Revision: 6266 Author: russblau Date: 2009-01-18 22:23:28 +0000 (Sun, 18 Jan 2009)

Log Message: ----------- Add redirect templates to category redirect list

Modified Paths: -------------- trunk/pywikipedia/families/commons_family.py trunk/pywikipedia/families/wikipedia_family.py trunk/pywikipedia/family.py trunk/pywikipedia/redirect.py trunk/pywikipedia/wikipedia.py trunk/pywikipedia/xmlreader.py

Modified: trunk/pywikipedia/families/commons_family.py =================================================================== --- trunk/pywikipedia/families/commons_family.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/families/commons_family.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -30,7 +30,16 @@ self.interwiki_forward = 'wikipedia'

self.category_redirect_templates = { - 'commons': ('Category redirect',), + 'commons': (u'Category redirect', + u'Categoryredirect', + u'See cat', + u'Seecat', + u'Catredirect', + u'Cat redirect', + u'CatRed', + u'Cat-red', + u'Catredir', + u'Redirect category'), }

self.disambiguationTemplates = {

Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/families/wikipedia_family.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -542,44 +542,78 @@

self.category_redirect_templates = { '_default': (), - 'ar': (u"تحويل تصنيف",), + 'ar': (u"تحويل تصنيف", + u"تحويلة تصنيف", + u"Category redirect", + u"تحويلة تصنيف",), 'arz': (u'تحويل تصنيف',), 'cs': (u'Zastaralá kategorie',), 'da': (u'Kategoriomdirigering',), 'de': (u'Kategorieweiterleitung',), 'en': (u"Category redirect", u"Category redirect3", - ), + u"Categoryredirect", + u"CR", + u"Catredirect", + u"Cat redirect", + u"Seecat",), 'es': (u'Categoría redirigida',), 'eu': (u'Kategoria redirect',), 'fa': (u'رده بهتر', u'انتقال رده', - u'فیلم‌های امریکایی'), + u'فیلم‌های امریکایی',), 'fr': (u'Redirection de catégorie',), - 'hi': (u'श्रेणीअनुप्रेषित',), - 'id': (u'Alih kategori',), + 'hi': (u'श्रेणीअनुप्रेषित', + u'Categoryredirect',), + 'id': (u'Alih kategori', + u'Alihkategori',), # 'it' has removed its template # 'ja' is discussing to remove this template 'ja': (u"Category redirect",), 'ko': (u'분류 넘겨주기',), 'mk': (u'Премести категорија',), - 'ms': (u'Pengalihan kategori',), + 'ms': (u'Pengalihan kategori', + u'Categoryredirect', + u'Category redirect',), 'mt': (u'Redirect kategorija',), # 'nl' has removed its template - 'no': (u"Kategoriomdirigering",), - 'pl': (u'Przekierowanie kategorii',), - 'pt': (u'Redirecionamento de categoria',), + 'no': (u"Category redirect", + u"Kategoriomdirigering", + u"Kategori-omdirigering",), + 'pl': (u'Przekierowanie kategorii', + u'Category redirect',), + 'pt': (u'Redirecionamento de categoria', + u'Redircat', + u'Redirect-categoria',), 'ro': (u'Redirect categorie',), - 'ru': (u'Переименованная категория',), - 'simple': (u"Category redirect",), - 'sq': (u'Kategori e zhvendosur',), + 'ru': (u'Переименованная категория', + u'Categoryredirect', + u'CategoryRedirect', + u'Category redirect', + u'Catredirect',), + 'simple': (u"Category redirect", + u"Catredirect",), + 'sq': (u'Kategori e zhvendosur', + u'Category redirect',), 'tl': (u'Category redirect',), - 'tr': (u'Kategori yönlendirme',), + 'tr': (u'Kategori yönlendirme', + u'Kat redir',), 'uk': (u'Categoryredirect',), - 'vi': (u'Đổi hướng thể loại',), + 'vi': (u'Đổi hướng thể loại', + u'Thể loại đổi hướng', + u'Chuyển hướng thể loại', + u'Categoryredirect', + u'Category redirect', + u'Catredirect', + u'Categoryredirect',), 'yi': (u'קאטעגאריע אריבערפירן',), - 'zh': (u'分类重定向',), - 'zh-yue': (u'分類彈去',), + 'zh': (u'分类重定向', + u'Cr', + u'CR', + u'Cat-redirect',), + 'zh-yue': (u'Category redirect', + u'分類彈去', + u'分類跳轉',), }

self.disambiguationTemplates = {

Modified: trunk/pywikipedia/family.py =================================================================== --- trunk/pywikipedia/family.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/family.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -2852,7 +2852,7 @@ }

# A list of category redirect template names in different languages - # Note: It is *not* necessary to list template redirects here + # Note: It *is* necessary to list template redirects here self.category_redirect_templates = { '_default': [] }

Modified: trunk/pywikipedia/redirect.py =================================================================== --- trunk/pywikipedia/redirect.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/redirect.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -252,7 +252,7 @@ mysite = wikipedia.getSite() # retrieve information from the live wiki's maintenance page # double redirect maintenance page's URL - # wikipedia.config.special_page_limit = 1000 + wikipedia.config.special_page_limit = 1000 path = mysite.double_redirects_address(default_limit = False) wikipedia.output(u'Retrieving special page...') maintenance_txt = mysite.getUrl(path)

Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/wikipedia.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -3415,7 +3415,13 @@ break groupID = groupMatch.group('name') or int(groupMatch.group('number')) replacement = replacement[:groupMatch.start()] + match.group(groupID) + replacement[groupMatch.end():] - text = text[:match.start()] + replacement + text[match.end():] + try: + text = text[:match.start()] + replacement + text[match.end():] + except: + print text + print match.start(), match.end() + print replacement + raise

# continue the search on the remaining text if allowoverlap:

Modified: trunk/pywikipedia/xmlreader.py =================================================================== --- trunk/pywikipedia/xmlreader.py 2009-01-18 15:06:07 UTC (rev 6265) +++ trunk/pywikipedia/xmlreader.py 2009-01-18 22:23:28 UTC (rev 6266) @@ -160,8 +160,8 @@ # Remove trailing newlines and spaces while text and text[-1] in '\n ': text = text[:-1] - # Replace newline by cr/nl - text = u'\r\n'.join(text.split('\n')) +## # Replace newline by cr/nl +## text = u'\r\n'.join(text.split('\n')) # Decode the timestamp timestamp = (self.timestamp[0:4]+ self.timestamp[5:7]+