fix: more python matching support (#1667)

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: spiffcs <spiffcs@users.noreply.github.com>

.github/workflows/validations.yaml

@@ -54,6 +54,13 @@ jobs:
           path: syft/pkg/cataloger/golang/test-fixtures/archs/binaries
           key: ${{ runner.os }}-unit-go-binaries-cache-${{ hashFiles( 'syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint' ) }}
 
+      - name: Restore binary cataloger test-fixture cache
+        id: unit-binary-cataloger-cache
+        uses: actions/cache@v3
+        with:
+          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/dynamic
+          key: ${{ runner.os }}-unit-binary-cataloger-cache-${{ hashFiles( 'syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint' ) }}
+
       - name: Run unit tests
         run: make unit
 

Makefile

@@ -11,10 +11,10 @@ GLOW_CMD = $(TEMP_DIR)/glow
 
 # Tool versions #################################
 GOLANGCILINT_VERSION := v1.51.2
-GOSIMPORTS_VERSION := v0.3.7
+GOSIMPORTS_VERSION := v0.3.8
 BOUNCER_VERSION := v0.4.0
 CHRONICLE_VERSION := v0.6.0
-GORELEASER_VERSION := v1.15.2
+GORELEASER_VERSION := v1.16.1
 YAJSV_VERSION := v1.4.1
 COSIGN_VERSION := v1.13.1
 QUILL_VERSION := v0.2.0
@@ -189,6 +189,10 @@ fingerprints:
 	cd test/integration/test-fixtures && \
 		make cache.fingerprint
 
+	# for BINARY test fixtures
+	cd syft/pkg/cataloger/binary/test-fixtures && \
+		make cache.fingerprint
+
 	# for JAVA BUILD test fixtures
 	cd syft/pkg/cataloger/java/test-fixtures/java-builds && \
 		make packages.fingerprint
@@ -214,6 +218,7 @@ fixtures:
 	$(call title,Generating test fixtures)
 	cd syft/pkg/cataloger/java/test-fixtures/java-builds && make
 	cd syft/pkg/cataloger/rpm/test-fixtures && make
+	cd syft/pkg/cataloger/binary/test-fixtures && make
 
 .PHONY: show-test-image-cache
 show-test-image-cache:  ## Show all docker and image tar cache
@@ -247,6 +252,11 @@ install-test-ci-mac: $(SNAPSHOT_DIR)
 	cd test/install && \
 		make ci-test-mac
 
+.PHONY: generate-compare-file
+generate-compare-file:
+	$(call title,Generating compare test file)
+	go run ./cmd/syft $(COMPARE_TEST_IMAGE) -o json > $(COMPARE_DIR)/test-fixtures/acceptance-centos-8.2.2004.json
+
 # note: we cannot clean the snapshot directory since the pipeline builds the snapshot separately
 .PHONY: compare-mac
 compare-mac: $(TEMP_DIR) $(SNAPSHOT_DIR)  ## Run compare tests on build snapshot binaries and packages (Mac)

go.mod

@@ -32,7 +32,7 @@ require (
 	github.com/sergi/go-diff v1.3.1
 	github.com/sirupsen/logrus v1.9.0
 	github.com/spdx/tools-golang v0.5.0-rc1
-	github.com/spf13/afero v1.9.4
+	github.com/spf13/afero v1.9.5
 	github.com/spf13/cobra v1.6.1
 	github.com/spf13/pflag v1.0.5
 	github.com/spf13/viper v1.15.0
@@ -42,9 +42,9 @@ require (
 	github.com/wagoodman/go-progress v0.0.0-20230301185719-21920a456ad5
 	github.com/wagoodman/jotframe v0.0.0-20211129225309-56b0d0a4aebb
 	github.com/xeipuuv/gojsonschema v1.2.0
-	golang.org/x/mod v0.8.0
-	golang.org/x/net v0.7.0
-	golang.org/x/term v0.5.0
+	golang.org/x/mod v0.9.0
+	golang.org/x/net v0.8.0
+	golang.org/x/term v0.6.0
 	gopkg.in/yaml.v2 v2.4.0
 )
 
@@ -126,9 +126,9 @@ require (
 	github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 // indirect
 	github.com/xo/terminfo v0.0.0-20210125001918-ca9a967f8778 // indirect
 	golang.org/x/sync v0.1.0 // indirect
-	golang.org/x/sys v0.5.0 // indirect
-	golang.org/x/text v0.7.0 // indirect
-	golang.org/x/tools v0.2.0 // indirect
+	golang.org/x/sys v0.6.0 // indirect
+	golang.org/x/text v0.8.0 // indirect
+	golang.org/x/tools v0.6.0 // indirect
 	golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 // indirect
 	google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef // indirect
 	google.golang.org/grpc v1.52.0 // indirect

go.sum

@@ -519,8 +519,8 @@ github.com/spdx/tools-golang v0.5.0-rc1 h1:ooCSe48QatlidqEFd+nSI308tyeNTR6NJvauU
 github.com/spdx/tools-golang v0.5.0-rc1/go.mod h1:LI6onw172PdO57Ob/hgnLDD4Y2PMnroeNT3wO/2WJJI=
 github.com/spf13/afero v1.3.3/go.mod h1:5KUK8ByomD5Ti5Artl0RtHeI5pTF7MIDuXL3yY520V4=
 github.com/spf13/afero v1.6.0/go.mod h1:Ai8FlHk4v/PARR026UzYexafAt9roJ7LcLMAmO6Z93I=
-github.com/spf13/afero v1.9.4 h1:Sd43wM1IWz/s1aVXdOBkjJvuP8UdyqioeE4AmM0QsBs=
-github.com/spf13/afero v1.9.4/go.mod h1:iUV7ddyEEZPO5gA3zD4fJt6iStLlL+Lg4m2cihcDf8Y=
+github.com/spf13/afero v1.9.5 h1:stMpOSZFs//0Lv29HduCmli3GUfpFoF3Y1Q/aXj/wVM=
+github.com/spf13/afero v1.9.5/go.mod h1:UBogFpq8E9Hx+xc5CNTTEpTnuHVmXDwZcZcE1eb/UhQ=
 github.com/spf13/cast v1.3.1/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
 github.com/spf13/cast v1.4.1/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
 github.com/spf13/cast v1.5.0 h1:rj3WzYc11XZaIZMPKmwP96zkFEnnAmV8s6XbB2aY32w=
@@ -627,7 +627,7 @@ golang.org/x/crypto v0.0.0-20201221181555-eec23a3978ad/go.mod h1:jdWPYTVW3xRLrWP
 golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
 golang.org/x/crypto v0.0.0-20210817164053-32db794688a5/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.0.0-20211108221036-ceb1ce70b4fa/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.3.0 h1:a06MkbcxBrEFc0w0QIZWXrH/9cCX6KJyWbBOIwAn+7A=
 golang.org/x/crypto v0.3.0/go.mod h1:hebNnKkNXi2UzZN1eVRvBB7co0a+JxK6XbPiWVs/3J4=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -670,8 +670,8 @@ golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.5.0/go.mod h1:5OXOZSfqPIIbmVBIIKWRFfZjPR0E5r58TLhUjH0a2Ro=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.8.0 h1:LUYupSeNrTNCGzR/hVBk2NHZO4hXcVaW1k4Qx7rjPx8=
-golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/mod v0.9.0 h1:KENHtAZL2y3NLMYZeHY9DW8HW8V+kQyJsY/V9JlKvCs=
+golang.org/x/mod v0.9.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181023162649-9b4f9f5ad519/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -715,10 +715,11 @@ golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1/go.mod h1:9tjilg8BloeKEkVJvy
 golang.org/x/net v0.0.0-20210503060351-7fd8e65b6420/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210505024714-0287a6fb4125/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210813160813-60bc85c4be6d/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.2.0/go.mod h1:KqCZLdyyvdV855qA2rE3GC2aiw5xGR5TEjj8smXukLY=
-golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
-golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.8.0 h1:Zrh2ngAOFYneWTAIAPethzeaQLuHwhuBkuV6ZiRnUaQ=
+golang.org/x/net v0.8.0/go.mod h1:QVkue5JL9kW//ek3r6jTKnTFis1tRmNAW2P1shuFdJc=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -824,15 +825,15 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
-golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0 h1:MVltZSvRTcU2ljQOhs94SXPftV6DCNnZViHeQps87pQ=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210615171337-6886f2dfbf5b/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.2.0/go.mod h1:TVmDHMZPmdnySmBfhjOoOdhjzdE1h4u1VwSiw2l1Nuc=
-golang.org/x/term v0.5.0 h1:n2a8QNdAb0sZNpU9R1ALUXBbY+w51fCQDN+7EdxNBsY=
-golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/term v0.6.0 h1:clScbb1cHjoCkyRbWwBEUZ5H/tIFu5TAXIqaZD0Gcjw=
+golang.org/x/term v0.6.0/go.mod h1:m6U89DPEgQRMq3DNkDClhWw02AUbt2daBVO4cn4Hv9U=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -843,8 +844,8 @@ golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.4.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
-golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.8.0 h1:57P1ETyNKtuIjB4SRd15iJxuhj8Gc416Y78H3qgMh68=
+golang.org/x/text v0.8.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -908,8 +909,8 @@ golang.org/x/tools v0.1.3/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.4/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.5/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
-golang.org/x/tools v0.2.0 h1:G6AHpWxTMGY1KyEYoAQ5WTtIekUUvDNjan3ugu60JvE=
-golang.org/x/tools v0.2.0/go.mod h1:y4OqIKeOV/fWJetJ8bXPU1sEVniLMIyDAZWeHdV+NTA=
+golang.org/x/tools v0.6.0 h1:BOw41kyTf3PuCW1pVQf8+Cyg8pMlkYB1oo9iJ6D/lKM=
+golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

