def clean(self):
self.text = lre.sub(self.pat, '', self.text).replace('\r',
'') # first order
self.text = lre.sub(
r'(?is)\{\{(|' + self.begin +
ur')?(?:{}):'.format('|'.join(self.siteDest.namespaces()[10])),
r'{{\1', self.text)
pat = r'(?is)\{\{(|' + self.begin + ')?((?:' + msg[
'wikitranslator-exempt-tag'] + r').*?\}\})'
self.text = lre.sub(
pat,
r'<!-- {{\1\3 ' + msg['wikitranslator-exempt-notice'] + ' -->',
self.text)
# use \3 because self.begin has a hidden parenthesis.
self.text = lre.sub(r'(?is)\[\[(|' + self.begin + ur')?Category:',
ur'[[\1หมวดหมู่:', self.text)
self.text = lre.sub(
r'(?is)\[\[(|' + self.begin + ur')?(?:Image|File):', ur'[[\1ไฟล์:',
self.text)
self.text = lre.sub(r'(?mi)^== *See also *== *$', u'== ดูเพิ่ม ==',
self.text)
self.text = lre.sub(r'(?mi)^== *External links *== *$',
u'== แหล่งข้อมูลอื่น ==', self.text)
self.text = lre.sub(r'(?mi)^== *References *== *$', u'== อ้างอิง ==',
self.text)
return self.text
def clean(self):
self.text = lre.sub(self.pat, '', self.text).replace('\r', '') # first order
self.text = lre.sub(r'(?is)\{\{(|' + self.begin + ur')?(?:{}):'.format('|'.join(self.siteDest.namespaces()[10])), r'{{\1', self.text)
pat = r'(?is)\{\{(|' + self.begin + ')?((?:' + msg['wikitranslator-exempt-tag'] + r').*?\}\})'
self.text = lre.sub(pat, r'<!-- {{\1\3 ' + msg['wikitranslator-exempt-notice'] + ' -->', self.text)
# use \3 because self.begin has a hidden parenthesis.
self.text = lre.sub(r'(?is)\[\[(|' + self.begin + ur')?Category:', ur'[[\1หมวดหมู่:', self.text)
self.text = lre.sub(r'(?is)\[\[(|' + self.begin + ur')?(?:Image|File):', ur'[[\1ไฟล์:', self.text)
self.text = lre.sub(r'(?mi)^== *See also *== *$', u'== ดูเพิ่ม ==', self.text)
self.text = lre.sub(r'(?mi)^== *External links *== *$', u'== แหล่งข้อมูลอื่น ==', self.text)
self.text = lre.sub(r'(?mi)^== *References *== *$', u'== อ้างอิง ==', self.text)
return self.text
def main():
if len(args) != 2:
return
pagemain = wp.Page(wp.toutf(args[0]))
newlink = wp.toutf(args[1])
pywikibot.output("old: " + pagemain.title())
pywikibot.output("new: " + newlink)
for page in pagemain.backlinks(content=True):
pywikibot.output("processing " + page.title())
txt = page.get()
page.put(lre.sub(r"\[\[" + lre.escape(pagemain.title()),
"[[" + newlink.replace("_", " "), txt), u"ย้ายลิงก์ไปหน้าใหม่")
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 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 fixRepetedVowelTitle(page):
"""
If found impossible vowel arrangement in title,
correct by moving that page.
