Github user holdenk commented on a diff in the pull request:
https://github.com/apache/spark/pull/13571#discussion_r72871316
--- Diff: python/pyspark/sql/functions.py ---
@@ -1731,13 +1749,115 @@ def sort_array(col, asc=True):
# ---------------------------- User Defined Function
----------------------------------
+def _wrap_jython_func(sc, src, ser_vars, ser_imports, setup_code,
returnType):
+ return sc._jvm.org.apache.spark.sql.execution.python.JythonFunction(
+ src, ser_vars, ser_imports, setup_code, sc._jsc.sc())
+
+
def _wrap_function(sc, func, returnType):
command = (func, returnType)
pickled_command, broadcast_vars, env, includes =
_prepare_for_python_RDD(sc, command)
return sc._jvm.PythonFunction(bytearray(pickled_command), env,
includes, sc.pythonExec,
sc.pythonVer, broadcast_vars,
sc._javaAccumulator)
+class UserDefinedJythonFunction(object):
+ """
+ User defined function in Jython - note this might be a bad idea to use.
+
+ .. versionadded:: 2.0
+ .. Note: Experimental
+ """
+ def __init__(self, func, returnType, name=None, setupCode=""):
+ self.func = func
+ self.returnType = returnType
+ self.setupCode = setupCode
+ self._judf = self._create_judf(name)
+
+ def _create_judf(self, name):
+ func = self.func
+ from pyspark.sql import SQLContext
+ sc = SparkContext.getOrCreate()
+ # Empty strings allow the Scala code to recognize no data and skip
adding the Jython
+ # code to handle vars or imports if not needed.
+ serialized_vars = ""
+ serialized_imports = ""
+ if isinstance(func, basestring):
+ src = func
+ else:
+ try:
+ import dill
--- End diff --
So dill lets us get at the source, and cloudpickle doesn't get the source.
Since Jython is a different VM we need to send the source - not the serialized
function.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
