Spaces:
Running
Running
File size: 4,912 Bytes
971ac20 5c0a088 971ac20 5c0a088 971ac20 5c0a088 971ac20 5c0a088 971ac20 5c0a088 f8946c1 5c0a088 f8946c1 971ac20 5c0a088 971ac20 5c0a088 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
from toolbox import CatchException, report_execption, get_log_folder, gen_time_str
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
from toolbox import write_history_to_file, promote_file_to_downloadzone
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from .crazy_utils import read_and_clean_pdf_text
from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
from colorful import *
import copy
import os
import math
import logging
def markdown_to_dict(article_content):
import markdown
from bs4 import BeautifulSoup
cur_t = ""
cur_c = ""
results = {}
for line in article_content:
if line.startswith('#'):
if cur_t!="":
if cur_t not in results:
results.update({cur_t:cur_c.lstrip('\n')})
else:
# 处理重名的章节
results.update({cur_t + " " + gen_time_str():cur_c.lstrip('\n')})
cur_t = line.rstrip('\n')
cur_c = ""
else:
cur_c += line
results_final = {}
for k in list(results.keys()):
if k.startswith('# '):
results_final['title'] = k.split('# ')[-1]
results_final['authors'] = results.pop(k).lstrip('\n')
if k.startswith('###### Abstract'):
results_final['abstract'] = results.pop(k).lstrip('\n')
results_final_sections = []
for k,v in results.items():
results_final_sections.append({
'heading':k.lstrip("# "),
'text':v if len(v) > 0 else f"The beginning of {k.lstrip('# ')} section."
})
results_final['sections'] = results_final_sections
return results_final
@CatchException
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
disable_auto_promotion(chatbot)
# 基本信息：功能、贡献者
chatbot.append([
"函数插件功能？",
"批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 尝试导入依赖，如果缺少依赖，则给出安装建议
try:
import nougat
import tiktoken
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 nougat-ocr tiktoken```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 清空历史，以免输入溢出
history = []
from .crazy_utils import get_files_from_everything
success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
# 检测输入参数，如没有给定输入参数，直接退出
if not success:
if txt == "": txt = '空空如也的输入栏'
# 如果没找到任何文件
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) # 刷新界面
return
# 开始正式执行任务
yield from 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
import copy
import tiktoken
TOKEN_LIMIT_PER_FRAGMENT = 1024
generated_conclusion_files = []
generated_html_files = []
DST_LANG = "中文"
from crazy_functions.crazy_utils import nougat_interface, construct_html
nougat_handle = nougat_interface()
for index, fp in enumerate(file_manifest):
chatbot.append(["当前进度：", f"正在解析论文，请稍候。（第一次运行时，需要花费较长时间下载NOUGAT参数）"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
fpp = yield from nougat_handle.NOUGAT_parse_pdf(fp, chatbot, history)
promote_file_to_downloadzone(fpp, rename_file=os.path.basename(fpp)+'.nougat.mmd', chatbot=chatbot)
with open(fpp, 'r', encoding='utf8') as f:
article_content = f.readlines()
article_dict = markdown_to_dict(article_content)
logging.info(article_dict)
yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|