mindnet/scripts/import_markdown.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Script: scripts/import_markdown.py — Markdown → Qdrant (Notes, Chunks, Edges)
Version: 3.7.2
Datum: 2025-09-30
# ---- helpers ----
def effective_chunk_profile(note_type: str, registry: dict) -> str | None:
    try:
        tcfg = (registry or {}).get("types", {}).get(note_type) or (registry or {}).get("types", {}).get("concept")
        prof = (tcfg or {}).get("chunk_profile")
        if isinstance(prof, str) and prof in {"short", "medium", "long"}:
            return prof
    except Exception:
        pass
    return None

def effective_retriever_weight(note_type: str, registry: dict) -> float | None:
    try:
        tcfg = (registry or {}).get("types", {}).get(note_type) or (registry or {}).get("types", {}).get("concept")
        w = (tcfg or {}).get("retriever_weight")
        if w is None:
            return None
        return float(w)
    except Exception:
        return None


Kurzbeschreibung
----------------
- Liest Markdown-Dateien ein und erzeugt Notes/Chunks/Edges **idempotent**.
- Änderungserkennung „Option C“: mehrere Hash-Varianten werden parallel in der Note
  gespeichert (Feld `hashes` mit Schlüsseln `<mode>:<source>:<normalize>`). Der Vergleich
  nutzt NUR den aktuellen Modus-Key — ein Moduswechsel triggert keine Massenänderungen mehr.
- „Erstimport-Fix“: Bei leerem Qdrant gilt Create-Fall automatisch als geändert.
- `--baseline-modes`: fehlende Hash-Varianten still nachtragen (nur Notes upserten).
- `--sync-deletes`: gezielte Lösch-Synchronisation (Dry-Run + Apply).
- `--only-path`: exakt **eine** Datei (Pfad) importieren — nützlich für Diagnosefälle.

Neu in 3.7.1/3.7.2
------------------
- Chunk-Payloads: `window` (für Embeddings), `text` (überlappungsfrei, verlustfrei rekonstruierbar),
  `start/end/overlap_*`. Embeddings nutzen `window`.
- **3.7.2:** Edges-Fehler führen nicht mehr zum Abbruch der gesamten Note; Note/Chunks werden trotzdem geschrieben.

Hash/Compare Konfiguration
--------------------------
- Vergleichsmodus:
    --hash-mode body|frontmatter|full
    oder ENV: MINDNET_HASH_MODE | MINDNET_HASH_COMPARE
- 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 ENV MINDNET_COMPARE_TEXT=true) vergleicht zusätzlich
  den parsed Body-Text direkt.

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

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

    # Erstimport nach truncate (Create-Fall)
    python3 -m scripts.import_markdown --vault ./vault --apply --purge-before-upsert

    # Nur eine Datei (Diagnose)
    python3 -m scripts.import_markdown --vault ./vault --only-path ./vault/30_projects/project-demo.md --apply

    # Sync-Deletes (Dry-Run → Apply)
    python3 -m scripts.import_markdown --vault ./vault --sync-deletes
    python3 -m scripts.import_markdown --vault ./vault --sync-deletes --apply
"""
from __future__ import annotations

import argparse
import json
import os
import sys
from typing import Dict, List, Optional, Tuple, Any, Set

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
try:
    from app.core.derive_edges import build_edges_for_note
except Exception:  # pragma: no cover
    from app.core.edges import build_edges_for_note  # type: ignore
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


# ---------------------------------------------------------------------
# Helper
# ---------------------------------------------------------------------

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 list_qdrant_note_ids(client, prefix: str) -> Set[str]:
    notes_col, _, _ = collections(prefix)
    out: Set[str] = set()
    next_page = None
    while True:
        pts, next_page = client.scroll(
            collection_name=notes_col,
            with_payload=True,
            with_vectors=False,
            limit=256,
            offset=next_page,
        )
        if not pts:
            break
        for p in pts:
            pl = p.payload or {}
            nid = pl.get("note_id")
            if isinstance(nid, str):
                out.add(nid)
        if next_page is None:
            break
    return out


def purge_note_artifacts(client, prefix: str, note_id: str) -> None:
    _, chunks_col, edges_col = collections(prefix)
    filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
    for col in (chunks_col, edges_col):
        try:
            client.delete(
                collection_name=col,
                points_selector=rest.FilterSelector(filter=filt),
                wait=True
            )
        except Exception as e:
            print(json.dumps({"note_id": note_id, "warn": f"delete in {col} via filter failed: {e}"}))


def delete_note_everywhere(client, prefix: str, note_id: str) -> None:
    notes_col, chunks_col, edges_col = collections(prefix)
    filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
    for col in (edges_col, chunks_col, notes_col):
        try:
            client.delete(
                collection_name=col,
                points_selector=rest.FilterSelector(filter=filt),
                wait=True
            )
        except Exception as e:
            print(json.dumps({"note_id": note_id, "warn": f"delete in {col} failed: {e}"}))


