Pywikibot-commits

pywikibot-commits@lists.wikimedia.org

1 participants
13418 discussions

[Gerrit] Port disambredir.py to core - change (pywikibot/core)
by jenkins-bot (Code Review) 23 Dec '13

23 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: Port disambredir.py to core ...................................................................... Port disambredir.py to core Change-Id: If6cb976cd47675ff780f49029f5fa5277b9fd95c --- A scripts/disambredir.py 1 file changed, 184 insertions(+), 0 deletions(-) Approvals: Merlijn van Deen: Looks good to me, approved jenkins-bot: Verified diff --git a/scripts/disambredir.py b/scripts/disambredir.py new file mode 100644 index 0000000..3af5c9f --- /dev/null +++ b/scripts/disambredir.py @@ -0,0 +1,184 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- +""" +Goes through the disambiguation pages, checks their links, and asks for +each link that goes to a redirect page whether it should be replaced. +""" +# +# (C) André Engels and others, 2006-2009 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' +# +import pywikibot +from pywikibot import pagegenerators +import re +import sys +from pywikibot import catlib + +msg = { + 'ar': u'تغيير التحويلات في صفحة توضيح', + 'be-x-old': u'Замена перанакіраваньняў на старонку неадназначнасьцяў', + 'en': u'Changing redirects on a disambiguation page', + 'he': u'משנה קישורים להפניות בדף פירושונים', + 'fa': u'اصلاح تغییرمسیرها در یک صفحه ابهام‌زدایی', + 'ja': u'ロボットによる: 曖昧さ回避ページのリダイレクト修正', + 'nl': u'Verandering van redirects op een doorverwijspagina', + 'pl': u'Zmiana przekierowań na stronie ujednoznaczającej', + 'pt': u'Arrumando redirects na página de desambiguação', + 'ru': u'Изменение перенаправлений на странице неоднозначности', + 'uk': u'Зміна перенаправлень на сторінці багатозначності', + 'zh': u'機器人: 修改消歧義頁中的重定向連結', +} + + +def firstcap(string): + return string[0].upper() + string[1:] + + +def treat(text, linkedPage, targetPage): + """ + Based on the method of the same name in solve_disambiguation.py. + """ + # make a backup of the original text so we can show the changes later + linkR = re.compile(r'\[\[(?P<title>[^\]\|#]*)(?P<section>#[^\]\|]*)?(\|(?P<label>[^\]]*))?\]\](?P<linktrail>' + linktrail + ')') + curpos = 0 + # This loop will run until we have finished the current page + while True: + m = linkR.search(text, pos=curpos) + if not m: + break + # Make sure that next time around we will not find this same hit. + curpos = m.start() + 1 + # ignore interwiki links and links to sections of the same page + if m.group('title') == '' or mysite.isInterwikiLink(m.group('title')): + continue + else: + actualLinkPage = pywikibot.Page(page.site, m.group('title')) + # Check whether the link found is to page. + if actualLinkPage != linkedPage: + continue + + # how many bytes should be displayed around the current link + context = 30 + # at the beginning of the link, start red color. + # at the end of the link, reset the color to default + pywikibot.output(text[max(0, m.start() - context): m.start()] + + '\03{lightred}' + text[m.start(): m.end()] + + '\03{default}' + text[m.end(): m.end() + context]) + while True: + choice = pywikibot.input( + u"Option (N=do not change, y=change link to \03{lightpurple}%s\03{default}, r=change and replace text, u=unlink)" % targetPage.title()) + try: + choice = choice[0] + except: + choice = 'N' + if choice in 'nNyYrRuU': + break + if choice in "nN": + continue + + # The link looks like this: + # [[page_title|link_text]]trailing_chars + page_title = m.group('title') + link_text = m.group('label') + if not link_text: + # or like this: [[page_title]]trailing_chars + link_text = page_title + if m.group('section') is None: + section = '' + else: + section = m.group('section') + trailing_chars = m.group('linktrail') + if trailing_chars: + link_text += trailing_chars + + if choice in "uU": + # unlink - we remove the section if there's any + text = text[:m.start()] + link_text + text[m.end():] + continue + replaceit = choice in "rR" + + if link_text[0].isupper(): + new_page_title = targetPage.title() + else: + new_page_title = targetPage.title()[0].lower() + \ + targetPage.title()[1:] + if replaceit and trailing_chars: + newlink = "[[%s%s]]%s" % (new_page_title, section, trailing_chars) + elif replaceit or (new_page_title == link_text and not section): + newlink = "[[%s]]" % new_page_title + # check if we can create a link with trailing characters instead of a + # pipelink + elif len(new_page_title) <= len(link_text) and \ + firstcap(link_text[:len(new_page_title)]) == \ + firstcap(new_page_title) and \ + re.sub(re.compile(linktrail), '', link_text[len(new_page_title):]) == '' and not section: + newlink = "[[%s]]%s" % (link_text[:len(new_page_title)], + link_text[len(new_page_title):]) + else: + newlink = "[[%s%s|%s]]" % (new_page_title, section, link_text) + text = text[:m.start()] + newlink + text[m.end():] + continue + return text + + +def workon(page, links): + text = page.get() + # Show the title of the page we're working on. + # Highlight the title in purple. + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % page.title()) + for page2 in links: + try: + target = page2.getRedirectTarget() + except (pywikibot.Error, pywikibot.SectionError): + continue + text = treat(text, page2, target) + if text != page.get(): + comment = pywikibot.translate(mysite, msg) + page.put(text, comment) + + +def main(): + global mysite, linktrail, page + start = [] + for arg in pywikibot.handleArgs(): + start.append(arg) + if start: + start = " ".join(start) + else: + start = "!" + mysite = pywikibot.getSite() + linktrail = mysite.linktrail() + try: + generator = pagegenerators.CategorizedPageGenerator( + mysite.disambcategory(), start=start) + except pywikibot.NoPage: + pywikibot.output( + "The bot does not know the disambiguation category for your wiki.") + raise + # only work on articles + generator = pagegenerators.NamespaceFilterPageGenerator(generator, [0]) + generator = pagegenerators.PreloadingGenerator(generator) + pagestodo = [] + pagestoload = [] + for page in generator: + if page.isRedirectPage(): + continue + linked = page.linkedPages() + pagestodo.append((page, linked)) + pagestoload += linked + if len(pagestoload) > 49: + pagestoload = pagegenerators.PreloadingGenerator(pagestoload) + for page, links in pagestodo: + workon(page, links) + pagestoload = [] + pagestodo = [] + +if __name__ == "__main__": + try: + main() + finally: + pywikibot.stopme() -- To view, visit https://gerrit.wikimedia.org/r/102912 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: If6cb976cd47675ff780f49029f5fa5277b9fd95c Gerrit-PatchSet: 7 Gerrit-Project: pywikibot/core Gerrit-Branch: master Gerrit-Owner: Vldandrew <vldandrew(a)gmail.com> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: Merlijn van Deen <valhallasw(a)arctus.nl> Gerrit-Reviewer: Strainu <wiki(a)strainu.ro> Gerrit-Reviewer: Vldandrew <vldandrew(a)gmail.com> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [L10N] remove wrong templates which does not exist on target... - change (pywikibot/i18n)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [L10N] remove wrong templates which does not exist on target wikipedia ...................................................................... [L10N] remove wrong templates which does not exist on target wikipedia Change-Id: Ifab9ee9dac3f2558fc9e813f9d33e1febbe5adb7 --- M redirect.py 1 file changed, 1 insertion(+), 14 deletions(-) Approvals: Merlijn van Deen: Looks good to me, approved jenkins-bot: Verified diff --git a/redirect.py b/redirect.py index ca9c5bc..cfe3dd2 100644 --- a/redirect.py +++ b/redirect.py @@ -20,7 +20,7 @@ 'redirect-fix-broken-moved': u'Edit summary when the bot fixes a broken redirect to a moved page whose origin has been deleted.