Skip to content

Commit 5da99d2

Browse files
authored
Merge pull request #54 from NicoACloutier/master
Add Huasteca Nahuatl language support
2 parents 0147af9 + e6316ff commit 5da99d2

File tree

8 files changed

+81
-1
lines changed

8 files changed

+81
-1
lines changed

data/articles/NahuatlHuasteca.txt

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
ne
2+
ni
3+
se

data/data.json

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -120,7 +120,8 @@
120120
"ndo": "na |oku|wa | na|a o|a n|ka |ntu| uu|tu |uth| om|e o|mba|ong|omu|ba | ok|uut| ne|he |the|ang|hem|emb|unt|o o|a u| wo|nge| iy|ehe|kal| no|a w|o n|no |nga|e n|ko |mun|oka|lo |o i|lon|we |ulu|a m|ala| ke|la |a k|u n|han|ku |gwa|osh|shi|ana|ngu|ilo|ano|ngo|keh| mo|ga |nen|man|ho |luk|tha|ge |gul|u k|eng|ha |a y|elo|uko|a e|ye |hil|uka|li |go |wan|ath|wo |thi|dhi|uun| pa|kwa| ta|a p|ya | sh| ko|nka|lwa| os|mwe|oma|ta |ema|sho| ka|e m| yo|sha|wok|ika|po |o w|onk|e p|pan|ith|a i|opa|gel|hik|iya|hi |aan|una|o g|kuk|alo|o e|nok|ndj|le |a a|men|yom|a s|i n| li|and| po|pam|lat|kan|ash|waa|aka|ame|gam|umb|a t|ond|yuu|o k|olo|ane|ing|igw|aa |ele|kul|mon| gw|ilw|gan|o y|iil|iyo| el|kut|nin|oko|ike|o m| ku|adh| ye|amw|ome|yeh|aye| ga| on| yi|a g|lyo|ne | ng|mbo|opo|kug|eko|yok|wom| oy|non|iye| go|ulo|e e| we| e |ina|ant|omo|ene| a |i k|mok|him| dh|und|ndu| me|eho|wen|nek| op|alu|e g|ima|kat|ota|oye|ila|ngw|yop|wat|ela|o u|a l| ii| ay| nd| th|o l|yon|ili|oon|okw|yaa|taa|lwe|omb| ni|aku|i m|mo |ula|ekw|enw|iyu|pok|epa|uki|ke | wu| mb|meh|e t|uni|nom|dho|pau|eta|yi | ly|o a|ono|lun|lak|ola|yo |lol|ank|bo |i o|awa|nwa|a h|naw|hok|nem|kom|ndo|o s|u t|vet|mbu|ani|uga|ndi|ukw|udh|lok|e k|alw|kwe|kun| ya",
121121
"quy": "chi|nch|hik|una| ka|anc|kun|man|ana|aq |cha|aku|pas|as |sqa|paq|nan|qa |apa|kan|ikp|ik |ech|spa| de|pa |cho|ere|der|rec|am | ru|an | ma| ch|kpa|asq|ta |na |nam|nak|taq|a k|qan|ina|run|lli|ach|nap|pi |mi | ll|yoq|asp|ima|hay|hin|aqa|nku|ant|ayn|oyo| hi| im|hoy|cio|nta|nas|q k|api|iw |wan|kuy|kay|liw|aci|ion|ipa|lla|oq |npa|ay |kas|a m|nac| na|inc|all|ama|ari|anp| ya|chu| hu|nin|pip|i k|qmi|hon|w r|ata|awa|a c|ota|in |yku|yna| wa|a h|has|a d|iku|a l| li|pan|ich|may| pi| ha|onc|a r|onk| ot|ku | qa|ank|aqm|mun|anm|hu |a p|nma| mu|qta|n h|pap|isq|yni|ikm|ma |wsa|aws|kaw|ibr|bre|lib|ayk|usp|nqa|e k| al|lin|n k|re |ara|nat|yac|kma|war|huk|uwa|yta|hwa|chw| sa|was|kus|yan|m d|kpi|q m|a i|q l|kin|tap|a a|kta|ikt|i c|a s|uy | ca|qaw|uku| tu| re|aqt|ask|qsi|sak|uch|q h|cas|tin|pak|ris|ski|sic|q d|nmi|s l|naq|tuk|mpa|a y|k c|uma|ien|ypi| am|qaq|qap|eqs|ayp|req|qpa|aqp|law|ayt|q c|pun| ni|a q|ruw|i h|haw|n c| pa|amp|par|k h| le|yma|ñun|ern|huñ|nni|n r|anq|map|aya|tar|s m|uñu|ten|val|ura|ita|arm|isu|s c|onn|igu| ri|qku|naw|k l|u l|his|ley|say|s y|rim|aru|rma|sun|ier|s o|qar|n p|a f|a t|esq|n a|oqm|s i|awk| va|w n|hap|lap|kup|i r|kam|uyk|sap| qe|ual|m p|ran|nya|gua| pe| go|gob|maq|sum|ast| su| ig",
122122
