add test cases

Author: Zhenhua Wang

sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeTableCommand.scala

@@ -103,8 +103,9 @@ case class AnalyzeTableCommand(tableName: String, noscan: Boolean = true) extend
       if (newTotalSize > 0 && newTotalSize != oldTotalSize) {
         newStats = Some(Statistics(sizeInBytes = newTotalSize))
       }
-      // We only set rowCount when noscan is false, because otherwise we can't know whether the
-      // row count we get (`oldRowCount`) is valid or not.
+      // We only set rowCount when noscan is false, because otherwise:
+      // 1. when total size is not changed, we don't need to alter the table;
+      // 2. when total size is changed, `oldRowCount` becomes invalid.
       // This is to make sure that we only record the right statistics.
       if (!noscan) {
         val newRowCount = Dataset.ofRows(sparkSession, relation).count()

sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala

@@ -30,6 +30,7 @@ import org.apache.spark.sql.execution.joins._
 import org.apache.spark.sql.hive.test.TestHiveSingleton
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.test.SQLTestUtils
+import org.apache.spark.sql.types.StructType
 
 class StatisticsSuite extends QueryTest with TestHiveSingleton with SQLTestUtils {
 
@@ -220,6 +221,11 @@ class StatisticsSuite extends QueryTest with TestHiveSingleton with SQLTestUtils
       checkMetastoreRelationStats(textTable, expectedStats =
         Some(Statistics(sizeInBytes = 5812, rowCount = Some(500))))
 
+      sql(s"ANALYZE TABLE $textTable COMPUTE STATISTICS noscan")
+      // when the total size is not changed, the old row count is kept
+      checkMetastoreRelationStats(textTable, expectedStats =
+        Some(Statistics(sizeInBytes = 5812, rowCount = Some(500))))
+
       sql(s"INSERT INTO TABLE $textTable SELECT * FROM src")
       sql(s"ANALYZE TABLE $textTable COMPUTE STATISTICS noscan")
       // update total size and remove the old and invalid row count
@@ -301,6 +307,18 @@ class StatisticsSuite extends QueryTest with TestHiveSingleton with SQLTestUtils
     }
   }
 
+  test("statistics collection of a table with zero column") {
+    val table_no_cols = "table_no_cols"
+    withTable(table_no_cols) {
+      val rddNoCols = sparkContext.parallelize(1 to 10).map(_ => Row.empty)
+      val dfNoCols = spark.createDataFrame(rddNoCols, StructType(Seq.empty))
+      dfNoCols.write.format("json").saveAsTable(table_no_cols)
+      sql(s"ANALYZE TABLE $table_no_cols COMPUTE STATISTICS")
+      checkLogicalRelationStats(table_no_cols, expectedStats =
+        Some(Statistics(sizeInBytes = 30, rowCount = Some(10))))
+    }
+  }
+
   test("estimates the size of a test MetastoreRelation") {
     val df = sql("""SELECT * FROM src""")
     val sizes = df.queryExecution.analyzed.collect { case mr: MetastoreRelation =>