Utente:Sanjilops/Shitconfig.py: differenze tra le versioni

mNessun oggetto della modifica
mNessun oggetto della modifica
 
(2 versioni intermedie di uno stesso utente non sono mostrate)
Riga 25: Riga 25:


# Banalità:
# Banalità:
(r"\[\[[Aa] nessuno importa", 7),
(r"\[\[a nessuno importa", 7),
(r"\bcalcio rotante\b", 9),
(r"\bcalc(io|i) rotant[ei]\b", 9),
(r"\bcalcio volante\b", 9),
(r"\bcalc(io|i) volant[ei]\b", 9),
(r"\bChuck( Norris)?\b", 9),
(r"\bChuck( Norris)?\b", 9),
(r"\bSupremo\b", 9),
(r"\bSommo\b", 9),
(r"\bSommo\b", 9),
(r"[Ll]\'Altissimo\b", 9),
(r"l\'Altissimo\b", 9),
(r"\bcalciorotat[aeio]\b", 9),
(r"\bcalciorotat[aeio]\b", 9),
(r"\b(Germano )?Mosconi\b", 7),
(r"\b(Germano )?Mosconi\b", 7),
(r"\b[Nn]iubb[io]+\b", 8),
(r"\bniubb[io]+\b", 8),
(r"\b[Nn]onciclopedia\b", 7),
(r"\bNonciclopedia\b", 7),
(r"\bPalpatine\b", 5),
(r"\bPalpatine\b", 5),
(r"\bSPARTAA+!*\b", 6),
(r"\bSPARTAA+!*\b", 6),
(r"\b[Ss]verveg(ia|es[ei])\b", 9),
(r"\bSverveg(ia|es[ei])\b", 9),


# Cliché delle citazioni:
# Cliché delle citazioni:
(r"mort[aeio][\s\.\;]*\|\s*\|?[Nn]i[etzsch]+e\|", 9),
(r"mort[aeio][\s\.\;]*\|\s*\|?[Nn]i[etzsch]+e\|", 10),
(ur"\|[Bb]imb[aeio]min(k|ch)ia\|", 9),
(ur"\|chiunque\|", 9),
(ur"\|[Cc]hiunque\|", 9),
(ur"\|nessuno\|", 9),
(ur"\|[Cc]oglione\|", 9),
(ur"\|tutti\|", 9),
(ur"\|[Nn]essuno\|", 9),
(ur"\|[Tt]utti\|", 9),


# Cliché dei link mascherati:
# Cliché dei link mascherati:
(r"\[\[[Cc]azzat[ae]\|", 9),
(r"\[\[fanculo\|qui\]\]", 9),
(r"\[\[[Cc]oglione\|", 9),
(r"\[\[ma anche no\|", 6),
(r"\[\[[Ff]anculo\|qui\]\]", 9),
(r"\[\[[Mm]a anche no\|", 6),




# Tormentoni musicali e mode (emo, truzzi, metal, ecc...):
# Tormentoni musicali e mode (emo, truzzi, metal, ecc...):
(r"\b[Bb]imb[aeio]min(k|ch)i(ese|[ae])\b", 7),
(r"\bbimb[aeio]min(k|ch)i(ese|[ae])\b", 7),
(r"\b[Dd]ark(etton[aei])?\b", 3),
(r"\bdark(etton[aei])?\b", 3),
(r"\b[Ee]mo\b", 9),
(r"\bemo\b", 9),
(r"\b([Hh\']eavy )?[Mm]etal(lar[aeio]|lon[aei]|lat[ae]|)\b", 7),
(r"\b([Hh\']eavy )?metal(lar[aeio]|lon[aei]|lat[ae]|)\b", 7),
(r"\b[Kk]aulitz\b", 9),
(r"\b(Tom |Bill )?Kaulitz\b", 10),
(r"\b[Pp]unk(etton[aei]|)\b", 5),
(r"\bpunk(etton[aei]|)\b", 5),
(r"\b[Rr]o(ck|cch|kk)e(tta)?r[aeio]?\b", 5),
(r"\bro(ck|cch|kk)e(tta)?r[aeio]?\b", 5),
(r"\b[Tt]ok[iy]o [Hh]otel\b", 9),
(r"\bTok[iy]o Hotel\b", 10),
(r"\b[Tt]ruzz(aggin[ei]|[aeio])\b", 9),
(r"\btruzz(aggin[ei]|[aeio])\b", 9),




