Merge branch 'streaming' into ScrapCode-streaming

Conflicts:
	streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala
	streaming/src/main/scala/spark/streaming/dstream/NetworkInputDStream.scala

1 files changed, 38 insertions, 0 deletions

diff --git a/python/pyspark/files.py b/python/pyspark/files.py
new file mode 100644
index 0000000000..001b7a28b6
--- /dev/null
+++ b/python/pyspark/files.py
@@ -0,0 +1,38 @@
+import os
+
+
+class SparkFiles(object):
+    """
+    Resolves paths to files added through
+    L{SparkContext.addFile()<pyspark.context.SparkContext.addFile>}.
+
+    SparkFiles contains only classmethods; users should not create SparkFiles
+    instances.
+    """
+
+    _root_directory = None
+    _is_running_on_worker = False
+    _sc = None
+
+    def __init__(self):
+        raise NotImplementedError("Do not construct SparkFiles objects")
+
+    @classmethod
+    def get(cls, filename):
+        """
+        Get the absolute path of a file added through C{SparkContext.addFile()}.
+        """
+        path = os.path.join(SparkFiles.getRootDirectory(), filename)
+        return os.path.abspath(path)
+
+    @classmethod
+    def getRootDirectory(cls):
+        """
+        Get the root directory that contains files added through
+        C{SparkContext.addFile()}.
+        """
+        if cls._is_running_on_worker:
+            return cls._root_directory
+        else:
+            # This will have to change if we support multiple SparkContexts:
+            return cls._sc._jvm.spark.SparkFiles.getRootDirectory()