\nParameters:\n* <code>%(to)s</code>: the new redirect target, as a wiki link.', 'redirect-fix-loop': u'Edit summary when the bot fixes redirect loops. <code>%(to)s</code> displays the new redirect target as a wiki link.', 'redirect-remove-loop': u'Edit summary when the bot tags a redirect loop for speedy deletion. The internal links are to pages on the English Wikipedia, [http://en.wikipedia.org/wiki/Wikipedia:CSD#G8 here] and [http://en.wikipedia.org/wiki/Wikipedia:Redirect here]. They won\'t work anywhere except on the English Wikipedia, as they stand.', - 'redirect-broken-redirect-template': u'Template for speedy deletion of broken redirect or redirect loops which the bot tags onto the redirect page. This message may contain additional informations like template parameters or reasons for the deletion request.\n\nNOTE: If this system message is not given for a language code, speedy deletion request by a bot is not supported on your site except there is a bot with sysop flag.\n\n{{doc-important|Only use your deletion template like <code><nowiki>{{delete}}</nowiki></code> which exist on your local project.}}', + 'redirect-broken-redirect-template': u'NOTE TO TRANSLATOR: This should only be translated by someone on the Wikipedia of your language code. Thank you.\n\nTemplate for speedy deletion of broken redirect or redirect loops which the bot tags onto the redirect page. This message may contain additional informations like template parameters or reasons for the deletion request.\n\nNOTE: If this system message is not given for a language code, speedy deletion request by a bot is not supported on your site except there is a bot with sysop flag.\n\n{{doc-important|Only use your deletion template like <code><nowiki>{{delete}}</nowiki></code> which exist on your local project.}}', }, # Author: Csisc 'aeb': { @@ -28,7 +28,6 @@ 'redirect-remove-broken': u'تحويلة إلى صفحة محذوفة أو غير موجودة', 'redirect-fix-loop': u'روبوت: تعديل حلقة إعادة التوجيه إلى %(to)s', 'redirect-remove-loop': u'هدف التحويلة يصنع عقدة تحويل: Robot', - 'redirect-broken-redirect-template': u'{{شطب|تحويلة مكسورة}}', }, # Author: Naudefj # Author: Xqt @@ -37,7 +36,6 @@ 'redirect-remove-broken': u'Robot: Aanstuur na \'n geskrapte of nie-bestaande bladsy', 'redirect-fix-loop': u'Robot: sirkulêre aanstuur na %(to)s reggemaak', 'redirect-remove-loop': u'Robot: Aanstuur vorm \'n sirkulêre lus', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Als-Holder # Author: Xqt @@ -84,7 +82,6 @@ 'redirect-fix-broken-moved': u'Bot: İşləməyən yönləndirilmənin yeri dəyişdirilmiş hədəf səhifəyə %(to)s düzəldilməsi', 'redirect-fix-loop': u'Bot: Sonsuz yönləndirilmənin %(to)s düzəldilməsi', 'redirect-remove-loop': u'Bot: Yönləndirilmə sonsuz yönləndirilmə formalaşdırır', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Amir a57 # Author: E THP @@ -93,7 +90,6 @@ 'redirect-remove-broken': u'[[ویکی‌پئدییا:سیل#یستیقامتلندیرمه|وپ:سیل]]: سیلینئن یا دا وار اولمایان صحیفه‌یه اولان ایستیقامیلندیرمه', 'redirect-fix-loop': u'روبوت: فیخینگ اوزوک اولان%(to)s یؤنلن‌دیرن', 'redirect-remove-loop': u'بوت: ایستیقامتلندیرمه هدفی بیر ایستیقامتلندیرمه دؤورو تشکیل ائدیر', - 'redirect-broken-redirect-template': u'{{سیل|y1}}', }, # Author: Haqmar # Author: Sagan @@ -102,7 +98,6 @@ 'redirect-remove-broken': u'Робот: булмаған йәки юйылған биткә йүнәлтеү', 'redirect-fix-loop': u'Робот: %(to)s битенә йүнәлтеүҙе төҙәтеү', 'redirect-remove-loop': u'Робот: бер ҡайҙа ла йүнәлтелмәгән', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Mucalexx # Author: Xqt @@ -114,10 +109,6 @@ }, 'bat-smg': { 'redirect-fix-double': u'Robots: Taisuoms dvėgobs paradresavėms → %(to)s', - }, - # Author: Stephensuleeman - 'bbc-latn': { - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: EugeneZelenko # Author: Jim-by @@ -140,7 +131,6 @@ 'redirect-fix-double': u'Robot: Pamasangan paugahan ganda ka %(to)s', 'redirect-remove-broken': u'[[WP:CSD#G8|G8]]: [[Wikipedia:Redirect|Paalihan]] ka tungkaran nang dihapus atawa kada ada', 'redirect-remove-loop': u'[[WP:CSD#G8|G8]]: Bidikan [[Wikipedia:Redirect|paalihan]] mahasilakan paalihan siklik', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Wikitanvir 'bn': { @@ -156,7 +146,6 @@ 'redirect-fix-broken-moved': u'Robot : O reizhañ an adkasoù torret war-zu ar bajenn bal %(to)s', 'redirect-fix-loop': u'Robot : O kempenn al lagadenn adkas war-zu %(to)s', 'redirect-remove-loop': u'Robot: Stumm ur c\'helc\'h-tro born zo gant an [[Wikipedia:Redirect|adkas]]', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: CERminator # Author: Edinwiki @@ -208,7 +197,6 @@ 'redirect-fix-double': u'Bot: Yn trwsio ailgyfeiriad dwbl i %(to)s', 'redirect-remove-broken': u'Bot: Yn ailgyfeirio i dudalen a ddilëwyd neu nad yw ar gael', 'redirect-remove-loop': u'Bot: Mae nod yr ailgyfeiriad yn ffurfio dolen ailgyfeirio', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Christian List # Author: Kaare @@ -389,7 +377,6 @@ 'redirect-fix-broken-moved': u'機械人：修復損壞个重定向頁到移動目標頁面 %(to)s', 'redirect-fix-loop': u'機械人：修復重定向迴圈至%(to)s', 'redirect-remove-loop': u'機械人：重定向目標構成循環', - 'redirect-broken-redirect-template': u'{{db-r1}}', }, # Author: Amire80 # Author: YaronSh -- To view, visit https://gerrit.wikimedia.org/r/102071 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ifab9ee9dac3f2558fc9e813f9d33e1febbe5adb7 Gerrit-PatchSet: 2 Gerrit-Project: pywikibot/i18n Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Merlijn van Deen <valhallasw(a)arctus.nl> Gerrit-Reviewer: Siebrand <siebrand(a)wikimedia.org> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] changes, code improvements, insert __version__ string - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes, code improvements, insert __version__ string ...................................................................... [PEP8] changes, code improvements, insert __version__ string Change-Id: Icff281c4d659d40a527eeecac12de17afaef8201 --- M data_ingestion.py 1 file changed, 80 insertions(+), 51 deletions(-) Approvals: Merlijn van Deen: Looks good to me, approved jenkins-bot: Verified diff --git a/data_ingestion.py b/data_ingestion.py index f5c8f3d..4098399 100644 --- a/data_ingestion.py +++ b/data_ingestion.py @@ -1,69 +1,85 @@ #!