feat: add catalog delete (#1377 )

docs: remove file classifier (#1397 )
chore: update latest cyclonedx library (#1390 )
2026-10-17 08:37:19 +02:00 · 2022-12-12 12:55:12 -05:00 · 2022-12-08 16:50:29 +00:00 · 2022-12-08 11:36:08 -05:00 · 2022-12-08 10:50:28 -05:00 · 2022-12-08 10:29:27 -05:00
65 changed files with 178902 additions and 6542 deletions
@@ -13,7 +13,7 @@ GOLANGCILINT_VERSION = v1.50.1
 GOSIMPORTS_VERSION = v0.3.4
 BOUNCER_VERSION = v0.4.0
 CHRONICLE_VERSION = v0.4.2
-GORELEASER_VERSION = v1.13.0
+GORELEASER_VERSION = v1.13.1
 YAJSV_VERSION = v1.4.1
 COSIGN_VERSION = v1.13.1
 QUILL_VERSION = v0.2.0
@@ -489,17 +489,6 @@ package:
    # same as -s ; SYFT_PACKAGE_CATALOGER_SCOPE env var
    scope: "squashed"

-# cataloging file classifications is exposed through the power-user subcommand
-file-classification:
-  cataloger:
-    # enable/disable cataloging of file classifications
-    # SYFT_FILE_CLASSIFICATION_CATALOGER_ENABLED env var
-    enabled: true
-
-    # the search space to look for file classifications (options: all-layers, squashed)
-    # SYFT_FILE_CLASSIFICATION_CATALOGER_SCOPE env var
-    scope: "squashed"
-
 # cataloging file contents is exposed through the power-user subcommand
 file-contents:
  cataloger:
@@ -22,7 +22,6 @@ func Tasks(app *config.Application) ([]Task, error) {
 		generateCatalogFileMetadataTask,
 		generateCatalogFileDigestsTask,
 		generateCatalogSecretsTask,
-		generateCatalogFileClassificationsTask,
 		generateCatalogContentsTask,
 	}

@@ -162,34 +161,6 @@ func generateCatalogSecretsTask(app *config.Application) (Task, error) {
 	return task, nil
 }

-func generateCatalogFileClassificationsTask(app *config.Application) (Task, error) {
-	if !app.FileClassification.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	// TODO: in the future we could expose out the classifiers via configuration
-	classifierCataloger, err := file.NewClassificationCataloger(file.DefaultClassifiers)
-	if err != nil {
-		return nil, err
-	}
-
-	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
-		resolver, err := src.FileResolver(app.FileClassification.Cataloger.ScopeOpt)
-		if err != nil {
-			return nil, err
-		}
-
-		result, err := classifierCataloger.Catalog(resolver)
-		if err != nil {
-			return nil, err
-		}
-		results.FileClassifications = result
-		return nil, nil
-	}
-
-	return task, nil
-}
-
 func generateCatalogContentsTask(app *config.Application) (Task, error) {
 	if !app.FileContents.Cataloger.Enabled {
 		return nil, nil
@@ -3,7 +3,7 @@ module github.com/anchore/syft
 go 1.18

