diff options
author | hyukjinkwon <gurwls223@gmail.com> | 2015-11-16 21:59:33 +0800 |
---|---|---|
committer | Cheng Lian <lian@databricks.com> | 2015-11-16 21:59:33 +0800 |
commit | e388b39d10fc269cdd3d630ea7d4ae80fd0efa97 (patch) | |
tree | 3f6222bb834833bfd20c4b95df4459e9153f1ca2 | |
parent | 7f8eb3bf6ed64eefc5472f5c5fb02e2db1e3f618 (diff) | |
download | spark-e388b39d10fc269cdd3d630ea7d4ae80fd0efa97.tar.gz spark-e388b39d10fc269cdd3d630ea7d4ae80fd0efa97.tar.bz2 spark-e388b39d10fc269cdd3d630ea7d4ae80fd0efa97.zip |
[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 <gurwls223@gmail.com>
Author: Hyukjin Kwon <gurwls223@gmail.com>
Closes #9658 from HyukjinKwon/SPARK-11692.
2 files changed, 27 insertions, 1 deletions
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 f28a18e275..5f9f908309 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() } 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 2aa5dca847..a148facd05 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 { |