From: groceryheist Date: Fri, 24 Aug 2018 01:52:54 +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/317bafb50db0c9dba34348e4414095cbe900a9ac?ds=inline;hp=-c Merge branch 'advanced_persistence' of code.communitydata.cc:mediawiki_dump_tools into advanced_persistence --- 317bafb50db0c9dba34348e4414095cbe900a9ac diff --combined wikiq index fbe043c,a6f079e..a2a11fa --- a/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 @@@ -183,7 -184,7 +184,7 @@@ class WikiqParser() # 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() @@@ -385,10 -386,10 +386,11 @@@ parser.add_argument('-p', '--persistenc 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('-n', '--namespace-include', dest="namespace_include", type=int, action='append', + parser.add_argument('-n', '--namespace-include', dest="namespace_filter", type=int, action='append', 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 @@@ -425,11 -426,12 +427,11 @@@ if len(args.dumpfiles) > 0 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() @@@ -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"