adjective_rule.txt

#################################
#  Gender-adjusting adjectives  #
#################################
#   written for FR, IT, ES, PT  #
#################################

# Default adjective is usually in
# Feminine Singular

#The braces define the language
#When it's "^X(.+)", it means "all adjectives starting with X"
#When it's "(.+)er$", it means "all adjectives ending with X"
#$1Y means, let's say it's AX, "write AY"
#First rule to fit is the first rule that gets applied

# Language replacement rules are done by language and use regexes: http://www.cplusplus.com/reference/regex/ECMAScript/
# They have the following general structure:
#	language = {
#		matcher = {
#			suffix = replacement_rule
#			suffix = replacement_rule
#			...
#		}
#	}
#
# Language should match the localisation files (eg. 'french', 'german', 'english')
# Matcher determines if to apply rules to an adjective, and is case insensitive.
#	The first matcher to match is the only one applied for a localisation.
#	It must be a regex, and must be in quotes
#		"^de (.+)" would match all adjectives beginning with "de "
#		"(.+)er$" would match all adjectives ending with "er"
# Suffix is added to the end of the localisation key.
#	_MS would make dfsdf become sfdfdf_MS
# Replacement rule is a regex replacement rule applied to the matched adjective.
#	If the matcher is written to only match some of the adjective ("er$"),
#	the replacement rule will only replace that part.
#	If the matcher is written to match the whole adjective ("(.+)er$"),
#	the replacement will replace the whole thing.
#	There are some special things with replacements:
#	If a matcher has items in parenthesis, those become groups that can be accessed
#	with $1, $2, etc. This can be used to bring in portions of matched adjectives.


french = {
#_MS, _FS, _MP, _FP are respectively m. sing., f. sing., m. pl., f. pl.
#_FR is added because of the language

	#Not-adjectives (i.e. literally "of X") - should not exist!
	"^de (.+)" = {
		_MS_FR = "de $1"
		_FS_FR = "de $1"
		_MP_FR = "de $1"
		_FP_FR = "de $1"
	}
	"^du (.+)" = {
		_MS_FR = "du $1"
		_FS_FR = "du $1"
		_MP_FR = "du $1"
		_FP_FR = "du $1"
	}
	"^des (.+)" = {
		_MS_FR = "des $1"
		_FS_FR = "des $1"
		_MP_FR = "des $1"
		_FP_FR = "des $1"
	}
	
	#Special rules
	"ouzbèke" = { # Uzbek
		_MS_FR = ouzbek
		_FS_FR = ouzbèke
		_MP_FR = ouzbeks
		_FP_FR = ouzbèkes
	}
	"grecque" = { # Greek
		_MS_FR = grec
		_FS_FR = grecque
		_MP_FR = grecs
		_FP_FR = grecques
	}
	"russe" = { # Russian
		_MS_FR = russe
		_FS_FR = russe
		_MP_FR = russes
		_FP_FR = russes
	}
	"suisse" = { # Swiss
		_MS_FR = suisse
		_FS_FR = suisse
		_MP_FR = suisses
		_FP_FR = suisses
	}
	"belge" = { # Belgian
		_MS_FR = belge
		_FS_FR = belge
		_MP_FR = belges
		_FP_FR = belges
	}
	
