Pywikibot-commits

pywikibot-commits@lists.wikimedia.org

1 participants
13421 discussions

[Gerrit] [PEP8] pep8 changes for copyright.py - change (pywikibot/compat)
by Xqt (Code Review) 17 Nov '13

17 Nov '13

Xqt has submitted this change and it was merged. Change subject: [PEP8] pep8 changes for copyright.py ...................................................................... [PEP8] pep8 changes for copyright.py Change-Id: Id4a7e0d1e8b8eee18d6d2caf0a4cc148e8cafe63 --- M copyright.py 1 file changed, 216 insertions(+), 160 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/copyright.py b/copyright.py index 7a8bcff..bddcfd0 100644 --- a/copyright.py +++ b/copyright.py @@ -11,7 +11,8 @@ Yahoo! search requires pYsearch module from http://pysearch.sourceforge.net and a Yahoo AppID from http://developer.yahoo.com. -Windows Live Search requires to get an AppID from http://search.msn.com/developer +Windows Live Search requires to get an AppID from +http://search.msn.com/developer and to download/install the SOAPpy module from http://pywebsvcs.sf.net or using SVN with the following command: @@ -77,16 +78,26 @@ """ # -# (C) Francesco Cosoleto, 2006 +# (c) Francesco Cosoleto, 2006 +# (c) Pywikibot team 2006-2013 # # Distributed under the terms of the MIT license. # +__version__ = '$Id$' +# -import re, codecs, os, time, urllib, urllib2, httplib +import re +import codecs +import os +import time +import urllib +import urllib2 +import httplib + import wikipedia as pywikibot -import pagegenerators, config +import pagegenerators +import config -__version__='$Id$' # Search keywords added to all the queries. no_result_with_those_words = '-Wikipedia' @@ -126,7 +137,7 @@ pages_for_exclusion_database = [ ('it', 'Wikipedia:Sospette violazioni di copyright/Lista di esclusione', - 'exclusion_list.txt'), + 'exclusion_list.txt'), ('en', 'Wikipedia:Mirrors_and_forks/Abc', 'Abc.txt'), ('en', 'Wikipedia:Mirrors_and_forks/Def', 'Def.txt'), ('en', 'Wikipedia:Mirrors_and_forks/Ghi', 'Ghi.txt'), @@ -135,12 +146,9 @@ ('en', 'Wikipedia:Mirrors_and_forks/Pqr', 'Pqr.txt'), ('en', 'Wikipedia:Mirrors_and_forks/Stu', 'Stu.txt'), ('en', 'Wikipedia:Mirrors_and_forks/Vwxyz', 'Vwxyz.txt'), - ('es', 'Wikipedia:Espejos de Wikipedia/Espejos_que_cumplen_la_GFDL_y_CC-BY-SA', 'Espejos.txt'), - #('de', 'Wikipedia:Weiternutzung', 'Weiternutzung.txt'), + ('es', 'Wikipedia:Espejos de Wikipedia/Espejos_que_cumplen_la_GFDL_y_CC-BY-SA', + 'Espejos.txt'), ('it', 'Wikipedia:Cloni', 'Cloni.txt'), - #('pl', 'Wikipedia:Mirrory_i_forki_polskiej_Wikipedii', 'Mirrory_i_forki_polskiej_Wikipedii.txt'), - #('pt', 'Wikipedia:Clones_da_Wikipédia', 'Clones_da_Wikipédia.txt'), - #('sv', 'Wikipedia:Spegelsidor', 'Spegelsidor.txt'), ] reports_cat = { @@ -273,19 +281,23 @@ error_color = '\03{%s}' % error_color default_color = '\03{default}' else: - warn_color = '' ; error_color = '' ; default_color = '' + warn_color = error_color = default_color = '' -def _output(text, prefix = None, color = ''): + +def _output(text, prefix=None, color=''): if prefix: pywikibot.output('%s%s: %s%s' % (color, prefix, default_color, text)) else: pywikibot.output('%s%s' % (color, text)) -def warn(text, prefix = None): - _output(text, prefix = prefix, color = warn_color) -def error(text ,prefix = None): - _output(text, prefix = prefix, color = error_color) +def warn(text, prefix=None): + _output(text, prefix=prefix, color=warn_color) + + +def error(text, prefix=None): + _output(text, prefix=prefix, color=error_color) + def skip_section(text): sect_titles = '|'.join(sections_to_skip[pywikibot.getSite().lang]) @@ -297,16 +309,18 @@ text = newtext return text + def cut_section(text, sectC): sectendC = re.compile('(?m)^==[^=]') start = sectC.search(text) if start: end = sectendC.search(text, start.end()) if end: - return text[:start.start()]+text[end.start():] + return text[:start.start()] + text[end.start():] else: return text[:start.start()] return text + class URLExclusion: def __init__(self): @@ -320,7 +334,7 @@ page = pywikibot.Page(pywikibot.getSite(i[0]), i[1]) yield page, path - def download(self, force_update = False): + def download(self, force_update=False): for page, path in self.pages_list(): download = force_update try: @@ -356,26 +370,27 @@ f.close() def update(self): - self.download(force_update = True) + self.download(force_update=True) self.scan() - def check(self, url, verbose = False): + def check(self, url, verbose=False): for entry in self.URLlist: - if entry in url: - if verbose > 1: - warn('URL Excluded: %s\nReason: %s' % (url, entry)) - elif verbose: - warn('URL Excluded: %s' % url) - return True + if entry in url: + if verbose > 1: + warn('URL Excluded: %s\nReason: %s' % (url, entry)) + elif verbose: + warn('URL Excluded: %s' % url) + return True return False def scan(self): - prelist = [] ; result_list = [] + prelist = [] + result_list = [] self.download() for page, path in self.pages_list(): if 'exclusion_list.txt' in path: - result_list += re.sub("</?pre>","", + result_list += re.sub("</?pre>", "", read_file(path, cut_comment=True, cut_newlines=True) @@ -383,11 +398,14 @@ else: data = read_file(path) # wikipedia:en:Wikipedia:Mirrors and forks - prelist += re.findall("(?i)url\s*=\s*<nowiki>(?:http://)?(.*)</nowiki>", data) - prelist += re.findall("(?i)\*\s*Site:\s*\[?(?:http://)?(.*)\]?", data) + prelist += re.findall("(?i)url\s*=\s*<nowiki>(?:http://)?(.*)</nowiki>", + data) + prelist += re.findall("(?i)\*\s*Site:\s*\[?(?:http://)?(.*)\]?", + data) # wikipedia:it:Wikipedia:Cloni if 'it/Cloni.txt' in path: - prelist += re.findall('(?mi)^==(?!=)\s*\[?\s*(?:<nowiki>)?\s*(?:http://)?(.*?)(?:</nowiki>)?\s*\]?\s*==', data) + prelist += re.findall('(?mi)^==(?!=)\s*\[?\s*(?:<nowiki>)?\s*(?:http://)?(.*?)(?:</nowiki>)?\s*\]?\s*==', + data) list1 = [] for entry in prelist: list1 += entry.split(", ") @@ -408,9 +426,8 @@ result_list.append(entry) result_list += read_file( - pywikibot.config.datafilepath(appdir, 'exclusion_list.txt'), - cut_comment = True, cut_newlines = True - ).splitlines() + pywikibot.config.datafilepath(appdir, 'exclusion_list.txt'), + cut_comment=True, cut_newlines=True).splitlines() for item in result_list: cleaned = item.strip() @@ -424,28 +441,26 @@ print "** " + entry def dump(self): - f = open(pywikibot.config.datafilepath(appdir, 'exclusion_list.dump'), 'w') + f = open(pywikibot.config.datafilepath(appdir, 'exclusion_list.dump'), + 'w') f.write('\n'.join(self.URLlist)) f.close() print "Exclusion list dump saved." -def read_file(filename, cut_comment = False, cut_newlines = False): +def read_file(filename, cut_comment=False, cut_newlines=False): text = u"" - f = codecs.open(filename, 'r', 'utf-8') text = f.read() f.close() - if cut_comment: text = re.sub(" ?#.*", "", text) - if cut_newlines: text = re.sub("(?m)^\r?\n", "", text) - return text -def write_log(text, filename = output_file): + +def write_log(text, filename=output_file): f = codecs.open(filename, 'a', 'utf-8') f.write(text) f.close() @@ -454,16 +469,13 @@ # Ignore text that contents comma separated list, only numbers, # punctuation... + def economize_query(text): # Comma separated list c = text.count(', ') if c > 4: l = len(text) r = 100 * float(c) / l - - #if r >= 4 and r < 7: - # write_log("%d/%d/%d: %s\n" % (l,c,r,text), "copyright/skip_%s.txt" % ("%0.1f" % r)) - if r >= comma_ratio: return True @@ -477,9 +489,10 @@ # and regex used in check_in_source() to reject pages with # 'Wikipedia'. + def join_family_data(reString, namespace): for s in pywikibot.Family().namespaces[namespace].itervalues(): - if type (s) == list: + if type(s) == list: for e in s: reString += '|' + e else: @@ -490,14 +503,17 @@ reWikipediaC = re.compile('(' + '|'.join(wikipedia_names.values()) + ')', re.I) reSectionNamesC = re.compile('(' + '|'.join(editsection_names.values()) + ')') -def remove_wikicode(text, re_dotall = False, remove_quote = exclude_quote, debug = False): + +def remove_wikicode(text, re_dotall=False, remove_quote=exclude_quote, + debug=False): if not text: return "" if debug: - write_log(text+'\n', "copyright/wikicode.txt") + write_log(text + '\n', "copyright/wikicode.txt") - text = re.sub('(?i)</?(p|u|i|b|em|div|span|font|small|big|code|tt).*?>', '', text) + text = re.sub('(?i)</?(p|u|i|b|em|div|span|font|small|big|code|tt).*?>', + '', text) text = re.sub('(?i)<(/\s*)?br(\s*/)?>', '', text) text = re.sub('', '', text) @@ -517,11 +533,11 @@ text = re.sub("(?i){{(unicode|polytonic)\|(.*?)}}", "\\1", text) if re_dotall: - flags = "(?xsim)" - # exclude wikitable - text = re.sub('(?s){\|.*?^\|}', '', text) + flags = "(?xsim)" + # exclude wikitable + text = re.sub('(?s){\|.*?^\|}', '', text) else: - flags = "(?xim)" + flags = "(?xim)" text = re.sub(""" %s @@ -564,7 +580,8 @@ try: xmldata = s.parse().toxml() - if '<wikipage>' in xmldata and '</wikipage>' in xmldata: + if '<wikipage>' in xmldata and \ + '</wikipage>' in xmldata: if xmldata.count('') == 1: text = text[:m.start()] + text[m.end():] except: @@ -580,19 +597,21 @@ text = re.sub("(?m)(^[ \t]+|[ \t]+\r?$)", "", text) if debug: - write_log(text+'\n', "copyright/wikicode_removed.txt") + write_log(text + '\n', "copyright/wikicode_removed.txt") return text + def n_index(text, n, sep): pos = 0 - while n>0: + while n > 0: try: pos = text.index(sep, pos + 1) n -= 1 except ValueError: return 0 return pos + def mysplit(text, dim, sep): if not sep in text: @@ -602,13 +621,14 @@ while t: if sep in t: n = n_index(t, dim, sep) - if n>0: + if n > 0: l.append(t[:n]) - t = t[n+1:] + t = t[n + 1:] continue l.append(t) break return l + class SearchEngine: @@ -620,7 +640,7 @@ def __del__(self): self.print_stats() - def query(self, lines = [], max_query_len = 1300, wikicode = True): + def query(self, lines=[], max_query_len=1300, wikicode=True): # Google max_query_len = 1480? # - '-Wikipedia ""' = 1467 @@ -637,12 +657,13 @@ if len(search_words) > min_query_string_len: if config.copyright_economize_query: if economize_query(search_words): - warn(search_words, prefix = 'Text excluded') + warn(search_words, prefix='Text excluded') consecutive = False continue n_query += 1 #pywikibot.output(search_words) - if config.copyright_max_query_for_page and n_query > config.copyright_max_query_for_page: + if config.copyright_max_query_for_page and \ + n_query > config.copyright_max_query_for_page: warn(u"Max query limit for page reached") return output if config.copyright_skip_query > n_query: @@ -651,15 +672,19 @@ search_words = search_words[:max_query_len] consecutive = False if " " in search_words: - search_words = search_words[:search_words.rindex(" ")] + search_words = search_words[ + :search_words.rindex(" ")] results = self.get_results(search_words) - - group_url = '' ; cmp_group_url = '' + group_url = '' + cmp_group_url = '' for url, engine, comment in results: if comment: - group_url += '\n*%s - %s (%s)' % (engine, url, "; ".join(comment)) + group_url += '\n*%s - %s (%s)' % (engine, + url, + "; ".join(comment) + ) else: group_url += '\n*%s - %s' % (engine, url) cmp_group_url += '\n*%s - %s' % (engine, url) @@ -683,19 +708,20 @@ else: consecutive = False else: - consecutive = False - + consecutive = False return output - def add_in_urllist(self, url, add_item, engine, cache_url = None): - if (engine == 'google' and config.copyright_check_in_source_google) or \ - (engine == 'yahoo' and config.copyright_check_in_source_yahoo) or \ - (engine == 'msn' and config.copyright_check_in_source_msn): - check_in_source = True - else: - check_in_source = False + def add_in_urllist(self, url, add_item, engine, cache_url=None): - if check_in_source or config.copyright_show_date or config.copyright_show_length: + check_in_source = (engine == 'google' and + config.copyright_check_in_source_google or + engine == 'yahoo' and + config.copyright_check_in_source_yahoo or + engine == 'msn' and + config.copyright_check_in_source_msn) + + if check_in_source or config.copyright_show_date or \ + config.copyright_show_length: s = None cache = False @@ -719,10 +745,10 @@ date = s.lastmodified() if date: if date[:3] != time.localtime()[:3]: - comment.append("%s/%s/%s" % (date[2], date[1], date[0])) + comment.append("%s/%s/%s" + % (date[2], date[1], date[0])) unit = 'bytes' - if config.copyright_show_length: length = s.length() if length > 1024: @@ -735,14 +761,13 @@ unit = 'MB' if length > 0: comment.append("%d %s" % (length, unit)) - if cache: if cache_url: if engine == 'google': - comment.append('[http://www.google.com/search?sourceid=navclient&q=cache:%s Google cache]' % urllib.quote(short_url(add_item))) + comment.append( + '[http://www.google.com/search?sourceid=navclient&q=cache:%s Google cache]' + % urllib.quote(short_url(add_item))) elif engine == 'yahoo': - #cache = False - #comment.append('[%s Yahoo cache]' % re.sub('&appid=[^&]*', '', urllib2.unquote(cache_url))) comment.append("''Yahoo cache''") elif engine == 'msn': comment.append('[%s Live cache]' @@ -750,7 +775,6 @@ else: comment.append('[http://web.archive.org/*/%s