# Volgarità varie:
# Volgarità varie:
(r"\ban(al(e|mente)|[io])\b", 8),
(r"\ban(al(e|mente)|[io])\b", 8),
(r"\bbagasci[ae]\b", 7),
(r"\bbagasc(ia|e)\b", 7),
(r"\bbocchin([io]|ar[aeio])\b", 6),
(r"\bbocchin([io]|ar[aeio])\b", 6),
(ur"\bca[cg]\w+\b", 9),
(ur"\bca[cg]\w+", 9),
(r"\bcazz(at[ae]|on[ei]|[io])\b", 9),
(r"\bcazz(at[ae]|on[ei]|[io])\b", 9),
(r"\b(rompi)?[Cc]oglion[ei])\b", 9),
(r"\bchiav[ai]\w+", 8),
(r"\b(rompi)?coglion[ei]\b", 9),
(r"\bcul[io]\b", 6),
(r"\bcul[io]\b", 6),
(r"\b[Dd]io ([Pp]orco|[Cc]ane)\b", 9),
(r"\bDio (Porco|Cane)\b", 10),
(r"\b(vaf)?fanculo\b", 8),
(r"\b(vaf)?fanculo\b", 8),
(r"\bfi[gc](a|he)\b", 7),
(r"\bfi[gc](a|he)\b", 7),
Riga 89: Riga 85:
(r"\bpene\b", 6),
(r"\bpene\b", 6),
(r"\bpompin[io]\b", 6),
(r"\bpompin[io]\b", 6),
(r"\b[Pp]orco [Dd]io\b", 9),
(r"\bPorco Dio\b", 10),
(r"\bprostitut[ae]\b", 6),
(r"\bprostitut[ae]\b", 6),
(r"\bputtan[ae]\b", 7),
(r"\bputtan[ae]\b", 7),
(r"\bricchion[ei]\b", 9),
(r"\bricchion[ei]\b", 9),
(r"\bsborra\w*\b", 8),
(r"\bsborra\w*", 8),
(r"\bscop[ai]\w+\b", 8),
(r"\bscop[ai]\w+", 8),
(r"\bseg(a|he|aiol[aeio])\b", 8),
(r"\bseg(a|he|aiol[aeio])\b", 8),
(r"\bsodomizz", 6),
(r"\bsodomizz[ai]\w+", 6),
(r"\bstronz[aeio](t[ae])?\b", 9),
(r"\bstronz[aeio](t[ae])?\b", 9),
(r"\bsperma\b", 6),
(r"\bsperma\b", 6),
(r"\bstupr\w+", 6),
(r"\bstupr\w+", 6),
(r"\btroi(on)?[ae]\b", 9),
(r"\btroi(on)?[ae]\b", 9),
(r"\btromb([ai]\w+|o)", 8),
(r"\btromb[ai]\w+", 8),
(r"\bzoccol[ae]\b", 7),
(r"\bzoccol[ae]\b", 7),



Versione attuale delle 00:17, 24 lug 2008

# -*- coding: utf-8 -*-

__version__ = '$Id: shitconfig.py 1.0 2008-07-23 17:40:00$'

configs = {
    # valori che servono per il calcolo della soglia di shitness,
    # secondo la formula:
    # shitLimit = shitLimitBase + (PageSize * shitLimitMul / 1024)
    'shitLimitBase': 5,
    'shitLimitMul': 10,

