from pathlib import Path import sqlite3 from sqlalchemy import create_engine, inspect, text from sqlalchemy.dialects.sqlite import dialect from sqlalchemy.schema import CreateTable from app.db import _ensure_runtime_schema from app.models import SystemUser def test_runtime_schema_adds_skipped_count_to_existing_crawl_runs_table(monkeypatch): engine = create_engine("sqlite:///:memory:") with engine.begin() as connection: connection.execute( text( """ CREATE TABLE crawl_runs ( id INTEGER PRIMARY KEY, source_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'running', found_count INTEGER NOT NULL DEFAULT 0, parsed_count INTEGER NOT NULL DEFAULT 0 ) """ ) ) monkeypatch.setattr("app.db.engine", engine) _ensure_runtime_schema() columns = {column["name"] for column in inspect(engine).get_columns("crawl_runs")} assert "skipped_count" in columns def test_runtime_schema_creates_employee_publications_table_when_employees_exist(monkeypatch): engine = create_engine("sqlite:///:memory:") with engine.begin() as connection: connection.execute( text( """ CREATE TABLE employees ( id INTEGER PRIMARY KEY, profile_key VARCHAR(255) NOT NULL UNIQUE, canonical_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'active', first_seen_at DATETIME NOT NULL, last_seen_at DATETIME NOT NULL, created_at DATETIME NOT NULL, updated_at DATETIME NOT NULL ) """ ) ) connection.execute( text( """ CREATE TABLE crawl_runs ( id INTEGER PRIMARY KEY, source_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'running', found_count INTEGER NOT NULL DEFAULT 0, parsed_count INTEGER NOT NULL DEFAULT 0, skipped_count INTEGER NOT NULL DEFAULT 0 ) """ ) ) monkeypatch.setattr("app.db.engine", engine) _ensure_runtime_schema() _ensure_runtime_schema() inspector = inspect(engine) assert "employee_publications" in inspector.get_table_names() columns = {column["name"] for column in inspector.get_columns("employee_publications")} assert {"employee_id", "publication_id", "doi_url", "authors", "raw_data", "source_hash"}.issubset(columns) def test_runtime_schema_creates_employee_news_links_table_when_employees_exist(monkeypatch): engine = create_engine("sqlite:///:memory:") with engine.begin() as connection: connection.execute( text( """ CREATE TABLE employees ( id INTEGER PRIMARY KEY, profile_key VARCHAR(255) NOT NULL UNIQUE, canonical_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'active', first_seen_at DATETIME NOT NULL, last_seen_at DATETIME NOT NULL, created_at DATETIME NOT NULL, updated_at DATETIME NOT NULL ) """ ) ) connection.execute( text( """ CREATE TABLE crawl_runs ( id INTEGER PRIMARY KEY, source_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'running', found_count INTEGER NOT NULL DEFAULT 0, parsed_count INTEGER NOT NULL DEFAULT 0, skipped_count INTEGER NOT NULL DEFAULT 0 ) """ ) ) monkeypatch.setattr("app.db.engine", engine) _ensure_runtime_schema() _ensure_runtime_schema() inspector = inspect(engine) assert "employee_news_links" in inspector.get_table_names() columns = {column["name"] for column in inspector.get_columns("employee_news_links")} assert {"employee_id", "title", "url", "summary", "published_at", "published_year", "source_hash", "raw_data"}.issubset(columns) def test_runtime_schema_adds_profile_verification_fields(monkeypatch): engine = create_engine("sqlite:///:memory:") with engine.begin() as connection: connection.execute( text( """ CREATE TABLE employees ( id INTEGER PRIMARY KEY, profile_key VARCHAR(255) NOT NULL UNIQUE, canonical_url TEXT NOT NULL, status VARCHAR(32) NOT NULL DEFAULT 'active', first_seen_at DATETIME NOT NULL, last_seen_at DATETIME NOT NULL, created_at DATETIME NOT NULL, updated_at DATETIME NOT NULL ) """ ) ) monkeypatch.setattr("app.db.engine", engine) _ensure_runtime_schema() inspector = inspect(engine) columns = {column["name"] for column in inspector.get_columns("employees")} assert {"profile_unavailable_streak", "last_profile_check_at", "has_academic_degree"}.issubset(columns) assert "employee_profile_urls" in inspector.get_table_names() def test_sqlite_council_role_migration_preserves_users_and_history(): original = str(CreateTable(SystemUser.__table__).compile(dialect=dialect())).replace(", 'council'", "") with sqlite3.connect(":memory:") as connection: connection.execute(original) connection.execute("CREATE TABLE user_actions (user_id INTEGER REFERENCES system_users(id))") connection.execute(""" INSERT INTO system_users (id, username, full_name, role, is_active, password_hash, must_change_password, session_version, failed_login_attempts, created_at) VALUES (17, 'reader', '', 'user', 1, 'fixture', 0, 4, 0, '2026-11-12') """) connection.execute("INSERT INTO user_actions VALUES (17)") before = connection.execute("SELECT * FROM system_users").fetchall() migration = Path("migrations/sqlite/014_system_user_council_role.sql").read_text(encoding="utf-8") connection.executescript(migration) assert connection.execute("SELECT * FROM system_users").fetchall() == before assert connection.execute("SELECT * FROM user_actions").fetchall() == [(17,)] connection.execute("UPDATE system_users SET role = 'council' WHERE id = 17") assert connection.execute("SELECT role FROM system_users").fetchone() == ("council",)