climperor/shared/import_relations_xlsx.py

"""Import qualitative relations from a Chinese draft spreadsheet.

Usage:
    python import_relations_xlsx.py
    python import_relations_xlsx.py "C:\\Users\\Administrator\\Downloads\\dota2.xlsx"

Writes data/relations.json. Skips category phrases (辅助/幻想系/...).
"""

from __future__ import annotations

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

import argparse
import json
from datetime import datetime, timezone

from shared.paths import SHARED_DATA
from shared.relations import (
    DEFAULT_RELATIONS,
    build_name_index,
    load_relations,
    resolve_name,
    save_relations,
    set_counter,
    set_synergy,
    split_names,
)

# Phrases that are roles/tags, not single heroes.
SKIP_TOKENS = {
    "辅助",
    "推进",
    "幻想系",
    "幻想",
    "所有肉核",
    "肉核",
    "高爆发",
    "奶妈",
    "核心",
}


def _should_skip(token: str) -> bool:
    t = token.strip()
    if not t:
        return True
    if t in SKIP_TOKENS:
        return True
    if "系" in t and t.endswith("系"):
        return True
    if t.startswith("所有"):
        return True
    if "魔晶" in t or "a仗" in t.lower():
        # item/facet interactions in hero columns — skip for edge seed
        return True
    return False


def import_xlsx(path: Path) -> tuple[dict, list[str]]:
    import openpyxl

    wb = openpyxl.load_workbook(path, data_only=True)
    index = build_name_index()
    data = load_relations()
    data["meta"] = {
        "source": str(path),
        "imported_at": datetime.now(timezone.utc).isoformat(),
        "note": "qualitative counters/synergies; no winrate",
    }
    unresolved: list[str] = []
    sheets = ["力量", "敏捷", "智力", "全才"]

    def resolve_list(cell, context: str) -> list[str]:
        keys = []
        for tok in split_names(cell):
            if _should_skip(tok):
                unresolved.append(f"{context}: skip tag '{tok}'")
                continue
            key = resolve_name(tok, index)
            if key is None:
                unresolved.append(f"{context}: unresolved '{tok}'")
                continue
            keys.append(key)
        return keys

    for sheet in sheets:
        if sheet not in wb.sheetnames:
            continue
        ws = wb[sheet]
        rows = list(ws.iter_rows(values_only=True))
        # find header
        header_i = None
        for i, row in enumerate(rows):
            if row and row[0] == "英雄":
                header_i = i
                break
        if header_i is None:
            continue
        for row in rows[header_i + 1 :]:
            if not row or not row[0]:
                continue
            hero_raw = str(row[0]).strip()
            hero = resolve_name(hero_raw, index)
            if hero is None:
                unresolved.append(f"{sheet}: hero unresolved '{hero_raw}'")
                continue
            # col1 被克制, col2 克制, col3 搭档
            countered_by = resolve_list(row[1] if len(row) > 1 else None, f"{hero_raw}/被克")
            counters = resolve_list(row[2] if len(row) > 2 else None, f"{hero_raw}/克制")
            partners = resolve_list(row[3] if len(row) > 3 else None, f"{hero_raw}/搭档")

            for other in counters:
                set_counter(data, hero, other, reason="")
            for other in countered_by:
                # other counters hero
                set_counter(data, other, hero, reason="")
            for other in partners:
                set_synergy(data, hero, other, reason="")

    return data, unresolved


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument(
        "xlsx",
        nargs="?",
        default=str(Path.home() / "Downloads" / "dota2.xlsx"),
        help="path to dota2.xlsx",
    )
    ap.add_argument("--out", default=str(DEFAULT_RELATIONS))
    args = ap.parse_args()
    path = Path(args.xlsx)
    if not path.is_file():
        raise SystemExit(f"file not found: {path}")

    data, unresolved = import_xlsx(path)
    out = save_relations(data, args.out)
    print(f"wrote {out}")
    print(f"counters={len(data['counters'])} synergies={len(data['synergies'])}")
    report = SHARED_DATA / "relations_import_report.json"
    report.write_text(
        json.dumps({"unresolved": unresolved, "count": len(unresolved)}, ensure_ascii=False, indent=2) + "\n",
        encoding="utf-8",
    )
    print(f"unresolved notes: {len(unresolved)} → {report}")
    for line in unresolved[:40]:
        print(" ", line)
    if len(unresolved) > 40:
        print(f"  ... +{len(unresolved) - 40} more")


if __name__ == "__main__":
    main()