Mercurial > hg > cc > azure

annotate master/bin/fixDates.py @ 28:db75ec542c66

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
more stuff
author Henry S. Thompson <ht@markup.co.uk>
date Sat, 10 Nov 2018 13:22:21 +0000
parents dd19cf97b6dd
children 580cc12c9712
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
24
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
1 #!/usr/bin/env python3
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
2 import sys,re
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
3 ok=re.compile('(https?) ([^ ]*) ((?:19|20)..) ([0-9][0-9]*)$')
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
4 #parseable=re.compile('.*[-:/]\w+[-:/]|\w+\s\d{4}|\d{10}')
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
5 from dateparser import parse
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
6
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
7 bogons=0
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
8 tab={}
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
9 months={'Jan':1,'Feb':2,'Mar':3,'Apr':4,'May':5,'Jun':6,
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
10 'Jul':7,'Aug':8,'Sep':9,'Oct':10,'Nov':11,'Dec':12}
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
11 for l in sys.stdin:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
12 ff=ok.match(l)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
13 if ff is not None:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
14 #print(l,end='')
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
15 scheme=ff.group(1)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
16 try:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
17 # More alphas then numerics...
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
18 try:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
19 month=months[ff.group(2)]
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
20 except KeyError:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
21 month=int(ff.group(2))
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
22 year=int(ff.group(3))
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
23 except:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
24 # Unusual month or year field
27
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
25 try:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
26 d=parse("%s %s"%(ff.group(2),ff.group(3)))
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
27 if d is None:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
28 print(5,ff.group(1),ff.group(2),ff.group(3),file=sys.stderr)
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
29 year=0
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
30 month=0
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
31 elif d.year<1970:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
32 year=0
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
33 month=1
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
34 elif d.year>2019:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
35 month=1
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
36 year=2019
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
37 else:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
38 month=d.month
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
39 year=d.year
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
40 except Exception as e:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
41 print(6,e,l,file=sys.stderr)
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
42 bogons+=1
24
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
43 count=int(ff.group(4))
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
44 key=(scheme,year,month)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
45 tab[key]=tab.get(key,0)+count
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
46 continue
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
47 cols=l.split()
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
48 scheme=cols[0]
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
49 if scheme[-1]==':':
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
50 scheme=scheme[0:-1]
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
51 if scheme not in ('http','https'):
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
52 # The last 3 lines are needed because we get both http: with nothing else, when there was no last-mod
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
53 # header, or http by itself, when the last-mod consisted entirely of TZ info, which then gets deleted
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
54 print(1,scheme,l,file=sys.stderr)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
55 bogons+=1
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
56 continue
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
57 try:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
58 cols=cols[1:]
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
59 count=int(cols.pop())
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
60 except:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
61 print(2,cols,file=sys.stderr)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
62 bogons+=1
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
63 continue
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
64 if cols==[]:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
65 key=(scheme,0,0)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
66 tab[key]=tab.get(key,0)+count
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
67 continue
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
68 l=' '.join(cols)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
69 try:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
70 d=parse(l)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
71 if d is None:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
72 print(3,d,l,count,file=sys.stderr)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
73 year=0
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
74 month=2
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
75 elif d.year<1970:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
76 key=(scheme,0,1)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
77 elif d.year>2019:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
78 key=(scheme,2019,1)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
79 else:
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
80 key=(scheme,d.year,d.month)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
81 tab[key]=tab.get(key,0)+count
27
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
82 except Exception as e:
24
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
83 print(4,e,l,file=sys.stderr)
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
84 bogons+=1
27
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
85 if tab=={}:
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
86 # ssh screwed up
dd19cf97b6dd attempt to fix robustness pblms
Henry S. Thompson <ht@markup.co.uk>
parents: 24
diff changeset
87 exit(1)
24
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
88 for ((s,m,y),c) in tab.items():
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
89 print(s,m,y,c,sep='\t')
b4e3beb2227e improved error handling,
Henry S. Thompson <ht@markup.co.uk>
parents: 20
diff changeset
90 print(bogons,file=sys.stderr)