OCRmyPDF/tests/test_quality.py

22 lines
630 B
Python
Raw Normal View History

2022-07-28 01:06:46 -07:00
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
2020-01-17 03:10:27 -08:00
2022-07-23 00:39:24 -07:00
from __future__ import annotations
from ocrmypdf import quality as qual
2020-01-17 03:10:27 -08:00
def test_quality_measurement():
oqd = qual.OcrQualityDictionary(
wordlist=["words", "words", "quick", "brown", "fox", "dog", "lazy"]
)
assert len(oqd.dictionary) == 6 # 6 unique
assert (
oqd.measure_words_matched("The quick brown fox jumps quickly over the lazy dog")
== 0.5
)
assert oqd.measure_words_matched("12345 10% _f 7fox -brown | words") == 1.0
assert oqd.measure_words_matched("quick quick quick") == 1.0