Files
settled-reach/tooling/db/wiki_sync.py
T
jpmschweitzerandClaude Opus 4.6 e5911838c0 chore(tooling): update tooling for GJ ID migration and wiki sync
Update wiki_sync.py and process-wiki-system-changes to remove
astronomical_id references. Add migrate-s-to-gj.py migration script.
Update generate-stubs.py and validate-ron for new schema.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 03:55:01 +01:00

719 lines
24 KiB
Python
Executable File

#!/usr/bin/env python3
"""
Settled Reach Wiki Sync — wiki frontmatter ↔ systems.db
Data flow:
- DB owns structured fields (identity, gates, history, economy, factions, culture)
- Wiki owns authored prose (supply_dependency, faction_notes, silence_topic,
narrative_hook, calibration_note)
- Wiki pages are generated from DB (structured infobox) + prose (authored body)
This module provides:
- import_from_wiki(): parse wiki frontmatter into systems.db (migration/bootstrap)
- generate_wiki(): render wiki pages from DB + existing prose
- stats(): show completion stats
Database: server/data/systems.db
Schema: server/data/systems-schema.sql
"""
import json
import re
import sqlite3
import sys
from pathlib import Path
# ---------------------------------------------------------------------------
# Paths
# ---------------------------------------------------------------------------
SCRIPT_DIR = Path(__file__).resolve().parent
WORKTREE_ROOT = (SCRIPT_DIR / ".." / "..").resolve()
SCHEMA_PATH = WORKTREE_ROOT / "server" / "data" / "systems-schema.sql"
WIKI_DIR = WORKTREE_ROOT / "wiki" / "star-systems"
DB_PATH = WORKTREE_ROOT / "server" / "data" / "systems.db"
# ---------------------------------------------------------------------------
# DB helpers
# ---------------------------------------------------------------------------
def get_connection():
conn = sqlite3.connect(str(DB_PATH))
conn.execute("PRAGMA journal_mode=WAL;")
conn.execute("PRAGMA foreign_keys=ON;")
conn.row_factory = sqlite3.Row
return conn
def ensure_schema(conn):
schema_sql = SCHEMA_PATH.read_text()
conn.executescript(schema_sql)
# ---------------------------------------------------------------------------
# Table → column mapping
# ---------------------------------------------------------------------------
# Maps each table to its columns (excluding system_id which is always the key)
TABLE_COLUMNS = {
"star_systems": [
"proper_name", "system_name", "star_type",
"spectral_class", "dist_ly", "geographic_sector", "geographic_band",
"political_zone",
"habitable_planet_count", "inhabited_planet_count", "asteroid_belt",
"gas_giant", "habitability_profile",
"earth_alignment", "earth_proximity", "earth_tension",
"stability_index", "system_volatility", "cultural_corridor",
"generation_priority",
],
"system_gates": [
"horizon_station", "aperture_count", "gate_connections",
"gate_topology", "span_gate_network",
],
"system_history": [
"settlement_wave", "founding_motivation", "founding_culture_primary",
"founding_culture_secondary", "cultural_persistence",
"religious_status", "religious_generation_count",
],
"system_economy": [
"economic_tier", "population", "economic_base_primary",
"economic_base_secondary", "distribution_index", "imprint_access",
],
"system_factions": [
"governance_type", "dominant_faction", "primary_fault_line",
"secondary_fault_line",
"assembly_presence", "commission_presence", "syndic_presence",
"syndic_type", "separatist_presence", "separatist_type",
"institute_presence", "guardians_presence",
],
"system_culture": [
"cultural_register", "cultural_register_secondary", "ambient_anxiety",
"local_pride", "atmospheric_tone", "atmospheric_tone_secondary",
"active_situation", "silence_threshold",
"primary_archetype", "secondary_archetype", "narrative_notable",
],
}
# All structured columns (flat list for frontmatter parsing)
ALL_STRUCTURED_COLUMNS = set()
for cols in TABLE_COLUMNS.values():
ALL_STRUCTURED_COLUMNS.update(cols)
ALL_STRUCTURED_COLUMNS.add("system_id")
INTEGER_COLUMNS = {
"habitable_planet_count", "inhabited_planet_count",
"asteroid_belt", "gas_giant", "horizon_station",
"aperture_count", "gate_connections",
"religious_generation_count", "economic_tier", "population",
"stability_index", "narrative_notable",
}
REAL_COLUMNS = {"dist_ly"}
BOOLEAN_COLUMNS = {"asteroid_belt", "gas_giant", "horizon_station", "narrative_notable"}
PROSE_SECTIONS = {
"supply dependency": "supply_dependency",
"faction notes": "faction_notes",
"silence topic": "silence_topic",
"narrative hook": "narrative_hook",
"calibration note": "calibration_note",
}
# ---------------------------------------------------------------------------
# Frontmatter parsing (for migration/bootstrap from existing wiki)
# ---------------------------------------------------------------------------
def parse_frontmatter(text: str) -> dict:
"""Extract YAML frontmatter between --- delimiters."""
