mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-08-22 16:25:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updating python formatting. (#1079)

Browse Source 
* Updating python formatting.

* Forgot gh action.

* Skipping isort to prevent circular imports.

* Updating stub.

* Removing `isort` (it contradicts `stub.py`).

* Fixing weird stub black/isort disagreeement.
This commit is contained in:
Nicolas Patry
2022-10-05 15:29:33 +02:00
committed by GitHub
parent 5f6e978452
commit 6113666624
43 changed files with 280 additions and 306 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
bindings/python/examples/custom_components.py
View File

@ -1,12 +1,11 @@
import jieba
from typing import List
from tokenizers import Tokenizer, Regex, NormalizedString, PreTokenizedString
from tokenizers.models import BPE
from tokenizers.pre_tokenizers import PreTokenizer
from tokenizers.normalizers import Normalizer
import jieba
from tokenizers import NormalizedString, PreTokenizedString, Regex, Tokenizer
from tokenizers.decoders import Decoder
from tokenizers.models import BPE
from tokenizers.normalizers import Normalizer
from tokenizers.pre_tokenizers import PreTokenizer
class JiebaPreTokenizer:
@ -21,9 +20,7 @@ class JiebaPreTokenizer:
# We can also easily do it in one line:
# return [normalized_string[w[1] : w[2]] for w in jieba.tokenize(str(normalized_string))]
def odd_number_split(
self, i: int, normalized_string: NormalizedString
) -> List[NormalizedString]:
def odd_number_split(self, i: int, normalized_string: NormalizedString) -> List[NormalizedString]:
# Just an odd example...
splits = []
last = 0