Add more tests.

poetry.lock

@@ -172,18 +172,18 @@ lxml = ["lxml"]
 
 [[package]]
 name = "boto3"
-version = "1.36.17"
+version = "1.36.19"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "boto3-1.36.17-py3-none-any.whl", hash = "sha256:59bcf0c4b04d9cc36f8b418ad17ab3c4a99a21a175d2fad7096aa21cbe84630b"},
-    {file = "boto3-1.36.17.tar.gz", hash = "sha256:5ecae20e780a3ce9afb3add532b61c466a8cb8960618e4fa565b3883064c1346"},
+    {file = "boto3-1.36.19-py3-none-any.whl", hash = "sha256:7784590369a9d545bb07b2de56b6ce4d5a5e232883a957f704c3f842caeba155"},
+    {file = "boto3-1.36.19.tar.gz", hash = "sha256:8c2c2a4ccdfe35dd2611ee1b7473dd2383948415c777e42dc4e7f1ebe371fe8c"},
 ]
 
 [package.dependencies]
-botocore = ">=1.36.17,<1.37.0"
+botocore = ">=1.36.19,<1.37.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.11.0,<0.12.0"
 
@@ -192,14 +192,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.36.17"
+version = "1.36.19"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "botocore-1.36.17-py3-none-any.whl", hash = "sha256:069858b2fd693548035d7fd53a774e37e4260fea64e0ac9b8a3aee904f9321df"},
-    {file = "botocore-1.36.17.tar.gz", hash = "sha256:cec13e0a7ce78e71aad0b397581b4e81824c7981ef4c261d2e296d200c399b09"},
+    {file = "botocore-1.36.19-py3-none-any.whl", hash = "sha256:98882c106fec4c08678ea028199f7f5119550fab95d682b30846f7aae04b7bec"},
+    {file = "botocore-1.36.19.tar.gz", hash = "sha256:cdf6729f601f82b1acdb9004b1f88b57cfb470f576394cdb3bbf5150f7fafb5b"},
 ]
 
 [package.dependencies]
@@ -860,14 +860,14 @@ tool = ["click (>=6.0.0)"]
 
 [[package]]
 name = "googleapis-common-protos"
-version = "1.66.0"
+version = "1.67.0"
 description = "Common protobufs used in Google APIs"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "googleapis_common_protos-1.66.0-py2.py3-none-any.whl", hash = "sha256:d7abcd75fabb2e0ec9f74466401f6c119a0b498e27370e9be4c94cb7e382b8ed"},
-    {file = "googleapis_common_protos-1.66.0.tar.gz", hash = "sha256:c3e7b33d15fdca5374cc0a7346dd92ffa847425cc4ea941d970f13680052ec8c"},
+    {file = "googleapis_common_protos-1.67.0-py2.py3-none-any.whl", hash = "sha256:579de760800d13616f51cf8be00c876f00a9f146d3e6510e19d1f4111758b741"},
+    {file = "googleapis_common_protos-1.67.0.tar.gz", hash = "sha256:21398025365f138be356d5923e9168737d94d46a72aefee4a6110a1f23463c86"},
 ]
 
 [package.dependencies]
@@ -1235,14 +1235,14 @@ files = [
 
 [[package]]
 name = "myst-parser"
-version = "4.0.0"
+version = "4.0.1"
 description = "An extended [CommonMark](https://spec.commonmark.org/) compliant parser,"
 optional = false
 python-versions = ">=3.10"
 groups = ["docs"]
 files = [
-    {file = "myst_parser-4.0.0-py3-none-any.whl", hash = "sha256:b9317997552424448c6096c2558872fdb6f81d3ecb3a40ce84a7518798f3f28d"},
-    {file = "myst_parser-4.0.0.tar.gz", hash = "sha256:851c9dfb44e36e56d15d05e72f02b80da21a9e0d07cba96baf5e2d476bb91531"},
+    {file = "myst_parser-4.0.1-py3-none-any.whl", hash = "sha256:9134e88959ec3b5780aedf8a99680ea242869d012e8821db3126d427edc9c95d"},
+    {file = "myst_parser-4.0.1.tar.gz", hash = "sha256:5cfea715e4f3574138aecbf7d54132296bfd72bb614d31168f48c477a830a7c4"},
 ]
 
 [package.dependencies]
@@ -1254,10 +1254,10 @@ pyyaml = "*"
 sphinx = ">=7,<9"
 
