Pywikipedia-l February 2008

pywikipedia-l@lists.wikimedia.org

22 participants
382 discussions

SVN: [4997] trunk/pywikipedia/pagegenerators.py
by wikipedian＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4997 Author: wikipedian Date: 2008-02-10 00:18:04 +0000 (Sun, 10 Feb 2008) Log Message: ----------- Oops, I didn't mean to commit this. Undo. Modified Paths: -------------- trunk/pywikipedia/pagegenerators.py Modified: trunk/pywikipedia/pagegenerators.py =================================================================== --- trunk/pywikipedia/pagegenerators.py 2008-02-09 23:39:24 UTC (rev 4996) +++ trunk/pywikipedia/pagegenerators.py 2008-02-10 00:18:04 UTC (rev 4997) @@ -529,11 +529,9 @@ if index is None: raise ValueError(u'Unknown namespace: %s' % ns) namespaces[i] = index - rTMP = re.compile(r'\d') for page in generator: - if rTMP.search(page.title()) == None: - if page.namespace() in namespaces: - yield page + if page.namespace() in namespaces: + yield page def RedirectFilterPageGenerator(generator): """

1 0

SVN: [4996] trunk/pywikipedia/interwiki.py
by wikipedian＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4996 Author: wikipedian Date: 2008-02-09 23:39:24 +0000 (Sat, 09 Feb 2008) Log Message: ----------- added hack to get rid of all those lmo: interwiki links Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2008-02-09 23:08:43 UTC (rev 4995) +++ trunk/pywikipedia/interwiki.py 2008-02-09 23:39:24 UTC (rev 4996) @@ -1076,8 +1076,16 @@ # Determine whether we need permission to submit ask = False if removing and removing != [page]: # Allow for special case of a self-pointing interwiki link - self.problem('Found incorrect link to %s in %s'% (",".join([x.site().lang for x in removing]), page.aslink(True)), createneed = False) - ask = True + ########## + # temporary hard-coded special case to get rid of thousands of broken links to the Lombard Wikipedia, + # where useless bot-created articles were mass-deleted. See for example: + # http://meta.wikimedia.org/wiki/Proposals_for_closing_projects/Closure_of_Lo… + if len(removing) == 1 and removing[0].site() == wikipedia.Site('lmo', 'wikipedia'): + wikipedia.output('Found bad link to %s. As many lmo pages were deleted, it is assumed that it can be safely removed.' % removing[0].aslink()) + else: + ########## + self.problem('Found incorrect link to %s in %s'% (",".join([x.site().lang for x in removing]), page.aslink(True)), createneed = False) + ask = True if globalvar.force: ask = False if globalvar.confirm:

1 0

SVN: [4995] trunk/pywikipedia
by wikipedian＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4995 Author: wikipedian Date: 2008-02-09 23:08:43 +0000 (Sat, 09 Feb 2008) Log Message: ----------- Fixed bug that lead to such strange messages: BUG>> title Page (Arizona) ([[pt:Page (Arizona)]]) not found in list Expected one of: [[pt:Page (Arizona)]] This is caused by a useless left-to-right marker in http://de.wikipedia.org/w/index.php?title=Page_%28Arizona%29&action=edit&ol… and other pages, just between pt: and Page. These markers are now automatically removed in the Page constructor. Modified Paths: -------------- trunk/pywikipedia/pagegenerators.py trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/pagegenerators.py =================================================================== --- trunk/pywikipedia/pagegenerators.py 2008-02-09 22:24:26 UTC (rev 4994) +++ trunk/pywikipedia/pagegenerators.py 2008-02-09 23:08:43 UTC (rev 4995) @@ -529,9 +529,11 @@ if index is None: raise ValueError(u'Unknown namespace: %s' % ns) namespaces[i] = index + rTMP = re.compile(r'\d') for page in generator: - if page.namespace() in namespaces: - yield page + if rTMP.search(page.title()) == None: + if page.namespace() in namespaces: + yield page def RedirectFilterPageGenerator(generator): """ Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2008-02-09 22:24:26 UTC (rev 4994) +++ trunk/pywikipedia/wikipedia.py 2008-02-09 23:08:43 UTC (rev 4995) @@ -325,6 +325,8 @@ # Replace underscores by spaces, also multiple spaces and underscores with a single space # Strip spaces at both ends t = re.sub('[ _]+', ' ', t).strip() + # Remove left-to-right and right-to-left markers. + t = re.sub(u'\u200e|\u200f', '', t) # leading colon implies main namespace instead of the default if t.startswith(':'): t = t[1:]

