DocxDocument forward reference (#7852)

haystack/components/converters/docx.py

@@ -25,7 +25,7 @@ class DocxToDocument:
  Converts Docx files to Documents.
 
  Uses `python-docx` library to convert the Docx file to a document.
- This component does not preserve page brakes in the original document.
+ This component does not preserve page breaks in the original document.
 
  Usage example:
  ```python
@@ -115,7 +115,7 @@ def run(
 
  return {"documents": documents}
 
- def _get_docx_metadata(self, document: DocxDocument) -> Dict[str, Union[str, int, datetime]]:
+ def _get_docx_metadata(self, document: "DocxDocument") -> Dict[str, Union[str, int, datetime]]:
  """
  Get all relevant data from the 'core_properties' attribute from a Docx Document.
 

test/components/converters/test_docx_file_to_document.py

@@ -27,12 +27,11 @@ def test_run(self, test_files_path, docx_converter):
  assert len(docs) == 1
  assert "History" in docs[0].content
 
+ @pytest.mark.integration
  def test_run_with_meta(self, test_files_path, docx_converter):
- with patch("haystack.components.converters.docx.DocxToDocument"):
- output = docx_converter.run(
- sources=[test_files_path / "docx" / "sample_docx_1.docx"],
- meta={"language": "it", "author": "test_author"},
- )
+ output = docx_converter.run(
+ sources=[test_files_path / "docx" / "sample_docx_1.docx"], meta={"language": "it", "author": "test_author"}
+ )
 
  # check that the metadata from the bytestream is merged with that from the meta parameter
  assert output["documents"][0].meta["author"] == "test_author"