feat: 初始化 doco 子项目 P1 阶段(视频双路拆分预处理)

doco/tests/test_video_split.py

@@ -0,0 +1,141 @@
+# -*- coding: utf-8 -*-
+"""
+video_split 单元测试
+"""
+
+import os
+import json
+from pathlib import Path
+
+import pytest
+
+# 确保 src 在 path 中
+import sys
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from doco.src.video_split import (
+    hamming_distance,
+    format_timestamp,
+    build_b_manuscript,
+    compute_phash,
+)
+
+
+class TestHammingDistance:
+    def test_identical_strings(self):
+        assert hamming_distance("abc", "abc") == 0
+
+    def test_different_strings(self):
+        assert hamming_distance("abc", "abd") == 1
+
+    def test_different_length(self):
+        # 长度不同时,返回较长字符串的长度
+        assert hamming_distance("abc", "ab") == 3
+
+
+class TestFormatTimestamp:
+    def test_zero(self):
+        assert format_timestamp(0) == "0m0s"
+
+    def test_seconds_only(self):
+        assert format_timestamp(30000) == "0m30s"  # 30秒
+
+    def test_minutes_and_seconds(self):
+        assert format_timestamp(90000) == "1m30s"  # 1分30秒
+
+    def test_longer(self):
+        assert format_timestamp(3723000) == "62m3s"  # 62分3秒
+
+
+class TestBuildBManuscript:
+    def test_empty_keyframes(self):
+        lines = build_b_manuscript([])
+        assert lines == []
+
+    def test_single_frame(self):
+        keyframes = [
+            {"timestamp_ms": 0, "ocr_text": "测试字幕"}
+        ]
+        lines = build_b_manuscript(keyframes)
+        assert len(lines) == 1
+        assert "[0m0s]" in lines[0]
+        assert "测试字幕" in lines[0]
+
+    def test_duplicate_text_merged(self):
+        """相邻同文本应合并"""
+        keyframes = [
+            {"timestamp_ms": 0, "ocr_text": "相同"},
+            {"timestamp_ms": 1000, "ocr_text": "相同"},
+            {"timestamp_ms": 2000, "ocr_text": "不同"},
+        ]
+        lines = build_b_manuscript(keyframes)
+        assert len(lines) == 2
+
+    def test_placeholder_skipped(self):
+        """OCR占位文本应跳过"""
+        keyframes = [
+            {"timestamp_ms": 0, "ocr_text": "[OCR待填充 frame=001.png]"},
+            {"timestamp_ms": 1000, "ocr_text": "真实字幕"},
+        ]
+        lines = build_b_manuscript(keyframes)
+        assert len(lines) == 1
+        assert "真实字幕" in lines[0]
+
+
+class TestKeyframesJson:
+    """验证 keyframes.json 输出格式"""
+
+    def test_keyframe_structure(self, tmp_path):
+        """验证单个关键帧的 JSON 结构"""
+        # 模拟关键帧数据
+        kf = {
+            "frame_index": 1,
+            "timestamp_ms": 1000,
+            "frame_image_path": str(tmp_path / "frame_0001.png"),
+            "phash": "ff00aabb12345678",
+            "ocr_text": "测试",
+        }
+
+        # 验证字段存在
+        assert "frame_index" in kf
+        assert "timestamp_ms" in kf
+        assert "frame_image_path" in kf
+        assert "phash" in kf
+        assert "ocr_text" in kf
+
+    def test_keyframes_json_output(self, tmp_path):
+        """验证完整 keyframes.json 输出"""
+        frames_dir = tmp_path / "frames"
+        frames_dir.mkdir()
+
+        # 创建一个测试图片
+        test_img = frames_dir / "frame_0001.png"
+        test_img.write_bytes(b"fake_png_data")
+
+        keyframes_data = {
+            "video_path": str(tmp_path / "video.mp4"),
+            "fps_sampled": 1,
+            "phash_threshold": 8,
+            "keyframes": [
+                {
+                    "frame_index": 0,
+                    "timestamp_ms": 0,
+                    "frame_image_path": str(test_img),
+                    "phash": "abcd1234",
+                    "ocr_text": "首帧",
+                }
+            ]
+        }
+
+        json_path = tmp_path / "keyframes.json"
+        with open(json_path, "w", encoding="utf-8") as f:
+            json.dump(keyframes_data, f, ensure_ascii=False, indent=2)
+
+        # 验证可读
+        with open(json_path, "r", encoding="utf-8") as f:
+            loaded = json.load(f)
+
+        assert loaded["fps_sampled"] == 1
+        assert loaded["phash_threshold"] == 8
+        assert len(loaded["keyframes"]) == 1
+        assert loaded["keyframes"][0]["frame_index"] == 0