 [package.extras]
-code-style = ["pre-commit (>=3.0,<4.0)"]
+code-style = ["pre-commit (>=4.0,<5.0)"]
 linkify = ["linkify-it-py (>=2.0,<3.0)"]
 rtd = ["ipython", "sphinx (>=7)", "sphinx-autodoc2 (>=0.5.0,<0.6.0)", "sphinx-book-theme (>=1.1,<2.0)", "sphinx-copybutton", "sphinx-design", "sphinx-pyscript", "sphinx-tippy (>=0.4.3)", "sphinx-togglebutton", "sphinxext-opengraph (>=0.9.0,<0.10.0)", "sphinxext-rediraffe (>=0.2.7,<0.3.0)"]
-testing = ["beautifulsoup4", "coverage[toml]", "defusedxml", "pytest (>=8,<9)", "pytest-cov", "pytest-param-files (>=0.6.0,<0.7.0)", "pytest-regressions", "sphinx-pytest"]
+testing = ["beautifulsoup4", "coverage[toml]", "defusedxml", "pygments (<2.19)", "pytest (>=8,<9)", "pytest-cov", "pytest-param-files (>=0.6.0,<0.7.0)", "pytest-regressions", "sphinx-pytest"]
 testing-docutils = ["pygments", "pytest (>=8,<9)", "pytest-param-files (>=0.6.0,<0.7.0)"]
 
 [[package]]

src/auto_archiver/modules/whisper_enricher/whisper_enricher.py

@@ -29,8 +29,7 @@ class WhisperEnricher(Enricher):
         job_results = {}
         for i, m in enumerate(to_enrich.media):
             if m.is_video() or m.is_audio():
-                # TODO: this used to pass all storage items to store now
-                # Now only passing S3, the rest will get added later in the usual order (?)
+                # Only storing S3, the rest will get added later in the usual order (?)
                 m.store(url=url, metadata=to_enrich, storages=[self.s3])
                 try:
                     job_id = self.submit_job(m)

tests/conftest.py

@@ -133,14 +133,6 @@ def unpickle():
     return _unpickle
 
 
-@pytest.fixture
-def mock_python_dependencies():
-    with patch("auto_archiver.core.module") as mock_check_python_dep:
-        # Mock all Python dependencies as available
-        mock_check_python_dep.return_value = True
-        yield mock_check_python_dep
-
-
 @pytest.fixture
 def mock_binary_dependencies():
     with patch("shutil.which") as mock_shutil_which:

tests/enrichers/test_metadata_enricher.py

@@ -14,7 +14,7 @@ def mock_media():
 
 
 @pytest.fixture
-def enricher(setup_module):
+def enricher(setup_module, mock_binary_dependencies):
     return setup_module("metadata_enricher", {})
 
 
@@ -74,3 +74,16 @@ def test_get_metadata_error_handling(mock_run, mock_logger_error, enricher):
     result = enricher.get_metadata("test.jpg")
     assert result == {}
     mock_logger_error.assert_called_once()
+
+
+@pytest.mark.skip(reason="Requires ExifTool to be installed. TODO mock")
+def test_metadata_pickle(enricher, unpickle):
+    # Uses a pickle of a YouTube short
+    metadata = unpickle("tests/data/metadata/metadata_enricher_ytshort_input.pickle")
+    expected = unpickle("tests/data/metadata/metadata_enricher_ytshort_expected.pickle")
+    enricher.enrich(metadata)
+    expected_media = expected.media
+    actual_media = metadata.media
+    assert len(expected_media) == len(actual_media)
+    assert actual_media[0].properties.get("metadata") == expected_media[0].properties.get("metadata")
+    assert metadata == expected

tests/enrichers/test_ssl_enricher.py

@@ -38,11 +38,13 @@ def test_empty_metadata(metadata, enricher):
 def test_ssl_enrich(metadata, enricher):
     with patch("ssl.get_server_certificate", return_value="TEST_CERT"), \
          patch("builtins.open", mock_open()) as mock_file:
+        media_len_before = len(metadata.media)
         enricher.enrich(metadata)
 
         ssl.get_server_certificate.assert_called_once_with(("example.com", 443))
         mock_file.assert_called_once_with(f"{enricher.tmp_dir}/example-com.pem", "w")
         mock_file().write.assert_called_once_with("TEST_CERT")
+        assert len(metadata.media) == media_len_before + 1
         # Ensure the certificate is added to metadata
         assert any(media.filename.endswith("example-com.pem") for media in metadata.media)
 

tests/enrichers/test_thumbnail_enricher.py

@@ -5,12 +5,12 @@ from auto_archiver.modules.thumbnail_enricher import ThumbnailEnricher
 
 
 @pytest.fixture
-def thumbnail_enricher(setup_module) -> ThumbnailEnricher:
-    configs: dict = {
+def thumbnail_enricher(setup_module, mock_binary_dependencies) -> ThumbnailEnricher:
+    config: dict = {
         "thumbnails_per_minute": 60,
         "max_thumbnails": 4,
     }
-    return setup_module("thumbnail_enricher", configs)
+    return setup_module("thumbnail_enricher", config)
 
 
 @pytest.fixture

tests/enrichers/test_whisper_enricher.py

@@ -8,6 +8,9 @@ from auto_archiver.modules.s3_storage import S3Storage
 from auto_archiver.modules.whisper_enricher import WhisperEnricher
 
