From e083334634ca0d7a25dee864fb2b9558ee92a2f7 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Mon, 18 Aug 2014 13:58:35 -0700 Subject: [SPARK-3103] [PySpark] fix saveAsTextFile() with utf-8 bugfix: It will raise an exception when it try to encode non-ASCII strings into unicode. It should only encode unicode as "utf-8". Author: Davies Liu Closes #2018 from davies/fix_utf8 and squashes the following commits: 4db7967 [Davies Liu] fix saveAsTextFile() with utf-8 (cherry picked from commit d1d0ee41c27f1d07fed0c5d56ba26c723cc3dc26) Signed-off-by: Josh Rosen --- python/pyspark/rdd.py | 4 +++- python/pyspark/tests.py | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'python') diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 240381e5ba..c708b69cc1 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1191,7 +1191,9 @@ class RDD(object): for x in iterator: if not isinstance(x, basestring): x = unicode(x) - yield x.encode("utf-8") + if isinstance(x, unicode): + x = x.encode("utf-8") + yield x keyed = self.mapPartitionsWithIndex(func) keyed._bypass_serializer = True keyed._jrdd.map(self.ctx._jvm.BytesToString()).saveAsTextFile(path) 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]) -- cgit v1.2.3