fix: improve determinism in java archive identification (#3085)

Signed-off-by: Keith Zantow <[email protected]>

go.mod

@@ -90,6 +90,7 @@ require (
 	github.com/BurntSushi/toml v1.4.0
 	github.com/adrg/xdg v0.5.0
 	github.com/magiconair/properties v1.8.7
+	golang.org/x/exp v0.0.0-20231108232855-2478ac86f678
 )
 
 require (
@@ -230,7 +231,6 @@ require (
 	go.uber.org/atomic v1.9.0 // indirect
 	go.uber.org/multierr v1.9.0 // indirect
 	golang.org/x/crypto v0.25.0 // indirect
-	golang.org/x/exp v0.0.0-20231108232855-2478ac86f678 // indirect
 	golang.org/x/sync v0.7.0 // indirect
 	golang.org/x/sys v0.22.0 // indirect
 	golang.org/x/term v0.22.0 // indirect

syft/pkg/cataloger/java/archive_parser.go

@@ -6,8 +6,11 @@ import (
 	"fmt"
 	"os"
 	"path"
+	"slices"
 	"strings"
 
+	"golang.org/x/exp/maps"
+
 	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/licenses"
 	"github.com/anchore/syft/internal/log"
@@ -298,7 +301,10 @@ func (j *archiveParser) guessMainPackageNameAndVersionFromPomInfo(ctx context.Co
 	properties, _ := pomPropertiesByParentPath(j.archivePath, j.location, pomPropertyMatches)
 	projects, _ := pomProjectByParentPath(j.archivePath, j.location, pomMatches)
 
-	for parentPath, propertiesObj := range properties {
+	parentPaths := maps.Keys(properties)
+	slices.Sort(parentPaths)
+	for _, parentPath := range parentPaths {
+		propertiesObj := properties[parentPath]
 		if artifactIDMatchesFilename(propertiesObj.ArtifactID, j.fileInfo.name) {
 			pomPropertiesObject = propertiesObj
 			if proj, exists := projects[parentPath]; exists {

syft/pkg/cataloger/java/archive_parser_test.go

@@ -1386,6 +1386,44 @@ func Test_parseJavaArchive_regressions(t *testing.T) {
 	}
 }
 
+func Test_deterministicMatchingPomProperties(t *testing.T) {
+	tests := []struct {
+		fixture         string
+		expectedName    string
+		expectedVersion string
+	}{
+		{
+			fixture:         "multiple-matching-2.11.5",
+			expectedName:    "multiple-matching-1",
+			expectedVersion: "2.11.5",
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.fixture, func(t *testing.T) {
+			fixturePath := generateJavaMetadataJarFixture(t, test.fixture)
+
+			for i := 0; i < 5; i++ {
+				func() {
+					fixture, err := os.Open(fixturePath)
+					require.NoError(t, err)
+
+					parser, cleanupFn, err := newJavaArchiveParser(file.LocationReadCloser{
+						Location:   file.NewLocation(fixture.Name()),
+						ReadCloser: fixture,
+					}, false, ArchiveCatalogerConfig{UseNetwork: false})
+					defer cleanupFn()
+					require.NoError(t, err)
+
+					name, version, _ := parser.guessMainPackageNameAndVersionFromPomInfo(context.TODO())
+					require.Equal(t, test.expectedName, name)
+					require.Equal(t, test.expectedVersion, version)
+				}()
+			}
+		})
+	}
+}
+
 func assignParent(parent *pkg.Package, childPackages ...pkg.Package) {
 	for i, jp := range childPackages {
 		if v, ok := jp.Metadata.(pkg.JavaArchive); ok {

syft/pkg/cataloger/java/test-fixtures/jar-metadata/Makefile

@@ -6,6 +6,7 @@ SBT_JACKSON_CORE = com.fasterxml.jackson.core.jackson-core-2.15.2
 OPENSAML_CORE = opensaml-core-3.4.6
 API_ALL_SOURCES = api-all-2.0.0-sources
 SPRING_INSTRUMENTATION = spring-instrumentation-4.3.0-1.0
+MULTIPLE_MATCHING = multiple-matching-2.11.5
 
 $(CACHE_DIR):
 	mkdir -p $(CACHE_DIR)
@@ -24,3 +25,6 @@ $(CACHE_DIR)/$(API_ALL_SOURCES).jar: $(CACHE_DIR)
 
 $(CACHE_DIR)/$(SPRING_INSTRUMENTATION).jar: $(CACHE_DIR)
 	cd $(SPRING_INSTRUMENTATION) && zip -r $(CACHE_PATH)/$(SPRING_INSTRUMENTATION).jar .
+
+$(CACHE_DIR)/$(MULTIPLE_MATCHING).jar: $(CACHE_DIR)
+	cd $(MULTIPLE_MATCHING) && zip -r $(CACHE_PATH)/$(MULTIPLE_MATCHING).jar .

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/MANIFEST.MF

@@ -0,0 +1,2 @@
+Manifest-Version: 1.0
+Created-By: Multi

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-1/pom.properties

@@ -0,0 +1,3 @@
+version=2.11.5
+groupId=org.multiple
+artifactId=multiple-matching-1

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-1/pom.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>org.multiple</groupId>
+    <artifactId>multiple-matching-1</artifactId>
+    <version>2.11.5</version>
+</project>

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-2/pom.properties

@@ -0,0 +1,3 @@
+version=2.11.5
+groupId=org.multiple
+artifactId=multiple-matching-2

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-2/pom.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>org.multiple</groupId>
+    <artifactId>multiple-matching-2</artifactId>
+    <version>2.11.5</version>
+</project>

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-3/pom.properties

@@ -0,0 +1,3 @@
+version=2.11.5
+groupId=org.multiple
+artifactId=multiple-matching-3

syft/pkg/cataloger/java/test-fixtures/jar-metadata/multiple-matching-2.11.5/META-INF/maven/org.multiple/multiple-matching-3/pom.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>org.multiple</groupId>
+    <artifactId>multiple-matching-3</artifactId>
+    <version>2.11.5</version>
+</project>