connector/read/PartitionReader.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.sql.connector.read;
0019
0020 import java.io.Closeable;
0021 import java.io.IOException;
0022
0023 import org.apache.spark.annotation.Evolving;
0024
0025 /**
0026  * A partition reader returned by {@link PartitionReaderFactory#createReader(InputPartition)} or
0027  * {@link PartitionReaderFactory#createColumnarReader(InputPartition)}. It's responsible for
0028  * outputting data for a RDD partition.
0029  *
0030  * Note that, Currently the type `T` can only be {@link org.apache.spark.sql.catalyst.InternalRow}
0031  * for normal data sources, or {@link org.apache.spark.sql.vectorized.ColumnarBatch} for columnar
0032  * data sources(whose {@link PartitionReaderFactory#supportColumnarReads(InputPartition)}
0033  * returns true).
0034  *
0035  * @since 3.0.0
0036  */
0037 @Evolving
0038 public interface PartitionReader<T> extends Closeable {
0039
0040   /**
0041    * Proceed to next record, returns false if there is no more records.
0042    *
0043    * @throws IOException if failure happens during disk/network IO like reading files.
0044    */
0045   boolean next() throws IOException;
0046
0047   /**
0048    * Return the current record. This method should return same value until `next` is called.
0049    */
0050   T get();
0051 }