Mercurial > hg > cc > cirrus_work
changeset 323:dc7847750384 trim
working on comparing miss key with miss url
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Fri, 23 Jan 2026 15:50:15 +0000 |
| parents | 783d65d43fb0 |
| children | 85612f32e9b6 |
| files | lib/python/cc/lmh/miss_bogons.py |
| diffstat | 1 files changed, 23 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib/python/cc/lmh/miss_bogons.py Fri Jan 23 15:50:15 2026 +0000 @@ -0,0 +1,23 @@ +#!/usr/bin/python3 +'''Compare the two columns of output from + cdb_one /tmp/hst/%d%d_a/shrunk.cdb 24 25 20230922103943 2>/tmp/hst/2424/cdx-00{}_misses + E.g. + b'4827://188.246.103.10/klubicko/?tab=events' b'10,103,246,188)/klubicko?tab=events' + b'4312://5.160.123.10/' b'10,123,160,5)/' +''' +import sys, re +kPat = re.compile("b'([0-9]*s?://)([^/]*)('$|/(.*)'$)") +kuPat = re.compile("^([^/]*)/?($|([?].*)$)") + +with open(sys.argv[1], 'r') as f: + for l in f: + (key, url) = l.rstrip().split(' ') + if (m:=kPat.match(key)): + (k_d,k_h,_,k_u) = m.groups() + else: + print("bad key |%s|"%key,file=sys.stderr) + exit(1) + #print(key,"|%s|%s|%s|"%(k_d,k_h,k_u)) + print(kuPat.sub('\\1\\2', k_u)) + +