syft/formats/common/spdxhelpers/license.go

@@ -24,6 +24,12 @@ func License(p pkg.Package) string {
 	// take all licenses and assume an AND expression; for information about license expressions see https://spdx.github.io/spdx-spec/appendix-IV-SPDX-license-expressions/
 	parsedLicenses := parseLicenses(p.Licenses)
 
+	for i, v := range parsedLicenses {
+		if strings.HasPrefix(v, spdxlicense.LicenseRefPrefix) {
+			parsedLicenses[i] = SanitizeElementID(v)
+		}
+	}
+
 	if len(parsedLicenses) == 0 {
 		return NOASSERTION
 	}

syft/formats/common/spdxhelpers/license_test.go

@@ -65,6 +65,17 @@ func Test_License(t *testing.T) {
 			},
 			expected: "GPL-2.0-only",
 		},
+		{
+			name: "includes valid LicenseRef-",
+			input: pkg.Package{
+				Licenses: []string{
+					"one thing first",
+					"two things/#$^second",
+					"MIT",
+				},
+			},
+			expected: "LicenseRef-one-thing-first AND LicenseRef-two-things----second AND MIT",
+		},
 	}
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {

syft/formats/common/spdxhelpers/to_format_model.go

@@ -514,8 +514,8 @@ func toFileTypes(metadata *source.FileMetadata) (ty []string) {
 
 func toOtherLicenses(catalog *pkg.Catalog) []*spdx.OtherLicense {
 	licenses := map[string]bool{}
-	for _, pkg := range catalog.Sorted() {
-		for _, license := range parseLicenses(pkg.Licenses) {
+	for _, p := range catalog.Sorted() {
+		for _, license := range parseLicenses(p.Licenses) {
 			if strings.HasPrefix(license, spdxlicense.LicenseRefPrefix) {
 				licenses[license] = true
 			}
@@ -526,7 +526,7 @@ func toOtherLicenses(catalog *pkg.Catalog) []*spdx.OtherLicense {
 		// separate the actual ID from the prefix
 		name := strings.TrimPrefix(license, spdxlicense.LicenseRefPrefix)
 		result = append(result, &spdx.OtherLicense{
-			LicenseIdentifier: license,
+			LicenseIdentifier: SanitizeElementID(license),
 			LicenseName:       name,
 			ExtractedText:     NONE, // we probably should have some extracted text here, but this is good enough for now
 		})

syft/formats/common/spdxhelpers/to_format_model_test.go

@@ -369,7 +369,7 @@ func Test_fileIDsForPackage(t *testing.T) {
 }
 
 func Test_H1Digest(t *testing.T) {
-	sbom := sbom.SBOM{}
+	s := sbom.SBOM{}
 	tests := []struct {
 		name           string
 		pkg            pkg.Package
@@ -416,7 +416,7 @@ func Test_H1Digest(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 			catalog := pkg.NewCatalog(test.pkg)
-			pkgs := toPackages(catalog, sbom)
+			pkgs := toPackages(catalog, s)
 			require.Len(t, pkgs, 1)
 			for _, p := range pkgs {
 				if test.expectedDigest == "" {
@@ -431,3 +431,67 @@ func Test_H1Digest(t *testing.T) {
 		})
 	}
 }
+
+func Test_OtherLicenses(t *testing.T) {
+	tests := []struct {
+		name     string
+		pkg      pkg.Package
+		expected []*spdx.OtherLicense
+	}{
+		{
+			name: "no licenseRef",
+			pkg: pkg.Package{
+				Licenses: []string{
+					"MIT",
+				},
+			},
+			expected: nil,
+		},
+		{
+			name: "single licenseRef",
+			pkg: pkg.Package{
+				Licenses: []string{
+					"un known",
+				},
+			},
+			expected: []*spdx.OtherLicense{
+				{
+					LicenseIdentifier: "LicenseRef-un-known",
+					LicenseName:       "un known",
+					ExtractedText:     NONE,
+				},
+			},
+		},
+		{
+			name: "multiple licenseRef",
+			pkg: pkg.Package{
+				Licenses: []string{
+					"un known",
+					"not known %s",
+					"MIT",
+				},
+			},
+			expected: []*spdx.OtherLicense{
+				{
+					LicenseIdentifier: "LicenseRef-un-known",
+					LicenseName:       "un known",
+					ExtractedText:     NONE,
+				},
+				{
+					LicenseIdentifier: "LicenseRef-not-known--s",
+					LicenseName:       "not known %s",
+					ExtractedText:     NONE,
+				},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			catalog := pkg.NewCatalog(test.pkg)
+			otherLicenses := toOtherLicenses(catalog)
+			require.Len(t, otherLicenses, len(test.expected))
+			require.Equal(t, test.expected, otherLicenses)
+		})
+	}
+}

syft/pkg/cataloger/apkdb/cataloger_test.go

@@ -24,6 +24,7 @@ func TestCataloger_Globs(t *testing.T) {
 			pkgtest.NewCatalogTester().
 				FromDirectory(t, test.fixture).
 				ExpectsResolverContentQueries(test.expected).
+				IgnoreUnfulfilledPathResponses("etc/apk/repositories").
 				TestCataloger(t, NewApkdbCataloger())
 		})
 	}

syft/pkg/cataloger/apkdb/parse_apk_db.go

@@ -3,7 +3,9 @@ package apkdb
 import (
 	"bufio"
 	"fmt"
+	"io"
 	"path"
+	"regexp"
 	"strconv"
 	"strings"
 
@@ -20,11 +22,15 @@ import (
 // integrity check
 var _ generic.Parser = parseApkDB
 
