mirror of
https://github.com/qurator-spk/dinglehopper.git
synced 2025-07-08 01:49:58 +02:00
Mike Gerber
325e5af5f5
Installing was broken since moving to pyproject.toml, which we didn't notice because of
leftover files in build/. Fix this by using the convention of having the source files
in src/ and adjusting pyproject.toml accordingly.
Fixes gh-86. 🤞
47 lines
1.1 KiB
Python
47 lines
1.1 KiB
Python
from __future__ import division
|
|
|
|
import unicodedata
|
|
from typing import Tuple
|
|
|
|
from multimethod import multimethod
|
|
from uniseg.graphemecluster import grapheme_clusters
|
|
|
|
from .edit_distance import distance
|
|
from .extracted_text import ExtractedText
|
|
|
|
|
|
@multimethod
|
|
def character_error_rate_n(reference: str, compared: str) -> Tuple[float, int]:
|
|
"""
|
|
Compute character error rate.
|
|
|
|
:return: character error rate and length of the reference
|
|
"""
|
|
|
|
d = distance(reference, compared)
|
|
n = len(list(grapheme_clusters(unicodedata.normalize("NFC", reference))))
|
|
|
|
if d == 0:
|
|
return 0, n
|
|
if n == 0:
|
|
return float("inf"), n
|
|
return d / n, n
|
|
|
|
# XXX Should we really count newlines here?
|
|
|
|
|
|
@multimethod
|
|
def character_error_rate_n(
|
|
reference: ExtractedText, compared: ExtractedText
|
|
) -> Tuple[float, int]:
|
|
return character_error_rate_n(reference.text, compared.text)
|
|
|
|
|
|
def character_error_rate(reference, compared) -> float:
|
|
"""
|
|
Compute character error rate.
|
|
|
|
:return: character error rate
|
|
"""
|
|
cer, _ = character_error_rate_n(reference, compared)
|
|
return cer
|