 require (
-	github.com/CycloneDX/cyclonedx-go v0.5.2
+	github.com/CycloneDX/cyclonedx-go v0.7.0
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d
 	github.com/acobaugh/osrelease v0.1.0
 	github.com/adrg/xdg v0.3.3
@@ -52,7 +52,7 @@ require (
 require (
 	github.com/Masterminds/sprig/v3 v3.2.2
 	github.com/anchore/go-logger v0.0.0-20220728155337-03b66a5207d8
-	github.com/anchore/stereoscope v0.0.0-20221006201143-d24c9d626b33
+	github.com/anchore/stereoscope v0.0.0-20221208011002-c5ff155d72f1
 	github.com/docker/docker v20.10.17+incompatible
 	github.com/google/go-containerregistry v0.11.0
 	github.com/in-toto/in-toto-golang v0.4.1-0.20221018183522-731d0640b65f
@@ -124,7 +124,7 @@ require (
 	github.com/cncf/udpa/go v0.0.0-20210930031921-04548b0d99d4 // indirect
 	github.com/cncf/xds/go v0.0.0-20211130200136-a8f946100490 // indirect
 	github.com/common-nighthawk/go-figure v0.0.0-20210622060536-734e95fb86be // indirect
-	github.com/containerd/containerd v1.6.8 // indirect
+	github.com/containerd/containerd v1.6.12 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.12.0 // indirect
 	github.com/coreos/go-oidc/v3 v3.4.0 // indirect
 	github.com/coreos/go-semver v0.3.0 // indirect
@@ -208,7 +208,7 @@ require (
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.16 // indirect
 	github.com/mattn/go-runewidth v0.0.13 // indirect
-	github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 // indirect
+	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/miekg/pkcs11 v1.1.1 // indirect
 	github.com/mitchellh/copystructure v1.2.0 // indirect
 	github.com/mitchellh/reflectwalk v1.0.2 // indirect
@@ -153,8 +153,8 @@ github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03
 github.com/BurntSushi/toml v0.4.1 h1:GaI7EiDXDRfa8VshkTj7Fym7ha+y8/XxIgD2okUIjLw=
 github.com/BurntSushi/toml v0.4.1/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
 github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
-github.com/CycloneDX/cyclonedx-go v0.5.2 h1:CkdGw2R/tZWmEbSypJVZG+3+2SAsDjJirfIrG/RbIVg=
-github.com/CycloneDX/cyclonedx-go v0.5.2/go.mod h1:nQCiF4Tvrg5Ieu8qPhYMvzPGMu5I7fANZkrSsJjl5mg=
+github.com/CycloneDX/cyclonedx-go v0.7.0 h1:jNxp8hL7UpcvPDFXjY+Y1ibFtsW+e5zyF9QoSmhK/zg=
+github.com/CycloneDX/cyclonedx-go v0.7.0/go.mod h1:W5Z9w8pTTL+t+yG3PCiFRGlr8PUlE0pGWzKSJbsyXkg=
 github.com/DataDog/zstd v1.4.5 h1:EndNeuB0l9syBZhut0wns3gV1hL8zX8LIu6ZiVHWLIQ=
 github.com/DataDog/zstd v1.4.5/go.mod h1:1jcaCB/ufaK+sKp1NBhlGmpz41jOoPQ35bpF36t7BBo=
 github.com/Djarvur/go-err113 v0.0.0-20210108212216-aea10b59be24/go.mod h1:4UJr5HIiMZrwgkSPdsjy2uOQExX/WEILpIrO9UPGuXs=
@@ -196,7 +196,7 @@ github.com/Microsoft/hcsshim v0.8.20/go.mod h1:+w2gRZ5ReXQhFOrvSQeNfhrYB/dg3oDwT
 github.com/Microsoft/hcsshim v0.8.21/go.mod h1:+w2gRZ5ReXQhFOrvSQeNfhrYB/dg3oDwTOcER2fw4I4=
 github.com/Microsoft/hcsshim v0.8.23/go.mod h1:4zegtUJth7lAvFyc6cH2gGQ5B3OFQim01nnU2M8jKDg=
 github.com/Microsoft/hcsshim v0.9.2/go.mod h1:7pLA8lDk46WKDWlVsENo92gC0XFa8rbKfyFRBqxEbCc=
-github.com/Microsoft/hcsshim v0.9.4/go.mod h1:7pLA8lDk46WKDWlVsENo92gC0XFa8rbKfyFRBqxEbCc=
+github.com/Microsoft/hcsshim v0.9.5/go.mod h1:7pLA8lDk46WKDWlVsENo92gC0XFa8rbKfyFRBqxEbCc=
 github.com/Microsoft/hcsshim/test v0.0.0-20201218223536-d3e5debf77da/go.mod h1:5hlzMzRKMLyo42nCZ9oml8AdTlq/0cvIaBv6tK1RehU=
 github.com/Microsoft/hcsshim/test v0.0.0-20210227013316-43a75bb4edd3/go.mod h1:mw7qgWloBUl75W/gVH3cQszUg1+gUITj7D6NY7ywVnY=
 github.com/NYTimes/gziphandler v0.0.0-20170623195520-56545f4a5d46/go.mod h1:3wb06e3pkSAbeQ52E9H9iFoQsEEwGN64994WTCIhntQ=
@@ -280,8 +280,8 @@ github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b h1:e1bmaoJfZV
 github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b/go.mod h1:Bkc+JYWjMCF8OyZ340IMSIi2Ebf3uwByOk6ho4wne1E=
 github.com/anchore/packageurl-go v0.1.1-0.20220428202044-a072fa3cb6d7 h1:kDrYkTSM9uIxaX/P9s0F4nKYNM+hnSgLJdLpqvsaQ/g=
 github.com/anchore/packageurl-go v0.1.1-0.20220428202044-a072fa3cb6d7/go.mod h1:Blo6OgJNiYF41ufcgHKkbCKF2MDOMlrqhXv/ij6ocR4=
-github.com/anchore/stereoscope v0.0.0-20221006201143-d24c9d626b33 h1:Y+9aMJMTEMH+kJJFEaxqrF6X1t9CkjpWjOzaCo1q5vM=
-github.com/anchore/stereoscope v0.0.0-20221006201143-d24c9d626b33/go.mod h1:WOWtswyDxLkBnizq9LihYa9uw88r1FhBvJo7g//Ljcc=
+github.com/anchore/stereoscope v0.0.0-20221208011002-c5ff155d72f1 h1:DXUAm/H9chRTEzMfkFyduBIcCiJyFXhCmv3zH3C0HGs=
+github.com/anchore/stereoscope v0.0.0-20221208011002-c5ff155d72f1/go.mod h1:/zjVnu2Jdl7xQCUtASegzeEg+IHKrM7SyMqdao3e+Nc=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
 github.com/andybalholm/brotli v1.0.2/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
@@ -401,8 +401,7 @@ github.com/bmatcuk/doublestar/v4 v4.0.2/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTS
 github.com/bmizerany/assert v0.0.0-20160611221934-b7ed37b82869/go.mod h1:Ekp36dRnpXw/yCqJaO+ZrUyxD+3VXMFFr56k5XYrpB4=
 github.com/bombsimon/wsl/v3 v3.3.0/go.mod h1:st10JtZYLE4D5sC7b8xV4zTKZwAQjCH/Hy2Pm1FNZIc=
 github.com/bradfitz/gomemcache v0.0.0-20190913173617-a41fca850d0b/go.mod h1:H0wQNHz2YrLsuXOZozoeDmnHXkNCRmMW0gwFWDfEZDA=
-github.com/bradleyjkemp/cupaloy/v2 v2.7.0 h1:AT0vOjO68RcLyenLCHOGZzSNiuto7ziqzq6Q1/3xzMQ=
-github.com/bradleyjkemp/cupaloy/v2 v2.7.0/go.mod h1:bm7JXdkRd4BHJk9HpwqAI8BoAY1lps46Enkdqw6aRX0=
+github.com/bradleyjkemp/cupaloy/v2 v2.8.0 h1:any4BmKE+jGIaMpnU8YgH/I2LPiLBufr6oMMlVBbn9M=
 github.com/breml/bidichk v0.1.1/go.mod h1:zbfeitpevDUGI7V91Uzzuwrn4Vls8MoBMrwtt78jmso=
 github.com/bshuster-repo/logrus-logstash-hook v0.4.1/go.mod h1:zsTqEiSzDgAa/8GZR7E1qaXrhYNDKBYy5/dWPTIflbk=
 github.com/buger/jsonparser v0.0.0-20180808090653-f4dd9f5a6b44/go.mod h1:bbYlZJ7hK1yFx9hf58LP0zeX7UjIGs20ufpu3evjr+s=
@@ -516,8 +515,8 @@ github.com/containerd/containerd v1.5.1/go.mod h1:0DOxVqwDy2iZvrZp2JUx/E+hS0UNTV
 github.com/containerd/containerd v1.5.7/go.mod h1:gyvv6+ugqY25TiXxcZC3L5yOeYgEw0QMhscqVp1AR9c=
 github.com/containerd/containerd v1.5.8/go.mod h1:YdFSv5bTFLpG2HIYmfqDpSYYTDX+mc5qtSuYx1YUb/s=
 github.com/containerd/containerd v1.6.1/go.mod h1:1nJz5xCZPusx6jJU8Frfct988y0NpumIq9ODB0kLtoE=
-github.com/containerd/containerd v1.6.8 h1:h4dOFDwzHmqFEP754PgfgTeVXFnLiRc6kiqC7tplDJs=
-github.com/containerd/containerd v1.6.8/go.mod h1:By6p5KqPK0/7/CgO/A6t/Gz+CUYUu2zf1hUaaymVXB0=
+github.com/containerd/containerd v1.6.12 h1:kJ9b3mOFKf8yqo05Ob+tMoxvt1pbVWhnB0re9Y+k+8c=
+github.com/containerd/containerd v1.6.12/go.mod h1:K4Bw7gjgh4TnkmQY+py/PYQGp4e7xgnHAeg87VeWb3A=
 github.com/containerd/continuity v0.0.0-20190426062206-aaeac12a7ffc/go.mod h1:GL3xCUCBDV3CZiTSEKksMWbLE66hEyuu9qyDOOqM47Y=
 github.com/containerd/continuity v0.0.0-20190815185530-f2a389ac0a02/go.mod h1:GL3xCUCBDV3CZiTSEKksMWbLE66hEyuu9qyDOOqM47Y=
 github.com/containerd/continuity v0.0.0-20191127005431-f65d91d395eb/go.mod h1:GL3xCUCBDV3CZiTSEKksMWbLE66hEyuu9qyDOOqM47Y=
@@ -526,6 +525,7 @@ github.com/containerd/continuity v0.0.0-20201208142359-180525291bb7/go.mod h1:kR
 github.com/containerd/continuity v0.0.0-20210208174643-50096c924a4e/go.mod h1:EXlVlkqNba9rJe3j7w3Xa924itAMLgZH4UD/Q4PExuQ=
 github.com/containerd/continuity v0.1.0/go.mod h1:ICJu0PwR54nI0yPEnJ6jcS+J7CZAUXrLh8lPo2knzsM=
 github.com/containerd/continuity v0.2.2/go.mod h1:pWygW9u7LtS1o4N/Tn0FoCFDIXZ7rxcMX7HX1Dmibvk=
+github.com/containerd/continuity v0.3.0/go.mod h1:wJEAIwKOm/pBZuBd0JmeTvnLquTB1Ag8espWhkykbPM=
 github.com/containerd/fifo v0.0.0-20180307165137-3d5202aec260/go.mod h1:ODA38xgv3Kuk8dQz2ZQXpnv/UZZUHUCL7pnLehbXgQI=
 github.com/containerd/fifo v0.0.0-20190226154929-a9fb20d87448/go.mod h1:ODA38xgv3Kuk8dQz2ZQXpnv/UZZUHUCL7pnLehbXgQI=
 github.com/containerd/fifo v0.0.0-20200410184934-f15a3290365b/go.mod h1:jPQ2IAeZRCYxpS/Cm1495vGFww6ecHmMk1YJH2Q5ln0=
@@ -1376,6 +1376,7 @@ github.com/mattn/go-colorable v0.1.6/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope
 github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
 github.com/mattn/go-colorable v0.1.9/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
 github.com/mattn/go-colorable v0.1.11/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
+github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
 github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
 github.com/mattn/go-ieproxy v0.0.0-20190610004146-91bb50d98149/go.mod h1:31jz6HNzdxOmlERGGEc4v/dMssOfmp2p5bT/okiKFFc=
@@ -1408,8 +1409,9 @@ github.com/mattn/go-sqlite3 v1.14.12/go.mod h1:NyWgC/yNuGj7Q9rpYnZvas74GogHl5/Z4
 github.com/mattn/go-zglob v0.0.1/go.mod h1:9fxibJccNxU2cnpIKLRRFA7zX7qhkJIQWBb449FYHOo=
 github.com/mattn/goveralls v0.0.2/go.mod h1:8d1ZMHsd7fW6IRPKQh46F2WRpyib5/X4FOpevwGNQEw=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
-github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 h1:I0XW9+e1XWDxdcEniV4rQAIOPUGDq67JSCiRCgGCZLI=
 github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
+github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
+github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/maxbrunsfeld/counterfeiter/v6 v6.2.2/go.mod h1:eD9eIE7cdwcMi9rYluz88Jz2VyhSmden33/aXg4oVIY=
 github.com/mbilski/exhaustivestruct v1.2.0/go.mod h1:OeTBVxQWoEmB2J2JCHmXWPJ0aksxSUOUy+nvtVEfzXc=
 github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517/go.mod h1:KQ7+USdGKfpPjXk4Ga+5XxQM4Lm4e3gAogrreFAYpOg=
@@ -2215,6 +2217,7 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.0.0-20211108221036-ceb1ce70b4fa/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20211215153901-e495a2d5b3d3/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220131195533-30dcbda58838/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/crypto v0.0.0-20220315160706-3147a52a75dd/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220411220226-7b82a4e95df4/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
@@ -2343,6 +2346,7 @@ golang.org/x/net v0.0.0-20220421235706-1d1ef9303861/go.mod h1:CfG3xpIq0wQ8r1q4Su
 golang.org/x/net v0.0.0-20220425223048-2871e0cb64e4/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
 golang.org/x/net v0.0.0-20220607020251-c690dde0001d/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.0.0-20220624214902-1bab6f366d9e/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.0.0-20220826154423-83b083e8dc8b/go.mod h1:YDH+HFinaLZZlnHAfSS6ZXJJ9M9t4Dl22yv3iI2vPwk=
 golang.org/x/net v0.0.0-20221012135044-0b7e1fb9d458 h1:MgJ6t2zo8v0tbmLCueaCbF1RM+TtB0rs3Lv8DGtOIpY=
 golang.org/x/net v0.0.0-20221012135044-0b7e1fb9d458/go.mod h1:YDH+HFinaLZZlnHAfSS6ZXJJ9M9t4Dl22yv3iI2vPwk=
@@ -2532,6 +2536,7 @@ golang.org/x/sys v0.0.0-20220128215802-99c3d69c2c27/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220209214540-3681064d5158/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220227234510-4e6760a101f9/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220328115105-d36c6a25d886/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220405210540-1e041c57c461/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220412211240-33da011f77ad/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220422013727-9388b58f7150/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220502124256-b6088ccd6cba/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -2539,6 +2544,7 @@ golang.org/x/sys v0.0.0-20220503163025-988cb79eb6c6/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220610221304-9f5ed59c137d/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220728004956-3c1f35247d10/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220928140112-f11e5e49a4ec h1:BkDtF2Ih9xZ7le9ndzTA7KJow28VbQW3odyk/8drmuI=
@@ -2878,6 +2884,7 @@ google.golang.org/genproto v0.0.0-20220421151946-72621c1f0bd3/go.mod h1:8w6bsBMX
 google.golang.org/genproto v0.0.0-20220422154200-b37d22cd5731/go.mod h1:8w6bsBMX6yCPbAVTeqQHvzxW0EIFigd5lZyahWgyfDo=
 google.golang.org/genproto v0.0.0-20220426171045-31bebdecfb46/go.mod h1:8w6bsBMX6yCPbAVTeqQHvzxW0EIFigd5lZyahWgyfDo=
 google.golang.org/genproto v0.0.0-20220429170224-98d788798c3e/go.mod h1:8w6bsBMX6yCPbAVTeqQHvzxW0EIFigd5lZyahWgyfDo=
+google.golang.org/genproto v0.0.0-20220502173005-c8bf987b8c21/go.mod h1:RAyBrSAP7Fh3Nc84ghnVLDPuV51xc9agzmm4Ph6i0Q4=
 google.golang.org/genproto v0.0.0-20220505152158-f39f71e6c8f3/go.mod h1:RAyBrSAP7Fh3Nc84ghnVLDPuV51xc9agzmm4Ph6i0Q4=
 google.golang.org/genproto v0.0.0-20220518221133-4f43b3371335/go.mod h1:RAyBrSAP7Fh3Nc84ghnVLDPuV51xc9agzmm4Ph6i0Q4=
 google.golang.org/genproto v0.0.0-20220523171625-347a074981d8/go.mod h1:RAyBrSAP7Fh3Nc84ghnVLDPuV51xc9agzmm4Ph6i0Q4=
@@ -3057,6 +3064,7 @@ k8s.io/cri-api v0.20.1/go.mod h1:2JRbKt+BFLTjtrILYVqQK5jqhI+XNdF6UiGMgczeBCI=
 k8s.io/cri-api v0.20.4/go.mod h1:2JRbKt+BFLTjtrILYVqQK5jqhI+XNdF6UiGMgczeBCI=
 k8s.io/cri-api v0.20.6/go.mod h1:ew44AjNXwyn1s0U4xCKGodU7J1HzBeZ1MpGrpa5r8Yc=
 k8s.io/cri-api v0.23.1/go.mod h1:REJE3PSU0h/LOV1APBrupxrEJqnoxZC8KWzkBUHwrK4=
+k8s.io/cri-api v0.25.0/go.mod h1:J1rAyQkSJ2Q6I+aBMOVgg2/cbbebso6FNa0UagiR0kc=
 k8s.io/gengo v0.0.0-20200413195148-3a45101e95ac/go.mod h1:ezvh/TsK7cY6rbqRK0oQQ8IAqLxYwwyPxAX1Pzy0ii0=
 k8s.io/gengo v0.0.0-20200428234225-8167cfdcfc14/go.mod h1:ezvh/TsK7cY6rbqRK0oQQ8IAqLxYwwyPxAX1Pzy0ii0=
 k8s.io/gengo v0.0.0-20201113003025-83324d819ded/go.mod h1:FiNAH4ZV3gBg2Kwh89tzAEV2be7d5xI0vBa/VySYy3E=
@@ -423,6 +423,7 @@ func Test_processSPDXLicense(t *testing.T) {
 				"cern-ohl-w-2":                             "CERN-OHL-W-2.0",
 				"cern-ohl-w-2.0":                           "CERN-OHL-W-2.0",
 				"cern-ohl-w-2.0.0":                         "CERN-OHL-W-2.0",
+				"checkmk":                                  "checkmk",
 				"clartistic":                               "ClArtistic",
 				"cnri-jython":                              "CNRI-Jython",
 				"cnri-python":                              "CNRI-Python",
@@ -521,6 +522,7 @@ func Test_processSPDXLicense(t *testing.T) {
 				"fsfap":                                    "FSFAP",
 				"fsful":                                    "FSFUL",
 				"fsfullr":                                  "FSFULLR",
+				"fsfullrwd":                                "FSFULLRWD",
 				"ftl":                                      "FTL",
 				"gd":                                       "GD",
 				"gfdl-1":                                   "GFDL-1.1-only",
@@ -668,6 +670,7 @@ func Test_processSPDXLicense(t *testing.T) {
 				"jasper-2.0.0":                             "JasPer-2.0",
 				"jpnic":                                    "JPNIC",
 				"json":                                     "JSON",
+				"knuth-ctan":                               "Knuth-CTAN",
 				"lal-1":                                    "LAL-1.2",
 				"lal-1.2":                                  "LAL-1.2",
 				"lal-1.2.0":                                "LAL-1.2",
@@ -716,6 +719,7 @@ func Test_processSPDXLicense(t *testing.T) {
 				"libselinux-1.0":                           "libselinux-1.0",
 				"libselinux-1.0.0":                         "libselinux-1.0",
 				"libtiff":                                  "libtiff",
+				"libutil-david-nugent":                     "libutil-David-Nugent",
 				"liliq-p-1":                                "LiLiQ-P-1.1",
 				"liliq-p-1.1":                              "LiLiQ-P-1.1",
 				"liliq-p-1.1.0":                            "LiLiQ-P-1.1",
@@ -1,9 +1,9 @@
 // Code generated by go generate; DO NOT EDIT.
-// This file was generated by robots at 2022-10-14 11:46:16.097525 -0400 EDT m=+0.276930979
+// This file was generated by robots at 2022-12-02 12:51:33.814385 -0500 EST m=+1.688731869
 // using data from https://spdx.org/licenses/licenses.json
 package spdxlicense

-const Version = "3.18"
+const Version = "3.19"

