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 +1,134 @@
+#!/usr/bin/env python3
+"""Ogham lexicon intersections + stamp [Огам: …] on the 1000-word catalog."""
+from __future__ import annotations
+
+import json
+import re
+from collections import defaultdict
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+CANON = ROOT / "oracle_enricher" / "data" / "traditions_canon.json"
+ASSET = ROOT / "assets" / "data" / "traditions_canon.json"
+LEX = ROOT / "oracle_enricher" / "data" / "lexicon.json"
+DART = ROOT / "lib" / "data" / "words_data.dart"
+HTML = ROOT / "lexicon_viewer.html"
+
+OGHAM_TAG_RE = re.compile(r"\[Огам:[^\]]*\]\s*")
+
+CLUSTERS = {
+    "beith": ["начало", "рост", "лес"],
+    "luis": ["защита", "взгляд", "огонь"],
+    "fern": ["щит", "воин", "вода"],
+    "sail": ["луна", "вода", "сон"],
+    "nion": ["древо", "ось", "небо", "земля"],
+    "uath": ["порог", "тайна", "защита"],
+    "duir": ["сила", "дверь", "корона"],
+    "tinne": ["огонь", "воин", "щит"],
+    "coll": ["мудрость", "книга", "плод"],
+    "ceirt": ["плод", "сад", "выбор"] if False else ["плод", "сад"],
+    "muin": ["путь", "связь", "тайна"],
+    "gort": ["связь", "путь", "рост"],
+    "ngetal": ["удар", "путь"],
+    "straif": ["тьма", "судьба", "тёрн"],
+    "ruis": ["смерть", "цикл"],
+    "ailm": ["свет", "взгляд", "небо"],
+    "onn": ["огонь", "рост"],
+    "ur": ["земля", "судьба"],
+    "eadha": ["страх", "воздух"],
+    "idho": ["смерть", "вечность", "цикл", "корень"],
+}
+
+
+def payload(e: dict) -> dict:
+    return {
+        "id": e["id"],
+        "word": e["word"],
+        "emoji": e.get("emoji", ""),
+        "pos": e.get("pos", ""),
+        "category": e.get("category", ""),
+        "desc": "",
+    }
+
+
+def main() -> None:
+    canon = json.loads(CANON.read_text(encoding="utf-8"))
+    lex = {e["word"]: e for e in json.loads(LEX.read_text(encoding="utf-8"))}
+    og = canon["ogham"]
+    word_to_tags: dict[str, list[str]] = defaultdict(list)
+
+    for st in og["stations"]:
+        sid = st["id"]
+        prim = (st.get("primary") or {}).get("word")
+        extra = []
+        for w in CLUSTERS.get(sid, []):
+            if w == prim or w not in lex or w in extra:
+                continue
+            extra.append(w)
+        st["cluster"] = [payload(lex[w]) for w in extra[:6]]
+        tag = f"[Огам: {st['name']}]"
+        if prim:
+            word_to_tags[prim].append(tag)
+        for w in extra:
+            word_to_tags[w].append(tag)
+
+    og["description"] = (
+        "20 священных fews (деревьев) в 4 аикмах. Значения с oghamlore, Druid Ogham "
+        "и пересечения со словарём 999. Сочетания в раскладе — соседство fews."
+    )
+
+    text = json.dumps(canon, ensure_ascii=False, indent=2) + "\n"
+    CANON.write_text(text, encoding="utf-8")
+    ASSET.write_text(text, encoding="utf-8")
+
+    dart_lines = DART.read_text(encoding="utf-8").splitlines(keepends=True)
+    i = 0
+    while i < len(dart_lines):
+        wm = re.match(r'(\s*word: ")([^"]+)(",\s*)$', dart_lines[i])
+        if wm:
+            word = wm.group(2)
+            for j in range(i + 1, min(i + 12, len(dart_lines))):
+                raw = dart_lines[j].rstrip("\n")
+                dm = re.match(r'^(\s*description: ")(.*)(",)\s*$', raw)
+                if dm:
+                    body = OGHAM_TAG_RE.sub("", dm.group(2)).strip()
+                    tags = word_to_tags.get(word)
+                    if tags:
+                        dart_lines[j] = f"{dm.group(1)}{' '.join(tags)} {body}{dm.group(3)}\n"
+                    else:
+                        dart_lines[j] = f"{dm.group(1)}{body}{dm.group(3)}\n"
+                    break
+                if dart_lines[j].strip().startswith("WordItem("):
+                    break
+        i += 1
+    dart2 = "".join(dart_lines)
+    DART.write_text(dart2, encoding="utf-8")
+
+    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:]
+        )
+    m = re.search(r"const WORDS_DATA = (\[.*?\]);", html, flags=re.DOTALL)
+    if m:
+        words = json.loads(m.group(1))
+        dart_descs = dict(re.findall(r'word: "([^"]+)"[\s\S]*?description: "([^"]*)"', dart2))
+        for w in words:
+            if w.get("word") in dart_descs:
+                w["description"] = dart_descs[w["word"]]
+        html = html[: m.start(1)] + json.dumps(words, ensure_ascii=False) + html[m.end(1) :]
+    HTML.write_text(html, encoding="utf-8")
+
+    print("ogham stations", len(og["stations"]), "words tagged", len(word_to_tags))
+    for st in og["stations"]:
+        print(f"  {st['id']:10} prim={(st.get('primary') or {}).get('word')} cl={[x['word'] for x in st['cluster']]}")
+
+
+if __name__ == "__main__":
+    main()