Merge branch 'master' into huggingface

crazy_functions/Latex全文润色.py

@@ -1,6 +1,6 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
-fast_debug = False
+from toolbox import update_ui, trimmed_format_exc
+from toolbox import CatchException, report_execption, write_results_to_file, zip_folder
+
 
 class PaperFileGroup():
     def __init__(self):
@@ -34,8 +34,27 @@ class PaperFileGroup():
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.tex")
 
         print('Segmentation: done')
+    def merge_result(self):
+        self.file_result = ["" for _ in range(len(self.file_paths))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
 
-def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
+    def write_result(self):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            with open(path + '.polish.tex', 'w', encoding='utf8') as f:
+                manifest.append(path + '.polish.tex')
+                f.write(res)
+        return manifest
+    
+    def zip_result(self):
+        import os, time
+        folder = os.path.dirname(self.file_paths[0])
+        t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+        zip_folder(folder, './gpt_log/', f'{t}-polished.zip')
+
+
+def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en', mode='polish'):
     import time, os, re
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
@@ -58,28 +77,27 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 抽取摘要 ----------> 
-    # if language == 'en':
-    #     abs_extract_inputs = f"Please write an abstract for this paper"
-
-    # # 单线，获取文章meta信息
-    # paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=abs_extract_inputs,
-    #     inputs_show_user=f"正在抽取摘要信息。",
-    #     llm_kwargs=llm_kwargs,
-    #     chatbot=chatbot, history=[],
-    #     sys_prompt="Your job is to collect information from materials。",
-    # )
 
     #  <-------- 多线程润色开始 ----------> 
     if language == 'en':
-        inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" + 
+        if mode == 'polish':
+            inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " + 
+                            "improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" + 
+                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        else:
+            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"Answer me only with the revised text:" + 
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"Polish {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
     elif language == 'zh':
-        inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        if mode == 'polish':
+            inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        else:
+            inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+                            f"\n\n{frag}" for frag in pfg.sp_file_contents] 
         inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
 
@@ -95,6 +113,17 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         scroller_max_len = 80
     )
 
+    #  <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ----------> 
+    try:
+        pfg.sp_file_result = []
+        for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
+            pfg.sp_file_result.append(gpt_say)
+        pfg.merge_result()
+        pfg.write_result()
+        pfg.zip_result()
+    except:
+        print(trimmed_format_exc())
+
     #  <-------- 整理结果，退出 ----------> 
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
     res = write_results_to_file(gpt_response_collection, file_name=create_report_file_name)
@@ -172,4 +201,42 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh')
+    yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh')
+
+
+
+
+@CatchException
+def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "对整个Latex项目进行纠错。函数插件贡献者: Binary-Husky"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import tiktoken
+    except:
+        report_execption(chatbot, history,
+                         a=f"解析项目: {txt}",
+                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    history = []    # 清空历史，以免输入溢出
+    import glob, os
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+    if len(file_manifest) == 0:
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en', mode='proofread')
+
+

crazy_functions/crazy_functions_test.py

@@ -81,29 +81,13 @@ def test_下载arxiv论文并翻译摘要():
 
