def _extract_sid_wid_from_url(self, sheet_url=None):
url = urlparse.urlparse(sheet_url)
query_string = urlparse.parse_qs(url.query)
fragment = urlparse.parse_qs(url.fragment)
sid = query_string['key'][0]
gid = fragment['gid'][0]
wid = basin.encode("0123456789abcdefghijklmnopqrstuvwxyz", int(gid) ^ 31578)
return sid, wid
def detail(request, id):
alphabet = '0123456789abcdefghijklmnopqrstuvwxyz'
nid = basin.decode(alphabet, id)
paste = get_object_or_404(Paste, pk=nid)
paste.short = basin.encode(alphabet, paste.id)
return render(request, 'paste_detail.html', {'paste' : paste})
def md5_to_bucket_shard(md5):
""" calculate the shard label of the bucket name from md5 """
# "Consider utilizing multiple buckets that start with different
# alphanumeric characters. This will ensure a degree of partitioning
# from the start. The higher your volume of concurrent PUT and
# GET requests, the more impact this will likely have."
# -- http://aws.amazon.com/articles/1904
# "Bucket names must be a series of one or more labels. Adjacent
# labels are separated by a single period (.). [...] Each label must
# start and end with a lowercase letter or a number. "
# -- http://docs.aws.amazon.com/AmazonS3/latest/dev/BucketRestrictions.html
# see also: http://en.wikipedia.org/wiki/Base_36
ALPHABET = "0123456789abcdefghijklmnopqrstuvwxyz"
# http://stats.stackexchange.com/a/70884/14900
# take the first two digits of the hash and turn that into an inteter
# this should be evenly distributed
int_value = int(md5[0], 16)+10*int(md5[1], 16)
# divide by the length of the alphabet and take the remainder
bucket = int_value % len(ALPHABET)
return basin.encode(ALPHABET, bucket)
def _encode(bytes):
return basin.encode('23456789abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNPQRSTUVWXYZ', basin.bytestring_to_integer(bytes))