"rmn": "aj |en | te|te | sa| le|aka|pen| si| e |el |ipe|si |kaj|sar| th|and| o |sav|qe |les| ma|es | ha|j t|hak|ja |ar |ave| an|a s|ta |i l|ia |nas| aj|ne | so|imn|mna|sqe|esq|nd |tha|haj|e s|e t|e a|enq|asq|man| ja|kan|e m| i | ta|the|mes|cia|bar|as |isa|utn|qo |hem|o s|s s| me|vel|ark|i t| na|kas|est| ba|s h|avo| di|ard| bi| pe|rka|lo | ak|ika|e r|a a| pr|e k|qi |mat|ima|e p|a t| av|e d|r s|n s|anu|nuś|o t|avi|orr|o a| ka| re|n a|re |aja|e o|sqo|sti| ov|õl |l p|nqe|ere|d o|vor|so |no |dik|rel|ove|n t|ve |e b|res|tim|ren| de|àci|o m|i a|but|len|ali|ari|rre|de | pa|ver| va|sqi|ara|ana|vip|rak|ang|vi | ra|or |ker|i s|eme|e z|ata|e l|a e|rip|rim|akh|la |o p|kar|e h|a p|na |ane|rin|ste|j b|er |ind|ni |tne| ph|nip|r t| ke|ti |are|ndo| je|l a|uśi|e n|khi| bu|kon|lim|al |tar|ekh|jek|àlo|o k| ko|rde|rab|aba| zi|ri |aća|ćar|śik|dõl|dor|on |ano|ven| ni|śaj| śa|khe|ća |ast|j s|uti|uni|tni|naś|i d|mut| po|i p|a m| pu|a l|l s|som|n n|ikh|nik|del|ala|ris|pes|pe |j m|enć|e e|nća|ndi|rdõ|kri|erd|śka|emu|men|alo|nis|aśt|śti|amu|kh |tis|uj |j p|do |ani|ate|nda|o b|nge|o z|soc|a d|muj|o j|da |pri|rdo| as|cie|l t|ro |i r|kla|ing|a j| ze|zen|j e|ziv|hin|aśk| st|maś|ran|pal|khl|mam|i b|oci|rea|l o|nqo| vi|n e",
123-
"cak": " am|e j| u |u x| x |q x|a m|q w|a o|kïl|mak| wa|q n|zob|rel|ikï| ac|jle|jir|mab|a b| ey| et|oma|rub|ani|jij|cho|on |n m|iya|ito|lan|uto| ja|ire|tzo|jon|i j|kic|jib|jo |wuj|w r|tiq|äx |na |oj |tij|i q|nub|q t|ak |n n|rij|j j|n p|hup|upa|ris| wu|xik|k w| na|aqa|q c|j p|rej|k n|q k|ilä|atz|zin|ja |kan|ejq|jqa|qal|ale|haj|h a|i a|ma |atb|tb |xtu|nib|z n|to |onï|b e| ij|n x|k c|iri|hik|ike|a j|ruq|kir|ïl |ine|ric|uj |chï|hïk|uwi|ijo|kit|o c| ut|zil| ka|nan|cha|läj|ajo|pan| ra|ira|raj|nir|q i|jin|nim|isa|l j| b |l k|ima|ke |ya |kik|j k|nïk|i m| sa| in|h o|laj|hin|itz|l n|uwä|j t| än|nel|rik|una|rut|k u| o |e r|iq |n t|h r|k i|kon|ruc|i x| aj|asl|sle|a t|utz|ob | üt|ütz|än | as|tik|i c| q |j c|maj|ala|oji|l w|l t|sam|k r|ron| tz|zij|wäc|äj |ab |ub |nik|il |uq |äch|qi |n k|a k|xti|ama| ko|ich|aji|l c|i t|lew|ew | ti|ruk|uwa|iki|wac|q r|k o|tz | an|n c|a x|h u|naq| a | ro|re |i w|aqi| oj|ule|ina|uch| ul| at| äl|al |a c|wi |uk | nu|ib |ïk |aj |n w|xa |äl |man|ono|len| xt| re|aq |i n|oje| xa|ach|taq|jel|pa | al|in | ma|noj|j r| pa|ij |q a|tzi|ta |en |i k|n j| k |k a|b ä|inä|ruw| ki|näq|äq |ik |uqa|hi |b a|l r| ni|huq|qa |n r|win|el |ch |chu| ta|i r|un |an |chi| wi|a r|jun| ju| ru| ch|ri | ri"
123+
"cak": " am|e j| u |u x| x |q x|a m|q w|a o|kïl|mak| wa|q n|zob|rel|ikï| ac|jle|jir|mab|a b| ey| et|oma|rub|ani|jij|cho|on |n m|iya|ito|lan|uto| ja|ire|tzo|jon|i j|kic|jib|jo |wuj|w r|tiq|äx |na |oj |tij|i q|nub|q t|ak |n n|rij|j j|n p|hup|upa|ris| wu|xik|k w| na|aqa|q c|j p|rej|k n|q k|ilä|atz|zin|ja |kan|ejq|jqa|qal|ale|haj|h a|i a|ma |atb|tb |xtu|nib|z n|to |onï|b e| ij|n x|k c|iri|hik|ike|a j|ruq|kir|ïl |ine|ric|uj |chï|hïk|uwi|ijo|kit|o c| ut|zil| ka|nan|cha|läj|ajo|pan| ra|ira|raj|nir|q i|jin|nim|isa|l j| b |l k|ima|ke |ya |kik|j k|nïk|i m| sa| in|h o|laj|hin|itz|l n|uwä|j t| än|nel|rik|una|rut|k u| o |e r|iq |n t|h r|k i|kon|ruc|i x| aj|asl|sle|a t|utz|ob | üt|ütz|än | as|tik|i c| q |j c|maj|ala|oji|l w|l t|sam|k r|ron| tz|zij|wäc|äj |ab |ub |nik|il |uq |äch|qi |n k|a k|xti|ama| ko|ich|aji|l c|i t|lew|ew | ti|ruk|uwa|iki|wac|q r|k o|tz | an|n c|a x|h u|naq| a | ro|re |i w|aqi| oj|ule|ina|uch| ul| at| äl|al |a c|wi |uk | nu|ib |ïk |aj |n w|xa |äl |man|ono|len| xt| re|aq |i n|oje| xa|ach|taq|jel|pa | al|in | ma|noj|j r| pa|ij |q a|tzi|ta |en |i k|n j| k |k a|b ä|inä|ruw| ki|näq|äq |ik |uqa|hi |b a|l r| ni|huq|qa |n r|win|el |ch |chu| ta|i r|un |an |chi| wi|a r|jun| ju| ru| ch|ri | ri",
124+
"nhw": "hua|qui|tla|an |li | qu| hu|uan| no| tl|pa |tli|que| ca|atl|cat|chi|a t|ca |hui|ahu|opa|nop|a n| pa|se |ipa|ya |pan| ni|ui |ica|uin|aya|ihu| am|jqu|ali|aca|ual|tl |iya|amo| se| to|ili|tec| ma|i t|ue | mo|hue|n n|ra |ara| ip|par|a q|me |a h|a i|ma |itl|a m|is |en |eli|aj |mo |co |i i|ua |a a|lis|noc|ote| te|och|uil|ana|i n|lan|i c|toc| ic|ati|i q|jto|as |ijt|n t|ech|i h|tot|eco| ti|ini|uic|oc |jca|uit|equ|ase|iqu|mpa|yay|lal|cua|ehu|itz|lac|ant|tij| it|a c|hi |lhu|amp|cah|tzi| an|ama|cam|ntl|int|i m|n q| in|len|mas|n i|tle|mac|i a|e t| xi|ema|ti |ise|ni |ia |uis|ohu|ajc|ijq|ita|oca| ya|e i|uen|ich|a s|yaj| ne|aqu|ac |uat|e h|os |a p|o q|ilh|hih|uii|man|uaj|nah|e c|nqu|na |etl|ta |alt|i p|ani|pam|ajt|n a|nti|uip|uel|n s|lme|nij|lah|oqu|ach| mi|tzt|ami|yac|anq|ro |uem|ijc|lat|seh|lti|nin|laj| el|uey| cu|ist|uas|one|zi |uet|moc|nal|ame|cht|alm|uiy|nca|s h|e n|o h|teq|til|o t|lam|eyi|tep|ima|ero| pe|oya|mot|zto|toy|otl|ona|tis|jtl|mit|o n|ite|toq|ala|caj|l h|nim|stl|s n| sa|noj|uej|uia| is|nel| na|hij|e q|lia|s i|epe|o a|n m|uij|tza|ajq|la |s t|iyo| si|per|imo|j n|neq|e p|uih|nec|ojq|jua|cui|lte|ael|mec|on |uay|uac|piy|sra|isr|rae|mat|s q|ayo|a y|atz|lit|elt|lij|i s|c t|l c|ito|ipi|xti"
124125
},
125126
"Cyrillic": {
126127
"rus": " пр| и |рав|ств| на|пра|го |ени|ове|во | ка|ани|ть | в | по| об|ия |сво| св|лов|на | че|ело|о н| со|ост|чел|ие |ого|ет |ния|ест|аво|ый |ажд| им|ние|век| не|льн|ли |ова|име|ать|при|т п|и п|каж|или|обо| ра|ых |жды| до|дый|воб|ек |бод|ва |й ч|его|ся |и с|ии |аци|еет|но |мее|и и|лен|ой |тва|ных|то | ил|к и|енн| бы|ию | за|ми |тво|и н|о п|ван|о с|сто|аль| вс|ом |о в|ьно|их |ног|и в|нов|ако|про|ий |сти|и о|пол|олж|дол|ое |бра|я в| ос|ным|жен|раз|ти |нос|я и| во|тор|все| ег|ей |тел|не |и р|ред|ель|тве|оди| ко|общ|о и| де|има|а и|чес|ним|сно|как| ли|щес|вле|ься|нны|аст|тьс|нно|осу|е д| от|пре|шен|а с|бще|осн|одн|быт|сов|ыть|лжн|ран|нию|иче|ак |ым |ват|что|сту|чен|е в| ст|рес|оль| ни|ном|род|ля |нар|вен|ду |оже|ны |е и| то|вер|а о|зов|м и|нац|ден|рин|туп|ежд|стр| чт|я п|она|дос|х и|й и|тоя|есп|лич|бес|обр|ото|о б|ьны|ь в|нии|е м|ую | мо|ем | ме|аро| ре|ава|кот|ав | вы|ам |жно|ста|ая |под|и к|ное| к | та| го|гос|суд|еоб|я н|ен |и д|мож|еск|ели|авн|ве |ече|уще|печ|дно|о д|ход|ка | дл|для|ово|ате|льс|ю и|в к|нен|ции|ной|уда|вов| бе|оро|нст|ами|циа|кон|сем|е о|вно| эт|азо|х п|ни |жде|м п|ког|от |дст|вны|сть|ые |о о|пос|сре|тра|ейс|так|и б|дов|му |я к|нал|дру| др|кой|тер|ь п|арс|изн|соц|еди|олн",
Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
ne
2+
ni
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
se