/usr/bin/python # -*- coding: utf-8 -*- -''' +""" A generic bot to do data ingestion (batch uploading) to Commons -''' -import pywikibot, upload -import posixpath, urlparse +""" +# +# (C) Pywikibot team, 2011-2013 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' +# + +import posixpath +import urlparse import urllib -import hashlib, base64 +import hashlib +import base64 import StringIO try: import json except ImportError: import simplejson as json +import pywikibot +import upload + class Photo(object): - ''' + """ Represents a Photo (or other file), with metadata, to upload to Commons. The constructor takes two parameters: URL (string) and metadata (dict with str:str key:value pairs) that can be referred to from the title & template generation. - - ''' + """ def __init__(self, URL, metadata): self.URL = URL self.metadata = metadata self.metadata["_url"] = URL - self.metadata["_filename"] = filename = posixpath.split(urlparse.urlparse(URL)[2])[1] + self.metadata["_filename"] = filename = posixpath.split( + urlparse.urlparse(URL)[2])[1] self.metadata["_ext"] = ext = filename.split(".")[-1] if ext == filename: self.metadata["_ext"] = ext = None self.contents = None def downloadPhoto(self): - ''' + """ Download the photo and store it in a StringIO.StringIO object. TODO: Add exception handling - ''' + + """ if not self.contents: - imageFile=urllib.urlopen(self.URL).read() + imageFile = urllib.urlopen(self.URL).read() self.contents = StringIO.StringIO(imageFile) return self.contents - def findDuplicateImages(self, site = pywikibot.getSite(u'commons', u'commons')): - ''' - Takes the photo, calculates the SHA1 hash and asks the mediawiki api for a list of duplicates. + def findDuplicateImages(self, + site=pywikibot.getSite(u'commons', u'commons')): + """ + Takes the photo, calculates the SHA1 hash and asks the mediawiki api + for a list of duplicates. TODO: Add exception handling, fix site thing - ''' + + """ hashObject = hashlib.sha1() hashObject.update(self.downloadPhoto().getvalue()) return site.getFilesFromAnHash(base64.b16encode(hashObject.digest())) def getTitle(self, fmt): """ - Given a format string with %(name)s entries, returns the string formatted with metadata + Given a format string with %(name)s entries, returns the string + formatted with metadata + """ return fmt % self.metadata def getDescription(self, template, extraparams={}): - ''' - Generate a description for a file - ''' + """ Generate a description for a file """ params = {} params.update(self.metadata) @@ -72,13 +88,15 @@ for key in sorted(params.keys()): value = params[key] if not key.startswith("_"): - description = description + (u'|%s=%s' % (key, self._safeTemplateValue(value))) + "\n" - description = description + u'}}' + description += (u'|%s=%s' + % (key, self._safeTemplateValue(value))) + "\n" + description += u'}}' return description def _safeTemplateValue(self, value): return value.replace("|", "{{!}}") + def CSVReader(fileobj, urlcolumn, *args, **kwargs): import csv @@ -88,30 +106,35 @@ yield Photo(line[urlcolumn], line) -def JSONReader(baseurl, start=0, end=100, JSONBase=None, metadataFunction=None, fileurl=u'fileurl'): - ''' +def JSONReader(baseurl, start=0, end=100, JSONBase=None, metadataFunction=None, + fileurl=u'fileurl'): + """ Loops over a bunch of json page and process them with processJSONPage(). Will yield Photo objects with metadata - ''' + + """ if baseurl: - for i in range(start , end): + for i in range(start, end): url = baseurl % (i,) - photo = processJSONPage(url, JSONBase=JSONBase, metadataFunction=metadataFunction, fileurl=u'fileurl') + photo = processJSONPage(url, JSONBase=JSONBase, + metadataFunction=metadataFunction, + fileurl=u'fileurl') if photo: yield photo - -def processJSONPage(url, JSONBase=None, metadataFunction=None, fileurl=u'fileurl'): - ''' +def processJSONPage(url, JSONBase=None, metadataFunction=None, + fileurl=u'fileurl'): + """ Process a single JSON page. For the JSON page you can rebase it to not get all the crap You can apply a custom metadata function to do some modification on the metadata and checking By default the field 'fileurl' is expected in the metadata to contain the file. You can change this. Will a return Photo object with metadata or None if something is wrong - ''' + + """ JSONPage = urllib.urlopen(url) JSONData = json.load(JSONPage) JSONPage.close() @@ -130,17 +153,20 @@ if metadataFunction: metadata = metadataFunction(metadata) - # If the metadataFunction didn't return none (something was wrong). Return the photo + # If the metadataFunction didn't return none (something was wrong). + # Return the photo if metadata: return Photo(metadata.get(fileurl), metadata) - return False + def JSONRebase(JSONData, JSONBase): - ''' + """ Moves the base of the JSON object to the part you're intrested in. - JSONBase is a list to crawl the tree. If one of the steps is not found, return None - ''' + JSONBase is a list to crawl the tree. If one of the steps is not found, + return None + + """ for step in JSONBase: if JSONData: if type(JSONData) == dict: @@ -148,21 +174,20 @@ elif type(JSONData) == list: # FIXME: Needs error, length etc checking JSONData = JSONData[step] - return JSONData def JSONTree(metadata, fieldlist, record): - ''' + """ metadata: Dict with end result key: The key we encountered record: Record to work on - ''' + """ if type(record) == list: for r in record: metadata = JSONTree(metadata, fieldlist, r) elif type(record) == dict: - for k,v in record.items(): + for k, v in record.items(): metadata = JSONTree(metadata, fieldlist + [k], v) elif type(record) == unicode: key = u'_'.join(fieldlist) @@ -172,11 +197,13 @@ newkey = key + u'_2' if not newkey in metadata: metadata[newkey] = record - return metadata + class DataIngestionBot: - def __init__(self, reader, titlefmt, pagefmt, site=pywikibot.getSite(u'commons', u'commons')): + + def __init__(self, reader, titlefmt, pagefmt, + site=pywikibot.getSite(u'commons', u'commons')): self.reader = reader self.titlefmt = titlefmt self.pagefmt = pagefmt @@ -190,17 +217,16 @@ title = photo.getTitle(self.titlefmt) description = photo.getDescription(self.pagefmt) - bot = upload.UploadRobot(url = photo.URL, - description = description, - useFilename = title, - keepFilename = True, - verifyDescription = False, + bot = upload.UploadRobot(url=photo.URL, + description=description, + useFilename=title, + keepFilename=True, + verifyDescription=False, ignoreWarning=True, - targetSite = self.site) + targetSite=self.site) bot._contents = photo.downloadPhoto().getvalue() bot._retrieved = True bot.run() - return title def doSingle(self): @@ -210,9 +236,12 @@ for photo in self.reader: self._doUpload(photo) -if __name__=="__main__": + +if __name__ == "__main__": reader = CSVReader(open('tests/data/csv_ingestion.csv'), 'url') - bot = DataIngestionBot(reader, "%(name)s - %(set)s.%(_ext)s", ":user:valhallasw/test_template", pywikibot.getSite('test', 'test')) + bot = DataIngestionBot(reader, "%(name)s - %(set)s.%(_ext)s", + ":user:valhallasw/test_template", + pywikibot.getSite('test', 'test')) bot.run() """ -- To view, visit https://gerrit.wikimedia.org/r/103252 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Icff281c4d659d40a527eeecac12de17afaef8201 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: Merlijn van Deen <valhallasw(a)arctus.nl> Gerrit-Reviewer: Multichill <maarten(a)mdammers.nl> Gerrit-Reviewer: jenkins-bot Gerrit-Reviewer: saper <saper(a)saper.info>

