Pywikipedia-l September 2007

pywikipedia-l@lists.wikimedia.org

24 participants
397 discussions

SVN: [4357] trunk/pywikipedia/copyright.py

by cosoleto＠svn.wikimedia.org

Revision: 4357 Author: cosoleto Date: 2007-09-24 18:23:48 +0000 (Mon, 24 Sep 2007) Log Message: ----------- fix, google cache Modified Paths: -------------- trunk/pywikipedia/copyright.py Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2007-09-24 17:55:32 UTC (rev 4356) +++ trunk/pywikipedia/copyright.py 2007-09-24 18:23:48 UTC (rev 4357) @@ -727,13 +727,13 @@ if length > 0: comment.append("%d %s" % (length, unit)) - if cache: - if engine == 'google': - comment.append('[http://www.google.com/search?sourceid=navclient&q=cache:%s google cache]' % add_item[7:]) - elif engine == 'yahoo': - cache = False - elif engine == 'msn': - cache = False + if cache: + if engine == 'google': + comment.append('[http://www.google.com/search?sourceid=navclient&q=cache:%s google cache]' % add_item[7:]) + elif engine == 'yahoo': + cache = False + elif engine == 'msn': + cache = False for i in range(len(url)): if add_item in url[i]:

16 years, 7 months

SVN: [4356] trunk/pywikipedia/userinterfaces/tkinter_interface.py

by russblau＠svn.wikimedia.org

Revision: 4356 Author: russblau Date: 2007-09-24 17:55:32 +0000 (Mon, 24 Sep 2007) Log Message: ----------- Still very primitive, but now it works. Modified Paths: -------------- trunk/pywikipedia/userinterfaces/tkinter_interface.py Modified: trunk/pywikipedia/userinterfaces/tkinter_interface.py =================================================================== --- trunk/pywikipedia/userinterfaces/tkinter_interface.py 2007-09-24 11:29:36 UTC (rev 4355) +++ trunk/pywikipedia/userinterfaces/tkinter_interface.py 2007-09-24 17:55:32 UTC (rev 4356) @@ -1,4 +1,3 @@ - __version__ = '$Id$' import time @@ -6,13 +5,23 @@ import tkMessageBox, tkSimpleDialog from Tkinter import * +# we run the Tkinter mainloop in a separate thread so as not to block +# the main bot code; however, this means that all communication with +# the Tkinter interface has to be done through events that will be processed +# by the mainloop in the separate thread. It is not possible for the +# interface code to call any of the Tkinter objects directly, except to +# put events on their queue (e.g., .after_idle()). + class MainloopThread(threading.Thread): def __init__(self, window): threading.Thread.__init__(self) self.window = window def run(self): - self.window.mainloop() + try: + self.window.mainloop() + except SystemExit: + return class EditBoxWindow: @@ -105,54 +114,82 @@ self.text = unicode(self.text, 'ascii') self.top.destroy() -class CustomMessageBox(tkMessageBox.Message): - def __init__(self, parent, question, options, hotkeys, default = None): - self.selection = None + +class CustomMessageBox(tkSimpleDialog.Dialog): + def __init__(self, master, question, options, hotkeys, default=None): + self.question = question + self.options = options self.hotkeys = hotkeys self.default = default - - self.top = Toplevel(parent) - Label(self.top, text=question).grid(columnspan = len(options)) - for i in range(len(options)): + tkSimpleDialog.Dialog.__init__(self, master) + + def body(self, master): + Label(self, text=self.question).grid(columnspan = len(self.options)) + btns = [] + for i in xrange(len(self.options)): # mark hotkey with underline - m = re.search('[%s%s]' % (hotkeys[i].lower(), hotkeys[i].upper()), options[i]) + m = re.search('[%s%s]' % (self.hotkeys[i].lower(), + self.hotkeys[i].upper()), self.options[i]) if m: pos = m.start() else: - options[i] += ' (%s)' % hotkeys[i] - pos = len(options[i]) - 2 - b = Button(self.top, text = options[i], underline = pos, command = lambda h=hotkeys[i]: self.select(h)) + self.options[i] += ' (%s)' % self.hotkeys[i] + pos = len(self.options[i]) - 2 + b = Button(self, text=self.options[i], + underline=pos, + command=lambda h=self.hotkeys[i]: self.select(h)) + self.bind("<Control-%s" % self.hotkeys[i], + lambda h=self.hotkeys[i]: self.select(h)) b.grid(row = 1, column = i) + btns.append(b) + if self.default and self.default in self.hotkeys: + return btns[self.hotkeys.index(self.default)] + else: + return btns[0] - def select(self, i): + def buttonbox(self): + return + + def select(self, i, event=None): self.selection = i - self.top.destroy() + self.ok() - def ask(self): + def apply(self): if self.default and not self.selection: - return self.default - else: - return self.selection + self.selection = self.default + +class OutputBox(Text): + def __init__(self, parent, *args, **kwargs): + Text.__init__(self, parent, *args, **kwargs) + + def show(self, text): + self.insert(END, text) + self.yview(END) + + class UI: def __init__(self, parent = None): # create a new window if necessary self.parent = parent or Tk() self.top_frame = Frame(parent) + scrollbar = Scrollbar(self.top_frame) - scrollbar = Scrollbar(self.top_frame) # textarea with vertical scrollbar - self.logBox = Text(self.top_frame, yscrollcommand=scrollbar.set) + self.logBox = OutputBox(self.top_frame, yscrollcommand=scrollbar.set) + # add scrollbar to main frame, associate it with our editbox scrollbar.pack(side=RIGHT, fill=Y) scrollbar.config(command=self.logBox.yview) + # put textarea into top frame, using all available space self.logBox.pack(anchor=CENTER, fill=BOTH) self.top_frame.pack(side=TOP) self.logBox.tag_config(12, foreground='red') self.logBox.tag_config(10, foreground='green') +# self.parent.mainloop() MainloopThread(self.parent).start() def output(self, text, urgency = 1, toStdout = False): @@ -165,44 +202,29 @@ TODO: introduce constants """ if urgency >= 2: - box = CustomMessageBox(self.parent, text, ['OK'], ['O'], 'O') - box.ask() + box = CustomMessageBox(self.parent) + self.parent.after_idle(box.display, text, ['OK'], ['O'], 'O') self.parent.wait_window(box.top) - # this alternative uses a too large font - # d = tkMessageBox.showinfo('title', text) elif urgency >= 1: - # Save the line number before appending text - lineCount = float(self.logBox.index(END).split('.')[0]) - 1 - self.logBox.insert(END, text) - # colors support currently broken, sorry. - #if colors: - ## How many characters we already added in this line - #offset = 0 - ## We create a tag region for each colored character. - ## It would be more efficient to try to use longer - ## regions. - #for i in range(len(colors)): - #if text[i] == '\n': - #lineCount += 1 - #offset = i + 1 - #if colors[i]: - #startidx = '%i.%i' % (lineCount, i - offset) - #endidx = '%i.%i' % (lineCount, i + 1 - offset) - ## tag the whole occurence (start included, stop excluded) - #self.logBox.tag_add(colors[i], startidx , endidx) - - - # auto-scroll down - self.logBox.see(END) + self.parent.after_idle(self.logBox.show, text) def input(self, question, password = False): """ Returns a unicode string. """ # TODO: hide input if password = True - answer = tkSimpleDialog.askstring('title', question) + self.parent.after_idle(self.ask, question) + # wait until the answer has been given + while not hasattr(self, "answer"): + time.sleep(1) + answer = self.answer + del self.answer return answer + def ask(self, question, password=False): + # this method is called from the mainloopThread + self.answer = tkSimpleDialog.askstring('Question', question) + def editText(self, text, jumpIndex = None, highlight = None): editBoxWindow = EditBoxWindow(text) editBoxWindow.highlight(highlight) @@ -210,7 +232,6 @@ return editBoxWindow.text def inputChoice(self, question, options, hotkeys, default = None): - d = CustomMessageBox(self.parent, question, options, hotkeys) self.parent.wait_window(d.top) answer = d.ask()