 def test_联网回答问题():
     from crazy_functions.联网的ChatGPT import 连接网络回答问题
-    # txt = "“我们称之为高效”是什么梗？"
-    # >>        从第0份、第1份、第2份搜索结果可以看出，“我们称之为高效”是指在游戏社区中，用户们用来形容一些游戏策略或行为非常高效且能够带来好的效果的用语。这个用语最初可能是在群星（Stellaris）这个游戏里面流行起来的，后来也传播到了其他游戏中，比如巨像（Titan）等游戏。其中第1份搜索结果中的一篇文章也指出，“我们称之为高效”这 一用语来源于群星（Stellaris）游戏中的一个情节。
-    # txt = "为什么说枪毙P社玩家没有一个冤枉的？"
-    # >>        它们都是关于一个知乎用户所发的帖子，引用了一群游戏玩家对于需要对P社玩家进行枪毙的讨论，这个话题的本质是玩家们对于P 社游戏中的政治与历史元素的不同看法，以及其中不少玩家以极端立场宣扬的想法和言论，因此有人就以枪毙这些玩家来回应此类言论。但是这个话题本身并没有实质内容，只是一个玩笑或者恶搞，并不应该被当做真实的态度或者观点，因此这种说法没有实际意义。
     # txt = "谁是应急食品？"
     # >>        '根据以上搜索结果可以得知，应急食品是“原神”游戏中的角色派蒙的外号。'
     # txt = "道路千万条，安全第一条。后面两句是？"
     # >>        '行车不规范，亲人两行泪。'
-    # txt = "What is in the canister?"
-    # >>        Rainbow Six Siege 游戏中 Smoke 的 Canister 中装有何种物质相关的官方信息。
-    # txt = "失败的man是什么?"
-    # >>        根据第1份搜索结果，可以得知失败的man是指一位在B站购买了蜘蛛侠COS服后穿上后被网友嘲笑的UP主，而“失败的man”是蜘蛛侠英文名“spiderman”的谐音梗，并且网友们还 给这位UP主起了“苍蝇侠”的外号。因此，失败的man是指这位UP主在穿上蜘蛛侠COS服后被网友嘲笑的情况。
-    # txt = "老六是什么，起源于哪里？"
-    # >>        老六是网络流行语，最初起源于游戏《CSGO》，指游戏中玩家中独来独往、游离于队伍之外的“自由人”或玩得比较菜或者玩得比较阴险的人 ，后来逐渐演变成指玩得比较阴险的玩家。
-    # txt = "罗小黑战记因为什么经常被吐槽？"
-    # >>        3. 更新速度。罗小黑战记的更新时间不定，时而快时而慢，给观众留下了等待的时间过长的印象。
-    # txt = "沙特、伊朗最近的关系如何？"
-    # >>        最近在中国的斡旋下，沙特和伊朗于3月10日达成了恢复两国外交关系的协议，这表明两国关系已经重新回到正常化状态。
     # txt = "You should have gone for the head. What does that mean?"
     # >>        The phrase "You should have gone for the head" is a quote from the Marvel movies, Avengers: Infinity War and Avengers: Endgame. It was spoken by the character Thanos in Infinity War and by Thor in Endgame.
     txt = "AutoGPT是什么？"
-    # >>        AutoGPT是一个基于GPT-4语言模型的开源应用程序。它可以根据用户需求自主执行任务，包括事件分析、营销方案撰写、代码编程、数学运算等等，并完全不需要用户插手。它可以自己思考，给出实现的步骤和实现细节，甚至可以自问自答执 行任务。最近它在GitHub上爆火，成为了业内最热门的项目之一。
-    # txt = "钟离带什么圣遗物？"
     for cookies, cb, hist, msg in 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): 
         print("当前问答：", cb[-1][-1].replace("\n"," "))
     for i, it in enumerate(cb): print亮蓝(it[0]); print亮黄(it[1])
@@ -115,6 +99,25 @@ def test_解析ipynb文件():
         print(cb)
 
 
+def test_数学动画生成manim():
+    from crazy_functions.数学动画生成manim import 动画生成
+    txt = "A ball split into 2, and then split into 4, and finally split into 8."
+    for cookies, cb, hist, msg in 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        print(cb)
+
+
+
+def test_Markdown多语言():
+    from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
+    txt = "README.md"
+    history = []
+    for lang in ["English", "French", "Japanese", "Korean", "Russian", "Italian", "German", "Portuguese", "Arabic"]:
+        plugin_kwargs = {"advanced_arg": lang}
+        for cookies, cb, hist, msg in Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+            print(cb)
+
+
+
 # test_解析一个Python项目()
 # test_Latex英文润色()
 # test_Markdown中译英()
@@ -124,7 +127,9 @@ def test_解析ipynb文件():
 # test_下载arxiv论文并翻译摘要()
 # test_解析一个Cpp项目()
 # test_联网回答问题()
-test_解析ipynb文件()
+# test_解析ipynb文件()
+# test_数学动画生成manim()
+test_Markdown多语言()
 
 input("程序完成，回车退出。")
 print("退出。")

crazy_functions/crazy_utils.py

@@ -259,9 +259,6 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         time.sleep(refresh_interval)
         cnt += 1
         worker_done = [h.done() for h in futures]
-        if all(worker_done):
-            executor.shutdown()
-            break
         # 更好的UI视觉效果
         observe_win = []
         # 每个线程都要“喂狗”（看门狗）
@@ -280,7 +277,10 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         # 在前端打印些好玩的东西
         chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
         yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
-    
+        if all(worker_done):
+            executor.shutdown()
+            break
+
     # 异步任务结束
     gpt_response_collection = []
     for inputs_show_user, f in zip(inputs_show_user_array, futures):

crazy_functions/批量Markdown翻译.py

@@ -1,4 +1,4 @@
-from toolbox import update_ui
+from toolbox import update_ui, trimmed_format_exc, gen_time_str
 from toolbox import CatchException, report_execption, write_results_to_file
 fast_debug = False
 
@@ -32,9 +32,21 @@ class PaperFileGroup():
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.md")
-
         print('Segmentation: done')
 
