| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288 |
- """add evidence packages and versioned platform demand objects
- Revision ID: 20260731_10
- Revises: 20260731_09
- Create Date: 2026-07-31
- """
- from __future__ import annotations
- from collections.abc import Sequence
- import sqlalchemy as sa
- from alembic import op
- revision: str = "20260731_10"
- down_revision: str | None = "20260731_09"
- branch_labels: str | Sequence[str] | None = None
- depends_on: str | Sequence[str] | None = None
- def _pipeline_table_options() -> dict[str, str]:
- bind = op.get_bind()
- if bind.dialect.name != "mysql":
- return {}
- row = bind.execute(
- sa.text(
- "SELECT CHARACTER_SET_NAME, COLLATION_NAME "
- "FROM INFORMATION_SCHEMA.COLUMNS "
- "WHERE TABLE_SCHEMA = DATABASE() "
- "AND TABLE_NAME = 'pipeline_run' "
- "AND COLUMN_NAME = 'run_id'"
- )
- ).one()
- return {
- "mysql_charset": str(row.CHARACTER_SET_NAME),
- "mysql_collate": str(row.COLLATION_NAME),
- }
- def upgrade() -> None:
- table_options = _pipeline_table_options()
- op.create_table(
- "evidence_package",
- sa.Column("package_id", sa.String(36), primary_key=True),
- sa.Column(
- "run_id",
- sa.String(36),
- sa.ForeignKey("pipeline_run.run_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column("biz_dt", sa.String(8), nullable=False),
- sa.Column("package_version", sa.Integer(), nullable=False),
- sa.Column("status", sa.String(24), nullable=False),
- sa.Column("source_snapshot_hash", sa.String(64), nullable=False),
- sa.Column("source_versions_json", sa.JSON(), nullable=False),
- sa.Column("evidence_count", sa.Integer(), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint("run_id", name="uk_evidence_package_run"),
- **table_options,
- )
- op.create_index(
- "idx_evidence_package_biz",
- "evidence_package",
- ["biz_dt", "created_at"],
- )
- op.create_table(
- "raw_demand_expression",
- sa.Column("expression_id", sa.String(36), primary_key=True),
- sa.Column(
- "package_id",
- sa.String(36),
- sa.ForeignKey("evidence_package.package_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column("source_type", sa.String(64), nullable=False),
- sa.Column("source_record_id", sa.String(128), nullable=False),
- sa.Column("raw_text", sa.String(512), nullable=False),
- sa.Column("original_payload_json", sa.JSON(), nullable=False),
- sa.Column("content_hash", sa.String(64), nullable=False),
- sa.Column("observed_biz_dt", sa.String(8), nullable=False),
- sa.Column("data_quality", sa.String(24), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint(
- "package_id",
- "source_type",
- "source_record_id",
- name="uk_raw_expression_source",
- ),
- **table_options,
- )
- op.create_index(
- "idx_raw_expression_package",
- "raw_demand_expression",
- ["package_id"],
- )
- op.create_index(
- "idx_raw_expression_hash",
- "raw_demand_expression",
- ["content_hash"],
- )
- op.create_table(
- "standard_demand_term",
- sa.Column("term_id", sa.String(36), primary_key=True),
- sa.Column("canonical_key", sa.String(64), nullable=False),
- sa.Column("canonical_text", sa.String(256), nullable=False),
- sa.Column("normalized_text", sa.String(256), nullable=False),
- sa.Column("status", sa.String(24), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.Column("updated_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint("canonical_key", name="uk_standard_demand_term_key"),
- **table_options,
- )
- op.create_index(
- "idx_standard_demand_term_text",
- "standard_demand_term",
- ["normalized_text"],
- )
- op.create_table(
- "standard_demand_alias",
- sa.Column("alias_id", sa.String(36), primary_key=True),
- sa.Column(
- "term_id",
- sa.String(36),
- sa.ForeignKey("standard_demand_term.term_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column(
- "expression_id",
- sa.String(36),
- sa.ForeignKey("raw_demand_expression.expression_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column("alias_text", sa.String(512), nullable=False),
- sa.Column("relation_type", sa.String(32), nullable=False),
- sa.Column("confidence", sa.Numeric(6, 5), nullable=False),
- sa.Column("reason", sa.Text(), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint(
- "term_id",
- "expression_id",
- name="uk_standard_demand_alias_expression",
- ),
- **table_options,
- )
- op.create_index(
- "idx_standard_demand_alias_term",
- "standard_demand_alias",
- ["term_id"],
- )
- op.create_table(
- "platform_demand",
