286 lines
9.3 KiB
Python
286 lines
9.3 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
export_markdown.py — Export aus Qdrant → Markdown (Vault-Struktur)
|
|
|
|
Version: 1.3 (2025-09-09)
|
|
|
|
Kurzbeschreibung
|
|
- Exportiert Notes (+ rekonstruierten Body aus Chunks) aus Qdrant in Dateien mit YAML-Frontmatter.
|
|
- Nutzt ENV-Variablen aus .env (QDRANT_URL, QDRANT_API_KEY, COLLECTION_PREFIX, VECTOR_DIM).
|
|
- Optionales CLI-Argument --prefix überschreibt COLLECTION_PREFIX, damit alle Tools konsistent sind.
|
|
- Unterstützung von Mehrfachauswahl per --note-id (mehrfach angeben).
|
|
|
|
Anwendungsfälle
|
|
- Kompletter Vault-Neuaufbau aus Qdrant
|
|
- Teil-Export einzelner Notizen
|
|
- Sicherung / Migration
|
|
|
|
Voraussetzungen
|
|
- Aktiviertes venv (empfohlen): `source .venv/bin/activate`
|
|
- Laufender Qdrant (URL/API-Key passend zu deiner Umgebung)
|
|
- Sammlungen: <prefix>_notes, <prefix>_chunks
|
|
- Chunk-Payload enthält Text in `text` (Fallback: `raw`), Reihenfolge über `seq` oder Nummer in `chunk_id`.
|
|
|
|
Aufrufe (Beispiele)
|
|
- Prefix über ENV (empfohlen):
|
|
export COLLECTION_PREFIX="mindnet"
|
|
python3 -m scripts.export_markdown --out ./_exportVault
|
|
|
|
- Prefix über CLI (überschreibt ENV):
|
|
python3 -m scripts.export_markdown --out ./_exportVault --prefix mindnet
|
|
|
|
- Nur bestimmte Notizen exportieren:
|
|
python3 -m scripts.export_markdown --out ./_exportVault \
|
|
--prefix mindnet \
|
|
--note-id 20250821-architektur-ki-trainerassistent-761cfe \
|
|
--note-id 20250821-personal-mind-ki-projekt-7b0d79
|
|
|
|
- Existierende Dateien überschreiben:
|
|
python3 -m scripts.export_markdown --out ./_exportVault --prefix mindnet --overwrite
|
|
|
|
Parameter
|
|
- --out PATH (Pflicht) Ziel-Verzeichnis des Export-Vaults (wird angelegt).
|
|
- --prefix TEXT (Optional) Collection-Prefix; überschreibt ENV COLLECTION_PREFIX.
|
|
- --note-id ID (Optional, mehrfach) Export auf bestimmte Note-IDs begrenzen.
|
|
- --overwrite (Optional) Bereits existierende Dateien überschreiben (default: skip).
|
|
- --dry-run (Optional) Nur anzeigen, was geschrieben würde; keine Dateien anlegen.
|
|
|
|
Änderungen ggü. v1.2
|
|
- Neues optionales CLI-Argument --prefix (ENV-Fallback bleibt).
|
|
- Robustere Qdrant-Scroll-Logik (neue Client-Signatur: (points, next_offset)).
|
|
- Verbesserte Sortierung der Chunks (seq > Nummer aus chunk_id > Fallback).
|
|
- Defensiver Umgang mit Frontmatter (nur sinnvolle Felder; Datumswerte als Strings).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
import os
|
|
import sys
|
|
import argparse
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Dict, List, Optional, Tuple
|
|
|
|
from dotenv import load_dotenv
|
|
from qdrant_client.http import models as rest
|
|
|
|
from app.core.qdrant import QdrantConfig, get_client
|
|
# ensure_collections ist für Export nicht nötig
|
|
|
|
# -------------------------
|
|
# Hilfsfunktionen
|
|
# -------------------------
|
|
|
|
def collections(prefix: str) -> Tuple[str, str, str]:
|
|
return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"
|
|
|
|
|
|
def scroll_all(client, collection: str, flt: Optional[rest.Filter] = None, with_payload=True, with_vectors=False):
|
|
"""Iterator über alle Punkte einer Collection (neue Qdrant-Client-Signatur)."""