+var (
+	repoRegex = regexp.MustCompile(`(?m)^https://.*\.alpinelinux\.org/alpine/v([^/]+)/([a-zA-Z0-9_]+)$`)
+)
+
 // parseApkDB parses packages from a given APK installed DB file. For more
 // information on specific fields, see https://wiki.alpinelinux.org/wiki/Apk_spec.
 //
-//nolint:funlen
-func parseApkDB(_ source.FileResolver, env *generic.Environment, reader source.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+//nolint:funlen,gocognit
+func parseApkDB(resolver source.FileResolver, env *generic.Environment, reader source.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
 	scanner := bufio.NewScanner(reader)
 
 	var apks []pkg.ApkMetadata
@@ -101,6 +107,19 @@ func parseApkDB(_ source.FileResolver, env *generic.Environment, reader source.L
 	if env != nil {
 		r = env.LinuxRelease
 	}
+	// this is somewhat ugly, but better than completely failing when we can't find the release,
+	// e.g. embedded deeper in the tree, like containers or chroots.
+	// but we now have no way of handling different repository sources. On the other hand,
+	// we never could before this. At least now, we can handle some.
+	// This should get fixed with https://gitlab.alpinelinux.org/alpine/apk-tools/-/issues/10875
+	if r == nil {
+		// find the repositories file from the relative directory of the DB file
+		releases := findReleases(resolver, reader.Location.RealPath)
+
+		if len(releases) > 0 {
+			r = &releases[0]
+		}
+	}
 
 	pkgs := make([]pkg.Package, 0, len(apks))
 	for _, apk := range apks {
@@ -110,6 +129,58 @@ func parseApkDB(_ source.FileResolver, env *generic.Environment, reader source.L
 	return pkgs, discoverPackageDependencies(pkgs), nil
 }
 
+func findReleases(resolver source.FileResolver, dbPath string) []linux.Release {
+	if resolver == nil {
+		return nil
+	}
+
+	reposLocation := path.Clean(path.Join(path.Dir(dbPath), "../../../etc/apk/repositories"))
+	locations, err := resolver.FilesByPath(reposLocation)
+	if err != nil {
+		log.Tracef("unable to find APK repositories file %q: %+v", reposLocation, err)
+		return nil
+	}
+
+	if len(locations) == 0 {
+		return nil
+	}
+	location := locations[0]
+
+	reposReader, err := resolver.FileContentsByLocation(location)
+	if err != nil {
+		log.Tracef("unable to fetch contents for APK repositories file %q: %+v", reposLocation, err)
+		return nil
+	}
+
+	return parseReleasesFromAPKRepository(source.LocationReadCloser{
+		Location:   location,
+		ReadCloser: reposReader,
+	})
+}
+
+func parseReleasesFromAPKRepository(reader source.LocationReadCloser) []linux.Release {
+	var releases []linux.Release
+
+	reposB, err := io.ReadAll(reader)
+	if err != nil {
+		log.Tracef("unable to read APK repositories file %q: %+v", reader.Location.RealPath, err)
+		return nil
+	}
+
+	parts := repoRegex.FindAllStringSubmatch(string(reposB), -1)
+	for _, part := range parts {
+		if len(part) >= 3 {
+			releases = append(releases, linux.Release{
+				Name:      "Alpine Linux",
+				ID:        "alpine",
+				VersionID: part[1],
+			})
+		}
+	}
+
+	return releases
+}
+
 func parseApkField(line string) *apkField {
 	parts := strings.SplitN(line, ":", 2)
 	if len(parts) != 2 {

syft/pkg/cataloger/apkdb/parse_apk_db_test.go

@@ -1,8 +1,10 @@
 package apkdb
 
 import (
+	"io"
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/google/go-cmp/cmp"
@@ -1186,3 +1188,49 @@ func Test_stripVersionSpecifier(t *testing.T) {
 		})
 	}
 }
+
+func TestParseReleasesFromAPKRepository(t *testing.T) {
+	tests := []struct {
+		repos string
+		want  []linux.Release
+		desc  string
+	}{
+		{
+			"https://foo.alpinelinux.org/alpine/v3.14/main",
+			[]linux.Release{
+				{Name: "Alpine Linux", ID: "alpine", VersionID: "3.14"},
+			},
+			"single repo",
+		},
+		{
+			`https://foo.alpinelinux.org/alpine/v3.14/main
+https://foo.alpinelinux.org/alpine/v3.14/community`,
+			[]linux.Release{
+				{Name: "Alpine Linux", ID: "alpine", VersionID: "3.14"},
+				{Name: "Alpine Linux", ID: "alpine", VersionID: "3.14"},
+			},
+			"multiple repos",
+		},
+		{
+			``,
+			nil,
+			"empty",
+		},
+		{
+			`https://foo.bar.org/alpine/v3.14/main
+https://foo.them.org/alpine/v3.14/community`,
+			nil,
+			"invalid repos",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.desc, func(t *testing.T) {
+			reposReader := io.NopCloser(strings.NewReader(tt.repos))
+			got := parseReleasesFromAPKRepository(source.LocationReadCloser{
+				Location:   source.NewLocation("test"),
+				ReadCloser: reposReader,
+			})
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}

syft/pkg/cataloger/binary/cataloger.go

@@ -74,12 +74,7 @@ func catalog(resolver source.FileResolver, cls classifier) (packages []pkg.Packa
 		return nil, err
 	}
 	for _, location := range locations {
-		reader, err := resolver.FileContentsByLocation(location)
-		if err != nil {
-			return nil, err
-		}
-		locationReader := source.NewLocationReadCloser(location, reader)
-		pkgs, err := cls.EvidenceMatcher(cls, locationReader)
+		pkgs, err := cls.EvidenceMatcher(resolver, cls, location)
 		if err != nil {
 			return nil, err
 		}

syft/pkg/cataloger/binary/cataloger_test.go

@@ -4,8 +4,11 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"strings"
 	"testing"
 
