qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-30 22:19:57 +02:00
Code Issues Releases Wiki Activity

🐛 Use typing.List instead of list, for Python <3.9

Browse source
This commit is contained in:
Mike Gerber 2024-01-03 20:52:07 +01:00
parent 071766efc2
commit c752793be6
3 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/dinglehopper/character_error_rate.py
View file

@ -1,5 +1,5 @@
import unicodedata import unicodedata
from typing import Tuple from typing import Tuple, List
from multimethod import multimethod from multimethod import multimethod
from uniseg.graphemecluster import grapheme_clusters from uniseg.graphemecluster import grapheme_clusters
@ -10,7 +10,7 @@ from .extracted_text import ExtractedText
@multimethod @multimethod
def character_error_rate_n( def character_error_rate_n(
reference: list[str], compared: list[str] reference: List[str], compared: List[str]
) -> Tuple[float, int]: ) -> Tuple[float, int]:
""" """
Compute character error rate. Compute character error rate.

3
src/dinglehopper/edit_distance.py
View file

@ -1,4 +1,5 @@
import unicodedata import unicodedata
from typing import List
from multimethod import multimethod from multimethod import multimethod
from rapidfuzz.distance import Levenshtein from rapidfuzz.distance import Levenshtein
@ -8,7 +9,7 @@ from .extracted_text import ExtractedText
@multimethod @multimethod
def distance(seq1: list[str], seq2: list[str]): def distance(seq1: List[str], seq2: List[str]):
"""Compute the Levenshtein edit distance between two lists of grapheme clusters. """Compute the Levenshtein edit distance between two lists of grapheme clusters.
This assumes that the grapheme clusters are already normalized. This assumes that the grapheme clusters are already normalized.

4
src/dinglehopper/extracted_text.py
View file

@ -4,7 +4,7 @@ import re
import unicodedata import unicodedata
from contextlib import suppress from contextlib import suppress
from itertools import repeat from itertools import repeat
from typing import Optional from typing import List, Optional
import attr import attr
import numpy as np import numpy as np
@ -135,7 +135,7 @@ class ExtractedText:
segments = attr.ib(type=Optional[list], converter=attr.converters.optional(list)) segments = attr.ib(type=Optional[list], converter=attr.converters.optional(list))
joiner = attr.ib(type=Optional[str]) joiner = attr.ib(type=Optional[str])
_text = attr.ib(type=Optional[str]) _text = attr.ib(type=Optional[str])
_grapheme_clusters = attr.ib(type=Optional[list[str]]) _grapheme_clusters = attr.ib(type=Optional[List[str]])
@segments.validator @segments.validator
def check(self, _, value): def check(self, _, value):