def fixSyntaxSave(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# link to the wiki working on
## TODO: disable this for difflinks and titled links
## http://de.wikipedia.org/w/index.php?title=Wikipedia%3aVandalismusmeldung&diff=103109563&oldid=103109271
## text = pywikibot.replaceExcept(text,
## r'\[https?://%s\.%s\.org/wiki/(?P<link>\S+)\s+(?P<title>.+?)\s?\]'
## % (self.site.lang, self.site.family.name),
## r'[[\g<link>|\g<title>]]', exceptions)
# external link in double brackets
text = pywikibot.replaceExcept(text,
r'\[\[(?P<url>https?://[^\]]+?)\]\]',
r'[\g<url>]', exceptions)
# external link starting with double bracket
text = pywikibot.replaceExcept(text,
r'\[\[(?P<url>https?://.+?)\]',
r'[\g<url>]', exceptions)
# external link and description separated by a dash, with
# whitespace in front of the dash, so that it is clear that
# the dash is not a legitimate part of the URL.
text = pywikibot.replaceExcept(text,
r'\[(?P<url>https?://[^\|\] \r\n]+?) +\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
# dash in external link, where the correct end of the URL can
# be detected from the file extension. It is very unlikely that
# this will cause mistakes.
text = pywikibot.replaceExcept(text,
r'\[(?P<url>https?://[^\|\] ]+?(\.pdf|\.html|\.htm|\.php|\.asp|\.aspx|\.jsp)) *\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
return text
def fixSyntaxSave(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# link to the wiki working on
## TODO: disable this for difflinks and titled links
## https://de.wikipedia.org/w/index.php?title=Wikipedia%3aVandalismusmeldung&diff=103109563&oldid=103109271
## text = pywikibot.replaceExcept(text,
## r'\[https?://%s\.%s\.org/wiki/(?P<link>\S+)\s+(?P<title>.+?)\s?\]'
## % (self.site.lang, self.site.family.name),
## r'[[\g<link>|\g<title>]]', exceptions)
# external link in double brackets
text = pywikibot.replaceExcept(
text,
r'\[\[(?P<url>https?://[^\]]+?)\]\]',
r'[\g<url>]', exceptions)
# external link starting with double bracket
text = pywikibot.replaceExcept(text,
r'\[\[(?P<url>https?://.+?)\]',
r'[\g<url>]', exceptions)
# external link and description separated by a dash, with
# whitespace in front of the dash, so that it is clear that
# the dash is not a legitimate part of the URL.
text = pywikibot.replaceExcept(
text,
r'\[(?P<url>https?://[^\|\] \r\n]+?) +\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
# dash in external link, where the correct end of the URL can
# be detected from the file extension. It is very unlikely that
# this will cause mistakes.
text = pywikibot.replaceExcept(
text,
r'\[(?P<url>https?://[^\|\] ]+?(\.pdf|\.html|\.htm|\.php|\.asp|\.aspx|\.jsp)) *\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
return text
def removeUselessSpaces(self, text):
multipleSpacesR = re.compile(' +')
spaceAtLineEndR = re.compile(' $')
exceptions = ['comment', 'math', 'nowiki', 'pre', 'startspace', 'table',
'template']
text = pywikibot.replaceExcept(text, multipleSpacesR, ' ', exceptions)
text = pywikibot.replaceExcept(text, spaceAtLineEndR, '', exceptions)
return text
def removeUselessSpaces(self, text):
multipleSpacesR = re.compile(' +')
spaceAtLineEndR = re.compile(' $')
exceptions = ['comment', 'math', 'nowiki', 'pre', 'startspace', 'table',
'template']
text = pywikibot.replaceExcept(text, multipleSpacesR, ' ', exceptions)
text = pywikibot.replaceExcept(text, spaceAtLineEndR, '', exceptions)
return text
def fixArabicLetters(self, text):
if self.site.lang=='ckb' or self.site.lang=='fa':
exceptions = [
'gallery',
'hyperlink',
'interwiki',
# but changes letters inside wikilinks
#'link',
'math',
'pre',
'template',
'timeline',
'ref',
'source',
'startspace',
'inputbox',
]
# do not change inside file links
namespaces = list(self.site.namespace(6, all = True))
pattern = re.compile(u'\[\[(' + '|'.join(namespaces) + '):.+?\..+?\]\]',
re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u',', u'،', exceptions)
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text,
ur'ه([.،_<\]\s])',
ur'ە\1', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ە', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ھ', exceptions)
text = pywikibot.replaceExcept(text, u'ك', u'ک', exceptions)
text = pywikibot.replaceExcept(text, ur'[ىي]', u'ی', exceptions)
# replace persian digits
for i in range(0,10):
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text,
u'۰۱۲۳۴۵۶۷۸۹'[i],
u'٠١٢٣٤٥٦٧٨٩'[i], exceptions)
else:
text = pywikibot.replaceExcept(text,
u'٠١٢٣٤٥٦٧٨٩'[i],
u'۰۱۲۳۴۵۶۷۸۹'[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'=".*?"', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE)
exceptions.append(pattern)
exceptions.append('table') #exclude tables for now
for i in range(0,10):
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text, str(i),
u'٠١٢٣٤٥٦٧٨٩'[i], exceptions)
else:
text = pywikibot.replaceExcept(text, str(i),
u'۰۱۲۳۴۵۶۷۸۹'[i], exceptions)
return text
def commonsfiledesc(self, text):
# section headers to {{int:}} versions
exceptions = ["comment", "includeonly", "math", "noinclude", "nowiki", "pre", "source", "ref", "timeline"]
text = pywikibot.replaceExcept(
text, r"([\r\n]|^)\=\= *Summary *\=\=", r"\1== {{int:filedesc}} ==", exceptions, True
)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *\[\[Commons:Copyright tags\|Licensing\]\]: *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *(Licensing|License information|{{int:license-header}}) *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
# frequent field values to {{int:}} versions
text = pywikibot.replaceExcept(
text,
r"([\r\n]\|[Ss]ource *\= *)(?:[Oo]wn work by uploader|[Oo]wn work|[Ee]igene [Aa]rbeit) *([\r\n])",
r"\1{{own}}\2",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text, r"(\| *Permission *\=) *(?:[Ss]ee below|[Ss]iehe unten) *([\r\n])", r"\1\2", exceptions, True
)
# added to transwikied pages
text = pywikibot.replaceExcept(text, r"__NOTOC__", "", exceptions, True)
# tracker element for js upload form
text = pywikibot.replaceExcept(text, r"<!-- *{{ImageUpload\|(?:full|basic)}} *-->", "", exceptions[1:], True)
text = pywikibot.replaceExcept(text, r"{{ImageUpload\|(?:basic|full)}}", "", exceptions, True)
# duplicated section headers
text = pywikibot.replaceExcept(
text,
r"([\r\n]|^)\=\= *{{int:filedesc}} *\=\=(?:[\r\n ]*)\=\= *{{int:filedesc}} *\=\=",
r"\1== {{int:filedesc}} ==",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text,
r"([\r\n]|^)\=\= *{{int:license}} *\=\=(?:[\r\n ]*)\=\= *{{int:license}} *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
return text
def fixReferences(self, text):
# http://en.wikipedia.org/wiki/User:AnomieBOT/source/tasks/OrphanReferenceFixer.pm
exceptions = ["nowiki", "comment", "math", "pre", "source", "startspace"]
# it should be name = " or name=" NOT name ="
text = re.sub(r'(?i)<ref +name(= *| *=)"', r'<ref name="', text)
# remove empty <ref/>-tag
text = pywikibot.replaceExcept(text, r"(?i)(<ref\s*/>|<ref *>\s*</ref>)", r"", exceptions)
text = pywikibot.replaceExcept(text, r"(?i)<ref\s+([^>]+?)\s*>\s*</ref>", r"<ref \1/>", exceptions)
return text
def removeUselessSpaces(self, text):
result = []
multipleSpacesR = re.compile(" +")
spaceAtLineEndR = re.compile(" $")
exceptions = ["comment", "math", "nowiki", "pre", "startspace", "table", "template"]
text = pywikibot.replaceExcept(text, multipleSpacesR, " ", exceptions)
text = pywikibot.replaceExcept(text, spaceAtLineEndR, "", exceptions)
return text
def fixReferences(self, text):
#http://en.wikipedia.org/wiki/User:AnomieBOT/source/tasks/OrphanReferenceFixer.pm
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# it should be name = " or name=" NOT name ="
text = re.sub(r'(?i)<ref +name(= *| *=)"', r'<ref name="', text)
#remove empty <ref/>-tag
text = pywikibot.replaceExcept(text, r'(?i)(<ref\s*/>|<ref *>\s*</ref>)',
r'', exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<ref\s+([^>]+?)\s*>\s*</ref>',
r'<ref \1/>', exceptions)
return text
def fixTypo(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source', 'startspace', 'gallery', 'hyperlink', 'interwiki', 'link']
# change <number> ccm -> <number> cm³
text = pywikibot.replaceExcept(text, ur'(\d)\s* ccm', ur'\1 cm³', exceptions)
text = pywikibot.replaceExcept(text, ur'(\d)\s*ccm', ur'\1 cm³', exceptions)
# Solve wrong Nº sign with °C or °F
# additional exception requested on fr-wiki for this stuff
pattern = re.compile(u'«.*?»', re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, ur'(\d)\s* [º°]([CF])', ur'\1 °\2', exceptions)
text = pywikibot.replaceExcept(text, ur'(\d)\s*[º°]([CF])', ur'\1 °\2', exceptions)
text = pywikibot.replaceExcept(text, ur'º([CF])', ur'°\1', exceptions)
return text
def markActiveTables(self, text):
"""
Mark all hidden table start and end tags.
Mark all table start and end tags that are not disabled by nowiki tags,
comments etc. We will then later only work on these marked tags.
