Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/12844#discussion_r62952863
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala ---
@@ -290,29 +291,92 @@ case class DescribeTableCommand(table:
TableIdentifier, isExtended: Boolean)
val result = new ArrayBuffer[Row]
sparkSession.sessionState.catalog.lookupRelation(table) match {
case catalogRelation: CatalogRelation =>
- catalogRelation.catalogTable.schema.foreach { column =>
- result += Row(column.name, column.dataType,
column.comment.orNull)
- }
-
- if (catalogRelation.catalogTable.partitionColumns.nonEmpty) {
- result += Row("# Partition Information", "", "")
- result += Row(s"# ${output(0).name}", output(1).name,
output(2).name)
-
- catalogRelation.catalogTable.partitionColumns.foreach { col =>
- result += Row(col.name, col.dataType, col.comment.orNull)
- }
+ if (isExtended) {
+ describeExtended(catalogRelation, result)
+ } else if (isFormatted) {
+ describeFormatted(catalogRelation, result)
+ } else {
+ describe(catalogRelation, result)
}
case relation =>
- relation.schema.fields.foreach { field =>
- val comment =
- if (field.metadata.contains("comment"))
field.metadata.getString("comment") else ""
- result += Row(field.name, field.dataType.simpleString, comment)
- }
+ describeSchema(relation.schema, result)
}
result
}
+
+ // Shows data columns and partitioned columns (if any)
+ private def describe(relation: CatalogRelation, buffer:
ArrayBuffer[Row]): Unit = {
+ describeSchema(relation.catalogTable.schema, buffer)
+
+ if (relation.catalogTable.partitionColumns.nonEmpty) {
+ append(buffer, "# Partition Information", "", "")
+ append(buffer, s"# ${output(0).name}", output(1).name,
output(2).name)
+ describeSchema(relation.catalogTable.partitionColumns, buffer)
+ }
+ }
+
+ private def describeExtended(relation: CatalogRelation, buffer:
ArrayBuffer[Row]): Unit = {
+ describe(relation, buffer)
+
+ append(buffer, "", "", "")
+ append(buffer, "# Detailed Table Information",
relation.catalogTable.toString, "")
--- End diff --
@liancheng To improve the output of `Explain`, I plan to change the default
implementation of `toString` of `case class CatalogTable`. That will also
affect the output of `Describe Extended`.
I checked what Hive did for the command `Describe Extended`, as follows.
`Detailed Table Information Table(tableName:t1, dbName:default, owner:root,
createTime:1462627092, lastAccessTime:0, retention:0,
sd:StorageDescriptor(cols:[FieldSchema(name:col, type:int, comment:null)],
location:hdfs://6b68a24121f4:9000/user/hive/warehouse/t1,
inputFormat:org.apache.hadoop.mapred.TextInputFormat,
outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat,
compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null,
serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,
parameters:{serialization.format=1}), bucketCols:[], sortCols:[],
parameters:{}, skewedInfo:SkewedInfo(skewedColNames:[], skewedColValues:[],
skewedColValueLocationMaps:{}), storedAsSubDirectories:false),
partitionKeys:[], parameters:{transient_lastDdlTime=1462627092},
viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE)`
Basically, in the implementation of `toString`, I will try to follow what
you did in `describeFormatted` but the contents will be in a single line. Feel
free to let me know if you have any concern or suggestion. 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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
