# app/core/derive_edges.py
from __future__ import annotations
import re
import unicodedata
from typing import Dict, List, Tuple

WIKILINK_RE = re.compile(r"\[\[([^\]|#]+)(?:#([^\]|]+))?(?:\|([^\]]+))?\]\]")

def _slug(s: str) -> str:
    s = s.strip()
    if s.endswith(".md"):
        s = s[:-3]
    s = unicodedata.normalize("NFKD", s)
    s = "".join(ch for ch in s if not unicodedata.combining(ch))
    s = s.replace("\\", "/")
    s = s.split("/")[-1]  # nur letzter Pfadteil
    s = s.lower()
    s = s.replace(" ", "-")
    s = re.sub(r"[^a-z0-9\-]+", "", s)
    s = re.sub(r"-{2,}", "-", s).strip("-")
    return s

def build_note_index(notes_payloads: List[dict]) -> Tuple[Dict[str, dict], Dict[str, dict], Dict[str, dict]]:
    by_id: Dict[str, dict] = {}
    by_slug: Dict[str, dict] = {}
    by_file_slug: Dict[str, dict] = {}
    for n in notes_payloads:
        nid = n.get("note_id") or n.get("id")
        if not nid:
            continue
        by_id[nid] = n
        title = n.get("title", "")
        path = n.get("path", "")  # z.B. "Ordner/Datei.md"
        file_slug = _slug(path.split("/")[-1]) if path else ""
        if title:
            by_slug[_slug(title)] = n
        if file_slug:
            by_file_slug[file_slug] = n
    return by_id, by_slug, by_file_slug

def resolve_target(note_like: str, idx: Tuple[Dict[str,dict],Dict[str,dict],Dict[str,dict]]) -> Tuple[str|None, str]:
    """
    Liefert (target_note_id | None, resolution_hint)
    """
    by_id, by_slug, by_file_slug = idx
    key = note_like.strip()
    if key in by_id:
        return key, "by_id"
    s = _slug(key)
    if s in by_slug:
        return by_slug[s]["note_id"], "by_slug"
    if s in by_file_slug:
        return by_file_slug[s]["note_id"], "by_file_slug"
    return None, "unresolved"

def derive_wikilink_edges(note_payload: dict, chunks_payloads: List[dict], note_index) -> List[dict]:
    """
    Erzeugt Edges aus [[...]] im Note-Text und in Chunk-Text:
      - references: source_note -> target_note
      - backlink:   target_note -> source_note
      - optional: references_at: source_chunk -> target_note (wo steht der Link?)
    """
    edges: List[dict] = []
    source_note_id = note_payload["note_id"]

    def _make_edge(kind: str, src: str, tgt: str, seq: int|None=None, extra: dict|None=None) -> dict:
        e = {
            "edge_id": None,  # später vergeben (qdrant_points macht robusten Fallback + UUID)
            "kind": kind,
            "source_id": src,
            "target_id": tgt,
        }
        if seq is not None:
            e["seq"] = seq
        if extra:
            e.update(extra)
        return e

    # 1) Links im Note-Gesamttext (falls vorhanden)
    fulltext = note_payload.get("fulltext") or note_payload.get("body") or ""
    if fulltext:
        for m in WIKILINK_RE.finditer(fulltext):
            raw_target, heading, alias = m.groups()
            target_id, how = resolve_target(raw_target, note_index)
            extra = {"raw": raw_target, "alias": alias, "heading": heading, "resolution": how}
            if target_id:
                edges.append(_make_edge("references", source_note_id, target_id, extra=extra))
                edges.append(_make_edge("backlink", target_id, source_note_id, extra=extra))
            else:
                # Unresolved: referenziere Slug/Raw, markiere Status
                extra["status"] = "unresolved"
                extra["target_label"] = raw_target
                edges.append(_make_edge("references", source_note_id, raw_target, extra=extra))

    # 2) Links in den einzelnen Chunks
    for i, ch in enumerate(chunks_payloads, start=1):
        txt = ch.get("text") or ch.get("content") or ""
        if not txt:
            continue
        for m in WIKILINK_RE.finditer(txt):
            raw_target, heading, alias = m.groups()
            target_id, how = resolve_target(raw_target, note_index)
            extra = {"raw": raw_target, "alias": alias, "heading": heading, "resolution": how}
            # optional: chunk→note Referenz (wo steht der Link?)
            if target_id:
                edges.append(_make_edge("references_at", ch["chunk_id"], target_id, seq=i, extra=extra))
                # die Note→Note-Kanten sind oben schon generiert; doppelt vermeiden:
            else:
                extra["status"] = "unresolved"
                extra["target_label"] = raw_target
                edges.append(_make_edge("references_at", ch["chunk_id"], raw_target, seq=i, extra=extra))

    return edges