pywikibot July 2007

pywikibot@lists.wikimedia.org

16 participants
48 discussions

[Pywikipedia-l] SVN: [3918] trunk/pywikiparser

by valhallasw＠svn.wikimedia.org

Revision: 3918 Author: valhallasw Date: 2007-07-28 13:29:12 +0000 (Sat, 28 Jul 2007) Log Message: ----------- Split parser. XML parser now with $Id$ ;) Modified Paths: -------------- trunk/pywikiparser/ObjectTree/XMLParse.py Added Paths: ----------- trunk/pywikiparser/Lexer.py trunk/pywikiparser/Parser.py Removed Paths: ------------- trunk/pywikiparser/parser.py Added: trunk/pywikiparser/Lexer.py =================================================================== --- trunk/pywikiparser/Lexer.py (rev 0) +++ trunk/pywikiparser/Lexer.py 2007-07-28 13:29:12 UTC (rev 3918) @@ -0,0 +1,110 @@ +# -*- coding: utf-8 -*- +""" Mediawiki wikitext lexer """ +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' + +import re + +class Token: + TEXT = 258 # Text + SQRE_OPEN = 259 # [ Square bracket open + SQRE_CLOSE = 260 # ] Square bracket close + PIPE = 261 # | Pipe symbol + EQUAL_SIGN = 262 # = Equal sign + APOSTROPHE = 263 # ' Apostrophe + CURL_OPEN = 264 # { Curly bracket open + CURL_CLOSE = 265 # } Curly bracket close + ANGL_OPEN = 266 # < Angular bracket open + ANGL_CLOSE = 267 # > Angular bracket close + NEWPAR = 268 # \n\n New paragraph + TAB_OPEN = 269 # {| Table opening symbol + TAB_NEWLINE = 270 # |- Table new row symbol + TAB_CLOSE = 271 # |} Table closing symbol + WHITESPACE = 272 # Whitespace with max 1 newline + EOF = 273 # End of file + +class Lexer: + """ Lexer class for mediawiki wikitext. Used by the Parser module + + >>> l = Lexer('Test with [[wikilink|description]], {{template|parameter\\'s|{{nested}}=booh}}, \n\n new paragraphs, <html>, {| tables |- |}') + >>> gen = l.lexer() + >>> [token for token in gen] + [(258, 'Test'), (272, ' '), (258, 'with'), (272, ' '), (259, 2), (258, 'wikilink'), (261, None), (258, 'description'), (260, 2), (258, ','), (272, ' '), (264, 2), (258, 'template'), (261, None), (258, 'parameter'), (263, 1), (258, 's'), (261, None), (264, 2), (258, 'nested'), (265, 2), (262, 1), (258, 'booh'), (265, 2), (258, ','), (268, ' \n\n '), (258, 'new'), (272, ' '), (258, 'paragraphs,'), (272, ' '), (266, 1), (258, 'html'), (267, 1), (258, ','), (272, ' '), (264, 1), (261, None), (272, ' '), (258, 'tables'), (272, ' '), (270, None), (258, '-'), (271, None), (273, None)] + """ + + def __init__(self, string): + self.data = (a for a in string) + + def lexer(self): + text = '' + try: + c = self.getchar() + while True: + if (c in ('[', ']', '{', '}', '<', '>', '=', '\'')): + if text: + yield (Token.TEXT, text) + text = '' + num = 1 + try: + t = self.getchar() + while (t == c): + num += 1 + t = self.getchar() + + finally: + if (c == '['): yield (Token.SQRE_OPEN, num) + elif (c == ']'): yield (Token.SQRE_CLOSE, num) + elif (c == '{'): yield (Token.CURL_OPEN, num) + elif (c == '}'): yield (Token.CURL_CLOSE, num) + elif (c == '<'): yield (Token.ANGL_OPEN, num) + elif (c == '>'): yield (Token.ANGL_CLOSE, num) + elif (c == '='): yield (Token.EQUAL_SIGN, num) + elif (c == '\''): yield(Token.APOSTROPHE, num) + c = t + elif (c == '|'): + if text: + yield (Token.TEXT, text) + text = '' + try: + t = self.getchar() + except StopIteration: + yield (Token.PIPE, None) + raise + + if (t == '-'): + yield (Token.TAB_NEWLINE, None) + c = self.getchar() + elif (t == '}'): + yield (Token.TAB_CLOSE, None) + c = self.getchar() + else: + yield (Token.PIPE, None) + c = t + elif re.match('\s', c): # whitespace eater pro (TM) + if text: + yield (Token.TEXT, text) + text = '' + ws = '' + try: + while re.match('\s', c): + ws += c + c = self.getchar() #eat up remaining whitespace + finally: + if (ws.count('\n') > 1): + yield (Token.NEWPAR, ws) + else: + yield (Token.WHITESPACE, ws) + else: + text = text + c + c = self.getchar() + except StopIteration: pass + if text: + yield (Token.TEXT, text) + yield (Token.EOF, None) + + def getchar(self): + return self.data.next() \ No newline at end of file Property changes on: trunk/pywikiparser/Lexer.py ___________________________________________________________________ Name: svn:keywords + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native Name: svn:executable *.txt + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native Name: svn:eol-style + native Modified: trunk/pywikiparser/ObjectTree/XMLParse.py =================================================================== --- trunk/pywikiparser/ObjectTree/XMLParse.py 2007-07-28 13:09:37 UTC (rev 3917) +++ trunk/pywikiparser/ObjectTree/XMLParse.py 2007-07-28 13:29:12 UTC (rev 3918) @@ -8,6 +8,7 @@ # # Distributed under the terms of the MIT license. # +__version__ = u'$Id$' import warnings import xml.sax Added: trunk/pywikiparser/Parser.py =================================================================== --- trunk/pywikiparser/Parser.py (rev 0) +++ trunk/pywikiparser/Parser.py 2007-07-28 13:29:12 UTC (rev 3918) @@ -0,0 +1,208 @@ +# -*- coding: utf-8 -*- +""" Mediawiki wikitext parser """ +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' + +# + +import re +import warnings + +import ObjectTree as dom + +from Lexer import Lexer, Token + + +# System loosely based on 'the dragon book': +# Compilers, Principles, Techniques and Tools, Aho, Sethi, Ullman, 1st edition, 1986 + +class ParseError(Exception): + """ booh """ + +class parser: + def __init__(self, string): + self.wikipwn = [a for a in lexer(string).lexer()] + self.counter = 0 + + def expect(self, types, values=None): + #print 'Expect: %s %s' % (types, values) + token = self.wikipwn[self.counter] + if (token[0] not in types): + if values: + raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) + else: + raise ParseError("Expected one of (%r), got %r" % (types, token)) + if values: + if (token[1] not in values): + raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) + self.counter += 1 + return token + + def parsetext(self): + data = '' + try: + while(True): data += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError, e: pass + + k = dom.Element('parsetext') + k.append(data) + return k + + def parseurl(self): + pre = self.expect([lexer.SQRE_OPEN])[1]-1 + url = self.expect([lexer.TEXT])[1] + # checkurl, raise ParseError + ws = '' + try: + ws = self.expect([lexer.WHITESPACE])[1] + except ParseError: pass + + if '\n' in ws: + raise ParseError('No newlines allowed in external links') + + desc = '' + try: + while(True): desc += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError, e: pass + + aft = self.expect([lexer.SQRE_CLOSE])[1]-1 + + root = dom.Element('parseurl') + root.append('['*pre) + extlink = root.appendElement('externallink') + extlink.appendElement('url').append(url) + if len(desc) > 0: + extlink.appendElement('description').append(desc) + root.append(']'*aft) + + return root + + def parsewikilink(self): + pre = self.expect([lexer.SQRE_OPEN])[1]-2 + if (pre < 0): raise ParseError('Not a wiki link') + + page = '' + try: + while(True): page += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError,e: pass + # if not re.match(...): raise ParseError + + root = dom.Element('parsewikilink') + root.append('['*pre) + pagelink = root.appendElement('pagelink') + pagelink.appendElement('title').append(page) + print 'wikilink: %s' % page + try: + while(True): + root.append(self.parseparameter(breaktokens=[lexer.SQRE_CLOSE])) + except ParseError, e: pass + print 'result: %r' % (root,) + aft = self.expect([lexer.SQRE_CLOSE])[1]-2 + if (aft < 0): + raise ParseError('Not a wiki link') + + root.append(']'*aft) + return root + + def parseparameter(self, breaktokens=None): + if breaktokens: + breaktokens.append(lexer.PIPE) + else: + breaktokens = [lexer.PIPE] + try: + while(True): self.expect([lexer.WHITESPACE]) #eat whitespace + except ParseError: pass + self.expect([lexer.PIPE]) + #now we can expect anything except a loose pipe. + data = self.parse(breaktokens=breaktokens) + return dom.Element('parameter', {}, data) + + def parseone(self, breaktokens=[]): + token = self.wikipwn[self.counter] + if (token[0] == lexer.EOF) or (token[0] in breaktokens): + raise StopIteration + + if (token[0] == lexer.TEXT or token[0] == lexer.WHITESPACE): #text + try: return self.parsetext(); + except ParseError, e: pass + + if (token[0] == lexer.SQRE_OPEN): #wikilink or external link + begin = self.counter + try: return self.parsewikilink(); + except ParseError, e: pass + self.counter = begin + try: return self.parseurl(); + except ParseError, e: pass + self.counter = begin + return ('[' * self.expect([lexer.SQRE_OPEN])[1]) + + if (token[0] == lexer.SQRE_CLOSE): + return ']'*self.expect([lexer.SQRE_CLOSE])[1] + + if (token[0] == lexer.PIPE): + self.expect([lexer.PIPE]) + return '|' + + if (token[0] == lexer.CURL_OPEN): + #parse_template + warnings.warn("Not implemented yet. Returning string") + return '{'*self.expect([lexer.CURL_OPEN])[1] + + if (token[0] == lexer.CURL_CLOSE): + return '}'*self.expect([lexer.CURL_CLOSE])[1] + + if (token[0] == lexer.ANGL_OPEN): + #parse html + warnings.warn("Not implemented yet. Returning string") + return '<'*self.expect([lexer.ANGL_OPEN])[1] + + if (token[0] == lexer.ANGL_CLOSE): + return '>'*self.expect([lexer.ANGL_CLOSE])[1] + + if (token[0] == lexer.NEWPAR): + self.expect([lexer.NEWPAR]) + return '\n\n' + + if (token[0] == lexer.TAB_OPEN): + # parse wikitable + warnings.warn("Not implemented yet. Returning string") + self.expect([lexer.TAB_OPEN]) + return '(|' + + if (token[0] == lexer.TAB_NEWLINE): + self.expect([lexer.TAB_NEWLINE]) + return '|-' + + if (token[0] == lexer.TAB_CLOSE): + self.expect([lexer.TAB_CLOSE]) + return '|}' + + if (token[0] == lexer.WHITESPACE): + return self.expect([lexer.WHITESPACE])[1] + + if (token[0] == lexer.EQUAL_SIGN): + return '='*self.expect([lexer.EQUAL_SIGN])[1] + + if (token[0] == lexer.APOSTROPHE): + return '\''*self.expect([lexer.APOSTROPHE])[1] + + else: + raise Exception, 'ZOMG THIS CANNOT HAPPEN' + + def parseonegenerator(self, *args, **kwargs): + while(True): + yield self.parseone(*args, **kwargs) + + def parse(self, *args, **kwargs): + root = dom.Element('wikipage') + for data in self.parseonegenerator(*args, **kwargs): + root.extend(data) + return root + + + + \ No newline at end of file Property changes on: trunk/pywikiparser/Parser.py ___________________________________________________________________ Name: svn:keywords + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native Name: svn:executable *.txt + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native Name: svn:eol-style + native Deleted: trunk/pywikiparser/parser.py =================================================================== --- trunk/pywikiparser/parser.py 2007-07-28 13:09:37 UTC (rev 3917) +++ trunk/pywikiparser/parser.py 2007-07-28 13:29:12 UTC (rev 3918) @@ -1,217 +0,0 @@ -# -*- coding: utf-8 -*- -""" Mediawiki wikitext parser """ -# -# (C) 2007 Merlijn 'valhallasw' van Deen -# -# Distributed under the terms of the MIT license. -# -__version__ = '$Id$' - -# - -import re -import xml.dom.minidom as dom - -# System loosely based on 'the dragon book': -# Compilers, Principles, Techniques and Tools, Aho, Sethi, Ullman, 1st edition, 1986 - -class ParseError(Exception): - """ booh """ - -class parser: - def __init__(self, string): - self.wikipwn = [a for a in lexer(string).lexer()] - self.counter = 0 - - def expect(self, types, values=None): - #print 'Expect: %s %s' % (types, values) - token = self.wikipwn[self.counter] - if (token[0] not in types): - if values: - raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) - else: - raise ParseError("Expected one of (%r), got %r" % (types, token)) - if values: - if (token[1] not in values): - raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) - self.counter += 1 - return token - - def parsetext(self): - data = '' - try: - while(True): data += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError, e: pass - return data - - def parseurl(self): - pre = self.expect([lexer.SQRE_OPEN])[1]-1 - url = self.expect([lexer.TEXT])[1] - # checkurl, raise ParseError - try: - ws = self.expect([lexer.WHITESPACE])[1] - except ParseError: - aft = self.expect([lexer.SQRE_CLOSE])[1]-1 - return ('['*pre, url, ']'*aft) - - if '\n' in ws: - raise ParseError('No newlines allowed in external links') - desc = '' - try: - while(True): desc += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError, e: pass - aft = self.expect([lexer.SQRE_CLOSE])[1]-1 - return ('['*pre, url, desc, ']'*aft) - - def parsewikilink(self): - pre = self.expect([lexer.SQRE_OPEN])[1]-2 - if (pre < 0): raise ParseError('Not a wiki link') - page = '' - try: - while(True): page += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError,e: pass - # if not re.match(...): raise ParseError - try: - aft = self.expect([lexer.SQRE_CLOSE])[1]-2 - except ParseError, e: pass - else: - if (aft < 0): - raise ParseError('Not a wiki link') - return ('['*pre, page, ']'*aft) - print 'boom.' - return 0 - - def parseone(self): - token = self.wikipwn[self.counter] - if (token[0] == lexer.EOF): - raise StopIteration - if (token[0] == lexer.TEXT or token[0] == lexer.WHITESPACE): #text - try: return self.parsetext(); - except ParseError, e: pass - if (token[0] == lexer.SQRE_OPEN): #wikilink or external link - begin = self.counter - try: return self.parsewikilink(); - except ParseError, e: pass - self.counter = begin - try: return self.parseurl(); - except ParseError, e: pass - self.counter = begin - return ('[' * self.expect([lexer.SQRE_OPEN])[1]) - - try: self.expect([lexer.SQRE_OPEN], [1]) - except ParseError, e: pass - else: return self.parseurl() - - # Wikilink - try: self.expect([lexer.SQRE_OPEN], [2]) #wikilink - except ParseError, e: pass - -class lexer: - class TEXT: - """ Text """ - class SQRE_OPEN: - """ Square bracket open """ - class SQRE_CLOSE: - """ Square bracket close """ - class PIPE: - """ Pipe symbol """ - class CURL_OPEN: - """ Curly bracket open """ - class CURL_CLOSE: - """ Curly bracket close """ - class ANGL_OPEN: - """ Angular bracket open """ - class ANGL_CLOSE: - """ Angular bracket close """ - class NEWPAR: - """ New paragraph """ - class TAB_OPEN: - """ Table open """ - class TAB_NEWLINE: - """ Table new row """ - class TAB_CLOSE: - """ Table close """ - class WHITESPACE: - """ Whitespace """ - class EQUAL_SIGN: - """ Equal sign """ - class APOSTROPHE: - """ Apostrophe """ - class EOF: - """ End Of File """ - - def __init__(self, string): - self.wikipwn = (a for a in string) - - def lexer(self): - text = '' - try: - c = self.getchar() - while True: - if (c in ('[', ']', '{', '}', '<', '>', '=', '\'')): - if text: - yield (lexer.TEXT, text) - text = '' - num = 1 - try: - t = self.getchar() - while (t == c): - t = self.getchar() - num += 1 - finally: - if (c == '['): yield (lexer.SQRE_OPEN, num) - elif (c == ']'): yield (lexer.SQRE_CLOSE, num) - elif (c == '{'): yield (lexer.CURL_OPEN, num) - elif (c == '}'): yield (lexer.CURL_CLOSE, num) - elif (c == '<'): yield (lexer.ANGL_OPEN, num) - elif (c == '>'): yield (lexer.ANGL_CLOSE, num) - elif (c == '='): yield (lexer.EQUAL_SIGN, num) - elif (c == '\''): yield(lexer.APOSTROPHE, num) - c = t - elif (c == '|'): - if text: - yield (lexer.TEXT, text) - text = '' - try: - t = self.getchar() - except StopIteration: - yield (lexer.PIPE, None) - raise - - if (t == '-'): - yield (lexer.TAB_NEWLINE, None) - c = self.getchar() - elif (t == '}'): - yield (lexer.TAB_CLOSE, None) - c = self.getchar() - else: - yield (lexer.PIPE, None) - c = t - elif re.match('\s', c): # whitespace eater pro (TM) - if text: - yield (lexer.TEXT, text) - text = '' - ws = '' - try: - while re.match('\s', c): - ws += c - c = self.getchar() #eat up remaining whitespace - finally: - if (ws.count('\n') > 1): - yield (lexer.NEWPAR, ws) - else: - yield (lexer.WHITESPACE, ws) - else: - text = text + c - c = self.getchar() - except StopIteration: pass - if text: - yield (lexer.TEXT, text) - yield (lexer.EOF, None) - - def getchar(self): - return self.wikipwn.next() - - - - \ No newline at end of file

