"""TTS input normalisation. Claude speaks in markdown/backticks; MeloTTS's
Korean normaliser crashes on a bare backtick (``KeyError: '`'``), which used to
take down the whole voice turn. normalize_for_speech() must strip formatting and
above all guarantee no backtick reaches the synthesiser."""

from wsai.backends.melo import normalize_for_speech


def test_backticks_are_always_removed():
    # The exact crash trigger: inline code, a fenced block, and a stray backtick.
    reply = "`ls -la` 를 써봐. 예시:\n```python\nprint('hi')\n```\n그리고 ` 이건 홀로 남은 백틱"
    out = normalize_for_speech(reply)
    assert "`" not in out            # the character that crashes MeloTTS is gone
    assert "ls -la" in out           # inner words are kept, just unwrapped
    assert "print('hi')" in out      # fenced code content survives as spoken text


def test_markdown_structure_flattened():
    reply = "# 제목\n- 첫째 항목\n- 둘째 항목\n**굵게** 그리고 _기울임_\n> 인용문"
    out = normalize_for_speech(reply)
    assert "#" not in out
    assert "**" not in out and "_" not in out
    assert not out.lstrip().startswith(("-", ">"))
    assert "첫째 항목" in out and "굵게" in out and "인용문" in out


def test_links_reduced_to_label():
    out = normalize_for_speech("자세히는 [문서](https://example.com/docs) 참고해")
    assert "문서" in out
    assert "http" not in out and "]" not in out and "(" not in out


def test_plain_text_is_left_intact():
    plain = "안녕, 지금 화면 잘 보고 있어. 뭐 도와줄까?"
    assert normalize_for_speech(plain) == plain


def test_empty_is_safe():
    assert normalize_for_speech("") == ""