16 years, 7 months

[ pywikipediabot-Bugs-1796174 ] category.py bug with -person and DEFAULTSORT templates

by SourceForge.net

Bugs item #1796174, was opened at 2007-09-17 05:25 Message generated for change (Comment added) made by nobody You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1796174&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: category Group: None Status: Open Resolution: None Priority: 5 Private: No Submitted By: Nobody/Anonymous (nobody) Assigned to: Nobody/Anonymous (nobody) Summary: category.py bug with -person and DEFAULTSORT templates Initial Comment: When using the -person switch on category.py to add categories to articles which use the {{DEFAULTSORT}} template, the script doesn't understand that the category already exists. For example: python category.py add -person (Add category "La Liga players") The article might look like: {{DEFAULTSORT:Pauleta}} [[Category:La Liga Players]] And the script will not understand that the category already exists for this article and add: [[Category:La Liga players|Pauleta]] ---------------------------------------------------------------------- Comment By: Nobody/Anonymous (nobody) Date: 2007-09-24 09:33 Message: Logged In: NO Also, the script SHOULD NOT add sorting information, even when using -person, to articles which use the DEFAULTSORT template. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1796174&group_…

16 years, 7 months

SVN: [4355] trunk/pywikipedia/spamremove.py

by leogregianin＠svn.wikimedia.org

Revision: 4355 Author: leogregianin Date: 2007-09-24 11:29:36 +0000 (Mon, 24 Sep 2007) Log Message: ----------- pt msg Modified Paths: -------------- trunk/pywikipedia/spamremove.py Modified: trunk/pywikipedia/spamremove.py =================================================================== --- trunk/pywikipedia/spamremove.py 2007-09-24 09:30:06 UTC (rev 4354) +++ trunk/pywikipedia/spamremove.py 2007-09-24 11:29:36 UTC (rev 4355) @@ -28,6 +28,7 @@ 'de': u'Entferne in Spam-Blacklist eingetragenen Weblink auf %s', 'en': u'Removing links to spammed site %s', 'nl': u'Links naar gespamde site %s verwijderd', + 'pt': u'Removendo links de spam do site %s', } spamSite = '' for arg in wikipedia.handleArgs():

16 years, 7 months

SVN: [4354] trunk/pywikipedia/copyright.py

by cosoleto＠svn.wikimedia.org

Revision: 4354 Author: cosoleto Date: 2007-09-24 09:30:06 +0000 (Mon, 24 Sep 2007) Log Message: ----------- fix typo Modified Paths: -------------- trunk/pywikipedia/copyright.py Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2007-09-24 09:17:56 UTC (rev 4353) +++ trunk/pywikipedia/copyright.py 2007-09-24 09:30:06 UTC (rev 4354) @@ -768,7 +768,7 @@ search_request_retry = config.copyright_connection_tries while search_request_retry: try: - data = google.doGoogleSearch('%s "%s"' % (no_result_with_those_words, query) + data = google.doGoogleSearch('%s "%s"' % (no_result_with_those_words, query)) search_request_retry = 0 for entry in data.results: add_in_urllist(url, entry.URL, 'google')

