You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@community.apache.org by se...@apache.org on 2016/04/11 01:49:41 UTC
svn commit: r1738495 -
/comdev/reporter.apache.org/trunk/scripts/mailglomper2.py
Author: sebb
Date: Sun Apr 10 23:49:41 2016
New Revision: 1738495
URL: http://svn.apache.org/viewvc?rev=1738495&view=rev
Log:
Don't process mailing lists for non-PMCs
Modified:
comdev/reporter.apache.org/trunk/scripts/mailglomper2.py
Modified: comdev/reporter.apache.org/trunk/scripts/mailglomper2.py
URL: http://svn.apache.org/viewvc/comdev/reporter.apache.org/trunk/scripts/mailglomper2.py?rev=1738495&r1=1738494&r2=1738495&view=diff
==============================================================================
--- comdev/reporter.apache.org/trunk/scripts/mailglomper2.py (original)
+++ comdev/reporter.apache.org/trunk/scripts/mailglomper2.py Sun Apr 10 23:49:41 2016
@@ -19,6 +19,7 @@ import urlutils
import urllib.error
import traceback
import errtee
+import committee_info
SECS_PER_DAY = 86400
SECS_PER_WEEK = 604800
@@ -188,12 +189,18 @@ tsprint("Started")
signal.signal(signal.SIGINT, handle) # This stops Python from raising KeyboardInterrupt
signal.signal(signal.SIGTERM, handle)
+pmcmails = committee_info.PMCmails()
+if 'empire-db' in pmcmails: # append entry
+ pmcmails.append('empire')
+
lastCheckpoint = time.time() # when output files were last saved
for mlist in re.finditer(r"<a href='([-a-z0-9]+)/'", data):
ml = mlist.group(1)
- # TODO reject all but current projects, meanwhile we don't want these:
- if ml.startswith('www-'):
- continue # don't want ASF mailing lists
+ pfx = ml.split('-')[0]
+ # skip all but current projects
+ if not pfx in pmcmails:
+ tsprint("Skipping " + ml) # temporary for checking
+ continue
tsprint("Processing: " + ml)
start = time.time()