@laitszkin/apollo-toolkit 3.13.2 → 3.14.1

package/docs-to-voice/scripts/docs_to_voice.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd -P)"
-
-if ! command -v python3 >/dev/null 2>&1; then
-  echo "[ERROR] python3 is required." >&2
-  exit 1
-fi
-
-exec python3 "$script_dir/docs_to_voice.py" "$@"

package/docs-to-voice/tests/test_docs_to_voice_api_max_chars.py

@@ -1,210 +0,0 @@
-import http.client
-import unittest
-from unittest.mock import patch
-
-from scripts.docs_to_voice import (
-    DocsToVoiceError,
-    api_text_length_units,
-    discover_api_max_chars,
-    extract_max_chars_from_text,
-    fetch_api_model_max_chars,
-    is_max_chars_disabled,
-    probe_api_max_chars,
-    request_model_studio_audio,
-    split_text_for_tts,
-)
-
-
-class ExtractMaxCharsFromTextTests(unittest.TestCase):
-    def test_extracts_limit_from_range_message(self):
-        message = (
-            "Model Studio TTS request failed (HTTP 400): "
-            "InvalidParameter: Range of input length should be [0, 600]"
-        )
-        self.assertEqual(extract_max_chars_from_text(message), 600)
-
-    def test_extracts_limit_with_comma(self):
-        message = "Maximum input length is 1,200 characters."
-        self.assertEqual(extract_max_chars_from_text(message), 1200)
-
-    def test_extracts_limit_from_chinese_message(self):
-        message = "請求失敗：輸入長度上限為 600 字元"
-        self.assertEqual(extract_max_chars_from_text(message), 600)
-
-    def test_returns_none_for_unrelated_message(self):
-        self.assertIsNone(extract_max_chars_from_text("network timeout"))
-
-
-class MaxCharsDisabledTests(unittest.TestCase):
-    def test_zero_string_disables_chunking(self):
-        self.assertTrue(is_max_chars_disabled("0"))
-
-    def test_non_zero_does_not_disable_chunking(self):
-        self.assertFalse(is_max_chars_disabled("1200"))
-
-
-class ApiTextLengthUnitsTests(unittest.TestCase):
-    def test_counts_chinese_as_two_units(self):
-        self.assertEqual(api_text_length_units("AB測試!"), 7)
-
-    def test_split_text_respects_weighted_units(self):
-        chunks = split_text_for_tts("測" * 301, 600, length_func=api_text_length_units)
-        self.assertEqual(len(chunks), 2)
-        self.assertEqual(chunks[0], "測" * 300)
-        self.assertEqual(chunks[1], "測")
-
-
-class FetchApiModelMaxCharsTests(unittest.TestCase):
-    @patch("scripts.docs_to_voice.fetch_json_payload")
-    def test_fetches_limit_from_model_catalog(self, mock_fetch_json_payload):
-        mock_fetch_json_payload.return_value = {
-            "output": {
-                "total": 1,
-                "models": [
-                    {
-                        "model": "qwen3-tts",
-                        "model_info": {"max_input_tokens": 600},
-                    }
-                ],
-            }
-        }
-
-        result = fetch_api_model_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-        )
-
-        self.assertEqual(result, 600)
-
-    @patch("scripts.docs_to_voice.fetch_json_payload")
-    def test_returns_none_when_catalog_request_fails(self, mock_fetch_json_payload):
-        mock_fetch_json_payload.side_effect = RuntimeError("network error")
-
-        result = fetch_api_model_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-        )
-
-        self.assertIsNone(result)
-
-    @patch("scripts.docs_to_voice.fetch_json_payload")
-    def test_fetches_limit_from_later_page_when_needed(self, mock_fetch_json_payload):
-        mock_fetch_json_payload.side_effect = [
-            {
-                "output": {
-                    "total": 101,
-                    "models": [{"model": "other-model", "model_info": {}}],
