minor pdf translation adjustment
This commit is contained in:
binary-husky
parent
744759704d
commit
bd5280df1b
@ -1,7 +1,7 @@
|
||||
from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
|
||||
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, get_conf, extract_archive
|
||||
from toolbox import get_upload_folder, zip_folder
|
||||
from toolbox import generate_file_link, zip_folder, trimmed_format_exc, trimmed_format_exc_markdown
|
||||
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
|
||||
@ -52,7 +52,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
yield from 解析PDF_DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
|
||||
return
|
||||
except:
|
||||
chatbot.append([None, "DOC2X服务不可用，现在将执行效果稍差的旧版代码。"])
|
||||
chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# ------- 第二种方法，效果次优 -------
|
||||
@ -146,6 +146,21 @@ def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, cha
|
||||
promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 生成在线预览html
|
||||
file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
# Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
md = re.sub(r'^<table>', r'😃<table>', md, flags=re.MULTILINE)
|
||||
html = markdown_convertion_for_file(md)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
|
||||
|
||||
|
||||
chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
|
||||
plugin_kwargs['markdown_expected_output_dir'] = ex_folder
|
||||
|
||||
@ -157,21 +172,16 @@ def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, cha
|
||||
# 修正一些公式问题
|
||||
with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
|
||||
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||
# Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
content = re.sub(r'^<table>', r'😃<table>', content, flags=re.MULTILINE)
|
||||
with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
|
||||
# 生成在线预览html
|
||||
file_name = '在线预览翻译' + gen_time_str() + '.html'
|
||||
# with open('crazy_functions/pdf_fns/report_template_v2.html', 'r', encoding='utf8') as f:
|
||||
# html_template = f.read()
|
||||
# html_template = html_template.replace("{MARKDOWN_FILE_PATH}", translated_f_name)
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
# with open(preview_fp, 'w', encoding='utf8') as f:
|
||||
# f.write(html_template)
|
||||
# 生成在线预览html
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
html = markdown_convertion_for_file(md)
|
||||
# print(html)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
# 生成包含图片的压缩包
|
||||
|
||||
@ -211,8 +211,21 @@ def markdown_convertion_for_file(txt):
|
||||
"""
|
||||
将Markdown格式的文本转换为HTML格式。如果包含数学公式，则先将公式转换为HTML格式。
|
||||
"""
|
||||
pre = '<div class="markdown-body">'
|
||||
suf = "</div>"
|
||||
from themes.theme import advanced_css
|
||||
pre = f"""
|
||||
<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>
|
||||
<body>
|
||||
<div class="test_temp1" style="width:10%; height: 500px; float:left;"></div>
|
||||
<div class="test_temp2" style="width:80%;padding: 40px;float:left;padding-left: 20px;padding-right: 20px;box-shadow: rgba(0, 0, 0, 0.2) 0px 0px 8px 8px;border-radius: 10px;">
|
||||
<div class="markdown-body">
|
||||
"""
|
||||
suf = """
|
||||
</div>
|
||||
</div>
|
||||
<div class="test_temp3" style="width:10%; height: 500px; float:left;"></div>
|
||||
</body>
|
||||
"""
|
||||
|
||||
if txt.startswith(pre) and txt.endswith(suf):
|
||||
# print('警告，输入了已经经过转化的字符串，二次转化可能出问题')
|
||||
return txt # 已经被转化过，不需要再次转化
|
||||
|
||||
13
toolbox.py
13
toolbox.py
@ -192,6 +192,8 @@ def trimmed_format_exc():
|
||||
replace_path = "."
|
||||
return str.replace(current_path, replace_path)
|
||||
|
||||
def trimmed_format_exc_markdown():
|
||||
return '\n\n```\n' + trimmed_format_exc() + '```'
|
||||
|
||||
def CatchException(f):
|
||||
"""
|
||||
@ -536,6 +538,17 @@ def on_file_uploaded(
|
||||
return chatbot, txt, txt2, cookies
|
||||
|
||||
|
||||
def generate_file_link(report_files:List[str]):
|
||||
file_links = ""
|
||||
for f in report_files:
|
||||
file_links += (
|
||||
f'<br/><a href="file={os.path.abspath(f)}" target="_blank">{f}</a>'
|
||||
)
|
||||
return file_links
|
||||
|
||||
|
||||
|
||||
|
||||
def on_report_generated(cookies:dict, files:List[str], chatbot:ChatBotWithCookies):
|
||||
if "files_to_promote" in cookies:
|
||||
report_files = cookies["files_to_promote"]
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user