style: fix black formatting

- dedup: hamming_distance汉明距离(8种场景) + VideoFingerprint数据结构 + _average_histogram_similarity直方图相似度(10种边界)
- render_subtitles: 颜色转换/位置映射/样式构建/文本转义/时间格式化 + generate_ass_subtitles文件生成(12种场景)
- tts_engine: VoiceoverSegment/VoiceoverResult数据结构 + generate_full_voiceover边界(7种) + generate_subtitle_voiceover边界(3种)
+73 tests 全绿

tests/unit/test_dedup_pure.py

@@ -0,0 +1,164 @@
+"""去重纯算法测试 — hamming_distance + histogram_similarity + VideoFingerprint."""
+
+from __future__ import annotations
+
+import sys
+from unittest.mock import MagicMock
+
+import numpy as np
+import pytest
+
+# 模块级mock cv2（dedup模块import时需要）
+sys.modules["cv2"] = MagicMock()
+
+from video_processing.dedup import (  # noqa: E402
+    VideoDeduplicator,
+    VideoFingerprint,
+    hamming_distance,
+)
+
+
+class TestHammingDistance:
+    """hamming_distance 汉明距离计算测试."""
+
+    def test_identical_hashes_zero(self):
+        """相同哈希距离为0."""
+        assert hamming_distance("ff", "ff") == 0
+        assert hamming_distance("00", "00") == 0
+
+    def test_all_different(self):
+        """全不同的8bit哈希距离为8."""
+        assert hamming_distance("00", "ff") == 8
+
+    def test_single_bit_diff(self):
+        """1个bit不同."""
+        # 0x01 = 00000001, 0x00 = 00000000 → 1 bit不同
+        assert hamming_distance("01", "00") == 1
+
+    def test_four_bits_diff(self):
+        """4个bit不同."""
+        # 0x0F = 00001111, 0xF0 = 11110000 → 8 bits都不同
+        assert hamming_distance("0f", "f0") == 8
+
+    def test_longer_hashes(self):
+        """更长的哈希（如64-bit pHash）."""
+        # 两个完全不同的64-bit哈希
+        assert hamming_distance("0000000000000000", "ffffffffffffffff") == 64
+
+    def test_partial_difference(self):
+        """部分bit不同."""
+        # a = 1010, 5 = 0101 → 4 bits不同（每个hex digit）
+        assert hamming_distance("aa", "55") == 8
+
+    def test_case_insensitive(self):
+        """十六进制不区分大小写."""
+        assert hamming_distance("FF", "ff") == 0
+        assert hamming_distance("AbC123", "aBc123") == 0
+
+    def test_different_length_hashes(self):
+        """不同长度的哈希（短的前补零）."""
+        # "ff" = 0xff = 255, "0ff" = 0x0ff = 255
+        # int("ff", 16) = 255, int("0ff", 16) = 255
+        assert hamming_distance("ff", "0ff") == 0
+
+
+class TestVideoFingerprint:
+    """VideoFingerprint 数据结构测试."""
+
+    def test_to_dict_contains_all_fields(self):
+        """to_dict返回完整字典."""
+        fp = VideoFingerprint(
+            md5="abc123",
+            keyframe_phashes=["hash1", "hash2"],
+            color_histograms=[[0.1, 0.2], [0.3, 0.4]],
+            duration=30.5,
+            resolution=(1920, 1080),
+        )
+        d = fp.to_dict()
+        assert d["md5"] == "abc123"
+        assert d["keyframe_phashes"] == ["hash1", "hash2"]
+        assert d["duration"] == 30.5
+        assert d["resolution"] == [1920, 1080]
+        assert "color_histograms" in d
+
+    def test_empty_phashes(self):
+        """空关键帧列表."""
+        fp = VideoFingerprint(
+            md5="test",
+            keyframe_phashes=[],
+            color_histograms=[],
+            duration=0.0,
+            resolution=(0, 0),
+        )
+        d = fp.to_dict()
+        assert d["keyframe_phashes"] == []
+        assert d["color_histograms"] == []
+
+
+class TestAverageHistogramSimilarity:
+    """_average_histogram_similarity 直方图相似度测试."""
