diff options
Diffstat (limited to 'python/pyspark')
-rw-r--r-- | python/pyspark/sql.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 46540ca3f1..95086a2258 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -1267,7 +1267,9 @@ class SQLContext: 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 = rdd.mapPartitions(func) keyed._bypass_serializer = True jrdd = keyed._jrdd.map(self._jvm.BytesToString()) |