合并master
This commit is contained in:
w_xiaolizu
@ -19,9 +19,9 @@ def switch_prompt(pfg, mode, more_requirement):
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread':
|
||||
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. " +
|
||||
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)]
|
||||
@ -70,6 +70,12 @@ def move_project(project_folder, arxiv_id=None):
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder,'*'))
|
||||
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
|
||||
|
||||
@ -90,7 +96,7 @@ def arxiv_download(chatbot, history, txt):
|
||||
except ValueError:
|
||||
return False
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt
|
||||
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'):
|
||||
@ -141,7 +147,11 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
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:
|
||||
@ -180,13 +190,13 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread.tex'):
|
||||
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_latex', switch_prompt=switch_prompt)
|
||||
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',
|
||||
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)
|
||||
|
||||
|
||||
@ -195,6 +205,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
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
|
||||
@ -278,6 +289,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
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
|
||||
|
||||
@ -192,7 +192,10 @@ def test_Latex():
|
||||
# txt = r"https://arxiv.org/abs/2306.07831"
|
||||
# txt = r"https://arxiv.org/abs/2212.10156"
|
||||
# txt = r"https://arxiv.org/abs/2211.11559"
|
||||
txt = r"https://arxiv.org/abs/2303.08774"
|
||||
# txt = r"https://arxiv.org/abs/2303.08774"
|
||||
# txt = r"https://arxiv.org/abs/2303.12712"
|
||||
# txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
|
||||
txt = r"C:\Users\fuqingxu\Desktop\9"
|
||||
|
||||
|
||||
for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
|
||||
@ -8,24 +8,49 @@ pj = os.path.join
|
||||
"""
|
||||
========================================================================
|
||||
Part One
|
||||
Latex segmentation to a linklist
|
||||
Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
|
||||
========================================================================
|
||||
"""
|
||||
PRESERVE = 0
|
||||
TRANSFORM = 1
|
||||
|
||||
def split_worker(text, mask, pattern, flags=0):
|
||||
def set_forbidden_text(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper
|
||||
e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
|
||||
you can mask out (mask = PRESERVE so that text become untouchable for GPT)
|
||||
everything between "\begin{equation}" and "\end{equation}"
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
mask[res.span()[0]:res.span()[1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def split_worker_careful_brace(text, mask, pattern, flags=0):
|
||||
def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area into preserve area
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\begin{abstract} blablablablablabla. \end{abstract}
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
if not forbid_wrapper:
|
||||
mask[res.span()[0]:res.span()[1]] = TRANSFORM
|
||||
else:
|
||||
mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE # '\\begin{abstract}'
|
||||
mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM # abstract
|
||||
mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE # abstract
|
||||
return text, mask
|
||||
|
||||
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.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
@ -40,9 +65,12 @@ def split_worker_careful_brace(text, mask, pattern, flags=0):
|
||||
mask[begin:end] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
|
||||
def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
@ -55,9 +83,12 @@ def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
|
||||
p += 1
|
||||
end = p
|
||||
mask[begin:end] = TRANSFORM
|
||||
if forbid_wrapper:
|
||||
mask[res.regs[0][0]:begin] = PRESERVE
|
||||
mask[end:res.regs[0][1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def split_worker_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
|
||||
def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
|
||||
"""
|
||||
Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
|
||||
Add it to preserve area
|
||||
@ -154,6 +185,7 @@ def rm_comments(main_file):
|
||||
else:
|
||||
new_file_remove_comment_lines.append(l)
|
||||
main_file = '\n'.join(new_file_remove_comment_lines)
|
||||
# main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file) # 将 \include 命令转换为 \input 命令
|
||||
main_file = re.sub(r'(?<!\\)%.*', '', main_file) # 使用正则表达式查找半行注释, 并替换为空字符串
|
||||
return main_file
|
||||
|
||||
@ -200,9 +232,11 @@ def merge_tex_files(project_foler, main_file, mode):
|
||||
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)
|
||||
assert match is not None, "Cannot find paper abstract section!"