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("--only-path", help="Exakt diesen Markdown-Pfad verarbeiten (ignoriert --note-id)")
    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/backlink:note (Default: aus)")
    ap.add_argument("--debug-hash-diff", action="store_true",
                    help="(reserviert) optionaler Body-Diff")
    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)")
    ap.add_argument("--sync-deletes", action="store_true",
                    help="Notes/Chunks/Edges löschen, die in Qdrant existieren aber im Vault fehlen (Dry-Run; mit --apply ausführen)")
    ap.add_argument("--prefix", help="Collection-Prefix (überschreibt ENV COLLECTION_PREFIX)")
    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()
    if args.prefix:
        cfg.prefix = args.prefix.strip()
    client = get_client(cfg)
    ensure_collections(client, cfg.prefix, cfg.dim)
    ensure_payload_indexes(client, cfg.prefix)

    root = os.path.abspath(args.vault)

    # Dateiliste bestimmen
    if args.only_path:
        only = os.path.abspath(args.only_path)
        files = [only]
    else:
        files = iter_md(root)
    if not files:
        print("Keine Markdown-Dateien gefunden.", file=sys.stderr)
        sys.exit(2)

    # Optional: Sync-Deletes vorab
    if args.sync_deletes:
        vault_note_ids: Set[str] = set()
        for path in files:
            try:
                parsed = read_markdown(path)
                if not parsed:
                    continue
                fm = normalize_frontmatter(parsed.frontmatter)
                nid = fm.get("id")
                if isinstance(nid, str):
                    vault_note_ids.add(nid)
            except Exception:
                continue
        qdrant_note_ids = list_qdrant_note_ids(client, cfg.prefix)
        to_delete = sorted(qdrant_note_ids - vault_note_ids)
        print(json.dumps({
            "action": "sync-deletes",
            "prefix": cfg.prefix,
            "qdrant_total": len(qdrant_note_ids),
            "vault_total": len(vault_note_ids),
            "to_delete_count": len(to_delete),
            "to_delete": to_delete[:50] + (["…"] if len(to_delete) > 50 else [])
        }, ensure_ascii=False))
        if args.apply and to_delete:
            for nid in to_delete:
                print(json.dumps({"action": "delete", "note_id": nid, "decision": "apply"}))
                delete_note_everywhere(client, cfg.prefix, nid)

    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: {type(e).__name__}: {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: {type(e).__name__}: {e}"}))
            continue

        if args.note_id and not args.only_path 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)
        new_hash_exact = (note_pl.get("hashes") or {}).get(key_current)
        needs_baseline = (old_hash_exact is None)

        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
        do_baseline_only = (args.baseline_modes and has_old and needs_baseline and not changed)
        # -------- Chunks / Embeddings --------
        chunk_pls: List[Dict[str, Any]] = []
        try:
            body_text = getattr(parsed, "body", "") or ""
            # ---- Type-Registry integration ----
            try:
                note_type = resolve_note_type(fm.get("type"), reg)
            except Exception:
                note_type = (fm.get("type") or "concept")
            fm["type"] = note_type or "concept"
            try:
                cfg_type = get_type_config(note_type, reg)
            except Exception:
                cfg_type = {}
            prof = effective_chunk_profile(note_type, reg)
            if prof:
                fm["chunk_profile"] = prof
            weight = cfg_type.get("retriever_weight")
            if weight is not None:
                fm["retriever_weight"] = float(weight)

            # Ensure note-level payload reflects registry fields
            try:
                if isinstance(note_pl, dict):
                    if fm.get("type"):
                        note_pl["type"] = fm["type"]
                    if fm.get("chunk_profile"):
                        note_pl["chunk_profile"] = fm["chunk_profile"]
                    if "retriever_weight" in fm:
                        note_pl["retriever_weight"] = fm["retriever_weight"]
            except Exception:
                pass

            chunks = assemble_chunks(fm["id"], body_text, fm.get("type", "concept"))
            chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text)
        except Exception as e:
            print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {type(e).__name__}: {e}"}))
            continue

        vecs: List[List[float]] = [[0.0] * cfg.dim for _ in chunk_pls]
        if embed_texts and chunk_pls:
            try:
                texts_for_embed = [(pl.get("window") or pl.get("text") or "") for pl in chunk_pls]
                vecs = embed_texts(texts_for_embed)
            except Exception as e:
                print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"}))


        # -------- Edges (robust) --------
        edges: List[Dict[str, Any]] = []
        edges_failed = False
        if changed and (not do_baseline_only):
            try:
                note_refs = note_pl.get("references") or []
                edges = build_edges_for_note(
                    note_id,
                    chunk_pls,
                    note_level_references=note_refs,
                    include_note_scope_refs=note_scope_refs,
                )
            except Exception as e:
                edges_failed = True
                edges = []
                # WICHTIG: Wir brechen NICHT mehr ab — Note & Chunks werden geschrieben.
                print(json.dumps({"path": path, "note_id": note_id, "warn": f"build_edges_for_note failed, skipping edges: {type(e).__name__}: {e}"}))

        # -------- Summary --------
        summary = {
            "note_id": note_id,
            "title": fm.get("title"),
            "chunks": len(chunk_pls),
            "edges": len(edges),
            "edges_failed": edges_failed,
            "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,
            "prefix": cfg.prefix,
        }
        print(json.dumps(summary, ensure_ascii=False))

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

        if do_baseline_only:
            merged_hashes = {}
            merged_hashes.update(old_hashes)
            merged_hashes.update(note_pl.get("hashes") or {})
            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

        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)
        if chunk_pls:
            chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs)
            upsert_batch(client, chunks_name, chunk_pts)
        if edges:
            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()