Add SafeBrowsingNavigationObserver to listen to navigation events

chrome/browser/safe_browsing/safe_browsing_navigation_observer_manager.h

+// 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.
+
+#ifndef CHROME_BROWSER_SAFE_BROWSING_SAFE_BROWSING_NAVIGATION_OBSERVER_MANAGER_H_
+#define CHROME_BROWSER_SAFE_BROWSING_SAFE_BROWSING_NAVIGATION_OBSERVER_MANAGER_H_
+
+#include "content/public/browser/notification_observer.h"
+#include "content/public/browser/notification_registrar.h"
+#include "content/public/browser/web_contents_observer.h"
+#include "url/gurl.h"
+
+namespace content {
+class NavigationHandle;
+struct ResourceRedirectDetails;
+}
+
+namespace safe_browsing {
+
+class SafeBrowsingNavigationObserver;
+struct NavigationEvent;
+struct ResolvedIPAddress;
+
+// Manager class for SafeBrowsingNavigationObserver, which is in charge of
+// cleaning up stale navigation events, and identifing landing page/landing
+// referrer for a specific download.
+// TODO(jialiul): For now, SafeBrowsingNavigationObserverManager also listens to
+// NOTIFICATION_RETARGETING as a way to detect cross frame/tab navigation.
+// Remove base class content::NotificationObserver when
+// WebContentsObserver::DidOpenRequestedURL() covers all retargeting cases.
+class SafeBrowsingNavigationObserverManager
+    : public content::NotificationObserver,
+      public base::RefCountedThreadSafe<SafeBrowsingNavigationObserverManager> {
+ public:
+  // Helper function to check if user gesture is older than
+  // kUserGestureTTLInSecond;
+  static bool IsUserGestureExpired(const base::Time& timestamp);
+  // Helper function to strip empty ref fragment from a URL.
+  static GURL ClearEmptyURLRef(const GURL& url);

[Charlie Reis, 2016/10/17 23:54:04]

nit: ClearEmptyRef

[Jialiu Lin, 2016/10/18 19:06:05]

Done.

+
+  SafeBrowsingNavigationObserverManager();
+
+  // Add |nav_event| to |navigation_map_| based on |nav_event_key|. Object
+  // pointed by |nav_event| will be no longer accessible after this function.
+  void RecordNavigationEvent(const GURL& nav_event_key,
+                             NavigationEvent* nav_event);
+  void RecordUserGestureForWebContents(content::WebContents* web_contents,
+                                       const base::Time& timestamp);
+  void OnUserGestureConsumed(content::WebContents* web_contents,
+                             const base::Time& timestamp);
+  void RecordHostToIpMapping(const std::string& host, const std::string& ip);
+  // Clean-ups need to be done when a WebContents gets destroyed.
+  void OnWebContentDestroyed(content::WebContents* web_contents);
+
+  // TODO(jialiul): more functions are coming for managing navigation_map_.
+
+ private:
+  friend class base::RefCountedThreadSafe<
+      SafeBrowsingNavigationObserverManager>;
+  friend class TestNavigationObserverManager;
+  friend class SBNavigationObserverBrowserTest;
+  friend class SBNavigationObserverTest;
+
+  struct GurlHash {
+    std::size_t operator()(const GURL& url) const {
+      return std::hash<std::string>()(url.spec());
+    }
+  };
+
+  typedef std::unordered_map<GURL, std::vector<NavigationEvent>, GurlHash>
+      NavigationMap;
+  typedef std::unordered_map<content::WebContents*, base::Time> UserGestureMap;
+  typedef std::unordered_map<std::string, std::vector<ResolvedIPAddress>>
+      HostToIpMap;
+
+  ~SafeBrowsingNavigationObserverManager() override;
+
+  // content::NotificationObserver:
+  void Observe(int type,
+               const content::NotificationSource& source,
+               const content::NotificationDetails& details) override;
+
+  void RecordRetargeting(const content::NotificationDetails& details);
+
+  NavigationMap* navigation_map() { return &navigation_map_; }
+
+  HostToIpMap* host_to_ip_map() { return &host_to_ip_map_; }
+
+  // navigation_map_ keeps track of all the observed navigations. This map is
+  // keyed on the resolved request url. In other words, in case of server
+  // redirects, its key is the last server redirect url, otherwise, it is the
+  // original target url. Since the same url can be requested multiple times
+  // across different tabs and frames, the value of this map is a vector of
+  // NavigationEvent ordered by navigation finish time.
+  // TODO(jialiul): Entries in navigation_map_ will be removed if they are older
+  // than 2 minutes since their corresponding navigations finish.
+  NavigationMap navigation_map_;
+
+  // user_gesture_map_ keeps track of the timestamp of last user gesture in
+  // in each WebContents. We assume for majority of cases, a navigation
+  // shortly after a user gesture indicate this navigation is user initiated.
+  UserGestureMap user_gesture_map_;
+
+  // Host to timestamped IP addresses map that covers all the main frame and
+  // sub frame URLs' hosts. Since it is possible for a host to resolve to more
+  // than one IP in even a short period of time, we map a single host to a
+  // vector of ResolvedIPAddresss. This map is used to fill in ip_address field
+  // in URLChainEntry in ClientDownlodRequest.

[Charlie Reis, 2016/10/17 23:54:04]

nit: ClientDownloadRequest

[Jialiu Lin, 2016/10/18 19:06:05]

Done.

+  HostToIpMap host_to_ip_map_;

[Charlie Reis, 2016/10/17 23:54:04]

It seems a bit complex/unfortunate to have to track this given how the IP
address can change over time, but I see that you've accounted for it.  What's
the reason it's necessary?

[Jialiu Lin, 2016/10/18 19:06:05]

SB backend wants this info to see :(1) if website is cloaking, (2) any
malicious/hijacked DNS servers, (3) potentially match them to a known malicious
IPs.

[Charlie Reis, 2016/10/19 17:10:45]

Acknowledged.

+
+  content::NotificationRegistrar registrar_;

[Charlie Reis, 2016/10/17 23:54:04]

nti: Add blank line after.

[Jialiu Lin, 2016/10/18 19:06:05]

Done.

+  DISALLOW_COPY_AND_ASSIGN(SafeBrowsingNavigationObserverManager);
+};
+}  // namespace safe_browsing
+
+#endif  // CHROME_BROWSER_SAFE_BROWSING_SAFE_BROWSING_NAVIGATION_OBSERVER_MANAGER_H_