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -68,25 +71,6 @@ func Test_Cataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 				Metadata:  metadata("postgresql-binary"),
 			},
 		},
-		{
-			name:       "positive-python-duplicates",
-			fixtureDir: "test-fixtures/classifiers/positive/python-duplicates",
-			expected: pkg.Package{
-				Name:      "python",
-				Version:   "3.8.16",
-				Type:      "binary",
-				PURL:      "pkg:generic/python@3.8.16",
-				Locations: locations("dir/python3.8", "python3.8", "libpython3.8.so", "patchlevel.h"),
-				Metadata: pkg.BinaryMetadata{
-					Matches: []pkg.ClassifierMatch{
-						match("python-binary", "dir/python3.8"),
-						match("python-binary", "python3.8"),
-						match("python-binary-lib", "libpython3.8.so"),
-						match("cpython-source", "patchlevel.h"),
-					},
-				},
-			},
-		},
 		{
 			name:       "positive-traefik-2.9.6",
 			fixtureDir: "test-fixtures/classifiers/positive/traefik-2.9.6",
@@ -308,32 +292,116 @@ func Test_Cataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			fixtureDir: "test-fixtures/classifiers/positive/python-binary-lib-3.7",
 			expected: pkg.Package{
 				Name:      "python",
-				Version:   "3.7.4a-vZ9",
-				PURL:      "pkg:generic/python@3.7.4a-vZ9",
+				Version:   "3.7.4",
+				PURL:      "pkg:generic/python@3.7.4",
 				Locations: locations("libpython3.7.so"),
 				Metadata:  metadata("python-binary-lib"),
 			},
 		},
+		{
+			name:       "positive-python-3.11.2-from-shared-lib",
+			fixtureDir: "test-fixtures/classifiers/dynamic/python-binary-shared-lib-3.11",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.11.2",
+				PURL:      "pkg:generic/python@3.11.2",
+				Locations: locations("python3", "libpython3.11.so.1.0"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("python-binary", "python3"),
+						match("python-binary", "libpython3.11.so.1.0"),
+						match("python-binary-lib", "libpython3.11.so.1.0"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-python-3.9-from-shared-redhat-lib",
+			fixtureDir: "test-fixtures/classifiers/dynamic/python-binary-shared-lib-redhat-3.9",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.9.13",
+				PURL:      "pkg:generic/python@3.9.13",
+				Locations: locations("python3.9", "libpython3.9.so.1.0"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("python-binary", "python3.9"),
+						match("python-binary", "libpython3.9.so.1.0"),
+						match("python-binary-lib", "libpython3.9.so.1.0"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-python-binary-with-version-3.9",
+			fixtureDir: "test-fixtures/classifiers/dynamic/python-binary-with-version-3.9",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.9.2",
+				PURL:      "pkg:generic/python@3.9.2",
+				Locations: locations("python3.9"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("python-binary", "python3.9"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-python-binary-3.4-alpine",
+			fixtureDir: "test-fixtures/classifiers/dynamic/python-binary-3.4-alpine",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.4.10",
+				PURL:      "pkg:generic/python@3.4.10",
+				Locations: locations("python3.4", "libpython3.4m.so.1.0"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("python-binary", "python3.4"),
+						match("python-binary", "libpython3.4m.so.1.0"),
+						match("python-binary-lib", "libpython3.4m.so.1.0"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-python-3.5-with-incorrect-match",
+			fixtureDir: "test-fixtures/classifiers/positive/python-3.5-with-incorrect-match",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.5.3",
+				PURL:      "pkg:generic/python@3.5.3",
+				Locations: locations("python3.5"),
+				Metadata:  metadata("python-binary"),
+			},
+		},
 		{
 			name:       "positive-python3.6",
 			fixtureDir: "test-fixtures/classifiers/positive/python-binary-3.6",
 			expected: pkg.Package{
 				Name:      "python",
-				Version:   "3.6.3a-vZ9",
-				PURL:      "pkg:generic/python@3.6.3a-vZ9",
+				Version:   "3.6.3",
+				PURL:      "pkg:generic/python@3.6.3",
 				Locations: locations("python3.6"),
 				Metadata:  metadata("python-binary"),
 			},
 		},
 		{
-			name:       "positive-patchlevel.h",
-			fixtureDir: "test-fixtures/classifiers/positive/python-source-3.9",
+			name:       "positive-python-duplicates",
+			fixtureDir: "test-fixtures/classifiers/positive/python-duplicates",
 			expected: pkg.Package{
 				Name:      "python",
-				Version:   "3.9-aZ5",
-				PURL:      "pkg:generic/python@3.9-aZ5",
-				Locations: locations("patchlevel.h"),
-				Metadata:  metadata("cpython-source"),
+				Version:   "3.8.16",
+				Type:      "binary",
+				PURL:      "pkg:generic/python@3.8.16",
+				Locations: locations("dir/python3.8", "python3.8", "libpython3.8.so"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("python-binary", "dir/python3.8"),
+						match("python-binary", "python3.8"),
+						match("python-binary-lib", "libpython3.8.so"),
+					},
+				},
 			},
 		},
 		{
@@ -475,6 +543,52 @@ func Test_Cataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 				Metadata:  metadata("rust-standard-library-linux"),
 			},
 		},
+		{
+			name:       "positive-ruby-3.2.1",
+			fixtureDir: "test-fixtures/classifiers/dynamic/ruby-library-3.2.1",
+			expected: pkg.Package{
+				Name:      "ruby",
+				Version:   "3.2.1",
+				Type:      "binary",
+				PURL:      "pkg:generic/ruby@3.2.1",
+				Locations: locations("ruby", "libruby.so.3.2.1"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("ruby-binary", "ruby"),
+						match("ruby-binary", "libruby.so.3.2.1"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-ruby-2.7.7",
+			fixtureDir: "test-fixtures/classifiers/dynamic/ruby-library-2.7.7",
+			expected: pkg.Package{
+				Name:      "ruby",
+				Version:   "2.7.7p221",
+				Type:      "binary",
+				PURL:      "pkg:generic/ruby@2.7.7p221",
+				Locations: locations("ruby", "libruby.so.2.7.7"),
+				Metadata: pkg.BinaryMetadata{
+					Matches: []pkg.ClassifierMatch{
+						match("ruby-binary", "ruby"),
+						match("ruby-binary", "libruby.so.2.7.7"),
+					},
+				},
+			},
+		},
+		{
+			name:       "positive-ruby-1.9.3p551",
+			fixtureDir: "test-fixtures/classifiers/positive/ruby-1.9.3p551",
+			expected: pkg.Package{
+				Name:      "ruby",
+				Version:   "1.9.3p551",
+				Type:      "binary",
+				PURL:      "pkg:generic/ruby@1.9.3p551",
+				Locations: locations("ruby"),
+				Metadata:  metadata("ruby-binary"),
+			},
+		},
 	}
 
 	for _, test := range tests {
@@ -490,20 +604,9 @@ func Test_Cataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			packages, _, err := c.Catalog(resolver)
 			require.NoError(t, err)
 
-			for _, p := range packages {
-				expectedLocations := test.expected.Locations.ToSlice()
-				gotLocations := p.Locations.ToSlice()
-				require.Len(t, gotLocations, len(expectedLocations))
+			require.Len(t, packages, 1)
 
-				for i, expectedLocation := range expectedLocations {
-					gotLocation := gotLocations[i]
-					if expectedLocation.RealPath != gotLocation.RealPath {
-						t.Fatalf("locations do not match; expected: %v got: %v", expectedLocations, gotLocations)
-					}
-				}
-
-				assertPackagesAreEqual(t, test.expected, p)
-			}
+			assertPackagesAreEqual(t, test.expected, packages[0])
 		})
 	}
 }
@@ -611,6 +714,21 @@ func match(classifier string, paths ...string) pkg.ClassifierMatch {
 }
 
 func assertPackagesAreEqual(t *testing.T, expected pkg.Package, p pkg.Package) {
+	var failMessages []string
+	expectedLocations := expected.Locations.ToSlice()
+	gotLocations := p.Locations.ToSlice()
+
+	if len(expectedLocations) != len(gotLocations) {
+		failMessages = append(failMessages, "locations are not equal length")
+	} else {
+		for i, expectedLocation := range expectedLocations {
+			gotLocation := gotLocations[i]
+			if expectedLocation.RealPath != gotLocation.RealPath {
+				failMessages = append(failMessages, fmt.Sprintf("locations do not match; expected: %v got: %v", expectedLocation.RealPath, gotLocation.RealPath))
+			}
+		}
+	}
+
 	m1 := expected.Metadata.(pkg.BinaryMetadata).Matches
 	m2 := p.Metadata.(pkg.BinaryMetadata).Matches
 	matches := true
@@ -633,17 +751,26 @@ func assertPackagesAreEqual(t *testing.T, expected pkg.Package, p pkg.Package) {
 	} else {
 		matches = false
 	}
+
+	if !matches {
+		failMessages = append(failMessages, "classifier matches not equal")
+	}
 	if expected.Name != p.Name ||
 		expected.Version != p.Version ||
-		expected.PURL != p.PURL ||
-		!matches {
-		assert.Failf(t, "packages not equal", "%v != %v", stringifyPkg(expected), stringifyPkg(p))
+		expected.PURL != p.PURL {
+		failMessages = append(failMessages, "packages do not match")
 	}
-}
 
