예제 #1
0
def test_deduplicate():
    directory = tempfile.TemporaryDirectory()
    original = testing.DEFAULT_TEST_IMAGES[0]
    duplicate = os.path.join(directory.name, 'image1.jpg')
    shutil.copy(original, duplicate)
    pairs = tools.deduplicate(files=[
        testing.DEFAULT_TEST_IMAGES[0], testing.DEFAULT_TEST_IMAGES[1],
        duplicate
    ],
                              hashers=[(hashers.PHash(hash_size=16), 0.25)])
    assert len(pairs) == 1
    file1, file2 = pairs[0]
    assert ((file1 == duplicate) and
            (file2 == original)) or ((file1 == original) and
                                     (file2 == duplicate))
예제 #2
0
def test_deduplicate_u8():
    # This test verifies that extensions.compute_euclidean_pairwise_duplicates
    # works properly.
    directory = tempfile.TemporaryDirectory()
    original = testing.DEFAULT_TEST_IMAGES[0]
    duplicate = os.path.join(directory.name, 'image1.jpg')
    shutil.copy(original, duplicate)
    pairs = tools.deduplicate(files=[
        testing.DEFAULT_TEST_IMAGES[0], testing.DEFAULT_TEST_IMAGES[1],
        duplicate
    ],
                              hashers=[(hashers.PHashU8(hash_size=16), 10)])
    assert len(pairs) == 1
    file1, file2 = pairs[0]
    assert ((file1 == duplicate) and
            (file2 == original)) or ((file1 == original) and
                                     (file2 == duplicate))
예제 #3
0
파일: db.py 프로젝트: zeebalogun/red-alert
def is_img_suspicious(img):
    duplicate_pairs = tools.deduplicate(files=filepaths,
                                        hashers=[(hashers.PHash(hash_size=16),
                                                  0.2)])
    print(duplicate_pairs)