chore: Capitalize DOCX in DOCXToDocument converter (#7931)

* Capitalize DOCX in DOCXToDocument converter

* Update docstrings

* Update test class name

* add releease notes

haystack/components/converters/__init__.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 from haystack.components.converters.azure import AzureOCRDocumentConverter
-from haystack.components.converters.docx import DocxMetadata, DocxToDocument
+from haystack.components.converters.docx import DOCXMetadata, DOCXToDocument
 from haystack.components.converters.html import HTMLToDocument
 from haystack.components.converters.markdown import MarkdownToDocument
 from haystack.components.converters.openapi_functions import OpenAPIServiceToFunctions
@@ -23,6 +23,6 @@ __all__ = [
     "MarkdownToDocument",
     "OpenAPIServiceToFunctions",
     "OutputAdapter",
-    "DocxToDocument",
-    "DocxMetadata",
+    "DOCXToDocument",
+    "DOCXMetadata",
 ]

haystack/components/converters/docx.py

@@ -21,7 +21,7 @@ with LazyImport("Run 'pip install python-docx'") as docx_import:
 
 
 @dataclass
-class DocxMetadata:
+class DOCXMetadata:
     """
     Describes the metadata of Docx file.
 
@@ -60,28 +60,28 @@ class DocxMetadata:
 
 
 @component
-class DocxToDocument:
+class DOCXToDocument:
     """
-    Converts Docx files to Documents.
+    Converts DOCX files to Documents.
 
-    Uses `python-docx` library to convert the Docx file to a document.
+    Uses `python-docx` library to convert the DOCX file to a document.
     This component does not preserve page breaks in the original document.
 
     Usage example:
     ```python
-    from haystack.components.converters.docx import DocxToDocument
+    from haystack.components.converters.docx import DOCXToDocument
 
-    converter = DocxToDocument()
+    converter = DOCXToDocument()
     results = converter.run(sources=["sample.docx"], meta={"date_added": datetime.now().isoformat()})
     documents = results["documents"]
     print(documents[0].content)
-    # 'This is a text from the Docx file.'
+    # 'This is a text from the DOCX file.'
     ```
     """
 
     def __init__(self):
         """
-        Create a DocxToDocument component.
+        Create a DOCXToDocument component.
         """
         docx_import.check()
 
@@ -92,7 +92,7 @@ class DocxToDocument:
         meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
     ):
         """
-        Converts Docx files to Documents.
+        Converts DOCX files to Documents.
 
         :param sources:
             List of file paths or ByteStream objects.
@@ -123,7 +123,7 @@ class DocxToDocument:
                 text = "\n".join(paragraphs)
             except Exception as e:
                 logger.warning(
-                    "Could not read {source} and convert it to a Docx Document, skipping. Error: {error}",
+                    "Could not read {source} and convert it to a DOCX Document, skipping. Error: {error}",
                     source=source,
                     error=e,
                 )
@@ -136,17 +136,17 @@ class DocxToDocument:
 
         return {"documents": documents}
 
-    def _get_docx_metadata(self, document: "DocxDocument") -> DocxMetadata:
+    def _get_docx_metadata(self, document: "DocxDocument") -> DOCXMetadata:
         """
-        Get all relevant data from the 'core_properties' attribute from a Docx Document.
+        Get all relevant data from the 'core_properties' attribute from a DOCX Document.
 
         :param document:
-            The Docx Document you want to extract metadata from
+            The DOCX Document you want to extract metadata from
 
         :returns:
-            A `DocxMetadata` dataclass all the relevant fields from the 'core_properties'
+            A `DOCXMetadata` dataclass all the relevant fields from the 'core_properties'
         """
-        return DocxMetadata(
+        return DOCXMetadata(
             author=document.core_properties.author,
             category=document.core_properties.category,
             comments=document.core_properties.comments,

releasenotes/notes/docxtodocument-rename-3acf592c89aea430.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Renamed component from DocxToDocument to DOCXToDocument to follow the naming convention of other converter components.

test/components/converters/test_docx_file_to_document.py

@@ -5,17 +5,17 @@ import pytest
 
 from haystack.dataclasses import ByteStream
 from haystack import Document
-from haystack.components.converters.docx import DocxToDocument, DocxMetadata
+from haystack.components.converters.docx import DOCXToDocument, DOCXMetadata
 
 
 @pytest.fixture
 def docx_converter():
-    return DocxToDocument()
+    return DOCXToDocument()
 
 
-class TestDocxToDocument:
+class TestDOCXToDocument:
     def test_init(self, docx_converter):
-        assert isinstance(docx_converter, DocxToDocument)
+        assert isinstance(docx_converter, DOCXToDocument)
 
     def test_run(self, test_files_path, docx_converter):
         """
@@ -29,7 +29,7 @@ class TestDocxToDocument:
         assert docs[0].meta.keys() == {"file_path", "docx"}
         assert docs[0].meta == {
             "file_path": str(paths[0]),
-            "docx": DocxMetadata(
+            "docx": DOCXMetadata(
                 author="Microsoft Office User",
                 category="",
                 comments="",
@@ -54,7 +54,7 @@ class TestDocxToDocument:
         doc = output["documents"][0]
         assert doc.meta == {
             "file_path": str(paths[0]),
-            "docx": DocxMetadata(
+            "docx": DOCXMetadata(
                 author="Microsoft Office User",
                 category="",
                 comments="",
@@ -106,7 +106,7 @@ class TestDocxToDocument:
         assert "History and standardization" in docs[1].content
 
     def test_document_with_docx_metadata_to_dict(self):
-        docx_metadata = DocxMetadata(
+        docx_metadata = DOCXMetadata(
             author="Microsoft Office User",
             category="category",
             comments="comments",