1 0

[Gerrit] [PEP8] changes - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes ...................................................................... [PEP8] changes Change-Id: I0562f6b814e4d83f5094d4cd851354cb86aee493 --- M daemonize.py 1 file changed, 4 insertions(+), 2 deletions(-) Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified diff --git a/daemonize.py b/daemonize.py index 121d3a3..0eb9ffb 100644 --- a/daemonize.py +++ b/daemonize.py @@ -1,16 +1,18 @@ # -*- coding: utf-8 -*- # -# (C) Pywikipedia bot team, 2007-2008, 2010 +# (C) Pywikibot team, 2007-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' # -import sys, os +import sys +import os is_daemon = False + def daemonize(close_fd=True, chdir=True, write_pid=False, redirect_std=None): """ Daemonize the current process. Only works on POSIX compatible operating systems. The process will fork to the background and return control to -- To view, visit https://gerrit.wikimedia.org/r/103250 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I0562f6b814e4d83f5094d4cd851354cb86aee493 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: Xqt <info(a)gno.de> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] changes, remove obsolete imports - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes, remove obsolete imports ...................................................................... [PEP8] changes, remove obsolete imports Change-Id: I48520186905bb209e43a875f575529e4cc71ae5b --- M create_categories.py 1 file changed, 9 insertions(+), 16 deletions(-) Approvals: Ladsgroup: Looks good to me, approved jenkins-bot: Verified diff --git a/create_categories.py b/create_categories.py index 32cada1..0a73ac4 100644 --- a/create_categories.py +++ b/create_categories.py @@ -24,22 +24,17 @@ -basename:"Cultural heritage monuments in" """ -__version__ = '$Id$' # # (C) Multichill, 2011 -# (C) xqt, 2011 +# (C) xqt, 2011-2013 # # Distributed under the terms of the MIT license. # +__version__ = '$Id$' # -import os, sys, re, codecs -import urllib, httplib, urllib2 -import catlib -import time -import socket -import StringIO -import wikipedia as pywikibot -import config + +import sys +import pywikibot import pagegenerators @@ -62,13 +57,11 @@ newpage.put(newtext, comment) else: #FIXME: Add overwrite option - pywikibot.output(u'%s already exists, skipping' % (newpage.title(),)) + pywikibot.output(u'%s already exists, skipping' % newpage.title()) def main(args): - ''' - Main loop. Get a generator and options. - ''' + """ Main loop. Get a generator and options. """ generator = None parent = u'' basename = u'' @@ -80,9 +73,9 @@ if arg == '-always': always = True elif arg.startswith('-parent:'): - parent = arg [len('-parent:'):].strip() + parent = arg[len('-parent:'):].strip() elif arg.startswith('-basename'): - basename = arg [len('-basename:'):].strip() + basename = arg[len('-basename:'):].strip() else: genFactory.handleArg(arg) -- To view, visit https://gerrit.wikimedia.org/r/103248 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I48520186905bb209e43a875f575529e4cc71ae5b Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: Multichill <maarten(a)mdammers.nl> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] changes, insert __version__ id - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes, insert __version__ id ...................................................................... [PEP8] changes, insert __version__ id Change-Id: Iab25774e256c0cfdd7ff1446ce5445320c6ed2fe --- M logindata.py 1 file changed, 25 insertions(+), 19 deletions(-) Approvals: Ladsgroup: Looks good to me, approved jenkins-bot: Verified diff --git a/logindata.py b/logindata.py index 152163b..7072354 100644 --- a/logindata.py +++ b/logindata.py @@ -1,31 +1,37 @@ # -*- coding: utf-8 -*- +""" +Usable example module: Use of pywikipedia as a +library. -# Usable example module: Use of pywikipedia as a -# library. -# -# Looks up the path to pywikipedia (pywikipedia_path) -# in a settings.py file. You'll need to provide that, -# and/or refactor. - +Looks up the path to pywikipedia (pywikipedia_path) +in a settings.py file. You'll need to provide that, +and/or refactor. +""" # (C) Kim Bruning for Wikiation, sponsored by Kennisnet, 2009 +# (C) Pywikipedia bot team, 2009-2013 # # Distributed under the terms of the MIT license. # +__version__ = '$Id$' +# -import sys, os +import sys +import os import settings + if settings.pywikipedia_path not in sys.path: sys.path.append(settings.pywikipedia_path) # pywikipedia can only set itself up if everything is # done in its own directory. This needs fixing sometime. # for now, we live with it. -cwd=os.getcwd() +cwd = os.getcwd() os.chdir(settings.pywikipedia_path) import wikipedia as pywikibot import login from simple_family import Family os.chdir(cwd) + class LoginData: """An example class that uses pywikipedia as a library. @@ -50,7 +56,7 @@ password='MY_SECRET_PASSWORD', RversionTab=None, api_supported=False - ): + ): """ paramaters: name: arbitrary name. Pick something easy to remember @@ -67,10 +73,10 @@ password: password for this user """ - self.lang=lang - self.user=user - self.password=password - self.family=base_family.Family( + self.lang = lang + self.user = user + self.password = password + self.family = base_family.Family( name=name, protocol=protocol, server=server, @@ -80,20 +86,20 @@ encoding=encoding, RversionTab=RversionTab, api_supported=api_supported) - self.site=None + self.site = None def login(self): """Attempt to log in on the site described by this class. Returns a pywikipedia site object""" - self.site=pywikibot.Site( + self.site = pywikibot.Site( code=self.lang, fam=self.family, user=self.user - ) - loginManager=login.LoginManager( + ) + loginManager = login.LoginManager( password=self.password, site=self.site, username=self.user - ) + ) loginManager.login() return self.site -- To view, visit https://gerrit.wikimedia.org/r/103235 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Iab25774e256c0cfdd7ff1446ce5445320c6ed2fe Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] changes, do not override standard object identifier - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes, do not override standard object identifier ...................................................................... [PEP8] changes, do not override standard object identifier Change-Id: Ie975c1e7d3d18224eb42ad9a4796ab01e6cad8cc --- M saveHTML.py 1 file changed, 60 insertions(+), 46 deletions(-) Approvals: Ladsgroup: Looks good to me, approved jenkins-bot: Verified diff --git a/saveHTML.py b/saveHTML.py index eb2b3fc..ef2e99c 100644 --- a/saveHTML.py +++ b/saveHTML.py @@ -23,15 +23,22 @@ """ # (C) 2004 Thomas R. Koll, <tomk32(a)tomk32.de> -# (C) Pywikipedia bot team, 2004-2011 +# (C) Pywikibot team, 2004-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' -import httplib, StringIO, re, sys, md5, os, string -import wikipedia as pywikibot +import httplib +import StringIO +import re +import sys +import md5 +import os +import string +import pywikibot from htmlentitydefs import * + def extractArticle(data): """ takes a string with the complete HTML-file @@ -41,7 +48,8 @@ images = [] s = StringIO.StringIO(data) - rPagestats = re.compile('.*(\<span id\=(\"|\')pagestats(\"|\')\>.*\<\/span\>).*') + rPagestats = re.compile( + '.*(\<span id\=(\"|\')pagestats(\"|\')\>.*\<\/span\>).*') rBody = re.compile('.*<div id\=\"content\">.*') rFooter = re.compile('.*<div id\=\"footer\">.*') rDivOpen = re.compile('.*<div ') @@ -49,9 +57,9 @@ divLevel = 1 divLast = -1 inArticle = 0 - inFooter = 0 - result = {'article':"", - 'footer':""} + inFooter = 0 + result = {'article': "", + 'footer': ""} for line in s: if line == "<p><br /></p>": continue @@ -65,7 +73,7 @@ divLast = divLevel-2 elif rFooter.match(line): divLast = divLevel-1 - inFooter = 1 + inFooter = 1 if inArticle: result['article'] += line elif inFooter: @@ -76,27 +84,27 @@ inArticle = 0 inFooter = 0 divLast = -1 - - return result -def html2txt(str): - dict = {"%C3%A4": "ä", - "%C3%B6": "ö", - "%C3%BC": "ü", - "%C3%84": "Ä", - "%C3%96": "Ö", - "%C3%9C": "Ü", - "%C3%9F": "ß", - "%27": "'", - "%28": "(", - "%29": ")", - "%2C": "," - } - for entry in dict: - str = re.sub(entry, dict[entry], str) - return str +def html2txt(s): + d = {"%C3%A4": "ä", + "%C3%B6": "ö", + "%C3%BC": "ü", + "%C3%84": "Ä", + "%C3%96": "Ö", + "%C3%9C": "Ü", + "%C3%9F": "ß", + "%27": "'", + "%28": "(", + "%29": ")", + "%2C": "," + } + + for entry in d: + s = re.sub(entry, dict[entry], s) + return s + def extractImages(data): """ takes a string with the complete HTML-file @@ -105,8 +113,12 @@ contain information on last change """ images = [] - rImage = re.compile('<a href=[\r\n]*?"/wiki/.*?:(.*?)".*?[\r\n]*?.*?class=[\r\n]*?"image"', re.MULTILINE) - rThumb = re.compile('<a href=[\r\n]*?"/wiki/.*?:(.*?)".*?[\r\n]*?.*?class=[\r\n]*?"internal".*?[\r\n]*?.*?<img', re.MULTILINE or re.DOTALL) + rImage = re.compile( + '<a href=[\r\n]*?"/wiki/.*?:(.*?)".*?[\r\n]*?.*?class=[\r\n]*?"image"', + re.MULTILINE) + rThumb = re.compile( + '<a href=[\r\n]*?"/wiki/.*?:(.*?)".*?[\r\n]*?.*?class=[\r\n]*?"internal".*?[\r\n]*?.*?<img', + re.MULTILINE or re.DOTALL) last = "" img = rImage.findall(data) timg = rThumb.findall(data) @@ -119,8 +131,8 @@ for image in img: path = md5.new(html2txt(image)).hexdigest() - images.append( {'image': image, - 'path' : str(path[0])+"/"+str(path[0:2])+"/"}) + images.append({'image': image, + 'path': str(path[0]) + "/" + str(path[0:2]) + "/"}) images.sort() return images @@ -137,16 +149,16 @@ if arg.startswith("-lang:"): lang = arg[6:] elif arg.startswith("-file:"): - f=open(arg[6:], 'r') - R=re.compile(r'.*\[\[([^\]]*)\]\].*') + f = open(arg[6:], 'r') + R = re.compile(r'.*\[\[([^\]]*)\]\].*') m = False for line in f.readlines(): - m=R.match(line) + m = R.match(line) if m: sa.append(string.replace(m.group(1), " ", "_")) else: - print "ERROR: Did not understand %s line:\n%s" % ( - arg[6:], repr(line)) + print("ERROR: Did not understand %s line:\n%s" + % arg[6:], repr(line)) f.close() elif arg.startswith("-o:"): output_directory = arg[3:] @@ -173,13 +185,14 @@ data = "" for article in sa: filename = article.replace("/", "_") - if os.path.isfile(output_directory + filename + ".txt") and overwrite_articles == False: + if not overwrite_articles and os.path.isfile( + output_directory + filename + ".txt"): print "skipping " + article continue data = "" ua = article while len(data) < 2: - url = '/wiki/'+ ua + url = '/wiki/' + ua conn.request("GET", url, "", headers) response = conn.getresponse() data = response.read() @@ -190,29 +203,29 @@ print ua data = extractArticle(data) - f = open (output_directory + filename + ".txt", 'w') - f.write (data['article'] + '\n' + data['footer']) + f = open(output_directory + filename + ".txt", 'w') + f.write(data['article'] + '\n' + data['footer']) f.close() print "saved " + article if save_images: images = extractImages(data['article']) for i in images: - if overwrite_images == False and os.path.isfile(output_directory + i['image']): + if not overwrite_images and os.path.isfile( + output_directory + i['image']): print "skipping existing " + i['image'] continue print 'downloading ' + i['image'], uo = pywikibot.MyURLopener - file = uo.open( "http://upload.wikimedia.org/wikipedia/" - +mysite.lang + '/' + i['path'] + i['image']) + file = uo.open("http://upload.wikimedia.org/wikipedia/" + + mysite.lang + '/' + i['path'] + i['image']) content = file.read() - if (len(content) < 500): + if len(content) < 500: uo.close() print "downloading from commons", uo = pywikibot.MyURLopener - file = uo.open( "http://commons.wikimedia.org/upload/" - + i['path'] + i['image']) - #print "http://commons.wikimedia.org/upload/", i['path'] , i['image'], file + file = uo.open("http://commons.wikimedia.org/upload/" + + i['path'] + i['image']) content = file.read() f = open(output_directory + i['image'], "wb") f.write(content) @@ -220,5 +233,6 @@ print "\t\t", (len(content)/1024), "KB done" conn.close() + if __name__ == "__main__": main() -- To view, visit https://gerrit.wikimedia.org/r/103211 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ie975c1e7d3d18224eb42ad9a4796ab01e6cad8cc Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Alex S.H. Lin <alexsh(a)mail2000.com.tw> Gerrit-Reviewer: Andre Engels <andreengels(a)gmail.com> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: Siebrand <siebrand(a)wikimedia.org> Gerrit-Reviewer: jenkins-bot

