import re, json
from pathlib import Path
from nltk.tokenize import word_tokenize
from Sastrawi.Stemmer.StemmerFactory import StemmerFactory

config = json.loads(
    (Path(__file__).parent / 'preprocessing_config.json')
    .read_text(encoding='utf-8')
)

kamus_normalisasi = config['kamus_normalisasi']
frasa_awal = config['frasa_awal']
frasa_akhir = config['frasa_akhir']
koreksi_validator = config['koreksi_validator']
list_stopwords = set(config['list_stopwords'])
kata_dilindungi_stemming = set(
    config['kata_dilindungi_stemming']
)

stemmer = StemmerFactory().create_stemmer()

def cleaning(text):
    text = str(text)

    # 1. Menghapus URL/Link (tidak peka huruf besar/kecil)
    text = re.sub(r"https?://\S+|www\.\S+", " ", text, flags=re.IGNORECASE)

    # 2. Menghapus mention (@), pertahankan isi hashtag (#)
    text = re.sub(r"@\w+", " ", text)
    text = re.sub(r"#(\w+)", r"\1", text)

    # 3. Menghapus angka
    text = re.sub(r"\d+", " ", text)

    # 4. Menghapus karakter selain huruf
    text = re.sub(r"[^a-zA-Z\s]", " ", text)

    # 5. Merapikan spasi berlebih
    text = re.sub(r"\s+", " ", text).strip()

    return text


def case_folding(text):
    # Mengubah seluruh teks menjadi huruf kecil
    return str(text).lower()


def ganti_frasa(text, kamus_frasa):
    for pola, ganti in kamus_frasa.items():
        text = re.sub(pola, ganti, text)
    return text


def normalisasi(text):
    text = ganti_frasa(str(text), frasa_awal)
    text = re.sub(r"\b\w+\b", lambda m: kamus_normalisasi.get(m.group(), m.group()), text)
    return ganti_frasa(text, frasa_akhir)


def koreksi_normalisasi_validator(text):
    text = str(text)
    text = re.sub(r"\bnge\s+lag\b", "lag", text)        # koreksi frasa hasil validasi
    text = re.sub(r"\bits\s+okey\b", "its okey", text)  # "its okey" dipertahankan
    return re.sub(r"\b\w+\b", lambda x: koreksi_validator.get(x.group(), x.group()), text)


def tokenisasi(text):
    return word_tokenize(str(text))


def hapus_stopword(tokens):
    return " ".join(
        kata for kata in tokens
        if kata not in list_stopwords and len(kata) > 1
    )


def stemming(text):
    hasil = []

    for kata in str(text).split():
        if kata in kata_dilindungi_stemming:
            hasil.append(kata)
        else:
            hasil.append(stemmer.stem(kata))

    return " ".join(hasil)


def preprocessing_kalimat_baru(text):

    # 1. Cleaning
    text = cleaning(text)

    # 2. Case Folding
    text = case_folding(text)

    # 3. Normalisasi
    text = normalisasi(text)
    text = koreksi_normalisasi_validator(text)

    # 4. Tokenisasi
    tokens = tokenisasi(text)

    # 5. Stopword Removal
    text = hapus_stopword(tokens)

    # 6. Stemming
    text = stemming(text)

    return text


def prediksi_sentimen(teks, model, vectorizer):
    if not isinstance(teks, str) or not teks.strip():
        raise ValueError("Masukkan komentar terlebih dahulu.")
    hasil = preprocessing_kalimat_baru(teks)
    if not hasil.strip():
        raise ValueError("Komentar tidak memiliki kata yang dapat diproses.")
    fitur = vectorizer.transform([hasil])
    if fitur.nnz == 0:
        raise ValueError("Kata dalam komentar belum dikenali model.")
    return int(model.predict(fitur)[0])