CREATE TABLE IF NOT EXISTS dataset_versions (
  id SERIAL PRIMARY KEY,
  hash VARCHAR(64) NOT NULL UNIQUE,
  previous_hash VARCHAR(64),
  crawl_run_id INTEGER REFERENCES crawl_runs(id),
  employee_count INTEGER NOT NULL DEFAULT 0,
  active_count INTEGER NOT NULL DEFAULT 0,
  dismissed_count INTEGER NOT NULL DEFAULT 0,
  created_at TIMESTAMPTZ NOT NULL DEFAULT now()
);

CREATE INDEX IF NOT EXISTS ix_dataset_versions_created_at
  ON dataset_versions (created_at);

CREATE TABLE IF NOT EXISTS dataset_version_items (
  id SERIAL PRIMARY KEY,
  dataset_version_id INTEGER NOT NULL REFERENCES dataset_versions(id),
  profile_key VARCHAR(255) NOT NULL,
  employee_id INTEGER REFERENCES employees(id),
  status VARCHAR(32) NOT NULL,
  checksum VARCHAR(64) NOT NULL,
  CONSTRAINT uq_dataset_version_items_version_profile UNIQUE (dataset_version_id, profile_key)
);

CREATE INDEX IF NOT EXISTS ix_dataset_version_items_hash
  ON dataset_version_items (dataset_version_id);

CREATE INDEX IF NOT EXISTS ix_dataset_version_items_profile_key
  ON dataset_version_items (profile_key);