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 +1,119 @@
+#!/usr/bin/env python3
+"""Build assets/data/tarot_majors.json from scraped corpus + unified texts."""
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+CORPUS = ROOT / "oracle_enricher" / "data" / "sources" / "tarot_majors_corpus.json"
+UNIFIED = ROOT / "oracle_enricher" / "out" / "tarot_unify" / "unified.json"
+CANON = ROOT / "oracle_enricher" / "data" / "traditions_canon.json"
+ASSET_CANON = ROOT / "assets" / "data" / "traditions_canon.json"
+OUT = ROOT / "assets" / "data" / "tarot_majors.json"
+HTML = ROOT / "lexicon_viewer.html"
+
+ROMAN = ["0", "I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X",
+         "XI", "XII", "XIII", "XIV", "XV", "XVI", "XVII", "XVIII", "XIX", "XX", "XXI"]
+
+
+def main() -> None:
+    if not CORPUS.exists():
+        raise SystemExit("нет tarot_majors_corpus.json — сначала scrape_tarot_majors.py")
+    corpus = json.loads(CORPUS.read_text(encoding="utf-8"))
+    unified = {}
+    if UNIFIED.exists():
+        unified = json.loads(UNIFIED.read_text(encoding="utf-8"))
+    canon = json.loads(CANON.read_text(encoding="utf-8"))
+    ID_MAP = {"wheel": "wheel_of_fortune"}
+    by_id = {s["id"]: s for s in canon["tarot"]["stations"]}
+
+    cards_out = []
+    for n in range(22):
+        cc = corpus["cards"][str(n)]
+        st = by_id.get(ID_MAP.get(cc["id"], cc["id"]), {})
+        uc = (unified.get("cards") or {}).get(str(n)) or {}
+        umeaning = (uc.get("meaning") or "").strip()
+        pairs = []
+        for other in range(22):
+            if other == n:
+                continue
+            key = f"{min(n, other):02d}-{max(n, other):02d}"
+            bucket = (corpus.get("pairs") or {}).get(key) or {}
+            readings = bucket.get("readings") or []
+            up = (unified.get("pairs") or {}).get(key) or {}
+            utext = (up.get("text") or "").strip()
+            preview = utext[:157] + "…" if len(utext) > 160 else utext
+            if not preview and readings:
+                preview = (readings[0].get("text") or "")[:160]
+            ost = by_id.get(corpus["cards"][str(other)]["id"], {})
+            pairs.append(
+                {
+                    "n": other,
+                    "id": corpus["cards"][str(other)]["id"],
+                    "name": corpus["cards"][str(other)]["name"],
+                    "symbol": ost.get("symbol", ""),
+                    "preview": preview,
+                    "text": utext,
+                    "readings": [] if utext else readings,
+                }
+            )
+        cards_out.append(
+            {
+                "n": n,
+                "id": cc["id"],
+                "name": cc["name"],
+                "symbol": st.get("symbol", ""),
+                "lore": (uc.get("core") or st.get("lore") or ""),
+                "group": f"Старшие Арканы · {ROMAN[n]} {cc['name']}",
+                "meaning": umeaning,
+                "shadow": (uc.get("shadow") or "").strip(),
+                "meanings": [] if umeaning else cc.get("meanings") or [],
+                "pairs": pairs,
+            }
+        )
+
+    # fix canon groups
+    for st in canon["tarot"]["stations"]:
+        # id fool → n 0
+        n = next((c["n"] for c in cards_out if c["id"] == st["id"]), None)
+        if n is None:
+            continue
+        st["group"] = f"Старшие Арканы · {ROMAN[n]} {cards_out[n]['name']}"
+        if cards_out[n]["lore"]:
+            st["lore"] = cards_out[n]["lore"]
+    canon["tarot"]["description"] = (
+        "22 Старших Аркана: одно сводное значение и сочетания друг с другом "
+        "(карусель, magya, эзопланета сведены в один текст)."
+    )
+    text_c = json.dumps(canon, ensure_ascii=False, indent=2) + "\n"
+    CANON.write_text(text_c, encoding="utf-8")
+    ASSET_CANON.write_text(text_c, encoding="utf-8")
+
+    blob = {
+        "system": "tarot_majors",
+        "card_count": 22,
+        "pair_count": sum(len(c["pairs"]) for c in cards_out) // 2,
+        "cards": cards_out,
+    }
+    OUT.parent.mkdir(parents=True, exist_ok=True)
+    OUT.write_text(json.dumps(blob, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+
+    if HTML.exists():
+        html = HTML.read_text(encoding="utf-8")
+        start = html.find("    const TRADITIONS_CANON = ")
+        end = html.find("    const WORDS_DATA = ")
+        if start > 0 and end > start:
+            html = (
+                html[:start]
+                + "    const TRADITIONS_CANON = "
+                + json.dumps(canon, ensure_ascii=False, indent=2)
+                + ";\n\n"
+                + html[end:]
+            )
+            HTML.write_text(html, encoding="utf-8")
+    print("wrote", OUT, "pairs", blob["pair_count"])
+
+
+if __name__ == "__main__":
+    main()