stashed commit

config.py

@@ -212,6 +212,11 @@ WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
 # 自定义按钮的最大数量限制
 NUM_CUSTOM_BASIC_BTN = 4
 
+
+# LATEX实验性功能
+LATEX_EXPERIMENTAL = False
+
+
 """
 在线大模型配置关联关系示意图
 │

crazy_functions/crazy_utils.py

@@ -205,13 +205,12 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         retry_op = retry_times_at_unknown_error
         exceeded_cnt = 0
         mutable[index][2] = "执行中"
+        detect_timeout = lambda: len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > watch_dog_patience
         while True:
             # watchdog error
-            if len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > watch_dog_patience: 
+            if detect_timeout(): raise RuntimeError("检测到程序终止。")
-                raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
-                # time.sleep(10); raise RuntimeError("测试")
                 gpt_say = predict_no_ui_long_connection(
                     inputs=inputs, llm_kwargs=llm_kwargs, history=history, 
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
@@ -219,7 +218,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 mutable[index][2] = "已成功"
                 return gpt_say
             except ConnectionAbortedError as token_exceeded_error:
-                # 【第二种情况】：Token溢出，
+                # 【第二种情况】：Token溢出
                 if handle_token_exceed:
                     exceeded_cnt += 1
                     # 【选择处理】 尝试计算比例，尽可能多地保留文本
@@ -240,6 +239,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     return gpt_say # 放弃
             except:
                 # 【第三种情况】：其他错误
+                if detect_timeout(): raise RuntimeError("检测到程序终止。")
                 tb_str = '```\n' + trimmed_format_exc() + '```'
                 print(tb_str)
                 gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
@@ -256,6 +256,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     for i in range(wait):
                         mutable[index][2] = f"{fail_info}等待重试 {wait-i}"; time.sleep(1)
                     # 开始重试
+                    if detect_timeout(): raise RuntimeError("检测到程序终止。")
                     mutable[index][2] = f"重试中 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}"
                     continue # 返回重试
                 else:

crazy_functions/latex_fns/latex_actions.py

@@ -1,9 +1,10 @@
 from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
-from toolbox import zip_folder, objdump, objload, promote_file_to_downloadzone
+from toolbox import get_conf, objdump, objload, promote_file_to_downloadzone
 from .latex_toolbox import PRESERVE, TRANSFORM
 from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
 from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
 from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
+from .latex_toolbox import find_title_and_abs
 
 import os, shutil
 import re
@@ -90,7 +91,15 @@ class LatexPaperSplit():
             "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。}}\\\\" 
+        self.title = "unknown"
+        self.abstract = "unknown"
 
+    def read_title_and_abstract(self, txt):
+        title, abstract = find_title_and_abs(txt)
+        if title is not None: 
+            self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
+        if abstract is not None: 
+            self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
 
     def merge_result(self, arr, mode, msg, buggy_lines=[], buggy_line_surgery_n_lines=10):
         """
@@ -234,8 +243,8 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     lps = LatexPaperSplit()
+    lps.read_title_and_abstract(merged_content)
     res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
-
     #  <-------- 拆分过长的latex片段 ----------> 
     pfg = LatexPaperFileGroup()
     for index, r in enumerate(res):
@@ -256,12 +265,19 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
 
     else:
         #  <-------- gpt 多线程请求 ----------> 
+        LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
+        history_array = [[""] for _ in range(n_split)]
+        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=[[""] for _ in range(n_split)],
+            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

crazy_functions/latex_fns/latex_toolbox.py

@@ -318,6 +318,40 @@ def merge_tex_files_(project_foler, main_file, mode):
         main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
     return main_file
 
+
+def find_title_and_abs(main_file):
+
+    def extract_abstract_1(text):
+        pattern = r"\\abstract\{(.*?)\}"
+        match = re.search(pattern, text, re.DOTALL)
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    def extract_abstract_2(text):
+        pattern = r"\\begin\{abstract\}(.*?)\\end\{abstract\}"
+        match = re.search(pattern, text, re.DOTALL)
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    def extract_title(string):
+        pattern = r"\\title\{(.*?)\}"
+        match = re.search(pattern, string, re.DOTALL)
+
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    abstract = extract_abstract_1(main_file)
+    if abstract is None:
+        abstract = extract_abstract_2(main_file)
+    title = extract_title(main_file)
+    return title, abstract
+
 def merge_tex_files(project_foler, main_file, mode):
     """
     Merge Tex project recrusively

tests/test_plugins.py

@@ -11,7 +11,9 @@ if __name__ == "__main__":
     from tests.test_utils import plugin_test
     # plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
 
-    plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2307.07522")
+    # plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2307.07522")
+
+    plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix")
 
     # plugin_test(plugin='crazy_functions.虚空终端->虚空终端', main_input='修改api-key为sk-jhoejriotherjep')