1 0

SVN: [4994] trunk/pywikipedia/interwiki.py
by wikipedian＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4994 Author: wikipedian Date: 2008-02-09 22:24:26 +0000 (Sat, 09 Feb 2008) Log Message: ----------- added -namespace parameter Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2008-02-09 20:09:38 UTC (rev 4993) +++ trunk/pywikipedia/interwiki.py 2008-02-09 22:24:26 UTC (rev 4994) @@ -46,6 +46,12 @@ Additionaly, these arguments can be used to restrict the bot to certain pages: + -namespace:n Number or name of namespace to process. The parameter can be + used multiple times. It works in combination with all other + parameters, except for the -start parameter. If you e.g. + want to iterate over all categories starting at M, use + -start:Category:M. + -number: used as -number:#, specifies that the robot should process that amount of pages and then stop. This is only useful in combination with -start. The default is not to stop. @@ -1443,6 +1449,9 @@ singlePageTitle = [] hints = [] start = None + # Which namespaces should be processed? + # default to [] which means all namespaces will be processed + namespaces = [] number = None warnfile = None # a normal PageGenerator (which doesn't give hints, only Pages) @@ -1532,6 +1541,11 @@ elif arg == '-continue': optContinue = True # deprecated for consistency with other scripts + elif arg.startswith('-namespace:'): + try: + namespaces.append(int(arg[11:])) + except ValueError: + namespaces.append(arg[11:]) elif arg.startswith('-number:'): number = int(arg[8:]) elif arg.startswith('-neverlink:'): @@ -1596,9 +1610,11 @@ bot = InterwikiBot() if hintlessPageGen: + hintlessPageGen = pagegenerators.NamespaceFilterPageGenerator(hintlessPageGen, namespaces) # we'll use iter() to create make a next() function available. - bot.setPageGenerator(iter(hintlessPageGen),number = number) + bot.setPageGenerator(iter(hintlessPageGen), number = number) elif warnfile: + # TODO: filter namespaces if -namespace parameter was used readWarnfile(warnfile, bot) else: singlePageTitle = ' '.join(singlePageTitle)

1 0

SVN: [4993] trunk/pywikipedia/wikipedia.py
by rotem＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4993 Author: rotem Date: 2008-02-09 20:09:38 +0000 (Sat, 09 Feb 2008) Log Message: ----------- Adding the fix again, fixed (count => count2). Modified Paths: -------------- trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2008-02-09 20:04:01 UTC (rev 4992) +++ trunk/pywikipedia/wikipedia.py 2008-02-09 20:09:38 UTC (rev 4993) @@ -1558,19 +1558,17 @@ def templates(self): """Return a list of Page objects for templates used on this Page. - + Template parameters are ignored. - """ return [template for (template, param) in self.templatesWithParams()] def templatesWithParams(self): """Return a list of templates used on this Page. - + Return value is a list of tuples. There is one tuple for each use of a template in the page, with the template Page as the first entry and a list of parameters as the second entry. - """ try: thistxt = self.get() @@ -1580,16 +1578,23 @@ # remove commented-out stuff etc. thistxt = removeDisabledParts(thistxt) - # marker for inside template + # marker for inside templates or parameters marker = '@@' while marker in thistxt: marker += '@' + # marker for links + marker2 = '##' + while marker2 in thistxt: + marker2 += '#' + result = [] - markers = {} + inside = {} count = 0 Rtemplate = re.compile(r'{{(msg:)?(?P<name>[^{\|]+?)(\|(?P<params>[^{]+?))?}}') + Rlink = re.compile(r'\[\[[^\]]+\]\]') Rmarker = re.compile('%s(\\d+)%s' % (marker, marker)) + Rmarker2 = re.compile('%s(\\d+)%s' % (marker2, marker2)) while Rtemplate.search(thistxt) is not None: for m in Rtemplate.finditer(thistxt): # Make sure it is not detected again @@ -1597,9 +1602,9 @@ text = m.group() thistxt = thistxt.replace(text, '%s%d%s' % (marker, count, marker)) for m2 in Rmarker.finditer(text): - # Make sure markers don't contain other markers - text = text.replace(m2.group(), markers[int(m2.group(1))]) - markers[count] = text + # Make sure stored templates don't contain markers + text = text.replace(m2.group(), inside[int(m2.group(1))]) + inside[count] = text # Name name = m.group('name') @@ -1620,12 +1625,22 @@ paramString = m.group('params') params = [] if paramString: + # Replace links to markers + links = {} + count2 = 0 + for m2 in Rlink.finditer(paramString): + count2 += 1 + text = m2.group() + paramString = paramString.replace(text, '%s%d%s' % (marker2, count2, marker2)) + links[count2] = text # Parse string markedParams = paramString.split('|') # Replace markers for param in markedParams: for m2 in Rmarker.finditer(param): - param = param.replace(m2.group(), markers[int(m2.group(1))]) + param = param.replace(m2.group(), inside[int(m2.group(1))]) + for m2 in Rmarker2.finditer(param): + param = param.replace(m2.group(), links[int(m2.group(1))]) params.append(param) # Add it to the result

