Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/19339#discussion_r141231147
--- Diff: python/pyspark/sql/readwriter.py ---
@@ -420,7 +425,29 @@ def csv(self, path, schema=None, sep=None,
encoding=None, quote=None, escape=Non
columnNameOfCorruptRecord=columnNameOfCorruptRecord,
multiLine=multiLine)
if isinstance(path, basestring):
path = [path]
- return
self._df(self._jreader.csv(self._spark._sc._jvm.PythonUtils.toSeq(path)))
+ if type(path) == list:
+ return
self._df(self._jreader.csv(self._spark._sc._jvm.PythonUtils.toSeq(path)))
+ elif isinstance(path, RDD):
+ def func(iterator):
+ for x in iterator:
+ if not isinstance(x, basestring):
+ x = unicode(x)
+ if isinstance(x, unicode):
+ x = x.encode("utf-8")
+ yield x
+ keyed = path.mapPartitions(func)
+ keyed._bypass_serializer = True
+ jrdd = keyed._jrdd.map(self._spark._jvm.BytesToString())
+ # see SPARK-22112
+ # There aren't any jvm api for creating a dataframe from rdd
storing csv.
--- End diff --
Let's fix these comments like,
```
SPARK-22112: There aren't any jvm api for creating a dataframe from rdd
storing csv.
...
```
or
```
There aren't any jvm api ...
...
for creating a dataframe from dataset storing csv. See SPARK-22112.
```
when we happened to fix some code around here or review other PRs fixing
some codes around here in the future.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
