Files
gpt_academic/crazy_functions/解析项目源代码炫酷版.py
qingxu fu fb22f716ff 3d interp
2023-07-25 10:09:50 +08:00

137 lines
7.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from toolbox import update_ui
from toolbox import CatchException, report_execption, write_results_to_file
from toolbox import objdump, objload
from .crazy_utils import input_clipping
class ThreeJSPlot():
def __init__(self) -> None:
self.files = None
def read_files(self, files):
self.files = files
def launch_render_interface(self):
from vhmap.mcom import mcom
self.visual_bridge = mcom()
def 解析源代码炫酷版(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
import os, copy
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 = []
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):
# 读取文件
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
prefix = "接下来请你逐文件分析下面的工程" if index==0 else ""
i_say = prefix + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)},文件代码是 ```{file_content}```'
i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {os.path.abspath(fp)}'
# 装载请求内容
inputs_array.append(i_say)
inputs_show_user_array.append(i_say_show_user)
history_array.append([])
sys_prompt_array.append("你是一个程序架构分析师,正在分析一个源代码项目。你的回答必须简单明了。")
def callback_when_intel_update(gpt_reply_array):
objdump((gpt_reply_array, file_manifest))
return
# 文件读取完成对每一个源代码文件生成一个请求线程发送到chatgpt进行分析
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,
history_array = history_array,
sys_prompt_array = sys_prompt_array,
llm_kwargs = llm_kwargs,
chatbot = chatbot,
show_user_at_complete = True,
callback_fn=callback_when_intel_update,
)
# 全部文件解析完成,结果写入文件,准备对工程源代码进行汇总分析
report_part_1 = copy.deepcopy(gpt_response_collection)
history_to_return = report_part_1
res = write_results_to_file(report_part_1)
chatbot.append(("完成?", "逐个文件分析已完成。" + res + "\n\n正在开始汇总。"))
yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
############################## <第二步,综合,单线程,分组+迭代处理> ##################################
############################## <END> ##################################
history_to_return.extend([])
res = write_results_to_file(history_to_return)
chatbot.append(("完成了吗?", res))
yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
@CatchException
def 解析一个Python项目炫酷版(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}/**/*.py', 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python文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
yield from 解析源代码炫酷版(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
@CatchException
def 解析任意code项目炫酷版(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)