feat: wiki 讀取與對白抽取腳本 (#4)

fetch_wiki.py 用 tea 讀取 wiki；extract_dialogues.py 抽出「」對白與前後文，
並用規則判定明確的說話者。原文與輸出放在 repo 之外。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

tools/corpus/fetch_wiki.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+"""用 tea 的驗證讀取 Gitea wiki 全部頁面，存成 markdown。
+
+用法：fetch_wiki.py <owner/repo> <輸出目錄>
+輸出目錄放在 repo 之外；原文不入版本控制。
+"""
+import base64
+import json
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+
+def tea_api(endpoint):
+    out = subprocess.run(["tea", "api", endpoint], capture_output=True, text=True, check=True).stdout
+    return json.loads(out)
+
+
+def list_pages(repo):
+    pages, page = [], 1
+    while True:
+        batch = tea_api(f"repos/{repo}/wiki/pages?page={page}&limit=50")
+        if not batch:
+            return pages
+        pages.extend(batch)
+        page += 1
+
+
+def safe_name(title):
+    return re.sub(r"[\\/:*?\"<>|]", "_", title).strip()
+
+
+def main():
+    repo, outdir = sys.argv[1], Path(sys.argv[2])
+    outdir.mkdir(parents=True, exist_ok=True)
+    pages = list_pages(repo)
+    seen = set()
+    for p in pages:
+        if p["title"] in seen:
+            continue
+        seen.add(p["title"])
+        page = tea_api(f"repos/{repo}/wiki/page/{p['sub_url']}")
+        text = base64.b64decode(page["content_base64"]).decode("utf-8")
+        (outdir / f"{safe_name(p['title'])}.md").write_text(text, encoding="utf-8")
+    print(f"{len(seen)} pages -> {outdir}")
+
+
+if __name__ == "__main__":
+    main()