Update copyright notices to use a central AUTHORS file.

[cumulus.git] / python / cumulus / store / s3.py

diff --git a/python/cumulus/store/s3.py b/python/cumulus/store/s3.py
index 65884ea..4ad403c 100644 (file)
--- a/python/cumulus/store/s3.py
+++ b/python/cumulus/store/s3.py
@@ -1,3 +1,23 @@
+# Cumulus: Efficient Filesystem Backup to the Cloud
+# Copyright (C) 2008-2010 The Cumulus Developers
+# See the AUTHORS file for a list of contributors.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+"""Amazon S3 storage backend.  Uses a URL of the form s3://BUCKET/PATH/."""
+
 import os, sys, tempfile
 import boto
 from boto.s3.bucket import Bucket
@@ -7,10 +27,21 @@ import cumulus.store
 
 class S3Store(cumulus.store.Store):
     def __init__(self, url, **kw):
-        (bucket, prefix) = self.path.lstrip("/").split("/", 1)
+        # Old versions of the Python urlparse library will take a URL like
+        # s3://bucket/path/ and include the bucket with the path, while new
+        # versions (2.6 and later) treat it as the netloc (which seems more
+        # correct).
+        #
+        # But, so that we can work with either behavior, for now just combine
+        # the netloc and path together before we do any further processing
+        # (which will then split the combined path apart into a bucket and path
+        # again).  If we didn't want to support Python 2.5, this would be
+        # easier as we could just use the netloc as the bucket directly.
+        path = self.netloc + '/' + self.path
+        (bucket, prefix) = path.lstrip("/").split("/", 1)
         self.conn = boto.connect_s3(is_secure=False)
         self.bucket = self.conn.create_bucket(bucket)
-        self.prefix = prefix.rstrip ("/")
+        self.prefix = prefix.strip("/")
         self.scan_cache = {}
 
     def _get_key(self, type, name):