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

chrome/browser/page_load_metrics/ads_detection.cc

Index: chrome/browser/page_load_metrics/ads_detection.cc
diff --git a/chrome/browser/page_load_metrics/ads_detection.cc b/chrome/browser/page_load_metrics/ads_detection.cc
new file mode 100644
index 0000000000000000000000000000000000000000..a770deb9abda91f1bdda924d5e6a788b0ce423a0
--- /dev/null
+++ b/chrome/browser/page_load_metrics/ads_detection.cc
@@ -0,0 +1,108 @@
+// 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/ads_detection.h"
+
+#include <memory>
+#include <string>
+
+#include "base/logging.h"
+#include "base/strings/string_util.h"
+#include "base/supports_user_data.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 {
+
+bool IsGoogleAd(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.
+
+  // 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& frame_url = navigation_handle->GetURL();
+  if (frame_url.host_piece() == "tpc.googlesyndication.com" &&
+      base::StartsWith(frame_url.path_piece(), "/safeframe",
+                       base::CompareCase::SENSITIVE)) {
+    return true;
+  }
+
+  return false;
+}
+
+class NavigationHandleAdsData : public base::SupportsUserData::Data {
+ public:
+  static NavigationHandleAdsData* GetOrCreate(
+      content::NavigationHandle* navigation_handle) {
+    DCHECK(navigation_handle);
+    NavigationHandleAdsData* ads_data = static_cast<NavigationHandleAdsData*>(

[Charlie Harrison, 2017/07/18 19:24:41]

Optional: I would much prefer the following, to avoid raw new:

if (NavigationHandleAdsData* existing_ads_data = ...) {
  return existing_ads_data;
}

auto ads_data = base::MakeUnique<NavigationHandleAdsData>();
auto* raw_ads_data = ads_data.get();
if (IsGoogleAd(navigation_handle)) 
  ads_data->ad_types().set(AD_TYPE_GOOGLE);
navigation_handle->SetUserData(kUserDataKey, std::move(ads_data));

// Comment about lifetime of the raw pointer.
return raw_ads_data.get();

[Łukasz Anforowicz, 2017/07/18 20:04:29]

Done (= I switched to base::MakeUnique<...>;  OTOH, I did this in a slightly
different way than suggested - for example we shouldn't do |raw_ads_data.get()|
after already |std::move|-ing the unique pointer into SetUserData).

[Charlie Harrison, 2017/07/18 20:07:28]

Right, my typo, you can just return raw_ads_data directly.

+        navigation_handle->GetUserData(kUserDataKey));
+    if (!ads_data) {
+      ads_data = new NavigationHandleAdsData;
+
+      // It is safe to retain |ads_data| raw pointer, despite passing an
+      // ownership to SetUserData, because |navigation_handle| will keep
+      // |ads_data| alive until the |navigation_handle| is destroyed.
+      navigation_handle->SetUserData(
+          kUserDataKey, std::unique_ptr<NavigationHandleAdsData>(ads_data));
+
+      if (IsGoogleAd(navigation_handle))
+        ads_data->ad_types().set(AD_TYPE_GOOGLE);
+    }
+
+    return ads_data;
+  }
+
+  ~NavigationHandleAdsData() override {}
+
+  AdTypes& ad_types() { return ad_types_; }
+  const AdTypes& ad_types() const { return ad_types_; }
+
+ private:
+  NavigationHandleAdsData() = default;
+
+  AdTypes ad_types_;
+
+  static const char kUserDataKey[];
+};

[Charlie Harrison, 2017/07/18 19:24:41]

DISALLOW_COPY_AND_ASSIGN?

[Łukasz Anforowicz, 2017/07/18 20:04:29]

Ooops.  Yes - DISALLOW_COPY_AND_ASSIGN!

+
+const char NavigationHandleAdsData::kUserDataKey[] = "AdsData";
+
+}  // namespace
+
+const AdTypes& GetDetectedAdTypes(
+    content::NavigationHandle* navigation_handle) {
+  DCHECK(navigation_handle);
+  return NavigationHandleAdsData::GetOrCreate(navigation_handle)->ad_types();
+}
+
+void SetDetectedAdTypes(content::NavigationHandle* navigation_handle,
+                        AdType type) {
+  DCHECK(navigation_handle);
+  NavigationHandleAdsData::GetOrCreate(navigation_handle)->ad_types().set(type);
+}