Various cleaups for AMP page load metrics.

chrome/browser/page_load_metrics/page_load_metrics_util.cc

 // Copyright 2015 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/page_load_metrics_util.h"
 
 #include <algorithm>
 
 #include "chrome/common/page_load_metrics/page_load_timing.h"
+#include "net/base/registry_controlled_domains/registry_controlled_domain.h"
+#include "url/gurl.h"
 
 namespace page_load_metrics {
 
 namespace {
 
 bool IsBackgroundAbort(const PageLoadExtraInfo& info) {
   if (!info.started_in_foreground || !info.first_background_time)
     return false;
 
   if (!info.page_end_time)
@@ skipping 16 matching lines @@
       return ABORT_CLOSE;
     case END_OTHER:
       return ABORT_OTHER;
     default:
       return ABORT_NONE;
   }
 }
 
 }  // namespace
 
+bool IsGoogleHostnameAndGetPrefix(const GURL& url,

[RyanSturm, 2017/05/15 20:42:06]

nit: Thoughts on getting rid of the out param and returning a
base::Optional<base::StringPiece>? Maybe rename it GetPrefixForGoogleHostName if
that makes sense.

[Bryan McQuade, 2017/05/16 03:59:15]

This is a great idea. I needed to change to optional<std::string> since we
sometimes return string offsets into a stack-allocated string piece, which blows
up. using std::string guarantees consistent storage that can live beyond
returning from a function.

+                                  base::StringPiece* out_google_host_prefix) {
+  const size_t registry_length =
+      net::registry_controlled_domains::GetRegistryLength(
+          url,
+
+          // Do not include unknown registries (registries that don't have any
+          // matches in effective TLD names).
+          net::registry_controlled_domains::EXCLUDE_UNKNOWN_REGISTRIES,
+
+          // Do not include private registries, such as appspot.com. We don't
+          // want to match URLs like www.google.appspot.com.
+          net::registry_controlled_domains::EXCLUDE_PRIVATE_REGISTRIES);
+
+  const base::StringPiece hostname = url.host_piece();
+  if (registry_length == 0 || registry_length == std::string::npos ||
+      registry_length >= hostname.length())
+    return false;
+
+  // Removes the tld and the preceding dot.
+  const base::StringPiece hostname_minus_registry =
+      hostname.substr(0, hostname.length() - (registry_length + 1));
+
+  if (hostname_minus_registry == "google") {
+    if (out_google_host_prefix)
+      *out_google_host_prefix = "";
+    return true;
+  }
+
+  if (!base::EndsWith(hostname_minus_registry, ".google",
+                      base::CompareCase::INSENSITIVE_ASCII)) {
+    return false;
+  }
+
+  if (out_google_host_prefix) {
+    *out_google_host_prefix = hostname_minus_registry.substr(
+        0, hostname_minus_registry.length() - strlen(".google"));
+  }
+  return true;
+}
+
+bool IsGoogleHostname(const GURL& url) {
+  return IsGoogleHostnameAndGetPrefix(url, nullptr);
+}
+
 bool WasStartedInForegroundOptionalEventInForeground(
     const base::Optional<base::TimeDelta>& event,
     const PageLoadExtraInfo& info) {
   return info.started_in_foreground && event &&
          (!info.first_background_time ||
           event.value() <= info.first_background_time.value());
 }
 
 PageAbortInfo GetPageAbortInfo(const PageLoadExtraInfo& info) {
   if (IsBackgroundAbort(info)) {
@@ skipping 51 matching lines @@
     const page_load_metrics::PageLoadExtraInfo& info,
     blink::WebLoadingBehaviorFlag behavior) {
   const int all_frame_loading_behavior_flags =
       info.main_frame_metadata.behavior_flags |
       info.subframe_metadata.behavior_flags;
 
   return (all_frame_loading_behavior_flags & behavior) != 0;
 }
 
 }  // namespace page_load_metrics