]> code.communitydata.science - mediawiki_dump_tools.git/blobdiff - wikiq
Add parameter for selecting specific namespaces.
[mediawiki_dump_tools.git] / wikiq
diff --git a/wikiq b/wikiq
index dc9d772a24f6c2b0c42d43b8708ba883b790c14c..fbe043c07a09ce1e5c403590a486bbe11ce8111f 100755 (executable)
--- a/wikiq
+++ b/wikiq
@@ -3,7 +3,6 @@
 # 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
@@ -184,7 +183,7 @@ 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()
@@ -386,7 +385,8 @@ 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_include", type=int, action='append',
+                    help="Id number of namspace to include.")
 
 
 args = parser.parse_args()
@@ -402,8 +402,8 @@ elif args.persist == "legacy":
 else:
     persist = PersistMethod.sequence
 
-if args.namespace_filter is not None:
-    namespaces = [int(ns) for ns in args.namespace_filter.split(',')]
+if args.namespace_include is not None:
+    namespaces = args.namespace_include
 else:
     namespaces = None
 
@@ -425,12 +425,11 @@ 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()
 
@@ -442,8 +441,7 @@ 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"

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