explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

add POS

Browse Source
This commit is contained in:
Jim O'Regan 2017-06-26 21:53:41 +01:00
parent 3c4d83aa6e
commit a8dff9133e
1 changed files with 65 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

130
spacy/lang/ga/tokenizer_exceptions.py
View File

@ -1,110 +1,110 @@
# encoding: utf8
from __future__ import unicode_literals
from ..symbols import ORTH, LEMMA, NORM
from ..symbols import ORTH, LEMMA, NORM, POS
_exc = {
"'acha'n": [
{ORTH: "'ach", LEMMA: "gach", NORM: "gach"},
{ORTH: "a'n", LEMMA: "aon", NORM: "aon"}],
{ORTH: "'ach", LEMMA: "gach", NORM: "gach", POS: DET},
{ORTH: "a'n", LEMMA: "aon", NORM: "aon", POS: DET}],
"dem'": [
{ORTH: "de", LEMMA: "de", NORM: "de"},
{ORTH: "m'", LEMMA: "mo", NORM: "mo"}],
{ORTH: "de", LEMMA: "de", NORM: "de", POS: ADP},
{ORTH: "m'", LEMMA: "mo", NORM: "mo", POS: DET}],
"ded'": [
{ORTH: "de", LEMMA: "de", NORM: "de"},
{ORTH: "d'", LEMMA: "do", NORM: "do"}],
{ORTH: "de", LEMMA: "de", NORM: "de", POS: ADP},
{ORTH: "d'", LEMMA: "do", NORM: "do", POS: DET}],
"lem'": [
{ORTH: "le", LEMMA: "le", NORM: "le"},
{ORTH: "m'", LEMMA: "mo", NORM: "mo"}],
{ORTH: "le", LEMMA: "le", NORM: "le", POS: ADP},
{ORTH: "m'", LEMMA: "mo", NORM: "mo", POS: DET}],
"led'": [
{ORTH: "le", LEMMA: "le", NORM: "le"},
{ORTH: "d'", LEMMA: "mo", NORM: "do"}],
{ORTH: "le", LEMMA: "le", NORM: "le", POS: ADP},
{ORTH: "d'", LEMMA: "mo", NORM: "do", POS: DET}],
"a.C.n.": [
{ORTH: "a.", LEMMA: "ante"},
{ORTH: "C.", LEMMA: "Christum"},
{ORTH: "n.", LEMMA: "natum"}],
{ORTH: "a.", LEMMA: "ante", POS: X},
{ORTH: "C.", LEMMA: "Christum", POS: X},
{ORTH: "n.", LEMMA: "natum", POS: X}],
"m.sh.": [
{ORTH: "m.", LEMMA: "mar"},
{ORTH: "sh.", LEMMA: "sampla"}],
{ORTH: "m.", LEMMA: "mar", POS: ADP},
{ORTH: "sh.", LEMMA: "sampla", POS: NOUN}],
"M.F.": [
{ORTH: "M.", LEMMA: "Meán"},
{ORTH: "F.", LEMMA: "Fómhar"}],
{ORTH: "M.", LEMMA: "Meán", POS: NOUN},
{ORTH: "F.", LEMMA: "Fómhar", POS: NOUN}],
"M.Fómh.": [
{ORTH: "M.", LEMMA: "Meán"},
{ORTH: "Fómh.", LEMMA: "Fómhar"}],
{ORTH: "M.", LEMMA: "Meán", POS: NOUN},
{ORTH: "Fómh.", LEMMA: "Fómhar", POS: NOUN}],
"R.C.": [
{ORTH: "Rr.", LEMMA: "roimh"},
{ORTH: "C.", LEMMA: "Críost"}],
{ORTH: "Rr.", LEMMA: "roimh", POS: ADP},
{ORTH: "C.", LEMMA: "Críost", POS: NOUN}],
"r.Ch.": [
{ORTH: "r.", LEMMA: "roimh"},
{ORTH: "Ch.", LEMMA: "Críost"}],
{ORTH: "r.", LEMMA: "roimh", POS: ADP},
{ORTH: "Ch.", LEMMA: "Críost", POS: NOUN}],
"r.Chr.": [
{ORTH: "r.", LEMMA: "roimh"},
{ORTH: "Chr.", LEMMA: "Críost"}],
{ORTH: "r.", LEMMA: "roimh", POS: ADP},
{ORTH: "Chr.", LEMMA: "Críost", POS: NOUN}],
"R.Ch.": [
{ORTH: "R.", LEMMA: "roimh"},
{ORTH: "Ch.", LEMMA: "Críost"}],
{ORTH: "R.", LEMMA: "roimh", POS: ADP},
{ORTH: "Ch.", LEMMA: "Críost", POS: NOUN}],
"R.Chr.": [
{ORTH: "R.", LEMMA: "roimh"},
{ORTH: "Chr.", LEMMA: "Críost"}],
{ORTH: "R.", LEMMA: "roimh", POS: ADP},
{ORTH: "Chr.", LEMMA: "Críost", POS: NOUN}],
"⁊rl.": [
{ORTH: "⁊", LEMMA: "agus"},
