def _get_filelist_remote(remote_uri, recursive = True):
## If remote_uri ends with '/' then all remote files will have
## the remote_uri prefix removed in the relative path.
## If, on the other hand, the remote_uri ends with something else
## (probably alphanumeric symbol) we'll use the last path part
## in the relative path.
##
## Complicated, eh? See an example:
## _get_filelist_remote("s3://bckt/abc/def") may yield:
## { 'def/file1.jpg' : {}, 'def/xyz/blah.txt' : {} }
## _get_filelist_remote("s3://bckt/abc/def/") will yield:
## { 'file1.jpg' : {}, 'xyz/blah.txt' : {} }
## Furthermore a prefix-magic can restrict the return list:
## _get_filelist_remote("s3://bckt/abc/def/x") yields:
## { 'xyz/blah.txt' : {} }
info(u"Retrieving list of remote files for %s ..." % remote_uri)
s3 = S3(Config())
response = s3.bucket_list(remote_uri.bucket(), prefix = remote_uri.object(), recursive = recursive)
rem_base_original = rem_base = remote_uri.object()
remote_uri_original = remote_uri
if rem_base != '' and rem_base[-1] != '/':
rem_base = rem_base[:rem_base.rfind('/')+1]
remote_uri = S3Uri("s3://%s/%s" % (remote_uri.bucket(), rem_base))
rem_base_len = len(rem_base)
rem_list = SortedDict(ignore_case = False)
break_now = False
for object in response['list']:
if object['Key'] == rem_base_original and object['Key'][-1] != os.path.sep:
## We asked for one file and we got that file :-)
key = os.path.basename(object['Key'])
object_uri_str = remote_uri_original.uri()
break_now = True
rem_list = SortedDict(ignore_case = False) ## Remove whatever has already been put to rem_list
else:
key = object['Key'][rem_base_len:] ## Beware - this may be '' if object['Key']==rem_base !!
object_uri_str = remote_uri.uri() + key
rem_list[key] = {
'size' : int(object['Size']),
'timestamp' : dateS3toUnix(object['LastModified']), ## Sadly it's upload time, not our lastmod time :-(
'md5' : object['ETag'][1:-1],
'object_key' : object['Key'],
'object_uri_str' : object_uri_str,
'base_uri' : remote_uri,
'dev' : None,
'inode' : None,
}
md5 = object['ETag'][1:-1]
rem_list.record_md5(key, md5)
if break_now:
break
return rem_list
def _get_filelist_remote(remote_uri, recursive = True):
## If remote_uri ends with '/' then all remote files will have
## the remote_uri prefix removed in the relative path.
## If, on the other hand, the remote_uri ends with something else
## (probably alphanumeric symbol) we'll use the last path part
## in the relative path.
##
## Complicated, eh? See an example:
## _get_filelist_remote("s3://bckt/abc/def") may yield:
## { 'def/file1.jpg' : {}, 'def/xyz/blah.txt' : {} }
## _get_filelist_remote("s3://bckt/abc/def/") will yield:
## { 'file1.jpg' : {}, 'xyz/blah.txt' : {} }
## Furthermore a prefix-magic can restrict the return list:
## _get_filelist_remote("s3://bckt/abc/def/x") yields:
## { 'xyz/blah.txt' : {} }
info(u"Retrieving list of remote files for %s ..." % remote_uri)
s3 = S3(Config())
response = s3.bucket_list(remote_uri.bucket(), prefix = remote_uri.object(), recursive = recursive)
rem_base_original = rem_base = remote_uri.object()
remote_uri_original = remote_uri
if rem_base != '' and rem_base[-1] != '/':
rem_base = rem_base[:rem_base.rfind('/')+1]
remote_uri = S3Uri("s3://%s/%s" % (remote_uri.bucket(), rem_base))
rem_base_len = len(rem_base)
rem_list = SortedDict(ignore_case = False)
break_now = False
for object in response['list']:
if object['Key'] == rem_base_original and object['Key'][-1] != os.path.sep:
## We asked for one file and we got that file :-)
key = os.path.basename(object['Key'])
object_uri_str = remote_uri_original.uri()
break_now = True
rem_list = SortedDict(ignore_case = False) ## Remove whatever has already been put to rem_list
else:
key = object['Key'][rem_base_len:] ## Beware - this may be '' if object['Key']==rem_base !!