1 0

[Gerrit] [PEP8] changes - change (pywikibot/compat)
by Xqt (Code Review) 22 Dec '13

22 Dec '13

Xqt has submitted this change and it was merged. Change subject: [PEP8] changes ...................................................................... [PEP8] changes Change-Id: I09610572778d1f8864bca0f9b8fa3b09e6cf0be3 --- M copyright_put.py 1 file changed, 2 insertions(+), 3 deletions(-) Approvals: Xqt: Looks good to me, approved diff --git a/copyright_put.py b/copyright_put.py index 7141642..cfefab8 100644 --- a/copyright_put.py +++ b/copyright_put.py @@ -234,9 +234,8 @@ if m: m_end = re.search(separatorC, wikitext[m.end():]) if m_end: - wikitext = wikitext[ - :m_end.start() + m.end()] + output_data + wikitext[ - m_end.start() + m.end():] + wikitext = (wikitext[:m_end.start() + m.end()] + + output_data + wikitext[m_end.start() + m.end():]) else: wikitext += '\n' + output_data else: -- To view, visit https://gerrit.wikimedia.org/r/103247 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I09610572778d1f8864bca0f9b8fa3b09e6cf0be3 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] changes - change (pywikibot/compat)
by Xqt (Code Review) 22 Dec '13