|
||||
pattern_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
|
||||
match_opt1 = pattern_opt1.search(main_file)
|
||||
match_opt2 = pattern_opt2.search(main_file)
|
||||
assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
|
||||
return main_file
|
||||
|
||||
|
||||
@ -283,46 +317,34 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
|
||||
|
||||
# 吸收title与作者以上的部分
|
||||
text, mask = split_worker(text, mask, r"(.*?)\\maketitle", re.DOTALL)
|
||||
# 删除iffalse注释
|
||||
text, mask = split_worker(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
|
||||
# 吸收在25行以内的begin-end组合
|
||||
text, mask = split_worker_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=25)
|
||||
text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL)
|
||||
# 吸收iffalse注释
|
||||
text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
|
||||
# 吸收在42行以内的begin-end组合
|
||||
text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
|
||||
# 吸收匿名公式
|
||||
text, mask = split_worker(text, mask, r"\$\$(.*?)\$\$", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [ r"\$\$(.*?)\$\$", r"\\\[.*?\\\]" ], re.DOTALL)
|
||||
# 吸收其他杂项
|
||||
text, mask = split_worker(text, mask, r"\\section\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\section\*\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\subsection\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\subsubsection\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\bibliography\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\bibliographystyle\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{figure\}(.*?)\\end\{figure\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{multline\}(.*?)\\end\{multline\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{table\}(.*?)\\end\{table\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{table\*\}(.*?)\\end\{table\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{minipage\}(.*?)\\end\{minipage\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{align\*\}(.*?)\\end\{align\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{align\}(.*?)\\end\{align\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{equation\}(.*?)\\end\{equation\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}", re.DOTALL)
|
||||
text, mask = split_worker(text, mask, r"\\includepdf\[(.*?)\]\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\item ")
|
||||
text, mask = split_worker(text, mask, r"\\label\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\begin\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\vspace\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\hspace\{(.*?)\}")
|
||||
text, mask = split_worker(text, mask, r"\\end\{(.*?)\}")
|
||||
text, mask = split_worker_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
|
||||
text, mask = split_worker_reverse_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [ r"\\section\{(.*?)\}", r"\\section\*\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
|
||||
text, mask = set_forbidden_text(text, mask, [ r"\\bibliography\{(.*?)\}", r"\\bibliographystyle\{(.*?)\}" ])
|
||||
text, mask = set_forbidden_text(text, mask, r"\\begin\{thebibliography\}.*?\\end\{thebibliography\}", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{figure\}(.*?)\\end\{figure\}", r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{multline\}(.*?)\\end\{multline\}", r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{table\}(.*?)\\end\{table\}", r"\\begin\{table\*\}(.*?)\\end\{table\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{minipage\}(.*?)\\end\{minipage\}", r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{align\*\}(.*?)\\end\{align\*\}", r"\\begin\{align\}(.*?)\\end\{align\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\begin\{equation\}(.*?)\\end\{equation\}", r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}"], re.DOTALL)
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\includepdf\[(.*?)\]\{(.*?)\}", r"\\clearpage", r"\\newpage", r"\\appendix", r"\\tableofcontents", r"\\include\{(.*?)\}"])
|
||||
text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item "])
|
||||
text, mask = set_forbidden_text_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
|
||||
# reverse 操作必须放在最后
|
||||
text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
|
||||
text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\abstract\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
|
||||
text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
|
||||
root = convert_to_linklist(text, mask)
|
||||
|
||||
# 修复括号
|
||||
@ -396,7 +418,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
prev_node = node
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 输出html调试文件，用红色标注处保留区（PRESERVE），用黑色标注转换区（TRANSFORM）
|
||||
with open(pj(project_folder, 'debug_log.html'), 'w', encoding='utf8') as f:
|
||||
segment_parts_for_gpt = []
|
||||
nodes = []
|
||||
@ -427,7 +449,7 @@ 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，" + \
|
||||
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）
|
||||
@ -448,8 +470,14 @@ class LatexPaperSplit():
|
||||
if mode == 'translate_zh':
|
||||
pattern = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
match = pattern.search(result_string)
|
||||
assert match is not None, "Cannot find paper abstract section!"
