Skip to content

[SPARK-21440][SQL][PYSPARK] Refactor ArrowConverters and add ArrayType and StructType support. #18655

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

Closed
ueshin wants to merge 17 commits into from
Closed

[SPARK-21440][SQL][PYSPARK] Refactor ArrowConverters and add ArrayType and StructType support. #18655

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
1439fe6
Introduce ArrowWriter and ArrowColumnVector.
ueshin Jul 13, 2017
6fcf700
Use ArrowWriter for ArrowConverters.
ueshin Jul 14, 2017
579def2
Refactor ArrowConverters.
ueshin Jul 14, 2017
58cd465
Move releasing memory into task completion listener.
ueshin Jul 17, 2017
8ffedda
Revert ArrowColumnVector related implementations to split a pr into m…
ueshin Jul 18, 2017
e3a4fc0
Use rowCount instead of rowId.
ueshin Jul 19, 2017
b5988f9
Move files back to arrow package.
ueshin Jul 19, 2017
a50a271
Modify ArrowUtils to avoid deprecated APIs.
ueshin Jul 19, 2017
7084b38
Modify to close resources also immediately after row iterator is cons…
ueshin Jul 20, 2017
53fba41
Merge branch 'master' into issues/SPARK-21440
ueshin Jul 20, 2017
6fc4da0
Add ArrowWriterSuite.
ueshin Jul 20, 2017
926a624
Merge branch 'master' into issues/SPARK-21440
ueshin Jul 26, 2017
5bbb46f
Remove DecimalType support for now.
ueshin Jul 26, 2017
beff6ef
Fix skip() for StructType.
ueshin Jul 26, 2017
19f3973
Address comments.
ueshin Jul 26, 2017
0bac10d
Modify skip semantic.
ueshin Jul 27, 2017
b85dc23
Inline writeNull().
ueshin Jul 27, 2017
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
Prev Previous commit
Next Next commit
Remove DecimalType support for now.
  • Loading branch information
@ueshin
ueshin committed Jul 26, 2017
commit 5bbb46f55a90bae3008ee374ef2c0349a3489c09
27 changes: 2 additions & 25 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,8 +60,6 @@ object ArrowWriter {
new FloatWriter(vector.asInstanceOf[NullableFloat4Vector])
case DoubleType =>
new DoubleWriter(vector.asInstanceOf[NullableFloat8Vector])
case DecimalType.Fixed(precision, scale) =>
new DecimalWriter(vector.asInstanceOf[NullableDecimalVector], precision, scale)
case StringType =>
new StringWriter(vector.asInstanceOf[NullableVarCharVector])
case BinaryType =>
Expand All @@ -76,6 +74,8 @@ object ArrowWriter {
createFieldWriter(v.getChildByOrdinal(ordinal))
}
new StructWriter(v, children.toArray)
case dt =>
throw new UnsupportedOperationException(s"Unsupported data type: ${dt.simpleString}")
}
}
}
Expand Down Expand Up @@ -269,29 +269,6 @@ private[arrow] class DoubleWriter(val valueVector: NullableFloat8Vector) extends
}
}

private[arrow] class DecimalWriter(
val valueVector: NullableDecimalVector,
precision: Int,
scale: Int) extends ArrowFieldWriter {

override def valueMutator: NullableDecimalVector#Mutator = valueVector.getMutator()

override def setNull(): Unit = {
valueMutator.setNull(count)
}

override def setValue(input: SpecializedGetters, ordinal: Int): Unit = {
valueMutator.setIndexDefined(count)
val decimal = input.getDecimal(ordinal, precision, scale)
decimal.changePrecision(precision, scale)
DecimalUtility.writeBigDecimalToArrowBuf(decimal.toJavaBigDecimal, valueVector.getBuffer, count)
}

override def skip(): Unit = {
valueMutator.setIndexDefined(count)
}
}

private[arrow] class StringWriter(val valueVector: NullableVarCharVector) extends ArrowFieldWriter {

override def valueMutator: NullableVarCharVector#Mutator = valueVector.getMutator()
Expand Down
82 changes: 2 additions & 80 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowConvertersSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ import org.scalatest.BeforeAndAfterAll
import org.apache.spark.SparkException
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.sql.test.SharedSQLContext
import org.apache.spark.sql.types.{BinaryType, Decimal, IntegerType, StructField, StructType}
import org.apache.spark.sql.types.{BinaryType, IntegerType, StructField, StructType}
import org.apache.spark.util.Utils


Expand Down Expand Up @@ -391,85 +391,6 @@ class ArrowConvertersSuite extends SharedSQLContext with BeforeAndAfterAll {
collectAndValidate(df, json, "floating_point-double_precision.json")
}

ignore("decimal conversion") {
val json =
s"""
|{
| "schema" : {
| "fields" : [ {
| "name" : "a_d",
| "nullable" : true,
| "type" : {
| "name" : "decimal",
| "precision" : 38,
| "scale" : 18
| },
| "children" : [ ],
| "typeLayout" : {
| "vectors" : [ {
| "type" : "VALIDITY",
| "typeBitWidth" : 1
| }, {
| "type" : "DATA",
| "typeBitWidth" : 64
| } ]
| }
| }, {
| "name" : "b_d",
| "nullable" : true,
| "type" : {
| "name" : "decimal",
| "precision" : 38,
| "scale" : 18
| },
| "children" : [ ],
| "typeLayout" : {
| "vectors" : [ {
| "type" : "VALIDITY",
| "typeBitWidth" : 1
| }, {
| "type" : "DATA",
| "typeBitWidth" : 64
| } ]
| }
| } ]
| },
| "batches" : [ {
| "count" : 6,
| "columns" : [ {
| "name" : "a_d",
| "count" : 6,
| "VALIDITY" : [ 1, 1, 1, 1, 1, 1 ],
| "DATA" : [
| 1.000000000000000000,
| 2.000000000000000000,
| 0.010000000000000000,
| 200.000000000000000000,
| 0.000100000000000000,
| 20000.000000000000000000 ]
| }, {
| "name" : "b_d",
| "count" : 6,
| "VALIDITY" : [ 1, 0, 0, 1, 0, 1 ],
| "DATA" : [
| 1.100000000000000000,
| 0E-18,
| 0E-18,
| 2.200000000000000000,
| 0E-18,
| 3.300000000000000000 ]
| } ]
| } ]
|}
""".stripMargin

val a_d = List(1.0, 2.0, 0.01, 200.0, 0.0001, 20000.0).map(Decimal(_))
val b_d = List(Some(Decimal(1.1)), None, None, Some(Decimal(2.2)), None, Some(Decimal(3.3)))
val df = a_d.zip(b_d).toDF("a_d", "b_d")

collectAndValidate(df, json, "decimalData.json")
}

test("index conversion") {
val data = List[Int](1, 2, 3, 4, 5, 6)
val json =
Expand Down Expand Up @@ -1561,6 +1482,7 @@ class ArrowConvertersSuite extends SharedSQLContext with BeforeAndAfterAll {
assert(msg.getCause.getClass === classOf[UnsupportedOperationException])
}

runUnsupported { decimalData.toArrowPayload.collect() }
runUnsupported { mapData.toDF().toArrowPayload.collect() }
runUnsupported { complexData.toArrowPayload.collect() }

Expand Down
4 changes: 0 additions & 4 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,10 +55,6 @@ class ArrowWriterSuite extends SparkFunSuite {
check(FloatType, Seq(1.0f, 2.0f, null, 4.0f), (reader, rowId) => reader.getFloat(rowId))
check(DoubleType, Seq(1.0d, 2.0d, null, 4.0d), (reader, rowId) => reader.getDouble(rowId))

check(DecimalType.SYSTEM_DEFAULT, Seq(Decimal(1), Decimal(2), null, Decimal(4)),
(reader, rowId) => reader.getDecimal(
rowId, DecimalType.SYSTEM_DEFAULT.precision, DecimalType.SYSTEM_DEFAULT.scale))

check(StringType,
Seq("a", "b", null, "d").map(UTF8String.fromString),
(reader, rowId) => reader.getUTF8String(rowId))
Expand Down