1 0

SVN: [4992] trunk/pywikipedia/wikipedia.py
by russblau＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4992 Author: russblau Date: 2008-02-09 20:04:01 +0000 (Sat, 09 Feb 2008) Log Message: ----------- Roll back to r4988; r4989 crashes on pages with nested templates. (Example: en.wikipedia.org/Shane_White) Modified Paths: -------------- trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2008-02-09 17:49:17 UTC (rev 4991) +++ trunk/pywikipedia/wikipedia.py 2008-02-09 20:04:01 UTC (rev 4992) @@ -1558,17 +1558,19 @@ def templates(self): """Return a list of Page objects for templates used on this Page. - + Template parameters are ignored. + """ return [template for (template, param) in self.templatesWithParams()] def templatesWithParams(self): """Return a list of templates used on this Page. - + Return value is a list of tuples. There is one tuple for each use of a template in the page, with the template Page as the first entry and a list of parameters as the second entry. + """ try: thistxt = self.get() @@ -1578,23 +1580,16 @@ # remove commented-out stuff etc. thistxt = removeDisabledParts(thistxt) - # marker for inside templates or parameters + # marker for inside template marker = '@@' while marker in thistxt: marker += '@' - # marker for links - marker2 = '##' - while marker2 in thistxt: - marker2 += '#' - result = [] - inside = {} + markers = {} count = 0 Rtemplate = re.compile(r'{{(msg:)?(?P<name>[^{\|]+?)(\|(?P<params>[^{]+?))?}}') - Rlink = re.compile(r'\[\[[^\]]+\]\]') Rmarker = re.compile('%s(\\d+)%s' % (marker, marker)) - Rmarker2 = re.compile('%s(\\d+)%s' % (marker2, marker2)) while Rtemplate.search(thistxt) is not None: for m in Rtemplate.finditer(thistxt): # Make sure it is not detected again @@ -1602,9 +1597,9 @@ text = m.group() thistxt = thistxt.replace(text, '%s%d%s' % (marker, count, marker)) for m2 in Rmarker.finditer(text): - # Make sure stored templates don't contain markers - text = text.replace(m2.group(), inside[int(m2.group(1))]) - inside[count] = text + # Make sure markers don't contain other markers + text = text.replace(m2.group(), markers[int(m2.group(1))]) + markers[count] = text # Name name = m.group('name') @@ -1625,22 +1620,12 @@ paramString = m.group('params') params = [] if paramString: - # Replace links to markers - links = {} - count2 = 0 - for m2 in Rlink.finditer(paramString): - count2 += 1 - text = m2.group() - paramString = paramString.replace(text, '%s%d%s' % (marker2, count, marker2)) - links[count2] = text # Parse string markedParams = paramString.split('|') # Replace markers for param in markedParams: for m2 in Rmarker.finditer(param): - param = param.replace(m2.group(), inside[int(m2.group(1))]) - for m2 in Rmarker2.finditer(param): - param = param.replace(m2.group(), links[int(m2.group(1))]) + param = param.replace(m2.group(), markers[int(m2.group(1))]) params.append(param) # Add it to the result

