feat: complete academic symbol lexicon heal, 2-column Cooper extraction, and updated assets

2026-10-09 15:26:58 +05:00
parent 7f91366201
commit 0b12e4583b
244 changed files with 611461 additions and 1617 deletions
@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+import json
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parent.parent
+ENRICHER = ROOT / 'oracle_enricher'
+KB_FILE = ENRICHER / 'out' / 'oracle_kb.json'
+DOSSIERS_DIR = ENRICHER / 'out' / 'dossiers'
+LEXICON_FILE = ENRICHER / 'data' / 'lexicon.json'
+OUT_FILE = ROOT / 'assets' / 'data' / 'oracle_kb.json'
+
+SEEDS = {'огонь', 'вода', 'волк', 'ключ', 'над', 'я', 'зеркало', 'путь', 'смерть', 'лишь'}
+
+def main():
+    lexicon = json.loads(LEXICON_FILE.read_text(encoding='utf-8'))
+    kb = json.loads(KB_FILE.read_text(encoding='utf-8')) if KB_FILE.exists() else {}
+
+    # Pre-map dossiers by word
+    dossiers = {}
+    for p in DOSSIERS_DIR.glob('*.json'):
+        try:
+            d = json.loads(p.read_text(encoding='utf-8'))
+            w = d.get('word')
+            if w:
+                dossiers[w] = d
+        except Exception:
+            pass
+
+    out_data = {}
+    real_canon_count = 0
+    for row in lexicon:
+        w = row['word']
+        w_id = row['id']
+        w_emoji = row.get('emoji', '')
+        dossier = dossiers.get(w, {})
+        canon = kb.get(w) or dossier.get('canon') or {}
+
+        is_seed = w in SEEDS
+        is_llm_canon = canon.get('via') in ('grok_cli', 'user_edit')
+        is_user_edited = bool(canon.get('user_edited'))
+        has_canon = is_seed or is_llm_canon or is_user_edited or (bool(canon.get('core')) and bool(canon.get('oracle')))
+
+        if has_canon:
+            real_canon_count += 1
+            core = canon.get('core') or ''
+            oracle = canon.get('oracle') or ''
+            layers = canon.get('layers') or []
+            shadow = canon.get('shadow') or ''
+            asks = canon.get('asks') or ''
+            step = canon.get('step') or ''
+            binds = canon.get('binds') or []
+            grammar = canon.get('grammar') or {
+                'operator': dossier.get('operator') or 'substance',
+                'valence': dossier.get('valence') or 'liminal',
+                'modifies': ''
+            }
+        else:
+            core = ''
+            oracle = ''
+            layers = []
+            shadow = (dossier.get('shadow_aspects') and ', '.join(dossier['shadow_aspects'])) or ''
+            asks = ''
+            step = ''
+            binds = []
+            grammar = {
+                'operator': dossier.get('operator') or 'substance',
+                'valence': dossier.get('valence') or 'liminal',
+                'modifies': ''
+            }
+
+        entry = {
+            'id': w_id,
+            'word': w,
+            'emoji': w_emoji,
+            'pos': row.get('pos') or dossier.get('pos') or canon.get('pos') or '',
+            'category': row.get('category') or dossier.get('category') or canon.get('category') or '',
+            'family': dossier.get('family') or canon.get('family') or '',
+            'operator': dossier.get('operator') or (canon.get('grammar') or {}).get('operator') or 'substance',
+            'valence': dossier.get('valence') or (canon.get('grammar') or {}).get('valence') or 'liminal',
+            'jurisdictions': dossier.get('jurisdictions') or canon.get('jurisdictions') or ['I'],
+            'lookup': dossier.get('lookup') or canon.get('lookup') or 'C',
+            'sources': dossier.get('sources') or [],
+            'has_canon': has_canon,
+            'user_edited': is_user_edited,
+            'core': core,
+            'oracle': oracle,
+            'layers': layers,
+            'shadow': shadow,
+            'asks': asks,
+            'step': step,
+            'binds': binds,
+            'grammar': grammar,
+        }
+        # Keyed both by word name AND by string id
+        out_data[w] = entry
+        out_data[str(w_id)] = entry
+
+    OUT_FILE.parent.mkdir(parents=True, exist_ok=True)
+    OUT_FILE.write_text(json.dumps(out_data, ensure_ascii=False, indent=2), encoding='utf-8')
+    print(f'Synchronized {len(lexicon)} words (total keys: {len(out_data)}) into {OUT_FILE} (real canons: {real_canon_count})')
+
+if __name__ == '__main__':
+    main()