+    def merge_result(self):
+        self.file_result = ["" for _ in range(len(self.file_paths))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
+
+    def write_result(self, language):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            with open(path + f'.{gen_time_str()}.{language}.md', 'w', encoding='utf8') as f:
+                manifest.append(path + f'.{gen_time_str()}.{language}.md')
+                f.write(res)
+        return manifest
+
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
     import time, os, re
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
@@ -53,7 +65,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     pfg.run_file_split(max_token_limit=1500)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 多线程翻译开始 ----------> 
     if language == 'en->zh':
         inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" + 
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
@@ -64,6 +76,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
+    else:
+        inputs_array = [f"This is a Markdown file, translate it into {language}, do not modify any existing Markdown commands, only answer me with translated results:" + 
+                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
+        sys_prompt_array = ["You are a professional academic paper translator." 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,
@@ -75,6 +92,14 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         # max_workers=5,  # OpenAI所允许的最大并行过载
         scroller_max_len = 80
     )
+    try:
+        pfg.sp_file_result = []
+        for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
+            pfg.sp_file_result.append(gpt_say)
+        pfg.merge_result()
+        pfg.write_result(language)
+    except:
+        print(trimmed_format_exc())
 
     #  <-------- 整理结果，退出 ----------> 
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
@@ -183,4 +208,40 @@ def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh->en')
+    yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh->en')
+
+
+@CatchException
+def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import tiktoken
+        import glob, os
+    except:
+        report_execption(chatbot, history,
+                         a=f"解析项目: {txt}",
+                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    history = []    # 清空历史，以免输入溢出
+    success, file_manifest, project_folder = get_files_from_everything(txt)
+    if not success:
+        # 什么都没有
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    if len(file_manifest) == 0:
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    language = plugin_kwargs.get("advanced_arg", 'Chinese')
+    yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language=language)

crazy_functions/批量总结PDF文档.py

@@ -41,8 +41,8 @@ def clean_text(raw_text):
     """
     对从 PDF 提取出的原始文本进行清洗和格式化处理。
     1. 对原始文本进行归一化处理。
-    2. 替换跨行的连词，例如 “Espe-\ncially” 转换为 “Especially”。
-    3. 根据 heuristic 规则判断换行符是否是段落分隔，并相应地进行替换。
+    2. 替换跨行的连词
+    3. 根据 heuristic 规则判断换行符是否是段落分隔，并相应地进行替换
     """
     # 对文本进行归一化处理
     normalized_text = normalize_text(raw_text)

crazy_functions/批量翻译PDF文档_多线程.py

@@ -58,14 +58,17 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
     import os
+    import copy
     import tiktoken
     TOKEN_LIMIT_PER_FRAGMENT = 1280
     generated_conclusion_files = []
+    generated_html_files = []
     for index, fp in enumerate(file_manifest):
 
         # 读取PDF文件
         file_content, page_one = read_and_clean_pdf_text(fp)
-
+        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
         # 递归地切割PDF文件
         from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
         from request_llm.bridge_all import model_info
@@ -74,7 +77,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
             txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
         page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+            txt=page_one, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
 
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
@@ -100,15 +103,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
                 "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
             # max_workers=5  # OpenAI所允许的最大并行过载
         )
-
+        gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
         # 整理报告的格式
-        for i,k in enumerate(gpt_response_collection): 
+        for i,k in enumerate(gpt_response_collection_md): 
             if i%2==0:
-                gpt_response_collection[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection)//2}]：\n "
+                gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
             else:
-                gpt_response_collection[i] = gpt_response_collection[i]
+                gpt_response_collection_md[i] = gpt_response_collection_md[i]
         final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
-        final.extend(gpt_response_collection)
+        final.extend(gpt_response_collection_md)
         create_report_file_name = f"{os.path.basename(fp)}.trans.md"
         res = write_results_to_file(final, file_name=create_report_file_name)
 
