Skip to content
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
25 changes: 25 additions & 0 deletions src/iceberg/avro/avro_reader.cc
Original file line number Diff line number Diff line change
Expand Up @@ -173,6 +173,27 @@ class AvroReader::Impl {
return arrow_schema;
}

Result<std::unordered_map<std::string, std::string>> Metadata() {
if (reader_ == nullptr) {
return Invalid("Reader is not opened");
}

const auto& metadata = reader_->metadata();

std::unordered_map<std::string, std::string> metadata_map;
metadata_map.reserve(metadata.size());

for (const auto& pair : metadata) {
auto [it, inserted] = metadata_map.try_emplace(
pair.first, std::string(pair.second.begin(), pair.second.end()));
if (!inserted) {
return Invalid("Duplicate metadata key found: {}", pair.first);
}
}

return metadata_map;
}

private:
Status InitReadContext() {
context_ = std::make_unique<ReadContext>();
Expand Down Expand Up @@ -241,6 +262,10 @@ Result<std::optional<ArrowArray>> AvroReader::Next() { return impl_->Next(); }

Result<ArrowSchema> AvroReader::Schema() { return impl_->Schema(); }

Result<std::unordered_map<std::string, std::string>> AvroReader::Metadata() {
return impl_->Metadata();
}

Status AvroReader::Open(const ReaderOptions& options) {
impl_ = std::make_unique<Impl>();
return impl_->Open(options);
Expand Down
2 changes: 2 additions & 0 deletions src/iceberg/avro/avro_reader.h
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,8 @@ class ICEBERG_BUNDLE_EXPORT AvroReader : public Reader {

Result<ArrowSchema> Schema() final;

Result<std::unordered_map<std::string, std::string>> Metadata() final;

private:
class Impl;
std::unique_ptr<Impl> impl_;
Expand Down
3 changes: 3 additions & 0 deletions src/iceberg/file_reader.h
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,9 @@ class ICEBERG_EXPORT Reader {

/// \brief Get the schema of the data.
virtual Result<ArrowSchema> Schema() = 0;

/// \brief Get the metadata of the file
virtual Result<std::unordered_map<std::string, std::string>> Metadata() = 0;
};

/// \brief A split of the file to read.
Expand Down
34 changes: 34 additions & 0 deletions src/iceberg/parquet/parquet_reader.cc
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
#include <arrow/record_batch.h>
#include <arrow/result.h>
#include <arrow/type.h>
#include <arrow/util/key_value_metadata.h>
#include <parquet/arrow/reader.h>
#include <parquet/arrow/schema.h>
#include <parquet/file_reader.h>
Expand Down Expand Up @@ -185,6 +186,35 @@ class ParquetReader::Impl {
return arrow_schema;
}

Result<std::unordered_map<std::string, std::string>> Metadata() {
if (reader_ == nullptr) {
return Invalid("Reader is not opened");
}

auto metadata = reader_->parquet_reader()->metadata();
if (!metadata) {
return Invalid("Failed to get Parquet file metadata");
}

const auto& kv_metadata = metadata->key_value_metadata();
if (!kv_metadata) {
return std::unordered_map<std::string, std::string>{};
}

std::unordered_map<std::string, std::string> metadata_map;
metadata_map.reserve(kv_metadata->size());

for (int i = 0; i < kv_metadata->size(); ++i) {
auto [it, inserted] =
metadata_map.try_emplace(kv_metadata->key(i), kv_metadata->value(i));
if (!inserted) {
return Invalid("Duplicate metadata key found: {}", kv_metadata->key(i));
}
}

return metadata_map;
}

private:
Status InitReadContext() {
context_ = std::make_unique<ReadContext>();
Expand Down Expand Up @@ -251,6 +281,10 @@ Result<std::optional<ArrowArray>> ParquetReader::Next() { return impl_->Next();

Result<ArrowSchema> ParquetReader::Schema() { return impl_->Schema(); }

Result<std::unordered_map<std::string, std::string>> ParquetReader::Metadata() {
return impl_->Metadata();
}

Status ParquetReader::Open(const ReaderOptions& options) {
impl_ = std::make_unique<Impl>();
return impl_->Open(options);
Expand Down
2 changes: 2 additions & 0 deletions src/iceberg/parquet/parquet_reader.h
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,8 @@ class ICEBERG_BUNDLE_EXPORT ParquetReader : public Reader {

Result<ArrowSchema> Schema() final;

Result<std::unordered_map<std::string, std::string>> Metadata() final;

private:
class Impl;
std::unique_ptr<Impl> impl_;
Expand Down
Loading