path: root/tests/test_tts.py

"""Tests for the TTS client wrappers (language handling and payloads)."""

import json
import tempfile
import unittest
import wave
from pathlib import Path
from unittest.mock import MagicMock, patch

from converter import config
from converter.converter import AudiobookConverter
from converter.tts import FasterTTSClient, QwenTTSClient, normalize_language


class NormalizeLanguageTests(unittest.TestCase):
    def test_display_names_case_insensitive(self):
        self.assertEqual(normalize_language("english"), "English")
        self.assertEqual(normalize_language("ENGLISH"), "English")
        self.assertEqual(normalize_language(" Japanese "), "Japanese")

    def test_auto_accepted(self):
        self.assertEqual(normalize_language("auto"), "Auto")
        self.assertEqual(normalize_language("Auto"), "Auto")

    def test_iso_aliases(self):
        self.assertEqual(normalize_language("en"), "English")
        self.assertEqual(normalize_language("ja"), "Japanese")
        self.assertEqual(normalize_language("zh"), "Chinese")
        self.assertEqual(normalize_language("ko"), "Korean")
        self.assertEqual(normalize_language("de"), "German")
        self.assertEqual(normalize_language("fr"), "French")
        self.assertEqual(normalize_language("ru"), "Russian")
        self.assertEqual(normalize_language("pt"), "Portuguese")
        self.assertEqual(normalize_language("es"), "Spanish")
        self.assertEqual(normalize_language("it"), "Italian")

    def test_all_supported_languages_round_trip(self):
        for name in config.TTS_LANGUAGES:
            self.assertEqual(normalize_language(name.lower()), name)

    def test_unknown_language_rejected_with_guidance(self):
        with self.assertRaises(ValueError) as ctx:
            normalize_language("klingon")
        message = str(ctx.exception)
        self.assertIn("klingon", message)
        self.assertIn("English", message)

    def test_none_and_empty_rejected(self):
        with self.assertRaises(ValueError):
            normalize_language(None)
        with self.assertRaises(ValueError):
            normalize_language("   ")


class QwenTTSClientLanguageTests(unittest.TestCase):
    """Language validation and defaults, without touching the network."""

    def _make_client(self, **kwargs):
        with patch.object(QwenTTSClient, "_connect"):
            return QwenTTSClient(**kwargs)

    def test_default_follows_config_for_each_mode(self):
        custom = self._make_client(voice_mode=config.VOICE_MODE_CUSTOM)
        self.assertEqual(custom.language, config.CUSTOM_VOICE_LANGUAGE)
        clone = self._make_client(voice_mode=config.VOICE_MODE_CLONE,
                                  voice_clone_ref_audio="ref.wav")
        self.assertEqual(clone.language, config.VOICE_CLONE_LANGUAGE)

    def test_explicit_language_normalized(self):
        client = self._make_client(voice_mode=config.VOICE_MODE_CUSTOM, language="ja")
        self.assertEqual(client.language, "Japanese")

    def test_invalid_language_fails_before_connect(self):
        with patch.object(QwenTTSClient, "_connect") as mock_connect:
            with self.assertRaises(ValueError):
                QwenTTSClient(language="klingon")
        mock_connect.assert_not_called()


class PayloadLanguageTests(unittest.TestCase):
    """The language must reach the API payload in every endpoint variant."""

    def setUp(self):
        self._tmp = tempfile.TemporaryDirectory()
        self.ref_audio = Path(self._tmp.name) / "reference.wav"
        self.ref_audio.write_bytes(b"x")

    def tearDown(self):
        self._tmp.cleanup()

    def _custom_client(self, language, endpoint, api_info=None):
        client = QwenTTSClient.__new__(QwenTTSClient)
        client.voice_mode = config.VOICE_MODE_CUSTOM
        client.language = language
        client.api_info = api_info if api_info is not None else {
            "named_endpoints": {endpoint: {}}
        }
        client.client = MagicMock()
        return client

