diff options
Diffstat (limited to 'python/pyspark/tests.py')
| -rw-r--r-- | python/pyspark/tests.py | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py index f1fece998c..69d543d9d0 100644 --- a/python/pyspark/tests.py +++ b/python/pyspark/tests.py @@ -256,6 +256,15 @@ class TestRDDFunctions(PySparkTestCase): raw_contents = ''.join(input(glob(tempFile.name + "/part-0000*"))) self.assertEqual(x, unicode(raw_contents.strip(), "utf-8")) + def test_save_as_textfile_with_utf8(self): + x = u"\u00A1Hola, mundo!" + data = self.sc.parallelize([x.encode("utf-8")]) + tempFile = tempfile.NamedTemporaryFile(delete=True) + tempFile.close() + data.saveAsTextFile(tempFile.name) + raw_contents = ''.join(input(glob(tempFile.name + "/part-0000*"))) + self.assertEqual(x, unicode(raw_contents.strip(), "utf-8")) + def test_transforming_cartesian_result(self): # Regression test for SPARK-1034 rdd1 = self.sc.parallelize([1, 2]) |