mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
eddeb36c96
<!--- Provide a general summary of your changes in the title. --> ## Description - [x] Use [`black`](https://github.com/ambv/black) to auto-format all `.py` files. - [x] Update flake8 config to exclude very large files (lemmatization tables etc.) - [x] Update code to be compatible with flake8 rules - [x] Fix various small bugs, inconsistencies and messy stuff in the language data - [x] Update docs to explain new code style (`black`, `flake8`, when to use `# fmt: off` and `# fmt: on` and what `# noqa` means) Once #2932 is merged, which auto-formats and tidies up the CLI, we'll be able to run `flake8 spacy` actually get meaningful results. At the moment, the code style and linting isn't applied automatically, but I'm hoping that the new [GitHub Actions](https://github.com/features/actions) will let us auto-format pull requests and post comments with relevant linting information. ### Types of change enhancement, code style ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
289 lines
7.3 KiB
Python
289 lines
7.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import LEMMA, PRON_LEMMA
|
|
|
|
|
|
# Used the table of pronouns at https://sv.wiktionary.org/wiki/deras
|
|
MORPH_RULES = {
|
|
"PRP": {
|
|
"jag": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Nom",
|
|
},
|
|
"mig": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Acc",
|
|
},
|
|
"mej": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Acc",
|
|
},
|
|
"du": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Case": "Nom",
|
|
},
|
|
"han": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Masc",
|
|
"Case": "Nom",
|
|
},
|
|
"honom": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Masc",
|
|
"Case": "Acc",
|
|
},
|
|
"hon": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Fem",
|
|
"Case": "Nom",
|
|
},
|
|
"henne": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Fem",
|
|
"Case": "Acc",
|
|
},
|
|
"det": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Neut",
|
|
},
|
|
"vi": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"oss": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Case": "Acc",
|
|
},
|
|
"ni": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"er": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Plur"},
|
|
"de": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"dom": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": ("Nom", "Acc"),
|
|
},
|
|
"dem": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": "Acc",
|
|
},
|
|
"min": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"mitt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"mina": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"din": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"ditt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"dina": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"hans": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": ("Sing", "Plur"),
|
|
"Gender": "Masc",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"hennes": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": ("Sing", "Plur"),
|
|
"Gender": "Fem",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"dess": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": ("Sing", "Plur"),
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vår": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"våran": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vårt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vårat": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"våra": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"eran": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"ert": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"erat": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"era": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"deras": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
},
|
|
"VBZ": {
|
|
"är": {
|
|
"VerbForm": "Fin",
|
|
"Person": ("One", "Two", "Three"),
|
|
"Tense": "Pres",
|
|
"Mood": "Ind",
|
|
}
|
|
},
|
|
"VBP": {"är": {"VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"}},
|
|
"VBD": {
|
|
"var": {"VerbForm": "Fin", "Tense": "Past", "Number": "Sing"},
|
|
"vart": {"VerbForm": "Fin", "Tense": "Past", "Number": "Plur"},
|
|
},
|
|
}
|