fix: Part of the docx document is parsed incorrectly

1Panel-dev · Jan 6, 2025 · 5171da9 · 5171da9
1 parent 00591a5
commit 5171da9
Showing 1 changed file with 5 additions and 3 deletions.
diff --git a/apps/common/handle/impl/doc_split_handle.py b/apps/common/handle/impl/doc_split_handle.py
@@ -113,8 +113,10 @@ class DocSplitHandle(BaseSplitHandle):
     def paragraph_to_md(paragraph: Paragraph, doc: Document, images_list, get_image_id):
         try:
             psn = paragraph.style.name
-            if psn.startswith('Heading'):
-                title = "".join(["#" for i in range(int(psn.replace("Heading ", '')))]) + " " + paragraph.text
+            if psn.startswith('Heading') or psn.startswith('TOC 标题') or psn.startswith('标题'):
+                title = "".join(["#" for i in range(
+                    int(psn.replace("Heading ", '').replace('TOC 标题', '').replace('标题',
+                                                                                    '')))]) + " " + paragraph.text
                 images = reduce(lambda x, y: [*x, *y],
                                 [get_paragraph_element_images(e, doc, images_list, get_image_id) for e in
                                  paragraph._element],
@@ -202,4 +204,4 @@ def get_content(self, file, save_image):
             return content
         except BaseException as e:
             traceback.print_exception(e)
-            return f'{e}'
+            return f'{e}'