in scripts/cronjobs/parsereleases.py [0:0]
def main():
uc = UrlCache(silent=True)
find_ls = uc.get(FIND_LS, name='find-ls2.txt.gz')
# -rw-rw-r-- 1 svnwc svnwc 479 2022-06-17 12:55 UTC ./.htaccess
# 0 1 2 3 4 5 6 7 8
with gzip.open(find_ls, mode='rt') as r:
for l in r:
fields = l.split() # split the find line (the split drops the final LF)
if not fields[0].startswith('-'): # only want plain files
continue
path = fields[8][2:] # last entry on line is the path; also drop the ./ prefix
segs = path.split('/')
if len(segs) == 1: # ignore top level files
continue
file = segs.pop() # basename
# Ignore invisible files
if file.startswith('.') or file in ['favicon.ico', 'META']:
continue
committeeId = segs[0]
if any( seg in SKIP_DIRS + CTTEE_FILTERS.get(committeeId,{}).get('DIRS',[]) for seg in segs):
# print('SKIP', segs)
continue
if committeeId in ['zzz']:
continue
if committeeId == 'incubator':
podling = segs[1]
committeeId = f'incubator-{podling}'
# Now store the info
stamp = fields[5]
parseFile(committeeId, file, stamp, path)