-func stringifyPkg(p pkg.Package) string {
-	matches := p.Metadata.(pkg.BinaryMetadata).Matches
-	return fmt.Sprintf("(name=%s, version=%s, purl=%s, matches=%+v)", p.Name, p.Version, p.PURL, matches)
+	if len(failMessages) > 0 {
+		assert.Failf(t, strings.Join(failMessages, "; "), "diff: %s",
+			cmp.Diff(expected, p,
+				cmp.Transformer("Locations", func(l source.LocationSet) []source.Location {
+					return l.ToSlice()
+				}),
+				cmpopts.IgnoreUnexported(pkg.Package{}, source.Location{}),
+				cmpopts.IgnoreFields(pkg.Package{}, "CPEs", "FoundBy", "MetadataType", "Type"),
+			))
+	}
 }
 
 type panicyResolver struct {

syft/pkg/cataloger/binary/classifier.go

@@ -2,14 +2,19 @@ package binary
 
 import (
 	"bytes"
+	"debug/elf"
+	"debug/macho"
+	"debug/pe"
 	"fmt"
 	"io"
 	"reflect"
 	"regexp"
+	"strings"
 	"text/template"
 
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/internal/unionreader"
@@ -49,12 +54,12 @@ type classifier struct {
 }
 
 // evidenceMatcher is a function called to catalog Packages that match some sort of evidence
-type evidenceMatcher func(classifier classifier, reader source.LocationReadCloser) ([]pkg.Package, error)
+type evidenceMatcher func(resolver source.FileResolver, classifier classifier, location source.Location) ([]pkg.Package, error)
 
 func evidenceMatchers(matchers ...evidenceMatcher) evidenceMatcher {
-	return func(classifier classifier, reader source.LocationReadCloser) ([]pkg.Package, error) {
+	return func(resolver source.FileResolver, classifier classifier, location source.Location) ([]pkg.Package, error) {
 		for _, matcher := range matchers {
-			match, err := matcher(classifier, reader)
+			match, err := matcher(resolver, classifier, location)
 			if err != nil {
 				return nil, err
 			}
@@ -68,12 +73,17 @@ func evidenceMatchers(matchers ...evidenceMatcher) evidenceMatcher {
 
 func fileNameTemplateVersionMatcher(fileNamePattern string, contentTemplate string) evidenceMatcher {
 	pat := regexp.MustCompile(fileNamePattern)
-	return func(classifier classifier, reader source.LocationReadCloser) ([]pkg.Package, error) {
-		if !pat.MatchString(reader.RealPath) {
+	return func(resolver source.FileResolver, classifier classifier, location source.Location) ([]pkg.Package, error) {
+		if !pat.MatchString(location.RealPath) {
 			return nil, nil
 		}
 
-		filepathNamedGroupValues := internal.MatchNamedCaptureGroups(pat, reader.RealPath)
+		filepathNamedGroupValues := internal.MatchNamedCaptureGroups(pat, location.RealPath)
+
+		// versions like 3.5 should not match any character, but explicit dot
+		for k, v := range filepathNamedGroupValues {
+			filepathNamedGroupValues[k] = strings.ReplaceAll(v, ".", "\\.")
+		}
 
 		tmpl, err := template.New("").Parse(contentTemplate)
 		if err != nil {
@@ -91,26 +101,70 @@ func fileNameTemplateVersionMatcher(fileNamePattern string, contentTemplate stri
 			return nil, fmt.Errorf("unable to compile rendered regex=%q: %w", patternBuf.String(), err)
 		}
 
-		contents, err := getContents(reader)
+		contents, err := getContents(resolver, location)
 		if err != nil {
 			return nil, fmt.Errorf("unable to get read contents for file: %w", err)
 		}
 
 		matchMetadata := internal.MatchNamedCaptureGroups(tmplPattern, string(contents))
-		return singlePackage(classifier, reader, matchMetadata), nil
+		return singlePackage(classifier, location, matchMetadata), nil
 	}
 }
 
 func fileContentsVersionMatcher(pattern string) evidenceMatcher {
 	pat := regexp.MustCompile(pattern)
-	return func(classifier classifier, reader source.LocationReadCloser) ([]pkg.Package, error) {
-		contents, err := getContents(reader)
+	return func(resolver source.FileResolver, classifier classifier, location source.Location) ([]pkg.Package, error) {
+		contents, err := getContents(resolver, location)
 		if err != nil {
 			return nil, fmt.Errorf("unable to get read contents for file: %w", err)
 		}
 
 		matchMetadata := internal.MatchNamedCaptureGroups(pat, string(contents))
-		return singlePackage(classifier, reader, matchMetadata), nil
+		return singlePackage(classifier, location, matchMetadata), nil
+	}
+}
+
+//nolint:gocognit
+func sharedLibraryLookup(sharedLibraryPattern string, sharedLibraryMatcher evidenceMatcher) evidenceMatcher {
+	pat := regexp.MustCompile(sharedLibraryPattern)
+	return func(resolver source.FileResolver, classifier classifier, location source.Location) (packages []pkg.Package, _ error) {
+		libs, err := sharedLibraries(resolver, location)
+		if err != nil {
+			return nil, err
+		}
+		for _, lib := range libs {
+			if !pat.MatchString(lib) {
+				continue
+			}
+
+			locations, err := resolver.FilesByGlob("**/" + lib)
+			if err != nil {
+				return nil, err
+			}
+			for _, libraryLication := range locations {
+				pkgs, err := sharedLibraryMatcher(resolver, classifier, libraryLication)
+				if err != nil {
+					return nil, err
+				}
+				for _, p := range pkgs {
+					// set the source binary as the first location
+					locationSet := source.NewLocationSet(location)
+					locationSet.Add(p.Locations.ToSlice()...)
+					p.Locations = locationSet
+					meta, _ := p.Metadata.(pkg.BinaryMetadata)
+					p.Metadata = pkg.BinaryMetadata{
+						Matches: append([]pkg.ClassifierMatch{
+							{
+								Classifier: classifier.Class,
+								Location:   location,
+							},
+						}, meta.Matches...),
+					}
+					packages = append(packages, p)
+				}
+			}
+		}
+		return packages, nil
 	}
 }
 
@@ -122,7 +176,7 @@ func mustPURL(purl string) packageurl.PackageURL {
 	return p
 }
 
-func singlePackage(classifier classifier, reader source.LocationReadCloser, matchMetadata map[string]string) []pkg.Package {
+func singlePackage(classifier classifier, location source.Location, matchMetadata map[string]string) []pkg.Package {
 	version, ok := matchMetadata["version"]
 	if !ok {
 		return nil
@@ -140,7 +194,7 @@ func singlePackage(classifier classifier, reader source.LocationReadCloser, matc
 	p := pkg.Package{
 		Name:         classifier.Package,
 		Version:      version,
-		Locations:    source.NewLocationSet(reader.Location),
+		Locations:    source.NewLocationSet(location),
 		Type:         pkg.BinaryPkg,
 		CPEs:         cpes,
 		FoundBy:      catalogerName,
@@ -149,7 +203,7 @@ func singlePackage(classifier classifier, reader source.LocationReadCloser, matc
 			Matches: []pkg.ClassifierMatch{
 				{
 					Classifier: classifier.Class,
-					Location:   reader.Location,
+					Location:   location,
 				},
 			},
 		},
@@ -174,8 +228,13 @@ func singlePackage(classifier classifier, reader source.LocationReadCloser, matc
 	return []pkg.Package{p}
 }
 