1 0

SVN: [4991] trunk/pywikipedia/families/i18n_family.py
by siebrand＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4991 Author: siebrand Date: 2008-02-09 17:49:17 +0000 (Sat, 09 Feb 2008) Log Message: ----------- Update namespaces Modified Paths: -------------- trunk/pywikipedia/families/i18n_family.py Modified: trunk/pywikipedia/families/i18n_family.py =================================================================== --- trunk/pywikipedia/families/i18n_family.py 2008-02-09 13:25:00 UTC (rev 4990) +++ trunk/pywikipedia/families/i18n_family.py 2008-02-09 17:49:17 UTC (rev 4991) @@ -21,6 +21,12 @@ self.namespaces[5] = { '_default': [u'Betawiki talk'], } + self.namespaces[100] = { + '_default': [u'Portal'], + } + self.namespaces[101] = { + '_default': [u'Portal talk'], + } self.namespaces[1102] = { '_default': [u'Translating'], }

1 0

[ pywikipediabot-Patches-1888694 ] solve_disambiguation.py - ko (Korean) translation
by SourceForge.net 09 Feb '08

09 Feb '08

Patches item #1888694, was opened at 2008-02-07 13:32 Message generated for change (Settings changed) made by rotemliss You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1888694&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: sf_noky (sf_nokymacha) Assigned to: Nobody/Anonymous (nobody) Summary: solve_disambiguation.py - ko (Korean) translation Initial Comment: solve_disambiguation.py - ko (Korean) translation. Thank you. ---------------------------------------------------------------------- Comment By: Rotem Liss (rotemliss) Date: 2008-02-09 15:25 Message: Logged In: YES user_id=1327030 Originator: NO Applied in r4990. ---------------------------------------------------------------------- Comment By: sf_noky (sf_nokymacha) Date: 2008-02-07 13:58 Message: Logged In: YES user_id=1966283 Originator: YES File Added: solve_disambiguation_diff1.txt ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1888694&group_…

1 0

[ pywikipediabot-Patches-1888694 ] solve_disambiguation.py - ko (Korean) translation
by SourceForge.net 09 Feb '08

09 Feb '08

Patches item #1888694, was opened at 2008-02-07 13:32 Message generated for change (Comment added) made by rotemliss You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1888694&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: None Priority: 5 Private: No Submitted By: sf_noky (sf_nokymacha) Assigned to: Nobody/Anonymous (nobody) Summary: solve_disambiguation.py - ko (Korean) translation Initial Comment: solve_disambiguation.py - ko (Korean) translation. Thank you. ---------------------------------------------------------------------- >Comment By: Rotem Liss (rotemliss) Date: 2008-02-09 15:25 Message: Logged In: YES user_id=1327030 Originator: NO Applied in r4990. ---------------------------------------------------------------------- Comment By: sf_noky (sf_nokymacha) Date: 2008-02-07 13:58 Message: Logged In: YES user_id=1966283 Originator: YES File Added: solve_disambiguation_diff1.txt ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1888694&group_…

1 0

SVN: [4990] trunk/pywikipedia/solve_disambiguation.py
by rotem＠svn.wikimedia.org 09 Feb '08

