Enhancement: Add Content-Type metadata to S3/GCP uploads

services/file_management.py

@@ -79,3 +79,16 @@ def download_file(url, storage_path="/tmp/"):
             os.remove(local_filename)
         raise e
 
+def get_content_type(file_path):
+    """Determine the MIME type of a file based on its extension.
+
+    Args:
+        file_path (str): Path to the file
+
+    Returns:
+        str: MIME type (e.g., 'video/mp4', 'image/png', 'application/json')
+             Returns 'application/octet-stream' if type cannot be determined
+    """
+    content_type, _ = mimetypes.guess_type(file_path)
+    return content_type if content_type else 'application/octet-stream'
+

services/gcp_toolkit.py

@@ -23,6 +23,7 @@
 from google.cloud import storage
 from google.cloud.run_v2 import JobsClient, RunJobRequest
 from google.api_core.exceptions import GoogleAPIError
+from services.file_management import get_content_type
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -65,6 +66,10 @@ def upload_to_gcs(file_path, bucket_name=GCP_BUCKET_NAME):
         logger.info(f"Uploading file to Google Cloud Storage: {file_path}")
         bucket = gcs_client.bucket(bucket_name)
         blob = bucket.blob(os.path.basename(file_path))
+
+        # Set content type before uploading
+        blob.content_type = get_content_type(file_path)
+
         blob.upload_from_filename(file_path)
         logger.info(f"File uploaded successfully to GCS: {blob.public_url}")
         return blob.public_url

services/s3_toolkit.py

@@ -20,6 +20,7 @@
 import boto3
 import logging
 from urllib.parse import urlparse, quote
+from services.file_management import get_content_type
 
 logger = logging.getLogger(__name__)
 
@@ -36,9 +37,12 @@ def upload_to_s3(file_path, s3_url, access_key, secret_key, bucket_name, region)
     client = session.client('s3', endpoint_url=s3_url)
 
     try:
+        # Detect content type from file extension
+        content_type = get_content_type(file_path)
+
         # Upload the file to the specified S3 bucket
         with open(file_path, 'rb') as data:
-            client.upload_fileobj(data, bucket_name, os.path.basename(file_path), ExtraArgs={'ACL': 'public-read'})
+            client.upload_fileobj(data, bucket_name, os.path.basename(file_path), ExtraArgs={'ACL': 'public-read', 'ContentType': content_type})
 
         # URL encode the filename for the URL
         encoded_filename = quote(os.path.basename(file_path))

services/v1/s3/upload.py

@@ -23,6 +23,7 @@
 from urllib.parse import urlparse, unquote, quote
 import uuid
 import re
+from services.file_management import get_content_type
 
 logger = logging.getLogger(__name__)
 
@@ -82,11 +83,15 @@ def stream_upload_to_s3(file_url, custom_filename=None, make_public=False, downl
         # Start a multipart upload
         logger.info(f"Starting multipart upload for {filename} to bucket {bucket_name}")
         acl = 'public-read' if make_public else 'private'
-
+
+        # Detect content type from filename
+        content_type = get_content_type(filename)
+
         multipart_upload = s3_client.create_multipart_upload(
             Bucket=bucket_name,
             Key=filename,
-            ACL=acl
+            ACL=acl,
+            ContentType=content_type
         )
 
         upload_id = multipart_upload['UploadId']