From: groceryheist Date: Thu, 7 Dec 2017 23:10:56 +0000 (-0800) Subject: support 7z archives with multiple files. add urlencode paraeter X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/commitdiff_plain/3f9da4074733981fa1dda6e88af75a19054e6c52?ds=sidebyside support 7z archives with multiple files. add urlencode paraeter --- diff --git a/wikiq b/wikiq index c2ac412..f25874e 100755 --- a/wikiq +++ b/wikiq @@ -16,7 +16,8 @@ from hashlib import sha1 from mw.xml_dump import Iterator from mw.lib import persistence from mw.lib import reverts - +from urllib.parse import quote +TO_ENCODE = ('title', 'editor') PERSISTENCE_RADIUS=7 def calculate_persistence(tokens_added): @@ -44,7 +45,7 @@ class WikiqPage(): __slots__ = ('id', 'title', 'namespace', 'redirect', 'restrictions', 'mwpage', '__revisions', 'collapse_user') - + def __init__(self, page, collapse_user=False): self.id = page.id self.title = page.title @@ -98,14 +99,18 @@ class WikiqPage(): return next(self.__revisions) class WikiqParser(): - def __init__(self, input_file, output_file, collapse_user=False, persist=False): + + + def __init__(self, input_file, output_file, collapse_user=False, persist=False, urlencode=False): + self.input_file = input_file self.output_file = output_file self.collapse_user = collapse_user self.persist = persist self.printed_header = False self.namespaces = [] - + self.urlencode = urlencode + def __get_namespace_from_title(self, title): default_ns = None @@ -122,7 +127,6 @@ class WikiqParser(): return default_ns def process(self): - print("Processing file: %s" % self.input_file.name, file=sys.stderr) # create a regex that creates the output filename # output_filename = re.sub(r'^.*/(enwiki\-\d+)\-.*p(\d+)p.*$', @@ -246,7 +250,7 @@ class WikiqParser(): rev_data["tokens_added"] = num_tokens rev_data["tokens_removed"] = len(tokens_removed) rev_data["tokens_window"] = len(window)-(i+1) - + self.print_rev_data(rev_data) page_count += 1 @@ -256,6 +260,10 @@ class WikiqParser(): def print_rev_data(self, rev_data): # if it's the first time through, print the header + if self.urlencode: + for field in TO_ENCODE: + rev_data[field] = quote(str(rev_data[field])) + if not self.printed_header: print("\t".join([str(k) for k in sorted(rev_data.keys())]), file=self.output_file) self.printed_header = True @@ -265,11 +273,11 @@ class WikiqParser(): def open_input_file(input_filename): if re.match(r'.*\.7z', input_filename): - cmd = ["7za", "x", "-so", input_filename] + cmd = ["7za", "x", "-so", input_filename, '*.xml'] elif re.match(r'.*\.gz', input_filename): cmd = ["zcat", input_filename] elif re.match(r'.*\.bz2', input_filename): - cmd = ["bzcat", input_filename] + cmd = ["zcat", input_filename] try: input_file = Popen(cmd, stdout=PIPE).stdout @@ -280,7 +288,8 @@ def open_input_file(input_filename): def open_output_file(input_filename): # create a regex that creates the output filename - output_filename = re.sub(r'\.xml(\.(7z|gz|bz2))?$', '', input_filename) + output_filename = re.sub(r'\.(7z|gz|bz2)?$', '', input_filename) + output_filename = re.sub(r'\.xml', '', output_filename) output_filename = output_filename + ".tsv" output_file = open(output_filename, "w") @@ -304,6 +313,9 @@ parser.add_argument('--collapse-user', dest="collapse_user", action="store_true" parser.add_argument('-p', '--persistence', dest="persist", action="store_true", 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.") +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.") + args = parser.parse_args() if len(args.dumpfiles) > 0: @@ -324,7 +336,11 @@ if len(args.dumpfiles) > 0: wikiq = WikiqParser(input_file, output_file, collapse_user=args.collapse_user, - persist=args.persist) + persist=args.persist, + urlencode=args.urlencode) + + print("Processing file: %s" % filename, file=sys.stderr) + wikiq.process() # close things @@ -333,7 +349,8 @@ if len(args.dumpfiles) > 0: else: wikiq = WikiqParser(sys.stdin, sys.stdout, collapse_user=args.collapse_user, - persist=args.persist) + persist=args.persist, + 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"