@@ -117,15 +120,97 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         chatbot.append((f"{fp}完成了吗？", res))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
+        # write html
+        try:
+            ch = construct_html() 
+            orig = ""
+            trans = ""
+            gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
+            for i,k in enumerate(gpt_response_collection_html): 
+                if i%2==0:
+                    gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
+                else:
+                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
+            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
+            final.extend(gpt_response_collection_html)
+            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"{os.path.basename(fp)}.trans.html"
+            ch.save_file(create_report_file_name)
+            generated_html_files.append(f'./gpt_log/{create_report_file_name}')
+        except:
+            from toolbox import trimmed_format_exc
+            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/总结论文-{os.path.basename(pdf_path)}'
+        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)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files)))
+    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)
+    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
+
+
+class construct_html():
+    def __init__(self) -> None:
+        self.css = """
+.row {
+  display: flex;
+  flex-wrap: wrap;
+}
+
+.column {
+  flex: 1;
+  padding: 10px;
+}
+
+.table-header {
+  font-weight: bold;
+  border-bottom: 1px solid black;
+}
+
+.table-row {
+  border-bottom: 1px solid lightgray;
+}
+
+.table-cell {
+  padding: 5px;
+}
+        """
+        self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
+
+
+    def add_row(self, a, b):
+        tmp = """
+<div class="row table-row">
+    <div class="column table-cell">REPLACE_A</div>
+    <div class="column table-cell">REPLACE_B</div>
+</div>
+        """
+        from toolbox import markdown_convertion
+        tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
+        tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
+        self.html_string += tmp
+
+
+    def save_file(self, file_name):
+        with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
+            f.write(self.html_string.encode('utf-8', 'ignore').decode())
+

crazy_functions/数学动画生成manim.py

@@ -0,0 +1,187 @@
+from toolbox import CatchException, update_ui, gen_time_str
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from .crazy_utils import input_clipping
+
+def inspect_dependency(chatbot, history):
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import manim
+        return True
+    except:
+        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖，安装方法:```pip install manimgl```"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return False
+
+def eval_manim(code):
+    import subprocess, sys, os, shutil
+
+    with open('gpt_log/MyAnimation.py', 'w', encoding='utf8') as f:
+        f.write(code)
+
+    def get_class_name(class_string):
+        import re
+        # Use regex to extract the class name
+        class_name = re.search(r'class (\w+)\(', class_string).group(1)
+        return class_name
+
+    class_name = get_class_name(code)
+
+    try: 
+        subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
+        shutil.move('media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{gen_time_str()}.mp4')
+        return f'gpt_log/{gen_time_str()}.mp4'
+    except subprocess.CalledProcessError as e:
+        output = e.output.decode()
+        print(f"Command returned non-zero exit status {e.returncode}: {output}.")
+        return f"Evaluating python script failed: {e.output}."
+    except: 
+        print('generating mp4 failed')
+        return "Generating mp4 failed."
+
+
+def get_code_block(reply):
+    import re
+    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
+    matches = re.findall(pattern, reply) # find all code blocks in text
+    if len(matches) != 1: 
+        raise RuntimeError("GPT is not generating proper code.")
+    return matches[0].strip('python') #  code block
+
+@CatchException
+def 动画生成(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
+    """
+    # 清空历史，以免输入溢出
+    history = []    
+
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "生成数学动画, 此插件处于开发阶段, 建议暂时不要使用, 作者: binary-husky, 插件初始化中 ..."
+    ])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖, 如果缺少依赖, 则给出安装建议
+    dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
+    if not dep_ok: return
+    
+    # 输入
+    i_say = f'Generate a animation to show: ' + txt
+    demo = ["Here is some examples of manim", examples_of_manim()]
+    _, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
+    # 开始
+    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=demo, 
+        sys_prompt=
+        r"Write a animation script with 3blue1brown's manim. "+
+        r"Please begin with `from manim import *`. " + 
+        r"Answer me with a code block wrapped by ```."
+    )
+    chatbot.append(["开始生成动画", "..."])
+    history.extend([i_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+    
+    # 将代码转为动画
+    code = get_code_block(gpt_say)
+    res = eval_manim(code)
+
+    chatbot.append(("生成的视频文件路径", res))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+# 在这里放一些网上搜集的demo，辅助gpt生成代码
+def examples_of_manim():
+    return r"""
+
+
+```
+
+class MovingGroupToDestination(Scene):
+    def construct(self):
+        group = VGroup(Dot(LEFT), Dot(ORIGIN), Dot(RIGHT, color=RED), Dot(2 * RIGHT)).scale(1.4)
+        dest = Dot([4, 3, 0], color=YELLOW)
+        self.add(group, dest)
+        self.play(group.animate.shift(dest.get_center() - group[2].get_center()))
+        self.wait(0.5)
+
+```
+
+
+```
+
+class LatexWithMovingFramebox(Scene):
+    def construct(self):
+        text=MathTex(
+            "\\frac{d}{dx}f(x)g(x)=","f(x)\\frac{d}{dx}g(x)","+",
+            "g(x)\\frac{d}{dx}f(x)"
+        )
+        self.play(Write(text))
+        framebox1 = SurroundingRectangle(text[1], buff = .1)
+        framebox2 = SurroundingRectangle(text[3], buff = .1)
+        self.play(
+            Create(framebox1),
+        )
+        self.wait()
+        self.play(
+            ReplacementTransform(framebox1,framebox2),
+        )
+        self.wait()
+
+```
+
+
+
+```
+
+class PointWithTrace(Scene):
+    def construct(self):
+        path = VMobject()
+        dot = Dot()
+        path.set_points_as_corners([dot.get_center(), dot.get_center()])
+        def update_path(path):
+            previous_path = path.copy()
+            previous_path.add_points_as_corners([dot.get_center()])
+            path.become(previous_path)
+        path.add_updater(update_path)
+        self.add(path, dot)
+        self.play(Rotating(dot, radians=PI, about_point=RIGHT, run_time=2))
+        self.wait()
+        self.play(dot.animate.shift(UP))
+        self.play(dot.animate.shift(LEFT))
+        self.wait()
+
+```
+
+```
+
+# do not use get_graph, this funciton is deprecated
+
+class ExampleFunctionGraph(Scene):
+    def construct(self):
+        cos_func = FunctionGraph(
+            lambda t: np.cos(t) + 0.5 * np.cos(7 * t) + (1 / 7) * np.cos(14 * t),
+            color=RED,
+        )
+
+        sin_func_1 = FunctionGraph(
+            lambda t: np.sin(t) + 0.5 * np.sin(7 * t) + (1 / 7) * np.sin(14 * t),
+            color=BLUE,
+        )
+
+        sin_func_2 = FunctionGraph(
+            lambda t: np.sin(t) + 0.5 * np.sin(7 * t) + (1 / 7) * np.sin(14 * t),
+            x_range=[-4, 4],
+            color=GREEN,
+        ).move_to([0, 1, 0])
+
+        self.add(cos_func, sin_func_1, sin_func_2)
+
+```
+"""

