Initial commit

This commit is contained in:
Jack Levy
2026-02-28 21:08:19 -05:00
commit e418dd9ae0
85 changed files with 5261 additions and 0 deletions

51
backend/alembic/env.py Normal file
View File

@@ -0,0 +1,51 @@
import os
from logging.config import fileConfig
from alembic import context
from sqlalchemy import engine_from_config, pool
# Import all models so Alembic can detect them
from app.database import Base
import app.models # noqa: F401 — registers all models with Base.metadata
config = context.config
# Override sqlalchemy.url from environment if set
sync_url = os.environ.get("SYNC_DATABASE_URL")
if sync_url:
config.set_main_option("sqlalchemy.url", sync_url)
if config.config_file_name is not None:
fileConfig(config.config_file_name)
target_metadata = Base.metadata
def run_migrations_offline() -> None:
url = config.get_main_option("sqlalchemy.url")
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
)
with context.begin_transaction():
context.run_migrations()
def run_migrations_online() -> None:
connectable = engine_from_config(
config.get_section(config.config_ini_section, {}),
prefix="sqlalchemy.",
poolclass=pool.NullPool,
)
with connectable.connect() as connection:
context.configure(connection=connection, target_metadata=target_metadata)
with context.begin_transaction():
context.run_migrations()
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()

View File

@@ -0,0 +1,26 @@
"""${message}
Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
${imports if imports else ""}
# revision identifiers, used by Alembic.
revision: str = ${repr(up_revision)}
down_revision: Union[str, None] = ${repr(down_revision)}
branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
def upgrade() -> None:
${upgrades if upgrades else "pass"}
def downgrade() -> None:
${downgrades if downgrades else "pass"}

View File

@@ -0,0 +1,205 @@
"""initial schema
Revision ID: 0001
Revises:
Create Date: 2025-01-01 00:00:00.000000
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects.postgresql import JSONB
revision: str = "0001"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ── members ──────────────────────────────────────────────────────────────
op.create_table(
"members",
sa.Column("bioguide_id", sa.String(), primary_key=True),
sa.Column("name", sa.String(), nullable=False),
sa.Column("first_name", sa.String()),
sa.Column("last_name", sa.String()),
sa.Column("party", sa.String(10)),
sa.Column("state", sa.String(5)),
sa.Column("chamber", sa.String(10)),
sa.Column("district", sa.String(10)),
sa.Column("photo_url", sa.String()),
sa.Column("official_url", sa.String()),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
# ── bills ─────────────────────────────────────────────────────────────────
op.create_table(
"bills",
sa.Column("bill_id", sa.String(), primary_key=True),
sa.Column("congress_number", sa.Integer(), nullable=False),
sa.Column("bill_type", sa.String(10), nullable=False),
sa.Column("bill_number", sa.Integer(), nullable=False),
sa.Column("title", sa.Text()),
sa.Column("short_title", sa.Text()),
sa.Column("sponsor_id", sa.String(), sa.ForeignKey("members.bioguide_id"), nullable=True),
sa.Column("introduced_date", sa.Date()),
sa.Column("latest_action_date", sa.Date()),
sa.Column("latest_action_text", sa.Text()),
sa.Column("status", sa.String(100)),
sa.Column("chamber", sa.String(10)),
sa.Column("congress_url", sa.String()),
sa.Column("govtrack_url", sa.String()),
sa.Column("last_checked_at", sa.DateTime(timezone=True)),
sa.Column("actions_fetched_at", sa.DateTime(timezone=True)),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
op.create_index("ix_bills_congress_number", "bills", ["congress_number"])
op.create_index("ix_bills_latest_action_date", "bills", ["latest_action_date"])
op.create_index("ix_bills_introduced_date", "bills", ["introduced_date"])
op.create_index("ix_bills_chamber", "bills", ["chamber"])
op.create_index("ix_bills_sponsor_id", "bills", ["sponsor_id"])
# Full-text search vector (tsvector generated column) — manual, not in autogenerate
op.execute("""
ALTER TABLE bills ADD COLUMN search_vector tsvector
GENERATED ALWAYS AS (
setweight(to_tsvector('english', coalesce(title, '')), 'A') ||
setweight(to_tsvector('english', coalesce(short_title, '')), 'A') ||
setweight(to_tsvector('english', coalesce(latest_action_text, '')), 'C')
) STORED
""")
op.execute("CREATE INDEX ix_bills_search_vector ON bills USING GIN(search_vector)")
# ── bill_actions ──────────────────────────────────────────────────────────
op.create_table(
"bill_actions",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("action_date", sa.Date()),
sa.Column("action_text", sa.Text()),
sa.Column("action_type", sa.String(100)),
sa.Column("chamber", sa.String(10)),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
op.create_index("ix_bill_actions_bill_id", "bill_actions", ["bill_id"])
op.create_index("ix_bill_actions_action_date", "bill_actions", ["action_date"])
# ── bill_documents ────────────────────────────────────────────────────────
op.create_table(
"bill_documents",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("doc_type", sa.String(50)),
sa.Column("doc_version", sa.String(50)),
sa.Column("govinfo_url", sa.String()),
sa.Column("raw_text", sa.Text()),
sa.Column("fetched_at", sa.DateTime(timezone=True)),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
op.create_index("ix_bill_documents_bill_id", "bill_documents", ["bill_id"])
# ── bill_briefs ───────────────────────────────────────────────────────────
op.create_table(
"bill_briefs",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("document_id", sa.Integer(), sa.ForeignKey("bill_documents.id", ondelete="SET NULL"), nullable=True),
sa.Column("summary", sa.Text()),
sa.Column("key_points", JSONB()),
sa.Column("risks", JSONB()),
sa.Column("deadlines", JSONB()),
sa.Column("topic_tags", JSONB()),
sa.Column("llm_provider", sa.String(50)),
sa.Column("llm_model", sa.String(100)),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
op.create_index("ix_bill_briefs_bill_id", "bill_briefs", ["bill_id"])
op.execute("CREATE INDEX ix_bill_briefs_topic_tags ON bill_briefs USING GIN(topic_tags)")
# ── committees ────────────────────────────────────────────────────────────
op.create_table(
"committees",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("committee_code", sa.String(20), unique=True, nullable=False),
sa.Column("name", sa.String(500)),
sa.Column("chamber", sa.String(10)),
sa.Column("committee_type", sa.String(50)),
)
# ── committee_bills ───────────────────────────────────────────────────────
op.create_table(
"committee_bills",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("committee_id", sa.Integer(), sa.ForeignKey("committees.id", ondelete="CASCADE"), nullable=False),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("referral_date", sa.Date()),
)
op.create_index("ix_committee_bills_bill_id", "committee_bills", ["bill_id"])
op.create_index("ix_committee_bills_committee_id", "committee_bills", ["committee_id"])
# ── news_articles ─────────────────────────────────────────────────────────
op.create_table(
"news_articles",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("source", sa.String(200)),
sa.Column("headline", sa.Text()),
sa.Column("url", sa.String(), unique=True),
sa.Column("published_at", sa.DateTime(timezone=True)),
sa.Column("relevance_score", sa.Float(), default=0.0),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
op.create_index("ix_news_articles_bill_id", "news_articles", ["bill_id"])
op.create_index("ix_news_articles_published_at", "news_articles", ["published_at"])
# ── trend_scores ──────────────────────────────────────────────────────────
op.create_table(
"trend_scores",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("bill_id", sa.String(), sa.ForeignKey("bills.bill_id", ondelete="CASCADE"), nullable=False),
sa.Column("score_date", sa.Date(), nullable=False),
sa.Column("newsapi_count", sa.Integer(), default=0),
sa.Column("gnews_count", sa.Integer(), default=0),
sa.Column("gtrends_score", sa.Float(), default=0.0),
sa.Column("composite_score", sa.Float(), default=0.0),
sa.UniqueConstraint("bill_id", "score_date", name="uq_trend_scores_bill_date"),
)
op.create_index("ix_trend_scores_bill_id", "trend_scores", ["bill_id"])
op.create_index("ix_trend_scores_score_date", "trend_scores", ["score_date"])
op.create_index("ix_trend_scores_composite", "trend_scores", ["composite_score"])
# ── follows ───────────────────────────────────────────────────────────────
op.create_table(
"follows",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("follow_type", sa.String(20), nullable=False),
sa.Column("follow_value", sa.String(), nullable=False),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
sa.UniqueConstraint("follow_type", "follow_value", name="uq_follows_type_value"),
)
# ── app_settings ──────────────────────────────────────────────────────────
op.create_table(
"app_settings",
sa.Column("key", sa.String(), primary_key=True),
sa.Column("value", sa.String()),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
)
def downgrade() -> None:
op.drop_table("app_settings")
op.drop_table("follows")
op.drop_table("trend_scores")
op.drop_table("news_articles")
op.drop_table("committee_bills")
op.drop_table("committees")
op.drop_table("bill_briefs")
op.drop_table("bill_documents")
op.drop_table("bill_actions")
op.drop_table("bills")
op.drop_table("members")