16 years, 8 months

[Pywikipedia-l] SVN: [3917] trunk/pywikiparser

by valhallasw＠svn.wikimedia.org

Revision: 3917 Author: valhallasw Date: 2007-07-28 13:09:37 +0000 (Sat, 28 Jul 2007) Log Message: ----------- ObjectTree modules (simple XML tree) Added Paths: ----------- trunk/pywikiparser/ObjectTree/ trunk/pywikiparser/ObjectTree/Element.py trunk/pywikiparser/ObjectTree/XMLParse.py trunk/pywikiparser/ObjectTree/__init__.py Added: trunk/pywikiparser/ObjectTree/Element.py =================================================================== --- trunk/pywikiparser/ObjectTree/Element.py (rev 0) +++ trunk/pywikiparser/ObjectTree/Element.py 2007-07-28 13:09:37 UTC (rev 3917) @@ -0,0 +1,111 @@ +# -*- coding: utf-8 -*- +""" +Simple object tree system for python. +This module contains the Element class +""" +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# +__version__ = u'$Id$' + +class Element(list): + """ + Element in the element tree. Usage examples: + + >>> book = Element(u'book', {u'title': u'Wikitext Parsing', u'authors': u'valhallasw'}) + >>> chapter = Element(u'chapter', {u'title': u'Wikitext'}) + >>> section = chapter.appendElement(u'section', {u'title': u'Basic principles of wikitext'}) + >>> book.append(chapter) + >>> section.append(u'Wikitext was created as a way to implement formatting in plain text files, in a user friendly way. ....') + >>> book.toxml() + u'<book authors="valhallasw" title="Wikitext Parsing"><chapter title="Wikitext"><section title="Basic principles of wikitext">Wikitext was created as a way to implement formatting in plain text files, in a user friendly way. ....</section></chapter></book>' + >>> print book.toxml(True, symbol=u' ') + <book authors="valhallasw" title="Wikitext Parsing"> + <chapter title="Wikitext"> + <section title="Basic principles of wikitext"> + Wikitext was created as a way to implement formatting in plain text files, in a user friendly way. .... + </section> + </chapter> + </book> + """ + + def __init__(self, element_name, element_attributes={}, contents=[]): + self.name = element_name + self.attributes = element_attributes + self.parent = None + for item in contents: + self.append(item) + + def toxml(self, pretty=False, level=1, symbol=u'\t'): + retval = u'<%s' % (self.name,) + for (attribute, value) in self.attributes.iteritems(): + retval += u' %s="%s"' % (attribute, xmlify(value)) + if len(self) == 0: + retval += u'/>' + return retval + retval += u'>' + if pretty: + for subelement in self: + if isinstance(subelement, unicode): + retval += u'\n' + symbol*level + xmlify(subelement) + else: + retval += u'\n' + symbol*level + subelement.toxml(pretty, level+1, symbol) + retval += u'\n' + symbol*(level-1) + '</%s>' % (self.name,) + else: + for subelement in self: + if isinstance(subelement, unicode): + retval += xmlify(subelement) + elif isinstance(subelement, str): + print "THIS SHOULD NOT HAPPEN: String '%s' found!" % subelement + retval += xmlify(subelement) + else: + retval += subelement.toxml(pretty, level+1, symbol) + retval += u'</%s>' % (self.name,) + return retval + + def __repr__(self): + return u"<'%s' element: %r %s>" % (self.name, self.attributes, list.__repr__(self)) + + def append(self, arg): + if isinstance(arg, basestring): + if len(arg) == 0: #don't attach empty strings + return + try: + if isinstance(self[-1], unicode): #we convert to unicode! + self[-1] += unicode(arg) + else: + list.append(self, unicode(arg)) + except IndexError: + list.append(self, unicode(arg)) + elif isinstance(arg, Element): + list.append(self, arg) + arg.parent = self + else: + raise TypeError(u'Argument is of %r; expected <type \'BaseElement\'>.' % (type(arg),)) + + + def appendElement(self, *args, **kwargs): + element = Element(*args, **kwargs) + self.append(element) + return element + +def xmlify(data): + """ + >>> xmlify(u'mooh&<>\\'"') + u'mooh&<>'"' + """ + data = data.replace(u'&', u'&') + data = data.replace(u'<', u'<') + data = data.replace(u'>', u'>') + data = data.replace(u"'", u''') + data = data.replace(u'"', u'"') + return data + +def _test(*args, **kwargs): + import doctest + doctest.testmod(*args, **kwargs) + +if __name__ == "__main__": + _test() \ No newline at end of file Property changes on: trunk/pywikiparser/ObjectTree/Element.py ___________________________________________________________________ Name: svn:keywords + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native Name: svn:executable *.txt + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native Name: svn:eol-style + native Added: trunk/pywikiparser/ObjectTree/XMLParse.py =================================================================== --- trunk/pywikiparser/ObjectTree/XMLParse.py (rev 0) +++ trunk/pywikiparser/ObjectTree/XMLParse.py 2007-07-28 13:09:37 UTC (rev 3917) @@ -0,0 +1,51 @@ +# -*- coding: utf-8 -*- +""" +Simple object tree system for python. +This module contains the XML parser +""" +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# + +import warnings +import xml.sax + +import Element + +class XMLParser(xml.sax.handler.ContentHandler): + def __init__(self): + self.root = Element('root') + self.currentNode = self.root + + def startElement(self, name, attrs): + self.currentNode = self.currentNode.appendElement(name, dict(attrs.items())) + + def endElement(self, name): + if self.currentNode.name == name: + self.currentNode = self.currentNode.parent + else: + warnings.warn("Parse warning: recieved </%s>, expected </%s>." % (name, self.currentNode.name)) + + def characters(self, data): + self.currentNode.append(data) + +def parseText(data): + """ Parses XML Text data to an object tree. + Examples: + >>> text = '<root>Hello, <bold>this</bold> is a test! <link rel="blah" /></root>' + >>> tree = parseText(text) + >>> tree + <'root' element: {} [u'Hello, ', <'bold' element: {} [u'this']>, u' is a test! ', <'link' element: {u'rel': u'blah'} []>]> + >>> tree.toxml() + u'<root>Hello, <bold>this</bold> is a test! <link rel="blah"/></root>' + + >>> parseText("<root><nonclosed></root>") + Traceback (most recent call last): + ... + SAXParseException: <unknown>:1:19: mismatched tag + """ + handler = XMLParser() + xml.sax.parseString(data, handler) + return handler.root[0] \ No newline at end of file Property changes on: trunk/pywikiparser/ObjectTree/XMLParse.py ___________________________________________________________________ Name: svn:keywords + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native Name: svn:executable *.txt + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native Name: svn:eol-style + native Added: trunk/pywikiparser/ObjectTree/__init__.py =================================================================== --- trunk/pywikiparser/ObjectTree/__init__.py (rev 0) +++ trunk/pywikiparser/ObjectTree/__init__.py 2007-07-28 13:09:37 UTC (rev 3917) @@ -0,0 +1,13 @@ +# -*- coding: utf-8 -*- +""" Simple object tree system for python """ +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# +__version__ = u'$Id$' + +__all__ = ['Element', 'XMLParse'] + +from Element import Element +from XMLParse import parseText \ No newline at end of file Property changes on: trunk/pywikiparser/ObjectTree/__init__.py ___________________________________________________________________ Name: svn:keywords + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native Name: svn:executable *.txt + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native Name: svn:eol-style + native

