Metadata extraction for Copyless Paste

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

Index: third_party/WebKit/Source/modules/copyless_paste/CopylessPasteExtractor.cpp
diff --git a/third_party/WebKit/Source/modules/copyless_paste/CopylessPasteExtractor.cpp b/third_party/WebKit/Source/modules/copyless_paste/CopylessPasteExtractor.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..b1b22782422c572f4159afdeca6fb8aac176333b
--- /dev/null
+++ b/third_party/WebKit/Source/modules/copyless_paste/CopylessPasteExtractor.cpp
@@ -0,0 +1,75 @@
+// 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/copyless_paste/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))
+      continue;
+    if (element.hasTagName(HTMLNames::scriptTag) &&

[esprehn, 2017/02/15 00:10:03]

no need to check hasTagName twice right?

[wychen, 2017/02/15 01:09:33]

Oops.

+        element.getAttribute(HTMLNames::typeAttr) == "application/ld+json") {
+      if (multiple) {
+        result.append(",");
+      }
+      result.append(element.textContent());
+      multiple = true;
+    }
+  }
+  result.append("]");
+  return result.toString();
+}
+
+}  // namespace
+
+// Do JSON-LD extraction, which is equivalant to the following JavaScript code:

[esprehn, 2017/02/15 00:10:03]

This belongs in the header file

[wychen, 2017/02/15 01:09:33]

Deleted.

+//
+// var a=document.querySelectorAll("script[type=\"application/ld+json\"]");
+// if(a) {
+//   var b=[];
+//   a.forEach(function(s) {b.push(JSON.parse(s.innerHTML)) });
+//   b;
+// }
+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));
+  extractionHistogram.count(static_cast<int>(1e6 * elapsedTime));
+  return result;
+}
+
+}  // namespace blink