Merge AnnexedFile|AnnexDistribution -> StableAnnexKey

This move simplifies the class set, and also the data structure of the `datalad-dataset-components` (see example inside). A `StableAnnexKey` is now a `Distribution`, and the corresponding `Resource` subclass is dropped without a replacement. There seems to be no loss of expressiveness. This makes `StableAnnexKey` the only current "content" alternative to a `GitBlob` (which has been renamed from `FileInGit` to emphasize the focus on the content, rather than any given name). A dedicated `annex-key` namespace has been introduced too Closes #50
psychoinformatics-de · Feb 26, 2024 · 7faaa87 · 7faaa87
1 parent 69a1232
commit 7faaa87
Show file tree

Hide file tree

Showing 5 changed files with 55 additions and 81 deletions.
diff --git a/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.json b/src/examples/datalad-dataset-components/ContainerSE-DatasetWFiles.json
@@ -39,7 +39,7 @@
       "gitsha": "13ffd94a94e32f9482528fc65d59562b011f6f87",
       "qualified_part": [
         {
-          "relation": "gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58",
+          "relation": "annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin",
           "name": "data.bin"
         },
         {
@@ -54,18 +54,15 @@
       "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
@@ -28,22 +28,22 @@ components:
     gitsha: 13ffd94a94e32f9482528fc65d59562b011f6f87
     qualified_part:
       - name: data.bin
-        relation: gitsha:b94ef1797f7bfc1ac979be122e1b538bbb0d1d58
+        relation: annexkey:MD5E-s3425--32a617360d10e3dcbfdd0885e8d64ab8.bin
       - name: README.txt
         relation: gitsha:56094a33cf330fef5b375aa813fc4dc07147729f
   # 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/linkml/ontology/git-annex.yaml b/src/linkml/ontology/git-annex.yaml
@@ -5,10 +5,10 @@ description: >
   TODO
 prefixes:
   annex: https://concepts.datalad.org/namespace/annex-uuid/
+  annexkey: https://concepts.datalad.org/namespace/annex-key/
   dlco: https://concepts.datalad.org/ontology/
 imports:
   - ../ontology/datasets
-  - ../ontology/git
   - ../ontology/properties
 default_prefix: dlco
 
@@ -59,21 +59,19 @@ classes:
         https://git-annex.branchable.com/design/external_special_remote_protocol).
         A state is more or less an additional/arbitrary set of parameters.
 
-  AnnexedFile:
-    mixin: true
-    is_a: FileInGit
-      #is_a: FileInGit
-    description: >-
-      A file in a Git repository that is managed by git-annex.
-    slot_usage:
-      distribution:
-        range: AnnexDistribution
-
-  AnnexDistribution:
+  StableAnnexKey:
     mixin: true
     is_a: Distribution
     description: >-
-      A distribution that is accessible via git-annex.
+      Git-annex file content blob. Keys are identified with a name. This
+      class represents keys with a stable, content-based key name, such
+      as MD5, SHA1, SHA256 and any cryptographically secure backend,
+      including the "E" variants. Importantly, not `URL` keys.
+    slots:
+      - name
     slot_usage:
       qualified_access:
         range: QualifiedAnnexAccess
+    see_also:
+      - https://git-annex.branchable.com/internals/key_format/
+      - https://git-annex.branchable.com/backends/
diff --git a/src/linkml/ontology/git.yaml b/src/linkml/ontology/git.yaml
@@ -107,25 +107,14 @@ classes:
       links other trees and blobs under particular names.
 
 
-  FileInGit:
+  GitBlob:
     mixin: true
-    is_a: File
+    is_a: Distribution
     mixins:
       - GitTracked
     description: >-
-      A `File` that is tracked with Git.
-    todos:
-      - Rename to `GitBlob`
-
-      #QualifiedGitTrackedPart:
-      #  mixin: true
-      #  is_a: QualifiedPart
-      #  description: >-
-      #    TODO we may need this to make relation point to resources with a
-      #    (Git) identifier only, such that we could reference by key
-      #  slot_usage:
-      #    relation:
-      #      range: FileInGit
+      Content (for example of a file) that is tracked with Git.
+
 
   GitUserAgent:
     mixin: true

diff --git a/src/linkml/schemas/datalad-dataset-components.yaml b/src/linkml/schemas/datalad-dataset-components.yaml
@@ -34,6 +34,7 @@ license: MIT
 
 prefixes:
   annex: https://concepts.datalad.org/namespace/annex-uuid/
+  annexkey: https://concepts.datalad.org/namespace/annex-key/
   bibo: http://purl.org/ontology/bibo/
   datalad: https://concepts.datalad.org/namespace/dataset-uuid/
   DCAT: http://www.w3.org/ns/dcat#
@@ -100,19 +101,6 @@ classes:
       relation:
         range: GitTrackedSE
 
-  AnnexDistributionSE:
-    class_uri: dlccs:AnnexDistributionSE
-    mixins:
-      - AnnexDistribution
-    description: >-
-      Schema element for a `AnnexDistribution`.
-    slot_usage:
-      qualified_access:
-        inlined: true
-        inlined_as_list: true
-        multivalued: true
-        range: QualifiedAnnexAccessSE
-
   QualifiedAnnexAccessSE:
     class_uri: dlccs:QualifiedAnnexAccessSE
     mixins:
@@ -198,11 +186,17 @@ classes:
       - FilesystemDirectoryItem
     description: >-
       Schema element for a `FilesystemDirectoryItem`.
+    slots:
+      - relation
     slot_usage:
       relation:
-        range: GitTrackedSE
+        # union range specification does not seem to work
+        #any_of:
+        #  - range: GitTrackedSE
+        #  - range: StableAnnexKeySE
+        range: ComponentSE
     todos:
-      - make relation range a class that can only be a tree or a blob
+      - figure out why a union range specification is not working
 
   CommittingSE:
     class_uri: dlccs:CommittingSE
@@ -230,26 +224,22 @@ classes:
     class_uri: dlccs:GitBlobSE
     is_a: GitTrackedSE
     mixins:
-      - FileInGit
+      - GitBlob
     description: >-
       Schema element for a `FileInGit`.
 
-  AnnexedFileSE:
-    class_uri: dlccs:AnnexedFileSE
-    is_a: GitTrackedSE
+  StableAnnexKeySE:
+    class_uri: dlccs:StableAnnexKeySE
+    is_a: ComponentSE
     mixins:
-      - AnnexedFile
+      - StableAnnexKey
     description: >-
-      Schema element for a `AnnexedFile`.
+      Schema element for a `StableAnnexKey`.
+    slots:
+      - meta_id
     slot_usage:
-      distribution:
+      qualified_access:
         inlined: true
-        multivalued: false
-        range: AnnexDistributionSE
-        notes:
-          - This is not multivalued, because the distribution of an annexed
-            file is an annex key, a bit identical blob. The only thing that
-            we can have multiple of are remote locations, where this key is
-            available. Even when have a URL key and the actual content may
-            be unknown (yet), the system is not made to switch between
-            distributions without filename changes.
+        inlined_as_list: true
+        multivalued: true
+        range: QualifiedAnnexAccessSE