16 years, 8 months

[Pywikipedia-l] SVN: [3916] trunk/pywikipedia

by valhallasw＠svn.wikimedia.org

Revision: 3916 Author: valhallasw Date: 2007-07-27 18:05:19 +0000 (Fri, 27 Jul 2007) Log Message: ----------- added 'some' $Id$'s Modified Paths: -------------- trunk/pywikipedia/basic.py trunk/pywikipedia/capitalize_redirects.py trunk/pywikipedia/casechecker.py trunk/pywikipedia/cosmetic_changes.py trunk/pywikipedia/delete.py trunk/pywikipedia/fixes.py trunk/pywikipedia/image.py trunk/pywikipedia/interwiki_graph.py trunk/pywikipedia/misspelling.py trunk/pywikipedia/query.py trunk/pywikipedia/rcsort.py trunk/pywikipedia/refcheck.py trunk/pywikipedia/spamremove.py trunk/pywikipedia/speedy_delete.py trunk/pywikipedia/templatecount.py trunk/pywikipedia/udp-log.py trunk/pywikipedia/unusedfiles.py trunk/pywikipedia/us-states.py trunk/pywikipedia/userlib.py trunk/pywikipedia/welcome.py trunk/pywikipedia/wikipediatools.py trunk/pywikipedia/wiktionarytest.py Modified: trunk/pywikipedia/basic.py =================================================================== --- trunk/pywikipedia/basic.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/basic.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- """ This is not a complete bot; rather, it is a template from which simple @@ -18,6 +18,7 @@ -debug: Don't do any changes. """ +__version__ = '$Id$' import wikipedia import pagegenerators import sys Modified: trunk/pywikipedia/capitalize_redirects.py =================================================================== --- trunk/pywikipedia/capitalize_redirects.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/capitalize_redirects.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,9 +1,10 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- # # (C) Yrithinnd # Class licensed under terms of the MIT license # +__version__ = '$Id$' import time, sys import wikipedia, pagegenerators, catlib Modified: trunk/pywikipedia/casechecker.py =================================================================== --- trunk/pywikipedia/casechecker.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/casechecker.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,8 +1,9 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- """ Script to enumerate all pages on the wiki and find all titles with mixed latin and cyrilic alphabets. """ +__version__ = '$Id$' # # Permutations code was taken from http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/190465 Modified: trunk/pywikipedia/cosmetic_changes.py =================================================================== --- trunk/pywikipedia/cosmetic_changes.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/cosmetic_changes.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ This module can do slight modifications to a wiki page source code such that the code looks cleaner. The changes are not supposed to change the look of the @@ -6,7 +6,7 @@ WARNING: This module needs more testing! """ - +__version__ = '$Id$' import wikipedia, pagegenerators import sys import re Modified: trunk/pywikipedia/delete.py =================================================================== --- trunk/pywikipedia/delete.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/delete.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ This script can be used to delete and undelete pages en masse. Of course, you will need an admin account on the relevant wiki. @@ -24,6 +24,7 @@ python delete.py -cat:"To delete" -always """ +__version__ = '$Id$' # # Distributed under the terms of the MIT license. # Modified: trunk/pywikipedia/fixes.py =================================================================== --- trunk/pywikipedia/fixes.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/fixes.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,5 +1,6 @@ -# -*- coding: utf-8 -*- - +# -*- coding: utf-8 -*- +""" File containing all standard fixes """ +__version__ = '$Id$' fixes = { # These replacements will convert HTML to wiki syntax where possible, and # make remaining tags XHTML compliant. Modified: trunk/pywikipedia/image.py =================================================================== --- trunk/pywikipedia/image.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/image.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ This script can be used to change one image to another or remove an image entirely. @@ -30,6 +30,7 @@ python image.py Flag.jpg Flag.svg """ +__version__ = '$Id$' # # Distributed under the terms of the MIT license. # Modified: trunk/pywikipedia/interwiki_graph.py =================================================================== --- trunk/pywikipedia/interwiki_graph.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/interwiki_graph.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,3 +1,5 @@ +""" Module with the graphviz drawing calls """ +__version__ = '$Id$' import threading pydotfound = True try: Modified: trunk/pywikipedia/misspelling.py =================================================================== --- trunk/pywikipedia/misspelling.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/misspelling.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ This script works similar to solve_disambiguation.py. It is supposed to fix links that contain common spelling mistakes. This is only possible on wikis @@ -20,6 +20,7 @@ -main only check pages in the main namespace, not in the talk, wikipedia, user, etc. namespaces. """ +__version__ = '$Id$' # (C) Daniel Herding, 2007 # Modified: trunk/pywikipedia/query.py =================================================================== --- trunk/pywikipedia/query.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/query.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,3 +1,6 @@ +""" Please describe your module here ;) """ + +__version__ = '$Id$' import wikipedia import simplejson import urllib Modified: trunk/pywikipedia/rcsort.py =================================================================== --- trunk/pywikipedia/rcsort.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/rcsort.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,10 +1,11 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- # A tool to see the recentchanges ordered by user instead of by date. This # is meant to be run as a CGI script. # Currently only works on Dutch Wikipedia, I do intend to make it more generally # usable. # Permission has been asked to run this on the toolserver. +__version__ = '$Id$' import cgi import cgitb Modified: trunk/pywikipedia/refcheck.py =================================================================== --- trunk/pywikipedia/refcheck.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/refcheck.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -""" +""" This script checks references to see if they are properly formatted. Right now it just counts the total number of transclusions of any number of given templates. @@ -18,6 +18,7 @@ python refcheck.py -count ref note -namespace:0 """ +__version__ = '$Id$' import wikipedia, config import replace, pagegenerators Modified: trunk/pywikipedia/spamremove.py =================================================================== --- trunk/pywikipedia/spamremove.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/spamremove.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- #!/usr/bin/python import wikipedia, editarticle @@ -20,6 +20,7 @@ in using this option! """ +__version__ = '$Id$' def main(): automatic = False Modified: trunk/pywikipedia/speedy_delete.py =================================================================== --- trunk/pywikipedia/speedy_delete.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/speedy_delete.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ This bot is used to quickly trawl through candidates for speedy deletion in a fast and semi-automated fashion. The bot displays the contents of each page one at a @@ -29,6 +29,7 @@ none needed yet """ +__version__ = '$Id$' # # Distributed under the terms of the MIT license. # Modified: trunk/pywikipedia/templatecount.py =================================================================== --- trunk/pywikipedia/templatecount.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/templatecount.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -""" +""" This script will display the list of pages transcluding a given list of templates. It can also be used to simply count the number of pages (rather than listing each individually). @@ -25,6 +25,7 @@ python templatecount.py -list -namespace:14 cfd cfdu """ +__version__ = '$Id$' import wikipedia, config import replace, pagegenerators Modified: trunk/pywikipedia/udp-log.py =================================================================== --- trunk/pywikipedia/udp-log.