spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From gatorsmile <...@git.apache.org>
Subject [GitHub] spark pull request #18975: [SPARK-4131] Support "Writing data into the files...
Date Mon, 04 Sep 2017 03:26:20 GMT
Github user gatorsmile commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18975#discussion_r136739126
  
    --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveDirCommand.scala
---
    @@ -0,0 +1,145 @@
    +/*
    + * 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.spark.sql.hive.execution
    +
    +import scala.language.existentials
    +
    +import org.apache.hadoop.fs.{FileSystem, Path}
    +import org.apache.hadoop.hive.common.FileUtils
    +import org.apache.hadoop.hive.ql.plan.TableDesc
    +import org.apache.hadoop.hive.serde.serdeConstants
    +import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe
    +import org.apache.hadoop.mapred._
    +
    +import org.apache.spark.sql.{Row, SparkSession}
    +import org.apache.spark.sql.catalyst.TableIdentifier
    +import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable}
    +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
    +import org.apache.spark.sql.execution.SparkPlan
    +import org.apache.spark.sql.hive.client.HiveClientImpl
    +
    +/**
    + * Command for writing the results of `query` to file system.
    + *
    + * The syntax of using this command in SQL is:
    + * {{{
    + *   INSERT OVERWRITE [LOCAL] DIRECTORY
    + *   path
    + *   [ROW FORMAT row_format]
    + *   [STORED AS file_format]
    + *   SELECT ...
    + * }}}
    + *
    + * @param isLocal whether the path specified in `storage` is a local directory
    + * @param storage storage format used to describe how the query result is stored.
    + * @param query the logical plan representing data to write to
    + * @param overwrite whthere overwrites existing directory
    + */
    +case class InsertIntoHiveDirCommand(
    +    isLocal: Boolean,
    +    storage: CatalogStorageFormat,
    +    query: LogicalPlan,
    +    overwrite: Boolean) extends SaveAsHiveFile {
    +
    +  override def children: Seq[LogicalPlan] = query :: Nil
    +
    +  override def run(sparkSession: SparkSession, children: Seq[SparkPlan]): Seq[Row] =
{
    +    assert(children.length == 1)
    +    assert(storage.locationUri.nonEmpty)
    +
    +//    val Array(cols, types) = children.head.output.foldLeft(Array("", "")) { case (r,
a) =>
    +//      r(0) = r(0) + a.name + ","
    +//      r(1) = r(1) + a.dataType.catalogString + ":"
    +//      r
    +//    }
    +//
    +//    val properties = new Properties()
    +//    properties.put("columns", cols.dropRight(1))
    +//    properties.put("columns.types", types.dropRight(1))
    +//    properties.put(serdeConstants.SERIALIZATION_LIB,
    +//      storage.serde.getOrElse(classOf[LazySimpleSerDe].getName))
    +//
    +//    import scala.collection.JavaConverters._
    +//    properties.putAll(storage.properties.asJava)
    +//
    +//    val tableDesc = new TableDesc(
    +//      Utils.classForName(storage.inputFormat.get).asInstanceOf[Class[_ <: InputFormat[_,
_]]],
    +//      Utils.classForName(storage.outputFormat.get),
    +//      properties
    +//    )
    --- End diff --
    
    Yes. The following dummy table looks fine to me. Could you remove the above lines? Thanks!


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message