"""
text = pywikibot.replaceExcept(text, _table_start_regex, '<##table##',
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
text = pywikibot.replaceExcept(text, _table_end_regex, '</##table##>',
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
return text
def commonsfiledesc(self, text):
# section headers to {{int:}} versions
exceptions = [
'comment', 'includeonly', 'math', 'noinclude', 'nowiki', 'pre',
'source', 'ref', 'timeline'
]
text = pywikibot.replaceExcept(text, r"([\r\n]|^)\=\= *Summary *\=\=",
r"\1== {{int:filedesc}} ==", exceptions,
True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *\[\[Commons:Copyright tags\|Licensing\]\]: *\=\=",
r"\1== {{int:license-header}} ==", exceptions, True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *(Licensing|License information|{{int:license}}) *\=\=",
r"\1== {{int:license-header}} ==", exceptions, True)
# frequent field values to {{int:}} versions
text = pywikibot.replaceExcept(
text,
r'([\r\n]\|[Ss]ource *\= *)(?:[Oo]wn work by uploader|[Oo]wn work|[Ee]igene [Aa]rbeit) *([\r\n])',
r'\1{{own}}\2', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'(\| *Permission *\=) *(?:[Ss]ee below|[Ss]iehe unten) *([\r\n])',
r'\1\2', exceptions, True)
# added to transwikied pages
text = pywikibot.replaceExcept(text, r'__NOTOC__', '', exceptions,
True)
# tracker element for js upload form
text = pywikibot.replaceExcept(
text, r'<!-- *{{ImageUpload\|(?:full|basic)}} *-->', '',
exceptions[1:], True)
text = pywikibot.replaceExcept(text,
r'{{ImageUpload\|(?:basic|full)}}', '',
exceptions, True)
# duplicated section headers
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:filedesc}} *\=\=(?:[\r\n ]*)\=\= *{{int:filedesc}} *\=\=',
r'\1== {{int:filedesc}} ==', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:license-header}} *\=\=(?:[\r\n ]*)\=\= *{{int:license-header}} *\=\=',
r'\1== {{int:license-header}} ==', exceptions, True)
return text
def fixArabicLetters(self, text):
exceptions = [
'gallery',
'hyperlink',
'interwiki',
# but changes letters inside wikilinks
#'link',
'math',
'pre',
'template',
'timeline',
'ref',
'source',
'startspace',
'inputbox',
]
# valid digits
digits = {
'ckb': u'٠١٢٣٤٥٦٧٨٩',
'fa': u'۰۱۲۳۴۵۶۷۸۹',
}
faChrs = u'ءاآأإئؤبپتثجچحخدذرزژسشصضطظعغفقکگلمنوهیةيك' + digits['fa']
new = digits.pop(self.site.lang)
# This only works if there are only two items in digits dict
old = digits[digits.keys()[0]]
# do not change inside file links
namespaces = list(self.site.namespace(6, all=True))
pattern = re.compile(
u'\[\[(' + '|'.join(namespaces) +
'):.+?\.\w+? *(\|((\[\[.*?\]\])|.)*)?\]\]',
re.UNICODE)
#not to let bot edits in latin content
exceptions.append(re.compile(u"[^%(fa)s] *?\"*? *?, *?[^%(fa)s]"
% {'fa': faChrs}))
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u',', u'،', exceptions)
if self.site.lang == 'ckb':
text = pywikibot.replaceExcept(text,
u'\u0647([.\u060c_<\\]\\s])',
u'\u06d5\\1', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ە', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ھ', exceptions)
text = pywikibot.replaceExcept(text, u'ك', u'ک', exceptions)
text = pywikibot.replaceExcept(text, u'[ىي]', u'ی', exceptions)
return text
# replace persian/arabic digits
## deactivated due to bug #3539407
for i in range(0, 10):
text = pywikibot.replaceExcept(text, old[i], new[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'\w+=(".+?"|\d+)', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE)
exceptions.append(pattern)
exceptions.append('table') # exclude tables for now
# replace digits
for i in range(0, 10):
text = pywikibot.replaceExcept(text, str(i), new[i], exceptions)
return text
def fixArabicLetters(self, text):
exceptions = [
'gallery',
'hyperlink',
'interwiki',
# but changes letters inside wikilinks
#'link',
'math',
'pre',
'template',
'timeline',
'ref',
'source',
'startspace',
'inputbox',
]
# valid digits
digits = {
'ckb': u'٠١٢٣٤٥٦٧٨٩',
'fa': u'۰۱۲۳۴۵۶۷۸۹',
}
faChrs = u'ءاآأإئؤبپتثجچحخدذرزژسشصضطظعغفقکگلمنوهیةيك' + digits['fa']
new = digits.pop(self.site.lang)
# This only works if there are only two items in digits dict
old = digits[digits.keys()[0]]
# do not change inside file links
namespaces = list(self.site.namespace(6, all=True))
pattern = re.compile(
u'\[\[(' + '|'.join(namespaces) +
'):.+?\.\w+? *(\|((\[\[.*?\]\])|.)*)?\]\]',
re.UNICODE)
#not to let bot edits in latin content
exceptions.append(re.compile(u"[^%(fa)s] *?\"*? *?, *?[^%(fa)s]"
% {'fa': faChrs}))
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u',', u'،', exceptions)
if self.site.lang == 'ckb':
text = pywikibot.replaceExcept(text,
u'\u0647([.\u060c_<\\]\\s])',
u'\u06d5\\1', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ە', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ھ', exceptions)
text = pywikibot.replaceExcept(text, u'ك', u'ک', exceptions)
text = pywikibot.replaceExcept(text, u'[ىي]', u'ی', exceptions)
return text
# replace persian/arabic digits
## deactivated due to bug #3539407
for i in range(0, 10):
text = pywikibot.replaceExcept(text, old[i], new[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'\w+=(".+?"|\d+)', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE)
exceptions.append(pattern)
exceptions.append('table') # exclude tables for now
# replace digits
for i in range(0, 10):
text = pywikibot.replaceExcept(text, str(i), new[i], exceptions)
return text
def fixReferences(self, text):
#https://en.wikipedia.org/wiki/User:AnomieBOT/source/tasks/OrphanReferenceFixer.pm
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# it should be name = " or name=" NOT name ="
text = re.sub(r'(?i)<ref +name(= *| *=)"', r'<ref name="', text)
#remove empty <ref/>-tag
text = pywikibot.replaceExcept(text,
r'(?i)(<ref\s*/>|<ref *>\s*</ref>)',
r'', exceptions)
text = pywikibot.replaceExcept(text,
r'(?i)<ref\s+([^>]+?)\s*>\s*</ref>',
r'<ref \1/>', exceptions)
return text
def fixSyntaxSave(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source', 'startspace']
# external link in double brackets
text = pywikibot.replaceExcept(text, r'\[\[(?P<url>https?://[^\]]+?)\]\]', r'[\g<url>]', exceptions)
# external link starting with double bracket
text = pywikibot.replaceExcept(text, r'\[\[(?P<url>https?://.+?)\]', r'[\g<url>]', exceptions)
# external link and description separated by a dash, with
# whitespace in front of the dash, so that it is clear that
# the dash is not a legitimate part of the URL.
text = pywikibot.replaceExcept(text, r'\[(?P<url>https?://[^\|\] \r\n]+?) +\| *(?P<label>[^\|\]]+?)\]', r'[\g<url> \g<label>]', exceptions)
# dash in external link, where the correct end of the URL can
# be detected from the file extension. It is very unlikely that
# this will cause mistakes.
text = pywikibot.replaceExcept(text, r'\[(?P<url>https?://[^\|\] ]+?(\.pdf|\.html|\.htm|\.php|\.asp|\.aspx|\.jsp)) *\| *(?P<label>[^\|\]]+?)\]', r'[\g<url> \g<label>]', exceptions)
return text
def commonsfiledesc(self, text):
# section headers to {{int:}} versions
exceptions = ['comment', 'includeonly', 'math', 'noinclude', 'nowiki',
'pre', 'source', 'ref', 'timeline']
text = pywikibot.replaceExcept(text,
r"([\r\n]|^)\=\= *Summary *\=\=",
r"\1== {{int:filedesc}} ==",
exceptions, True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *\[\[Commons:Copyright tags\|Licensing\]\]: *\=\=",
r"\1== {{int:license}} ==", exceptions, True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *(Licensing|License information|{{int:license-header}}) *\=\=",
r"\1== {{int:license}} ==", exceptions, True)
# frequent field values to {{int:}} versions
text = pywikibot.replaceExcept(
text,
r'([\r\n]\|[Ss]ource *\= *)(?:[Oo]wn work by uploader|[Oo]wn work|[Ee]igene [Aa]rbeit) *([\r\n])',
r'\1{{own}}\2', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'(\| *Permission *\=) *(?:[Ss]ee below|[Ss]iehe unten) *([\r\n])',
r'\1\2', exceptions, True)
# added to transwikied pages
text = pywikibot.replaceExcept(text, r'__NOTOC__', '', exceptions, True)
# tracker element for js upload form
text = pywikibot.replaceExcept(
text,
r'<!-- *{{ImageUpload\|(?:full|basic)}} *-->',
'', exceptions[1:], True)
text = pywikibot.replaceExcept(text, r'{{ImageUpload\|(?:basic|full)}}',
'', exceptions, True)
# duplicated section headers
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:filedesc}} *\=\=(?:[\r\n ]*)\=\= *{{int:filedesc}} *\=\=',
r'\1== {{int:filedesc}} ==', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:license}} *\=\=(?:[\r\n ]*)\=\= *{{int:license}} *\=\=',
r'\1== {{int:license}} ==', exceptions, True)
return text
def markActiveTables(self, text):
"""
Mark all table start and end tags that are not disabled by nowiki tags, comments etc.
We will then later only work on these marked tags.
"""
tableStartTagR = re.compile("<table", re.IGNORECASE)
tableEndTagR = re.compile("</table>", re.IGNORECASE)
text = pywikibot.replaceExcept(text, tableStartTagR, "<##table##",
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
text = pywikibot.replaceExcept(text, tableEndTagR, "</##table##>",
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
return text
def translateMagicWords(self, text):
"""
Makes sure that localized namespace names are used.
"""
# not wanted at ru
# arz uses english stylish codes
if self.site.lang not in ['arz', 'ru']:
exceptions = ['nowiki', 'comment', 'math', 'pre']
for magicWord in [
'img_thumbnail',
'img_left',
'img_center',
'img_right',
'img_none',
'img_framed',
'img_frameless',
'img_border',
'img_upright',
]:
aliases = self.site.getmagicwords(magicWord)
if not aliases:
continue
text = pywikibot.replaceExcept(
text, r'\[\[(?P<left>.+?:.+?\..+?\|) *(' +
'|'.join(aliases) + ') *(?P<right>(\|.*?)?\]\])',
r'[[\g<left>' + aliases[0] + '\g<right>', exceptions)
return text
def markActiveTables(self, text):
"""
Mark all table start and end tags that are not disabled by nowiki tags, comments etc.
We will then later only work on these marked tags.