archive.org]' % short_url(add_item)) - for i in range(len(url)): if add_item in url[i]: if engine not in url[i][1]: @@ -761,7 +785,7 @@ url.append((add_item, engine, comment)) return - def soap(self, engine, query, url, numresults = 10): + def soap(self, engine, query, url, numresults=10): print " %s query..." % engine.capitalize() search_request_retry = config.copyright_connection_tries query_success = False @@ -771,18 +795,21 @@ if engine == 'google': import google google.LICENSE_KEY = config.google_key - data = google.doGoogleSearch('%s "%s"' % (no_result_with_those_words, query)) + data = google.doGoogleSearch('%s "%s"' + % (no_result_with_those_words, + query)) for entry in data.results: - self.add_in_urllist(url, entry.URL, 'google', entry.cachedSize) - + self.add_in_urllist(url, entry.URL, 'google', + entry.cachedSize) self.num_google_queries += 1 elif engine == 'yahoo': import yahoo.search.web - data = yahoo.search.web.WebSearch(config.yahoo_appid, query='"%s" %s' % ( + data = yahoo.search.web.WebSearch(config.yahoo_appid, + query='"%s" %s' % ( query.encode('utf_8'), no_result_with_those_words - ), results = numresults) + ), results=numresults) for entry in data.parse_results(): cacheurl = None if entry.Cache: @@ -796,18 +823,26 @@ from SOAPpy import WSDL try: - server = WSDL.Proxy('http://soap.search.msn.com/webservices.asmx?wsdl') + server = WSDL.Proxy( + 'http://soap.search.msn.com/webservices.asmx?wsdl') except Exception, err: error("Live Search Error: %s" % err) raise - params = {'AppID': config.msn_appid, 'Query': '%s "%s"' % (no_result_with_those_words, query), - 'CultureInfo': region_code, 'SafeSearch': 'Off', 'Requests': { - 'SourceRequest':{'Source': 'Web', 'Offset': 0, 'Count': 10, 'ResultFields': 'All',}}} + params = {'AppID': config.msn_appid, + 'Query': '%s "%s"' % (no_result_with_those_words, + query), + 'CultureInfo': region_code, + 'SafeSearch': 'Off', + 'Requests': { + 'SourceRequest': {'Source': 'Web', + 'Offset': 0, + 'Count': 10, + 'ResultFields': 'All', + }}} results = '' - - server_results = server.Search(Request = params) + server_results = server.Search(Request=params) if server_results.Responses[0].Results: results = server_results.Responses[0].Results[0] if results: @@ -817,22 +852,23 @@ cacheurl = None if hasattr(entry, 'CacheUrl'): cacheurl = entry.CacheUrl - self.add_in_urllist(url, entry.Url, 'msn', cacheurl) + self.add_in_urllist(url, entry.Url, 'msn', + cacheurl) else: cacheurl = None if hasattr(results, 'CacheUrl'): cacheurl = results.CacheUrl - self.add_in_urllist(url, results.Url, 'msn', cacheurl) - + self.add_in_urllist(url, results.Url, 'msn', + cacheurl) self.num_msn_queries += 1 - search_request_retry = 0 query_success = True except KeyboardInterrupt: raise except Exception, err: # Something is going wrong... - if 'Daily limit' in str(err) or 'Insufficient quota for key' in str(err): + if 'Daily limit' in str(err) or \ + 'Insufficient quota for key' in str(err): exceeded_in_queries('google') elif 'limit exceeded' in str(err): exceeded_in_queries('yahoo') @@ -847,20 +883,20 @@ if not query_success: error('No response for: %s' % query, "Error (%s)" % engine) - def get_results(self, query, numresults = 10): + def get_results(self, query, numresults=10): result_list = list() query = re.sub("[()\"<>]", "", query) # pywikibot.output(query) if config.copyright_google: self.soap('google', query, result_list) if config.copyright_yahoo: - self.soap('yahoo', query, result_list, numresults = numresults) + self.soap('yahoo', query, result_list, numresults=numresults) if config.copyright_msn: self.soap('msn', query, result_list) offset = 0 for i in range(len(result_list)): - if self.URLexcl.check(result_list[i + offset][0], verbose = True): + if self.URLexcl.check(result_list[i + offset][0], verbose=True): result_list.pop(i + offset) offset += -1 return result_list @@ -878,8 +914,10 @@ source_seen = set() positive_source_seen = set() + class NoWebPage(Exception): """Web page does not exist (404)""" + class URL_exclusion(Exception): """URL in exclusion list""" @@ -899,9 +937,9 @@ self._url = url try: - self._urldata = urllib2.urlopen(urllib2.Request(self._url, None, { 'User-Agent': pywikibot.useragent })) - #except httplib.BadStatusLine, line: - # print 'URL: %s\nBad status line: %s' % (url, line) + self._urldata = urllib2.urlopen( + urllib2.Request(self._url, None, + {'User-Agent': pywikibot.useragent})) except urllib2.HTTPError, err: error("HTTP error: %d / %s (%s)" % (err.code, err.msg, url)) if err.code >= 400: @@ -919,22 +957,17 @@ self._content_type = self._urldata.info().getheader('Content-Type') def length(self): - if hasattr(self, '_length'): - if self._length: - return int(self._length) - if hasattr(self, '_contents'): - return len(self._contents) - - # print "No length for " + self._url - - return None + if hasattr(self, '_length'): + if self._length: + return int(self._length) + if hasattr(self, '_contents'): + return len(self._contents) def lastmodified(self): - if hasattr(self, '_lastmodified'): - return self._lastmodified - return None + if hasattr(self, '_lastmodified'): + return self._lastmodified - def get(self, force = False): + def get(self, force=False): # Exclude URL with listed file extension. if self._url[-4:] in [".pdf", ".doc", ".ppt"]: raise URL_exclusion @@ -942,10 +975,9 @@ # Make sure we did try to get the contents once if not hasattr(self, '_contents'): self._contents = self._urldata.read() - return self._contents - def check_regexp(self, reC, text, filename = None): + def check_regexp(self, reC, text, filename=None): m = reC.search(text) if m: global positive_source_seen @@ -965,10 +997,8 @@ if not hasattr(self, '_urldata'): return False - if self._url in positive_source_seen: return True - if self._url in source_seen: return False @@ -985,16 +1015,21 @@ text = text.decode("utf-8", 'replace') else: # <META> declaration with "http-equiv" set to "Content-Type" in HTML document. - if 'text/html' in self._content_type and (re.search("(?is)<meta\s.*?charset\s*=\s*[\"\']*\s*UTF-8.*?>", text) or re.search("(?is)<\?.*?encoding\s*=\s*[\"\']*\s*UTF-8.*?\?>", text)): + if 'text/html' in self._content_type and ( + re.search("(?is)<meta\s.*?charset\s*=\s*[\"\']*\s*UTF-8.*?>", + text) or + re.search("(?is)<\?.*?encoding\s*=\s*[\"\']*\s*UTF-8.*?\?>", + text)): text = text.decode("utf-8", 'replace') if config.copyright_check_in_source_section_names: - if self.check_regexp(reSectionNamesC, text, "copyright/sites_with_'[edit]'.txt"): + if self.check_regexp(reSectionNamesC, text, + "copyright/sites_with_'[edit]'.txt"): return True - if self.check_regexp(reWikipediaC, text, "copyright/sites_with_'wikipedia'.txt"): + if self.check_regexp(reWikipediaC, text, + "copyright/sites_with_'wikipedia'.txt"): return True - source_seen.add(self._url) return False @@ -1007,14 +1042,19 @@ exec('config.copyright_' + engine + ' = False') # Sleeping if config.copyright_exceeded_in_queries == 2: - error("Got a queries exceeded error from %s. Sleeping for %d hours..." % (engine.capitalize(), config.copyright_exceeded_in_queries_sleep_hours)) - time.sleep(config.copyright_exceeded_in_queries_sleep_hours * 60 * 60) + error("Got a queries exceeded error from %s. Sleeping for %d hours..." + % (engine.capitalize(), + config.copyright_exceeded_in_queries_sleep_hours)) + time.sleep(config.copyright_exceeded_in_queries_sleep_hours * 3600) # Stop execution if config.copyright_exceeded_in_queries == 3: raise 'Got a queries exceeded error.' + def get_by_id(title, id): - return pywikibot.getSite().getUrl("/w/index.php?title=%s&oldid=%s&action=raw" % (title, id)) + return pywikibot.getSite().getUrl( + "/w/index.php?title=%s&oldid=%s&action=raw" % (title, id)) + def checks_by_ids(ids): for title, id in ids: @@ -1025,9 +1065,9 @@ if output: write_log( "=== [[" + title + "]] ===\n{{botbox|%s|prev|%s|%s|00}}" - % (title.replace(" ", "_").replace("\"", "%22"), - id, "author") - + output, + % (title.replace(" ", "_").replace("\"", "%22"), + id, "author") + + output, pywikibot.config.datafilepath(appdir, "ID_output.txt")) @@ -1047,7 +1087,7 @@ newpage = page.getRedirectTarget() pywikibot.output(u'Page %s redirects to \'%s\'' % (page.title(asLink=True), newpage.title())) - bot = CheckRobot(iter([newpage,])) + bot = CheckRobot(iter([newpage])) bot.run() continue except pywikibot.SectionError: @@ -1067,40 +1107,46 @@ text = skip_section(original_text) if remove_wikicode_dotall: - text = remove_wikicode(text, re_dotall = True) + text = remove_wikicode(text, re_dotall=True) - output = self.SearchEngine.query(lines = text.splitlines(), wikicode = not remove_wikicode_dotall) + output = self.SearchEngine.query( + lines=text.splitlines(), + wikicode=not remove_wikicode_dotall) if output: - write_log('=== [[' + page.title() + ']] ===' + output + '\n', - filename = output_file) + write_log('=== [[%s]] ===%s\n' % (page.title(), output), + filename=output_file) def short_url(url): - return url[url.index('://')+3:] + return url[url.index('://') + 3:] + def put(page, text, comment): while True: try: - page.put(text, comment = comment) + page.put(text, comment=comment) break except pywikibot.SpamfilterError, url: - warn(url, prefix = "Spam filter") + warn(url, prefix="Spam filter") text = re.sub(url[0], '<blacklist>' + short_url(url[0]), text) except pywikibot.EditConflict: warn("Edit conflict") raise pywikibot.EditConflict + def check_config(var, license_id, license_name): if var: if not license_id: - warn(u"You don't have set a " + license_name + ", search engine is disabled.", - prefix = "WARNING") + warn(u"You don't have set a %s, search engine is disabled." + % license_name, prefix="WARNING") return False return var + def setSavepath(path): global output_file output_file = path + def main(): gen = None @@ -1153,10 +1199,11 @@ number_of_words = int(arg[8:]) elif arg.startswith('-text'): if len(arg) >= 6: - text = arg[6:] + text = arg[6:] elif arg.startswith('-page'): if len(arg) == 5: - PageTitles.append(pywikibot.input(u'Which page do you want to change?')) + PageTitles.append(pywikibot.input( + u'Which page do you want to change?')) else: PageTitles.append(arg[6:]) elif arg.startswith('-namespace:'): @@ -1169,23 +1216,29 @@ elif arg == '-repeat': repeat = True elif arg.startswith('-new'): - if len(arg) >=5: - number = int(arg[5:]) - gen = pagegenerators.NewpagesPageGenerator(number = number, repeat = repeat) - # Preload generator work better if 'pageNumber' is not major than 'number', - # this avoid unnecessary delay. + if len(arg) >= 5: + number = int(arg[5:]) + gen = pagegenerators.NewpagesPageGenerator(number=number, + repeat=repeat) + # Preload generator work better if 'pageNumber' is not major than + # 'number', this avoid unnecessary delay. if number < pageNumber: pageNumber = number else: genFactory.handleArg(arg) if PageTitles: - pages = [pywikibot.Page(pywikibot.getSite(), PageTitle) for PageTitle in PageTitles] + pages = [pywikibot.Page(pywikibot.getSite(), + PageTitle) for PageTitle in PageTitles] gen = iter(pages) - config.copyright_yahoo = check_config(config.copyright_yahoo, config.yahoo_appid, "Yahoo AppID") - config.copyright_google = check_config(config.copyright_google, config.google_key, "Google Web API license key") - config.copyright_msn = check_config(config.copyright_msn, config.msn_appid, "Live Search AppID") + config.copyright_yahoo = check_config(config.copyright_yahoo, + config.yahoo_appid, "Yahoo AppID") + config.copyright_google = check_config(config.copyright_google, + config.google_key, + "Google Web API license key") + config.copyright_msn = check_config(config.copyright_msn, + config.msn_appid, "Live Search AppID") if ids: checks_by_ids(ids) @@ -1197,21 +1250,24 @@ pywikibot.output(__doc__, 'utf-8') if text: - output = SearchEngine().query(lines = text.splitlines()) + output = SearchEngine().query(lines=text.splitlines()) if output: pywikibot.output(output) if not gen: return - if namespaces != []: - gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces) - preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber = pageNumber) + if namespaces: + gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces) + preloadingGen = pagegenerators.PreloadingGenerator(gen, + pageNumber=pageNumber) bot = CheckRobot(preloadingGen) bot.run() if number_of_words > 22 and config.copyright_msn: - warn("Live Search requires a lower value for 'number_of_words' variable " - "(current value is %d, a good value may be 22)." % (number_of_words), prefix = 'Warning') + warn("Live Search requires a lower value for 'number_of_words' " + "variable (current value is %d, a good value may be 22)." + % (number_of_words), prefix='Warning') + if __name__ == "__main__": try: -- To view, visit https://gerrit.wikimedia.org/r/95833 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Id4a7e0d1e8b8eee18d6d2caf0a4cc148e8cafe63 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] update language_by_size from compat - change (pywikibot/core)
by jenkins-bot (Code Review) 16 Nov '13

