CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

改进Doc2X请求，并增加xelatex编译的支持 (#2058)

Browse Source 
* doc2x请求函数格式清理

* 更新中间部分

* 添加doc2x超时设置并添加对xelatex编译的支持

* Bug修复以及增加对xelatex安装的检测

* 增强弱网环境下的稳定性

* 修复模型中_无法显示的问题

* add xelatex logs

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>
This commit is contained in:
Menghuan
2024-12-07 23:23:59 +08:00
committed by GitHub
parent 7bf094b6b6
commit e3f84069ee
4 changed files with 246 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
crazy_functions/latex_fns/latex_actions.py
View File

@@ -300,7 +300,8 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
# <-------- 写出文件 ---------->
msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
model_name = llm_kwargs['llm_model'].replace('_', '\\_') # 替换LLM模型名称中的下划线为转义字符
msg = f"当前大语言模型: {model_name}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
final_tex = lps.merge_result(pfg.file_result, mode, msg)
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
@@ -351,6 +352,41 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
yield from update_ui_lastest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面
# 检查是否需要使用xelatex
def check_if_need_xelatex(tex_path):
try:
with open(tex_path, 'r', encoding='utf-8', errors='replace') as f:
content = f.read(5000)
# 检查是否有使用xelatex的宏包
need_xelatex = any(
pkg in content
for pkg in ['fontspec', 'xeCJK', 'xetex', 'unicode-math', 'xltxtra', 'xunicode']
)
if need_xelatex:
logger.info(f"检测到宏包需要xelatex编译, 切换至xelatex编译")
else:
logger.info(f"未检测到宏包需要xelatex编译, 使用pdflatex编译")
return need_xelatex
except Exception:
return False
# 根据编译器类型返回编译命令
def get_compile_command(compiler, filename):
compile_command = f'{compiler} -interaction=batchmode -file-line-error {filename}.tex'
logger.info('Latex 编译指令: ', compile_command)
return compile_command
# 确定使用的编译器
compiler = 'pdflatex'
if check_if_need_xelatex(pj(work_folder_modified, f'{main_file_modified}.tex')):
logger.info("检测到宏包需要xelatex编译，切换至xelatex编译")
# Check if xelatex is installed
try:
import subprocess
subprocess.run(['xelatex', '--version'], capture_output=True, check=True)
compiler = 'xelatex'
except (subprocess.CalledProcessError, FileNotFoundError):
raise RuntimeError("检测到需要使用xelatex编译，但系统中未安装xelatex。请先安装texlive或其他提供xelatex的LaTeX发行版。")
while True:
import os
@@ -361,10 +397,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
# https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history) # 刷新Gradio前端界面
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
# 只有第二步成功，才能继续下面的步骤
@@ -375,10 +411,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux', work_folder_modified)
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history) # 刷新Gradio前端界面
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
if mode!='translate_zh':
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
@@ -386,10 +422,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history) # 刷新Gradio前端界面
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
ok = compile_latex_with_timeout(f'bibtex merge_diff.aux', work_folder)
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
# <---------- 检查结果 ----------->
results_ = ""