|
|
next_offset = None
|
|
while True:
|
|
points, next_offset = client.scroll(
|
|
collection_name=collection,
|
|
scroll_filter=flt,
|
|
with_payload=with_payload,
|
|
with_vectors=with_vectors,
|
|
limit=256,
|
|
offset=next_offset,
|
|
)
|
|
for p in points:
|
|
yield p
|
|
if next_offset is None:
|
|
break
|
|
|
|
|
|
def ensure_dir(path: Path):
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
def select_frontmatter(note_pl: Dict) -> Dict:
|
|
"""
|
|
Reduziert Payload auf für den Vault sinnvolle Frontmatter-Felder.
|
|
Pflichtfelder laut Schema: note_id (id), title, type, status, created, path
|
|
Optional: updated, tags
|
|
"""
|
|
# Backward-compat: manche Payloads nutzen 'id' statt 'note_id'
|
|
note_id = note_pl.get("note_id") or note_pl.get("id")
|
|
fm = {
|
|
"id": note_id,
|
|
"title": note_pl.get("title"),
|
|
"type": note_pl.get("type"),
|
|
"status": note_pl.get("status"),
|
|
"created": note_pl.get("created"),
|
|
"path": note_pl.get("path"),
|
|
}
|
|
# optional
|
|
if note_pl.get("updated") is not None:
|
|
fm["updated"] = note_pl.get("updated")
|
|
if note_pl.get("tags"):
|
|
fm["tags"] = note_pl.get("tags")
|
|
return fm
|
|
|
|
|
|
def yaml_block(frontmatter: Dict) -> str:
|
|
"""
|
|
Sehr einfache YAML-Serialisierung (ohne zusätzliche Abhängigkeiten).
|
|
Annahme: Werte sind Strings/Listen; Datumsangaben bereits als Strings.
|
|
"""
|
|
lines = ["---"]
|
|
for k, v in frontmatter.items():
|
|
if v is None:
|
|
continue
|
|
if isinstance(v, list):
|
|
# einfache Listen-Notation
|
|
lines.append(f"{k}:")
|
|
for item in v:
|
|
lines.append(f" - {item}")
|
|
else:
|
|
# Strings ggf. doppelt quoten, wenn Sonderzeichen enthalten
|
|
s = str(v)
|
|
if any(ch in s for ch in [":", "-", "#", "{", "}", "[", "]", ","]):
|
|
lines.append(f'{k}: "{s}"')
|
|
else:
|
|
lines.append(f"{k}: {s}")
|
|
lines.append("---")
|
|
return "\n".join(lines)
|
|
|
|
|
|
def chunk_sort_key(pl: Dict) -> Tuple[int, int]:
|
|
"""
|
|
Bestimme eine stabile Sortierreihenfolge:
|
|
1) seq (falls vorhanden)
|
|
2) Nummer aus chunk_id (…#<n>)
|
|
3) Fallback: 0
|
|
"""
|
|
seq = pl.get("seq")
|
|
if isinstance(seq, int):
|
|
return (0, seq)
|
|
cid = pl.get("chunk_id") or pl.get("id") or ""
|
|
n = 0
|
|
if "#" in cid:
|
|
try:
|
|
n = int(cid.split("#", 1)[1])
|
|
except ValueError:
|
|
n = 0
|
|
return (1, n)
|
|
|
|
|
|
def reconstruct_body(chunk_payloads: List[Dict]) -> str:
|
|
parts: List[str] = []
|
|
chunk_payloads_sorted = sorted(chunk_payloads, key=chunk_sort_key)
|
|
for pl in chunk_payloads_sorted:
|
|
txt = pl.get("text") or pl.get("raw") or ""
|
|
parts.append(txt.rstrip("\n"))
|
|
return "\n\n".join(parts).rstrip() + "\n"
|
|
|
|
|
|
def safe_write(out_path: Path, content: str, overwrite: bool) -> str:
|
|
if out_path.exists() and not overwrite:
|
|
return "skip"
|
|
ensure_dir(out_path)
|
|
out_path.write_text(content, encoding="utf-8")
|
|
return "write"
|
|
|
|
|
|
def fetch_note_chunks(client, chunks_col: str, note_id: str) -> List[Dict]:
|
|
flt = rest.Filter(
|
|
must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]
|
|
)
|
|
out: List[Dict] = []
|
|
for p in scroll_all(client, chunks_col, flt, with_payload=True, with_vectors=False):
|
|
if p.payload:
|
|
out.append(p.payload)
|
|
return out
|
|
|
|
|
|
def make_export_path(export_root: Path, note_pl: Dict) -> Path:
|
|
# prefer payload 'path', sonst Titel-basierte Fallback-Datei
|
|
rel = (note_pl.get("path") or f"{note_pl.get('title') or 'Note'}.md").strip("/")
