Method ingest

uncompyle6/scanners/scanner2.py:184–502

Create "tokens" the bytecode of an Python code object. Largely these are the opcode name, but in some cases that has been modified to make parsing easier. returning a list of uncompyle6 Token's. Some transformations are made to assist the deparsing grammar:

(self, co, classname=None, code_objects={}, show_asm=None)

        return free, names, varnames

    def ingest(self, co, classname=None, code_objects={}, show_asm=None):
        """
        Create "tokens" the bytecode of an Python code object. Largely these
        are the opcode name, but in some cases that has been modified to make parsing
        easier.
        returning a list of uncompyle6 Token's.

        Some transformations are made to assist the deparsing grammar:
           -  various types of LOAD_CONST's are categorized in terms of what they load
           -  COME_FROM instructions are added to assist parsing control structures
           -  operands with stack argument counts or flag masks are appended to the opcode name, e.g.:
              *  BUILD_LIST, BUILD_SET
              *  MAKE_FUNCTION and FUNCTION_CALLS append the number of positional arguments
           -  EXTENDED_ARGS instructions are removed

        Also, when we encounter certain tokens, we add them to a set which will cause custom
        grammar rules. Specifically, variable arg tokens like MAKE_FUNCTION or BUILD_LIST
        cause specific rules for the specific number of arguments they take.
        """
        if not show_asm:
            show_asm = self.show_asm

        bytecode = self.build_instructions(co)

        if show_asm in ("both", "before"):
            print("\n# ---- disassembly:")
            bytecode.disassemble_bytes(
                co.co_code,
                varnames=co.co_varnames,
                names=co.co_names,
                constants=co.co_consts,
                cells=bytecode._cell_names,
                line_starts=bytecode._linestarts,
                asm_format="extended",
            )

        # list of tokens/instructions
        new_tokens = []

        # "customize" is in the process of going away here
        customize = {}
        if self.is_pypy:
            customize["PyPy"] = 0

        codelen = len(self.code)

        free, names, varnames = self.unmangle_code_names(co, classname)
        self.names = names

        # Scan for assertions. Later we will
        # turn 'LOAD_GLOBAL' to 'LOAD_ASSERT'.
        # 'LOAD_ASSERT' is used in assert statements.
        self.load_asserts = set()
        for i in self.op_range(0, codelen):
            # We need to detect the difference between:
            #   raise AssertionError
            #  and
            #   assert ...