Merge Frontier, Update to Version 3.72 (#1553)
* Zhipu sdk update 适配最新的智谱SDK，支持GLM4v (#1502) * 适配 google gemini 优化为从用户input中提取文件 * 适配最新的智谱SDK、支持glm-4v * requirements.txt fix * pending history check --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * Update "生成多种Mermaid图表" plugin: Separate out the file reading function (#1520) * Update crazy_functional.py with new functionality deal with PDF * Update crazy_functional.py and Mermaid.py for plugin_kwargs * Update crazy_functional.py with new chart type: mind map * Update SELECT_PROMPT and i_say_show_user messages * Update ArgsReminder message in get_crazy_functions() function * Update with read md file and update PROMPTS * Return the PROMPTS as the test found that the initial version worked best * Update Mermaid chart generation function * version 3.71 * 解决issues #1510 * Remove unnecessary text from sys_prompt in 解析历史输入 function * Remove sys_prompt message in 解析历史输入 function * Update bridge_all.py: supports gpt-4-turbo-preview (#1517) * Update bridge_all.py: supports gpt-4-turbo-preview supports gpt-4-turbo-preview * Update bridge_all.py --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * Update config.py: supports gpt-4-turbo-preview (#1516) * Update config.py: supports gpt-4-turbo-preview supports gpt-4-turbo-preview * Update config.py --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * Refactor 解析历史输入 function to handle file input * Update Mermaid chart generation functionality * rename files and functions --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com> Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * 接入mathpix ocr功能 (#1468) * Update Latex输出PDF结果.py 借助mathpix实现了PDF翻译中文并重新编译PDF * Update config.py add mathpix appid & appkey * Add 'PDF翻译中文并重新编译PDF' feature to plugins. --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * fix zhipuai * check picture * remove glm-4 due to bug * 修改config * 检查MATHPIX_APPID * Remove unnecessary code and update function_plugins dictionary * capture non-standard token overflow * bug fix #1524 * change mermaid style * 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽 (#1530) * 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽 * 微调未果 先stage一下 * update --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * ver 3.72 * change live2d * save the status of ``clear btn` in cookie * 前端选择保持 * js ui bug fix * reset btn bug fix * update live2d tips * fix missing get_token_num method * fix live2d toggle switch * fix persistent custom btn with cookie * fix zhipuai feedback with core functionality * Refactor button update and clean up functions --------- Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com> Co-authored-by: Menghuan1918 <menghuan2003@outlook.com> Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com> Co-authored-by: Hao Ma <893017927@qq.com> Co-authored-by: zeyuan huang <599012428@qq.com>
This commit is contained in:
binary-husky
484
crazy_functions/Latex输出PDF.py
Normal file
484
crazy_functions/Latex输出PDF.py
Normal file
@@ -0,0 +1,484 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time, json, tarfile
|
||||
|
||||
pj = os.path.join
|
||||
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
|
||||
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
- pfg: Proofreader or Translator instance.
|
||||
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
|
||||
|
||||
Returns:
|
||||
- inputs_array: A list of strings containing prompts for users to respond to.
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread_en':
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [
|
||||
r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
|
||||
else:
|
||||
assert False, "未知指令"
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
|
||||
"""
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir) == 0: return project_folder
|
||||
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
|
||||
return project_folder
|
||||
|
||||
|
||||
def move_project(project_folder, arxiv_id=None):
|
||||
"""
|
||||
Create a new work folder and copy the project folder to it.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path of the project.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the new work folder.