 var licenseIDs = map[string]string{
 	"0bsd":                                   "0BSD",
@@ -372,6 +372,7 @@ var licenseIDs = map[string]string{
 	"cern-ohl-w-2":                             "CERN-OHL-W-2.0",
 	"cern-ohl-w-2.0":                           "CERN-OHL-W-2.0",
 	"cern-ohl-w-2.0.0":                         "CERN-OHL-W-2.0",
+	"checkmk":                                  "checkmk",
 	"clartistic":                               "ClArtistic",
 	"cnri-jython":                              "CNRI-Jython",
 	"cnri-python":                              "CNRI-Python",
@@ -470,6 +471,7 @@ var licenseIDs = map[string]string{
 	"fsfap":                                    "FSFAP",
 	"fsful":                                    "FSFUL",
 	"fsfullr":                                  "FSFULLR",
+	"fsfullrwd":                                "FSFULLRWD",
 	"ftl":                                      "FTL",
 	"gd":                                       "GD",
 	"gfdl-1":                                   "GFDL-1.1-only",
@@ -617,6 +619,7 @@ var licenseIDs = map[string]string{
 	"jasper-2.0.0":                             "JasPer-2.0",
 	"jpnic":                                    "JPNIC",
 	"json":                                     "JSON",
+	"knuth-ctan":                               "Knuth-CTAN",
 	"lal-1":                                    "LAL-1.2",
 	"lal-1.2":                                  "LAL-1.2",
 	"lal-1.2.0":                                "LAL-1.2",
@@ -665,6 +668,7 @@ var licenseIDs = map[string]string{
 	"libselinux-1.0":                           "libselinux-1.0",
 	"libselinux-1.0.0":                         "libselinux-1.0",
 	"libtiff":                                  "libtiff",
+	"libutil-david-nugent":                     "libutil-David-Nugent",
 	"liliq-p-1":                                "LiLiQ-P-1.1",
 	"liliq-p-1.1":                              "LiLiQ-P-1.1",
 	"liliq-p-1.1.0":                            "LiLiQ-P-1.1",
@@ -984,7 +988,7 @@ var licenseIDs = map[string]string{
 	"sspl-1":                                   "SSPL-1.0",
 	"sspl-1.0":                                 "SSPL-1.0",
 	"sspl-1.0.0":                               "SSPL-1.0",
-	"standardml-nj":                            "StandardML-NJ",
+	"standardml-nj":                            "SMLNJ",
 	"sugarcrm-1":                               "SugarCRM-1.1.3",
 	"sugarcrm-1.1":                             "SugarCRM-1.1.3",
 	"sugarcrm-1.1.3":                           "SugarCRM-1.1.3",
@@ -1,38 +0,0 @@
-package file
-
-import (
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/source"
-)
-
-type ClassificationCataloger struct {
-	classifiers []Classifier
-}
-
-func NewClassificationCataloger(classifiers []Classifier) (*ClassificationCataloger, error) {
-	return &ClassificationCataloger{
-		classifiers: classifiers,
-	}, nil
-}
-
-func (i *ClassificationCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]Classification, error) {
-	results := make(map[source.Coordinates][]Classification)
-
-	numResults := 0
-	for _, location := range allRegularFiles(resolver) {
-		for _, classifier := range i.classifiers {
-			result, err := classifier.Classify(resolver, location)
-			if err != nil {
-				log.Warnf("file classification cataloger failed with class=%q at location=%+v: %+v", classifier.Class, location, err)
-				continue
-			}
-			if result != nil {
-				results[location.Coordinates] = append(results[location.Coordinates], *result)
-				numResults++
-			}
-		}
-	}
-	log.Debugf("file classifier discovered %d results", numResults)
-
-	return results, nil
-}
@@ -1,210 +0,0 @@
-package file
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/anchore/stereoscope/pkg/imagetest"
-	"github.com/anchore/syft/syft/source"
-)
-
-func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
-	tests := []struct {
-		name        string
-		fixtureDir  string
-		location    string
-		expected    []Classification
-		expectedErr func(assert.TestingT, error, ...interface{}) bool
-	}{
-		{
-			name:       "positive-libpython3.7.so",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "libpython3.7.so",
-			expected: []Classification{
-				{
-					Class: "python-binary",
-					Metadata: map[string]string{
-						"version": "3.7.4a-vZ9",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-		{
-			name:       "positive-python3.6",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "python3.6",
-			expected: []Classification{
-				{
-					Class: "python-binary",
-					Metadata: map[string]string{
-						"version": "3.6.3a-vZ9",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-		{
-			name:       "positive-patchlevel.h",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "patchlevel.h",
-			expected: []Classification{
-				{
-					Class: "cpython-source",
-					Metadata: map[string]string{
-						"version": "3.9-aZ5",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-		{
-			name:       "positive-go",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "go",
-			expected: []Classification{
-				{
-					Class: "go-binary",
-					Metadata: map[string]string{
-						"version": "1.14",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-		{
-			name:       "positive-go-hint",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "VERSION",
-			expected: []Classification{
-				{
-					Class: "go-binary-hint",
-					Metadata: map[string]string{
-						"version": "1.15",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-		{
-			name:       "positive-busybox",
-			fixtureDir: "test-fixtures/classifiers/positive",
-			location:   "[", // note: busybox is a link to [
-			expected: []Classification{
-				{
-					Class:       "busybox-binary",
-					VirtualPath: "busybox",
-					Metadata: map[string]string{
-						"version": "3.33.3",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-
-			c, err := NewClassificationCataloger(DefaultClassifiers)
-			test.expectedErr(t, err)
-
-			src, err := source.NewFromDirectory(test.fixtureDir)
-			test.expectedErr(t, err)
-
-			resolver, err := src.FileResolver(source.SquashedScope)
-			test.expectedErr(t, err)
-
-			actualResults, err := c.Catalog(resolver)
-			test.expectedErr(t, err)
-
-			ok := false
-			for actualLoc, actualClassification := range actualResults {
-				if test.location == actualLoc.RealPath {
-					ok = true
-					assert.Equal(t, test.expected, actualClassification)
-				}
-			}
-
-			if !ok {
-				t.Fatalf("could not find test location=%q", test.location)
-			}
-
-		})
-	}
-}
-
-func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T) {
-	tests := []struct {
-		name         string
-		fixtureImage string
-		location     string
-		expected     []Classification
-		expectedErr  func(assert.TestingT, error, ...interface{}) bool
-	}{
-		{
-			name:         "busybox-regression",
-			fixtureImage: "image-busybox",
-			location:     "/bin/[",
-			expected: []Classification{
-				{
-					Class:       "busybox-binary",
-					VirtualPath: "/bin/busybox",
-					Metadata: map[string]string{
-						"version": "1.35.0",
-					},
-				},
-			},
-			expectedErr: assert.NoError,
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-
-			c, err := NewClassificationCataloger(DefaultClassifiers)
-			test.expectedErr(t, err)
-
-			img := imagetest.GetFixtureImage(t, "docker-archive", test.fixtureImage)
-			src, err := source.NewFromImage(img, "test-img")
-			test.expectedErr(t, err)
-
-			resolver, err := src.FileResolver(source.SquashedScope)
-			test.expectedErr(t, err)
-
-			actualResults, err := c.Catalog(resolver)
-			test.expectedErr(t, err)
-
-			ok := false
-			for actuaLoc, actualClassification := range actualResults {
-				if actuaLoc.RealPath == test.location {
-					ok = true
-					assert.Equal(t, test.expected, actualClassification)
-				}
-			}
-
-			if !ok {
-				t.Fatalf("could not find test location=%q", test.location)
-			}
-
-		})
-	}
-}
-
-func TestClassifierCataloger_DefaultClassifiers_NegativeCases(t *testing.T) {
-
-	c, err := NewClassificationCataloger(DefaultClassifiers)
-	assert.NoError(t, err)
-
-	src, err := source.NewFromDirectory("test-fixtures/classifiers/negative")
-	assert.NoError(t, err)
-
-	resolver, err := src.FileResolver(source.SquashedScope)
-	assert.NoError(t, err)
-
-	actualResults, err := c.Catalog(resolver)
-	assert.NoError(t, err)
-	assert.Equal(t, 0, len(actualResults))
-
-}
@@ -1,153 +0,0 @@
-package file
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"regexp"
-	"text/template"
-
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/syft/source"
-)
-
-var DefaultClassifiers = []Classifier{
-	{
-		Class: "python-binary",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)python(?P<version>[0-9]+\.[0-9]+)$`),
-			regexp.MustCompile(`(.*/|^)libpython(?P<version>[0-9]+\.[0-9]+).so.*$`),
-		},
-		EvidencePatternTemplates: []string{
-			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`,
-		},
-	},
-	{
-		Class: "cpython-source",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)patchlevel.h$`),
-		},
-		EvidencePatternTemplates: []string{
-			`(?m)#define\s+PY_VERSION\s+"?(?P<version>[0-9\.\-_a-zA-Z]+)"?`,
-		},
-	},
-	{
-		Class: "go-binary",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)go$`),
-		},
-		EvidencePatternTemplates: []string{
-			`(?m)go(?P<version>[0-9]+\.[0-9]+(\.[0-9]+|beta[0-9]+|alpha[0-9]+|rc[0-9]+)?)`,
-		},
-	},
-	{
-		Class: "nodejs-binary",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)node$`),
-		},
-		EvidencePatternTemplates: []string{
-			// regex that matches node.js/vx.y.z
-			`(?m)node\.js\/v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`,
-		},
-	},
-	{
-		Class: "go-binary-hint",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)VERSION$`),
-		},
-		EvidencePatternTemplates: []string{
-			`(?m)go(?P<version>[0-9]+\.[0-9]+(\.[0-9]+|beta[0-9]+|alpha[0-9]+|rc[0-9]+)?)`,
-		},
-	},
-	{
-		Class: "busybox-binary",
-		FilepathPatterns: []*regexp.Regexp{
-			regexp.MustCompile(`(.*/|^)busybox$`),
-		},
-		EvidencePatternTemplates: []string{
-			`(?m)BusyBox\s+v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`,
-		},
-	},
-}
-
-type Classifier struct {
-	Class                    string
-	FilepathPatterns         []*regexp.Regexp
-	EvidencePatternTemplates []string
-}
-
-type Classification struct {
-	Class       string            `json:"class"`
-	VirtualPath string            `json:"virtual_path"`
-	Metadata    map[string]string `json:"metadata"`
-}
-
-func (c Classifier) Classify(resolver source.FileResolver, location source.Location) (*Classification, error) {
-	doesFilepathMatch, filepathNamedGroupValues := FilepathMatches(c.FilepathPatterns, location)
-	if !doesFilepathMatch {
-		return nil, nil
-	}
-
-	contentReader, err := resolver.FileContentsByLocation(location)
-	if err != nil {
-		return nil, err
-	}
-	defer internal.CloseAndLogError(contentReader, location.VirtualPath)
-
-	// TODO: there is room for improvement here, as this may use an excessive amount of memory. Alternate approach is to leverage a RuneReader.
-	contents, err := io.ReadAll(contentReader)
-	if err != nil {
-		return nil, err
-	}
-
-	var result *Classification
-	for _, patternTemplate := range c.EvidencePatternTemplates {
-		tmpl, err := template.New("").Parse(patternTemplate)
-		if err != nil {
-			return nil, fmt.Errorf("unable to parse classifier template=%q : %w", patternTemplate, err)
-		}
-
-		patternBuf := &bytes.Buffer{}
-		err = tmpl.Execute(patternBuf, filepathNamedGroupValues)
-		if err != nil {
-			return nil, fmt.Errorf("unable to render template: %w", err)
-		}
-
-		pattern, err := regexp.Compile(patternBuf.String())
-		if err != nil {
-			return nil, fmt.Errorf("unable to compile rendered regex=%q: %w", patternBuf.String(), err)
-		}
-
-		if !pattern.Match(contents) {
-			continue
-		}
-
-		matchMetadata := internal.MatchNamedCaptureGroups(pattern, string(contents))
-		if result == nil {
-			result = &Classification{
-				Class:       c.Class,
-				VirtualPath: location.VirtualPath,
-				Metadata:    matchMetadata,
-			}
-		} else {
-			for key, value := range matchMetadata {
-				result.Metadata[key] = value
-			}
-		}
-	}
-	return result, nil
-}
-
-func FilepathMatches(patterns []*regexp.Regexp, location source.Location) (bool, map[string]string) {
-	for _, path := range []string{location.RealPath, location.VirtualPath} {
-		if path == "" {
-			continue
-		}
-		for _, pattern := range patterns {
-			if pattern.MatchString(path) {
-				return true, internal.MatchNamedCaptureGroups(pattern, path)
-			}
-		}
-	}
-	return false, nil
-}
@@ -1,97 +0,0 @@
-package file
-
-import (
-	"regexp"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/anchore/syft/syft/source"
-)
-
-func TestFilepathMatches(t *testing.T) {
-	tests := []struct {
-		name                string
-		location            source.Location
-		patterns            []string
-		expectedMatches     bool
-		expectedNamedGroups map[string]string
-	}{
-		{
-			name: "simple-filename-match",
-			location: source.Location{
-				Coordinates: source.Coordinates{
-					RealPath: "python2.7",
-				},
-			},
-			patterns: []string{
-				`python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: true,
-		},
-		{
-			name: "filepath-match",
-			location: source.Location{
-				Coordinates: source.Coordinates{
-					RealPath: "/usr/bin/python2.7",
-				},
-			},
-			patterns: []string{
-				`python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: true,
-		},
-		{
-			name: "virtual-filepath-match",
-			location: source.Location{
-				VirtualPath: "/usr/bin/python2.7",
-			},
-			patterns: []string{
-				`python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: true,
-		},
-		{
-			name: "full-filepath-match",
-			location: source.Location{
-				VirtualPath: "/usr/bin/python2.7",
-			},
-			patterns: []string{
-				`.*/bin/python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: true,
-		},
-		{
-			name: "anchored-filename-match-FAILS",
-			location: source.Location{
-				Coordinates: source.Coordinates{
-					RealPath: "/usr/bin/python2.7",
-				},
-			},
-			patterns: []string{
-				`^python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: false,
-		},
-		{
-			name:     "empty-filename-match-FAILS",
-			location: source.Location{},
-			patterns: []string{
-				`^python([0-9]+\.[0-9]+)$`,
-			},
-			expectedMatches: false,
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			var patterns []*regexp.Regexp
-			for _, p := range test.patterns {
-				patterns = append(patterns, regexp.MustCompile(p))
-			}
-			actualMatches, actualNamedGroups := FilepathMatches(patterns, test.location)
-			assert.Equal(t, test.expectedMatches, actualMatches)
-			assert.Equal(t, test.expectedNamedGroups, actualNamedGroups)
-		})
-	}
-}
@@ -1 +0,0 @@
-go1.14
@@ -216,7 +216,7 @@ func collectRelationships(bom *cyclonedx.BOM, s *sbom.SBOM, idMap map[string]int
 		}

 		for _, t := range *d.Dependencies {
-			to, toExists := idMap[t.Ref].(artifact.Identifiable)
+			to, toExists := idMap[t].(artifact.Identifiable)
 			if !toExists {
 				continue
 			}
@@ -173,12 +173,8 @@ func Test_decode(t *testing.T) {
 				},
 				Dependencies: &[]cyclonedx.Dependency{
 					{
-						Ref: "p1",
-						Dependencies: &[]cyclonedx.Dependency{
-							{
-								Ref: "p2",
-							},
-						},
+						Ref:          "p1",
+						Dependencies: &[]string{"p2"},
 					},
 				},
 			},
@@ -263,8 +259,9 @@ func Test_decode(t *testing.T) {

 func Test_missingDataDecode(t *testing.T) {
 	bom := &cyclonedx.BOM{
-		Metadata:   nil,
-		Components: &[]cyclonedx.Component{},
+		Metadata:    nil,
+		Components:  &[]cyclonedx.Component{},
+		SpecVersion: cyclonedx.SpecVersion1_4,
 	}

