eval_code.py

import copy
import json
import time

"""
We will handle here the code evaluation phase.

"""
import json


EVAL_ANSWER_NOEVAL = 0
EVAL_ANSWER_POSITIVE = 1
EVAL_ANSWER_NEGATIVE = -1

CODE_AUGMENTATIONS=[
    ("NO_COMPILE", "The code provided is not a valid C code"),
    ("DRY", "Don't repeat yourself."),
    ("SRP", "Single object[function] responsability"),
    ("MC", "Magic constants."),
    ("NAME", "Meaningful names in the code."),
]


def clean_prompt_answer(answer):
    """
    Chatgpt4 is ok, does not pollute the code but 3.5 encloses it in ```

    :param answer:
    :return:
    """
    cleaned = []
    for l in answer.split("\n"):
        if l.startswith("```"):
            continue
        else:
            cleaned.append(l)
    return "\n".join(cleaned)

def parse_chatgpt_answer(ans_text):
    try:
        js_answer = json.loads(ans_text)
    except:
        # for now we dump the error in console
        import traceback
        exception = traceback.format_exc()
        print(exception)
        return {"error":exception}
    return js_answer

def eval_code_by_chatgpt(openai_client, ccode):
    """
    Will evaluate a piece of code using our heavily tuned prompt!

    :param openai_client:
    :param ccode:
    :return:
    """
    # time.sleep(3)
    try:
        return """[
  {
    "criteria": "DRY",
    "explanation": "The memory allocation and initialization for ``p1``, ``p2``, and ``p3`` are repetitive. Consider creating a function like ``allocateAndInitializeMemory``."
  },
  {
    "criteria": "DRY",
    "explanation": "Tne second DRY failure, because this is the observed ChatGPT behaviour."
  },

  {
    "criteria": "SRP",
    "explanation": "The ``main`` function handles memory allocation, initialization, and printing. You should separate these responsibilities into different functions like ``allocateMemory``, ``initializeData``, and ``printData``."
  },
  {
    "criteria": "NAME",
    "explanation": "``x1`` should be called ``title``, ``y1`` should be called ``author``, ``z1`` should be called ``year``, ``p1`` should be called ``titlePtr``, ``p2`` should be called ``authorPtr``, ``p3`` should be called ``yearPtr``."
  }
]"""
        assert openai_client is not None
    except:
        import traceback
        traceback.print_exc()
        return {"error":"There was an error while parsing the answer. Maybe ChatGPT is overloaded?"}



def add_evaluation_fields_on_js_answer(json_answer, all_criterias = None):
    """
    Adds some JSON fields to store the human feedback.

    The textual human feedback will always be in the 0 position.

    :param json_answer:
    :return:
    """
    if all_criterias is None:
        all_criterias = CODE_AUGMENTATIONS
    enhanced_answer = []
    overall_feedback = {
        "criteria":"HUMAN_FEEDBACK",
        "explanation":"",
        "EVAL": EVAL_ANSWER_NOEVAL
    }

    if all_criterias is not None:
        existing = {c["criteria"] for c in json_answer}
        for criteria in all_criterias:
            if criteria[0] not in existing:
                json_answer.append({"criteria":criteria[0], "explanation":"Not infringed"})

    enhanced_answer.append(overall_feedback)
    for ans in json_answer:
        ans = copy.deepcopy(ans)
        ans["EVAL"] = EVAL_ANSWER_NOEVAL
        enhanced_answer.append(ans)

    return enhanced_answer

def eval_the_piece_of_c_code(openai_client, ccode):
    """
    Main entrypoint to this module. Will be called from backend. Will block so multithreading pls.

    Will return a proprer json and will have EVAL fields, too.

    :param ccode:
    :return:
    """
    chatgpt_ans = eval_code_by_chatgpt(openai_client, ccode)
    chatgpt_js = parse_chatgpt_answer(chatgpt_ans)
    enhanced_answer = add_evaluation_fields_on_js_answer(chatgpt_js)
    return enhanced_answer