match = re.match(r"^---\n(.*?\n)---", text, re.DOTALL)
if not match:
return {}
result = {}
lines = match.group(1).split("\n")
i = 0
while i < len(lines):
line = lines[i].strip()
i += 1
if not line or line.startswith("#"):
continue
if ":" not in line:
continue
key, _, value = line.partition(":")
key = key.strip()
value = value.strip()
# YAML list (historical_events)
if key == "historical_events":
items = []
if value == "[]":
result[key] = items
continue
while i < len(lines):
next_line = lines[i]
stripped = next_line.strip()
if not stripped or (not next_line.startswith(" ") and not next_line.startswith("\t")):
break
if stripped.startswith("- "):
item = {}
item_content = stripped[2:].strip()
if ":" in item_content:
ik, _, iv = item_content.partition(":")
iv = iv.strip()
if iv == "~" or iv.lower() == "null":
iv = None
else:
try:
iv = int(iv)
except (ValueError, TypeError):
pass
item[ik.strip()] = iv
items.append(item)
i += 1
elif stripped.startswith("#"):
break
elif ":" in stripped:
ik, _, iv = stripped.partition(":")
iv = iv.strip()
if iv == "~" or iv.lower() == "null":
iv = None
else:
try:
iv = int(iv)
except (ValueError, TypeError):
pass
if items:
items[-1][ik.strip()] = iv
i += 1
else:
break
result[key] = items
continue
# Strip quotes
if value.startswith('"') and value.endswith('"'):
value = value[1:-1]
elif value.startswith("'") and value.endswith("'"):
value = value[1:-1]
if value == "~" or value.lower() == "null" or value == "":
value = None
else:
result[key] = value
continue
result[key] = value
return result
def parse_body_sections(text: str) -> dict[str, str]:
"""Extract authored prose from ## sections in the markdown body."""
match = re.match(r"^---\n.*?\n---\n", text, re.DOTALL)
body = text[match.end():] if match else text
sections: dict[str, str] = {}
current_key: str | None = None
current_lines: list[str] = []
for line in body.split("\n"):
if line.startswith("## "):
if current_key is not None:
sections[current_key] = "\n".join(current_lines).strip()
header = line[3:].strip().lower()
current_key = PROSE_SECTIONS.get(header)
current_lines = []
elif current_key is not None:
if line.strip().startswith("<!--") and line.strip().endswith("-->"):
continue
current_lines.append(line)
if current_key is not None:
sections[current_key] = "\n".join(current_lines).strip()
return sections
def coerce_value(col, val):
"""Coerce a value for SQLite insertion."""
if val is None:
return None
val_str = str(val).strip()
if val_str == "" or val_str == "~" or val_str.lower() == "null":
return None
if col in BOOLEAN_COLUMNS:
lower = val_str.lower()
if lower in ("true", "yes", "1"):
return 1
if lower in ("false", "no", "0"):
return 0
return None
if col in INTEGER_COLUMNS:
try:
return int(val_str)
except (ValueError, TypeError):
return None
if col in REAL_COLUMNS:
try:
return float(val_str)
except (ValueError, TypeError):
return None
return val_str
# ---------------------------------------------------------------------------
# Import from wiki (migration/bootstrap)
# ---------------------------------------------------------------------------
def import_from_wiki():
"""Parse all wiki frontmatter and populate systems.db."""
