kevincmchen commented on a change in pull request #31560: URL: https://github.com/apache/spark/pull/31560#discussion_r579631281
########## File path: sql/core/src/test/java/test/org/apache/spark/sql/connector/JavaSimpleWritableDataSource.java ########## @@ -0,0 +1,370 @@ +/* + * 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 java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStreamReader; +import java.util.Arrays; +import java.util.Iterator; + +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.SimpleCounter; +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; + +/** + * A HDFS based transactional writable data source which is implemented by java. + * Each task writes data to `target/_temporary/uniqueId/$jobId-$partitionId-$attemptNumber`. + * Each job moves files from `target/_temporary/uniqueId/` to `target`. + */ +public class JavaSimpleWritableDataSource implements TestingV2Source, SessionConfigSupport { + + private final StructType tableSchema = new StructType().add("i", "long").add("j", "long"); + + @Override + public String keyPrefix() { + return "javaSimpleWritableDataSource"; + } + + 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 (IOException e) { + throw new RuntimeException(e); Review comment: I feel the same. ########## 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 { Review comment: I have already fixed it, thx a lot. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
