Repository: spark Updated Branches: refs/heads/branch-2.0 f12b74c02 -> 4dcbde48d
[SPARK-17808][PYSPARK] Upgraded version of Pyrolite to 4.13 ## What changes were proposed in this pull request? Upgraded to a newer version of Pyrolite which supports serialization of a BinaryType StructField for PySpark.SQL ## How was this patch tested? Added a unit test which fails with a raised ValueError when using the previous version of Pyrolite 4.9 and Python3 Author: Bryan Cutler <cutl...@gmail.com> Closes #15386 from BryanCutler/pyrolite-upgrade-SPARK-17808. (cherry picked from commit 658c7147f5bf637f36e8c66b9207d94b1e7c74c5) Signed-off-by: Sean Owen <so...@cloudera.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/4dcbde48 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/4dcbde48 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/4dcbde48 Branch: refs/heads/branch-2.0 Commit: 4dcbde48de6c46e2fd8ccfec732b8ff5c24f97a4 Parents: f12b74c Author: Bryan Cutler <cutl...@gmail.com> Authored: Tue Oct 11 08:29:52 2016 +0200 Committer: Sean Owen <so...@cloudera.com> Committed: Wed Oct 12 10:04:40 2016 +0100 ---------------------------------------------------------------------- core/pom.xml | 2 +- dev/deps/spark-deps-hadoop-2.2 | 2 +- dev/deps/spark-deps-hadoop-2.3 | 2 +- dev/deps/spark-deps-hadoop-2.4 | 2 +- dev/deps/spark-deps-hadoop-2.6 | 2 +- dev/deps/spark-deps-hadoop-2.7 | 2 +- python/pyspark/sql/tests.py | 8 ++++++++ 7 files changed, 14 insertions(+), 6 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/core/pom.xml ---------------------------------------------------------------------- diff --git a/core/pom.xml b/core/pom.xml index 9140251..aad87f7 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -316,7 +316,7 @@ <dependency> <groupId>net.razorvine</groupId> <artifactId>pyrolite</artifactId> - <version>4.9</version> + <version>4.13</version> <exclusions> <exclusion> <groupId>net.razorvine</groupId> http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/dev/deps/spark-deps-hadoop-2.2 ---------------------------------------------------------------------- diff --git a/dev/deps/spark-deps-hadoop-2.2 b/dev/deps/spark-deps-hadoop-2.2 index 8c9e559..34cd4e6 100644 --- a/dev/deps/spark-deps-hadoop-2.2 +++ b/dev/deps/spark-deps-hadoop-2.2 @@ -141,7 +141,7 @@ pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar py4j-0.10.3.jar -pyrolite-4.9.jar +pyrolite-4.13.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar scala-parser-combinators_2.11-1.0.4.jar http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/dev/deps/spark-deps-hadoop-2.3 ---------------------------------------------------------------------- diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3 index 839e084..8ae3c5e 100644 --- a/dev/deps/spark-deps-hadoop-2.3 +++ b/dev/deps/spark-deps-hadoop-2.3 @@ -148,7 +148,7 @@ pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar py4j-0.10.3.jar -pyrolite-4.9.jar +pyrolite-4.13.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar scala-parser-combinators_2.11-1.0.4.jar http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/dev/deps/spark-deps-hadoop-2.4 ---------------------------------------------------------------------- diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4 index ed84de7..7c69102 100644 --- a/dev/deps/spark-deps-hadoop-2.4 +++ b/dev/deps/spark-deps-hadoop-2.4 @@ -148,7 +148,7 @@ pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar py4j-0.10.3.jar -pyrolite-4.9.jar +pyrolite-4.13.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar scala-parser-combinators_2.11-1.0.4.jar http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/dev/deps/spark-deps-hadoop-2.6 ---------------------------------------------------------------------- diff --git a/dev/deps/spark-deps-hadoop-2.6 b/dev/deps/spark-deps-hadoop-2.6 index 6e7c9cb..041e01e 100644 --- a/dev/deps/spark-deps-hadoop-2.6 +++ b/dev/deps/spark-deps-hadoop-2.6 @@ -156,7 +156,7 @@ pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar py4j-0.10.3.jar -pyrolite-4.9.jar +pyrolite-4.13.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar scala-parser-combinators_2.11-1.0.4.jar http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/dev/deps/spark-deps-hadoop-2.7 ---------------------------------------------------------------------- diff --git a/dev/deps/spark-deps-hadoop-2.7 b/dev/deps/spark-deps-hadoop-2.7 index a61f31e..4f70bff 100644 --- a/dev/deps/spark-deps-hadoop-2.7 +++ b/dev/deps/spark-deps-hadoop-2.7 @@ -157,7 +157,7 @@ pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar py4j-0.10.3.jar -pyrolite-4.9.jar +pyrolite-4.13.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar scala-parser-combinators_2.11-1.0.4.jar http://git-wip-us.apache.org/repos/asf/spark/blob/4dcbde48/python/pyspark/sql/tests.py ---------------------------------------------------------------------- diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 3343bd7..a71457a 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -1703,6 +1703,14 @@ class SQLTests(ReusedPySparkTestCase): count = df.count() self.assertEquals(count, 4) + def test_BinaryType_serialization(self): + # Pyrolite version <= 4.9 could not serialize BinaryType with Python3 SPARK-17808 + schema = StructType([StructField('mybytes', BinaryType())]) + data = [[bytearray(b'here is my data')], + [bytearray(b'and here is some more')]] + df = self.spark.createDataFrame(data, schema=schema) + df.collect() + class HiveSparkSubmitTests(SparkSubmitTests): --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org