Added gd language folder (#13570)

Implemented a foundational Scottish Gaelic (gd) language option with tokenizer_exceptions and stop_words files.

spacy/lang/gd/__init__.py

@@ -0,0 +1,18 @@
+from typing import Optional
+
+from ...language import BaseDefaults, Language
+from .stop_words import STOP_WORDS
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class ScottishDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    stop_words = STOP_WORDS
+
+
+class Scottish(Language):
+    lang = "gd"
+    Defaults = ScottishDefaults
+
+
+__all__ = ["Scottish"]

spacy/lang/gd/stop_words.py

@@ -0,0 +1,386 @@
+STOP_WORDS = set(
+    """
+'ad
+'ar
+'d # iad
+'g # ag
+'ga
+'gam
+'gan
+'gar
+'gur
+'m # am
+'n # an
+'n seo
+'na
+'nad
+'nam
+'nan
+'nar
+'nuair
+'nur
+'s
+'sa
+'san
+'sann
+'se
+'sna
+a
+a'
+a'd # agad
+a'm # agam
+a-chèile
+a-seo
+a-sin
+a-siud
+a chionn
+a chionn 's
+a chèile
+a chéile
+a dh'
+a h-uile
+a seo
+ac' # aca
+aca
+aca-san
+acasan
+ach
+ag
+agad
+agad-sa
+agads'
+agadsa
+agaibh
+agaibhse
+againn
+againne
+agam
+agam-sa
+agams'
+agamsa
+agus
+aice
+aice-se
+aicese
+aig
+aig' # aige
+aige
+aige-san
+aigesan
+air
+air-san
+air neo
+airsan
+am
+an
+an seo
+an sin
+an siud
+an uair
+ann
+ann a
+ann a'
+ann a shin
+ann am
+ann an
+annad
+annam
+annam-s'
+annamsa
+anns
+anns an
+annta
+aon
+ar
+as
+asad
+asda
+asta
+b'
+bho
+bhon
+bhuaidhe # bhuaithe
+bhuainn
+bhuaipe
+bhuaithe
+bhuapa
+bhur
+brì
+bu
+c'à
+car son
+carson
+cha
+chan
+chionn
+choir
+chon
+chun
+chèile
+chéile
+chòir
+cia mheud
+ciamar
+co-dhiubh
+cuide
+cuin
+cuin'
+cuine
+cà
+cà'
+càil
+càit
+càit'
+càite
+cò
+cò mheud
+có
+d'
+da
+de
+dh'
+dha
+dhaibh
+dhaibh-san
+dhaibhsan
+dhan
+dhasan
+dhe
+dhen
+dheth
+dhi
+dhiom
+dhiot
+dhith
+dhiubh
+dhomh
+dhomh-s'
+dhomhsa
+dhu'sa # dhut-sa
+dhuibh
+dhuibhse
+dhuinn
+dhuinne
+dhuit
+dhut
+dhutsa
+dhut-sa
+dhà
+dhà-san
+dhàsan
+dhòmhsa
+diubh
+do
+docha
+don
+dà
+dè
+dè mar
+dé
+dé mar
+dòch'
+dòcha
+e
+eadar
+eatarra
+eatorra
+eile
+esan
+fa
+far
+feud
+fhad
+fheudar
+fhearr
+fhein
+fheudar
+fheàrr
+fhèin
+fhéin
+fhìn
+fo
+fodha
+fodhainn
+foipe
+fon
+fèin
+ga
+gach
+gam
+gan
+ge brith
+ged
+gu
+gu dè
+gu ruige
+gun
+gur
+gus
+i
+iad
+iadsan
+innte
+is
+ise
+le
+leam
+leam-sa
+leamsa
+leat
+leat-sa
+leatha
+leatsa
+leibh
+leis
+leis-san
+leoth'
+leotha
+leotha-san
+linn
+m'
+m'a
+ma
+mac
+man
+mar
+mas
+mathaid
+mi
+mis'
+mise
+mo
+mu
+mu 'n
+mun
+mur
+mura
+mus
+na
+na b'
+na bu
+na iad
+nach
+nad
+nam
+nan
+nar
+nas
+neo
+no
+nuair
+o
+o'n
+oir
+oirbh
+oirbh-se
+oirnn
+oirnne
+oirre
+on
+orm
+orm-sa
+ormsa
+orra
+orra-san
+orrasan
+ort
+os
+r'
+ri
+ribh
+rinn
+ris
+rithe
+rithe-se
+rium
+rium-sa
+riums'
+riumsa
+riut
+riuth'
+riutha
+riuthasan
+ro
+ro'n
+roimh
+roimhe
+romhainn
+romham
+romhpa
+ron
+ruibh
+ruinn
+ruinne
+sa
+san
+sann
+se
+seach
+seo
+seothach
+shin
+sibh
+sibh-se
+sibhse
+sin
+sineach
+sinn
+sinne
+siod
+siodach
+siud
+siudach
+sna # ann an
+sè
+t'
+tarsaing
+tarsainn
+tarsuinn
+thar
+thoigh
+thro
+thu
+thuc'
+thuca
+thugad
+thugaibh
+thugainn
+thugam
+thugamsa
+thuice
+thuige
+thus'
+thusa
+timcheall
+toigh
+toil
+tro
+tro' # troimh
+troimh
+troimhe
+tron
+tu
+tusa
+uair
+ud
+ugaibh
+ugam-s'
+ugam-sa
+uice
+uige
+uige-san
+umad
+unnta # ann an
+ur
+urrainn
+à
+às
+àsan
+á
+ás
+è
+ì
+ò
+ó
+""".split("\n")
+)