fix: skip comment blocks in DOCXToDocument (#8764)

* fix bug #8759 * Apply suggestions from code review * release note --------- Co-authored-by: Stefano Fiorucci <[email protected]>
deepset-ai · Jan 24, 2025 · c989d9c · c989d9c
1 parent 223373e
commit c989d9c
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 0 deletions.
diff --git a/haystack/components/converters/docx.py b/haystack/components/converters/docx.py
@@ -23,6 +23,7 @@
     from docx.document import Document as DocxDocument
     from docx.table import Table
     from docx.text.paragraph import Paragraph
+    from lxml.etree import _Comment
 
 
 @dataclass
@@ -210,6 +211,8 @@ def _extract_elements(self, document: "DocxDocument") -> List[str]:
         """
         elements = []
         for element in document.element.body:
+            if isinstance(element, _Comment):
+                continue
             if element.tag.endswith("p"):
                 paragraph = Paragraph(element, document)
                 if paragraph.contains_page_break:

diff --git a/releasenotes/notes/docx-skip-comment-blocks-d3a555d0324788c7.yaml b/releasenotes/notes/docx-skip-comment-blocks-d3a555d0324788c7.yaml
@@ -0,0 +1,4 @@
+---
+fixes:
+  - |
+    The DOCXToDocument component now skips comment blocks in DOCX files that previously caused errors.