From 14e6dc94f68e57de82841c4ebbb573797a53869c Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Wed, 11 Jun 2014 15:54:41 -0700 Subject: HOTFIX: PySpark tests should be order insensitive. This has been messing up the SQL PySpark tests on Jenkins. Author: Patrick Wendell 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 --- python/pyspark/sql.py | 8 ++++---- sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala | 1 + 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index b4e9618cc2..960d0a8244 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) 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 7ad8edf5a5..44b19bca46 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. -- cgit v1.2.3