Merge pull request #47 from psychoinformatics-de/commit-model

Model `DataladDataset` as a Git `Commit`

.gitignore

@@ -2,3 +2,4 @@
 build/
 *-stamp
 .*.swp
+*.rdf

Makefile

@@ -25,7 +25,6 @@ build/linkml-docs: \
 	build/linkml-docs/ontology \
 	build/linkml-docs/datalad-dataset-components \
 	build/linkml-docs/datalad-dataset-version
-#   build/linkml-docs/git-provenance-schema
 build/linkml-docs/%: src/linkml/schemas/%.yaml src/extra-docs/%-schema
 	export OUTDIR=$$([ "$*" = "ontology" ] && echo $@ || echo build/linkml-docs/schemas/$*) && \
 	gen-doc \
@@ -52,7 +51,6 @@ check-models: \
 	check-model-datalad-dataset-components \
 	check-model-datalad-dataset-version \
 	check-model-ontology
-#	check-model-git-provenance
 check-model-%: src/linkml/schemas/%.yaml
 	@echo [Check $<]
 	@echo "Run linter"
@@ -84,8 +82,6 @@ check-validation: \
 	convert-examples-datalad-dataset-version \
 	check-validation-datalad-dataset-version \
 	convert-examples-ontology
-#	convert-examples-git-provenance
-#	check-validation-git-provenance
 check-validation-%:
 	$(MAKE) check-valid-validation-$* check-invalid-validation-$*
 check-valid-validation-%: tests/%-schema/validation src/linkml/schemas/%.yaml
@@ -103,7 +99,6 @@ convert-examples: \
 	convert-examples-datalad-dataset-components \
 	convert-examples-datalad-dataset-version \
 	convert-examples-ontology
-#	convert-examples-git-provenance
 convert-examples-%: src/linkml/schemas/%.yaml src/examples/%
 	# loop over all examples, skip the schema file itself
 	for ex in $^/*.yaml; do \

patches/jsonschemavalidator_plainyaml.diff

@@ -0,0 +1,34 @@
+See https://github.com/linkml/linkml/issues/1806 for
+problem and rationale re this patch
+--- jsonschemavalidator.py	2024-02-23 16:19:45.946867800 +0100
++++ jsonschemavalidator.py	2024-02-23 16:18:26.363624044 +0100
+@@ -187,7 +187,27 @@
+         inargs["fmt"] = input_format
+
+     try:
+-        data_as_dict = loader.load_as_dict(source=input, **inargs)
++        if input_format == 'yaml':
++            from io import StringIO
++            from hbreader import FileInfo
++            import os
++            import yaml
++            metadata = FileInfo()
++            data = loader._read_source(
++                input,
++                metadata=metadata,
++                accept_header="text/yaml, application/yaml;q=0.9",
++            )
++            if isinstance(data, str):
++                data = StringIO(data)
++                if metadata and metadata.source_file:
++                    data.name = os.path.relpath(metadata.source_file,
++                                                metadata.base_path)
++                data_as_dict = yaml.load(data, yaml.BaseLoader)
++            else:
++                data_as_dict = data
++        else:
++            data_as_dict = loader.load_as_dict(source=input, **inargs)
+     except NotImplementedError:
+         obj = loader.load(source=input, target_class=py_target_class, **inargs)
+         data_as_dict = as_simple_dict(obj)
+

patches/rdflib_dumper_canonical.diff

@@ -0,0 +1,22 @@
+Make linkml-convert produce deterministic RDF output.
+See https://github.com/linkml/linkml/issues/1943 for details
+and caveats
+--- rdflib_dumper.py	2024-02-24 07:36:07.532183567 +0100
++++ rdflib_dumper.py	2024-02-24 07:36:26.279874637 +0100
+@@ -6,6 +6,7 @@
+
+ from curies import Converter
+ from rdflib import Graph, URIRef, XSD
++from rdflib.compare import to_canonical_graph
+ from rdflib.term import Node, BNode, Literal
+ from rdflib.namespace import RDF
+
+@@ -66,7 +67,7 @@
+         if schemaview.namespaces()._base:
+             g.base = schemaview.namespaces()._base
+         self.inject_triples(element, schemaview, g)
+-        return g
++        return to_canonical_graph(g)
+
+     def inject_triples(self, element: Any, schemaview: SchemaView, graph: Graph, target_type: ElementName = None) -> Node:
+         """

src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.json

@@ -8,7 +8,14 @@
     {
       "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
       "meta_type": "dlccs:DataladDatasetVersionSE",
-      "is_version_of": "datalad:0b76362c-aa27-11ee-be29-b3b123281259"
+      "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+      "is_version_of": "datalad:0b76362c-aa27-11ee-be29-b3b123281259",
+      "was_generated_by": {
+        "was_associated_with": {
+          "name": "Jane Doe",
+          "email": "[email protected]"
+        }
+      }
     }
   ],
   "@type": "ContainerSE"

