diff options
author | Wenchen Fan <cloud0fan@outlook.com> | 2015-02-06 13:08:09 -0800 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-02-06 13:08:09 -0800 |
commit | 4793c8402a19afe4df51129a7f99e07494a76af2 (patch) | |
tree | a24381d399893601e2ab1647f34fd85d90d796ca /sql/hive | |
parent | bc36356080e3b52aaf61fc1e6b204146ab96d29f (diff) | |
download | spark-4793c8402a19afe4df51129a7f99e07494a76af2.tar.gz spark-4793c8402a19afe4df51129a7f99e07494a76af2.tar.bz2 spark-4793c8402a19afe4df51129a7f99e07494a76af2.zip |
[SPARK-5278][SQL] Introduce UnresolvedGetField and complete the check of ambiguous reference to fields
When the `GetField` chain(`a.b.c.d.....`) is interrupted by `GetItem` like `a.b[0].c.d....`, then the check of ambiguous reference to fields is broken.
The reason is that: for something like `a.b[0].c.d`, we first parse it to `GetField(GetField(GetItem(Unresolved("a.b"), 0), "c"), "d")`. Then in `LogicalPlan#resolve`, we resolve `"a.b"` and build a `GetField` chain from bottom(the relation). But for the 2 outer `GetFiled`, we have to resolve them in `Analyzer` or do it in `GetField` lazily, check data type of child, search needed field, etc. which is similar to what we have done in `LogicalPlan#resolve`.
So in this PR, the fix is just copy the same logic in `LogicalPlan#resolve` to `Analyzer`, which is simple and quick, but I do suggest introduce `UnresolvedGetFiled` like I explained in https://github.com/apache/spark/pull/2405.
Author: Wenchen Fan <cloud0fan@outlook.com>
Closes #4068 from cloud-fan/simple and squashes the following commits:
a6857b5 [Wenchen Fan] fix import order
8411c40 [Wenchen Fan] use UnresolvedGetField
Diffstat (limited to 'sql/hive')
-rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala | 2 | ||||
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala | 27 |
2 files changed, 18 insertions, 11 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 4b7fa06532..2a4b880921 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -1038,7 +1038,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C nodeToExpr(qualifier) match { case UnresolvedAttribute(qualifierName) => UnresolvedAttribute(qualifierName + "." + cleanIdentifier(attr)) - case other => GetField(other, attr) + case other => UnresolvedGetField(other, attr) } /* Stars (*) */ diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala index 178ece4477..ff8130ae5f 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala @@ -17,8 +17,7 @@ package org.apache.spark.sql.hive.execution -import org.apache.spark.sql.hive.test.TestHive -import org.apache.spark.sql.hive.test.TestHive.{sparkContext, sql} +import org.apache.spark.sql.hive.test.TestHive.{sparkContext, jsonRDD, sql} import org.apache.spark.sql.hive.test.TestHive.implicits._ case class Nested(a: Int, B: Int) @@ -29,16 +28,24 @@ case class Data(a: Int, B: Int, n: Nested, nestedArray: Seq[Nested]) */ class HiveResolutionSuite extends HiveComparisonTest { - case class NestedData(a: Seq[NestedData2], B: NestedData2) - case class NestedData2(a: NestedData3, B: NestedData3) - case class NestedData3(a: Int, B: Int) - test("SPARK-3698: case insensitive test for nested data") { - sparkContext.makeRDD(Seq.empty[NestedData]).registerTempTable("nested") + jsonRDD(sparkContext.makeRDD( + """{"a": [{"a": {"a": 1}}]}""" :: Nil)).registerTempTable("nested") // This should be successfully analyzed sql("SELECT a[0].A.A from nested").queryExecution.analyzed } + test("SPARK-5278: check ambiguous reference to fields") { + jsonRDD(sparkContext.makeRDD( + """{"a": [{"b": 1, "B": 2}]}""" :: Nil)).registerTempTable("nested") + + // there are 2 filed matching field name "b", we should report Ambiguous reference error + val exception = intercept[RuntimeException] { + sql("SELECT a[0].b from nested").queryExecution.analyzed + } + assert(exception.getMessage.contains("Ambiguous reference to fields")) + } + createQueryTest("table.attr", "SELECT src.key FROM src ORDER BY key LIMIT 1") @@ -68,7 +75,7 @@ class HiveResolutionSuite extends HiveComparisonTest { test("case insensitivity with scala reflection") { // Test resolution with Scala Reflection - TestHive.sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) + sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) .registerTempTable("caseSensitivityTest") val query = sql("SELECT a, b, A, B, n.a, n.b, n.A, n.B FROM caseSensitivityTest") @@ -79,14 +86,14 @@ class HiveResolutionSuite extends HiveComparisonTest { ignore("case insensitivity with scala reflection joins") { // Test resolution with Scala Reflection - TestHive.sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) + sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) .registerTempTable("caseSensitivityTest") sql("SELECT * FROM casesensitivitytest a JOIN casesensitivitytest b ON a.a = b.a").collect() } test("nested repeated resolution") { - TestHive.sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) + sparkContext.parallelize(Data(1, 2, Nested(1,2), Seq(Nested(1,2))) :: Nil) .registerTempTable("nestedRepeatedTest") assert(sql("SELECT nestedArray[0].a FROM nestedRepeatedTest").collect().head(0) === 1) } |