 	_, err := ToSyftModel(bom)
@@ -287,7 +284,9 @@ func Test_missingDataDecode(t *testing.T) {
 }

 func Test_missingComponentsDecode(t *testing.T) {
-	bom := &cyclonedx.BOM{}
+	bom := &cyclonedx.BOM{
+		SpecVersion: cyclonedx.SpecVersion1_4,
+	}
 	bomBytes, _ := json.Marshal(&bom)
 	decode := GetDecoder(cyclonedx.BOMFileFormatJSON)

@@ -157,8 +157,10 @@ func toDependencies(relationships []artifact.Relationship) []cyclonedx.Dependenc
 			continue
 		}

-		innerDeps := []cyclonedx.Dependency{}
-		innerDeps = append(innerDeps, cyclonedx.Dependency{Ref: deriveBomRef(*fromPkg)})
+		// ind dep
+
+		innerDeps := []string{}
+		innerDeps = append(innerDeps, deriveBomRef(*fromPkg))
 		result = append(result, cyclonedx.Dependency{
 			Ref:          deriveBomRef(*toPkg),
 			Dependencies: &innerDeps,
@@ -6,12 +6,11 @@ import (
 )

 type File struct {
-	ID              string                `json:"id"`
-	Location        source.Coordinates    `json:"location"`
-	Metadata        *FileMetadataEntry    `json:"metadata,omitempty"`
-	Contents        string                `json:"contents,omitempty"`
-	Digests         []file.Digest         `json:"digests,omitempty"`
-	Classifications []file.Classification `json:"classifications,omitempty"`
+	ID       string             `json:"id"`
+	Location source.Coordinates `json:"location"`
+	Metadata *FileMetadataEntry `json:"metadata,omitempty"`
+	Contents string             `json:"contents,omitempty"`
+	Digests  []file.Digest      `json:"digests,omitempty"`
 }

 type FileMetadataEntry struct {
@@ -102,23 +102,17 @@ func toFile(s sbom.SBOM) []model.File {
 			digests = digestsForLocation
 		}

-		var classifications []file.Classification
-		if classificationsForLocation, exists := artifacts.FileClassifications[coordinates]; exists {
-			classifications = classificationsForLocation
-		}
-
 		var contents string
 		if contentsForLocation, exists := artifacts.FileContents[coordinates]; exists {
 			contents = contentsForLocation
 		}

 		results = append(results, model.File{
-			ID:              string(coordinates.ID()),
-			Location:        coordinates,
-			Metadata:        toFileMetadataEntry(coordinates, metadata),
-			Digests:         digests,
-			Classifications: classifications,
-			Contents:        contents,
+			ID:       string(coordinates.ID()),
+			Location: coordinates,
+			Metadata: toFileMetadataEntry(coordinates, metadata),
+			Digests:  digests,
+			Contents: contents,
 		})
 	}

@@ -26,6 +26,15 @@ loopNewIDs:
 	}
 }

+func (s *orderedIDSet) delete(id artifact.ID) {
+	for i, existingID := range s.slice {
+		if existingID == id {
+			s.slice = append(s.slice[:i], s.slice[i+1:]...)
+			return
+		}
+	}
+}
+
 // Catalog represents a collection of Packages.
 type Catalog struct {
 	byID      map[artifact.ID]Package
@@ -92,30 +101,32 @@ func (c *Catalog) Packages(ids []artifact.ID) (result []Package) {
 	return result
 }

-// Add a package to the Catalog.
-func (c *Catalog) Add(p Package) {
+// Add n packages to the catalog.
+func (c *Catalog) Add(pkgs ...Package) {
 	c.lock.Lock()
 	defer c.lock.Unlock()

-	id := p.ID()
-	if id == "" {
-		log.Warnf("found package with empty ID while adding to the catalog: %+v", p)
-		p.SetID()
-		id = p.ID()
-	}
-
-	if existing, exists := c.byID[id]; exists {
-		// there is already a package with this fingerprint merge the existing record with the new one
-		if err := existing.merge(p); err != nil {
-			log.Warnf("failed to merge packages: %+v", err)
-		} else {
-			c.byID[id] = existing
-			c.addPathsToIndex(p)
+	for _, p := range pkgs {
+		id := p.ID()
+		if id == "" {
+			log.Warnf("found package with empty ID while adding to the catalog: %+v", p)
+			p.SetID()
+			id = p.ID()
 		}
-		return
-	}

-	c.addToIndex(p)
+		if existing, exists := c.byID[id]; exists {
+			// there is already a package with this fingerprint merge the existing record with the new one
+			if err := existing.merge(p); err != nil {
+				log.Warnf("failed to merge packages: %+v", err)
+			} else {
+				c.byID[id] = existing
+				c.addPathsToIndex(p)
+			}
+			return
+		}
+
+		c.addToIndex(p)
+	}
 }

 func (c *Catalog) addToIndex(p Package) {
@@ -157,6 +168,59 @@ func (c *Catalog) addPathToIndex(id artifact.ID, path string) {
 	c.idsByPath[path] = pathIndex
 }

+func (c *Catalog) Delete(ids ...artifact.ID) {
+	c.lock.Lock()
+	defer c.lock.Unlock()
+
+	for _, id := range ids {
+		p, exists := c.byID[id]
+		if !exists {
+			return
+		}
+
+		delete(c.byID, id)
+		c.deleteNameFromIndex(p)
+		c.deleteTypeFromIndex(p)
+		c.deletePathsFromIndex(p)
+	}
+}
+
+func (c *Catalog) deleteNameFromIndex(p Package) {
+	nameIndex := c.idsByName[p.Name]
+	nameIndex.delete(p.id)
+	c.idsByName[p.Name] = nameIndex
+}
+
+func (c *Catalog) deleteTypeFromIndex(p Package) {
+	typeIndex := c.idsByType[p.Type]
+	typeIndex.delete(p.id)
+	c.idsByType[p.Type] = typeIndex
+}
+
+func (c *Catalog) deletePathsFromIndex(p Package) {
+	observedPaths := internal.NewStringSet()
+	for _, l := range p.Locations.ToSlice() {
+		if l.RealPath != "" && !observedPaths.Contains(l.RealPath) {
+			c.deletePathFromIndex(p.id, l.RealPath)
+			observedPaths.Add(l.RealPath)
+		}
+		if l.VirtualPath != "" && l.RealPath != l.VirtualPath && !observedPaths.Contains(l.VirtualPath) {
+			c.deletePathFromIndex(p.id, l.VirtualPath)
+			observedPaths.Add(l.VirtualPath)
+		}
+	}
+}
+
+func (c *Catalog) deletePathFromIndex(id artifact.ID, path string) {
+	pathIndex := c.idsByPath[path]
+	pathIndex.delete(id)
+	if len(pathIndex.slice) == 0 {
+		delete(c.idsByPath, path)
+	} else {
+		c.idsByPath[path] = pathIndex
+	}
+}
+
 // Enumerate all packages for the given type(s), enumerating all packages if no type is specified.
 func (c *Catalog) Enumerate(types ...Type) <-chan Package {
 	channel := make(chan Package)
@@ -16,6 +16,148 @@ type expectedIndexes struct {
 	byPath map[string]*strset.Set
 }

+func TestCatalogDeleteRemovesPackages(t *testing.T) {
+	tests := []struct {
+		name            string
+		pkgs            []Package
+		deleteIDs       []artifact.ID
+		expectedIndexes expectedIndexes
+	}{
+		{
+			name: "delete one package",
+			pkgs: []Package{
+				{
+					id:      "pkg:deb/debian/1",
+					Name:    "debian",
+					Version: "1",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/c/path", "/another/path1"),
+					),
+				},
+				{
+					id:      "pkg:deb/debian/2",
+					Name:    "debian",
+					Version: "2",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/d/path", "/another/path2"),
+					),
+				},
+			},
+			deleteIDs: []artifact.ID{
+				artifact.ID("pkg:deb/debian/1"),
+			},
+			expectedIndexes: expectedIndexes{
+				byType: map[Type]*strset.Set{
+					DebPkg: strset.New("pkg:deb/debian/2"),
+				},
+				byPath: map[string]*strset.Set{
+					"/d/path":        strset.New("pkg:deb/debian/2"),
+					"/another/path2": strset.New("pkg:deb/debian/2"),
+				},
+			},
+		},
+		{
+			name: "delete multiple packages",
+			pkgs: []Package{
+				{
+					id:      "pkg:deb/debian/1",
+					Name:    "debian",
+					Version: "1",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/c/path", "/another/path1"),
+					),
+				},
+				{
+					id:      "pkg:deb/debian/2",
+					Name:    "debian",
+					Version: "2",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/d/path", "/another/path2"),
+					),
+				},
+				{
+					id:      "pkg:deb/debian/3",
+					Name:    "debian",
+					Version: "3",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/e/path", "/another/path3"),
+					),
+				},
+			},
+			deleteIDs: []artifact.ID{
+				artifact.ID("pkg:deb/debian/1"),
+				artifact.ID("pkg:deb/debian/3"),
+			},
+			expectedIndexes: expectedIndexes{
+				byType: map[Type]*strset.Set{
+					DebPkg: strset.New("pkg:deb/debian/2"),
+				},
+				byPath: map[string]*strset.Set{
+					"/d/path":        strset.New("pkg:deb/debian/2"),
+					"/another/path2": strset.New("pkg:deb/debian/2"),
+				},
+			},
+		},
+		{
+			name: "delete non-existent package",
+			pkgs: []Package{
+				{
+					id:      artifact.ID("pkg:deb/debian/1"),
+					Name:    "debian",
+					Version: "1",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/c/path", "/another/path1"),
+					),
+				},
+				{
+					id:      artifact.ID("pkg:deb/debian/2"),
+					Name:    "debian",
+					Version: "2",
+					Type:    DebPkg,
+					Locations: source.NewLocationSet(
+						source.NewVirtualLocation("/d/path", "/another/path2"),
+					),
+				},
+			},
+			deleteIDs: []artifact.ID{
+				artifact.ID("pkg:deb/debian/3"),
+			},
+			expectedIndexes: expectedIndexes{
+				byType: map[Type]*strset.Set{
+					DebPkg: strset.New("pkg:deb/debian/1", "pkg:deb/debian/2"),
+				},
+				byPath: map[string]*strset.Set{
+					"/c/path":        strset.New("pkg:deb/debian/1"),
+					"/another/path1": strset.New("pkg:deb/debian/1"),
+					"/d/path":        strset.New("pkg:deb/debian/2"),
+					"/another/path2": strset.New("pkg:deb/debian/2"),
+				},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			c := NewCatalog()
+			for _, p := range test.pkgs {
+				c.Add(p)
+			}
+
+			for _, id := range test.deleteIDs {
+				c.Delete(id)
+			}
+
+			assertIndexes(t, c, test.expectedIndexes)
+		})
+	}
+}
+
 func TestCatalogAddPopulatesIndex(t *testing.T) {

 	var pkgs = []Package{
@@ -3,13 +3,10 @@ package apkdb
 import (
 	"bufio"
 	"fmt"
-	"io"
 	"path"
 	"strconv"
 	"strings"

-	"github.com/mitchellh/mapstructure"
-
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
@@ -22,28 +19,73 @@ import (
 // integrity check
 var _ generic.Parser = parseApkDB

