fix: 处理PDF中出现 \0 字符报 Null characters are not allowed

--bug=1048190 --user=刘瑞斌 【知识库】- 上传PDF文档 报错  ，关联issue #1468 https://www.tapd.cn/57709429/s/1611070

Author: liuruibin

apps/common/handle/impl/pdf_split_handle.py

@@ -104,6 +104,9 @@ def handle_pdf_content(file, pdf_document):
 
             content += page_content
 
+            # Null characters are not allowed.
+            content = content.replace('\0', '')
+
             elapsed_time = time.time() - start_time
             max_kb.debug(
                 f"File: {file.name}, Page: {page_num + 1}, Time : {elapsed_time: .3f}s,   content-length: {len(page_content)}")
@@ -156,6 +159,10 @@ def handle_toc(doc, limit):
                         text = text[:idx]
 
                 chapter_text += text  # 提取文本
+
+            # Null characters are not allowed.
+            chapter_text = chapter_text.replace('\0', '')
+
             # 限制章节内容长度
             if 0 < limit < len(chapter_text):
                 split_text = PdfSplitHandle.split_text(chapter_text, limit)
@@ -228,6 +235,9 @@ def handle_links(doc, pattern_list, with_filter, limit):
                                 text = text[:idx]
                         chapter_text += text
 
+                    # Null characters are not allowed.
+                    chapter_text = chapter_text.replace('\0', '')
+
                     # 限制章节内容长度
                     if 0 < limit < len(chapter_text):
                         split_text = PdfSplitHandle.split_text(chapter_text, limit)