16 Nov '13

jenkins-bot has submitted this change and it was merged. Change subject: update language_by_size from compat ...................................................................... update language_by_size from compat Change-Id: I76a13a397640ec6ba68716b7f10a95c06c47425e --- M pywikibot/families/wikipedia_family.py M pywikibot/families/wikivoyage_family.py M pywikibot/families/wiktionary_family.py 3 files changed, 19 insertions(+), 19 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/pywikibot/families/wikipedia_family.py b/pywikibot/families/wikipedia_family.py index 09f87be..99be2b4 100644 --- a/pywikibot/families/wikipedia_family.py +++ b/pywikibot/families/wikipedia_family.py @@ -13,31 +13,31 @@ self.languages_by_size = [ 'en', 'nl', 'de', 'sv', 'fr', 'it', 'ru', 'es', 'pl', 'war', 'ceb', 'vi', 'ja', 'pt', 'zh', 'uk', 'ca', 'no', 'fi', 'fa', 'id', 'cs', - 'ko', 'hu', 'ar', 'ro', 'ms', 'sr', 'min', 'tr', 'kk', 'sk', 'eo', + 'ko', 'hu', 'ar', 'ms', 'ro', 'sr', 'min', 'tr', 'kk', 'sk', 'eo', 'da', 'eu', 'lt', 'bg', 'he', 'hr', 'sl', 'uz', 'vo', 'et', 'hi', - 'gl', 'nn', 'simple', 'hy', 'la', 'az', 'el', 'sh', 'oc', 'th', + 'gl', 'nn', 'simple', 'la', 'hy', 'az', 'el', 'sh', 'oc', 'th', 'ka', 'mk', 'new', 'be', 'pms', 'tl', 'ta', 'te', 'ht', 'tt', 'be-x-old', 'lv', 'cy', 'sq', 'bs', 'mg', 'br', 'jv', 'lb', 'mr', - 'is', 'ml', 'my', 'ba', 'yo', 'an', 'lmo', 'fy', 'af', 'pnb', 'ga', - 'bn', 'zh-yue', 'ur', 'sw', 'bpy', 'io', 'ky', 'ne', 'gu', 'scn', + 'is', 'ml', 'my', 'ba', 'yo', 'an', 'af', 'lmo', 'fy', 'pnb', 'ga', + 'bn', 'zh-yue', 'ur', 'sw', 'bpy', 'io', 'ne', 'ky', 'gu', 'scn', 'tg', 'nds', 'ku', 'cv', 'ast', 'qu', 'sco', 'su', 'als', 'kn', - 'ia', 'bug', 'nap', 'bat-smg', 'am', 'map-bms', 'wa', 'ckb', 'gd', - 'hif', 'mn', 'zh-min-nan', 'arz', 'mzn', 'yi', 'vec', 'sah', 'nah', - 'sa', 'roa-tara', 'os', 'si', 'bar', 'pam', 'hsb', 'pa', 'se', 'li', + 'ia', 'bug', 'nap', 'bat-smg', 'am', 'ckb', 'map-bms', 'wa', 'gd', + 'hif', 'mn', 'arz', 'zh-min-nan', 'mzn', 'yi', 'vec', 'sah', 'nah', + 'sa', 'roa-tara', 'si', 'os', 'bar', 'pam', 'hsb', 'pa', 'se', 'li', 'mi', 'fo', 'co', 'ilo', 'gan', 'bo', 'frr', 'glk', 'rue', 'bcl', - 'nds-nl', 'fiu-vro', 'mrj', 'ce', 'tk', 'ps', 'vls', 'xmf', 'gv', + 'ce', 'nds-nl', 'fiu-vro', 'mrj', 'tk', 'ps', 'vls', 'xmf', 'gv', 'or', 'diq', 'zea', 'kv', 'km', 'pag', 'mhr', 'csb', 'dv', 'vep', 'nrm', 'hak', 'rm', 'koi', 'udm', 'lad', 'wuu', 'lij', 'zh-classical', 'sc', 'fur', 'stq', 'mt', 'ug', 'ay', 'so', 'pi', - 'nov', 'bh', 'ksh', 'gn', 'kw', 'gag', 'ang', 'pcd', 'as', 'eml', - 'ace', 'nv', 'szl', 'ext', 'frp', 'ie', 'mwl', 'ln', 'pfl', 'krc', - 'lez', 'xal', 'haw', 'pdc', 'rw', 'crh', 'dsb', 'to', 'arc', 'kl', - 'myv', 'kab', 'sn', 'bjn', 'pap', 'tpi', 'lo', 'kbd', 'lbe', 'wo', + 'nov', 'bh', 'ksh', 'gn', 'gag', 'kw', 'ang', 'pcd', 'as', 'eml', + 'ace', 'nv', 'szl', 'ext', 'frp', 'ie', 'mwl', 'ln', 'pfl', 'lez', + 'krc', 'xal', 'haw', 'pdc', 'rw', 'crh', 'dsb', 'to', 'arc', 'kl', + 'myv', 'kab', 'sn', 'bjn', 'pap', 'tpi', 'kbd', 'lo', 'lbe', 'wo', 'mdf', 'jbo', 'cbk-zam', 'av', 'srn', 'ty', 'kg', 'ab', 'na', 'tet', 'ltg', 'ig', 'bxr', 'nso', 'za', 'kaa', 'zu', 'chy', 'rmy', 'cu', 'tn', 'chr', 'cdo', 'roa-rup', 'bi', 'got', 'pih', 'sm', 'bm', 'iu', - 'ss', 'sd', 'pnt', 'ki', 'ee', 'tyv', 'ha', 'om', 'fj', 'ti', 'ts', - 'ks', 'tw', 'sg', 've', 'rn', 'st', 'cr', 'dz', 'ak', 'ff', 'tum', + 'ss', 'sd', 'pnt', 'ki', 'tyv', 'ee', 'ha', 'om', 'fj', 'ti', 'ts', + 'ks', 'tw', 'sg', 've', 'st', 'rn', 'cr', 'dz', 'ak', 'tum', 'ff', 'ik', 'lg', 'ny', 'ch', 'xh', ] diff --git a/pywikibot/families/wikivoyage_family.py b/pywikibot/families/wikivoyage_family.py index e50608e..83c97d0 100644 --- a/pywikibot/families/wikivoyage_family.py +++ b/pywikibot/families/wikivoyage_family.py @@ -12,7 +12,7 @@ super(Family, self).__init__() self.name = 'wikivoyage' self.languages_by_size = [ - 'en', 'de', 'pt', 'it', 'fr', 'nl', 'pl', 'ru', 'es', 'vi', 'sv', + 'en', 'de', 'pt', 'fr', 'it', 'nl', 'pl', 'ru', 'es', 'vi', 'sv', 'he', 'ro', 'uk', 'el', ] diff --git a/pywikibot/families/wiktionary_family.py b/pywikibot/families/wiktionary_family.py index 6f1334c..ca3b9e6 100644 --- a/pywikibot/families/wiktionary_family.py +++ b/pywikibot/families/wiktionary_family.py @@ -13,15 +13,15 @@ self.languages_by_size = [ 'en', 'mg', 'fr', 'zh', 'lt', 'ru', 'el', 'es', 'pl', 'sv', 'ko', 'de', 'tr', 'nl', 'ku', 'ta', 'io', 'kn', 'fi', 'vi', 'hu', 'pt', - 'chr', 'no', 'ml', 'my', 'id', 'it', 'li', 'et', 'ro', 'ja', 'te', + 'chr', 'no', 'ml', 'my', 'id', 'it', 'li', 'ro', 'et', 'ja', 'te', 'fa', 'cs', 'ca', 'ar', 'eu', 'jv', 'gl', 'lo', 'uk', 'br', 'fj', 'eo', 'bg', 'hr', 'th', 'oc', 'is', 'vo', 'ps', 'zh-min-nan', - 'simple', 'cy', 'scn', 'uz', 'sr', 'af', 'ast', 'sw', 'da', 'fy', - 'tl', 'he', 'az', 'nn', 'wa', 'ur', 'la', 'sq', 'hy', 'sm', 'sl', + 'simple', 'cy', 'uz', 'scn', 'sr', 'af', 'ast', 'sw', 'da', 'fy', + 'tl', 'az', 'he', 'nn', 'wa', 'ur', 'la', 'sq', 'hy', 'sm', 'sl', 'nah', 'pnb', 'ka', 'hi', 'tt', 'bs', 'lb', 'lv', 'tk', 'sk', 'hsb', 'nds', 'kk', 'ky', 'be', 'mk', 'km', 'ga', 'wo', 'ms', 'ang', 'co', 'sa', 'gn', 'mr', 'csb', 'st', 'ia', 'ug', 'sd', 'sh', 'si', 'tg', - 'mn', 'kl', 'or', 'jbo', 'an', 'vec', 'ln', 'fo', 'zu', 'gu', 'kw', + 'mn', 'kl', 'or', 'jbo', 'vec', 'an', 'ln', 'fo', 'zu', 'gu', 'kw', 'gv', 'rw', 'qu', 'ss', 'ie', 'mt', 'om', 'bn', 'roa-rup', 'iu', 'pa', 'so', 'am', 'su', 'za', 'gd', 'mi', 'tpi', 'ne', 'yi', 'ti', 'sg', 'na', 'dv', 'tn', 'ts', 'ha', 'ks', 'ay', -- To view, visit https://gerrit.wikimedia.org/r/95829 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I76a13a397640ec6ba68716b7f10a95c06c47425e Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/core Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [BUGFIX] fix for "got" namespace alias - change (pywikibot/compat)
by jenkins-bot (Code Review) 16 Nov '13

