INNER CODE UNIT · Python

format_text_with_latex

RQLuo/MixTeX-Latex-OCR · mixtex_data_gen/gen.py:83

def format_text_with_latex(words, formulas, lines):
    output = ''
    count = 0
    for char in tqdm(words):
        count += 1
        if len(char) >= 2 and random.random() < 0.01:
            if random.random() < 0.5:
                output += ' \\textbf{' + char + '} '
            else:
                output += ' \\textit{' + char + '} '
        else:
            output += char
        if count % 100 == 0:
            output += '\n \\newpage \n'
        if random.random() < 0.5:
            if random.random() < 0.03:
                formula = random.sample(formulas, 1)[0]
                if random.random() < 0.03:

View source record →