diff options
author | Davies Liu <davies.liu@gmail.com> | 2014-09-03 11:49:45 -0700 |
---|---|---|
committer | Josh Rosen <joshrosen@apache.org> | 2014-09-03 11:49:45 -0700 |
commit | 6481d27425f6d42ead36663c9a4ef7ee13b3a8c9 (patch) | |
tree | 051c394c0735be33d4bb7f9fd90f403e9b5f2dcd /python/pyspark/broadcast.py | |
parent | 6a72a36940311fcb3429bd34c8818bc7d513115c (diff) | |
download | spark-6481d27425f6d42ead36663c9a4ef7ee13b3a8c9.tar.gz spark-6481d27425f6d42ead36663c9a4ef7ee13b3a8c9.tar.bz2 spark-6481d27425f6d42ead36663c9a4ef7ee13b3a8c9.zip |
[SPARK-3309] [PySpark] Put all public API in __all__
Put all public API in __all__, also put them all in pyspark.__init__.py, then we can got all the documents for public API by `pydoc pyspark`. It also can be used by other programs (such as Sphinx or Epydoc) to generate only documents for public APIs.
Author: Davies Liu <davies.liu@gmail.com>
Closes #2205 from davies/public and squashes the following commits:
c6c5567 [Davies Liu] fix message
f7b35be [Davies Liu] put SchemeRDD, Row in pyspark.sql module
7e3016a [Davies Liu] add __all__ in mllib
6281b48 [Davies Liu] fix doc for SchemaRDD
6caab21 [Davies Liu] add public interfaces into pyspark.__init__.py
Diffstat (limited to 'python/pyspark/broadcast.py')
-rw-r--r-- | python/pyspark/broadcast.py | 24 |
1 files changed, 14 insertions, 10 deletions
diff --git a/python/pyspark/broadcast.py b/python/pyspark/broadcast.py index 675a2fcd2f..5c7c9cc161 100644 --- a/python/pyspark/broadcast.py +++ b/python/pyspark/broadcast.py @@ -31,6 +31,10 @@ import os from pyspark.serializers import CompressedSerializer, PickleSerializer + +__all__ = ['Broadcast'] + + # Holds broadcasted data received from Java, keyed by its id. _broadcastRegistry = {} @@ -59,11 +63,20 @@ class Broadcast(object): """ self.bid = bid if path is None: - self.value = value + self._value = value self._jbroadcast = java_broadcast self._pickle_registry = pickle_registry self.path = path + @property + def value(self): + """ Return the broadcasted value + """ + if not hasattr(self, "_value") and self.path is not None: + ser = CompressedSerializer(PickleSerializer()) + self._value = ser.load_stream(open(self.path)).next() + return self._value + def unpersist(self, blocking=False): self._jbroadcast.unpersist(blocking) os.unlink(self.path) @@ -72,15 +85,6 @@ class Broadcast(object): self._pickle_registry.add(self) return (_from_id, (self.bid, )) - def __getattr__(self, item): - if item == 'value' and self.path is not None: - ser = CompressedSerializer(PickleSerializer()) - value = ser.load_stream(open(self.path)).next() - self.value = value - return value - - raise AttributeError(item) - if __name__ == "__main__": import doctest |