- sa.Column("platform_demand_id", sa.String(36), primary_key=True),
- sa.Column("canonical_key", sa.String(64), nullable=False),
- sa.Column("name", sa.String(256), nullable=False),
- sa.Column("description", sa.Text(), nullable=False),
- sa.Column("status", sa.String(24), nullable=False),
- sa.Column("lifecycle_state", sa.String(24), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.Column("updated_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint("canonical_key", name="uk_platform_demand_key"),
- **table_options,
- )
- op.create_index("idx_platform_demand_name", "platform_demand", ["name"])
- op.create_index("idx_platform_demand_status", "platform_demand", ["status"])
- op.create_table(
- "platform_demand_version",
- sa.Column("platform_demand_version_id", sa.String(36), primary_key=True),
- sa.Column(
- "platform_demand_id",
- sa.String(36),
- sa.ForeignKey("platform_demand.platform_demand_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column(
- "term_id",
- sa.String(36),
- sa.ForeignKey("standard_demand_term.term_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column(
- "package_id",
- sa.String(36),
- sa.ForeignKey("evidence_package.package_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column(
- "run_id",
- sa.String(36),
- sa.ForeignKey("pipeline_run.run_id", ondelete="RESTRICT"),
- nullable=False,
- ),
- sa.Column("source_demand_grade_id", sa.BigInteger(), nullable=False),
- sa.Column("version_no", sa.Integer(), nullable=False),
- sa.Column("biz_dt", sa.String(8), nullable=False),
- sa.Column("name", sa.String(256), nullable=False),
- sa.Column("description", sa.Text(), nullable=False),
- sa.Column("cognition_confidence", sa.Numeric(6, 5), nullable=False),
- sa.Column("reason", sa.Text(), nullable=False),
- sa.Column("change_type", sa.String(24), nullable=False),
- sa.Column("evidence_hash", sa.String(64), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint(
- "platform_demand_id",
- "version_no",
- name="uk_platform_demand_version_no",
- ),
- sa.UniqueConstraint(
- "platform_demand_id",
- "run_id",
- name="uk_platform_demand_version_run",
- ),
- **table_options,
- )
- op.create_index(
- "idx_platform_demand_version_biz",
- "platform_demand_version",
- ["biz_dt", "run_id"],
- )
- op.create_table(
- "platform_demand_category_rel",
- sa.Column("rel_id", sa.String(36), primary_key=True),
- sa.Column(
- "platform_demand_version_id",
- sa.String(36),
- sa.ForeignKey(
- "platform_demand_version.platform_demand_version_id",
- ondelete="RESTRICT",
- ),
- nullable=False,
- ),
- sa.Column("category_id", sa.BigInteger(), nullable=False),
- sa.Column("relation_type", sa.String(32), nullable=False),
- sa.Column("relation_source", sa.String(64), nullable=False),
- sa.Column("reason", sa.Text(), nullable=False),
- sa.Column("confidence", sa.Numeric(6, 5), nullable=False),
- sa.Column("is_inferred", sa.Boolean(), nullable=False),
- sa.Column("status", sa.String(24), nullable=False),
- sa.Column("valid_from_biz_dt", sa.String(8), nullable=False),
- sa.Column("created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False),
- sa.UniqueConstraint(
- "platform_demand_version_id",
- "category_id",
- "relation_type",
- name="uk_platform_demand_category_rel",
- ),
- **table_options,
- )
- op.create_index(
- "idx_platform_demand_category_node",
- "platform_demand_category_rel",
- ["category_id"],
- )
- def downgrade() -> None:
- op.drop_index(
- "idx_platform_demand_category_node",
- table_name="platform_demand_category_rel",
- )
- op.drop_table("platform_demand_category_rel")
- op.drop_index(
- "idx_platform_demand_version_biz",
- table_name="platform_demand_version",
- )
- op.drop_table("platform_demand_version")
- op.drop_index("idx_platform_demand_status", table_name="platform_demand")
- op.drop_index("idx_platform_demand_name", table_name="platform_demand")
- op.drop_table("platform_demand")
- op.drop_index(
- "idx_standard_demand_alias_term",
- table_name="standard_demand_alias",
- )
- op.drop_table("standard_demand_alias")
- op.drop_index(
- "idx_standard_demand_term_text",
- table_name="standard_demand_term",
- )
- op.drop_table("standard_demand_term")
- op.drop_index("idx_raw_expression_hash", table_name="raw_demand_expression")
- op.drop_index("idx_raw_expression_package", table_name="raw_demand_expression")
- op.drop_table("raw_demand_expression")
- op.drop_index("idx_evidence_package_biz", table_name="evidence_package")
- op.drop_table("evidence_package")
|