"""
tableStartTagR = re.compile("<table", re.IGNORECASE)
tableEndTagR = re.compile("</table>", re.IGNORECASE)
text = pywikibot.replaceExcept(text, tableStartTagR, "<##table##",
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
text = pywikibot.replaceExcept(text, tableEndTagR, "</##table##>",
exceptions=['comment', 'math',
'nowiki', 'pre', 'source'])
return text
def majUneSeuleListe(self, listePages, titrePageRandomArticles):
pageAsLinkBoolean = True
if titrePageRandomArticles in blackList:
pageAsLinkBoolean = False
exceptions = []
texteARajouter = u""
x = 0
# Création d'un texte contenant la liste des pages
for page in listePages:
x = x + 1
texteARajouter = texteARajouter + u"\n|" + str(x) + u"=" + page.title(asLink=pageAsLinkBoolean)
nbPages = x
pageRandomArticles = pywikibot.Page(self.site, titrePageRandomArticles)
text = pageRandomArticles.get()
pywikibot.output(u"\n> \03{lightblue}Traitement de %s\03{default} <" % pageRandomArticles.title())
text = self.suppressionAncienneListe(text)
old = re.compile(u"\{\{#switch:\{\{rand\|(1\||2=)[0-9]*\}\}")
new = (u"{{#switch:{{rand|1|%i}}%s" % (nbPages, texteARajouter))
text = pywikibot.replaceExcept(text, old, new, exceptions)
if not self.save(text, pageRandomArticles, self.summary):
pywikibot.output(u'Aucun changement nécessaire')
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == 'wikipedia:arz':
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ['nowiki', 'comment', 'math', 'pre']
for nsNumber in family.namespaces:
if not family.isDefinedNSLanguage(nsNumber, self.site.lang):
# Skip undefined namespaces
continue
namespaces = list(family.namespace(self.site.lang, nsNumber, all=True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == 'wikipedia' and \
self.site.lang in ('en', 'fr'):
# do not change "Image" on en-wiki and fr-wiki
for image in [u'Image', u'image']:
if image in namespaces:
namespaces.remove(image)
# skip main (article) namespace
if thisNs and namespaces:
text = pywikibot.replaceExcept(text, r'\[\[\s*(' + '|'.join(namespaces) + ') *:(?P<nameAndLabel>.*?)\]\]', r'[[' + thisNs + ':\g<nameAndLabel>]]', exceptions)
return text
def suppressionAncienneListe(self, text, nombreCrochets=2):
exceptions = []
#old = re.compile(u"(\n\|[0-9]{1,} *= *[\[\{]{2}.*[\]\}]{2}|\n[0-9]{1,} *= *[\[\{]{2}.*[\]\}]{2}\|)")
old = re.compile(u"(\n\|[0-9]{1,} *= *[\[\{]{0,2}.*[\]\}]{0,2}|\n[0-9]{1,} *= *[\[\{]{0,2}.*[\]\}]{0,2}\|)")
new = u""
text = pywikibot.replaceExcept(text, old, new, exceptions)
return text
def majUneSeuleListe(self, listePages, titrePageRandomArticles):
pageAsLinkBoolean = True
if titrePageRandomArticles in blackList:
pageAsLinkBoolean = False
exceptions = []
texteARajouter = u""
x = 0
# Création d'un texte contenant la liste des pages
for page in listePages:
x = x + 1
texteARajouter = texteARajouter + u"\n|" + str(
x) + u"=" + page.title(asLink=pageAsLinkBoolean)
nbPages = x
pageRandomArticles = pywikibot.Page(self.site, titrePageRandomArticles)
text = pageRandomArticles.get()
pywikibot.output(u"\n> \03{lightblue}Traitement de %s\03{default} <" %
pageRandomArticles.title())
text = self.suppressionAncienneListe(text)
old = re.compile(u"\{\{#switch:\{\{rand\|(1\||2=)[0-9]*\}\}")
new = (u"{{#switch:{{rand|1|%i}}%s" % (nbPages, texteARajouter))
text = pywikibot.replaceExcept(text, old, new, exceptions)
if not self.save(text, pageRandomArticles, self.summary):
pywikibot.output(u'Aucun changement nécessaire')
def translateMagicWords(self, text):
"""
Makes sure that localized namespace names are used.
"""
# not wanted at ru
# arz uses english stylish codes
if self.site.lang not in ["arz", "ru"]:
exceptions = ["nowiki", "comment", "math", "pre"]
for magicWord in [
"img_thumbnail",
"img_left",
"img_center",
"img_right",
"img_none",
"img_framed",
"img_frameless",
"img_border",
"img_upright",
]:
aliases = self.site.getmagicwords(magicWord)
if not aliases:
continue
text = pywikibot.replaceExcept(
text,
r"\[\[(?P<left>.+?:.+?\..+?\|) *(" + "|".join(aliases) + ") *(?P<right>(\|.*?)?\]\])",
r"[[\g<left>" + aliases[0] + "\g<right>",
exceptions,
)
return text
def removeNonBreakingSpaceBeforePercent(self, text):
"""
Newer MediaWiki versions automatically place a non-breaking space in
front of a percent sign, so it is no longer required to place it
manually.
"""
text = pywikibot.replaceExcept(text, r"(\d) %", r"\1 %", ["timeline"])
return text
def removeNonBreakingSpaceBeforePercent(self, text):
'''
Newer MediaWiki versions automatically place a non-breaking space in
front of a percent sign, so it is no longer required to place it
manually.
'''
text = pywikibot.replaceExcept(text, r'(\d) %', r'\1 %', ['timeline'])
return text
def removeNonBreakingSpaceBeforePercent(self, text):
'''
Newer MediaWiki versions automatically place a non-breaking space in
front of a percent sign, so it is no longer required to place it
manually.
'''
text = pywikibot.replaceExcept(text, r'(\d) %', r'\1 %', ['timeline'])
return text
def fixHtml(self, text):
# Everything case-insensitive (?i)
# Keep in mind that MediaWiki automatically converts <br> to <br />
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
text = pywikibot.replaceExcept(text, r'(?i)<b>(.*?)</b>', r"'''\1'''",
exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<strong>(.*?)</strong>',
r"'''\1'''", exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<i>(.*?)</i>', r"''\1''",
exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<em>(.*?)</em>', r"''\1''",
exceptions)
# horizontal line without attributes in a single line
text = pywikibot.replaceExcept(text, r'(?i)([\r\n])<hr[ /]*>([\r\n])',
r'\1----\2', exceptions)
# horizontal line with attributes; can't be done with wiki syntax
# so we only make it XHTML compliant
text = pywikibot.replaceExcept(text, r'(?i)<hr ([^>/]+?)>',
r'<hr \1 />',
exceptions)
# a header where only spaces are in the same line
for level in range(1, 7):
equals = '\\1%s \\2 %s\\3' % ("=" * level, "=" * level)
text = pywikibot.replaceExcept(
text,
r'(?i)([\r\n]) *<h%d> *([^<]+?) *</h%d> *([\r\n])'
% (level, level),
r'%s' % equals,
exceptions)
# TODO: maybe we can make the bot replace <p> tags with \r\n's.
return text
def fixHtml(self, text):
# Everything case-insensitive (?i)
# Keep in mind that MediaWiki automatically converts <br> to <br />
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
text = pywikibot.replaceExcept(text, r'(?i)<b>(.*?)</b>', r"'''\1'''",
exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<strong>(.*?)</strong>',
r"'''\1'''", exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<i>(.*?)</i>', r"''\1''",
exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<em>(.*?)</em>', r"''\1''",
exceptions)
# horizontal line without attributes in a single line
text = pywikibot.replaceExcept(text, r'(?i)([\r\n])<hr[ /]*>([\r\n])',
r'\1----\2', exceptions)
# horizontal line with attributes; can't be done with wiki syntax
# so we only make it XHTML compliant
text = pywikibot.replaceExcept(text, r'(?i)<hr ([^>/]+?)>',
r'<hr \1 />',
exceptions)
# a header where only spaces are in the same line
for level in range(1, 7):
equals = '\\1%s \\2 %s\\3' % ("=" * level, "=" * level)
text = pywikibot.replaceExcept(
text,
r'(?i)([\r\n]) *<h%d> *([^<]+?) *</h%d> *([\r\n])'
% (level, level),
r'%s' % equals,
exceptions)
# TODO: maybe we can make the bot replace <p> tags with \r\n's.
return text
def fixStyle(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# convert prettytable to wikitable class
if self.site.language in ('de', 'en'):
text = pywikibot.replaceExcept(text,
r'(class="[^"]*)prettytable([^"]*")',
r'\1wikitable\2', exceptions)
return text
def suppressionAncienneListe(self, text, nombreCrochets=2):
exceptions = []
#old = re.compile(u"(\n\|[0-9]{1,} *= *[\[\{]{2}.*[\]\}]{2}|\n[0-9]{1,} *= *[\[\{]{2}.*[\]\}]{2}\|)")
old = re.compile(
u"(\n\|[0-9]{1,} *= *[\[\{]{0,2}.*[\]\}]{0,2}|\n[0-9]{1,} *= *[\[\{]{0,2}.*[\]\}]{0,2}\|)"
)
new = u""
text = pywikibot.replaceExcept(text, old, new, exceptions)
return text
def fixStyle(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# convert prettytable to wikitable class
if self.site.language in ('de', 'en'):
text = pywikibot.replaceExcept(text,
ur'(class="[^"]*)prettytable([^"]*")',
ur'\1wikitable\2', exceptions)
return text
def fixTypo(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace', 'gallery', 'hyperlink', 'interwiki', 'link']
# change <number> ccm -> <number> cm³
text = pywikibot.replaceExcept(text, r'(\d)\s* ccm',
r'\1 ' + u'cm³', exceptions)
text = pywikibot.replaceExcept(text,
r'(\d)\s*ccm', r'\1 ' + u'cm³',
exceptions)
# Solve wrong Nº sign with °C or °F
# additional exception requested on fr-wiki for this stuff
pattern = re.compile(u'«.*?»', re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, r'(\d)\s* ' + u'[º°]([CF])',
r'\1 ' + u'°' + r'\2', exceptions)
text = pywikibot.replaceExcept(text, r'(\d)\s*' + u'[º°]([CF])',
r'\1 ' + u'°' + r'\2', exceptions)
text = pywikibot.replaceExcept(text, u'º([CF])', u'°' + r'\1',
exceptions)
return text
def fixArabicLetters(self, text):
exceptions = [
"gallery",
"hyperlink",
"interwiki",
# but changes letters inside wikilinks
#'link',
"math",
"pre",
"template",
"timeline",
"ref",
"source",
"startspace",
"inputbox",
]
# valid digits
digits = {"ckb": u"٠١٢٣٤٥٦٧٨٩", "fa": u"۰۱۲۳۴۵۶۷۸۹"}
new = digits.pop(self.site.lang)
# This only works if there are only two items in digits dict
old = digits[digits.keys()[0]]
# do not change inside file links
namespaces = list(self.site.namespace(6, all=True))
pattern = re.compile(u"\[\[(" + "|".join(namespaces) + "):.+?\.\w+? *(\|((\[\[.*?\]\])|.)*)?\]\]", re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u",", u"،", exceptions)
if self.site.lang == "ckb":
text = pywikibot.replaceExcept(text, ur"ه([.،_<\]\s])", ur"ە\1", exceptions)
text = pywikibot.replaceExcept(text, u"ه", u"ە", exceptions)
text = pywikibot.replaceExcept(text, u"ه", u"ھ", exceptions)
text = pywikibot.replaceExcept(text, u"ك", u"ک", exceptions)
text = pywikibot.replaceExcept(text, ur"[ىي]", u"ی", exceptions)
return text
# replace persian/arabic digits
## deactivated due to bug #3539407
for i in xrange(0, 10):
text = pywikibot.replaceExcept(text, old[i], new[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'\w+=(".+?"|\d+)', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u"<[/]*?[^</]+?[/]*?>", re.UNICODE)
exceptions.append(pattern)
exceptions.append("table") # exclude tables for now
# replace digits
for i in xrange(0, 10):
text = pywikibot.replaceExcept(text, str(i), new[i], exceptions)
return text
def cleanUpSectionHeaders(self, text):
"""
For better readability of section header source code, puts a space
between the equal signs and the title.