|
||||
"""
|
||||
import shutil, time
|
||||
time.sleep(2) # avoid time string conflict
|
||||
if arxiv_id is not None:
|
||||
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
|
||||
else:
|
||||
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
|
||||
try:
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder, '*'))
|
||||
items = [item for item in items if os.path.basename(item) != '__MACOSX']
|
||||
if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
|
||||
if os.path.isdir(items[0]): project_folder = items[0]
|
||||
|
||||
shutil.copytree(src=project_folder, dst=new_workfolder)
|
||||
return new_workfolder
|
||||
|
||||
|
||||
def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
def check_cached_translation_pdf(arxiv_id):
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
|
||||
if not os.path.exists(translation_dir):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
target_file_compare = pj(translation_dir, 'comparison.pdf')
|
||||
if os.path.exists(target_file_compare):
|
||||
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
|
||||
def is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None # 是本地文件，跳过下载
|
||||
|
||||
# <-------------- inspect format ------------->
|
||||
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(1) # 刷新界面
|
||||
|
||||
url_ = txt # https://arxiv.org/abs/1707.06690
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
|
||||
|
||||
url_tar = url_.replace('/abs/', '/e-print/')
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
|
||||
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
|
||||
os.makedirs(translation_dir, exist_ok=True)
|
||||
|
||||
# <-------------- download arxiv source file ------------->
|
||||
dst = pj(translation_dir, arxiv_id + '.tar')
|
||||
if os.path.exists(dst):
|
||||
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
|
||||
else:
|
||||
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
|
||||
proxies = get_conf('proxies')
|
||||
r = requests.get(url_tar, proxies=proxies)
|
||||
with open(dst, 'wb+') as f:
|
||||
f.write(r.content)
|
||||
# <-------------- extract file ------------->
|
||||
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
|
||||
from toolbox import extract_archive
|
||||
extract_archive(file_path=dst, dest_dir=extract_dst)
|
||||
return extract_dst, arxiv_id
|
||||
|
||||
|
||||
def pdf2tex_project(pdf_file_path):
|
||||
# Mathpix API credentials
|
||||
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
|
||||
headers = {"app_id": app_id, "app_key": app_key}
|
||||
|
||||
# Step 1: Send PDF file for processing
|
||||
options = {
|
||||
"conversion_formats": {"tex.zip": True},
|
||||
"math_inline_delimiters": ["$", "$"],
|
||||
"rm_spaces": True
|
||||
}
|
||||
|
||||
response = requests.post(url="https://api.mathpix.com/v3/pdf",
|
||||
headers=headers,
|
||||
data={"options_json": json.dumps(options)},
|
||||
files={"file": open(pdf_file_path, "rb")})
|
||||
|
||||
if response.ok:
|
||||
pdf_id = response.json()["pdf_id"]
|
||||
print(f"PDF processing initiated. PDF ID: {pdf_id}")
|
||||
|
||||
# Step 2: Check processing status
|
||||
while True:
|
||||
conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
|
||||
conversion_data = conversion_response.json()
|
||||
|
||||
if conversion_data["status"] == "completed":
|
||||
print("PDF processing completed.")
|
||||
break
|
||||
elif conversion_data["status"] == "error":
|
||||
print("Error occurred during processing.")
|
||||
else:
|
||||
print(f"Processing status: {conversion_data['status']}")
|
||||
time.sleep(5) # wait for a few seconds before checking again
|
||||
|
||||
# Step 3: Save results to local files
|
||||
output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
|
||||
if not os.path.exists(output_dir):
|
||||
os.makedirs(output_dir)
|
||||
|
||||
url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
|
||||
response = requests.get(url, headers=headers)
|
||||
file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
|
||||
output_name = f"{file_name_wo_dot}.tex.zip"
|
||||
output_path = os.path.join(output_dir, output_name)
|
||||
with open(output_path, "wb") as output_file:
|
||||
output_file.write(response.content)
|
||||
print(f"tex.zip file saved at: {output_path}")
|
||||
|
||||
import zipfile
|
||||
unzip_dir = os.path.join(output_dir, file_name_wo_dot)
|
||||
with zipfile.ZipFile(output_path, 'r') as zip_ref:
|
||||
zip_ref.extractall(unzip_dir)
|
||||
|
||||
return unzip_dir
|
||||
|
||||
else:
|
||||
print(f"Error sending PDF for processing. Status code: {response.status_code}")
|
||||
return None
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append(["函数插件功能？",
|
||||
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(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
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id=None)
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='proofread_en',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_proofread_en',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
try:
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
except tarfile.ReadError as e:
|
||||
yield from update_ui_lastest_msg(
|
||||
"无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
|
||||
chatbot=chatbot, history=history)
|
||||
return
|
||||
|
||||
if txt.endswith('.pdf'):
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id)
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.pdf文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
if len(file_manifest) != 1:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
|
||||
if len(app_id) == 0 or len(app_key) == 0:
|
||||
report_exception(chatbot, history, a=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- convert pdf into tex ------------->
|
||||
project_folder = pdf2tex_project(file_manifest[0])
|
||||
|
||||
# Translate English Latex to Chinese Latex, and compile it
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder)
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
@@ -1,313 +0,0 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time, tarfile
|
||||
pj = os.path.join
|
||||
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
|
||||
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
- pfg: Proofreader or Translator instance.
|
||||
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
|
||||
|
||||
Returns:
|
||||
- inputs_array: A list of strings containing prompts for users to respond to.
