X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/5b6aaad86232a364f071f4705d18aaa01a7581f6..17529cdd485b507517014b8ada5097531e97051e:/wikiq diff --git a/wikiq b/wikiq index 47dd687..632b05c 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): + 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 not in self.namespace_filter: + continue + rev_detector = mwreverts.Detector() if self.persist != PersistMethod.none: @@ -202,7 +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 @@ -368,12 +379,14 @@ 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") +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() @@ -389,6 +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) @@ -407,11 +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() @@ -423,7 +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"