Toggle search
Toggle menu
2.9K
19.7K
5.1K
7.9M
Portal Wiki
Toggle preferences menu
Toggle personal menu
Not logged in
Your IP address will be publicly visible if you make any edits.

User:WindBOT/CoreSource: Difference between revisions

From the Portal Wiki
More actions
← Older edit
m backport changes from tf wiki
Added new built-in filter: Simplify anchors
 
(6 intermediate revisions by the same user not shown)
Line 30: Line 30:
import wikiUpload
import wikiUpload
import feedparser
import feedparser
import steam
try:
import steam
except:
steam = None
from wikiUpload import wikiUploader
from wikiUpload import wikiUploader


from botConfig import config
from botConfig import config
steam.set_api_key(config['steamAPI'])
if steam is not None and 'steamAPI' in config:
steam.set_api_key(config['steamAPI'])
config['runtime'] = {
config['runtime'] = {
'rcid': -1,
'rcid': -1,
Line 148: Line 152:
summary = getSummary(summary)
summary = getSummary(summary)
p = page(p)
p = page(p)
print 'Editing', p.title, 'with summary', summary
try:
print 'Editing', p.title, 'with summary', summary
except:
pass
try:
try:
if nocreate:
if nocreate:
Line 200: Line 207:
except:
except:
warning('Couldn\'t update edit count.')
warning('Couldn\'t update edit count.')
# Because SOME LIBRARY will not use singletons, this has to be done at the bot level
# rather than the individual filter level to avoid loading the damn thing twice.
steamGameSchemas = {}
def steamGetGameSchema(game):
global steamGameSchemas
if steam is None:
return None
if game not in steamGameSchemas:
steamGameSchemas[game] = game.item_schema()
return steamGameSchemas[game]
steamGameAssets = {}
def steamGetGameAssets(game):
global steamGameAssets
if steam is None:
return None
if game not in steamGameAssets:
steamGameAssets[game] = game.assets()
return steamGameAssets[game]


def compileRegex(regex, flags=re.IGNORECASE):
def compileRegex(regex, flags=re.IGNORECASE):
Line 232: Line 258:
self.setLabel(None)
self.setLabel(None)
self.setLink(u'')
self.setLink(u'')
self.anchor = None
self.joined = False
self.joined = False
if len(content) > 2:
if len(content) > 2:
Line 241: Line 268:
if lnk.find(u':') == -1:
if lnk.find(u':') == -1:
lnk = lnk.replace(u'_', u' ')
lnk = lnk.replace(u'_', u' ')
anchor = None
if lnk.find(u'#') != -1:
lnk, anchor = lnk.split(u'#', 1)
self.setAnchor(anchor)
self.setLink(lnk)
self.setLink(lnk)
if len(split) == 2:
if len(split) == 2:
Line 246: Line 277:
else:
else:
self.setLabel(split[0])
self.setLabel(split[0])
self.joined = True
self.joined = anchor is None
elif content[0] == u'[' and content[-1] == u']':
elif content[0] == u'[' and content[-1] == u']':
split = content[1:-1].split(u' ', 1)
split = content[1:-1].split(u' ', 1)
Line 259: Line 290:
def getBody(self):
def getBody(self):
return u(self.body)
return u(self.body)
def getLink(self):
def getLink(self, withAnchor=False):
if withAnchor and self.getAnchor() is not None:
return u(self.link) + u'#' + self.getAnchor()
return u(self.link)
return u(self.link)
def getAnchor(self):
return self.anchor
def getLabel(self):
def getLabel(self):
if self.label is None:
if self.label is None:
Line 272: Line 307:
self.body = u(body)
self.body = u(body)
def setLink(self, link):
def setLink(self, link):
self.link = u(link)
link = u(link)
if self.getType() == u'internal' and link.find(u'#') != -1:
link, anchor = link.split(u'#', 1)
self.setAnchor(anchor)
self.link = link
if self.joined:
if self.joined:
self.label = u(link)
self.label = u(link)
replaceDots = compileRegex(r'(?:\.[a-f\d][a-f\d])+')
def _replaceDots(self, g):
s = ''
g = g.group(0)
for i in xrange(0, len(g), 3):
s += chr(int(g[i + 1:i + 3], 16))
return s.decode('utf8')
def setAnchor(self, anchor):
if self.getType() == u'internal':
u(anchor).replace(u'_', u' ')
try:
anchor = link.replaceDots.sub(self._replaceDots, anchor)
except:
pass
self.anchor = anchor
def setLabel(self, label):
def setLabel(self, label):
if label is None:
if label is None:
Line 288: Line 342:
def __unicode__(self):
def __unicode__(self):
label = self.getLabel()
label = self.getLabel()
tmpLink = self.getLink()
tmpLink = self.getLink(withAnchor=True)
if self.getType() == u'internal':
if self.getType() == u'internal':
tmpLink2 = tmpLink.replace(u'_', u' ')
tmpLink2 = tmpLink.replace(u'_', u' ')
Line 585: Line 639:
content = content.replace(s[0], s[1])
content = content.replace(s[0], s[1])
return content
return content
def regReplaceCallBack(sub, match):
def regReplaceCallBack(sub, match):
groupcount = 1
groupcount = 1
Line 700: Line 753:
f, params = f
f, params = f
for i in range(len(linklist)):
for i in range(len(linklist)):
if linklist[i] is not None:
if linklist[i] is not None and isinstance(linklist[i], link):
oldLink = u(linklist[i])
oldLink = u(linklist[i])
linklist[i] = f(linklist[i], **kwargs)
linklist[i] = f(linklist[i], **kwargs)
Line 716: Line 769:
f, params = f
f, params = f
for i in range(len(templatelist)):
for i in range(len(templatelist)):
if templatelist[i] is not None:
if templatelist[i] is not None and isinstance(templatelist[i], template):
oldTemplate = u(templatelist[i])
oldTemplate = u(templatelist[i])
templatelist[i] = f(templatelist[i], **kwargs)
templatelist[i] = f(templatelist[i], **kwargs)
Line 748: Line 801:
return setFilterName(curry(dumbReplacement, rs), u'DumbReplacements(' + u(rs) + u')')
return setFilterName(curry(dumbReplacement, rs), u'DumbReplacements(' + u(rs) + u')')
def dumbReplace(subject, replacement):
def dumbReplace(subject, replacement):
return setFilterName(dumbReplaces({subject: replacement}), u'DumbReplacement(' + u(subject) + u' -> ' + u(replacement) + u')')
return setFilterName(dumbReplaces({subject: replacement}), u'DumbReplacement(' + u(subject) + u' \u2192 ' + u(replacement) + u')')
def wordRegex(word, **kwargs):
def wordRegex(word, **kwargs):
flags = None
flags = None
Line 755: Line 808:
word = word[0]
word = word[0]
word = u(re.sub(r'[-_ ]+', r'[-_ ]', u(word)))
word = u(re.sub(r'[-_ ]+', r'[-_ ]', u(word)))
word = u(r"(?<![\u00E8-\u00F8\xe8-\xf8\w])(?<!'')(?<!" + r'"' + r")(?:\b|^)" + word + r"(?:\b(?![\u00E8-\u00F8\xe8-\xf8\w])(?!''|" + r'"' + r")|$)")
word = u(r"(?<![\u00E8-\u00F8\xe8-\xf8\w])(?<!'')(?<!" + r'"' + ")(?:\\b|(?<=[ \\[\\]\\(\\):;.,\"'*\\xab\\xbb])|^)" + word + r"(?:\b(?![\u00E8-\u00F8\xe8-\xf8\w])(?!''|" + r'"' + ")|(?=[ \\[\\]\(\\):;.,\"'*\\xab\\xbb])|$)")
if flags is None:
if flags is None:
return word
return word
Line 780: Line 833:
else:
else:
rs[wordRegex(w, **kwargs)] = correct
rs[wordRegex(w, **kwargs)] = correct
return setFilterName(regexes(rs), u'WordFilter(' + u'/'.join(badwords2) + u' -> ' + correct + u')')
return setFilterName(regexes(rs), u'WordFilter(' + u'/'.join(badwords2) + u' \u2192 ' + correct + u')')
def enforceCapitalization(*words, **kwargs):
def enforceCapitalization(*words, **kwargs):
for w in words:
for w in words:
Line 994: Line 1,047:
except:
except:
error('Couldn\'t grab page', p)
error('Couldn\'t grab page', p)
coderegex = compileRegex(r'^(?: [^\r\n]*(?:[\r\n]+|$))+', re.MULTILINE)
coderegex = compileRegex(r'^(?: [^\r\n]*(?:[\r\n]+|$))+', re.MULTILINE)
trimcode = compileRegex(r'^ |</?nowiki>', re.MULTILINE)
trimcode = compileRegex(r'^ |</?nowiki>', re.MULTILINE)
for m in coderegex.finditer(code):
for m in coderegex.finditer(code):
try:
try:
Line 1,174: Line 1,227:
for f in fs:
for f in fs:
try:
try:
os.remove(tempFile)
os.remove(f)
except:
except:
pass
pass
Retrieved from "https://theportalwiki.com/wiki/User:WindBOT/CoreSource"