Merge pull request #193 from lsst-sqre:tickets/DM-51816

DM-51816: Stop distinguishing collaborations from authors

Author: jonathansick

CHANGELOG.md

@@ -2,6 +2,16 @@
 
 <!-- scriv-insert-here -->
 
+<a id='changelog-0.17.0'></a>
+
+## 0.17.0 (2025-07-15)
+
+### Backwards-incompatible changes
+
+- Dropped the `collaboration` table from the database schema and removed related code from the application. Originally in Ook we wanted to treat human authors separate from pseudo authors in order to make building out a staff directory easier. However, working against the grain of authordb.yaml (the canonical source for Rubin author data) has proven to be difficult. Now collaborations/collective authors will appear in the `/authors/` endpoints and in the `author` database table.
+
+- Requires database migration, `113ced7d2d29`.
+
 <a id='changelog-0.16.0'></a>
 
 ## 0.16.0 (2025-07-11)

alembic/README.md

@@ -7,7 +7,7 @@
 First, the existing database schema should be reflected in the [schema_dump.sql](schema_dump.sql) file. Specifically, the `COPY public.alembic_version` line should have the ID of the latest existing migration. If the schema dump is not up-to-date, check out a version of Ook that has the schema for the last migration and run the following command from the repo's root directory:
 
 ```bash
-nox -s db-dump-schema
+nox -s dump-db-schema
 ```
 
 This updates [schema_dump.sql](schema_dump.sql).

alembic/schema_dump.sql

@@ -0,0 +1,61 @@
+"""Drop collaboration table.
+
+Revision ID: 113ced7d2d29
+Revises: 176f421b2597
+Create Date: 2025-07-15 17:30:15.521566+00:00
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "113ced7d2d29"
+down_revision: str | None = "176f421b2597"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.drop_index(
+        op.f("ix_collaboration_internal_id"), table_name="collaboration"
+    )
+    op.drop_index(op.f("ix_collaboration_name"), table_name="collaboration")
+    op.drop_table("collaboration")
+
+
+def downgrade() -> None:
+    op.create_table(
+        "collaboration",
+        sa.Column("id", sa.BIGINT(), autoincrement=True, nullable=False),
+        sa.Column(
+            "internal_id", sa.TEXT(), autoincrement=False, nullable=False
+        ),
+        sa.Column("name", sa.TEXT(), autoincrement=False, nullable=False),
+        sa.Column(
+            "date_updated",
+            postgresql.TIMESTAMP(timezone=True),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id", name=op.f("collaboration_pkey")),
+        sa.UniqueConstraint(
+            "internal_id",
+            "name",
+            name=op.f("uq_collaboration_internal_id_name"),
+            postgresql_include=[],
+            postgresql_nulls_not_distinct=False,
+        ),
+    )
+    op.create_index(
+        op.f("ix_collaboration_name"), "collaboration", ["name"], unique=False
+    )
+    op.create_index(
+        op.f("ix_collaboration_internal_id"),
+        "collaboration",
+        ["internal_id"],
+        unique=True,
+    )

alembic/versions/20250715_1730_113ced7d2d29_drop_collaboration_table.py

@@ -1,11 +1,6 @@
 """SQLAlchemy database schema."""
 
-from .authors import (
-    SqlAffiliation,
-    SqlAuthor,
-    SqlAuthorAffiliation,
-    SqlCollaboration,
-)
+from .authors import SqlAffiliation, SqlAuthor, SqlAuthorAffiliation
 from .base import Base
 from .glossary import SqlTerm, term_relationships
 from .links import SqlLink, SqlSdmColumnLink, SqlSdmSchemaLink, SqlSdmTableLink
@@ -16,7 +11,6 @@
     "SqlAffiliation",
     "SqlAuthor",
     "SqlAuthorAffiliation",
-    "SqlCollaboration",
     "SqlLink",
     "SqlSdmColumn",
     "SqlSdmColumnLink",

src/ook/dbschema/__init__.py

@@ -21,7 +21,6 @@
     "SqlAffiliation",
     "SqlAuthor",
     "SqlAuthorAffiliation",
-    "SqlCollaboration",
 ]
 
 
@@ -86,44 +85,6 @@ class SqlAuthor(Base):
     """The date this record was last updated."""
 
 
-class SqlCollaboration(Base):
-    """A SQLAlchemy model for collaborations."""
-
-    __tablename__ = "collaboration"
-
-    __table_args__ = (
-        UniqueConstraint(
-            "internal_id", "name", name="uq_collaboration_internal_id_name"
-        ),
-    )
-
-    id: Mapped[int] = mapped_column(
-        BigInteger, primary_key=True, autoincrement=True
-    )
-    """The primary key."""
-
-    internal_id: Mapped[str] = mapped_column(
-        UnicodeText, nullable=False, index=True, unique=True
-    )
-    """The internal ID of the collaboration.
-
-    This is the key for the collaboration in lsst-texmf's authordb.yaml file.
-    """
-
-    name: Mapped[str | None] = mapped_column(
-        UnicodeText, nullable=False, index=True
-    )
-    """The name of the collaboration (unicode)."""
-
-    date_updated: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False
-    )
-    """The date this record was last updated."""
-
-    # TODO(jonathansick): consider adding an ordered many-to-many
-    # relationship to authors, but this is not needed for now.
-
-
 class SqlAffiliation(Base):
     """A SQLAlchemy model for affiliations."""
 

src/ook/dbschema/authors.py

@@ -4,7 +4,7 @@
 
 from pydantic import BaseModel, Field
 
-__all__ = ["Address", "Affiliation", "Author", "Collaboration"]
+__all__ = ["Address", "Affiliation", "Author"]
 
 
 class Address(BaseModel):
@@ -59,16 +59,6 @@ class Affiliation(BaseModel):
     )
 
 
-class Collaboration(BaseModel):
-    """A collaboration."""
-
-    name: str = Field(description="Name of the collaboration.")
-
-    internal_id: str = Field(
-        description="Internal ID of the collaboration.",
-    )
-
-
 class Author(BaseModel):
     """An author."""
 

src/ook/domain/authors.py

@@ -127,12 +127,6 @@ async def _ingest_authordb(
         await self._author_store.upsert_authors(
             list(authors.values()), delete_stale_records=delete_stale_records
         )
-        await self._author_store.upsert_collaborations(
-            collaborations=list(
-                author_db_data.collaborations_to_domain().values()
-            ),
-            delete_stale_records=delete_stale_records,
-        )
 
     async def _ingest_glossary(self, repo: LsstTexmfGitHubRepo) -> None:
         """Ingest the glossarydefs.csv file."""