lirui-apache commented on a change in pull request #11942: URL: https://github.com/apache/flink/pull/11942#discussion_r417264432
########## File path: flink-formats/flink-orc/src/main/java/org/apache/flink/orc/OrcFileSystemFormatFactory.java ########## @@ -0,0 +1,230 @@ +/* + * 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.flink.orc; + +import org.apache.flink.api.common.io.FileInputFormat; +import org.apache.flink.api.common.io.InputFormat; +import org.apache.flink.api.common.serialization.BulkWriter; +import org.apache.flink.api.common.serialization.Encoder; +import org.apache.flink.core.fs.FileInputSplit; +import org.apache.flink.core.fs.Path; +import org.apache.flink.orc.vector.RowDataVectorizer; +import org.apache.flink.orc.writer.OrcBulkWriterFactory; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.descriptors.DescriptorProperties; +import org.apache.flink.table.factories.FileSystemFormatFactory; +import org.apache.flink.table.filesystem.PartitionPathUtils; +import org.apache.flink.table.types.DataType; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.table.types.logical.RowType; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.orc.TypeDescription; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.Optional; +import java.util.Properties; + +import static org.apache.flink.table.data.vector.VectorizedColumnBatch.DEFAULT_SIZE; +import static org.apache.flink.table.descriptors.FormatDescriptorValidator.FORMAT; +import static org.apache.flink.table.filesystem.RowPartitionComputer.restorePartValueFromType; + +/** + * Orc {@link FileSystemFormatFactory} for file system. + */ +public class OrcFileSystemFormatFactory implements FileSystemFormatFactory { + + /** + * Prefix for orc-related properties, besides format, start with "orc". + * See more in {@link org.apache.orc.OrcConf}. + */ + public static final String ORC_PROPERTIES = "format.orc"; Review comment: rename to `ORC_PROPERTY_PREFIX`? ########## File path: flink-formats/flink-orc/src/main/java/org/apache/flink/orc/vector/RowDataVectorizer.java ########## @@ -0,0 +1,144 @@ +/* + * 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.flink.orc.vector; + +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.types.logical.DecimalType; +import org.apache.flink.table.types.logical.LocalZonedTimestampType; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.table.types.logical.TimestampType; + +import org.apache.hadoop.hive.common.type.HiveDecimal; +import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.ColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; + +import java.sql.Timestamp; + +/** + * A {@link Vectorizer} of {@link RowData} type element. + */ +public class RowDataVectorizer extends Vectorizer<RowData> { + + private final LogicalType[] fieldTypes; + + public RowDataVectorizer(String schema, LogicalType[] fieldTypes) { + super(schema); + this.fieldTypes = fieldTypes; + } + + @Override + public void vectorize(RowData row, VectorizedRowBatch batch) { + int rowId = batch.size++; + for(int i = 0; i < row.getArity(); ++i) { + setColumn(rowId, batch.cols[i], fieldTypes[i], row, i); + } + } + + private static void setColumn( + int rowId, ColumnVector column, LogicalType type, RowData row, int i) { Review comment: rename i to `columnId`? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
