[SPARK-7662] [SQL] Resolve correct names for generator in projection

```
select explode(map(value, key)) from src;
```
Throws exception
```
org.apache.spark.sql.AnalysisException: The number of aliases supplied in the AS clause does not match the number of columns output by the UDTF expected 2 aliases but got _c0 ;
at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:38)
at org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:43)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveGenerate$$makeGeneratorOutput(Analyzer.scala:605)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$$anonfun$apply$16$$anonfun$22.apply(Analyzer.scala:562)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$$anonfun$apply$16$$anonfun$22.apply(Analyzer.scala:548)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$$anonfun$apply$16.applyOrElse(Analyzer.scala:548)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$$anonfun$apply$16.applyOrElse(Analyzer.scala:538)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
```

Author: Cheng Hao <hao.cheng@intel.com>

Closes #6178 from chenghao-intel/explode and squashes the following commits:

916fbe9 [Cheng Hao] add more strict rules for TGF alias
5c3f2c5 [Cheng Hao] fix bug in unit test
e1d93ab [Cheng Hao] Add more unit test
19db09e [Cheng Hao] resolve names for generator in projection

1 files changed, 15 insertions, 0 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
index dfa4215f2e..c239e83271 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
@@ -561,6 +561,21 @@ class Analyzer(
     /** Extracts a [[Generator]] expression and any names assigned by aliases to their output. */
     private object AliasedGenerator {
       def unapply(e: Expression): Option[(Generator, Seq[String])] = e match {
+        case Alias(g: Generator, name)
+          if g.elementTypes.size > 1 && java.util.regex.Pattern.matches("_c[0-9]+", name) => {
+          // Assume the default name given by parser is "_c[0-9]+",
+          // TODO in long term, move the naming logic from Parser to Analyzer.
+          // In projection, Parser gave default name for TGF as does for normal UDF,
+          // but the TGF probably have multiple output columns/names.
+          //    e.g. SELECT explode(map(key, value)) FROM src;
+          // Let's simply ignore the default given name for this case.
+          Some((g, Nil))
+        }
+        case Alias(g: Generator, name) if g.elementTypes.size > 1 =>
+          // If not given the default names, and the TGF with multiple output columns
+          failAnalysis(
+            s"""Expect multiple names given for ${g.getClass.getName},
+               |but only single name '${name}' specified""".stripMargin)
         case Alias(g: Generator, name) => Some((g, name :: Nil))
         case MultiAlias(g: Generator, names) => Some(g, names)
         case _ => None