fix: Fixed docx import with headers that are also lists (#842)

* Fix for docx when headers are also lists, now recorded as appropriate headers and subheaders, unit test included Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Update docling/backend/msword_backend.py Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com> * Update docling/backend/msword_backend.py Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com> --------- Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
DS4SD · Jan 31, 2025 · 2c037ae · 2c037ae
1 parent 2a1f8af
commit 2c037ae
Show file tree

Hide file tree

Showing 5 changed files with 868 additions and 6 deletions.
diff --git a/docling/backend/msword_backend.py b/docling/backend/msword_backend.py
@@ -240,7 +240,11 @@ def handle_text_elements(self, element, docx_obj, doc):
             numid = None
 
         # Handle lists
-        if numid is not None and ilevel is not None:
+        if (
+            numid is not None
+            and ilevel is not None
+            and p_style_id not in ["Title", "Heading"]
+        ):
             self.add_listitem(
                 element,
                 docx_obj,
@@ -254,12 +258,22 @@ def handle_text_elements(self, element, docx_obj, doc):
             )
             self.update_history(p_style_id, p_level, numid, ilevel)
             return
-        elif numid is None and self.prev_numid() is not None:  # Close list
-            for key, val in self.parents.items():
-                if key >= self.level_at_new_list:
+        elif (
+            numid is None
+            and self.prev_numid() is not None
+            and p_style_id not in ["Title", "Heading"]
+        ):  # Close list
+            if self.level_at_new_list:
+                for key in range(len(self.parents)):
+                    if key >= self.level_at_new_list:
+                        self.parents[key] = None
+                self.level = self.level_at_new_list - 1
+                self.level_at_new_list = None
+            else:
+                for key in range(len(self.parents)):
                     self.parents[key] = None
-            self.level = self.level_at_new_list - 1
-            self.level_at_new_list = None
+                self.level = 0
+
         if p_style_id in ["Title"]:
             for key, val in self.parents.items():
                 self.parents[key] = None

diff --git a/tests/data/docx/unit_test_headers_numbered.docx b/tests/data/docx/unit_test_headers_numbered.docx
diff --git a/tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.itxt b/tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.itxt
@@ -0,0 +1,52 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Test Document
+    item-2 at level 2: paragraph: 
+    item-3 at level 2: section_header: Section 1
+  item-4 at level 1: paragraph: 
+  item-5 at level 1: paragraph: Paragraph 1.1
+  item-6 at level 1: paragraph: 
+  item-7 at level 1: paragraph: Paragraph 1.2
+  item-8 at level 1: paragraph: 
+  item-9 at level 1: section: group header-0
+    item-10 at level 2: section: group header-1
+      item-11 at level 3: section_header: Section 1.1
+        item-12 at level 4: paragraph: 
+        item-13 at level 4: paragraph: Paragraph 1.1.1
+        item-14 at level 4: paragraph: 
+        item-15 at level 4: paragraph: Paragraph 1.1.2
+        item-16 at level 4: paragraph: 
+      item-17 at level 3: section_header: Section 1.2
+        item-18 at level 4: paragraph: 
+        item-19 at level 4: paragraph: Paragraph 1.1.1
+        item-20 at level 4: paragraph: 
+        item-21 at level 4: paragraph: Paragraph 1.1.2
+        item-22 at level 4: paragraph: 
+        item-23 at level 4: section_header: Section 1.2.3
+          item-24 at level 5: paragraph: 
+          item-25 at level 5: paragraph: Paragraph 1.2.3.1
+          item-26 at level 5: paragraph: 
+          item-27 at level 5: paragraph: Paragraph 1.2.3.1
+          item-28 at level 5: paragraph: 
+          item-29 at level 5: paragraph: 
+    item-30 at level 2: section_header: Section 2
+  item-31 at level 1: paragraph: 
+  item-32 at level 1: paragraph: Paragraph 2.1
+  item-33 at level 1: paragraph: 
+  item-34 at level 1: paragraph: Paragraph 2.2
+  item-35 at level 1: paragraph: 
+  item-36 at level 1: section: group header-0
+    item-37 at level 2: section: group header-1
+      item-38 at level 3: section: group header-2
+        item-39 at level 4: section_header: Section 2.1.1
+          item-40 at level 5: paragraph: 
+          item-41 at level 5: paragraph: Paragraph 2.1.1.1
+          item-42 at level 5: paragraph: 
+          item-43 at level 5: paragraph: Paragraph 2.1.1.1
+          item-44 at level 5: paragraph: 
+      item-45 at level 3: section_header: Section 2.1
+        item-46 at level 4: paragraph: 
+        item-47 at level 4: paragraph: Paragraph 2.1.1
+        item-48 at level 4: paragraph: 
+        item-49 at level 4: paragraph: Paragraph 2.1.2
+        item-50 at level 4: paragraph: 
+        item-51 at level 4: paragraph: