合并重复的函数
This commit is contained in:
qingxu fu
parent
471a369bb8
commit
278464bfb7
@ -1,6 +1,14 @@
|
||||
from functools import lru_cache
|
||||
from toolbox import gen_time_str
|
||||
from toolbox import promote_file_to_downloadzone
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
from colorful import *
|
||||
import requests
|
||||
import random
|
||||
from functools import lru_cache
|
||||
import copy
|
||||
import os
|
||||
import math
|
||||
|
||||
class GROBID_OFFLINE_EXCEPTION(Exception): pass
|
||||
|
||||
def get_avail_grobid_url():
|
||||
@ -28,3 +36,133 @@ def parse_pdf(pdf_path, grobid_url):
|
||||
raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
|
||||
return article_dict
|
||||
|
||||
|
||||
def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files):
|
||||
# -=-=-=-=-=-=-=-= 写出第1个文件：翻译前后混合 -=-=-=-=-=-=-=-=
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=f"{gen_time_str()}translated_and_original.md", file_fullname=None)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
|
||||
# -=-=-=-=-=-=-=-= 写出第2个文件：仅翻译后的文本 -=-=-=-=-=-=-=-=
|
||||
translated_res_array = []
|
||||
# 记录当前的大章节标题：
|
||||
last_section_name = ""
|
||||
for index, value in enumerate(gpt_response_collection):
|
||||
# 先挑选偶数序列号：
|
||||
if index % 2 != 0:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[index-1].split('\n')[0].split(" Part")[0]
|
||||
# 如果index是1的话，则直接使用first section name：
|
||||
if cur_section_name != last_section_name:
|
||||
cur_value = cur_section_name + '\n'
|
||||
last_section_name = copy.deepcopy(cur_section_name)
|
||||
else:
|
||||
cur_value = ""
|
||||
# 再做一个小修改：重新修改当前part的标题，默认用英文的
|
||||
cur_value += value
|
||||
translated_res_array.append(cur_value)
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array,
|
||||
file_basename = f"{gen_time_str()}-translated_only.md",
|
||||
file_fullname = None,
|
||||
auto_caption = False)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
return res_path
|
||||
|
||||
def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
|
||||
from crazy_functions.crazy_utils import construct_html
|
||||
from crazy_functions.crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
|
||||
prompt = "以下是一篇学术论文的基本信息:\n"
|
||||
# title
|
||||
title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
|
||||
# authors
|
||||
authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
|
||||
# abstract
|
||||
abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
|
||||
# command
|
||||
prompt += f"请将题目和摘要翻译为{DST_LANG}。"
|
||||
meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
|
||||
|
||||
# 单线，获取文章meta信息
|
||||
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=prompt,
|
||||
inputs_show_user=prompt,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot, history=[],
|
||||
sys_prompt="You are an academic paper reader。",
|
||||
)
|
||||
|
||||
# 多线，翻译
|
||||
inputs_array = []
|
||||
inputs_show_user_array = []
|
||||
|
||||
# get_token_num
|
||||
from request_llm.bridge_all import model_info
|
||||
enc = model_info[llm_kwargs['llm_model']]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
|
||||
def break_down(txt):
|
||||
raw_token_num = get_token_num(txt)
|
||||
if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
|
||||
return [txt]
|
||||
else:
|
||||
# raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
|
||||
# find a smooth token limit to achieve even seperation
|
||||
count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
|
||||
token_limit_smooth = raw_token_num // count + count
|
||||
return breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn=get_token_num, limit=token_limit_smooth)
|
||||
|
||||
for section in article_dict.get('sections'):
|
||||
if len(section['text']) == 0: continue
|
||||
section_frags = break_down(section['text'])
|
||||
for i, fragment in enumerate(section_frags):
|
||||
heading = section['heading']
|
||||
if len(section_frags) > 1: heading += f' Part-{i+1}'
|
||||
inputs_array.append(
|
||||
f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
|
||||
)
|
||||
inputs_show_user_array.append(
|
||||
f"# {heading}\n\n{fragment}"
|
||||
)
|
||||
|
||||
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,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history_array=[meta for _ in inputs_array],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
|
||||
)
|
||||
# -=-=-=-=-=-=-=-= 写出Markdown文件 -=-=-=-=-=-=-=-=
|
||||
produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
|
||||
|
||||
# -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
if i%2==0:
|
||||
gpt_response_collection_html[i] = inputs_show_user_array[i//2]
|
||||
else:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[i-1].split('\n')[0].split(" Part")[0]
|
||||
cur_value = cur_section_name + "\n" + gpt_response_collection_html[i]
|
||||
gpt_response_collection_html[i] = cur_value
|
||||
|
||||
final = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_html)
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
trans = k
|
||||
ch.add_row(a=orig, b=trans)
|
||||
create_report_file_name = f"{os.path.basename(fp)}.trans.html"
|
||||
html_file = ch.save_file(create_report_file_name)
|
||||
generated_conclusion_files.append(html_file)
|
||||
promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)
|
||||
|
||||
@ -1,11 +1,12 @@
|
||||
from toolbox import CatchException, report_execption, gen_time_str
|
||||
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, get_log_folder
|
||||
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
|
||||
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
|
||||
@ -47,7 +48,7 @@ def markdown_to_dict(article_content):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port, only_chinese=True):
|
||||
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
|
||||
@ -84,15 +85,15 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
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, only_chinese)
|
||||
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, only_chinese=True):
|
||||
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 = 1280
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 512
|
||||
generated_conclusion_files = []
|
||||
generated_html_files = []
|
||||
DST_LANG = "中文"
|
||||
@ -106,129 +107,7 @@ def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
article_content = f.readlines()
|
||||
article_dict = markdown_to_dict(article_content)
|
||||
logging.info(article_dict)
|
||||
|
||||
prompt = "以下是一篇学术论文的基本信息:\n"
|
||||
# title
|
||||
title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
|
||||
# authors
|
||||
authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
|
||||
# abstract
|
||||
abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
|
||||
# command
|
||||
prompt += f"请将题目和摘要翻译为{DST_LANG}。"
|
||||
meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
|
||||
|
||||
# 单线，获取文章meta信息
|
||||
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=prompt,
|
||||
inputs_show_user=prompt,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot, history=[],
|
||||
sys_prompt="You are an academic paper reader。",
|
||||
)
|
||||
|
||||
# 多线，翻译
|
||||
inputs_array = []
|
||||
inputs_show_user_array = []
|
||||
|
||||
# get_token_num
|
||||
from request_llm.bridge_all import model_info
|
||||
enc = model_info[llm_kwargs['llm_model']]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
|
||||
def break_down(txt):
|
||||
raw_token_num = get_token_num(txt)
|
||||
if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
|
||||
return [txt]
|
||||
else:
|
||||
# raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
|
||||
# find a smooth token limit to achieve even seperation
|
||||
count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
|
||||
token_limit_smooth = raw_token_num // count + count
|
||||
return breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn=get_token_num, limit=token_limit_smooth)
|
||||
|
||||
for section in article_dict.get('sections'):
|
||||
if len(section['text']) == 0: continue
|
||||
section_frags = break_down(section['text'])
|
||||
for i, fragment in enumerate(section_frags):
|
||||
heading = section['heading']
|
||||
if len(section_frags) > 1: heading += f' Part-{i+1}'
|
||||
inputs_array.append(
|
||||
f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
|
||||
)
|
||||
inputs_show_user_array.append(
|
||||
f"# {heading}\n\n{fragment}"
|
||||
)
|
||||
|
||||
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,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history_array=[meta for _ in inputs_array],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
|
||||
)
|
||||
if only_chinese:
|
||||
# 直接提取出翻译的内容，然后保存下去：
|
||||
chinese_list = []
|
||||
# 记录当前的大章节标题：
|
||||
last_section_name = ""
|
||||
for index, value in enumerate(gpt_response_collection):
|
||||
# 先挑选偶数序列号：
|
||||
if index % 2 != 0:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[index-1].split('\n')[0].split(" Part")[0]
|
||||
|
||||
# 如果index是1的话，则直接使用first section name：
|
||||
if cur_section_name != last_section_name:
|
||||
cur_value = cur_section_name + '\n'
|
||||
last_section_name = copy.deepcopy(cur_section_name)
|
||||
else:
|
||||
cur_value = ""
|
||||
# 再判断翻译是否错误，如果错误，则直接贴原来的英文：
|
||||
if "The OpenAI account associated" in value:
|
||||
cur_value += gpt_response_collection[index-1]
|
||||
else:
|
||||
# 再做一个小修改：重新修改当前part的标题，默认用英文的
|
||||
cur_value += value
|
||||
|
||||
chinese_list.append(cur_value)
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + chinese_list, file_basename=None, file_fullname=None)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
else:
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=None, file_fullname=None)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
|
||||
# 叠加HTML文件
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
if i%2==0:
|
||||
gpt_response_collection_html[i] = inputs_show_user_array[i//2]
|
||||
else:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[i-1].split('\n')[0].split(" Part")[0]
|
||||
cur_value = cur_section_name + "\n" + gpt_response_collection_html[i]
|
||||
gpt_response_collection_html[i] = cur_value
|
||||
|
||||
final = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_html)
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
trans = k
|
||||
ch.add_row(a=orig, b=trans)
|
||||
create_report_file_name = f"{os.path.basename(fp)}.trans.html"
|
||||
html_file = ch.save_file(create_report_file_name)
|
||||
generated_html_files.append(html_file)
|
||||
promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)
|
||||
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
|
||||
|
||||
@ -1,17 +1,17 @@
|
||||
from toolbox import CatchException, report_execption, write_results_to_file
|
||||
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, get_log_folder
|
||||
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
|
||||
from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
|
||||
from colorful import *
|
||||
import glob
|
||||
import copy
|
||||
import os
|
||||
import math
|
||||
|
||||
@CatchException
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port, only_chinese=True):
|
||||
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
|
||||
@ -51,16 +51,15 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
# 开始正式执行任务
|
||||
grobid_url = get_avail_grobid_url()
|
||||
if grobid_url is not None:
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url, only_chinese=only_chinese)
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
else:
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
|
||||
def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url, only_chinese=True):
|
||||
import copy
|
||||
import tiktoken
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 200
|
||||
def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
|
||||
import copy, json
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 512
|
||||
generated_conclusion_files = []
|
||||
generated_html_files = []
|
||||
DST_LANG = "中文"
|
||||
@ -68,137 +67,23 @@ def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
for index, fp in enumerate(file_manifest):
|
||||
chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
article_dict = parse_pdf(fp, grobid_url)
|
||||
grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
|
||||
with open(grobid_json_res, 'w+', encoding='utf8') as f:
|
||||
f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
|
||||
promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
|
||||
|
||||
if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
|
||||
prompt = "以下是一篇学术论文的基本信息:\n"
|
||||
# title
|
||||
title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
|
||||
# authors
|
||||
authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
|
||||
# abstract
|
||||
abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
|
||||
# command
|
||||
prompt += f"请将题目和摘要翻译为{DST_LANG}。"
|
||||
meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
|
||||
|
||||
# 单线，获取文章meta信息
|
||||
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=prompt,
|
||||
inputs_show_user=prompt,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot, history=[],
|
||||
sys_prompt="You are an academic paper reader。",
|
||||
)
|
||||
|
||||
# 多线，翻译
|
||||
inputs_array = []
|
||||