Example: ==Section title== becomes == Section title ==
NOTE: This space is recommended in the syntax help on the English and
German Wikipedia. It might be that it is not wanted on other wikis.
If there are any complaints, please file a bug report.
"""
for level in range(1, 7):
equals = '=' * level
text = pywikibot.replaceExcept(text, r'\n' + equals + ' *(?P<title>[^=]+?) *' + equals + ' *\r\n', '\n' + equals + ' \g<title> ' + equals + '\r\n', ['comment', 'math', 'nowiki', 'pre'])
return text
def replaceDeprecatedTemplates(self, text):
exceptions = ['comment', 'math', 'nowiki', 'pre']
if self.site.family.name in deprecatedTemplates and self.site.lang in deprecatedTemplates[self.site.family.name]:
for template in deprecatedTemplates[self.site.family.name][self.site.lang]:
old = template[0]
new = template[1]
if new == None:
new = ''
else:
new = '{{'+new+'}}'
if not self.site.nocapitalize:
old = '[' + old[0].upper() + old[0].lower() + ']' + old[1:]
text = pywikibot.replaceExcept(text, r'\{\{([mM][sS][gG]:)?' + old + '(?P<parameters>\|[^}]+|)}}', new, exceptions)
return text
def cleanUpSectionHeaders(self, text):
"""
For better readability of section header source code, puts a space
between the equal signs and the title.
Example: ==Section title== becomes == Section title ==
NOTE: This space is recommended in the syntax help on the English and
German Wikipedia. It might be that it is not wanted on other wikis.
If there are any complaints, please file a bug report.
"""
return pywikibot.replaceExcept(
text, r'(?m)^(={1,7}) *(?P<title>[^=]+?) *\1 *\r?\n',
r'\1 \g<title> \1%s' % config.LS,
['comment', 'math', 'nowiki', 'pre'])
def fixTypo(self, text):
exceptions = [
"nowiki",
"comment",
"math",
"pre",
"source",
"startspace",
"gallery",
"hyperlink",
"interwiki",
"link",
]
# change <number> ccm -> <number> cm³
text = pywikibot.replaceExcept(text, ur"(\d)\s* ccm", ur"\1 cm³", exceptions)
text = pywikibot.replaceExcept(text, ur"(\d)\s*ccm", ur"\1 cm³", exceptions)
# Solve wrong Nº sign with °C or °F
# additional exception requested on fr-wiki for this stuff
pattern = re.compile(u"«.*?»", re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, ur"(\d)\s* [º°]([CF])", ur"\1 °\2", exceptions)
text = pywikibot.replaceExcept(text, ur"(\d)\s*[º°]([CF])", ur"\1 °\2", exceptions)
text = pywikibot.replaceExcept(text, ur"º([CF])", ur"°\1", exceptions)
return text
def cleanUpSectionHeaders(self, text):
"""
For better readability of section header source code, puts a space
between the equal signs and the title.
Example: ==Section title== becomes == Section title ==
NOTE: This space is recommended in the syntax help on the English and
German Wikipedia. It might be that it is not wanted on other wikis.
If there are any complaints, please file a bug report.
"""
return pywikibot.replaceExcept(
text,
r'(?m)^(={1,7}) *(?P<title>[^=]+?) *\1 *\r?\n',
r'\1 \g<title> \1%s' % config.LS,
['comment', 'math', 'nowiki', 'pre'])
def doReplacements(self, original_text):
"""
Returns the text which is generated by applying all replacements to
the given text.
"""
new_text = original_text
exceptions = []
if "inside-tags" in self.exceptions:
exceptions += self.exceptions["inside-tags"]
if "inside" in self.exceptions:
exceptions += self.exceptions["inside"]
for old, new in self.replacements:
if self.sleep != None:
time.sleep(self.sleep)
new_text = pywikibot.replaceExcept(new_text, old, new, exceptions, allowoverlap=self.allowoverlap)
return new_text
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == 'wikipedia:arz':
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ['nowiki', 'comment', 'math', 'pre']
for nsNumber in self.site.namespaces():
if nsNumber in (0, 2, 3):
# skip main (article) namespace
# skip user namespace, maybe gender is used
continue
# a clone is needed. Won't change the namespace dict
namespaces = list(self.site.namespace(nsNumber, all=True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == 'wikipedia':
if self.site.lang in ('en', 'fr') and \
family.versionnumber(self.site.lang) >= 14:
# do not change "Image" on en-wiki and fr-wiki
assert u'Image' in namespaces
namespaces.remove(u'Image')
if self.site.lang == 'hu':
# do not change "Kép" on hu-wiki
assert u'Kép' in namespaces
namespaces.remove(u'Kép')
elif self.site.lang == 'pt':
# bug #3346901 should be implemented
continue
# lowerspaced and underscored namespaces
for i in xrange(len(namespaces)):
item = namespaces[i].replace(' ', '[ _]')
item = u'[%s%s]' % (item[0], item[0].lower()) + item[1:]
namespaces[i] = item
namespaces.append(thisNs[0].lower() + thisNs[1:])
if thisNs and namespaces:
text = pywikibot.replaceExcept(
text,
r'\[\[\s*(%s) *:(?P<nameAndLabel>.*?)\]\]'
% '|'.join(namespaces),
r'[[%s:\g<nameAndLabel>]]' % thisNs,
exceptions)
return text
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == 'wikipedia:arz':
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ['nowiki', 'comment', 'math', 'pre']
for nsNumber in self.site.namespaces():
if nsNumber in (0, 2, 3):
# skip main (article) namespace
# skip user namespace, maybe gender is used
continue
# a clone is needed. Won't change the namespace dict
namespaces = list(self.site.namespace(nsNumber, all=True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == 'wikipedia':
if self.site.lang in ('en', 'fr') and \
LV(self.site.version()) >= LV('1.14'):
# do not change "Image" on en-wiki and fr-wiki
assert u'Image' in namespaces
namespaces.remove(u'Image')
if self.site.lang == 'hu':
# do not change "Kép" on hu-wiki
assert u'Kép' in namespaces
namespaces.remove(u'Kép')
elif self.site.lang == 'pt':
# bug #3346901 should be implemented
continue
# lowerspaced and underscored namespaces
for i in range(len(namespaces)):
item = namespaces[i].replace(' ', '[ _]')
item = u'[%s%s]' % (item[0], item[0].lower()) + item[1:]
namespaces[i] = item
namespaces.append(thisNs[0].lower() + thisNs[1:])
if thisNs and namespaces:
text = pywikibot.replaceExcept(
text,
r'\[\[\s*(%s) *:(?P<nameAndLabel>.*?)\]\]'
% '|'.join(namespaces),
r'[[%s:\g<nameAndLabel>]]' % thisNs,
exceptions)
return text
def putSpacesInLists(self, text):
"""
For better readability of bullet list and enumeration wiki source code,
puts a space between the * or # and the text.
NOTE: This space is recommended in the syntax help on the English,
German, and French Wikipedia. It might be that it is not wanted on other
wikis. If there are any complaints, please file a bug report.
"""
exceptions = ['comment', 'math', 'nowiki', 'pre', 'source', 'timeline']
if not (self.redirect or self.template) and \
pywikibot.calledModuleName() != 'capitalize_redirects':
text = pywikibot.replaceExcept(
text,
r'(?m)^(?P<bullet>[:;]*(\*+|#+)[:;\*#]*)(?P<char>[^\s\*#:;].+?)', '\g<bullet> \g<char>',
exceptions)
return text
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == "wikipedia:arz":
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ["nowiki", "comment", "math", "pre"]
for nsNumber in self.site.namespaces():
if nsNumber in (0, 2, 3):
# skip main (article) namespace
# skip user namespace, maybe gender is used
continue
# a clone is needed. Won't change the namespace dict
namespaces = list(self.site.namespace(nsNumber, all=True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == "wikipedia":
if self.site.lang in ("en", "fr") and family.versionnumber(self.site.lang) >= 14:
# do not change "Image" on en-wiki and fr-wiki
assert u"Image" in namespaces
namespaces.remove(u"Image")
if self.site.lang == "hu":
# do not change "Kép" on hu-wiki
assert u"Kép" in namespaces
namespaces.remove(u"Kép")
elif self.site.lang == "pt":
# bug #3346901 should be implemented
continue
# lowerspaced and underscored namespaces
for i in xrange(len(namespaces)):
item = namespaces[i].replace(" ", "[ _]")
item = u"[%s%s]" % (item[0], item[0].lower()) + item[1:]
namespaces[i] = item
namespaces.append(thisNs[0].lower() + thisNs[1:])
if thisNs and namespaces:
text = pywikibot.replaceExcept(
text,
r"\[\[\s*(%s) *:(?P<nameAndLabel>.*?)\]\]" % "|".join(namespaces),
r"[[%s:\g<nameAndLabel>]]" % thisNs,
exceptions,
)
return text
def replaceDeprecatedTemplates(self, text):
exceptions = ['comment', 'math', 'nowiki', 'pre']
if self.site.family.name in deprecatedTemplates and \
self.site.lang in deprecatedTemplates[self.site.family.name]:
for template in deprecatedTemplates[self.site.family.name][self.site.lang]:
old = template[0]
new = template[1]
if new is None:
new = ''
else:
new = '{{%s}}' % new
if not self.site.nocapitalize:
old = '[' + old[0].upper() + old[0].lower() + ']' + old[1:]
text = pywikibot.replaceExcept(
text,
r'\{\{([mM][sS][gG]:)?%s(?P<parameters>\|[^}]+|)}}' % old,
new, exceptions)
return text
def putSpacesInLists(self, text):
"""
For better readability of bullet list and enumeration wiki source code,
puts a space between the * or # and the text.
