diff options
Diffstat (limited to '')
| -rw-r--r-- | tests/tasks/test_source_parser.py | 88 |
1 files changed, 48 insertions, 40 deletions
diff --git a/tests/tasks/test_source_parser.py b/tests/tasks/test_source_parser.py index 3c3a93e..38752b0 100644 --- a/tests/tasks/test_source_parser.py +++ b/tests/tasks/test_source_parser.py @@ -24,7 +24,7 @@ def source_parser_module(app: Flask, monkeypatch: pytest.MonkeyPatch) -> ModuleT return source_parser -def test_parse_entry_returns_microformats_entry( +def test_parse_h_entry_returns_microformats_entry( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -45,13 +45,13 @@ def test_parse_entry_returns_microformats_entry( assert element is not None - entry = source_parser_module.parse_entry(element, SOURCE_URL) + entry = source_parser_module.parse_h_entry(element, SOURCE_URL) assert "h-entry" in entry["type"] assert entry["properties"]["url"] == [SOURCE_URL] -def test_parse_entry_rejects_non_entry(source_parser_module: ModuleType) -> None: +def test_parse_h_entry_rejects_non_entry(source_parser_module: ModuleType) -> None: document = parse_html( """ <article> @@ -68,10 +68,12 @@ def test_parse_entry_rejects_non_entry(source_parser_module: ModuleType) -> None source_parser_module.SourceScanError, match="Expected exactly one parsed h-entry", ): - source_parser_module.parse_entry(element, SOURCE_URL) + source_parser_module.parse_h_entry(element, SOURCE_URL) -def test_primary_entry_returns_source_entry(source_parser_module: ModuleType) -> None: +def test_find_primary_h_entry_returns_source_entry( + source_parser_module: ModuleType, +) -> None: document = parse_html( f""" <article class="h-entry" id="source"> @@ -90,14 +92,14 @@ def test_primary_entry_returns_source_entry(source_parser_module: ModuleType) -> """ ) - element, entry = source_parser_module.primary_entry(document, SOURCE_URL) + element, entry = source_parser_module.find_primary_h_entry(document, SOURCE_URL) assert element["id"] == "source" assert entry["properties"]["name"] == ["Example post"] assert entry["properties"]["url"] == [SOURCE_URL] -def test_primary_entry_rejects_missing_h_entry( +def test_find_primary_h_entry_rejects_missing_h_entry( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -112,10 +114,10 @@ def test_primary_entry_rejects_missing_h_entry( source_parser_module.SourceScanError, match="Expected exactly one h-entry, found 0", ): - source_parser_module.primary_entry(document, SOURCE_URL) + source_parser_module.find_primary_h_entry(document, SOURCE_URL) -def test_primary_entry_rejects_multiple_h_entries( +def test_find_primary_h_entry_rejects_multiple_h_entries( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -141,10 +143,12 @@ def test_primary_entry_rejects_multiple_h_entries( source_parser_module.SourceScanError, match="Expected exactly one h-entry, found 2", ): - source_parser_module.primary_entry(document, SOURCE_URL) + source_parser_module.find_primary_h_entry(document, SOURCE_URL) -def test_primary_entry_rejects_nested_h_entry(source_parser_module: ModuleType) -> None: +def test_find_primary_h_entry_rejects_nested_h_entry( + source_parser_module: ModuleType, +) -> None: document = parse_html( f""" <article class="h-entry"> @@ -170,10 +174,12 @@ def test_primary_entry_rejects_nested_h_entry(source_parser_module: ModuleType) source_parser_module.SourceScanError, match="Expected exactly one h-entry, found 2", ): - source_parser_module.primary_entry(document, SOURCE_URL) + source_parser_module.find_primary_h_entry(document, SOURCE_URL) -def test_primary_entry_rejects_missing_u_url(source_parser_module: ModuleType) -> None: +def test_find_primary_h_entry_rejects_missing_u_url( + source_parser_module: ModuleType, +) -> None: document = parse_html( """ <article class="h-entry"> @@ -185,10 +191,10 @@ def test_primary_entry_rejects_missing_u_url(source_parser_module: ModuleType) - ) with pytest.raises(source_parser_module.SourceScanError, match="does not match"): - source_parser_module.primary_entry(document, SOURCE_URL) + source_parser_module.find_primary_h_entry(document, SOURCE_URL) -def test_primary_entry_rejects_nonmatching_u_url( +def test_find_primary_h_entry_rejects_nonmatching_u_url( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -209,10 +215,10 @@ def test_primary_entry_rejects_nonmatching_u_url( ) with pytest.raises(source_parser_module.SourceScanError, match="does not match"): - source_parser_module.primary_entry(document, SOURCE_URL) + source_parser_module.find_primary_h_entry(document, SOURCE_URL) -def test_content_element_returns_e_content(source_parser_module: ModuleType) -> None: +def test_find_e_content_returns_e_content(source_parser_module: ModuleType) -> None: document = parse_html( """ <article class="h-entry"> @@ -227,12 +233,12 @@ def test_content_element_returns_e_content(source_parser_module: ModuleType) -> assert entry is not None - content = source_parser_module.content_element(entry) + content = source_parser_module.find_e_content(entry) assert content["id"] == "content" -def test_content_element_rejects_missing_e_content( +def