Repository: spark Updated Branches: refs/heads/master fe78b8b6f -> 14e6dc94f
HOTFIX: PySpark tests should be order insensitive. This has been messing up the SQL PySpark tests on Jenkins. Author: Patrick Wendell <pwend...@gmail.com> Closes #1054 from pwendell/pyspark and squashes the following commits: 1eb5487 [Patrick Wendell] False change 06f062d [Patrick Wendell] HOTFIX: PySpark tests should be order insensitive Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/14e6dc94 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/14e6dc94 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/14e6dc94 Branch: refs/heads/master Commit: 14e6dc94f68e57de82841c4ebbb573797a53869c Parents: fe78b8b Author: Patrick Wendell <pwend...@gmail.com> Authored: Wed Jun 11 15:54:41 2014 -0700 Committer: Patrick Wendell <pwend...@gmail.com> Committed: Wed Jun 11 15:54:41 2014 -0700 ---------------------------------------------------------------------- python/pyspark/sql.py | 8 ++++---- sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala | 1 + 2 files changed, 5 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/14e6dc94/python/pyspark/sql.py ---------------------------------------------------------------------- diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index b4e9618..960d0a8 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -117,7 +117,7 @@ class SQLContext: >>> srdd = sqlCtx.inferSchema(rdd) >>> srdd.saveAsParquetFile(parquetFile) >>> srdd2 = sqlCtx.parquetFile(parquetFile) - >>> srdd.collect() == srdd2.collect() + >>> sorted(srdd.collect()) == sorted(srdd2.collect()) True """ jschema_rdd = self._ssql_ctx.parquetFile(path) @@ -141,7 +141,7 @@ class SQLContext: >>> srdd = sqlCtx.inferSchema(rdd) >>> sqlCtx.registerRDDAsTable(srdd, "table1") >>> srdd2 = sqlCtx.table("table1") - >>> srdd.collect() == srdd2.collect() + >>> sorted(srdd.collect()) == sorted(srdd2.collect()) True """ return SchemaRDD(self._ssql_ctx.table(tableName), self) @@ -293,7 +293,7 @@ class SchemaRDD(RDD): >>> srdd = sqlCtx.inferSchema(rdd) >>> srdd.saveAsParquetFile(parquetFile) >>> srdd2 = sqlCtx.parquetFile(parquetFile) - >>> srdd2.collect() == srdd.collect() + >>> sorted(srdd2.collect()) == sorted(srdd.collect()) True """ self._jschema_rdd.saveAsParquetFile(path) @@ -307,7 +307,7 @@ class SchemaRDD(RDD): >>> srdd = sqlCtx.inferSchema(rdd) >>> srdd.registerAsTable("test") >>> srdd2 = sqlCtx.sql("select * from test") - >>> srdd.collect() == srdd2.collect() + >>> sorted(srdd.collect()) == sorted(srdd2.collect()) True """ self._jschema_rdd.registerAsTable(name) http://git-wip-us.apache.org/repos/asf/spark/blob/14e6dc94/sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala index 7ad8edf..44b19bc 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala @@ -33,6 +33,7 @@ import org.apache.spark.api.java.JavaRDD import java.util.{Map => JMap} /** + * ***FALSE CHANGE*** * :: AlphaComponent :: * An RDD of [[Row]] objects that has an associated schema. In addition to standard RDD functions, * SchemaRDDs can be used in relational queries, as shown in the examples below.