mirror of
https://github.com/qurator-spk/dinglehopper.git
synced 2025-06-08 11:20:26 +02:00
Fix a few typos
This commit is contained in:
parent
308165b7eb
commit
6f61e8ec44
4 changed files with 8 additions and 6 deletions
|
@ -1,6 +1,7 @@
|
||||||
import math
|
import math
|
||||||
import unicodedata
|
import unicodedata
|
||||||
from math import ceil
|
from math import ceil
|
||||||
|
from typing import Union
|
||||||
|
|
||||||
from rapidfuzz.distance import Levenshtein
|
from rapidfuzz.distance import Levenshtein
|
||||||
|
|
||||||
|
@ -14,7 +15,7 @@ def align(t1, t2):
|
||||||
return seq_align(s1, s2)
|
return seq_align(s1, s2)
|
||||||
|
|
||||||
|
|
||||||
def score_hint(er: float, n: int) -> int | None:
|
def score_hint(er: float, n: int) -> Union[int, None]:
|
||||||
"""Calculate RapidFuzz score hint for a given error rate and count.
|
"""Calculate RapidFuzz score hint for a given error rate and count.
|
||||||
|
|
||||||
Gives the score hint for the distance functions (= expected distance) or None if
|
Gives the score hint for the distance functions (= expected distance) or None if
|
||||||
|
|
|
@ -1,5 +1,5 @@
|
||||||
import unicodedata
|
import unicodedata
|
||||||
from typing import Tuple
|
from typing import List, Tuple
|
||||||
|
|
||||||
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.
|
||||||
|
|
|
@ -2,13 +2,14 @@ import unicodedata
|
||||||
|
|
||||||
from multimethod import multimethod
|
from multimethod import multimethod
|
||||||
from rapidfuzz.distance import Levenshtein
|
from rapidfuzz.distance import Levenshtein
|
||||||
|
from typing import List
|
||||||
from uniseg.graphemecluster import grapheme_clusters
|
from uniseg.graphemecluster import grapheme_clusters
|
||||||
|
|
||||||
from .extracted_text import ExtractedText
|
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.
|
||||||
|
|
|
@ -4,7 +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 Optional, List
|
||||||
|
|
||||||
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):
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue