Skip to content

feat: write manifest avro metadata #261

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

Merged
merged 2 commits into from
Oct 17, 2025
Merged

feat: write manifest avro metadata #261

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c661697
feat: write manifest avro metadata
Oct 17, 2025
26d4a3f
add ToJsonString to avoid include nlohmann/json.hpp
Oct 17, 2025
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
10 changes: 9 additions & 1 deletion src/iceberg/avro/avro_writer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,8 +68,16 @@ class AvroWriter::Impl {
ICEBERG_ASSIGN_OR_RAISE(auto output_stream,
CreateOutputStream(options, kDefaultBufferSize));
arrow_output_stream_ = output_stream->arrow_output_stream();
std::map<std::string, std::vector<uint8_t>> metadata;
for (const auto& [key, value] : options.properties) {
std::vector<uint8_t> vec;
vec.reserve(value.size());
vec.assign(value.begin(), value.end());
metadata.emplace(key, std::move(vec));
}
writer_ = std::make_unique<::avro::DataFileWriter<::avro::GenericDatum>>(
std::move(output_stream), *avro_schema_);
std::move(output_stream), *avro_schema_, 16 * 1024 /*syncInterval*/,
::avro::NULL_CODEC /*codec*/, metadata);
datum_ = std::make_unique<::avro::GenericDatum>(*avro_schema_);
ICEBERG_RETURN_UNEXPECTED(ToArrowSchema(*write_schema_, &arrow_schema_));
return {};
Expand Down
3 changes: 3 additions & 0 deletions src/iceberg/manifest_adapter.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,9 @@ class ICEBERG_EXPORT ManifestAdapter {
Status StartAppending();
Result<ArrowArray*> FinishAppending();
int64_t size() const { return size_; }
const std::unordered_map<std::string, std::string>& metadata() const {
return metadata_;
}

protected:
ArrowArray array_;
Expand Down
52 changes: 27 additions & 25 deletions src/iceberg/manifest_writer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,14 +53,16 @@ Status ManifestWriter::Close() {
return writer_->Close();
}

Result<std::unique_ptr<Writer>> OpenFileWriter(std::string_view location,
std::shared_ptr<Schema> schema,
std::shared_ptr<FileIO> file_io) {
Result<std::unique_ptr<Writer>> OpenFileWriter(
std::string_view location, std::shared_ptr<Schema> schema,
std::shared_ptr<FileIO> file_io,
std::unordered_map<std::string, std::string> properties) {
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
WriterFactoryRegistry::Open(FileFormatType::kAvro, {.path = std::string(location),
.schema = std::move(schema),
.io = std::move(file_io)}));
auto writer, WriterFactoryRegistry::Open(FileFormatType::kAvro,
{.path = std::string(location),
.schema = std::move(schema),
.io = std::move(file_io),
.properties = std::move(properties)}));
return writer;
}

Expand All @@ -73,9 +75,9 @@ Result<std::unique_ptr<ManifestWriter>> ManifestWriter::MakeV1Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_location, std::move(schema),
std::move(file_io), adapter->metadata()));
return std::make_unique<ManifestWriter>(std::move(writer), std::move(adapter));
}

Expand All @@ -88,9 +90,9 @@ Result<std::unique_ptr<ManifestWriter>> ManifestWriter::MakeV2Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_location, std::move(schema),
std::move(file_io), adapter->metadata()));
return std::make_unique<ManifestWriter>(std::move(writer), std::move(adapter));
}

Expand All @@ -104,9 +106,9 @@ Result<std::unique_ptr<ManifestWriter>> ManifestWriter::MakeV3Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_location, std::move(schema),
std::move(file_io), adapter->metadata()));
return std::make_unique<ManifestWriter>(std::move(writer), std::move(adapter));
}

Expand Down Expand Up @@ -142,9 +144,9 @@ Result<std::unique_ptr<ManifestListWriter>> ManifestListWriter::MakeV1Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_list_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_list_location, std::move(schema),
std::move(file_io), adapter->metadata()));
return std::make_unique<ManifestListWriter>(std::move(writer), std::move(adapter));
}

Expand All @@ -158,9 +160,9 @@ Result<std::unique_ptr<ManifestListWriter>> ManifestListWriter::MakeV2Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_list_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_list_location, std::move(schema),
std::move(file_io), adapter->metadata()));

return std::make_unique<ManifestListWriter>(std::move(writer), std::move(adapter));
}
Expand All @@ -175,9 +177,9 @@ Result<std::unique_ptr<ManifestListWriter>> ManifestListWriter::MakeV3Writer(
ICEBERG_RETURN_UNEXPECTED(adapter->StartAppending());

auto schema = adapter->schema();
ICEBERG_ASSIGN_OR_RAISE(
auto writer,
OpenFileWriter(manifest_list_location, std::move(schema), std::move(file_io)));
ICEBERG_ASSIGN_OR_RAISE(auto writer,
OpenFileWriter(manifest_list_location, std::move(schema),
std::move(file_io), adapter->metadata()));
return std::make_unique<ManifestListWriter>(std::move(writer), std::move(adapter));
}

