spaCy/spacy/lang/en/tokenizer_exceptions.py
2023-06-26 11:41:03 +02:00

527 lines
14 KiB
Python

from typing import Dict, List
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc: Dict[str, List[Dict]] = {}
_exclude = [
"Ill",
"ill",
"Its",
"its",
"Hell",
"hell",
"Shell",
"shell",
"Shed",
"shed",
"were",
"Were",
"Well",
"well",
"Whore",
"whore",
]
# Pronouns
for pron in ["i"]:
for orth in [pron, pron.title()]:
_exc[orth + "'m"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'m", NORM: "am"},
]
_exc[orth + "m"] = [
{ORTH: orth, NORM: pron},
{ORTH: "m"},
]
_exc[orth + "'ma"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'m", NORM: "am"},
{ORTH: "a", NORM: "gonna"},
]
_exc[orth + "ma"] = [
{ORTH: orth, NORM: pron},
{ORTH: "m", NORM: "am"},
{ORTH: "a", NORM: "gonna"},
]
for pron in ["i", "you", "he", "she", "it", "we", "they"]:
for orth in [pron, pron.title()]:
_exc[orth + "'ll"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'ll", NORM: "will"},
]
_exc[orth + "ll"] = [
{ORTH: orth, NORM: pron},
{ORTH: "ll", NORM: "will"},
]
_exc[orth + "'ll've"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'ll", NORM: "will"},
{ORTH: "'ve", NORM: "have"},
]
_exc[orth + "llve"] = [
{ORTH: orth, NORM: pron},
{ORTH: "ll", NORM: "will"},
{ORTH: "ve", NORM: "have"},
]
_exc[orth + "'d"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'d", NORM: "'d"},
]
_exc[orth + "d"] = [
{ORTH: orth, NORM: pron},
{ORTH: "d", NORM: "'d"},
]
_exc[orth + "'d've"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'d", NORM: "would"},
{ORTH: "'ve", NORM: "have"},
]
_exc[orth + "dve"] = [
{ORTH: orth, NORM: pron},
{ORTH: "d", NORM: "would"},
{ORTH: "ve", NORM: "have"},
]
for pron in ["i", "you", "we", "they"]:
for orth in [pron, pron.title()]:
_exc[orth + "'ve"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'ve", NORM: "have"},
]
_exc[orth + "ve"] = [
{ORTH: orth, NORM: pron},
{ORTH: "ve", NORM: "have"},
]
for pron in ["you", "we", "they"]:
for orth in [pron, pron.title()]:
_exc[orth + "'re"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'re", NORM: "are"},
]
_exc[orth + "re"] = [
{ORTH: orth, NORM: pron},
{ORTH: "re", NORM: "are"},
]
for pron in ["he", "she", "it"]:
for orth in [pron, pron.title()]:
_exc[orth + "'s"] = [
{ORTH: orth, NORM: pron},
{ORTH: "'s", NORM: "'s"},
]
_exc[orth + "s"] = [
{ORTH: orth, NORM: pron},
{ORTH: "s"},
]
# W-words, relative pronouns, prepositions etc.
for word, morph in [
("who", None),
("what", None),
("when", None),
("where", None),
("why", None),
("how", None),
("there", None),
("that", "Number=Sing|Person=3"),
("this", "Number=Sing|Person=3"),
("these", "Number=Plur|Person=3"),
("those", "Number=Plur|Person=3"),
]:
for orth in [word, word.title()]:
if morph != "Number=Plur|Person=3":
_exc[orth + "'s"] = [
{ORTH: orth, NORM: word},
{ORTH: "'s", NORM: "'s"},
]
_exc[orth + "s"] = [{ORTH: orth, NORM: word}, {ORTH: "s"}]
