Skip to content

[SPARK-41096][SQL] Support reading parquet FIXED_LEN_BYTE_ARRAY type #38628

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
kazuyukitanimura wants to merge 2 commits into from
Closed

[SPARK-41096][SQL] Support reading parquet FIXED_LEN_BYTE_ARRAY type #38628

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
035045d
[SPARK-XXXXX][SQL] Support reading parquet FLBA type
kazuyukitanimura Nov 9, 2022
5d45c1c
[SPARK-41096][SQL] Support reading parquet FIXED_LEN_BYTE_ARRAY type
kazuyukitanimura Nov 10, 2022
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
2 changes: 2 additions & 0 deletions .../java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,8 @@ public ParquetVectorUpdater getUpdater(ColumnDescriptor descriptor, DataType spa
return new FixedLenByteArrayAsLongUpdater(arrayLen);
} else if (canReadAsBinaryDecimal(descriptor, sparkType)) {
return new FixedLenByteArrayUpdater(arrayLen);
} else if (sparkType == DataTypes.BinaryType) {
return new FixedLenByteArrayUpdater(arrayLen);
}
break;
default:
Expand Down
1 change: 1 addition & 0 deletions ...ain/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,6 +297,7 @@ class ParquetToSparkSchemaConverter(
case _: DecimalLogicalTypeAnnotation =>
makeDecimalType(Decimal.maxPrecisionForBytes(parquetType.getTypeLength))
case _: IntervalLogicalTypeAnnotation => typeNotImplemented()
case null => BinaryType
case _ => illegalType()
}

Expand Down
36 changes: 36 additions & 0 deletions ...re/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ import org.apache.parquet.hadoop._
import org.apache.parquet.hadoop.example.ExampleParquetWriter
import org.apache.parquet.hadoop.metadata.CompressionCodecName
import org.apache.parquet.hadoop.metadata.CompressionCodecName.GZIP
import org.apache.parquet.io.api.Binary
import org.apache.parquet.schema.{MessageType, MessageTypeParser}

import org.apache.spark.{SPARK_VERSION_SHORT, SparkException, TestUtils}
Expand Down Expand Up @@ -111,6 +112,41 @@ class ParquetIOSuite extends QueryTest with ParquetTest with SharedSparkSession
}
}

test("SPARK-41096: FIXED_LEN_BYTE_ARRAY support") {
Seq(true, false).foreach { dictionaryEnabled =>
def makeRawParquetFile(path: Path): Unit = {
val schemaStr =
"""message root {
| required FIXED_LEN_BYTE_ARRAY(1) a;
| required FIXED_LEN_BYTE_ARRAY(3) b;
|}
""".stripMargin
val schema = MessageTypeParser.parseMessageType(schemaStr)

val writer = createParquetWriter(schema, path, dictionaryEnabled)

(0 until 10).map(_.toString).foreach { n =>
val record = new SimpleGroup(schema)
record.add(0, Binary.fromString(n))
record.add(1, Binary.fromString(n + n + n))
writer.write(record)
}
writer.close()
}

withTempDir { dir =>
val path = new Path(dir.toURI.toString, "part-r-0.parquet")
makeRawParquetFile(path)
Seq(true, false).foreach { vectorizedReaderEnabled =>
readParquetFile(path.toString, vectorizedReaderEnabled) { df =>
checkAnswer(df, (48 until 58).map(n => // char '0' is 48 in ascii
Row(Array(n), Array(n, n, n))))
}
}
}
}
}

test("string") {
val data = (1 to 4).map(i => Tuple1(i.toString))
// Property spark.sql.parquet.binaryAsString shouldn't affect Parquet files written by Spark SQL
Expand Down