Merge pull request #54 from psychoinformatics-de/rf-49

Various concept simplifications
psychoinformatics-de · Feb 26, 2024 · 41dc75e · 41dc75e
2 parents 4085e11 + 2afc2ce
commit 41dc75e
Show file tree

Hide file tree

Showing 16 changed files with 267 additions and 145 deletions.
diff --git a/Makefile b/Makefile
@@ -103,6 +103,7 @@ convert-examples-%: src/linkml/schemas/%.yaml src/examples/%
 			linkml-convert \
 				-s "$<" \
 				--target-class-from-path \
+				--infer \
 				-t "$$outf" \
 				"$$ex" \
 				> $${ex%.yaml}.$${outf}.tmp && \

diff --git a/src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.json b/src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.json
@@ -9,7 +9,9 @@
       "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
       "meta_type": "dlccs:DataladDatasetVersionSE",
       "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+      "distribution": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
       "is_version_of": "datalad:0b76362c-aa27-11ee-be29-b3b123281259",
+      "tree": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
       "was_generated_by": {
         "was_associated_with": {
           "name": "Jane Doe",

diff --git a/src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.yaml b/src/examples/datalad-dataset-components/ContainerSE-DataladDatasetVersion-linkage.yaml
@@ -6,6 +6,7 @@ components:
     meta_type: dlccs:DataladDatasetVersionSE
     gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
     is_version_of: datalad:0b76362c-aa27-11ee-be29-b3b123281259
+    tree: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
     was_generated_by:
       was_associated_with:
         name: Jane Doe

diff --git a/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.json b/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.json
@@ -9,49 +9,60 @@
       "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
       "meta_type": "dlccs:DataladDatasetVersionSE",
       "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+      "distribution": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
       "has_annex_remote": [
         "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf"
       ],
-      "has_part": [
-        "gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
-        "gitsha:56094a33cf330fef5b375aa813fc4dc07147729f"
-      ],
       "is_version_of": "datalad:0b76362c-aa27-11ee-be29-b3b123281259",
-      "qualified_part": [
-        {
-          "relation": "gitsha:56094a33cf330fef5b375aa813fc4dc07147729f",
-          "at_location": "subdir/README.txt"
-        },
-        {
-          "relation": "gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
-          "at_location": "subdir/data.bin"
-        }
-      ],
+      "tree": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
       "was_generated_by": {
         "was_associated_with": {
           "name": "Jane Doe",
           "email": "[email protected]"
         }
       }
     },
+    {
+      "meta_id": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "meta_type": "dlccs:GitTreeSE",
+      "gitsha": "712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "qualified_part": [
+        {
+          "relation": "gitsha:13ffd94a94e32f9482528fc65d59562b011f6f87",
+          "name": "subdir"
+        }
+      ]
+    },
+    {
+      "meta_id": "gitsha:13ffd94a94e32f9482528fc65d59562b011f6f87",
+      "meta_type": "dlccs:GitTreeSE",
+      "gitsha": "13ffd94a94e32f9482528fc65d59562b011f6f87",
+      "qualified_part": [
+        {
+          "relation": "annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin",
+          "name": "data.bin"
+        },
+        {
+          "relation": "gitsha:56094a33cf330fef5b375aa813fc4dc07147729f",
+          "name": "README.txt"
+        }
+      ]
+    },
     {
       "meta_id": "gitsha:56094a33cf330fef5b375aa813fc4dc07147729f",
       "meta_type": "dlccs:GitBlobSE",
       "gitsha": "56094a33cf330fef5b375aa813fc4dc07147729f"
     },
     {
-      "meta_id": "gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
-      "meta_type": "dlccs:AnnexedFileSE",
-      "gitsha": "b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
-      "distribution": {
-        "qualified_access": [
-          {
-            "relation": "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf",
-            "access_id": "MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.txt"
-          }
-        ],
-        "byte_size": 3425
-      }
+      "meta_id": "annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin",
+      "meta_type": "dlccs:StableAnnexKeySE",
+      "qualified_access": [
+        {
+          "relation": "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf",
+          "access_id": "MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin"
+        }
+      ],
+      "byte_size": 3425
     },
     {
       "meta_id": "annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf",

