Multi-dimension rappor metrics

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"
+#include "components/rappor/bloom_filter.h"
 
 namespace rappor {
 
 RapporMetric::RapporMetric(const std::string& metric_name,
-                           const RapporParameters& parameters,
-                           int32_t cohort_seed)
+                           const RapporParameters& parameters)
     : metric_name_(metric_name),
       parameters_(parameters),
       sample_count_(0),
-      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);
-  // Since cohort_seed is in the range [0, kMaxCohorts), num_cohorts should
-  // divide kMaxCohorts for each cohort to have equal weight.
-  DCHECK_EQ(0, RapporParameters::kMaxCohorts % parameters.num_cohorts);
+      sample_(parameters.bloom_filter_size_bytes + parameters.flag_bytes) {
 }
 
 RapporMetric::~RapporMetric() {}
 
-void RapporMetric::AddSample(const std::string& str) {
+void RapporMetric::AddSample(const Sample& sample) {
   ++sample_count_;
   // Replace the previous sample with a 1 in sample_count_ chance so that each
   // sample has equal probability of being reported.
   if (base::RandGenerator(sample_count_) == 0) {
-    bloom_filter_.SetString(str);
+    sample_ = sample;
   }
 }
 
 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());
@@ skipping 15 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);
+void RapporMetric::SetSampleForTesting(const Sample& sample) {
+  sample_ = sample;
+}
+
+void SetSampleBits(const RapporParameters& parameters, int32_t cohort_seed,
+                   const std::string& str, uint64_t flags, Sample* output) {
+  DCHECK_GE(cohort_seed, 0);
+  DCHECK_LT(cohort_seed, RapporParameters::kMaxCohorts);
+  // Since cohort_seed is in the range [0, kMaxCohorts), num_cohorts should
+  // divide kMaxCohorts for each cohort to have equal weight.
+  DCHECK_EQ(0, RapporParameters::kMaxCohorts % parameters.num_cohorts);
+  output->resize(parameters.bloom_filter_size_bytes + parameters.flag_bytes);
+  internal::SetBloomBits(parameters.bloom_filter_size_bytes,
+               parameters.bloom_filter_hash_function_count,
+               (cohort_seed % parameters.num_cohorts) *
+                        parameters.bloom_filter_hash_function_count,
+               str,
+               output);
+  DCHECK_EQ(0ul, flags >> (parameters.flag_bytes * 8));
+  for(int i = 0; i < parameters.flag_bytes; i++) {
+    uint8_t flag_byte = (flags >> (i * 8)) % (1 << 8);
+    (*output)[parameters.bloom_filter_size_bytes + i] = flag_byte;
+  }
 }
 
 }  // namespace rappor