#!/usr/bin/env python3
"""
i18n-verify-keys.py — Detect missing/extra translation keys between zh-CN and en-US.

Usage:
    python3 scripts/i18n-verify-keys.py          # Report only
    python3 scripts/i18n-verify-keys.py --fix     # Copy zh-CN values as placeholder

Exit code: 0 if keys are in sync, 1 if there are missing keys.
"""
import json
import sys
import os
import argparse

def flatten(d, prefix=''):
    items = {}
    for k, v in d.items():
        full = f'{prefix}.{k}' if prefix else k
        if isinstance(v, dict):
            items.update(flatten(v, full))
        else:
            items[full] = v
    return items

def set_nested(d, key_path, value):
    parts = key_path.split('.')
    current = d
    for part in parts[:-1]:
        if part not in current or not isinstance(current[part], dict):
            current[part] = {}
        current = current[part]
    current[parts[-1]] = value

def main():
    parser = argparse.ArgumentParser(description='Verify i18n key parity between zh-CN and en-US')
    parser.add_argument('--fix', action='store_true', help='Copy zh-CN values as placeholder for missing en-US keys')
    args = parser.parse_args()

    base = os.path.join(os.path.dirname(__file__), '..', 'frontend', 'src', 'locales')
    zh_path = os.path.join(base, 'zh-CN.json')
    en_path = os.path.join(base, 'en-US.json')

    zh = json.load(open(zh_path))
    en = json.load(open(en_path))

    zh_flat = flatten(zh)
    en_flat = flatten(en)

    missing_en = sorted(set(zh_flat) - set(en_flat))
    extra_en = sorted(set(en_flat) - set(zh_flat))

    print(f'zh-CN keys: {len(zh_flat)}')
    print(f'en-US keys: {len(en_flat)}')
    print(f'Missing in en-US: {len(missing_en)}')
    print(f'Extra in en-US:   {len(extra_en)}')

    if missing_en:
        # Group by namespace
        ns = {}
        for k in missing_en:
            prefix = k.split('.')[0] + '.' + k.split('.')[1] if '.' in k else k
            ns[prefix] = ns.get(prefix, 0) + 1
        print('\nMissing by sub-namespace:')
        for k, v in sorted(ns.items()):
            print(f'  {k}.* : {v} keys')

        print('\nFirst 20 missing keys:')
        for k in missing_en[:20]:
            print(f'  - {k} = {zh_flat[k]}')

    if extra_en:
        print('\nExtra en-US keys (not in zh-CN):')
        for k in extra_en[:10]:
            print(f'  + {k}')

    if args.fix and missing_en:
        for key in missing_en:
            set_nested(en, key, zh_flat[key])
        with open(en_path, 'w', encoding='utf-8') as f:
            json.dump(en, f, ensure_ascii=False, indent=2)
            f.write('\n')
        print(f'\n[fix] Copied {len(missing_en)} zh-CN values as en-US placeholders.')
        print('[fix] NOTE: Replace with proper English translations!')

    if missing_en or extra_en:
        sys.exit(1)
    else:
        print('\n✅ zh-CN and en-US keys are in sync.')
        sys.exit(0)

if __name__ == '__main__':
    main()