-func getContents(reader source.LocationReadCloser) ([]byte, error) {
-	unionReader, err := unionreader.GetUnionReader(reader.ReadCloser)
+func getContents(resolver source.FileResolver, location source.Location) ([]byte, error) {
+	reader, err := resolver.FileContentsByLocation(location)
+	if err != nil {
+		return nil, err
+	}
+
+	unionReader, err := unionreader.GetUnionReader(reader)
 	if err != nil {
 		return nil, fmt.Errorf("unable to get union reader for file: %w", err)
 	}
@@ -195,3 +254,43 @@ func singleCPE(cpeString string) []cpe.CPE {
 		cpe.Must(cpeString),
 	}
 }
+
+// sharedLibraries returns a list of all shared libraries found within a binary, currently
+// supporting: elf, macho, and windows pe
+func sharedLibraries(resolver source.FileResolver, location source.Location) ([]string, error) {
+	contents, err := getContents(resolver, location)
+	if err != nil {
+		return nil, err
+	}
+
+	r := bytes.NewReader(contents)
+
+	e, _ := elf.NewFile(r)
+	if e != nil {
+		symbols, err := e.ImportedLibraries()
+		if err != nil {
+			log.Debugf("unable to read elf binary at: %s -- %s", location.RealPath, err)
+		}
+		return symbols, nil
+	}
+
+	m, _ := macho.NewFile(r)
+	if m != nil {
+		symbols, err := m.ImportedLibraries()
+		if err != nil {
+			log.Debugf("unable to read macho binary at: %s -- %s", location.RealPath, err)
+		}
+		return symbols, nil
+	}
+
+	p, _ := pe.NewFile(r)
+	if p != nil {
+		symbols, err := p.ImportedLibraries()
+		if err != nil {
+			log.Debugf("unable to read pe binary at: %s -- %s", location.RealPath, err)
+		}
+		return symbols, nil
+	}
+
+	return nil, nil
+}

syft/pkg/cataloger/binary/classifier_test.go

@@ -67,10 +67,8 @@ func Test_ClassifierCPEs(t *testing.T) {
 			locations, err := resolver.FilesByPath(test.fixture)
 			require.NoError(t, err)
 			require.Len(t, locations, 1)
-			location := locations[0]
-			readCloser, err := resolver.FileContentsByLocation(location)
-			require.NoError(t, err)
-			pkgs, err := test.classifier.EvidenceMatcher(test.classifier, source.NewLocationReadCloser(location, readCloser))
+
+			pkgs, err := test.classifier.EvidenceMatcher(resolver, test.classifier, locations[0])
 			require.NoError(t, err)
 
 			require.Len(t, pkgs, 1)

syft/pkg/cataloger/binary/default_classifiers.go

@@ -9,9 +9,16 @@ var defaultClassifiers = []classifier{
 	{
 		Class:    "python-binary",
 		FileGlob: "**/python*",
-		EvidenceMatcher: fileNameTemplateVersionMatcher(
-			`(.*/|^)python(?P<version>[0-9]+\.[0-9]+)$`,
-			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
+		EvidenceMatcher: evidenceMatchers(
+			// try to find version information from libpython shared libraries
+			sharedLibraryLookup(
+				`^libpython[0-9]+(?:\.[0-9]+)+[a-z]?\.so.*$`,
+				libpythonMatcher),
+			// check for version information in the binary
+			fileNameTemplateVersionMatcher(
+				`(?:.*/|^)python(?P<version>[0-9]+(?:\.[0-9]+)+)$`,
+				pythonVersionTemplate),
+		),
 		Package: "python",
 		PURL:    mustPURL("pkg:generic/python@version"),
 		CPEs: []cpe.CPE{
@@ -20,25 +27,11 @@ var defaultClassifiers = []classifier{
 		},
 	},
 	{
-		Class:    "python-binary-lib",
-		FileGlob: "**/libpython*.so*",
-		EvidenceMatcher: fileNameTemplateVersionMatcher(
-			`(.*/|^)libpython(?P<version>[0-9]+\.[0-9]+).so.*$`,
-			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
-		Package: "python",
-		PURL:    mustPURL("pkg:generic/python@version"),
-		CPEs: []cpe.CPE{
-			cpe.Must("cpe:2.3:a:python_software_foundation:python:*:*:*:*:*:*:*:*"),
-			cpe.Must("cpe:2.3:a:python:python:*:*:*:*:*:*:*:*"),
-		},
-	},
-	{
-		Class:    "cpython-source",
-		FileGlob: "**/patchlevel.h",
-		EvidenceMatcher: fileContentsVersionMatcher(
-			`(?m)#define\s+PY_VERSION\s+"?(?P<version>[0-9\.\-_a-zA-Z]+)"?`),
-		Package: "python",
-		PURL:    mustPURL("pkg:generic/python@version"),
+		Class:           "python-binary-lib",
+		FileGlob:        "**/libpython*.so*",
+		EvidenceMatcher: libpythonMatcher,
+		Package:         "python",
+		PURL:            mustPURL("pkg:generic/python@version"),
 		CPEs: []cpe.CPE{
 			cpe.Must("cpe:2.3:a:python_software_foundation:python:*:*:*:*:*:*:*:*"),
 			cpe.Must("cpe:2.3:a:python:python:*:*:*:*:*:*:*:*"),
@@ -227,4 +220,31 @@ var defaultClassifiers = []classifier{
 		PURL:    mustPURL("pkg:generic/rust@version"),
 		CPEs:    singleCPE("cpe:2.3:a:rust-lang:rust:*:*:*:*:*:*:*:*"),
 	},
+	{
+		Class:    "ruby-binary",
+		FileGlob: "**/ruby",
+		EvidenceMatcher: evidenceMatchers(
+			rubyMatcher,
+			sharedLibraryLookup(
+				// try to find version information from libruby shared libraries
+				`^libruby\.so.*$`,
+				rubyMatcher),
+		),
+		Package: "ruby",
+		PURL:    mustPURL("pkg:generic/ruby@version"),
+		CPEs:    singleCPE("cpe:2.3:a:ruby-lang:ruby:*:*:*:*:*:*:*:*"),
+	},
 }
+
+// in both binaries and shared libraries, the version pattern is [NUL]3.11.2[NUL]
+var pythonVersionTemplate = `(?m)\x00(?P<version>{{ .version }}[-._a-zA-Z0-9]*)\x00`
+
+var libpythonMatcher = fileNameTemplateVersionMatcher(
+	`(?:.*/|^)libpython(?P<version>[0-9]+(?:\.[0-9]+)+)[a-z]?\.so.*$`,
+	pythonVersionTemplate,
+)
+
+var rubyMatcher = fileContentsVersionMatcher(
+	// ruby 3.2.1 (2023-02-08 revision 31819e82c8) [x86_64-linux]
+	// ruby 2.7.7p221 (2022-11-24 revision 168ec2b1e5) [x86_64-linux]
+	`(?m)ruby (?P<version>[0-9]\.[0-9]\.[0-9](p[0-9]+)?) `)