if not WIKI_DIR.is_dir():
return {"ok": False, "error": f"Wiki directory not found: {WIKI_DIR}"}
conn = get_connection()
ensure_schema(conn)
warnings = []
imported = 0
for d in sorted(WIKI_DIR.iterdir()):
if not d.is_dir():
continue
index_file = d / "index.md"
if not index_file.exists():
warnings.append(f"Missing index.md in {d.name}")
continue
text = index_file.read_text(encoding="utf-8")
fm = parse_frontmatter(text)
sid = fm.get("system_id")
if not sid:
warnings.append(f"No system_id in {d.name}/index.md")
continue
try:
# Upsert into each table
for table, columns in TABLE_COLUMNS.items():
all_cols = ["system_id"] + columns
if table == "star_systems":
all_cols.append("updated_at")
values = [sid]
for col in columns:
values.append(coerce_value(col, fm.get(col)))
if table == "star_systems":
values.append(None) # updated_at = DEFAULT
placeholders = ", ".join(["?"] * len(all_cols))
col_list = ", ".join(all_cols)
if table == "star_systems":
update_set = ", ".join(
f"{c} = excluded.{c}" for c in columns
) + ", updated_at = datetime('now')"
else:
update_set = ", ".join(
f"{c} = excluded.{c}" for c in columns
)
sql = (
f"INSERT INTO {table} ({col_list}) "
f"VALUES ({placeholders}) "
f"ON CONFLICT(system_id) DO UPDATE SET {update_set}"
)
conn.execute(sql, values)
# Historical events
events = fm.get("historical_events", [])
if isinstance(events, list):
conn.execute(
"DELETE FROM historical_events WHERE system_id = ?", (sid,)
)
for idx, event in enumerate(events):
if isinstance(event, dict):
conn.execute(
"INSERT INTO historical_events "
"(system_id, event_type, age_years, sort_order) "
"VALUES (?, ?, ?, ?)",
(sid, event.get("type", ""), event.get("age_years"), idx),
)
imported += 1
except sqlite3.Error as exc:
warnings.append(f"Error on {sid}: {exc}")
conn.commit()
conn.close()
return {
"ok": True,
"systems_imported": imported,
"warnings": warnings,
"summary": f"Imported {imported} systems into {DB_PATH}",
}
# ---------------------------------------------------------------------------
# Wiki page generation (DB → wiki infobox)
# ---------------------------------------------------------------------------
def _format_population(pop):
"""Format population with commas."""
if pop is None:
return "~"
try:
return f"{int(pop):,}"
except (ValueError, TypeError):
return str(pop)
def generate_infobox(conn, sid: str) -> str:
"""Generate the READ-ONLY infobox markdown for a system."""
s = conn.execute("SELECT * FROM star_systems WHERE system_id = ?", (sid,)).fetchone()
if not s:
return ""
g = conn.execute("SELECT * FROM system_gates WHERE system_id = ?", (sid,)).fetchone()
h = conn.execute("SELECT * FROM system_history WHERE system_id = ?", (sid,)).fetchone()
e = conn.execute("SELECT * FROM system_economy WHERE system_id = ?", (sid,)).fetchone()
f = conn.execute("SELECT * FROM system_factions WHERE system_id = ?", (sid,)).fetchone()
c = conn.execute("SELECT * FROM system_culture WHERE system_id = ?", (sid,)).fetchone()
events = conn.execute(
"SELECT event_type, age_years FROM historical_events "
"WHERE system_id = ? ORDER BY sort_order", (sid,)
).fetchall()
lines = [
"## System Profile",
"<!-- READ-ONLY — generated from systems.db -->",
"",
"| | |",
"|---|---|",
]
# Star
spectral = s["spectral_class"] or s["star_type"] or "~"
dist = f"{s['dist_ly']:.1f} ly" if s["dist_ly"] is not None else "~"
lines.append(f"| **Star** | {spectral} · {dist} |")
# Bodies
hab = s["habitable_planet_count"]
inh = s["inhabited_planet_count"]