data/prepositions/NahuatlHuasteca.txt

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
ipan
2+
pan
3+
ika
4+
ka
5+
ihuaya
6+
huaya
7+
ipampa
8+
pampa

data/pronouns/NahuatlHuasteca.txt

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
na
2+
nejuatl
3+
ta
4+
tejuatl
5+
ya
6+
yejuatl
7+
tejuanti
8+
amojuanti
9+
yejuanti

data/stopwords/NahuatlHuasteca.txt

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
ipan
2+
pan
3+
ika
4+
ka
5+
ihuaya
6+
huaya
7+
ipampa
8+
pampa
9+
na
10+
nejuatl
11+
ta
12+
tejuatl
13+
ya
14+
yejuatl
15+
tejuanti
16+
amojuanti
17+
yejuanti
18+
ne
19+
ni
20+
se
21+
ihuan
22+
huan
23+
nopa
24+
para
25+
amo
26+
ma
27+
tlen
28+
quema
29+
quen
30+
campa
31+
pero
32+
huajca
33+
san
34+
nojquiya
35+
teipa
36+
teipan
37+
miyac
38+
hasta
39+
mas
40+
quej
41+
tlawel
42+
ama
43+
aman
44+
seyoc
45+
sequinoc
46+
nelia
47+
ayacmo
48+
quena
49+
sempa
50+
pa
51+
nepa
52+
ompa
53+
nika
54+
nikan

src/types.jl

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -111,6 +111,7 @@ struct Rundi <: Language; end; english_name(::Type{Rundi}) = "Rundi"; name(::Typ
111111
struct Shona <: Language; end; english_name(::Type{Shona}) = "Shona"; name(::Type{Shona}) = "ChiShona"; isocode(::Type{Shona}) = "sna"
112112
struct Uyghur <: Language; end; english_name(::Type{Uyghur}) = "Uyghur"; name(::Type{Uyghur}) = "ئۇيغۇرچە"; isocode(::Type{Uyghur}) = "uig"
113113
struct Swahili <: Language; end; english_name(::Type{Swahili}) = "Swahili"; name(::Type{Swahili}) = "Kiswahili"; isocode(::Type{Swahili}) = "swh"
114+
struct NahuatlHuasteca <: Language; end; english_name(::Type{NahuatlHuasteca}) = "NahuatlHuasteca"; name(::Type{NahuatlHuasteca}) = "Nahuatlajtoli"; isocode(::Type{NahuatlHuasteca}) = "nhw"
114115

115116
global const code_to_lang = Dict{String, Language}(
116117
"epo" => Esperanto(),
@@ -197,6 +198,7 @@ global const code_to_lang = Dict{String, Language}(
197198
"run" => Rundi(),
198199
"sna" => Shona(),
199200
"uig" => Uyghur(),
201+
"nhw" => NahuatlHuasteca(),
200202
)
201203

202204
"""

0 commit comments

Comments
 (0)