Skip to content
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

Jump to bottom

[SPARK-11153] [SQL] Disables Parquet filter push-down for string and binary columns #9152

Closed
wants to merge 1 commit into from
Closed

[SPARK-11153] [SQL] Disables Parquet filter push-down for string and binary columns #9152

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
27 changes: 27 additions & 0 deletions ...re/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,8 @@ private[sql] object ParquetFilters {
case DoubleType =>
(n: String, v: Any) => FilterApi.eq(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
// Binary.fromString and Binary.fromByteArray don't accept null values
case StringType =>
(n: String, v: Any) => FilterApi.eq(
Expand All @@ -69,6 +71,7 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.eq(
binaryColumn(n),
Option(v).map(b => Binary.fromByteArray(v.asInstanceOf[Array[Byte]])).orNull)
*/
}

private val makeNotEq: PartialFunction[DataType, (String, Any) => FilterPredicate] = {
Expand All @@ -82,6 +85,9 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.notEq(floatColumn(n), v.asInstanceOf[java.lang.Float])
case DoubleType =>
(n: String, v: Any) => FilterApi.notEq(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Any) => FilterApi.notEq(
binaryColumn(n),
Expand All @@ -90,6 +96,7 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.notEq(
binaryColumn(n),
Option(v).map(b => Binary.fromByteArray(v.asInstanceOf[Array[Byte]])).orNull)
*/
}

private val makeLt: PartialFunction[DataType, (String, Any) => FilterPredicate] = {
Expand All @@ -101,13 +108,17 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.lt(floatColumn(n), v.asInstanceOf[java.lang.Float])
case DoubleType =>
(n: String, v: Any) => FilterApi.lt(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Any) =>
FilterApi.lt(binaryColumn(n),
Binary.fromByteArray(v.asInstanceOf[String].getBytes("utf-8")))
case BinaryType =>
(n: String, v: Any) =>
FilterApi.lt(binaryColumn(n), Binary.fromByteArray(v.asInstanceOf[Array[Byte]]))
*/
}

private val makeLtEq: PartialFunction[DataType, (String, Any) => FilterPredicate] = {
Expand All @@ -119,13 +130,17 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.ltEq(floatColumn(n), v.asInstanceOf[java.lang.Float])
case DoubleType =>
(n: String, v: Any) => FilterApi.ltEq(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Any) =>
FilterApi.ltEq(binaryColumn(n),
Binary.fromByteArray(v.asInstanceOf[String].getBytes("utf-8")))
case BinaryType =>
(n: String, v: Any) =>
FilterApi.ltEq(binaryColumn(n), Binary.fromByteArray(v.asInstanceOf[Array[Byte]]))
*/
}

private val makeGt: PartialFunction[DataType, (String, Any) => FilterPredicate] = {
Expand All @@ -137,13 +152,17 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.gt(floatColumn(n), v.asInstanceOf[java.lang.Float])
case DoubleType =>
(n: String, v: Any) => FilterApi.gt(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Any) =>
FilterApi.gt(binaryColumn(n),
Binary.fromByteArray(v.asInstanceOf[String].getBytes("utf-8")))
case BinaryType =>
(n: String, v: Any) =>
FilterApi.gt(binaryColumn(n), Binary.fromByteArray(v.asInstanceOf[Array[Byte]]))
*/
}

private val makeGtEq: PartialFunction[DataType, (String, Any) => FilterPredicate] = {
Expand All @@ -155,13 +174,17 @@ private[sql] object ParquetFilters {
(n: String, v: Any) => FilterApi.gtEq(floatColumn(n), v.asInstanceOf[java.lang.Float])
case DoubleType =>
(n: String, v: Any) => FilterApi.gtEq(doubleColumn(n), v.asInstanceOf[java.lang.Double])

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Any) =>
FilterApi.gtEq(binaryColumn(n),
Binary.fromByteArray(v.asInstanceOf[String].getBytes("utf-8")))
case BinaryType =>
(n: String, v: Any) =>
FilterApi.gtEq(binaryColumn(n), Binary.fromByteArray(v.asInstanceOf[Array[Byte]]))
*/
}

private val makeInSet: PartialFunction[DataType, (String, Set[Any]) => FilterPredicate] = {
Expand All @@ -177,6 +200,9 @@ private[sql] object ParquetFilters {
case DoubleType =>
(n: String, v: Set[Any]) =>
FilterApi.userDefined(doubleColumn(n), SetInFilter(v.asInstanceOf[Set[java.lang.Double]]))

// See https://issues.apache.org/jira/browse/SPARK-11153
/*
case StringType =>
(n: String, v: Set[Any]) =>
FilterApi.userDefined(binaryColumn(n),
Expand All @@ -185,6 +211,7 @@ private[sql] object ParquetFilters {
(n: String, v: Set[Any]) =>
FilterApi.userDefined(binaryColumn(n),
SetInFilter(v.map(e => Binary.fromByteArray(e.asInstanceOf[Array[Byte]]))))
*/
}

/**
Expand Down
6 changes: 4 additions & 2 deletions ...rc/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,8 @@ class ParquetFilterSuite extends QueryTest with ParquetTest with SharedSQLContex
}
}

test("filter pushdown - string") {
// See https://issues.apache.org/jira/browse/SPARK-11153
ignore("filter pushdown - string") {
withParquetDataFrame((1 to 4).map(i => Tuple1(i.toString))) { implicit df =>
checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row])
checkFilterPredicate(
Expand Down Expand Up @@ -247,7 +248,8 @@ class ParquetFilterSuite extends QueryTest with ParquetTest with SharedSQLContex
}
}

test("filter pushdown - binary") {
// See https://issues.apache.org/jira/browse/SPARK-11153
ignore("filter pushdown - binary") {
implicit class IntToBinary(int: Int) {
def b: Array[Byte] = int.toString.getBytes("UTF-8")
}
Expand Down