if hab is not None or inh is not None:
hab_s = f"{hab} habitable" if hab is not None else "~"
inh_s = f"{inh} inhabited" if inh is not None else "~"
lines.append(f"| **Bodies** | {hab_s} · {inh_s} |")
# Gates
if g:
ap = g["aperture_count"] if g["aperture_count"] is not None else "~"
topo = g["gate_topology"] or "~"
lines.append(f"| **Gates** | {ap} aperture · {topo} |")
# Settlement
if h:
wave = h["settlement_wave"] or "~"
lines.append(f"| **Settlement** | {wave} |")
# Historical events
if events:
ev_parts = []
for ev in events:
age = f"{ev['age_years']}y" if ev["age_years"] is not None else "~"
ev_parts.append(f"{ev['event_type']} ({age})")
lines.append(f"| **History** | {', '.join(ev_parts)} |")
# Economy
if e and (e["population"] is not None or e["economic_tier"] is not None):
pop = _format_population(e["population"])
tier = f"Tier {e['economic_tier']}" if e["economic_tier"] is not None else "~"
base_parts = []
if e["economic_base_primary"]:
base_parts.append(e["economic_base_primary"])
if e["economic_base_secondary"]:
base_parts.append(e["economic_base_secondary"])
base = " / ".join(base_parts) if base_parts else "~"
if e["population"] is not None:
lines.append(f"| **Population** | {pop} |")
lines.append(f"| **Economy** | {tier} · {base} |")
# Governance
if f and (f["governance_type"] or f["dominant_faction"]):
gov = f["governance_type"] or "~"
dom = f["dominant_faction"] or "~"
lines.append(f"| **Governance** | {gov} · {dom} |")
# Culture
if c and c["atmospheric_tone"]:
tone = c["atmospheric_tone"]
if c["atmospheric_tone_secondary"]:
tone += f" / {c['atmospheric_tone_secondary']}"
lines.append(f"| **Atmosphere** | {tone} |")
# Stability
stab = s["stability_index"]
if stab is not None:
vol = s["system_volatility"] or "~"
lines.append(f"| **Stability** | {stab} · {vol} |")
# Political
if s["earth_alignment"]:
lines.append(f"| **Earth Alignment** | {s['earth_alignment']} |")
lines.append("")
return "\n".join(lines)
def generate_topology(conn, sid: str, star_map_path: Path) -> str:
"""Generate the READ-ONLY topology section from star-map.json."""
try:
with open(star_map_path) as f:
data = json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
return "## Topology\n<!-- READ-ONLY — regenerated from star-map.json edges -->\n"
# Find hop distance
hop = "~"
for node in data["nodes"]:
if node["system_id"] == sid:
hop = node.get("hop_distance_from_gateway", "~")
break
# Find adjacent systems
adjacent = set()
for a, b in data["edges"]:
if a == sid:
adjacent.add(b)
elif b == sid:
adjacent.add(a)
adj_str = ", ".join(sorted(adjacent)) if adjacent else "none"
return (
"## Topology\n"
"<!-- READ-ONLY — regenerated from star-map.json edges -->\n"
f"- **Hop Distance from Gateway:** {hop}\n"
f"- **Adjacent Systems:** {adj_str}\n"
)
def generate_wiki_page(conn, sid: str, star_map_path: Path) -> str:
"""Generate a complete wiki page from DB + existing prose."""
s = conn.execute("SELECT * FROM star_systems WHERE system_id = ?", (sid,)).fetchone()
if not s:
return ""
system_name = s["proper_name"] or s["system_name"] or f"System {sid}"
star_type = s["star_type"] or "~"
sector = s["geographic_sector"] or "~"
# Title block
title = f"# {system_name}\n**{sid}** | {star_type}-type | {sector}\n\n---\n\n"
# Infobox
infobox = generate_infobox(conn, sid)
# Topology
topology = generate_topology(conn, sid, star_map_path)
return title + infobox + "\n---\n\n" + topology
def generate_wiki(prose_only_update=False):
"""Generate/update wiki pages from DB.