"""
opagetitle = page.title()
pagetitle = opagetitle
for i in checkVowel:
pagetitle = lre.sub(i + u"+", i, pagetitle)
if pagetitle != opagetitle:
pywikibot.output("ย้ายบทความชื่อมีสระซ้อน")
reason = u"โรบอต: เปลี่ยนชื่อบทความมีสระซ้อน"
try:
page.move(pagetitle, reason=reason)
except:
wp.error()
else:
page = pywikibot.Page(pywikibot.getSite(), page.title())
page.delete(reason=reason, prompt=False, mark=True)
def finalize(self):
self.text = cgi.escape(self.clean())
self.text = lre.sub(
r'(?is)' + self.begin, "<a href='" + '//' + self.siteSource.code +
'.wikipedia.org/wiki/' + r"\1 ' title='\1'>", self.text)
self.text = self.text.replace(self.end, '</a>')
def rmtag(self, tag):
self.content = lre.sub("(?s)<{tag}>.*?</{tag}>".format(tag=tag), "",
self.content)
def process(page, config, sources):
if config.get('disable', False): return
source = wp.Page(config["source"])
today = site.getcurrenttime()
originalText = page.get() if page.exists() else None
if ("stable" in config and (today - pywikibot.Timestamp.fromISOformat(
source.getVersionHistory(total=1)[0][1])).days <
int(config["stable"])):
return
page.u_elist = []
deprecated = []
checkcat = []
if sources:
source = sources[source]
text = source.text
if page.namespace() == 828:
text = lre.sub('(?<!:)[Tt]emplate:', u'แม่แบบ:', text)
for item in config["findText"]:
if len(item) == 3:
num, find, replace = item
regex = False
elif len(item) == 4:
num, find, replace, regex = item
else:
page.u_elist.append(u"คำเตือน: ข้อความค้นหาและแทนที่อันดับที่ {} มีจำนวนพารามิเตอร์ไม่ถูกต้อง".format(num))
continue
if regex:
newtext = lre.sub(find, replace, text)
else:
newtext = text.replace(find, replace)
if newtext == text and find != replace:
page.u_elist.append(u"คำเตือน: ไม่เกิดการแทนที่ข้อความที่ {}".format(num))
text = newtext
def matchbrace(s, i):
lv = 0
for i in xrange(i, len(s)):
if s[i] == "{": lv += 1
elif s[i] == "}": lv -= 1
if lv == 0:
return i
# not return i + 1 to avoid index out of range
for item in config["addParam"]:
if len(item) == 3:
num, param, translate = item
else:
page.u_elist.append(u"คำเตือน: ข้อความแปลที่ {} มีจำนวนพารามิเตอร์ไม่ถูกต้อง".format(num))
continue
lst = []
for i in lre.finditer(r"\{\{\{\s*" + param + "\s*[\|\}]", text):
begin, end = i.span()
end = matchbrace(text, begin)
lst.append((begin, "begin"))
lst.append((end, "end"))
lst = sorted(lst)
lst.append((sys.maxint, sys.maxint))
ilst = 0
out = []
for i in xrange(len(text)):
if i == lst[ilst][0]:
if lst[ilst][1] == "begin":
out.append("{{{" + translate + "|")
else:
out.append("}}}")
# we should put text[i] before "}}}",
# but since text[i] == "}", there is no problem :)
ilst += 1
out.append(text[i])
newtext = "".join(out)
if newtext == text:
page.u_elist.append(u"คำเตือน: ไม่เกิดการแปลพารามิเตอร์ที่ {}".format(num))
text = newtext
"""
for item in config["obsolete"]:
if len(item) == 3:
num, oldParam, newParam = item
showError = False
elif len(item) == 4:
num, oldParam, newParam, showError = item
else:
page.u_elist.append(u"คำเตือน: การตรวจสอบพารามิเตอร์ล้าสมัยที่ {} มีจำนวนพารามิเตอร์ไม่ถูกต้อง".format(num))
continue
category = wp.Category("Category:" + page.title().replace(":", "") +
u" ที่ใช้พารามิเตอร์ " + oldParam)
checkcat.append(category)
deprecated.append(u'<includeonly>{{{{#if:{{{{{{{}|}}}}}}|[[{}]]'
.format(oldParam, category.title()) +
((u'<span class="error">พารามิเตอร์ {} '
u'ล้าสมัยแล้ว โปรดใช้ {} แทนที่</span><br />')
.format(oldParam, newParam)
if showError else u'') +
u'}}</includeonly>')
text = "".join(deprecated) + text
"""
#=======
if page.userName() not in ['^Nullzerobot', 'Nullzerobot', 'Nullzero']:
page.u_elist.append(u"คำเตือน: ผู้แก้ไขหน้านี้ครั้งสุดท้ายคือ " + page.userName())
if (not page.u_elist) and (text == originalText):
pywikibot.output((u"ไม่มีการเปลี่ยนแปลงในหน้า {}; "
u"ยกเลิกการปรับปรุงและแจ้งเตือน").format(source.title()))
return
if page.namespace() == 828 and 'wrappers' in text:
page.u_elist.append(u"คำเตือน: มอดูลนี้มี wrapper")
if debug:
pywikibot.showDiff(originalText or "", text)
return
if config.get("sandbox", False):
page = wp.Page(page.title() + "/sandbox")
page.u_text = text
page.put(text, u"ปรับปรุงหน้าอัตโนมัติโดยบอต", async=True, callback=callback)
def finalize(self):
self.text = cgi.escape(self.clean())
self.text = lre.sub(r'(?is)' + self.begin, "<a href='" + '//' + self.siteSource.code + '.wikipedia.org/wiki/' + r"\1 ' title='\1'>", self.text)
self.text = self.text.replace(self.end, '</a>')
def rmtag(self, tag):
self.content = lre.sub("(?s)<{tag}>.*?</{tag}>".format(tag=tag), "", self.content)
def fixRepetedVowel(content):
"""If found impossible vowel arrangement in text, correct it."""
