mindnet/scripts/import_markdown.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Script: scripts/import_markdown.py — Markdown → Qdrant (Notes, Chunks, Edges)
Version: 3.6.2
Datum: 2025-09-09

Kurzbeschreibung
----------------
- Liest Markdown-Dateien ein und erzeugt Notes/Chunks/Edges **idempotent**.
- Robuste Änderungserkennung: Mehrfach-Hashes werden parallel in der Note gespeichert
  (Option C). Vergleich erfolgt **modusgenau** anhand von `hashes[<mode>:<source>:<normalize>]`.
  Ein Wechsel des Vergleichsmodus führt so **nicht** zu Massenänderungen.
- **Fix (v3.6.2):** Bei **erstem Import** (kein Alt-Payload) wird die Note als **geändert**
  behandelt → Create (Notes/Chunks/Edges) findet zuverlässig statt.
- Baseline-Modus: Mit `--baseline-modes` werden **fehlende** Hash-Varianten
  im Feld `hashes` „still“ nachgetragen (Upsert NUR Notes; Legacy-Hashfelder bleiben unangetastet).

Konfiguration Hash/Compare
--------------------------
- Vergleichsmodus: `--hash-mode body|frontmatter|full`
  - oder ENV: `MINDNET_HASH_MODE` / `MINDNET_HASH_COMPARE` (Body|Frontmatter|Full)
- Quelle: `--hash-source parsed|raw` (ENV: `MINDNET_HASH_SOURCE`, Default parsed)
- Normalisierung: `--hash-normalize canonical|none` (ENV: `MINDNET_HASH_NORMALIZE`, Default canonical)
- Optional: `--compare-text` (oder `MINDNET_COMPARE_TEXT=true`) vergleicht zusätzlich den parsed Body-Text direkt.

Weitere ENV / Qdrant
--------------------
- QDRANT_URL | QDRANT_HOST/QDRANT_PORT | QDRANT_API_KEY
- COLLECTION_PREFIX (Default: mindnet)
- VECTOR_DIM (Default: 384)
- MINDNET_NOTE_SCOPE_REFS: true|false (Default: false)

Aufruf-Beispiele
----------------
    # Standard (Body, parsed, canonical)
    python3 -m scripts.import_markdown --vault ./vault

    # Baseline (füllt hashes für parsed:canonical Tripel „still“ auf)
    MINDNET_HASH_SOURCE=parsed MINDNET_HASH_NORMALIZE=canonical \
    python3 -m scripts.import_markdown --vault ./vault --apply --baseline-modes

    # Frontmatter-Vergleich ohne Massenänderungen (nach Baseline)
    MINDNET_HASH_COMPARE=Frontmatter \
    python3 -m scripts.import_markdown --vault ./vault

    # Sehr sensibel (raw + none) und direkten Textvergleich
    python3 -m scripts.import_markdown --vault ./vault --apply --hash-source raw --hash-normalize none --compare-text
"""
from __future__ import annotations

import argparse
import difflib
import json
import os
import sys
from typing import Dict, List, Optional, Tuple, Any
from collections.abc import Mapping

from dotenv import load_dotenv
from qdrant_client.http import models as rest

from app.core.parser import (
    read_markdown,
    normalize_frontmatter,
    validate_required_frontmatter,
)
from app.core.note_payload import make_note_payload
from app.core.chunker import assemble_chunks
from app.core.chunk_payload import make_chunk_payloads
from app.core.edges import build_edges_for_note
from app.core.qdrant import (
    QdrantConfig,
    get_client,
    ensure_collections,
    ensure_payload_indexes,
)
from app.core.qdrant_points import (
    points_for_chunks,
    points_for_note,
    points_for_edges,
    upsert_batch,
)

try:
    from app.core.embed import embed_texts  # optional
except Exception:
    embed_texts = None


# ---------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------

def iter_md(root: str) -> List[str]:
    out: List[str] = []
    for dirpath, _, filenames in os.walk(root):
        for fn in filenames:
            if not fn.lower().endswith(".md"):
                continue
            p = os.path.join(dirpath, fn)
            pn = p.replace("\\", "/")
            if any(ex in pn for ex in ["/.obsidian/", "/_backup_frontmatter/", "/_imported/"]):
                continue
            out.append(p)
    return sorted(out)

def collections(prefix: str) -> Tuple[str, str, str]:
    return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"

def fetch_existing_note_payload(client, prefix: str, note_id: str) -> Optional[Dict]:
    notes_col, _, _ = collections(prefix)
    f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
    points, _ = client.scroll(
        collection_name=notes_col,
        scroll_filter=f,
        with_payload=True,
        with_vectors=False,
        limit=1,
    )
    if not points:
        return None
    return points[0].payload or {}

def purge_note_artifacts(client, prefix: str, note_id: str) -> None:
    """
    Löscht alle Chunks & Edges zu einer Note mittels Filter-Selector (kompatibel mit aktuellen Qdrant-Clients).
    """
    _, chunks_col, edges_col = collections(prefix)
    filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])

