http://www.mediawiki.org/wiki/Special:Code/MediaWiki/84673
Revision: 84673
Author: diederik
Date: 2011-03-24 12:59:14 +0000 (Thu, 24 Mar 2011)
Log Message:
-----------
A bit more detailed progress logging.
Modified Paths:
--------------
trunk/tools/editor_trends/etl/enricher.py
Modified: trunk/tools/editor_trends/etl/enricher.py
===================================================================
--- trunk/tools/editor_trends/etl/enricher.py 2011-03-24 12:56:10 UTC (rev
84672)
+++ trunk/tools/editor_trends/etl/enricher.py 2011-03-24 12:59:14 UTC (rev
84673)
@@ -420,8 +420,8 @@
line = line.strip()
yield line
fh.close()
+ print 'Reached end of BZ2 file.'
-
def setup(storage):
keyspace_name = 'enwiki'
if storage == 'cassandra':
@@ -434,7 +434,7 @@
input_queue = JoinableQueue()
#files =
['C:\\Users\\diederik.vanliere\\Downloads\\enwiki-latest-pages-articles1.xml.bz2']
#files =
['/home/diederik/kaggle/enwiki-20100904-pages-meta-history2.xml.bz2']
- path =
'/media/77fc623f-78c1-4f1e-be57-0f3043d778aa/wikipedia_dumps/batch1/'
+ path = '/media/wikipedia_dumps/batch1/'
files = file_utils.retrieve_file_list(path, 'bz2', mask=None)
for file in files:
_______________________________________________
MediaWiki-CVS mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-cvs