|
|
# Normalisierung Windows-Backslashes etc.
|
|
rel = rel.replace("\\", "/")
|
|
return export_root.joinpath(rel)
|
|
|
|
|
|
# -------------------------
|
|
# Main
|
|
# -------------------------
|
|
|
|
def main():
|
|
load_dotenv()
|
|
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--out", required=True, help="Ziel-Verzeichnis für den Export-Vault")
|
|
ap.add_argument("--prefix", help="Collection-Prefix (überschreibt ENV COLLECTION_PREFIX)")
|
|
ap.add_argument("--note-id", action="append", help="Nur bestimmte Note-ID exportieren (mehrfach möglich)")
|
|
ap.add_argument("--overwrite", action="store_true", help="Existierende Dateien überschreiben")
|
|
ap.add_argument("--dry-run", action="store_true", help="Nur anzeigen, keine Dateien schreiben")
|
|
args = ap.parse_args()
|
|
|
|
# Qdrant-Konfiguration
|
|
cfg = QdrantConfig.from_env()
|
|
if args.prefix:
|
|
# CLI-Präfix hat Vorrang
|
|
cfg.prefix = args.prefix
|
|
|
|
client = get_client(cfg)
|
|
notes_col, chunks_col, _ = collections(cfg.prefix)
|
|
|
|
# Filter für Noten-Auswahl
|
|
note_filter: Optional[rest.Filter] = None
|
|
if args.note_id:
|
|
should = [rest.FieldCondition(key="note_id", match=rest.MatchValue(value=nid)) for nid in args.note_id]
|
|
note_filter = rest.Filter(should=should)
|
|
|
|
export_root = Path(args.out).resolve()
|
|
export_root.mkdir(parents=True, exist_ok=True)
|
|
|
|
total = 0
|
|
written = 0
|
|
skipped = 0
|
|
|
|
# Notes aus Qdrant holen
|
|
for p in scroll_all(client, notes_col, note_filter, with_payload=True, with_vectors=False):
|
|
pl = p.payload or {}
|
|
note_id = pl.get("note_id") or pl.get("id")
|
|
title = pl.get("title")
|
|
|
|
# Frontmatter & Body
|
|
fm = select_frontmatter(pl)
|
|
yaml = yaml_block(fm)
|
|
chunks = fetch_note_chunks(client, chunks_col, note_id)
|
|
body = reconstruct_body(chunks)
|
|
|
|
content = f"{yaml}\n{body}"
|
|
out_path = make_export_path(export_root, pl)
|
|
|
|
decision = "dry-run"
|
|
if not args.dry_run:
|
|
decision = safe_write(out_path, content, args.overwrite)
|
|
if decision == "write":
|
|
written += 1
|
|
elif decision == "skip":
|
|
skipped += 1
|
|
|
|
total += 1
|
|
print(json.dumps({
|
|
"note_id": note_id,
|
|
"title": title,
|
|
"file": str(out_path),
|
|
"chunks": len(chunks),
|
|
"decision": decision
|
|
}, ensure_ascii=False))
|
|
|
|
print(json.dumps({
|
|
"summary": {
|
|
"notes_total": total,
|
|
"written": written,
|
|
"skipped": skipped,
|
|
"out_dir": str(export_root)
|
|
}
|
|
}, ensure_ascii=False))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|