spaCy/spacy/lang/ca/tokenizer_exceptions.py
Adriane Boyd fe5f5d6ac6
Update Catalan tokenizer (#9297)
* Update Makefile

For more recent python version

* updated for bsc changes

New tokenization changes

* Update test_text.py

* updating tests and requirements

* changed failed test in test/lang/ca

changed failed test in test/lang/ca

* Update .gitignore

deleted stashed changes line

* back to python 3.6 and remove transformer requirements

As per request

* Update test_exception.py

Change the test

* Update test_exception.py

Remove test print

* Update Makefile

For more recent python version

* updated for bsc changes

New tokenization changes

* updating tests and requirements

* Update requirements.txt

Removed spacy-transfromers from requirements

* Update test_exception.py

Added final punctuation to ensure consistency

* Update Makefile

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Format

* Update test to check all tokens

Co-authored-by: cayorodriguez <crodriguezp@gmail.com>
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2021-09-27 14:42:30 +02:00

69 lines
1.9 KiB
Python
Executable File

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...util import update_exc
_exc = {}
for exc_data in [
{ORTH: "aprox.", NORM: "aproximadament"},
{ORTH: "pàg.", NORM: "pàgina"},
{ORTH: "p.ex.", NORM: "per exemple"},
{ORTH: "gen.", NORM: "gener"},
{ORTH: "feb.", NORM: "febrer"},
{ORTH: "abr.", NORM: "abril"},
{ORTH: "jul.", NORM: "juliol"},
{ORTH: "set.", NORM: "setembre"},
{ORTH: "oct.", NORM: "octubre"},
{ORTH: "nov.", NORM: "novembre"},
{ORTH: "dec.", NORM: "desembre"},
{ORTH: "Dr.", NORM: "doctor"},
{ORTH: "Dra.", NORM: "doctora"},
{ORTH: "Sr.", NORM: "senyor"},
{ORTH: "Sra.", NORM: "senyora"},
{ORTH: "Srta.", NORM: "senyoreta"},
{ORTH: "núm", NORM: "número"},
{ORTH: "St.", NORM: "sant"},
{ORTH: "Sta.", NORM: "santa"},
{ORTH: "pl.", NORM: "plaça"},
{ORTH: "à."},
{ORTH: "è."},
{ORTH: "é."},
{ORTH: "í."},
{ORTH: "ò."},
{ORTH: "ó."},
{ORTH: "ú."},
{ORTH: "'l"},
{ORTH: "'ls"},
{ORTH: "'m"},
{ORTH: "'n"},
{ORTH: "'ns"},
{ORTH: "'s"},
{ORTH: "'t"},
]:
_exc[exc_data[ORTH]] = [exc_data]
_exc["del"] = [{ORTH: "d", NORM: "de"}, {ORTH: "el"}]
_exc["dels"] = [{ORTH: "d", NORM: "de"}, {ORTH: "els"}]
_exc["al"] = [{ORTH: "a"}, {ORTH: "l", NORM: "el"}]
_exc["als"] = [{ORTH: "a"}, {ORTH: "ls", NORM: "els"}]
_exc["pel"] = [{ORTH: "p", NORM: "per"}, {ORTH: "el"}]
_exc["pels"] = [{ORTH: "p", NORM: "per"}, {ORTH: "els"}]
_exc["holahola"] = [{ORTH: "holahola", NORM: "cocacola"}]
# Times
_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", NORM: "p.m."}]
for h in range(1, 12 + 1):
for period in ["a.m.", "am"]:
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "a.m."}]
for period in ["p.m.", "pm"]:
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "p.m."}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)