ahmedabu98 commented on code in PR #33504: URL: https://github.com/apache/beam/pull/33504#discussion_r1981956572
########## sdks/java/io/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/ReadUtils.java: ########## @@ -0,0 +1,296 @@ +/* + * 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. + */ +package org.apache.beam.sdk.io.iceberg; + +import static org.apache.beam.sdk.util.Preconditions.checkStateNotNull; +import static org.apache.iceberg.util.SnapshotUtil.ancestorsOf; + +import java.nio.ByteBuffer; +import java.util.Collection; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.concurrent.TimeUnit; +import java.util.function.BiFunction; +import java.util.stream.Collectors; +import org.apache.beam.sdk.io.iceberg.IcebergIO.ReadRows.StartingStrategy; +import org.apache.beam.sdk.schemas.Schema; +import org.apache.beam.sdk.transforms.DoFn; +import org.apache.beam.sdk.transforms.PTransform; +import org.apache.beam.sdk.transforms.ParDo; +import org.apache.beam.sdk.transforms.windowing.BoundedWindow; +import org.apache.beam.sdk.values.PCollection; +import org.apache.beam.sdk.values.Row; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.MoreObjects; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.Preconditions; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Lists; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Sets; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.data.IdentityPartitionConverters; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.encryption.EncryptedFiles; +import org.apache.iceberg.encryption.EncryptedInputFile; +import org.apache.iceberg.hadoop.HadoopInputFile; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.mapping.NameMappingParser; +import org.apache.iceberg.parquet.ParquetReader; +import org.apache.iceberg.types.Conversions; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.PartitionUtil; +import org.apache.iceberg.util.SnapshotUtil; +import org.apache.parquet.HadoopReadOptions; +import org.apache.parquet.ParquetReadOptions; +import org.checkerframework.checker.nullness.qual.Nullable; +import org.joda.time.Instant; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Helper class for source operations. */ +public class ReadUtils { + private static final Logger LOG = LoggerFactory.getLogger(ReadUtils.class); + + // default is 8MB. keep this low to avoid overwhelming memory + static final int MAX_FILE_BUFFER_SIZE = 1 << 20; // 1MB + private static final Collection<String> READ_PROPERTIES_TO_REMOVE = + Sets.newHashSet( + "parquet.read.filter", + "parquet.private.read.filter.predicate", + "parquet.read.support.class", + "parquet.crypto.factory.class"); + static final String OPERATION = "operation"; + static final String RECORD = "record"; + static final String DEFAULT_WATERMARK_TIME_UNIT = TimeUnit.MICROSECONDS.name(); + + /** Extracts {@link Row}s after a CDC streaming read. */ + public static PTransform<PCollection<Row>, PCollection<Row>> extractRecords() { + return new ExtractRecords(); + } + + public static Schema outputCdcSchema(Schema tableSchema) { + return Schema.builder() + .addRowField(RECORD, tableSchema) + .addNullableStringField(OPERATION) + .build(); + } + + public static Schema outputCdcSchema(org.apache.iceberg.Schema tableSchema) { + return outputCdcSchema(IcebergUtils.icebergSchemaToBeamSchema(tableSchema)); + } + + static ParquetReader<Record> createReader(FileScanTask task, Table table) { + String filePath = task.file().path().toString(); + InputFile inputFile; + try (FileIO io = table.io()) { + EncryptedInputFile encryptedInput = + EncryptedFiles.encryptedInput(io.newInputFile(filePath), task.file().keyMetadata()); + inputFile = table.encryption().decrypt(encryptedInput); + } + Map<Integer, ?> idToConstants = + ReadUtils.constantsMap(task, IdentityPartitionConverters::convertConstant, table.schema()); + + ParquetReadOptions.Builder optionsBuilder; + if (inputFile instanceof HadoopInputFile) { + // remove read properties already set that may conflict with this read + Configuration conf = new Configuration(((HadoopInputFile) inputFile).getConf()); + for (String property : READ_PROPERTIES_TO_REMOVE) { + conf.unset(property); + } + optionsBuilder = HadoopReadOptions.builder(conf); + } else { + optionsBuilder = ParquetReadOptions.builder(); + } + optionsBuilder = + optionsBuilder + .withRange(task.start(), task.start() + task.length()) + .withMaxAllocationInBytes(MAX_FILE_BUFFER_SIZE); + + @Nullable String nameMapping = table.properties().get(TableProperties.DEFAULT_NAME_MAPPING); + NameMapping mapping = + nameMapping != null ? NameMappingParser.fromJson(nameMapping) : NameMapping.empty(); + + return new ParquetReader<>( + inputFile, + table.schema(), + optionsBuilder.build(), + fileSchema -> GenericParquetReaders.buildReader(table.schema(), fileSchema, idToConstants), + mapping, + task.residual(), + false, + true); + } + + static Map<Integer, ?> constantsMap( + FileScanTask task, + BiFunction<Type, Object, Object> converter, + org.apache.iceberg.Schema schema) { + PartitionSpec spec = task.spec(); + Set<Integer> idColumns = spec.identitySourceIds(); + org.apache.iceberg.Schema partitionSchema = TypeUtil.select(schema, idColumns); + boolean projectsIdentityPartitionColumns = !partitionSchema.columns().isEmpty(); + + if (projectsIdentityPartitionColumns) { + return PartitionUtil.constantsMap(task, converter); + } else { + return Collections.emptyMap(); + } + } + + static @Nullable Long getFromSnapshotExclusive(Table table, IcebergScanConfig scanConfig) { + @Nullable StartingStrategy startingStrategy = scanConfig.getStartingStrategy(); + boolean isStreaming = MoreObjects.firstNonNull(scanConfig.getStreaming(), false); + if (startingStrategy == null) { + startingStrategy = isStreaming ? StartingStrategy.LATEST : StartingStrategy.EARLIEST; + } + + // 1. fetch from from_snapshot + @Nullable Long fromSnapshot = scanConfig.getFromSnapshotInclusive(); + // 2. fetch from from_timestamp + @Nullable Long fromTimestamp = scanConfig.getFromTimestamp(); + if (fromTimestamp != null) { + fromSnapshot = SnapshotUtil.oldestAncestorAfter(table, fromTimestamp).snapshotId(); + } + // 3. get current snapshot if starting_strategy is LATEST + if (fromSnapshot == null && startingStrategy.equals(StartingStrategy.LATEST)) { + fromSnapshot = table.currentSnapshot().snapshotId(); + } Review Comment: Done -- 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: github-unsubscr...@beam.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
