"""Record what an annotation run produced, and how specific each HPO term is

Two changes, both so the ranking can stop asserting things it has not measured:

- jobs.has_frequencies / has_effect_scores: whether the run looked up allele frequencies and
  CADD/AlphaMissense at all. Without this the API cannot tell "absent from gnomAD" (strong
  evidence) from "nobody checked gnomAD" (no evidence), and scored both as maximally rare.
- hpo_terms: each term's information content, so a phenotype match is weighted by how specific
  the matching term is rather than counting every term alike.

Existing rows default to false, which is correct: every job recorded before this ran used VEP's
database mode, which returns neither frequencies nor plugin scores.

Revision ID: b7d4e2f80c31
Revises: 9a1c2d3e4f50
"""
from collections.abc import Sequence

import sqlalchemy as sa
from alembic import op

revision: str = "b7d4e2f80c31"
down_revision: str | None = "9a1c2d3e4f50"
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None


def upgrade() -> None:
    op.add_column(
        "jobs",
        sa.Column("has_frequencies", sa.Boolean(), nullable=False, server_default=sa.false()),
    )
    op.add_column(
        "jobs",
        sa.Column("has_effect_scores", sa.Boolean(), nullable=False, server_default=sa.false()),
    )
    op.create_table(
        "hpo_terms",
        sa.Column("hpo_id", sa.String(length=20), primary_key=True),
        sa.Column("name", sa.String(length=200), nullable=False),
        sa.Column("ic", sa.Float(), nullable=False),
    )


def downgrade() -> None:
    op.drop_table("hpo_terms")
    op.drop_column("jobs", "has_effect_scores")
    op.drop_column("jobs", "has_frequencies")