    # "motivo" dei tag {{accusa}} e {{cancellazione}}:
    'tagMessage': u"Bassa qualità generale",

    # messaggio delle modifiche compiute dal bot:
    'editMessage': u"Bot: Nonci-shit-detector (vers. 1.0)",

    # devo analizzare tutte le pagine che hanno shitness maggiore di
    # zero (anche se non superano lo soglia)?
    'zeroTolerance': False,
}

shitTable = [

    # Banalità:
    (r"\[\[a nessuno importa", 7),
    (r"\bcalc(io|i) rotant[ei]\b", 9),
    (r"\bcalc(io|i) volant[ei]\b", 9),
    (r"\bChuck( Norris)?\b", 9),
    (r"\bSommo\b", 9),
    (r"l\'Altissimo\b", 9),
    (r"\bcalciorotat[aeio]\b", 9),
    (r"\b(Germano )?Mosconi\b", 7),
    (r"\bniubb[io]+\b", 8),
    (r"\bNonciclopedia\b", 7),
    (r"\bPalpatine\b", 5),
    (r"\bSPARTAA+!*\b", 6),
    (r"\bSverveg(ia|es[ei])\b", 9),

    # Cliché delle citazioni:
    (r"mort[aeio][\s\.\;]*\|\s*\|?[Nn]i[etzsch]+e\|", 10),
    (ur"\|chiunque\|", 9),
    (ur"\|nessuno\|", 9),
    (ur"\|tutti\|", 9),

    # Cliché dei link mascherati:
    (r"\[\[fanculo\|qui\]\]", 9),
    (r"\[\[ma anche no\|", 6),


    # Tormentoni musicali e mode (emo, truzzi, metal, ecc...):
    (r"\bbimb[aeio]min(k|ch)i(ese|[ae])\b", 7),
    (r"\bdark(etton[aei])?\b", 3),
    (r"\bemo\b", 9),
    (r"\b([Hh\']eavy )?metal(lar[aeio]|lon[aei]|lat[ae]|)\b", 7),
    (r"\b(Tom |Bill )?Kaulitz\b", 10),
    (r"\bpunk(etton[aei]|)\b", 5),
    (r"\bro(ck|cch|kk)e(tta)?r[aeio]?\b", 5),
    (r"\bTok[iy]o Hotel\b", 10),
    (r"\btruzz(aggin[ei]|[aeio])\b", 9),


    # Volgarità varie:
    (r"\ban(al(e|mente)|[io])\b", 8),
    (r"\bbagasc(ia|e)\b", 7),
    (r"\bbocchin([io]|ar[aeio])\b", 6),
    (ur"\bca[cg]\w+", 9),
    (r"\bcazz(at[ae]|on[ei]|[io])\b", 9),
    (r"\bchiav[ai]\w+", 8),
    (r"\b(rompi)?coglion[ei]\b", 9),
    (r"\bcul[io]\b", 6),
    (r"\bDio (Porco|Cane)\b", 10),
    (r"\b(vaf)?fanculo\b", 8),
    (r"\bfi[gc](a|he)\b", 7),
    (r"\bfott[aeiou]\w+\b", 7),
    (r"\bfroc(io|i)\b", 9),
    (r"\bincul[ae]\b", 9),
    (r"\bmasturb", 6),
    (r"\bmerd(on)?[aei]\b", 9),
    (r"\bminchi[ae]\b", 6),
    (r"\bmignott(on)?[ae]\b", 7),
    (r"\borg(ia|e)\b", 7),
    (r"\bpalle\b", 6),
    (r"\bpene\b", 6),
    (r"\bpompin[io]\b", 6),
    (r"\bPorco Dio\b", 10),
    (r"\bprostitut[ae]\b", 6),
    (r"\bputtan[ae]\b", 7),
    (r"\bricchion[ei]\b", 9),
    (r"\bsborra\w*", 8),
    (r"\bscop[ai]\w+", 8),
    (r"\bseg(a|he|aiol[aeio])\b", 8),
    (r"\bsodomizz[ai]\w+", 6),
    (r"\bstronz[aeio](t[ae])?\b", 9),
    (r"\bsperma\b", 6),
    (r"\bstupr\w+", 6),
    (r"\btroi(on)?[ae]\b", 9),
    (r"\btromb[ai]\w+", 8),
    (r"\bzoccol[ae]\b", 7),

    # Uso banale dell'omosessualità:
    (r"\bfinocchio?\b", 9),
    (r"\bgay\b", 6),
    (ur"\bomosessual(ità|[ei])", 6),
    (r"\btrans(essual[ei]|-?gender|)\b", 8),
]