16 Nov '13

jenkins-bot has submitted this change and it was merged. Change subject: [BUGFIX] fix for "got" namespace alias ...................................................................... [BUGFIX] fix for "got" namespace alias Change-Id: I7d2b72bb244afe911e26592509727de658d54d75 --- M families/wikipedia_family.py 1 file changed, 1 insertion(+), 1 deletion(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/families/wikipedia_family.py b/families/wikipedia_family.py index d26519b..5e22feb 100644 --- a/families/wikipedia_family.py +++ b/families/wikipedia_family.py @@ -446,7 +446,7 @@ 'gl': u'Conversa Wikipedia', 'glk': u'بحث Wikipedia', 'gn': u'Vikipetã myangekõi', - 'got': u'??? Wikipedia ?????????', + 'got': u'𐌸𐌹𐍃 Wikipedia 𐌲𐌰𐍅𐌰𐌿𐍂𐌳𐌾𐌰', 'gu': u'વિકિપીડિયા ચર્ચા', 'gv': u'Resooney Wikipedia', 'ha': u'Wikipedia talk', -- To view, visit https://gerrit.wikimedia.org/r/95830 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I7d2b72bb244afe911e26592509727de658d54d75 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] update namespace aliases - change (pywikibot/compat)
by jenkins-bot (Code Review) 16 Nov '13

16 Nov '13

jenkins-bot has submitted this change and it was merged. Change subject: update namespace aliases ...................................................................... update namespace aliases Change-Id: I9032199c9c77154f7852822634393ab9409a31cf --- M families/wikibooks_family.py 1 file changed, 2 insertions(+), 2 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/families/wikibooks_family.py b/families/wikibooks_family.py index 9ae2e09..caf7667 100644 --- a/families/wikibooks_family.py +++ b/families/wikibooks_family.py @@ -63,7 +63,7 @@ 'af': u'Wikibooks', 'ang': u'Wikibooks', 'ar': [u'ويكي الكتب', u'Wikibooks'], - 'az': u'Wikibooks', + 'az': [u'Vikikitab', u'Wikibooks'], 'be': u'Wikibooks', 'bg': [u'Уикикниги', u'Wikibooks'], 'bn': [u'উইকিবই', u'WB', u'Wikibooks'], @@ -146,7 +146,7 @@ 'af': u'Wikibooksbespreking', 'ang': u'Wikibooks talk', 'ar': u'نقاش ويكي الكتب', - 'az': [u'Wikibooks müzakirəsi', u'Wikibooks talk'], + 'az': [u'Vikikitab müzakirəsi', u'Wikibooks müzakirəsi', u'Wikibooks talk'], 'be': [u'Размовы пра Wikibooks', u'Wikibooks размовы'], 'bg': u'Уикикниги беседа', 'bn': [u'উইকিবই আলোচনা', u'উইকিবই আলাপ'], -- To view, visit https://gerrit.wikimedia.org/r/95827 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I9032199c9c77154f7852822634393ab9409a31cf Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] update language_by_size - change (pywikibot/compat)
by Xqt (Code Review) 16 Nov '13

