Merge branch 'GHSA-3jw4-f3wg-xr4c'

Author: binary-husky

crazy_functions/Latex输出PDF.py

@@ -107,6 +107,10 @@ def is_float(s):
         except ValueError:
             return False
 
+    if txt.startswith('https://arxiv.org/pdf/'):
+        arxiv_id = txt.split('/')[-1]   # 2402.14207v2.pdf
+        txt = arxiv_id.split('v')[0]  # 2402.14207
+
     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
@@ -121,6 +125,7 @@ def is_float(s):
     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
@@ -458,23 +463,23 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
             promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
 
             comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
-            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)        
+            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
 
             zip_res = zip_result(project_folder)
             promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
 
             return True
-        
+
         except:
             report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
             yield from update_ui(chatbot=chatbot, history=history)
-            
+
             chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
             yield from update_ui(chatbot=chatbot, history=history)
 
             except_flag = True
-            
-    
+
+
     elif not repeat or except_flag:
         yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
 

crazy_functions/latex_fns/latex_actions.py

@@ -259,40 +259,25 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     inputs_array, sys_prompt_array = switch_prompt(pfg, mode)
     inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
 
-    if os.path.exists(pj(project_folder,'temp.pkl')):
-
-        #  <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
-        pfg = objload(file=pj(project_folder,'temp.pkl'))
-
-    else:
-        #  <-------- gpt 多线程请求 ---------->
-        history_array = [[""] for _ in range(n_split)]
-        # LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
-        # if LATEX_EXPERIMENTAL:
-        #     paper_meta = f"The paper you processing is `{lps.title}`, a part of the abstraction is `{lps.abstract}`"
-        #     paper_meta_max_len = 888
-        #     history_array = [[ paper_meta[:paper_meta_max_len] + '...',  "Understand, what should I do?"] for _ in range(n_split)]
-
-        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=inputs_array,
-            inputs_show_user_array=inputs_show_user_array,
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=history_array,
-            sys_prompt_array=sys_prompt_array,
-            # max_workers=5,  # 并行任务数量限制, 最多同时执行5个, 其他的排队等待
-            scroller_max_len = 40
-        )
-
-        #  <-------- 文本碎片重组为完整的tex片段 ---------->
-        pfg.sp_file_result = []
-        for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
-            pfg.sp_file_result.append(gpt_say)
-        pfg.merge_result()
-
-        # <-------- 临时存储用于调试 ---------->
-        pfg.get_token_num = None
-        objdump(pfg, file=pj(project_folder,'temp.pkl'))
+    #  <-------- gpt 多线程请求 ---------->
+    history_array = [[""] for _ in range(n_split)]
+
+    gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+        inputs_array=inputs_array,
+        inputs_show_user_array=inputs_show_user_array,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history_array=history_array,
+        sys_prompt_array=sys_prompt_array,
+        # max_workers=5,  # 并行任务数量限制, 最多同时执行5个, 其他的排队等待
+        scroller_max_len = 40
+    )
+
+    #  <-------- 文本碎片重组为完整的tex片段 ---------->
+    pfg.sp_file_result = []
+    for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
+        pfg.sp_file_result.append(gpt_say)
+    pfg.merge_result()
 
     write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)