object_uri_str = remote_uri.uri() + key
rem_list[key] = {
'size' : int(object['Size']),
'timestamp' : dateS3toUnix(object['LastModified']), ## Sadly it's upload time, not our lastmod time :-(
'md5' : object['ETag'][1:-1],
'object_key' : object['Key'],
'object_uri_str' : object_uri_str,
'base_uri' : remote_uri,
'dev' : None,
'inode' : None,
}
md5 = object['ETag'][1:-1]
rem_list.record_md5(key, md5)
if break_now:
break
return rem_list
def fetch_remote_list(args, require_attribs = False, recursive = None):
def _get_filelist_remote(remote_uri, recursive = True):
## If remote_uri ends with '/' then all remote files will have
## the remote_uri prefix removed in the relative path.
## If, on the other hand, the remote_uri ends with something else
## (probably alphanumeric symbol) we'll use the last path part
## in the relative path.
##
## Complicated, eh? See an example:
## _get_filelist_remote("s3://bckt/abc/def") may yield:
## { 'def/file1.jpg' : {}, 'def/xyz/blah.txt' : {} }
## _get_filelist_remote("s3://bckt/abc/def/") will yield:
## { 'file1.jpg' : {}, 'xyz/blah.txt' : {} }
## Furthermore a prefix-magic can restrict the return list:
## _get_filelist_remote("s3://bckt/abc/def/x") yields:
## { 'xyz/blah.txt' : {} }
info(u"Retrieving list of remote files for %s ..." % remote_uri)
s3 = S3(Config())
response = s3.bucket_list(remote_uri.bucket(), prefix = remote_uri.object(), recursive = recursive)
rem_base_original = rem_base = remote_uri.object()
remote_uri_original = remote_uri
if rem_base != '' and rem_base[-1] != '/':
rem_base = rem_base[:rem_base.rfind('/')+1]
remote_uri = S3Uri("s3://%s/%s" % (remote_uri.bucket(), rem_base))
rem_base_len = len(rem_base)
rem_list = SortedDict(ignore_case = False)
break_now = False
for object in response['list']:
if object['Key'] == rem_base_original and object['Key'][-1] != os.path.sep:
## We asked for one file and we got that file :-)
key = os.path.basename(object['Key'])
object_uri_str = remote_uri_original.uri()
break_now = True
rem_list = SortedDict(ignore_case = False) ## Remove whatever has already been put to rem_list
else:
key = object['Key'][rem_base_len:] ## Beware - this may be '' if object['Key']==rem_base !!
object_uri_str = remote_uri.uri() + key
rem_list[key] = {
'size' : int(object['Size']),
'timestamp' : dateS3toUnix(object['LastModified']), ## Sadly it's upload time, not our lastmod time :-(
'md5' : object['ETag'][1:-1],
'object_key' : object['Key'],
'object_uri_str' : object_uri_str,
'base_uri' : remote_uri,
'dev' : None,
'inode' : None,
}
md5 = object['ETag'][1:-1]
rem_list.record_md5(key, md5)
if break_now:
break
return rem_list
cfg = Config()
remote_uris = []
remote_list = SortedDict(ignore_case = False)
if type(args) not in (list, tuple):
args = [args]
if recursive == None:
recursive = cfg.recursive
for arg in args:
uri = S3Uri(arg)
if not uri.type == 's3':
raise ParameterError("Expecting S3 URI instead of '%s'" % arg)
remote_uris.append(uri)
if recursive:
for uri in remote_uris:
objectlist = _get_filelist_remote(uri)
for key in objectlist:
remote_list[key] = objectlist[key]
remote_list.record_md5(key, objectlist.get_md5(key))
else:
for uri in remote_uris:
uri_str = str(uri)
## Wildcards used in remote URI?
## If yes we'll need a bucket listing...
if uri_str.find('*') > -1 or uri_str.find('?') > -1:
first_wildcard = uri_str.find('*')
first_questionmark = uri_str.find('?')
if first_questionmark > -1 and first_questionmark < first_wildcard:
first_wildcard = first_questionmark
prefix = uri_str[:first_wildcard]
rest = uri_str[first_wildcard+1:]
## Only request recursive listing if the 'rest' of the URI,
## i.e. the part after first wildcard, contains '/'
need_recursion = rest.find('/') > -1
objectlist = _get_filelist_remote(S3Uri(prefix), recursive = need_recursion)
for key in objectlist:
## Check whether the 'key' matches the requested wildcards
if glob.fnmatch.fnmatch(objectlist[key]['object_uri_str'], uri_str):
remote_list[key] = objectlist[key]
else:
## No wildcards - simply append the given URI to the list
key = os.path.basename(uri.object())
if not key:
raise ParameterError(u"Expecting S3 URI with a filename or --recursive: %s" % uri.uri())
remote_item = {
'base_uri': uri,
'object_uri_str': unicode(uri),
'object_key': uri.object()
}
if require_attribs:
response = S3(cfg).object_info(uri)
remote_item.update({
'size': int(response['headers']['content-length']),
'md5': response['headers']['etag'].strip('"\''),
'timestamp' : dateRFC822toUnix(response['headers']['date'])
})
# get md5 from header if it's present. We would have set that during upload
if response['headers'].has_key('x-amz-meta-s3cmd-attrs'):
attrs = parse_attrs_header(response['headers']['x-amz-meta-s3cmd-attrs'])
if attrs.has_key('md5'):
remote_item.update({'md5': attrs['md5']})
remote_list[key] = remote_item
return remote_list
def fetch_remote_list(args, require_attribs = False, recursive = None):
def _get_filelist_remote(remote_uri, recursive = True):