-                }
-            },
-            {
-                "output": {
-                    "total": 101,
-                    "models": [
-                        {
-                            "model": "qwen3-tts",
-                            "description": "Range of input length should be [0, 800]",
-                        }
-                    ],
-                }
-            },
-        ]
-
-        result = fetch_api_model_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-        )
-
-        self.assertEqual(result, 800)
-        self.assertEqual(mock_fetch_json_payload.call_count, 2)
-
-
-class ProbeApiMaxCharsTests(unittest.TestCase):
-    @patch("scripts.docs_to_voice.request_model_studio_audio")
-    def test_probe_extracts_limit_from_api_error(self, mock_request_model_studio_audio):
-        mock_request_model_studio_audio.side_effect = DocsToVoiceError(
-            "Model Studio TTS request failed (HTTP 400): "
-            "InvalidParameter: Range of input length should be [0, 600]"
-        )
-
-        result = probe_api_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-            voice="Cherry",
-        )
-
-        self.assertEqual(result, 600)
-
-    @patch("scripts.docs_to_voice.request_model_studio_audio")
-    def test_probe_returns_none_when_probe_request_succeeds(self, mock_request_model_studio_audio):
-        mock_request_model_studio_audio.return_value = {
-            "audio_url": "https://example.com/audio.wav",
-            "audio_data": "",
-            "audio_format": "wav",
-        }
-
-        result = probe_api_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-            voice="Cherry",
-        )
-
-        self.assertIsNone(result)
-
-
-class DiscoverApiMaxCharsTests(unittest.TestCase):
-    @patch("scripts.docs_to_voice.probe_api_max_chars")
-    @patch("scripts.docs_to_voice.fetch_api_model_max_chars")
-    def test_prefers_catalog_limit(self, mock_fetch_api_model_max_chars, mock_probe_api_max_chars):
-        mock_fetch_api_model_max_chars.return_value = 700
-
-        result = discover_api_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-            voice="Cherry",
-        )
-
-        self.assertEqual(result, 700)
-        mock_probe_api_max_chars.assert_not_called()
-
-    @patch("scripts.docs_to_voice.probe_api_max_chars")
-    @patch("scripts.docs_to_voice.fetch_api_model_max_chars")
-    def test_falls_back_to_probe_limit(self, mock_fetch_api_model_max_chars, mock_probe_api_max_chars):
-        mock_fetch_api_model_max_chars.return_value = None
-        mock_probe_api_max_chars.return_value = 600
-
-        result = discover_api_max_chars(
-            api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-            api_key="test-key",
-            model="qwen3-tts",
-            voice="Cherry",
-        )
-
-        self.assertEqual(result, 600)
-        mock_probe_api_max_chars.assert_called_once()
-
-
-class RequestModelStudioAudioTests(unittest.TestCase):
-    @patch("scripts.docs_to_voice.urllib.request.urlopen")
-    def test_wraps_http_client_disconnect_as_user_error(self, mock_urlopen):
-        mock_urlopen.side_effect = http.client.RemoteDisconnected(
-            "Remote end closed connection without response"
-        )
-
-        with self.assertRaisesRegex(DocsToVoiceError, "Remote end closed connection"):
-            request_model_studio_audio(
-                api_endpoint="https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
-                api_key="test-key",
-                model="qwen3-tts",
-                voice="Cherry",
-                text="test",
-            )
-
-
-if __name__ == "__main__":
-    unittest.main()

package/docs-to-voice/tests/test_docs_to_voice_sentence_timeline.py

@@ -1,115 +0,0 @@
-import json
-import pathlib
-import tempfile
-import unittest
-from unittest.mock import patch
-
-from scripts.docs_to_voice import (
-    DocsToVoiceError,
-    api_text_length_units,
-    split_text_into_api_sentence_requests,
-    write_sentence_timeline_files,
-)
-
-
-class ApiSentenceRequestTests(unittest.TestCase):
-    def test_builds_one_request_per_sentence_by_default(self):
-        source_text = "第一句。第二句！第三句？"
-        sentences, request_items = split_text_into_api_sentence_requests(
-            source_text=source_text,
-            max_chars=None,
-            length_func=api_text_length_units,
-        )
-
-        self.assertEqual(sentences, ["第一句。", "第二句！", "第三句？"])
-        self.assertEqual([item["sentence_index"] for item in request_items], [0, 1, 2])
-        self.assertEqual([item["text"] for item in request_items], sentences)
-
-    def test_splits_oversized_sentence_and_keeps_sentence_index(self):
-        source_text = "測" * 301
-        sentences, request_items = split_text_into_api_sentence_requests(
-            source_text=source_text,
-            max_chars=600,
-            length_func=api_text_length_units,
-        )
-
-        self.assertEqual(sentences, [source_text])
-        self.assertEqual(len(request_items), 2)
-        self.assertEqual([item["sentence_index"] for item in request_items], [0, 0])
-        self.assertEqual(request_items[0]["text"], "測" * 300)
-        self.assertEqual(request_items[1]["text"], "測")
-
-    def test_raises_when_text_is_empty(self):
-        with self.assertRaises(DocsToVoiceError):
-            split_text_into_api_sentence_requests(
-                source_text="   \n",
-                max_chars=600,
-                length_func=api_text_length_units,
-            )
-
-
-class SentenceTimelineTests(unittest.TestCase):
-    def test_uses_sentence_audio_durations_for_timestamp(self):
-        with tempfile.TemporaryDirectory() as temp_dir:
-            temp_dir_path = pathlib.Path(temp_dir)
-            audio_path = temp_dir_path / "voice.wav"
-
-            with patch("scripts.docs_to_voice.read_duration_seconds", return_value=2.0):
-                write_sentence_timeline_files(
-                    source_text="甲。乙。",
-                    audio_path=audio_path,
-                    sentence_durations=[1.2, 0.8],
-                    timing_mode_hint="sentence-audio",
-                )
-
-            timeline_json_path = temp_dir_path / "voice.timeline.json"
-            timeline_payload = json.loads(timeline_json_path.read_text(encoding="utf-8"))
-
-            self.assertEqual(timeline_payload["timing_mode"], "sentence-audio")
-            self.assertEqual(timeline_payload["sentences"][0]["start_ms"], 0)
-            self.assertEqual(timeline_payload["sentences"][0]["end_ms"], 1200)
-            self.assertEqual(timeline_payload["sentences"][1]["start_ms"], 1200)
-            self.assertEqual(timeline_payload["sentences"][1]["end_ms"], 2000)
-
-    def test_scales_sentence_duration_to_match_output_duration(self):
-        with tempfile.TemporaryDirectory() as temp_dir:
-            temp_dir_path = pathlib.Path(temp_dir)
-            audio_path = temp_dir_path / "voice.wav"
-
-            with patch("scripts.docs_to_voice.read_duration_seconds", return_value=4.0):
-                write_sentence_timeline_files(
-                    source_text="甲。乙。",
-                    audio_path=audio_path,
-                    sentence_durations=[1.0, 1.0],
-                    timing_mode_hint="sentence-audio",
-                )
-
-            timeline_json_path = temp_dir_path / "voice.timeline.json"
-            timeline_payload = json.loads(timeline_json_path.read_text(encoding="utf-8"))
-
-            self.assertEqual(timeline_payload["timing_mode"], "sentence-audio")
-            self.assertEqual(timeline_payload["sentences"][0]["end_ms"], 2000)
-            self.assertEqual(timeline_payload["sentences"][1]["end_ms"], 4000)
-
-    def test_falls_back_when_sentence_duration_count_mismatched(self):
-        with tempfile.TemporaryDirectory() as temp_dir:
-            temp_dir_path = pathlib.Path(temp_dir)
-            audio_path = temp_dir_path / "voice.wav"
-
-            with patch("scripts.docs_to_voice.read_duration_seconds", return_value=2.0):
-                write_sentence_timeline_files(
-                    source_text="甲。乙。",
-                    audio_path=audio_path,
-                    sentence_durations=[2.0],
-                    timing_mode_hint="sentence-audio",
-                )
-
-            timeline_json_path = temp_dir_path / "voice.timeline.json"
-            timeline_payload = json.loads(timeline_json_path.read_text(encoding="utf-8"))
-
-            self.assertEqual(timeline_payload["timing_mode"], "duration-weighted")
-            self.assertEqual(timeline_payload["sentences"][1]["end_ms"], 2000)
-
-
-if __name__ == "__main__":
-    unittest.main()

package/docs-to-voice/tests/test_docs_to_voice_settings.py

@@ -1,43 +0,0 @@
-import os
-import unittest
-
-from scripts.docs_to_voice import resolve_setting
-
-
-class ResolveSettingTests(unittest.TestCase):
-    def setUp(self):
-        self.env_key = "DOCS_TO_VOICE_TEST_SETTING"
-        self.previous = os.environ.get(self.env_key)
-        os.environ.pop(self.env_key, None)
-
-    def tearDown(self):
-        os.environ.pop(self.env_key, None)
-        if self.previous is not None:
-            os.environ[self.env_key] = self.previous
-
-    def test_cli_value_has_highest_priority(self):
-        os.environ[self.env_key] = "env-value"
-        result = resolve_setting("cli-value", self.env_key, {"DOCS_TO_VOICE_TEST_SETTING": "file-value"})
-        self.assertEqual(result, "cli-value")
-
-    def test_env_file_has_priority_over_process_env(self):
-        os.environ[self.env_key] = "env-value"
-        result = resolve_setting(None, self.env_key, {"DOCS_TO_VOICE_TEST_SETTING": "file-value"})
-        self.assertEqual(result, "file-value")
-
-    def test_blank_cli_value_falls_back_to_env_file(self):
-        result = resolve_setting("   ", self.env_key, {"DOCS_TO_VOICE_TEST_SETTING": "file-value"})
-        self.assertEqual(result, "file-value")
-
-    def test_process_env_used_when_env_file_missing(self):
-        os.environ[self.env_key] = "env-value"
-        result = resolve_setting(None, self.env_key, {})
-        self.assertEqual(result, "env-value")
-
-    def test_default_used_when_no_source_available(self):
-        result = resolve_setting(None, self.env_key, {}, "default-value")
-        self.assertEqual(result, "default-value")
-
-
-if __name__ == "__main__":
-    unittest.main()

