zhztheplayer commented on code in PR #11373: URL: https://github.com/apache/incubator-gluten/pull/11373#discussion_r2687457745
########## tools/gluten-it/common/src/main/scala/org/apache/gluten/integration/hdfs/HdfsTableCreator.scala: ########## @@ -0,0 +1,71 @@ +/* + * 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.gluten.integration.hdfs + +import org.apache.spark.sql.{AnalysisException, SparkSession} + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.{FileSystem, Path} + +import java.net.URI + +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +object HdfsTableCreator { + + def create(spark: SparkSession, source: String, dataPath: String): Unit = { + val uri = URI.create(dataPath) + val fs = FileSystem.get(uri, new Configuration()) + + val basePath = new Path(dataPath) + val statuses = fs.listStatus(basePath) + + val tableDirs = statuses.filter(_.isDirectory).map(_.getPath) + + val tableNames = ArrayBuffer[String]() + + val existedTableNames = mutable.ArrayBuffer[String]() + val createdTableNames = mutable.ArrayBuffer[String]() + val recoveredPartitionTableNames = mutable.ArrayBuffer[String]() Review Comment: @infvg Thanks for iterating. The approach looks much better to me know. Now, can we unify `HdfsTableCreator` and the local implementation `DiscoverSchema`? The HDFS APIs you are calling in `HdfsTableCreator` should work for local files as well. ########## tools/gluten-it/common/src/main/scala/org/apache/gluten/integration/hdfs/HdfsTableCreator.scala: ########## @@ -0,0 +1,71 @@ +/* + * 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.gluten.integration.hdfs + +import org.apache.spark.sql.{AnalysisException, SparkSession} + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.{FileSystem, Path} + +import java.net.URI + +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +object HdfsTableCreator { + + def create(spark: SparkSession, source: String, dataPath: String): Unit = { + val uri = URI.create(dataPath) + val fs = FileSystem.get(uri, new Configuration()) + + val basePath = new Path(dataPath) + val statuses = fs.listStatus(basePath) + + val tableDirs = statuses.filter(_.isDirectory).map(_.getPath) + + val tableNames = ArrayBuffer[String]() + + val existedTableNames = mutable.ArrayBuffer[String]() + val createdTableNames = mutable.ArrayBuffer[String]() + val recoveredPartitionTableNames = mutable.ArrayBuffer[String]() Review Comment: @infvg Thanks for iterating. The approach looks much better to me now. Now, can we unify `HdfsTableCreator` and the local implementation `DiscoverSchema`? The HDFS APIs you are calling in `HdfsTableCreator` should work for local files as well. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
