python/pyspark/files.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 import os
0019
0020
0021 __all__ = ['SparkFiles']
0022
0023
0024 class SparkFiles(object):
0025
0026     """
0027     Resolves paths to files added through :meth:`SparkContext.addFile`.
0028
0029     SparkFiles contains only classmethods; users should not create SparkFiles
0030     instances.
0031     """
0032
0033     _root_directory = None
0034     _is_running_on_worker = False
0035     _sc = None
0036
0037     def __init__(self):
0038         raise NotImplementedError("Do not construct SparkFiles objects")
0039
0040     @classmethod
0041     def get(cls, filename):
0042         """
0043         Get the absolute path of a file added through :meth:`SparkContext.addFile`.
0044         """
0045         path = os.path.join(SparkFiles.getRootDirectory(), filename)
0046         return os.path.abspath(path)
0047
0048     @classmethod
0049     def getRootDirectory(cls):
0050         """
0051         Get the root directory that contains files added through
0052         :meth:`SparkContext.addFile`.
0053         """
0054         if cls._is_running_on_worker:
0055             return cls._root_directory
0056         else:
0057             # This will have to change if we support multiple SparkContexts:
0058             return cls._sc._jvm.org.apache.spark.SparkFiles.getRootDirectory()