合并重复的函数

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -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