kse-02/genetic.py

import argparse
import os
import random
from functools import partial

import frozendict
import tqdm
from deap import creator, base, tools, algorithms

import fuzzer
import instrument
import operators
from fuzzer import generate_test_case, get_test_class

INDMUPROB = 0.05
MUPROB = 0.33
CXPROB = 0.33
TOURNSIZE = 3
NPOP = 1000
NGEN = 200
REPS = 1

OUT_DIR = os.path.join(os.path.dirname(__file__), "tests")


class Archive:
    true_branches: dict[int, any]
    false_branches: dict[int, any]
    false_score: dict[int, any]
    true_score: dict[int, any]

    def __init__(self):
        self.reset()

    def reset(self):
        self.true_branches = {}
        self.false_branches = {}
        self.true_score = {}
        self.false_score = {}

    def branches_covered(self) -> int:
        return len(self.true_branches.keys()) + len(self.false_branches.keys())

    def branches_str(self) -> str:
        branch_ids = sorted([f"{branch:2d}T" for branch in self.true_branches.keys()] +
                            [f"{branch:2d}F" for branch in self.false_branches.keys()])
        return ' '.join([branch.strip() for branch in branch_ids])

    def build_suite(self) -> set[instrument.Params]:
        return set(list(self.true_branches.values()) + list(self.false_branches.values()))


def normalize(x):
    return x / (1.0 + x)


def init_deap():
    creator.create("FitnessMin", base.Fitness, weights=(-1.0,))
    creator.create("Individual", list, fitness=creator.FitnessMin)


def generate(orig_name: str) -> set[instrument.Params]:
    f_name = instrument.BranchTransformer.to_instrumented_name(orig_name)
    args = instrument.functions[f_name]

    range_start, range_end = instrument.n_of_branches[f_name]
    total_branches = (range_end - range_start) * 2  # *2 because of True and False
    archive = Archive()

    toolbox = base.Toolbox()
    toolbox.register("attr_test_case", lambda: list(generate_test_case(f_name, args).items()))
    toolbox.register("individual", tools.initIterate, creator.Individual, lambda: toolbox.attr_test_case())
    toolbox.register("population", tools.initRepeat, list, toolbox.individual)
    toolbox.register("evaluate", partial(compute_fitness, f_name, archive))

    def mate(tc1, tc2):
        t1, t2 = frozendict.frozendict(tc1), frozendict.frozendict(tc2)
        o1, o2 = fuzzer.crossover(t1, t2, args)
        i1, i2 = creator.Individual(o1.items()), creator.Individual(o2.items())
        return i1, i2

    def mutate(tc):
        t = frozendict.frozendict(tc)
        o = fuzzer.mutate(t, args)
        i1 = creator.Individual(o.items())
        return i1,

    toolbox.register("mate", mate)
    toolbox.register("mutate", mutate)
    toolbox.register("select", tools.selTournament, tournsize=TOURNSIZE)

    top_result = set()
    top_coverage = 0

    for i in range(REPS):
        archive.reset()
        population = toolbox.population(n=NPOP)

        # Create statistics object
        stats = tools.Statistics(lambda ind: ind.fitness.values)
        stats.register("min", min)
        stats.register("max", max)

        population, logbook = algorithms.eaSimple(population, toolbox, CXPROB, MUPROB, NGEN, verbose=False, stats=stats)

        for gen, record in enumerate(logbook):
            print(f"Generation {gen}: min={record['min']} max={record['max']}")

        print(population)

        tot_covered = archive.branches_covered()

        cov: float = (tot_covered / total_branches) * 100

        branches = archive.branches_str()
        print(f"{orig_name}: rep #{i:02d}: Cov: {cov:02.02f}% ({tot_covered}/{total_branches} branches): {branches}")

        if cov > top_coverage:
            top_result = archive.build_suite()
            top_coverage = cov

            if tot_covered == total_branches:
                break

    return top_result


def compute_fitness(f_name: str, archive: Archive, individual: list) -> tuple[float]:
    x = frozendict.frozendict(individual)
    range_start, range_end = instrument.n_of_branches[f_name]

    # Reset any distance values from previous executions
    operators.distances_true = {}
    operators.distances_false = {}
    # archive.true_branches = {}
    # archive.false_branches = {}

    # the archive_true_branches and archive_false_branches are reset after
    # each generation. This is intentional as they are used to archive branches that
    # have already been covered, and their presence increases the fitness value of
    # test cases that would re-cover them

    # Run the function under test
    try:
        out = instrument.invoke(f_name, x)
    except AssertionError:
        print(f_name, x, "=", "[FAILS] fitness = 100.0")
        return 100.0,

    fitness = 0.0
    branches = False

    # print(operators.distances_true, operators.distances_false)

    # Sum up branch distances
    for branch in range(range_start, range_end):
        if branch in operators.distances_true:
            fitness += normalize(operators.distances_true[branch])
            branches = True

            if operators.distances_true[branch] == 0:  # if test is true for this branch
                if branch not in archive.false_score or archive.false_score[branch] > operators.distances_false[branch]:
                    archive.true_branches[branch] = x
                    archive.false_score[branch] = operators.distances_false[branch]

        if branch in operators.distances_false:
            fitness += normalize(operators.distances_false[branch])
            branches = True

            if operators.distances_false[branch] == 0:  # if test is true for this branch
                if branch not in archive.true_score or archive.true_score[branch] > operators.distances_true[branch]:
                    archive.false_branches[branch] = x
                    archive.true_score[branch] = operators.distances_true[branch]

    if not branches:
        return 100.0,

    print(f_name, x, "=", out, "fitness =", fitness)
    return fitness,


def build_suite(filename: str, f_names: list[str]):
    suite = [(name, generate(name)) for name in f_names]

    with open(os.path.join(OUT_DIR, f"test_{filename}.py"), "w") as f:
        f.write(fuzzer.get_test_import_stmt(f_names))
        f.write("\n\n")
        f.write("\n\n".join([get_test_class(name, cases) for name, cases in suite]))


def main():
    random.seed(0)  # init random seed

    parser = argparse.ArgumentParser(prog='genetic.py',
                                     description='Runs genetic algorithm for test case generation. Works on benchmark '
                                                 'files situated in the \'benchmark\' directory.')
    parser.add_argument('file', type=str, help="File to test",
                        nargs="*")

    instrument.load_benchmark(save_instrumented=False, files=parser.parse_args().file)
    init_deap()

    for file_name, functions in tqdm.tqdm(instrument.get_benchmark().items(), desc="Generating tests"):
        build_suite(file_name, functions)


if __name__ == '__main__':
    main()