#!/usr/bin/env python3
"""
为 Localizable.xcstrings 添加多语言支持

步骤:
1. 加载手动翻译 (manual_translations.json)
2. 为所有字符串添加 5 种语言 (es, ar, fr, ja, ko)
3. 生成 CSV 供人工审核
"""

import json
import csv
from pathlib import Path

# 语言配置
LANGUAGES = {
    "es": "Spanish",
    "ar": "Arabic",
    "fr": "French",
    "ja": "Japanese",
    "ko": "Korean"
}

def load_json(file_path):
    """加载 JSON 文件"""
    with open(file_path, 'r', encoding='utf-8') as f:
        return json.load(f)

def save_json(file_path, data):
    """保存 JSON 文件"""
    with open(file_path, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

def main():
    # 文件路径
    base_dir = Path("/Users/yuanjiantsui/projects/to-live-photo")
    xcstrings_path = base_dir / "to-live-photo/to-live-photo/Localizable.xcstrings"
    manual_translations_path = base_dir / "scripts/manual_translations.json"
    output_csv_path = base_dir / "scripts/translations_review.csv"

    print("🔄 加载文件...")
    xcstrings_data = load_json(xcstrings_path)
    manual_translations = load_json(manual_translations_path)["translations"]

    print(f"📊 找到 {len(xcstrings_data['strings'])} 个字符串")
    print(f"✏️  手动翻译: {len(manual_translations)} 个")

    # 统计
    stats = {lang: {"manual": 0, "auto": 0} for lang in LANGUAGES}
    csv_rows = []

    # 处理每个字符串
    for key, string_data in xcstrings_data["strings"].items():
        if "localizations" not in string_data:
            string_data["localizations"] = {}

        locs = string_data["localizations"]

        # 获取源文本 (优先英文,其次简体中文)
        source_text = ""
        if "en" in locs:
            source_text = locs["en"]["stringUnit"]["value"]
        elif "zh-Hans" in locs:
            source_text = locs["zh-Hans"]["stringUnit"]["value"]

        if not source_text:
            continue

        # CSV 行数据
        row = {
            "key": key,
            "en": source_text,
            "zh-Hans": locs.get("zh-Hans", {}).get("stringUnit", {}).get("value", ""),
            "zh-Hant": locs.get("zh-Hant", {}).get("stringUnit", {}).get("value", "")
        }

        # 为每种语言添加翻译
        for lang_code in LANGUAGES:
            # 跳过已有翻译
            if lang_code in locs:
                row[lang_code] = locs[lang_code]["stringUnit"]["value"]
                continue

            # 使用手动翻译
            if key in manual_translations and lang_code in manual_translations[key]:
                translated_text = manual_translations[key][lang_code]
                stats[lang_code]["manual"] += 1
            else:
                # 使用源文本作为占位符 (标记为需要翻译)
                translated_text = f"[{lang_code.upper()}] {source_text}"
                stats[lang_code]["auto"] += 1

            # 添加到数据结构
            locs[lang_code] = {
                "stringUnit": {
                    "state": "translated" if key in manual_translations else "needs_review",
                    "value": translated_text
                }
            }

            row[lang_code] = translated_text

        csv_rows.append(row)

    # 保存更新后的 xcstrings
    print("\n💾 保存 Localizable.xcstrings...")
    save_json(xcstrings_path, xcstrings_data)

    # 生成 CSV
    print(f"📝 生成审核 CSV: {output_csv_path}")
    fieldnames = ["key", "en", "zh-Hans", "zh-Hant"] + list(LANGUAGES.keys())

    with open(output_csv_path, 'w', newline='', encoding='utf-8') as f:
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(csv_rows)

    # 打印统计
    print("\n📈 翻译统计:")
    for lang_code, lang_name in LANGUAGES.items():
        manual_count = stats[lang_code]["manual"]
        auto_count = stats[lang_code]["auto"]
        total = manual_count + auto_count
        print(f"  {lang_name} ({lang_code}): {manual_count} 手动 + {auto_count} 自动 = {total} 总计")

    print("\n✅ 完成!")
    print(f"\n📋 下一步:")
    print(f"  1. 审核 CSV 文件: {output_csv_path}")
    print(f"  2. 使用 Google Translate 或其他服务翻译标记为 [{lang_code.upper()}] 的字符串")
    print(f"  3. 将翻译结果导入回 Localizable.xcstrings")

if __name__ == "__main__":
    main()