[GitHub] [spark] yaooqinn commented on a change in pull request #26942: [SPARK-30301][SQL] Fix wrong results when datetimes as fields of complex types

[GitBox <gi...@apache.org>]

yaooqinn commented on a change in pull request #26942: [SPARK-30301][SQL] Fix wrong results when datetimes as fields of complex types
URL: https://github.com/apache/spark/pull/26942#discussion_r397625334
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
 ##########
 @@ -56,78 +56,41 @@ object HiveResult {
       // We need the types so we can output struct field names
       val types = executedPlan.output.map(_.dataType)
       // Reformat to match hive tab delimited output.
-      result.map(_.zip(types).map(toHiveString)).map(_.mkString("\t"))
+      result.map(_.zip(types).map(e => toHiveString(e)))
+        .map(_.mkString("\t"))
   }
 
-  private val primitiveTypes = Seq(
-    StringType,
-    IntegerType,
-    LongType,
-    DoubleType,
-    FloatType,
-    BooleanType,
-    ByteType,
-    ShortType,
-    DateType,
-    TimestampType,
-    BinaryType)
-
   private lazy val zoneId = DateTimeUtils.getZoneId(SQLConf.get.sessionLocalTimeZone)
   private lazy val dateFormatter = DateFormatter(zoneId)
   private lazy val timestampFormatter = TimestampFormatter.getFractionFormatter(zoneId)
 
-  /** Hive outputs fields of structs slightly differently than top level attributes. */
-  private def toHiveStructString(a: (Any, DataType)): String = a match {
-    case (struct: Row, StructType(fields)) =>
-      struct.toSeq.zip(fields).map {
-        case (v, t) => s""""${t.name}":${toHiveStructString((v, t.dataType))}"""
-      }.mkString("{", ",", "}")
-    case (seq: Seq[_], ArrayType(typ, _)) =>
-      seq.map(v => (v, typ)).map(toHiveStructString).mkString("[", ",", "]")
-    case (map: Map[_, _], MapType(kType, vType, _)) =>
-      map.map {
-        case (key, value) =>
-          toHiveStructString((key, kType)) + ":" + toHiveStructString((value, vType))
-      }.toSeq.sorted.mkString("{", ",", "}")
-    case (null, _) => "null"
-    case (s: String, StringType) => "\"" + s + "\""
-    case (decimal, DecimalType()) => decimal.toString
-    case (interval: CalendarInterval, CalendarIntervalType) =>
-      SQLConf.get.intervalOutputStyle match {
-        case SQL_STANDARD => toSqlStandardString(interval)
-        case ISO_8601 => toIso8601String(interval)
-        case MULTI_UNITS => toMultiUnitsString(interval)
-      }
-    case (other, tpe) if primitiveTypes contains tpe => other.toString
-  }
-
   /** Formats a datum (based on the given data type) and returns the string representation. */
-  def toHiveString(a: (Any, DataType)): String = a match {
-    case (struct: Row, StructType(fields)) =>
-      struct.toSeq.zip(fields).map {
-        case (v, t) => s""""${t.name}":${toHiveStructString((v, t.dataType))}"""
-      }.mkString("{", ",", "}")
-    case (seq: Seq[_], ArrayType(typ, _)) =>
-      seq.map(v => (v, typ)).map(toHiveStructString).mkString("[", ",", "]")
-    case (map: Map[_, _], MapType(kType, vType, _)) =>
-      map.map {
-        case (key, value) =>
-          toHiveStructString((key, kType)) + ":" + toHiveStructString((value, vType))
-      }.toSeq.sorted.mkString("{", ",", "}")
-    case (null, _) => "NULL"
+  def toHiveString(a: (Any, DataType), nested: Boolean = false): String = a match {
+    case (null, _) => if (nested) "null" else "NULL"
+    case (b, BooleanType) => b.toString
     case (d: Date, DateType) => dateFormatter.format(DateTimeUtils.fromJavaDate(d))
     case (t: Timestamp, TimestampType) =>
-      DateTimeUtils.timestampToString(timestampFormatter, DateTimeUtils.fromJavaTimestamp(t))
+      timestampFormatter.format(DateTimeUtils.fromJavaTimestamp(t))
     case (bin: Array[Byte], BinaryType) => new String(bin, StandardCharsets.UTF_8)
 
 Review comment:
   
   ```sql
   [root@quickstart /]# beeline -u 'jdbc:hive2://localhost:10000'
   2020-03-25 06:02:31,786 WARN  [main] mapreduce.TableMapReduceUtil: The hbase-prefix-tree module jar containing PrefixTreeCodec is not present.  Continuing without it.
   scan complete in 4ms
   Connecting to jdbc:hive2://localhost:10000
   Connected to: Apache Hive (version 1.1.0-cdh5.7.0)
   Driver: Hive JDBC (version 1.1.0-cdh5.7.0)
   Transaction isolation: TRANSACTION_REPEATABLE_READ
   Beeline version 1.1.0-cdh5.7.0 by Apache Hive
   0: jdbc:hive2://localhost:10000> select k, array(k) from bt;
   INFO  : Compiling command(queryId=hive_20200325060202_e14c040e-6556-4eb3-98c8-295e929d1a65): select k, array(k) from bt
   INFO  : Semantic Analysis Completed
   INFO  : Returning Hive schema: Schema(fieldSchemas:[FieldSchema(name:k, type:binary, comment:null), FieldSchema(name:_c1, type:array<binary>, comment:null)], properties:null)
   INFO  : Completed compiling command(queryId=hive_20200325060202_e14c040e-6556-4eb3-98c8-295e929d1a65); Time taken: 1.108 seconds
   INFO  : Concurrency mode is disabled, not creating a lock manager
   INFO  : Executing command(queryId=hive_20200325060202_e14c040e-6556-4eb3-98c8-295e929d1a65): select k, array(k) from bt
   INFO  : Completed executing command(queryId=hive_20200325060202_e14c040e-6556-4eb3-98c8-295e929d1a65); Time taken: 0.005 seconds
   INFO  : OK
   +--------+----------+--+
   |   k    |   _c1    |
   +--------+----------+--+
   | spark  | [spark]  |
   | hello  | [hello]  |
   | 3      | [3]      |
   | .      | [.]      |
   | 0      | [0]      |
   +--------+----------+--+
   ```

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

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