|
||||
position = match.end()
|
||||
if not match:
|
||||
# match \abstract{xxxx}
|
||||
pattern_compile = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
|
||||
match = pattern_compile.search(result_string)
|
||||
position = match.regs[1][0]
|
||||
else:
|
||||
# match \begin{abstract}xxxx\end{abstract}
|
||||
position = match.end()
|
||||
result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
|
||||
return result_string
|
||||
|
||||
@ -468,6 +496,7 @@ class LatexPaperSplit():
|
||||
args=(txt, project_folder, return_dict, opts))
|
||||
p.start()
|
||||
p.join()
|
||||
p.close()
|
||||
self.nodes = return_dict['nodes']
|
||||
self.sp = return_dict['segment_parts_for_gpt']
|
||||
return self.sp
|
||||
@ -522,11 +551,11 @@ class LatexPaperFileGroup():
|
||||
f.write(res)
|
||||
return manifest
|
||||
|
||||
def write_html(sp_file_contents, sp_file_result, chatbot):
|
||||
def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
|
||||
|
||||
# write html
|
||||
try:
|
||||
import copy
|
||||
import shutil
|
||||
from .crazy_utils import construct_html
|
||||
from toolbox import gen_time_str
|
||||
ch = construct_html()
|
||||
@ -544,6 +573,7 @@ def write_html(sp_file_contents, sp_file_result, chatbot):
|
||||
ch.add_row(a=orig, b=trans)
|
||||
create_report_file_name = f"{gen_time_str()}.trans.html"
|
||||
ch.save_file(create_report_file_name)
|
||||
shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, 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
|
||||
@ -624,7 +654,8 @@ 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)
|
||||
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']}。"
|
||||
@ -661,10 +692,9 @@ def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work
|
||||
print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
|
||||
return False, -1, [-1]
|
||||
|
||||
|
||||
def compile_latex_with_timeout(command, timeout=60):
|
||||
def compile_latex_with_timeout(command, cwd, timeout=60):
|
||||
import subprocess
|
||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
|
||||
try:
|
||||
stdout, stderr = process.communicate(timeout=timeout)
|
||||
except subprocess.TimeoutExpired:
|
||||
@ -688,24 +718,24 @@ 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
|
||||
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)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', 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
|
||||
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)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', 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
|
||||
if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'bibtex {main_file_original}.aux'); os.chdir(current_dir)
|
||||
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')):
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux'); os.chdir(current_dir)
|
||||
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
|
||||
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)
|
||||
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)
|
||||
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)
|
||||
|
||||
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
|
||||
@ -713,13 +743,12 @@ 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')
|
||||
|
||||
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)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', 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)
|
||||
|
||||
|
||||
# <---------- 检查结果 ----------->
|
||||
results_ = ""
|
||||
@ -731,13 +760,16 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
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
|
||||
|
||||
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, 即将退出 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
os.chdir(current_dir)
|
||||
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
|
||||
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
|
||||
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, rename_file=None, chatbot=chatbot)
|
||||
|
||||
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
|
||||
return True # 成功啦
|
||||
else:
|
||||
if n_fix>=max_try: break
|
||||
@ -753,7 +785,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
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
|
||||
if not can_retry: break
|
||||
|
||||
os.chdir(current_dir)
|
||||
return False # 失败啦
|
||||
|
||||
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
from toolbox import CatchException, report_execption, write_results_to_file
|
||||
from toolbox import update_ui
|
||||
from toolbox import update_ui, promote_file_to_downloadzone
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .crazy_utils import read_and_clean_pdf_text
|
||||
@ -147,23 +147,14 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
print('writing html result failed:', trimmed_format_exc())
|
||||
|
||||
# 准备文件的下载
|
||||
import shutil
|
||||
for pdf_path in generated_conclusion_files:
|
||||
# 重命名文件
|
||||
rename_file = f'./gpt_log/翻译-{os.path.basename(pdf_path)}'
|
||||
if os.path.exists(rename_file):
|
||||
os.remove(rename_file)
|
||||
shutil.copyfile(pdf_path, rename_file)
|
||||
if os.path.exists(pdf_path):
|
||||
os.remove(pdf_path)
|
||||
rename_file = f'翻译-{os.path.basename(pdf_path)}'
|
||||
promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
|
||||
for html_path in generated_html_files:
|
||||
# 重命名文件
|
||||
rename_file = f'./gpt_log/翻译-{os.path.basename(html_path)}'
|
||||
if os.path.exists(rename_file):
|
||||
os.remove(rename_file)
|
||||
shutil.copyfile(html_path, rename_file)
