Handle header and footer

Signed-off-by: SimJeg <sjegou@nvidia.com>
2025-07-27 04:24:45 +00:00 · 2025-04-01 11:36:47 +02:00 · 2025-04-01 11:36:47 +02:00 · 61bd559f78
commit 61bd559f78
parent 1033c25435
2 changed files with 2 additions and 0 deletions
--- a/docling/backend/msword_backend.py
+++ b/docling/backend/msword_backend.py
@ -116,7 +116,9 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
        doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
        if self.is_valid():
            assert self.docx_obj is not None
+            doc = self.walk_linear(self.docx_obj.sections[0].header._element, self.docx_obj, doc)
            doc = self.walk_linear(self.docx_obj.element.body, self.docx_obj, doc)
+            doc = self.walk_linear(self.docx_obj.sections[-1].footer._element, self.docx_obj, doc)
            return doc
        else:
            raise RuntimeError(
--- a/tests/data/docx/unit_test_formatting.docx
+++ b/tests/data/docx/unit_test_formatting.docx