X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/e4222c45ddea22e543fe4a4bdbcc38b4ac3645bb..c84844cfb58f343e6632f1a6c57f702bd96c616d:/wikiq diff --git a/wikiq b/wikiq index dc9d772..67785fe 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 @@ -128,7 +128,7 @@ class WikiqPage(): class WikiqParser(): - def __init__(self, input_file, output_file, collapse_user=False, persist=None, urlencode=False, namespaces = None): + def __init__(self, input_file, output_file, collapse_user=False, persist=None, urlencode=False, namespaces = None, revert_radius=15): """ Parameters: persist : what persistence method to use. Takes a PersistMethod value @@ -141,6 +141,7 @@ class WikiqParser(): self.printed_header = False self.namespaces = [] self.urlencode = urlencode + self.revert_radius = revert_radius if namespaces is not None: self.namespace_filter = set(namespaces) else: @@ -184,10 +185,12 @@ 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() + print(self.revert_radius) + rev_detector = mwreverts.Detector(radius = self.revert_radius) + if self.persist != PersistMethod.none: window = deque(maxlen=PERSISTENCE_RADIUS) @@ -205,8 +208,6 @@ class WikiqParser(): from mw.lib import persistence state = persistence.State() - - # Iterate through a page's revisions for rev in page: @@ -381,12 +382,22 @@ parser.add_argument('--collapse-user', dest="collapse_user", action="store_true" help="Operate only on the final revision made by user a user within all sequences of consecutive edits made by a user. This can be useful for addressing issues with text persistence measures.") parser.add_argument('-p', '--persistence', dest="persist", default=None, const='', type=str, choices = ['','segment','sequence','legacy'], nargs='?', - help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure. This may by slow. Use -p=segment for advanced persistence calculation method that is robust to content moves. This might be very slow. Use -p=legacy for legacy behavior.") + help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure. This may by slow. The defualt is -p=sequence, which uses the same algorithm as in the past, but with improvements to wikitext parsing. Use -p=legacy for old behavior used in older research projects. Use -p=segment for advanced persistence calculation method that is robust to content moves, but prone to bugs, and slower.") 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. Can be specified more than once.") + +parser.add_argument('-rr', + '--revert-radius', + dest="revert_radius", + type=int, + action='store', + default=15, + help="Number of edits to check when looking for reverts (default: 15)") + args = parser.parse_args() @@ -403,7 +414,7 @@ else: 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 @@ -425,12 +436,13 @@ 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, + revert_radius=args.revert_radius) wikiq.process() @@ -438,12 +450,14 @@ if len(args.dumpfiles) > 0: input_file.close() output_file.close() else: - wikiq = WikiqParser(sys.stdin, sys.stdout, + wikiq = WikiqParser(sys.stdin, + sys.stdout, collapse_user=args.collapse_user, persist=persist, persist_legacy=args.persist_legacy, urlencode=args.urlencode, - namespaces = namespaces) + namespaces=namespaces, + revert_radius=args.revert_radius) 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"