-// parseApkDb parses individual packages from a given Alpine DB file. For more information on specific fields
-// see https://wiki.alpinelinux.org/wiki/Apk_spec .
+// 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) {
-	// larger capacity for the scanner.
-	const maxScannerCapacity = 1024 * 1024
-	// a new larger buffer for the scanner
-	bufScan := make([]byte, maxScannerCapacity)
-	pkgs := make([]pkg.Package, 0)
-
 	scanner := bufio.NewScanner(reader)
-	scanner.Buffer(bufScan, maxScannerCapacity)
-	onDoubleLF := func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		for i := 0; i < len(data); i++ {
-			if i > 0 && data[i-1] == '\n' && data[i] == '\n' {
-				return i + 1, data[:i-1], nil
+
+	var apks []pkg.ApkMetadata
+	var currentEntry pkg.ApkMetadata
+	entryParsingInProgress := false
+	fileParsingCtx := newApkFileParsingContext()
+
+	// creating a dedicated append-like function here instead of using `append(...)`
+	// below since there is nontrivial logic to be performed for each finalized apk
+	// entry.
+	appendApk := func(p pkg.ApkMetadata) {
+		if files := fileParsingCtx.files; len(files) >= 1 {
+			// attached accumulated files to current package
+			p.Files = files
+
+			// reset file parsing for next use
+			fileParsingCtx = newApkFileParsingContext()
+		}
+
+		nilFieldsToEmptySlice(&p)
+		apks = append(apks, p)
+	}
+
+	for scanner.Scan() {
+		line := scanner.Text()
+
+		if line == "" {
+			// i.e. apk entry separator
+
+			if entryParsingInProgress {
+				// current entry is complete
+				appendApk(currentEntry)
 			}
+
+			entryParsingInProgress = false
+
+			// zero-out currentEntry for use by any future entry
+			currentEntry = pkg.ApkMetadata{}
+
+			continue
 		}
-		if !atEOF {
-			return 0, nil, nil
+
+		field := parseApkField(line)
+		if field == nil {
+			log.Warnf("unable to parse field data from line %q", line)
+			continue
 		}
-		// deliver the last token (which could be an empty string)
-		return 0, data, bufio.ErrFinalToken
+
+		entryParsingInProgress = true
+
+		field.apply(&currentEntry, fileParsingCtx)
+	}
+
+	if entryParsingInProgress {
+		// There was no final empty line, so currentEntry hasn't been added to the
+		// collection yet; but we've now reached the end of scanning, so let's be sure to
+		// add currentEntry to the collection.
+		appendApk(currentEntry)
+	}
+
+	if err := scanner.Err(); err != nil {
+		return nil, nil, fmt.Errorf("failed to parse APK installed DB file: %w", err)
 	}

 	var r *linux.Release
@@ -51,128 +93,192 @@ func parseApkDB(_ source.FileResolver, env *generic.Environment, reader source.L
 		r = env.LinuxRelease
 	}

-	scanner.Split(onDoubleLF)
-	for scanner.Scan() {
-		metadata, err := parseApkDBEntry(strings.NewReader(scanner.Text()))
-		if err != nil {
-			return nil, nil, err
-		}
-		if metadata != nil {
-			pkgs = append(pkgs, newPackage(*metadata, r, reader.Location))
-		}
-	}
-
-	if err := scanner.Err(); err != nil {
-		return nil, nil, fmt.Errorf("failed to parse APK DB file: %w", err)
+	pkgs := make([]pkg.Package, 0, len(apks))
+	for _, apk := range apks {
+		pkgs = append(pkgs, newPackage(apk, r, reader.Location))
 	}

 	return pkgs, discoverPackageDependencies(pkgs), nil
 }

-// parseApkDBEntry reads and parses a single pkg.ApkMetadata element from the stream, returning nil if their are no more entries.
-//
+func parseApkField(line string) *apkField {
+	parts := strings.SplitN(line, ":", 2)
+	if len(parts) != 2 {
+		return nil
+	}
+
+	f := apkField{
+		name:  parts[0],
+		value: parts[1],
+	}
+
+	return &f
+}
+
+type apkField struct {
+	name  string
+	value string
+}
+
 //nolint:funlen
-func parseApkDBEntry(reader io.Reader) (*pkg.ApkMetadata, error) {
-	var entry pkg.ApkMetadata
-	pkgFields := make(map[string]interface{})
+func (f apkField) apply(p *pkg.ApkMetadata, ctx *apkFileParsingContext) {
+	switch f.name {
+	// APKINDEX field parsing

-	// We want sane defaults for collections, i.e. an empty array instead of null.
-	pkgFields["D"] = []string{}
-	pkgFields["p"] = []string{}
-	files := make([]pkg.ApkFileRecord, 0)
-
-	var fileRecord *pkg.ApkFileRecord
-	lastFile := "/"
-
-	scanner := bufio.NewScanner(reader)
-	for scanner.Scan() {
-		line := scanner.Text()
-		fields := strings.SplitN(line, ":", 2)
-		if len(fields) != 2 {
-			continue
+	case "P":
+		p.Package = f.value
+	case "o":
+		p.OriginPackage = f.value
+	case "m":
+		p.Maintainer = f.value
+	case "V":
+		p.Version = f.value
+	case "L":
+		p.License = f.value
+	case "A":
+		p.Architecture = f.value
+	case "U":
+		p.URL = f.value
+	case "T":
+		p.Description = f.value
+	case "S":
+		i, err := strconv.Atoi(f.value)
+		if err != nil {
+			log.Warnf("unable to parse value %q for field %q: %w", f.value, f.name, err)
+			return
 		}

-		key := fields[0]
-		value := strings.TrimSpace(fields[1])
-
-		switch key {
-		case "D", "p":
-			entries := strings.Split(value, " ")
-			pkgFields[key] = entries
-		case "F":
-			currentFile := "/" + value
-
-			newFileRecord := pkg.ApkFileRecord{
-				Path: currentFile,
-			}
-			files = append(files, newFileRecord)
-			fileRecord = &files[len(files)-1]
-
-			// future aux references are relative to previous "F" records
-			lastFile = currentFile
-			continue
-		case "R":
-			newFileRecord := pkg.ApkFileRecord{
-				Path: path.Join(lastFile, value),
-			}
-			files = append(files, newFileRecord)
-			fileRecord = &files[len(files)-1]
-		case "a", "M":
-			ownershipFields := strings.Split(value, ":")
-			if len(ownershipFields) < 3 {
-				log.Warnf("unexpected APK ownership field: %q", value)
-				continue
-			}
-			if fileRecord == nil {
-				log.Warnf("ownership field with no parent record: %q", value)
-				continue
-			}
-			fileRecord.OwnerUID = ownershipFields[0]
-			fileRecord.OwnerGID = ownershipFields[1]
-			fileRecord.Permissions = ownershipFields[2]
-			// note: there are more optional fields available that we are not capturing, e.g.:
-			// "0:0:755:Q1JaDEHQHBbizhEzoWK1YxuraNU/4="
-		case "Z":
-			if fileRecord == nil {
-				log.Warnf("checksum field with no parent record: %q", value)
-				continue
-			}
-			fileRecord.Digest = processChecksum(value)
-		case "I", "S":
-			// coerce to integer
-			iVal, err := strconv.Atoi(value)
-			if err != nil {
-				return nil, fmt.Errorf("failed to parse APK int: '%+v'", value)
-			}
-			pkgFields[key] = iVal
-		default:
-			pkgFields[key] = value
+		p.Size = i
+	case "I":
+		i, err := strconv.Atoi(f.value)
+		if err != nil {
+			log.Warnf("unable to parse value %q for field %q: %w", f.value, f.name, err)
+			return
 		}
+
+		p.InstalledSize = i
+	case "D":
+		deps := parseListValue(f.value)
+		p.Dependencies = deps
+	case "p":
+		provides := parseListValue(f.value)
+		p.Provides = provides
+	case "C":
+		p.Checksum = f.value
+	case "c":
+		p.GitCommit = f.value
+
+	// File/directory field parsing:
+
+	case "F":
+		directory := path.Join("/", f.value)
+
+		ctx.files = append(ctx.files, pkg.ApkFileRecord{Path: directory})
+		ctx.indexOfLatestDirectory = len(ctx.files) - 1
+	case "M":
+		i := ctx.indexOfLatestDirectory
+		latest := ctx.files[i]
+
+		var ok bool
+		latest.OwnerUID, latest.OwnerGID, latest.Permissions, ok = processFileInfo(f.value)
+		if !ok {
+			log.Warnf("unexpected value for APK ACL field %q: %q", f.name, f.value)
+			return
+		}
+
+		// save updated directory
+		ctx.files[i] = latest
+	case "R":
+		var regularFile string
+
+		dirIndex := ctx.indexOfLatestDirectory
+		if dirIndex < 0 {
+			regularFile = path.Join("/", f.value)
+		} else {
+			latestDirPath := ctx.files[dirIndex].Path
+			regularFile = path.Join(latestDirPath, f.value)
+		}
+
+		ctx.files = append(ctx.files, pkg.ApkFileRecord{Path: regularFile})
+		ctx.indexOfLatestRegularFile = len(ctx.files) - 1
+	case "a":
+		i := ctx.indexOfLatestRegularFile
+		latest := ctx.files[i]
+
+		var ok bool
+		latest.OwnerUID, latest.OwnerGID, latest.Permissions, ok = processFileInfo(f.value)
+		if !ok {
+			log.Warnf("unexpected value for APK ACL field %q: %q", f.name, f.value)
+			return
+		}
+
+		// save updated file
+		ctx.files[i] = latest
+	case "Z":
+		i := ctx.indexOfLatestRegularFile
+		latest := ctx.files[i]
+		latest.Digest = processChecksum(f.value)
+
+		// save updated file
+		ctx.files[i] = latest
+	}
+}
+
+func processFileInfo(v string) (uid, gid, perms string, ok bool) {
+	ok = false
+
+	fileInfo := strings.Split(v, ":")
+	if len(fileInfo) < 3 {
+		return
 	}

-	decoder, err := mapstructure.NewDecoder(&mapstructure.DecoderConfig{
-		// By default, mapstructure compares field names in a *case-insensitive* manner.
-		// That would be the wrong approach here, since these apk files use case
-		// *sensitive* field names (e.g. 'P' vs. 'p').
-		MatchName: func(mapKey, fieldName string) bool {
-			return mapKey == fieldName
-		},
-		Result: &entry,
-	})
-	if err != nil {
-		return nil, err
+	uid = fileInfo[0]
+	gid = fileInfo[1]
+	perms = fileInfo[2]
+
+	// note: there are more optional fields available that we are not capturing,
+	// e.g.: "0:0:755:Q1JaDEHQHBbizhEzoWK1YxuraNU/4="
+
+	ok = true
+	return
+}
+
+// apkFileParsingContext helps keep track of what file data has been captured so far for the APK currently being parsed.
+type apkFileParsingContext struct {
+	files                    []pkg.ApkFileRecord
+	indexOfLatestDirectory   int
+	indexOfLatestRegularFile int
+}
+
+func newApkFileParsingContext() *apkFileParsingContext {
+	return &apkFileParsingContext{
+		indexOfLatestDirectory:   -1, // no directories yet
+		indexOfLatestRegularFile: -1, // no regular files yet
+	}
+}
+
+// parseListValue parses a space-separated list from an apk entry field value.
+func parseListValue(value string) []string {
+	items := strings.Split(value, " ")
+	if len(items) >= 1 {
+		return items
 	}

-	if err := decoder.Decode(pkgFields); err != nil {
-		return nil, fmt.Errorf("unable to parse APK metadata: %w", err)
-	}
-	if entry.Package == "" {
-		return nil, nil
+	return nil
+}
+
+func nilFieldsToEmptySlice(p *pkg.ApkMetadata) {
+	if p.Dependencies == nil {
+		p.Dependencies = []string{}
 	}

-	entry.Files = files
+	if p.Provides == nil {
+		p.Provides = []string{}
+	}

-	return &entry, nil
+	if p.Files == nil {
+		p.Files = []pkg.ApkFileRecord{}
+	}
 }

 func processChecksum(value string) *file.Digest {
@@ -1,8 +1,8 @@
 package apkdb

 import (
-	"bufio"
 	"os"
+	"path/filepath"
 	"testing"

 	"github.com/google/go-cmp/cmp"
@@ -60,16 +60,15 @@ func TestExtraFileAttributes(t *testing.T) {

 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
-			f, err := os.Open("test-fixtures/extra-file-attributes")
-			require.NoError(t, err)
-			t.Cleanup(func() { require.NoError(t, f.Close()) })
+			fixturePath := "test-fixtures/extra-file-attributes"
+			lrc := newLocationReadCloser(t, fixturePath)

-			reader := bufio.NewReader(f)
+			pkgs, _, err := parseApkDB(nil, new(generic.Environment), lrc)
+			assert.NoError(t, err)
+			require.Len(t, pkgs, 1)
+			metadata := pkgs[0].Metadata.(pkg.ApkMetadata)

-			entry, err := parseApkDBEntry(reader)
-			require.NoError(t, err)
-
-			if diff := cmp.Diff(entry.Files, test.expected.Files); diff != "" {
+			if diff := cmp.Diff(test.expected.Files, metadata.Files); diff != "" {
 				t.Errorf("Files mismatch (-want +got):\n%s", diff)
 			}
 		})
@@ -615,17 +614,14 @@ func TestSinglePackageDetails(t *testing.T) {

 	for _, test := range tests {
 		t.Run(test.fixture, func(t *testing.T) {
-			f, err := os.Open(test.fixture)
+			lrc := newLocationReadCloser(t, test.fixture)
+
+			pkgs, _, err := parseApkDB(nil, new(generic.Environment), lrc)
 			require.NoError(t, err)
-			t.Cleanup(func() { require.NoError(t, f.Close()) })
+			require.Len(t, pkgs, 1)
+			metadata := pkgs[0].Metadata.(pkg.ApkMetadata)

