spaCy/spacy/lang/bn/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

258 lines
7.3 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from ...symbols import LEMMA, PRON_LEMMA
MORPH_RULES = {
"PRP": {
"": {LEMMA: PRON_LEMMA, "PronType": "Dem"},
"আমাকে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "One",
"PronType": "Prs",
"Case": "Acc",
},
"কি": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Gender": "Neut",
"PronType": "Int",
"Case": "Acc",
},
"সে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Three",
"PronType": "Prs",
"Case": "Nom",
},
"কিসে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Gender": "Neut",
"PronType": "Int",
"Case": "Acc",
},
"তাকে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Three",
"PronType": "Prs",
"Case": "Acc",
},
"স্বয়ং": {LEMMA: PRON_LEMMA, "Reflex": "Yes", "PronType": "Ref"},
"কোনগুলো": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Gender": "Neut",
"PronType": "Int",
"Case": "Acc",
},
"তুমি": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Case": "Nom",
},
"তুই": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Case": "Nom",
},
"তাদেরকে": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Three",
"PronType": "Prs",
"Case": "Acc",
},
"আমরা": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "One ",
"PronType": "Prs",
"Case": "Nom",
},
"যিনি": {LEMMA: PRON_LEMMA, "Number": "Sing", "PronType": "Rel", "Case": "Nom"},
"আমাদেরকে": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "One",
"PronType": "Prs",
"Case": "Acc",
},
"কোন": {LEMMA: PRON_LEMMA, "Number": "Sing", "PronType": "Int", "Case": "Acc"},
"কারা": {LEMMA: PRON_LEMMA, "Number": "Plur", "PronType": "Int", "Case": "Acc"},
"তোমাকে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Case": "Acc",
},
"তোকে": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Case": "Acc",
},
"খোদ": {LEMMA: PRON_LEMMA, "Reflex": "Yes", "PronType": "Ref"},
"কে": {LEMMA: PRON_LEMMA, "Number": "Sing", "PronType": "Int", "Case": "Acc"},
"যারা": {LEMMA: PRON_LEMMA, "Number": "Plur", "PronType": "Rel", "Case": "Nom"},
"যে": {LEMMA: PRON_LEMMA, "Number": "Sing", "PronType": "Rel", "Case": "Nom"},
"তোমরা": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Case": "Nom",
},
"তোরা": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Case": "Nom",
},
"তোমাদেরকে": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Case": "Acc",
},
"তোদেরকে": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Case": "Acc",
},
"আপন": {LEMMA: PRON_LEMMA, "Reflex": "Yes", "PronType": "Ref"},
"": {LEMMA: PRON_LEMMA, "PronType": "Dem"},
"নিজ": {LEMMA: PRON_LEMMA, "Reflex": "Yes", "PronType": "Ref"},
"কার": {LEMMA: PRON_LEMMA, "Number": "Sing", "PronType": "Int", "Case": "Acc"},
"যা": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Gender": "Neut",
"PronType": "Rel",
"Case": "Nom",
},
"তারা": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Three",
"PronType": "Prs",
"Case": "Nom",
},
"আমি": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "One",
"PronType": "Prs",
"Case": "Nom",
},
},
"PRP$": {
"আমার": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "One",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"মোর": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "One",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"মোদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "One",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"তার": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Three",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"তোমাদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"আমাদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "One",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"তোমার": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"তোর": {
LEMMA: PRON_LEMMA,
"Number": "Sing",
"Person": "Two",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"তাদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Three",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"কাদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"PronType": "Int",
"Case": "Acc",
},
"তোদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"Person": "Two",
"PronType": "Prs",
"Poss": "Yes",
"Case": "Nom",
},
"যাদের": {
LEMMA: PRON_LEMMA,
"Number": "Plur",
"PronType": "Int",
"Case": "Acc",
},
},
}