Github user BryanCutler commented on a diff in the pull request: https://github.com/apache/spark/pull/20280#discussion_r161865195 --- Diff: python/pyspark/sql/tests.py --- @@ -2306,18 +2306,20 @@ def test_toDF_with_schema_string(self): self.assertEqual(df.schema.simpleString(), "struct<key:string,value:string>") self.assertEqual(df.collect(), [Row(key=str(i), value=str(i)) for i in range(100)]) - # field names can differ. - df = rdd.toDF(" a: int, b: string ") --- End diff -- This test was flawed because it only worked because ("a", "b") is in the same alphabetical order as ("key", "value"). If it was ("key", "aaa") then it would fail.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org