text_quality.feature.scorer.garbage

Module Contents

Classes

GarbageDetector

Abstract class for scorers to compute feature values

class text_quality.feature.scorer.garbage.GarbageDetector[source]

Bases: text_quality.feature.scorer.scorer.Scorer

Abstract class for scorers to compute feature values

_VOWELS = 'aäàáâǎeéèêëěiîïíìıoöôòóǒuüûùúǔ'[source]
EPR_RULE1 = 21[source]
EPR_RULE2 = 3[source]
EPR_RULE3 = 4[source]
EPR_RULE4 = 6[source]
EPR_RULE5 = 8[source]
EPR_RULE9 = 2[source]
score(tokens: List[str]) float[source]

See Nautilus-OCR