-			reader := bufio.NewReader(f)
-
-			entry, err := parseApkDBEntry(reader)
-			require.NoError(t, err)
-			require.NotNil(t, entry)
-
-			if diff := cmp.Diff(*entry, test.expected); diff != "" {
+			if diff := cmp.Diff(test.expected, metadata); diff != "" {
 				t.Errorf("Entry mismatch (-want +got):\n%s", diff)
 			}
 		})
@@ -765,7 +761,6 @@ func TestMultiplePackages(t *testing.T) {
 	}}

 	pkgtest.TestFileParserWithEnv(t, fixture, parseApkDB, &env, expectedPkgs, expectedRelationships)
-
 }

 func Test_processChecksum(t *testing.T) {
@@ -791,15 +786,15 @@ func Test_processChecksum(t *testing.T) {
 			},
 		},
 	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			assert.Equal(t, &tt.want, processChecksum(tt.value))
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, &test.want, processChecksum(test.value))
 		})
 	}
 }

 func Test_discoverPackageDependencies(t *testing.T) {
-
 	tests := []struct {
 		name  string
 		genFn func() ([]pkg.Package, []artifact.Relationship)
@@ -934,9 +929,10 @@ func Test_discoverPackageDependencies(t *testing.T) {
 			},
 		},
 	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			pkgs, wantRelationships := tt.genFn()
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			pkgs, wantRelationships := test.genFn()
 			gotRelationships := discoverPackageDependencies(pkgs)
 			d := cmp.Diff(wantRelationships, gotRelationships, cmpopts.IgnoreUnexported(pkg.Package{}, source.LocationSet{}))
 			if d != "" {
@@ -1007,3 +1003,89 @@ func TestPackageDbDependenciesByParse(t *testing.T) {
 		})
 	}
 }
+
+func Test_parseApkDB_expectedPkgNames(t *testing.T) {
+	tests := []struct {
+		fixture      string
+		wantPkgNames []string
+		wantErr      assert.ErrorAssertionFunc
+	}{
+		{
+			fixture: "very-large-entries",
+			wantPkgNames: []string{
+				"ca-certificates-bundle",
+				"glibc-locale-posix",
+				"wolfi-baselayout",
+				"glibc",
+				"libcrypto3",
+				"libssl3",
+				"zlib",
+				"apk-tools",
+				"ncurses-terminfo-base",
+				"ncurses",
+				"bash",
+				"libcap",
+				"bubblewrap",
+				"busybox",
+				"libbrotlicommon1",
+				"libbrotlidec1",
+				"libnghttp2-14",
+				"libcurl4",
+				"curl",
+				"expat",
+				"libpcre2-8-0",
+				"git",
+				"binutils",
+				"libstdc++-dev",
+				"libgcc",
+				"libstdc++",
+				"gmp",
+				"isl",
+				"mpfr",
+				"mpc",
+				"gcc",
+				"linux-headers",
+				"glibc-dev",
+				"make",
+				"pkgconf",
+				"build-base",
+				"go",
+				"tree",
+				"sdk",
+			},
+			wantErr: assert.NoError,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.fixture, func(t *testing.T) {
+			fixturePath := filepath.Join("test-fixtures", test.fixture)
+			lrc := newLocationReadCloser(t, fixturePath)
+
+			pkgs, _, err := parseApkDB(nil, new(generic.Environment), lrc)
+			test.wantErr(t, err)
+
+			names := toPackageNames(pkgs)
+			if diff := cmp.Diff(test.wantPkgNames, names); diff != "" {
+				t.Errorf("Packages mismatch (-want +got):\n%s", diff)
+			}
+		})
+	}
+}
+
+func toPackageNames(pkgs []pkg.Package) []string {
+	names := make([]string, 0, len(pkgs))
+	for _, p := range pkgs {
+		names = append(names, p.Name)
+	}
+
+	return names
+}
+
+func newLocationReadCloser(t *testing.T, path string) source.LocationReadCloser {
+	f, err := os.Open(path)
+	require.NoError(t, err)
+	t.Cleanup(func() { f.Close() })
+
+	return source.NewLocationReadCloser(source.NewLocation(path), f)
+}
@@ -0,0 +1,78 @@
+package binary
+
+import (
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+)
+
+const catalogerName = "binary-cataloger"
+
+func NewCataloger() *Cataloger {
+	return &Cataloger{}
+}
+
+// Cataloger is the cataloger responsible for surfacing evidence of a very limited set of binary files,
+// which have been identified by the classifiers. The Cataloger is _NOT_ a place to catalog any and every
+// binary, but rather the specific set that has been curated to be important, predominantly related to toolchain-
+// related runtimes like Python, Go, Java, or Node. Some exceptions can be made for widely-used binaries such
+// as busybox.
+type Cataloger struct{}
+
+// Name returns a string that uniquely describes the Cataloger
+func (c Cataloger) Name() string {
+	return catalogerName
+}
+
+// Catalog is given an object to resolve file references and content, this function returns any discovered Packages
+// after analyzing the catalog source.
+func (c Cataloger) Catalog(resolver source.FileResolver) ([]pkg.Package, []artifact.Relationship, error) {
+	var packages []pkg.Package
+	var relationships []artifact.Relationship
+
+	for _, classifier := range defaultClassifiers {
+		locations, err := resolver.FilesByGlob(classifier.FileGlob)
+		if err != nil {
+			return nil, nil, err
+		}
+		for _, location := range locations {
+			reader, err := resolver.FileContentsByLocation(location)
+			if err != nil {
+				return nil, nil, err
+			}
+			locationReader := source.NewLocationReadCloser(location, reader)
+			newPkgs, err := classifier.EvidenceMatcher(classifier, locationReader)
+			if err != nil {
+				return nil, nil, err
+			}
+		newPackages:
+			for i := range newPkgs {
+				newPkg := &newPkgs[i]
+				for j := range packages {
+					p := &packages[j]
+					// consolidate identical packages found in different locations,
+					// but continue to track each location
+					if packagesMatch(p, newPkg) {
+						p.Locations.Add(newPkg.Locations.ToSlice()...)
+						continue newPackages
+					}
+				}
+				packages = append(packages, *newPkg)
+			}
+		}
+	}
+
+	return packages, relationships, nil
+}
+
+// packagesMatch returns true if the binary packages "match" based on basic criteria
+func packagesMatch(p1 *pkg.Package, p2 *pkg.Package) bool {
+	if p1.Name != p2.Name ||
+		p1.Version != p2.Version ||
+		p1.Language != p2.Language ||
+		p1.Type != p2.Type {
+		return false
+	}
+
+	return true
+}
@@ -0,0 +1,269 @@
+package binary
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+)
+
+func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
+	tests := []struct {
+		name       string
+		fixtureDir string
+		expected   pkg.Package
+	}{
+		{
+			name:       "positive-libpython3.7.so",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.7.4a-vZ9",
+				Locations: singleLocation("libpython3.7.so"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "python-binary-lib",
+				},
+			},
+		},
+		{
+			name:       "positive-python3.6",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.6.3a-vZ9",
+				Locations: singleLocation("python3.6"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "python-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-patchlevel.h",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "python",
+				Version:   "3.9-aZ5",
+				Locations: singleLocation("patchlevel.h"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "cpython-source",
+				},
+			},
+		},
+		{
+			name:       "positive-go",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "go",
+				Version:   "1.14",
+				Locations: singleLocation("go"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "go-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-node",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "node",
+				Version:   "19.2.1",
+				Locations: singleLocation("node"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "nodejs-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-go-hint",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "go",
+				Version:   "1.15",
+				Locations: singleLocation("VERSION"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "go-binary-hint",
+				},
+			},
+		},
+		{
+			name:       "positive-busybox",
+			fixtureDir: "test-fixtures/classifiers/positive",
+			expected: pkg.Package{
+				Name:      "busybox",
+				Version:   "3.33.3",
+				Locations: singleLocation("["), // note: busybox is a link to [
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "busybox-binary",
+					VirtualPath: "busybox",
+				},
+			},
+		},
+		{
+			name:       "positive-java-openjdk",
+			fixtureDir: "test-fixtures/classifiers/positive/openjdk",
+			expected: pkg.Package{
+				Name:      "java",
+				Version:   "1.8.0_352-b08",
+				Type:      "binary",
+				Locations: singleLocation("java"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "java-binary-openjdk",
+					VirtualPath: "java",
+				},
+			},
+		},
+		{
+			name:       "positive-java-oracle",
+			fixtureDir: "test-fixtures/classifiers/positive/oracle",
+			expected: pkg.Package{
+				Name:      "java",
+				Version:   "19.0.1+10-21",
+				Type:      "binary",
+				Locations: singleLocation("java"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "java-binary-oracle",
+					VirtualPath: "java",
+				},
+			},
+		},
+		{
+			name:       "positive-java-oracle-macos",
+			fixtureDir: "test-fixtures/classifiers/positive/oracle-macos",
+			expected: pkg.Package{
+				Name:      "java",
+				Version:   "19.0.1+10-21",
+				Type:      "binary",
+				Locations: singleLocation("java"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "java-binary-oracle",
+					VirtualPath: "java",
+				},
+			},
+		},
+		{
+			name:       "positive-java-ibm",
+			fixtureDir: "test-fixtures/classifiers/positive/ibm",
+			expected: pkg.Package{
+				Name:      "java",
+				Version:   "1.8.0-foreman_2022_09_22_15_30-b00",
+				Type:      "binary",
+				Locations: singleLocation("java"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "java-binary-ibm",
+					VirtualPath: "java",
+				},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			c := NewCataloger()
+
+			src, err := source.NewFromDirectory(test.fixtureDir)
+			require.NoError(t, err)
+
+			resolver, err := src.FileResolver(source.SquashedScope)
+			require.NoError(t, err)
+
+			packages, _, err := c.Catalog(resolver)
+			require.NoError(t, err)
+
+			ok := false
+			for _, p := range packages {
+				if test.expected.Locations.ToSlice()[0].RealPath == p.Locations.ToSlice()[0].RealPath {
+					ok = true
+					assertPackagesAreEqual(t, test.expected, p)
+				}
+			}
+
+			if !ok {
+				t.Fatalf("could not find test location=%q", test.expected.Locations.ToSlice()[0].RealPath)
+			}
+
+		})
+	}
+}
+
+func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T) {
+	tests := []struct {
+		name         string
+		fixtureImage string
+		expected     pkg.Package
+	}{
+		{
+			name:         "busybox-regression",
+			fixtureImage: "image-busybox",
+			expected: pkg.Package{
+				Name:      "busybox",
+				Version:   "1.35.0",
+				Locations: singleLocation("/bin/["),
+				Metadata: pkg.BinaryMetadata{
+					Classifier:  "busybox-binary",
+					VirtualPath: "/bin/busybox",
+				},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			c := NewCataloger()
+
+			img := imagetest.GetFixtureImage(t, "docker-archive", test.fixtureImage)
+			src, err := source.NewFromImage(img, "test-img")
+			require.NoError(t, err)
+
+			resolver, err := src.FileResolver(source.SquashedScope)
+			require.NoError(t, err)
+
+			packages, _, err := c.Catalog(resolver)
+			require.NoError(t, err)
+
+			ok := false
+			for _, p := range packages {
+				if test.expected.Locations.ToSlice()[0].RealPath == p.Locations.ToSlice()[0].RealPath {
+					ok = true
+					assertPackagesAreEqual(t, test.expected, p)
+				}
+			}
+
+			if !ok {
+				t.Fatalf("could not find test location=%q", test.expected.Locations.ToSlice()[0].RealPath)
+			}
+
+		})
+	}
+}
+
+func TestClassifierCataloger_DefaultClassifiers_NegativeCases(t *testing.T) {
+	c := NewCataloger()
+
+	src, err := source.NewFromDirectory("test-fixtures/classifiers/negative")
+	assert.NoError(t, err)
+
+	resolver, err := src.FileResolver(source.SquashedScope)
+	assert.NoError(t, err)
+
+	actualResults, _, err := c.Catalog(resolver)
+	assert.NoError(t, err)
+	assert.Equal(t, 0, len(actualResults))
+}
+
+func singleLocation(s string) source.LocationSet {
+	return source.NewLocationSet(source.NewLocation(s))
+}
+
+func assertPackagesAreEqual(t *testing.T, expected pkg.Package, p pkg.Package) {
+	meta1 := expected.Metadata.(pkg.BinaryMetadata)
+	meta2 := p.Metadata.(pkg.BinaryMetadata)
+	if expected.Name != p.Name ||
+		expected.Version != p.Version ||
+		meta1.Classifier != meta2.Classifier {
+		assert.Failf(t, "packages not equal", "%v != %v", expected, p)
+	}
+}
@@ -0,0 +1,179 @@
+package binary
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"reflect"
+	"regexp"
+	"text/template"
+
+	"github.com/anchore/packageurl-go"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/unionreader"
+	"github.com/anchore/syft/syft/source"
+)
+
+var emptyPURL = packageurl.PackageURL{}
+
+// classifier is a generic package classifier that can be used to match a package definition
+// to a file that meets the given content criteria of the evidenceMatcher.
+type classifier struct {
+	Class string
+
+	// FileGlob is a selector to narrow down file inspection using the **/glob* syntax
+	FileGlob string
+
+	// EvidenceMatcher is what will be used to match against the file in the source
+	// location. If the matcher returns a package, the file will be considered a candidate.
+	EvidenceMatcher evidenceMatcher
+
+	// Information below is used to specify the Package information when returned
+
+	// Package is the name to use for the package
+	Package string
+
+	// Language is the language to classify this package as
+	Language pkg.Language
+
+	// Type is the package type to use for the package
+	Type pkg.Type
+
+	// PURL is the Package URL to use when generating a package
+	PURL packageurl.PackageURL
+
+	// CPEs are the specific CPEs we want to include for this binary with updated version information
+	CPEs []pkg.CPE
+}
+
+// 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)
+
+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 nil, nil
+		}
+
+		filepathNamedGroupValues := internal.MatchNamedCaptureGroups(pat, reader.RealPath)
+
+		tmpl, err := template.New("").Parse(contentTemplate)
+		if err != nil {
+			return nil, fmt.Errorf("unable to parse classifier template=%q : %w", contentTemplate, err)
+		}
+
+		patternBuf := &bytes.Buffer{}
+		err = tmpl.Execute(patternBuf, filepathNamedGroupValues)
+		if err != nil {
+			return nil, fmt.Errorf("unable to render template: %w", err)
+		}
+
+		tmplPattern, err := regexp.Compile(patternBuf.String())
+		if err != nil {
+			return nil, fmt.Errorf("unable to compile rendered regex=%q: %w", patternBuf.String(), err)
+		}
+
+		contents, err := getContents(reader)
+		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
+	}
+}
+
+func fileContentsVersionMatcher(pattern string) evidenceMatcher {
+	pat := regexp.MustCompile(pattern)
+	return func(classifier classifier, reader source.LocationReadCloser) ([]pkg.Package, error) {
+		contents, err := getContents(reader)
+		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
+	}
+}
+
+func mustPURL(purl string) packageurl.PackageURL {
+	p, err := packageurl.FromString(purl)
+	if err != nil {
+		panic(fmt.Sprintf("invalid PURL: %s", p))
+	}
+	return p
+}
+
+func singlePackage(classifier classifier, reader source.LocationReadCloser, matchMetadata map[string]string) []pkg.Package {
+	version, ok := matchMetadata["version"]
+	if !ok {
+		return nil
+	}
+
+	update := matchMetadata["update"]
+
+	var cpes []pkg.CPE
+	for _, cpe := range classifier.CPEs {
+		cpe.Version = version
+		cpe.Update = update
+		cpes = append(cpes, cpe)
+	}
+
+	p := pkg.Package{
+		Name:         classifier.Package,
+		Version:      version,
+		Language:     pkg.Binary,
+		Locations:    source.NewLocationSet(reader.Location),
+		Type:         pkg.BinaryPkg,
+		CPEs:         cpes,
+		FoundBy:      catalogerName,
+		MetadataType: pkg.BinaryMetadataType,
+		Metadata: pkg.BinaryMetadata{
+			Classifier:  classifier.Class,
+			RealPath:    reader.RealPath,
+			VirtualPath: reader.VirtualPath,
+		},
+	}
+
+	if classifier.Type != "" {
+		p.Type = classifier.Type
+	}
+
+	if !reflect.DeepEqual(classifier.PURL, emptyPURL) {
+		purl := classifier.PURL
+		purl.Version = version
+		p.PURL = purl.ToString()
+	}
+
+	if classifier.Language != "" {
+		p.Language = classifier.Language
+	}
+
+	p.SetID()
+
+	return []pkg.Package{p}
+}
+
+func getContents(reader source.LocationReadCloser) ([]byte, error) {
+	unionReader, err := unionreader.GetUnionReader(reader.ReadCloser)
+	if err != nil {
+		return nil, fmt.Errorf("unable to get union reader for file: %w", err)
+	}
+
+	// TODO: there may be room for improvement here, as this may use an excessive amount of memory. Alternate approach is to leverage a RuneReader.
+	contents, err := io.ReadAll(unionReader)
+	if err != nil {
+		return nil, fmt.Errorf("unable to get contents for file: %w", err)
+	}
+
+	return contents, nil
+}
+
+// singleCPE returns a []pkg.CPE based on the cpe string or panics if the CPE is invalid
+func singleCPE(cpe string) []pkg.CPE {
+	return []pkg.CPE{
+		pkg.MustCPE(cpe),
+	}
+}
@@ -1,7 +1,6 @@
-package generic
+package binary