	#Actual adjectives
	"(.+)èse$" = {
		_MS_FR = $1ès
		_FS_FR = $1èse
		_MP_FR = $1ès
		_FP_FR = $1èses
	}
	"(.+)eux$" = {
		_MS_FR = $1eux
		_FS_FR = $1euse
		_MP_FR = $1eux
		_FP_FR = $1euses
	}
	"(.+)èque$" = {
		_MS_FR = $1èque
		_FS_FR = $1èque
		_MP_FR = $1èques
		_FP_FR = $1èques
	}
	"(.+)que$" = {
		_MS_FR = $1c
		_FS_FR = $1ques
		_MP_FR = $1cs
		_FP_FR = $1ques
	}
	"(.+)gue$" = {
		_MS_FR = $1g
		_FS_FR = $1gue
		_MP_FR = $1gs
		_FP_FR = $1gues
	}
	"(.+)che$" = {
		_MS_FR = $1c
		_FS_FR = $1che
		_MP_FR = $1cs
		_FP_FR = $1ches
	}
	"(.+)ausse$" = {
		_MS_FR = $1aux
		_FS_FR = $1ausse
		_MP_FR = $1aux
		_FP_FR = $1ausses
	}
	"(.+)sse$" = {
		_MS_FR = $1s
		_FS_FR = $1sse
		_MP_FR = $1s
		_FP_FR = $1sses
	}
	"(.+)ère$" = {
		_MS_FR = $1er
		_FS_FR = $1ère
		_MP_FR = $1ers
		_FP_FR = $1ères
	}
	"(.+)trice$" = {
		_MS_FR = $1teur
		_FS_FR = $1trice
		_MP_FR = $1teurs
		_FP_FR = $1trices
	}
	"(.+)euse$" = {
		_MS_FR = $1eux
		_FS_FR = $1euse
		_MP_FR = $1eux
		_FP_FR = $1euses
	}
	"(.+)ve$" = {
		_MS_FR = $1f
		_FS_FR = $1ve
		_MP_FR = $1fs
		_FP_FR = $1ves
	}
	"(.+)nne$" = {
		_MS_FR = $1n
		_FS_FR = $1nne
		_MP_FR = $1ns
		_FP_FR = $1nnes
	}
	"(.+)lle$" = {
		_MS_FR = $1l
		_FS_FR = $1lle
		_MP_FR = $1ls
		_FP_FR = $1lles
	}
	"(.+)iste$" = {
		_MS_FR = $1iste
		_FS_FR = $1iste
		_MP_FR = $1istes
		_FP_FR = $1istes
	}
	"(.+)asque$" = {
		_MS_FR = $1asque
		_FS_FR = $1asque
		_MP_FR = $1asques
		_FP_FR = $1asques
	}
	"(.+)ène$" = {
		_MS_FR = $1ène
		_FS_FR = $1ène
		_MP_FR = $1ènes
		_FP_FR = $1ènes
	}
	"(.+)ète$" = {
		_MS_FR = $1ète
		_FS_FR = $1ète
		_MP_FR = $1ètes
		_FP_FR = $1ètes
	}
	"(.+)ote$" = {
		_MS_FR = $1ote
		_FS_FR = $1ote
		_MP_FR = $1otes
		_FP_FR = $1otes
	}
	"(.+)ite$" = {
		_MS_FR = $1ite
		_FS_FR = $1ite
		_MP_FR = $1ites
		_FP_FR = $1ites
	}
  
 	"(.+)e$" = { # Problem is, some adjectives have -e in both genders...
		_MS_FR = $1
		_FS_FR = $1e
		_MP_FR = $1s
		_FP_FR = $1es
	}
  
	
	#Fallback
	"^(.+)$" = {
		_MS = $1
		_FS = $1
		_MP = $1s
		_FP = $1s
	}
}

italian = {
#_MS, _FS, _MP, _FP are respectively m. sing., f. sing., m. pl., f. pl.
#_IT is added because of the language code
#Default adjective in Italian is f. sing.

	#Not-adjectives (i.e. literally "of X")
	"^di (.+)" = {
		_MS_IT = "di $1"
		_FS_IT = "di $1"
		_MP_IT = "di $1"
		_FP_IT = "di $1"
	}
	"^d'(.+)" = {
		_MS_IT = "d'$1"
		_FS_IT = "d'$1"
		_MP_IT = "d'$1"
		_FP_IT = "d'$1"
	}
	"^del (.+)" = {
		_MS_IT = "del $1"
		_FS_IT = "del $1"
		_MP_IT = "del $1"
		_FP_IT = "del $1"
	}
	"^della (.+)" = {
		_MS_IT = "della $1"
		_FS_IT = "della $1"
		_MP_IT = "della $1"
		_FP_IT = "della $1"
	}
	"(.+)é$" = { #Burkinabé (of Burkina Faso)
		_MS_IT = $1é
		_FS_IT = $1é
		_MP_IT = $1é
		_FP_IT = $1é
	}
	"(.+)i$" = {
		_MS_IT = $1i
		_FS_IT = $1i
		_MP_IT = $1i
		_FP_IT = $1i
	}
	
