INNER CODE UNIT · Python

remove_whitespace_signature

lefterisloukas/edgar-crawler · extract_items.py:280

        def remove_whitespace_signature(match):
            ws = r"[^\S\r\n]"
            return f'{match[1]}{re.sub(ws, r"", match[2])}{match[4]}{match[5]}'

        # Fix broken section headers (PART, ITEM, SIGNATURE)
        text = re.sub(
            r"(\n[^\S\r\n]*)(P[^\S\r\n]*A[^\S\r\n]*R[^\S\r\n]*T)([^\S\r\n]+)((\d{1,2}|[IV]{1,2})[AB]?)",
            remove_whitespace,
            text,
            flags=re.IGNORECASE,
        )
        text = re.sub(
            r"(\n[^\S\r\n]*)(I[^\S\r\n]*T[^\S\r\n]*E[^\S\r\n]*M)([^\S\r\n]+)(\d{1,2}[AB]?)",
            remove_whitespace,
            text,
            flags=re.IGNORECASE,
        )
        text = re.sub(

View source record →