mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
e626a011cc
* Enable lex_attrs on Finnish * Copy the Danish tokenizer rules to Finnish Specifically, don't break hyphenated compound words * Contributor agreement * A new file for Finnish tokenizer rules instead of including the Danish ones
34 lines
933 B
Python
34 lines
933 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
|
||
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
from ..punctuation import TOKENIZER_SUFFIXES
|
||
|
||
|
||
_quotes = CONCAT_QUOTES.replace("'", "")
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
|
||
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
|
||
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
|
||
]
|
||
)
|
||
|
||
_suffixes = [
|
||
suffix
|
||
for suffix in TOKENIZER_SUFFIXES
|
||
if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
|
||
]
|
||
|
||
|
||
TOKENIZER_INFIXES = _infixes
|
||
TOKENIZER_SUFFIXES = _suffixes
|