package/docs-to-voice/tests/test_docs_to_voice_shell_wrapper.py

@@ -1,51 +0,0 @@
-#!/usr/bin/env python3
-
-from __future__ import annotations
-
-import json
-import os
-import subprocess
-import sys
-import tempfile
-import unittest
-from pathlib import Path
-
-
-SCRIPT_PATH = Path(__file__).resolve().parents[1] / "scripts" / "docs_to_voice.py"
-SHELL_SCRIPT_PATH = Path(__file__).resolve().parents[1] / "scripts" / "docs_to_voice.sh"
-
-
-class DocsToVoiceShellWrapperTests(unittest.TestCase):
-    def test_shell_wrapper_execs_python_script_with_same_arguments(self) -> None:
-        with tempfile.TemporaryDirectory() as temp_dir:
-            capture_path = Path(temp_dir) / "argv.json"
-            fake_python = Path(temp_dir) / "python3"
-            fake_python.write_text(
-                f"#!{sys.executable}\n"
-                "import json, os, sys\n"
-                "with open(os.environ['CAPTURE_PATH'], 'w', encoding='utf-8') as handle:\n"
-                "    json.dump(sys.argv[1:], handle)\n",
-                encoding="utf-8",
-            )
-            fake_python.chmod(0o755)
-
-            env = dict(os.environ)
-            env["PATH"] = f"{temp_dir}:{env['PATH']}"
-            env["CAPTURE_PATH"] = str(capture_path)
-
-            result = subprocess.run(
-                ["bash", str(SHELL_SCRIPT_PATH), "--input", "notes.md", "--project-dir", "/tmp/project"],
-                capture_output=True,
-                text=True,
-                env=env,
-                check=False,
-            )
-
-            self.assertEqual(result.returncode, 0, result.stderr)
-            argv = json.loads(capture_path.read_text(encoding="utf-8"))
-            self.assertEqual(argv[0], str(SCRIPT_PATH))
-            self.assertEqual(argv[1:], ["--input", "notes.md", "--project-dir", "/tmp/project"])
-
-
-if __name__ == "__main__":
-    unittest.main()

package/docs-to-voice/tests/test_docs_to_voice_speech_rate.py

@@ -1,57 +0,0 @@
-import unittest
-
-from scripts.docs_to_voice import (
-    DocsToVoiceError,
-    build_atempo_filter_chain,
-    scale_sentence_durations,
-    validate_speech_rate,
-)
-
-
-class ValidateSpeechRateTests(unittest.TestCase):
-    def test_accepts_positive_float(self):
-        self.assertEqual(validate_speech_rate("1.25"), 1.25)
-
-    def test_returns_none_for_blank_value(self):
-        self.assertIsNone(validate_speech_rate("   "))
-
-    def test_rejects_non_positive_value(self):
-        with self.assertRaisesRegex(DocsToVoiceError, "--speech-rate"):
-            validate_speech_rate("0")
-
-    def test_rejects_non_numeric_value(self):
-        with self.assertRaisesRegex(DocsToVoiceError, "--speech-rate"):
-            validate_speech_rate("fast")
-
-    def test_rejects_non_finite_values(self):
-        for value in ("nan", "inf", "-inf"):
-            with self.subTest(value=value):
-                with self.assertRaisesRegex(DocsToVoiceError, "--speech-rate"):
-                    validate_speech_rate(value)
-
-
-class BuildAtempoFilterChainTests(unittest.TestCase):
-    def test_builds_single_stage_filter(self):
-        self.assertEqual(build_atempo_filter_chain(1.25), "atempo=1.25")
-
-    def test_builds_multi_stage_filter_for_high_rate(self):
-        self.assertEqual(build_atempo_filter_chain(4.0), "atempo=2.0,atempo=2.0")
-
-    def test_builds_multi_stage_filter_for_low_rate(self):
-        self.assertEqual(build_atempo_filter_chain(0.25), "atempo=0.5,atempo=0.5")
-
-
-class ScaleSentenceDurationsTests(unittest.TestCase):
-    def test_scales_all_sentence_durations(self):
-        self.assertEqual(
-            scale_sentence_durations([1.2, 0.8], 2.0),
-            [0.6, 0.4],
-        )
-
-    def test_returns_original_when_rate_is_one(self):
-        values = [1.2, 0.8]
-        self.assertEqual(scale_sentence_durations(values, 1.0), values)
-
-
-if __name__ == "__main__":
-    unittest.main()