## If remote_uri ends with '/' then all remote files will have
## the remote_uri prefix removed in the relative path.
## If, on the other hand, the remote_uri ends with something else
## (probably alphanumeric symbol) we'll use the last path part
## in the relative path.
##
## Complicated, eh? See an example:
## _get_filelist_remote("s3://bckt/abc/def") may yield:
## { 'def/file1.jpg' : {}, 'def/xyz/blah.txt' : {} }
## _get_filelist_remote("s3://bckt/abc/def/") will yield:
## { 'file1.jpg' : {}, 'xyz/blah.txt' : {} }
## Furthermore a prefix-magic can restrict the return list:
## _get_filelist_remote("s3://bckt/abc/def/x") yields:
## { 'xyz/blah.txt' : {} }
info(u"Retrieving list of remote files for %s ..." % remote_uri)
s3 = S3(Config())
response = s3.bucket_list(remote_uri.bucket(), prefix = remote_uri.object(), recursive = recursive)
rem_base_original = rem_base = remote_uri.object()
remote_uri_original = remote_uri
if rem_base != '' and rem_base[-1] != '/':
rem_base = rem_base[:rem_base.rfind('/')+1]
remote_uri = S3Uri("s3://%s/%s" % (remote_uri.bucket(), rem_base))
rem_base_len = len(rem_base)
rem_list = SortedDict(ignore_case = False)
break_now = False
for object in response['list']:
if object['Key'] == rem_base_original and object['Key'][-1] != os.path.sep:
## We asked for one file and we got that file :-)
key = os.path.basename(object['Key'])
object_uri_str = remote_uri_original.uri()
break_now = True
rem_list = SortedDict(ignore_case = False) ## Remove whatever has already been put to rem_list
else:
key = object['Key'][rem_base_len:] ## Beware - this may be '' if object['Key']==rem_base !!
object_uri_str = remote_uri.uri() + key
rem_list[key] = {
'size' : int(object['Size']),
'timestamp' : dateS3toUnix(object['LastModified']), ## Sadly it's upload time, not our lastmod time :-(
'md5' : object['ETag'][1:-1],
'object_key' : object['Key'],
'object_uri_str' : object_uri_str,
'base_uri' : remote_uri,
'dev' : None,
'inode' : None,
}
md5 = object['ETag'][1:-1]
rem_list.record_md5(key, md5)
if break_now:
break
return rem_list
cfg = Config()
remote_uris = []
remote_list = SortedDict(ignore_case = False)
if type(args) not in (list, tuple):
args = [args]
if recursive == None:
recursive = cfg.recursive
for arg in args:
uri = S3Uri(arg)
if not uri.type == 's3':
raise ParameterError("Expecting S3 URI instead of '%s'" % arg)
remote_uris.append(uri)
if recursive:
for uri in remote_uris:
objectlist = _get_filelist_remote(uri)
for key in objectlist:
remote_list[key] = objectlist[key]
remote_list.record_md5(key, objectlist.get_md5(key))
else:
for uri in remote_uris:
uri_str = str(uri)
## Wildcards used in remote URI?
## If yes we'll need a bucket listing...
if uri_str.find('*') > -1 or uri_str.find('?') > -1:
first_wildcard = uri_str.find('*')
first_questionmark = uri_str.find('?')
if first_questionmark > -1 and first_questionmark < first_wildcard:
first_wildcard = first_questionmark
prefix = uri_str[:first_wildcard]
rest = uri_str[first_wildcard+1:]
## Only request recursive listing if the 'rest' of the URI,
## i.e. the part after first wildcard, contains '/'
need_recursion = rest.find('/') > -1
objectlist = _get_filelist_remote(S3Uri(prefix), recursive = need_recursion)
for key in objectlist:
## Check whether the 'key' matches the requested wildcards
if glob.fnmatch.fnmatch(objectlist[key]['object_uri_str'], uri_str):
remote_list[key] = objectlist[key]
else:
## No wildcards - simply append the given URI to the list
key = os.path.basename(uri.object())
if not key:
raise ParameterError(u"Expecting S3 URI with a filename or --recursive: %s" % uri.uri())
remote_item = {
'base_uri': uri,
'object_uri_str': unicode(uri),
'object_key': uri.object()
}
if require_attribs:
response = S3(cfg).object_info(uri)
remote_item.update({
'size': int(response['headers']['content-length']),
'md5': response['headers']['etag'].strip('"\''),
'timestamp' : dateRFC822toUnix(response['headers']['date'])
})
# get md5 from header if it's present. We would have set that during upload
if response['headers'].has_key('x-amz-meta-s3cmd-attrs'):
attrs = parse_attrs_header(response['headers']['x-amz-meta-s3cmd-attrs'])
if attrs.has_key('md5'):
remote_item.update({'md5': attrs['md5']})
remote_list[key] = remote_item
return remote_list