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread_en':
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
|
||||
else:
|
||||
assert False, "未知指令"
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
|
||||
"""
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir) == 0: return project_folder
|
||||
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
|
||||
return project_folder
|
||||
|
||||
def move_project(project_folder, arxiv_id=None):
|
||||
"""
|
||||
Create a new work folder and copy the project folder to it.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path of the project.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the new work folder.
|
||||
"""
|
||||
import shutil, time
|
||||
time.sleep(2) # avoid time string conflict
|
||||
if arxiv_id is not None:
|
||||
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
|
||||
else:
|
||||
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
|
||||
try:
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder,'*'))
|
||||
items = [item for item in items if os.path.basename(item)!='__MACOSX']
|
||||
if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
|
||||
if os.path.isdir(items[0]): project_folder = items[0]
|
||||
|
||||
shutil.copytree(src=project_folder, dst=new_workfolder)
|
||||
return new_workfolder
|
||||
|
||||
def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
def check_cached_translation_pdf(arxiv_id):
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
|
||||
if not os.path.exists(translation_dir):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
target_file_compare = pj(translation_dir, 'comparison.pdf')
|
||||
if os.path.exists(target_file_compare):
|
||||
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
def is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None # 是本地文件，跳过下载
|
||||
|
||||
# <-------------- inspect format ------------->
|
||||
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(1) # 刷新界面
|
||||
|
||||
url_ = txt # https://arxiv.org/abs/1707.06690
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
|
||||
|
||||
url_tar = url_.replace('/abs/', '/e-print/')
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
|
||||
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
|
||||
os.makedirs(translation_dir, exist_ok=True)
|
||||
|
||||
# <-------------- download arxiv source file ------------->
|
||||
dst = pj(translation_dir, arxiv_id+'.tar')
|
||||
if os.path.exists(dst):
|
||||
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
|
||||
else:
|
||||
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
|
||||
proxies = get_conf('proxies')
|
||||
r = requests.get(url_tar, proxies=proxies)
|
||||
with open(dst, 'wb+') as f:
|
||||
f.write(r.content)
|
||||
# <-------------- extract file ------------->
|
||||
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
|
||||
from toolbox import extract_archive
|
||||
extract_archive(file_path=dst, dest_dir=extract_dst)
|
||||
return extract_dst, arxiv_id
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([ "函数插件功能？",
|
||||
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(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
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id=None)
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
try:
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
except tarfile.ReadError as e:
|
||||
yield from update_ui_lastest_msg(
|
||||
"无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
|
||||
chatbot=chatbot, history=history)
|
||||
return
|
||||
|
||||
if txt.endswith('.pdf'):
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id)
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
85
crazy_functions/pdf_fns/parse_word.py
Normal file
85
crazy_functions/pdf_fns/parse_word.py
Normal file
@@ -0,0 +1,85 @@
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
|
||||
import os
|
||||
import re
|
||||
def extract_text_from_files(txt, chatbot, history):
|
||||
"""
|
||||
查找pdf/md/word并获取文本内容并返回状态以及文本
|
||||
|
||||
输入参数 Args:
|
||||
chatbot: chatbot inputs and outputs （用户界面对话窗口句柄，用于数据流可视化）
|
||||
history (list): List of chat history （历史，对话历史列表）
|
||||
|
||||
输出 Returns:
|
||||
文件是否存在(bool)
|
||||
final_result(list):文本内容
|
||||
page_one(list):第一页内容/摘要
|
||||
file_manifest(list):文件路径
|
||||
excption(string):需要用户手动处理的信息,如没出错则保持为空
|
||||
"""
|
||||
|
||||
final_result = []
|
||||
page_one = []
|
||||
file_manifest = []
|
||||
excption = ""
|
||||
|
||||
if txt == "":
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
#查找输入区内容中的文件
|
||||
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
|
||||
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
|
||||
file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
|
||||
file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
|
||||
|
||||
if file_doc:
|
||||
excption = "word"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
|
||||
file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
|
||||
if file_num == 0:
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
if file_pdf:
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
import fitz
|
||||
except:
|
||||
excption = "pdf"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(pdf_manifest):
|
||||
file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
final_result.append(file_content)
|
||||
page_one.append(pdf_one)
|
||||
file_manifest.append(os.path.relpath(fp, folder_pdf))
|
||||
|
||||
if file_md:
|
||||
for index, fp in enumerate(md_manifest):
