feat: add init_landing_seeds.py for empty-landing bootstrap

Creates minimal .jsonl.gz and .json.gz seed files so all SQLMesh staging
models can compile and run before real extraction data arrives.

Each seed has a single null record filtered by the staging model's WHERE
clause (tenant_id IS NOT NULL, geoname_id IS NOT NULL, type IS NOT NULL, etc).

Covers both formats (JSONL + blob) for the UNION ALL transition CTEs:
  playtomic/1970/01/: tenants.{jsonl,json}.gz, availability seeds (morning + recheck)
  geonames/1970/01/: cities_global.{jsonl,json}.gz
  overpass_tennis/1970/01/: courts.{jsonl,json}.gz
  overpass/1970/01/: courts.json.gz (padel, unchanged format)
  eurostat/1970/01/: urb_cpop1.json.gz, ilc_di03.json.gz
  eurostat_city_labels/1970/01/: cities_codelist.json.gz
  ons_uk/1970/01/: lad_population.json.gz
  census_usa/1970/01/: acs5_places.json.gz

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/init_landing_seeds.py

@@ -0,0 +1,101 @@
+"""Create minimal landing zone seed files so SQLMesh models can run before real data arrives.
+
+Each seed contains one null/empty record that is filtered out by the staging model's
+WHERE clause. Seeds live in the 1970/01 epoch so they're never confused with real data.
+
+Usage:
+    uv run python scripts/init_landing_seeds.py [--landing-dir data/landing]
+
+Idempotent: skips existing files.
+"""
+
+import argparse
+import gzip
+import json
+from pathlib import Path
+
+
+def create_seed(dest: Path, content: bytes) -> None:
+    """Write content to a gzip file atomically. Skips if the file already exists."""
+    if dest.exists():
+        return
+    dest.parent.mkdir(parents=True, exist_ok=True)
+    tmp = dest.with_suffix(dest.suffix + ".tmp")
+    with gzip.open(tmp, "wb") as f:
+        f.write(content)
+    tmp.rename(dest)
+    print(f"  created: {dest}")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--landing-dir", default="data/landing", type=Path)
+    args = parser.parse_args()
+    base: Path = args.landing_dir
+
+    seeds = {
+        # --- Playtomic tenants ---
+        # JSONL: one null tenant (filtered by WHERE tenant_id IS NOT NULL)
+        "playtomic/1970/01/tenants.jsonl.gz":
+            b'{"tenant_id":null}\n',
+        # Blob: empty tenants array
+        "playtomic/1970/01/tenants.json.gz":
+            json.dumps({"tenants": [], "count": 0}).encode(),
+
+        # --- Playtomic availability (morning) ---
+        # JSONL: one null venue (filtered by WHERE tenant_id IS NOT NULL)
+        "playtomic/1970/01/availability_1970-01-01.jsonl.gz":
+            b'{"tenant_id":null,"date":"1970-01-01","captured_at_utc":"1970-01-01T00:00:00Z","slots":null}\n',
+        # Blob: empty venues array
+        "playtomic/1970/01/availability_1970-01-01.json.gz":
+            json.dumps({"date": "1970-01-01", "captured_at_utc": "1970-01-01T00:00:00Z",
+                        "venue_count": 0, "venues": []}).encode(),
+
+        # --- Playtomic recheck (blob only, small format) ---
+        "playtomic/1970/01/availability_1970-01-01_recheck_00.json.gz":
+            json.dumps({"date": "1970-01-01", "captured_at_utc": "1970-01-01T00:00:00Z",
+                        "recheck_hour": 0, "venues": []}).encode(),
+
+        # --- GeoNames ---
+        # JSONL: one null city (filtered by WHERE geoname_id IS NOT NULL)
+        "geonames/1970/01/cities_global.jsonl.gz":
+            b'{"geoname_id":null}\n',
+        # Blob: empty rows array
+        "geonames/1970/01/cities_global.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+
+        # --- Overpass tennis ---
+        # JSONL: one null element (filtered by WHERE type IS NOT NULL)
+        "overpass_tennis/1970/01/courts.jsonl.gz":
+            b'{"type":null,"id":null}\n',
+        # Blob: empty elements array
+        "overpass_tennis/1970/01/courts.json.gz":
+            json.dumps({"version": 0.6, "elements": []}).encode(),
+
+        # --- Overpass padel (unchanged format) ---
+        "overpass/1970/01/courts.json.gz":
+            json.dumps({"version": 0.6, "elements": []}).encode(),
+
+        # --- Eurostat ---
+        "eurostat/1970/01/urb_cpop1.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+        "eurostat/1970/01/ilc_di03.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+        "eurostat_city_labels/1970/01/cities_codelist.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+
+        # --- National statistics ---
+        "ons_uk/1970/01/lad_population.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+        "census_usa/1970/01/acs5_places.json.gz":
+            json.dumps({"rows": [], "count": 0}).encode(),
+    }
+
+    print(f"Initialising landing seeds in: {base}")
+    for rel_path, content in seeds.items():
+        create_seed(base / rel_path, content)
+    print("Done.")
+
+
+if __name__ == "__main__":
+    main()