NOTE: This space is recommended in the syntax help on the English,
German, and French Wikipedia. It might be that it is not wanted on other
wikis. If there are any complaints, please file a bug report.
"""
if not self.template:
exceptions = ['comment', 'math', 'nowiki', 'pre', 'source', 'template',
'timeline', self.site.redirectRegex()]
text = pywikibot.replaceExcept(
text,
r'(?m)^(?P<bullet>[:;]*(\*+|#+)[:;\*#]*)(?P<char>[^\s\*#:;].+?)',
'\g<bullet> \g<char>',
exceptions)
return text
def translateMagicWords(self, text):
"""
Makes sure that localized namespace names are used.
"""
# not wanted at ru
# arz uses english stylish codes
if self.site.lang not in ['arz', 'ru']:
exceptions = ['nowiki', 'comment', 'math', 'pre']
for magicWord in ['img_thumbnail', 'img_left', 'img_center',
'img_right', 'img_none', 'img_framed',
'img_frameless', 'img_border', 'img_upright', ]:
aliases = self.site.getmagicwords(magicWord)
if not aliases: continue
text = pywikibot.replaceExcept(
text,
r'\[\[(?P<left>.+?:.+?\..+?\|) *(' + '|'.join(aliases) + \
') *(?P<right>(\|.*?)?\]\])',
r'[[\g<left>' + aliases[0] + '\g<right>', exceptions)
return text
def doReplacements(self, original_text):
"""
Returns the text which is generated by applying all replacements to
the given text.
"""
new_text = original_text
exceptions = []
if "inside-tags" in self.exceptions:
exceptions += self.exceptions['inside-tags']
if "inside" in self.exceptions:
exceptions += self.exceptions['inside']
for old, new in self.replacements:
if self.sleep is not None:
time.sleep(self.sleep)
new_text = pywikibot.replaceExcept(new_text,
old,
new,
exceptions,
allowoverlap=self.allowoverlap)
return new_text
def __iter__(self):
try:
for entry in self.parser:
if self.skipping:
if entry.title != self.xmlStart:
continue
self.skipping = False
if not self.isTitleExcepted(entry.title) \
and not self.isTextExcepted(entry.text):
new_text = entry.text
for old, new in self.replacements:
new_text = pywikibot.replaceExcept(
new_text, old, new, self.excsInside, self.site)
if new_text != entry.text:
yield pywikibot.Page(self.site, entry.title)
except KeyboardInterrupt:
try:
if not self.skipping:
pywikibot.output(
u'To resume, use "-xmlstart:%s" on the command line.' %
entry.title)
except NameError:
pass
def cleanUpLinks(self, text):
# helper function which works on one link and either returns it
# unmodified, or returns a replacement.
def handleOneLink(match):
titleWithSection = match.group('titleWithSection')
label = match.group('label')
trailingChars = match.group('linktrail')
newline = match.group('newline')
if not self.site.isInterwikiLink(titleWithSection):
# The link looks like this:
# [[page_title|link_text]]trailing_chars
# We only work on namespace 0 because pipes and linktrails work
# differently for images and categories.
page = pywikibot.Page(pywikibot.Link(titleWithSection,
self.site))
try:
namespace = page.namespace()
except pywikibot.InvalidTitle:
return match.group()
if namespace == 0:
# Replace underlines by spaces, also multiple underlines
titleWithSection = re.sub('_+', ' ', titleWithSection)
# Remove double spaces
titleWithSection = re.sub(' +', ' ', titleWithSection)
# Remove unnecessary leading spaces from title,
# but remember if we did this because we eventually want
# to re-add it outside of the link later.
titleLength = len(titleWithSection)
titleWithSection = titleWithSection.lstrip()
hadLeadingSpaces = (len(titleWithSection) != titleLength)
hadTrailingSpaces = False
# Remove unnecessary trailing spaces from title,
# but remember if we did this because it may affect
# the linktrail and because we eventually want to
# re-add it outside of the link later.
if not trailingChars:
titleLength = len(titleWithSection)
titleWithSection = titleWithSection.rstrip()
hadTrailingSpaces = (len(titleWithSection) !=
titleLength)
# Convert URL-encoded characters to unicode
titleWithSection = pywikibot.url2unicode(titleWithSection,
site=self.site)
if titleWithSection == '':
# just skip empty links.
return match.group()
# Remove unnecessary initial and final spaces from label.
# Please note that some editors prefer spaces around pipes.
# (See [[en:Wikipedia:Semi-bots]]). We remove them anyway.
if label is not None:
# Remove unnecessary leading spaces from label,
# but remember if we did this because we want
# to re-add it outside of the link later.
labelLength = len(label)
label = label.lstrip()
hadLeadingSpaces = (len(label) != labelLength)
# Remove unnecessary trailing spaces from label,
# but remember if we did this because it affects
# the linktrail.
if not trailingChars:
labelLength = len(label)
label = label.rstrip()
hadTrailingSpaces = (len(label) != labelLength)
else:
label = titleWithSection
if trailingChars:
label += trailingChars
if titleWithSection == label or \
titleWithSection[0].lower() + \
titleWithSection[1:] == label:
newLink = "[[%s]]" % label
# Check if we can create a link with trailing characters
# instead of a pipelink
elif (len(titleWithSection) <= len(label) and
label[:len(titleWithSection)] == titleWithSection and
re.sub(trailR, '',
label[len(titleWithSection):]) == ''):
newLink = "[[%s]]%s" % (label[:len(titleWithSection)],
label[len(titleWithSection):])
else:
# Try to capitalize the first letter of the title.
# Maybe this feature is not useful for languages that
# don't capitalize nouns...
#if not self.site.nocapitalize:
if self.site.sitename() == 'wikipedia:de':
titleWithSection = (titleWithSection[0].upper() +
titleWithSection[1:])
newLink = "[[%s|%s]]" % (titleWithSection, label)
# re-add spaces that were pulled out of the link.
# Examples:
# text[[ title ]]text -> text [[title]] text
# text[[ title | name ]]text -> text [[title|name]] text
# text[[ title |name]]text -> text[[title|name]]text
# text[[title| name]]text -> text [[title|name]]text
if hadLeadingSpaces and not newline:
newLink = ' ' + newLink
if hadTrailingSpaces:
newLink = newLink + ' '
if newline:
newLink = newline + newLink
return newLink
# don't change anything
return match.group()
trailR = re.compile(self.site.linktrail())
# The regular expression which finds links. Results consist of four groups:
# group <newline> depends whether the links starts with a new line.
# group <titleWithSection> is the page title and section, that is,
# everything before | or ]. It'll include the # to make life easier for us.
# group <label> is the alternative link title between | and ].
# group <linktrail> is the link trail after ]] which are part of the word.
# note that the definition of 'letter' varies from language to language.
linkR = re.compile(
r'(?P<newline>[\n]*)\[\[(?P<titleWithSection>[^\]\|]+)(\|(?P<label>[^\]\|]*))?\]\](?P<linktrail>' +
self.site.linktrail() + ')')
text = pywikibot.replaceExcept(text, linkR, handleOneLink,
['comment', 'math', 'nowiki', 'pre',
'startspace'])
return text
def majAvecSousPages(self, listePages, titrePageRandomArticles):
########## Variables paramétrables ##########
nbMaxPagesParPaquet = 1200
#############################################
exceptions = []
texte = u""
nombrePagesDansChaqueListe = []
paquetsListesPages = []
x = 0
pageAsLinkBoolean = True
if titrePageRandomArticles in blackList:
pageAsLinkBoolean = False
# Création des paquets de listes de pages
for page in listePages:
x = x + 1
if page != u"{[COUPURE NOUVELLE PAGE]}":
texte = texte + u"\n|" + str(x) + u"=" + page.title(
asLink=pageAsLinkBoolean)
if x == nbMaxPagesParPaquet:
paquetsListesPages.append(texte)
nombrePagesDansChaqueListe.append(nbMaxPagesParPaquet)
texte = u""
x = 0
elif page == u"{[COUPURE NOUVELLE PAGE]}" and x > 1:
#pywikibot.output(u"{[COUPURE NOUVELLE PAGE]}")
paquetsListesPages.append(texte)
nombrePagesDansChaqueListe.append(x)
texte = u""
x = 0
if x != 0:
nombrePagesDansChaqueListe.append(x)
paquetsListesPages.append(texte)
pywikibot.output("nombrePagesDansChaqueListe = %s" %
nombrePagesDansChaqueListe)
num = 0
listeSousPages = []
for texte in paquetsListesPages:
nbPages = nombrePagesDansChaqueListe[num]
num = num + 1
texteARajouter = texte
page = pywikibot.Page(self.site,
(u"%s/%i" % (titrePageRandomArticles, num)))
listeSousPages.append(
u"%s/%i" %
(titrePageRandomArticles.replace(u"Modèle:", u""), num))
try:
text = page.get()
pywikibot.output(
u"\n> \03{lightblue}Traitement de %s\03{default} <" %
page.title())
text = self.suppressionAncienneListe(text)
old = re.compile(
u"\{\{#switch:\{\{rand\|(0\||1\||2=)[0-9]*\}\}\|?")
new = (u"{{#switch:{{rand|1|%i}}%s" %
(nbPages, texteARajouter))
text = pywikibot.replaceExcept(text, old, new, exceptions)
if not self.save(text, page, self.summary):
pywikibot.output(u'Aucun changement nécessaire')
except pywikibot.NoPage:
pywikibot.output(u'Page %s inexistante' % page.title())
text = (u"{{#switch:{{rand|1|%i}}%s\n}}" %
(nbPages, texteARajouter))
###### À décommenter pour le bon fonctionnement ######
if not self.creerPage(text, page, self.summary):
pywikibot.output(u'La page n\'a pas été crée…')
###
# On traite à présent la page même du random pour mettre à jour le nombre de sous-pages existantes
page = pywikibot.Page(self.site, titrePageRandomArticles)
text = page.get()
pywikibot.output(u"\n> \03{lightblue}Traitement de %s\03{default} <" %
page.title())
texteARajouter = u""
z = 0
for titreSousPage in listeSousPages:
z = z + 1
texteARajouter = texteARajouter + u"\n|%i={{%s}}" % (z,
titreSousPage)
text = self.suppressionAncienneListe(text)
#pywikibot.output(texteARajouter)
old = re.compile(u"\{\{#switch:\{\{rand\|(1\||2=)[0-9]*\}\}")
new = (u"{{#switch:{{rand|1|%i}}%s" %
(len(listeSousPages), texteARajouter))
text = pywikibot.replaceExcept(text, old, new, exceptions)
if not self.save(text, page, self.summary):
pywikibot.output(u'Aucun changement nécessaire')
def transferImage(self, sourceImagePage):
"""Gets a wikilink to an image, downloads it and its description,
and uploads it to another wikipedia.