_exc[orth + "'ll"] = [
{ORTH: orth, NORM: word},
{ORTH: "'ll", NORM: "will"},
]
_exc[orth + "ll"] = [
{ORTH: orth, NORM: word},
{ORTH: "ll", NORM: "will"},
]
_exc[orth + "'ll've"] = [
{ORTH: orth, NORM: word},
{ORTH: "'ll", NORM: "will"},
{ORTH: "'ve", NORM: "have"},
]
_exc[orth + "llve"] = [
{ORTH: orth, NORM: word},
{ORTH: "ll", NORM: "will"},
{ORTH: "ve", NORM: "have"},
]
if morph != "Number=Sing|Person=3":
_exc[orth + "'re"] = [
{ORTH: orth, NORM: word},
{ORTH: "'re", NORM: "are"},
]
_exc[orth + "re"] = [
{ORTH: orth, NORM: word},
{ORTH: "re", NORM: "are"},
]
_exc[orth + "'ve"] = [
{ORTH: orth, NORM: word},
{ORTH: "'ve"},
]
_exc[orth + "ve"] = [
{ORTH: orth},
{ORTH: "ve", NORM: "have"},
]
_exc[orth + "'d"] = [
{ORTH: orth, NORM: word},
{ORTH: "'d", NORM: "'d"},
]
_exc[orth + "d"] = [
{ORTH: orth, NORM: word},
{ORTH: "d", NORM: "'d"},
]
_exc[orth + "'d've"] = [
{ORTH: orth, NORM: word},
{ORTH: "'d", NORM: "would"},
{ORTH: "'ve", NORM: "have"},
]
_exc[orth + "dve"] = [
{ORTH: orth, NORM: word},
{ORTH: "d", NORM: "would"},
{ORTH: "ve", NORM: "have"},
]
# Verbs
for verb_data in [
{ORTH: "ca", NORM: "can"},
{ORTH: "could", NORM: "could"},
{ORTH: "do", NORM: "do"},
{ORTH: "does", NORM: "does"},
{ORTH: "did", NORM: "do"},
{ORTH: "had", NORM: "have"},
{ORTH: "may", NORM: "may"},
{ORTH: "might", NORM: "might"},
{ORTH: "must", NORM: "must"},
{ORTH: "need", NORM: "need"},
{ORTH: "ought", NORM: "ought"},
{ORTH: "sha", NORM: "shall"},
{ORTH: "should", NORM: "should"},
{ORTH: "wo", NORM: "will"},
{ORTH: "would", NORM: "would"},
]:
verb_data_tc = dict(verb_data)
verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
for data in [verb_data, verb_data_tc]:
_exc[data[ORTH] + "n't"] = [
dict(data),
{ORTH: "n't", NORM: "not"},
]
_exc[data[ORTH] + "nt"] = [
dict(data),
{ORTH: "nt", NORM: "not"},
]
_exc[data[ORTH] + "n't've"] = [
dict(data),
{ORTH: "n't", NORM: "not"},
{ORTH: "'ve", NORM: "have"},
]
_exc[data[ORTH] + "ntve"] = [
dict(data),
{ORTH: "nt", NORM: "not"},
{ORTH: "ve", NORM: "have"},
]
for verb_data in [
{ORTH: "could", NORM: "could"},
{ORTH: "might", NORM: "might"},
{ORTH: "must", NORM: "must"},
{ORTH: "should", NORM: "should"},
{ORTH: "would", NORM: "would"},
]:
verb_data_tc = dict(verb_data)
verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
for data in [verb_data, verb_data_tc]:
_exc[data[ORTH] + "'ve"] = [dict(data), {ORTH: "'ve"}]
_exc[data[ORTH] + "ve"] = [dict(data), {ORTH: "ve"}]
for verb_data in [
{ORTH: "ai", "number": 2},
{ORTH: "are", NORM: "are", "number": 2},
{ORTH: "is", NORM: "is"},
{ORTH: "was", NORM: "was"},
{ORTH: "were", NORM: "were"},
{ORTH: "have", NORM: "have"},
{ORTH: "has", NORM: "has"},
{ORTH: "dare", NORM: "dare"},
]:
verb_data_tc = dict(verb_data) # type: ignore[call-overload]
verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
for data in [verb_data, verb_data_tc]: # type: ignore[assignment]
