData(
@@ skipping 41 matching lines @@
   if (id_and_data != ad_frames_data_.end()) {
     // An existing subframe is navigating again.
     if (id_and_data->second) {
       // The subframe was an ad to begin with, keep tracking it as an ad.
       ProcessOngoingNavigationResource(frame_tree_node_id);
 
       if (frame_tree_node_id == id_and_data->second->frame_tree_node_id) {
         // This is the top-most frame in the ad.
         UMA_HISTOGRAM_BOOLEAN(
             "PageLoad.Clients.Ads.Google.Navigations.AdFrameRenavigatedToAd",
-            FrameIsAd(navigation_handle));
+            IsAdFrame(navigation_handle));
       }
       return;
     }
     // This frame was previously not an ad, process it as usual. If it had
     // any child frames that were ads, those will still be recorded.
     UMA_HISTOGRAM_BOOLEAN(
         "PageLoad.Clients.Ads.Google.Navigations.NonAdFrameRenavigatedToAd",
-        FrameIsAd(navigation_handle));
+        IsAdFrame(navigation_handle));
   }
 
   // Determine who the parent frame's ad ancestor is.
   const auto& parent_id_and_data =
       ad_frames_data_.find(parent_frame_host->GetFrameTreeNodeId());
   if (parent_id_and_data == ad_frames_data_.end()) {
     // We don't know who the parent for this frame is. One possibility is that
     // it's a frame from a previous navigation.
     RecordParentExistsForSubFrame(false /* parent_exists */);
 
     return;
   }
   RecordParentExistsForSubFrame(true /* parent_exists */);
 
   AdFrameData* ad_data = parent_id_and_data->second;
 
-  if (!ad_data && FrameIsAd(navigation_handle)) {
+  if (!ad_data && IsAdFrame(navigation_handle)) {
     // This frame is not nested within an ad frame but is itself an ad.
     ad_frames_data_storage_.emplace_back(frame_tree_node_id);
     ad_data = &ad_frames_data_storage_.back();
   }
 
   ad_frames_data_[frame_tree_node_id] = ad_data;
 
   ProcessOngoingNavigationResource(frame_tree_node_id);
 }
 
@@ skipping 150 matching lines @@
 void AdsPageLoadMetricsObserver::ProcessOngoingNavigationResource(
     FrameTreeNodeId frame_tree_node_id) {
   const auto& frame_id_and_request =
       ongoing_navigation_resources_.find(frame_tree_node_id);
   if (frame_id_and_request == ongoing_navigation_resources_.end())
     return;
 
   ProcessLoadedResource(frame_id_and_request->second);
   ongoing_navigation_resources_.erase(frame_id_and_request);
 }