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_content = f.read()
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE) #接下来提取md中的一级/二级标题作为摘要
|
||||
if len(headers) > 0:
|
||||
page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
|
||||
else:
|
||||
page_one.append("")
|
||||
final_result.append(file_content)
|
||||
file_manifest.append(os.path.relpath(fp, folder_md))
|
||||
|
||||
if file_word:
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
from docx import Document
|
||||
except:
|
||||
excption = "word_pip"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(word_manifest):
|
||||
doc = Document(fp)
|
||||
file_content = '\n'.join([p.text for p in doc.paragraphs])
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
page_one.append(file_content[:200])
|
||||
final_result.append(file_content)
|
||||
file_manifest.append(os.path.relpath(fp, folder_word))
|
||||
|
||||
return True, final_result, page_one, file_manifest, excption
|
||||
@@ -1,6 +1,5 @@
|
||||
from toolbox import CatchException, update_ui, report_exception
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import read_and_clean_pdf_text
|
||||
import datetime
|
||||
|
||||
#以下是每类图表的PROMPT
|
||||
@@ -162,7 +161,7 @@ mindmap
|
||||
```
|
||||
"""
|
||||
|
||||
def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
|
||||
def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
|
||||
############################## <第 0 步，切割输入> ##################################
|
||||
# 借用PDF切割中的函数对文本进行切割
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
@@ -170,8 +169,6 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
|
||||
############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
|
||||
i_say_show_user = f'首先你从历史记录或文件中提取摘要。'; gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
results = []
|
||||
MAX_WORD_TOTAL = 4096
|
||||
n_txt = len(txt)
|
||||
@@ -179,7 +176,7 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
|
||||
if n_txt >= 20: print('文章极长，不能达到预期效果')
|
||||
for i in range(n_txt):
|
||||
NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i]}"
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
|
||||
i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
|
||||
llm_kwargs, chatbot,
|
||||
@@ -232,34 +229,10 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="你精通使用mermaid语法来绘制图表,首先确保语法正确,其次避免在mermaid语法中使用不允许的字符,此外也应当分考虑图表的可读性。"
|
||||
sys_prompt=""
|
||||
)
|
||||
history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
def 输入区文件处理(txt):
|
||||
if txt == "": return False, txt
|
||||
success = True
|
||||
import glob
|
||||
from .crazy_utils import get_files_from_everything
|
||||
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
|
||||
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
|
||||
if len(pdf_manifest) == 0 and len(md_manifest) == 0:
|
||||
return False, txt #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
final_result = ""
|
||||
if file_pdf:
|
||||
for index, fp in enumerate(pdf_manifest):
|
||||
file_content, page_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
final_result += "\n" + file_content
|
||||
if file_md:
|
||||
for index, fp in enumerate(md_manifest):
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_content = f.read()
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
final_result += "\n" + file_content
|
||||
return True, final_result
|
||||
|
||||
@CatchException
|
||||
def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
@@ -277,26 +250,47 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"根据当前聊天历史或文件中(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
|
||||
"根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
|
||||
\n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
|
||||
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 fitz
|
||||
except:
|
||||
report_exception(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 pymupdf```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
if os.path.exists(txt): #如输入区无内容则直接解析历史记录
|
||||
file_exist, txt = 输入区文件处理(txt)
|
||||
from crazy_functions.pdf_fns.parse_word import extract_text_from_files
|
||||
file_exist, final_result, page_one, file_manifest, excption = extract_text_from_files(txt, chatbot, history)
|
||||
else:
|
||||
file_exist = False
|
||||
excption = ""
|
||||
file_manifest = []
|
||||
|
||||
if file_exist : history = [] #如输入区内容为文件则清空历史记录
|
||||
history.append(txt) #将解析后的txt传递加入到历史中
|
||||
|
||||
yield from 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs)
|
||||
if excption != "":
|
||||
if excption == "word":
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
b = f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。")
|
||||
|
||||
elif excption == "pdf":
|
||||
report_exception(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 pymupdf```。")
|
||||
|
||||
elif excption == "word_pip":
|
||||
report_exception(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 python-docx pywin32```。")
|
||||
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
else:
|
||||
if not file_exist:
|
||||
history.append(txt) #如输入区不是文件则将输入区内容加入历史记录
|
||||
i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
|
||||
else:
|
||||
file_num = len(file_manifest)
|
||||
for i in range(file_num): #依次处理文件
|
||||
i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
history = [] #如输入区内容为文件则清空历史记录
|
||||
history.append(final_result[i])
|
||||
yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
|
||||
Reference in New Issue
Block a user