test_find_e_content_rejects_missing_e_content( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -251,10 +257,10 @@ def test_content_element_rejects_missing_e_content( source_parser_module.SourceScanError, match="Expected exactly one e-content, found 0", ): - source_parser_module.content_element(entry) + source_parser_module.find_e_content(entry) -def test_content_element_rejects_multiple_e_content( +def test_find_e_content_rejects_multiple_e_content( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -279,10 +285,12 @@ def test_content_element_rejects_multiple_e_content( source_parser_module.SourceScanError, match="Expected exactly one e-content, found 2", ): - source_parser_module.content_element(entry) + source_parser_module.find_e_content(entry) -def test_canonical_url_returns_absolute_url(source_parser_module: ModuleType) -> None: +def test_declared_canonical_url_returns_absolute_url( + source_parser_module: ModuleType, +) -> None: document = parse_html( f""" <html> @@ -296,14 +304,14 @@ def test_canonical_url_returns_absolute_url(source_parser_module: ModuleType) -> """ ) - result = source_parser_module.canonical_url( + result = source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=None ) assert result == SOURCE_URL -def test_canonical_url_returns_none_when_missing( +def test_declared_canonical_url_returns_none_when_missing( source_parser_module: ModuleType, ) -> None: document = parse_html( @@ -316,14 +324,14 @@ def test_canonical_url_returns_none_when_missing( """ ) - result = source_parser_module.canonical_url( + result = source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=None ) assert result is None -def test_canonical_url_resolves_relative_url_with_base_url( +def test_declared_canonical_url_resolves_relative_url_with_base_url( source_parser_module: ModuleType, ) -> None: source_parser_module.is_http_url.side_effect = [False, True] @@ -341,7 +349,7 @@ def test_canonical_url_resolves_relative_url_with_base_url( """ ) - result = source_parser_module.canonical_url( + result = source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=BASE_URL ) @@ -367,7 +375,7 @@ def test_relative_canonical_requires_base_url(source_parser_module: ModuleType) with pytest.raises( source_parser_module.SourceScanError, match="relative canonical" ): - source_parser_module.canonical_url( + source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=None ) @@ -389,7 +397,7 @@ def test_empty_canonical_is_rejected(source_parser_module: ModuleType) -> None: with pytest.raises( source_parser_module.SourceScanError, match="empty canonical URL" ): - source_parser_module.canonical_url( + source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=BASE_URL ) @@ -907,7 +915,7 @@ def test_scan_source_ignores_reaction_to_matching_hostname( assert scanned.targets == frozenset() -def test_canonical_url_rejects_non_http_resolved_url( +def test_declared_canonical_url_rejects_non_http_resolved_url( source_parser_module: ModuleType, ) -> None: source_parser_module.is_http_url.return_value = False @@ -929,17 +937,17 @@ def test_canonical_url_rejects_non_http_resolved_url( source_parser_module.SourceScanError, match="Canonical URL is not a valid HTTP or HTTPS URL", ): - source_parser_module.canonical_url( + source_parser_module.declared_canonical_url( document, relative_path=Path("example/index.html"), base_url=BASE_URL ) -def test_property_urls_ignores_non_mapping_properties( +def test_mf2_string_values_ignores_non_mapping_properties( source_parser_module: ModuleType, ) -> None: entry = {"properties": "invalid"} - assert tuple(source_parser_module.property_urls(entry, "url")) == () + assert tuple(source_parser_module.mf2_string_values(entry, "url")) == () @pytest.mark.parametrize( @@ -960,7 +968,7 @@ def test_property_urls_ignores_non_mapping_properties( ), ], ) -def test_parse_entry_rejects_invalid_parser_output( +def test_parse_h_entry_rejects_invalid_parser_output( source_parser_module: ModuleType, monkeypatch: MonkeyPatch, parsed: object, @@ -981,27 +989,27 @@ def test_parse_entry_rejects_invalid_parser_output( monkeypatch.setattr(source_parser.mf2py, "parse", lambda **kwargs: parsed) with pytest.raises(source_parser_module.SourceScanError, match=message): - source_parser_module.parse_entry(element, SOURCE_URL) + source_parser_module.parse_h_entry(element, SOURCE_URL) -def test_normalize_target_ignores_empty_target( +def test_normalize_target_url_ignores_empty_target( source_parser_module: ModuleType, ) -> None: assert ( - source_parser_module.normalize_target( + source_parser_module.normalize_target_url( " ", base_url=SOURCE_URL, source_url=SOURCE_URL ) is None ) -def test_normalize_target_ignores_url_rejected_by_validator( +def test_normalize_target_url_ignores_url_rejected_by_validator( source_parser_module: ModuleType, ) -> None: source_parser_module.is_http_url.return_value = False assert ( - source_parser_module.normalize_target( + source_parser_module.normalize_target_url( "https://example.com/target", base_url=SOURCE_URL, source_url=SOURCE_URL ) is None |