diff --git a/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.yaml b/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.yaml
@@ -7,37 +7,43 @@ components:
   - meta_id: gitsha:558275f650574389dcbbf7cd8ab5046482473fc8
     meta_type: dlccs:DataladDatasetVersionSE
     gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
+    tree: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
     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
-    has_part:
-      # could link an entire tree as one part, which would have parts
-      # of its own
-      # such a tree would also need to support `qualified_part`
-      - gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58
-      - gitsha:56094a33cf330fef5b375aa813fc4dc07147729f
+  # root tree of dataset version
+  - meta_id: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
+    meta_type: dlccs:GitTreeSE
+    gitsha: 712f54082540c4f07f4f18e50fcd47e2ae9b95ed
     qualified_part:
-      - at_location: subdir/README.txt
+      - name: subdir
+        relation: gitsha:13ffd94a94e32f9482528fc65d59562b011f6f87
+  # subdir tree of dataset version
+  - meta_id: gitsha:13ffd94a94e32f9482528fc65d59562b011f6f87
+    meta_type: dlccs:GitTreeSE
+    gitsha: 13ffd94a94e32f9482528fc65d59562b011f6f87
+    qualified_part:
+      - name: data.bin
+        relation: annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin
+      - name: README.txt
         relation: gitsha:56094a33cf330fef5b375aa813fc4dc07147729f
-      - at_location: subdir/data.bin
-        relation: gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58
   # git blob
   - meta_id: gitsha:56094a33cf330fef5b375aa813fc4dc07147729f
     meta_type: dlccs:GitBlobSE
     gitsha: 56094a33cf330fef5b375aa813fc4dc07147729f
   # annexed file
-  - meta_id: gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58
-    meta_type: dlccs:AnnexedFileSE
-    gitsha: b94ef1797f7bfc1ac979be122e1b538bbb0d1d58
-    distribution:
-      byte_size: 3425
-      qualified_access:
-        - access_id: MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.txt
-          relation: annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf
+  - meta_id: annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin
+    meta_type: dlccs:StableAnnexKeySE
+    byte_size: 3425
+    qualified_access:
+      # TODO access_id is not needed in most cases, should likely
+      # because some kind of `STATE` report
+      - access_id: MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin
+        relation: annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf
   # annex remote
   - meta_id: annex:7e0bf3e7-7d46-4093-813e-b4009826c3bf
     meta_type: dlccs:AnnexRemoteSE

diff --git a/src/examples/datalad-dataset-components/ContainerSE-DatasetWSubdataset.json b/src/examples/datalad-dataset-components/ContainerSE-DatasetWSubdataset.json
@@ -0,0 +1,45 @@
+{
+  "components": [
+    {
+      "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
+      "meta_type": "dlccs:DataladDatasetVersionSE",
+      "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+      "distribution": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "has_part": [
+        "gitsha:d956832059a7837ad31e60a84ec1399b3460e0e3"
+      ],
+      "tree": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "was_generated_by": {
+        "was_associated_with": {
+          "name": "Jane Doe",
+          "email": "[email protected]"
+        }
+      }
+    },
+    {
+      "meta_id": "gitsha:d956832059a7837ad31e60a84ec1399b3460e0e3",
+      "meta_type": "dlccs:DataladDatasetVersionSE",
+      "gitsha": "d956832059a7837ad31e60a84ec1399b3460e0e3",
+      "distribution": "gitsha:0dc0410fd3328c608ca8d89802fb0f9f4a84abf9",
+      "tree": "gitsha:0dc0410fd3328c608ca8d89802fb0f9f4a84abf9",
+      "was_generated_by": {
+        "was_associated_with": {
+          "name": "John Doe",
+          "email": "[email protected]"
+        }
+      }
+    },
+    {
+      "meta_id": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "meta_type": "dlccs:GitTreeSE",
+      "gitsha": "712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+      "qualified_part": [
+        {
+          "relation": "gitsha:0dc0410fd3328c608ca8d89802fb0f9f4a84abf9",
+          "name": "subds"
+        }
+      ]
+    }
+  ],
+  "@type": "ContainerSE"
+}
diff --git a/src/examples/datalad-dataset-components/ContainerSE-DatasetWSubdataset.yaml b/src/examples/datalad-dataset-components/ContainerSE-DatasetWSubdataset.yaml
@@ -0,0 +1,30 @@
+components:
+  # (super)dataset version
+  - meta_id: gitsha:558275f650574389dcbbf7cd8ab5046482473fc8
+    meta_type: dlccs:DataladDatasetVersionSE
+    gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
+    tree: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
+    has_part:
+      # the DataladDatasetVersion instance is the part
+      - gitsha:d956832059a7837ad31e60a84ec1399b3460e0e3
+    was_generated_by:
+      was_associated_with:
+        name: Jane Doe
+        email: [email protected]
+  # (sub)dataset version
+  - meta_id: gitsha:d956832059a7837ad31e60a84ec1399b3460e0e3
+    meta_type: dlccs:DataladDatasetVersionSE
+    gitsha: d956832059a7837ad31e60a84ec1399b3460e0e3
+    tree: gitsha:0dc0410fd3328c608ca8d89802fb0f9f4a84abf9
+    was_generated_by:
+      was_associated_with:
+        name: John Doe
+        email: [email protected]
+  # root tree of (super)dataset version
+  - meta_id: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
+    meta_type: dlccs:GitTreeSE
+    gitsha: 712f54082540c4f07f4f18e50fcd47e2ae9b95ed
+    qualified_part:
+      - name: subds
+        # link (sub)dataset version tree directly
+        relation: gitsha:0dc0410fd3328c608ca8d89802fb0f9f4a84abf9
diff --git a/src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.json b/src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.json
@@ -2,6 +2,8 @@
   "meta_id": "gitsha:558275f650574389dcbbf7cd8ab5046482473fc8",
   "meta_type": "dlccs:DataladDatasetVersionSE",
   "gitsha": "558275f650574389dcbbf7cd8ab5046482473fc8",
+  "distribution": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
+  "tree": "gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed",
   "was_derived_from": [
     "gitsha:a52963ce19a3e3628e9976555ffc8c422b29f054"
   ],

