Alternative Multi-dimensional Rappor

components/rappor/bloom_filter.cc

 // Copyright 2014 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 "components/rappor/bloom_filter.h"
 
 #include "base/logging.h"
 #include "third_party/smhasher/src/City.h"
 
 namespace rappor {
@@ skipping 25 matching lines @@
   }
 }
 
 void BloomFilter::SetBytesForTesting(const ByteVector& bytes) {
   DCHECK_EQ(bytes_.size(), bytes.size());
   for (size_t i = 0; i < bytes_.size(); ++i) {
     bytes_[i] = bytes[i];
   }
 }
 
+namespace internal {
+
+uint64_t GetBloomBits(uint32_t bytes_size,
+                      uint32_t hash_function_count,
+                      uint32_t hash_seed_offset,
+                      const std::string& str) {
+  DCHECK_LE(bytes_size, 8u);

[Alexei Svitkine (slow), 2015/04/23 21:42:34]

Add a comment above this check (i.e. in order for the hash to fit into 64 bits).

[Steven Holte, 2015/04/24 16:59:05]

Done.

+  uint64_t output = 0;
+  for (size_t i = 0; i < hash_function_count; ++i) {
+    // Using CityHash here because we have support for it in Dremel.  Many hash
+    // functions, such as MD5, SHA1, or Murmur, would probably also work.
+    uint32_t index =
+        CityHash64WithSeed(str.data(), str.size(), hash_seed_offset + i);

[Alexei Svitkine (slow), 2015/04/23 21:42:34]

Nit: Make a helper in the anon namespace that wraps this so this comment doesn't
have to be repeated.

Should take str, and seed as params.

[Steven Holte, 2015/04/24 16:59:05]

Done.

+    output |= 1 << (index % (bytes_size * 8));

[Alexei Svitkine (slow), 2015/04/23 21:42:34]

Nit: Move bytes_size * 8 to a variable outside the loop.

[Steven Holte, 2015/04/24 16:59:05]

Done.

+  }
+  return output;
+}
+
+}  // namespace internal
+
 }  // namespace rappor