"""Map chat files to the character (or group) whose lines they contain.

Built from character_data/{id}.json "mentions" (produced by
build_character_data.py), keeping only characters that have a voice wiki in
character_wikis/. When several characters claim the same file (group chats,
flashback variants), the character whose id matches the filename stem wins,
then the longest id as tie-break.

Speaker attribution within a mapped file (see build_character_wikis.py):
- Conversations: "message" = the mapped character, "options" = player/owner.
- Filler Chats: type "1" = player/owner, type "-1" = system, anything else =
  the mapped character/group.
"""

import json
import re
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent))
import config


def _stem_key(rel_path: str) -> str:
    """Normalised filename stem: 'Flashback 1 Ralph.json' -> 'flashback1ralph'."""
    return re.sub(r"[^a-z0-9]", "", Path(rel_path).stem.lower())


def build_dialogue_map() -> dict[str, str]:
    """Return {rel_path inside the source pack: character_id}."""
    claims: dict[str, list[str]] = {}
    for char_file in sorted(config.CHAR_DATA_DIR.glob("*.json")):
        char_id = char_file.stem
        if not (config.CHAR_WIKI_DIR / f"{char_id}.md").exists():
            continue
        data = json.loads(char_file.read_text(encoding="utf-8"))
        for mention in data.get("mentions", []):
            rel = mention.removeprefix("English_JSON/")
            claims.setdefault(rel, []).append(char_id)

    mapping: dict[str, str] = {}
    for rel, char_ids in claims.items():
        stem = _stem_key(rel)
        exact = [c for c in char_ids if stem.endswith(c)]
        candidates = exact or char_ids
        mapping[rel] = max(candidates, key=len)
    return mapping


def load_wiki(char_id: str) -> str:
    return (config.CHAR_WIKI_DIR / f"{char_id}.md").read_text(encoding="utf-8").strip()


def display_name(char_id: str) -> str:
    """Character display name from character_data (falls back to the id)."""
    char_file = config.CHAR_DATA_DIR / f"{char_id}.json"
    if char_file.exists():
        names = json.loads(char_file.read_text(encoding="utf-8")).get("name") or []
        if names:
            return names[0]
    return char_id


if __name__ == "__main__":
    dmap = build_dialogue_map()
    print(f"{len(dmap)} chat files mapped to {len(set(dmap.values()))} characters")
    for rel, cid in sorted(dmap.items())[:10]:
        print(f"  {cid:15s} {rel}")