16 Nov '13

Xqt has submitted this change and it was merged. Change subject: update language_by_size ...................................................................... update language_by_size Change-Id: I9a84dd5338c59ba579a9aaf10dcf2623c4fbbba2 --- M families/wikipedia_family.py M families/wikivoyage_family.py M families/wiktionary_family.py 3 files changed, 20 insertions(+), 20 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/families/wikipedia_family.py b/families/wikipedia_family.py index af57c9e..d26519b 100644 --- a/families/wikipedia_family.py +++ b/families/wikipedia_family.py @@ -13,31 +13,31 @@ self.languages_by_size = [ 'en', 'nl', 'de', 'sv', 'fr', 'it', 'ru', 'es', 'pl', 'war', 'ceb', 'vi', 'ja', 'pt', 'zh', 'uk', 'ca', 'no', 'fi', 'fa', 'id', 'cs', - 'ko', 'hu', 'ar', 'ro', 'ms', 'sr', 'min', 'tr', 'kk', 'sk', 'eo', + 'ko', 'hu', 'ar', 'ms', 'ro', 'sr', 'min', 'tr', 'kk', 'sk', 'eo', 'da', 'eu', 'lt', 'bg', 'he', 'hr', 'sl', 'uz', 'vo', 'et', 'hi', - 'gl', 'nn', 'simple', 'hy', 'la', 'az', 'el', 'sh', 'oc', 'th', + 'gl', 'nn', 'simple', 'la', 'hy', 'az', 'el', 'sh', 'oc', 'th', 'ka', 'mk', 'new', 'be', 'pms', 'tl', 'ta', 'te', 'ht', 'tt', 'be-x-old', 'lv', 'cy', 'sq', 'bs', 'mg', 'br', 'jv', 'lb', 'mr', - 'is', 'ml', 'my', 'ba', 'yo', 'an', 'lmo', 'fy', 'af', 'pnb', 'ga', - 'bn', 'zh-yue', 'ur', 'sw', 'bpy', 'io', 'ky', 'ne', 'gu', 'scn', + 'is', 'ml', 'my', 'ba', 'yo', 'an', 'af', 'lmo', 'fy', 'pnb', 'ga', + 'bn', 'zh-yue', 'ur', 'sw', 'bpy', 'io', 'ne', 'ky', 'gu', 'scn', 'tg', 'nds', 'ku', 'cv', 'ast', 'qu', 'sco', 'su', 'als', 'kn', - 'ia', 'bug', 'nap', 'bat-smg', 'am', 'map-bms', 'wa', 'ckb', 'gd', - 'hif', 'mn', 'zh-min-nan', 'arz', 'mzn', 'yi', 'vec', 'sah', 'nah', - 'sa', 'roa-tara', 'os', 'si', 'bar', 'pam', 'hsb', 'pa', 'se', 'li', + 'ia', 'bug', 'nap', 'bat-smg', 'am', 'ckb', 'map-bms', 'wa', 'gd', + 'hif', 'mn', 'arz', 'zh-min-nan', 'mzn', 'yi', 'vec', 'sah', 'nah', + 'sa', 'roa-tara', 'si', 'os', 'bar', 'pam', 'hsb', 'pa', 'se', 'li', 'mi', 'fo', 'co', 'ilo', 'gan', 'bo', 'frr', 'glk', 'rue', 'bcl', - 'nds-nl', 'fiu-vro', 'mrj', 'ce', 'tk', 'ps', 'vls', 'xmf', 'gv', + 'ce', 'nds-nl', 'fiu-vro', 'mrj', 'tk', 'ps', 'vls', 'xmf', 'gv', 'or', 'diq', 'zea', 'kv', 'km', 'pag', 'mhr', 'csb', 'dv', 'vep', 'nrm', 'hak', 'rm', 'koi', 'udm', 'lad', 'wuu', 'lij', 'zh-classical', 'sc', 'fur', 'stq', 'mt', 'ug', 'ay', 'so', 'pi', - 'nov', 'bh', 'ksh', 'gn', 'kw', 'gag', 'ang', 'pcd', 'as', 'eml', - 'ace', 'nv', 'szl', 'ext', 'frp', 'ie', 'mwl', 'ln', 'pfl', 'krc', - 'lez', 'xal', 'haw', 'pdc', 'rw', 'crh', 'dsb', 'to', 'arc', 'kl', - 'myv', 'kab', 'sn', 'bjn', 'pap', 'tpi', 'lo', 'kbd', 'lbe', 'wo', + 'nov', 'bh', 'ksh', 'gn', 'gag', 'kw', 'ang', 'pcd', 'as', 'eml', + 'ace', 'nv', 'szl', 'ext', 'frp', 'ie', 'mwl', 'ln', 'pfl', 'lez', + 'krc', 'xal', 'haw', 'pdc', 'rw', 'crh', 'dsb', 'to', 'arc', 'kl', + 'myv', 'kab', 'sn', 'bjn', 'pap', 'tpi', 'kbd', 'lo', 'lbe', 'wo', 'mdf', 'jbo', 'cbk-zam', 'av', 'srn', 'ty', 'kg', 'ab', 'na', 'tet', 'ltg', 'ig', 'bxr', 'nso', 'za', 'kaa', 'zu', 'chy', 'rmy', 'cu', 'tn', 'chr', 'cdo', 'roa-rup', 'bi', 'got', 'pih', 'sm', 'bm', 'iu', - 'ss', 'sd', 'pnt', 'ki', 'ee', 'tyv', 'ha', 'om', 'fj', 'ti', 'ts', - 'ks', 'tw', 'sg', 've', 'rn', 'st', 'cr', 'dz', 'ak', 'ff', 'tum', + 'ss', 'sd', 'pnt', 'ki', 'tyv', 'ee', 'ha', 'om', 'fj', 'ti', 'ts', + 'ks', 'tw', 'sg', 've', 'st', 'rn', 'cr', 'dz', 'ak', 'tum', 'ff', 'ik', 'lg', 'ny', 'ch', 'xh', ] @@ -446,7 +446,7 @@ 'gl': u'Conversa Wikipedia', 'glk': u'بحث Wikipedia', 'gn': u'Vikipetã myangekõi', - 'got': u'𐌸𐌹𐍃 Wikipedia 𐌲𐌰𐍅𐌰𐌿𐍂𐌳𐌾𐌰', + 'got': u'??? Wikipedia ?????????', 'gu': u'વિકિપીડિયા ચર્ચા', 'gv': u'Resooney Wikipedia', 'ha': u'Wikipedia talk', diff --git a/families/wikivoyage_family.py b/families/wikivoyage_family.py index 14dab2c..ffb9954 100644 --- a/families/wikivoyage_family.py +++ b/families/wikivoyage_family.py @@ -12,7 +12,7 @@ super(Family, self).__init__() self.name = 'wikivoyage' self.languages_by_size = [ - 'en', 'de', 'pt', 'it', 'fr', 'nl', 'pl', 'ru', 'es', 'vi', 'sv', + 'en', 'de', 'pt', 'fr', 'it', 'nl', 'pl', 'ru', 'es', 'vi', 'sv', 'he', 'ro', 'uk', 'el', ] diff --git a/families/wiktionary_family.py b/families/wiktionary_family.py index 8c975e1..c6d99b6 100644 --- a/families/wiktionary_family.py +++ b/families/wiktionary_family.py @@ -13,15 +13,15 @@ self.languages_by_size = [ 'en', 'mg', 'fr', 'zh', 'lt', 'ru', 'el', 'es', 'pl', 'sv', 'ko', 'de', 'tr', 'nl', 'ku', 'ta', 'io', 'kn', 'fi', 'vi', 'hu', 'pt', - 'chr', 'no', 'ml', 'my', 'id', 'it', 'li', 'et', 'ro', 'ja', 'te', + 'chr', 'no', 'ml', 'my', 'id', 'it', 'li', 'ro', 'et', 'ja', 'te', 'fa', 'cs', 'ca', 'ar', 'eu', 'jv', 'gl', 'lo', 'uk', 'br', 'fj', 'eo', 'bg', 'hr', 'th', 'oc', 'is', 'vo', 'ps', 'zh-min-nan', - 'simple', 'cy', 'scn', 'uz', 'sr', 'af', 'ast', 'sw', 'da', 'fy', - 'tl', 'he', 'az', 'nn', 'wa', 'ur', 'la', 'sq', 'hy', 'sm', 'sl', + 'simple', 'cy', 'uz', 'scn', 'sr', 'af', 'ast', 'sw', 'da', 'fy', + 'tl', 'az', 'he', 'nn', 'wa', 'ur', 'la', 'sq', 'hy', 'sm', 'sl', 'nah', 'pnb', 'ka', 'hi', 'tt', 'bs', 'lb', 'lv', 'tk', 'sk', 'hsb', 'nds', 'kk', 'ky', 'be', 'mk', 'km', 'ga', 'wo', 'ms', 'ang', 'co', 'sa', 'gn', 'mr', 'csb', 'st', 'ia', 'ug', 'sd', 'sh', 'si', 'tg', - 'mn', 'kl', 'or', 'jbo', 'an', 'vec', 'ln', 'fo', 'zu', 'gu', 'kw', + 'mn', 'kl', 'or', 'jbo', 'vec', 'an', 'ln', 'fo', 'zu', 'gu', 'kw', 'gv', 'rw', 'qu', 'ss', 'ie', 'mt', 'om', 'bn', 'roa-rup', 'iu', 'pa', 'so', 'am', 'su', 'za', 'gd', 'mi', 'tpi', 'ne', 'yi', 'ti', 'sg', 'na', 'dv', 'tn', 'ts', 'ha', 'ks', 'ay', -- To view, visit https://gerrit.wikimedia.org/r/95826 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I9a84dd5338c59ba579a9aaf10dcf2623c4fbbba2 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] update namespace alias for ko-wikt - change (pywikibot/compat)
by Xqt (Code Review) 16 Nov '13

16 Nov '13

Xqt has submitted this change and it was merged. Change subject: update namespace alias for ko-wikt ...................................................................... update namespace alias for ko-wikt Change-Id: I9dfc0376758f4a1ba6ad90acded3e115da41ae3a --- M families/wiktionary_family.py 1 file changed, 1 insertion(+), 1 deletion(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/families/wiktionary_family.py b/families/wiktionary_family.py index bb3ac27..8c975e1 100644 --- a/families/wiktionary_family.py +++ b/families/wiktionary_family.py @@ -130,7 +130,7 @@ 'kl': u'Wiktionary', 'km': u'Wiktionary', 'kn': u'Wiktionary', - 'ko': [u'위키낱말사전', u'Wiktionary'], + 'ko': [u'위키낱말사전', u'Wiktionary', u'낱'], 'ks': u'Wiktionary', 'ku': [u'Wîkîferheng', u'Wiktionary'], 'kw': u'Wiktionary', -- To view, visit https://gerrit.wikimedia.org/r/95824 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I9dfc0376758f4a1ba6ad90acded3e115da41ae3a Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] pep8 changes - change (pywikibot/compat)
by Xqt (Code Review) 16 Nov '13