    def _clone_client(self, language, endpoint, api_info=None, ref_text="hello"):
        client = QwenTTSClient.__new__(QwenTTSClient)
        client.voice_mode = config.VOICE_MODE_CLONE
        client.language = language
        client.voice_clone_ref_audio = str(self.ref_audio)
        client.voice_clone_ref_text = ref_text
        client.clone_api_info = api_info if api_info is not None else {
            "named_endpoints": {endpoint: {}}
        }
        client.clone_client = MagicMock()
        client._ref_audio_filedata = {"dummy": "payload"}
        return client

    def test_custom_voice_run_instruct_uses_language(self):
        client = self._custom_client("Japanese", "/run_instruct")
        client._generate_custom_voice("text")
        kwargs = client.client.predict.call_args.kwargs
        self.assertEqual(kwargs["lang_disp"], "Japanese")

    def test_custom_voice_alt_endpoint_uses_language(self):
        client = self._custom_client("French", "/run_custom_voice")
        client._generate_custom_voice("text")
        kwargs = client.client.predict.call_args.kwargs
        self.assertEqual(kwargs["language"], "French")

    def test_voice_clone_run_voice_clone_uses_language(self):
        client = self._clone_client("Japanese", "/run_voice_clone")
        client._generate_voice_clone("text")
        kwargs = client.clone_client.predict.call_args.kwargs
        self.assertEqual(kwargs["lang_disp"], "Japanese")

    def test_voice_clone_alt_endpoint_uses_language(self):
        client = self._clone_client("Korean", "/generate_voice_clone")
        client._generate_voice_clone("text")
        kwargs = client.clone_client.predict.call_args.kwargs
        self.assertEqual(kwargs["language"], "Korean")

    def test_voice_clone_alt_endpoint_includes_optional_params(self):
        api_info = {
            "named_endpoints": {
                "/generate_voice_clone": {
                    "parameters": [
                        {"parameter_name": "model_size"},
                        {"parameter_name": "seed"},
                    ]
                }
            }
        }
        client = self._clone_client("English", "/generate_voice_clone", api_info=api_info)
        client._generate_voice_clone("text")
        kwargs = client.clone_client.predict.call_args.kwargs
        self.assertEqual(kwargs["model_size"], config.VOICE_CLONE_MODEL_SIZE)
        self.assertEqual(kwargs["seed"], config.VOICE_CLONE_SEED)
        self.assertNotIn("max_chunk_chars", kwargs)


class FasterTTSClientHealthTests(unittest.TestCase):
    """Connection behavior of the faster-qwen3-tts client."""

    def _health_response(self, model_loaded=True):
        response = MagicMock()
        response.__enter__.return_value = response
        response.read.return_value = json.dumps(
            {"status": "ok", "model_loaded": model_loaded}).encode("utf-8")
        return response

    def test_unreachable_server_raises_with_readme_pointer(self):
        import urllib.error
        with patch("converter.tts.urllib.request.urlopen",
                   side_effect=urllib.error.URLError("Connection refused")):
            with self.assertRaises(RuntimeError) as ctx:
                FasterTTSClient()
        message = str(ctx.exception)
        self.assertIn("not reachable", message)
        self.assertIn("README", message)

    def test_model_not_loaded_raises(self):
        with patch("converter.tts.urllib.request.urlopen",
                   return_value=self._health_response(model_loaded=False)):
            with self.assertRaises(RuntimeError) as ctx:
                FasterTTSClient()
        self.assertIn("not loaded", str(ctx.exception))

    def test_healthy_server_defaults_from_config(self):
        with patch("converter.tts.urllib.request.urlopen",
                   return_value=self._health_response()):
            client = FasterTTSClient()
        self.assertEqual(client.voice, config.FASTER_TTS_VOICE)
        self.assertEqual(client.api_url, config.FASTER_TTS_API_URL.rstrip("/"))

    def test_explicit_voice_and_url_override_config(self):
        with patch("converter.tts.urllib.request.urlopen",
                   return_value=self._health_response()):
            client = FasterTTSClient(voice="narrator", api_url="http://10.0.0.5:9000/")
        self.assertEqual(client.voice, "narrator")
        self.assertEqual(client.api_url, "http://10.0.0.5:9000")


class FasterTTSClientGenerateTests(unittest.TestCase):
    """Chunk generation: sub-chunking, WAV output, retries, bookkeeping."""

