dongxiao1198 commented on code in PR #143: URL: https://github.com/apache/iceberg-cpp/pull/143#discussion_r2203979933
########## src/iceberg/manifest_reader_internal.cc: ########## @@ -0,0 +1,233 @@ +/* + * 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 "manifest_reader_internal.h" + +#include <array> + +#include <nanoarrow/nanoarrow.h> + +#include "iceberg/arrow_c_data_guard_internal.h" +#include "iceberg/manifest_entry.h" +#include "iceberg/manifest_list.h" +#include "iceberg/schema.h" +#include "iceberg/schema_internal.h" +#include "iceberg/type.h" +#include "iceberg/util/macros.h" + +namespace iceberg { + +#define ARROW_RETURN_IF_NOT_OK(status, error) \ + if (status != NANOARROW_OK) [[unlikely]] { \ + return InvalidArrowData("Nanoarrow error: {}", error.message); \ + } + +Result<std::vector<ManifestFile>> ParseManifestListEntry(ArrowSchema* schema, + ArrowArray* array_in, + const Schema& iceberg_schema) { + if (schema->n_children != array_in->n_children) { + return InvalidArgument("Columns size not match between schema:{} and array:{}", + schema->n_children, array_in->n_children); + } + if (iceberg_schema.fields().size() != array_in->n_children) { + return InvalidArgument("Columns size not match between schema:{} and array:{}", + iceberg_schema.fields().size(), array_in->n_children); + } + + ArrowError error; + ArrowArrayView array_view; + auto status = ArrowArrayViewInitFromSchema(&array_view, schema, &error); + ARROW_RETURN_IF_NOT_OK(status, error); + internal::ArrowArrayViewGuard view_guard(&array_view); + status = ArrowArrayViewSetArray(&array_view, array_in, &error); + ARROW_RETURN_IF_NOT_OK(status, error); + status = ArrowArrayViewValidate(&array_view, NANOARROW_VALIDATION_LEVEL_FULL, &error); + ARROW_RETURN_IF_NOT_OK(status, error); + + std::vector<ManifestFile> manifest_files; + manifest_files.resize(array_in->length); + + for (int64_t idx = 0; idx < array_in->n_children; idx++) { + const auto& field = iceberg_schema.GetFieldByIndex(idx); + if (!field.has_value()) { + return InvalidArgument("Field not found in schema: {}", idx); + } + auto field_name = field.value().get().name(); + auto view_of_column = array_view.children[idx]; + +#define PARSE_PRIMITIVE_FIELD(field_name, type) \ + for (size_t row_idx = 0; row_idx < view_of_column->length; row_idx++) { \ + if (!ArrowArrayViewIsNull(view_of_column, row_idx)) { \ + auto value = ArrowArrayViewGetIntUnsafe(view_of_column, row_idx); \ + manifest_files[row_idx].field_name = static_cast<type>(value); \ + } \ + } + + if (field_name == ManifestFile::kManifestPath.name()) { + for (size_t row_idx = 0; row_idx < view_of_column->length; row_idx++) { + if (!ArrowArrayViewIsNull(view_of_column, row_idx)) { + auto value = ArrowArrayViewGetStringUnsafe(view_of_column, row_idx); + std::string path_str(value.data, value.size_bytes); + manifest_files[row_idx].manifest_path = path_str; + } + } + } else if (field_name == ManifestFile::kManifestLength.name()) { + PARSE_PRIMITIVE_FIELD(manifest_length, int64_t); + } else if (field_name == ManifestFile::kPartitionSpecId.name()) { + PARSE_PRIMITIVE_FIELD(partition_spec_id, int32_t); + } else if (field_name == ManifestFile::kContent.name()) { + for (size_t row_idx = 0; row_idx < view_of_column->length; row_idx++) { + if (!ArrowArrayViewIsNull(view_of_column, row_idx)) { + auto value = ArrowArrayViewGetIntUnsafe(view_of_column, row_idx); + manifest_files[row_idx].content = static_cast<ManifestFile::Content>(value); + } + } + } else if (field_name == ManifestFile::kSequenceNumber.name()) { + PARSE_PRIMITIVE_FIELD(sequence_number, int64_t); + } else if (field_name == ManifestFile::kMinSequenceNumber.name()) { + PARSE_PRIMITIVE_FIELD(min_sequence_number, int64_t); + } else if (field_name == ManifestFile::kAddedSnapshotId.name()) { + PARSE_PRIMITIVE_FIELD(added_snapshot_id, int64_t); + } else if (field_name == ManifestFile::kAddedFilesCount.name()) { + PARSE_PRIMITIVE_FIELD(added_files_count, int32_t); + } else if (field_name == ManifestFile::kExistingFilesCount.name()) { + PARSE_PRIMITIVE_FIELD(existing_files_count, int32_t); + } else if (field_name == ManifestFile::kDeletedFilesCount.name()) { + PARSE_PRIMITIVE_FIELD(deleted_files_count, int32_t); + } else if (field_name == ManifestFile::kAddedRowsCount.name()) { + PARSE_PRIMITIVE_FIELD(added_rows_count, int64_t); + } else if (field_name == ManifestFile::kExistingRowsCount.name()) { + PARSE_PRIMITIVE_FIELD(existing_rows_count, int64_t); + } else if (field_name == ManifestFile::kDeletedRowsCount.name()) { + PARSE_PRIMITIVE_FIELD(deleted_rows_count, int64_t); + } else if (field_name == ManifestFile::kPartitions.name()) { Review Comment: logical to parse std::vector<PartitionFieldSummary> partitions is really, i will make a new function for it. -- 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]