Returns the filename which was used to upload the image
This function is used by imagetransfer.py and by copy_table.py
"""
sourceSite = sourceImagePage.site()
url = sourceImagePage.fileUrl().encode('utf-8')
pywikibot.output(u"URL should be: %s" % url)
# localize the text that should be printed on the image description page
try:
description = sourceImagePage.get()
# try to translate license templates
if (sourceSite.sitename(),
self.targetSite.sitename()) in licenseTemplates:
for old, new in licenseTemplates[(
sourceSite.sitename(),
self.targetSite.sitename())].iteritems():
new = '{{%s}}' % new
old = re.compile('{{%s}}' % old)
description = pywikibot.replaceExcept(
description, old, new,
['comment', 'math', 'nowiki', 'pre'])
description = pywikibot.translate(self.targetSite, copy_message) \
% (sourceSite, description)
description += '\n\n' + sourceImagePage.getFileVersionHistoryTable(
)
# add interwiki link
if sourceSite.family == self.targetSite.family:
description += "\r\n\r\n" + unicode(sourceImagePage)
except pywikibot.NoPage:
description = ''
print "Image does not exist or description page is empty."
except pywikibot.IsRedirectPage:
description = ''
print "Image description page is redirect."
else:
bot = upload.UploadRobot(url=url,
description=description,
targetSite=self.targetSite,
urlEncoding=sourceSite.encoding(),
keepFilename=self.keep_name,
verifyDescription=not self.keep_name)
# try to upload
targetFilename = bot.run()
if targetFilename and self.targetSite.family.name == 'commons' and \
self.targetSite.lang == 'commons':
# upload to Commons was successful
reason = pywikibot.translate(sourceSite, nowCommonsMessage)
# try to delete the original image if we have a sysop account
if sourceSite.family.name in config.sysopnames and \
sourceSite.lang in config.sysopnames[sourceSite.family.name]:
if sourceImagePage.delete(reason):
return
if sourceSite.lang in nowCommonsTemplate and \
sourceSite.family.name in config.usernames and \
sourceSite.lang in config.usernames[sourceSite.family.name]:
# add the nowCommons template.
pywikibot.output(u'Adding nowCommons template to %s' %
sourceImagePage.title())
sourceImagePage.put(
sourceImagePage.get() + '\n\n' +
nowCommonsTemplate[sourceSite.lang] % targetFilename,
comment=nowCommonsMessage[sourceSite.lang])
def run(self):
#############################################
##### (fr) : Paramètres modifiables
##### (en) : Modifiable parameters
#############################################
exceptions = []
titreModeleOld = u'Infobox Stade'
## Obsolète : cf. ƒ2 plus bas
# ‹!› Ne pas mettre de parenthèses !
#titreModeleOldRe = u'[iI]nfobox Émission de télévision|[iI]nfobox [Tt]élévision|[Ii]nfobox Télévision nouveau|[Ii]nfobox TV émission'
modeleOld = pywikibot.Page(self.site, u'Modèle:%s' % titreModeleOld)
modeleNew = u'\\1Infobox Stade'
checkNamespace = True
checkNumberNamespace = 0
onlySaveIfMajorChange = True
ajoutParametresAbsents = False
alignementSignesEgal = True
useCategories = False
listeTitresCategories = [
u"Détection temporaire paramètre float Infobox ville"
]
#### Expérimental : ƒ2 ####
"""
Recherche automatique des redirections afin de remplir la
variable titreModeleOldRe avec une expression régulière.
‹!› La variable titreModeleOldRe ne doit pas contenir de
parenthèses codantes, auquel cas les expressions régulières
utilisant la variable seraient faussées.
"""
premiereLettreMinuscule = titreModeleOld[0:1].lower()
premiereLettreMajuscule = titreModeleOld[0:1].upper()
resteTitre = titreModeleOld[1:]
titreModeleOldRe = u'[%s%s]%s' % (premiereLettreMinuscule,
premiereLettreMajuscule, resteTitre)
for page in modeleOld.getReferences(redirectsOnly=True):
premiereLettreMinuscule = page.title(asLink=False)[0:1].lower()
premiereLettreMajuscule = page.title(asLink=False)[0:1].upper()
resteTitre = titreModeleOld[1:]
titreModeleOldRe += u'|[%s%s]%s' % (
premiereLettreMinuscule, premiereLettreMajuscule, resteTitre)
############################
## Obsolète : Remplacé par la détection de l'argument
## '-reprise:' (voir fonction main()).
# (fr) : Activer ce paramètre permet de reprendre le
# traitement à partir de la page donnée
# (en) : Enable this parameter allows restarting the treatment
# form the page given
#reprise = True
#titreReprise = u"La Folle Route"
##### (fr) : Modifications majeures #####
##### (en) : Major changes #####
## (fr) : Liste de recherches ##
## (en) : Find list ##
listeRechercheElements = {
#1 : u'\n? *\| *surnom *= *.*'
#1 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[hH]autes[ -][pP]yrénées *\] *\](\n.*)*géoloc-département) *= *(\n|\})',
#5 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[hH]auts[ -][dD]e[ -][sS]eine]**\] *\](\n.*)*géoloc-département) *= *(\n|\})',
#6 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[sS]eine[ -][sS]aint[ -][dD]enis *\] *\](\n.*)*géoloc-département) *= *(\n|\})',
#7 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[Vv]al[ -][Dd]e[ -][mM]arne *\] *\](\n.*)*géoloc-département) *= *(\n|\})'
#8 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[sS]eine *\] *\](\n.*)*géoloc-département) *= *(\n|\})',
#9 : u'(\n? *\| *département *= [^\n]*\[ *\[ *[sS]eine *\] *\](\n.*)*géoloc-département) *= *(\n|\})'
#1 : u'(\n? *\| *)site production( *= *.*)',
#2 : u"(\n? *\| *(précédé|suivi) *par *= *)''(.*)''"
#3 : u'(\n? *\| *)carte2( *= *.*)',
#4 : u'(\n? *\| *taille-logo *= *.*) *(px|cm|mm) *'
#1 : re.compile(u'(alt moy *= *[0-9]*) *m *'),
#2 : re.compile(u'(\| *)arrondissement( *= *)(.*)')
#6 : u'(\n *\|.*) *= *\{ *\{ *[Ff][Oo][Rr][Mm][Aa][Tt][Nn][Uu][Mm] *: *([0-9]*) *\} *\}',
#7 : u'(\n? *\| *région) *= *\[ *\[ *Région (.*)',
#8 : u'(\n? *\| *région) *= *\[ *\[.*\| *([bB]retagne|[cC]entre).*\] *\]',
#9 : u'(\n? *\| *région) *= *\[ *\[.*\| *[Rr]éunion.*\] *\]',
#10: u'(.*) *= *[Nn]\.? *[Cc]\.? *',
#1 : u'(\n? *\| *(longitude|latitude)) *= *([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*[Ee](st)?',
#2 : u'(\n? *\| *(longitude|latitude)) *= *([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*([Oo](uest)?|[Ww](est)?)',
#3 : u'(\n? *\| *(longitude|latitude)) *= *([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*[Nn](ord)?',
#4 : u'(\n? *\| *(longitude|latitude)) *= *([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*([0-9]*)[°\'‘’" ]*[Ss](ud)?'
#6 : u'(\n? *\| *(longitude|latitude) *= .*)//',
#1 : u'\n? *\| *(float) *= *.*', ## Paramètres à supprimer
#8 : re.compile(u'(\n?) *\| *Région *= *(.*)'),
#1 : re.compile(ur'\| *coordonnées *=.*(.*\| *latitude *= *[^\n]+.*\| *longitude *= *[^\n]+\n|.*\| *longitude *= *[^\n]+.*\| *latitude *= *[^\n]+\n)', re.DOTALL),
#2 : re.compile(ur'(\| *latitude *= *[^\n]+.*\| *longitude *= *[^\n]+.*|\| *longitude *= *[^\n]+.*\| *latitude *= *[^\n]+.*)\| *coordonnées *=[^\n]*\n?', re.DOTALL),
#3 : u'(\n?) *\| *coordonnées *= *\{ *\{ *[Cc]oord *\| *([0-9\.-]+) *\| *([0-9\.]+) *\| *([0-9\.]+) *\| *([NS]) *\| *([0-9\.-]+) *\| *([0-9\.]+) *\| *([0-9\.]+) *\| *([EW])[^.\}]*\} *\}',
#4 : u'(\n?) *\| *coordonnées *= *\{ *\{ *[Cc]oord *\| *([0-9\.-]+) *\| *([NS]) *\| *([0-9\.-]+) *\| *([EW])[^.\}]*\} *\}',
#5 : u'(\n?) *\| *coordonnées *= *\{ *\{ *[Cc]oord *\| *([0-9\.-]+) *\| *([0-9\.-]+)[^.\}]*\} *\}',
#6 : u'(\n?) *\| *coordonnées *= *[^0-9\n]*'
#5 : re.compile(ur'\{ *\{ *[Cc]oord[\n]*\} *\}(.*\| *latitude *= *[^\n]+.*\| *longitude *= *[^\n]+.*|.*\| *longitude *= *[^\n]+.*\| *latitude *= *[^\n]+)', re.DOTALL)
#13 : u'(\n? *\| *(longitude|latitude)) *= *([0-9\.]*) *[Ee](st)?'
