# HG changeset patch # User Henry Thompson # Date 1692475349 14400 # Node ID 7bbb14f6e3946d2266f44b0adb67005deceba56a # Parent e115f2e89af652a1548a5238f430c1bebcd26055# Parent bf09a1d80d7b98895a5735aae3fe1cb59ca46c01 merge diff -r bf09a1d80d7b -r 7bbb14f6e394 all_warc_lmh_out.tar.gz Binary file all_warc_lmh_out.tar.gz has changed diff -r bf09a1d80d7b -r 7bbb14f6e394 bin/sort_date.py --- a/bin/sort_date.py Fri Aug 18 18:25:54 2023 +0100 +++ b/bin/sort_date.py Sat Aug 19 16:02:29 2023 -0400 @@ -39,12 +39,13 @@ epoch = 32535215999.0 parts = urlsplit(uri) nl = parts.netloc + pq = '?%s'%parts.query if parts.query else ''; #print('nl',nl,file=sys.stderr) if ':' in nl: pa,pp=nl.split(':') - return ('%s:%s)%s'%(auth(pa), pp, parts.path),epoch) + return ('%s:%s)%s%s'%(auth(pa), pp, parts.path, pq),epoch) else: - return ('%s)%s'%(auth(nl), parts.path),epoch) + return ('%s)%s%s'%(auth(nl), parts.path, pq),epoch) except (TypeError,IndexError,ValueError) as e: print(dateTime.rstrip(),e,sep='\t',file=sys.stderr) return