feat: store kingfisher process collection notes

data_registry/admin.py

@@ -259,6 +259,12 @@ class Media:
                 ),
             },
         ),
+        (
+            "Logs",
+            {
+                "fields": ("process_notes",),
+            },
+        ),
         (
             "Overview",
             {
@@ -299,6 +305,7 @@ class Media:
         "active",
         "archived",
         "context",
+        "process_notes",
         "start",
         "end",
         # Overview

data_registry/migrations/0059_job_process_notes.py

@@ -0,0 +1,21 @@
+# Generated by Django 4.2.14 on 2024-12-18 19:20
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("data_registry", "0058_alter_collection_update_frequency"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="job",
+            name="process_notes",
+            field=models.JSONField(
+                blank=True,
+                default=dict,
+                help_text="The collection notes from Kingfisher Process.",
+            ),
+        ),
+    ]

data_registry/models.py

@@ -68,6 +68,11 @@ class Status(models.TextChoices):
         "<dd>The name of the dataset in Pelican</dd>"
         "</dl>",
     )
+    process_notes = models.JSONField(
+        blank=True,
+        default=dict,
+        help_text="The collection notes from Kingfisher Process.",
+    )
 
     # Job logic
     archived = models.BooleanField(

data_registry/process_manager/task/process.py

@@ -45,27 +45,23 @@ def run(self):
     def get_status(self):
         process_id = self.job.context["process_id"]  # set in Collect.get_status()
 
-        response = self.request(
+        tree = self.request(
             "GET",
             url_for_collection(process_id, "tree"),
             error_message=f"Unable to get status of collection {process_id}",
-        )
-
-        tree = response.json()
+        ).json()
 
         original_collection = next(c for c in tree if c["transform_type"] == "")
         compiled_collection = next(c for c in tree if c["transform_type"] == "compile-releases")
 
         if not compiled_collection["completed_at"]:
             return Task.Status.RUNNING
 
-        response = self.request(
+        meta = self.request(
             "GET",
             url_for_collection(compiled_collection["id"], "metadata"),
             error_message=f"Unable to get metadata of collection {compiled_collection['id']}",
-        )
-
-        meta = response.json()
+        ).json()
 
         # The metadata can be empty (or partial) if the collection contained no data.
         if meta:
@@ -76,6 +72,13 @@ def get_status(self):
             self.job.ocid_prefix = meta.get("ocid_prefix") or ""
 
         self.job.context["process_id_pelican"] = compiled_collection["id"]
+
+        self.job.process_notes = self.request(
+            "GET",
+            url_for_collection(original_collection["id"], "notes"),
+            error_message=f"Unable to get notes of collection {original_collection['id']}",
+        ).json()
+
         self.job.save(
             update_fields=[
                 "modified",
@@ -85,6 +88,7 @@ def get_status(self):
                 "license",
                 "publication_policy",
                 "ocid_prefix",
+                "process_notes",
             ]
         )