temp commit

alembic/versions/20260224_0018_add_openalex_enriched_to_publications.py

@@ -0,0 +1,30 @@
+"""Add openalex_enriched to publications
+
+Revision ID: 20260224_0018
+Revises: fa0c5e3262d5
+Create Date: 2026-02-24 19:10:00.000000
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '20260224_0018'
+down_revision: str | Sequence[str] | None = 'fa0c5e3262d5'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('publications', sa.Column('openalex_enriched', sa.Boolean(), server_default=sa.text('false'), nullable=False))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('publications', 'openalex_enriched')
+    # ### end Alembic commands ###

alembic/versions/20260224_0019_add_resolving_to_runstatus.py

@@ -0,0 +1,31 @@
+"""Add resolving to RunStatus enum
+
+Revision ID: 20260224_0019
+Revises: 20260224_0018
+Create Date: 2026-02-24 22:20:00.000000
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision: str = '20260224_0019'
+down_revision: str | Sequence[str] | None = '20260224_0018'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    # Use COMMIT to break out of the transaction block that Alembic creates in env.py.
+    # Postgres restricts ALTER TYPE ... ADD VALUE inside transactions when the type is in use.
+    # This is the robust, non-patchwork way to ensure the schema evolves correctly.
+    op.execute("COMMIT")
+    op.execute("ALTER TYPE run_status ADD VALUE IF NOT EXISTS 'resolving' AFTER 'running'")
+
+
+def downgrade() -> None:
+    # Enum values cannot be easily removed in Postgres without recreating the type,
+    # which is risky and usually avoided in simple migrations.
+    pass

alembic/versions/20260224_0020_add_openalex_last_attempt_at.py

@@ -0,0 +1,26 @@
+"""Add openalex_last_attempt_at to publications
+
+Revision ID: 20260224_0020
+Revises: 20260224_0019
+Create Date: 2026-02-24 22:50:00.000000
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '20260224_0020'
+down_revision: str | Sequence[str] | None = '20260224_0019'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.add_column('publications', sa.Column('openalex_last_attempt_at', sa.DateTime(timezone=True), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column('publications', 'openalex_last_attempt_at')

alembic/versions/20260225_0021_enforce_single_active_run_per_user.py

@@ -0,0 +1,70 @@
+"""Enforce one active crawl run per user.
+
+Revision ID: 20260225_0021
+Revises: 20260224_0020
+Create Date: 2026-02-25 09:10:00.000000
+"""
+
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "20260225_0021"
+down_revision: str | Sequence[str] | None = "20260224_0020"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+INDEX_NAME = "uq_crawl_runs_user_active"
+ACTIVE_STATUSES = ("running", "resolving")
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    indexes = {index["name"] for index in inspector.get_indexes("crawl_runs")}
+
+    op.execute("ALTER TYPE run_status ADD VALUE IF NOT EXISTS 'canceled'")
+
+    op.execute(
+        """
+        WITH ranked AS (
+            SELECT
+                id,
+                ROW_NUMBER() OVER (
+                    PARTITION BY user_id
+                    ORDER BY start_dt DESC, id DESC
+                ) AS rn
+            FROM crawl_runs
+            WHERE status IN ('running', 'resolving')
+        )
+        UPDATE crawl_runs AS runs
+        SET
+            status = 'failed',
+            end_dt = COALESCE(runs.end_dt, NOW())
+        FROM ranked
+        WHERE runs.id = ranked.id
+          AND ranked.rn > 1
+        """
+    )
+
+    if INDEX_NAME not in indexes:
+        op.create_index(
+            INDEX_NAME,
+            "crawl_runs",
+            ["user_id"],
+            unique=True,
+            postgresql_where=sa.text(
+                "status IN ('running'::run_status, 'resolving'::run_status)"
+            ),
+        )
+
+
+def downgrade() -> None:
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    indexes = {index["name"] for index in inspector.get_indexes("crawl_runs")}
+    if INDEX_NAME in indexes:
+        op.drop_index(INDEX_NAME, table_name="crawl_runs")

alembic/versions/20260225_0022_add_canonical_title_hash_to_publications.py

@@ -0,0 +1,35 @@
+"""Add canonical_title_hash to publications for cross-scholar dedup.
+
+Revision ID: 20260225_0022
+Revises: 20260225_0021
+Create Date: 2026-02-25 10:00:00.000000
+"""
+
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "20260225_0022"
+down_revision: str | Sequence[str] | None = "20260225_0021"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "publications",
+        sa.Column("canonical_title_hash", sa.String(64), nullable=True),
+    )
+    op.create_index(
+        "ix_publications_canonical_title_hash",
+        "publications",
+        ["canonical_title_hash"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("ix_publications_canonical_title_hash", table_name="publications")
+    op.drop_column("publications", "canonical_title_hash")

alembic/versions/44f7e10ef777_remove_doi_from_publications_and_.py

@@ -0,0 +1,27 @@
+"""remove_doi_from_publications_and_migrate_identifiers
+
+Revision ID: 44f7e10ef777
+Revises: 20260222_0016
+Create Date: 2026-02-22 17:03:56.261936
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '44f7e10ef777'
+down_revision: str | Sequence[str] | None = '20260222_0016'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    pass
+

alembic/versions/fa0c5e3262d5_add_api_integration_keys_to_usersetting.py

@@ -0,0 +1,39 @@
+"""Add API integration keys to UserSetting
+
+Revision ID: fa0c5e3262d5
+Revises: 44f7e10ef777
+Create Date: 2026-02-23 14:25:45.021512
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'fa0c5e3262d5'
+down_revision: str | Sequence[str] | None = '44f7e10ef777'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_publications_doi'), table_name='publications')
+    op.drop_column('publications', 'doi')
+    op.add_column('user_settings', sa.Column('openalex_api_key', sa.String(length=255), nullable=True))
+    op.add_column('user_settings', sa.Column('crossref_api_token', sa.String(length=255), nullable=True))
+    op.add_column('user_settings', sa.Column('crossref_api_mailto', sa.String(length=255), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('user_settings', 'crossref_api_mailto')
+    op.drop_column('user_settings', 'crossref_api_token')
+    op.drop_column('user_settings', 'openalex_api_key')
+    op.add_column('publications', sa.Column('doi', sa.VARCHAR(length=255), autoincrement=False, nullable=True))
+    op.create_index(op.f('ix_publications_doi'), 'publications', ['doi'], unique=False)
+    # ### end Alembic commands ###
+