fix parsing for 'format' as direct schema URI

Author: fmigneault

CHANGES.rst

@@ -20,6 +20,10 @@ Fixes:
   operations to extract applicable media-types. These cases will be ignored, since media-types cannot be inferred
   from them. The `WPS` or `OAS` I/O definitions should instead provide the applicable media-types
   (relates to `common-workflow-language/cwl-v1.3#52 <https://github.com/common-workflow-language/cwl-v1.3/issues/52>`_).
+- Fix ``format`` parsing when trying to infer media-types from various I/O definition representations using a
+  reference provided as an URI schema from an ontology. Parsing caused the URI to be split, causing an invalid
+  resolution. If no appropriate media-type is provided, JSON will be used by default, while preserving the submitted
+  schema URI.
 
 .. _changes_5.7.0:
 

tests/test_formats.py

@@ -156,6 +156,21 @@ def test_get_format_media_type_no_extension(test_extension):
     fmt = f.get_format(test_extension)
     assert fmt == Format(test_extension, extension=None)
     assert fmt.extension == ""
+    assert fmt.schema == ""
+
+
+@pytest.mark.parametrize(
+    "test_format",
+    [
+        "http://www.opengis.net/def/glossary/term/FeatureCollection",
+        "https://geojson.org/schema/FeatureCollection.json",
+    ]
+)
+def test_get_format_media_type_no_extension_with_schema(test_format):
+    fmt = f.get_format(test_format)
+    assert fmt.extension == ".json"
+    assert fmt.mime_type == f.ContentType.APP_JSON
+    assert fmt.schema == test_format
 
 
 @pytest.mark.parametrize(

weaver/formats.py

@@ -669,7 +669,10 @@ def get_format(media_type, default=None):
     if not ctype:
         return None
     ext = get_extension(ctype)
-    fmt = Format(ctype, extension=ext)
+    if ctype.startswith("http") and ctype.endswith(ext.strip(".")):
+        fmt = Format(ContentType.APP_JSON, extension=".json", schema=ctype)
+    else:
+        fmt = Format(ctype, extension=ext)
     return fmt
 
 
@@ -966,14 +969,20 @@ def clean_media_type_format(media_type, suffix_subtype=False, strip_parameters=F
         media_type = f"{typ}/{sub}{parts[1]}"
     for v in FORMAT_NAMESPACE_DEFINITIONS.values():
         if v in media_type:
-            media_type = media_type.replace(v, "")
-            break
+            maybe_type = media_type.replace(v, "").strip("/")
+            # ignore if URI was partial prefix match, not sufficiently specific
+            # allow 1 '/' for '<type>/<subtype>', or 0 for an explicit named schema reference
+            if maybe_type.count("/") < 2:
+                media_type = maybe_type
+                break
     for v in FORMAT_NAMESPACE_DEFINITIONS:
         if media_type.startswith(f"{v}:"):
-            media_type = media_type.replace(f"{v}:", "")
-            break
+            maybe_type = media_type.replace(f"{v}:", "")
+            if maybe_type.count("/") < 2:
+                media_type = maybe_type
+                break
     search = True
-    for _map in [EDAM_MAPPING, OGC_MAPPING, OPENGIS_MAPPING]:
+    for _map in FORMAT_NAMESPACE_MAPPINGS.values():
         if not search:
             break
         for v in _map.values():