Expand Down
12 changes: 7 additions & 5 deletions src/iceberg/v1_metadata.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,9 @@

#include "iceberg/v1_metadata.h"

#include <nlohmann/json.hpp>

#include "iceberg/json_internal.h"
#include "iceberg/manifest_entry.h"
#include "iceberg/manifest_list.h"
#include "iceberg/schema.h"
Expand Down Expand Up @@ -47,15 +50,14 @@ Status ManifestEntryAdapterV1::Init() {
DataFile::kSplitOffsets.field_id(),
DataFile::kSortOrderId.field_id(),
};
// TODO(xiao.dong) schema to json
metadata_["schema"] = "{}";
// TODO(xiao.dong) partition spec to json
metadata_["partition-spec"] = "{}";
ICEBERG_RETURN_UNEXPECTED(InitSchema(kManifestEntryFieldIds));
metadata_["schema"] = ToJson(*manifest_schema_).dump();
if (partition_spec_ != nullptr) {
metadata_["partition-spec"] = ToJson(*partition_spec_).dump();
metadata_["partition-spec-id"] = std::to_string(partition_spec_->spec_id());
}
metadata_["format-version"] = "1";
return InitSchema(kManifestEntryFieldIds);
return {};
}

Status ManifestEntryAdapterV1::Append(const ManifestEntry& entry) {
Expand Down
13 changes: 8 additions & 5 deletions src/iceberg/v2_metadata.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,13 @@

#include "iceberg/v2_metadata.h"

#include <nlohmann/json.hpp>

#include "iceberg/json_internal.h"
#include "iceberg/manifest_entry.h"
#include "iceberg/manifest_list.h"
#include "iceberg/schema.h"
#include "iceberg/util/macros.h"

namespace iceberg {

Expand Down Expand Up @@ -50,16 +54,15 @@ Status ManifestEntryAdapterV2::Init() {
DataFile::kSortOrderId.field_id(),
DataFile::kReferencedDataFile.field_id(),
};
// TODO(xiao.dong) schema to json
metadata_["schema"] = "{}";
// TODO(xiao.dong) partition spec to json
metadata_["partition-spec"] = "{}";
ICEBERG_RETURN_UNEXPECTED(InitSchema(kManifestEntryFieldIds));
metadata_["schema"] = ToJson(*manifest_schema_).dump();
if (partition_spec_ != nullptr) {
metadata_["partition-spec"] = ToJson(*partition_spec_).dump();
metadata_["partition-spec-id"] = std::to_string(partition_spec_->spec_id());
}
metadata_["format-version"] = "2";
metadata_["content"] = "data";
return InitSchema(kManifestEntryFieldIds);
return {};
}

Status ManifestEntryAdapterV2::Append(const ManifestEntry& entry) {
Expand Down
12 changes: 7 additions & 5 deletions src/iceberg/v3_metadata.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,9 @@

#include "iceberg/v3_metadata.h"

#include <nlohmann/json.hpp>

#include "iceberg/json_internal.h"
#include "iceberg/manifest_entry.h"
#include "iceberg/manifest_list.h"
#include "iceberg/schema.h"
Expand Down Expand Up @@ -54,16 +57,15 @@ Status ManifestEntryAdapterV3::Init() {
DataFile::kContentOffset.field_id(),
DataFile::kContentSize.field_id(),
};
// TODO(xiao.dong) schema to json
metadata_["schema"] = "{}";
// TODO(xiao.dong) partition spec to json
metadata_["partition-spec"] = "{}";
ICEBERG_RETURN_UNEXPECTED(InitSchema(kManifestEntryFieldIds));
metadata_["schema"] = ToJson(*manifest_schema_).dump();
if (partition_spec_ != nullptr) {
metadata_["partition-spec"] = ToJson(*partition_spec_).dump();
metadata_["partition-spec-id"] = std::to_string(partition_spec_->spec_id());
}
metadata_["format-version"] = "3";
metadata_["content"] = "data";
return InitSchema(kManifestEntryFieldIds);
return {};
}

Status ManifestEntryAdapterV3::Append(const ManifestEntry& entry) {
Expand Down
Loading