	#Special rules
	"belga" = { #Belgian
		_MS_IT = "belga"
		_FS_IT = "belga"
		_MP_IT = "belgi"
		_FP_IT = "belghe"
	}
	"austriaca" = { #Austrian
		_MS_IT = "austriaco"
		_FS_IT = "austriaca"
		_MP_IT = "austriaci"
		_FP_IT = "austriache"
	}
	"britannica" = { #British
		_MS_IT = "britannico"
		_FS_IT = "britannica"
		_MP_IT = "britannici"
		_FP_IT = "britanniche"
	}
	"greca" = { #Greek
		_MS_IT = "greco"
		_FS_IT = "greca"
		_MP_IT = "greci"
		_FP_IT = "greche"
  }
	"bosniaca" = { #Bosniak
		_MS_IT = "bosniaco"
		_FS_IT = "bosniaca"
		_MP_IT = "bosniaci"
		_FP_IT = "bosniache"
	}
	"libica" = { #Lybian
		_MS_IT = "libico"
		_FS_IT = "libica"
		_MP_IT = "libici"
		_FP_IT = "libiche"
	}
	
	#Actual adjectives
	"(.+)ita$" = {
		_MS_IT = $1ita
		_FS_IT = $1ita
		_MP_IT = $1iti
		_FP_IT = $1ite
	}
	"(.+)ana$" = {
		_MS_IT = $1ano
		_FS_IT = $1ana
		_MP_IT = $1ani
		_FP_IT = $1ane
	}
	"(.+)ese$" = {
		_MS_IT = $1ese
		_FS_IT = $1ese
		_MP_IT = $1esi
		_FP_IT = $1esi
	}
	"(.+)ense$" = {
		_MS_IT = $1ense
		_FS_IT = $1ense
		_MP_IT = $1ensi
		_FP_IT = $1ensi
	}
	"(.+)ina$" = {
		_MS_IT = $1ino
		_FS_IT = $1ina
		_MP_IT = $1ini
		_FP_IT = $1ine
	}
	"(.+)ena$" = {
		_MS_IT = $1eno
		_FS_IT = $1ena
		_MP_IT = $1eni
		_FP_IT = $1ene
	}
	"(.+)egna$" = {
		_MS_IT = $1egno
		_FS_IT = $1egna
		_MP_IT = $1egni
		_FP_IT = $1egne
	}
	"(.+)ota$" = {
		_MS_IT = $1ota
		_FS_IT = $1ota
		_MP_IT = $1oti
		_FP_IT = $1ote
	}
	"(.+)ca$" = {
		_MS_IT = $1co
		_FS_IT = $1ca
		_MP_IT = $1chi
		_FP_IT = $1che
	}
	"(.+)cia$" = {
		_MS_IT = $1cio
		_FS_IT = $1cia
		_MP_IT = $1ci
		_FP_IT = $1ce
	}
	"(.+)ista$" = {
		_MS_IT = $1ista
		_FS_IT = $1ista
		_MP_IT = $1isti
		_FP_IT = $1iste
	}
	"(.+)ia$" = {
		_MS_IT = $1io
		_FS_IT = $1ia
		_MP_IT = $1i
		_FP_IT = $1ie
	}
	"(.+)a$" = {
		_MS_IT = $1o
		_FS_IT = $1a
		_MP_IT = $1i
		_FP_IT = $1e
	}
	"(.+)e$" = {
		_MS_IT = $1e
		_FS_IT = $1e
		_MP_IT = $1i
		_FP_IT = $1i
	}
	
	#Fallback
	"^(.+)$" = {
		_MS_IT = $1
		_FS_IT = $1
		_MP_IT = $1
		_FP_IT = $1
	}
}

spanish = {
#_MS, _FS, _MP, _FP are respectively m. sing., f. sing., m. pl., f. pl.
#_ES is used because of the language code
#Default adjective in Spanish is f. sing.

