Elaborator for OCRed strings

main.py

from ocre import OCRElaborator

if __name__ == '__main__':
    img_paths = ['test.png', 'test2.png']
    elaborator = OCRElaborator(img_paths)
    print(elaborator.run())

ocre.py

'''
Use Tesseract as an OCR engine.
'''

import pytesseract


class OCRElaborator:
    
    # TODO: allows user to specify methods to be applied.
    available_methods = [
        'delete_duplicated_CR',
        'cancel_hyphenation',
    ]

    def __init__(self, img_paths: list[str]) -> None:
        self.img_paths = img_paths
    
    @staticmethod
    def __ocr(img_path: str) -> str:
        return pytesseract.image_to_string(img_path, lang='eng')
    
    @staticmethod
    def __delete_duplicated_CR(sentence: str) -> str:
        proced_sentence = ''
        for i in range(len(sentence)):
            if sentence[i-1] == '\n' and sentence[i] == '\n':
                continue
            else:
                proced_sentence += sentence[i]
        
        return proced_sentence

    @staticmethod
    def __cancel_hyphenation(sentence: str) -> str:
        proced_sentence = ''
        for i in range(len(sentence)):
            if sentence[i-1] == '-' and sentence[i] == '\n':
                proced_sentence = proced_sentence[:-1]
            elif sentence[i] == '\n':
                proced_sentence += ' '
            else:
                proced_sentence += sentence[i]
        
        return proced_sentence

    @staticmethod
    def __link(sentences: str) -> str:
        return ' '.join(sentences)
    
    def run(self) -> str:
        proced_sentences = []
        for img_path in self.img_paths:
            sentence = self.__ocr(img_path)
            sentence = self.__delete_duplicated_CR(sentence)
            sentence = self.__cancel_hyphenation(sentence)

            proced_sentences.append(sentence)
        
        return self.__link(proced_sentences)