Skip to content

[SPARK-11836] [SQL] use existing SQLContext for udf/cast (1.5 branch) #9915

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-11836] [SQL] use existing SQLContext for udf/cast (1.5 branch) #9915

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions python/pyspark/sql/column.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,9 +318,9 @@ def cast(self, dataType):
if isinstance(dataType, basestring):
jc = self._jc.cast(dataType)
elif isinstance(dataType, DataType):
sc = SparkContext._active_spark_context
ssql_ctx = sc._jvm.SQLContext(sc._jsc.sc())
jdt = ssql_ctx.parseDataType(dataType.json())
from pyspark.sql import SQLContext
ctx = SQLContext._instantiatedContext
jdt = ctx._ssql_ctx.parseDataType(dataType.json())
jc = self._jc.cast(jdt)
else:
raise TypeError("unexpected type: %s" % type(dataType))
Expand Down
3 changes: 3 additions & 0 deletions python/pyspark/sql/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,8 @@ class SQLContext(object):
SQLContext in the JVM, instead we make all calls to this object.
"""

_instantiatedContext = None

@ignore_unicode_prefix
def __init__(self, sparkContext, sqlContext=None):
"""Creates a new SQLContext.
Expand All @@ -99,6 +101,7 @@ def __init__(self, sparkContext, sqlContext=None):
self._scala_SQLContext = sqlContext
_monkey_patch_RDD(self)
install_exception_handler()
SQLContext._instantiatedContext = self

@property
def _ssql_ctx(self):
Expand Down
5 changes: 3 additions & 2 deletions python/pyspark/sql/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1422,14 +1422,15 @@ def __init__(self, func, returnType, name=None):
self._judf = self._create_judf(name)

def _create_judf(self, name):
from pyspark.sql import SQLContext
f, returnType = self.func, self.returnType # put them in closure `func`
func = lambda _, it: map(lambda x: returnType.toInternal(f(*x)), it)
ser = AutoBatchedSerializer(PickleSerializer())
command = (func, None, ser, ser)
sc = SparkContext._active_spark_context
pickled_command, broadcast_vars, env, includes = _prepare_for_python_RDD(sc, command, self)
ssql_ctx = sc._jvm.SQLContext(sc._jsc.sc())
jdt = ssql_ctx.parseDataType(self.returnType.json())
ctx = SQLContext._instantiatedContext
jdt = ctx._ssql_ctx.parseDataType(self.returnType.json())
if name is None:
name = f.__name__ if hasattr(f, '__name__') else f.__class__.__name__
judf = sc._jvm.UserDefinedPythonFunction(name, bytearray(pickled_command), env, includes,
Expand Down