# HG changeset patch
# User Henry S. Thompson <ht@inf.ed.ac.uk>
# Date 1704991485 0
# Node ID 0ffa655efc219b7d68621a5cee8ead1c27512e33
# Parent  6faed9e5d9c9d83329f8489dddf8e8428f8ba30a
add some debugging info

diff -r 6faed9e5d9c9 -r 0ffa655efc21 lib/python/cc/lmh/lmh.py
--- a/lib/python/cc/lmh/lmh.py	Thu Jan 11 16:43:16 2024 +0000
+++ b/lib/python/cc/lmh/lmh.py	Thu Jan 11 16:44:45 2024 +0000
@@ -48,7 +48,11 @@
 
   infile_pat='/beegfs/common_crawl/CC-MAIN-%s/*.%s/orig/%s/*%s.warc.gz'%(
     CCdate, segment, filetype, fileno)
-  infile_name=glob.glob(infile_pat)[0]
+  try:
+    infile_name=glob.glob(infile_pat)[0]
+  except IndexError:
+    print(infile_pat,CCdata,segment,filetype,fileno,file=sys.stderr)
+    raise
 
   (_,_,_,_,_,_,_,ff)=infile_name.split('/')