mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 11:59:14 +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.
70 lines
1.5 KiB
Python
70 lines
1.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import ORTH, LEMMA, NORM, PRON_LEMMA
|
|
|
|
|
|
_exc = {
|
|
"pal": [{ORTH: "pa", LEMMA: "para"}, {ORTH: "l", LEMMA: "el", NORM: "el"}],
|
|
"pala": [{ORTH: "pa", LEMMA: "para"}, {ORTH: "la", LEMMA: "la", NORM: "la"}],
|
|
}
|
|
|
|
|
|
for exc_data in [
|
|
{ORTH: "aprox.", LEMMA: "aproximadamente"},
|
|
{ORTH: "dna.", LEMMA: "docena"},
|
|
{ORTH: "esq.", LEMMA: "esquina"},
|
|
{ORTH: "pág.", LEMMA: "página"},
|
|
{ORTH: "p.ej.", LEMMA: "por ejemplo"},
|
|
{ORTH: "Ud.", LEMMA: PRON_LEMMA, NORM: "usted"},
|
|
{ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"},
|
|
{ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
|
|
{ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
|
|
# Times
|
|
|
|
_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", LEMMA: "p.m."}]
|
|
|
|
|
|
for h in range(1, 12 + 1):
|
|
for period in ["a.m.", "am"]:
|
|
_exc["%d%s" % (h, period)] = [{ORTH: "%d" % h}, {ORTH: period, LEMMA: "a.m."}]
|
|
for period in ["p.m.", "pm"]:
|
|
_exc["%d%s" % (h, period)] = [{ORTH: "%d" % h}, {ORTH: period, LEMMA: "p.m."}]
|
|
|
|
|
|
for orth in [
|
|
"a.C.",
|
|
"a.J.C.",
|
|
"apdo.",
|
|
"Av.",
|
|
"Avda.",
|
|
"Cía.",
|
|
"etc.",
|
|
"Gob.",
|
|
"Gral.",
|
|
"Ing.",
|
|
"J.C.",
|
|
"Lic.",
|
|
"m.n.",
|
|
"no.",
|
|
"núm.",
|
|
"P.D.",
|
|
"Prof.",
|
|
"Profa.",
|
|
"q.e.p.d.",
|
|
"S.A.",
|
|
"S.L.",
|
|
"s.s.s.",
|
|
"Sr.",
|
|
"Sra.",
|
|
"Srta.",
|
|
]:
|
|
_exc[orth] = [{ORTH: orth}]
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|