Collect separate V8 histograms for Top10 non-Google sites

content/renderer/render_thread_impl.cc

 // Copyright (c) 2012 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 "content/renderer/render_thread_impl.h"
 
 #include <algorithm>
 #include <limits>
 #include <map>
 #include <vector>
 
 #include "base/allocator/allocator_extension.h"
 #include "base/command_line.h"
 #include "base/lazy_instance.h"
 #include "base/location.h"
 #include "base/logging.h"
 #include "base/memory/discardable_memory_allocator.h"
 #include "base/memory/shared_memory.h"
 #include "base/metrics/field_trial.h"
 #include "base/metrics/histogram.h"
 #include "base/path_service.h"
 #include "base/single_thread_task_runner.h"
 #include "base/strings/string16.h"
 #include "base/strings/string_number_conversions.h"
+#include "base/strings/string_split.h"
 #include "base/strings/string_tokenizer.h"
 #include "base/strings/sys_string_conversions.h"
 #include "base/strings/utf_string_conversions.h"
 #include "base/thread_task_runner_handle.h"
 #include "base/threading/simple_thread.h"
 #include "base/threading/thread_local.h"
 #include "base/threading/thread_restrictions.h"
 #include "base/trace_event/memory_dump_manager.h"
 #include "base/trace_event/trace_event.h"
 #include "base/values.h"
@@ skipping 246 matching lines @@
   if (host == "mail.google.com")
     return ".gmail";
   if (host == "docs.google.com" || host == "drive.google.com")
     return ".docs";
   if (host == "plus.google.com")
     return ".plus";
   if (host == "inbox.google.com")
     return ".inbox";
   if (host == "www.youtube.com")
     return ".youtube";
+
+  // The Top10 sites have different TLD and/or subdomains
+  // depending on the localization
+   if (host == "sina.com.cn")
+    return ".top10";
+
+  std::vector<base::StringPiece> host_tokens = base::SplitStringPiece(
+    host, ".", base::TRIM_WHITESPACE, base::SPLIT_WANT_NONEMPTY);
+
+  if (host_tokens.size() == 3) {
+    if ((host_tokens[1] == "facebook") ||
+        (host_tokens[1] == "baidu") ||
+        (host_tokens[1] == "yahoo") ||
+        (host_tokens[1] == "amazon") ||
+        (host_tokens[1] == "qq") ||
+        (host_tokens[1] == "twitter") ||
+        (host_tokens[1] == "taobao") ||
+        (host_tokens[1] == "live") ||
+        (host_tokens[1] == "linkedin"))

[jochen (gone - plz use gerrit), 2015/10/21 13:17:57]

according to http://www.alexa.com/topsites linkedin is #11 (excluding google
sites), but wikipedia is on the list

I'm not sure we should ignore the TLDs, I also don't understand why you require
three components?

what about .co.uk? if you really want to filter out the tld, use
net::registry_controlled_domains::GetDomainAndRegistry() to extract this
information.

I would vote for just hardcoding the names.

also, please add { } for a multi-line if

[Michael Hablich, 2015/10/22 13:16:35]

You are right: Removed linkedin, added wikipedia

Using GetDomainAndRegistry now, thanks

I still against hardcoding the names because just have a look at wikipedia:
de.wikipedia.org, jp.wikipedia.org and the reverse is also happening like in
Amazon's case: amazon.com, amazon.de. I think we do not only want US-centric
data.

+      return ".top10";
+  }
+
   return std::string();
 }
 
 void* CreateHistogram(
     const char *name, int min, int max, size_t buckets) {
   if (min <= 0)
     min = 1;
   std::string histogram_name;
   RenderThreadImpl* render_thread_impl = RenderThreadImpl::current();
   if (render_thread_impl) {  // Can be null in tests.
@@ skipping 1667 matching lines @@
 }
 
 void RenderThreadImpl::PendingRenderFrameConnect::OnConnectionError() {
   size_t erased =
       RenderThreadImpl::current()->pending_render_frame_connects_.erase(
           routing_id_);
   DCHECK_EQ(1u, erased);
 }
 
 }  // namespace content