inputs_show_user_array = []
|
||||
|
||||
# get_token_num
|
||||
from request_llm.bridge_all import model_info
|
||||
enc = model_info[llm_kwargs['llm_model']]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
|
||||
def break_down(txt):
|
||||
raw_token_num = get_token_num(txt)
|
||||
if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
|
||||
return [txt]
|
||||
else:
|
||||
# raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
|
||||
# find a smooth token limit to achieve even seperation
|
||||
count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
|
||||
token_limit_smooth = raw_token_num // count + count
|
||||
return breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn=get_token_num, limit=token_limit_smooth)
|
||||
|
||||
for section in article_dict.get('sections'):
|
||||
if len(section['text']) == 0: continue
|
||||
section_frags = break_down(section['text'])
|
||||
for i, fragment in enumerate(section_frags):
|
||||
heading = section['heading']
|
||||
if len(section_frags) > 1: heading += f' Part-{i+1}'
|
||||
inputs_array.append(
|
||||
f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
|
||||
)
|
||||
inputs_show_user_array.append(
|
||||
f"# {heading}\n\n{fragment}"
|
||||
)
|
||||
|
||||
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,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history_array=[meta for _ in inputs_array],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
|
||||
)
|
||||
if only_chinese:
|
||||
# 直接提取出翻译的内容，然后保存下去：
|
||||
chinese_list = []
|
||||
# 记录当前的大章节标题：
|
||||
last_section_name = ""
|
||||
for index, value in enumerate(gpt_response_collection):
|
||||
# 先挑选偶数序列号：
|
||||
if index % 2 != 0:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[index-1].split('\n')[0].split(" Part")[0]
|
||||
|
||||
# 如果index是1的话，则直接使用first section name：
|
||||
if cur_section_name != last_section_name:
|
||||
cur_value = cur_section_name + '\n'
|
||||
last_section_name = copy.deepcopy(cur_section_name)
|
||||
else:
|
||||
cur_value = ""
|
||||
# 再判断翻译是否错误，如果错误，则直接贴原来的英文：
|
||||
if "The OpenAI account associated" in value:
|
||||
cur_value += gpt_response_collection[index-1]
|
||||
else:
|
||||
# 再做一个小修改：重新修改当前part的标题，默认用英文的
|
||||
cur_value += value
|
||||
|
||||
chinese_list.append(cur_value)
|
||||
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + chinese_list, file_basename=None, file_fullname=None)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
else:
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=None, file_fullname=None)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
|
||||
generated_conclusion_files.append(res_path)
|
||||
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
if i%2==0:
|
||||
gpt_response_collection_html[i] = inputs_show_user_array[i//2]
|
||||
else:
|
||||
# 先提取当前英文标题：
|
||||
cur_section_name = gpt_response_collection[i-1].split('\n')[0].split(" Part")[0]
|
||||
cur_value = cur_section_name + "\n" + gpt_response_collection_html[i]
|
||||
gpt_response_collection_html[i] = cur_value
|
||||
|
||||
final = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_html)
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
trans = k
|
||||
ch.add_row(a=orig, b=trans)
|
||||
create_report_file_name = f"{os.path.basename(fp)}.trans.html"
|
||||
html_file = ch.save_file(create_report_file_name)
|
||||
generated_html_files.append(html_file)
|
||||
promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)
|
||||
|
||||
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
|
||||
|
||||
|
||||
def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
"""
|
||||
此函数已经弃用
|
||||
"""
|
||||
import copy
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 200
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 512
|
||||
generated_conclusion_files = []
|
||||
generated_html_files = []
|
||||
from crazy_functions.crazy_utils import construct_html
|
||||
@ -210,25 +95,20 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
|
||||
# 递归地切割PDF文件
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
# from .crazy_utils import split_main_text
|
||||
from request_llm.bridge_all import model_info
|
||||
enc = model_info["gpt-3.5-turbo"]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
||||
txt=file_content, get_token_fn=get_token_num, limit=256)
|
||||
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
||||
page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