22 Dec '13

Xqt has submitted this change and it was merged. Change subject: [PEP8] changes ...................................................................... [PEP8] changes Change-Id: Ie759c4d8253e270e8ad7071a23a4eff4dd56f6ed --- M misspelling.py M ndashredir.py M nowcommons.py M statistics_in_wikitable.py 4 files changed, 75 insertions(+), 56 deletions(-) Approvals: Xqt: Looks good to me, approved diff --git a/misspelling.py b/misspelling.py index 8c891c3..287b4b4 100644 --- a/misspelling.py +++ b/misspelling.py @@ -20,14 +20,16 @@ -main only check pages in the main namespace, not in the talk, wikipedia, user, etc. namespaces. """ -__version__ = '$Id$' # (C) Daniel Herding, 2007 -# (C) Pywikipedia bot team 2007-2013 +# (C) Pywikibot team, 2007-2013 # # Distributed under the terms of the MIT license. +# +__version__ = '$Id$' +# -import wikipedia as pywikibot +import pywikibot import catlib import pagegenerators as pg import solve_disambiguation @@ -73,7 +75,8 @@ def createPageGenerator(self, firstPageTitle): if pywikibot.getSite().lang in self.misspellingCategory: - misspellingCategoryTitle = self.misspellingCategory[pywikibot.getSite().lang] + misspellingCategoryTitle = self.misspellingCategory[ + pywikibot.getSite().lang] misspellingCategory = catlib.Category(pywikibot.getSite(), misspellingCategoryTitle) generator = pg.CategorizedPageGenerator(misspellingCategory, @@ -81,14 +84,16 @@ start=firstPageTitle) else: misspellingTemplateName = 'Template:%s' \ - % self.misspellingTemplate[pywikibot.getSite().lang] + % self.misspellingTemplate[ + pywikibot.getSite().lang] misspellingTemplate = pywikibot.Page(pywikibot.getSite(), misspellingTemplateName) generator = pg.ReferringPageGenerator(misspellingTemplate, onlyTemplateInclusion=True) if firstPageTitle: pywikibot.output( - u'-start parameter unsupported on this wiki because there is no category for misspellings.') + u'-start parameter unsupported on this wiki because there ' + u'is no category for misspellings.') preloadingGen = pg.PreloadingGenerator(generator) return preloadingGen @@ -119,8 +124,8 @@ dn=False): # TODO: setSummaryMessage() in solve_disambiguation now has parameters # new_targets and unlink. Make use of these here. - comment = pywikibot.translate(self.mysite, self.msg) \ - % disambPage.title() + comment = pywikibot.translate( + self.mysite, self.msg) % disambPage.title() pywikibot.setAction(comment) @@ -146,6 +151,7 @@ bot = MisspellingRobot(always, firstPageTitle, main_only) bot.run() + if __name__ == "__main__": try: main() diff --git a/ndashredir.py b/ndashredir.py index 61759ea..4ffed75 100644 --- a/ndashredir.py +++ b/ndashredir.py @@ -40,31 +40,35 @@ """ # -# (C) Bináris, 2012 +# (c) Bináris, 2012 +# (c) pywikibot team, 2012-2013 # # Distributed under the terms of the MIT license. # -__version__='$Id$' +__version__ = '$Id$' +# -import codecs, re -import wikipedia as pywikibot +import codecs +import re +import pywikibot from pagegenerators import RegexFilterPageGenerator as RPG from pywikibot import i18n + def main(*args): - regex = ur'.*[–—]' # Alt 0150 (n dash), alt 0151 (m dash), respectively. + regex = ur'.*[–—]' # Alt 0150 (n dash), alt 0151 (m dash), respectively. ns = 0 start = '!' - filename = None # The name of the file to save titles - titlefile = None # The file object itself - ignorefilename = None # The name of the ignore file - ignorelist = [] # A list to ignore titles that redirect to somewhere else + filename = None # The name of the file to save titles + titlefile = None # The file object itself + ignorefilename = None # The name of the ignore file + ignorelist = [] # A list to ignore titles that redirect to somewhere else # Handling parameters: for arg in pywikibot.handleArgs(*args): if arg == '-start': start = pywikibot.input( - u'From which title do you want to continue?') + u'From which title do you want to continue?') elif arg.startswith('-start:'): start = arg[7:] elif arg in ['-ns', '-namespace']: @@ -98,42 +102,42 @@ ignorelist = re.findall(ur'\[\[:?(.*?)\]\]', igfile.read()) igfile.close() except IOError: - pywikibot.output("%s cannot be opened for reading." % ignorefilename) + pywikibot.output("%s cannot be opened for reading." + % ignorefilename) return # Ready to initialize site = pywikibot.getSite() redirword = site.redirect() gen = RPG(site.allpages( - start=start, namespace=ns, includeredirects=False), [regex]) + start=start, namespace=ns, includeredirects=False), [regex]) # Processing: for page in gen: title = page.title() editSummary = i18n.twtranslate(site, 'ndashredir-create', {'title': title}) - newtitle = title.replace(u'–','-').replace(u'—','-') + newtitle = title.replace(u'–', '-').replace(u'—', '-') # n dash -> hyphen, m dash -> hyphen, respectively redirpage = pywikibot.Page(site, newtitle) if redirpage.exists(): if redirpage.isRedirectPage() and \ - redirpage.getRedirectTarget() == page: - pywikibot.output( - u'[[%s]] already redirects to [[%s]], nothing to do with it.' - % (newtitle, title)) + redirpage.getRedirectTarget() == page: + pywikibot.output(u'[[%s]] already redirects to [[%s]], nothing ' + u'to do with it.' % (newtitle, title)) elif newtitle in ignorelist: pywikibot.output( u'Skipping [[%s]] because it is on your ignore list.' % newtitle) else: pywikibot.output( - (u'\03{lightyellow}Skipping [[%s]] because it exists ' - u'already with a different content.\03{default}') + u'\03{lightyellow}Skipping [[%s]] because it exists ' + u'already with a different content.\03{default}' % newtitle) if titlefile: - s = u'\n#%s does not redirect to %s.' %\ - (redirpage.title(asLink=True, textlink=True), - page.title(asLink=True, textlink=True)) + s = u'\n#%s does not redirect to %s.' % ( + redirpage.title(asLink=True, textlink=True), + page.title(asLink=True, textlink=True)) # For the unlikely case if someone wants to run it in # file namespace. titlefile.write(s) @@ -154,7 +158,8 @@ # RegexFilterPageGenerator or throttle.py or anything else and cannot # be catched in this loop.) if titlefile: - titlefile.close() # For the spirit of programming (it was flushed) + titlefile.close() # For the spirit of programming (it was flushed) + if __name__ == "__main__": try: diff --git a/nowcommons.py b/nowcommons.py index fe54bad..e06a0c2 100644 --- a/nowcommons.py +++ b/nowcommons.py @@ -48,16 +48,19 @@ # # (C) Wikipedian, 2006-2007 # (C) Siebrand Mazeland, 2007-2008 -# (C) xqt, 2010-2012 -# (C) Pywikipedia bot team, 2006-2013 +# (C) xqt, 2010-2013 +# (C) Pywikibot team, 2006-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' # -import sys, re, webbrowser, urllib -import wikipedia as pywikibot +import sys +import re +import webbrowser +import urllib +import pywikibot import pagegenerators as pg import image # only for nowCommonsMessage @@ -119,7 +122,7 @@ 'it': [ u'NowCommons', ], - 'ja':[ + 'ja': [ u'NowCommons', ], 'ko': [ @@ -128,7 +131,7 @@ u'공용 중복', u'Nowcommons', ], - 'nds-nl' : [ + 'nds-nl': [ u'NoenCommons', u'NowCommons', ], @@ -152,7 +155,7 @@ u'Перенесено на Викисклад', u'На Викискладе', ], - 'zh':[ + 'zh': [ u'NowCommons', u'Nowcommons', u'NCT', @@ -175,7 +178,7 @@ word_to_skip = { 'en': [], 'it': ['stemma', 'stub', 'hill40 '], - } +} #nowCommonsMessage = imagetransfer.nowCommonsMessage @@ -200,7 +203,7 @@ images_processed = list() while 1: url = 'http://toolserver.org/~multichill/nowcommons.php?language=%s&page=%s&filter=' % (lang, num_page) - HTML_text = self.site.getUrl(url, no_hostname = True) + HTML_text = self.site.getUrl(url, no_hostname=True) reg = r'<[Aa] href="(?P<urllocal>.*?)">(?P<imagelocal>.*?)</[Aa]> +?</td><td>\n\s*?' reg += r'<[Aa] href="(?P<urlcommons>http://commons.wikimedia.org/.*?)">Image:(?P<imagecommons>.*?)</[Aa]> +?</td><td>' regex = re.compile(reg, re.UNICODE) @@ -309,7 +312,7 @@ for page in self.getPageGenerator(): if use_hash: # Page -> Has the namespace | commons image -> Not - images_list = page # 0 -> local image, 1 -> commons image + images_list = page # 0 -> local image, 1 -> commons image page = pywikibot.Page(self.site, images_list[0]) else: # If use_hash is true, we have already print this before, no need @@ -345,7 +348,7 @@ u'\"\03{lightred}%s\03{default}\" is still used in %i pages.' % (localImagePage.title(withNamespace=False), len(usingPages))) - if replace == True: + if replace: pywikibot.output( u'Replacing \"\03{lightred}%s\03{default}\" by \"\03{lightgreen}%s\03{default}\".' % (localImagePage.title(withNamespace=False), @@ -358,9 +361,10 @@ oImageRobot.run() # If the image is used with the urlname the # previous function won't work - if len(list(pywikibot.ImagePage(self.site, - page.title()).usingPages())) > 0 and \ - replaceloose: + if len(list(pywikibot.ImagePage( + self.site, + page.title()).usingPages())) > 0 and \ + replaceloose: oImageRobot = image.ImageRobot( pg.FileLinksGenerator( localImagePage), @@ -377,7 +381,9 @@ if usingPages > 0 and use_hash: # just an enter pywikibot.input( - u'There are still %s pages with this image, confirm the manual removal from them please.' + u'There are still %s pages with this ' + u'image, confirm the manual removal ' + u'from them please.' % usingPages) else: @@ -388,15 +394,17 @@ u'No page is using \"\03{lightgreen}%s\03{default}\" anymore.' % localImagePage.title(withNamespace=False)) commonsText = commonsImagePage.get() - if replaceonly == False: + if not replaceonly: if md5 == commonsImagePage.getFileMd5Sum(): pywikibot.output( u'The image is identical to the one on Commons.') - if len(localImagePage.getFileVersionHistory()) > 1 and not use_hash: - pywikibot.output( - u"This image has a version history. Please delete it manually after making sure that the old versions are not worth keeping.""") + if len(localImagePage.getFileVersionHistory()) > 1 and \ + not use_hash: + pywikibot.output(u""" +This image has a version history. Please delete it manually after +making sure that the old versions are not worth keeping.""") continue - if autonomous == False: + if not autonomous: pywikibot.output( u'\n\n>>>> Description on \03{lightpurple}%s\03{default} <<<<\n' % page.title()) @@ -406,17 +414,17 @@ % commonsImagePage.title()) pywikibot.output(commonsText) choice = pywikibot.inputChoice( -u'Does the description on Commons contain all required source and license\n' - u'information?', + u'Does the description on Commons contain all ' + u'required source and license\ninformation?', ['yes', 'no'], ['y', 'N'], 'N') if choice.lower() in ['y', 'yes']: localImagePage.delete( comment + ' [[:commons:Image:%s]]' - % filenameOnCommons, prompt = False) + % filenameOnCommons, prompt=False) else: localImagePage.delete( comment + ' [[:commons:Image:%s]]' - % filenameOnCommons, prompt = False) + % filenameOnCommons, prompt=False) else: pywikibot.output( u'The image is not identical to the one on Commons.') diff --git a/statistics_in_wikitable.py b/statistics_in_wikitable.py index e2604c8..73e2204 100644 --- a/statistics_in_wikitable.py +++ b/statistics_in_wikitable.py @@ -38,7 +38,7 @@ class StatisticsBot: - + def __init__(self, screen, your_page): """ Constructor. Parameter: -- To view, visit https://gerrit.wikimedia.org/r/103246 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ie759c4d8253e270e8ad7071a23a4eff4dd56f6ed 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] changes - change (pywikibot/compat)
by jenkins-bot (Code Review) 22 Dec '13

