294 lines
10 KiB
Python
294 lines
10 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
Modul: app/core/note_payload.py
|
||
Version: 1.5.1
|
||
Datum: 2025-09-09
|
||
|
||
Kurzbeschreibung
|
||
----------------
|
||
Erzeugt den Qdrant-Payload für **Notes**. Neben stabiler Hash-Bildung zur
|
||
Idempotenz wird der vollständige Body unter ``fulltext`` persistiert und
|
||
der Dateipfad relativ zum Vault gespeichert. Das erlaubt eine verlustfreie
|
||
Rekonstruktion im Export (erst ``fulltext``, sonst Chunks).
|
||
|
||
Wichtig
|
||
-------
|
||
- **Nur Inhalte** gehen in den Hash: Weder Dateisystem-Zeitstempel (mtime/ctime)
|
||
noch sonstige FS-Metadaten werden berücksichtigt.
|
||
- Hash-Quelle: Parser-Body (Default) oder Rohdatei-Body (Frontmatter via Regex entfernt).
|
||
|
||
Änderungen in v1.5.1
|
||
--------------------
|
||
- Neue Env-Var **MINDNET_HASH_COMPARE** als Synonym zu MINDNET_HASH_MODE.
|
||
- Akzeptiert komfortable Werte (case-insensitive): **Body**, **Frontmatter**, **Full**.
|
||
*Full* wird intern zu ``body+frontmatter`` normalisiert.
|
||
- CLI akzeptiert weiterhin ``--hash-mode``; Importer reicht diese Einstellung durch.
|
||
|
||
Hash-Steuerung
|
||
--------------
|
||
- Modus (welche Teile in den Hash einfließen):
|
||
* ``body`` (Default)
|
||
* ``frontmatter``
|
||
* ``body+frontmatter`` (Synonym CLI/ENV: ``full``)
|
||
Quelle:
|
||
* Funktionsparameter ``hash_mode`` (höchste Priorität)
|
||
* Env ``MINDNET_HASH_MODE`` oder **``MINDNET_HASH_COMPARE``** (Fallback)
|
||
Normalisierung:
|
||
* ``canonical`` (Default) | ``none`` — via Param ``hash_normalize`` oder Env ``MINDNET_HASH_NORMALIZE``
|
||
Quelle des Body-Textes:
|
||
* ``parsed`` (Default) | ``raw`` — via Param ``hash_source`` oder Env ``MINDNET_HASH_SOURCE``
|
||
|
||
CLI (Sichtprüfung)
|
||
------------------
|
||
python3 -m app.core.note_payload --from-file ./vault/demo.md --vault-root ./vault --print --hash-source raw
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
import argparse
|
||
import hashlib
|
||
import json
|
||
import os
|
||
from typing import Any, Dict, Optional, Tuple
|
||
|
||
try:
|
||
from app.core.parser import read_markdown, extract_wikilinks, FRONTMATTER_RE
|
||
except Exception: # pragma: no cover
|
||
from .parser import read_markdown, extract_wikilinks, FRONTMATTER_RE # type: ignore
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Helpers
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def _canon_frontmatter(fm: Dict[str, Any]) -> str:
|
||
"""Kanonische, stabile JSON-Serialisierung der Frontmatter für Hashbildung."""
|
||
return json.dumps(fm or {}, ensure_ascii=False, separators=(",", ":"), sort_keys=True)
|
||
|
||
def _normalize_body(body: str, mode: str) -> str:
|
||
"""Normalisiert den Body für reproduzierbare Hashes (oder nicht)."""
|
||
if mode == "none":
|
||
return body if body is not None else ""
|
||
# canonical: \r\n→\n, trailing spaces entfernen
|
||
text = (body or "").replace("\r\n", "\n").replace("\r", "\n")
|
||
text = "\n".join(line.rstrip() for line in text.split("\n"))
|
||
return text
|
||
|
||
def _resolve_hash_mode(explicit: Optional[str]) -> str:
|
||
"""
|
||
Normalisiert den Hash-Modus auf einen der Werte:
|
||
'body' | 'frontmatter' | 'body+frontmatter'
|
||
Akzeptiert auch 'full' als Alias für 'body+frontmatter'.
|
||
Beachtet zusätzlich die Env-Variablen MINDNET_HASH_MODE und MINDNET_HASH_COMPARE.