src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.yaml

@@ -4,4 +4,9 @@ components:
     uuid: 0b76362c-aa27-11ee-be29-b3b123281259
   - meta_id: gitsha:558275f650574389dcbbf7cd8ab5046482473fc8
     meta_type: dlccs:DataladDatasetVersionSE
+    gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
     is_version_of: datalad:0b76362c-aa27-11ee-be29-b3b123281259
+    was_generated_by:
+      was_associated_with:
+        name: Jane Doe
+        email: [email protected]

src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.json

@@ -8,6 +8,7 @@
     {
       "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
       "meta_type": "dlccs:DataladDatasetVersionSE",
+      "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
       "has_annex_remote": [
         "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf"
       ],
@@ -25,7 +26,13 @@
           "relation": "gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
           "at_location": "subdir/data.bin"
         }
-      ]
+      ],
+      "was_generated_by": {
+        "was_associated_with": {
+          "name": "Jane Doe",
+          "email": "[email protected]"
+        }
+      }
     },
     {
       "meta_id": "gitsha:56094a33cf330fef5b375aa813fc4dc07147729f",

src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.yaml

@@ -6,6 +6,11 @@ components:
   # dataset version
   - meta_id: gitsha:558275f650574389dcbbf7cd8ab5046482473fc8
     meta_type: dlccs:DataladDatasetVersionSE
+    gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
+    was_generated_by:
+      was_associated_with:
+        name: Jane Doe
+        email: [email protected]
     is_version_of: datalad:0b76362c-aa27-11ee-be29-b3b123281259
     has_annex_remote:
       - annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf

src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.json

@@ -0,0 +1,22 @@
+{
+  "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
+  "meta_type": "dlccs:DataladDatasetVersionSE",
+  "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+  "was_derived_from": [
+    "gitsha:a52963ce19a3e3628e9976555ffc8c422b29f054"
+  ],
+  "was_generated_by": {
+    "was_associated_with": {
+      "name": "Jane Doe",
+      "email": "[email protected]"
+    },
+    "was_informed_by": {
+      "was_associated_with": {
+        "name": "Jane Doe",
+        "email": "[email protected]"
+      }
+    }
+  },
+  "description": "This message describes the changes done for this particular Dataset version.\n",
+  "@type": "DataladDatasetVersionSE"
+}

src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.yaml

@@ -0,0 +1,22 @@
+meta_id: gitsha:558275f650574389dcbbf7cd8ab5046482473fc8
+meta_type: dlccs:DataladDatasetVersionSE
+gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
+description: >
+  This message describes the changes done for this particular
+  Dataset version.
+was_derived_from: 
+  - gitsha:a52963ce19a3e3628e9976555ffc8c422b29f054
+was_generated_by:
+  # we cannot declare a datetime here, without causing validation
+  # issues: https://github.com/linkml/linkml/issues/1806
+  #ended_at: 2002-05-30T09:30:10+06:00
+  was_associated_with:
+    name: Jane Doe
+    email: [email protected]
+  was_informed_by:
+    # we cannot declare a datetime here, without causing validation
+    # issues: https://github.com/linkml/linkml/issues/1806
+    #ended_at: 2001-02-28T18:27:04+02:00
+    was_associated_with:
+      name: Jane Doe
+      email: [email protected]

src/examples/datalad-dataset-version/DataladDatasetVersionSE-full.json

@@ -2,6 +2,7 @@
   "is_version_of": {
     "uuid": "0b76362c-aa27-11ee-be29-b3b123281259"
   },
+  "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
   "has_annex_remote": {
     "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf": {
       "meta_id": "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf",
@@ -32,5 +33,11 @@
       "at_location": "README.txt"
     }
   ],
+  "was_generated_by": {
+    "was_associated_with": {
+      "name": "Jane Doe",
+      "email": "[email protected]"
+    }
+  },
   "@type": "DataladDatasetVersionSE"
 }

src/examples/datalad-dataset-version/DataladDatasetVersionSE-full.yaml

@@ -1,3 +1,8 @@
+gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
+was_generated_by:
+  was_associated_with:
+    name: Jane Doe
+    email: [email protected]
 is_version_of:
   uuid: 0b76362c-aa27-11ee-be29-b3b123281259
 has_annex_remote:

src/examples/datalad-dataset-version/DataladDatasetVersionSE-minimal.json

@@ -2,5 +2,12 @@
   "is_version_of": {
     "uuid": "0b76362c-aa27-11ee-be29-b3b123281259"
   },
+  "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+  "was_generated_by": {
+    "was_associated_with": {
+      "name": "Jane Doe",
+      "email": "[email protected]"
+    }
+  },
   "@type": "DataladDatasetVersionSE"
 }