int/gpt_academic
1
0
派生 0
镜像自地址 https://github.com/binary-husky/gpt_academic.git 已同步 2025-12-06 22:46:48 +00:00
代码 工单 软件包 项目 版本发布 百科 动态

typo: Fix typos and rename functions across multiple files (#2130)

浏览代码 
* typo: Fix typos and rename functions across multiple files

This commit addresses several minor issues:
- Corrected spelling of function names (e.g., `update_ui_lastest_msg` to `update_ui_latest_msg`)
- Fixed typos in comments and variable names
- Corrected capitalization in some strings (e.g., "ArXiv" instead of "Arixv")
- Renamed some variables for consistency
- Corrected some console-related parameter names (e.g., `console_slience` to `console_silence`)

The changes span multiple files across the project, including request LLM bridges, crazy functions, and utility modules.

* fix: f-string expression part cannot include a backslash (#2139)

* raise error when the uploaded tar contain hard/soft link (#2136)

* minor bug fix

* fine tune reasoning css

* upgrade internet gpt plugin

* Update README.md

* fix GHSA-gqp5-wm97-qxcv

* typo fix

* update readme

---------

Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>
Co-authored-by: binary-husky <qingxu.fu@outlook.com>
这个提交包含在：
Steven Moder
2025-03-02 02:16:10 +08:00
提交者 GitHub
父节点 5dffe8627f
当前提交 4a79aa6a93
共有 74 个文件被更改，包括 325 次插入 和 325 次删除
下载 Patch 文件 下载 Diff 文件 展开所有文件 折叠所有文件

30
crazy_functions/latex_fns/latex_actions.py
查看文件

@@ -3,7 +3,7 @@ import re
import shutil
import numpy as np
from loguru import logger
from toolbox import update_ui, update_ui_lastest_msg, get_log_folder, gen_time_str
from toolbox import update_ui, update_ui_latest_msg, get_log_folder, gen_time_str
from toolbox import get_conf, promote_file_to_downloadzone
from crazy_functions.latex_fns.latex_toolbox import PRESERVE, TRANSFORM
from crazy_functions.latex_fns.latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
@@ -20,7 +20,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
"""
break down latex file to a linked list,
each node use a preserve flag to indicate whether it should
be proccessed by GPT.
be processed by GPT.
"""
text = txt
mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
@@ -85,14 +85,14 @@ class LatexPaperSplit():
"""
break down latex file to a linked list,
each node use a preserve flag to indicate whether it should
be proccessed by GPT.
be processed by GPT.
"""
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）
# 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README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。}}\\\\"
self.title = "unknown"
self.abstract = "unknown"
@@ -151,7 +151,7 @@ class LatexPaperSplit():
"""
break down latex file to a linked list,
each node use a preserve flag to indicate whether it should
be proccessed by GPT.
be processed by GPT.
P.S. use multiprocessing to avoid timeout error
"""
import multiprocessing
@@ -351,7 +351,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
max_try = 32
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
yield from update_ui_latest_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:
@@ -396,32 +396,32 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
shutil.copyfile(may_exist_bbl, target_bbl)
# 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
yield from update_ui_latest_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(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
yield from update_ui_latest_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(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
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
ok = compile_latex_with_timeout(f'bibtex {main_file_original}.aux', work_folder_original)
if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
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
yield from update_ui_latest_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(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
yield from update_ui_latest_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
logger.info( 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', 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
yield from update_ui_latest_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(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(get_compile_command(compiler, 'merge_diff'), work_folder)
@@ -435,13 +435,13 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
yield from update_ui_latest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
if diff_pdf_success:
result_pdf = pj(work_folder_modified, f'merge_diff.pdf') # get pdf path
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
if modified_pdf_success:
yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history) # 刷新Gradio前端界面
yield from update_ui_latest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history) # 刷新Gradio前端界面
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
if os.path.exists(pj(work_folder, '..', 'translation')):
@@ -472,7 +472,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
work_folder_modified=work_folder_modified,
fixed_line=fixed_line
)
yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history) # 刷新Gradio前端界面
yield from update_ui_latest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history) # 刷新Gradio前端界面
if not can_retry: break
return False # 失败啦

36
crazy_functions/latex_fns/latex_toolbox.py
查看文件

@@ -168,7 +168,7 @@ def set_forbidden_text(text, mask, pattern, flags=0):
def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
"""
Move area out of preserve area (make text editable for GPT)
count the number of the braces so as to catch compelete text area.
count the number of the braces so as to catch complete text area.
e.g.
\begin{abstract} blablablablablabla. \end{abstract}
"""
@@ -188,7 +188,7 @@ def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
"""
Add a preserve text area in this paper (text become untouchable for GPT).
count the number of the braces so as to catch compelete text area.
count the number of the braces so as to catch complete text area.
e.g.
\caption{blablablablabla\texbf{blablabla}blablabla.}
"""
@@ -214,7 +214,7 @@ def reverse_forbidden_text_careful_brace(
):
"""
Move area out of preserve area (make text editable for GPT)
count the number of the braces so as to catch compelete text area.
count the number of the braces so as to catch complete text area.
e.g.
\caption{blablablablabla\texbf{blablabla}blablabla.}
"""
@@ -287,23 +287,23 @@ def find_main_tex_file(file_manifest, mode):
在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
"""
canidates = []
candidates = []
for texf in file_manifest:
if os.path.basename(texf).startswith("merge"):
continue
with open(texf, "r", encoding="utf8", errors="ignore") as f:
file_content = f.read()
if r"\documentclass" in file_content:
canidates.append(texf)
candidates.append(texf)
else:
continue
if len(canidates) == 0:
if len(candidates) == 0:
raise RuntimeError("无法找到一个主Tex文件（包含documentclass关键字）")
elif len(canidates) == 1:
return canidates[0]
else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
canidates_score = []
elif len(candidates) == 1:
return candidates[0]
else: # if len(candidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
candidates_score = []
# 给出一些判定模板文档的词作为扣分项
unexpected_words = [
"\\LaTeX",
@@ -316,19 +316,19 @@ def find_main_tex_file(file_manifest, mode):
"reviewers",
]
expected_words = ["\\input", "\\ref", "\\cite"]
for texf in canidates:
canidates_score.append(0)
for texf in candidates:
candidates_score.append(0)
with open(texf, "r", encoding="utf8", errors="ignore") as f:
file_content = f.read()
file_content = rm_comments(file_content)
for uw in unexpected_words:
if uw in file_content:
canidates_score[-1] -= 1
candidates_score[-1] -= 1
for uw in expected_words:
if uw in file_content:
canidates_score[-1] += 1
select = np.argmax(canidates_score) # 取评分最高者返回
return canidates[select]
candidates_score[-1] += 1
select = np.argmax(candidates_score) # 取评分最高者返回
return candidates[select]
def rm_comments(main_file):
@@ -374,7 +374,7 @@ def find_tex_file_ignore_case(fp):
def merge_tex_files_(project_foler, main_file, mode):
"""
Merge Tex project recrusively
Merge Tex project recursively
"""
main_file = rm_comments(main_file)
for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
@@ -429,7 +429,7 @@ def find_title_and_abs(main_file):
def merge_tex_files(project_foler, main_file, mode):
"""
Merge Tex project recrusively
Merge Tex project recursively
P.S. 顺便把CTEX塞进去以支持中文
P.S. 顺便把Latex的注释去除
"""