+
+    def test_identical_histograms(self):
+        """完全相同的直方图相似度为1.0."""
+        hist = [[0.5, 0.5, 0.0], [0.3, 0.4, 0.3]]
+        sim = VideoDeduplicator._average_histogram_similarity(hist, hist)
+        assert sim == pytest.approx(1.0)
+
+    def test_empty_first_list(self):
+        """第一组为空返回0."""
+        sim = VideoDeduplicator._average_histogram_similarity([], [[0.5, 0.5]])
+        assert sim == 0.0
+
+    def test_empty_second_list(self):
+        """第二组为空返回0."""
+        sim = VideoDeduplicator._average_histogram_similarity([[0.5, 0.5]], [])
+        assert sim == 0.0
+
+    def test_both_empty(self):
+        """两组都为空返回0."""
+        sim = VideoDeduplicator._average_histogram_similarity([], [])
+        assert sim == 0.0
+
+    def test_orthogonal_histograms(self):
+        """正交直方图相似度为0."""
+        # [1, 0] 和 [0, 1] 正交
+        sim = VideoDeduplicator._average_histogram_similarity([[1.0, 0.0]], [[0.0, 1.0]])
+        assert sim == pytest.approx(0.0)
+
+    def test_partial_similarity(self):
+        """部分相似."""
+        # [1, 1] 和 [1, 0] 的余弦相似度 = 1/√2 ≈ 0.707
+        sim = VideoDeduplicator._average_histogram_similarity([[1.0, 1.0]], [[1.0, 0.0]])
+        assert sim == pytest.approx(1.0 / (2**0.5), rel=0.01)
+
+    def test_multiple_frames_best_match(self):
+        """多帧时取最佳匹配."""
+        # 第一帧完全不同，第二帧完全相同 → 平均 best = (0 + 1) / 2 = 0.5
+        sim = VideoDeduplicator._average_histogram_similarity(
+            [[1.0, 0.0], [0.0, 1.0]],
+            [[0.0, 1.0]],  # 只有一帧，和第一帧0相似，和第二帧1相似
+        )
+        # 第一帧最佳匹配=0，第二帧最佳匹配=1，平均=0.5
+        assert sim == pytest.approx(0.5)
+
+    def test_zero_norm_histogram_skipped(self):
+        """零范数直方图被跳过."""
+        sim = VideoDeduplicator._average_histogram_similarity([[0.0, 0.0]], [[1.0, 1.0]])
+        # 第一组的零范数被跳过，similarities为空，返回0
+        assert sim == 0.0
+
+    def test_different_length_histograms(self):
+        """不同长度的直方图取最小长度对齐."""
+        sim = VideoDeduplicator._average_histogram_similarity(
+            [[1.0, 1.0, 0.0, 0.0]],  # 4维
+            [[1.0, 1.0]],  # 2维
+        )
+        # 对齐到前2维，都是[1,1]，相似度1.0
+        assert sim == pytest.approx(1.0)
+
+    def test_similarity_in_zero_one_range(self):
+        """相似度在[0, 1]范围内."""
+        hist_a = [np.random.rand(96).tolist() for _ in range(5)]
+        hist_b = [np.random.rand(96).tolist() for _ in range(5)]
+        sim = VideoDeduplicator._average_histogram_similarity(hist_a, hist_b)
+        assert 0.0 <= sim <= 1.0

tests/unit/test_render_subtitles_pure.py

@@ -0,0 +1,310 @@
+"""字幕渲染纯函数测试 — _build_ass_style + generate_ass_subtitles."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+from video_processing.render_subtitles import (
+    _build_ass_style,
+    _escape_ass_text,
+    _format_ass_time,
+    _hex_to_ass_color,
+    _position_to_ass_alignment,
+    generate_ass_subtitles,
+)
+
+
+class TestHexToAssColor:
+    """_hex_to_ass_color 颜色转换测试."""
+
+    def test_white(self):
+        """白色 #FFFFFF → &HFFFFFF (ASS BGR格式)."""
