Randomly select a single rappor sample when more than one is collected.

components/rappor/rappor_metric.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/rappor_metric.h"
 
 #include "base/logging.h"
+#include "base/rand_util.h"
 
 namespace rappor {
 
 RapporMetric::RapporMetric(const std::string& metric_name,
                            const RapporParameters& parameters,
                            int32_t cohort_seed)
     : metric_name_(metric_name),
       parameters_(parameters),

[Alexei Svitkine (slow), 2014/07/30 17:12:47]

Init sample_count_ here.

[Steven Holte, 2014/08/04 23:30:26]

Done.

       bloom_filter_(parameters.bloom_filter_size_bytes,
                     parameters.bloom_filter_hash_function_count,
                     (cohort_seed % parameters.num_cohorts) *
                         parameters.bloom_filter_hash_function_count) {
   DCHECK_GE(cohort_seed, 0);
   DCHECK_LT(cohort_seed, RapporParameters::kMaxCohorts);
 }
 
 RapporMetric::~RapporMetric() {}
 
 void RapporMetric::AddSample(const std::string& str) {
-  bloom_filter_.AddString(str);
+  ++sample_count;

[Alexei Svitkine (slow), 2014/07/30 17:12:47]

Should be sample_count_, not sample_count.

[Steven Holte, 2014/08/04 23:30:26]

Done.

+  // Replace the previous sample with a 1 in sample_count chance so that each

[Alexei Svitkine (slow), 2014/07/30 17:12:47]

Nit: sample_count_.

[Steven Holte, 2014/08/04 23:30:26]

Done.

+  // sample has equal probability of being reported.
+  if (base::RandGenerator(sample_count) == 0) {
+    bloom_filter_.Clear();
+    bloom_filter_.AddString(str);

[Alexei Svitkine (slow), 2014/07/30 17:12:47]

Any reason why we can't just change AddString() to SetString() which does Clear
internally?

[Steven Holte, 2014/08/04 23:30:26]

Done.

+  }
 }
 
 ByteVector RapporMetric::GetReport(const std::string& secret) const {
   // Generate a deterministically random mask of fake data using the
   // client's secret key + real data as a seed.  The inclusion of the secret
   // in the seed avoids correlations between real and fake data.
   // The seed isn't a human-readable string.
   const std::string personalization_string = metric_name_ +
       std::string(bytes().begin(), bytes().end());
   HmacByteVectorGenerator hmac_generator(bytes().size(), secret,
@@ skipping 14 matching lines @@
       coin_generator.GetWeightedRandomByteVector(parameters().zero_coin_prob);
   ByteVector one_coins =
       coin_generator.GetWeightedRandomByteVector(parameters().one_coin_prob);
 
   // Create a randomized response report on the fake and redacted data, sending
   // the outcome of flipping a zero coin for the zero bits in that data, and of
   // flipping a one coin for the one bits in that data, as the final report.
   return *ByteVectorMerge(*fake_and_redacted_bits, zero_coins, &one_coins);
 }
 
+void RapporMetric::SetBytesForTesting(const ByteVector& bytes) {
+  bloom_filter_.SetBytesForTesting(bytes);
+}
+
 }  // namespace rappor