WangGuangxin commented on a change in pull request #24043: [SPARK-11412][SQL]
Support merge schema for ORC
URL: https://github.com/apache/spark/pull/24043#discussion_r293009015
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcSourceSuite.scala
##########
@@ -188,6 +190,49 @@ abstract class OrcSuite extends OrcTest with
BeforeAndAfterAll {
}
}
+ protected def testMergeSchemasInParallel(
+ ignoreCorruptFiles: Boolean,
+ parallelSchemaReader: (Seq[FileStatus], Configuration, Boolean) =>
Seq[StructType]): Unit = {
+ withSQLConf(
+ SQLConf.IGNORE_CORRUPT_FILES.key -> ignoreCorruptFiles.toString,
+ SQLConf.ORC_IMPLEMENTATION.key -> orcImp) {
+ withTempDir { dir =>
+ val fs = FileSystem.get(spark.sessionState.newHadoopConf())
+ val basePath = dir.getCanonicalPath
+
+ val path1 = new Path(basePath, "first")
+ val path2 = new Path(basePath, "second")
+ val path3 = new Path(basePath, "third")
+
+ spark.range(1).toDF("a").coalesce(1).write.orc(path1.toString)
+ spark.range(1, 2).toDF("b").coalesce(1).write.orc(path2.toString)
+ spark.range(2, 3).toDF("a").coalesce(1).write.json(path3.toString)
+
+ val fileStatuses =
+ Seq(fs.listStatus(path1), fs.listStatus(path2),
fs.listStatus(path3)).flatten
+
+ val schema = SchemaMergeUtils.mergeSchemasInParallel(
+ spark,
+ fileStatuses,
+ parallelSchemaReader)
+
+ assert(schema.isDefined == true)
Review comment:
done
----------------------------------------------------------------
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
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
