Repository: spark Updated Branches: refs/heads/master 7f8eb3bf6 -> e388b39d1
[SPARK-11692][SQL] Support for Parquet logical types, JSON and BSON (embedded types) Parquet supports some JSON and BSON datatypes. They are represented as binary for BSON and string (UTF-8) for JSON internally. I searched a bit and found Apache drill also supports both in this way, [link](https://drill.apache.org/docs/parquet-format/). Author: hyukjinkwon <gurwls...@gmail.com> Author: Hyukjin Kwon <gurwls...@gmail.com> Closes #9658 from HyukjinKwon/SPARK-11692. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e388b39d Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e388b39d Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e388b39d Branch: refs/heads/master Commit: e388b39d10fc269cdd3d630ea7d4ae80fd0efa97 Parents: 7f8eb3b Author: hyukjinkwon <gurwls...@gmail.com> Authored: Mon Nov 16 21:59:33 2015 +0800 Committer: Cheng Lian <l...@databricks.com> Committed: Mon Nov 16 21:59:33 2015 +0800 ---------------------------------------------------------------------- .../parquet/CatalystSchemaConverter.scala | 3 ++- .../datasources/parquet/ParquetIOSuite.scala | 25 ++++++++++++++++++++ 2 files changed, 27 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/e388b39d/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystSchemaConverter.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystSchemaConverter.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystSchemaConverter.scala index f28a18e..5f9f908 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystSchemaConverter.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystSchemaConverter.scala @@ -170,9 +170,10 @@ private[parquet] class CatalystSchemaConverter( case BINARY => originalType match { - case UTF8 | ENUM => StringType + case UTF8 | ENUM | JSON => StringType case null if assumeBinaryIsString => StringType case null => BinaryType + case BSON => BinaryType case DECIMAL => makeDecimalType() case _ => illegalType() } http://git-wip-us.apache.org/repos/asf/spark/blob/e388b39d/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala index 2aa5dca..a148fac 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala @@ -259,6 +259,31 @@ class ParquetIOSuite extends QueryTest with ParquetTest with SharedSQLContext { } } + test("SPARK-11692 Support for Parquet logical types, JSON and BSON (embedded types)") { + val parquetSchema = MessageTypeParser.parseMessageType( + """message root { + | required binary a(JSON); + | required binary b(BSON); + |} + """.stripMargin) + + withTempPath { location => + val extraMetadata = Map.empty[String, String].asJava + val fileMetadata = new FileMetaData(parquetSchema, extraMetadata, "Spark") + val path = new Path(location.getCanonicalPath) + val footer = List( + new Footer(path, new ParquetMetadata(fileMetadata, Collections.emptyList())) + ).asJava + + ParquetFileWriter.writeMetadataFile(sparkContext.hadoopConfiguration, path, footer) + + val jsonDataType = sqlContext.read.parquet(path.toString).schema(0).dataType + assert(jsonDataType === StringType) + val bsonDataType = sqlContext.read.parquet(path.toString).schema(1).dataType + assert(bsonDataType === BinaryType) + } + } + test("compression codec") { def compressionCodecFor(path: String, codecName: String): String = { val codecs = for { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