16 Nov '13

Xqt has submitted this change and it was merged. Change subject: [PEP8] pep8 changes ...................................................................... [PEP8] pep8 changes Change-Id: I78812c95db15fced70996283458aacc18db34bea --- M commonscat.py 1 file changed, 188 insertions(+), 175 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/commonscat.py b/commonscat.py index 6de1b96..d8e1791 100644 --- a/commonscat.py +++ b/commonscat.py @@ -45,7 +45,7 @@ # # (C) Multichill, 2008-2009 -# (C) Xqt, 2009-2012 +# (C) Xqt, 2009-2013 # (C) Pywikipedia bot team, 2008-2012 # # Distributed under the terms of the MIT license. @@ -53,8 +53,12 @@ __version__ = '$Id$' # +import re + import wikipedia as pywikibot -import config, pagegenerators, add_text, re +import config +import pagegenerators +import add_text docuReplacements = { '&params;': pagegenerators.parameterHelp @@ -64,86 +68,90 @@ # No entry needed if it is like _default commonscatTemplates = { '_default': (u'Commonscat', []), - 'af' : (u'CommonsKategorie', [u'commonscat']), - 'an' : (u'Commonscat', [u'Commons cat']), - 'ar' : (u'تصنيف كومنز', [u'Commonscat', u'تصنيف كومونز', - u'Commons cat', u'CommonsCat']), - 'arz' : (u'Commons cat', [u'Commoncat']), - 'az' : (u'CommonsKat', [u'Commonscat']), - 'bn' : (u'কমন্সক্যাট', [u'Commonscat']), - 'ca' : (u'Commonscat', [u'Commons cat', u'Commons category']), - 'crh' : (u'CommonsKat', [u'Commonscat']), - 'cs' : (u'Commonscat', [u'Commons cat']), - 'da' : (u'Commonscat', [u'Commons cat', u'Commons category', - u'Commonscat left', u'Commonscat2']), - 'de' : (u'Commonscat', [u'Commons cat',]), - 'en' : (u'Commons category', [u'Commoncat', u'Commonscat', u'Commons cat', - u'Commons+cat', u'Commonscategory', - u'Commons and category', u'Commonscat-inline', - u'Commons category-inline', u'Commons2', - u'Commons category multi', - u'Cms-catlist-up', u'Catlst commons', - u'Commonscat show2', - u'Sister project links']), - 'es' : (u'Commonscat', [u'Ccat', u'Commons cat', u'Categoría Commons', - u'Commonscat-inline']), - 'et' : (u'Commonsi kategooria', [u'Commonscat', u'Commonskat', u'Commons cat', u'Commons category']), - 'eu' : (u'Commonskat', [u'Commonscat']), - 'fa' : (u'ویکی‌انبار-رده', [u'Commonscat', u'Commons cat', u'انبار رده', - u'Commons category', u'انبار-رده', - u'جعبه پیوند به پروژه‌های خواهر', - u'در پروژه‌های خواهر', u'پروژه‌های خواهر']), - 'fr' : (u'Commonscat', [u'CommonsCat', u'Commons cat', - u'Commons category']), - 'frp' : (u'Commonscat', [u'CommonsCat']), - 'ga' : (u'Catcómhaoin', [u'Commonscat']), - 'hi' : (u'Commonscat', [u'Commons2', u'Commons cat', u'Commons category']), - 'hu' : (u'Commonskat', [u'Közvagyonkat']), - 'hy' : (u'Վիքիպահեստ կատեգորիա', [u'Commonscat', u'Commons cat', - u'Commons category']), - 'id' : (u'Commonscat', [u'Commons cat', u'Commons2', - u'CommonsCat', u'Commons category']), - 'is' : (u'CommonsCat', [u'Commonscat']), - 'ja' : (u'Commonscat', [u'Commons cat', u'Commons category']), - 'jv' : (u'Commonscat', [u'Commons cat']), - 'kaa' : (u'Commons cat', [u'Commonscat']), - 'kk' : (u'Commonscat', [u'Commons2']), - 'ko' : (u'Commonscat', [u'Commons cat', u'공용분류']), - 'la' : (u'CommuniaCat', []), - 'mk' : (u'Ризница-врска', [u'Commonscat', u'Commons cat', u'CommonsCat', - u'Commons2', u'Commons category']), - 'ml' : (u'Commonscat', [u'Commons cat', u'Commons2']), - 'ms' : (u'Kategori Commons', [u'Commonscat', u'Commons category']), - 'nn' : (u'Commonscat', [u'Commons cat']), - 'os' : (u'Commonscat', [u'Commons cat']), - 'pt' : (u'Commonscat', [u'Commons cat']), - 'ro' : (u'Commonscat', [u'Commons cat']), - 'ru' : (u'Commonscat', [u'Викисклад-кат', u'Commons category']), - 'simple' : (u'Commonscat' ,[u'Commons cat', u'Commons cat multi', - u'Commons category', u'Commons category multi', - u'CommonsCompact', u'Commons-inline']), - 'sh' : (u'Commonscat', [u'Commons cat']), - 'sl' : (u'Kategorija v Zbirki', [u'Commonscat', u'Kategorija v zbirki', - u'Commons cat', u'Katzbirke']), - 'sv' : (u'Commonscat', [u'Commonscat-rad', u'Commonskat', u'Commons cat', - u'Commonscatbox', u'Commonscat-box']), - 'sw' : (u'Commonscat', [u'Commons2', u'Commons cat']), - 'te' : (u'Commonscat', [u'Commons cat']), - 'tr' : (u'Commons kategori', [u'CommonsKat', u'Commonscat', - u'Commons cat']), - 'uk' : (u'Commonscat', [u'Commons cat', u'Category', u'Commonscat-inline']), - 'vi' : (u'Commonscat', [u'Commons2', u'Commons cat', u'Commons category', - u'Commons+cat']), - 'zh' : (u'Commonscat', [u'Commons cat', u'Commons category']), - 'zh-classical' : (u'共享類', [u'Commonscat']), - 'zh-yue' : (u'同享類', [u'Commonscat', u'共享類 ', u'Commons cat', - u'Commons category']), + 'af': (u'CommonsKategorie', [u'commonscat']), + 'an': (u'Commonscat', [u'Commons cat']), + 'ar': (u'تصنيف كومنز', + [u'Commonscat', u'تصنيف كومونز', u'Commons cat', u'CommonsCat']), + 'arz': (u'Commons cat', [u'Commoncat']), + 'az': (u'CommonsKat', [u'Commonscat']), + 'bn': (u'কমন্সক্যাট', [u'Commonscat']), + 'ca': (u'Commonscat', [u'Commons cat', u'Commons category']), + 'crh': (u'CommonsKat', [u'Commonscat']), + 'cs': (u'Commonscat', [u'Commons cat']), + 'da': (u'Commonscat', + [u'Commons cat', u'Commons category', u'Commonscat left', + u'Commonscat2']), + 'de': (u'Commonscat', [u'Commons cat']), + 'en': (u'Commons category', + [u'Commoncat', u'Commonscat', u'Commons cat', u'Commons+cat', + u'Commonscategory', u'Commons and category', u'Commonscat-inline', + u'Commons category-inline', u'Commons2', u'Commons category multi', + u'Cms-catlist-up', u'Catlst commons', u'Commonscat show2', + u'Sister project links']), + 'es': (u'Commonscat', + [u'Ccat', u'Commons cat', u'Categoría Commons', + u'Commonscat-inline']), + 'et': (u'Commonsi kategooria', + [u'Commonscat', u'Commonskat', u'Commons cat', u'Commons category']), + 'eu': (u'Commonskat', [u'Commonscat']), + 'fa': (u'ویکی‌انبار-رده', + [u'Commonscat', u'Commons cat', u'انبار رده', u'Commons category', + u'انبار-رده', u'جعبه پیوند به پروژه‌های خواهر', + u'در پروژه‌های خواهر', u'پروژه‌های خواهر']), + 'fr': (u'Commonscat', [u'CommonsCat', u'Commons cat', u'Commons category']), + 'frp': (u'Commonscat', [u'CommonsCat']), + 'ga': (u'Catcómhaoin', [u'Commonscat']), + 'hi': (u'Commonscat', [u'Commons2', u'Commons cat', u'Commons category']), + 'hu': (u'Commonskat', [u'Közvagyonkat']), + 'hy': (u'Վիքիպահեստ կատեգորիա', + [u'Commonscat', u'Commons cat', u'Commons category']), + 'id': (u'Commonscat', + [u'Commons cat', u'Commons2', u'CommonsCat', u'Commons category']), + 'is': (u'CommonsCat', [u'Commonscat']), + 'ja': (u'Commonscat', [u'Commons cat', u'Commons category']), + 'jv': (u'Commonscat', [u'Commons cat']), + 'kaa': (u'Commons cat', [u'Commonscat']), + 'kk': (u'Commonscat', [u'Commons2']), + 'ko': (u'Commonscat', [u'Commons cat', u'공용분류']), + 'la': (u'CommuniaCat', []), + 'mk': (u'Ризница-врска', + [u'Commonscat', u'Commons cat', u'CommonsCat', u'Commons2', + u'Commons category']), + 'ml': (u'Commonscat', [u'Commons cat', u'Commons2']), + 'ms': (u'Kategori Commons', [u'Commonscat', u'Commons category']), + 'nn': (u'Commonscat', [u'Commons cat']), + 'os': (u'Commonscat', [u'Commons cat']), + 'pt': (u'Commonscat', [u'Commons cat']), + 'ro': (u'Commonscat', [u'Commons cat']), + 'ru': (u'Commonscat', [u'Викисклад-кат', u'Commons category']), + 'simple': (u'Commonscat', + [u'Commons cat', u'Commons cat multi', u'Commons category', + u'Commons category multi', u'CommonsCompact', + u'Commons-inline']), + 'sh': (u'Commonscat', [u'Commons cat']), + 'sl': (u'Kategorija v Zbirki', + [u'Commonscat', u'Kategorija v zbirki', u'Commons cat', + u'Katzbirke']), + 'sv': (u'Commonscat', + [u'Commonscat-rad', u'Commonskat', u'Commons cat', u'Commonscatbox', + u'Commonscat-box']), + 'sw': (u'Commonscat', [u'Commons2', u'Commons cat']), + 'te': (u'Commonscat', [u'Commons cat']), + 'tr': (u'Commons kategori', + [u'CommonsKat', u'Commonscat', u'Commons cat']), + 'uk': (u'Commonscat', [u'Commons cat', u'Category', u'Commonscat-inline']), + 'vi': (u'Commonscat', + [u'Commons2', u'Commons cat', u'Commons category', u'Commons+cat']), + 'zh': (u'Commonscat', [u'Commons cat', u'Commons category']), + 'zh-classical': (u'共享類', [u'Commonscat']), + 'zh-yue': (u'同享類', + [u'Commonscat', u'共享類 ', u'Commons cat', u'Commons category']), } ignoreTemplates = { 'af': [u'commons'], 'ar': [u'تحويلة تصنيف', u'كومنز', u'كومونز', u'Commons'], - 'be-x-old' : [u'Commons', u'Commons category'], + 'be-x-old': [u'Commons', u'Commons category'], 'cs': [u'Commons', u'Sestřičky', u'Sisterlinks'], 'da': [u'Commons', u'Commons left', u'Commons2', u'Commonsbilleder', u'Commonskat', u'Commonscat2', u'GalleriCommons', u'Søsterlinks'], @@ -169,9 +177,9 @@ (u'Projektoj', 'commonscat=')], 'es': [u'Commons', u'IprCommonscat'], 'eu': [u'Commons'], - 'fa': [u'Commons', u'ویکی‌انبار', - u'Category redirect',u'رده بهتر', - u'جعبه پیوند به پروژه‌های خواهر',u'در پروژه‌های خواهر',u'پروژه‌های خواهر'], + 'fa': [u'Commons', u'ویکی‌انبار', u'Category redirect', u'رده بهتر', + u'جعبه پیوند به پروژه‌های خواهر', u'در پروژه‌های خواهر', + u'پروژه‌های خواهر'], 'fi': [u'Commonscat-rivi', u'Commons-rivi', u'Commons'], 'fr': [u'Commons', u'Commons-inline', (u'Autres projets', 'commons=')], 'fy': [u'Commons', u'CommonsLyts'], @@ -186,7 +194,8 @@ 'om': [u'Commons'], 'pt': [u'Correlatos'], 'simple': [u'Sisterlinks'], - 'ru': [u'Навигация', u'Навигация для категорий', u'КПР', u'КБР', u'Годы в России', u'commonscat-inline'], + 'ru': [u'Навигация', u'Навигация для категорий', u'КПР', u'КБР', + u'Годы в России', u'commonscat-inline'], 'tt': [u'Навигация'], 'zh': [u'Category redirect', u'cr', u'Commons', u'Sisterlinks', u'Sisterlinkswp', @@ -203,7 +212,7 @@ 'en': u'Bot: Changing commonscat link from [[:Commons:Category:%(oldcat)s|%(oldcat)s]] to [[:Commons:Category:%(newcat)s|%(newcat)s]]', 'fa': u'ربات: تغییر پیوند به انبار از [[:Commons:Category:%(oldcat)s|%(oldcat)s]] به [[:Commons:Category:%(newcat)s|%(newcat)s]]', 'fr': u'Robot: Changé commonscat link de [[:Commons:Category:%(oldcat)s|%(oldcat)s]] à [[:Commons:Category:%(newcat)s|%(newcat)s]]', - 'frr':u'Bot: Feranere commonscat link faan [[:Commons:Category:%(oldcat)s|%(oldcat)s]] tu [[:Commons:Category:%(newcat)s|%(newcat)s]]', + 'frr': u'Bot: Feranere commonscat link faan [[:Commons:Category:%(oldcat)s|%(oldcat)s]] tu [[:Commons:Category:%(newcat)s|%(newcat)s]]', 'is': u'Vélmenni: Breyti Commonscat tengli frá [[:Commons:Category:%(oldcat)s|%(oldcat)s]] í [[:Commons:Category:%(newcat)s|%(newcat)s]]', 'pdc': u'Waddefresser: commonscat Gleecher vun [[:Commons:Category:%(oldcat)s|%(oldcat)s]] nooch [[:Commons:Category:%(newcat)s|%(newcat)s]] geennert', 'ru': u'Бот: Изменение commonscat-ссылки с [[:Commons:Category:%(oldcat)s|%(oldcat)s]] на [[:Commons:Category:%(newcat)s|%(newcat)s]]', @@ -227,31 +236,26 @@ self.treat(page) def treat(self, page): - """ - Loads the given page, does some changes, and saves it. - """ + """ Loads the given page, does some changes, and saves it. """ if not page.exists(): - pywikibot.output(u'Page %s does not exist. Skipping.' - % page.title(asLink=True)) + pywikibot.output(u'Page %s does not exist. Skipping.' + % page.title(asLink=True)) elif page.isRedirectPage(): - pywikibot.output(u'Page %s is a redirect. Skipping.' - % page.title(asLink=True)) + pywikibot.output(u'Page %s is a redirect. Skipping.' + % page.title(asLink=True)) elif page.isCategoryRedirect(): - pywikibot.output(u'Page %s is a category redirect. Skipping.' - % page.title(asLink=True)) + pywikibot.output(u'Page %s is a category redirect. Skipping.' + % page.title(asLink=True)) elif page.isDisambig(): - pywikibot.output(u'Page %s is a disambiguation. Skipping.' - % page.title(asLink=True)) + pywikibot.output(u'Page %s is a disambiguation. Skipping.' + % page.title(asLink=True)) else: (status, always) = self.addCommonscat(page) return def load(self, page): - """ - Loads the given page, does some changes, and saves it. - """ + """ Loads the given page, does some changes, and saves it. """ try: - # Load the page text = page.get() except pywikibot.NoPage: pywikibot.output(u"Page %s does not exist; skipping." @@ -272,7 +276,7 @@ % page.title()) # show what was changed pywikibot.showDiff(page.get(), text) - pywikibot.output(u'Comment: %s' %comment) + pywikibot.output(u'Comment: %s' % comment) if not self.always: choice = pywikibot.inputChoice( u'Do you want to accept these changes?', @@ -297,20 +301,20 @@ % (page.title())) except pywikibot.SpamfilterError, error: pywikibot.output( -u'Cannot change %s because of spam blacklist entry %s' + u'Cannot change %s because of spam blacklist entry %s' % (page.title(), error.url)) else: return True return False @classmethod - def getCommonscatTemplate (self, lang=None): - '''Get the template name in a language. Expects the language code. + def getCommonscatTemplate(self, lang=None): + """Get the template name in a language. Expects the language code. Return as tuple containing the primary template and it's alternatives - ''' + """ if lang in commonscatTemplates: - return commonscatTemplates[lang] + return commonscatTemplates[lang] else: return commonscatTemplates[u'_default'] @@ -332,8 +336,8 @@ return True return False - def updateInterwiki (self, wikipediaPage = None, commonsPage = None): - '''Update the interwiki's at commons from a wikipedia page. The bot just + def updateInterwiki(self, wikipediaPage=None, commonsPage=None): + """Update the interwiki's at commons from a wikipedia page. The bot just replaces the interwiki links at the commons page with the interwiki's from the wikipedia page. This should probably be more intelligent. We could use add all the interwiki's and remove duplicates. Or only remove @@ -342,70 +346,72 @@ This function is disabled for the moment until i figure out what the best way is to update the interwiki's. - ''' + """ interwikis = {} - comment= u'' + comment = u'' interwikilist = wikipediaPage.interwiki() interwikilist.append(wikipediaPage) for interwikiPage in interwikilist: - interwikis[interwikiPage.site()]=interwikiPage + interwikis[interwikiPage.site()] = interwikiPage oldtext = commonsPage.get() # The commonssite object doesnt work with interwiki's newtext = pywikibot.replaceLanguageLinks(oldtext, interwikis, pywikibot.getSite(u'nl')) - comment = u'Updating interwiki\'s from [[' + \ - wikipediaPage.site().language() + \ - u':' + wikipediaPage.title() + u']]' + comment = u'Updating interwiki\'s from [[%s:%s]]' \ + % (wikipediaPage.site.lang, wikipediaPage.title()) if newtext != oldtext: #This doesnt seem to work. Newtext has some trailing whitespace pywikibot.showDiff(oldtext, newtext) commonsPage.put(newtext=newtext, comment=comment) - def addCommonscat (self, page): - '''Take a page. Go to all the interwiki page looking for a commonscat + def addCommonscat(self, page): + """Take a page. Go to all the interwiki page looking for a commonscat template. When all the interwiki's links are checked and a proper category is found add it to the page. - ''' - pywikibot.output(u'Working on ' + page.title()); - #Get the right templates for this page + """ + pywikibot.output(u'Working on ' + page.title()) + # Get the right templates for this page primaryCommonscat, commonscatAlternatives = self.getCommonscatTemplate( page.site().language()) - commonscatLink = self.getCommonscatLink (page) + commonscatLink = self.getCommonscatLink(page) if commonscatLink: pywikibot.output(u'Commonscat template is already on %s' % page.title()) - (currentCommonscatTemplate, currentCommonscatTarget, LinkText, Note) = commonscatLink - checkedCommonscatTarget = self.checkCommonscatLink(currentCommonscatTarget) - if (currentCommonscatTarget==checkedCommonscatTarget): - #The current commonscat link is good + (currentCommonscatTemplate, + currentCommonscatTarget, LinkText, Note) = commonscatLink + checkedCommonscatTarget = self.checkCommonscatLink( + currentCommonscatTarget) + if (currentCommonscatTarget == checkedCommonscatTarget): + # The current commonscat link is good pywikibot.output(u'Commonscat link at %s to Category:%s is ok' - % (page.title() , currentCommonscatTarget)); + % (page.title(), currentCommonscatTarget)) return (True, self.always) - elif checkedCommonscatTarget!=u'': - #We have a new Commonscat link, replace the old one + elif checkedCommonscatTarget != u'': + # We have a new Commonscat link, replace the old one self.changeCommonscat(page, currentCommonscatTemplate, - currentCommonscatTarget, primaryCommonscat, - checkedCommonscatTarget, LinkText, Note) + currentCommonscatTarget, + primaryCommonscat, + checkedCommonscatTarget, LinkText, Note) return (True, self.always) else: #Commonscat link is wrong commonscatLink = self.findCommonscatLink(page) - if (commonscatLink!=u''): - self.changeCommonscat (page, currentCommonscatTemplate, - currentCommonscatTarget, primaryCommonscat, - commonscatLink) + if (commonscatLink != u''): + self.changeCommonscat(page, currentCommonscatTemplate, + currentCommonscatTarget, + primaryCommonscat, commonscatLink) #else #Should i remove the commonscat link? elif self.skipPage(page): pywikibot.output("Found a template in the skip list. Skipping %s" - % page.title()); + % page.title()) else: commonscatLink = self.findCommonscatLink(page) - if (commonscatLink!=u''): + if (commonscatLink != u''): if commonscatLink == page.title(): textToAdd = u'{{%s}}' % primaryCommonscat else: @@ -416,20 +422,19 @@ self.summary, None, None, self.always) - return (True, self.always); + return (True, self.always) + return (True, self.always) - return (True, self.always); - - def changeCommonscat (self, page=None, oldtemplate=u'', oldcat=u'', - newtemplate=u'', newcat=u'', linktitle=u'', - description=u''): - ''' Change the current commonscat template and target. ''' + def changeCommonscat(self, page=None, oldtemplate=u'', oldcat=u'', + newtemplate=u'', newcat=u'', linktitle=u'', + description=u''): + """ Change the current commonscat template and target. """ if oldcat == '3=S' or linktitle == '3=S': - return #additional param on de-wiki, TODO: to be handled + return # additional param on de-wiki, TODO: to be handled if not linktitle and (page.title().lower() in oldcat.lower() or oldcat.lower() in page.title().lower()): linktitle = oldcat - if linktitle and newcat <> page.title(withNamespace=False): + if linktitle and newcat != page.title(withNamespace=False): newtext = re.sub(u'(?i)\{\{%s\|?[^{}]*(?:\{\{.*\}\})?\}\}' % oldtemplate, u'{{%s|%s|%s}}' % (newtemplate, newcat, linktitle), @@ -439,30 +444,33 @@ % oldtemplate, u'{{%s}}' % newtemplate, page.get()) - elif oldcat.strip() != newcat: #strip trailing white space + elif oldcat.strip() != newcat: # strip trailing white space newtext = re.sub(u'(?i)\{\{%s\|?[^{}]*(?:\{\{.*\}\})?\}\}' - %oldtemplate, + % oldtemplate, u'{{%s|%s}}' % (newtemplate, newcat), page.get()) - else: # nothing left to do + else: # nothing left to do return if self.summary: comment = self.summary else: - comment = pywikibot.translate(page.site(), msg_change) \ - % {'oldcat':oldcat, 'newcat':newcat} + comment = pywikibot.translate(page.site(), + msg_change) % {'oldcat': oldcat, + 'newcat': newcat} self.save(newtext, page, comment) - def findCommonscatLink (self, page=None): + def findCommonscatLink(self, page=None): for ipage in page.interwiki(): try: if(ipage.exists() and not ipage.isRedirectPage() and not ipage.isDisambig()): - commonscatLink = self.getCommonscatLink (ipage) + commonscatLink = self.getCommonscatLink(ipage) if commonscatLink: - (currentTemplate, possibleCommonscat, linkText, Note) = commonscatLink - checkedCommonscat = self.checkCommonscatLink(possibleCommonscat) - if (checkedCommonscat!= u''): + (currentTemplate, + possibleCommonscat, linkText, Note) = commonscatLink + checkedCommonscat = self.checkCommonscatLink( + possibleCommonscat) + if (checkedCommonscat != u''): pywikibot.output( u"Found link for %s at [[%s:%s]] to %s." % (page.title(), ipage.site().language(), @@ -473,21 +481,20 @@ return u'' return u'' - - def getCommonscatLink (self, wikipediaPage=None): + def getCommonscatLink(self, wikipediaPage=None): ''' Go through the page and return a tuple of (<templatename>, <target>) ''' primaryCommonscat, commonscatAlternatives = self.getCommonscatTemplate( wikipediaPage.site().language()) commonscatTemplate = u'' - commonscatTarget = u'' + commonscatTarget = u'' commonscatLinktext = u'' - commonscatNote = u'' - #See if commonscat is present + commonscatNote = u'' + # See if commonscat is present for template in wikipediaPage.templatesWithParams(): - if template[0]==primaryCommonscat \ + if template[0] == primaryCommonscat \ or template[0] in commonscatAlternatives: commonscatTemplate = template[0] if (len(template[1]) > 0): @@ -502,14 +509,14 @@ commonscatLinktext, commonscatNote) return None - def checkCommonscatLink (self, name = ""): - ''' - This function will retun the name of a valid commons category + def checkCommonscatLink(self, name=""): + """ This function will return the name of a valid commons category If the page is a redirect this function tries to follow it. If the page doesnt exists the function will return an empty string - ''' + + """ if pywikibot.verbose: - pywikibot.output("getCommonscat: " + name ) + pywikibot.output("getCommonscat: " + name) try: commonsSite = self.site.image_repository() #This can throw a pywikibot.BadTitle @@ -531,13 +538,15 @@ return self.checkCommonscatLink(m.group('newcat2')) else: pywikibot.output( - u'getCommonscat: Deleted by %s. Couldn\'t find move target in \" %s \"' + u'getCommonscat: Deleted by %s. Couldn\'t find ' + u'move target in "%s"' % (loguser, logcomment)) return u'' except StopIteration: if pywikibot.verbose: pywikibot.output( - u"getCommonscat: The category doesnt exist and nothing found in the deletion log.") + u"getCommonscat: The category doesnt exist and " + u"nothing found in the deletion log.") return u'' elif commonsPage.isRedirectPage(): if pywikibot.verbose: @@ -550,8 +559,8 @@ pywikibot.output( u"getCommonscat: The category is a category redirect") for template in commonsPage.templatesWithParams(): - if ((template[0]=="Category redirect") - and (len(template[1]) > 0)): + if (template[0] == "Category redirect" and + len(template[1]) > 0): return self.checkCommonscatLink(template[1][0]) elif commonsPage.isDisambig(): if pywikibot.verbose: @@ -561,17 +570,21 @@ else: return commonsPage.title(withNamespace=False) except pywikibot.BadTitle: - #Funky title so not correct + # Funky title so not correct return u'' except pywikibot.PageNotFound: return u'' + def main(): - ''' - Parse the command line arguments and get a pagegenerator to work on. + """ Parse the command line arguments and get a pagegenerator to work on. Iterate through all the pages. - ''' - summary = None; generator = None; checkcurrent = False; always = False + """ + + summary = None + generator = None + checkcurrent = False + always = False ns = [] ns.append(14) # Load a lot of default generators @@ -586,8 +599,8 @@ elif arg.startswith('-checkcurrent'): checkcurrent = True primaryCommonscat, commonscatAlternatives = \ - CommonscatBot.getCommonscatTemplate( - pywikibot.getSite().language()) + CommonscatBot.getCommonscatTemplate( + pywikibot.getSite().language()) generator = pagegenerators.NamespaceFilterPageGenerator( pagegenerators.ReferringPageGenerator( pywikibot.Page(pywikibot.getSite(), @@ -602,8 +615,8 @@ if not generator: generator = genFactory.getCombinedGenerator() if not generator: - raise add_text.NoEnoughData( -u'You have to specify the generator you want to use for the script!') + raise add_text.NoEnoughData(u'You have to specify the generator you ' + u'want to use for the script!') pregenerator = pagegenerators.PreloadingGenerator(generator) bot = CommonscatBot(pregenerator, always, summary) -- To view, visit https://gerrit.wikimedia.org/r/95823 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I78812c95db15fced70996283458aacc18db34bea Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] pep8 changes - change (pywikibot/compat)
by jenkins-bot (Code Review) 16 Nov '13