+        assert _hex_to_ass_color("#FFFFFF") == "&HFFFFFF"
+
+    def test_black(self):
+        """黑色 #000000 → &H000000."""
+        assert _hex_to_ass_color("#000000") == "&H000000"
+
+    def test_red(self):
+        """红色 #FF0000 → ASS是BGR顺序 → &H0000FF."""
+        assert _hex_to_ass_color("#FF0000") == "&H0000FF"
+
+    def test_blue(self):
+        """蓝色 #0000FF → BGR → &HFF0000."""
+        assert _hex_to_ass_color("#0000FF") == "&HFF0000"
+
+    def test_green(self):
+        """绿色 #00FF00 → BGR → &H00FF00."""
+        assert _hex_to_ass_color("#00FF00") == "&H00FF00"
+
+    def test_lowercase(self):
+        """小写hex也支持."""
+        assert _hex_to_ass_color("#ff0000") == "&H0000FF"
+
+    def test_no_hash_prefix(self):
+        """不带#的颜色."""
+        assert _hex_to_ass_color("FF0000") == "&H0000FF"
+
+    def test_invalid_length_fallback(self):
+        """长度不对返回默认黑色."""
+        assert _hex_to_ass_color("#FFF") == "&H000000"
+
+
+class TestPositionToAssAlignment:
+    """_position_to_ass_alignment 位置映射测试."""
+
+    def test_top_center(self):
+        """top → 上中(8)."""
+        assert _position_to_ass_alignment("top") == 8
+
+    def test_bottom_center(self):
+        """bottom → 下中(2)."""
+        assert _position_to_ass_alignment("bottom") == 2
+
+    def test_center_middle(self):
+        """center → 居中(5)."""
+        assert _position_to_ass_alignment("center") == 5
+
+    def test_unknown_defaults_to_top(self):
+        """未知位置默认顶部(8)."""
+        assert _position_to_ass_alignment("unknown") == 8
+        assert _position_to_ass_alignment("top_left") == 8
+        assert _position_to_ass_alignment("bottom_right") == 8
+
+    def test_empty_string_defaults_to_top(self):
+        """空字符串默认顶部."""
+        assert _position_to_ass_alignment("") == 8
+
+
+class TestBuildAssStyle:
+    """_build_ass_style ASS样式行构建测试."""
+
+    def test_basic_style_line(self):
+        """基本样式行包含关键字段."""
+        line = _build_ass_style("Default")
+        assert line.startswith("Style: Default,")
+        assert "思源黑体" in line
+        assert "48" in line  # font_size
+
+    def test_bold_enabled(self):
+        """加粗时Bold=-1."""
+        line = _build_ass_style("Bold", bold=True)
+        assert "Style: Bold," in line
+        # Bold字段位置：第7个逗号分隔字段=Bold=-1
+        parts = line.split(",")
+        # Name, Fontname, Fontsize, Primary, Secondary, Outline, Back, Bold, ...
+        assert parts[7] == "-1"  # Bold
+
+    def test_bold_disabled(self):
+        """不加粗时Bold=0."""
+        line = _build_ass_style("Normal", bold=False)
+        parts = line.split(",")
+        assert parts[7] == "0"
+
+    def test_italic_enabled(self):
+        """斜体时Italic=-1."""
+        line = _build_ass_style("Italic", italic=True)
+        parts = line.split(",")
+        assert parts[8] == "-1"  # Italic
+
+    def test_custom_font_size(self):
+        """自定义字号."""
+        line = _build_ass_style("Big", font_size=72)
+        parts = line.split(",")
+        assert parts[2] == "72"  # Fontsize
+
+    def test_custom_alignment(self):
+        """自定义对齐方式."""
+        line = _build_ass_style("Bottom", alignment=2)
+        # Alignment是第16个字段（数一下）
+        # Name, Fontname, Fontsize, Primary, Secondary, Outline, Back, Bold, Italic, Underline, Strikeout, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, ...
+        parts = line.split(",")
+        assert parts[18] == "2"  # Alignment (0-indexed: 18)
+
+    def test_outline_width(self):
+        """描边宽度."""
