Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/14344#discussion_r72035518
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
---
@@ -501,6 +501,143 @@ case class MapObjects private(
}
}
+object ExternalMapToCatalyst {
+ private val curId = new java.util.concurrent.atomic.AtomicInteger()
+
+ def apply(
+ inputMap: Expression,
+ keyType: DataType,
+ keyConverter: Expression => Expression,
+ valueType: DataType,
+ valueConverter: Expression => Expression): ExternalMapToCatalyst = {
+ val id = curId.getAndIncrement()
+ val keyName = "ExternalMapToCatalyst_key" + id
+ val valueName = "ExternalMapToCatalyst_value" + id
+ val valueIsNull = "ExternalMapToCatalyst_value_isNull" + id
+
+ ExternalMapToCatalyst(
+ keyName,
+ keyType,
+ keyConverter(LambdaVariable(keyName, "false", keyType)),
+ valueName,
+ valueIsNull,
+ valueType,
+ valueConverter(LambdaVariable(valueName, valueIsNull, valueType)),
+ inputMap
+ )
+ }
+}
+
+case class ExternalMapToCatalyst private(
+ key: String,
+ keyType: DataType,
+ keyConverter: Expression,
+ value: String,
+ valueIsNull: String,
+ valueType: DataType,
+ valueConverter: Expression,
+ child: Expression)
+ extends UnaryExpression with NonSQLExpression {
+
+ override def foldable: Boolean = false
+
+ override def dataType: MapType = MapType(keyConverter.dataType,
valueConverter.dataType)
+
+ override def eval(input: InternalRow): Any =
+ throw new UnsupportedOperationException("Only code-generated
evaluation is supported")
+
+ override protected def doGenCode(ctx: CodegenContext, ev: ExprCode):
ExprCode = {
+ val inputMap = child.genCode(ctx)
+ val genKeyConverter = keyConverter.genCode(ctx)
+ val genValueConverter = valueConverter.genCode(ctx)
+ val length = ctx.freshName("length")
+ val index = ctx.freshName("index")
+ val convertedKeys = ctx.freshName("convertedKeys")
+ val convertedValues = ctx.freshName("convertedValues")
+ val entry = ctx.freshName("entry")
+ val entries = ctx.freshName("entries")
+
+ val (defineEntries, defineKeyValue) = child.dataType match {
+ case ObjectType(cls) if classOf[java.util.Map[_,
_]].isAssignableFrom(cls) =>
+ val javaIteratorCls = classOf[java.util.Iterator[_]].getName
+ val javaMapEntryCls = classOf[java.util.Map.Entry[_, _]].getName
+
+ val defineEntries =
+ s"final $javaIteratorCls $entries =
${inputMap.value}.entrySet().iterator();"
+
+ val defineKeyValue =
+ s"""
+ final $javaMapEntryCls $entry = ($javaMapEntryCls)
$entries.next();
+ ${ctx.javaType(keyType)} $key = (${ctx.boxedType(keyType)})
$entry.getKey();
+ ${ctx.javaType(valueType)} $value =
(${ctx.boxedType(valueType)}) $entry.getValue();
+ """
+
+ defineEntries -> defineKeyValue
+
+ case ObjectType(cls) if classOf[scala.collection.Map[_,
_]].isAssignableFrom(cls) =>
+ val scalaIteratorCls = classOf[Iterator[_]].getName
+ val scalaMapEntryCls = classOf[Tuple2[_, _]].getName
+
+ val defineEntries = s"final $scalaIteratorCls $entries =
${inputMap.value}.iterator();"
+
+ val defineKeyValue =
+ s"""
+ final $scalaMapEntryCls $entry = ($scalaMapEntryCls)
$entries.next();
+ ${ctx.javaType(keyType)} $key = (${ctx.boxedType(keyType)})
$entry._1();
+ ${ctx.javaType(valueType)} $value =
(${ctx.boxedType(valueType)}) $entry._2();
+ """
+
+ defineEntries -> defineKeyValue
+ }
+
+ val valueNullCheck = if (ctx.isPrimitiveType(valueType)) {
+ s"boolean $valueIsNull = false;"
+ } else {
+ s"boolean $valueIsNull = $value == null;"
+ }
+
+ val arrayCls = classOf[GenericArrayData].getName
+ val mapCls = classOf[ArrayBasedMapData].getName
+ val convertedKeyType = ctx.boxedType(keyConverter.dataType)
+ val convertedValueType = ctx.boxedType(valueConverter.dataType)
+ val code =
+ s"""
+ ${inputMap.code}
+ ${ctx.javaType(dataType)} ${ev.value} =
${ctx.defaultValue(dataType)};
+ if (!${inputMap.isNull}) {
+ final int $length = ${inputMap.value}.size();
+ final Object[] $convertedKeys = new Object[$length];
+ final Object[] $convertedValues = new Object[$length];
+ int $index = 0;
+ $defineEntries
+ while($entries.hasNext()) {
+ $defineKeyValue
+ $valueNullCheck
+
+ ${genKeyConverter.code}
+ if (${genKeyConverter.isNull}) {
+ throw new RuntimeException("Cannot use null as map key!");
+ } else {
+ $convertedKeys[$index] = ($convertedKeyType)
${genKeyConverter.value};
--- End diff --
The type casting doesn't seem to be necessary here since `convertedKeys` is
an `Object[]`.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
