feat(video_analysis): ocr_frames.py with TDD (4 tests, winsdk + tesseract backends)

tests/test_video_analysis_ocr_frames.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import patch
+
+from scripts.video_analysis.ocr_frames import (
+ format_ocr_markdown,
+ list_frame_files,
+ ocr_frames,
+)
+
+
+def test_list_frame_files_returns_sorted(tmp_path: Path) -> None:
+ (tmp_path / "frame_00001.jpg").write_bytes(b"x")
+ (tmp_path / "frame_00002.jpg").write_bytes(b"x")
+ (tmp_path / "frame_00010.jpg").write_bytes(b"x")
+ (tmp_path / "ignored.txt").write_bytes(b"x")
+ files = list_frame_files(tmp_path)
+ assert len(files) == 3
+ assert files[0].name == "frame_00001.jpg"
+ assert files[2].name == "frame_00010.jpg"
+
+
+def test_format_ocr_markdown_empty() -> None:
+ out = format_ocr_markdown([])
+ assert "# OCR Results" in out
+
+
+def test_format_ocr_markdown_with_frames() -> None:
+ frames = [("frame_00001.jpg", "Hello world", "2026-06-21T00:00:00Z")]
+ out = format_ocr_markdown(frames)
+ assert "frame_00001.jpg" in out
+ assert "Hello world" in out
+
+
+def test_ocr_frames_calls_backend(tmp_path: Path) -> None:
+ (tmp_path / "frame_00001.jpg").write_bytes(b"fake-jpg-bytes")
+ with patch("scripts.video_analysis.ocr_frames._ocr_single_image") as mock_ocr:
+  mock_ocr.return_value = ("extracted text", 0.95)
+  result = ocr_frames(tmp_path, tmp_path / "ocr.md", backend="tesseract")
+  assert result.is_ok()
+  assert (tmp_path / "ocr.md").exists()