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/udp-log.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -#/usr/bin/env python +#/usr/bin/env python # -*- coding: utf-8 -*- # # (C) Misza13 <misza1313(a)gmail.com>, 2007 @@ -6,6 +6,7 @@ # Distributed under the terms of the MIT license. # import sys, re, socket +__version__ = '$Id$' TARGET_HOST = 'tools.wikimedia.de' TARGET_PORT = 42448 Modified: trunk/pywikipedia/unusedfiles.py =================================================================== --- trunk/pywikipedia/unusedfiles.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/unusedfiles.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,10 +1,12 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- """ This bot appends some text to all unused images and other text to the respective uploaders. You are asked for confirmation before every change. """ +__version__ = '$Id$' + import wikipedia import pagegenerators import sys Modified: trunk/pywikipedia/us-states.py =================================================================== --- trunk/pywikipedia/us-states.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/us-states.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -#coding: utf-8 +#coding: utf-8 """ Check pages on the English Wikipedia whether they are in the form Something, State, and if so, create a redirect from Something, ST. @@ -14,6 +14,7 @@ -force: Don't ask whether to create pages, just create them. """ +__version__ = '$Id$' # # (C) Andre Engels, 2004 # Modified: trunk/pywikipedia/userlib.py =================================================================== --- trunk/pywikipedia/userlib.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/userlib.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,11 +1,14 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ Library to work with users, their pages and talk pages. """ +__version__ = '$Id$' import re, httplib import wikipedia + + class AutoblockUserError(wikipedia.Error): """ The class AutoblockUserError is an exception that is raised whenever Modified: trunk/pywikipedia/welcome.py =================================================================== --- trunk/pywikipedia/welcome.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/welcome.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- """ Script to welcome new users. This script works out of the box for Wikis that @@ -11,12 +11,12 @@ Ensure you have community support before running this bot! URLs to current implementations: -* Arabic Wikipedia: http://ar.wikipedia.org/wiki/ويكيبيديا:سجل الترحيب +* Arabic Wikipedia: http://ar.wikipedia.org/wiki/?????????:??? ??????? * Wikimedia Commons: http://commons.wikimedia.org/wiki/Commons:Welcome_log * Dutch Wikipedia: http://nl.wikipedia.org/wiki/Wikipedia:Logboek_welkom * Italian Wikipedia: http://it.wikipedia.org/wiki/Wikipedia:Benvenuto_log * English Wikiquote: http://en.wikiquote.org/wiki/Wikiquote:Welcome_log -* Persian Wikipedia: http://fa.wikipedia.org/wiki/ویکی‌پدیا:سیاهه خوشامد +* Persian Wikipedia: http://fa.wikipedia.org/wiki/?????????:????? ?????? Everything that needs customisation to support additional projects is indicated by comments. @@ -149,7 +149,7 @@ # # Distributed under the terms of the MIT license. # -__version__ = '$Id: welcome.py,v 1.4 2007/04/14 18:05:42 siebrand Exp' +__version__ = '$Id$' # import wikipedia, string @@ -188,10 +188,10 @@ #The page where the bot will save the log (e.g. Wikipedia:Welcome log). logbook = { 'commons': u'Project:Welcome log', - 'ar': u'Project:سجل الترحيب', + 'ar': u'Project:??? ???????', 'de': None, # no welcome log on de: 'en': u'Project:Welcome log', - 'fa': u'Project:سیاهه خوشامد', + 'fa': u'Project:????? ??????', 'it': u'Project:Benvenuto log', 'nl': u'Project:Logboek welkom', 'no': u'Project:Velkomstlogg', @@ -200,10 +200,10 @@ #The edit summary for the welcome message (e.g. Welcome!). summary = { 'commons':u'Welcome!', - 'ar':u'مرحبا!', + 'ar':u'?????!', 'de':u'Herzlich willkommen!', 'en':u'Welcome!', - 'fa':u'خوش آمدید!', + 'fa':u'??? ?????!', 'it':u'Benvenuto!', 'nl':u'Welkom!', 'no':u'Velkommen!', @@ -214,10 +214,10 @@ # sign, so in this way it will change according to your parameters). netext = { 'commons':u'{{subst:welcome}}%s', - 'ar':u'{{نسخ:مستخدم:Alnokta/ترحيب}}%s', + 'ar':u'{{???:??????:Alnokta/?????}}%s', 'de':u'{{subst:Hallo}} %s', 'en':u'{{subst:welcome}}%s', - 'fa':u'{{جا:خوشامد}}%s', + 'fa':u'{{??:??????}}%s', 'it':u'{{Benvebot}} %s', 'nl':u'{{Welkomstbericht}}%s', 'no':u'{{subst:bruker:jhs/vk}}%s', @@ -226,10 +226,10 @@ # The edit summary for updating the welcome log (e.g. Updating log). summary2 = { 'commons':u'Updating log', - 'ar':u'تحديث السجل', + 'ar':u'????? ?????', 'de':u'Aktualisiere Logdatei', 'en':u'Updating log', - 'fa':u'به روز رسانی سیاهه', + 'fa':u'?? ??? ????? ?????', 'it':u'Aggiorno il log', 'nl':u'Logboek bijwerken', 'no':u'Oppdaterer logg', @@ -238,10 +238,10 @@ # The page where the bot will report users with a possibly bad username. report_page = { 'commons': u'Project:Administrators\' noticeboard/User problems/Usernames to be checked', - 'ar': 'Project:إخطار الإداريين/أسماء مستخدمين للفحص', + 'ar': 'Project:????? ?????????/????? ???????? ?????', 'de': u'Benutzer:Filnik/Report', 'en': u'Project:Administrator intervention against vandalism', - 'fa': u'Project:تابلوی اعلانات مدیران/گزارش ربات', + 'fa': u'Project:?????? ??????? ??????/????? ????', 'it': u'Utente:Filbot/Report', 'nl': u'Project:Verzoekpagina voor moderatoren/RegBlok/Te controleren gebruikersnamen', 'no': u'Bruker:JhsBot II/Rapport', @@ -250,10 +250,10 @@ # The edit summary for reporting a possibly bad username. comment = { 'commons':u'Adding a username that needs to be checked', - 'ar':u'إضافة اسم مستخدم يحتاج للفحص', + 'ar':u'????? ??? ?????? ????? ?????', 'de':u'Ergänze zu überprüfenden Benutzernamen', 'en':u'Adding a username that needs to be checked', - 'fa':u'افزودن حساب کاربری نیازمند بررسی', + 'fa':u'?????? ???? ?????? ??????? ?????', 'it':u'Aggiunto utente da controllare', 'nl':u'Te controleren gebruikersnaam toegevoegd', 'no':u'Legger til et brukernavn som m? sjekkes', @@ -263,9 +263,9 @@ # (this parameter is optional). bad_pag = { 'commons': u'Project:Welcome log/Bad_names', - 'ar': u'Project:سجل الترحيب/أسماء سيئة', + 'ar': u'Project:??? ???????/????? ????', 'en': u'Project:Welcome log/Bad_names', - 'fa': u'Project:سیاهه خوشامد/نام بد', + 'fa': u'Project:????? ??????/??? ??', 'it': u'Utente:Filbot/Bad_words', 'nl': u'Project:Logboek_welkom/Bad_names', 'no': u'Bruker:JhsBot/Daarlige ord', @@ -278,7 +278,7 @@ 'ar':u"\n*{{user13|%s}}" + timeselected, 'de':u'\n*[[Benutzer Diskussion:%s]] ' + timeselected, 'en':u'\n*{{Userlinks|%s}} ' + timeselected, - 'fa':u'\n*{{کاربر|%s}}' + timeselected, + 'fa':u'\n*{{?????|%s}}' + timeselected, 'it':u"\n{{Reported|%s|", 'nl':u'\n*{{linkgebruiker%s}} ' + timeselected, 'no':u'\n*{{bruker|%s}} ' + timeselected, @@ -287,15 +287,15 @@ # Set where you load your list of signatures that the bot will load if you use # the random argument (this parameter is optional). random_sign = { - 'ar': u'ويكيبيديا:سجل الترحيب/توقيعات', - 'fa': u'Project:سیاهه خوشامد/امضاها', + 'ar': u'?????????:??? ???????/???????', + 'fa': u'Project:????? ??????/??????', 'en': u'User:Filnik/Sign', 'it': u'Project:Benvenuto log/User', } # The page where the bot reads the real-time whitelist page. # (this parameter is optional). whitelist_pg = { - 'ar':u'ويكيبيديا:سجل الترحيب/قائمةبيضاء', + 'ar':u'?????????:??? ???????/??????????', 'en':u'User:Filnik/whitelist', 'it':u'Utente:Filbot/whitelist', } Modified: trunk/pywikipedia/wikipediatools.py =================================================================== --- trunk/pywikipedia/wikipediatools.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/wikipediatools.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,3 +1,4 @@ +__version__ = '$Id$' import os, sys def absoluteFilename(*f): Modified: trunk/pywikipedia/wiktionarytest.py =================================================================== --- trunk/pywikipedia/wiktionarytest.py 2007-07-27 17:56:52 UTC (rev 3915) +++ trunk/pywikipedia/wiktionarytest.py 2007-07-27 18:05:19 UTC (rev 3916) @@ -1,7 +1,8 @@ -#!/usr/bin/python +#!/usr/bin/python # -*- coding: utf-8 -*- """Unit tests for Wiktionary.py""" +__version__ = '$Id$' import wiktionary import unittest

