"""smoke: transcribe_audio / core.asr_lfasr 的纯本地部分(不联讯飞)。

验证:
  1. asr_lfasr.parse_transcript:json_1best 为串(lattice)与对象(lattice2)两形态、
     空文本段跳过、rl 角色提取;
  2. asr_lfasr.format_transcript:多说话人按连续同角色合并「【说话人N】」段落,
     单说话人纯文本;
  3. TranscribeAudioTool 入参错误路径(路径不存在 / 扩展名不对 / 视频提示 / 空文件 /
     越界 / 坏 language),全部在上传前早返,不触网。

跑法: .venv/Scripts/python.exe scripts/smoke_transcribe_audio.py
"""
from __future__ import annotations

import json
import sys
import tempfile
from pathlib import Path

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

from core.asr_lfasr import format_transcript, parse_transcript  # noqa: E402
from tools.transcribe_audio import TranscribeAudioTool  # noqa: E402

FAIL = 0


def check(name: str, ok: bool, detail: str = "") -> None:
    global FAIL
    tag = "PASS" if ok else "FAIL"
    print(f"[{tag}] {name}" + (f" -- {detail}" if detail else ""))
    if not ok:
        FAIL = 1


def seg(text: str, rl: str = "0") -> dict:
    """构造一个 lattice 项(json_1best 为再编码 JSON 串,官方返回形态)。"""
    st = {"rl": rl, "rt": [{"ws": [{"cw": [{"w": ch}]} for ch in text]}]}
    return {"json_1best": json.dumps({"st": st}, ensure_ascii=False)}


def main() -> int:
    # ---- 1. parse_transcript ----
    order = json.dumps({"lattice": [seg("今天开会", "1"), seg("好的", "2"), seg("", "1")]},
                       ensure_ascii=False)
    segs = parse_transcript(order)
    check("parse: 2 segments (empty skipped)", len(segs) == 2, str(segs))
    check("parse: roles extracted", segs == [("1", "今天开会"), ("2", "好的")], str(segs))

    # lattice2 形态:json_1best 已是对象
    obj_item = json.loads(seg("测试", "0")["json_1best"])
    segs2 = parse_transcript(json.dumps({"lattice2": [{"json_1best": obj_item}]},
                                        ensure_ascii=False))
    check("parse: lattice2 object form", segs2 == [("", "测试")], str(segs2))

    # ---- 2. format_transcript ----
    multi = [("1", "大家好。"), ("1", "开始吧。"), ("2", "收到。"), ("1", "散会。")]
    out = format_transcript(multi)
    check("format: multi-speaker merged",
          out == "【说话人1】大家好。开始吧。\n\n【说话人2】收到。\n\n【说话人1】散会。",
          repr(out))
    single = [("1", "自言"), ("1", "自语")]
    check("format: single speaker plain", format_transcript(single) == "自言自语")
    check("format: no-role plain", format_transcript([("", "甲"), ("", "乙")]) == "甲乙")

    # ---- 3. tool 早返错误路径(不触网) ----
    with tempfile.TemporaryDirectory(prefix="zcbot-smoke-ta-") as td:
        root = Path(td)
        wd = root / "taskdir"
        wd.mkdir()
        tool = TranscribeAudioTool(working_dir=wd, base_dir=wd, user_root=root)

        r = tool.execute(audio="inbound/nope.m4a")
        check("missing file -> [Error]", r.startswith("[Error]") and "找不到" in r, r[:60])

        (wd / "notes.docx").write_bytes(b"PK\x03\x04fake")
        r = tool.execute(audio="notes.docx")
        check("non-audio ext -> [Error]", r.startswith("[Error]") and "扩展名" in r, r[:60])

        (wd / "clip.mp4").write_bytes(b"\x00\x00\x00\x18ftyp")
        r = tool.execute(audio="clip.mp4")
        check("video ext -> hint to extract audio",
              r.startswith("[Error]") and "音轨" in r, r[:80])

        (wd / "empty.mp3").write_bytes(b"")
        r = tool.execute(audio="empty.mp3")
        check("empty file -> [Error]", r.startswith("[Error]") and "空" in r, r[:60])

        outside = root.parent / "zcbot-smoke-outside.mp3"
        try:
            outside.write_bytes(b"xx")
            r = tool.execute(audio=str(outside))
            check("out-of-root abs path -> [Error]",
                  r.startswith("[Error]") and "越界" in r, r[:60])
        finally:
            outside.unlink(missing_ok=True)

        r = tool.execute(audio="a.mp3", language="fr")
        check("bad language -> [Error]", r.startswith("[Error]") and "language" in r, r[:60])

    print("RESULT:", "FAIL" if FAIL else "ALL PASS")
    return FAIL


if __name__ == "__main__":
    raise SystemExit(main())