Skip to content

[SPARK-25102][Spark Core] Write Spark version information to Parquet … #22255

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
space-d-n wants to merge 2 commits into from
Closed

[SPARK-25102][Spark Core] Write Spark version information to Parquet … #22255

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
ec9c130
[SPARK-25102][Spark Core] Write Spark version information to Parquet …
space-d-n Aug 28, 2018
9792185
[SPARK-25102][Spark Core] Write Spark version information to Parquet …
space-d-n Aug 30, 2018
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
5 changes: 5 additions & 0 deletions ...c/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetWriteSupport.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ import org.apache.parquet.hadoop.api.WriteSupport
import org.apache.parquet.hadoop.api.WriteSupport.WriteContext
import org.apache.parquet.io.api.{Binary, RecordConsumer}

import org.apache.spark.SPARK_VERSION
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.SpecializedGetters
Expand Down Expand Up @@ -115,6 +116,10 @@ private[parquet] class ParquetWriteSupport extends WriteSupport[InternalRow] wit
}
}

override def getName: String = {
SPARK_VERSION
}

private def writeFields(
row: InternalRow, schema: StructType, fieldWriters: Array[ValueWriter]): Unit = {
var i = 0
Expand Down
23 changes: 23 additions & 0 deletions ...est/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormatSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
package org.apache.spark.sql.execution.datasources.parquet

import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.parquet.format.converter.ParquetMetadataConverter
import org.apache.parquet.hadoop.ParquetFileReader

import org.apache.spark.SparkException
import org.apache.spark.sql.QueryTest
Expand Down Expand Up @@ -56,4 +58,25 @@ class ParquetFileFormatSuite extends QueryTest with ParquetTest with SharedSQLCo
}.getCause
assert(exception.getMessage().contains("Could not read footer for file"))
}

test("read version from parquet file footer metadata") {
withTempDir { dir =>
val config = spark.sessionState.newHadoopConf()
val fs = FileSystem.get(config)
val basePath = dir.getCanonicalPath

val pathToDirectory = new Path(basePath, "path")

spark.range(1).toDF("a").coalesce(1).write.save(pathToDirectory.toString)

val pathToFile = fs.globStatus(new Path(basePath, "path/part*"))(0).getPath

val fileFooter = ParquetFileReader
.readFooter(config, pathToFile, ParquetMetadataConverter.SKIP_ROW_GROUPS)
val fileWriterModelName = fileFooter.getFileMetaData
.getKeyValueMetaData.get("writer.model.name")

assert(fileWriterModelName == spark.version)
}
}
}