+        line = _build_ass_style("Outline", outline_width=3.0)
+        parts = line.split(",")
+        assert parts[16] == "3.0"  # Outline (BorderStyle后是Outline)
+
+
+class TestEscapeAssText:
+    """_escape_ass_text 文本转义测试."""
+
+    def test_plain_text_unchanged(self):
+        """普通文本不变."""
+        assert _escape_ass_text("hello world") == "hello world"
+
+    def test_newline_converted(self):
+        """换行符转成\\N."""
+        assert _escape_ass_text("line1\nline2") == "line1\\Nline2"
+
+    def test_crlf_converted(self):
+        """CRLF转成\\N."""
+        assert _escape_ass_text("a\r\nb") == "a\\Nb"
+
+    def test_carriage_return_converted(self):
+        """纯\\r转成\\N."""
+        assert _escape_ass_text("a\rb") == "a\\Nb"
+
+    def test_curly_braces_replaced(self):
+        """大括号转成圆括号（防止ASS样式注入）."""
+        assert _escape_ass_text("{text}") == "(text)"
+
+    def test_mixed_special_chars(self):
+        """混合特殊字符."""
+        result = _escape_ass_text("line1\nline2 {bold}\rlast")
+        assert "line1\\Nline2 (bold)\\Nlast" == result
+
+
+class TestFormatAssTime:
+    """_format_ass_time 时间格式化测试."""
+
+    def test_zero_seconds(self):
+        """0秒."""
+        assert _format_ass_time(0) == "0:00:00.00"
+
+    def test_seconds_only(self):
+        """只有秒."""
+        assert _format_ass_time(5.5) == "0:00:05.50"
+
+    def test_minutes_and_seconds(self):
+        """几分几秒."""
+        assert _format_ass_time(65.25) == "0:01:05.25"
+
+    def test_hours(self):
+        """几小时."""
+        assert _format_ass_time(3661.5) == "1:01:01.50"
+
+    def test_always_two_decimal_places(self):
+        """总是两位小数."""
+        assert _format_ass_time(1.0) == "0:00:01.00"
+        assert _format_ass_time(1.1) == "0:00:01.10"
+
+
+class TestGenerateAssSubtitles:
+    """generate_ass_subtitles ASS字幕文件生成测试."""
+
+    def test_no_subtitles_empty_file(self, tmp_path):
+        """没有字幕生成空文件."""
+        output = tmp_path / "empty.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=10.0,
+        )
+        assert result == output
+        assert output.exists()
+        assert output.read_text(encoding="utf-8") == ""
+
+    def test_title_only(self, tmp_path):
+        """只有标题."""
+        output = tmp_path / "title.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=30.0,
+            title_text="测试标题",
+        )
+        assert result == output
+        content = output.read_text(encoding="utf-8")
+        assert "Script Info" in content
+        assert "PlayResX: 1080" in content
+        assert "PlayResY: 1920" in content
+        assert "测试标题" in content
+        assert "V4+ Styles" in content
+        assert "Events" in content
+
+    def test_subtitle_only(self, tmp_path):
+        """只有底部字幕."""
+        output = tmp_path / "sub.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=15.0,
+            subtitle_text="这是字幕",
+        )
+        assert result == output
+        content = output.read_text(encoding="utf-8")
+        assert "这是字幕" in content
+        assert "PlayResX: 1080" in content
+
+    def test_both_title_and_subtitle(self, tmp_path):
+        """标题+字幕都有."""
+        output = tmp_path / "both.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=720,
+            video_height=1280,
+            video_duration=20.0,
+            title_text="大标题",
+            subtitle_text="底部字幕",
+        )
+        content = output.read_text(encoding="utf-8")
+        assert "大标题" in content
+        assert "底部字幕" in content
+        # 应该有两种样式（title和subtitle）
+        assert content.count("Style:") >= 2
+
+    def test_title_disabled_by_config(self, tmp_path):
+        """通过config禁用标题."""
+        output = tmp_path / "disabled_title.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=10.0,
+            title_text="标题",
+            title_config={"enabled": False},
+            subtitle_text="字幕",
+        )
+        content = output.read_text(encoding="utf-8")
+        assert "标题" not in content
+        assert "字幕" in content
+
+    def test_empty_title_text_not_rendered(self, tmp_path):
+        """空标题文本不渲染."""
