[SPARK-33267][SQL] Fix NPE issue on 'In' filter when one of values contains null
### What changes were proposed in this pull request? This PR proposes to fix the NPE issue on `In` filter when one of values contain null. In real case, you can trigger this issue when you try to push down the filter with `in (..., null)` against V2 source table. `DataSourceStrategy` caches the mapping (filter instance -> expression) in HashMap, which leverages hash code on the key, hence it could trigger the NPE issue. ### Why are the changes needed? This is an obvious bug as `In` filter doesn't care about null value when calculating hash code. ### Does this PR introduce _any_ user-facing change? Yes, previously the query with having `null` in "in" condition against data source V2 source table supporting push down filter failed with NPE, whereas after the PR the query will not fail. ### How was this patch tested? UT added. The new UT fails without the PR and passes with the PR. Closes #30170 from HeartSaVioR/SPARK-33267. Authored-by: Jungtaek Lim (HeartSaVioR) <kabhwan.opensource@gmail.com> Signed-off-by: Dongjoon Hyun <dhyun@apple.com>
This commit is contained in:
parent
a6216e2446
commit
a744fea3be
|
@ -164,7 +164,7 @@ case class In(attribute: String, values: Array[Any]) extends Filter {
|
||||||
var h = attribute.hashCode
|
var h = attribute.hashCode
|
||||||
values.foreach { v =>
|
values.foreach { v =>
|
||||||
h *= 41
|
h *= 41
|
||||||
h += v.hashCode()
|
h += (if (v != null) v.hashCode() else 0)
|
||||||
}
|
}
|
||||||
h
|
h
|
||||||
}
|
}
|
||||||
|
|
|
@ -413,6 +413,16 @@ class DataSourceV2Suite extends QueryTest with SharedSparkSession with AdaptiveS
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
test("SPARK-33267: push down with condition 'in (..., null)' should not throw NPE") {
|
||||||
|
Seq(classOf[AdvancedDataSourceV2], classOf[JavaAdvancedDataSourceV2]).foreach { cls =>
|
||||||
|
withClue(cls.getName) {
|
||||||
|
val df = spark.read.format(cls.getName).load()
|
||||||
|
// before SPARK-33267 below query just threw NPE
|
||||||
|
df.select('i).where("i in (1, null)").collect()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue