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..0c9d66d988f782d9261d1475e85cd15eabc31392
--- /dev/null
+++ b/chrome/browser/page_load_metrics/ads_detection.cc
@@ -0,0 +1,128 @@
+// 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 <utility>
+
+#include "base/logging.h"
+#include "base/macros.h"
+#include "base/memory/ptr_util.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 page_load_metrics {
+
+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.

[Charlie Reis, 2017/07/20 17:06:16]

Are we ok with this for the process model decision (i.e., once an ad frame,
always an ad frame)?  I guess that's probably ok.

[jkarlin, 2017/07/20 17:19:43]

Actually, that comment (the once an ad always an ad comment) is specific to
PageLoadMetrics and doesn't belong here.

Let's use GetRenderFrameHost and return false if it's nullptr.

[Łukasz Anforowicz, 2017/07/20 17:33:51]

I think this is okay for now.
I agree that we should use |navigation_handle->GetRenderFrameHost()| here (and
delete the comment above), but this is problematic because of
https://crbug.com/746638 (which makes it hard to distinguish between
navigation-finished was called because 1) navigation has committed or 2)
navigation was aborted or cancelled or has failed.

+  // 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).

[Charlie Reis, 2017/07/20 17:06:16]

nit: privileges

[Łukasz Anforowicz, 2017/07/20 17:33:51]

Done.

+  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 {

[Charlie Reis, 2017/07/20 17:06:16]

nit: Please add comment, along the lines of "Associates the detected AdTypes for
a navigation with its NavigationHandle."

[Łukasz Anforowicz, 2017/07/20 17:33:51]

Done.

+ public:
+  static NavigationHandleAdsData* GetOrCreate(
+      content::NavigationHandle* navigation_handle) {
+    DCHECK(navigation_handle);
+    NavigationHandleAdsData* ads_data = static_cast<NavigationHandleAdsData*>(
+        navigation_handle->GetUserData(kUserDataKey));
+    if (!ads_data) {
+      std::unique_ptr<NavigationHandleAdsData> new_ads_data =
+          base::MakeUnique<NavigationHandleAdsData>();
+
+      // It is safe to retain |ads_data| raw pointer, despite passing an
+      // ownership of |new_ads_data| to SetUserData, because |navigation_handle|
+      // will keep the NavigationHandleAdsData instance alive until the
+      // |navigation_handle| is destroyed.
+      ads_data = new_ads_data.get();
+
+      navigation_handle->SetUserData(kUserDataKey, std::move(new_ads_data));
+    }
+
+    return ads_data;
+  }
+
+  NavigationHandleAdsData() = default;
+  ~NavigationHandleAdsData() override {}
+
+  AdTypes& ad_types() { return ad_types_; }
+  const AdTypes& ad_types() const { return ad_types_; }
+
+ private:
+  AdTypes ad_types_;
+
+  static const char kUserDataKey[];
+
+  DISALLOW_COPY_AND_ASSIGN(NavigationHandleAdsData);
+};
+
+const char NavigationHandleAdsData::kUserDataKey[] = "AdsData";

[Charlie Reis, 2017/07/20 17:06:16]

nit: Move above the NavigationHandleAdsData class.

[Łukasz Anforowicz, 2017/07/20 17:33:51]

This wouldn't compile (error: use of undeclared identifier
'NavigationHandleAdsData').

I could make this compile by making kUserDataKey a namespace-level variable, but
I prefer to keep kUserDataKey a static, *private* member of
NavigationHandleAdsData class.

I tried to get rid of the separate definition, by moving the string literal into
the class declaration, but I couldn't make this compile (constexpr is needed,
but then things fail to link).

[Charlie Reis, 2017/07/20 20:10:53]

Ah, sorry, I didn't see it was a member, just that it was used before this line.
 No need to move.

+
+}  // namespace
+
+const AdTypes& GetDetectedAdTypes(
+    content::NavigationHandle* navigation_handle) {
+  DCHECK(navigation_handle);
+
+  // Verify that we are called after the navigation is ready to commit.
+  // Being called late enough in the navigation process ensures that
+  // 1) subresource filter got a chance to run its heuristics
+  // 2) the URL looked at by IsGoogleAd is the final, redirected URL.
+  DCHECK((navigation_handle->GetNetErrorCode() != net::Error::OK) ||
+         navigation_handle->GetRenderFrameHost());
+
+  NavigationHandleAdsData* ads_data =
+      NavigationHandleAdsData::GetOrCreate(navigation_handle);
+  if (IsGoogleAd(navigation_handle))
+    ads_data->ad_types().set(AD_TYPE_GOOGLE);
+  return ads_data->ad_types();
+}
+
+void SetDetectedAdType(content::NavigationHandle* navigation_handle,
+                       AdType type) {
+  DCHECK(navigation_handle);
+  NavigationHandleAdsData::GetOrCreate(navigation_handle)->ad_types().set(type);
+}
+
+}  // namespace page_load_metrics