def _download_to_fileob(self, fileobj, num_chunks, chunk_size,
verify_hashes, retry_exceptions):
for i in range(num_chunks):
byte_range = ((i * chunk_size), ((i + 1) * chunk_size) - 1)
data, expected_tree_hash = self._download_byte_range(
byte_range, retry_exceptions)
if verify_hashes:
actual_tree_hash = tree_hash_from_str(data)
if expected_tree_hash != actual_tree_hash:
raise TreeHashDoesNotMatchError(
"The calculated tree hash %s does not match the "
"expected tree hash %s for the byte range %s" %
(actual_tree_hash, expected_tree_hash, byte_range))
fileobj.write(data)
def _download_to_fileob(self, fileobj, num_chunks, chunk_size, verify_hashes,
retry_exceptions):
for i in range(num_chunks):
byte_range = ((i * chunk_size), ((i + 1) * chunk_size) - 1)
data, expected_tree_hash = self._download_byte_range(
byte_range, retry_exceptions)
if verify_hashes:
actual_tree_hash = tree_hash_from_str(data)
if expected_tree_hash != actual_tree_hash:
raise TreeHashDoesNotMatchError(
"The calculated tree hash %s does not match the "
"expected tree hash %s for the byte range %s" % (
actual_tree_hash, expected_tree_hash, byte_range))
fileobj.write(data)
def get_output(self, byte_range=None, validate_checksum=False):
"""
This operation downloads the output of the job. Depending on
the job type you specified when you initiated the job, the
output will be either the content of an archive or a vault
inventory.
You can download all the job output or download a portion of
the output by specifying a byte range. In the case of an
archive retrieval job, depending on the byte range you
specify, Amazon Glacier returns the checksum for the portion
of the data. You can compute the checksum on the client and
verify that the values match to ensure the portion you
downloaded is the correct data.
:type byte_range: tuple
:param range: A tuple of integer specifying the slice (in bytes)
of the archive you want to receive
:type validate_checksum: bool
:param validate_checksum: Specify whether or not to validate
the associate tree hash. If the response does not contain
a TreeHash, then no checksum will be verified.
"""
response = self.vault.layer1.get_job_output(self.vault.name,
self.id,
byte_range)
if validate_checksum and 'TreeHash' in response:
data = response.read()
actual_tree_hash = tree_hash_from_str(data)
if response['TreeHash'] != actual_tree_hash:
raise TreeHashDoesNotMatchError(
"The calculated tree hash %s does not match the "
"expected tree hash %s for the byte range %s" % (
actual_tree_hash, response['TreeHash'], byte_range))
return response
def get_output(self, byte_range=None, validate_checksum=False):
"""
This operation downloads the output of the job. Depending on
the job type you specified when you initiated the job, the
output will be either the content of an archive or a vault
inventory.
You can download all the job output or download a portion of
the output by specifying a byte range. In the case of an
archive retrieval job, depending on the byte range you
specify, Amazon Glacier returns the checksum for the portion
of the data. You can compute the checksum on the client and
verify that the values match to ensure the portion you
downloaded is the correct data.
:type byte_range: tuple
:param range: A tuple of integer specifying the slice (in bytes)
of the archive you want to receive
:type validate_checksum: bool
:param validate_checksum: Specify whether or not to validate
the associate tree hash. If the response does not contain
a TreeHash, then no checksum will be verified.
"""
response = self.vault.layer1.get_job_output(self.vault.name,
self.id,
byte_range)
if validate_checksum and 'TreeHash' in response:
data = response.read()
actual_tree_hash = tree_hash_from_str(data)
if response['TreeHash'] != actual_tree_hash:
raise TreeHashDoesNotMatchError(
"The calculated tree hash %s does not match the "
"expected tree hash %s for the byte range %s" % (
actual_tree_hash, response['TreeHash'], byte_range))
return response