16 Nov '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] pep8 changes ...................................................................... [PEP8] pep8 changes Change-Id: I5ee3047a6ad1a325e81a7db0590697d9d57500fc --- M commons_link.py 1 file changed, 31 insertions(+), 28 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/commons_link.py b/commons_link.py index 26933ae..d40de55 100644 --- a/commons_link.py +++ b/commons_link.py @@ -27,42 +27,43 @@ """ # # (C) Leonardo Gregianin, 2006 -# (C) Pywikipedia team, 2007-2011 +# (C) Pywikibot team, 2007-2013 # # Distributed under the terms of the MIT license. # -__version__='$Id$' +__version__ = '$Id$' import re import wikipedia as pywikibot -import pagegenerators, catlib +import pagegenerators +import catlib comment1 = { - 'ar':u'روبوت: تضمين قالب كومنز', - 'cs':u'Robot přidal šablonu commons', - 'en':u'Robot: Include commons template', - 'fa':u'ربات: افزودن الگوی ویکی‌انبار', - 'he':u'בוט: מוסיף תבנית Commons', - 'ja':u'ロボットによる: テンプレcommons追加', - 'nl':u'Bot: sjabloon commons toegevoegd', - 'zh':u'機器人: 增加commons模板', + 'ar': u'روبوت: تضمين قالب كومنز', + 'cs': u'Robot přidal šablonu commons', + 'en': u'Robot: Include commons template', + 'fa': u'ربات: افزودن الگوی ویکی‌انبار', + 'he': u'בוט: מוסיף תבנית Commons', + 'ja': u'ロボットによる: テンプレcommons追加', + 'nl': u'Bot: sjabloon commons toegevoegd', + 'zh': u'機器人: 增加commons模板', } comment2 = { - 'ar':u'روبوت: تضمين قالب تصنيف كومنز', - 'cs':u'Robot přidal šablonu commonscat', - 'en':u'Robot: Include commonscat template', - 'fa':u'ربات: افزودن الگوی رده‌بندی ویکی‌انبار', - 'he':u'בוט: מוסיף תבנית Commonscat', - 'ja':u'ロボットによる: テンプレcommonscat追加', - 'nl':u'Bot: sjabloon commonscat toegevoegd', - 'zh':u'機器人: 增加commonscat模板', + 'ar': u'روبوت: تضمين قالب تصنيف كومنز', + 'cs': u'Robot přidal šablonu commonscat', + 'en': u'Robot: Include commonscat template', + 'fa': u'ربات: افزودن الگوی رده‌بندی ویکی‌انبار', + 'he': u'בוט: מוסיף תבנית Commonscat', + 'ja': u'ロボットによる: テンプレcommonscat追加', + 'nl': u'Bot: sjabloon commonscat toegevoegd', + 'zh': u'機器人: 增加commonscat模板', } class CommonsLinkBot: - def __init__(self, generator, acceptall = False): + def __init__(self, generator, acceptall=False): self.generator = generator self.acceptall = acceptall @@ -79,9 +80,9 @@ text = oldText # for commons template - findTemplate=re.compile(ur'\{\{[Cc]ommonscat') + findTemplate = re.compile(ur'\{\{[Cc]ommonscat') s = findTemplate.search(text) - findTemplate2=re.compile(ur'\{\{[Ss]isterlinks') + findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks') s2 = findTemplate2.search(text) if s or s2: pywikibot.output(u'** Already done.') @@ -105,7 +106,8 @@ page.put(text, msg) except pywikibot.EditConflict: pywikibot.output( - u'Skipping %s because of edit conflict' + u'Skipping %s because of edit ' + u'conflict' % (page.title())) except pywikibot.NoPage: @@ -129,15 +131,15 @@ try: getcommonscat = commonsCategory.get(get_redirect=True) commonsCategoryTitle = commonsCategory.title() - categoryname = commonsCategoryTitle.split('Category:',1)[1] + categoryname = commonsCategoryTitle.split('Category:', 1)[1] if page.title() == categoryname: oldText = page.get() text = oldText # for commonscat template - findTemplate=re.compile(ur'\{\{[Cc]ommons') + findTemplate = re.compile(ur'\{\{[Cc]ommons') s = findTemplate.search(text) - findTemplate2=re.compile(ur'\{\{[Ss]isterlinks') + findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks') s2 = findTemplate2.search(text) if s or s2: pywikibot.output(u'** Already done.') @@ -161,7 +163,8 @@ page.put(text, msg) except pywikibot.EditConflict: pywikibot.output( - u'Skipping %s because of edit conflict' + u'Skipping %s because of edit ' + u'conflict' % (page.title())) except pywikibot.NoPage: @@ -191,7 +194,7 @@ gen = pagegenerators.AllpagesPageGenerator( start.title(withNamespace=False), namespace=start.namespace(), - includeredirects = False) + includeredirects=False) elif arg.startswith('-cat:'): cat = catlib.Category(pywikibot.getSite(), 'Category:%s' % arg[5:]) -- To view, visit https://gerrit.wikimedia.org/r/95813 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I5ee3047a6ad1a325e81a7db0590697d9d57500fc Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] pep8 changes - change (pywikibot/compat)
by jenkins-bot (Code Review) 16 Nov '13