16 years, 8 months

[Pywikipedia-l] SVN: [3915] trunk/pywikipedia/welcome.py

by valhallasw＠svn.wikimedia.org

Revision: 3915 Author: valhallasw Date: 2007-07-27 17:56:52 +0000 (Fri, 27 Jul 2007) Log Message: ----------- test commit; testing if re-setting svn:keyword helps Property Changed: ---------------- trunk/pywikipedia/welcome.py Property changes on: trunk/pywikipedia/welcome.py ___________________________________________________________________ Name: svn:keywords - Author Date Id Revision + Id Author Date Revision

16 years, 8 months

[Pywikipedia-l] SVN: [3914] trunk

by valhallasw＠svn.wikimedia.org

Revision: 3914 Author: valhallasw Date: 2007-07-27 15:27:56 +0000 (Fri, 27 Jul 2007) Log Message: ----------- moved wikitext parser to own project directory Added Paths: ----------- trunk/pywikiparser/ trunk/pywikiparser/parser.py Removed Paths: ------------- trunk/pywikipedia/parser.py Copied: trunk/pywikiparser/parser.py (from rev 3913, trunk/pywikipedia/parser.py) =================================================================== --- trunk/pywikiparser/parser.py (rev 0) +++ trunk/pywikiparser/parser.py 2007-07-27 15:27:56 UTC (rev 3914) @@ -0,0 +1,217 @@ +# -*- coding: utf-8 -*- +""" Mediawiki wikitext parser """ +# +# (C) 2007 Merlijn 'valhallasw' van Deen +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' + +# + +import re +import xml.dom.minidom as dom + +# System loosely based on 'the dragon book': +# Compilers, Principles, Techniques and Tools, Aho, Sethi, Ullman, 1st edition, 1986 + +class ParseError(Exception): + """ booh """ + +class parser: + def __init__(self, string): + self.wikipwn = [a for a in lexer(string).lexer()] + self.counter = 0 + + def expect(self, types, values=None): + #print 'Expect: %s %s' % (types, values) + token = self.wikipwn[self.counter] + if (token[0] not in types): + if values: + raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) + else: + raise ParseError("Expected one of (%r), got %r" % (types, token)) + if values: + if (token[1] not in values): + raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) + self.counter += 1 + return token + + def parsetext(self): + data = '' + try: + while(True): data += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError, e: pass + return data + + def parseurl(self): + pre = self.expect([lexer.SQRE_OPEN])[1]-1 + url = self.expect([lexer.TEXT])[1] + # checkurl, raise ParseError + try: + ws = self.expect([lexer.WHITESPACE])[1] + except ParseError: + aft = self.expect([lexer.SQRE_CLOSE])[1]-1 + return ('['*pre, url, ']'*aft) + + if '\n' in ws: + raise ParseError('No newlines allowed in external links') + desc = '' + try: + while(True): desc += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError, e: pass + aft = self.expect([lexer.SQRE_CLOSE])[1]-1 + return ('['*pre, url, desc, ']'*aft) + + def parsewikilink(self): + pre = self.expect([lexer.SQRE_OPEN])[1]-2 + if (pre < 0): raise ParseError('Not a wiki link') + page = '' + try: + while(True): page += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] + except ParseError,e: pass + # if not re.match(...): raise ParseError + try: + aft = self.expect([lexer.SQRE_CLOSE])[1]-2 + except ParseError, e: pass + else: + if (aft < 0): + raise ParseError('Not a wiki link') + return ('['*pre, page, ']'*aft) + print 'boom.' + return 0 + + def parseone(self): + token = self.wikipwn[self.counter] + if (token[0] == lexer.EOF): + raise StopIteration + if (token[0] == lexer.TEXT or token[0] == lexer.WHITESPACE): #text + try: return self.parsetext(); + except ParseError, e: pass + if (token[0] == lexer.SQRE_OPEN): #wikilink or external link + begin = self.counter + try: return self.parsewikilink(); + except ParseError, e: pass + self.counter = begin + try: return self.parseurl(); + except ParseError, e: pass + self.counter = begin + return ('[' * self.expect([lexer.SQRE_OPEN])[1]) + + try: self.expect([lexer.SQRE_OPEN], [1]) + except ParseError, e: pass + else: return self.parseurl() + + # Wikilink + try: self.expect([lexer.SQRE_OPEN], [2]) #wikilink + except ParseError, e: pass + +class lexer: + class TEXT: + """ Text """ + class SQRE_OPEN: + """ Square bracket open """ + class SQRE_CLOSE: + """ Square bracket close """ + class PIPE: + """ Pipe symbol """ + class CURL_OPEN: + """ Curly bracket open """ + class CURL_CLOSE: + """ Curly bracket close """ + class ANGL_OPEN: + """ Angular bracket open """ + class ANGL_CLOSE: + """ Angular bracket close """ + class NEWPAR: + """ New paragraph """ + class TAB_OPEN: + """ Table open """ + class TAB_NEWLINE: + """ Table new row """ + class TAB_CLOSE: + """ Table close """ + class WHITESPACE: + """ Whitespace """ + class EQUAL_SIGN: + """ Equal sign """ + class APOSTROPHE: + """ Apostrophe """ + class EOF: + """ End Of File """ + + def __init__(self, string): + self.wikipwn = (a for a in string) + + def lexer(self): + text = '' + try: + c = self.getchar() + while True: + if (c in ('[', ']', '{', '}', '<', '>', '=', '\'')): + if text: + yield (lexer.TEXT, text) + text = '' + num = 1 + try: + t = self.getchar() + while (t == c): + t = self.getchar() + num += 1 + finally: + if (c == '['): yield (lexer.SQRE_OPEN, num) + elif (c == ']'): yield (lexer.SQRE_CLOSE, num) + elif (c == '{'): yield (lexer.CURL_OPEN, num) + elif (c == '}'): yield (lexer.CURL_CLOSE, num) + elif (c == '<'): yield (lexer.ANGL_OPEN, num) + elif (c == '>'): yield (lexer.ANGL_CLOSE, num) + elif (c == '='): yield (lexer.EQUAL_SIGN, num) + elif (c == '\''): yield(lexer.APOSTROPHE, num) + c = t + elif (c == '|'): + if text: + yield (lexer.TEXT, text) + text = '' + try: + t = self.getchar() + except StopIteration: + yield (lexer.PIPE, None) + raise + + if (t == '-'): + yield (lexer.TAB_NEWLINE, None) + c = self.getchar() + elif (t == '}'): + yield (lexer.TAB_CLOSE, None) + c = self.getchar() + else: + yield (lexer.PIPE, None) + c = t + elif re.match('\s', c): # whitespace eater pro (TM) + if text: + yield (lexer.TEXT, text) + text = '' + ws = '' + try: + while re.match('\s', c): + ws += c + c = self.getchar() #eat up remaining whitespace + finally: + if (ws.count('\n') > 1): + yield (lexer.NEWPAR, ws) + else: + yield (lexer.WHITESPACE, ws) + else: + text = text + c + c = self.getchar() + except StopIteration: pass + if text: + yield (lexer.TEXT, text) + yield (lexer.EOF, None) + + def getchar(self): + return self.wikipwn.next() + + + + \ No newline at end of file Deleted: trunk/pywikipedia/parser.py =================================================================== --- trunk/pywikipedia/parser.py 2007-07-27 14:26:25 UTC (rev 3913) +++ trunk/pywikipedia/parser.py 2007-07-27 15:27:56 UTC (rev 3914) @@ -1,217 +0,0 @@ -# -*- coding: utf-8 -*- -""" Mediawiki wikitext parser """ -# -# (C) 2007 Merlijn 'valhallasw' van Deen -# -# Distributed under the terms of the MIT license. -# -__version__ = '$Id$' - -# - -import re -import xml.dom.minidom as dom - -# System loosely based on 'the dragon book': -# Compilers, Principles, Techniques and Tools, Aho, Sethi, Ullman, 1st edition, 1986 - -class ParseError(Exception): - """ booh """ - -class parser: - def __init__(self, string): - self.wikipwn = [a for a in lexer(string).lexer()] - self.counter = 0 - - def expect(self, types, values=None): - #print 'Expect: %s %s' % (types, values) - token = self.wikipwn[self.counter] - if (token[0] not in types): - if values: - raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) - else: - raise ParseError("Expected one of (%r), got %r" % (types, token)) - if values: - if (token[1] not in values): - raise ParseError("Expected one of (%r, %r), got %r" % (types, values, token)) - self.counter += 1 - return token - - def parsetext(self): - data = '' - try: - while(True): data += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError, e: pass - return data - - def parseurl(self): - pre = self.expect([lexer.SQRE_OPEN])[1]-1 - url = self.expect([lexer.TEXT])[1] - # checkurl, raise ParseError - try: - ws = self.expect([lexer.WHITESPACE])[1] - except ParseError: - aft = self.expect([lexer.SQRE_CLOSE])[1]-1 - return ('['*pre, url, ']'*aft) - - if '\n' in ws: - raise ParseError('No newlines allowed in external links') - desc = '' - try: - while(True): desc += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError, e: pass - aft = self.expect([lexer.SQRE_CLOSE])[1]-1 - return ('['*pre, url, desc, ']'*aft) - - def parsewikilink(self): - pre = self.expect([lexer.SQRE_OPEN])[1]-2 - if (pre < 0): raise ParseError('Not a wiki link') - page = '' - try: - while(True): page += self.expect([lexer.TEXT, lexer.WHITESPACE])[1] - except ParseError,e: pass - # if not re.match(...): raise ParseError - try: - aft = self.expect([lexer.SQRE_CLOSE])[1]-2 - except ParseError, e: pass - else: - if (aft < 0): - raise ParseError('Not a wiki link') - return ('['*pre, page, ']'*aft) - print 'boom.' - return 0 - - def parseone(self): - token = self.wikipwn[self.counter] - if (token[0] == lexer.EOF): - raise StopIteration - if (token[0] == lexer.TEXT or token[0] == lexer.WHITESPACE): #text - try: return self.parsetext(); - except ParseError, e: pass - if (token[0] == lexer.SQRE_OPEN): #wikilink or external link - begin = self.counter - try: return self.parsewikilink(); - except ParseError, e: pass - self.counter = begin - try: return self.parseurl(); - except ParseError, e: pass - self.counter = begin - return ('[' * self.expect([lexer.SQRE_OPEN])[1]) - - try: self.expect([lexer.SQRE_OPEN], [1]) - except ParseError, e: pass - else: return self.parseurl() - - # Wikilink - try: self.expect([lexer.SQRE_OPEN], [2]) #wikilink - except ParseError, e: pass - -class lexer: - class TEXT: - """ Text """ - class SQRE_OPEN: - """ Square bracket open """ - class SQRE_CLOSE: - """ Square bracket close """ - class PIPE: - """ Pipe symbol """ - class CURL_OPEN: - """ Curly bracket open """ - class CURL_CLOSE: - """ Curly bracket close """ - class ANGL_OPEN: - """ Angular bracket open """ - class ANGL_CLOSE: - """ Angular bracket close """ - class NEWPAR: - """ New paragraph """ - class TAB_OPEN: - """ Table open """ - class TAB_NEWLINE: - """ Table new row """ - class TAB_CLOSE: - """ Table close """ - class WHITESPACE: - """ Whitespace """ - class EQUAL_SIGN: - """ Equal sign """ - class APOSTROPHE: - """ Apostrophe """ - class EOF: - """ End Of File """ - - def __init__(self, string): - self.wikipwn = (a for a in string) - - def lexer(self): - text = '' - try: - c = self.getchar() - while True: - if (c in ('[', ']', '{', '}', '<', '>', '=', '\'')): - if text: - yield (lexer.TEXT, text) - text = '' - num = 1 - try: - t = self.getchar() - while (t == c): - t = self.getchar() - num += 1 - finally: - if (c == '['): yield (lexer.SQRE_OPEN, num) - elif (c == ']'): yield (lexer.SQRE_CLOSE, num) - elif (c == '{'): yield (lexer.CURL_OPEN, num) - elif (c == '}'): yield (lexer.CURL_CLOSE, num) - elif (c == '<'): yield (lexer.ANGL_OPEN, num) - elif (c == '>'): yield (lexer.ANGL_CLOSE, num) - elif (c == '='): yield (lexer.EQUAL_SIGN, num) - elif (c == '\''): yield(lexer.APOSTROPHE, num) - c = t - elif (c == '|'): - if text: - yield (lexer.TEXT, text) - text = '' - try: - t = self.getchar() - except StopIteration: - yield (lexer.PIPE, None) - raise - - if (t == '-'): - yield (lexer.TAB_NEWLINE, None) - c = self.getchar() - elif (t == '}'): - yield (lexer.TAB_CLOSE, None) - c = self.getchar() - else: - yield (lexer.PIPE, None) - c = t - elif re.match('\s', c): # whitespace eater pro (TM) - if text: - yield (lexer.TEXT, text) - text = '' - ws = '' - try: - while re.match('\s', c): - ws += c - c = self.getchar() #eat up remaining whitespace - finally: - if (ws.count('\n') > 1): - yield (lexer.NEWPAR, ws) - else: - yield (lexer.WHITESPACE, ws) - else: - text = text + c - c = self.getchar() - except StopIteration: pass - if text: - yield (lexer.TEXT, text) - yield (lexer.EOF, None) - - def getchar(self): - return self.wikipwn.next() - - - - \ No newline at end of file

