Add parsing arbitrary code items

This commit is contained in:
mrhblfx 2023-04-16 23:00:45 +08:00
parent f0fbc65a36
commit 2f9a4e1618
4 changed files with 84 additions and 25 deletions

View File

@ -162,7 +162,7 @@ def get_crazy_functions():
"AsButton": False, # 加入下拉菜单中
"Function": HotReload(Markdown英译中)
},
})
###################### 第三组插件 ###########################
@ -179,8 +179,16 @@ def get_crazy_functions():
except Exception as err:
print(f'[下载arxiv论文并翻译摘要] 插件导入失败 {str(err)}')
from crazy_functions.解析项目源代码 import 解析任意code项目
function_plugins.update({
"解析任意code项目": {
"Color": "stop",
"AsButton": False,
"Function": HotReload(解析任意code项目)
},
})
###################### 第n组插件 ###########################
return function_plugins

View File

@ -11,7 +11,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
history_array = []
sys_prompt_array = []
report_part_1 = []
assert len(file_manifest) <= 1024, "源文件太多超过1024个, 请缩减输入文件的数量。或者您也可以选择删除此行警告并修改代码拆分file_manifest列表从而实现分批次处理。"
############################## <第一步,逐个文件分析,多线程> ##################################
for index, fp in enumerate(file_manifest):
@ -63,10 +63,10 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
current_iteration_focus = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
i_say = f'根据以上分析对程序的整体功能和构架重新做出概括。然后用一张markdown表格整理每个文件的功能包括{previous_iteration_files_string})。'
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 = copy.deepcopy(this_iteration_gpt_response_collection)
this_iteration_history.append(last_iteration_result)
result = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
inputs=i_say, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
history=this_iteration_history, # 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])
@ -222,8 +222,8 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
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):
history = [] # 清空历史,以免输入溢出
@ -243,9 +243,9 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何lua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)
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CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史,以免输入溢出
@ -263,4 +263,35 @@ def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何CSharp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)
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
@CatchException
def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
txt_include = plugin_kwargs.get("txt_include")
txt_except = plugin_kwargs.get("txt_except")
# 将要匹配的后缀
pattern_include = [_.lstrip(" .,").rstrip(" ,") for _ in txt_include.split(" ") if _ != ""]
pattern_include = [_.lstrip(" .,").rstrip(" ,") for __ in pattern_include for _ in __.split(",") if _ != ""]
pattern_include = [_.lstrip(" .,").rstrip(" ,") for __ in pattern_include for _ in __.split("") if _ != ""]
# 将要忽略匹配的后缀
pattern_except = [_.lstrip(" .,").rstrip(" ,") for _ in txt_except.split(" ") if _ != ""]
pattern_except = [_.lstrip(" .,").rstrip(" ,") for __ in pattern_except for _ in __.split(",") if _ != ""]
pattern_except = [_.lstrip(" .,").rstrip(" ,") for __ in pattern_except for _ in __.split("") if _ != ""]
pattern_except += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析上传的压缩文件
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}/**/*.*', recursive=True) if os.path.isfile(f) and \
([] == pattern_include or f.split(".")[-1] in pattern_include) and f.split(".")[-1] not in pattern_except]
if len(file_manifest) == 0:
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何文件: {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)