 import (
-	"regexp"
 	"testing"

 	"github.com/stretchr/testify/require"
@@ -14,35 +13,27 @@ func Test_ClassifierCPEs(t *testing.T) {
 	tests := []struct {
 		name       string
 		fixture    string
-		classifier Classifier
+		classifier classifier
 		cpes       []string
 	}{
 		{
 			name:    "no CPEs",
 			fixture: "test-fixtures/version.txt",
-			classifier: Classifier{
-				Package: "some-app",
-				FilepathPatterns: []*regexp.Regexp{
-					regexp.MustCompile(".*/version.txt"),
-				},
-				EvidencePatterns: []*regexp.Regexp{
-					regexp.MustCompile(`(?m)my-verison:(?P<version>[0-9.]+)`),
-				},
-				CPEs: []pkg.CPE{},
+			classifier: classifier{
+				Package:         "some-app",
+				FileGlob:        ".*/version.txt",
+				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
+				CPEs:            []pkg.CPE{},
 			},
 			cpes: nil,
 		},
 		{
 			name:    "one CPE",
 			fixture: "test-fixtures/version.txt",
-			classifier: Classifier{
-				Package: "some-app",
-				FilepathPatterns: []*regexp.Regexp{
-					regexp.MustCompile(".*/version.txt"),
-				},
-				EvidencePatterns: []*regexp.Regexp{
-					regexp.MustCompile(`(?m)my-verison:(?P<version>[0-9.]+)`),
-				},
+			classifier: classifier{
+				Package:         "some-app",
+				FileGlob:        ".*/version.txt",
+				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
 				CPEs: []pkg.CPE{
 					pkg.MustCPE("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*"),
 				},
@@ -54,14 +45,10 @@ func Test_ClassifierCPEs(t *testing.T) {
 		{
 			name:    "multiple CPEs",
 			fixture: "test-fixtures/version.txt",
-			classifier: Classifier{
-				Package: "some-app",
-				FilepathPatterns: []*regexp.Regexp{
-					regexp.MustCompile(".*/version.txt"),
-				},
-				EvidencePatterns: []*regexp.Regexp{
-					regexp.MustCompile(`(?m)my-verison:(?P<version>[0-9.]+)`),
-				},
+			classifier: classifier{
+				Package:         "some-app",
+				FileGlob:        ".*/version.txt",
+				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
 				CPEs: []pkg.CPE{
 					pkg.MustCPE("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*"),
 					pkg.MustCPE("cpe:2.3:a:some:apps:*:*:*:*:*:*:*:*"),
@@ -83,9 +70,13 @@ func Test_ClassifierCPEs(t *testing.T) {
 			location := locations[0]
 			readCloser, err := resolver.FileContentsByLocation(location)
 			require.NoError(t, err)
-			p, _, err := test.classifier.Examine(source.NewLocationReadCloser(location, readCloser))
+			pkgs, err := test.classifier.EvidenceMatcher(test.classifier, source.NewLocationReadCloser(location, readCloser))
 			require.NoError(t, err)

+			require.Len(t, pkgs, 1)
+
+			p := pkgs[0]
+
 			var cpes []string
 			for _, c := range p.CPEs {
 				cpes = append(cpes, pkg.CPEString(c))
@@ -0,0 +1,89 @@
+package binary
+
+import "github.com/anchore/syft/syft/pkg"
+
+var defaultClassifiers = []classifier{
+	{
+		Class:    "python-binary",
+		FileGlob: "**/python*",
+		EvidenceMatcher: fileNameTemplateVersionMatcher(
+			`(.*/|^)python(?P<version>[0-9]+\.[0-9]+)$`,
+			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
+		Package: "python",
+	},
+	{
+		Class:    "python-binary-lib",
+		FileGlob: "**/libpython*.so*",
+		EvidenceMatcher: fileNameTemplateVersionMatcher(
+			`(.*/|^)libpython(?P<version>[0-9]+\.[0-9]+).so.*$`,
+			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
+		Package: "python",
+	},
+	{
+		Class:    "cpython-source",
+		FileGlob: "**/patchlevel.h",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			`(?m)#define\s+PY_VERSION\s+"?(?P<version>[0-9\.\-_a-zA-Z]+)"?`),
+		Package: "python",
+	},
+	{
+		Class:    "go-binary",
+		FileGlob: "**/go",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			`(?m)go(?P<version>[0-9]+\.[0-9]+(\.[0-9]+|beta[0-9]+|alpha[0-9]+|rc[0-9]+)?)\x00`),
+		Package: "go",
+		CPEs:    singleCPE("cpe:2.3:a:golang:go:*:*:*:*:*:*:*:*"),
+	},
+	{
+		Class:    "java-binary-openjdk",
+		FileGlob: "**/java",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			// [NUL]openjdk[NUL]java[NUL]1.8[NUL]1.8.0_352-b08[NUL]
+			`(?m)\x00openjdk\x00java\x00(?P<release>[0-9]+[.0-9]+)\x00(?P<version>[0-9]+[-._a-zA-Z0-9]+)\x00`),
+		Package: "java",
+		// TODO the updates might need to be part of the CPE, like: 1.8.0:update152
+		CPEs: singleCPE("cpe:2.3:a:oracle:openjdk:*:*:*:*:*:*:*:*"),
+	},
+	{
+		Class:    "java-binary-ibm",
+		FileGlob: "**/java",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			// [NUL]java[NUL]1.8[NUL][NUL][NUL][NUL]1.8.0-foreman_2022_09_22_15_30-b00[NUL]
+			`(?m)\x00java\x00(?P<release>[0-9]+[.0-9]+)\x00{4}(?P<version>[0-9]+[-._a-zA-Z0-9]+)\x00`),
+		Package: "java",
+		CPEs:    singleCPE("cpe:2.3:a:ibm:java:*:*:*:*:*:*:*:*"),
+	},
+	{
+		Class:    "java-binary-oracle",
+		FileGlob: "**/java",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			// [NUL]19.0.1+10-21[NUL]
+			`(?m)\x00(?P<version>[0-9]+[.0-9]+[+][-0-9]+)\x00`),
+		Package: "java",
+		CPEs:    singleCPE("cpe:2.3:a:oracle:jre:*:*:*:*:*:*:*:*"),
+	},
+	{
+		Class:    "nodejs-binary",
+		FileGlob: "**/node",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			`(?m)node\.js\/v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
+		Package:  "node",
+		Language: pkg.JavaScript,
+		PURL:     mustPURL("pkg:generic/node@version"),
+		CPEs:     singleCPE("cpe:2.3:a:nodejs:node.js:*:*:*:*:*:*:*:*"),
+	},
+	{
+		Class:    "go-binary-hint",
+		FileGlob: "**/VERSION",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			`(?m)go(?P<version>[0-9]+\.[0-9]+(\.[0-9]+|beta[0-9]+|alpha[0-9]+|rc[0-9]+)?)`),
+		Package: "go",
+	},
+	{
+		Class:    "busybox-binary",
+		FileGlob: "**/busybox",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			`(?m)BusyBox\s+v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
+		Package: "busybox",
+	},
+}
@@ -0,0 +1,2 @@
+# this should match node 19.2.1
+node.js/v19.2.1
@@ -12,6 +12,7 @@ import (
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/alpm"
 	"github.com/anchore/syft/syft/pkg/cataloger/apkdb"
+	"github.com/anchore/syft/syft/pkg/cataloger/binary"
 	"github.com/anchore/syft/syft/pkg/cataloger/cpp"
 	"github.com/anchore/syft/syft/pkg/cataloger/dart"
 	"github.com/anchore/syft/syft/pkg/cataloger/deb"
@@ -40,7 +41,6 @@ func ImageCatalogers(cfg Config) []pkg.Cataloger {
 		python.NewPythonPackageCataloger(),
 		php.NewPHPComposerInstalledCataloger(),
 		javascript.NewJavascriptPackageCataloger(),
-		javascript.NewNodeBinaryCataloger(),
 		deb.NewDpkgdbCataloger(),
 		rpm.NewRpmDBCataloger(),
 		java.NewJavaCataloger(cfg.Java()),
@@ -49,6 +49,7 @@ func ImageCatalogers(cfg Config) []pkg.Cataloger {
 		dotnet.NewDotnetDepsCataloger(),
 		portage.NewPortageCataloger(),
 		sbom.NewSBOMCataloger(),
+		binary.NewCataloger(),
 	}, cfg.Catalogers)
 }

@@ -61,7 +62,6 @@ func DirectoryCatalogers(cfg Config) []pkg.Cataloger {
 		python.NewPythonPackageCataloger(),
 		php.NewPHPComposerLockCataloger(),
 		javascript.NewJavascriptLockCataloger(),
-		javascript.NewNodeBinaryCataloger(),
 		deb.NewDpkgdbCataloger(),
 		rpm.NewRpmDBCataloger(),
 		rpm.NewFileCataloger(),
@@ -78,6 +78,7 @@ func DirectoryCatalogers(cfg Config) []pkg.Cataloger {
 		portage.NewPortageCataloger(),
 		haskell.NewHackageCataloger(),
 		sbom.NewSBOMCataloger(),
+		binary.NewCataloger(),
 	}, cfg.Catalogers)
 }

