gpt-academic / crazy_functions /批量Markdown翻译.py
qingxu99's picture
Markdown翻译支持github url
5eea959
raw
history blame
8.24 kB
from toolbox import update_ui
from toolbox import CatchException, report_execption, write_results_to_file
fast_debug = False
class PaperFileGroup():
def __init__(self):
self.file_paths = []
self.file_contents = []
self.sp_file_contents = []
self.sp_file_index = []
self.sp_file_tag = []
# count_token
from request_llm.bridge_all import model_info
enc = model_info["gpt-3.5-turbo"]['tokenizer']
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
self.get_token_num = get_token_num
def run_file_split(self, max_token_limit=1900):
"""
将长文本分离开来
"""
for index, file_content in enumerate(self.file_contents):
if self.get_token_num(file_content) < max_token_limit:
self.sp_file_contents.append(file_content)
self.sp_file_index.append(index)
self.sp_file_tag.append(self.file_paths[index])
else:
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
for j, segment in enumerate(segments):
self.sp_file_contents.append(segment)
self.sp_file_index.append(index)
self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.md")
print('Segmentation: done')
def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
import time, os, re
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
# <-------- 读取Markdown文件,删除其中的所有注释 ---------->
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
# 记录删除注释后的文本
pfg.file_paths.append(fp)
pfg.file_contents.append(file_content)
# <-------- 拆分过长的Markdown文件 ---------->
pfg.run_file_split(max_token_limit=1500)
n_split = len(pfg.sp_file_contents)
# <-------- 多线程润色开始 ---------->
if language == 'en->zh':
inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
elif language == 'zh->en':
inputs_array = [f"This is a Markdown file, translate it into English, do not modify any existing Markdown commands:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array=inputs_array,
inputs_show_user_array=inputs_show_user_array,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
history_array=[[""] for _ in range(n_split)],
sys_prompt_array=sys_prompt_array,
# max_workers=5, # OpenAI所允许的最大并行过载
scroller_max_len = 80
)
# <-------- 整理结果,退出 ---------->
create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
res = write_results_to_file(gpt_response_collection, file_name=create_report_file_name)
history = gpt_response_collection
chatbot.append((f"{fp}完成了吗?", res))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@CatchException
def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
# 基本信息:功能、贡献者
chatbot.append([
"函数插件功能?",
"对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 尝试导入依赖,如果缺少依赖,则给出安装建议
try:
import tiktoken
import glob, os
except:
report_execption(chatbot, history,
a=f"解析项目: {txt}",
b=f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade tiktoken```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
history = [] # 清空历史,以免输入溢出
if txt.startswith('http'):
# 网络的远程文件
txt = txt.replace("https://github.com/", "https://raw.githubusercontent.com/")
txt = txt.replace("/blob/", "/")
import requests
from toolbox import get_conf
proxies, = get_conf('proxies')
r = requests.get(txt, proxies=proxies)
with open('./gpt_log/temp.md', 'wb+') as f: f.write(r.content)
project_folder = './gpt_log/'
file_manifest = ['./gpt_log/temp.md']
elif txt.endswith('.md'):
# 直接给定文件
file_manifest = [txt]
project_folder = os.path.dirname(txt)
elif os.path.exists(txt):
# 本地路径,递归搜索
project_folder = txt
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.md', recursive=True)]
else:
# 什么都没有
if txt == "": txt = '空空如也的输入栏'
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if len(file_manifest) == 0:
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en->zh')
@CatchException
def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
# 基本信息:功能、贡献者
chatbot.append([
"函数插件功能?",
"对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 尝试导入依赖,如果缺少依赖,则给出安装建议
try:
import tiktoken
except:
report_execption(chatbot, history,
a=f"解析项目: {txt}",
b=f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade tiktoken```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
history = [] # 清空历史,以免输入溢出
import glob, os
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if txt.endswith('.md'):
file_manifest = [txt]
else:
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.md', recursive=True)]
if len(file_manifest) == 0:
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh->en')