]> code.communitydata.science - mediawiki_dump_tools.git/commitdiff
Merge branch 'advanced_persistence' of code.communitydata.cc:mediawiki_dump_tools...
authorgroceryheist <nathante@uw.edu>
Fri, 24 Aug 2018 01:27:09 +0000 (18:27 -0700)
committergroceryheist <nathante@uw.edu>
Fri, 24 Aug 2018 01:27:09 +0000 (18:27 -0700)
1  2 
wikiq

diff --combined wikiq
index a584390b4eedef9b606ba5dff7ac5b0d0fcccbb6,dc9d772a24f6c2b0c42d43b8708ba883b790c14c..a6f079eff7e3c80d04b251949eef8269d3e837ae
--- 1/wikiq
--- 2/wikiq
+++ b/wikiq
@@@ -128,7 -128,7 +128,7 @@@ class WikiqPage()
  
  class WikiqParser():
      
-     def __init__(self, input_file, output_file, collapse_user=False, persist=None, urlencode=False):
+     def __init__(self, input_file, output_file, collapse_user=False, persist=None, urlencode=False, namespaces = None):
          """ 
          Parameters:
             persist : what persistence method to use. Takes a PersistMethod value
          self.printed_header = False
          self.namespaces = []
          self.urlencode = urlencode
-         
+         if namespaces is not None:
+             self.namespace_filter = set(namespaces)
+         else:
+             self.namespace_filter = None
      def __get_namespace_from_title(self, title):
          default_ns = None
  
  
          # Iterate through pages
          for page in dump:
+             namespace = page.namespace if page.namespace is not None else self.__get_namespace_from_title(page.title)
+             # skip namespaces not in the filter
+             if self.namespace_filter is not None:
+                 if namespace in self.namespace_filter:
+                     continue
              rev_detector = mwreverts.Detector()
  
              if self.persist != PersistMethod.none:
                      from mw.lib import persistence
                      state = persistence.State()
  
+                 
              # Iterate through a page's revisions
              for rev in page:
  
                              'articleid' : page.id,
                              'editor_id' : "" if rev.deleted.user == True or rev.user.id is None else rev.user.id,
                              'title' : '"' + page.title + '"',
-                             'namespace' : page.namespace if page.namespace is not None else self.__get_namespace_from_title(page.title),
+                             'namespace' : namespace,
                              'deleted' : "TRUE" if rev.deleted.text else "FALSE" } 
  
                  # if revisions are deleted, /many/ things will be missing
@@@ -373,12 -386,11 +386,12 @@@ 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('-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()
- print(args)
  # set persistence method
  
  if args.persist is None:
@@@ -390,6 -402,11 +403,11 @@@ 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(',')]
+ else:
+     namespaces = None
  if len(args.dumpfiles) > 0:
      for filename in args.dumpfiles:
          input_file = open_input_file(filename)
              output_file = open_output_file(filename)
  
              wikiq = WikiqParser(input_file, output_file, 
-                             collapse_user=args.collapse_user,
+                                 collapse_user=args.collapse_user,
                                  persist=persist,
-                             urlencode=args.urlencode)
+                                 urlencode=args.urlencode,
+                                 namespaces = namespaces)
  
          wikiq.process()
  
@@@ -423,7 -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"

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