def glob():
lre.pats["entry"] = lre.lre(ur"(?sm)\{\{\s*แจ้งปรับปรุงหน้าอัตโนมัติ\s*"
ur"((?:\{\{.*?\}\}|.)*?)\s*\}\}")
lre.pats["param"] = lre.lre(r"(?s)\|\s*((?:\{\{.*?\}\}|.)*?)\s*(?=\|)")
lre.pats["num"] = lre.lre(r"\d+$")
lre.pats["user0"] = lre.lre(r"\{\{User0\|(.*?)\}\}")
lre.pats["trimComment"] = lre.lre(r"<!--#(.*?)#-->")
def glob():
global paten, patWOen, patlink, patoldlink, dummytext, patLI
prepat = r"(?m)^[\*\#]+\s*\[\[(?!:en:)(.*?)(?:\|.*?)?\]\]"
sufpat = r".*?\[\[(:en:.*?)\]\]"
patoldlink = lre.lre(r"(?m)(^--> \[\[.*?\]\] <!--\n)+")
patlink = lre.lre(r"(?m)(?<=^--> )\[\[.*\]\](?= <!--$)")
patWOen = lre.lre(prepat)
paten = lre.lre(prepat + sufpat)
dummytext = "<!-- dummy for putting -->"
def dorender(self):
if self.tabactive == 'page':
self.content = self.page.get()
self.pat_before = '~~~#m!'
self.pat_after = self.pat_before[::-1]
self.pat = self.pat_before + r'\d+' + self.pat_after
self.begin_assert = '((?:(?!~~~).)*?)'
self.begin = '~~~#h!'
self.begin = self.begin + self.begin_assert + self.begin[::-1]
self.end = '~~~#e!'
self.leadlink = lre.lre(r'^[\[\{]+')
self.traillink = lre.lre(r'[#{].*$')
self.cnt = 0
self.text = []
ptr = 0
while ptr < len(self.content):
if self.content[ptr:ptr + 2] == '{{' or self.content[ptr:ptr +
2] == '[[':
self.text.append(self.content[ptr])
self.text.append(self.pat_before)
self.text.append(str(self.cnt))
self.cnt += 1
self.text.append(self.pat_after)
self.text.append(self.content[ptr + 1])
ptr += 2
else:
self.text.append(self.content[ptr])
ptr += 1
self.text = ''.join(self.text)
self.content = self.text
self.rmtag('pre')
self.rmtag('nowiki')
self.rmtag('source')
self.content = lre.sub('(?s)<!--.*?-->', '', self.content)
matches = list(
lre.finditer('(?s)(' + self.pat + r')(.*?)(?=[|}\]\n])',
self.content))
links = []
for match in matches:
links.append(match.group(2))
translatedLinks = self.translate(links)
for i, match in enumerate(matches):
self.text = self.text.replace(match.group(), translatedLinks[i], 1)
self.finalize()
def mosteditsArt():
"""
most edits
"""
regexArt = lre.genData(conf.tagind, u"บทความแก้ไขมากสุด")
regexArtlist = lre.genData(conf.tagind, u"บทความรายชื่อแก้ไขมากสุด")
oldtable = getdat(regexArt)
oldtablelist = getdat(regexArtlist)
table = []
tablelist = []
ptr = 0
patListName = lre.lre(lre.sep(conf.listname))
for page, revisions in site.mostrevisionspages():
if len(tablelist) < 5 and patListName.search(page.title()):
tablelist.append([page.title(),
getrankold(page.title(), oldtablelist),
revisions,
firstContributor(page)])
elif len(table) < 10 and not patListName.search(page.title()):
table.append([page.title(),
getrankold(page.title(), oldtable),
revisions,
firstContributor(page)])
elif (len(tablelist) >= 5) and (len(table) >= 10):
break
writetable(table, regexArt)
writetable(tablelist, regexArtlist)
def dorender(self):
if self.tabactive == 'page':
self.content = self.page.get()
self.pat_before = '~~~#m!'
self.pat_after = self.pat_before[::-1]
self.pat = self.pat_before + r'\d+' + self.pat_after
self.begin_assert = '((?:(?!~~~).)*?)'
self.begin = '~~~#h!'
self.begin = self.begin + self.begin_assert + self.begin[::-1]
self.end = '~~~#e!'