View File

@@ -0,0 +1,30 @@
"""widen chamber and party columns
Revision ID: 0002
Revises: 0001
Create Date: 2026-02-28 00:00:00.000000
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
revision: str = "0002"
down_revision: Union[str, None] = "0001"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.alter_column("members", "chamber", type_=sa.String(50))
op.alter_column("members", "party", type_=sa.String(50))
op.alter_column("bills", "chamber", type_=sa.String(50))
op.alter_column("bill_actions", "chamber", type_=sa.String(50))
def downgrade() -> None:
op.alter_column("bill_actions", "chamber", type_=sa.String(10))
op.alter_column("bills", "chamber", type_=sa.String(10))
op.alter_column("members", "party", type_=sa.String(10))
op.alter_column("members", "chamber", type_=sa.String(10))

View File

@@ -0,0 +1,26 @@
"""widen member state and district columns
Revision ID: 0003
Revises: 0002
Create Date: 2026-03-01 00:00:00.000000
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
revision: str = "0003"
down_revision: Union[str, None] = "0002"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.alter_column("members", "state", type_=sa.String(50))
op.alter_column("members", "district", type_=sa.String(50))
def downgrade() -> None:
op.alter_column("members", "district", type_=sa.String(10))
op.alter_column("members", "state", type_=sa.String(5))

View File

@@ -0,0 +1,27 @@
"""add brief_type to bill_briefs
Revision ID: 0004
Revises: 0003
Create Date: 2026-03-01 00:00:00.000000
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
revision: str = "0004"
down_revision: Union[str, None] = "0003"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.add_column(
"bill_briefs",
sa.Column("brief_type", sa.String(20), nullable=False, server_default="full"),
)
def downgrade() -> None:
op.drop_column("bill_briefs", "brief_type")