diff options
author | Davies Liu <davies.liu@gmail.com> | 2014-08-18 13:58:35 -0700 |
---|---|---|
committer | Josh Rosen <joshrosen@apache.org> | 2014-08-18 13:58:47 -0700 |
commit | e083334634ca0d7a25dee864fb2b9558ee92a2f7 (patch) | |
tree | 6302cb51e1573f51144dfd83f919216c2cd8b3e7 | |
parent | cc4015d2fa3785b92e6ab079b3abcf17627f7c56 (diff) | |
download | spark-e083334634ca0d7a25dee864fb2b9558ee92a2f7.tar.gz spark-e083334634ca0d7a25dee864fb2b9558ee92a2f7.tar.bz2 spark-e083334634ca0d7a25dee864fb2b9558ee92a2f7.zip |
[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 <davies.liu@gmail.com>
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 <joshrosen@apache.org>
-rw-r--r-- | python/pyspark/rdd.py | 4 | ||||
-rw-r--r-- | python/pyspark/tests.py | 9 |
2 files changed, 12 insertions, 1 deletions
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]) |