    try:
        client.delete(
            collection_name=chunks_col,
            points_selector=rest.FilterSelector(filter=filt),
            wait=True
        )
    except Exception as e:
        print(json.dumps({"note_id": note_id, "warn": f"delete chunks via filter failed: {e}"}))

    try:
        client.delete(
            collection_name=edges_col,
            points_selector=rest.FilterSelector(filter=filt),
            wait=True
        )
    except Exception as e:
        print(json.dumps({"note_id": note_id, "warn": f"delete edges via filter failed: {e}"}))

def _normalize_rel_path(abs_path: str, vault_root: str) -> str:
    try:
        rel = os.path.relpath(abs_path, vault_root)
    except Exception:
        rel = abs_path
    return rel.replace("\\", "/").lstrip("/")

def _resolve_mode(val: Optional[str]) -> str:
    v = (val or os.environ.get("MINDNET_HASH_MODE") or os.environ.get("MINDNET_HASH_COMPARE") or "body").strip().lower()
    if v in ("full", "fulltext", "body+frontmatter", "bodyplusfrontmatter"):
        return "full"
    if v in ("frontmatter", "fm"):
        return "frontmatter"
    return "body"

def _env(key: str, default: str) -> str:
    return (os.environ.get(key) or default).strip().lower()


# ---------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------

def main() -> None:
    load_dotenv()
    ap = argparse.ArgumentParser()
    ap.add_argument("--vault", required=True, help="Pfad zum Obsidian-Vault (Root-Ordner)")
    ap.add_argument("--apply", action="store_true", help="Schreibt in Qdrant; ohne Flag nur Dry-Run")
    ap.add_argument("--purge-before-upsert", action="store_true",
                    help="Vor Upsert Chunks & Edges der GEÄNDERTEN Note löschen")
    ap.add_argument("--note-id", help="Nur eine bestimmte Note-ID verarbeiten")
    ap.add_argument("--embed-note", action="store_true", help="Optional: Note-Volltext einbetten")
    ap.add_argument("--force-replace", action="store_true",
                    help="Änderungserkennung ignorieren und immer upserten (+ optional Purge)")
    ap.add_argument("--hash-mode", choices=["body", "frontmatter", "full"], default=None,
                    help="Vergleichsmodus (Body | Frontmatter | Full)")
    ap.add_argument("--hash-normalize", choices=["canonical", "none"], default=None)
    ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None,
                    help="Quelle für die Hash-Berechnung (Default: parsed)")
    ap.add_argument("--note-scope-refs", action="store_true",
                    help="(Optional) erzeugt zusätzlich references:note (Default: aus)")
    ap.add_argument("--debug-hash-diff", action="store_true",
                    help="Zeigt einen kurzen Diff zwischen altem und neuem Body")
    ap.add_argument("--compare-text", action="store_true",
                    help="Parsed fulltext zusätzlich direkt vergleichen (über Hash hinaus)")
    ap.add_argument("--baseline-modes", action="store_true",
                    help="Fehlende Hash-Varianten im Feld 'hashes' still nachtragen (Upsert NUR Notes)")
    args = ap.parse_args()

    mode = _resolve_mode(args.hash_mode)  # body|frontmatter|full
    src = _env("MINDNET_HASH_SOURCE", args.hash_source or "parsed")  # parsed|raw
    norm = _env("MINDNET_HASH_NORMALIZE", args.hash_normalize or "canonical")  # canonical|none
    note_scope_refs_env = (_env("MINDNET_NOTE_SCOPE_REFS", "false") == "true")
    note_scope_refs = args.note_scope_refs or note_scope_refs_env
    compare_text = args.compare_text or (_env("MINDNET_COMPARE_TEXT", "false") == "true")

    cfg = QdrantConfig.from_env()
    client = get_client(cfg)
    ensure_collections(client, cfg.prefix, cfg.dim)
    ensure_payload_indexes(client, cfg.prefix)

    root = os.path.abspath(args.vault)
    files = iter_md(root)
    if not files:
        print("Keine Markdown-Dateien gefunden.", file=sys.stderr)
        sys.exit(2)

    key_current = f"{mode}:{src}:{norm}"

    processed = 0
    for path in files:
        # -------- Parse & Validate --------
        try:
            parsed = read_markdown(path)
        except Exception as e:
            print(json.dumps({"path": path, "error": f"read_markdown failed: {e}"}))
            continue
        if parsed is None:
            print(json.dumps({"path": path, "error": "read_markdown returned None"}))
            continue

        try:
            fm = normalize_frontmatter(parsed.frontmatter)
            validate_required_frontmatter(fm)
        except Exception as e:
            print(json.dumps({"path": path, "error": f"Frontmatter invalid: {e}"}))
            continue

        if args.note_id and fm.get("id") != args.note_id:
            continue

        processed += 1

        # -------- Build new payload (includes 'hashes') --------
        note_pl = make_note_payload(
            parsed,
            vault_root=root,
            hash_mode=mode,
            hash_normalize=norm,
            hash_source=src,
            file_path=path,
        )
        if not note_pl.get("fulltext"):
            note_pl["fulltext"] = getattr(parsed, "body", "") or ""

        note_id = note_pl.get("note_id") or fm.get("id")
        if not note_id:
            print(json.dumps({"path": path, "error": "Missing note_id after payload build"}))
            continue

