Add common page filtering logic for page load metrics.

chrome/renderer/page_load_metrics/renderer_page_track_decider.cc

Index: chrome/renderer/page_load_metrics/renderer_page_track_decider.cc
diff --git a/chrome/renderer/page_load_metrics/renderer_page_track_decider.cc b/chrome/renderer/page_load_metrics/renderer_page_track_decider.cc
new file mode 100644
index 0000000000000000000000000000000000000000..daa664afdf16008c8acaba354030b3d99acfd4b8
--- /dev/null
+++ b/chrome/renderer/page_load_metrics/renderer_page_track_decider.cc
@@ -0,0 +1,62 @@
+// Copyright 2016 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/renderer/page_load_metrics/renderer_page_track_decider.h"
+
+#include <string>
+
+#include "chrome/renderer/searchbox/search_bouncer.h"
+#include "third_party/WebKit/public/platform/WebURLResponse.h"
+#include "third_party/WebKit/public/web/WebDataSource.h"
+#include "third_party/WebKit/public/web/WebDocument.h"
+#include "url/gurl.h"
+
+namespace page_load_metrics {
+
+RendererPageTrackDecider::RendererPageTrackDecider(
+    const blink::WebDocument* document,
+    const blink::WebDataSource* data_source)
+    : document_(document), data_source_(data_source) {}
+
+RendererPageTrackDecider::~RendererPageTrackDecider() {}
+
+bool RendererPageTrackDecider::HasCommitted() {
+  // RendererPageTrackDecider is only instantiated for committed pages. TODO
+  // see if blink exposes a concept of whether the current page is provisional
+  // or committed.
+  return true;
+}
+
+bool RendererPageTrackDecider::IsHTTPOrHTTPSUrl() {
+  const GURL url = document_->url();

[Charlie Harrison, 2016/09/14 13:20:05]

Can this method be just one line?

[Bryan McQuade, 2016/09/14 15:10:58]

Yeah - the reason I did this is a bit silly - WebDocument::url() returns a
WebUrl, which has a conversion operator to produce a GURL. So if I just wrote

document_->url().SchemeIsHTTPOrHTTPS();

compilation fails because there is no SchemeIsHTTPOrHTTPS on WebURL. But I can
do it in one line using a static cast, which is shorter.

+  return url.SchemeIsHTTPOrHTTPS();
+}
+
+bool RendererPageTrackDecider::IsNewTabPageUrl() {
+  return SearchBouncer::GetInstance()->IsNewTabPage(document_->url());
+}
+
+bool RendererPageTrackDecider::IsChromeErrorPage() {
+  return data_source_->hasUnreachableURL();
+}
+
+bool RendererPageTrackDecider::IsHTTPErrorPage() {
+  // 2xx and 3xx (304 not modified) response codes are not error pages.
+  int status_code_family = data_source_->response().httpStatusCode() / 100;
+  return status_code_family != 2 && status_code_family != 3;
+}
+
+bool RendererPageTrackDecider::IsHTMLOrXHTMLPage() {
+  // Ignore non-HTML documents (e.g. SVG). Note that images are treated by
+  // Blink as HTML documents, so to exclude images, we must perform
+  // additional mime type checking below.
+  if (!document_->isHTMLDocument() && !document_->isXHTMLDocument())
+    return false;
+
+  // Ignore non-HTML mime types (e.g. images).
+  std::string mime_type = data_source_->response().mimeType().utf8();

[Charlie Harrison, 2016/09/14 13:20:05]

Could you directly compare the WebString without copying to std::string?

[Bryan McQuade, 2016/09/14 15:10:58]

Ah, I think so, yes. The default WebString equality comparison treats the mime
type as latin1 characters, which seems like it should be fine here. Done,
thanks!

+  return mime_type == "text/html" || mime_type == "application/xhtml+xml";
+}
+
+}  // namespace page_load_metrics