Resubmit: Add real file for AdNetworks DB

This is a resubmit of https://codereview.chromium.org/268063004/.

The previous version was reverted because it caused a memory leak. This was a
problem with RefCounting from ui::ResourceBundle::LoadDataResourceBytes(), which
has been fixed.

Details:
Even though the method returns a non-refcounted ptr to a RefCountedStaticMemory
(which according to the class comment, "the ref counting does not matter" [1]),
the ref-counting _does_ matter. The fix for this went in as part of a refactor
in https://codereview.chromium.org/263953003/.

[1] http://src.chromium.org/viewvc/chrome/trunk/src/base/memory/ref_counted_memory.h?revision=267321 line 44

BUG=357204

TBR=jhawkins@chromium.org (previously approved)
TBR=felt@chromium.org (very minor changes)

Review URL: https://codereview.chromium.org/274563003

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@269494 0039d316-1c4b-4281-b951-d872f2087c98

chrome/browser/extensions/activity_log/hashed_ad_network_database.cc

@@ -31,7 +31,8 @@ const size_t kChecksumHashSize = 32u;
 }  // namespace
 
 HashedAdNetworkDatabase::HashedAdNetworkDatabase(
-    scoped_refptr<base::RefCountedStaticMemory> entries_memory) {
+    scoped_refptr<base::RefCountedStaticMemory> entries_memory)
+    : is_valid_(false) {
   // This can legitimately happen in unit tests.
   if (!entries_memory)
     return;
@@ -67,6 +68,8 @@ HashedAdNetworkDatabase::HashedAdNetworkDatabase(
     memcpy(&value, index, kUrlHashSize);
     entries_.insert(value);
   }
+
+  is_valid_ = true;
 }
 
 HashedAdNetworkDatabase::~HashedAdNetworkDatabase() {}

chrome/browser/extensions/activity_log/hashed_ad_network_database.h

@@ -23,10 +23,17 @@ class HashedAdNetworkDatabase : public AdNetworkDatabase {
       scoped_refptr<base::RefCountedStaticMemory> memory);
   virtual ~HashedAdNetworkDatabase();
 
+  bool is_valid() const { return is_valid_; }
+
  private:
   // AdNetworkDatabase implementation.
   virtual bool IsAdNetwork(const GURL& url) const OVERRIDE;
 
+  // Whether or not the database is valid, i.e., has correctly parsed the hash
+  // file. If it is not, it will always return false for IsAdNetwork(), since
+  // it cannot match against known hashes.
+  bool is_valid_;
+
   // The set of partial hashes for known ad networks.
   base::hash_set<int64> entries_;
 };

chrome/browser/extensions/activity_log/hashed_ad_network_database_unittest.cc

@@ -49,6 +49,7 @@ const size_t kDataResourceSize = kChecksumSize + kAdNetworkHostHashesTotalSize;
 class HashedAdNetworkDatabaseUnitTest : public testing::Test {
  protected:
   virtual void SetUp() OVERRIDE;
+  virtual void TearDown() OVERRIDE;
 
  private:
   // Generate a piece of memory with a hash structure identical to the real one,
@@ -68,6 +69,11 @@ void HashedAdNetworkDatabaseUnitTest::SetUp() {
       scoped_ptr<AdNetworkDatabase>(new HashedAdNetworkDatabase(memory_)));
 }
 
+void HashedAdNetworkDatabaseUnitTest::TearDown() {
+  // Reset the database.
+  AdNetworkDatabase::SetForTesting(scoped_ptr<AdNetworkDatabase>());
+}
+
 void HashedAdNetworkDatabaseUnitTest::GenerateMockMemory() {
   int64 host_hashes[kNumAdNetworkHosts];
 
@@ -94,6 +100,9 @@ void HashedAdNetworkDatabaseUnitTest::GenerateMockMemory() {
   memory_ = new base::RefCountedStaticMemory(raw_data_, kDataResourceSize);
 };
 
+// Test that the logic for the Ad Network Database works. That is, the hashing
+// scheme works, correctly reports when URLs are present in the database,
+// treats hosts and sumdomains correctly, etc.
 TEST_F(HashedAdNetworkDatabaseUnitTest, HashedAdNetworkDatabaseTest) {
   const AdNetworkDatabase* database = AdNetworkDatabase::Get();
   ASSERT_TRUE(database);
@@ -130,4 +139,23 @@ TEST_F(HashedAdNetworkDatabaseUnitTest, HashedAdNetworkDatabaseTest) {
       GURL("chrome-extension://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")));
 }
 
+// Test that the HashAdNetworkDatabse test works with the real file. For
+// security and privacy purposes, we cannot verify that real URLs are
+// recognized. However, we can at least verify that the file is recognized and
+// parsed.
+TEST(HashedAdNetworkDatabaseWithRealFileUnitTest,
+     HashedAdNetworkDatabaseRealFileTest) {
+  // This constructs the database, and, since we didn't mock up any memory, it
+  // uses the real file.
+  const AdNetworkDatabase* database = AdNetworkDatabase::Get();
+  ASSERT_TRUE(database);
+  const HashedAdNetworkDatabase* hashed_database =
+      static_cast<const HashedAdNetworkDatabase*>(database);
+  EXPECT_TRUE(hashed_database->is_valid());
+
+  // We can also safely assume that a made-up url is not in the database.
+  EXPECT_FALSE(database->IsAdNetwork(
+      GURL("http://www.this-is-definitely-not-a-real-site.orarealtld")));
+}
+
 }  // namespace extensions