improve help for namespace-include

[mediawiki_dump_tools.git] / wikiq

diff --git a/wikiq b/wikiq
index a6f079eff7e3c80d04b251949eef8269d3e837ae..ae6b40f07970b08975afbd545827c09b5509d08a 100755 (executable)
--- a/wikiq
+++ b/wikiq
@@ -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
 # 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
 import argparse
 import sys
 import os, os.path


@@ -184,7 +184,7 @@ class WikiqParser():
 
             # skip namespaces not in the filter
             if self.namespace_filter is not None:
 
             # 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()
                     continue
 
             rev_detector = mwreverts.Detector()


@@ -205,8 +205,6 @@ class WikiqParser():
                     from mw.lib import persistence
                     state = persistence.State()
 
                     from mw.lib import persistence
                     state = persistence.State()
 

-                
-

             # Iterate through a page's revisions
             for rev in page:
 
             # Iterate through a page's revisions
             for rev in page:
 


@@ -387,7 +385,8 @@ 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_filter", type=int, action='append',
                     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_filter", type=int, action='append',

-                    help="Id number of namspace to include.")
+                    help="Id number of namspace to include. Can be specified more than once.")
+

 
 
 args = parser.parse_args()
 
 
 args = parser.parse_args()


@@ -404,7 +403,7 @@ else:
     persist = PersistMethod.sequence
 
 if args.namespace_filter is not None:
     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
 
 else:
     namespaces = None
 


@@ -426,12 +425,11 @@ if len(args.dumpfiles) > 0:
             filename = os.path.join(output_dir, os.path.basename(filename))
             output_file = open_output_file(filename)
 
             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()
 
 
         wikiq.process()
 


@@ -443,7 +441,8 @@ else:
                         collapse_user=args.collapse_user,
                         persist=persist,
                         persist_legacy=args.persist_legacy,
                         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"
     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"