self.leadlink = lre.lre(r'^[\[\{]+')
self.traillink = lre.lre(r'[#{].*$')
self.cnt = 0
self.text = []
ptr = 0
while ptr < len(self.content):
if self.content[ptr:ptr+2] == '{{' or self.content[ptr:ptr+2] == '[[':
self.text.append(self.content[ptr])
self.text.append(self.pat_before)
self.text.append(str(self.cnt))
self.cnt += 1
self.text.append(self.pat_after)
self.text.append(self.content[ptr + 1])
ptr += 2
else:
self.text.append(self.content[ptr])
ptr += 1
self.text = ''.join(self.text)
self.content = self.text
self.rmtag('pre')
self.rmtag('nowiki')
self.rmtag('source')
self.content = lre.sub('(?s)<!--.*?-->', '', self.content)
matches = list(lre.finditer('(?s)(' + self.pat + r')(.*?)(?=[|}\]\n])', self.content))
links = []
for match in matches:
links.append(match.group(2))
translatedLinks = self.translate(links)
for i, match in enumerate(matches):
self.text = self.text.replace(match.group(), translatedLinks[i], 1)
self.finalize()
def glob():
global datenow, template
template = wp.Page(conf.templateName)
lre.pats["tl"] = lre.lre(ur"(?i)\{\{\s*%s\s*\}\}\s*" %
lre.sep([page.title(withNamespace=False) for page in
list(template.backlinks(filterRedirects=True)) +
[template]]))
datenow = site.getcurrenttime()
def glob():
patintclass = lre.lre(ur"(?ms)\|\s*title\s*=(.*?)$")
delimit = [ur"\s*[\•\·]\s*", ur"\ +[\•\.\·\-] +", ur"\ *\{\{(?:[\,\•·]|[\•\·\!]w|·wrap|จุด)\}\}\s*", ur"\s*\&\#124\;\s*"]
delimit = lre.sep(delimit) + ur"(?!(?:(?![\[\]]).)*\])"
patdel = lre.lre(u"(?s)(\|\ *list\d+(?:(?!below|seealso|" + #u"(?<=\]\])" +
delimit + u").)*)" + #u"(?<=\]\])" +
delimit)
patnl = lre.lre(u"(list\d+)\s*=\s*(?![\|\s\}])")
patwrap = lre.lre(u"\{\{[Nn]owrap\s*(?:\|(.*?))?\}\}\ *")
patrmwrap = lre.lre(u"\{\{[Nn]owrap.*?\}\}\ *")
triml = lre.lre(u"\n+")
patbr = lre.lre(u"(?m)^(\*[^\n]*)<\s*/?\s*br\s*/?\s*>")
alltag = [u"small", u"span", u"div"]
patopen = lre.lre(u"(?m)^\*\ *(<" + lre.sep(alltag) + u">)\s*\[\[")
patclose = lre.lre(u"\]\]\ *(</" + lre.sep(alltag) + u">)")
def glob():
lre.pats["subtl"] = lre.lre("\{\{\{(.*?)\}\}\}")
def glob():
lre.pats["trimComment"] = lre.lre(r"<!--#(.*?)#-->")
def glob():
global patclear
patclear = lre.lre(ur"(?ms)^(\!.*?$\n).*?(^\|\})")
def glob():
global dummytext
dummytext = "<!-- dummy -->"
lre.pats["maintaincat"] = lre.lre("(?i)article|stub|wikipedia|without")
lre.pats["name"] = lre.lre(r"\[\[:(.*?)\]\]")
lre.pats["dummy"] = lre.lre(dummytext + r"\s*")
def glob():
lre.pats["site_APISite_li"] = lre.lre("(?<=<li>).*?(?=</li>)")
def glob():
lre.pats["stripcomment"] = lre.lre(u"(?s):?\s*เนื้อหาเดิม.*")
lre.pats["ref"] = lre.lre(u"(?ms)^== *อ้างอิง *==.*")
def glob():
lre.pats["name"] = lre.lre(r"\[\[:.*?:(.*?)\]\]")
# strip namespace in order to i18n properly
lre.pats["endtable"] = lre.lre(ur"(?m)^\|\}")
def glob():
global pageMain, contentMain
pageMain = None
contentMain = None
lre.pats["tspan"] = lre.lre("<.*?>")
def glob():
lre.pats["rmdisam"] = lre.lre(ur"\s+\([^\(]*?\)\s*$")
lre.pats["thai"] = lre.lre(u"[\u0e00-\u0e7f]")
lre.pats["exc"] = lre.lre("(?m)^\* *\[\[ *(.*?) *\]\] *$")