16 years, 7 months

SVN: [4353] trunk/pywikipedia

by cosoleto＠svn.wikimedia.org

Revision: 4353 Author: cosoleto Date: 2007-09-24 09:17:56 +0000 (Mon, 24 Sep 2007) Log Message: ----------- copyright.py: Fixed problem with preload generator and new pages generetor (pointed out by Filnik)). Added note to help users of Python 2.5.0 to install SOAPpy 0.12.0. copyright_put.py, copyright_clean.py: Minor fixes, and code cleanup. Modified Paths: -------------- trunk/pywikipedia/CONTENTS trunk/pywikipedia/copyright.py trunk/pywikipedia/copyright_clean.py trunk/pywikipedia/copyright_put.py Modified: trunk/pywikipedia/CONTENTS =================================================================== --- trunk/pywikipedia/CONTENTS 2007-09-24 09:07:53 UTC (rev 4352) +++ trunk/pywikipedia/CONTENTS 2007-09-24 09:17:56 UTC (rev 4353) @@ -85,7 +85,7 @@ clean_sandbox.py : This bot makes the cleaned of the page of tests. commons_link.py : This robot include commons template to linking Commons and your wiki project. -copyright.py : This robot check copyright text in Google and Yahoo. +copyright.py : This robot check copyright text in Google, Yahoo! and Live Search. cosmetic_changes.py : Can do slight modifications to a wiki page source code such that the code looks cleaner. delete.py : This script can be used to delete pages en masse. Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2007-09-24 09:07:53 UTC (rev 4352) +++ trunk/pywikipedia/copyright.py 2007-09-24 09:17:56 UTC (rev 4353) @@ -13,6 +13,10 @@ Windows Live Search requires to install the SOAPpy module from http://pywebsvcs.sf.net and get an AppID from http://search.msn.com/developer. +If you use Python 2.5 and have SOAPpy version 0.12.0, you must edit three +files (SOAPpy/Client.py, SOAPpy/Server.py, SOAPpy/Types.py) to fix a simple +syntax error by moving 'from __future__ imports...' line to beginning of the +code. You can run the bot with the following commandline parameters: @@ -75,6 +79,9 @@ __version__='$Id$' +# +no_result_with_those_words = '-Wikipedia' + # Try to skip quoted text. exclude_quote = True @@ -413,7 +420,7 @@ text = re.sub('^[:*]?\s*[“][^”]+[”]\.?\s*(($|<ref>).*?($|</ref>))?\.?$', "", text) # remove URL - text = re.sub('https?://[\w/.,;:@&=%#\\\?_!~*\'|()\"+-]+', ' ', text) + text = re.sub('(ftp|https?)://[\w/.,;:@&=%#\\\?_!~*\'|()\"+-]+', ' ', text) # remove Image tags text = reImageC.sub("", text) @@ -761,7 +768,7 @@ search_request_retry = config.copyright_connection_tries while search_request_retry: try: - data = google.doGoogleSearch('-Wikipedia "' + query + '"') + data = google.doGoogleSearch('%s "%s"' % (no_result_with_those_words, query) search_request_retry = 0 for entry in data.results: add_in_urllist(url, entry.URL, 'google') @@ -780,9 +787,10 @@ if config.copyright_yahoo: import yahoo.search.web print " Yahoo query..." - data = yahoo.search.web.WebSearch(config.yahoo_appid, query='"' + - query.encode('utf_8') + - '" -Wikipedia', results=numresults) + data = yahoo.search.web.WebSearch(config.yahoo_appid, query='"%s" %s' % ( + query.encode('utf_8'), + no_result_with_those_words + ), results = numresults) search_request_retry = config.copyright_connection_tries while search_request_retry: try: @@ -805,7 +813,8 @@ except: print "Live Search Error" raise - params = {'AppID': config.msn_appid, 'Query': '-Wikipedia "' + query + '"', 'CultureInfo': 'en-US', 'SafeSearch': 'Off', 'Requests': { + params = {'AppID': config.msn_appid, 'Query': '%s "%s"' % (no_result_with_those_words, query), + 'CultureInfo': 'en-US', 'SafeSearch': 'Off', 'Requests': { 'SourceRequest':{'Source': 'Web', 'Offset': 0, 'Count': 10, 'ResultFields': 'All',}}} search_request_retry = config.copyright_connection_tries @@ -919,9 +928,6 @@ PageTitles = [] # IDs which will be processed when the -ids parameter is used ids = None - # will become True when the user presses a ('yes to all') or uses the -always - # commandline paramater. - acceptall = False # Which namespaces should be processed? # default to [] which means all namespaces will be processed namespaces = [] @@ -929,6 +935,10 @@ repeat = False # text = None + # Number of pages to load at a time by Preload generator + pageNumber = 40 + # Default number of pages for NewPages generator + number = 60 firstPageTitle = None # This factory is responsible for processing command line arguments @@ -936,11 +946,6 @@ # to work on. genFactory = pagegenerators.GeneratorFactory() - - 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") - # Read commandline parameters. for arg in wikipedia.handleArgs(): if arg == '-y': @@ -967,11 +972,6 @@ elif arg.startswith('-text'): if len(arg) >= 6: text = arg[6:] - elif arg.startswith('-xml'): - if len(arg) == 4: - xmlFilename = wikipedia.input(u'Please enter the XML dump\'s filename:') - else: - xmlFilename = arg[5:] elif arg.startswith('-page'): if len(arg) == 5: PageTitles.append(wikipedia.input(u'Which page do you want to change?')) @@ -988,9 +988,12 @@ repeat = True elif arg.startswith('-new'): if len(arg) >=5: - gen = pagegenerators.NewpagesPageGenerator(number=int(arg[5:]), repeat = repeat) - else: - gen = pagegenerators.NewpagesPageGenerator(number=60, repeat = repeat) + 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: generator = genFactory.handleArg(arg) if generator: @@ -1000,13 +1003,17 @@ pages = [wikipedia.Page(wikipedia.