syft/pkg/cataloger/binary/test-fixtures/.gitignore

@@ -0,0 +1 @@
+classifiers/dynamic

syft/pkg/cataloger/binary/test-fixtures/Makefile

@@ -0,0 +1,74 @@
+.PHONY: all
+all: \
+	classifiers/dynamic/python-binary-shared-lib-3.11 \
+	classifiers/dynamic/python-binary-shared-lib-redhat-3.9 \
+	classifiers/dynamic/python-binary-with-version-3.9 \
+	classifiers/dynamic/python-binary-3.4-alpine \
+	classifiers/dynamic/ruby-library-3.2.1 \
+	classifiers/dynamic/ruby-library-2.7.7
+
+classifiers/dynamic/python-binary-shared-lib-3.11:
+	$(eval $@_image := "python:3.11-slim@sha256:0b106e1d2bf485c2a41474bc9cd5103e9eea4e179f40f10741b53b127059221e")
+	./get-image-file.sh $($@_image) \
+		/usr/local/bin/python3.11 \
+		$@/python3
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libpython3.11.so.1.0 \
+		$@/libpython3.11.so.1.0
+
+classifiers/dynamic/python-binary-shared-lib-redhat-3.9:
+	$(eval $@_image := "registry.access.redhat.com/ubi8/python-39@sha256:f3cf958b96ce016b63e3e163e488f52e42891304dafef5a0811563f22e3cbad0")
+	./get-image-file.sh $($@_image) \
+		/usr/bin/python3.9 \
+		$@/python3.9
+	./get-image-file.sh $($@_image) \
+		/usr/lib64/libpython3.9.so.1.0 \
+		$@/libpython3.9.so.1.0
+
+classifiers/dynamic/python-binary-with-version-3.9:
+	$(eval $@_image := "python:3.9.16-bullseye@sha256:93fb93c461a2e47a2176706fad1f39eaacd5dd40e19c0b018699a28c03eb2e2a")
+	./get-image-file.sh $($@_image) \
+		/usr/bin/python3.9 \
+		$@/python3.9
+
+classifiers/dynamic/python-binary-3.4-alpine:
+	$(eval $@_image := "python:3.4-alpine@sha256:c210b660e2ea553a7afa23b41a6ed112f85dbce25cbcb567c75dfe05342a4c4b")
+	./get-image-file.sh $($@_image) \
+		/usr/local/bin/python3.4 \
+		$@/python3.4
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libpython3.4m.so.1.0 \
+		$@/libpython3.4m.so.1.0
+
+classifiers/dynamic/ruby-library-3.2.1:
+	$(eval $@_image := "ruby:3.2.1-bullseye@sha256:b4a140656b0c5d26c0a80559b228b4d343f3fdbf56682fcbe88f6db1fa9afa6b")
+	./get-image-file.sh $($@_image) \
+		/usr/local/bin/ruby \
+		$@/ruby
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libruby.so.3.2.1 \
+		$@/libruby.so.3.2.1
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libruby.so.3.2 \
+		$@/libruby.so.3.2
+
+classifiers/dynamic/ruby-library-2.7.7:
+	$(eval $@_image := "ruby:2.7.7-bullseye@sha256:055191740a063f33fef1f09423e5ed8f91143aae62a3772a90910118464c5120")
+	./get-image-file.sh $($@_image) \
+		/usr/local/bin/ruby \
+		$@/ruby
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libruby.so.2.7.7 \
+		$@/libruby.so.2.7.7
+	./get-image-file.sh $($@_image) \
+		/usr/local/lib/libruby.so.2.7 \
+		$@/libruby.so.2.7
+
+.PHONY: clean
+clean:
+	rm -rf classifiers/dynamic
+
+.PHONY: cache.fingerprint
+cache.fingerprint: # for CI
+	$(title,Install test fixture fingerprint)
+	@find ./classifiers/dynamic/* -type f -exec md5sum {} + | awk '{print $1}' | sort | tee /dev/stderr | md5sum | tee cache.fingerprint >> cache.fingerprint

syft/pkg/cataloger/binary/test-fixtures/classifiers/positive/python-source-3.9/patchlevel.h

@@ -1,7 +0,0 @@
-# note: this SHOULD match as python 3.9
-
-some source code...
-
-#define    PY_VERSION   3.9-aZ5
-
-more source!

syft/pkg/cataloger/binary/test-fixtures/classifiers/positive/ruby-1.9.3p551/ruby

@@ -0,0 +1,9 @@
+super from singleton method that is defined to multiple classes is not supported; this will be fixed in 1.9.3 or later
+/usr/local/lib/ruby/site_ruby/1.9.1
+/usr/local/lib/ruby/site_ruby/1.9.1/x86_64-linux
+/usr/local/lib/ruby/vendor_ruby/1.9.1
+/usr/local/lib/ruby/vendor_ruby/1.9.1/x86_64-linux
+/usr/local/lib/ruby/1.9.1
+/usr/local/lib/ruby/1.9.1/x86_64-linux
+ruby 1.9.3p551 (2014-11-13 revision 48407) [x86_64-linux]
+1.9.3

syft/pkg/cataloger/binary/test-fixtures/get-image-file.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+set -uxe
+
+CTRID=$(docker create $1)
+
+function cleanup() {
+  docker rm "${CTRID}"
+}
+
+trap cleanup EXIT
+set +e
+
+mkdir -p $(dirname $3)
+
+docker cp ${CTRID}:$2 $3

syft/pkg/cataloger/common/cpe/candidate_by_package_type.go

@@ -350,6 +350,27 @@ var defaultCandidateRemovals = buildCandidateRemovalLookup(
 			candidateKey{PkgName: "redis"},
 			candidateRemovals{VendorsToRemove: []string{"redis"}},
 		},
+		// NPM packages
+		{
+			pkg.NpmPkg,
+			candidateKey{PkgName: "redis"},
+			candidateRemovals{VendorsToRemove: []string{"redis"}},
+		},
+		{
+			pkg.NpmPkg,
+			candidateKey{PkgName: "php"},
+			candidateRemovals{VendorsToRemove: []string{"php"}},
+		},
+		{
+			pkg.NpmPkg,
+			candidateKey{PkgName: "delegate"},
+			candidateRemovals{VendorsToRemove: []string{"delegate"}},
+		},
+		{
+			pkg.NpmPkg,
+			candidateKey{PkgName: "docker"},
+			candidateRemovals{VendorsToRemove: []string{"docker"}},
+		},
 	})
 
 // buildCandidateLookup is a convenience function for creating the defaultCandidateAdditions set

syft/pkg/cataloger/common/cpe/generate.go

@@ -93,13 +93,6 @@ func candidateVendors(p pkg.Package) []string {
 		}
 	}
 
-	// some ecosystems do not have enough metadata to determine the vendor accurately, in which case we selectively
-	// allow * as a candidate. Note: do NOT allow Java packages to have * vendors.
-	switch p.Language {
-	case pkg.Ruby, pkg.JavaScript:
-		vendors.addValue(wfn.Any)
-	}
-
 	switch p.MetadataType {
 	case pkg.RpmMetadataType:
 		vendors.union(candidateVendorsForRPM(p))
@@ -111,8 +104,15 @@ func candidateVendors(p pkg.Package) []string {
 		vendors.union(candidateVendorsForJava(p))
 	case pkg.ApkMetadataType:
 		vendors.union(candidateVendorsForAPK(p))
+	case pkg.NpmPackageJSONMetadataType:
+		vendors.union(candidateVendorsForJavascript(p))
 	}
 
+	// We should no longer be generating vendor candidates with these values ["" and "*"]
+	// (since CPEs will match any other value)
+	vendors.removeByValue("")
+	vendors.removeByValue("*")
+
 	// try swapping hyphens for underscores, vice versa, and removing separators altogether
 	addDelimiterVariations(vendors)
 