16 years, 8 months

[Pywikipedia-l] SVN: [3913] trunk/pywikipedia/welcome.py

by valhallasw＠svn.wikimedia.org

Revision: 3913 Author: valhallasw Date: 2007-07-27 14:26:25 +0000 (Fri, 27 Jul 2007) Log Message: ----------- update for persian wikipedia by hojjat Modified Paths: -------------- trunk/pywikipedia/welcome.py Modified: trunk/pywikipedia/welcome.py =================================================================== --- trunk/pywikipedia/welcome.py 2007-07-27 13:14:30 UTC (rev 3912) +++ trunk/pywikipedia/welcome.py 2007-07-27 14:26:25 UTC (rev 3913) @@ -16,6 +16,7 @@ * Dutch Wikipedia: http://nl.wikipedia.org/wiki/Wikipedia:Logboek_welkom * Italian Wikipedia: http://it.wikipedia.org/wiki/Wikipedia:Benvenuto_log * English Wikiquote: http://en.wikiquote.org/wiki/Wikiquote:Welcome_log +* Persian Wikipedia: http://fa.wikipedia.org/wiki/ویکی‌پدیا:سیاهه خوشامد Everything that needs customisation to support additional projects is indicated by comments. @@ -190,6 +191,7 @@ 'ar': u'Project:سجل الترحيب', 'de': None, # no welcome log on de: 'en': u'Project:Welcome log', + 'fa': u'Project:سیاهه خوشامد', 'it': u'Project:Benvenuto log', 'nl': u'Project:Logboek welkom', 'no': u'Project:Velkomstlogg', @@ -201,6 +203,7 @@ 'ar':u'مرحبا!', 'de':u'Herzlich willkommen!', 'en':u'Welcome!', + 'fa':u'خوش آمدید!', 'it':u'Benvenuto!', 'nl':u'Welkom!', 'no':u'Velkommen!', @@ -214,6 +217,7 @@ 'ar':u'{{نسخ:مستخدم:Alnokta/ترحيب}}%s', 'de':u'{{subst:Hallo}} %s', 'en':u'{{subst:welcome}}%s', + 'fa':u'{{جا:خوشامد}}%s', 'it':u'{{Benvebot}} %s', 'nl':u'{{Welkomstbericht}}%s', 'no':u'{{subst:bruker:jhs/vk}}%s', @@ -225,6 +229,7 @@ 'ar':u'تحديث السجل', 'de':u'Aktualisiere Logdatei', 'en':u'Updating log', + 'fa':u'به روز رسانی سیاهه', 'it':u'Aggiorno il log', 'nl':u'Logboek bijwerken', 'no':u'Oppdaterer logg', @@ -236,6 +241,7 @@ 'ar': 'Project:إخطار الإداريين/أسماء مستخدمين للفحص', 'de': u'Benutzer:Filnik/Report', 'en': u'Project:Administrator intervention against vandalism', + 'fa': u'Project:تابلوی اعلانات مدیران/گزارش ربات', 'it': u'Utente:Filbot/Report', 'nl': u'Project:Verzoekpagina voor moderatoren/RegBlok/Te controleren gebruikersnamen', 'no': u'Bruker:JhsBot II/Rapport', @@ -247,6 +253,7 @@ 'ar':u'إضافة اسم مستخدم يحتاج للفحص', 'de':u'Ergänze zu überprüfenden Benutzernamen', 'en':u'Adding a username that needs to be checked', + 'fa':u'افزودن حساب کاربری نیازمند بررسی', 'it':u'Aggiunto utente da controllare', 'nl':u'Te controleren gebruikersnaam toegevoegd', 'no':u'Legger til et brukernavn som m? sjekkes', @@ -258,6 +265,7 @@ 'commons': u'Project:Welcome log/Bad_names', 'ar': u'Project:سجل الترحيب/أسماء سيئة', 'en': u'Project:Welcome log/Bad_names', + 'fa': u'Project:سیاهه خوشامد/نام بد', 'it': u'Utente:Filbot/Bad_words', 'nl': u'Project:Logboek_welkom/Bad_names', 'no': u'Bruker:JhsBot/Daarlige ord', @@ -270,6 +278,7 @@ 'ar':u"\n*{{user13|%s}}" + timeselected, 'de':u'\n*[[Benutzer Diskussion:%s]] ' + timeselected, 'en':u'\n*{{Userlinks|%s}} ' + timeselected, + 'fa':u'\n*{{کاربر|%s}}' + timeselected, 'it':u"\n{{Reported|%s|", 'nl':u'\n*{{linkgebruiker%s}} ' + timeselected, 'no':u'\n*{{bruker|%s}} ' + timeselected, @@ -279,6 +288,7 @@ # the random argument (this parameter is optional). random_sign = { 'ar': u'ويكيبيديا:سجل الترحيب/توقيعات', + 'fa': u'Project:سیاهه خوشامد/امضاها', 'en': u'User:Filnik/Sign', 'it': u'Project:Benvenuto log/User', } @@ -290,7 +300,7 @@ 'it':u'Utente:Filbot/whitelist', } # Add your project (in alphabetical order) if you want that the bot start. -project_inserted = ['ar', 'commons', 'de', 'en', 'it', 'nl', 'no', 'sq'] +project_inserted = ['ar', 'commons', 'de', 'en', 'fa', 'it', 'nl', 'no', 'sq'] # Ok, that's all. What is below, is the rest of code, now the code is fixed # and it will run correctly in your project ;)

