Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity
spaCy/spacy/lang/da/morph_rules.py

309 lines
10 KiB
Python
Raw Normal View History

Fix PRON_LEMMA imports
2017-11-06 16:41:53 +00:00
from ...symbols import LEMMA, PRON_LEMMA
Add more Danish morph rules and clean up existing ones
2017-11-30 10:17:19 +00:00
# Source: Danish Universal Dependencies and http://fjern-uv.dk/pronom.php
# Note: The Danish Universal Dependencies specify Case=Acc for all instances
# of "den"/"det" even when the case is in fact "Nom". In the rules below, Case
# is left unspecified for "den" and "det".
Add Morph_rules. (TODO: Not working?)
2017-07-03 13:49:09 +00:00
MORPH_RULES = {
"PRON": {
💫 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 16:03:03 +00:00
"jeg": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Sing|Person=1|PronType=Prs
"mig": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Sing|Person=1|PronType=Prs
"min": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Com",
}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"mit": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Neut",
}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"vor": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Com",
}, # Gender=Com|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"vort": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Neut",
}, # Gender=Neut|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"du": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Sing",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Sing|Person=2|PronType=Prs
"dig": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Sing",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Sing|Person=2|PronType=Prs
"din": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Com",
}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"dit": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Neut",
}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"han": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Sing|Person=3|PronType=Prs
"hun": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Sing|Person=3|PronType=Prs
"den": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs, See note above.
"det": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Gender": "Neut",
}, # Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs See note above.
"ham": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs
"hende": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs
"sin": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Com",
"Reflex": "Yes",
}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"sit": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
"Poss": "Yes",
"Gender": "Neut",
"Reflex": "Yes",
}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"vi": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Plur|Person=1|PronType=Prs
"os": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Plur|Person=1|PronType=Prs
"mine": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Poss": "Yes",
}, # Number=Plur|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"vore": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
"Poss": "Yes",
}, # Number=Plur|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"I": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Plur",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Number=Plur|Person=2|PronType=Prs
"jer": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Plur",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Number=Plur|Person=2|PronType=Prs
"dine": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Number": "Plur",
"Poss": "Yes",
}, # Number=Plur|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"de": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Case": "Nom",
}, # Case=Nom|Number=Plur|Person=3|PronType=Prs
"dem": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Case": "Acc",
}, # Case=Acc|Number=Plur|Person=3|PronType=Prs
"sine": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
"Poss": "Yes",
"Reflex": "Yes",
}, # Number=Plur|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"vores": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "One",
"Poss": "Yes",
}, # Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs
"De": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Case": "Nom",
"Gender": "Com",
}, # Case=Nom|Gender=Com|Person=2|Polite=Form|PronType=Prs
"Dem": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Case": "Acc",
"Gender": "Com",
}, # Case=Acc|Gender=Com|Person=2|Polite=Form|PronType=Prs
"Deres": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Poss": "Yes",
}, # Person=2|Polite=Form|Poss=Yes|PronType=Prs
"jeres": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Two",
"Poss": "Yes",
}, # Number[psor]=Plur|Person=2|Poss=Yes|PronType=Prs
"sig": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Case": "Acc",
"Reflex": "Yes",
}, # Case=Acc|Person=3|PronType=Prs|Reflex=Yes
"hans": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Poss": "Yes",
}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"hendes": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Poss": "Yes",
}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"dens": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Poss": "Yes",
}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"dets": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Poss": "Yes",
}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"deres": {
LEMMA: PRON_LEMMA,
"PronType": "Prs",
"Person": "Three",
"Poss": "Yes",
}, # Number[psor]=Plur|Person=3|Poss=Yes|PronType=Prs
Add Morph_rules. (TODO: Not working?)
2017-07-03 13:49:09 +00:00
},
"VERB": {
💫 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 16:03:03 +00:00
"er": {LEMMA: "være", "VerbForm": "Fin", "Tense": "Pres"},
"var": {LEMMA: "være", "VerbForm": "Fin", "Tense": "Past"},
},
Add Morph_rules. (TODO: Not working?)
2017-07-03 13:49:09 +00:00
}
for tag, rules in MORPH_RULES.items():
for key, attrs in dict(rules).items():
rules[key.title()] = attrs