diff --git a/src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.yaml b/src/examples/datalad-dataset-components/DataladDatasetVersionSE-commitprops.yaml
@@ -4,6 +4,7 @@ gitsha: 558275f650574389dcbbf7cd8ab5046482473fc8
 description: >
   This message describes the changes done for this particular
   Dataset version.
+tree: gitsha:712f54082540c4f07f4f18e50fcd47e2ae9b95ed
 was_derived_from: 
   - gitsha:a52963ce19a3e3628e9976555ffc8c422b29f054
 was_generated_by:

diff --git a/src/linkml/ontology/datalad.yaml b/src/linkml/ontology/datalad.yaml
@@ -27,6 +27,9 @@ classes:
     slots:
       - has_annex_remote
     slot_usage:
+      distribution:
+        range: FilesystemDirectory
+        equals_expression: "{tree}"
       is_version_of:
         range: DataladDataset
     todos:

diff --git a/src/linkml/ontology/datasets.yaml b/src/linkml/ontology/datasets.yaml
@@ -127,7 +127,7 @@ classes:
         inlined_as_list: true
       type:
         description: >-
-          Type of resource, e.g. `Dataset`, `Directory`, or `File`.
+          Type of resource, e.g. `Dataset`.
 
   QualifiedAccess:
     description: >-
@@ -153,15 +153,12 @@ classes:
     broad_mappings:
       - DCAT:Relationship
     slots:
+      - name
       - relation
-      - at_location
     slot_usage:
-      at_location:
+      name:
         description: >-
-          The relative location of the part within the containing entity.
-        range: PosixRelPath
-      relation:
-        range: Resource
+          The name of the part within the containing entity.
     comments:
       - This class is a key element of the data model. It enables referencing
         a particular resource (e.g., a file's content, or versioned directory
@@ -185,39 +182,6 @@ classes:
       - distribution
       - is_version_of
 
-  Directory:
-    is_a: Resource
-    description: >-
-       Cataloging structure which contains references to other files,
-       and possibly other directories (or datasets).
-    exact_mappings:
-      - ncit:NCIT_C62486
-    broad_mappings:
-      - ncit:NCIT_C49057
-    narrow_mappings:
-      - ncit:NCIT_C172256
-
-  File:
-    mixin: true
-    is_a: Resource
-    description: >-
-      Resource for storing information, which is available to a computer
-      program and is usually based on some kind of durable storage.
-      A file is a conceptual entity, and can be represented by one or more
-      distributions that serialize the file for transfer. Distributions of
-      a file can be provided via data services.
-    slots:
-      - distribution
-    exact_mappings:
-      - afo:AFR_0000639
-    comments:
-      - Being a conceptual entity, this class does not include properties
-        for exact identification of a file's content. This is the domain
-        of a `Distribution`.
-      - It would make sense to avoid assigning a global identifier to an
-        instance of this class and instead specify inline within its
-        immediate context (e.g., a `QualifiedPart` of another `Resource`).
-
   Distribution:
     mixin: true
     description: >-
@@ -235,6 +199,33 @@ classes:
         Compared to `DCAT:Distribution` this class has a `qualified_access`
         property to enable the specification of access-related parameters
         that cannot be inferred from a standard `DCAT:Distribution`.
+    todos:
+      - Now that there is a `Directory` subclass, re-evaluate the utility
+        of the `checksum` property at this level.
+
+  FilesystemDirectory:
+    mixin: true
+    is_a: Distribution
+    description: >-
+       Filesystem structure which contains references to files,
+       or other directories.
+    slots:
+      - qualified_part
+    slot_usage:
+      qualified_part:
+        range: FilesystemDirectoryItem
+    exact_mappings:
+      - ncit:NCIT_C62486
+    broad_mappings:
+      - ncit:NCIT_C49057
+    narrow_mappings:
+      - ncit:NCIT_C172256
+
+  FilesystemDirectoryItem:
+    mixin: true
+    is_a: QualifiedPart
+    description: >-
+       Named reference of a content item in the context of a `FilesystemDirectory`
 
   DataService:
     class_uri: dlco:DataService