    def setUp(self):
        self._tmp = tempfile.TemporaryDirectory()
        self._chunks = patch.object(config, "CHUNKS_FOLDER", Path(self._tmp.name))
        self._chunks.start()
        self._sleep = patch("converter.tts.time.sleep")
        self._sleep.start()

    def tearDown(self):
        self._sleep.stop()
        self._chunks.stop()
        self._tmp.cleanup()

    def _make_client(self):
        client = FasterTTSClient.__new__(FasterTTSClient)
        client.voice = "default"
        client.api_url = "http://127.0.0.1:8000"
        return client

    def _read_wav(self, path):
        with wave.open(str(path), "rb") as wav_file:
            return (wav_file.getnchannels(), wav_file.getsampwidth(),
                    wav_file.getframerate(), wav_file.readframes(wav_file.getnframes()))

    def test_generate_chunk_writes_valid_wav(self):
        client = self._make_client()
        pcm = b"\x01\x00" * 100
        with patch.object(client, "_request_pcm", return_value=pcm):
            result = client.generate_chunk("Hello world.", 1)
        self.assertIsNotNone(result)
        path = Path(result)
        self.assertEqual(path.name, "chunk_0001.wav")
        channels, sampwidth, framerate, frames = self._read_wav(path)
        self.assertEqual(channels, 1)
        self.assertEqual(sampwidth, 2)
        self.assertEqual(framerate, config.FASTER_TTS_SAMPLE_RATE)
        self.assertEqual(frames, pcm)

    def test_long_text_is_subchunked_and_concatenated_in_order(self):
        client = self._make_client()
        sentences = [" ".join(f"word{i}" for i in range(6)) + "." for _ in range(3)]
        text = " ".join(sentences)
        pcm_parts = [b"\x01\x00" * 10, b"\x02\x00" * 20, b"\x03\x00" * 30]
        with patch.object(config, "FASTER_SUBCHUNK_WORDS", 10), \
                patch.object(client, "_request_pcm", side_effect=pcm_parts) as mock_pcm:
            result = client.generate_chunk(text, 1)
        self.assertEqual(mock_pcm.call_count, 3)
        _, _, _, frames = self._read_wav(Path(result))
        self.assertEqual(frames, b"".join(pcm_parts))

    def test_stale_chunk_files_are_removed(self):
        stale = Path(self._tmp.name) / "chunk_0001.mp3"
        stale.write_bytes(b"old")
        client = self._make_client()
        with patch.object(client, "_request_pcm", return_value=b"\x01\x00"):
            client.generate_chunk("Hello.", 1)
        remaining = sorted(path.name for path in Path(self._tmp.name).glob("chunk_0001.*"))
        self.assertEqual(remaining, ["chunk_0001.wav"])

    def test_transient_failure_is_retried(self):
        client = self._make_client()
        pcm = b"\x01\x00" * 10
        with patch.object(client, "_request_pcm",
                          side_effect=[RuntimeError("boom"), pcm]) as mock_pcm:
            result = client.generate_chunk("Hello.", 1)
        self.assertIsNotNone(result)
        self.assertEqual(mock_pcm.call_count, 2)

    def test_empty_pcm_response_is_treated_as_failure(self):
        client = self._make_client()
        pcm = b"\x01\x00" * 10

        def _response(body):
            response = MagicMock()
            response.__enter__.return_value = response
            response.read.return_value = body
            return response

        with patch("converter.tts.urllib.request.urlopen",
                   side_effect=[_response(b""), _response(pcm)]) as mock_urlopen:
            result = client.generate_chunk("Hello.", 1)
        self.assertIsNotNone(result)
        self.assertEqual(mock_urlopen.call_count, 2)
        _, _, _, frames = self._read_wav(Path(result))
        self.assertEqual(frames, pcm)

