INNER CODE UNIT · Python

character_flags

lean-dojo/TorchLean · scripts/generate_unicode_table.py:47

def character_flags(codepoint: int) -> int:
    """Encode the parser-relevant Boolean properties of one code point."""
    character = chr(codepoint)
    flags = 0
    if character.isalnum():
        flags |= ALPHANUMERIC
    if character.isidentifier():
        flags |= IDENTIFIER_START
    if ("a" + character).isidentifier():
        flags |= IDENTIFIER_CONTINUE
    if unicodedata.decimal(character, None) is not None:
        flags |= DECIMAL
    return flags


def character_payload(codepoint: int) -> int:
    """Encode the flags together with the decimal zero for interval splitting.

View source record →