_exc[data[ORTH] + "n't"] = [
dict(data),
{ORTH: "n't", NORM: "not"},
]
_exc[data[ORTH] + "nt"] = [
dict(data),
{ORTH: "nt", NORM: "not"},
]
# Other contractions with trailing apostrophe
for exc_data in [
{ORTH: "doin", NORM: "doing"},
{ORTH: "goin", NORM: "going"},
{ORTH: "nothin", NORM: "nothing"},
{ORTH: "nuthin", NORM: "nothing"},
{ORTH: "ol", NORM: "old"},
{ORTH: "somethin", NORM: "something"},
]:
exc_data_tc = dict(exc_data)
exc_data_tc[ORTH] = exc_data_tc[ORTH].title()
for data in [exc_data, exc_data_tc]:
data_apos = dict(data)
data_apos[ORTH] = data_apos[ORTH] + "'"
_exc[data[ORTH]] = [dict(data)]
_exc[data_apos[ORTH]] = [dict(data_apos)]
# Other contractions with leading apostrophe
for exc_data in [
{ORTH: "em", NORM: "them"},
{ORTH: "ll", NORM: "will"},
{ORTH: "nuff", NORM: "enough"},
]:
exc_data_apos = dict(exc_data)
exc_data_apos[ORTH] = "'" + exc_data_apos[ORTH]
for data in [exc_data, exc_data_apos]:
_exc[data[ORTH]] = [data]
# Times
for h in range(1, 12 + 1):
for period in ["a.m.", "am"]:
_exc[f"{h}{period}"] = [
{ORTH: f"{h}"},
{ORTH: period, NORM: "a.m."},
]
for period in ["p.m.", "pm"]:
_exc[f"{h}{period}"] = [
{ORTH: f"{h}"},
{ORTH: period, NORM: "p.m."},
]
# Rest
_other_exc = {
"y'all": [{ORTH: "y'", NORM: "you"}, {ORTH: "all"}],
"yall": [{ORTH: "y", NORM: "you"}, {ORTH: "all"}],
"how'd'y": [{ORTH: "how"}, {ORTH: "'d"}, {ORTH: "'y", NORM: "you"}],
"How'd'y": [{ORTH: "How", NORM: "how"}, {ORTH: "'d"}, {ORTH: "'y", NORM: "you"}],
"not've": [{ORTH: "not"}, {ORTH: "'ve", NORM: "have"}],
"notve": [{ORTH: "not"}, {ORTH: "ve", NORM: "have"}],
"Not've": [{ORTH: "Not", NORM: "not"}, {ORTH: "'ve", NORM: "have"}],
"Notve": [{ORTH: "Not", NORM: "not"}, {ORTH: "ve", NORM: "have"}],
"cannot": [{ORTH: "can"}, {ORTH: "not"}],
"Cannot": [{ORTH: "Can", NORM: "can"}, {ORTH: "not"}],
"gonna": [{ORTH: "gon", NORM: "going"}, {ORTH: "na", NORM: "to"}],
"Gonna": [{ORTH: "Gon", NORM: "going"}, {ORTH: "na", NORM: "to"}],
"gotta": [{ORTH: "got"}, {ORTH: "ta", NORM: "to"}],
"Gotta": [{ORTH: "Got", NORM: "got"}, {ORTH: "ta", NORM: "to"}],
"let's": [{ORTH: "let"}, {ORTH: "'s", NORM: "us"}],
"Let's": [{ORTH: "Let", NORM: "let"}, {ORTH: "'s", NORM: "us"}],
"c'mon": [{ORTH: "c'm", NORM: "come"}, {ORTH: "on"}],
"C'mon": [{ORTH: "C'm", NORM: "come"}, {ORTH: "on"}],
}
_exc.update(_other_exc)
for exc_data in [
{ORTH: "'S", NORM: "'s"},
{ORTH: "'s", NORM: "'s"},
{ORTH: "\u2018S", NORM: "'s"},
{ORTH: "\u2018s", NORM: "'s"},
{ORTH: "and/or", NORM: "and/or"},
{ORTH: "w/o", NORM: "without"},
{ORTH: "'re", NORM: "are"},
{ORTH: "'Cause", NORM: "because"},
{ORTH: "'cause", NORM: "because"},
{ORTH: "'cos", NORM: "because"},
{ORTH: "'Cos", NORM: "because"},
{ORTH: "'coz", NORM: "because"},
{ORTH: "'Coz", NORM: "because"},
{ORTH: "'cuz", NORM: "because"},
{ORTH: "'Cuz", NORM: "because"},
{ORTH: "'bout", NORM: "about"},
{ORTH: "ma'am", NORM: "madam"},
