import os
import re
import subprocess
import sys
from typing import List, Dict

import pandas as pd
from tqdm import tqdm

ROOT_DIR = os.path.dirname(__file__)
IN_SOURCE_DIR = os.path.join(ROOT_DIR, "benchmark")
IN_TEST_DIR = os.path.join(ROOT_DIR, "tests")
IN_FUZZER_TEST_DIR = os.path.join(ROOT_DIR, "fuzzer_tests")
MUT_PY_PATH = os.path.join(ROOT_DIR, 'env37', 'bin', 'mut.py')
REPS: int = 10


def run_mutpy(test_path: str, source_path: str) -> float:
    output = subprocess.check_output(
        [sys.executable, MUT_PY_PATH, '-t', source_path, '-u', test_path]).decode('utf-8')
    score = re.search('Mutation score \\[.*]: (\\d+\\.\\d+)%', output).group(1)
    return float(score)


def mutate_suite(out_file: str, in_test_dir: str, to_test: List[str]):
    scores: List[Dict[str, any]] = []

    if os.path.isfile(out_file):  # do not re-generate if file exists
        return

    for filename in tqdm(to_test, desc=f"mut.py [{os.path.basename(out_file)}]"):
        source_path = os.path.join(IN_SOURCE_DIR, f"{filename}.py")
        test_path = os.path.join(in_test_dir, f"test_{filename}.py")
        scores.append({
            'file': filename,
            'score': run_mutpy(test_path, source_path)
        })

    df = pd.DataFrame.from_records(scores)
    df.to_csv(out_file)


def main():
    files = [os.path.splitext(f) for f in os.listdir(IN_SOURCE_DIR)]
    to_test = [file[0] for file in files if file[1] == ".py"]
    to_test = [e for t in to_test for e in ([t] * REPS)]

    mutate_suite(os.path.join(IN_TEST_DIR, 'mutation_results_genetic.csv'), IN_TEST_DIR, to_test)
    mutate_suite(os.path.join(IN_FUZZER_TEST_DIR, 'mutation_results_fuzzer.csv'), IN_FUZZER_TEST_DIR, to_test)


if __name__ == "__main__":
    main()