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.
150 lines
3.3 KiB
Python
150 lines
3.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import LEMMA, NORM, ORTH, PRON_LEMMA, PUNCT, TAG
|
|
|
|
_exc = {}
|
|
|
|
|
|
# Verbs
|
|
|
|
for verb_data in [
|
|
{ORTH: "driver"},
|
|
{ORTH: "kör"},
|
|
{ORTH: "hörr", LEMMA: "hör"},
|
|
{ORTH: "fattar"},
|
|
{ORTH: "hajar", LEMMA: "förstår"},
|
|
{ORTH: "lever"},
|
|
{ORTH: "serr", LEMMA: "ser"},
|
|
{ORTH: "fixar"},
|
|
]:
|
|
verb_data_tc = dict(verb_data)
|
|
verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
|
|
for data in [verb_data, verb_data_tc]:
|
|
_exc[data[ORTH] + "u"] = [
|
|
dict(data),
|
|
{ORTH: "u", LEMMA: PRON_LEMMA, NORM: "du"},
|
|
]
|
|
|
|
|
|
for exc_data in [
|
|
{ORTH: "jan.", LEMMA: "januari"},
|
|
{ORTH: "febr.", LEMMA: "februari"},
|
|
{ORTH: "feb.", LEMMA: "februari"},
|
|
{ORTH: "apr.", LEMMA: "april"},
|
|
{ORTH: "jun.", LEMMA: "juni"},
|
|
{ORTH: "jul.", LEMMA: "juli"},
|
|
{ORTH: "aug.", LEMMA: "augusti"},
|
|
{ORTH: "sept.", LEMMA: "september"},
|
|
{ORTH: "sep.", LEMMA: "september"},
|
|
{ORTH: "okt.", LEMMA: "oktober"},
|
|
{ORTH: "nov.", LEMMA: "november"},
|
|
{ORTH: "dec.", LEMMA: "december"},
|
|
{ORTH: "mån.", LEMMA: "måndag"},
|
|
{ORTH: "tis.", LEMMA: "tisdag"},
|
|
{ORTH: "ons.", LEMMA: "onsdag"},
|
|
{ORTH: "tors.", LEMMA: "torsdag"},
|
|
{ORTH: "fre.", LEMMA: "fredag"},
|
|
{ORTH: "lör.", LEMMA: "lördag"},
|
|
{ORTH: "sön.", LEMMA: "söndag"},
|
|
{ORTH: "Jan.", LEMMA: "Januari"},
|
|
{ORTH: "Febr.", LEMMA: "Februari"},
|
|
{ORTH: "Feb.", LEMMA: "Februari"},
|
|
{ORTH: "Apr.", LEMMA: "April"},
|
|
{ORTH: "Jun.", LEMMA: "Juni"},
|
|
{ORTH: "Jul.", LEMMA: "Juli"},
|
|
{ORTH: "Aug.", LEMMA: "Augusti"},
|
|
{ORTH: "Sept.", LEMMA: "September"},
|
|
{ORTH: "Sep.", LEMMA: "September"},
|
|
{ORTH: "Okt.", LEMMA: "Oktober"},
|
|
{ORTH: "Nov.", LEMMA: "November"},
|
|
{ORTH: "Dec.", LEMMA: "December"},
|
|
{ORTH: "Mån.", LEMMA: "Måndag"},
|
|
{ORTH: "Tis.", LEMMA: "Tisdag"},
|
|
{ORTH: "Ons.", LEMMA: "Onsdag"},
|
|
{ORTH: "Tors.", LEMMA: "Torsdag"},
|
|
{ORTH: "Fre.", LEMMA: "Fredag"},
|
|
{ORTH: "Lör.", LEMMA: "Lördag"},
|
|
{ORTH: "Sön.", LEMMA: "Söndag"},
|
|
{ORTH: "sthlm", LEMMA: "Stockholm"},
|
|
{ORTH: "gbg", LEMMA: "Göteborg"},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
|
|
ABBREVIATIONS = [
|
|
"ang",
|
|
"anm",
|
|
"bil",
|
|
"bl.a",
|
|
"d.v.s",
|
|
"doc",
|
|
"dvs",
|
|
"e.d",
|
|
"e.kr",
|
|
"el",
|
|
"eng",
|
|
"etc",
|
|
"exkl",
|
|
"f",
|
|
"f.d",
|
|
"f.kr",
|
|
"f.n",
|
|
"f.ö",
|
|
"fid",
|
|
"fig",
|
|
"forts",
|
|
"fr.o.m",
|
|
"förf",
|
|
"inkl",
|
|
"jur",
|
|
"kap",
|
|
"kl",
|
|
"kor",
|
|
"kr",
|
|
"kungl",
|
|
"lat",
|
|
"m.a.o",
|
|
"m.fl",
|
|
"m.m",
|
|
"max",
|
|
"milj",
|
|
"min",
|
|
"mos",
|
|
"mt",
|
|
"o.d",
|
|
"o.s.v",
|
|
"obs",
|
|
"osv",
|
|
"p.g.a",
|
|
"proc",
|
|
"prof",
|
|
"ref",
|
|
"resp",
|
|
"s.a.s",
|
|
"s.k",
|
|
"s.t",
|
|
"sid",
|
|
"s:t",
|
|
"t.ex",
|
|
"t.h",
|
|
"t.o.m",
|
|
"t.v",
|
|
"tel",
|
|
"ung",
|
|
"vol",
|
|
"äv",
|
|
"övers",
|
|
]
|
|
ABBREVIATIONS = [abbr + "." for abbr in ABBREVIATIONS] + ABBREVIATIONS
|
|
|
|
for orth in ABBREVIATIONS:
|
|
_exc[orth] = [{ORTH: orth}]
|
|
|
|
# Sentences ending in "i." (as in "... peka i."), "m." (as in "...än 2000 m."),
|
|
# should be tokenized as two separate tokens.
|
|
for orth in ["i", "m"]:
|
|
_exc[orth + "."] = [{ORTH: orth, LEMMA: orth, NORM: orth}, {ORTH: ".", TAG: PUNCT}]
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|