修复pdf翻译的问题

crazy_functions/批量翻译PDF文档_多线程.py

@@ -58,14 +58,17 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
     import os
+    import copy
     import tiktoken
     TOKEN_LIMIT_PER_FRAGMENT = 1280
     generated_conclusion_files = []
+    generated_html_files = []
     for index, fp in enumerate(file_manifest):
 
         # 读取PDF文件
         file_content, page_one = read_and_clean_pdf_text(fp)
-
+        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+        page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
         # 递归地切割PDF文件
         from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
         from request_llm.bridge_all import model_info
@@ -74,7 +77,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
             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=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+            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]
@@ -100,15 +103,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
                 "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
-        for i,k in enumerate(gpt_response_collection): 
+        for i,k in enumerate(gpt_response_collection_md): 
             if i%2==0:
-                gpt_response_collection[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection)//2}]：\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 "
             else:
-                gpt_response_collection[i] = gpt_response_collection[i]
+                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)
+        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)
 
@@ -117,15 +120,97 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         chatbot.append((f"{fp}完成了吗？", res))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
+        # write html
+        try:
+            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] = paper_fragments[i//2].replace('#', '')
+                else:
+                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
+            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "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"
+            ch.save_file(create_report_file_name)
+            generated_html_files.append(f'./gpt_log/{create_report_file_name}')
+        except:
+            from toolbox import trimmed_format_exc
+            print('writing html result failed:', trimmed_format_exc())
+
     # 准备文件的下载
     import shutil
     for pdf_path in generated_conclusion_files:
         # 重命名文件
-        rename_file = f'./gpt_log/总结论文-{os.path.basename(pdf_path)}'
+        rename_file = f'./gpt_log/翻译-{os.path.basename(pdf_path)}'
         if os.path.exists(rename_file):
             os.remove(rename_file)
         shutil.copyfile(pdf_path, rename_file)
         if os.path.exists(pdf_path):
             os.remove(pdf_path)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files)))
+    for html_path in generated_html_files:
+        # 重命名文件
+        rename_file = f'./gpt_log/翻译-{os.path.basename(html_path)}'
+        if os.path.exists(rename_file):
+            os.remove(rename_file)
+        shutil.copyfile(html_path, rename_file)
+        if os.path.exists(html_path):
+            os.remove(html_path)
+    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
+
+
+class construct_html():
+    def __init__(self) -> None:
+        self.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;
+}
+        """
+        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 = """
+<div class="row table-row">
+    <div class="column table-cell">REPLACE_A</div>
+    <div class="column table-cell">REPLACE_B</div>
+</div>
+        """
+        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(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
+            f.write(self.html_string.encode('utf-8', 'ignore').decode())
+

toolbox.py

@@ -168,14 +168,17 @@ def write_results_to_file(history, file_name=None):
     with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
         f.write('# chatGPT 分析报告\n')
         for i, content in enumerate(history):
-            try:    # 这个bug没找到触发条件，暂时先这样顶一下
-                if type(content) != str:
-                    content = str(content)
+            try:    
+                if type(content) != str: content = str(content)
             except:
                 continue
             if i % 2 == 0:
                 f.write('## ')
-            f.write(content)
+            try:
+                f.write(content)
+            except:
+                # remove everything that cannot be handled by utf8
+                f.write(content.encode('utf-8', 'ignore').decode())
             f.write('\n\n')
     res = '以上材料已经被写入' + os.path.abspath(f'./gpt_log/{file_name}')
     print(res)