Skip to content

Add time domain to input_spec proto and implement modular timestamp bucketing in input_encoding. #142

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add time domain to input_spec proto and implement modular timestamp bucketing in input_encoding. #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 9 additions & 15 deletions willow/api/client.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@

#include "willow/api/client.h"

#include <cstddef>
#include <cstdint>
#include <memory>
#include <string>
Expand All @@ -22,7 +23,6 @@

#include "absl/status/status.h"
#include "absl/status/statusor.h"
#include "absl/strings/str_cat.h"
#include "absl/strings/string_view.h"
#include "ffi_utils/cxx_utils.h"
#include "ffi_utils/status_macros.h"
Expand All @@ -45,24 +45,18 @@ absl::StatusOr<willow::AggregationConfigProto> CreateAggregationConfig(
config_proto.set_max_number_of_decryptors(max_number_of_decryptors);
config_proto.set_max_decryptor_dropouts(max_decryptor_dropouts);
config_proto.set_key_id(std::string(key_id));
// All metrics have same vector length, corresponding to the Cartesian product
// of group-by domains.
int64_t flattened_domain_size = 1;
for (const auto& group_by_spec : input_spec_proto.group_by_vector_specs()) {
if (group_by_spec.domain_spec().string_values().values_size() == 0) {
return absl::InvalidArgumentError(absl::StrCat(
"Missing domain, invalid domain type (must be StringValues), or "
"empty string_values for group by vector: ",
group_by_spec.vector_name()));
}
flattened_domain_size *=
group_by_spec.domain_spec().string_values().values_size();
}

// Validate the input spec and create the codec (for vector length).
SECAGG_ASSIGN_OR_RETURN(
auto codec, willow::Codec::CreateFlatHistogramCodec(input_spec_proto));

// Build VectorConfig (length and bound) for each metric.
for (const auto& metric_spec : input_spec_proto.metric_vector_specs()) {
auto& vector_config =
(*config_proto.mutable_vector_configs())[metric_spec.vector_name()];
vector_config.set_length(flattened_domain_size);
SECAGG_ASSIGN_OR_RETURN(size_t length, codec->GetEncodedVectorLength(
metric_spec.vector_name()));
vector_config.set_length(length);
if (metric_spec.has_domain_spec() &&
metric_spec.domain_spec().has_interval()) {
vector_config.set_bound(
Expand Down
46 changes: 43 additions & 3 deletions willow/input_encoding/BUILD
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,40 +23,80 @@ package(
default_visibility = ["//visibility:public"],
)

cc_library(
name = "time_utils",
srcs = [
"time_utils.cc",
],
hdrs = [
"time_utils.h",
],
deps = [
"@protobuf//:duration_cc_proto",
"@protobuf//:timestamp_cc_proto",
"@abseil-cpp//absl/status",
"@abseil-cpp//absl/status:statusor",
"@abseil-cpp//absl/strings",
"@abseil-cpp//absl/time",
"//willow/proto/willow:input_spec_cc_proto",
],
)

cc_library(
name = "codec",
srcs = [
"codec_factory.cc",
"codec.cc",
],
hdrs = [
"codec.h",
"codec_factory.h",
],
deps = [
":time_utils",
"@abseil-cpp//absl/container:flat_hash_map",
"@abseil-cpp//absl/log:check",
"@abseil-cpp//absl/memory",
"@abseil-cpp//absl/status",
"@abseil-cpp//absl/status:statusor",
"@abseil-cpp//absl/strings",
"@abseil-cpp//absl/time",
"//ffi_utils:status_macros",
"//willow/proto/willow:input_spec_cc_proto",
],
)

cc_test(
name = "explicit_codec_test",
srcs = ["explicit_codec_test.cc"],
name = "codec_test",
srcs = ["codec_test.cc"],
deps = [
":codec",
":time_utils",
"@protobuf//:duration_cc_proto",
"@googletest//:gtest_main",
"@abseil-cpp//absl/container:flat_hash_map",
"@abseil-cpp//absl/status",
"@abseil-cpp//absl/time",
"//ffi_utils:status_matchers",
"//willow/proto/willow:input_spec_cc_proto",
"//willow/testing_utils:testing_utils_cc",
],
)

cc_test(
name = "time_utils_test",
srcs = ["time_utils_test.cc"],
deps = [
":time_utils",
"@protobuf//:duration_cc_proto",
"@protobuf//:timestamp_cc_proto",
"@googletest//:gtest_main",
"@abseil-cpp//absl/status",
"@abseil-cpp//absl/time",
"//ffi_utils:status_matchers",
"//willow/proto/willow:input_spec_cc_proto",
],
)

pytype_pybind_extension(
name = "codec_bindings",
srcs = ["codec_bindings.cc"],
Expand Down
Loading