27
main.py
View File

@ -44,7 +44,7 @@ proxy_info = check_proxy(proxies)
gr_L1 = lambda: gr.Row().style()
gr_L2 = lambda scale: gr.Column(scale=scale)
if LAYOUT == "TOP-DOWN":
if LAYOUT == "TOP-DOWN":
gr_L1 = lambda: DummyWith()
gr_L2 = lambda scale: gr.Row()
CHATBOT_HEIGHT /= 2
@ -83,9 +83,23 @@ with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=
variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
crazy_fns[k]["Button"] = gr.Button(k, variant=variant)
crazy_fns[k]["Button"].style(size="sm")
with gr.Row():
with gr.Accordion("解析任意code项目", open=True):
gr.Markdown("输入的文件后缀用空格或逗号隔开, 可混合使用空格逗号")
with gr.Row():
gr.Markdown("将要匹配文件的后缀, 不输入则代表解析所有文件")
txt_pattern_include = gr.Textbox(show_label=False, placeholder="例如: .c .cpp .py").style(container=False)
with gr.Row():
gr.Markdown("将要忽略匹配文件的后缀")
txt_pattern_except = gr.Textbox(show_label=False, placeholder="例如: .png, .jpg wav flac").style(container=False)
code_plugin_name = "解析任意code项目"
variant = crazy_fns[code_plugin_name]["Color"] if "Color" in crazy_fns[code_plugin_name] else "secondary"
crazy_fns[code_plugin_name]["Button"] = gr.Button(code_plugin_name, variant=variant)
crazy_fns[code_plugin_name]["Button"].style(size="sm")
with gr.Row():
with gr.Accordion("更多函数插件", open=True):
dropdown_fn_list = [k for k in crazy_fns.keys() if not crazy_fns[k].get("AsButton", True)]
dropdown_fn_list.remove(code_plugin_name)
with gr.Column(scale=1):
dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
with gr.Column(scale=1):
@ -118,7 +132,8 @@ with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=
return ret
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2] )
# 整理反复出现的控件句柄组合
input_combo = [cookies, txt, txt2, top_p, temperature, chatbot, history, system_prompt]
add_input_combo = (txt_pattern_include, txt_pattern_except)
input_combo = [cookies, txt, txt2, top_p, temperature, chatbot, history, system_prompt, *add_input_combo]
output_combo = [cookies, chatbot, history, status]
predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=input_combo, outputs=output_combo)
# 提交按钮、重置按钮
@ -140,6 +155,10 @@ with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=
click_handle = crazy_fns[k]["Button"].click(ArgsGeneralWrapper(crazy_fns[k]["Function"]), [*input_combo, gr.State(PORT)], output_combo)
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
cancel_handles.append(click_handle)
# 函数插件-解析任意code项目
click_handle = crazy_fns[code_plugin_name]["Button"].click(ArgsGeneralWrapper(crazy_fns[code_plugin_name]["Function"]), [*input_combo, gr.State(PORT)], output_combo)
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
cancel_handles.append(click_handle)
# 函数插件-下拉菜单与随变按钮的互动
def on_dropdown_changed(k):
variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
@ -147,7 +166,7 @@ with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=
dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt] )
# 随变按钮的回调函数注册
def route(k, *args, **kwargs):
if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs)
click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo)
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
@ -164,7 +183,7 @@ def auto_opentab_delay():
print(f"如果浏览器没有自动打开请复制并转到以下URL")
print(f"\t(亮色主题): http://localhost:{PORT}")
print(f"\t(暗色主题): http://localhost:{PORT}/?__dark-theme=true")
def open():
def open():
time.sleep(2) # 打开浏览器
webbrowser.open_new_tab(f"http://localhost:{PORT}/?__dark-theme=true")
threading.Thread(target=open, name="open-browser", daemon=True).start()

View File

@ -27,23 +27,24 @@ def ArgsGeneralWrapper(f):
"""
装饰器函数用于重组输入参数改变输入参数的顺序与结构
"""
def decorated(cookies, txt, txt2, top_p, temperature, chatbot, history, system_prompt, *args):
def decorated(cookies, txt, txt2, top_p, temperature, chatbot, history, system_prompt, txt_include, txt_except, *args):
txt_passon = txt
if txt == "" and txt2 != "": txt_passon = txt2
# 引入一个有cookie的chatbot
cookies.update({
'top_p':top_p,
'top_p':top_p,
'temperature':temperature,
})
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'],
'top_p':top_p,
'top_p':top_p,
'temperature':temperature,
}
plugin_kwargs = {
# 目前还没有
}
# plugin_kwargs = {
# # 目前还没有
# }
plugin_kwargs = dict(txt_include = txt_include, txt_except = txt_except)
chatbot_with_cookie = ChatBotWithCookies(cookies)
chatbot_with_cookie.write_list(chatbot)
yield from f(txt_passon, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, system_prompt, *args)
@ -279,7 +280,7 @@ def markdown_convertion(txt):
return content
else:
return tex2mathml_catch_exception(content)
def markdown_bug_hunt(content):
"""
解决一个mdx_math的bug$包裹begin命令时多余<script>
@ -287,7 +288,7 @@ def markdown_convertion(txt):
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
content = content.replace('</script>\n</script>', '</script>')
return content
if ('$' in txt) and ('```' not in txt): # 有$标识的公式符号,且没有代码段```的标识
# convert everything to html format
@ -308,7 +309,7 @@ def markdown_convertion(txt):
def close_up_code_segment_during_stream(gpt_reply):
"""
在gpt输出代码的中途输出了前面的```但还没输出完后面的```补上后面的```
Args:
gpt_reply (str): GPT模型返回的回复字符串
@ -518,7 +519,7 @@ class DummyWith():
它的作用是没用即在代码结构不变得情况下取代其他的上下文管理器
上下文管理器是一种Python对象用于与with语句一起使用
以确保一些资源在代码块执行期间得到正确的初始化和清理
上下文管理器必须实现两个方法分别为 __enter__() __exit__()
上下文管理器必须实现两个方法分别为 __enter__() __exit__()
在上下文执行开始的情况下__enter__()方法会在代码块被执行前被调用
而在上下文执行结束时__exit__()方法则会被调用
"""