]> code.communitydata.science - mediawiki_dump_tools.git/commitdiff
Merge branch 'advanced_persistence' of code.communitydata.cc:mediawiki_dump_tools...
authorgroceryheist <nathante@uw.edu>
Fri, 24 Aug 2018 01:52:54 +0000 (18:52 -0700)
committergroceryheist <nathante@uw.edu>
Fri, 24 Aug 2018 02:00:49 +0000 (19:00 -0700)
1  2 
wikiq

diff --cc wikiq
index fbe043c07a09ce1e5c403590a486bbe11ce8111f,a6f079eff7e3c80d04b251949eef8269d3e837ae..a2a11fac72651c77381af71a56e3f246c90dedf3
--- 1/wikiq
--- 2/wikiq
+++ b/wikiq
@@@ -3,6 -3,7 +3,7 @@@
  # original wikiq headers are: title articleid revid date_time anon
  # editor editor_id minor text_size text_entropy text_md5 reversion
  # additions_size deletions_size
 -import pdb
++
  import argparse
  import sys
  import os, os.path
@@@ -389,6 -390,6 +390,7 @@@ parser.add_argument('-n', '--namespace-
                      help="Id number of namspace to include.")
  
  
++
  args = parser.parse_args()
  
  # set persistence method
@@@ -402,8 -403,8 +404,8 @@@ elif args.persist == "legacy"
  else:
      persist = PersistMethod.sequence
  
- if args.namespace_include is not None:
-     namespaces = args.namespace_include
+ if args.namespace_filter is not None:
 -    namespaces = [int(ns) for ns in args.namespace_filter.split(',')]
++    namespaces = args.namespace_filter
  else:
      namespaces = None
  
@@@ -441,7 -443,7 +443,8 @@@ else
                          collapse_user=args.collapse_user,
                          persist=persist,
                          persist_legacy=args.persist_legacy,
--                        urlencode=args.urlencode)
++                        urlencode=args.urlencode,
++                        namespaces = namespaces)
      wikiq.process()
  
  # stop_words = "a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your"

Community Data Science Collective || Want to submit a patch?