From: groceryheist Date: Fri, 24 Aug 2018 01:27:09 +0000 (-0700) Subject: Merge branch 'advanced_persistence' of code.communitydata.cc:mediawiki_dump_tools... X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/commitdiff_plain/d93769c21f276b77b288070fc29d7aace408af0e?hp=e4222c45ddea22e543fe4a4bdbcc38b4ac3645bb Merge branch 'advanced_persistence' of code.communitydata.cc:mediawiki_dump_tools into advanced_persistence --- diff --git a/wikiq b/wikiq index dc9d772..a6f079e 100755 --- a/wikiq +++ b/wikiq @@ -386,7 +386,8 @@ parser.add_argument('-p', '--persistence', dest="persist", default=None, const=' parser.add_argument('-u', '--url-encode', dest="urlencode", action="store_true", help="Output url encoded text strings. This works around some data issues like newlines in editor names. In the future it may be used to output other text data.") -parser.add_argument('-ns', '--namespace-filter', dest="namespace_filter", type=str, help="Comma-seperate list of namespaces numbers to include", default=None) +parser.add_argument('-n', '--namespace-include', dest="namespace_filter", type=int, action='append', + help="Id number of namspace to include.") args = parser.parse_args() @@ -442,8 +443,7 @@ else: collapse_user=args.collapse_user, persist=persist, persist_legacy=args.persist_legacy, - urlencode=args.urlencode, - namespaces = namespaces) + urlencode=args.urlencode) 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"