scripts/parse_validate_notes.py hinzugefügt

scripts/parse_validate_notes.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+import argparse
+import os
+import sys
+import glob
+from jsonschema import ValidationError
+from app.core.parser import read_markdown, validate_required_frontmatter, normalize_frontmatter
+from app.core.note_payload import make_note_payload
+from app.core.validate_note import validate_note_payload
+
+def iter_md_files(root: str, include: str, exclude: list[str]) -> list[str]:
+    # include z.B. "**/*.md"
+    all_files = glob.glob(os.path.join(root, include), recursive=True)
+    def is_excluded(p: str) -> bool:
+        p_norm = p.replace("\\", "/")
+        return any(x in p_norm for x in exclude)
+    return [p for p in all_files if p.lower().endswith(".md") and not is_excluded(p)]
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--vault", required=True, help="Pfad zum Obsidian Vault")
+    ap.add_argument("--include", default="**/*.md")
+    ap.add_argument("--exclude", nargs="*", default=["/.obsidian/", "/_imported/"])
+    args = ap.parse_args()
+
+    root = os.path.abspath(args.vault)
+    files = iter_md_files(root, args.include, args.exclude)
+
+    if not files:
+        print("Keine Markdown-Dateien gefunden.", file=sys.stderr)
+        sys.exit(2)
+
+    ok, failed = 0, 0
+    for path in files:
+        try:
+            parsed = read_markdown(path)
+            fm = normalize_frontmatter(parsed.frontmatter)
+            validate_required_frontmatter(fm)
+            # Note-Payload gemäß note.schema.json validieren
+            payload = make_note_payload(parsed, vault_root=root)
+            validate_note_payload(payload)
+            ok += 1
+        except (ValidationError, ValueError) as e:
+            failed += 1
+            print(f"❌ {os.path.relpath(path, root)} :: {e}", file=sys.stderr)
+
+    print(f"✅ Valid: {ok} | ❌ Invalid: {failed}")
+    if failed:
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()