crazy_functions/解析项目源代码.py

@@ -7,6 +7,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
     msg = '正常'
+    summary_batch_isolation = True
     inputs_array = []
     inputs_show_user_array = []
     history_array = []
@@ -59,10 +60,17 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         # 把“请对下面的程序文件做一个概述” 替换成 精简的 "文件名：{all_file[index]}"
         for index, content in enumerate(this_iteration_gpt_response_collection):
             if index%2==0: this_iteration_gpt_response_collection[index] = f"{file_rel_path[index//2]}" # 只保留文件名节省token
-        previous_iteration_files.extend([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
+        this_iteration_files = [os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)]
+        previous_iteration_files.extend(this_iteration_files)
         previous_iteration_files_string = ', '.join(previous_iteration_files)
-        current_iteration_focus = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
-        i_say = f'用一张Markdown表格简要描述以下文件的功能：{previous_iteration_files_string}。根据以上分析，用一句话概括程序的整体功能。'
+        current_iteration_focus = ', '.join(this_iteration_files)
+        if summary_batch_isolation: focus = current_iteration_focus
+        else:                       focus = previous_iteration_files_string
+        i_say = f'用一张Markdown表格简要描述以下文件的功能：{focus}。根据以上分析，用一句话概括程序的整体功能。'
+        if last_iteration_result != "":
+            sys_prompt_additional = "已知某些代码的局部作用是:" + last_iteration_result + "\n请继续分析其他源代码，从而更全面地理解项目的整体功能。"
+        else:
+            sys_prompt_additional = ""
         inputs_show_user = f'根据以上分析，对程序的整体功能和构架重新做出概括，由于输入长度限制，可能需要分组处理，本组文件为 {current_iteration_focus} + 已经汇总的文件组。'
         this_iteration_history = copy.deepcopy(this_iteration_gpt_response_collection)
         this_iteration_history.append(last_iteration_result)
@@ -71,10 +79,19 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         result = yield from request_gpt_model_in_new_thread_with_ui_alive(
             inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
             history=this_iteration_history_feed,   # 迭代之前的分析
-            sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。")
-        report_part_2.extend([i_say, result])
-        last_iteration_result = result
+            sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
+        
+        summary = "请用一句话概括这些文件的整体功能"
+        summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=summary, 
+            inputs_show_user=summary, 
+            llm_kwargs=llm_kwargs, 
+            chatbot=chatbot,
+            history=[i_say, result],   # 迭代之前的分析
+            sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
 
+        report_part_2.extend([i_say, result])
+        last_iteration_result = summary_result
         file_manifest = file_manifest[batchsize:]
         gpt_response_collection = gpt_response_collection[batchsize*2:]
 
@@ -232,6 +249,25 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
+@CatchException
+def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    history = []  # 清空历史，以免输入溢出
+    import glob, os
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.rs', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.toml', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.lock', recursive=True)]
+    if len(file_manifest) == 0:
+        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何golang文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
 def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):