mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
ee011ca963
* Add missing punctuation for Tigrinya and Amharic * Fix numeral and ordinal numbers for Tigrinya - Amharic was used in many cases - Also fixed some typos * Update Tigrinya stop-words * Contributor agreement for fgaim * Fix typo in "ti" lang test * Remove multi-word entries from numbers and ordinals
20 lines
545 B
Python
20 lines
545 B
Python
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
|
|
from ..char_classes import UNITS, ALPHA_UPPER
|
|
|
|
_list_punct = LIST_PUNCT + "፡ ። ፣ ፤ ፥ ፦ ፧ ፠ ፨".strip().split()
|
|
|
|
_suffixes = (
|
|
_list_punct
|
|
+ LIST_ELLIPSES
|
|
+ LIST_QUOTES
|
|
+ [
|
|
r"(?<=[0-9])\+",
|
|
# Tigrinya is written from Left-To-Right
|
|
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
|
|
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
|
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
|
|
]
|
|
)
|
|
|
|
TOKENIZER_SUFFIXES = _suffixes
|