22 Dec '13

jenkins-bot has submitted this change and it was merged. Change subject: [PEP8] changes ...................................................................... [PEP8] changes Change-Id: Ib49a06dc3cef0a95eb7c462249b36963f6684119 --- M maintainer.py M maintcont.py M match_images.py M movepages.py M mysql_autoconnection.py 5 files changed, 121 insertions(+), 82 deletions(-) Approvals: Ladsgroup: Looks good to me, approved jenkins-bot: Verified diff --git a/maintainer.py b/maintainer.py index 55d29d9..c55f0c1 100644 --- a/maintainer.py +++ b/maintainer.py @@ -7,10 +7,14 @@ Warning: experimental software, use at your own risk """ -__version__ = '$Id$' - # Author: Balasyum # http://hu.wikipedia.org/wiki/User:Balasyum +# (C) Balasyum, 2008 +# (C) Pywikibot team, 2008-2013 +# +# Distributed under the terms of the MIT license. +__version__ = '$Id$' +# import random import thread @@ -31,6 +35,7 @@ class rcFeeder(SingleServerIRCBot): + def __init__(self, channel, nickname, server, port=6667): SingleServerIRCBot.__init__(self, [(server, port)], nickname, nickname) self.channel = channel @@ -48,10 +53,10 @@ def on_pubmsg(self, c, e): try: - msg = unicode(e.arguments()[0],'utf-8') + msg = unicode(e.arguments()[0], 'utf-8') except UnicodeDecodeError: return - name = msg[8:msg.find(u'14',9)] + name = msg[8:msg.find(u'14', 9)] if 'rciw' in self.tasks: self.rcbot.addQueue(name) if 'censure' in self.tasks: @@ -95,7 +100,7 @@ do = cmd.split() if do[0] == "accepted": print "Joined the network" - thread.start_new_thread(self.activator,()) + thread.start_new_thread(self.activator, ()) elif do[0] == "tasklist" and len(do) > 1: self.feed.tasks = do[1].split('|') diff --git a/maintcont.py b/maintcont.py index f6562e1..d42299c 100644 --- a/maintcont.py +++ b/maintcont.py @@ -8,10 +8,14 @@ Warning: experimental software, use at your own risk """ -__version__ = '$Id$' - # Author: Balasyum # http://hu.wikipedia.org/wiki/User:Balasyum +# (C) Balasyum, 2008 +# (C) Pywikibot team, 2009-2013 +# +# Distributed under the terms of the MIT license. +__version__ = '$Id$' +# import externals externals.check_setup('irclib') @@ -25,6 +29,7 @@ projtasks = {} mainters = [] activity = {} + class MaintcontBot(SingleServerIRCBot): def __init__(self, nickname, server, port=6667): @@ -72,9 +77,9 @@ print "mainter name:", mainter[0], "job:", mainter[1] print "--------------------" print - time.sleep(1*60) + time.sleep(1 * 60) - def retasker(self, group, optask = ''): + def retasker(self, group, optask=''): ingroup = 0 for mainter in mainters: if mainter[1] == group: @@ -92,10 +97,11 @@ if mainter[1] != group: continue tts = '|'.join(tpc[int(round(i * tpcn)):int(round((i + 1) * tpcn))]) - if tts != False: + if tts: self.connection.privmsg(mainter[0], "tasklist " + tts) i += 1 + def main(): bot = MaintcontBot("maintcont", "irc.freenode.net") bot.start() diff --git a/match_images.py b/match_images.py index c621a4e..56ac171 100644 --- a/match_images.py +++ b/match_images.py @@ -1,6 +1,6 @@ #!/usr/bin/python # -*- coding: utf-8 -*- -''' +""" Program to match two images based on histograms. Usage: @@ -9,23 +9,29 @@ This is just a first version so that other people can play around with it. Expect the code to change a lot! -''' +""" # -# (C) Multichill, 2009 +# (c) Multichill, 2009 +# (c) pywikibot team, 2009-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' +# -import sys, math, StringIO -import wikipedia, config +import StringIO +import wikipedia +import config from PIL import Image + def matchImagePages(imagePageA, imagePageB): - ''' + """ This functions expects two image page objects. - It will return True if the image are the same and False if the images are not the same - ''' + It will return True if the image are the same and False if the images are + not the same + + """ imageA = getImageFromImagePage(imagePageA) imageB = getImageFromImagePage(imagePageB) @@ -35,17 +41,23 @@ imageB = imageB.resize((imA_width, imA_height)) - imageA_topleft = imageA.crop((0,0, int(imA_width/2), int(imA_height/2))) - imageB_topleft = imageB.crop((0,0, int(imA_width/2), int(imA_height/2))) + imageA_topleft = imageA.crop((0, 0, int(imA_width / 2), int(imA_height / 2))) + imageB_topleft = imageB.crop((0, 0, int(imA_width / 2), int(imA_height / 2))) - imageA_topright = imageA.crop((int(imA_width/2),0, imA_width, int(imA_height/2))) - imageB_topright = imageB.crop((int(imA_width/2),0, imA_width, int(imA_height/2))) + imageA_topright = imageA.crop((int(imA_width / 2), 0, imA_width, + int(imA_height / 2))) + imageB_topright = imageB.crop((int(imA_width / 2), 0, imA_width, + int(imA_height / 2))) - imageA_bottomleft = imageA.crop((0, int(imA_height/2), int(imA_width/2), imA_height)) - imageB_bottomleft = imageB.crop((0, int(imA_height/2), int(imA_width/2), imA_height)) + imageA_bottomleft = imageA.crop((0, int(imA_height / 2), int(imA_width / 2), + imA_height)) + imageB_bottomleft = imageB.crop((0, int(imA_height / 2), int(imA_width / 2), + imA_height)) - imageA_bottomright = imageA.crop((int(imA_width/2),int(imA_height/2), imA_width, imA_height)) - imageB_bottomright = imageB.crop((int(imA_width/2),int(imA_height/2), imA_width, imA_height)) + imageA_bottomright = imageA.crop((int(imA_width / 2), int(imA_height / 2), + imA_width, imA_height)) + imageB_bottomright = imageB.crop((int(imA_width / 2), int(imA_height / 2), + mA_width, imA_height)) imageA_center = imageA.crop((int(imA_width * 0.25), int(imA_height * 0.25), int(imA_width * 0.75), int(imA_height * 0.75))) imageB_center = imageB.crop((int(imA_width * 0.25), int(imA_height * 0.25), int(imA_width * 0.75), int(imA_height * 0.75))) @@ -56,7 +68,8 @@ bottomleftScore = matchImages(imageA_bottomleft, imageB_bottomleft) bottomrightScore = matchImages(imageA_bottomright, imageB_bottomright) centerScore = matchImages(imageA_center, imageB_center) - averageScore = (wholeScore + topleftScore + toprightScore + bottomleftScore + bottomrightScore + centerScore)/6 + averageScore = (wholeScore + topleftScore + toprightScore + + bottomleftScore + bottomrightScore + centerScore) / 6 print u'Whole image ' + str(wholeScore) print u'Top left of image ' + str(topleftScore) @@ -75,40 +88,37 @@ print u'Not the same.' return False + def getImageFromImagePage(imagePage): - ''' - Get the image object to work based on an imagePage object - ''' - imageURL=imagePage.fileUrl() - imageURLopener= wikipedia.MyURLopener + """ Get the image object to work based on an imagePage object """ + imageURL = imagePage.fileUrl() + imageURLopener = wikipedia.MyURLopener imageWebFile = imageURLopener.open(imageURL) imageBuffer = StringIO.StringIO(imageWebFile.read()) image = Image.open(imageBuffer) return image + def matchImages(imageA, imageB): - ''' - Match two image objects. Return the ratio of pixels that match - ''' + """ Match two image objects. Return the ratio of pixels that match """ histogramA = imageA.histogram() histogramB = imageB.histogram() totalMatch = 0 totalPixels = 0 - if not (len(histogramA)==len(histogramB)): + if not (len(histogramA) == len(histogramB)): return 0 for i in range(0, len(histogramA)): totalMatch = totalMatch + min(histogramA[i], histogramB[i]) totalPixels = totalPixels + max(histogramA[i], histogramB[i]) - if (totalPixels==0): - return 0; + if totalPixels == 0: + return 0 return float(totalMatch)/float(totalPixels)*100 - def main(): @@ -149,31 +159,41 @@ else: images.append(arg) - if not (len(images)==2): + if not (len(images) == 2): raise wikipedia.Error, 'require two images to work on.' else: - imageTitleA=images[0] - imageTitleB=images[1] + imageTitleA = images[0] + imageTitleB = images[1] if not (imageTitleA == u''): if not (langA == u''): if not (familyA == u''): - imagePageA = wikipedia.ImagePage(wikipedia.getSite(langA, familyA), imageTitleA) + imagePageA = wikipedia.ImagePage(wikipedia.getSite(langA, + familyA), + imageTitleA) else: - imagePageA = wikipedia.ImagePage(wikipedia.getSite(langA, u'wikipedia'), imageTitleA) + imagePageA = wikipedia.ImagePage(wikipedia.getSite(langA, + u'wikipedia'), imageTitleA) else: - imagePageA = wikipedia.ImagePage(wikipedia.getSite(u'commons', u'commons'), imageTitleA) + imagePageA = wikipedia.ImagePage(wikipedia.getSite(u'commons', + u'commons'), + imageTitleA) if not (imageTitleB == u''): if not (langB == u''): if not (familyB == u''): - imagePageB = wikipedia.ImagePage(wikipedia.getSite(langB, familyB), imageTitleB) + imagePageB = wikipedia.ImagePage(wikipedia.getSite(langB, + familyB), + imageTitleB) else: - imagePageB = wikipedia.ImagePage(wikipedia.getSite(langB, u'wikipedia'), imageTitleB) + imagePageB = wikipedia.ImagePage(wikipedia.getSite(langB, + u'wikipedia'), imageTitleB) else: - imagePageB = wikipedia.ImagePage(wikipedia.getSite(u'commons', u'commons'), imageTitleB) + imagePageB = wikipedia.ImagePage(wikipedia.getSite(u'commons', + u'commons'), + imageTitleB) - if (imagePageA and imagePageB): + if imagePageA and imagePageB: matchImagePages(imagePageA, imagePageB) diff --git a/movepages.py b/movepages.py index af29f7b..1f2edf9 100644 --- a/movepages.py +++ b/movepages.py @@ -32,15 +32,16 @@ # # (C) Leonardo Gregianin, 2006 # (C) Andreas J. Schwab, 2007 -# (C) Pywikipedia bot team, 2006-2013 +# (C) Pywikibot team, 2006-2013 # # Distributed under the terms of the MIT license. # +__version__ = '$Id$' +# -__version__='$Id$' - -import sys, re -import wikipedia as pywikibot +import sys +import re +import pywikibot from pywikibot import i18n import pagegenerators @@ -147,7 +148,7 @@ u'Change the page title to "%s"?' % newPageTitle, ['yes', 'no', 'all', 'quit'], ['y', 'n', 'a', 'q']) - if choice2 == 'y': + if choice2 == 'y': self.moveOne(page, newPageTitle) elif choice2 == 'a': self.appendAll = True @@ -162,7 +163,7 @@ searchPattern = pywikibot.input(u'Enter the search pattern:') self.replacePattern = pywikibot.input( u'Enter the replace pattern:') - self.regex=re.compile(searchPattern) + self.regex = re.compile(searchPattern) if page.title() == page.title(withNamespace=False): newPageTitle = self.regex.sub(self.replacePattern, page.title()) diff --git a/mysql_autoconnection.py b/mysql_autoconnection.py index 23d13ff..7116dd9 100644 --- a/mysql_autoconnection.py +++ b/mysql_autoconnection.py @@ -5,14 +5,18 @@ reconnect them. """ # -# (C) Bryan Tong Minh, 2007 +# (c) Bryan Tong Minh, 2007 +# (c) pywikibot team, 2008-2013 # # Distributed under the terms of the MIT license. # __version__ = '$Id$' +# -import MySQLdb, MySQLdb.cursors +import MySQLdb +import MySQLdb.cursors import time + class Connection(object): """A wrapper to the MySQLdb database and cursor object. @@ -20,17 +24,17 @@ into one object. """ RECOVERABLE_ERRORS = ( - 1040, # Too many connections - 1152, # Aborted connection - 2002, # Connection error - 2003, # Can't connect - 2006, # Server gone - 2013, # Server lost - 2014, # Commands out of sync - ) + 1040, # Too many connections + 1152, # Aborted connection + 2002, # Connection error + 2003, # Can't connect + 2006, # Server gone + 2013, # Server lost + 2014, # Commands out of sync + ) - def __init__(self, retry_timeout = 60, max_retries = -1, - callback = lambda *args: None, *conn_args, **conn_kwargs): + def __init__(self, retry_timeout=60, max_retries=-1, + callback=lambda *args: None, *conn_args, **conn_kwargs): self.retry_timeout = retry_timeout self.max_retries = max_retries @@ -51,6 +55,7 @@ self.callback(self) time.sleep(self.current_retry * self.retry_timeout) self.current_retry += 1 + def __call(self, (object, function_name), *args, **kwargs): try: return getattr(object, function_name)(*args, **kwargs) @@ -89,7 +94,7 @@ except: pass - def cursor(self, cursorclass = MySQLdb.cursors.Cursor): + def cursor(self, cursorclass=MySQLdb.cursors.Cursor): if type(cursorclass) is not type(self.__cursor): self.__cursor = self.database.cursor(cursorclass) return self @@ -97,6 +102,7 @@ # Mimic cursor object def __iter__(self): return self.__cursor.__iter__() + def __getattr__(self, name, *args, **kwargs): if hasattr(self.database, name): obj = self.database @@ -109,22 +115,26 @@ class CallWrapper(object): + def __init__(self, executor, function): self.__executor = executor self.__function = function + def __call__(self, *args, **kwargs): - return self.__executor(self.__function, - *args, **kwargs) + return self.__executor(self.__function, *args, **kwargs) + def __getattr__(self, name): getattr(self.__function, name) -def connect(retry_timeout = 60, max_retries = -1, - callback = lambda *args: None, *conn_args, **conn_kwargs): - return Connection(retry_timeout = retry_timeout, - max_retries = max_retries, - callback = callback, - *conn_args, **conn_kwargs) +def connect(retry_timeout=60, max_retries=-1, + callback=lambda *args: None, *conn_args, **conn_kwargs): + + return Connection(retry_timeout=retry_timeout, + max_retries=max_retries, + callback=callback, + *conn_args, **conn_kwargs) + if __name__ == '__main__': def callback(conn): @@ -134,8 +144,8 @@ username = raw_input('Username: ') password = raw_input('Password: ') - conn = connect(retry_timeout = 5, max_retries = 4, callback = callback, - host = host, user = username, passwd = password, charset = 'utf8') + conn = connect(retry_timeout=5, max_retries=4, callback=callback, + host=host, user=username, passwd=password, charset='utf8') cur = conn.cursor() print 'Connected!' conn.execute('SELECT 1') @@ -159,6 +169,3 @@ print conn.fetchall() print 'Query ok!' raw_input() - - - -- To view, visit https://gerrit.wikimedia.org/r/103245 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ib49a06dc3cef0a95eb7c462249b36963f6684119 Gerrit-PatchSet: 1 Gerrit-Project: pywikibot/compat Gerrit-Branch: master Gerrit-Owner: Xqt <info(a)gno.de> Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com> Gerrit-Reviewer: jenkins-bot

1 0

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

Pywikibot-commits