Created
October 25, 2013 22:26
-
-
Save dustin/7162792 to your computer and use it in GitHub Desktop.
dehumanizing/rewriting/combining sizing stuff
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| import re | |
| import string | |
| import fileinput | |
| import collections | |
| abbrevs = ( | |
| (1<<50L, 'PB'), | |
| (1<<40L, 'TB'), | |
| (1<<30L, 'GB'), | |
| (1<<20L, 'MB'), | |
| (1<<10L, 'kB'), | |
| (1, 'b') | |
| ) | |
| revabrevs = dict([(v, k) for k, v in abbrevs]) | |
| ROBOT=re.compile(r'(\d+)([A-z]+)-') | |
| def de_humanize_bytes(s): | |
| match = ROBOT.search(s) | |
| return int(match.groups()[0]) * revabrevs[match.groups()[1]] | |
| found = collections.defaultdict(lambda: 0) | |
| for line in fileinput.input(): | |
| line = string.replace(line, " byte", "b") | |
| line = string.replace(line, " - ", "-") | |
| parts = line.split(" ") | |
| found[parts[0]] += int(parts[1]) | |
| histo = [(k,de_humanize_bytes(k),v) for k,v in found.iteritems()] | |
| histo.sort(key=lambda x: x[1]) | |
| for bucket, _, count in histo: | |
| print bucket, count | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment