Parse and generate ipynb (Issue #501)

Implemented code to parse and generate the ipynb files. The solution addresses Issue #501.

crazy_functional.py

@@ -19,12 +19,18 @@ def get_crazy_functions():
     from crazy_functions.解析项目源代码 import 解析一个Lua项目
     from crazy_functions.解析项目源代码 import 解析一个CSharp项目
     from crazy_functions.总结word文档 import 总结word文档
+    from crazy_functions.解析JupyterNotebook import 解析ipynb文件
     function_plugins = {
 
         "解析整个Python项目": {
             "Color": "stop",    # 按钮颜色
             "Function": HotReload(解析一个Python项目)
         },
+        "解析Jupyter Notebook文件": {
+            "Color": "stop",
+            "AsButton":False,
+            "Function": HotReload(解析ipynb文件),
+        },
         "批量总结Word文档": {
             "Color": "stop",
             "Function": HotReload(总结word文档)

crazy_functions/解析JupyterNotebook.py

@@ -0,0 +1,135 @@
+from toolbox import update_ui
+from toolbox import CatchException, report_execption
+fast_debug = True
+
+
+class PaperFileGroup():
+    def __init__(self):
+        self.file_paths = []
+        self.file_contents = []
+        self.sp_file_contents = []
+        self.sp_file_index = []
+        self.sp_file_tag = []
+
+        # count_token
+        from request_llm.bridge_all import model_info
+        enc = model_info["gpt-3.5-turbo"]['tokenizer']
+        def get_token_num(txt): return len(
+            enc.encode(txt, disallowed_special=()))
+        self.get_token_num = get_token_num
+
+    def run_file_split(self, max_token_limit=1900):
+        """
+        将长文本分离开来
+        """
+        for index, file_content in enumerate(self.file_contents):
+            if self.get_token_num(file_content) < max_token_limit:
+                self.sp_file_contents.append(file_content)
+                self.sp_file_index.append(index)
+                self.sp_file_tag.append(self.file_paths[index])
+            else:
+                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(
+                    file_content, self.get_token_num, max_token_limit)
+                for j, segment in enumerate(segments):
+                    self.sp_file_contents.append(segment)
+                    self.sp_file_index.append(index)
+                    self.sp_file_tag.append(
+                        self.file_paths[index] + f".part-{j}.txt")
+
+
+
+def parseNotebook(filename, enable_markdown=1):
+    import json
+
+    CodeBlocks = []
+    with open(filename, 'r', encoding='utf-8', errors='replace') as f:
+        notebook = json.load(f)
+    for cell in notebook['cells']:
+        if cell['cell_type'] == 'code' and cell['source']:
+            # remove blank lines
+            cell['source'] = [line for line in cell['source'] if line.strip()
+                              != '']
+            CodeBlocks.append("".join(cell['source']))
+        elif enable_markdown and cell['cell_type'] == 'markdown' and cell['source']:
+            cell['source'] = [line for line in cell['source'] if line.strip()
+                              != '']
+            CodeBlocks.append("Markdown:"+"".join(cell['source']))
+
+    Code = ""
+    for idx, code in enumerate(CodeBlocks):
+        Code += f"This is {idx+1}th code block: \n"
+        Code += code+"\n"
+
+    return Code 
+
+
+def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+
+    pfg = PaperFileGroup()
+
+    print(file_manifest)
+    for fp in file_manifest:
+        file_content = parseNotebook(fp, enable_markdown=1)
+        pfg.file_paths.append(fp)
+        pfg.file_contents.append(file_content)
+
+    #  <-------- 拆分过长的IPynb文件 ---------->
+    pfg.run_file_split(max_token_limit=1024)
+    n_split = len(pfg.sp_file_contents)
+
+    inputs_array = [f"This is a  Jupyter Notebook file, tell me about Each Block in Chinese. Focus Just On Code." +
+                    f"If a block starts with `Markdown` which means it's a markdown block in ipynbipynb. " +
+                    f"Start a new line for a block and block num use Chinese." +
+                    f"\n\n{frag}" for frag in pfg.sp_file_contents]
+    inputs_show_user_array = [f"{f}的分析如下" for f in pfg.sp_file_tag]
+    sys_prompt_array = ["You are a professional programmer."] * 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)],
+        sys_prompt_array=sys_prompt_array,
+        # max_workers=5,  # OpenAI所允许的最大并行过载
+        scroller_max_len=80
+    )
+
+    #  <-------- 整理结果，退出 ---------->
+    block_result = "  \n".join(gpt_response_collection)
+    chatbot.append(("解析的结果如下", block_result))
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+
+@CatchException
+def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    chatbot.append([
+        "函数插件功能？",
+        "对IPynb文件进行解析"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    history = []    # 清空历史
+    import glob
+    import 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
+    if txt.endswith('.ipynb'):
+        file_manifest = [txt]
+    else:
+        file_manifest = [f for f in glob.glob(
+            f'{project_folder}/**/*.ipynb', 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.ipynb文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    yield from ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, )