This commit is contained in:
kaixindelele
2023-06-21 17:58:13 +08:00
parent b24e664a85
commit 78df094eb9
13 changed files with 696 additions and 153 deletions

View File

@ -175,9 +175,8 @@ def merge_tex_files(project_foler, main_file, mode):
main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
# fontset=windows
import platform
if platform.system() != 'Windows':
main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows]{\2}",main_file)
main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows]{\1}",main_file)
main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
# find paper abstract
pattern = re.compile(r'\\begin\{abstract\}.*\n')
match = pattern.search(main_file)
@ -213,6 +212,8 @@ def fix_content(final_tex, node_string):
final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
if "Traceback" in final_tex and "[Local Message]" in final_tex:
final_tex = node_string # 出问题了,还原原文
if node_string.count('\\begin') != final_tex.count('\\begin'):
final_tex = node_string # 出问题了,还原原文
if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
@ -404,7 +405,7 @@ class LatexPaperSplit():
def __init__(self) -> None:
self.nodes = None
self.msg = "{\\scriptsize\\textbf{警告该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成" + \
"版权归原文作者所有。翻译内容可靠性无任何保障,请仔细鉴别并以原文为准。" + \
"版权归原文作者所有。翻译内容可靠性无保障,请仔细鉴别并以原文为准。" + \
"项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
# 请您不要删除或修改这行警告除非您是论文的原作者如果您是论文原作者欢迎加REAME中的QQ联系开发者
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响,禁止移除或修改此警告。}}\\\\"
@ -498,7 +499,32 @@ class LatexPaperFileGroup():
f.write(res)
return manifest
def write_html(sp_file_contents, sp_file_result, chatbot):
# write html
try:
import copy
from .crazy_utils import construct_html
from toolbox import gen_time_str
ch = construct_html()
orig = ""
trans = ""
final = []
for c,r in zip(sp_file_contents, sp_file_result):
final.append(c)
final.append(r)
for i, k in enumerate(final):
if i%2==0:
orig = k
if i%2==1:
trans = k
ch.add_row(a=orig, b=trans)
create_report_file_name = f"{gen_time_str()}.trans.html"
ch.save_file(create_report_file_name)
promote_file_to_downloadzone(file=f'./gpt_log/{create_report_file_name}', chatbot=chatbot)
except:
from toolbox import trimmed_format_exc
print('writing html result failed:', trimmed_format_exc())
def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
import time, os, re
@ -575,6 +601,7 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
pfg.get_token_num = None
objdump(pfg, file=pj(project_folder,'temp.pkl'))
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot)
# <-------- 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']}"
@ -624,7 +651,7 @@ def compile_latex_with_timeout(command, timeout=60):
return False
return True
def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder):
def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
import os, time
current_dir = os.getcwd()
n_fix = 1
@ -635,6 +662,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
while True:
import os
# 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
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
@ -656,15 +684,16 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
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
print( 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')
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')
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
print( 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')
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')
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
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'bibtex merge_diff.aux'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
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
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'bibtex merge_diff.aux'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
# <--------------------->
os.chdir(current_dir)
@ -685,9 +714,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
if os.path.exists(pj(work_folder, '..', 'translation')):
shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
promote_file_to_downloadzone(result_pdf, chatbot=chatbot)
# 我重新指定了参数传入。
# promote_file_to_downloadzone(file=result_pdf, rename_file=None, chatbot=chatbot)
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)
return True # 成功啦
else:
if n_fix>=max_try: break