Skip to content

fix: Spark 4.0-preview1 SPARK-47120 #1156

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 11, 2024
Merged

fix: Spark 4.0-preview1 SPARK-47120 #1156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 3 additions & 13 deletions dev/diffs/4.0.0-preview1.diff
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2088,7 +2088,7 @@ index cd6f41b4ef4..4b6a17344bc 100644
ParquetOutputFormat.WRITER_VERSION -> ParquetProperties.WriterVersion.PARQUET_2_0.toString
)
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
index 795e9f46a8d..6285a1e388b 100644
index 795e9f46a8d..5306c94a686 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
@@ -1100,7 +1100,11 @@ abstract class ParquetFilterSuite extends QueryTest with ParquetTest with Shared
Expand Down Expand Up @@ -2150,17 +2150,7 @@ index 795e9f46a8d..6285a1e388b 100644
// block 1:
// null count min max
// page-0 0 0 99
@@ -2211,7 +2225,8 @@ abstract class ParquetFilterSuite extends QueryTest with ParquetTest with Shared
}
}

- test("SPARK-47120: subquery literal filter pushdown") {
+ test("SPARK-47120: subquery literal filter pushdown",
+ IgnoreComet("TODO: https://github.com/apache/datafusion-comet/issues/551")) {
withTable("t1", "t2") {
sql("create table t1(d date) using parquet")
sql("create table t2(d date) using parquet")
@@ -2301,7 +2316,11 @@ class ParquetV1FilterSuite extends ParquetFilterSuite {
@@ -2301,7 +2315,11 @@ class ParquetV1FilterSuite extends ParquetFilterSuite {
assert(pushedParquetFilters.exists(_.getClass === filterClass),
s"${pushedParquetFilters.map(_.getClass).toList} did not contain ${filterClass}.")

Expand All @@ -2173,7 +2163,7 @@ index 795e9f46a8d..6285a1e388b 100644
} else {
assert(selectedFilters.isEmpty, "There is filter pushed down")
}
@@ -2362,7 +2381,11 @@ class ParquetV2FilterSuite extends ParquetFilterSuite {
@@ -2362,7 +2380,11 @@ class ParquetV2FilterSuite extends ParquetFilterSuite {
assert(pushedParquetFilters.exists(_.getClass === filterClass),
s"${pushedParquetFilters.map(_.getClass).toList} did not contain ${filterClass}.")

Expand Down
2 changes: 1 addition & 1 deletion docs/source/user-guide/source.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ Official source releases can be downloaded from https://dist.apache.org/repos/di

```console
# Pick the latest version
export COMET_VERSION=0.3.0
export COMET_VERSION=0.4.0
# Download the tarball
curl -O "https://dist.apache.org/repos/dist/release/datafusion/datafusion-comet-$COMET_VERSION/apache-datafusion-comet-$COMET_VERSION.tar.gz"
# Unpack
Expand Down
10 changes: 6 additions & 4 deletions spark/src/main/scala/org/apache/comet/parquet/ParquetFilters.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -723,20 +723,22 @@ class ParquetFilters(
.lift(nameToParquetField(name).fieldType)
.map(_(nameToParquetField(name).fieldNames, value))

case sources.LessThan(name, value) if canMakeFilterOn(name, value) =>
case sources.LessThan(name, value) if (value != null) && canMakeFilterOn(name, value) =>
makeLt
.lift(nameToParquetField(name).fieldType)
.map(_(nameToParquetField(name).fieldNames, value))
case sources.LessThanOrEqual(name, value) if canMakeFilterOn(name, value) =>
case sources.LessThanOrEqual(name, value)
if (value != null) && canMakeFilterOn(name, value) =>
makeLtEq
.lift(nameToParquetField(name).fieldType)
.map(_(nameToParquetField(name).fieldNames, value))

case sources.GreaterThan(name, value) if canMakeFilterOn(name, value) =>
case sources.GreaterThan(name, value) if (value != null) && canMakeFilterOn(name, value) =>
makeGt
.lift(nameToParquetField(name).fieldType)
.map(_(nameToParquetField(name).fieldNames, value))
case sources.GreaterThanOrEqual(name, value) if canMakeFilterOn(name, value) =>
case sources.GreaterThanOrEqual(name, value)
if (value != null) && canMakeFilterOn(name, value) =>
makeGtEq
.lift(nameToParquetField(name).fieldType)
.map(_(nameToParquetField(name).fieldNames, value))
Expand Down
Loading