Add filters to package cataloger (#1021)

* Add filters to package cataloger

This PR adds filters so a package without name or version doesn't go in
the list of all discovered packages.

Integration and cli tests were added to validate the feature.

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* add nolint:funlen to cataloger/catalog.go

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* don't require package version

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* add package filtering to generic and python cataloger

also removes cli tests in favor of integration and unit tests

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* drop nolint:funlen

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* check for no-removal operation

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* remove unused fixtures

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* rename no-version file to hide semantic version

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* drop integration tests and add pkg func for validation

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* python cataloger use global pkg validation

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* check for valid packages on deb/go/rpm catalogers

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* update rpm cataloger after rebase

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* nit with pointers

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* simpler use of package validation

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* remmove double pkg validations

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* rename func param to artifactsToExclude

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* add test for relationships and bug fix

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

* feedback changes

Signed-off-by: Jonas Xavier <jonasx@anchore.com>

syft/pkg/cataloger/python/package_cataloger.go

@@ -51,7 +51,7 @@ func (c *PackageCataloger) Catalog(resolver source.FileResolver) ([]pkg.Package,
 		if err != nil {
 			return nil, nil, fmt.Errorf("unable to catalog python package=%+v: %w", location.RealPath, err)
 		}
-		if p != nil {
+		if pkg.IsValid(p) {
 			pkgs = append(pkgs, *p)
 		}
 	}

syft/pkg/cataloger/python/package_cataloger_test.go

@@ -14,6 +14,21 @@ func TestPythonPackageWheelCataloger(t *testing.T) {
 		fixtures        []string
 		expectedPackage pkg.Package
 	}{
+		{
+			name:     "egg-file-no-version",
+			fixtures: []string{"test-fixtures/no-version-py3.8.egg-info"},
+			expectedPackage: pkg.Package{
+				Name:         "no-version",
+				Type:         pkg.PythonPkg,
+				Language:     pkg.Python,
+				FoundBy:      "python-package-cataloger",
+				MetadataType: pkg.PythonPackageMetadataType,
+				Metadata: pkg.PythonPackageMetadata{
+					Name:                 "no-version",
+					SitePackagesRootPath: "test-fixtures",
+				},
+			},
+		},
 		{
 			name: "egg-info directory",
 			fixtures: []string{
@@ -169,6 +184,9 @@ func TestIgnorePackage(t *testing.T) {
 		{
 			MetadataFixture: "test-fixtures/Python-2.7.egg-info",
 		},
+		{
+			MetadataFixture: "test-fixtures/empty-1.0.0-py3.8.egg-info",
+		},
 	}
 
 	for _, test := range tests {

syft/pkg/cataloger/python/test-fixtures/no-version-py3.8.egg-info

@@ -0,0 +1 @@
+Name: no-version