 
+TEST_S3_URL = "http://cdn.example.com/test.mp4"
+
+
 @pytest.fixture
 def enricher():
     """Fixture with mocked S3 and API dependencies"""
@@ -20,7 +23,7 @@ def enricher():
         "steps": {"storages": ["s3_storage"]}
     }
     mock_s3 = MagicMock(spec=S3Storage)
-    mock_s3.get_cdn_url.return_value = "http://s3.example.com/media.mp3"
+    mock_s3.get_cdn_url.return_value = TEST_S3_URL
     instance = WhisperEnricher()
     instance.name = "whisper_enricher"
     instance.display_name = "Whisper Enricher"
@@ -53,7 +56,7 @@ def test_successful_job_submission(enricher, metadata, mock_requests):
     """Test successful media processing with S3 configured"""
     whisper, mock_s3 = enricher
     # Configure mock S3 URL to match test expectation
-    mock_s3.get_cdn_url.return_value = "http://cdn.example.com/test.mp4"
+    mock_s3.get_cdn_url.return_value = TEST_S3_URL
 
     # Create test media with matching CDN URL
     m = Media("test.mp4")
@@ -78,6 +81,7 @@ def test_successful_job_submission(enricher, metadata, mock_requests):
         mock_status_response,  # First call: status check
         mock_artifacts_response  # Second call: artifacts check
     ]
+
     # Run enrichment (without opening file)
     whisper.enrich(metadata)
     # Check API interactions
@@ -89,5 +93,43 @@ def test_successful_job_submission(enricher, metadata, mock_requests):
     # Verify job status checks
     assert mock_requests.get.call_count == 2
     assert "artifact_0_text" in metadata.media[0].get("whisper_model")
-    assert "test transcript" in metadata.metadata.get("content")
+    assert metadata.media[0].get("whisper_model") == {'artifact_0_text': 'test transcript', 'job_artifacts_check': 'http://testapi/jobs/job123/artifacts', 'job_id': 'job123', 'job_status_check': 'http://testapi/jobs/job123'}
+
+
+
+def test_submit_job(enricher):
+    """Test job submission method"""
+    whisper, _ = enricher
+    m = Media("test.mp4")
+    m.add_url(TEST_S3_URL)
+    with patch("auto_archiver.modules.whisper_enricher.whisper_enricher.requests") as mock_requests:
+        mock_response = MagicMock()
+        mock_response.status_code = 201
+        mock_response.json.return_value = {"id": "job123"}
+        mock_requests.post.return_value = mock_response
+        job_id = whisper.submit_job(m)
+    assert job_id == "job123"
+
+def test_submit_raises_status(enricher):
+    whisper, _ = enricher
+    m = Media("test.mp4")
+    m.add_url(TEST_S3_URL)
+    with patch("auto_archiver.modules.whisper_enricher.whisper_enricher.requests") as mock_requests:
+        mock_response = MagicMock()
+        mock_response.status_code = 400
+        mock_response.json.return_value = {"id": "job123"}
+        mock_requests.post.return_value = mock_response
+        with pytest.raises(AssertionError) as exc_info:
+            whisper.submit_job(m)
+        assert str(exc_info.value) == "calling the whisper api http://testapi returned a non-success code: 400"
+
+# @pytest.mark.parametrize("test_url, status", ["http://cdn.example.com/test.mp4",])
+def test_submit_job_fails(enricher):
+    """Test assertion fails with non-S3 URL"""
+    whisper, mock_s3 = enricher
+    m = Media("test.mp4")
+    m.add_url("http://cdn.wrongurl.com/test.mp4")
+    with pytest.raises(AssertionError):
+        whisper.submit_job(m)
+
 

tests/test_metadata.py

@@ -162,4 +162,25 @@ def test_get_context():
 
 
 def test_choose_most_complete():
-    pass
+    m_more = Metadata()
+    m_more.set_title("Title 1")
+    m_more.set_content("Content 1")
+    m_more.set_url("https://example.com")
+
+    m_less = Metadata()
+    m_less.set_title("Title 2")
+    m_less.set_content("Content 2")
+    m_less.set_url("https://example.com")
+    m_less.set_context("key", "value")
+
+    res = Metadata.choose_most_complete([m_more, m_less])
+    assert res.metadata.get("title") == "Title 1"
+
+def test_choose_most_complete_from_pickles(unpickle):
+    # test most complete from pickles before and after an enricher has run
+    # Only compares length of media, not the actual media
+    m_before_enriching = unpickle("/Users/erinclark/PycharmProjects/auto-archiver/tests/data/metadata/metadata_enricher_ytshort_input.pickle")
+    m_after_enriching = unpickle("/Users/erinclark/PycharmProjects/auto-archiver/tests/data/metadata/metadata_enricher_ytshort_expected.pickle")
+    # Iterates `for r in results[1:]:`
+    res = Metadata.choose_most_complete([Metadata(), m_after_enriching, m_before_enriching])
+    assert res.media == m_after_enriching.media