spaCy/spacy/lang/ca/punctuation.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

58 lines
1.6 KiB
Python
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
from ..char_classes import LIST_CURRENCY
from ..char_classes import CURRENCY
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
from ..char_classes import merge_chars, _units
ELISION = " ' ".strip().replace(" ", "").replace("\n", "")
_prefixes = (
["§", "%", "=", "", "", "-", r"\+(?![0-9])"]
+ LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}][{el}])(?=[{a}0-9])".format(a=ALPHA, el=ELISION),
r"('ls|'l|'ns|'t|'m|'n|-les|-la|-lo|-li|-los|-me|-nos|-te|-vos|-se|-hi|-ne|-ho)(?![A-Za-z])|(-l'|-m'|-t'|-n')",
]
)
_units = _units.replace("% ", "")
UNITS = merge_chars(_units)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_ICONS
+ [r"-", "", ""]
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_PREFIXES = _prefixes