|
||||
if os.path.exists(html_path):
|
||||
os.remove(html_path)
|
||||
rename_file = f'翻译-{os.path.basename(html_path)}'
|
||||
promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
|
||||
chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
@ -13,7 +13,9 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
# 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
|
||||
# 的长度必须小于 2500 个 Token
|
||||
file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
|
||||
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
|
||||
102
crazy_functions/联网的ChatGPT_bing版.py
Normal file
102
crazy_functions/联网的ChatGPT_bing版.py
Normal file
@ -0,0 +1,102 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from request_llm.bridge_all import model_info
|
||||
|
||||
|
||||
def bing_search(query, proxies=None):
|
||||
query = query
|
||||
url = f"https://cn.bing.com/search?q={query}"
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'}
|
||||
response = requests.get(url, headers=headers, proxies=proxies)
|
||||
soup = BeautifulSoup(response.content, 'html.parser')
|
||||
results = []
|
||||
for g in soup.find_all('li', class_='b_algo'):
|
||||
anchors = g.find_all('a')
|
||||
if anchors:
|
||||
link = anchors[0]['href']
|
||||
if not link.startswith('http'):
|
||||
continue
|
||||
title = g.find('h2').text
|
||||
item = {'title': title, 'link': link}
|
||||
results.append(item)
|
||||
|
||||
for r in results:
|
||||
print(r['link'])
|
||||
return results
|
||||
|
||||
|
||||
def scrape_text(url, proxies) -> str:
|
||||
"""Scrape text from a webpage
|
||||
|
||||
Args:
|
||||
url (str): The URL to scrape text from
|
||||
|
||||
Returns:
|
||||
str: The scraped text
|
||||
"""
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
|
||||
'Content-Type': 'text/plain',
|
||||
}
|
||||
try:
|
||||
response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
|
||||
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
|
||||
except:
|
||||
return "无法连接到该网页"
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
for script in soup(["script", "style"]):
|
||||
script.extract()
|
||||
text = soup.get_text()
|
||||
lines = (line.strip() for line in text.splitlines())
|
||||
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
|
||||
text = "\n".join(chunk for chunk in chunks if chunk)
|
||||
return text
|
||||
|
||||
@CatchException
|
||||
def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
"""
|
||||
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行
|
||||
plugin_kwargs 插件模型的参数，暂时没有用武之地
|
||||
chatbot 聊天显示框的句柄，用于显示给用户
|
||||
history 聊天历史，前情提要
|
||||
system_prompt 给gpt的静默提醒
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
|
||||
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板。您若希望分享新的功能模组，请不吝PR！"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
|
||||
|
||||
# ------------- < 第1步：爬取搜索引擎的结果 > -------------
|
||||
from toolbox import get_conf
|
||||
proxies, = get_conf('proxies')
|
||||
urls = bing_search(txt, proxies)
|
||||
history = []
|
||||
|
||||
# ------------- < 第2步：依次访问网页 > -------------
|
||||
max_search_result = 8 # 最多收纳多少个网页的结果
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
res = scrape_text(url['link'], proxies)
|
||||
history.extend([f"第{index}份搜索结果：", res])
|
||||
chatbot.append([f"第{index}份搜索结果：", res[:500]+"......"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
|
||||
|
||||
# ------------- < 第3步：ChatGPT综合 > -------------
|
||||
i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
|
||||
i_say, history = input_clipping( # 裁剪输入，从最长的条目开始裁剪，防止爆token
|
||||
inputs=i_say,
|
||||
history=history,
|
||||
max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
|
||||
)
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
|
||||
)
|
||||
chatbot[-1] = (i_say, gpt_say)
|
||||
history.append(i_say);history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
import datetime
|
||||
import datetime, re
|
||||
|
||||
@CatchException
|
||||
def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
"""
|
||||
@ -18,12 +19,34 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
for i in range(5):
|
||||
currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
|
||||
currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
|
||||
i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
|
||||
i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？用中文列举两条，然后分别给出描述事件的两个英文单词。' + '当你给出关键词时，使用以下json格式：{"KeyWords":[EnglishKeyWord1,EnglishKeyWord2]}。'
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
|
||||
sys_prompt='输出格式示例：1908年，美国消防救援事业发展的“美国消防协会”成立。关键词：{"KeyWords":["Fire","American"]}。'
|
||||
)
|
||||
gpt_say = get_images(gpt_say)
|
||||
chatbot[-1] = (i_say, gpt_say)
|
||||
history.append(i_say);history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
|
||||
def get_images(gpt_say):
|
||||
def get_image_by_keyword(keyword):
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
response = requests.get(f'https://wallhaven.cc/search?q={keyword}', timeout=2)
|
||||
for image_element in BeautifulSoup(response.content, 'html.parser').findAll("img"):
|
||||
if "data-src" in image_element: break
|
||||
return image_element["data-src"]
|
||||
|
||||
for keywords in re.findall('{"KeyWords":\[(.*?)\]}', gpt_say):
|
||||
keywords = [n.strip('"') for n in keywords.split(',')]
|
||||
try:
|
||||
description = keywords[0]
|
||||
url = get_image_by_keyword(keywords[0])
|
||||
img_tag = f"\n\n"
|
||||
gpt_say += img_tag
|
||||
except:
|
||||
continue
|
||||
return gpt_say
|
||||
Reference in New Issue
Block a user