app/core/parser.py hinzugefügt

app/core/parser.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+from dataclasses import dataclass
+import re
+import os
+import unicodedata
+import yaml
+from typing import Tuple, Dict
+
+FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n?", re.DOTALL)  # YAML-Frontmatter am Anfang
+
+@dataclass
+class ParsedNote:
+    frontmatter: Dict
+    body: str
+    path: str
+
+def _strip_bom(text: str) -> str:
+    return text.lstrip("\ufeff")
+
+def _normalize_text(t: str) -> str:
+    # Unicode-NFKC + vereinheitlichte Zeilenenden + Trim
+    t = unicodedata.normalize("NFKC", t)
+    t = t.replace("\r\n", "\n").replace("\r", "\n")
+    return t
+
+def read_markdown(path: str) -> ParsedNote:
+    with open(path, "r", encoding="utf-8") as f:
+        raw = _strip_bom(f.read())
+    raw = _normalize_text(raw)
+
+    m = FRONTMATTER_RE.match(raw)
+    front, body = {}, raw
+    if m:
+        yaml_block = m.group(1)
+        body = raw[m.end():]
+        try:
+            front = yaml.safe_load(yaml_block) or {}
+            if not isinstance(front, dict):
+                raise ValueError("Frontmatter must be a mapping")
+        except yaml.YAMLError as e:
+            raise ValueError(f"Invalid YAML frontmatter in {path}: {e}") from e
+
+    return ParsedNote(frontmatter=front, body=body, path=path)
+
+RE_WIKILINK = re.compile(r"\[\[([^\]\|#]+)(?:#[^\]]+)?(?:\|[^\]]+)?\]\]")  # [[id]] | [[id#anchor]] | [[id|label]]
+
+def extract_wikilinks(text: str) -> list[str]:
+    return list({m.group(1).strip() for m in RE_WIKILINK.finditer(text)})
+
+def validate_required_frontmatter(fm: dict, required=("title","id","type","status","created")):
+    missing = [k for k in required if k not in fm or fm[k] in (None, "")]
+    if missing:
+        raise ValueError(f"Missing required frontmatter fields: {', '.join(missing)}")
+
+    # einfache Plausibilitäten
+    if not isinstance(fm.get("tags", []), (list, tuple)):
+        if "tags" in fm and fm["tags"] not in (None, ""):
+            raise ValueError("tags must be a list of strings")
+
+def normalize_frontmatter(fm: dict) -> dict:
+    # kleinere Normalisierungen ohne die Semantik zu verändern
+    out = dict(fm)
+    if "tags" in out and isinstance(out["tags"], list):
+        out["tags"] = [str(t).strip() for t in out["tags"]]
+    if "embedding_exclude" in out:
+        out["embedding_exclude"] = bool(out["embedding_exclude"])
+    return out