Misplaced Pages

Revision as of 14:22, 10 August 2008

# This is a title blacklist; every title that matches regex here are forbidden to create and edit.
# Use "#" for comments; see the talk page for more options.
# Please log additions to the title blacklist log.
# Note: internally, the pattern delimiter is '/', so be sure to escape all '/'s.
# Also, UTF-8 mode is enabled.
# Do not use literal non-breaking spaces in regexes; some browsers cannot handle them.

# Obscure ASCII character lookalikes
.*.* # Select letterlike symbols (excluding Kelvin, Angstrom and Ohm signs, see talk)
.*.* # Circled and parenthesized Latin letters
.*.* <errmsg=titleblacklist-custom-fullwidth> # Fullwidth Latin letters
.*.* <moveonly> # Question mark lookalikes, used for page move vandalism
.*.* # Phonetic extensions, almost never used in valid titles
.*.* <moveonly> # IPA extensions, somewhat more common, so blocking only moves for now
.*.* <moveonly> # Select mathematical operators (excluding "−", "∞" and some other common ones)
.*.* <moveonly> # Misc./supplemental mathematical symbols

# Other undesirable characters
.*.* <errmsg=titleblacklist-custom-nbsp> # Non-breaking and other unusual spaces, with custom error message
.*.* # BiDi overrides
.*.* # "Other punctuation", with some exceptions (may need more, this is a huge character class); note that single-character titles are permitted by the title whitelist
.*\p{Cc}.* # Control characters
.*\x{FEFF}.* # Byte order mark
.*.* # Swastikas, hammer-and-sickle
.*\x{00AD}.* # Soft-hyphen
.*.* # Very few characters outside the Basic Multilingual Plane are useful in titles

# Excessive punctuation or repetition
.*{3}(?<!!!!).*
.*\s+.*
.*‽‽.* <moveonly>
.*¿¿.* <moveonly>
.*HA.* <casesensitive | moveonly>
.*GG.* <casesensitive | moveonly>
.*R.* <moveonly>
.*{2}.*
.*{5}.*
.*()\1{4}.* <moveonly>
.*(.)\1{10}.* <newaccountonly>
.*\p{Lu}(\P{L}*\p{Lu}){9}.* <casesensitive | moveonly>  # TOO MUCH ALL CAPS

# Inverted question mark with non-Latin text, used for "upside-down" page move vandalism
.*¿.*.*
.*.*¿.*

# Attack titles and/or page move vandalism targets
.*JEWS DID WTC.*
.*on whee+ls.* <moveonly>
.*on wh33ls.*
.*on whiels.*
.*onwheels.*
.*on rails.* <moveonly>
.*on treads.* <moveonly>
.*Template.*arab.*world.*unity 
.*Seth.*Patinkin.*
.*Jan.*Szatkowski.*
.*(Bill|William).*Beggs.*
.*massive.* <moveonly>
.*ENORMOUS COCK.*
.*BITCH.* <casesensitive>
.*COCK.* <casesensitive>
.*ċock.*
.*cck.*
.*CUM.* <casesensitive>
.*DICK.* <casesensitive>
.*giant d.* <moveonly>
.*giiant.*
.*ck make.* <moveonly>
.*have sex.* <moveonly>
.*(?:suck|his|your|my) penis.* <moveonly>
.*(?:http|https|ftp|mailto|torrent|ed2k)\:\/\/+\.+.*
.*\bis\s+an?\s+(?:dick|cunt|fag|bitch|shit|fuck|loser|ass|gay|ghey|moron|retard|stupid|slut|pa?edo).* <autoconfirmed>
.*\bis\s+an?\s+(?:dick|cunt|fag|bitch|shit|fuck|loser|ass|gay|ghey|moron|retard|stupid|slut|pa?edo).* <moveonly>
.*\bnimp\.org.*
.*JIHAD, BITCHES.*
.*Vandalism is Terrorism.*
.*WANT TO HA.* <moveonly>
.*waant to h.* <moveonly>
.*\bAvri.* <moveonly>
.*Brian.*Peppers.*
.*suck my.* <moveonly>
.*GE ORGAS.* <moveonly>
.*ge orrg.* <moveonly>
.*RM, STICKY.*
.*rm sticky.* <moveonly>
.*TAIN OUT OF.* <moveonly>
.*ngger.* <moveonly>
.*nigger.*nigger.*
.*niggger.*
.*nigggger.*
.*niggggger.*
.*skater girl.* <moveonly>
.*sk8r.* <moveonly>
.*loves the.* <moveonly>
.*cking fail.*
.*Epic fail.*
.*Lol.* <moveonly>
.*LAWL.* <moveonly>
.*WHUT.* <moveonly>
.*What what.* <moveonly>
.*p\? G.* <moveonly>
.*p Gi.* <moveonly>
.*Grp.* <moveonly>
.*Grwp.*
.*Haggis.* <moveonly>
.*GGER.* <casesensitive>
.*HE.* <casesensitive>
.*HR.* <casesensitive>
.*AR.* <casesensitive>
.*ERMY.* <casesensitive>
.*ERMEE.* <casesensitive>
.*ERMI.* <casesensitive>
.*RMIE.* <casesensitive>
.*RMEY.* <casesensitive>
.*Rapes babies.*
.*instead f.* <moveonly>

User( talk)?:71\.107\.(1(2|\d)|2(\d|5))\.(?\d\d?|2(5|\d)) <autoconfirmed>

# Page move targets
.*.* <moveonly>
(.*\W)?(|\\W\)+(\W|\W.*\W)?((|\/\W?\\)(\W|\W.*\W)?)+((\W|\W.*\W)?)+((|\/\W?\\)(\W|\W.*\W)?)*+(\W.*)? <moveonly> # HAGGR
(.*\W)?+(\W|\W.*\W)?((|\/\W?\\)(\W|\W.*\W)?)*((\W|\W.*\W)?)+((|\/\W?\\)(\W|\W.*\W)?)+(|\\W\)+(\W.*)?  <moveonly> # RGGAH
(.*\W)?(|\\W\)+(\W|\W.*\W)?((\W|\W.*\W)?)*((\W|\W.*\W)?)+((\W|\W.*\W)?)++(\W.*)?  <moveonly> # HERMY
(.*\W)?+(\W|\W.*\W)?((\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)*(|\\W\)+(\W.*)? <moveonly> # YMREH
.*((\W|\W.*\W)?(\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)+.* <moveonly>
.*I\W*B\W*H\W*H\W*F\W*S.* <moveonly>
.*I\W*F\W*S\W*N\W*Z.* <moveonly>
Misplaced Pages( talk)?:(*(?-i:).*|(.*\W)?+(\W|\W.*\W)?(((\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)++|((\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)+Y+)(\W.*)?) <moveonly> # No haggery in project space, please. (Only ASCII/Latin1 characters needed in this regexp.)
(Help|Portal)( talk)?:(.*(?-i:).*|(.*\W)?+(\W|\W.*\W)?(((\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)++|((\W|\W.*\W)?)+((\W|\W.*\W)?)+((\W|\W.*\W)?)+Y+)(\W.*)?) <moveonly> # ..nor in help or portal spaces either. (Only ASCII/Latin1 characters needed in this regexp.)

# Potentially confusing mixed-script titles (alas, can't entirely disallow Cyrillic/Greek + Latin, too common)
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)*.*\p{Cyrillic}.* # Cyrillic + Non-ASCII Latin
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{Cyrillic}*\p{Cyrillic}.*.* # Cyrillic + Non-ASCII Latin
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)*.*\p{Greek}.* # Greek + Non-ASCII Latin
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{Greek}*\p{Greek}.*.* # Greek + Non-ASCII Latin
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{Cyrillic}*\p{Cyrillic}.*\p{Greek}.* # Cyrillic + Greek
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{Greek}*\p{Greek}.*\p{Cyrillic}.* # Cyrillic + Greek
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Armenian}.*.* # Armenian + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Armenian}.* # Armenian + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Bengali}.*.* # Bengali + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Bengali}.* # Bengali + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Cherokee}.*.* # Cherokee + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Cherokee}.* # Cherokee + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Ethiopic}.*.* # Ethiopic + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Ethiopic}.* # Ethiopic + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Georgian}.*.* # Georgian + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Georgian}.* # Georgian + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Gujarati}.*.* # Gujarati + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Gujarati}.* # Gujarati + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Gurmukhi}.*.* # Gurmukhi + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Gurmukhi}.* # Gurmukhi + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Kannada}.*.* # Kannada + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Kannada}.* # Kannada + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Khmer}.*.* # Khmer + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Khmer}.* # Khmer + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Lao}.*.* # Lao + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Lao}.* # Lao + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Malayalam}.*.* # Malayalam + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Malayalam}.* # Malayalam + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Myanmar}.*.* # Myanmar + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Myanmar}.* # Myanmar + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Oriya}.*.* # Oriya + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Oriya}.* # Oriya + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Runic}.*.* # Runic + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Runic}.* # Runic + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Sinhala}.*.* # Sinhala + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Sinhala}.* # Sinhala + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Syriac}.*.* # Syriac + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Syriac}.* # Syriac + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Tamil}.*.* # Tamil + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Tamil}.* # Tamil + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Telugu}.*.* # Telugu + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Telugu}.* # Telugu + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Thaana}.*.* # Thaana + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Thaana}.* # Thaana + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Thai}.*.* # Thai + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Thai}.* # Thai + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*\p{Tibetan}.*.* # Tibetan + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:)\P{L}*.*\p{Tibetan}.* # Tibetan + anything else
(?!(User|Misplaced Pages|Image)( talk)?:|Talk:).*.* # Unused obscure scripts

# Disallow pagemoves to mixed-script titles (can't blacklist these entirely, way too many legitimate uses)
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*\p{Latin}.*.* <moveonly> # Latin + non-Latin
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*.*\p{Latin}.* <moveonly> # Latin + non-Latin
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*\p{Greek}.*.* <moveonly> # Greek + non-Greek
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*.*\p{Greek}.* <moveonly> # Greek + non-Greek
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*\p{Cyrillic}.*.* <moveonly> # Cyrillic + non-Cyrillic
(?!(User|Misplaced Pages)( talk)?:|Talk:)\P{L}*.*\p{Cyrillic}.* <moveonly> # Cyrillic + non-Cyrillic
# Slightly different regexp for user/project/talk pages, to allow e.g. Latin subpages of Cyrillic usernames:
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}*\p{Latin}*.* <moveonly> # Latin + non-Latin 
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}**\p{Latin}.* <moveonly> # Latin + non-Latin
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}*\p{Greek}*.* <moveonly> # Greek + non-Greek
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}**\p{Greek}.* <moveonly> # Greek + non-Greek
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}*\p{Cyrillic}*.* <moveonly> # Cyrillic + non-Cyrillic
((User|Misplaced Pages)( talk)?:|Talk:)(.*\/)?\P{L}**\p{Cyrillic}.* <moveonly> # Cyrillic + non-Cyrillic
.*(\P{L}*){4}.* <casesensitive | moveonly> # Non-Latin all caps