Merge pull request #502 from mrhblfx/new_code_fun
解析项目源代码（手动指定和筛选源代码文件类型）
This commit is contained in:
binary-husky
GitHub
commit
7d14de79bf
@ -174,7 +174,7 @@ def get_crazy_functions():
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(Markdown英译中)
|
||||
},
|
||||
|
||||
|
||||
})
|
||||
|
||||
###################### 第三组插件 ###########################
|
||||
@ -187,7 +187,7 @@ def get_crazy_functions():
|
||||
"Function": HotReload(下载arxiv论文并翻译摘要)
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
from crazy_functions.联网的ChatGPT import 连接网络回答问题
|
||||
function_plugins.update({
|
||||
"连接网络回答问题（先输入问题，再点击按钮，需要访问谷歌）": {
|
||||
@ -197,5 +197,16 @@ def get_crazy_functions():
|
||||
}
|
||||
})
|
||||
|
||||
from crazy_functions.解析项目源代码 import 解析任意code项目
|
||||
function_plugins.update({
|
||||
"解析项目源代码（手动指定和筛选源代码文件类型）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
"ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
|
||||
"Function": HotReload(解析任意code项目)
|
||||
},
|
||||
})
|
||||
|
||||
###################### 第n组插件 ###########################
|
||||
return function_plugins
|
||||
|
||||
@ -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) <= 512, "源文件太多（超过512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 +263,45 @@ 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_pattern = plugin_kwargs.get("advanced_arg")
|
||||
txt_pattern = txt_pattern.replace("，", ",")
|
||||
# 将要匹配的模式(例如: *.c, *.cpp, *.py, config.toml)
|
||||
pattern_include = [_.lstrip(" ,").rstrip(" ,") for _ in txt_pattern.split(",") if _ != "" and not _.strip().startswith("^")]
|
||||
if not pattern_include: pattern_include = ["*"] # 不输入即全部匹配
|
||||
# 将要忽略匹配的文件后缀(例如: ^*.c, ^*.cpp, ^*.py)
|
||||
pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
|
||||
pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
|
||||
# 将要忽略匹配的文件名(例如: ^README.md)
|
||||
pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
|
||||
# 生成正则表达式
|
||||
pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
|
||||
pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
|
||||
|
||||
history.clear()
|
||||
import glob, os, re
|
||||
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
|
||||
# 若上传压缩文件, 先寻找到解压的文件夹路径, 从而避免解析压缩文件
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir)>0 and maybe_dir[0].endswith('.extract'):
|
||||
extract_folder_path = maybe_dir[0]
|
||||
else:
|
||||
extract_folder_path = project_folder
|
||||
# 按输入的匹配模式寻找上传的非压缩文件和已解压的文件
|
||||
file_manifest = [f for pattern in pattern_include for f in glob.glob(f'{extract_folder_path}/**/{pattern}', recursive=True) if "" != extract_folder_path and \
|
||||
os.path.isfile(f) and (not re.search(pattern_except, f) or pattern.endswith('.' + re.search(pattern_except, f).group().split('.')[-1]))]
|
||||
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)
|
||||
29
main.py
29
main.py
@ -45,7 +45,7 @@ def main():
|
||||
|
||||
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
|
||||
@ -88,9 +88,12 @@ def main():
|
||||
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)]
|
||||
with gr.Column(scale=1):
|
||||
with gr.Row():
|
||||
dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
|
||||
with gr.Column(scale=1):
|
||||
with gr.Row():
|
||||
plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
|
||||
placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
|
||||
with gr.Row():
|
||||
switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary")
|
||||
with gr.Row():
|
||||
with gr.Accordion("点击展开“文件上传区”。上传本地文件可供红色函数插件调用。", open=False) as area_file_up:
|
||||
@ -100,7 +103,7 @@ def main():
|
||||
top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
|
||||
temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
|
||||
max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="Local LLM MaxLength",)
|
||||
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
|
||||
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
|
||||
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
|
||||
|
||||
gr.Markdown(description)
|
||||
@ -122,11 +125,12 @@ def main():
|
||||
ret.update({area_input_secondary: gr.update(visible=("底部输入区" in a))})
|
||||
ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
|
||||
ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
|
||||
if "底部输入区" in a: ret.update({txt: gr.update(value="")})
|
||||
return ret
|
||||
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2] )
|
||||
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
|
||||
# 整理反复出现的控件句柄组合
|
||||
input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt]
|
||||
input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
|
||||
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
|
||||
@ -153,14 +157,19 @@ def main():
|
||||
# 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"
|
||||
return {switchy_bt: gr.update(value=k, variant=variant)}
|
||||
dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt] )
|
||||
ret = {switchy_bt: gr.update(value=k, variant=variant)}
|
||||
if crazy_fns[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=True, label=f"插件[{k}]的高级参数说明：" + crazy_fns[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
|
||||
else:
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
|
||||
return ret
|
||||
dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
|
||||
def on_md_dropdown_changed(k):
|
||||
return {chatbot: gr.update(label="当前模型："+k)}
|
||||
md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
|
||||
# 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])
|
||||
@ -178,7 +187,7 @@ def main():
|
||||
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()
|
||||
|
||||
16
toolbox.py
16
toolbox.py
@ -24,23 +24,23 @@ 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, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, *args):
|
||||
def decorated(cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg, *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': llm_model,
|
||||
'top_p':top_p,
|
||||
'top_p':top_p,
|
||||
'max_length': max_length,
|
||||
'temperature':temperature,
|
||||
}
|
||||
plugin_kwargs = {
|
||||
# 目前还没有
|
||||
"advanced_arg": plugin_advanced_arg,
|
||||
}
|
||||
chatbot_with_cookie = ChatBotWithCookies(cookies)
|
||||
chatbot_with_cookie.write_list(chatbot)
|
||||
@ -219,7 +219,7 @@ 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（单$包裹begin命令时多余<script>）
|
||||
@ -227,7 +227,7 @@ def markdown_convertion(txt):
|
||||
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
|
||||
content = content.replace('</script>\n</script>', '</script>')
|
||||
return content
|
||||
|
||||
|
||||
|
||||
if ('$' 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
|
||||
@ -248,7 +248,7 @@ 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。
|
||||
|
||||
@ -511,7 +511,7 @@ class DummyWith():
|
||||
它的作用是……额……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__()和 __exit__()。
|
||||
上下文管理器必须实现两个方法，分别为 __enter__()和 __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。
|
||||
"""
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user