X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/f468d1a5b60dce36e5d132c65c3cada921dbb4a7..7d62ff9fb779a204912080574b859b8ca4e60a9f:/wikiq

diff --git a/wikiq b/wikiq
index 7cf4be2..ae6b40f 100755
--- 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
-import pdb
+
 import argparse
 import sys
 import os, os.path
@@ -63,6 +63,11 @@ class WikiqPage():
     def __init__(self, page, namespace_map, collapse_user=False):
         self.id = page.id
         self.namespace = page.namespace
+        # following mwxml, we assume namespace 0 in cases where
+        # page.namespace is inconsistent with namespace_map
+        if page.namespace not in namespace_map:
+            self.title = page.title
+            page.namespace = 0
         if page.namespace != 0:
             self.title = ':'.join([namespace_map[page.namespace], page.title])
         else:
@@ -123,7 +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
@@ -136,7 +141,11 @@ class WikiqParser():
         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
 
@@ -171,6 +180,13 @@ class WikiqParser():
 
         # 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 not in self.namespace_filter:
+                    continue
+
             rev_detector = mwreverts.Detector()
 
             if self.persist != PersistMethod.none:
@@ -197,7 +213,7 @@ class WikiqParser():
                             '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
@@ -368,6 +384,11 @@ 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('-n', '--namespace-include', dest="namespace_filter", type=int, action='append',
+                    help="Id number of namspace to include. Can be specified more than once.")
+
+
+
 args = parser.parse_args()
 
 # set persistence method
@@ -381,6 +402,11 @@ elif args.persist == "legacy":
 else:
     persist = PersistMethod.sequence
 
+if args.namespace_filter is not None:
+    namespaces = args.namespace_filter
+else:
+    namespaces = None
+
 if len(args.dumpfiles) > 0:
     for filename in args.dumpfiles:
         input_file = open_input_file(filename)
@@ -399,11 +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, 
+        wikiq = WikiqParser(input_file, output_file, 
                             collapse_user=args.collapse_user,
-                                persist=persist,
-                            urlencode=args.urlencode)
-
+                            persist=persist,
+                            urlencode=args.urlencode,
+                            namespaces = namespaces)
 
         wikiq.process()
 
@@ -415,7 +441,8 @@ 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"