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>
2026-11-04 08:26:38 +01:00 · 2022-06-03 13:17:43 -04:00
parent 82de24cf7c
commit caff67289a
17 changed files with 269 additions and 26 deletions
@@ -7,28 +7,31 @@ import (
 	"testing"

 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"

 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
 )

-func parser(_ string, reader io.Reader) ([]*pkg.Package, []artifact.Relationship, error) {
-	contents, err := ioutil.ReadAll(reader)
-	if err != nil {
-		panic(err)
-	}
-	return []*pkg.Package{
-		{
-			Name: string(contents),
-		},
-	}, nil, nil
-}
-
 func TestGenericCataloger(t *testing.T) {
+	allParsedPathes := make(map[string]bool)
+	parser := func(path string, reader io.Reader) ([]*pkg.Package, []artifact.Relationship, error) {
+		allParsedPathes[path] = true
+		contents, err := ioutil.ReadAll(reader)
+		require.NoError(t, err)
+
+		p := &pkg.Package{Name: string(contents)}
+		r := artifact.Relationship{From: p, To: p,
+			Type: artifact.ContainsRelationship,
+		}
+
+		return []*pkg.Package{p}, []artifact.Relationship{r}, nil
+	}

 	globParsers := map[string]ParserFn{
 		"**/a-path.txt": parser,
+		"**/empty.txt":  parser,
 	}
 	pathParsers := map[string]ParserFn{
 		"test-fixtures/another-path.txt": parser,
@@ -36,21 +39,27 @@ func TestGenericCataloger(t *testing.T) {
 	}
 	upstream := "some-other-cataloger"

-	expectedSelection := []string{"test-fixtures/last/path.txt", "test-fixtures/another-path.txt", "test-fixtures/a-path.txt"}
+	expectedSelection := []string{"test-fixtures/last/path.txt", "test-fixtures/another-path.txt", "test-fixtures/a-path.txt", "test-fixtures/empty.txt"}
 	resolver := source.NewMockResolverForPaths(expectedSelection...)
 	cataloger := NewGenericCataloger(pathParsers, globParsers, upstream)

+	actualPkgs, relationships, err := cataloger.Catalog(resolver)
+	assert.NoError(t, err)
+
 	expectedPkgs := make(map[string]pkg.Package)
 	for _, path := range expectedSelection {
+		require.True(t, allParsedPathes[path])
 		expectedPkgs[path] = pkg.Package{
 			FoundBy: upstream,
 			Name:    fmt.Sprintf("%s file contents!", path),
 		}
 	}

-	actualPkgs, _, err := cataloger.Catalog(resolver)
-	assert.NoError(t, err)
-	assert.Len(t, actualPkgs, len(expectedPkgs))
+	assert.Len(t, allParsedPathes, len(expectedSelection))
+	// empty.txt won't become a package
+	assert.Len(t, actualPkgs, len(expectedPkgs)-1)
+	// right now, a relationship is created for each package, but if the relationship includes an invalid package it should be dropped.
+	assert.Len(t, relationships, len(actualPkgs))

 	for _, p := range actualPkgs {
 		ref := p.Locations.ToSlice()[0]
@@ -69,3 +78,99 @@ func TestGenericCataloger(t *testing.T) {
 		}
 	}
 }
+
+func Test_removeRelationshipsWithArtifactIDs(t *testing.T) {
+	one := &pkg.Package{Name: "one", Version: "1.0"}
+	two := &pkg.Package{Name: "two", Version: "1.0"}
+	three := &pkg.Package{Name: "three", Version: "1.0"}
+	four := &pkg.Package{Name: "four", Version: "bla"}
+	five := &pkg.Package{Name: "five", Version: "1.0"}
+
+	pkgs := make([]artifact.Identifiable, 0)
+	for _, p := range []*pkg.Package{one, two, three, four, five} {
+		// IDs are necessary for comparison
+		p.SetID()
+		pkgs = append(pkgs, p)
+	}
+
+	type args struct {
+		remove        map[artifact.ID]struct{}
+		relationships []artifact.Relationship
+	}
+	tests := []struct {
+		name string
+		args args
+		want []artifact.Relationship
+	}{
+		{
+			name: "nothing-to-remove",
+			args: args{
+				relationships: []artifact.Relationship{
+					{From: one, To: two},
+				},
+			},
+			want: []artifact.Relationship{
+				{From: one, To: two},
+			},
+		},
+		{
+			name: "remove-all-relationships",
+			args: args{
+				remove: map[artifact.ID]struct{}{
+					one.ID():   {},
+					three.ID(): {},
+				},
+				relationships: []artifact.Relationship{
+					{From: one, To: two},
+					{From: two, To: three},
+					{From: three, To: four},
+				},
+			},
+			want: []artifact.Relationship(nil),
+		},
+		{
+			name: "remove-half-of-relationships",
+			args: args{
+				remove: map[artifact.ID]struct{}{
+					one.ID(): {},
+				},
+				relationships: []artifact.Relationship{
+					{From: one, To: two},
+					{From: one, To: three},
+					{From: two, To: three},
+					{From: three, To: four},
+				},
+			},
+			want: []artifact.Relationship{
+				{From: two, To: three},
+				{From: three, To: four},
+			},
+		},
+		{
+			name: "remove-repeated-relationships",
+			args: args{
+				remove: map[artifact.ID]struct{}{
+					one.ID(): {},
+					two.ID(): {},
+				},
+				relationships: []artifact.Relationship{
+					{From: one, To: two},
+					{From: one, To: three},
+					{From: two, To: three},
+					{From: two, To: three},
+					{From: three, To: four},
+					{From: four, To: five},
+				},
+			},
+			want: []artifact.Relationship{
+				{From: three, To: four},
+				{From: four, To: five},
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equalf(t, tt.want, removeRelationshipsWithArtifactIDs(tt.args.remove, tt.args.relationships), "removeRelationshipsWithArtifactIDs(%v, %v)", tt.args.remove, tt.args.relationships)
+		})
+	}
+}