{ORTH: "Ma'am", NORM: "madam"},
{ORTH: "o'clock", NORM: "o'clock"},
{ORTH: "O'clock", NORM: "o'clock"},
{ORTH: "lovin'", NORM: "loving"},
{ORTH: "Lovin'", NORM: "loving"},
{ORTH: "lovin", NORM: "loving"},
{ORTH: "Lovin", NORM: "loving"},
{ORTH: "havin'", NORM: "having"},
{ORTH: "Havin'", NORM: "having"},
{ORTH: "havin", NORM: "having"},
{ORTH: "Havin", NORM: "having"},
{ORTH: "doin'", NORM: "doing"},
{ORTH: "Doin'", NORM: "doing"},
{ORTH: "doin", NORM: "doing"},
{ORTH: "Doin", NORM: "doing"},
{ORTH: "goin'", NORM: "going"},
{ORTH: "Goin'", NORM: "going"},
{ORTH: "goin", NORM: "going"},
{ORTH: "Goin", NORM: "going"},
{ORTH: "Mt.", NORM: "Mount"},
{ORTH: "Ak.", NORM: "Alaska"},
{ORTH: "Ala.", NORM: "Alabama"},
{ORTH: "Apr.", NORM: "April"},
{ORTH: "Ariz.", NORM: "Arizona"},
{ORTH: "Ark.", NORM: "Arkansas"},
{ORTH: "Aug.", NORM: "August"},
{ORTH: "Calif.", NORM: "California"},
{ORTH: "Colo.", NORM: "Colorado"},
{ORTH: "Conn.", NORM: "Connecticut"},
{ORTH: "Dec.", NORM: "December"},
{ORTH: "Del.", NORM: "Delaware"},
{ORTH: "Feb.", NORM: "February"},
{ORTH: "Fla.", NORM: "Florida"},
{ORTH: "Ga.", NORM: "Georgia"},
{ORTH: "Ia.", NORM: "Iowa"},
{ORTH: "Id.", NORM: "Idaho"},
{ORTH: "Ill.", NORM: "Illinois"},
{ORTH: "Ind.", NORM: "Indiana"},
{ORTH: "Jan.", NORM: "January"},
{ORTH: "Jul.", NORM: "July"},
{ORTH: "Jun.", NORM: "June"},
{ORTH: "Kan.", NORM: "Kansas"},
{ORTH: "Kans.", NORM: "Kansas"},
{ORTH: "Ky.", NORM: "Kentucky"},
{ORTH: "La.", NORM: "Louisiana"},
{ORTH: "Mar.", NORM: "March"},
{ORTH: "Mass.", NORM: "Massachusetts"},
{ORTH: "Mich.", NORM: "Michigan"},
{ORTH: "Minn.", NORM: "Minnesota"},
{ORTH: "Miss.", NORM: "Mississippi"},
{ORTH: "N.C.", NORM: "North Carolina"},
{ORTH: "N.D.", NORM: "North Dakota"},
{ORTH: "N.H.", NORM: "New Hampshire"},
{ORTH: "N.J.", NORM: "New Jersey"},
{ORTH: "N.M.", NORM: "New Mexico"},
{ORTH: "N.Y.", NORM: "New York"},
{ORTH: "Neb.", NORM: "Nebraska"},
{ORTH: "Nebr.", NORM: "Nebraska"},
{ORTH: "Nev.", NORM: "Nevada"},
{ORTH: "Nov.", NORM: "November"},
{ORTH: "Oct.", NORM: "October"},
{ORTH: "Okla.", NORM: "Oklahoma"},
{ORTH: "Ore.", NORM: "Oregon"},
{ORTH: "Pa.", NORM: "Pennsylvania"},
{ORTH: "S.C.", NORM: "South Carolina"},
{ORTH: "Sep.", NORM: "September"},
{ORTH: "Sept.", NORM: "September"},
{ORTH: "Tenn.", NORM: "Tennessee"},
{ORTH: "Va.", NORM: "Virginia"},
{ORTH: "Wash.", NORM: "Washington"},
{ORTH: "Wis.", NORM: "Wisconsin"},
]:
_exc[exc_data[ORTH]] = [exc_data]
for orth in [
"'d",
"a.m.",
"Adm.",
"Bros.",
"co.",
"Co.",
"Corp.",
"D.C.",
"Dr.",
"e.g.",
"E.g.",
"E.G.",
"Gen.",
"Gov.",
"i.e.",
"I.e.",
"I.E.",
"Inc.",
"Jr.",
"Ltd.",
"Md.",
"Messrs.",
"Mo.",
"Mont.",
"Mr.",
"Mrs.",
"Ms.",
"p.m.",
"Ph.D.",
"Prof.",
"Rep.",
"Rev.",
"Sen.",
"St.",
"vs.",
"v.s.",
]:
_exc[orth] = [{ORTH: orth}]
for string in _exclude:
if string in _exc:
_exc.pop(string)
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)