src/translator.py

"""
邮件翻译模块 - 调用 LLM 自动识别语言并翻译为指定目标语言
支持：
  - 自动语言检测（通过 LLM 判断）
  - 翻译为英文或中文
  - 保留邮件格式（换行、段落）
"""

import json
import logging
import asyncio
from typing import Optional

from openai import AsyncOpenAI, OpenAI

from src import config as cfg

logger = logging.getLogger(__name__)


# ─── 系统提示词 ───

TRANSLATE_SYSTEM_PROMPT = """You are a professional email translator.
Your task is to translate recruitment-related emails accurately.

Rules:
1. Detect the source language automatically from the email content.
2. Translate the email body to the target language naturally and accurately.
3. Preserve formatting: line breaks, paragraphs, bullet points.
4. Keep company names, proper nouns, and technical terms intact (don't translate names).
5. Maintain the original tone (formal/informal) appropriate for recruitment context.
6. If the email is already in the target language, return it unchanged.

You MUST respond with valid JSON only:
{
  "source_language": "<detected language name, e.g. 'English', 'Chinese', 'French'>",
  "source_language_code": "<ISO 639-1 code, e.g. 'en', 'zh', 'fr'>",
  "translated_text": "<translated email body>",
  "is_already_target": <true if already in target language>
}
"""

# ─── 数据类 ───

class TranslationResult:
    def __init__(
        self,
        source_language: str = "",
        source_language_code: str = "",
        translated_text: str = "",
        is_already_target: bool = False,
        error: str = "",
    ):
        self.source_language = source_language
        self.source_language_code = source_language_code
        self.translated_text = translated_text
        self.is_already_target = is_already_target
        self.error = error

    @property
    def is_valid(self) -> bool:
        return not self.error and bool(self.translated_text)


# ─── 核心函数 ───

def _build_translate_prompt(text: str, target_language: str) -> str:
    return f"""Translate the following email to {target_language}.

Email Body:
{text}

Return the translation in the required JSON format."""


def _parse_translate_response(content: str) -> TranslationResult:
    """解析 LLM 翻译响应"""
    content = content.strip()
    # 去除 markdown 代码块
    if content.startswith("```"):
        lines = content.split("\n")
        content = "\n".join(
            lines[1:-1] if lines[-1].strip() == "```" else lines[1:]
        )
    content = content.strip()

    try:
        data = json.loads(content)
    except json.JSONDecodeError as e:
        logger.error(f"翻译响应 JSON 解析失败: {e}\n原始内容: {content[:200]}")
        # 降级：把整个内容当译文
        return TranslationResult(
            source_language="Unknown",
            source_language_code="unknown",
            translated_text=content[:2000],
            error=f"JSON 解析失败，已截断展示: {e}",
        )

    return TranslationResult(
        source_language=data.get("source_language", "Unknown"),
        source_language_code=data.get("source_language_code", "unknown"),
        translated_text=data.get("translated_text", content[:2000]),
        is_already_target=data.get("is_already_target", False),
    )


async def translate_email_async(
    text: str,
    target_language: str = "English",
) -> TranslationResult:
    """
    异步翻译邮件正文
    :param text: 邮件正文
    :param target_language: 目标语言（如 "English" 或 "Chinese"）
    """
    if not text or not text.strip():
        return TranslationResult(error="邮件正文为空，无需翻译")

    api_key = cfg.get_llm_api_key()
    if not api_key:
        return TranslationResult(error="未配置 LLM API Key，无法翻译")

    try:
        model = cfg.get_llm_model()
        base_url = cfg.get_llm_base_url()

        client_kwargs = {"api_key": api_key}
        if base_url:
            client_kwargs["base_url"] = base_url

        client = AsyncOpenAI(**client_kwargs)
        user_prompt = _build_translate_prompt(text[:4000], target_language)

        logger.info(f"正在翻译邮件至 {target_language}...")

        response = await client.chat.completions.create(
            model=model,
            messages=[
                {"role": "system", "content": TRANSLATE_SYSTEM_PROMPT},
                {"role": "user", "content": user_prompt},
            ],
            temperature=0.1,
            max_tokens=2048,
            response_format={"type": "json_object"},
        )

        content = response.choices[0].message.content or ""
        result = _parse_translate_response(content)
        logger.info(
            f"翻译完成: {result.source_language} -> {target_language}"
            f" (已是目标语言: {result.is_already_target})"
        )
        return result

    except Exception as e:
        logger.error(f"翻译失败: {e}", exc_info=True)
        return TranslationResult(error=f"翻译失败: {str(e)[:120]}")


def translate_email_sync(
    text: str,
    target_language: str = "English",
) -> TranslationResult:
    """同步版本"""
    try:
        loop = asyncio.get_event_loop()
        if loop.is_running():
            import concurrent.futures
            with concurrent.futures.ThreadPoolExecutor() as pool:
                future = pool.submit(
                    asyncio.run,
                    translate_email_async(text, target_language),
                )
                return future.result(timeout=60)
        else:
            return loop.run_until_complete(
                translate_email_async(text, target_language)
            )
    except RuntimeError:
        return asyncio.run(translate_email_async(text, target_language))