Merge pull request #1111 from kaixindelele/only_chinese_pdf

提升PDF翻译插件的效果

crazy_functions/pdf_fns/parse_pdf.py

@@ -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)

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
@@ -92,7 +93,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 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"
@@ -106,96 +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)
-
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
-        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],
-        )
-        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:
-                gpt_response_collection_html[i] = gpt_response_collection_html[i]
-
-        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)
 
     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

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,12 +1,12 @@
-from toolbox import CatchException, report_execption, get_log_folder
+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
+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
 
@@ -58,8 +58,8 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
 
 def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
-    import copy
+    import copy, json
-    TOKEN_LIMIT_PER_FRAGMENT = 1280
+    TOKEN_LIMIT_PER_FRAGMENT = 512
     generated_conclusion_files = []
     generated_html_files = []
     DST_LANG = "中文"
@@ -67,104 +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"
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
-        # 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],
-        )
-        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:
-                gpt_response_collection_html[i] = gpt_response_collection_html[i]
-
-        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)
-
     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 = 1280
+    TOKEN_LIMIT_PER_FRAGMENT = 512
     generated_conclusion_files = []
     generated_html_files = []
     from crazy_functions.crazy_utils import construct_html

themes/common.css

@@ -19,3 +19,8 @@
 .wrap.svelte-xwlu1w {
     min-height: var(--size-32);
 }
+
+/* status bar height */
+.min.svelte-1yrv54 {
+    min-height: var(--size-12);
+}

toolbox.py

@@ -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)