feat: テンプレート選定・依存チェックヘルパーを追加

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

PythonProj/ScanOCR/スクリプト/extract_and_rename.py

@@ -30,6 +30,44 @@ from box_detector import detect_template_fields, to_ratio_box
 
 DPI = 300  # PDF→画像変換の解像度。テンプレートも同じDPIで作成/スキャンしてください
 
+import importlib
+
+TEMPLATE_EXTENSIONS = {".png", ".jpg", ".jpeg", ".bmp"}
+
+
+def select_template_file(template_dir: Path) -> Path:
+    candidates = sorted(
+        p for p in template_dir.iterdir()
+        if p.is_file() and p.suffix.lower() in TEMPLATE_EXTENSIONS
+    )
+    if not candidates:
+        raise FileNotFoundError(
+            f"テンプレートフォルダに画像ファイルが見つかりません: {template_dir}"
+        )
+    return candidates[0]
+
+
+REQUIRED_MODULES = ("cv2", "numpy", "PIL", "pytesseract", "pdf2image")
+
+
+def check_dependencies(modules: tuple[str, ...] = REQUIRED_MODULES) -> list[str]:
+    missing = []
+    for mod in modules:
+        try:
+            importlib.import_module(mod)
+        except ImportError:
+            missing.append(mod)
+    return missing
+
+
+def check_external_tools(tesseract_exe: Path, poppler_exe: Path) -> list[str]:
+    missing = []
+    if not tesseract_exe.exists():
+        missing.append(str(tesseract_exe))
+    if not poppler_exe.exists():
+        missing.append(str(poppler_exe))
+    return missing
+
 
 @dataclass
 class FieldBox:

PythonProj/ScanOCR/スクリプト/tests/test_extract_and_rename.py

@@ -0,0 +1,58 @@
+from pathlib import Path
+
+from extract_and_rename import (
+    check_dependencies,
+    check_external_tools,
+    select_template_file,
+)
+
+
+def test_select_template_file_picks_first_by_name(tmp_path):
+    (tmp_path / "b_template.png").write_bytes(b"x")
+    (tmp_path / "a_template.png").write_bytes(b"x")
+    (tmp_path / "note.txt").write_bytes(b"x")  # 対象外拡張子
+
+    result = select_template_file(tmp_path)
+
+    assert result == tmp_path / "a_template.png"
+
+
+def test_select_template_file_no_candidates_raises(tmp_path):
+    (tmp_path / "note.txt").write_bytes(b"x")
+
+    try:
+        select_template_file(tmp_path)
+        assert False, "FileNotFoundErrorが送出されるべき"
+    except FileNotFoundError:
+        pass
+
+
+def test_check_dependencies_detects_missing_module():
+    result = check_dependencies(("this_module_does_not_exist_xyz",))
+    assert result == ["this_module_does_not_exist_xyz"]
+
+
+def test_check_dependencies_detects_installed_module():
+    result = check_dependencies(("os",))
+    assert result == []
+
+
+def test_check_external_tools_detects_missing(tmp_path):
+    tesseract = tmp_path / "tools" / "tesseract" / "tesseract.exe"
+    poppler = tmp_path / "tools" / "poppler" / "pdftoppm.exe"
+
+    result = check_external_tools(tesseract, poppler)
+
+    assert str(tesseract) in result
+    assert str(poppler) in result
+
+
+def test_check_external_tools_all_present(tmp_path):
+    tesseract = tmp_path / "tesseract.exe"
+    poppler = tmp_path / "pdftoppm.exe"
+    tesseract.write_bytes(b"x")
+    poppler.write_bytes(b"x")
+
+    result = check_external_tools(tesseract, poppler)
+
+    assert result == []