#1 : u"((\n? *\| *)image *=.*) ((\$®\$|\|)[0-9]+px *)",
#2 : u"(\n? *\| *)image *= *\[ *\[ *([iI]mage|[Ff]ichier|[Ff]ile) *: *([^\|]+) *(((\||\$®\$)[^\|]*)?) *\] *\]"
1: u"→"
}
## (fr) : Liste de remplacements ##
## (en) : Replace list ##
listeRemplacementsElements = {
1: u" {{info|→|prêt}}"
#2 : u"\\1image = \\3\\1légende = \\4"
#2 : u"\\1\\3"
#1 : u'\\1 = Hautes-Pyrénées\\3',
#3 : u'\\1 | latitude = \\2/\\3/\\4/\\5\n | longitude = \\6/\\7/\\8/\\9',
#4 : u'\\1 | latitude = \\2/\\3\n | longitude = \\4/\\5',
#5 : u'\\1 | latitude = \\2\n | longitude = \\3',
#6 : u'\\1 | latitude = \n | longitude = '
#1 : u'|nom de division = [[Départements d\'Haïti|Département]]\n|division =\\3',
#2 : u'|nom de division2 = Arrondissement\n|division2 = \\3'
#7 : u'\\1 = [[\\2',
#8 : u'\\1 = [[Région \\2|\\2]]',
#9 : u'\\1 = [[La Réunion|Réunion]]',
#10 : u'\\1 = ',
#1 : u'\\1 = \\3/\\4/\\5/E',
#2 : u'\\1 = \\3/\\4/\\5/W',
#3 : u'\\1 = \\3/\\4/\\5/N',
#4 : u'\\1 = \\3/\\4/\\5/S'
}
## (fr) : Liste d'ajouts ##
## (en) : Adds list ##
##### (fr) : Modifications mineures #####
##### (en) : Minor changes #####
listeConditionsPositivesAjouts = {
#1 : u""
}
listeConditionsNegativesAjouts = {
#1 : u"\| *carte *= *[EÉée]tats-Unis/[fF]loride"
}
listeElementsAAjouter = {
#1 : u"| carte=États-Unis/Floride"
}
## (fr) : Liste de recherches ##
## (en) : Find list ##
listeRechercheElementsMineure = {
#1 : u'(\| *image *=.*\n) *\| *([^=]*\n)',
#2 : u'(\n? *\| *(longueur|largeur) *= *[0-9]*),'
}
## (fr) : Liste de remplacements ##
## (en) : Replace list ##
listeRemplacementsElementsMineure = {
#1 : u'\\1 | légende = \\2',
#2 : u'\\1.'
}
#############################################
#### (fr) : Début du traitement
#### (en) : Beginning of the treatment
#############################################
if not self.debug:
if not useCategories:
listePages = [
page for page in modeleOld.getReferences(
follow_redirects=False,
withTemplateInclusion=True,
onlyTemplateInclusion=True,
redirectsOnly=False)
]
else:
listePages = []
for titreCategorie in listeTitresCategories:
cat = pywikibot.Category(self.site, titreCategorie)
listePages.extend(list(cat.articles()))
pywikibot.output(u'Taille de la liste = %i' % len(listePages))
listePagesARetirer = []
if self.reprise:
for page in listePages:
if page.title() == self.titreReprise:
break
listePagesARetirer.append(page)
if checkNamespace:
for page in listePages:
if page.namespace(
) != checkNumberNamespace and not page in listePagesARetirer:
listePagesARetirer.append(page)
for page in listePagesARetirer:
listePages.remove(page)
elif self.debug:
listePages = [
pywikibot.Page(self.site, u'User:Toto Azéro/Bac à sable')
]
pywikibot.output(u"Nombre de pages à traiter : %i" % len(listePages))
for page in listePages:
if onlySaveIfMajorChange:
possibiliteSauvegarder = False
else:
possibiliteSauvegarder = True
text = self.load(page)
pywikibot.output(
u"\n> \03{lightblue}Traitement de %s\03{default} <" %
page.title())
############
### À utiliser uniquement dans les cas exceptionnels :
### permet d'autoriser la sauvegarde dans un cas précis
global exception_possibiliteSauvegarder
exception_possibiliteSauvegarder = False
#textOld = text
#text = re.sub(u'(\n? *\| *date-sans *=[^\n]*) *\} *\} *(([\n]+.*)*géoloc-département *= *)', u'\\1\\2}}', text)
#if text != textOld:
# exception_possibiliteSauvegarder = True
#############
#################################################################
############ TRAVAIL SUR L'INFOBOX EXTRAITE DU TEXTE ############
#################################################################
##### Délimiter le début de l'infobox
try:
matchDebut = re.search(u'\{ *\{ *(%s)' % titreModeleOldRe,
text).group(0)
except:
pywikibot.output(
u"\03{lightred}Absence du modèle %s sur la page %s\03{default}"
% (titreModeleOld, page.title()))
continue
positionMatchDebut = text.index(matchDebut)
extraitText = text[positionMatchDebut:]
#### Délimiter la fin possible de l'infobox
#### (i.e. les premiers u'}}' trouvés)
# ‹!› Le résultat n'est pas forcément la fin réelle
# de l'infobox : en effet, cet ordre ne tient pas
# compte de probables modèles présents dans l'infobox
# et s'arrêtera aux premiers u'}}' trouvés, quels
# qu'ils soient !
matchFin = re.search(u' *\} *\}', extraitText).group(0)
positionMatchFin = extraitText.index(matchFin)
extraitText = extraitText[0:(positionMatchFin + len(matchFin))]
# NB : dans extraitText[0:(positionMatchFin + len(matchFin))],
# on ajoute la longueur des u'}}' pour qu'ils se
# trouvent bien dans l'extrait traité
# Principe de la boucle : tant que le nombre de u'{'
# et celui de u'}' ne sont pas équibilibrés, la variable
# extraitText est agrandie jusqu'au u'}}' suivants trouvés
# dans le texte.
positionMatchFin = text.index(extraitText)
resteText = text[positionMatchFin + len(extraitText):]
while extraitText.count('{') != extraitText.count('}'):
matchFin = re.search(
u'([^\{\}]* *\} *\}|(\{ *\{[^\{\}]*\} *\})+[^\{\}]* *\} *\})',
resteText).group(0)
positionMatchFin = resteText.index(matchFin)
extraitTextOld = extraitText
extraitText = extraitText + resteText[0:(positionMatchFin +
len(matchFin))]
resteText = resteText[positionMatchFin + len(matchFin):]
### On travaille sur cet extrait puis on effectuera
### les remplacements sur le texte à la fin
extraitTextNew = extraitText
##### Normalisation de l'infobox pour éviter des problèmes dans son traitement #####
## Enlever les u'|' inutiles et les placer au début du paramètre suivant ##
# ex : |cp=66360| \n maire=Gérard Rabat
# → |cp=66360\n | maire=Gérard Rabat
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'(\|[^\[\]\{\}]*=.*)\|\n'),
u'\\1\n |', exceptions)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'\|? *([^\[\]\{\}]*=.*)\| *\n *\|'), u'| \\1\n |',
exceptions)
####
### Ce qui suit est spécifique
### à l'infobox {{Infobox Commune de France}}
## Déplacement d'une image mise à côté du nom de la commune (le blason) dans le paramètre 'armoiries' ##
# ex : |nomcommune = Saint-Didier-en-Velay [[Image:Blason_Saint-Didier-en-Velay_43.svg|80 px]]
# → |nomcommune = Saint-Didier-en-Velay […] |armoiries = Blason_Saint-Didier-en-Velay_43.svg
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(
u'(\| *nomcommune *= *[^\|]*\n?)\[ *\[ *([fF]ichier|[Ii]mage|[Ff]ile) *: *([^\|]*)\|? *([Cc]enter|[Cc]entre|[Ll]eft|[Rr]ight)?[^\]]*\] *\]'
), u'\\1|armoiries = \\3', exceptions)
## On fait passer les u'}}' à la ligne s'ils sont en bout de ligne d'un paramètre ##
# ex : u'| géoloc-département = | }}'
# → u'| géoloc-département = \n}}' #
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'(\n *\|? *.*=.*) *\|+ *\} *\}$'),
u'\\1\n}}', exceptions)
# ex : u'| géoloc-département = }}'
# → u'| géoloc-département = \n}}' #
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'(\n *\|? *.*=.*) *\} *\}$'),
u'\\1\n}}', exceptions)
####
## On fait passer un éventuel u'|' présent en bout de ligne du début de l'infobox ##
# ex : u'{{Infobox Commune de France|\n\|'
# → u'{{Infobox Commune de France\n|'
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'\{ *\{ *(%s[^\n]*) *\| *\n+ *\|' %
titreModeleOldRe), u'{{\\1\n | ', exceptions)
# ex : u'{{Infobox Commune de France|'
# → u'{{Infobox Commune de France\n|'
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'\{ *\{ *(%s[^\n]*) *\| *\n' % titreModeleOldRe),
u'{{\\1\n | ', exceptions)
## Suppression de plusieurs u'|' successifs ##
# ex : {{Infobox Commune de France||nomcommune=Baudrecourt
# → {{Infobox Commune de France|nomcommune=Baudrecourt
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'(\{ *\{ *(%s.*)) *(\| *){2,}' % titreModeleOldRe),
u'\\1|', exceptions)
#print u'0-5\n' + extraitTextNew
## Faire passer les u'|' présents en fin de ligne en début de ligne suivante ##
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'(\n?[^\[\]\{\}\n]*=[^=\n]*) *\| *\n'),
u'\\1\n | ', exceptions)
#extraitTextNew = pywikibot.replaceExcept(extraitTextNew, re.compile(u'(\n?[^=]*=[^=]*) *\| *\n'), u'\\1\n | ', exceptions)
#print u'1\n' + extraitTextNew
extraitTextNewOld = extraitTextNew
###################################################
###### Modifications pour éviter des erreurs ######
###################################################
## TODO/À faire (ƒ4) : commenter les différents remplacements
re1 = re.compile(
u'(\| *[^\[\]\{\}]*= *\[ *\[ *([fF]ichier|[Ff]ile|[Ii]mage) *:[^=\]]*\|[^=\]]*)='
)
re2 = re.compile(
u'(\| *[^\[\]\{\}]*= *[^\[\]\{\}]*\[ *\[[^\[\]\{\}]*)=([^\[\]\{\}]*\] *\])'
)
re3 = re.compile(
u'(\| *[^\[\]\{\}]*= *[^\[\]\{\}]*\{ *\{[^\[\]\{\}]*)=([^\[\]\{\}]*\} *\})'
)
re4 = re.compile(u'(\| *[^\[\]\{\}]*=.*\{ *\{.*)\|(.*\} *\})')
re5 = re.compile(u'\|([^\[\]\{\}\|\n]*=) *')
#re5 = re.compile(u'(\| *[^\[\]\{\}]*=.*\{ *\{[^\}\|]*(\n+[^\}]*)+)\|([^\}]*(\n*[^\}]*)+\} *\})')
while re.search(re1, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re1, u'\\1$±$', exceptions)
while re.search(re2, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re2, u'\\1$±$\\2', exceptions)
