X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/829ffcffae80c4ece0e10116ba12e117b4c39ef7..e4222c45ddea22e543fe4a4bdbcc38b4ac3645bb:/wikiq diff --git a/wikiq b/wikiq index 47dd687..dc9d772 100755 --- a/wikiq +++ b/wikiq @@ -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 @@ -141,7 +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 @@ -176,6 +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 in self.namespace_filter: + continue + rev_detector = mwreverts.Detector() if self.persist != PersistMethod.none: @@ -194,6 +205,8 @@ class WikiqParser(): from mw.lib import persistence state = persistence.State() + + # Iterate through a page's revisions for rev in page: @@ -202,7 +215,7 @@ 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 @@ -373,7 +386,7 @@ 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") +parser.add_argument('-ns', '--namespace-filter', dest="namespace_filter", type=str, help="Comma-seperate list of namespaces numbers to include", default=None) args = parser.parse_args() @@ -389,6 +402,11 @@ 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) @@ -408,9 +426,10 @@ if len(args.dumpfiles) > 0: 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 @@ 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"