Scripts to download files from google storage based on sha1 sums

third_party/gsutil/boto/glacier/utils.py

+# Copyright (c) 2012 Amazon.com, Inc. or its affiliates.  All Rights Reserved
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish, dis-
+# tribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the fol-
+# lowing conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABIL-
+# ITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# SHALL THE AUTHOR BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+#
+import hashlib
+import math
+
+
+_MEGABYTE = 1024 * 1024
+DEFAULT_PART_SIZE = 4 * _MEGABYTE
+MAXIMUM_NUMBER_OF_PARTS = 10000
+
+
+def minimum_part_size(size_in_bytes):
+    # The default part size (4 MB) will be too small for a very large
+    # archive, as there is a limit of 10,000 parts in a multipart upload.
+    # This puts the maximum allowed archive size with the default part size
+    # at 40,000 MB. We need to do a sanity check on the part size, and find
+    # one that works if the default is too small.
+    part_size = _MEGABYTE
+    if (DEFAULT_PART_SIZE * MAXIMUM_NUMBER_OF_PARTS) < size_in_bytes:
+        if size_in_bytes > (4096 * _MEGABYTE * 10000):
+            raise ValueError("File size too large: %s" % size_in_bytes)
+        min_part_size = size_in_bytes / 10000
+        power = 3
+        while part_size < min_part_size:
+            part_size = math.ldexp(_MEGABYTE, power)
+            power += 1
+        part_size = int(part_size)
+    else:
+        part_size = DEFAULT_PART_SIZE
+    return part_size
+
+
+def chunk_hashes(bytestring, chunk_size=_MEGABYTE):
+    chunk_count = int(math.ceil(len(bytestring) / float(chunk_size)))
+    hashes = []
+    for i in xrange(chunk_count):
+        start = i * chunk_size
+        end = (i + 1) * chunk_size
+        hashes.append(hashlib.sha256(bytestring[start:end]).digest())
+    return hashes
+
+
+def tree_hash(fo):
+    """
+    Given a hash of each 1MB chunk (from chunk_hashes) this will hash
+    together adjacent hashes until it ends up with one big one. So a
+    tree of hashes.
+    """
+    hashes = []
+    hashes.extend(fo)
+    while len(hashes) > 1:
+        new_hashes = []
+        while True:
+            if len(hashes) > 1:
+                first = hashes.pop(0)
+                second = hashes.pop(0)
+                new_hashes.append(hashlib.sha256(first + second).digest())
+            elif len(hashes) == 1:
+                only = hashes.pop(0)
+                new_hashes.append(only)
+            else:
+                break
+        hashes.extend(new_hashes)
+    return hashes[0]
+
+
+def compute_hashes_from_fileobj(fileobj, chunk_size=1024 * 1024):
+    """Compute the linear and tree hash from a fileobj.
+
+    This function will compute the linear/tree hash of a fileobj
+    in a single pass through the fileobj.
+
+    :param fileobj: A file like object.
+
+    :param chunk_size: The size of the chunks to use for the tree
+        hash.  This is also the buffer size used to read from
+        `fileobj`.
+
+    :rtype: tuple
+    :return: A tuple of (linear_hash, tree_hash).  Both hashes
+        are returned in hex.
+
+    """
+    linear_hash = hashlib.sha256()
+    chunks = []
+    chunk = fileobj.read(chunk_size)
+    while chunk:
+        linear_hash.update(chunk)
+        chunks.append(hashlib.sha256(chunk).digest())
+        chunk = fileobj.read(chunk_size)
+    return linear_hash.hexdigest(), bytes_to_hex(tree_hash(chunks))
+
+
+def bytes_to_hex(str_as_bytes):
+    return ''.join(["%02x" % ord(x) for x in str_as_bytes]).strip()