Merge pull request #68 from djarecka/id_check

adding id check to the validation
ReproNim · Oct 31, 2024 · aecab71 · aecab71
2 parents 889fafe + 1a8304f
commit aecab71
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 16 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -26,7 +26,7 @@ repos:
     rev: v2.3.0
     hooks:
     -   id: codespell
-        args: [--toml, pyproject.toml]
+        args: [--toml, pyproject.toml, --skip="CHANGELOG.md"]
         additional_dependencies: [tomli]
 
 # Format TOML files

diff --git a/reproschema/jsonldutils.py b/reproschema/jsonldutils.py
@@ -99,13 +99,15 @@ def load_file(
     return data
 
 
-def validate_data(data):
+def validate_data(data, schemaname):
     """Validate an expanded jsonld document against the pydantic model.
 
     Parameters
     ----------
     data : dict
         Python dictionary containing JSONLD object
+    schemaname : str
+        Name of the schema (name of the file) being validated
 
     Returns
     -------
@@ -115,14 +117,16 @@ def validate_data(data):
         Validation errors if any returned by pydantic
 
     """
-    # do we need it?
-    # kwargs = {"algorithm": "URDNA2015", "format": "application/n-quads"}
-    # normalized = jsonld.normalize(data, kwargs)
     obj_type = identify_model_class(data["@type"][0])
     data_fixed = [fixing_old_schema(data, copy_data=True)]
     context = read_contextfile(CONTEXTFILE_URL)
     data_fixed_comp = jsonld.compact(data_fixed, context)
     del data_fixed_comp["@context"]
+    if obj_type.__name__ in ["Item", "Activity", "Protocol"]:
+        if data_fixed_comp["id"].split("/")[-1] != schemaname:
+            raise Exception(
+                f"Document {data['@id']} does not match the schema name {schemaname}"
+            )
     conforms = False
     v_text = ""
     try:

diff --git a/reproschema/tests/data/activities/activity1_embed.jsonld b/reproschema/tests/data/activities/activity1_embed.jsonld
@@ -1,7 +1,7 @@
 {
     "@context": "../../contexts/generic",
     "@type": "reproschema:Activity",
-    "@id": "activity1.jsonld",
+    "@id": "activity1_embed.jsonld",
     "prefLabel": "Example 1",
     "description": "Activity example 1",
     "schemaVersion": "1.0.0-rc4",

diff --git a/reproschema/tests/data/protocols/protocol1_embed.jsonld b/reproschema/tests/data/protocols/protocol1_embed.jsonld
@@ -1,7 +1,7 @@
 {
     "@context": "../../contexts/generic",
 	"@type": "reproschema:Protocol",
-	"@id": "protocol1.jsonld",
+	"@id": "protocol1_embed.jsonld",
 	"prefLabel": {
 		"en": "Protocol1",
 		"es": "Protocol1_es"

diff --git a/reproschema/validate.py b/reproschema/validate.py
@@ -92,7 +92,7 @@ def validate_dir(
                 if stop is not None:
                     stop_server(stop)
                 raise ValueError(f"Empty data graph in file {name}")
-            conforms, vtext = validate_data(data)
+            conforms, vtext = validate_data(data, schemaname=Path(name).name)
         except (ValueError, json.JSONDecodeError):
             if stop is not None:
                 stop_server(stop)
@@ -133,27 +133,20 @@ def validate(path):
 
     """
     if Path(path).is_dir():
-
         lgr.info(f"Validating directory {path}")
-
         stop, port = start_server()
         http_kwargs = {"port": port}
         started = True
-
         conforms, _ = validate_dir(
             path, started=started, http_kwargs=http_kwargs, stop=stop
         )
-
         stop_server(stop)
-
     else:
-
         if Path(path).name in FILES_TO_SKIP:
             lgr.info(f"Skipping file {path}")
             return True
-
         data = load_file(path, started=False)
-        conforms, vtext = validate_data(data)
+        conforms, vtext = validate_data(data, schemaname=Path(path).name)
         if not conforms:
             lgr.critical(f"File {path} has validation errors.")
             raise ValueError(vtext)