    def test_exhausted_subchunk_retries_fail_the_chunk(self):
        client = self._make_client()
        with patch.object(client, "_request_pcm",
                          side_effect=RuntimeError("down")) as mock_pcm:
            result = client.generate_chunk("Hello.", 1)
        self.assertIsNone(result)
        self.assertEqual(mock_pcm.call_count, config.FASTER_SUBCHUNK_RETRIES)

    def test_empty_text_fails_the_chunk(self):
        client = self._make_client()
        with patch.object(client, "_request_pcm") as mock_pcm:
            result = client.generate_chunk("   ", 1)
        self.assertIsNone(result)
        mock_pcm.assert_not_called()

    def test_request_payload_includes_voice_text_and_format(self):
        client = self._make_client()
        response = MagicMock()
        response.__enter__.return_value = response
        response.read.return_value = b"\x01\x00" * 10
        with patch("converter.tts.urllib.request.urlopen",
                   return_value=response) as mock_urlopen:
            pcm = client._request_pcm("Hello world.")
        self.assertEqual(pcm, b"\x01\x00" * 10)
        request = mock_urlopen.call_args[0][0]
        self.assertEqual(request.full_url, "http://127.0.0.1:8000/v1/audio/speech")
        payload = json.loads(request.data.decode("utf-8"))
        self.assertEqual(payload["input"], "Hello world.")
        self.assertEqual(payload["voice"], "default")
        self.assertEqual(payload["response_format"], "pcm")


class FasterModeWiringTests(unittest.TestCase):
    """AudiobookConverter wiring for the --faster backend."""

    def test_faster_mode_uses_faster_client_without_reference(self):
        with patch("converter.converter.FasterTTSClient") as mock_faster, \
                patch("converter.converter.QwenTTSClient") as mock_qwen:
            AudiobookConverter(voice_mode=config.VOICE_MODE_CLONE,
                               faster=True, faster_voice="narrator")
        mock_faster.assert_called_once_with(voice="narrator")
        mock_qwen.assert_not_called()

    def test_non_faster_clone_mode_still_requires_reference(self):
        with patch("converter.converter.QwenTTSClient"):
            with self.assertRaises(ValueError):
                AudiobookConverter(voice_mode=config.VOICE_MODE_CLONE)

    def test_faster_mode_still_validates_other_settings(self):
        with patch("converter.converter.FasterTTSClient"):
            with self.assertRaises(ValueError):
                AudiobookConverter(faster=True, speed=0)
            with self.assertRaises(ValueError):
                AudiobookConverter(faster=True, language="klingon")

    def _faster_converter(self, faster_voice=None):
        with patch("converter.converter.FasterTTSClient"):
            return AudiobookConverter(voice_mode=config.VOICE_MODE_CLONE,
                                      faster=True, faster_voice=faster_voice)

    def test_narrator_tag_uses_faster_voice_name(self):
        converter = self._faster_converter(faster_voice="male_richard_poe")
        self.assertEqual(converter._narrator_tag(), "male_richard_poe")

    def test_narrator_tag_falls_back_to_config_voice(self):
        converter = self._faster_converter()
        self.assertEqual(converter._narrator_tag(), config.FASTER_TTS_VOICE)

    def test_banner_and_narrator_work_without_reference_audio(self):
        converter = self._faster_converter(faster_voice="male_richard_poe")
        converter._print_banner()  # must not raise (regression: Path(None))
        self.assertIsNone(converter.voice_clone_ref_audio)

    def test_non_faster_narrator_tag_unchanged(self):
        with tempfile.TemporaryDirectory() as tmp:
            ref = Path(tmp) / "ref.wav"
            ref.write_bytes(b"x")
            with patch("converter.converter.QwenTTSClient"):
                converter = AudiobookConverter(voice_mode=config.VOICE_MODE_CLONE,
                                               voice_clone_ref_audio=str(ref))
        self.assertEqual(converter._narrator_tag(), "ref")


if __name__ == "__main__":
    unittest.main()