+        output = tmp_path / "empty_title.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=10.0,
+            title_text="   ",
+            subtitle_text="有字幕",
+        )
+        content = output.read_text(encoding="utf-8")
+        assert "有字幕" in content
+
+    def test_custom_title_color(self, tmp_path):
+        """自定义标题颜色."""
+        output = tmp_path / "color.ass"
+        result = generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=10.0,
+            title_text="红色标题",
+            title_config={"color": "#FF0000"},
+        )
+        content = output.read_text(encoding="utf-8")
+        # 红色 → ASS BGR格式 &H0000FF
+        assert "&H0000FF" in content
+
+    def test_dialogue_line_format(self, tmp_path):
+        """Dialogue行格式正确."""
+        output = tmp_path / "dialogue.ass"
+        generate_ass_subtitles(
+            output,
+            video_width=1080,
+            video_height=1920,
+            video_duration=5.0,
+            subtitle_text="测试字幕文本",
+        )
+        content = output.read_text(encoding="utf-8")
+        assert "Dialogue:" in content
+        assert "测试字幕文本" in content

tests/unit/test_tts_engine_pure.py

@@ -0,0 +1,184 @@
+"""TTS配音引擎纯逻辑测试 — 数据结构 + 边界情况（mock TTS服务）."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import MagicMock
+
+import pytest
+from video_processing.tts_engine import (
+    TtsEngine,
+    VoiceoverResult,
+    VoiceoverSegment,
+)
+
+from packages.domain.tts_config import TtsConfig
+from packages.ports.tts_service import TtsError
+
+
+class TestVoiceoverSegment:
+    """VoiceoverSegment 数据结构测试."""
+
+    def test_default_values(self):
+        """默认值正确."""
+        seg = VoiceoverSegment(text="你好")
+        assert seg.text == "你好"
+        assert seg.start_time == 0.0
+        assert seg.end_time == 0.0
+        assert seg.audio_path is None
+        assert seg.duration == 0.0
+
+    def test_full_values(self):
+        """完整字段."""
+        seg = VoiceoverSegment(
+            text="测试",
+            start_time=1.5,
+            end_time=3.5,
+            audio_path=Path("/tmp/test.wav"),
+            duration=2.0,
+        )
+        assert seg.text == "测试"
+        assert seg.start_time == 1.5
+        assert seg.end_time == 3.5
+        assert seg.audio_path == Path("/tmp/test.wav")
+        assert seg.duration == 2.0
+
+
+class TestVoiceoverResult:
+    """VoiceoverResult 数据结构测试."""
+
+    def test_failure_default(self):
+        """失败结果默认值."""
+        result = VoiceoverResult(success=False)
+        assert result.success is False
+        assert result.segments == []
+        assert result.total_duration == 0.0
+        assert result.error_message == ""
+
+    def test_success_with_segments(self):
+        """成功结果带片段."""
+        seg = VoiceoverSegment(text="hi", duration=5.0)
+        result = VoiceoverResult(
+            success=True,
+            segments=[seg],
+            total_duration=5.0,
+        )
+        assert result.success is True
+        assert len(result.segments) == 1
+        assert result.total_duration == 5.0
+
+    def test_failure_with_message(self):
+        """失败带错误信息."""
+        result = VoiceoverResult(success=False, error_message="TTS出错")
+        assert result.success is False
+        assert result.error_message == "TTS出错"
+
+
+class TestTtsEngineFullVoiceover:
+    """TtsEngine.generate_full_voiceover 整段配音测试（mock TTS）."""
+
+    def _make_engine(self, tmp_path: Path, tts: MagicMock | None = None) -> TtsEngine:
+        """创建测试用TtsEngine."""
+        if tts is None:
+            tts = MagicMock()
+            tts.synthesize.return_value = str(tmp_path / "out.wav")
+        return TtsEngine(tts_service=tts, work_dir=tmp_path)
+
+    def test_disabled_returns_failure(self, tmp_path):
+        """配音未启用→失败."""
