excel_tool/pdfzh_translator.py

# 改编自： https://github.com/Byaidu/PDFMathTranslate/blob/main/pdf2zh/translator.py
import html
import logging
import os
import re
from json import dumps, loads
from dotenv import load_dotenv

import openai
import requests

# Load environment variables
load_dotenv()

class BaseTranslator:
    def __init__(self, service, lang_out, lang_in, model):
        self.service = service
        self.lang_out = lang_out
        self.lang_in = lang_in
        self.model = model

    def translate(self, text) -> str: ...  # noqa: E704

    def __str__(self):
        return f"{self.service} {self.lang_out} {self.lang_in}"


class GoogleTranslator(BaseTranslator):
    def __init__(self, service, lang_out, lang_in, model):
        lang_out = "zh-CN" if lang_out == "auto" else lang_out
        lang_in = "en" if lang_in == "auto" else lang_in
        super().__init__(service, lang_out, lang_in, model)
        self.session = requests.Session()
        self.base_link = "http://translate.google.com/m"
        self.headers = {
            "User-Agent": "Mozilla/4.0 (compatible;MSIE 6.0;Windows NT 5.1;SV1;.NET CLR 1.1.4322;.NET CLR 2.0.50727;.NET CLR 3.0.04506.30)"  # noqa: E501
        }

    def translate(self, text):
        text = text[:5000]  # google translate max length
        response = self.session.get(
            self.base_link,
            params={"tl": self.lang_out, "sl": self.lang_in, "q": text},
            headers=self.headers,
        )
        re_result = re.findall(
            r'(?s)class="(?:t0|result-container)">(.*?)<', response.text
        )
        if response.status_code == 400:
            result = "IRREPARABLE TRANSLATION ERROR"
        elif len(re_result) == 0:
            raise ValueError("Empty translation result")
        else:
            result = html.unescape(re_result[0])
        return result


class OpenAITranslator(BaseTranslator):
    def __init__(self, service, lang_out, lang_in, model):
        lang_out = "zh-CN" if lang_out == "auto" else lang_out
        lang_in = "en" if lang_in == "auto" else lang_in
        super().__init__(service, lang_out, lang_in, model)
        self.options = {"temperature": 0}  # 随机采样可能会打断公式标记
        # Configure OpenAI client with environment variables
        self.client = openai.OpenAI(
            api_key=os.getenv('OPENAI_API_KEY')
        )

    def translate(self, text) -> str:
        response = self.client.chat.completions.create(
            model=os.getenv('LLM_MODEL', self.model),  # Use env var or fallback to default
            **self.options,
            messages=[
                {
                    "role": "system",
                    "content": "You are a professional,authentic machine translation engine.",
                },
                {
                    "role": "user",
                    "content": f"Translate the following markdown source text to {self.lang_out}. Keep the formula notation $v*$ unchanged. Output translation directly without any additional text.\nSource Text: {text}\nTranslated Text:",  # noqa: E501
                },
            ],
        )
        return response.choices[0].message.content.strip()