for i in checkVowel:
content = lre.sub(i + u"+", i, content)
return content
def main():
if "-html" not in args:
return
page = wp.Page(wp.toutf(raw_input()))
dic = {}
while True:
if not page.exists():
dic["error"] = u"ไม่มีหน้าดังกล่าว"
break
elif page.isRedirectPage():
page = page.getRedirectTarget()
else:
try:
oldtext = page.get()
except:
dic["error"] = u"เกิดข้อผิดพลาดไม่ทราบสาเหตุ"
break
if "error" not in dic:
actuallen = lambda text: sum([int(32 < ord(i) < anchorBegin)
for i in text])
resgen = lambda x: "passed" if x else "failed"
oldtext = lre.sub(r"[\t\r\f\v]", " ", oldtext)
def placemarker(s):
placemarker.i += 1
return unichr((placemarker.i % (anchorEnd - anchorBegin + 1)) +
anchorBegin)
placemarker.i = 0
oldtext = lre.sub("(?m)^|$", placemarker, oldtext)
oldtext = lre.sub(r"(?m)(?<=\|)(?=[^\[\]]*\]\])", placemarker, oldtext)
oldtext = lre.sub(r"(?m)(?<=\])(?!\])", placemarker, oldtext)
oldtext = lre.sub(r"(?m)(?<!\{)(?=\{)", placemarker, oldtext)
oldtext = lre.sub(r"(?m)(?<=\})(?!\})", placemarker, oldtext)
text = oldtext
text, numinline0 = lre.subn(r"(?s)<ref[^>]*?/ *>", "", text)
text, numinline = lre.subn(r"(?s)<ref.*?</ref>", "", text)
numinline += numinline0
dic["inline"] = {}
dic["inline"]["value"] = (u"มีอ้างอิงในบรรทัดทั้งหมดจำนวน %d แห่ง" %
numinline)
dic["inline"]["result"] = "normal"
dic["inline"]["text"] = u"อ้างอิง"
text = rem(text)
lentext = actuallen(text)
dic["newtext"] = showdiff(oldtext, text)
dic["len"] = {}
dic["len"]["text"] = u"ความยาว"
dic["len"]["result"] = resgen(lentext >= 2000)
dic["len"]["value"] = u"%d อักขระ..." % lentext
now = site.getcurrenttime()
revid = None
revtimestamp = None
for rev in page.getVersionHistory(total=5000):
ts = pywikibot.Timestamp.fromISOformat(rev[1])
revid = rev[0]
if (now - ts).days <= 14:
revtimestamp = ts
else:
break
dic["oldlen"] = {}
dic["oldlen"]["text"] = u"รุ่นเก่า"
if revtimestamp is None:
dic["oldlen"]["result"] = resgen(False)
dic["oldlen"]["value"] = u"ไม่พบรุ่นเก่าภายในเวลา 14 วัน"
else:
lenold = actuallen(rem(page.getOldVersion(revid)))
dic["oldlen"]["result"] = resgen(
(float(lentext)/float(lenold)) >= 3.0)
dic["oldlen"]["value"] = (u"รุ่นเก่าก่อนการแก้ไขเมื่อ %s "
u"(%d วันที่แล้ว) "
u"มีความยาว %d อักขระ "
u"จะได้ว่าขณะนี้มีเนื้อหาเป็น %.3f "
u"เท่าเมื่อเทียบกับขณะนั้น..." %
(revtimestamp.strftime("%Y-%m-%d %H:%M:%S"),
(now - revtimestamp).days, lenold,
float(lentext)/float(lenold)))
creator = page.getVersionHistory(reverseOrder=True, total=1)[0]
tscreate = pywikibot.Timestamp.fromISOformat(creator[1])
dic["create"] = {}
dic["create"]["text"] = u"สร้างบทความ"
dic["create"]["result"] = resgen((now - tscreate).days <= 14)
dic["create"]["value"] = (u"บทความนี้สร้างโดย %s "
u"เมื่อ %s (%d วันที่แล้ว)" % (creator[2],
tscreate.strftime("%Y-%m-%d %H:%M:%S"),
(now - tscreate).days))
if ((dic["create"]["result"] == resgen(True)) or
(dic["oldlen"]["result"] ==
resgen(True))):
if dic["create"]["result"] == resgen(False):
dic["create"]["result"] = "normal"
if dic["oldlen"]["result"] == resgen(False):
dic["oldlen"]["result"] = "normal"
print json.dumps(dic)