syft/pkg/cataloger/common/cpe/generate_test.go

@@ -117,15 +117,20 @@ func TestGeneratePackageCPEs(t *testing.T) {
 		{
 			name: "javascript language",
 			p: pkg.Package{
-				Name:     "name",
-				Version:  "3.2",
-				FoundBy:  "some-analyzer",
-				Language: pkg.JavaScript,
-				Type:     pkg.DebPkg,
+				Name:         "name",
+				Version:      "3.2",
+				FoundBy:      "some-analyzer",
+				Language:     pkg.JavaScript,
+				MetadataType: pkg.NpmPackageJSONMetadataType,
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Author: "jon",
+					URL:    "https://github.com/bob/npm-name",
+				},
 			},
 			expected: []string{
 				"cpe:2.3:a:name:name:3.2:*:*:*:*:*:*:*",
-				"cpe:2.3:a:*:name:3.2:*:*:*:*:*:*:*",
+				"cpe:2.3:a:jon:name:3.2:*:*:*:*:*:*:*",
+				"cpe:2.3:a:bob:name:3.2:*:*:*:*:*:*:*",
 			},
 		},
 		{
@@ -142,10 +147,10 @@ func TestGeneratePackageCPEs(t *testing.T) {
 						"someones name",
 						"someones.elses.name@gmail.com",
 					},
+					Homepage: "https://github.com/tom/ruby-name",
 				},
 			},
 			expected: []string{
-				"cpe:2.3:a:*:name:3.2:*:*:*:*:*:*:*",
 				"cpe:2.3:a:name:name:3.2:*:*:*:*:*:*:*",
 				"cpe:2.3:a:ruby-lang:name:3.2:*:*:*:*:*:*:*",
 				"cpe:2.3:a:ruby:name:3.2:*:*:*:*:*:*:*",
@@ -154,6 +159,7 @@ func TestGeneratePackageCPEs(t *testing.T) {
 				"cpe:2.3:a:someones-name:name:3.2:*:*:*:*:*:*:*",
 				"cpe:2.3:a:someones_elses_name:name:3.2:*:*:*:*:*:*:*",
 				"cpe:2.3:a:someones_name:name:3.2:*:*:*:*:*:*:*",
+				"cpe:2.3:a:tom:name:3.2:*:*:*:*:*:*:*",
 			},
 		},
 		{
@@ -641,7 +647,6 @@ func TestGeneratePackageCPEs(t *testing.T) {
 				},
 			},
 			expected: []string{
-				"cpe:2.3:a:*:bundler:2.1.4:*:*:*:*:*:*:*",
 				"cpe:2.3:a:bundler:bundler:2.1.4:*:*:*:*:*:*:*",
 				"cpe:2.3:a:ruby-lang:bundler:2.1.4:*:*:*:*:*:*:*",
 				"cpe:2.3:a:ruby:bundler:2.1.4:*:*:*:*:*:*:*",

syft/pkg/cataloger/common/cpe/javascript.go

@@ -0,0 +1,32 @@
+package cpe
+
+import "github.com/anchore/syft/syft/pkg"
+
+func candidateVendorsForJavascript(p pkg.Package) fieldCandidateSet {
+	if p.MetadataType != pkg.NpmPackageJSONMetadataType {
+		return nil
+	}
+
+	vendors := newFieldCandidateSet()
+	metadata, ok := p.Metadata.(pkg.NpmPackageJSONMetadata)
+	if !ok {
+		return nil
+	}
+
+	if metadata.Author != "" {
+		vendors.add(fieldCandidate{
+			value:                 normalizePersonName(stripEmailSuffix(metadata.Author)),
+			disallowSubSelections: true,
+		})
+	}
+
+	if metadata.URL != "" {
+		vendors.union(candidateVendorsFromURL(metadata.URL))
+	}
+
+	if metadata.Homepage != "" {
+		vendors.union(candidateVendorsFromURL(metadata.Homepage))
+	}
+
+	return vendors
+}

syft/pkg/cataloger/common/cpe/ruby.go

@@ -17,5 +17,10 @@ func candidateVendorsForRuby(p pkg.Package) fieldCandidateSet {
 			disallowSubSelections: true,
 		})
 	}
+
+	if metadata.Homepage != "" {
+		vendors.union(candidateVendorsFromURL(metadata.Homepage))
+	}
+
 	return vendors
 }

syft/pkg/cataloger/common/cpe/vendors_from_url.go

@@ -21,7 +21,7 @@ var (
 	}
 
 	vendorExtractionPatterns = []*regexp.Regexp{
-		regexp.MustCompile(`^https://(?:github|gitlab)\.com/(?P<vendor>[\w\-]*?)/.*$`),
+		regexp.MustCompile(`^(?:https|http|git)://(?:github|gitlab)\.com/(?P<vendor>[\w\-]*?)/.*$`),
 	}
 )
 

syft/pkg/cataloger/common/cpe/vendors_from_url_test.go

@@ -52,6 +52,16 @@ func Test_candidateVendorsFromURL(t *testing.T) {
 			url:      "https://github.com/armadillo/abcxyz-12345/a/b/c/d/e/f/g",
 			expected: []string{"armadillo"},
 		},
+		{
+			name:     "github username from git://",
+			url:      "git://github.com/abc/xyz.git",
+			expected: []string{"abc"},
+		},
+		{
+			name:     "github username from http://",
+			url:      "http://github.com/abc/xyz.git",
+			expected: []string{"abc"},
+		},
 	}
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {

syft/pkg/cataloger/dotnet/package.go

@@ -45,7 +45,17 @@ func packageURL(m pkg.DotnetDepsMetadata) string {
 	var qualifiers packageurl.Qualifiers
 
 	return packageurl.NewPackageURL(
-		packageurl.TypeDotnet,
+		// This originally was packageurl.TypeDotnet, but this isn't a valid PURL type, according to:
+		// https://github.com/package-url/purl-spec/blob/master/PURL-TYPES.rst
+		// Some history:
+		//   https://github.com/anchore/packageurl-go/pull/8 added the type to Anchore's fork
+		//   due to this PR: https://github.com/anchore/syft/pull/951
+		// There were questions about "dotnet" being the right purlType at the time, but it was
+		// acknowledged that scanning a dotnet file does not necessarily mean the packages found
+		// are nuget packages and so the alternate type was added. Since this is still an invalid
+		// PURL type, however, we will use TypeNuget and revisit at such time there is a better
+		// official PURL type available.
+		packageurl.TypeNuget,
 		"",
 		m.Name,
 		m.Version,

syft/pkg/cataloger/dotnet/parse_dotnet_deps_test.go

@@ -16,7 +16,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "AWSSDK.Core",
 			Version:      "3.7.10.6",
-			PURL:         "pkg:dotnet/AWSSDK.Core@3.7.10.6",
+			PURL:         "pkg:nuget/AWSSDK.Core@3.7.10.6",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -32,7 +32,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.DependencyInjection.Abstractions",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.DependencyInjection.Abstractions@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.DependencyInjection.Abstractions@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -48,7 +48,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.DependencyInjection",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.DependencyInjection@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.DependencyInjection@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -64,7 +64,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.Logging.Abstractions",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.Logging.Abstractions@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.Logging.Abstractions@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -80,7 +80,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.Logging",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.Logging@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.Logging@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -97,7 +97,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.Options",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.Options@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.Options@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -113,7 +113,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Microsoft.Extensions.Primitives",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/Microsoft.Extensions.Primitives@6.0.0",
+			PURL:         "pkg:nuget/Microsoft.Extensions.Primitives@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -129,7 +129,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Newtonsoft.Json",
 			Version:      "13.0.1",
-			PURL:         "pkg:dotnet/Newtonsoft.Json@13.0.1",
+			PURL:         "pkg:nuget/Newtonsoft.Json@13.0.1",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -145,7 +145,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Serilog.Sinks.Console",
 			Version:      "4.0.1",
-			PURL:         "pkg:dotnet/Serilog.Sinks.Console@4.0.1",
+			PURL:         "pkg:nuget/Serilog.Sinks.Console@4.0.1",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -161,7 +161,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "Serilog",
 			Version:      "2.10.0",
-			PURL:         "pkg:dotnet/Serilog@2.10.0",
+			PURL:         "pkg:nuget/Serilog@2.10.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -177,7 +177,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "System.Diagnostics.DiagnosticSource",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/System.Diagnostics.DiagnosticSource@6.0.0",
+			PURL:         "pkg:nuget/System.Diagnostics.DiagnosticSource@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,
@@ -193,7 +193,7 @@ func TestParseDotnetDeps(t *testing.T) {
 		{
 			Name:         "System.Runtime.CompilerServices.Unsafe",
 			Version:      "6.0.0",
-			PURL:         "pkg:dotnet/System.Runtime.CompilerServices.Unsafe@6.0.0",
+			PURL:         "pkg:nuget/System.Runtime.CompilerServices.Unsafe@6.0.0",
 			Locations:    fixtureLocationSet,
 			Language:     pkg.Dotnet,
 			Type:         pkg.DotnetPkg,