||||
txt=page_one, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
||||
## 用我这个分段切分。
|
||||
# paper_fragments = split_main_text(text=file_content, max_token=TOKEN_LIMIT_PER_FRAGMENT)
|
||||
# page_one_fragments = split_main_text(text=page_one, max_token=TOKEN_LIMIT_PER_FRAGMENT)
|
||||
txt=page_one, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
|
||||
|
||||
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
|
||||
# paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
|
||||
paper_meta = page_one_fragments[:]
|
||||
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
|
||||
|
||||
# 单线，获取文章meta信息
|
||||
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“作者单位”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分，不要提取Introduction部分的内容。请提取：{paper_meta}",
|
||||
inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
|
||||
inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot, history=[],
|
||||
@ -244,62 +124,24 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
chatbot=chatbot,
|
||||
history_array=[[paper_meta] for _ in paper_fragments],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文的部分章节文本，准确翻译成中文。注意：1. 文章中的每一句话都要翻译，并且消除输入文本前后的无意义乱码，2. 请自动识别小章节标题(小标题长度不要超过20个字符，也不要少于3个字符)，并且用'### xxx'的markdown格式标记出来。" for _ in paper_fragments],
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
|
||||
# max_workers=5 # OpenAI所允许的最大并行过载
|
||||
)
|
||||
gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
|
||||
# 整理报告的格式
|
||||
add_origin = True
|
||||
for i, k in enumerate(gpt_response_collection_md):
|
||||
if i % 2 ==0:
|
||||
cur_trans = gpt_response_collection_md[i]
|
||||
# 做个小小的处理，把翻译的结果中非常长的“#”去掉
|
||||
temp_trans = ""
|
||||
for line_text in cur_trans.split('\n'):
|
||||
if len(line_text) == 0:
|
||||
# print("空行")
|
||||
temp_trans += "\n\n"
|
||||
else:
|
||||
if "#" in line_text[0]:
|
||||
if len(line_text.split(' ')) > 12:
|
||||
temp_trans += line_text.replace('#', '')
|
||||
else:
|
||||
temp_trans += line_text
|
||||
temp_trans += "\n\n"
|
||||
else:
|
||||
temp_trans += line_text + "\n\n"
|
||||
|
||||
# gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')} \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
|
||||
if add_origin:
|
||||
for i,k in enumerate(gpt_response_collection_md):
|
||||
if i%2==0:
|
||||
gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')} \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
|
||||
else:
|
||||
gpt_response_collection_md[i] = ""
|
||||
else:
|
||||
cur_trans = gpt_response_collection_md[i]
|
||||
# 做个小小的处理，把翻译的结果中非常长的“#”去掉
|
||||
temp_trans = ""
|
||||
for line_text in cur_trans.split('\n'):
|
||||
if len(line_text) == 0:
|
||||
# print("空行")
|
||||
temp_trans += "\n\n"
|
||||
else:
|
||||
if "#" in line_text[0]:
|
||||
if len(line_text) > 12:
|
||||
temp_trans += line_text.replace('#', '')
|
||||
else:
|
||||
temp_trans += line_text
|
||||
temp_trans += "\n\n"
|
||||
else:
|
||||
temp_trans += line_text + "\n\n"
|
||||
|
||||
gpt_response_collection_md[i] = temp_trans
|
||||
gpt_response_collection_md[i] = gpt_response_collection_md[i]
|
||||
final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_md)
|
||||
create_report_file_name = f"{os.path.basename(fp)}.trans.md"
|
||||
res = write_results_to_file(final, file_name=create_report_file_name)
|
||||
res = write_history_to_file(final, create_report_file_name)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
|
||||
# 更新UI
|
||||
generated_conclusion_files.append(f'./gpt_log/{create_report_file_name}')
|
||||
generated_conclusion_files.append(f'{get_log_folder()}/{create_report_file_name}')
|
||||
chatbot.append((f"{fp}完成了吗？", res))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
@ -216,7 +216,7 @@ def get_reduce_token_percent(text):
|
||||
return 0.5, '不详'
|
||||
|
||||
|
||||
def write_history_to_file(history, file_basename=None, file_fullname=None):
|
||||
def write_history_to_file(history, file_basename=None, file_fullname=None, auto_caption=True):
|
||||
"""
|
||||
将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
|
||||
"""
|
||||
@ -235,7 +235,7 @@ def write_history_to_file(history, file_basename=None, file_fullname=None):
|
||||
if type(content) != str: content = str(content)
|
||||
except:
|
||||
continue
|
||||
if i % 2 == 0:
|
||||
if i % 2 == 0 and auto_caption:
|
||||
f.write('## ')
|
||||
try:
|
||||
f.write(content)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user