+        engine = self._make_engine(tmp_path)
+        config = TtsConfig(enabled=False, text="测试")
+        result = engine.generate_full_voiceover(config)
+        assert result.success is False
+        assert "未启用" in result.error_message
+        assert len(result.segments) == 0
+
+    def test_empty_text_returns_failure(self, tmp_path):
+        """文本为空→失败."""
+        engine = self._make_engine(tmp_path)
+        config = TtsConfig(enabled=True, text="   ")
+        result = engine.generate_full_voiceover(config)
+        assert result.success is False
+        assert "文本为空" in result.error_message
+
+    def test_success_creates_segment(self, tmp_path):
+        """成功合成返回正确结构."""
+        mock_tts = MagicMock()
+        output_file = tmp_path / "voiceover_full.wav"
+        output_file.write_bytes(b"fake audio")
+        mock_tts.synthesize.return_value = str(output_file)
+
+        engine = self._make_engine(tmp_path, mock_tts)
+        config = TtsConfig(enabled=True, text="测试文本", voice_id="female_warm", speed=1.0)
+
+        result = engine.generate_full_voiceover(config)
+
+        assert result.success is True
+        assert len(result.segments) == 1
+        assert result.segments[0].text == "测试文本"
+        assert result.segments[0].start_time == 0.0
+        assert result.total_duration > 0
+        mock_tts.synthesize.assert_called_once()
+
+    def test_tts_error_returns_failure_gracefully(self, tmp_path):
+        """TTS抛错→优雅降级返回失败."""
+        mock_tts = MagicMock()
+        mock_tts.synthesize.side_effect = TtsError("合成失败")
+
+        engine = self._make_engine(tmp_path, mock_tts)
+        config = TtsConfig(enabled=True, text="测试")
+
+        result = engine.generate_full_voiceover(config)
+        assert result.success is False
+        assert "合成失败" in result.error_message
+
+    def test_generic_exception_returns_failure(self, tmp_path):
+        """其他异常也降级返回失败."""
+        mock_tts = MagicMock()
+        mock_tts.synthesize.side_effect = RuntimeError("未知错误")
+
+        engine = self._make_engine(tmp_path, mock_tts)
+        config = TtsConfig(enabled=True, text="测试")
+
+        result = engine.generate_full_voiceover(config)
+        assert result.success is False
+        assert "未知错误" in result.error_message
+
+    def test_work_dir_created(self, tmp_path):
+        """工作目录自动创建."""
+        new_dir = tmp_path / "nested" / "tts"
+        mock_tts = MagicMock()
+        TtsEngine(tts_service=mock_tts, work_dir=new_dir)
+        assert new_dir.exists()
+
+
+class TestTtsEngineSubtitleVoiceover:
+    """TtsEngine.generate_subtitle_voiceover 字幕配音测试（mock TTS）."""
+
+    def _make_engine(self, tmp_path: Path, tts: MagicMock | None = None) -> TtsEngine:
+        if tts is None:
+            tts = MagicMock()
+        return TtsEngine(tts_service=tts, work_dir=tmp_path)
+
+    def test_disabled_returns_failure(self, tmp_path):
+        """配音未启用→失败."""
+        engine = self._make_engine(tmp_path)
+        config = TtsConfig(enabled=False, text="")
+        result = engine.generate_subtitle_voiceover(config, [{"text": "hi", "start_time": 0, "end_time": 1}])
+        assert result.success is False
+        assert "未启用" in result.error_message
+
+    def test_empty_subtitles_returns_failure(self, tmp_path):
+        """字幕列表为空→失败."""
+        engine = self._make_engine(tmp_path)
+        config = TtsConfig(enabled=True, text="")
+        result = engine.generate_subtitle_voiceover(config, [])
+        assert result.success is False
+        assert "字幕为空" in result.error_message
+
+    def test_none_subtitles_returns_failure(self, tmp_path):
+        """None字幕也失败."""
+        engine = self._make_engine(tmp_path)
+        config = TtsConfig(enabled=True, text="")
+        result = engine.generate_subtitle_voiceover(config, None)  # type: ignore
+        assert result.success is False