jenkins-bot has submitted this change and it was merged. ( https://gerrit.wikimedia.org/r/462283 )

Change subject: [cleanup] cleanup scripts/weblinkchecker.py ......................................................................

[cleanup] cleanup scripts/weblinkchecker.py

- remove preleading "u" from strings - use single quotes for string literals - use str.format(...) instead for modulo for changed lines.

Change-Id: I8f7922e60ae95bf316ea323df5f8ce792f30d76e --- M scripts/weblinkchecker.py 1 file changed, 67 insertions(+), 63 deletions(-)

Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified

diff --git a/scripts/weblinkchecker.py b/scripts/weblinkchecker.py index a46fe34..6923a6f 100755 --- a/scripts/weblinkchecker.py +++ b/scripts/weblinkchecker.py @@ -355,7 +355,7 @@ if not self.serverEncoding: try: pywikibot.output( - u'Contacting server %s to find out its default encoding...' + 'Contacting server %s to find out its default encoding...' % self.host) conn = self.getConnection() conn.request('HEAD', '/', None, self.header) @@ -366,7 +366,7 @@ if not self.serverEncoding: # TODO: We might also load a page, then check for an encoding # definition in a HTML meta tag. - pywikibot.output('Error retrieving server's default charset. ' + pywikibot.output("Error retrieving server's default charset. " 'Using ISO 8859-1.') # most browsers use ISO 8859-1 (Latin-1) as the default. self.serverEncoding = 'iso8859-1' @@ -447,8 +447,9 @@ self.changeUrl(redirTarget) return True elif redirTarget.startswith('/'): - self.changeUrl(u'%s://%s%s' - % (self.protocol, self.host, redirTarget)) + self.changeUrl('{0}://{1}{2}' + .format(self.protocol, self.host, + redirTarget)) return True else: # redirect to relative position # cut off filename @@ -462,9 +463,9 @@ # change /foo/bar/ to /foo/ directory = directory[:-1] directory = directory[:directory.rindex('/') + 1] - self.changeUrl('%s://%s%s%s' - % (self.protocol, self.host, directory, - redirTarget)) + self.changeUrl('{0}://{1}{2}{3}' + .format(self.protocol, self.host, directory, + redirTarget)) return True else: return False # not a redirect @@ -478,10 +479,10 @@ try: wasRedirected = self.resolveRedirect(useHEAD=useHEAD) except UnicodeError as error: - return False, u'Encoding Error: %s (%s)' % ( + return False, 'Encoding Error: {0} ({1})'.format( error.__class__.__name__, error) except httplib.error as error: - return False, u'HTTP Error: %s' % error.__class__.__name__ + return False, 'HTTP Error: {}'.format(error.__class__.__name__) except socket.error as error: # https://docs.python.org/2/library/socket.html : # socket.error : @@ -500,7 +501,7 @@ # TODO: decode msg. On Linux, it's encoded in UTF-8. # How is it encoded in Windows? Or can we somehow just # get the English message? - return False, u'Socket Error: %s' % repr(msg) + return False, 'Socket Error: {}'.format(repr(msg)) if wasRedirected: if self.url in self.redirectChain: if useHEAD: @@ -514,10 +515,11 @@ HTTPignore=self.HTTPignore) return redirChecker.check(useHEAD=False) else: - urlList = ['[%s]' % url + urlList = ['[{0}]'.format(url) for url in self.redirectChain + [self.url]] return (False, - u'HTTP Redirect Loop: %s' % ' -> '.join(urlList)) + 'HTTP Redirect Loop: {0}'.format( + ' -> '.join(urlList))) elif len(self.redirectChain) >= 19: if useHEAD: # Some servers don't seem to handle HEAD requests properly, @@ -530,11 +532,11 @@ HTTPignore=self.HTTPignore) return redirChecker.check(useHEAD=False) else: - urlList = ['[%s]' % url + urlList = ['[{0}]'.format(url) for url in self.redirectChain + [self.url]] return (False, - u'Long Chain of Redirects: %s' - % ' -> '.join(urlList)) + 'Long Chain of Redirects: {0}' + .format(' -> '.join(urlList))) else: redirChecker = LinkChecker(self.url, self.redirectChain, self.serverEncoding, @@ -544,24 +546,25 @@ try: conn = self.getConnection() except httplib.error as error: - return False, u'HTTP Error: %s' % error.__class__.__name__ + return False, 'HTTP Error: {0}'.format( + error.__class__.__name__) try: - conn.request('GET', '%s%s' - % (self.path, self.query), None, self.header) + conn.request('GET', '{0}{1}'.format(self.path, self.query), + None, self.header) except socket.error as error: - return False, u'Socket Error: %s' % repr(error[1]) + return False, 'Socket Error: {0}'.format(repr(error[1])) try: self.response = conn.getresponse() except Exception as error: - return False, u'Error: %s' % error + return False, 'Error: {0}'.format(error) # read the server's encoding, in case we need it later self.readEncodingFromResponse(self.response) # site down if the server status is between 400 and 499 alive = self.response.status not in range(400, 500) if self.response.status in self.HTTPignore: alive = False - return alive, '%s %s' % (self.response.status, - self.response.reason) + return alive, '{0} {1}'.format(self.response.status, + self.response.reason)