|
||
"""
|
||
if explicit:
|
||
val = explicit.strip().lower()
|
||
else:
|
||
val = (os.environ.get("MINDNET_HASH_MODE") or os.environ.get("MINDNET_HASH_COMPARE") or "body").strip().lower()
|
||
if val in ("full", "fulltext", "body+frontmatter", "bodyplusfrontmatter"):
|
||
return "body+frontmatter"
|
||
if val in ("frontmatter", "fm"):
|
||
return "frontmatter"
|
||
# default & fallbacks
|
||
return "body"
|
||
|
||
def _read_raw_body_from_file(file_path: Optional[str]) -> Tuple[str, Dict[str, Any]]:
|
||
"""Liest die Rohdatei und extrahiert Body & Frontmatter ohne Parser-Logik.
|
||
|
||
Rückgabe:
|
||
(body_text, frontmatter_dict)
|
||
"""
|
||
if not file_path or not os.path.exists(file_path):
|
||
return "", {}
|
||
try:
|
||
with open(file_path, "r", encoding="utf-8") as f:
|
||
raw = f.read()
|
||
except Exception:
|
||
return "", {}
|
||
# Frontmatter per Regex entfernen
|
||
m = FRONTMATTER_RE.match(raw)
|
||
fm = {}
|
||
if m:
|
||
fm_txt = m.group(1)
|
||
try:
|
||
import yaml # lazy
|
||
fm = yaml.safe_load(fm_txt) or {}
|
||
except Exception:
|
||
fm = {}
|
||
body = raw[m.end():]
|
||
else:
|
||
body = raw
|
||
return body, fm
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Hashing
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def compute_hash(
|
||
*,
|
||
body: Optional[str],
|
||
frontmatter: Optional[Dict[str, Any]],
|
||
mode: Optional[str] = None,
|
||
normalize: Optional[str] = None,
|
||
) -> str:
|
||
"""
|
||
Berechnet einen Hex-Hash gemäß ``mode`` und ``normalize``.
|
||
|
||
mode:
|
||
- "body" (Default)
|
||
- "frontmatter"
|
||
- "body+frontmatter"
|
||
normalize:
|
||
- "canonical" (Default)
|
||
- "none"
|
||
"""
|
||
mode = _resolve_hash_mode(mode)
|
||
normalize = (normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical")).strip().lower()
|
||
|
||
body = _normalize_body(body or "", normalize)
|
||
fm_s = _canon_frontmatter(frontmatter or {})
|
||
|
||
h = hashlib.sha256()
|
||
if mode == "frontmatter":
|
||
h.update(fm_s.encode("utf-8"))
|
||
elif mode == "body+frontmatter":
|
||
h.update(body.encode("utf-8"))
|
||
h.update(b"\n--FM--\n")
|
||
h.update(fm_s.encode("utf-8"))
|
||
else: # body
|
||
h.update(body.encode("utf-8"))
|
||
return h.hexdigest()
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Kernfunktion
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def make_note_payload(
|
||
parsed: Any,
|
||
vault_root: Optional[str] = None,
|
||
*,
|
||
hash_mode: Optional[str] = None,
|
||
hash_normalize: Optional[str] = None,
|
||
hash_source: Optional[str] = None,
|
||
file_path: Optional[str] = None,
|
||
) -> Dict[str, Any]:
|
||
"""
|
||
Erzeugt den Payload für eine geparste Note.
|
||
|
||
Parameters
|
||
----------
|
||
parsed : Any
|
||
Objekt mit Attributen/Keys ``frontmatter``, ``body``, ``path``.
|
||
vault_root : Optional[str]
|
||
Vault-Wurzel (für Pfad-Relativierung). Wenn ``None``, wird ``path`` unverändert übernommen.
|
||
hash_mode : Optional[str]
|
||
"body" | "frontmatter" | "body+frontmatter" | "full" (Alias; überschreibt ENV).
|
||
hash_normalize : Optional[str]
|
||
"canonical" | "none" (überschreibt ENV).
|
||
hash_source : Optional[str]
|
||
"parsed" (Default) oder "raw". Wenn "raw", wird der Body aus der Rohdatei gelesen.
|
||
file_path : Optional[str]
|
||
Pfad zur Markdown-Datei, erforderlich für ``hash_source=raw``.
|
||
|
||
Returns
|
||
-------
|
||
Dict[str, Any]
|
||
Qdrant-Payload für die Notes-Collection.
