settled-reach/tooling/planet-gen/atlas_common.py

#!/usr/bin/env python3
"""
atlas_common.py — shared atlas-DB utilities for the planet-gen importers.

Extracted from the retired generate_atlas.py (D-223, #951). The atlas city/road/
river geometry *generator* was retired when authored geometry was dropped in
favour of the deterministic server-side cascade (Phase 4); markers.json is now a
flavoured name pool only. What remained were the schema/DB helpers shared by the
surviving build-time importers (heightmaps, province boundaries, city names) and
the naming pipeline. Those live here so there is a single home for them with no
dependency on the deleted geometry-production code.

This is a library module — it does NOT re-exec the venv. The importing scripts
(import_heightmaps.py, import_province_boundaries.py, import_city_names.py,
gemma_naming.py) own the venv bootstrap before importing this module.

Decisions: D-223 (authored content as flavoured name pool), D-191 (atlas index).
"""

import sqlite3
from pathlib import Path

import yaml

# ---------------------------------------------------------------------------
# Paths and grid constants
# ---------------------------------------------------------------------------
TOOLING_DIR = Path(__file__).resolve().parent
REPO_ROOT = (TOOLING_DIR / ".." / "..").resolve()

DB_PATH = REPO_ROOT / "server" / "data" / "systems.db"
WIKI_SYSTEMS = REPO_ROOT / "wiki" / "star-systems"
SYSTEMS_SCHEMA_PATH = REPO_ROOT / "server" / "data" / "systems-schema.sql"

# Heightmap pixel-space grid (D-202). Geometry derives from this resolution.
GRID_W = 512
GRID_H = 256

# Delimiters for the single canonical atlas_* DDL block in
# server/data/systems-schema.sql. `_load_atlas_schema()` extracts everything
# between these markers at runtime so this file does not duplicate the schema
# (and drift from it).
_ATLAS_SCHEMA_BEGIN_MARKER = "-- BEGIN ATLAS INDEX"
_ATLAS_SCHEMA_END_MARKER = "-- END ATLAS INDEX"


# ---------------------------------------------------------------------------
# Schema
# ---------------------------------------------------------------------------

def _load_atlas_schema() -> str:
    """Return the atlas_* DDL block from systems-schema.sql.

    systems-schema.sql is the single source of truth for the atlas index
    tables (see the BEGIN ATLAS INDEX / END ATLAS INDEX markers). We extract
    just that block and run it through `executescript` so callers work against
    any DB state (fresh or partially-migrated) without maintaining a second
    copy of the DDL here.
    """
    if not SYSTEMS_SCHEMA_PATH.exists():
        raise RuntimeError(
            f"systems-schema.sql not found at {SYSTEMS_SCHEMA_PATH} — "
            "atlas importers cannot proceed without the canonical schema."
        )
    text = SYSTEMS_SCHEMA_PATH.read_text()
    try:
        start = text.index(_ATLAS_SCHEMA_BEGIN_MARKER)
        end = text.index(_ATLAS_SCHEMA_END_MARKER, start)
    except ValueError as e:
        raise RuntimeError(
            f"systems-schema.sql is missing the {_ATLAS_SCHEMA_BEGIN_MARKER}/"
            f"{_ATLAS_SCHEMA_END_MARKER} block — has the schema been "
            "restructured?"
        ) from e
    return text[start:end]


def ensure_atlas_schema(conn: sqlite3.Connection) -> None:
    """Apply the canonical atlas_* DDL from systems-schema.sql.

    Idempotent: all statements inside the block use CREATE TABLE / INDEX
    IF NOT EXISTS, so running this on an already-migrated DB is a no-op.

    Also ensures the meta stamp table exists (#855, #856).
    """
    conn.executescript(_load_atlas_schema())
    conn.executescript(
        """
        CREATE TABLE IF NOT EXISTS meta (
            generator_name TEXT PRIMARY KEY,
            schema_version TEXT NOT NULL,
            schema_sha TEXT,
            generator_sha TEXT NOT NULL,
            generated_at TEXT NOT NULL DEFAULT (datetime('now'))
        );
        """
    )
    # Add schema_sha column to existing DBs that pre-date #888 (#888 migration).
    try:
        conn.execute("ALTER TABLE meta ADD COLUMN schema_sha TEXT")
    except sqlite3.OperationalError as e:
        if "duplicate column" not in str(e).lower():
            raise


# ---------------------------------------------------------------------------
# Body definition loading
# ---------------------------------------------------------------------------

def load_body_def(body_dir: Path) -> dict | None:
    """Load body definition from body index.md frontmatter."""
    index_md = body_dir / "index.md"
    if not index_md.exists():
        return None
    content = index_md.read_text()
    if not content.startswith("---"):
        return None
    try:
        end = content.index("---", 3)
        bd = yaml.safe_load(content[3:end])
    except (ValueError, yaml.YAMLError):
        return None
    if not bd or "id" not in bd or "planet_class" not in bd:
        return None
    return bd


# ---------------------------------------------------------------------------
# DB queries
# ---------------------------------------------------------------------------

def query_inhabited_bodies(conn: sqlite3.Connection) -> list[dict]:
    """Query systems.db for all inhabited bodies with terrain_reference set."""
    rows = conn.execute("""
        SELECT
            b.body_id,
            b.system_id,
            b.terrain_reference,
            b.population,
            b.settlement_pattern,
            b.planet_class,
            b.economic_role,
            COALESCE(b.cultural_corridor, s.cultural_corridor) AS cultural_corridor
        FROM bodies b
        JOIN star_systems s ON b.system_id = s.system_id
        WHERE b.inhabited = 1
          AND b.terrain_reference IS NOT NULL
          AND b.population > 0
        ORDER BY b.system_id, b.body_id
    """).fetchall()

    return [
        {
            "body_id": row[0],
            "system_id": row[1],
            "terrain_reference": row[2],
            "population": row[3] or 0,
            "settlement_pattern": row[4],
            "planet_class": row[5],
            "economic_role": row[6],
            "cultural_corridor": row[7],
        }
        for row in rows
    ]