# 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
# skip namespaces not in the filter
if self.namespace_filter is not None:
- if namespace in self.namespace_filter:
+ if namespace not in self.namespace_filter:
continue
rev_detector = mwreverts.Detector()
help="Id number of namspace to include.")
+
args = parser.parse_args()
# set persistence method
persist = PersistMethod.sequence
if args.namespace_filter is not None:
- namespaces = [int(ns) for ns in args.namespace_filter.split(',')]
+ namespaces = args.namespace_filter
else:
namespaces = None
filename = os.path.join(output_dir, os.path.basename(filename))
output_file = open_output_file(filename)
- wikiq = WikiqParser(input_file, output_file,
- collapse_user=args.collapse_user,
- persist=persist,
- urlencode=args.urlencode,
- namespaces = namespaces)
-
+ wikiq = WikiqParser(input_file, output_file,
+ collapse_user=args.collapse_user,
+ persist=persist,
+ urlencode=args.urlencode,
+ namespaces = namespaces)
wikiq.process()
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"