wgtmac commented on code in PR #112: URL: https://github.com/apache/iceberg-cpp/pull/112#discussion_r2177702777
########## src/iceberg/table_scan.cc: ########## @@ -0,0 +1,286 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +#include "iceberg/table_scan.h" + +#include <algorithm> +#include <ranges> + +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/manifest_reader.h" +#include "iceberg/schema.h" +#include "iceberg/schema_field.h" +#include "iceberg/snapshot.h" +#include "iceberg/table.h" +#include "iceberg/table_metadata.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +namespace { +/// \brief Use indexed data structures for efficient lookups +struct DeleteFileIndex { + /// \brief Index by sequence number for quick filtering + std::multimap<int64_t, ManifestEntry*> sequence_index; + + /// \brief Build the index from a list of manifest entries. + void BuildIndex(const std::vector<std::unique_ptr<ManifestEntry>>& entries) { + sequence_index.clear(); + + for (const auto& entry : entries) { + const int64_t seq_num = + entry->sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + sequence_index.emplace(seq_num, entry.get()); + } + } + + /// \brief Find delete files that match the sequence number of a data entry. + std::vector<ManifestEntry*> FindRelevantEntries(const ManifestEntry& data_entry) const { + std::vector<ManifestEntry*> relevant_deletes; + + // Use lower_bound for efficient range search + auto data_sequence_number = + data_entry.sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + for (auto it = sequence_index.lower_bound(data_sequence_number); + it != sequence_index.end(); ++it) { + // Additional filtering logic here Review Comment: What is the additional filtering logic? Did you mean to further check if the delete files can be filtered? ########## src/iceberg/table_scan.cc: ########## @@ -0,0 +1,286 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +#include "iceberg/table_scan.h" + +#include <algorithm> +#include <ranges> + +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/manifest_reader.h" +#include "iceberg/schema.h" +#include "iceberg/schema_field.h" +#include "iceberg/snapshot.h" +#include "iceberg/table.h" +#include "iceberg/table_metadata.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +namespace { +/// \brief Use indexed data structures for efficient lookups +struct DeleteFileIndex { + /// \brief Index by sequence number for quick filtering + std::multimap<int64_t, ManifestEntry*> sequence_index; + + /// \brief Build the index from a list of manifest entries. + void BuildIndex(const std::vector<std::unique_ptr<ManifestEntry>>& entries) { + sequence_index.clear(); + + for (const auto& entry : entries) { + const int64_t seq_num = + entry->sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + sequence_index.emplace(seq_num, entry.get()); + } + } + + /// \brief Find delete files that match the sequence number of a data entry. + std::vector<ManifestEntry*> FindRelevantEntries(const ManifestEntry& data_entry) const { + std::vector<ManifestEntry*> relevant_deletes; + + // Use lower_bound for efficient range search + auto data_sequence_number = + data_entry.sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + for (auto it = sequence_index.lower_bound(data_sequence_number); + it != sequence_index.end(); ++it) { + // Additional filtering logic here + relevant_deletes.push_back(it->second); + } + + return relevant_deletes; + } +}; + +/// \brief Get matched delete files for a given data entry. +std::vector<std::shared_ptr<DataFile>> GetMatchedDeletes( + const ManifestEntry& data_entry, const DeleteFileIndex& delete_file_index) { + const auto relevant_entries = delete_file_index.FindRelevantEntries(data_entry); + std::vector<std::shared_ptr<DataFile>> matched_deletes; + if (relevant_entries.empty()) { + return matched_deletes; + } + + matched_deletes.reserve(relevant_entries.size()); + for (const auto& delete_entry : relevant_entries) { + // TODO(gty404): check if the delete entry contains the data entry's file path + matched_deletes.emplace_back(delete_entry->data_file); + } + return matched_deletes; +} +} // namespace + +// implement FileScanTask +FileScanTask::FileScanTask(std::shared_ptr<DataFile> file, + std::vector<std::shared_ptr<DataFile>> delete_files, + int64_t