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") + if ids: checks_by_ids(ids) if not gen and not ids and not text: # syntax error, show help text from the top of this file wikipedia.output(__doc__, 'utf-8') - + if text: output = query(lines = text.splitlines()) if output: @@ -1017,7 +1024,7 @@ sys.exit() if namespaces != []: gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces) - preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber = 20) + preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber = pageNumber) bot = CheckRobot(preloadingGen) bot.run() Modified: trunk/pywikipedia/copyright_clean.py =================================================================== --- trunk/pywikipedia/copyright_clean.py 2007-09-24 09:07:53 UTC (rev 4352) +++ trunk/pywikipedia/copyright_clean.py 2007-09-24 09:17:56 UTC (rev 4353) @@ -27,7 +27,7 @@ # # {{botbox|title|newid|oldid|author|...}} -rev_templateC = re.compile("(?m)^(?:{{/t\|.*?}}\n?)?{{botbox\|.*?\|(.*?)\|") +rev_templateC = re.compile("(?m)^(?:{{/t\|.*?}}\n?)?{{(?:/box|botbox)\|.*?\|(.*?)\|") def query_yurik_api(data): @@ -48,21 +48,8 @@ return data -def manage_query(items, mode = "titles"): - """No more of 100 titles at a time using Yurik's API""" - - global query_results - - for s in mysplit(items, 100, "|"): - if mode == "titles": - query_results.append(simplejson.loads(query_yurik_api(('titles', s)))) - - elif mode == 'revids': - query_results2.append(simplejson.loads(query_yurik_api(('revids', s)))) - return - def page_exist(title): - for pageobjs in query_results: + for pageobjs in query_results_titles: for key in pageobjs['pages']: if pageobjs['pages'][key]['title'] == title: if int(key) >= 0: @@ -71,7 +58,7 @@ return False def revid_exist(revid): - for pageobjs in query_results2: + for pageobjs in query_results_revids: for id in pageobjs['pages']: for rv in range(len(pageobjs['pages'][id]['revisions'])): if pageobjs['pages'][id]['revisions'][rv]['revid'] == int(revid): @@ -85,7 +72,7 @@ for page in gen: data = page.get() - wikipedia.output(page.title()) + wikipedia.output(page.aslink()) output = '' # @@ -104,11 +91,14 @@ titles = headC.findall(data) revids = rev_templateC.findall(data) - query_results = list() - query_results2 = list() + query_results_titles = list() + query_results_revids = list() - manage_query(query.ListToParam(titles)) - manage_query(query.ListToParam(revids), "revids") + # No more of 100 titles at a time using Yurik's API + for s in mysplit(query.ListToParam(titles), 100, "|"): + query_results_titles.append(simplejson.loads(query_yurik_api(('titles', s)))) + for s in mysplit(query.ListToParam(revids), 100, "|"): + query_results_revids.append(simplejson.loads(query_yurik_api(('revids', s)))) comment_entry = list() add_separator = False @@ -131,7 +121,7 @@ exist = True if page_exist(title): # check {{botbox}} - revid = re.search("{{botbox\|.*?\|(.*?)\|", data[head.end():stop]) + revid = re.search("{{(?:/box|botbox)\|.*?\|(.*?)\|", data[head.end():stop]) if revid: if not revid_exist(revid.group(1)): exist = False Modified: trunk/pywikipedia/copyright_put.py =================================================================== --- trunk/pywikipedia/copyright_put.py 2007-09-24 09:07:53 UTC (rev 4352) +++ trunk/pywikipedia/copyright_put.py 2007-09-24 09:17:56 UTC (rev 4353) @@ -38,8 +38,8 @@ } stat_msg = { - 'en': [u'Statistics', u'Page', u'Entries', u'Total', 'Update'], - 'it': [u'Statistiche', u'Pagina', u'Segnalazioni', u'Totale', u'Ultimo aggiornamento'], + 'en': [u'Statistics', u'Page', u'Entries', u'Size', u'Total', 'Update'], + 'it': [u'Statistiche', u'Pagina', u'Segnalazioni', u'Lunghezza', u'Totale', u'Ultimo aggiornamento'], } wiki_save_path = wikipedia.translate(wikipedia.getSite(), wiki_save_path) @@ -87,10 +87,11 @@ ! %s ! %s ! %s +! %s |- -""" % ( msg[1], msg[2], 'Google', 'Yahoo', 'Live Search' ) +""" % ( msg[1], msg[2], msg[3], 'Google', 'Yahoo', 'Live Search' ) - gnt = 0 ; ynt = 0 ; mnt = 0 ; ent = 0 + gnt = 0 ; ynt = 0 ; mnt = 0 ; ent = 0 ; sn = 0 ; snt = 0 for page in gen: data = page.get() @@ -100,18 +101,19 @@ mn = stat_sum('(msn|live)', data) en = len(re.findall('=== \[\[', data)) + sn = len(data) - gnt += gn ; ynt += yn ; mnt += mn ; ent += en + gnt += gn ; ynt += yn ; mnt += mn ; ent += en ; snt += sn - output += u"|%s||%s||%s||%s||%s\n|-\n" % (page.aslink(), en, gn, yn, mn) + output += u"|%s||%s||%s KB||%s||%s||%s\n|-\n" % (page.aslink(), en, sn / 1024, gn, yn, mn) output += u"""| |||||||| |- -|'''%s'''||%s||%s||%s||%s +|'''%s'''||%s||%s KB||%s||%s||%s |- -|colspan="5" align=right style="background-color:#eeeeee;"|<small>''%s: %s''</small> +|colspan="6" align=right style="background-color:#eeeeee;"|<small>''%s: %s''</small> |} -""" % (msg[3], ent, gnt, ynt, mnt, msg[4], time.strftime("%d " + "%s" % (date.monthName(wikipedia.getSite().language(), time.localtime()[1])) + " %Y")) +""" % (msg[4], ent, snt / 1024, gnt, ynt, mnt, msg[5], time.strftime("%d " + "%s" % (date.monthName(wikipedia.getSite().language(), time.localtime()[1])) + " %Y")) return output