	#Not-adjectives (i.e. literally "of X")
	"^de (.+)" = {
		_MS_ES = "de $1"
		_FS_ES = "de $1"
		_MP_ES = "de $1"
		_FP_ES = "de $1"
	}
	"^del (.+)" = {
		_MS_ES = "del $1"
		_FS_ES = "del $1"
		_MP_ES = "del $1"
		_FP_ES = "del $1"
	}
	
	#Special rules
	"alemana" = { #German
		_MS_ES = "alemán"
		_FS_ES = "alemana"
		_MP_ES = "alemanes"
		_FP_ES = "alemanas"
	}
	"belga" = { #Belgian
		_MS_ES = "belga"
		_FS_ES = "belga"
		_MP_ES = "belgas"
		_FP_ES = "belgas"
	}
	"croata" = { #Croat
		_MS_ES = "croata"
		_FS_ES = "croata"
		_MP_ES = "croatas"
		_FP_ES = "croatas"
	}
	
	#Actual adjectives
	"(.+)i$" = { 
		_MS_ES = $1í
		_FS_ES = $1í
		_MP_ES = $1íes
		_FP_ES = $1íes
	}
	"(.+)í$" = { 
		_MS_ES = $1í
		_FS_ES = $1í
		_MP_ES = $1íes
		_FP_ES = $1íes
	}
	"(.+)al$" = { 
		_MS_ES = $1al
		_FS_ES = $1al
		_MP_ES = $1ales
		_FP_ES = $1ales
	}
	"(.+)e$" = { 
		_MS_ES = $1e
		_FS_ES = $1e
		_MP_ES = $1es
		_FP_ES = $1es
	}
	"(.+)esa$" = { 
		_MS_ES = $1és
		_FS_ES = $1esa
		_MP_ES = $1eses
		_FP_ES = $1esas
	}
	"(.+)ola$" = { 
		_MS_ES = $1ol
		_FS_ES = $1ola
		_MP_ES = $1oles
		_FP_ES = $1olas
	}
	"(.+)ona$" = { 
		_MS_ES = $1ón
		_FS_ES = $1ona
		_MP_ES = $1ones
		_FP_ES = $1onas
	}
	"(.+)ita$" = { 
		_MS_ES = $1ita
		_FS_ES = $1ita
		_MP_ES = $1itas
		_FP_ES = $1itas
	}
	"(.+)ota$" = { 
		_MS_ES = $1ota
		_FS_ES = $1ota
		_MP_ES = $1otas
		_FP_ES = $1otas
	}
	"(.+)ista$" = { 
		_MS_ES = $1ista
		_FS_ES = $1ista
		_MP_ES = $1istas
		_FP_ES = $1istas
	}
	"(.+)a$" = { 
		_MS_ES = $1o
		_FS_ES = $1a
		_MP_ES = $1os
		_FP_ES = $1as
	}
	
	#Fallback
	"(.+)ch$" = {
		_MS_ES = $1ch
		_FS_ES = $1ch
		_MP_ES = $1ches
		_FP_ES = $1ches
	}
	"(.+)d$" = {
		_MS_ES = $1d
		_FS_ES = $1d
		_MP_ES = $1des
		_FP_ES = $1des
	}
	"(.+)j$" = {
		_MS_ES = $1j
		_FS_ES = $1j
		_MP_ES = $1jes
		_FP_ES = $1jes
	}
	"(.+)l$" = {
		_MS_ES = $1l
		_FS_ES = $1l
		_MP_ES = $1les
		_FP_ES = $1les
	}
	"(.+)n$" = {
		_MS_ES = $1n
		_FS_ES = $1na
		_MP_ES = $1nes
		_FP_ES = $1nas
	}
	"(.+)r$" = {
		_MS_ES = $1r
		_FS_ES = $1r
		_MP_ES = $1res
		_FP_ES = $1res
	}
	"(.+)s$" = {
		_MS_ES = $1s
		_FS_ES = $1s
		_MP_ES = $1ses
		_FP_ES = $1ses
	}
	"(.+)x$" = {
		_MS_ES = $1x
		_FS_ES = $1x
		_MP_ES = $1xes
		_FP_ES = $1xes
	}
	"(.+)y$" = {
		_MS_ES = $1y
		_FS_ES = $1y
		_MP_ES = $1yes
		_FP_ES = $1yes
	}
	"(.+)z$" = {
		_MS_ES = $1z
		_FS_ES = $1z
		_MP_ES = $1zes
		_FP_ES = $1zes
	}
	"^(.+)$" = {
		_MS_ES = $1
		_FS_ES = $1
		_MP_ES = $1s
		_FP_ES = $1s
	}
}

braz_por = {
#_MS, _FS, _MP, _FP are respectively m. sing., f. sing., m. pl., f. pl.
#_PT is used because of the language code

