Class MarkdownConverter

tools/to_markdown.py:90–448

Convert structured recognition results to Markdown format

class MarkdownConverter:
    """Convert structured recognition results to Markdown format"""

    def __init__(self):
        # Define heading levels for different section types
        self.heading_levels = {
            'sec_0': '#',
            'sec_1': '##',
            'sec_2': '###',
            'sec_3': '###',
            'sec_4': '###',
            'sec_5': '###',
        }

        # Define which labels need special handling
        self.special_labels = {
            'sec_0', 'sec_1', 'sec_2', 'sec_3', 'sec_4', 'sec_5', 'list',
            'equ', 'tab', 'fig'
        }

        # Define replacements for special formulas
        self.replace_dict = {
            '\\bm': '\mathbf ',
            '\eqno': '\quad ',
            '\quad': '\quad ',
            '\leq': '\leq ',
            '\pm': '\pm ',
            '\\varmathbb': '\mathbb ',
            '\in fty': '\infty',
            '\mu': '\mu ',
            '\cdot': '\cdot ',
            '\langle': '\langle ',
            '\pm': '\pm '
        }
        # self.bigpattern = pattern = r"\\(big|Big|bigg|Bigg)\{(\\?[()\[\]{}]|\\langle|\\rangle)|\|\}"

    def try_remove_newline(self, text: str) -> str:
        try:
            # Preprocess text to handle line breaks
            text = text.strip()
            text = text.replace('-\n', '')

            # Handle Chinese text line breaks
            def is_chinese(char):
                return '\u4e00' <= char <= '\u9fff'

            lines = text.split('\n')
            processed_lines = []

            # Process all lines except the last one
            for i in range(len(lines) - 1):
                current_line = lines[i].strip()
                next_line = lines[i + 1].strip()

                # Always add the current line, but determine if we need a newline
                if current_line:  # If current line is not empty
                    if next_line:  # If next line is not empty
                        # For Chinese text handling