chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

新版HTML报告页面

Browse Source
This commit is contained in:
qingxu fu 2023-10-16 22:13:59 +08:00
parent ea28db855d
commit 4ad432e1da
7 changed files with 158 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
crazy_functions/crazy_utils.py
View File

@ -767,54 +767,6 @@ def try_install_deps(deps, reload_m=[]):
importlib.reload(__import__(m))
HTML_CSS = """
.row {
display: flex;
flex-wrap: wrap;
}
.column {
flex: 1;
padding: 10px;
}
.table-header {
font-weight: bold;
border-bottom: 1px solid black;
}
.table-row {
border-bottom: 1px solid lightgray;
}
.table-cell {
padding: 5px;
}
"""
TABLE_CSS = """
<div class="row table-row">
<div class="column table-cell">REPLACE_A</div>
<div class="column table-cell">REPLACE_B</div>
</div>
"""
class construct_html():
def __init__(self) -> None:
self.css = HTML_CSS
self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
def add_row(self, a, b):
tmp = TABLE_CSS
from toolbox import markdown_convertion
tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
self.html_string += tmp
def save_file(self, file_name):
with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
f.write(self.html_string.encode('utf-8', 'ignore').decode())
return os.path.join(get_log_folder(), file_name)
def get_plugin_arg(plugin_kwargs, key, default):
# 如果参数是空的
if (key in plugin_kwargs) and (plugin_kwargs[key] == ""): plugin_kwargs.pop(key)

2
crazy_functions/latex_fns/latex_actions.py
View File

@ -423,7 +423,7 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
# write html
try:
import shutil
from ..crazy_utils import construct_html
from crazy_functions.pdf_fns.report_gen_html import construct_html
from toolbox import gen_time_str
ch = construct_html()
orig = ""

2
crazy_functions/pdf_fns/parse_pdf.py
View File

@ -73,7 +73,7 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
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.pdf_fns.report_gen_html 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

48
crazy_functions/pdf_fns/report_gen_html.py Normal file
View File

@ -0,0 +1,48 @@
from toolbox import update_ui, get_conf, trimmed_format_exc, get_log_folder
import os
class construct_html():
def __init__(self) -> None:
self.html_string = ""
def add_row(self, a, b):
from toolbox import markdown_convertion
template = """
{
primary_col: {
header: `__PRIMARY_HEADER__`,
msg: `__PRIMARY_MSG__`,
},
secondary_rol: {
header: `__SECONDARY_HEADER__`,
msg: `__SECONDARY_MSG__`,
}
},
"""
template_ = template
if len(a.split('\n')) == 1:
template_ = template_.replace("__PRIMARY_HEADER__", markdown_convertion(a[:10]) + ' ...')
template_ = template_.replace("__PRIMARY_MSG__", markdown_convertion(a))
else:
template_ = template_.replace("__PRIMARY_HEADER__", markdown_convertion(a.split('\n')[0]))
template_ = template_.replace("__PRIMARY_MSG__", markdown_convertion('\n'.join(a.split('\n')[1:])))
if len(b.split('\n')) == 1:
template_ = template_.replace("__SECONDARY_HEADER__", markdown_convertion(b[:10]) + ' ...')
template_ = template_.replace("__SECONDARY_MSG__", markdown_convertion(b))
else:
template_ = template_.replace("__SECONDARY_HEADER__", markdown_convertion(b.split('\n')[0]))
template_ = template_.replace("__SECONDARY_MSG__", markdown_convertion('\n'.join(b.split('\n')[1:])))
self.html_string += template_
def save_file(self, file_name):
from toolbox import get_log_folder
with open('crazy_functions/pdf_fns/report_template.html', 'r', encoding='utf8') as f:
html_template = f.read()
html_template = html_template.replace("__TF_ARR__", self.html_string)
with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
f.write(html_template.encode('utf-8', 'ignore').decode())
return os.path.join(get_log_folder(), file_name)

104
crazy_functions/pdf_fns/report_template.html Normal file
View File

File diff suppressed because one or more lines are too long

3
crazy_functions/批量翻译PDF文档_NOUGAT.py
View File

@ -97,7 +97,8 @@ def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwa
generated_conclusion_files = []
generated_html_files = []
DST_LANG = "中文"
from crazy_functions.crazy_utils import nougat_interface, construct_html
from crazy_functions.crazy_utils import nougat_interface
from crazy_functions.pdf_fns.report_gen_html import 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

4
crazy_functions/批量翻译PDF文档_多线程.py
View File

@ -63,7 +63,7 @@ def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwa
generated_conclusion_files = []
generated_html_files = []
DST_LANG = "中文"
from crazy_functions.crazy_utils import construct_html
from crazy_functions.pdf_fns.report_gen_html import construct_html
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)
@ -86,7 +86,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
TOKEN_LIMIT_PER_FRAGMENT = 1024
generated_conclusion_files = []
generated_html_files = []
from crazy_functions.crazy_utils import construct_html
from crazy_functions.pdf_fns.report_gen_html import construct_html
for index, fp in enumerate(file_manifest):
# 读取PDF文件
file_content, page_one = read_and_clean_pdf_text(fp)