extract the tags from an elf file

dataset.py

def _generate_tags(self, binary_elf: ELFFile):
    text_section = binary_elf.get_section_by_name(".text")

    # text_section["sh_addr"] is the address of the .text section.
    # We need the addresses of the symbols to be relative to the .text section so we subtract sh_addr from them.
    function_addresses = [function_address - text_section["sh_addr"] for function_address in self._get_function_addresses(binary_elf)]
    
    tags = numpy.zeros(text_section.data_size, dtype=int)
    tags[function_addresses] = 1
    return tags

@staticmethod
def _get_function_addresses(binary_elf):
    symbol_table = binary_elf.get_section_by_name(".symtab")

    # st_value is the address of the symbol in the binary.
    # There are more types of symbol than function so we make sure we only get the function symbols
    return [symbol["st_value"] for symbol in symbol_table.iter_symbols()
            if symbol["st_info"]["type"] == "STT_FUNC" and symbol["st_size"] != 0]