start, int64_t length, + std::shared_ptr<Expression> residual) + : data_file_(std::move(file)), + delete_files_(std::move(delete_files)), + start_(start), + length_(length), + residual_(std::move(residual)) {} + +const std::shared_ptr<DataFile>& FileScanTask::data_file() const { return data_file_; } + +const std::vector<std::shared_ptr<DataFile>>& FileScanTask::delete_files() const { + return delete_files_; +} + +int64_t FileScanTask::start() const { return start_; } + +int64_t FileScanTask::length() const { return length_; } + +int64_t FileScanTask::size_bytes() const { Review Comment: ```suggestion int64_t FileScanTask::SizeBytes() const { ``` This is not trivial. ########## src/iceberg/table_scan.cc: ########## @@ -0,0 +1,286 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +#include "iceberg/table_scan.h" + +#include <algorithm> +#include <ranges> + +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/manifest_reader.h" +#include "iceberg/schema.h" +#include "iceberg/schema_field.h" +#include "iceberg/snapshot.h" +#include "iceberg/table.h" +#include "iceberg/table_metadata.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +namespace { +/// \brief Use indexed data structures for efficient lookups +struct DeleteFileIndex { + /// \brief Index by sequence number for quick filtering + std::multimap<int64_t, ManifestEntry*> sequence_index; + + /// \brief Build the index from a list of manifest entries. + void BuildIndex(const std::vector<std::unique_ptr<ManifestEntry>>& entries) { + sequence_index.clear(); + + for (const auto& entry : entries) { + const int64_t seq_num = + entry->sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + sequence_index.emplace(seq_num, entry.get()); + } + } + + /// \brief Find delete files that match the sequence number of a data entry. + std::vector<ManifestEntry*> FindRelevantEntries(const ManifestEntry& data_entry) const { + std::vector<ManifestEntry*> relevant_deletes; + + // Use lower_bound for efficient range search + auto data_sequence_number = + data_entry.sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + for (auto it = sequence_index.lower_bound(data_sequence_number); + it != sequence_index.end(); ++it) { + // Additional filtering logic here + relevant_deletes.push_back(it->second); + } + + return relevant_deletes; + } +}; + +/// \brief Get matched delete files for a given data entry. +std::vector<std::shared_ptr<DataFile>> GetMatchedDeletes( + const ManifestEntry& data_entry, const DeleteFileIndex& delete_file_index) { + const auto relevant_entries = delete_file_index.FindRelevantEntries(data_entry); + std::vector<std::shared_ptr<DataFile>> matched_deletes; + if (relevant_entries.empty()) { + return matched_deletes; + } + + matched_deletes.reserve(relevant_entries.size()); + for (const auto& delete_entry : relevant_entries) { + // TODO(gty404): check if the delete entry contains the data entry's file path + matched_deletes.emplace_back(delete_entry->data_file); + } + return matched_deletes; +} +} // namespace + +// implement FileScanTask +FileScanTask::FileScanTask(std::shared_ptr<DataFile> file, + std::vector<std::shared_ptr<DataFile>> delete_files, + int64_t start, int64_t length, + std::shared_ptr<Expression> residual) + : data_file_(std::move(file)), + delete_files_(std::move(delete_files)), + start_(start), + length_(length), + residual_(std::move(residual)) {} + +const std::shared_ptr<DataFile>& FileScanTask::data_file() const { return data_file_; } + +const std::vector<std::shared_ptr<DataFile>>& FileScanTask::delete_files() const { + return delete_files_; +} + +int64_t FileScanTask::start() const { return start_; } + +int64_t FileScanTask::length() const { return length_; } + +int64_t FileScanTask::size_bytes() const { + int64_t sizeInBytes = length_; + std::ranges::for_each(delete_files_, [&sizeInBytes](const auto& delete_file) { + sizeInBytes += delete_file->file_size_in_bytes; + }); + return sizeInBytes; +} + +int32_t FileScanTask::files_count() const { Review Comment: I'm not sure if we need to rename it to `FilesCount()`. @lidavidm suggestion? ########## src/iceberg/table_scan.cc: ########## @@ -0,0 +1,286 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +#include "iceberg/table_scan.h" + +#include <algorithm> +#include <ranges> + +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/manifest_reader.h" +#include "iceberg/schema.h" +#include "iceberg/schema_field.h" +#include "iceberg/snapshot.h" +#include "iceberg/table.h" +#include "iceberg/table_metadata.