09 Feb '08

Revision: 4990 Author: rotem Date: 2008-02-09 13:25:00 +0000 (Sat, 09 Feb 2008) Log Message: ----------- (patch 1888694) solve_disambiguation.py - ko (Korean) translation Modified Paths: -------------- trunk/pywikipedia/solve_disambiguation.py Modified: trunk/pywikipedia/solve_disambiguation.py =================================================================== --- trunk/pywikipedia/solve_disambiguation.py 2008-02-09 13:19:02 UTC (rev 4989) +++ trunk/pywikipedia/solve_disambiguation.py 2008-02-09 13:25:00 UTC (rev 4990) @@ -86,6 +86,7 @@ 'it': u'Sistemazione automatica della disambigua: %s - Inversione di redirect %s', 'lt': u'Nuorodų į nukrepiamąjį straipsnį keitimas: %s - Pakeistos nuorodos į %s', 'kk': u'Айрықты мағыналарды бот көмегімен шешу: %s - Changed link(s) to %s', + 'ko': u'로봇의 도움을 받아 동음이의 처리 : [[%s]] - %s 문서로 링크 걸음', 'nl': u'Robot-geholpen doorverwijzing: [[%s]] - Link(s) veranderd naar %s', 'no': u'bot: Retter lenke til peker: %s - Endret lenke(r) til %s', 'pl': u'Wspomagane przez robota ujednoznacznienie: %s - Zmieniono link(i) %s', @@ -107,6 +108,7 @@ 'it': u'Sistemazione automatica della disambigua: %s - Collegamenti rimossi', 'lt': u'Nuorodų į nukrepiamąjį straipsnį keitimas: %s - Pašalintos nuorodos', 'kk': u'Айрықты мағыналарды бот көмегімен шешу: %s - Removed link(s).', + 'ko': u'로봇의 도움을 받아 동음이의 처리: [[%s]] - 링크 제거', 'nl': u'Robot-geholpen doorverwijzing: [[%s]] - Link(s) weggehaald.', 'no': u'bot: Retter lenke til peker: %s - Fjernet lenke(r)', 'pl': u'Wspomagane przez robota ujednoznacznienie: %s - Usunięto link(i)', @@ -128,6 +130,7 @@ 'it': u'Sistemazione automatica del redirect: %s - Inversione di redirect %s', 'lt': u'Nuorodų į peradresavimo straipsnį keitimas: %s - Pakeistos nuorodos į %s', 'kk': u'Айрықты мағыналарды бот көмегімен шешу: %s - Changed link(s) to %s', + 'ko': u'로봇의 도움을 받아 동음이의 처리: [[%s]] - %s 문서로 링크 걸음', 'nl': u'Robot-geholpen redirect-oplossing: [[%s]] - Link(s) veranderd naar %s', 'no': u'bot: Endrer omdirigeringslenke: %s - Endret lenke(r) til %s', 'pl': u'Wspomagane przez robota ujednoznacznienie: %s - Zmieniono link(i) %s', @@ -149,6 +152,7 @@ 'it': u'Sistemazione automatica del redirect: %s - Collegamenti rimossi', 'lt': u'Nuorodų į peradresavimo straipsnį keitimas: %s - Pašalintos nuorodos', 'kk': u'Айрықты мағыналарды бот көмегімен шешу: %s - Removed link(s).', + 'ko': u'로봇의 도움을 받아 동음이의 처리: [[%s]] - 링크 제거', 'nl': u'Robot-geholpen redirect-oplossing: [[%s]] - Link(s) weggehaald', 'no': u'bot: Endrer omdirigeringslenke: %s - Fjernet lenke(r)', 'pl': u'Wspomagane przez robota ujednoznacznienie: %s - Usunięto link(i)', @@ -167,6 +171,7 @@ 'it': u'%s_(disambigua)', 'lt': u'%s_(reikšmės)', 'kk': u'%s_(айрық)', + 'ko': u'%s_(동음이의)', 'nl': u'%s_(doorverwijspagina)', 'no': u'%s_(peker)', 'pl': u'%s_(ujednoznacznienie)', @@ -275,6 +280,10 @@ 'kk': [ u'Санат:Айрықты бет', ], + 'ko': [ + u'위키백과:(동음이의) 문서의 목록', + u'위키백과:동음이의어 문서의 목록', + ], 'lt': [ u'Wikipedia:Rodomi nukreipiamieji straipsniai', ],

1 0

← Newer
1
...
28
29
30
31
32
33
34
...
39
Older →

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Pywikipedia-l February 2008