settled-reach/tooling/db/backfill_cultural_corridor.py

#!/usr/bin/env python3
"""
Backfill star_systems.cultural_corridor and bodies.cultural_corridor.

The schema has a `cultural_corridor` column on both tables, but
`wiki_sync.py` never populated it from the wiki index.md files — the
cultural/geographic identity of each system lives in
`star_systems.geographic_sector` instead (values: core, north_reach,
south_reach, east_reach, west_reach, deep_frontier). These two fields
refer to the same concept: which arc of the reach the system belongs
to. Leaving `cultural_corridor` NULL on 99%+ of rows defeats every
downstream consumer that actually wants to filter by corridor
(gemma_naming.py, future atlas UI queries, narrative tools).

This script treats `geographic_sector` as the source of truth and
copies it into `cultural_corridor`:

    star_systems.cultural_corridor := star_systems.geographic_sector
        WHERE cultural_corridor IS NULL

    bodies.cultural_corridor := parent star_systems.cultural_corridor
        WHERE bodies.cultural_corridor IS NULL

It is safe to re-run — idempotent, NULL-only updates, explicit
transaction wrapper so a crash never leaves a half-populated state.
Run it after any `wiki_sync.py` pass that creates fresh systems.db
rows.

Usage:
    tooling/db/backfill_cultural_corridor.py
    tooling/db/backfill_cultural_corridor.py --db path/to/systems.db
    tooling/db/backfill_cultural_corridor.py --dry-run

Decisions: D-191 (atlas pipeline — downstream consumer)
"""

import argparse
import sqlite3
import sys
from pathlib import Path

SCRIPT_DIR = Path(__file__).resolve().parent
REPO_ROOT = (SCRIPT_DIR / ".." / "..").resolve()
DB_PATH = REPO_ROOT / "server" / "data" / "systems.db"


def main():
    parser = argparse.ArgumentParser(
        description="Backfill cultural_corridor on star_systems and bodies"
    )
    parser.add_argument("--db", default=str(DB_PATH), help="Path to systems.db")
    parser.add_argument(
        "--dry-run",
        action="store_true",
        help="Report counts without writing",
    )
    args = parser.parse_args()

    db_path = Path(args.db)
    if not db_path.exists():
        print(f"error: {db_path} not found", file=sys.stderr)
        sys.exit(1)

    conn = sqlite3.connect(str(db_path))
    conn.execute("PRAGMA foreign_keys=ON")

    # Counts before.
    before_systems_null = conn.execute(
        "SELECT COUNT(*) FROM star_systems WHERE cultural_corridor IS NULL"
    ).fetchone()[0]
    before_bodies_null = conn.execute(
        "SELECT COUNT(*) FROM bodies WHERE cultural_corridor IS NULL"
    ).fetchone()[0]

    print(f"\n  cultural_corridor backfill")
    print(f"  DB: {db_path}")
    if args.dry_run:
        print(f"  Mode: DRY RUN")
    print()
    print(f"  Before:")
    print(f"    star_systems.cultural_corridor NULL: {before_systems_null}")
    print(f"    bodies.cultural_corridor NULL:       {before_bodies_null}")

    conn.execute("BEGIN")
    try:
        # 1. Star systems — copy geographic_sector into cultural_corridor
        #    where the latter is still NULL. If geographic_sector is also
        #    NULL, leave cultural_corridor NULL — there is nothing to
        #    copy and a bogus placeholder is worse than honest NULL.
        sys_rows_updated = conn.execute(
            """
            UPDATE star_systems
               SET cultural_corridor = geographic_sector
             WHERE cultural_corridor IS NULL
               AND geographic_sector IS NOT NULL
            """
        ).rowcount

        # 2. Bodies — inherit from the parent star_systems row.
        body_rows_updated = conn.execute(
            """
            UPDATE bodies
               SET cultural_corridor = (
                   SELECT s.cultural_corridor
                     FROM star_systems s
                    WHERE s.system_id = bodies.system_id
               )
             WHERE cultural_corridor IS NULL
               AND EXISTS (
                   SELECT 1
                     FROM star_systems s
                    WHERE s.system_id = bodies.system_id
                      AND s.cultural_corridor IS NOT NULL
               )
            """
        ).rowcount

        if args.dry_run:
            conn.rollback()
            print()
            print(f"  Would update:")
            print(f"    star_systems: {sys_rows_updated}")
            print(f"    bodies:       {body_rows_updated}")
            print(f"\n  Dry run — no changes written.")
        else:
            conn.commit()
            print()
            print(f"  Updated:")
            print(f"    star_systems: {sys_rows_updated}")
            print(f"    bodies:       {body_rows_updated}")

            # Counts after.
            after_systems_null = conn.execute(
                "SELECT COUNT(*) FROM star_systems WHERE cultural_corridor IS NULL"
            ).fetchone()[0]
            after_bodies_null = conn.execute(
                "SELECT COUNT(*) FROM bodies WHERE cultural_corridor IS NULL"
            ).fetchone()[0]
            print()
            print(f"  After:")
            print(f"    star_systems.cultural_corridor NULL: {after_systems_null}")
            print(f"    bodies.cultural_corridor NULL:       {after_bodies_null}")

            # Show the distribution so the outcome is visible.
            print()
            print(f"  star_systems.cultural_corridor distribution:")
            for corridor, count in conn.execute(
                "SELECT cultural_corridor, COUNT(*) FROM star_systems "
                "GROUP BY cultural_corridor ORDER BY COUNT(*) DESC"
            ).fetchall():
                print(f"    {corridor!r}: {count}")
    except BaseException:
        conn.rollback()
        conn.close()
        raise

    conn.close()
    print()


if __name__ == "__main__":
    main()