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +namespace { +/// \brief Use indexed data structures for efficient lookups +struct DeleteFileIndex { + /// \brief Index by sequence number for quick filtering + std::multimap<int64_t, ManifestEntry*> sequence_index; + + /// \brief Build the index from a list of manifest entries. + void BuildIndex(const std::vector<std::unique_ptr<ManifestEntry>>& entries) { + sequence_index.clear(); + + for (const auto& entry : entries) { + const int64_t seq_num = + entry->sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + sequence_index.emplace(seq_num, entry.get()); + } + } + + /// \brief Find delete files that match the sequence number of a data entry. + std::vector<ManifestEntry*> FindRelevantEntries(const ManifestEntry& data_entry) const { + std::vector<ManifestEntry*> relevant_deletes; + + // Use lower_bound for efficient range search + auto data_sequence_number = + data_entry.sequence_number.value_or(TableMetadata::kInitialSequenceNumber); + for (auto it = sequence_index.lower_bound(data_sequence_number); + it != sequence_index.end(); ++it) { + // Additional filtering logic here + relevant_deletes.push_back(it->second); + } + + return relevant_deletes; + } +}; + +/// \brief Get matched delete files for a given data entry. +std::vector<std::shared_ptr<DataFile>> GetMatchedDeletes( + const ManifestEntry& data_entry, const DeleteFileIndex& delete_file_index) { + const auto relevant_entries = delete_file_index.FindRelevantEntries(data_entry); + std::vector<std::shared_ptr<DataFile>> matched_deletes; + if (relevant_entries.empty()) { + return matched_deletes; + } + + matched_deletes.reserve(relevant_entries.size()); + for (const auto& delete_entry : relevant_entries) { + // TODO(gty404): check if the delete entry contains the data entry's file path + matched_deletes.emplace_back(delete_entry->data_file); + } + return matched_deletes; +} +} // namespace + +// implement FileScanTask +FileScanTask::FileScanTask(std::shared_ptr<DataFile> file, + std::vector<std::shared_ptr<DataFile>> delete_files, + int64_t start, int64_t length, + std::shared_ptr<Expression> residual) + : data_file_(std::move(file)), + delete_files_(std::move(delete_files)), + start_(start), + length_(length), + residual_(std::move(residual)) {} + +const std::shared_ptr<DataFile>& FileScanTask::data_file() const { return data_file_; } + +const std::vector<std::shared_ptr<DataFile>>& FileScanTask::delete_files() const { + return delete_files_; +} + +int64_t FileScanTask::start() const { return start_; } + +int64_t FileScanTask::length() const { return length_; } + +int64_t FileScanTask::size_bytes() const { + int64_t sizeInBytes = length_; + std::ranges::for_each(delete_files_, [&sizeInBytes](const auto& delete_file) { + sizeInBytes += delete_file->file_size_in_bytes; + }); + return sizeInBytes; +} + +int32_t FileScanTask::files_count() const { + return static_cast<int32_t>(delete_files_.size() + 1); +} + +int64_t FileScanTask::estimated_row_count() const { Review Comment: ditto ########## src/iceberg/table_scan.cc: ########## @@ -0,0 +1,286 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +#include "iceberg/table_scan.h" + +#include <algorithm> +#include <ranges> + +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/manifest_reader.h" +#include "iceberg/schema.h" +#include "iceberg/schema_field.h" +#include "iceberg/snapshot.h" +#include "iceberg/table.h" +#include "iceberg/table_metadata.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +namespace { +/// \brief Use indexed data structures for efficient lookups +struct DeleteFileIndex { + /// \brief Index by sequence number for quick filtering + std::multimap<int64_t, ManifestEntry*> sequence_index; + + /// \brief Build the index from a list of manifest entries. + void BuildIndex(const std::vector<std::unique_ptr<ManifestEntry>>& entries) { + sequence_index.clear(); Review Comment: Is `DeleteFileIndex` supposed to be reused? Does it make sense to make `BuildIndex` private and call it from the ctor? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
