Linkml based description

README.rst

@@ -18,3 +18,9 @@ Testing
 
   sudo apt-get install jsonschema-jv
   jv -output detailed execution_report.schema.json example.json
+
+
+.. code:: bash
+
+  job_report.py [-h] [-j JOB_ID] [-k API_KEY] [-u API_URL] [-o OUT]
+

example.json

@@ -2,14 +2,16 @@
   "report_format_version": "0.0.2",
   "affiliation": [ "https://ror.org/044rwnt51" ],
 
-  "tool_identifier": [
-    "http://toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa/0.7.18" ,
-    "https://bio.tools/bwa",
-    "https://identifiers.org/RRID/RRID:SCR_010910" ],
-  "tool_name": "BWA",
-  "tool_version": "0.7.18",
-  "tool_package_version": "0.7.18-he4a0461_1",
-  "input_size": 50000,
+  "tool": {
+    "identifier": [
+      "http://toolshed.g2.bx.psu.edu/repos/devteam/bwa/bwa/0.7.18" ,
+      "https://bio.tools/bwa",
+      "https://identifiers.org/RRID/RRID:SCR_010910" ],
+    "name": "BWA",
+    "version": "0.7.18",
+    "package_version": "0.7.18-he4a0461_1"
+  },
+  "input_size_bytes": 50000,
 
   "infra": [
     { "infra_name": "de.NBI Cloud BW",
@@ -39,10 +41,10 @@
   "cpu_mods": "spectre_v1 spectre_v2 spec_store_bypass mds swapgs itlb_multihit srbds mmio_stale_data retbleed gds",
   "cpu_cores_assigned": 1,
 
-  "start_time": "2024-10-16T11:11:35",
-  "end_time": "2024-10-16T11:12:20",
+  "start_time": "2024-10-16T11:11:35Z",
+  "end_time": "2024-10-16T11:12:20Z",
 
-  "final_outputs_size": 192000,
+  "final_outputs_size_bytes": 192000,
   "memory_used": 243059916,
   "cpu_cores_used": 1,
   "gpu_cores_used": 0

execution_report.linkml.yaml

@@ -0,0 +1,127 @@
+id: https://elixir-europe.org/platforms/compute/execution_report.linkml.yaml
+name: execution_report
+description: Gives credit for the specific execution of a data analysis tool.
+prefixes:
+  linkml: https://w3id.org/linkml/
+  report: https://w3id.example.com/execution_report#
+  schema: http://schema.org/
+imports:
+  - linkml:types
+default_range: string
+version: "0.0.2"
+
+classes:
+  Provider:
+    description: Infrastructure provider.
+    attributes:
+      infra_name:
+        description: |
+          Name of the infrastructure (who should get credit).
+      infra_identifier:
+        description: |
+          Unique identifier for this infrastructure.
+        multivalued: true
+        inlined_as_list: true
+      infra_version:
+        slot_uri: schema:softwareVersion
+        description: |
+          For software-based infrastructure: the version.
+
+  Address:
+    description: |
+      The name of the physical location where the computation took place.
+    class_uri: schema:PostalAddress
+    attributes:
+      addressCountry:
+        slot_uri: schema:addressCountry
+      postalCode:
+        slot_uri: schema:postalCode
+      addressRegion:
+        slot_uri: schema:addressRegion
+      addressLocality:
+        slot_uri: schema:addressLocality
+  Location:
+    class_uri: schema:Place
+    description: |
+      Physical location where the computer was. Don't really care more than city/country.
+    attributes:
+      name:
+        slot_uri: schema:name
+      address:
+        range: Address
+
+  Tool:
+    class_uri: schema:SoftwareApplication
+    description: The data analysis tool that was executed, for which this tool execution report was generated about.
+    attributes:
+      name:
+        description: |
+          What the tool author calls the tool.
+        slot_uri: schema:name
+      identifier:
+        description: |
+          Tool identifier from bio.tools, an RRID, or other source. Multiple identifiers can be supplied for tools known to multiple registries
+        multivalued: true
+        inlined_as_list: true
+        slot_uri: schema:identifier
+        range: uri
+        # `identifier: true`, can't be used as there is more than 1
+      version:
+        slot_uri: schema:softwareVersion
+      package_version:
+        description: |
+          Version of the tool that was actually run, ideally captured from the tool itself or a packaging system (apt, conda, pip, etc..).
+
+  Report:
+    description: "Tool execution report. Gives credit for the specific execution of a data analysis tool."
+    tree_root: true
+    # https://schema.org/CreateAction ???
+    attributes:
+      report_format_version:
+        description: |
+          The version of the execution schema used.
+        pattern: "0.0.2"
+      affiliation:
+        description: |
+          Identifier of the project associated with this tool execution. Ideally from the Research Organization Registry (ROR) https://ror.org/.
+        slot_uri: schema:affiliation
+        multivalued: true
+        inlined_as_list: true
+      tool:
+        range: Tool
+      input_size_bytes:
+        description: |
+          The total size of the inputs in bytes, MUST be (rounded or binned, details TBD).
+        range: integer
+        unit:
+          ucum_code: By # bytes
+      infra:
+        multivalued: true
+        inlined_as_list: true
+        range: Provider
+      location:
+        description: |
+          Physical location
+        range: Location
+      cpu_identifier:
+      cpu_mods:
+      cpu_cores_assigned:
+        range: integer
+      start_time:
+        range: datetime
+        slot_uri: schema:startTime
+      end_time:
+        range: datetime
+        slot_uri: schema:endTime
+      duration:
+      final_outputs_size_bytes:
+        range: integer
+        unit:
+          ucum_code: By
+      memory_used:
+        range: integer
+      cpu_cores_used:
+        range: integer
+      gpu_cores_used:
+        range: integer
+