For each system:
- Generates the title + infobox + topology (from DB/star-map)
- Preserves existing authored prose sections from the wiki file
- Writes the combined result back
"""
conn = get_connection()
star_map_path = WORKTREE_ROOT / "docs" / "design" / "star-map.json"
systems = conn.execute("SELECT system_id FROM star_systems ORDER BY system_id").fetchall()
updated = 0
created = 0
for row in systems:
sid = row["system_id"]
dirname = sid.replace(" ", "-")
outdir = WIKI_DIR / dirname
outfile = outdir / "index.md"
# Read existing prose if file exists
existing_prose = {}
if outfile.exists():
text = outfile.read_text(encoding="utf-8")
existing_prose = parse_body_sections(text)
# Generate structured parts
s = conn.execute("SELECT * FROM star_systems WHERE system_id = ?", (sid,)).fetchone()
system_name = s["proper_name"] or s["system_name"] or f"System {sid}"
star_type = s["star_type"] or "~"
sector = s["geographic_sector"] or "~"
infobox = generate_infobox(conn, sid)
topology = generate_topology(conn, sid, star_map_path)
# Build page
page_lines = [
f"# {system_name}",
f"**{sid}** | {star_type}-type | {sector}",
"",
"---",
"",
infobox,
"---",
"",
]
# Prose sections — preserve existing content or leave placeholder
for header, key in PROSE_SECTIONS.items():
section_title = header.title()
content = existing_prose.get(key, "")
page_lines.append(f"## {section_title}")
if content:
page_lines.append("")
page_lines.append(content)
else:
comment_map = {
"supply_dependency": "<!-- Required for manufacturing/transit_logistics base and narrative_notable systems -->",
"faction_notes": "<!-- Significant local factions not covered by standard columns -->",
"silence_topic": "<!-- Required for narrative_notable and Institutional Core / Diplomatic Periphery zones -->",
"narrative_hook": "<!-- Required if narrative_notable = true. One sentence. -->",
"calibration_note": "<!-- Unusual column combinations requiring justification -->",
}
page_lines.append(comment_map.get(key, ""))
page_lines.append("")
# Topology (always last)
page_lines.append(topology)
outdir.mkdir(parents=True, exist_ok=True)
outfile.write_text("\n".join(page_lines), encoding="utf-8")
if outfile.exists():
updated += 1
else:
created += 1
conn.close()
return {
"ok": True,
"updated": updated,
"created": created,
"summary": f"Generated {updated + created} wiki pages",
}
# ---------------------------------------------------------------------------
# Stats
# ---------------------------------------------------------------------------
def stats():
"""Show per-table fill rates."""
conn = get_connection()
try:
row = conn.execute("SELECT COUNT(*) as cnt FROM star_systems").fetchone()
total = row["cnt"]
if total == 0:
print("No systems in database. Run import first.")
return {"ok": True, "total": 0}
print(f"Star systems: {total}")
print(f"Database: {DB_PATH}")
print()
total_cells = 0
filled_cells = 0
for table, columns in TABLE_COLUMNS.items():
table_filled = 0
table_total = total * len(columns)
for col in columns:
r = conn.execute(
f"SELECT COUNT(*) as cnt FROM {table} WHERE {col} IS NOT NULL"
).fetchone()
table_filled += r["cnt"]
total_cells += table_total
filled_cells += table_filled
pct = table_filled / table_total * 100 if table_total > 0 else 0
bar = "#" * int(pct / 5) + "." * (20 - int(pct / 5))
print(f" {table:20s} {table_filled:4d}/{table_total:4d} {bar} {pct:.0f}%")
# Historical events
ev_count = conn.execute("SELECT COUNT(*) as cnt FROM historical_events").fetchone()["cnt"]
ev_systems = conn.execute(
"SELECT COUNT(DISTINCT system_id) as cnt FROM historical_events"
).fetchone()["cnt"]
print(f" {'historical_events':20s} {ev_count} events across {ev_systems} systems")
overall = filled_cells / total_cells * 100 if total_cells > 0 else 0
print(f"\nOverall: {filled_cells}/{total_cells} ({overall:.1f}%)")
return {"ok": True, "total": total, "filled": filled_cells, "pct": round(overall, 1)}
except sqlite3.OperationalError as exc:
print(f"Table not found — run import first: {exc}")
return {"ok": False, "error": str(exc)}
finally:
conn.close()
# ---------------------------------------------------------------------------
# CLI
# ---------------------------------------------------------------------------
def main():
help_text = f"""\
Wiki Sync — systems.db ↔ wiki pages
Usage:
wiki_sync.py import Parse wiki frontmatter into systems.db (bootstrap)
wiki_sync.py generate Generate wiki pages from systems.db
wiki_sync.py stats Show completion stats
wiki_sync.py --help Show this help
Database: {DB_PATH}
Schema: {SCHEMA_PATH}
Wiki: {WIKI_DIR}
"""
if len(sys.argv) < 2 or sys.argv[1] in ("--help", "-h", "help"):
print(help_text)
sys.exit(0)
cmd = sys.argv[1]
if cmd == "import":
result = import_from_wiki()
print(json.dumps(result, indent=2))
elif cmd == "generate":
result = generate_wiki()
print(json.dumps(result, indent=2))
elif cmd == "stats":
stats()
else:
print(json.dumps({"ok": False, "error": f"Unknown: {cmd}"}, indent=2))
sys.exit(1)
if __name__ == "__main__":
main()