解决用户文件上传冲突

Latex File Name Bug Patch

crazy_functions/latex_utils.py

@@ -189,6 +189,18 @@ def rm_comments(main_file):
     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
 
+def find_tex_file_ignore_case(fp):
+    dir_name = os.path.dirname(fp)
+    base_name = os.path.basename(fp)
+    if not base_name.endswith('.tex'): base_name+='.tex'
+    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    # go case in-sensitive
+    import glob
+    for f in glob.glob(dir_name+'/*.tex'):
+        base_name_s = os.path.basename(fp)
+        if base_name_s.lower() == base_name.lower(): return f
+    return None
+
 def merge_tex_files_(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -197,15 +209,11 @@ def merge_tex_files_(project_foler, main_file, mode):
     for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
         f = s.group(1)
         fp = os.path.join(project_foler, f)
-        if os.path.exists(fp):  
-            # e.g., \input{srcs/07_appendix.tex}
-            with open(fp, 'r', encoding='utf-8', errors='replace') as fx:
-                c = fx.read()
-        else:  
-            # e.g., \input{srcs/07_appendix}
-            assert os.path.exists(fp+'.tex'), f'即找不到{fp}，也找不到{fp}.tex，Tex源文件缺失！'
-            with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
-                c = fx.read()
+        fp = find_tex_file_ignore_case(fp)
+        if fp:
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+        else:
+            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
         c = merge_tex_files_(project_foler, c, mode)
         main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
     return main_file

crazy_functions/总结word文档.py

@@ -14,17 +14,19 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             doc = Document(fp)
             file_content = "\n".join([para.text for para in doc.paragraphs])
         else:
-            import win32com.client
-            word = win32com.client.Dispatch("Word.Application")
-            word.visible = False
-            # 打开文件
-            print('fp', os.getcwd())
-            doc = word.Documents.Open(os.getcwd() + '/' + fp)
-            # file_content = doc.Content.Text
-            doc = word.ActiveDocument
-            file_content = doc.Range().Text
-            doc.Close()
-            word.Quit()
+            try:
+                import win32com.client
+                word = win32com.client.Dispatch("Word.Application")
+                word.visible = False
+                # 打开文件
+                doc = word.Documents.Open(os.getcwd() + '/' + fp)
+                # file_content = doc.Content.Text
+                doc = word.ActiveDocument
+                file_content = doc.Range().Text
+                doc.Close()
+                word.Quit()
+            except:
+                raise RuntimeError('请先将.doc文档转换为.docx文档。')
 
         print(file_content)
         # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名

docs/use_azure.md

@@ -100,10 +100,12 @@
 # 修改 config.py
 
 ```
-AZURE_ENDPOINT = "填入终结点"
+LLM_MODEL = "azure-gpt-3.5"  # 指定启动时的默认模型，当然事后从下拉菜单选也ok
+
+AZURE_ENDPOINT = "填入终结点" # 见上述图片
 AZURE_API_KEY = "填入azure openai api的密钥"
 AZURE_API_VERSION = "2023-05-15"  # 默认使用 2023-05-15 版本，无需修改
-AZURE_ENGINE = "填入部署名" # 见上图
+AZURE_ENGINE = "填入部署名" # 见上述图片
 
 ```
 

main.py

@@ -155,7 +155,7 @@ def main():
             click_handle = functional[k]["Button"].click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(k)], outputs=output_combo)
             cancel_handles.append(click_handle)
         # 文件上传区，接收文件后与chatbot的互动
-        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes], [chatbot, txt, txt2])
+        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2])
         # 函数插件-固定按钮区
         for k in crazy_fns:
             if not crazy_fns[k].get("AsButton", True): continue
@@ -185,6 +185,12 @@ def main():
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
         stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
+        def init_cookie(cookies, chatbot):
+            # 为每一位访问的用户赋予一个独一无二的uuid编码
+            import uuid
+            cookies.update({'user-uuid': 'user-'+uuid.uuid4().hex})
+            return cookies
+        demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
 
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def auto_opentab_delay():

toolbox.py

@@ -452,7 +452,7 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
         else: current = []
         chatbot._cookies.update({'file_to_promote': [new_path] + current})
 
-def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
+def on_file_uploaded(files, chatbot, txt, txt2, checkboxes, cookies):
     """
     当文件被上传时的回调函数
     """
@@ -463,24 +463,23 @@ def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
     import time
     import glob
     from toolbox import extract_archive
-    try:
-        shutil.rmtree('./private_upload/')
-    except:
-        pass
+    user_uuid = cookies.get('user-uuid', 'unknown_user')
+    try: shutil.rmtree(f'./private_upload/{user_uuid}')
+    except: pass
     time_tag = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
-    os.makedirs(f'private_upload/{time_tag}', exist_ok=True)
+    os.makedirs(f'private_upload/{user_uuid}/{time_tag}', exist_ok=True)
     err_msg = ''
     for file in files:
         file_origin_name = os.path.basename(file.orig_name)
-        shutil.copy(file.name, f'private_upload/{time_tag}/{file_origin_name}')
-        err_msg += extract_archive(f'private_upload/{time_tag}/{file_origin_name}',
-                                   dest_dir=f'private_upload/{time_tag}/{file_origin_name}.extract')
-    moved_files = [fp for fp in glob.glob('private_upload/**/*', recursive=True)]
+        shutil.copy(file.name, f'private_upload/{user_uuid}/{time_tag}/{file_origin_name}')
+        err_msg += extract_archive(f'private_upload/{user_uuid}/{time_tag}/{file_origin_name}',
+                                   dest_dir=f'private_upload/{user_uuid}/{time_tag}/{file_origin_name}.extract')
+    moved_files = [fp for fp in glob.glob(f'private_upload/{user_uuid}/**/*', recursive=True)]
     if "底部输入区" in checkboxes:
         txt = ""
-        txt2 = f'private_upload/{time_tag}'
+        txt2 = f'private_upload/{user_uuid}/{time_tag}'
     else:
-        txt = f'private_upload/{time_tag}'
+        txt = f'private_upload/{user_uuid}/{time_tag}'
         txt2 = ""
     moved_files_str = '\t\n\n'.join(moved_files)
     chatbot.append(['我上传了文件，请查收',