|
||
"""
|
||
# "Duck typing": dict oder Objekt akzeptieren
|
||
if isinstance(parsed, dict):
|
||
fm = parsed.get("frontmatter") or {}
|
||
body = parsed.get("body") or ""
|
||
path = parsed.get("path") or ""
|
||
else:
|
||
fm = getattr(parsed, "frontmatter", {}) or {}
|
||
body = getattr(parsed, "body", "") or ""
|
||
path = getattr(parsed, "path", "") or ""
|
||
|
||
# Hash-Quelle bestimmen
|
||
src = (hash_source or os.environ.get("MINDNET_HASH_SOURCE", "parsed")).strip().lower()
|
||
raw_body, raw_fm = ("", {})
|
||
if src == "raw":
|
||
raw_body, raw_fm = _read_raw_body_from_file(file_path or path)
|
||
# Roh-FM ergänzen (nicht überschreiben)
|
||
if isinstance(raw_fm, dict) and raw_fm:
|
||
merged_fm = dict(fm)
|
||
for k, v in raw_fm.items():
|
||
merged_fm.setdefault(k, v)
|
||
fm = merged_fm
|
||
|
||
# Hash gemäß Modus/Quelle bilden
|
||
body_for_hash = raw_body if src == "raw" else body
|
||
hash_fulltext = compute_hash(body=body_for_hash, frontmatter=fm, mode=hash_mode, normalize=hash_normalize)
|
||
|
||
# Pfad relativieren
|
||
rel_path = path
|
||
try:
|
||
if vault_root:
|
||
rel = os.path.relpath(path, vault_root)
|
||
rel = rel.replace("\\", "/").lstrip("/") # normalisieren
|
||
rel_path = rel
|
||
except Exception:
|
||
pass # Pfad ist nicht kritisch für Hash/ID
|
||
|
||
# Note-Level-Wikilinks (Fallback, wenn Chunks nicht geliefert werden)
|
||
note_level_refs = list(dict.fromkeys(extract_wikilinks(body))) if body else []
|
||
|
||
payload: Dict[str, Any] = {
|
||
"note_id": fm.get("id") or fm.get("note_id"),
|
||
"title": fm.get("title"),
|
||
"type": fm.get("type"),
|
||
"status": fm.get("status"),
|
||
"created": fm.get("created"),
|
||
"updated": fm.get("updated"),
|
||
"path": rel_path or fm.get("path"),
|
||
"tags": fm.get("tags"),
|
||
"hash_fulltext": hash_fulltext,
|
||
# Volltext persistieren (verlustfreie Rekonstruktion) – aus PARSED-Body
|
||
"fulltext": body,
|
||
# Fallback-Refs auf Note-Ebene
|
||
"references": note_level_refs,
|
||
}
|
||
|
||
for k in ("area", "project", "source", "lang", "slug", "aliases"):
|
||
if k in fm:
|
||
payload[k] = fm[k]
|
||
|
||
# Optional: Roh-Body-Hash zusätzlich persistieren
|
||
if os.environ.get("MINDNET_HASH_STORE_RAW", "false").strip().lower() == "true" and src == "raw":
|
||
try:
|
||
payload["hash_raw_body"] = compute_hash(body=raw_body, frontmatter=fm, mode="body", normalize="none")
|
||
except Exception:
|
||
pass
|
||
|
||
return payload
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# CLI – Sichtprüfung
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def _cli() -> None:
|
||
ap = argparse.ArgumentParser(description="Note-Payload aus Markdown erzeugen und anzeigen")
|
||
ap.add_argument("--from-file", dest="src", required=True, help="Pfad zur Markdown-Datei")
|
||
ap.add_argument("--vault-root", dest="vault_root", default=None, help="Vault-Wurzel zur Pfad-Relativierung")
|
||
ap.add_argument("--print", dest="do_print", action="store_true", help="Payload auf stdout ausgeben")
|
||
ap.add_argument("--hash-mode", choices=["body", "frontmatter", "body+frontmatter", "full"], default=None)
|
||
ap.add_argument("--hash-normalize", choices=["canonical", "none"], default=None)
|
||
ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None)
|
||
args = ap.parse_args()
|
||
|
||
parsed = read_markdown(args.src)
|
||
payload = make_note_payload(parsed, vault_root=args.vault_root,
|
||
hash_mode=args.hash_mode, hash_normalize=args.hash_normalize,
|
||
hash_source=args.hash_source, file_path=args.src)
|
||
|
||
if args.do_print:
|
||
print(json.dumps(payload, ensure_ascii=False, indent=2))
|
||
|
||
|
||
if __name__ == "__main__": # pragma: no cover
|
||
_cli()
|