26 lines
547 B
Python
26 lines
547 B
Python
|
from ..char_classes import (
|
||
|
|
ALPHA_UPPER,
|
||
|
|
CURRENCY,
|
||
|
|
LIST_ELLIPSES,
|
||
|
|
LIST_PUNCT,
|
||
|
|
LIST_QUOTES,
|
||
|
|
UNITS,
|
||
|
|
)
|
||
|
|
|
||
|
|
_list_punct = LIST_PUNCT + "፡ ። ፣ ፤ ፥ ፦ ፧ ፠ ፨".strip().split()
|
||
|
|
|
||
|
|
_suffixes = (
|
||
|
|
_list_punct
|
||
|
|
+ LIST_ELLIPSES
|
||
|
|
+ LIST_QUOTES
|
||
|
|
+ [
|
||
|
|
r"(?<=[0-9])\+",
|
||
|
|
# Amharic 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
|