16 Nov '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] pep8 changes ...................................................................... [PEP8] pep8 changes Change-Id: I9f6283462b2bed90b5d737ed976521901fb17506 --- M commons_category_redirect.py 1 file changed, 27 insertions(+), 19 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/commons_category_redirect.py b/commons_category_redirect.py index 534bd13..b1a06a5 100644 --- a/commons_category_redirect.py +++ b/commons_category_redirect.py @@ -1,60 +1,67 @@ #!/usr/bin/python # -*- coding: utf-8 -*- """ -Script to clean up http://commons.wikimedia.org/wiki/Category:Non-empty_category_redirects +Script to clean up +http://commons.wikimedia.org/wiki/Category:Non-empty_category_redirects -Moves all images, pages and categories in redirect categories to the target category. +Moves all images, pages and categories in redirect categories to the target +category. """ # # (C) Multichill, 2008 -# (C) Pywikipedia team, 2008-2011 +# (C) Pywikibot team, 2008-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' -import wikipedia as pywikibot -import config, catlib -from category import * from datetime import datetime from datetime import timedelta -redirect_templates = [u'Category redirect', u'Categoryredirect', u'See cat', u'Seecat', u'Catredirect', u'Cat redirect', u'CatRed', u'Catredir'] +import wikipedia as pywikibot +import config +import catlib +from category import * + +redirect_templates = [u'Category redirect', u'Categoryredirect', u'See cat', + u'Seecat', u'Catredirect', u'Cat redirect', u'CatRed', + u'Catredir'] move_message = u'Moving from [[%s|%s]] to [[%s|%s]] (following [[Template:Category redirect|category redirect]])' -cooldown = 7 # days +cooldown = 7 # days + def get_redirect_cat(category=None): - ''' - Return the target category - ''' + """ Return the target category """ destination = None site = pywikibot.getSite(u'commons', u'commons') for template in category.templatesWithParams(): if ((template[0] in redirect_templates) and (len(template[1]) > 0)): #destination = template[1][0]; - destination =catlib.Category(site, template[1][0]) + destination = catlib.Category(site, template[1][0]) if not destination.exists(): return None return destination + def readyToEdit(old_category): - ''' If the category is edited more recenty than cooldown, return false, + """ If the category is edited more recenty than cooldown, return false, otherwise true. - ''' - dateformat ="%Y%m%d%H%M%S" + """ + dateformat = "%Y%m%d%H%M%S" today = datetime.now() deadline = today + timedelta(days=-cooldown) old_category.get() return (deadline.strftime(dateformat) > old_category.editTime()) + def main(): - ''' Main loop. Loop over all categories of + """ Main loop. Loop over all categories of Category:Non-empty_category_redirects and move all content. - ''' + """ site = pywikibot.getSite(u'commons', u'commons') dirtycat = catlib.Category(site, u'Category:Non-empty category redirects') @@ -62,8 +69,8 @@ catbot = None for old_category in dirtycat.subcategories(): - # We want to wait several days after the last edit before we start moving - # things around. This it to prevent edit wars and vandals. + # We want to wait several days after the last edit before we start + # moving things around. This it to prevent edit wars and vandals. if(readyToEdit(old_category)): destination = get_redirect_cat(old_category) if destination: @@ -94,6 +101,7 @@ except: pywikibot.output(u'Dummy edit at %s failed' % old_category.title()) + if __name__ == "__main__": try: main() -- To view, visit https://gerrit.wikimedia.org/r/95812 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I9f6283462b2bed90b5d737ed976521901fb17506 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] remaining pep8 changes - change (pywikibot/compat)
by Xqt (Code Review) 16 Nov '13

16 Nov '13

Xqt has submitted this change and it was merged. Change subject: [PEP8] remaining pep8 changes ...................................................................... [PEP8] remaining pep8 changes Change-Id: I915cba5f57ee3f8e9901ccee039ca2fda932373e --- M checkimages.py 1 file changed, 1 insertion(+), 1 deletion(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/checkimages.py b/checkimages.py index da98deb..8f25dfc 100644 --- a/checkimages.py +++ b/checkimages.py @@ -1209,7 +1209,7 @@ # Don't report, but continue with the check # (we don't now if this is the first time we check this file # or not) - return True + return True # The talk page includes "_" between the two names, in this way I # replace them to " " -- To view, visit https://gerrit.wikimedia.org/r/95811 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I915cba5f57ee3f8e9901ccee039ca2fda932373e Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

Pywikibot-commits