import sys
import pandas as pd
sys.path.append('Backend')

from app.parsers.column_finder import find_column, get_value
from app.parsers.mappings import (
    YEAR_CONFIG, IDENTITAS_MAPPING, PEKERJAAN_MAPPING, STUDI_LANJUT_MAPPING,
    KESESUAIAN_MAPPING, KOMPETENSI_LULUS_MAPPING, KOMPETENSI_SAAT_INI_MAPPING,
    METODE_PEMBELAJARAN_MAPPING, WAKTU_CARI_KERJA_MAPPING, CARA_CARI_KERJA_MAPPING,
    LAMARAN_KEAKTIFAN_MAPPING, KESESUAIAN_PEKERJAAN_MAPPING, get_field_code
)
from app.parsers.converters import konversi_jawaban, parse_2024_value

all_mapping = {}
all_mapping.update(IDENTITAS_MAPPING)
all_mapping.update(PEKERJAAN_MAPPING)
all_mapping.update(STUDI_LANJUT_MAPPING)
all_mapping.update(KESESUAIAN_MAPPING)
all_mapping.update(KOMPETENSI_LULUS_MAPPING)
all_mapping.update(KOMPETENSI_SAAT_INI_MAPPING)
all_mapping.update(METODE_PEMBELAJARAN_MAPPING)
all_mapping.update(WAKTU_CARI_KERJA_MAPPING)
all_mapping.update(CARA_CARI_KERJA_MAPPING)
all_mapping.update(LAMARAN_KEAKTIFAN_MAPPING)
all_mapping.update(KESESUAIAN_PEKERJAAN_MAPPING)

years = ['2019', '2020', '2021', '2022', '2023']

for yr in years:
    fpath = f'Data_Tracerstudy/Data_{yr}_Tracer_study.csv'
    df = pd.read_csv(fpath, sep=';', encoding='utf-8-sig')
    source_cols = list(df.columns)
    
    print("=" * 60)
    print(f"ANALISIS DATA TAHUN {yr} (Total: {len(df)} rows, {len(source_cols)} cols)")
    print("=" * 60)
    
    # 1. Cek baris yang skip (terutama 2021)
    nim_col = find_column(source_cols, IDENTITAS_MAPPING['nim'])
    skipped_indices = []
    for idx, row in df.iterrows():
        nim = get_value(row, source_cols, IDENTITAS_MAPPING['nim'], '')
        if not nim or str(nim).strip() in ['', 'nan', 'none']:
            skipped_indices.append(idx)
    if skipped_indices:
        print(f"[!] SKIPPED ROWS ({len(skipped_indices)} baris): index {skipped_indices}")
        for sidx in skipped_indices:
            print(f"    Sample row {sidx}: {df.iloc[sidx].dropna().to_dict()}")
    else:
        print(f"[*] Tidak ada baris yang diskip berdasarkan NIM.")
        
    # 2. Cek pemetaan kolom ke all_mapping
    unmapped_fields = []
    mapped_fields = {}
    for field, possible_cols in all_mapping.items():
        found = find_column(source_cols, possible_cols)
        if found:
            mapped_fields[field] = found
        else:
            unmapped_fields.append((field, possible_cols[0] if possible_cols else ''))
            
    print(f"\n[*] Total fields di mapping: {len(all_mapping)}")
    print(f"[*] Berhasil dimap ke kolom CSV: {len(mapped_fields)}")
    print(f"[*] TIDAK BERHASIL DIMAP ({len(unmapped_fields)} fields):")
    for uf, fc in unmapped_fields:
        # cari apakah kodenya ada di source_cols
        code = get_field_code(uf, all_mapping)
        similar = [c for c in source_cols if code and code.lower() in c.lower()]
        print(f"    - {uf} (kode: {code}): mirip di CSV -> {similar}")
        
    # 3. Cek kolom spesifik yang user sebutkan:
    # kerja_tidak_sesuai_2, cari_melamar_tanpa_lowongan
    print(f"\n[*] Pengecekan Khusus Field Target:")
    targets = ['kerja_tidak_sesuai_1', 'kerja_tidak_sesuai_2', 'cari_iklan', 'cari_melamar_tanpa_lowongan', 'cari_bursa_pameran']
    for t in targets:
        col = mapped_fields.get(t)
        code = get_field_code(t, all_mapping)
        if col:
            sample_raw = df[col].dropna().unique()
            print(f"    {t} ({code}) -> col '{col}': raw unique values = {sample_raw[:5]}")
            # Cek konversi
            conv_samples = [(v, konversi_jawaban(code, v)) for v in sample_raw[:3]]
            print(f"       Hasil konversi: {conv_samples}")
        else:
            print(f"    {t} ({code}) -> TIDAK DITEMUKAN DI CSV!")
    print()