Alternative Multi-dimensional Rappor

components/rappor/sample.cc

Index: components/rappor/sample.cc
diff --git a/components/rappor/sample.cc b/components/rappor/sample.cc
new file mode 100644
index 0000000000000000000000000000000000000000..c509729373172358f1cb06c6535e6517d49d2a3b
--- /dev/null
+++ b/components/rappor/sample.cc
@@ -0,0 +1,66 @@
+// 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/sample.h"
+
+#include <map>
+#include <string>
+
+#include "components/metrics/metrics_hashes.h"
+#include "components/rappor/bloom_filter.h"
+#include "components/rappor/byte_vector_utils.h"
+#include "components/rappor/proto/rappor_metric.pb.h"
+#include "components/rappor/reports.h"
+
+namespace rappor {
+
+Sample::Sample(int32_t cohort_seed, const RapporParameters& parameters)
+  : parameters_(parameters),
+    bloom_offset_((cohort_seed % parameters_.num_cohorts) *
+          parameters_.bloom_filter_hash_function_count) {
+}
+
+Sample::~Sample() {
+
+}
+
+void Sample::SetStringField(const std::string& fieldName,
+                            const std::string& value) {
+  fields[fieldName] = internal::GetBloomBits(
+      parameters_.bloom_filter_size_bytes,
+      parameters_.bloom_filter_hash_function_count,
+      bloom_offset_,
+      value);
+  sizes[fieldName] = parameters_.bloom_filter_size_bytes;
+}
+
+void Sample::SetFlagsField(const std::string& fieldName,
+                           uint64_t flags) {
+  fields[fieldName] = flags;
+  sizes[fieldName] = parameters_.flag_bytes;

[Alexei Svitkine (slow), 2015/04/16 15:09:43]

Hmm, this flag_bytes field now specified the value for all possible flag fields?

What would be the downside to always using e.g. 64bits here? Would that increase
the payload?

[Steven Holte, 2015/04/22 19:24:28]

The main drawback is that we would generate unnecessary PRR bits for this, which
could potentially be used for fingerprinting.

[Alexei Svitkine (slow), 2015/04/22 20:26:30]

I see, how about having the user specify the number of bits as a param to the
SetFlagField() call?

+}
+
+void Sample::ExportMetrics(const std::string& secret,
+                           const std::string& metricName,
+                           RapporReports* reports) const {
+  for (std::map<std::string, uint64_t>::const_iterator it = fields.begin();

[Alexei Svitkine (slow), 2015/04/16 15:09:43]

Nit: Use C++ for loop syntax.

[Steven Holte, 2015/04/22 19:24:28]

Done.

+       it != fields.end();
+       ++it) {
+    uint64_t value = it->second;
+    size_t size = sizes.at(it->first);
+    ByteVector value_bytes(size);
+    for (size_t i = 0; i < size; i++) {
+      value_bytes[i] = (value & (0xff << (i * 8))) >> (i * 8);
+    }
+    ByteVector report_bytes = internal::GenerateReport(
+        secret, parameters_, value_bytes);
+
+    RapporReports::Report* report = reports->add_report();
+    report->set_name_hash(metrics::HashMetricName(
+        metricName + "." + it->first));
+    report->set_bits(std::string(report_bytes.begin(), report_bytes.end()));
+  }
+}
+
+}  // namespace rappor