spaCy/spacy/lang/en/morph_rules.py
Ines Montani eddeb36c96
💫 Tidy up and auto-format .py files (#2983)
<!--- 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.
2018-11-30 17:03:03 +01:00

330 lines
8.3 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from ...symbols import LEMMA, PRON_LEMMA
MORPH_RULES = {
"PRP": {
"I": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Nom",
},
"me": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Acc",
},
"you": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two"},
"he": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Masc",
"Case": "Nom",
},
"him": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Masc",
"Case": "Acc",
},
"she": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Fem",
"Case": "Nom",
},
"her": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Fem",
"Case": "Acc",
},
"it": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Neut",
},
"we": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Case": "Nom",
},
"us": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Case": "Acc",
},
"they": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Case": "Nom",
},
"them": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Case": "Acc",
},
"mine": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Poss": "Yes",
"Reflex": "Yes",
},
"his": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Masc",
"Poss": "Yes",
"Reflex": "Yes",
},
"hers": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Fem",
"Poss": "Yes",
"Reflex": "Yes",
},
"its": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Neut",
"Poss": "Yes",
"Reflex": "Yes",
},
"ours": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Poss": "Yes",
"Reflex": "Yes",
},
"yours": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Plur",
"Poss": "Yes",
"Reflex": "Yes",
},
"theirs": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Poss": "Yes",
"Reflex": "Yes",
},
"myself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Acc",
"Reflex": "Yes",
},
"yourself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Case": "Acc",
"Reflex": "Yes",
},
"himself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Gender": "Masc",
"Reflex": "Yes",
},
"herself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Gender": "Fem",
"Reflex": "Yes",
},
"itself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Gender": "Neut",
"Reflex": "Yes",
},
"themself": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Reflex": "Yes",
},
"ourselves": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Case": "Acc",
"Reflex": "Yes",
},
"yourselves": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Case": "Acc",
"Reflex": "Yes",
},
"themselves": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Case": "Acc",
"Reflex": "Yes",
},
},
"PRP$": {
"my": {
LEMMA: PRON_LEMMA,
"Person": "One",
"Number": "Sing",
"PronType": "Prs",
"Poss": "Yes",
},
"your": {LEMMA: PRON_LEMMA, "Person": "Two", "PronType": "Prs", "Poss": "Yes"},
"his": {
LEMMA: PRON_LEMMA,
"Person": "Three",
"Number": "Sing",
"Gender": "Masc",
"PronType": "Prs",
"Poss": "Yes",
},
"her": {
LEMMA: PRON_LEMMA,
"Person": "Three",
"Number": "Sing",
"Gender": "Fem",
"PronType": "Prs",
"Poss": "Yes",
},
"its": {
LEMMA: PRON_LEMMA,
"Person": "Three",
"Number": "Sing",
"Gender": "Neut",
"PronType": "Prs",
"Poss": "Yes",
},
"our": {
LEMMA: PRON_LEMMA,
"Person": "One",
"Number": "Plur",
"PronType": "Prs",
"Poss": "Yes",
},
"their": {
LEMMA: PRON_LEMMA,
"Person": "Three",
"Number": "Plur",
"PronType": "Prs",
"Poss": "Yes",
},
},
"VBZ": {
"am": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "One",
"Tense": "Pres",
"Mood": "Ind",
},
"are": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "Two",
"Tense": "Pres",
"Mood": "Ind",
},
"is": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "Three",
"Tense": "Pres",
"Mood": "Ind",
},
"'re": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "Two",
"Tense": "Pres",
"Mood": "Ind",
},
"'s": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "Three",
"Tense": "Pres",
"Mood": "Ind",
},
},
"VBP": {
"are": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"},
"'re": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"},
"am": {
LEMMA: "be",
"VerbForm": "Fin",
"Person": "One",
"Tense": "Pres",
"Mood": "Ind",
},
},
"VBD": {
"was": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Past", "Number": "Sing"},
"were": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Past", "Number": "Plur"},
},
}
for tag, rules in MORPH_RULES.items():
for key, attrs in dict(rules).items():
rules[key.title()] = attrs