Function clean_str

nano_graphrag/_utils.py:141–149

Clean an input string by removing HTML escapes, control characters, and other unwanted characters.

(input: Any)

# Refer the utils functions of the official GraphRAG implementation:
# https://github.com/microsoft/graphrag
def clean_str(input: Any) -> str:
    """Clean an input string by removing HTML escapes, control characters, and other unwanted characters."""
    # If we get non-string input, just give it back
    if not isinstance(input, str):
        return input

    result = html.unescape(input.strip())
    # https://stackoverflow.com/questions/4324790/removing-control-characters-from-a-string-in-python
    return re.sub(r"[\x00-\x1f\x7f-\x9f]", "", result)


# Utils types -----------------------------------------------------------------------