|
from request_llm.bridge_chatgpt import predict_no_ui |
|
from toolbox import update_ui |
|
from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down |
|
import re |
|
import unicodedata |
|
fast_debug = False |
|
|
|
def is_paragraph_break(match): |
|
""" |
|
根据给定的匹配结果来判断换行符是否表示段落分隔。 |
|
如果换行符前为句子结束标志(句号,感叹号,问号),且下一个字符为大写字母,则换行符更有可能表示段落分隔。 |
|
也可以根据之前的内容长度来判断段落是否已经足够长。 |
|
""" |
|
prev_char, next_char = match.groups() |
|
|
|
|
|
sentence_endings = ".!?" |
|
|
|
|
|
min_paragraph_length = 140 |
|
|
|
if prev_char in sentence_endings and next_char.isupper() and len(match.string[:match.start(1)]) > min_paragraph_length: |
|
return "\n\n" |
|
else: |
|
return " " |
|
|
|
def normalize_text(text): |
|
""" |
|
通过把连字(ligatures)等文本特殊符号转换为其基本形式来对文本进行归一化处理。 |
|
例如,将连字 "fi" 转换为 "f" 和 "i"。 |
|
""" |
|
|
|
normalized_text = unicodedata.normalize("NFKD", text) |
|
|
|
|
|
cleaned_text = re.sub(r'[^\x00-\x7F]+', '', normalized_text) |
|
|
|
return cleaned_text |
|
|
|
def clean_text(raw_text): |
|
""" |
|
对从 PDF 提取出的原始文本进行清洗和格式化处理。 |
|
1. 对原始文本进行归一化处理。 |
|
2. 替换跨行的连词,例如 “Espe-\ncially” 转换为 “Especially”。 |
|
3. 根据 heuristic 规则判断换行符是否是段落分隔,并相应地进行替换。 |
|
""" |
|
|
|
normalized_text = normalize_text(raw_text) |
|
|
|
|
|
text = re.sub(r'(\w+-\n\w+)', lambda m: m.group(1).replace('-\n', ''), normalized_text) |
|
|
|
|
|
newlines = re.compile(r'(\S)\n(\S)') |
|
|
|
|
|
final_text = re.sub(newlines, lambda m: m.group(1) + is_paragraph_break(m) + m.group(2), text) |
|
|
|
return final_text.strip() |
|
|
|
def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt): |
|
import time, glob, os, fitz |
|
print('begin analysis on:', file_manifest) |
|
for index, fp in enumerate(file_manifest): |
|
with fitz.open(fp) as doc: |
|
file_content = "" |
|
for page in doc: |
|
file_content += page.get_text() |
|
file_content = clean_text(file_content) |
|
print(file_content) |
|
|
|
prefix = "接下来请你逐文件分析下面的论文文件,概括其内容" if index==0 else "" |
|
i_say = prefix + f'请对下面的文章片段用中文做一个概述,文件名是{os.path.relpath(fp, project_folder)},文章内容是 ```{file_content}```' |
|
i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}' |
|
chatbot.append((i_say_show_user, "[Local Message] waiting gpt response.")) |
|
yield from update_ui(chatbot=chatbot, history=history) |
|
|
|
if not fast_debug: |
|
msg = '正常' |
|
|
|
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, llm_kwargs, plugin_kwargs, history=[]) |
|
|
|
chatbot[-1] = (i_say_show_user, gpt_say) |
|
history.append(i_say_show_user); history.append(gpt_say) |
|
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) |
|
if not fast_debug: time.sleep(2) |
|
|
|
all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)]) |
|
i_say = f'根据以上你自己的分析,对全文进行概括,用学术性语言写一段中文摘要,然后再写一段英文摘要(包括{all_file})。' |
|
chatbot.append((i_say, "[Local Message] waiting gpt response.")) |
|
yield from update_ui(chatbot=chatbot, history=history) |
|
|
|
if not fast_debug: |
|
msg = '正常' |
|
|
|
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, llm_kwargs, plugin_kwargs, history=history) |
|
|
|
chatbot[-1] = (i_say, gpt_say) |
|
history.append(i_say); history.append(gpt_say) |
|
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) |
|
res = write_results_to_file(history) |
|
chatbot.append(("完成了吗?", res)) |
|
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) |
|
|
|
|
|
@CatchException |
|
def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): |
|
import glob, os |
|
|
|
|
|
chatbot.append([ |
|
"函数插件功能?", |
|
"批量总结PDF文档。函数插件贡献者: ValeriaWong,Eralien"]) |
|
yield from update_ui(chatbot=chatbot, history=history) |
|
|
|
|
|
try: |
|
import fitz |
|
except: |
|
report_execption(chatbot, history, |
|
a = f"解析项目: {txt}", |
|
b = f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade pymupdf```。") |
|
yield from update_ui(chatbot=chatbot, history=history) |
|
return |
|
|
|
|
|
history = [] |
|
|
|
|
|
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) |
|
return |
|
|
|
|
|
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', 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.tex或.pdf文件: {txt}") |
|
yield from update_ui(chatbot=chatbot, history=history) |
|
return |
|
|
|
|
|
yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt) |
|
|