Add check of the mangled list to the s3-resource/<path> endpoint

app/main.py

@@ -44,7 +44,7 @@
 from app.scicrunch_process_results import process_results, process_get_first_scaffold_info, reform_aggregation_results, \
     reform_curies_results, reform_dataset_results, reform_related_terms, reform_anatomy_results
 from app.serializer import ContactRequestSchema
-from app.utilities import img_to_base64_str
+from app.utilities import img_to_base64_str, check_path_in_mangled_list
 from app.osparc.osparc import start_simulation as do_start_simulation
 from app.osparc.osparc import check_simulation as do_check_simulation
 from app.biolucida_process_results import process_results as process_biolucida_results
@@ -379,11 +379,12 @@ def url_exists(path, bucket_name=Config.DEFAULT_S3_BUCKET_NAME):
 
     query_args = request.args
     s3BucketName = query_args.get("s3BucketName", bucket_name)
+    s3_path = check_path_in_mangled_list(path)
 
     try:
         head_response = s3.head_object(
             Bucket=s3BucketName,
-            Key=path,
+            Key=s3_path,
             RequestPayer="requester"
         )
     except ClientError:
@@ -426,11 +427,12 @@ def direct_download_url(path, bucket_name=Config.DEFAULT_S3_BUCKET_NAME):
 
     query_args = request.args
     s3BucketName = query_args.get("s3BucketName", bucket_name)
+    s3_path = check_path_in_mangled_list(path)
 
     try:
         head_response = s3.head_object(
             Bucket=s3BucketName,
-            Key=path,
+            Key=s3_path,
             RequestPayer="requester"
         )
         content_length = head_response.get('ContentLength', Config.DIRECT_DOWNLOAD_LIMIT)
@@ -443,7 +445,7 @@ def direct_download_url(path, bucket_name=Config.DEFAULT_S3_BUCKET_NAME):
 
     response = s3.get_object(
         Bucket=s3BucketName,
-        Key=path,
+        Key=s3_path,
         RequestPayer="requester"
     )
 

app/manifest_name_to_discover_name.py

@@ -5008,5 +5008,7 @@
             'files/primary/sub-Cadaver-Subject-2/Ultrasound_raw_Cadaver_Subject 2.mp4': 'files/primary/sub-Cadaver-Subject-2/Ultrasound_raw_Cadaver_Subject_2.mp4',
             'files/primary/sub-Cadaver-Subject-3/Ultrasound_raw_Cadaver_Subject 3.mp4': 'files/primary/sub-Cadaver-Subject-3/Ultrasound_raw_Cadaver_Subject_3.mp4',
             'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-3_Pgp9.5.jpx': 'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-3 Pgp9.5.jpx',
-            'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-4_Pgp9.5.jpx': 'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-4 Pgp9.5.jpx'
+            'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-4_Pgp9.5.jpx': 'files/derivative/sam-P21 BAT/ses-Pgp9.5/P21-4 Pgp9.5.jpx',
+            'files/derivative/mapped_Pig 7_thumbnail.jpeg': 'files/derivative/mapped_Pig_7_thumbnail.jpeg',
+            'files/derivative/mapped_Pig 16_thumbnail.jpeg': 'files/derivative/mapped_Pig_16_thumbnail.jpeg'
 }

app/utilities.py

@@ -1,6 +1,18 @@
 import base64
 from io import BytesIO
+from app.manifest_name_to_discover_name import name_map
 
+def check_path_in_mangled_list(s3_path):
+
+    # Split out the file part of the path
+    s3_paths = s3_path.split('files/')
+    s3_paths[1] = 'files/' + s3_paths[1]  # Add the part we split on back
+
+    # Switch the path to the mapped one if it is listed
+    if s3_paths[1] in name_map:
+        s3_paths[1] = name_map[s3_paths[1]]
+
+    return s3_paths[0] + s3_paths[1]  # Return the path with dataset info at the front
 
 def img_to_base64_str(img):
     """

tests/test_dataset_info.py

@@ -273,3 +273,9 @@ def test_pennsieve_identifier_dataset_search(client):
     print(first_result)
     for r in result[BIOLUCIDA_3D]:
         print(r['dataset']['path'])
+
+def test_name_mangling_for_s3_resource(client):
+    # This test uses a file on dataset 328 which has a file where space is converted to underscore
+    # to check the name mangling code is working
+    r = client.get('/s3-resource/328/1/files/derivative/mapped_Pig%207_thumbnail.jpeg?s3BucketName=prd-sparc-discover-use1')
+    assert r.status_code == 200