16 years, 7 months

[ pywikipediabot-Bugs-1797224 ] .categories()

by SourceForge.net

Bugs item #1797224, was opened at 2007-09-18 19:52 Message generated for change (Comment added) made by wikipedian You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1797224&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: None Group: None >Status: Closed >Resolution: Invalid Priority: 5 Private: No Submitted By: Nobody/Anonymous (nobody) Assigned to: Nobody/Anonymous (nobody) Summary: .categories() Initial Comment: This is the relevant part of code in Wikipedia.py, which gets the list of categories on a page: catNamespace = '|'.join(site.category_namespaces()) R = re.compile(r'\[\[\s*(?P<namespace>%s)\s*:\s*(?P<catName>.+?)(?:\|(?P<sortKey>.+?))?\s*\]\]' % catNamespace) for match in R.finditer(text): cat = catlib.Category(site, '%s:%s' % (match.group('namespace'), match.group('catName')), sortKey = match.group('sortKey')) result.append(cat) return result To me, it means it will also include those category commands that are inside <noinclude> or <nowiki> or are commented out (<!--) in the returned result, which should be fixed. ---------------------------------------------------------------------- >Comment By: Daniel Herding (wikipedian) Date: 2007-09-24 11:09 Message: Logged In: YES user_id=880694 Originator: NO one line above the code you pasted, there is this: # Ignore category links within nowiki tags, pre tags, includeonly tags, # and HTML comments text = removeDisabledParts(text) So I think we can close this. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1797224&group_…

