scripts/dump_note_chunks.py hinzugefügt

scripts/dump_note_chunks.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+import argparse, os, glob
+from app.core.parser import read_markdown, normalize_frontmatter, validate_required_frontmatter
+from app.core.chunker import assemble_chunks
+
+def iter_md(root: str):
+    return [p for p in glob.glob(os.path.join(root, "**", "*.md"), recursive=True)]
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--vault", required=True)
+    ap.add_argument("--note-id", required=True)
+    args = ap.parse_args()
+
+    root = os.path.abspath(args.vault)
+    for path in iter_md(root):
+        parsed = read_markdown(path)
+        fm = normalize_frontmatter(parsed.frontmatter)
+        try:
+            validate_required_frontmatter(fm)
+        except Exception:
+            continue
+        if fm.get("id") != args.note_id:
+            continue
+
+        chunks = assemble_chunks(fm["id"], parsed.body, fm.get("type","concept"))
+        print(f"# {fm['title']} ({fm['id']}) — {len(chunks)} chunks\n")
+        for ch in chunks:
+            print(f"--- {ch.id} | {ch.token_count} tok | {ch.section_path} ---")
+            print(ch.text.strip())
+            print()
+        break
+    else:
+        print("Note nicht gefunden oder Frontmatter unvollständig.")
+
+if __name__ == "__main__":
+    main()