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

from pathlib import Path

from extract_and_rename import (
    check_dependencies,
    check_external_tools,
    run_queue,
    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 == []


def _make_dirs(tmp_path):
    dirs = {
        "scan": tmp_path / "スキャン",
        "output": tmp_path / "アウトプット",
        "success": tmp_path / "成功",
        "failed": tmp_path / "失敗",
        "log": tmp_path / "ログ",
    }
    dirs["scan"].mkdir()
    return dirs


def test_run_queue_success_moves_and_copies(tmp_path):
    dirs = _make_dirs(tmp_path)
    pdf = dirs["scan"] / "scan001.pdf"
    pdf.write_bytes(b"dummy")

    def fake_process_pdf(path, boxes, margin):
        return ("氏名A", "20260802")

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=fake_process_pdf,
        key_check=lambda: False,
        sleep_func=lambda s: None,
    )

    assert (dirs["output"] / "氏名A" / "氏名A_20260802.pdf").exists()
    assert (dirs["success"] / "scan001.pdf").exists()
    assert not pdf.exists()

    from datetime import datetime
    log_content = (dirs["log"] / f"{datetime.now().strftime('%Y-%m-%d')}.log").read_text(encoding="utf-8-sig")
    assert "結果=成功" in log_content


def test_run_queue_missing_name_moves_to_failed(tmp_path):
    dirs = _make_dirs(tmp_path)
    pdf = dirs["scan"] / "scan002.pdf"
    pdf.write_bytes(b"dummy")

    def fake_process_pdf(path, boxes, margin):
        return (None, "20260802")

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=fake_process_pdf,
        key_check=lambda: False,
        sleep_func=lambda s: None,
    )

    assert (dirs["failed"] / "scan002.pdf").exists()
    assert not pdf.exists()


def test_run_queue_exception_moves_to_failed(tmp_path):
    dirs = _make_dirs(tmp_path)
    pdf = dirs["scan"] / "scan003.pdf"
    pdf.write_bytes(b"dummy")

    def fake_process_pdf(path, boxes, margin):
        raise RuntimeError("OCRエラー")

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=fake_process_pdf,
        key_check=lambda: False,
        sleep_func=lambda s: None,
    )

    assert (dirs["failed"] / "scan003.pdf").exists()


def test_run_queue_stops_on_key_press(tmp_path):
    dirs = _make_dirs(tmp_path)
    pdf = dirs["scan"] / "scan004.pdf"
    pdf.write_bytes(b"dummy")

    calls = []

    def fake_process_pdf(path, boxes, margin):
        calls.append(path)
        return ("氏名A", "20260802")

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=fake_process_pdf,
        key_check=lambda: True,  # 常に押下扱い
        sleep_func=lambda s: None,
    )

    assert calls == []
    assert pdf.exists()  # 処理されず残る


def test_run_queue_skips_file_deleted_before_processing(tmp_path):
    dirs = _make_dirs(tmp_path)
    pdf = dirs["scan"] / "scan005.pdf"
    pdf.write_bytes(b"dummy")

    calls = []

    def fake_process_pdf(path, boxes, margin):
        calls.append(path)
        return ("氏名A", "20260802")

    def key_check_and_delete():
        if pdf.exists():
            pdf.unlink()
        return False

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=fake_process_pdf,
        key_check=key_check_and_delete,
        sleep_func=lambda s: None,
    )

    assert calls == []


def test_run_queue_empty_scan_dir_returns_immediately(tmp_path):
    dirs = _make_dirs(tmp_path)

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=lambda p, b, m: ("氏名A", "20260802"),
        key_check=lambda: False,
        sleep_func=lambda s: None,
    )
    # 例外が出ずに戻ることのみ確認


def test_run_queue_name_collision_gets_suffix(tmp_path):
    dirs = _make_dirs(tmp_path)
    existing_output_dir = dirs["output"] / "氏名A"
    existing_output_dir.mkdir(parents=True)
    (existing_output_dir / "氏名A_20260802.pdf").write_bytes(b"old")

    pdf = dirs["scan"] / "scan006.pdf"
    pdf.write_bytes(b"dummy")

    run_queue(
        dirs["scan"], dirs["output"], dirs["success"], dirs["failed"], dirs["log"],
        boxes=[], margin=0.1, stable_wait_sec=0, stable_retries=1,
        process_pdf_func=lambda p, b, m: ("氏名A", "20260802"),
        key_check=lambda: False,
        sleep_func=lambda s: None,
    )

    assert (existing_output_dir / "氏名A_20260802(2).pdf").exists()