class LinkCheckThread(threading.Thread): @@ -586,8 +589,8 @@ 'Connection': 'keep-alive', } # identification for debugging purposes - self.setName((u'%s - %s' % (page.title(), url)).encode('utf-8', - 'replace')) + self.setName(('{0} - {1}'.format(page.title(), + url().encode('utf-8', 'replace')))) self.HTTPignore = HTTPignore self._use_fake_user_agent = config.fake_user_agent_default.get( 'weblinkchecker', False) @@ -606,8 +609,8 @@ 'weblinkchecker-badurl_msg', {'URL': self.url}) except Exception: - pywikibot.output('Exception while processing URL %s in page %s' - % (self.url, self.page.title())) + pywikibot.output('Exception while processing URL {0} in page {1}' + .format(self.url, self.page.title())) raise if (r.status == requests.codes.ok and str(r.status) not in self.HTTPignore): @@ -616,11 +619,11 @@ message = '{0}'.format(r.status) if ok: if self.history.setLinkAlive(self.url): - pywikibot.output('*Link to %s in [[%s]] is back alive.' - % (self.url, self.page.title())) + pywikibot.output('*Link to {0} in [[{1}]] is back alive.' + .format(self.url, self.page.title())) else: - pywikibot.output('*[[%s]] links to %s - %s.' - % (self.page.title(), self.url, message)) + pywikibot.output('*[[{0}]] links to {1} - {2}.' + .format(self.page.title(), self.url, message)) self.history.setLinkDead(self.url, message, self.page, config.weblink_dead_days)