16 years, 7 months

SVN: [4352] trunk/pywikipedia/wikipedia.py

by cosoleto＠svn.wikimedia.org

Revision: 4352 Author: cosoleto Date: 2007-09-24 09:07:53 +0000 (Mon, 24 Sep 2007) Log Message: ----------- bug fix in newpages(), page length was not correctly reported Modified Paths: -------------- trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-24 09:05:25 UTC (rev 4351) +++ trunk/pywikipedia/wikipedia.py 2007-09-24 09:07:53 UTC (rev 4352) @@ -3635,12 +3635,12 @@ get_throttle() html = self.getUrl(path) - entryR = re.compile('<li[^>]*>(?P<date>.+?) \S*?<a href=".+?" title="(?P<title>.+?)">.+?</a>.+?[$\[](?P<length>\d+)[^$\]]*[\)\]] .?<a href=".+?" title=".+?:(?P<username>.+?)">') + entryR = re.compile('<li[^>]*>(?P<date>.+?) \S*?<a href=".+?" title="(?P<title>.+?)">.+?</a>.+?[$\[](?P<length>[\d,.]+)[^$\]]*[\)\]] .?<a href=".+?" title=".+?:(?P<username>.+?)">') for m in entryR.finditer(html): date = m.group('date') title = m.group('title') title = title.replace('"', '"') - length = int(m.group('length')) + length = int(re.sub("[,.]", "", m.group('length'))) loggedIn = u'' username = m.group('username') comment = u''

16 years, 7 months

[ pywikipediabot-Patches-1794705 ] Fixing fallbacks in wikipedia.py for some Turkic languages

by SourceForge.net

Patches item #1794705, was opened at 2007-09-14 15:13 Message generated for change (Comment added) made by wikipedian You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1794705&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: None Group: None >Status: Closed >Resolution: Accepted Priority: 5 Private: No Submitted By: AlefZet (alefzet) Assigned to: Nobody/Anonymous (nobody) Summary: Fixing fallbacks in wikipedia.py for some Turkic languages Initial Comment: kk, ky & tt are very close each to other (Kypchak group). az, tk & tr are very close each to other (Oghuz group). ug & uz are very close each to other (Karluk group). Karluk group is some kind between Kypchak and Oghuz, but closest to Oghuz. ---------------------------------------------------------------------- >Comment By: Daniel Herding (wikipedian) Date: 2007-09-24 11:05 Message: Logged In: YES user_id=880694 Originator: NO Thanks. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1794705&group_…

16 years, 7 months

SVN: [4351] trunk/pywikipedia/wikipedia.py

by wikipedian＠svn.wikimedia.org

Revision: 4351 Author: wikipedian Date: 2007-09-24 09:05:25 +0000 (Mon, 24 Sep 2007) Log Message: ----------- applied patch [ 1794705 ] Fixing fallbacks in wikipedia.py for some Turkic languages by AlefZet Modified Paths: -------------- trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-24 09:04:17 UTC (rev 4350) +++ trunk/pywikipedia/wikipedia.py 2007-09-24 09:05:25 UTC (rev 4351) @@ -4595,13 +4595,13 @@ return ['pt'] if code in ['mo','roa-rup']: return ['ro'] - if code in ['av','bxr','cv','hy','lbe','ru-sib','tg','tt','udm','uk','xal']: + if code in ['av','bxr','cv','hy','lbe','ru-sib','tg','udm','uk','xal']: return ['ru'] if code in ['be','be-x-old']: return ['be','be-x-old','ru'] - if code in ['kk','ky','tk']: - return ['tr','ru'] - if code in ['diq','ug','uz']: + if code in ['ky','tt','uz']: + return ['kk','tr','ru'] + if code in ['az','diq','tk','ug']: return ['tr'] if code in ['ja','minnan','zh','zh-cn']: return ['zh','zh-tw','zh-classical','zh-cn']

16 years, 7 months

← Newer
1
...
5
6
7
8
9
10
11
...
40
Older →

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Pywikipedia-l September 2007