while re.search(re3, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re3, u'\\1$±$\\2', exceptions)
while re.search(re4, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re4, u'\\1$®$\\2', exceptions)
while re.search(re5, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re5, u'$¡$\\1 ', exceptions)
extraitTextNew = extraitTextNew.replace(u'|', u'$®$')
extraitTextNew = extraitTextNew.replace(u'$¡$', u'|')
###################################################
#print u'2\n' + extraitTextNew
#pywikibot.showDiff(extraitTextNewOld, extraitTextNew)
## Séparer tous les paramètres présents sur une même ligne ##
# ex : u'|nomcommune = Saint-Félix-de-Sorgues|région = [[Midi-Pyrénées]]'
# → u'|nomcommune = Saint-Félix-de-Sorgues
# |région = [[Midi-Pyrénées]]'
verificationStop = re.compile(
u'(\| *[^\[\]\{\}]*=[^\n]*)(\| *[^\[\]\{\}]*=[^\n]*)')
#print extraitTextNew
while re.search(verificationStop, extraitTextNew):
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(
u'(\| *[^\[\]\{\}]*=[^\n]*)(\| *[^\[\]\{\}]*=[^\n]*)'),
u'\\1\n\\2', exceptions)
#print u'3\n' + extraitTextNew
verificationStop = re.compile(
u'(\| *[^\[\{]+=.*\[ *\[(.*\|)+.*\] *\][^\[\n]*)(\| *[^\[\{]+=.*)'
)
while re.search(verificationStop, extraitTextNew):
##PROBLEME ICI (RESOlU ?)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(
u'(\| *[^\[\{]+=.*\[ *\[(.*\|)+.*\] *\][^\[\n]*)(\| *[^\[\{]+=.*)'
), u'\\1\n\\2', exceptions)
#print u'4\n' + extraitTextNew
#print extraitTextNew
## Fait passer les parmètre en bout d'annonce du modèle à la ligne
# ex : {{Infobox Commune de France|nomcommune=Baudrecourt
# → {{Infobox Commune de France
# | nomcommune=Baudrecourt
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew,
re.compile(u'\{ *\{ *(%s) *\| *(.*)\n' % titreModeleOldRe),
u'{{\\1\n | \\2\n', exceptions)
#print extraitTextNew
## Suppression d'un '|' inutile (ex : '| }}')
# ex : | }}
# → }}
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'\n *\|+ *\} *\}'), u'\n}}',
exceptions)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'\n *(\|?.*=.*) *\| *\} *\}'),
u'\n\\1}}', exceptions)
#print u'5\n' + extraitTextNew
extraitTextNewOld = extraitTextNew
## Modifications majeures ##
for x in listeRechercheElements:
elementAChercher = listeRechercheElements[x]
print 'x = %i' % x
print elementAChercher
print re.search(elementAChercher, extraitTextNew)
print listeRemplacementsElements[x]
print re.sub(elementAChercher, listeRemplacementsElements[x],
extraitTextNew)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, elementAChercher,
listeRemplacementsElements[x], exceptions)
#extraitTextNew = re.sub(elementAChercher, listeRemplacementsElements[x], extraitTextNew)
#print extraitTextNew
#print extraitTextNew
## Ajouts majeurs ##
for x in listeElementsAAjouter:
elementAAjouter = listeElementsAAjouter[x]
conditionNegative = listeConditionsNegativesAjouts[x]
conditionPositive = listeConditionsPositivesAjouts[x]
#print elementAAjouter
if not re.search(conditionNegative,
extraitTextNew) and re.search(
conditionPositive, extraitTextNew):
positionFin = extraitTextNew.rindex('\n}}')
#print positionFin
#print extraitTextNew[0:positionFin]
extraitTextNew = extraitTextNew[
0:
positionFin] + u"\n" + elementAAjouter + extraitTextNew[
positionFin:]
#print u'5-5\n' + extraitTextNew
### Enlever les séparateurs des milliers dans certains paramètres donnés
listeElements = []
for element in listeElements:
m = re.search(u'(%s *= *)([0-9]* [0-9]* *)' % element,
extraitTextNew)
if m != None:
new = m.group(1) + m.group(2).replace(u' ', u'')
#print u'1-1 : %s — %s' % (m.group(0), new)
extraitTextNew = extraitTextNew.replace(m.group(0), new)
#print extraitTextNew
## Vérifier si une modification majeure a eu lieu
if (extraitTextNew != extraitTextNewOld and
onlySaveIfMajorChange) or exception_possibiliteSauvegarder:
possibiliteSauvegarder = True
#pywikibot.showDiff(extraitTextNewOld, extraitTextNew)
for x in listeRechercheElementsMineure: # Modifications mineures
elementAChercher = listeRechercheElementsMineure[x]
#print 'x = %i' % x
#print elementAChercher
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, elementAChercher,
listeRemplacementsElementsMineure[x], exceptions)
#print extraitTextNew
else:
continue
#listeElements = [u'longitude', u'latitude']
#for element in listeElements:
# m = re.search(u'\n? *\| *%s *= *([-—–]?[0-9\.]+)' % element, extraitTextNew)
# m2 = re.search(u'\n? *\| *%s *= *[0-9]+\.[0-9]{4,}' % element, extraitTextNew)
# if m != None and m2 != None:
# extraitTextNew = extraitTextNew.replace(m.group(1), (u'%.4f' % float(m.group(1))))
extraitTextNew = pywikibot.replaceExcept(extraitTextNew,
re.compile(u'\n *\| *'),
u'\n | ', exceptions)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'(\| *[a-zé²\- _]{2,17}) *= *'),
u'\\1 = ', exceptions)
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, re.compile(u'(\|.*=.*)\| *$'), u'\\1',
exceptions)
### Fin modification pour éviter des erreurs (1/2)
extraitTextNew = extraitTextNew.replace(u'$±$', u'=')
##### Ajouts de tous les paramètres absents #####
listeParametresActuelsAvecValeurs = extraitTextNew.split(
u'\n | ')[1:]
listeParametres = [
u'nomcommune',
u'image',
u'image-desc',
u'armoiries',
u'armoiries-desc',
u'armoiries-taille',
u'logo',
u'logo-desc',
u'logo-taille', #u'collectivité',
u'région',
u'canton',
u'arrondissement',
u'insee',
u'cp',
u'maire',
u'mandat',
u'intercomm',
u'latitude',
u'longitude',
u'alt mini',
u'alt maxi',
u'km²',
u'sans',
u'date-sans',
u'aire-urbaine',
u'date-aire-urbaine',
u'nomhab',
u'siteweb',
u'géoloc-département'
]
if ajoutParametresAbsents:
for parametre in listeParametres:
if not parametre in extraitTextNew:
parametrePrecedent = listeParametres[
listeParametres.index(parametre) - 1]
old = re.compile(u'(\n? *\| *%s *= *.*)' %
parametrePrecedent)
new = u'\\1\n | %s = ' % parametre
extraitTextNew = pywikibot.replaceExcept(
extraitTextNew, old, new, exceptions)
#print '6\n' + extraitTextNew
##### Alignement des signes u'=' #####
listeParametresAvecValeurs = extraitTextNew.split(u'\n | ')[1:]
tailleMaxParametre = 0
for parametreAvecValeur in listeParametresAvecValeurs:
#print parametreAvecValeur
match = re.search(u' *=', parametreAvecValeur).group(0)
positionSigneEgal = parametreAvecValeur.index(match)
partieParametre = parametreAvecValeur[0:positionSigneEgal]
#print 'partieParametre = %s ; taille = %s' % (partieParametre, len(partieParametre))
if len(partieParametre) > tailleMaxParametre:
tailleMaxParametre = len(partieParametre)
tailleMaxParametre = tailleMaxParametre + 1 # Permet de laisser un espace avant le plus long paramètre…
#print '\ntailleMaxParametre = %i' % tailleMaxParametre
if not alignementSignesEgal:
listeParametresAvecValeurs = []
#print listeParametresAvecValeurs
for parametreAvecValeur in listeParametresAvecValeurs:
#print parametreAvecValeur
positionSigneEgal = parametreAvecValeur.index(u'=')
partieParametre = parametreAvecValeur[0:positionSigneEgal]
partieParametreNew = partieParametre
while len(partieParametreNew) < tailleMaxParametre:
partieParametreNew = partieParametreNew + u' '
while len(partieParametreNew) > tailleMaxParametre:
partieParametreNew = partieParametreNew[0:-1]
#print str(len(partieParametreNew)) + partieParametreNew
#print 'partieParametre = ' + partieParametre
parametreAvecValeurNew = pywikibot.replaceExcept(
parametreAvecValeur, u'^%s' % partieParametre,
partieParametreNew, exceptions)
#parametreAvecValeurNew = parametreAvecValeur.replace(u' | ' + partieParametre, u' | ' + partieParametreNew)
#print 'partieParametreNew = ' + partieParametreNew
extraitTextNew = extraitTextNew.replace(
u'\n | ' + parametreAvecValeur,
u'\n | ' + parametreAvecValeurNew)
### Fin modification pour éviter des erreurs (2/2)
extraitTextNew = extraitTextNew.replace(u'$®$', u'|')
#print extraitTextNew
###### Mettre à jour le texte grâce à l'extrait modifié et le publier ######
#print extraitTextNew
text = text.replace(extraitText, extraitTextNew)
resume = self.summary
#if re.search(u'longitude *= *[^\n]+.*', text) and re.search(u'latitude *= *[^\n]+.*', text):
# resume = u'[[WP:RBOT]] : Suppression du paramètre \'coordonnées\' dans le [[modèle:Infobox Pont]] au profit des paramètres \'latitude\' et \'longitude\''
#if re.search(u'\{ *\{ *[Cc]oord *\|.*\} *\}', text) and re.search(u'\| *latitude *= *.+', text) and re.search(u'\| *longitude *= *.+', text):
# text = pywikibot.replaceExcept(text, re.compile(u'\{ *\{ *[Cc]oord *\|.*\} *\}\n?'), u'', exceptions)
# resume = resume + u' ; suppression du modèle {{coord}} faisant doublon avec ces paramètres'
#print extraitTextNew
print u"‹!› Modifications ‹!›"
pywikibot.showDiff(page.get(), text)
#if checkNamespace and page.namespace() == checkNumberNamespace:
#print possibiliteSauvegarder
if possibiliteSauvegarder:
if not self.save(text, page, resume):
pywikibot.output(u'La page %s n\'a pas été sauvegardée' %
page.title(asLink=True))
def validXhtml(self, text):
text = pywikibot.replaceExcept(text, r'(?i)<br[ /]*>', r'<br />',
['comment', 'math', 'nowiki', 'pre'])
return text