@@ -658,8 +661,8 @@ self.site = site self.semaphore = threading.Semaphore() self.datfilename = pywikibot.config.datafilepath( - 'deadlinks', 'deadlinks-%s-%s.dat' % (self.site.family.name, - self.site.code)) + 'deadlinks', 'deadlinks-{0}-{1}.dat'.format(self.site.family.name, + self.site.code)) # Count the number of logged links, so that we can insert captions # from time to time self.logCount = 0 @@ -673,19 +676,20 @@ def log(self, url, error, containingPage, archiveURL): """Log an error report to a text file in the deadlinks subdirectory.""" if archiveURL: - errorReport = u'* %s ([%s archive])\n' % (url, archiveURL) + errorReport = '* {0} ([{1} archive])\n'.format(url, archiveURL) else: - errorReport = u'* %s\n' % url + errorReport = '* {0}\n'.format(url) for (pageTitle, date, error) in self.historyDict[url]: # ISO 8601 formulation isoDate = time.strftime('%Y-%m-%d %H:%M:%S', time.gmtime(date)) - errorReport += "** In [[%s]] on %s, %s\n" % (pageTitle, isoDate, - error) - pywikibot.output(u"** Logging link for deletion.") + errorReport += '** In [[{0}]] on {1}, {2}\n'.format( + pageTitle, isoDate, error) + pywikibot.output('** Logging link for deletion.') txtfilename = pywikibot.config.datafilepath('deadlinks', - 'results-%s-%s.txt' - % (self.site.family.name, - self.site.lang)) + 'results-{0}-{1}.txt' + .format( + self.site.family.name, + self.site.lang)) with codecs.open(txtfilename, 'a', 'utf-8') as txtfile: self.logCount += 1 if self.logCount % 30 == 0: @@ -832,21 +836,20 @@ count = '' # Check if there is already such a caption on # the talk page. - while re.search('= *%s%s *=' % (caption, count), + while re.search('= *{0}{1} *='.format(caption, count), content) is not None: i += 1 count = ' ' + str(i) caption += count - content += '== %s ==\n\n%s\n\n%s%s\n--~~~~' % \ - (caption, - i18n.twtranslate(containingPage.site, - 'weblinkchecker-report'), - errorReport, - archiveMsg) - comment = '[[%s#%s|→]] %s' % \ - (talkPage.title(), caption, - i18n.twtranslate(containingPage.site, - 'weblinkchecker-summary')) + content += '== {0} ==\n\n{1}\n\n{2}{3}\n--~~~~'.format( + caption, i18n.twtranslate(containingPage.site, + 'weblinkchecker-report'), + errorReport, archiveMsg) + + comment = '[[{0}#{1}|→]] {2}'.format( + talkPage.title(), caption, + i18n.twtranslate(containingPage.site, + 'weblinkchecker-summary')) try: talkPage.put(content, comment) except pywikibot.SpamfilterError as error: @@ -870,7 +873,7 @@ generator=generator, site=site)

if config.report_dead_links_on_talk: - pywikibot.log("Starting talk page thread") + pywikibot.log('Starting talk page thread') reportThread = DeadLinkReportThread() # thread dies when program terminates # reportThread.setDaemon(True) @@ -960,7 +963,8 @@ HTTPignore = []

if isinstance(memento_client, ImportError): - warn('memento_client not imported: %s' % memento_client, ImportWarning) + warn('memento_client not imported: {0}'.format(memento_client), + ImportWarning)

# Process global args and prepare generator args parser local_args = pywikibot.handle_args(args) @@ -980,7 +984,7 @@ elif arg.startswith('-xmlstart'): if len(arg) == 9: xmlStart = pywikibot.input( - u'Please enter the dumped article to start with:') + 'Please enter the dumped article to start with:') else: xmlStart = arg[10:] elif arg.startswith('-xml'): @@ -1016,18 +1020,18 @@ # Don't wait longer than 30 seconds for threads to finish. while countLinkCheckThreads() > 0 and waitTime < 30: try: - pywikibot.output(u"Waiting for remaining %i threads to " - u"finish, please wait..." - % countLinkCheckThreads()) + pywikibot.output('Waiting for remaining {0} threads to ' + 'finish, please wait...' + .format(countLinkCheckThreads())) # wait 1 second time.sleep(1) waitTime += 1 except KeyboardInterrupt: - pywikibot.output(u'Interrupted.') + pywikibot.output('Interrupted.') break if countLinkCheckThreads() > 0: - pywikibot.output(u'Remaining %i threads will be killed.' - % countLinkCheckThreads()) + pywikibot.output('Remaining {0} threads will be killed.' + .format(countLinkCheckThreads())) # Threads will die automatically because they are daemonic. if bot.history.reportThread: bot.history.reportThread.shutdown() @@ -1037,9 +1041,9 @@ while bot.history.reportThread.isAlive(): time.sleep(0.1) except KeyboardInterrupt: - pywikibot.output(u'Report thread interrupted.') + pywikibot.output('Report thread interrupted.') bot.history.reportThread.kill() - pywikibot.output(u'Saving history...') + pywikibot.output('Saving history...') bot.history.save() return True else: @@ -1047,5 +1051,5 @@ return False

-if __name__ == "__main__": +if __name__ == '__main__': main()