[GitHub] [spark] huaxingao commented on a diff in pull request #40058: [SPARK-39859][SQL] Support v2 DESCRIBE TABLE EXTENDED for columns

["huaxingao (via GitHub)" <gi...@apache.org>]

huaxingao commented on code in PR #40058:
URL: https://github.com/apache/spark/pull/40058#discussion_r1109118698


##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeColumnExec.scala:
##########
@@ -42,7 +44,43 @@ case class DescribeColumnExec(
       CharVarcharUtils.getRawType(column.metadata).getOrElse(column.dataType).catalogString)
     rows += toCatalystRow("comment", comment)
 
-    // TODO: The extended description (isExtended = true) can be added here.
+    if (isExtended && colStats.nonEmpty) {
+      if (colStats.get.min().isPresent) {
+        rows += toCatalystRow("min", colStats.get.min().toString)
+      } else {
+        rows += toCatalystRow("min", "NULL")
+      }
+
+      if (colStats.get.max().isPresent) {
+        rows += toCatalystRow("max", colStats.get.max().toString)
+      } else {
+        rows += toCatalystRow("max", "NULL")
+      }
+
+      if (colStats.get.nullCount().isPresent) {
+        rows += toCatalystRow("num_nulls", colStats.get.nullCount().getAsLong.toString)
+      } else {
+        rows += toCatalystRow("num_nulls", "NULL")
+      }
+
+      if (colStats.get.distinctCount().isPresent) {
+        rows += toCatalystRow("distinct_count", colStats.get.distinctCount().getAsLong.toString)
+      } else {
+        rows += toCatalystRow("distinct_count", "NULL")
+      }
+
+      if (colStats.get.avgLen().isPresent) {
+        rows += toCatalystRow("avg_col_len", colStats.get.avgLen().getAsLong.toString)
+      } else {
+        rows += toCatalystRow("avg_col_len", "NULL")
+      }
+
+      if (colStats.get.avgLen().isPresent) {
+        rows += toCatalystRow("max_col_len", colStats.get.avgLen().getAsLong.toString)
+      } else {
+        rows += toCatalystRow("max_col_len", "NULL")
+      }

Review Comment:
   Fixed. Thanks



##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala:
##########
@@ -329,10 +329,17 @@ class DataSourceV2Strategy(session: SparkSession) extends Strategy with Predicat
       }
       DescribeTableExec(output, r.table, isExtended) :: Nil
 
-    case DescribeColumn(_: ResolvedTable, column, isExtended, output) =>
+    case DescribeColumn(r: ResolvedTable, column, isExtended, output) =>
       column match {
         case c: Attribute =>
-          DescribeColumnExec(output, c, isExtended) :: Nil
+          val colStats =
+            r.table.asReadable.newScanBuilder(CaseInsensitiveStringMap.empty()).build() match {
+            case s: SupportsReportStatistics =>
+              val stats = s.estimateStatistics()
+              Some(stats.columnStats().get(FieldReference.column(c.name)))

Review Comment:
   I think this is controlled by `SQLConf.CASE_SENSITIVE`



-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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