16 years, 8 months

[Pywikipedia-l] Update to welcome.py

by Hojjat

Hello. Attached you can find a patch file which updates welcome.py so it would contain the required details for a bot to work with Persian (fa) Wikipedia. I opened a request on the bug tracker (on SourceForge) today in this regard as well, but Merlijn told me to create a patch for it. The current patch is more complete that what I sent there. With this patch, that bug is obsolete, so treat it is you should. Best regards, Huji

16 years, 8 months

[Pywikipedia-l] SVN: [3912] trunk/pywikipedia/family.py

by wikipedian＠svn.wikimedia.org

Revision: 3912 Author: wikipedian Date: 2007-07-27 13:14:30 +0000 (Fri, 27 Jul 2007) Log Message: ----------- kab: namespaces Modified Paths: -------------- trunk/pywikipedia/family.py Modified: trunk/pywikipedia/family.py =================================================================== --- trunk/pywikipedia/family.py 2007-07-27 13:14:21 UTC (rev 3911) +++ trunk/pywikipedia/family.py 2007-07-27 13:14:30 UTC (rev 3912) @@ -1032,7 +1032,7 @@ 'is': u'Snið', 'jv': u'Cithakan', 'ka': u'თარგი', - 'kab': u'Talγa', + 'kab': u'Talɣa', 'kk': u'Үлгі', 'kn': u'ಟೆಂಪ್ಲೇಟು', 'ko': u'틀', @@ -1147,7 +1147,7 @@ 'ja': u'Template‐ノート', 'jv': u'Dhiskusi Cithakan', 'ka': u'თარგი განხილვა', - 'kab': u'Amyannan n talγa', + 'kab': u'Amyannan n talɣa', 'kk': u'Үлгі талқылауы', 'kn': u'ಟೆಂಪ್ಲೇಟು ಚರ್ಚೆ', 'ko': u'틀토론',

16 years, 8 months

[Pywikipedia-l] SVN: [3911] trunk/pywikipedia/pagegenerators.py

by wikipedian＠svn.wikimedia.org

Revision: 3911 Author: wikipedian Date: 2007-07-27 13:14:21 +0000 (Fri, 27 Jul 2007) Log Message: ----------- made -start parameter not run on redirects (that's what's needed in nearly all cases) Modified Paths: -------------- trunk/pywikipedia/pagegenerators.py Modified: trunk/pywikipedia/pagegenerators.py =================================================================== --- trunk/pywikipedia/pagegenerators.py 2007-07-27 13:13:29 UTC (rev 3910) +++ trunk/pywikipedia/pagegenerators.py 2007-07-27 13:14:21 UTC (rev 3911) @@ -564,7 +564,7 @@ firstPageTitle = arg[7:] namespace = wikipedia.Page(wikipedia.getSite(), firstPageTitle).namespace() firstPageTitle = wikipedia.Page(wikipedia.getSite(), firstPageTitle).titleWithoutNamespace() - gen = AllpagesPageGenerator(firstPageTitle, namespace) + gen = AllpagesPageGenerator(firstPageTitle, namespace, includeredirects = False) elif arg.startswith('-new'): if len(arg) >=5: gen = NewpagesPageGenerator(number = int(arg[5:]))

16 years, 8 months

[Pywikipedia-l] SVN: [3910] trunk/pywikipedia/fixes.py

by wikipedian＠svn.wikimedia.org

Revision: 3910 Author: wikipedian Date: 2007-07-27 13:13:29 +0000 (Fri, 27 Jul 2007) Log Message: ----------- improvements for grammar-de Modified Paths: -------------- trunk/pywikipedia/fixes.py Modified: trunk/pywikipedia/fixes.py =================================================================== --- trunk/pywikipedia/fixes.py 2007-07-27 12:41:12 UTC (rev 3909) +++ trunk/pywikipedia/fixes.py 2007-07-27 13:13:29 UTC (rev 3910) @@ -59,15 +59,18 @@ 'replacements': [ #(u'([Ss]owohl) ([^,\.]+?), als auch', r'\1 \2 als auch'), #(u'([Ww]eder) ([^,\.]+?), noch', r'\1 \2 noch'), + # + # Vorsicht bei Substantiven, z. B. 3-Jähriger! (u'(\d+)(minütig|stündig|tägig|wöchig|jährig|minütlich|stündlich|täglich|wöchentlich|jährlich|fach|mal|malig|köpfig|teilig|gliedrig|geteilt|elementig|dimensional|bändig|eckig|farbig|stimmig)', r'\1-\2'), # zusammengesetztes Wort, Bindestrich wird durchgeschleift - (u'(\d+|\d+[\.,]\d+)(\$|€|DM|£|¥|mg|g|kg|ml|cl|l|t|ms|min|µm|mm|cm|dm|m|km|°C|kB|MB|TB|W|kW|MW|PS|Nm|eV|J|kcal|mA|mV|kV|Ω|Hz|kHz|MHz|GHz|mol|Pa|Bq|Sv|mSv)([²³]?-[\w\[])', r'\1-\2\3'), - (u'(\d+|\d+[\.,]\d+)(\$|€|DM|£|¥|mg|g|kg|ml|cl|l|t|ms|min|µm|mm|cm|dm|m|km|°C|kB|MB|TB|W|kW|MW|PS|Nm|eV|J|kcal|mA|mV|kV|Ω|Hz|kHz|MHz|GHz|mol|Pa|Bq|Sv|mSv)(?=\W|²|³|$)', r'\1 \2'), + (u'(?<!\w)(\d+|\d+[\.,]\d+)(\$|€|DM|£|¥|mg|g|kg|ml|cl|l|t|ms|min|µm|mm|cm|dm|m|km|°C|kB|MB|TB|W|kW|MW|PS|Nm|eV|J|kcal|mA|mV|kV|Ω|Hz|kHz|MHz|GHz|mol|Pa|Bq|Sv|mSv)([²³]?-[\w\[])', r'\1-\2\3'), + # Größenangabe ohne Leerzeichen vor Einheit # weggelassen wegen vieler falsch Positiver: s, A, V, C, S, % + (u'(?<!\w)(\d+|\d+[\.,]\d+)(\$|€|DM|£|¥|mg|g|kg|ml|cl|l|t|ms|min|µm|mm|cm|dm|m|km|°C|kB|MB|TB|W|kW|MW|PS|Nm|eV|J|kcal|mA|mV|kV|Ω|Hz|kHz|MHz|GHz|mol|Pa|Bq|Sv|mSv)(?=\W|²|³|$)', r'\1 \2'), # Kein Leerzeichen zwischen Tag und Monat (u'(\d+)\.(Januar|Februar|März|April|Mai|Juni|Juli|August|September|Oktober|November|Dezember)', r'\1. \2'), # Keine führende Null beim Datum - (u'0(\d+)\. (Januar|Februar|März|April|Mai|Juni|Juli|August|September|Oktober|November|Dezember)', r'\1. \2'), + #(u'0(\d+)\. (Januar|Februar|März|April|Mai|Juni|Juli|August|September|Oktober|November|Dezember)', r'\1. \2'), # Kein Leerzeichen nach Komma (u'([a-z](\]\])?,)((\[\[)?[a-zA-Z])', r'\1 \3'), # Leerzeichen und Komma vertauscht

16 years, 8 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

pywikibot July 2007