def unsafe_execute()

in human_eval_infilling/execution.py [0:0]

• 29 lines of code
• 9 McCabe index (conditional complexity)

def unsafe_execute(problem, completion, result, timeout):

    with create_tempdir():

        # These system calls are needed when cleaning up tempdir.
        import os
        import shutil

        rmtree = shutil.rmtree
        rmdir = os.rmdir
        chdir = os.chdir

        # Disable functionalities that can make destructive changes to the test.
        reliability_guard()

        # Construct the check program and run it.
        check_program = (
            problem["prompt"]
            + completion
            + problem["suffix"]
            + "\n"
            + problem["test"]
            + "\n"
            + f"check({problem['entry_point']})"
        )

        try:
            exec_globals = {}
            with swallow_io():
                with time_limit(timeout):
# WARNING
# This program exists to execute untrusted model-generated code. Although
# it is highly unlikely that model-generated code will do something overtly
# malicious in response to this test suite, model-generated code may act
# destructively due to a lack of model capability or alignment.
# Users are strongly encouraged to sandbox this evaluation suite so that it
# does not perform destructive actions on their host or network. For more
# information on how OpenAI sandboxes its code, see the accompanying paper.
# Once you have read this disclaimer and taken appropriate precautions,
# uncomment the following line and proceed at your own risk:
#                     exec(check_program, exec_globals)
            result.append("passed")
        except TimeoutException:
            result.append("timed out")
        except BaseException as e:
            result.append(f"failed: {e}")

        # Needed for cleaning up.
        shutil.rmtree = rmtree
        os.rmdir = rmdir
        os.chdir = chdir