feat: Set ByteStream's mime_type attribute for web based resources (#…

…7681)

haystack/components/fetchers/link_content.py

@@ -151,6 +151,7 @@ def run(self, urls: List[str]):
             for stream_metadata, stream in results:  # type: ignore
                 if stream_metadata is not None and stream is not None:
                     stream.meta.update(stream_metadata)
+                    stream.mime_type = stream.meta.get("content_type", None)
                     streams.append(stream)
 
         return {"streams": streams}

haystack/components/routers/file_type_router.py

@@ -90,7 +90,7 @@ def run(self, sources: List[Union[str, Path, ByteStream]]) -> Dict[str, List[Uni
             if isinstance(source, Path):
                 mime_type = self._get_mime_type(source)
             elif isinstance(source, ByteStream):
-                mime_type = source.meta.get("content_type", None)
+                mime_type = source.mime_type
             else:
                 raise ValueError(f"Unsupported data source type: {type(source).__name__}")
 

releasenotes/notes/enhanced-mime-type-handling-182fb64a0f5fb852.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+ - |
+   Improved MIME type management by directly setting MIME types on ByteStreams, enhancing the overall handling and routing of different file types. This update makes MIME type data more consistently accessible and simplifies the process of working with various document formats.

test/components/routers/test_file_router.py

@@ -50,7 +50,7 @@ def test_run_with_bytestreams(self, test_files_path):
         byte_streams = []
         for path, mime_type in zip(file_paths, mime_types):
             stream = ByteStream(path.read_bytes())
-            stream.meta["content_type"] = mime_type
+            stream.mime_type = mime_type
             byte_streams.append(stream)
 
         # add unclassified ByteStream
@@ -81,7 +81,7 @@ def test_run_with_bytestreams_and_file_paths(self, test_files_path):
         byte_stream_sources = []
         for path, mime_type in zip(file_paths, mime_types):
             stream = ByteStream(path.read_bytes())
-            stream.meta["content_type"] = mime_type
+            stream.mime_type = mime_type
             byte_stream_sources.append(stream)
 
         mixed_sources = file_paths[:2] + byte_stream_sources[2:]
@@ -165,9 +165,12 @@ def test_exact_mime_type_matching(self, mock_file):
         """
         Test if the component correctly matches mime types exactly, without regex patterns.
         """
-        txt_stream = ByteStream(io.BytesIO(b"Text file content"), meta={"content_type": "text/plain"})
-        jpg_stream = ByteStream(io.BytesIO(b"JPEG file content"), meta={"content_type": "image/jpeg"})
-        mp3_stream = ByteStream(io.BytesIO(b"MP3 file content"), meta={"content_type": "audio/mpeg"})
+        txt_stream = ByteStream(io.BytesIO(b"Text file content").read())
+        txt_stream.mime_type = "text/plain"
+        jpg_stream = ByteStream(io.BytesIO(b"JPEG file content").read())
+        jpg_stream.mime_type = "image/jpeg"
+        mp3_stream = ByteStream(io.BytesIO(b"MP3 file content").read())
+        mp3_stream.mime_type = "audio/mpeg"
 
         byte_streams = [txt_stream, jpg_stream, mp3_stream]