Metadata extraction for Copyless Paste

third_party/WebKit/Source/modules/document_metadata/CopylessPasteExtractor.cpp

Index: third_party/WebKit/Source/modules/document_metadata/CopylessPasteExtractor.cpp
diff --git a/third_party/WebKit/Source/modules/document_metadata/CopylessPasteExtractor.cpp b/third_party/WebKit/Source/modules/document_metadata/CopylessPasteExtractor.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..6c3d28c0bdca950a58155c1dc2f00a1453193d71
--- /dev/null
+++ b/third_party/WebKit/Source/modules/document_metadata/CopylessPasteExtractor.cpp
@@ -0,0 +1,65 @@
+// 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 "modules/document_metadata/CopylessPasteExtractor.h"
+
+#include "core/HTMLNames.h"
+#include "core/dom/Document.h"
+#include "core/dom/ElementTraversal.h"
+#include "core/frame/LocalFrame.h"
+#include "core/html/HTMLElement.h"
+#include "platform/Histogram.h"
+#include "platform/instrumentation/tracing/TraceEvent.h"
+#include "wtf/text/StringBuilder.h"
+
+namespace blink {
+
+namespace {
+
+String extractMetadata(Element& root) {
+  StringBuilder result;
+  result.append("[");
+  bool multiple = false;
+  for (Element& element : ElementTraversal::descendantsOf(root)) {
+    if (element.hasTagName(HTMLNames::scriptTag) &&
+        element.getAttribute(HTMLNames::typeAttr) == "application/ld+json") {
+      if (multiple) {
+        result.append(",");
+      }
+      result.append(element.textContent());
+      multiple = true;
+    }
+  }
+  result.append("]");
+  return result.toString();
+}
+
+}  // namespace
+
+String CopylessPasteExtractor::extract(Document& document) {
+  TRACE_EVENT0("blink", "CopylessPasteExtractor::extract");
+
+  if (!document.frame() || !document.frame()->isMainFrame())
+    return emptyString;
+
+  DCHECK(document.hasFinishedParsing());
+
+  Element* html = document.documentElement();
+  if (!html)
+    return emptyString;
+
+  double startTime = monotonicallyIncreasingTime();
+
+  // Traverse the DOM tree and extract the metadata.
+  String result = extractMetadata(*html);
+
+  double elapsedTime = monotonicallyIncreasingTime() - startTime;
+
+  DEFINE_STATIC_LOCAL(CustomCountHistogram, extractionHistogram,
+                      ("CopylessPaste.ExtractionUs", 1, 1000000, 50));

[haraken, 2017/02/16 02:33:35]

Have you already added the histogram to histograms.xml?

[wychen, 2017/02/16 17:29:30]

Oops. Thanks for your eagle eyes!

+  extractionHistogram.count(static_cast<int>(1e6 * elapsedTime));
+  return result;
+}
+
+}  // namespace blink