Mercurial > hg > cc > cirrus_work
comparison bin/sort_date.py @ 83:d92bd8527718
use surt instead of trying to create index term by hand
author | Henry Thompson <ht@markup.co.uk> |
---|---|
date | Sat, 19 Aug 2023 16:33:23 -0400 |
parents | 7bbb14f6e394 |
children | c18c307cc325 |
comparison
equal
deleted
inserted
replaced
82:7bbb14f6e394 | 83:d92bd8527718 |
---|---|
3 # Recommended to also sed '/GMT$/s/\([^ ]\)GMT$/\1 GMT/' | 3 # Recommended to also sed '/GMT$/s/\([^ ]\)GMT$/\1 GMT/' |
4 # to fix a common 'bad' timestamp (~ .2% of inputs) | 4 # to fix a common 'bad' timestamp (~ .2% of inputs) |
5 import email.utils | 5 import email.utils |
6 import sys | 6 import sys |
7 from urllib.parse import urlsplit, unquote | 7 from urllib.parse import urlsplit, unquote |
8 from surt import surt | |
8 import re | 9 import re |
9 # Thanks to https://stackoverflow.com/a/8776871 | 10 # Thanks to https://stackoverflow.com/a/8776871 |
10 import locale | 11 import locale |
11 from functools import cmp_to_key | 12 from functools import cmp_to_key |
12 | 13 |
35 try: | 36 try: |
36 try: | 37 try: |
37 epoch = email.utils.parsedate_to_datetime(dateTime).timestamp() | 38 epoch = email.utils.parsedate_to_datetime(dateTime).timestamp() |
38 except OverflowError: | 39 except OverflowError: |
39 epoch = 32535215999.0 | 40 epoch = 32535215999.0 |
41 return (surt(uri),epoch) | |
40 parts = urlsplit(uri) | 42 parts = urlsplit(uri) |
41 nl = parts.netloc | 43 nl = parts.netloc |
42 pq = '?%s'%parts.query if parts.query else ''; | 44 pq = '?%s'%parts.query if parts.query else ''; |
43 #print('nl',nl,file=sys.stderr) | 45 #print('nl',nl,file=sys.stderr) |
44 if ':' in nl: | 46 if ':' in nl: |