	#Not-adjectives (i.e. literally "of X")
	"^de (.+)" = {
		_MS_PT = "de $1"
		_FS_PT = "de $1"
		_MP_PT = "de $1"
		_FP_PT = "de $1"
	}
	"^d'(.+)" = {
		_MS_PT = "d'$1"
		_FS_PT = "d'$1"
		_MP_PT = "d'$1"
		_FP_PT = "d'$1"
	}
	"^do (.+)" = {
		_MS_PT = "do $1"
		_FS_PT = "do $1"
		_MP_PT = "do $1"
		_FP_PT = "do $1"
	}
	"^da (.+)" = {
		_MS_PT = "da $1"
		_FS_PT = "da $1"
		_MP_PT = "da $1"
		_FP_PT = "da $1"
	}
	"^dos (.+)" = {
		_MS_PT = "dos $1"
		_FS_PT = "dos $1"
		_MP_PT = "dos $1"
		_FP_PT = "dos $1"
	}
	"^das (.+)" = {
		_MS_PT = "das $1"
		_FS_PT = "das $1"
		_MP_PT = "das $1"
		_FP_PT = "das $1"
	}
	
	#Special rules
	"belga" = { #Belgian
		_MS_PT = "belga"
		_FS_PT = "belga"
		_MP_PT = "belgas"
		_FP_PT = "belgas"
	}
	"croata" = { #Croatian
		_MS_PT = "croata"
		_FS_PT = "croata"
		_MP_PT = "croatas"
		_FP_PT = "croatas"
	}
	"letã" = { #Latvian
		_MS_PT = letão
		_FS_PT = letã
		_MP_PT = latões
		_FP_PT = letãs
	}
	
	#Actual adjectives
	"(.+)ota$" = {
		_MS_PT = $1ota
		_FS_PT = $1ota
		_MP_PT = $1otas
		_FP_PT = $1otas
	}
	"(.+)ita$" = {
		_MS_PT = $1ita
		_FS_PT = $1ita
		_MP_PT = $1itas
		_FP_PT = $1itas
	}
	"(.+)ol$" = {
		_MS_PT = $1ol
		_FS_PT = $1ol
		_MP_PT = $1óis
		_FP_PT = $1óis
	}
	"(.+)i$" = {
		_MS_PT = $1i
		_FS_PT = $1i
		_MP_PT = $1is
		_FP_PT = $1is
	}
	"(.+)ia$" = {
		_MS_PT = $1u
		_FS_PT = $1ia
		_MP_PT = $1us
		_FP_PT = $1ias
	}
	"(.+)esa$" = {
		_MS_PT = $1ês
		_FS_PT = $1esa
		_MP_PT = $1eses
		_FP_PT = $1esas
	}
	"(.+)ola$" = {
		_MS_PT = $1ol
		_FS_PT = $1ola
		_MP_PT = $1óis
		_FP_PT = $1olas
	}
	"(.+)e$" = {
		_MS_PT = $1e
		_FS_PT = $1e
		_MP_PT = $1es
		_FP_PT = $1es
	}
	"(.+)mã$" = {
		_MS_PT = $1mão
		_FS_PT = $1mã
		_MP_PT = $1mães
		_FP_PT = $1mãs
	}
	"(.+)tã$" = {
		_MS_PT = $1tão
		_FS_PT = $1tã
		_MP_PT = $1tões
		_FP_PT = $1tãs
	}
	"(.+)ã$" = {
		_MS_PT = $1ão
		_FS_PT = $1ã
		_MP_PT = $1ãos
		_FP_PT = $1ãs
	}
	"(.+)a$" = {
		_MS_PT = $1o
		_FS_PT = $1a
		_MP_PT = $1os
		_FP_PT = $1as
	}
	
	#Fallback
	"^(.+)$" = {
		_MS_PT = $1
		_FS_PT = $1
		_MP_PT = $1's
		_FP_PT = $1's
	}
}