        # -------- Fetch old payload --------
        old_payload = None if args.force_replace else fetch_existing_note_payload(client, cfg.prefix, note_id)
        has_old = old_payload is not None

        old_hashes = (old_payload or {}).get("hashes") or {}
        old_hash_exact = old_hashes.get(key_current)

        # Neu-Hash (aktueller Modus) aus neuem Payload
        new_hash_exact = (note_pl.get("hashes") or {}).get(key_current)

        needs_baseline = (old_hash_exact is None)

        # Change-Detection:
        # - CREATE: wenn es KEIN Alt-Payload gibt -> changed=True
        # - UPDATE: baseline existiert UND Hash differiert
        # - force/text_changed wie gehabt
        hash_changed = (old_hash_exact is not None and new_hash_exact is not None and old_hash_exact != new_hash_exact)

        text_changed = False
        if compare_text:
            old_text = (old_payload or {}).get("fulltext") or ""
            new_text = note_pl.get("fulltext") or ""
            text_changed = (old_text != new_text)

        changed = args.force_replace or (not has_old) or hash_changed or text_changed

        # Baseline-only nur, wenn Alt-Payload existiert UND Key fehlt UND keine sonstige Änderung
        do_baseline_only = (args.baseline_modes and has_old and needs_baseline and not changed)

        # -------- Optional: Chunks / Embeddings / Edges vorbereiten --------
        # CREATE/UPDATE: wir brauchen Chunks/Edges; Baseline-only: nein
        chunks = []
        chunk_pls = []
        edges = []
        vecs = []
        if (args.apply and (changed and (not do_baseline_only))):
            try:
                chunks = assemble_chunks(fm["id"], getattr(parsed, "body", "") or "", fm.get("type", "concept"))
                chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks)
            except Exception as e:
                print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {e}"}))
                continue

            if embed_texts:
                try:
                    vecs = embed_texts([getattr(c, "text", "") for c in chunks])  # type: ignore[attr-defined]
                except Exception as e:
                    print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"}))
                    vecs = [[0.0] * cfg.dim for _ in chunks]
            else:
                vecs = [[0.0] * cfg.dim for _ in chunks]

            try:
                note_refs = note_pl.get("references") or []
                edges = build_edges_for_note(
                    note_id,
                    chunk_pls,
                    note_refs,
                    include_note_scope_refs=note_scope_refs,
                )
            except Exception as e:
                print(json.dumps({"path": path, "note_id": note_id, "error": f"build_edges_for_note failed: {e}"}))
                continue

        # -------- Summary --------
        summary = {
            "note_id": note_id,
            "title": fm.get("title"),
            "chunks": len(chunk_pls),
            "edges": len(edges),
            "changed": changed,
            "needs_baseline_for_mode": needs_baseline,
            "decision": ("baseline-only" if args.apply and do_baseline_only else
                         "apply" if args.apply and changed else
                         "apply-skip-unchanged" if args.apply and not changed else
                         "dry-run"),
            "path": note_pl["path"],
            "hash_mode": mode,
            "hash_normalize": norm,
            "hash_source": src,
        }
        print(json.dumps(summary, ensure_ascii=False))

        # -------- Writes --------
        if not args.apply:
            continue

        # BASELINE-ONLY: fehlenden Key nachtragen, ohne legacy Felder anzutasten
        if do_baseline_only:
            merged_hashes = {}
            merged_hashes.update(old_hashes)
            merged_hashes.update(note_pl.get("hashes") or {})
            # Legacy-Hashfelder unverändert lassen, falls vorhanden
            if old_payload:
                note_pl["hash_fulltext"] = old_payload.get("hash_fulltext", note_pl.get("hash_fulltext"))
                note_pl["hash_signature"] = old_payload.get("hash_signature", note_pl.get("hash_signature"))
            note_pl["hashes"] = merged_hashes
            notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim)
            upsert_batch(client, notes_name, note_pts)
            continue

        # Normale CREATE/UPDATE
        if not changed:
            continue

        if args.purge_before_upsert and has_old:
            try:
                purge_note_artifacts(client, cfg.prefix, note_id)
            except Exception as e:
                print(json.dumps({"path": path, "note_id": note_id, "warn": f"purge failed: {e}"}))

        notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim)
        upsert_batch(client, notes_name, note_pts)
        chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs)
        upsert_batch(client, chunks_name, chunk_pts)
        edges_name, edge_pts = points_for_edges(cfg.prefix, edges)
        upsert_batch(client, edges_name, edge_pts)

    print(f"Done. Processed notes: {processed}")


if __name__ == "__main__":
    main()