{ORTH: "rl.", LEMMA: "araile"}],
{ORTH: "⁊", LEMMA: "agus", POS: CCONJ},
{ORTH: "rl.", LEMMA: "araile", POS: ADJ}],
"srl.": [
{ORTH: "s", LEMMA: "agus"},
{ORTH: "rl.", LEMMA: "araile"}],
{ORTH: "s", LEMMA: "agus", POS: CCONJ},
{ORTH: "rl.", LEMMA: "araile", POS: ADJ}],
}
for exc_data in [
{ORTH: "'gus", LEMMA: "agus", NORM: "agus"},
{ORTH: "'ach", LEMMA: "gach", NORM: "gach"},
{ORTH: "'gus", LEMMA: "agus", NORM: "agus", POS: CCONJ},
{ORTH: "'ach", LEMMA: "gach", NORM: "gach", POS: DET},
{ORTH: "ao'", LEMMA: "aon", NORM: "aon"},
{ORTH: "'niar", LEMMA: "aniar", NORM: "aniar"},
{ORTH: "'níos", LEMMA: "aníos", NORM: "aníos"},
{ORTH: "'ndiu", LEMMA: "inniu", NORM: "inniu"},
{ORTH: "'nocht", LEMMA: "anocht", NORM: "anocht"},
{ORTH: "m'", LEMMA: "mo"},,
{ORTH: "Aib.", LEMMA: "Aibreán"},
{ORTH: "Ath.", LEMMA: "athair"},
{ORTH: "Beal.", LEMMA: "Bealtaine"},
{ORTH: "Co.", LEMMA: "contae"},
{ORTH: "Ean.", LEMMA: "Eanáir"},
{ORTH: "Feab.", LEMMA: "Feabhra"},
{ORTH: "gCo.", LEMMA: "contae"},
{ORTH: ".i.", LEMMA: "eadhon"},
{ORTH: "lch.", LEMMA: "leathanach"},
{ORTH: "Lch.", LEMMA: "leathanach"},
{ORTH: "lgh.", LEMMA: "leathanach"},
{ORTH: "Lgh.", LEMMA: "leathanach"},
{ORTH: "Lún.", LEMMA: "Lúnasa"},
{ORTH: "Már.", LEMMA: "Márta"},
{ORTH: "Meith.", LEMMA: "Meitheamh"},
{ORTH: "Noll.", LEMMA: "Nollaig"},
{ORTH: "Samh.", LEMMA: "Samhain"},
{ORTH: "tAth.", LEMMA: "athair"},
{ORTH: "tUas.", LEMMA: "Uasal"},
{ORTH: "teo.", LEMMA: "teoranta"},
{ORTH: "Teo.", LEMMA: "teoranta"},
{ORTH: "Uas.", LEMMA: "Uasal"},
{ORTH: "uimh.", LEMMA: "uimhir"},
{ORTH: "Uimh.", LEMMA: "uimhir"}]:
{ORTH: "'niar", LEMMA: "aniar", NORM: "aniar", POS: ADV},
{ORTH: "'níos", LEMMA: "aníos", NORM: "aníos", POS: ADV},
{ORTH: "'ndiu", LEMMA: "inniu", NORM: "inniu", POS: ADV},
{ORTH: "'nocht", LEMMA: "anocht", NORM: "anocht", POS: ADV},
{ORTH: "m'", LEMMA: "mo", POS: DET},
{ORTH: "Aib.", LEMMA: "Aibreán", POS: NOUN},
{ORTH: "Ath.", LEMMA: "athair", POS: NOUN},
{ORTH: "Beal.", LEMMA: "Bealtaine", POS: NOUN},
{ORTH: "Co.", LEMMA: "contae", POS: NOUN},
{ORTH: "Ean.", LEMMA: "Eanáir", POS: NOUN},
{ORTH: "Feab.", LEMMA: "Feabhra", POS: NOUN},
{ORTH: "gCo.", LEMMA: "contae", POS: NOUN},
{ORTH: ".i.", LEMMA: "eadhon", POS: ADV},
{ORTH: "lch.", LEMMA: "leathanach", POS: NOUN},
{ORTH: "Lch.", LEMMA: "leathanach", POS: NOUN},
{ORTH: "lgh.", LEMMA: "leathanach", POS: NOUN},
{ORTH: "Lgh.", LEMMA: "leathanach", POS: NOUN},
{ORTH: "Lún.", LEMMA: "Lúnasa", POS: NOUN},
{ORTH: "Már.", LEMMA: "Márta", POS: NOUN},
{ORTH: "Meith.", LEMMA: "Meitheamh", POS: NOUN},
{ORTH: "Noll.", LEMMA: "Nollaig", POS: NOUN},
{ORTH: "Samh.", LEMMA: "Samhain", POS: NOUN},
{ORTH: "tAth.", LEMMA: "athair", POS: NOUN},
{ORTH: "tUas.", LEMMA: "Uasal", POS: NOUN},
{ORTH: "teo.", LEMMA: "teoranta", POS: NOUN},
{ORTH: "Teo.", LEMMA: "teoranta", POS: NOUN},
{ORTH: "Uas.", LEMMA: "Uasal", POS: NOUN},
{ORTH: "uimh.", LEMMA: "uimhir", POS: NOUN},
{ORTH: "Uimh.", LEMMA: "uimhir", POS: NOUN}]:
_exc[exc_data[ORTH]] = [dict(exc_data)],
for orth in [