dongjoon-hyun commented on a change in pull request #31560: URL: https://github.com/apache/spark/pull/31560#discussion_r577344791
########## File path: sql/core/src/test/java/test/org/apache/spark/sql/connector/JavaSimpleWritableDataSource.java ########## @@ -0,0 +1,374 @@ +/* + * 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 test.org.apache.spark.sql.connector; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.*; +import org.apache.spark.deploy.SparkHadoopUtil; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.catalyst.expressions.GenericInternalRow; +import org.apache.spark.sql.connector.TestingV2Source; +import org.apache.spark.sql.connector.catalog.SessionConfigSupport; +import org.apache.spark.sql.connector.catalog.SupportsWrite; +import org.apache.spark.sql.connector.catalog.Table; +import org.apache.spark.sql.connector.read.InputPartition; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.apache.spark.sql.connector.read.PartitionReaderFactory; +import org.apache.spark.sql.connector.read.ScanBuilder; +import org.apache.spark.sql.connector.write.*; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.util.CaseInsensitiveStringMap; +import org.apache.spark.util.SerializableConfiguration; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStreamReader; +import java.util.Arrays; +import java.util.Iterator; + +public class JavaSimpleWritableDataSource implements TestingV2Source, SessionConfigSupport { + + private final StructType tableSchema = new StructType().add("i", "long").add("j", "long"); + + @Override + public String keyPrefix() { + return "javaSimpleWritableDataSource"; + } + + @Override + public Table getTable(CaseInsensitiveStringMap options) { + return new MyTable(options); + } + + static class JavaCSVInputPartitionReader implements InputPartition { + private String path; + + JavaCSVInputPartitionReader(String path) { + this.path = path; + } + + public String getPath() { + return path; + } + + public void setPath(String path) { + this.path = path; + } + } + + static class JavaCSVReaderFactory implements PartitionReaderFactory { + + private final SerializableConfiguration conf; + + JavaCSVReaderFactory(SerializableConfiguration conf) { + this.conf = conf; + } + + @Override + public PartitionReader<InternalRow> createReader(InputPartition partition) { + String path = ((JavaCSVInputPartitionReader) partition).getPath(); + Path filePath = new Path(path); + try { + FileSystem fs = filePath.getFileSystem(conf.value()); + return new PartitionReader<InternalRow>() { + private final FSDataInputStream inputStream = fs.open(filePath); + private final Iterator<String> lines = + new BufferedReader(new InputStreamReader(inputStream)).lines().iterator(); + private String currentLine = ""; + + @Override + public boolean next() { + if (lines.hasNext()) { + currentLine = lines.next(); + return true; + } else { + return false; + } + } + + @Override + public InternalRow get() { + Object[] objects = + Arrays.stream(currentLine.split(",")) + .map(String::trim) + .map(Long::parseLong) + .toArray(); + return new GenericInternalRow(objects); + } + + @Override + public void close() throws IOException { + inputStream.close(); + } + }; + } catch (IOException e) { + throw new RuntimeException(e); + } + } + } + + static class JavaSimpleCounter { + private static Integer count = 0; + + public static void increaseCounter() { + count += 1; + } + + public static int getCounter() { + return count; + } + + public static void resetCounter() { + count = 0; + } + } + + static class JavaCSVDataWriterFactory implements DataWriterFactory { + private final String path; + private final String jobId; + private final SerializableConfiguration conf; + + JavaCSVDataWriterFactory(String path, String jobId, SerializableConfiguration conf) { + this.path = path; + this.jobId = jobId; + this.conf = conf; + } + + @Override + public DataWriter<InternalRow> createWriter(int partitionId, long taskId) { + try { + Path jobPath = new Path(new Path(path, "_temporary"), jobId); + Path filePath = new Path(jobPath, String.format("%s-%d-%d", jobId, partitionId, taskId)); + FileSystem fs = filePath.getFileSystem(conf.value()); + return new JavaCSVDataWriter(fs, filePath); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + } + + static class JavaCSVDataWriter implements DataWriter<InternalRow> { + private final FileSystem fs; + private final Path file; + private final FSDataOutputStream out; + + JavaCSVDataWriter(FileSystem fs, Path file) throws IOException { + this.fs = fs; + this.file = file; + out = fs.create(file); + } + + @Override + public void write(InternalRow record) throws IOException { + out.writeBytes(String.format("%d,%d\n", record.getLong(0), record.getLong(1))); + } + + @Override + public WriterCommitMessage commit() throws IOException { + out.close(); + return null; + } + + @Override + public void abort() throws IOException { + try { + out.close(); + } finally { + fs.delete(file, false); + } + } + + @Override + public void close() {} + } + + class MyScanBuilder extends JavaSimpleScanBuilder { + private final String path; + private final Configuration conf; + + MyScanBuilder(String path, Configuration conf) { + this.path = path; + this.conf = conf; + } + + @Override + public InputPartition[] planInputPartitions() { + Path dataPath = new Path(this.path); + try { + FileSystem fs = dataPath.getFileSystem(conf); + if (fs.exists(dataPath)) { + return Arrays.stream(fs.listStatus(dataPath)) + .filter( + status -> { + String name = status.getPath().getName(); + return !name.startsWith("_") && !name.startsWith("."); + }) + .map(f -> new JavaCSVInputPartitionReader(f.getPath().toUri().toString())) + .toArray(InputPartition[]::new); + } else { + return new InputPartition[0]; + } + } catch (Exception e) { Review comment: This test case can be a reference model for the other developers. Are you suggesting `Java Data Source` should follow this kind of `Exception` wrapping? ---------------------------------------------------------------- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