@@ -91,7 +92,6 @@ func AllCatalogers(cfg Config) []pkg.Cataloger {
 		python.NewPythonPackageCataloger(),
 		javascript.NewJavascriptLockCataloger(),
 		javascript.NewJavascriptPackageCataloger(),
-		javascript.NewNodeBinaryCataloger(),
 		deb.NewDpkgdbCataloger(),
 		rpm.NewRpmDBCataloger(),
 		rpm.NewFileCataloger(),
@@ -111,6 +111,7 @@ func AllCatalogers(cfg Config) []pkg.Cataloger {
 		portage.NewPortageCataloger(),
 		haskell.NewHackageCataloger(),
 		sbom.NewSBOMCataloger(),
+		binary.NewCataloger(),
 	}, cfg.Catalogers)
 }

@@ -11,6 +11,12 @@ type candidateComposite struct {
 	candidateAddition
 }

+type candidateRemovalComposite struct {
+	pkg.Type
+	candidateKey
+	candidateRemovals
+}
+
 // defaultCandidateAdditions is all of the known cases for product and vendor field values that should be used when
 // select package information is discovered
 var defaultCandidateAdditions = buildCandidateLookup(
@@ -123,6 +129,16 @@ var defaultCandidateAdditions = buildCandidateLookup(
 		},
 	})

+var defaultCandidateRemovals = buildCandidateRemovalLookup(
+	[]candidateRemovalComposite{
+		// Python packages
+		{
+			pkg.PythonPkg,
+			candidateKey{PkgName: "redis"},
+			candidateRemovals{VendorsToRemove: []string{"redis"}},
+		},
+	})
+
 // buildCandidateLookup is a convenience function for creating the defaultCandidateAdditions set
 func buildCandidateLookup(cc []candidateComposite) (ca map[pkg.Type]map[candidateKey]candidateAddition) {
 	ca = make(map[pkg.Type]map[candidateKey]candidateAddition)
@@ -136,12 +152,30 @@ func buildCandidateLookup(cc []candidateComposite) (ca map[pkg.Type]map[candidat
 	return ca
 }

+// buildCandidateRemovalLookup is a convenience function for creating the defaultCandidateRemovals set
+func buildCandidateRemovalLookup(cc []candidateRemovalComposite) (ca map[pkg.Type]map[candidateKey]candidateRemovals) {
+	ca = make(map[pkg.Type]map[candidateKey]candidateRemovals)
+	for _, c := range cc {
+		if _, ok := ca[c.Type]; !ok {
+			ca[c.Type] = make(map[candidateKey]candidateRemovals)
+		}
+		ca[c.Type][c.candidateKey] = c.candidateRemovals
+	}
+	return ca
+}
+
 // candidateKey represents the set of inputs that should be matched on in order to signal more candidate additions to be used.
 type candidateKey struct {
 	Vendor  string
 	PkgName string
 }

+// candidateRemovals are the specific removals that should be considered during CPE generation (given a specific candidateKey)
+type candidateRemovals struct {
+	ProductsToRemove []string
+	VendorsToRemove  []string
+}
+
 // candidateAddition are the specific additions that should be considered during CPE generation (given a specific candidateKey)
 type candidateAddition struct {
 	AdditionalProducts []string
@@ -192,3 +226,35 @@ func findAdditionalProducts(allAdditions map[pkg.Type]map[candidateKey]candidate

 	return products
 }
+
+// findVendorsToRemove searches all possible vendor removals that could be removed during the CPE generation process (given package info + a vendor candidate)
+func findVendorsToRemove(allRemovals map[pkg.Type]map[candidateKey]candidateRemovals, ty pkg.Type, pkgName string) (vendors []string) {
+	removals, ok := allRemovals[ty]
+	if !ok {
+		return nil
+	}
+
+	if removal, ok := removals[candidateKey{
+		PkgName: pkgName,
+	}]; ok {
+		vendors = append(vendors, removal.VendorsToRemove...)
+	}
+
+	return vendors
+}
+
+// findProductsToRemove searches all possible product removals that could be removed during the CPE generation process (given package info)
+func findProductsToRemove(allRemovals map[pkg.Type]map[candidateKey]candidateRemovals, ty pkg.Type, pkgName string) (products []string) {
+	removals, ok := allRemovals[ty]
+	if !ok {
+		return nil
+	}
+
+	if removal, ok := removals[candidateKey{
+		PkgName: pkgName,
+	}]; ok {
+		products = append(products, removal.ProductsToRemove...)
+	}
+
+	return products
+}
@@ -154,3 +154,81 @@ func Test_additionalVendors(t *testing.T) {
 		})
 	}
 }
+
+func Test_findVendorsToRemove(t *testing.T) {
+	//GIVEN
+	tests := []struct {
+		name     string
+		ty       pkg.Type
+		pkgName  string
+		expected []string
+	}{
+		{
+			name:     "vendor removal match by input package name",
+			ty:       pkg.JavaPkg,
+			pkgName:  "my-package-name",
+			expected: []string{"awesome-vendor-addition"},
+		},
+		{
+			name:    "vendor removal miss by input package name",
+			ty:      pkg.JavaPkg,
+			pkgName: "my-package-name-1",
+		},
+	}
+
+	allRemovals := map[pkg.Type]map[candidateKey]candidateRemovals{
+		pkg.JavaPkg: {
+			candidateKey{
+				PkgName: "my-package-name",
+			}: {
+				VendorsToRemove: []string{"awesome-vendor-addition"},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			//WHEN + THEN
+			assert.Equal(t, test.expected, findVendorsToRemove(allRemovals, test.ty, test.pkgName))
+		})
+	}
+}
+
+func Test_findProductsToRemove(t *testing.T) {
+	//GIVEN
+	tests := []struct {
+		name     string
+		ty       pkg.Type
+		pkgName  string
+		expected []string
+	}{
+		{
+			name:     "vendor removal match by input package name",
+			ty:       pkg.JavaPkg,
+			pkgName:  "my-package-name",
+			expected: []string{"awesome-vendor-addition"},
+		},
+		{
+			name:    "vendor removal miss by input package name",
+			ty:      pkg.JavaPkg,
+			pkgName: "my-package-name-1",
+		},
+	}
+
+	allRemovals := map[pkg.Type]map[candidateKey]candidateRemovals{
+		pkg.JavaPkg: {
+			candidateKey{
+				PkgName: "my-package-name",
+			}: {
+				ProductsToRemove: []string{"awesome-vendor-addition"},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			//WHEN + THEN
+			assert.Equal(t, test.expected, findProductsToRemove(allRemovals, test.ty, test.pkgName))
+		})
+	}
+}
@@ -116,6 +116,9 @@ func candidateVendors(p pkg.Package) []string {
 		vendors.addValue(findAdditionalVendors(defaultCandidateAdditions, p.Type, p.Name, vendor)...)
 	}

+	// remove known mis
+	vendors.removeByValue(findVendorsToRemove(defaultCandidateRemovals, p.Type, p.Name)...)
+
 	return vendors.uniqueValues()
 }

@@ -148,6 +151,9 @@ func candidateProducts(p pkg.Package) []string {
 	// add known candidate additions
 	products.addValue(findAdditionalProducts(defaultCandidateAdditions, p.Type, p.Name)...)

+	// remove known candidate removals
+	products.removeByValue(findProductsToRemove(defaultCandidateRemovals, p.Type, p.Name)...)
+
 	return products.uniqueValues()
 }

@@ -666,6 +666,27 @@ func TestGeneratePackageCPEs(t *testing.T) {
 				"cpe:2.3:a:stephanie_morillo:bundler:2.1.4:*:*:*:*:*:*:*",
 			},
 		},
+		{
+			name: "regression: python redis shadows normal redis",
+			p: pkg.Package{
+				Name:     "redis",
+				Version:  "2.1.4",
+				Type:     pkg.PythonPkg,
+				FoundBy:  "some-analyzer",
+				Language: pkg.Python,
+			},
+			expected: []string{
+				"cpe:2.3:a:python-redis:python-redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python-redis:python_redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python-redis:redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python:python-redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python:python_redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python:redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python_redis:python-redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python_redis:python_redis:2.1.4:*:*:*:*:*:*:*",
+				"cpe:2.3:a:python_redis:redis:2.1.4:*:*:*:*:*:*:*",
+			},
+		},
 	}

 	for _, test := range tests {
@@ -118,6 +118,8 @@ func (c *Cataloger) Catalog(resolver source.FileResolver) ([]pkg.Package, []arti
 	for _, req := range c.selectFiles(resolver) {
 		location, parser := req.Location, req.Parser

+		log.WithFields("path", location.RealPath).Trace("parsing file contents")
+
 		contentReader, err := resolver.FileContentsByLocation(location)
 		if err != nil {
 			logger.WithFields("location", location.RealPath, "error", err).Warn("unable to fetch contents")
@@ -1,100 +0,0 @@
-package generic
-
-import (
-	"fmt"
-	"io"
-	"path"
-	"regexp"
-
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/file"
-	"github.com/anchore/syft/syft/pkg"
-	"github.com/anchore/syft/syft/pkg/cataloger/internal/unionreader"
-	"github.com/anchore/syft/syft/source"
-)
-
-// Classifier is a generic package classifier that can be used to match a package definition
-// to a file that meets the given content criteria of the EvidencePatternTemplates.
-type Classifier struct {
-	Package string
-	// FilepathPatterns is a list of regular expressions that will be used to match against the file path of a given
-	// source location. If any of the patterns match, the file will be considered a candidate for parsing.
-	// If no patterns are provided, the reader is automatically considered a candidate.
-	FilepathPatterns []*regexp.Regexp
-	// EvidencePatterns is a list of regular expressions that will be used to match against the file contents of a
-	// given file in the source location. If any of the patterns match, the file will be considered a candidate for parsing.
-	EvidencePatterns []*regexp.Regexp
-	// CPEs are the specific CPEs we want to include for this binary with updated version information
-	CPEs []pkg.CPE
-}
-
-func (c Classifier) Examine(reader source.LocationReadCloser) (p *pkg.Package, r *artifact.Relationship, err error) {
-	doesFilepathMatch := true
-	if len(c.FilepathPatterns) > 0 {
-		doesFilepathMatch, _ = file.FilepathMatches(c.FilepathPatterns, reader.Location)
-	}
-
-	if !doesFilepathMatch {
-		return nil, nil, fmt.Errorf("location: %s did not match any patterns for package=%q", reader.Location, c.Package)
-	}
-
-	contents, err := getContents(reader)
-	if err != nil {
-		return nil, nil, fmt.Errorf("unable to get read contents for file: %w", err)
-	}
-
-	var classifiedPackage *pkg.Package
-	for _, evidencePattern := range c.EvidencePatterns {
-		if !evidencePattern.Match(contents) {
-			continue
-		}
-
-		matchMetadata := internal.MatchNamedCaptureGroups(evidencePattern, string(contents))
-		version, ok := matchMetadata["version"]
-		if !ok {
-			log.Debugf("no version found in binary from pattern %v", evidencePattern)
-			continue
-		}
-
-		var cpes []pkg.CPE
-		for _, cpe := range c.CPEs {
-			cpe.Version = version
-			if err == nil {
-				cpes = append(cpes, cpe)
-			}
-		}
-
-		classifiedPackage = &pkg.Package{
-			Name:         path.Base(reader.VirtualPath),
-			Version:      version,
-			Language:     pkg.Binary,
-			Locations:    source.NewLocationSet(reader.Location),
-			Type:         pkg.BinaryPkg,
-			CPEs:         cpes,
-			MetadataType: pkg.BinaryMetadataType,
-			Metadata: pkg.BinaryMetadata{
-				Classifier:  c.Package,
-				RealPath:    reader.RealPath,
-				VirtualPath: reader.VirtualPath,
-			},
-		}
-		break
-	}
-	return classifiedPackage, nil, nil
-}
-
-func getContents(reader source.LocationReadCloser) ([]byte, error) {
-	unionReader, err := unionreader.GetUnionReader(reader.ReadCloser)
-	if err != nil {
-		return nil, fmt.Errorf("unable to get union reader for file: %w", err)
-	}
-
-	contents, err := io.ReadAll(unionReader)
-	if err != nil {
-		return nil, fmt.Errorf("unable to get contents for file: %w", err)
-	}
-
-	return contents, nil
-}
@@ -2,6 +2,8 @@ package golang

 import (
 	"debug/buildinfo"
+	"fmt"
+	"io"
 	"runtime/debug"

 	"github.com/anchore/syft/internal/log"
@@ -14,31 +16,20 @@ func scanFile(reader unionreader.UnionReader, filename string) ([]*debug.BuildIn
 	// with more than one binary
 	readers, err := unionreader.GetReaders(reader)
 	if err != nil {
-		log.Warnf("golang cataloger: failed to open a binary: %v", err)
+		log.WithFields("error", err).Warnf("failed to open a golang binary")
 		return nil, nil
 	}

 	var builds []*debug.BuildInfo
 	for _, r := range readers {
-		bi, err := buildinfo.Read(r)
-
-		// note: the stdlib does not export the error we need to check for
+		bi, err := getBuildInfo(r)
 		if err != nil {
-			if err.Error() == "not a Go executable" {
-				// since the cataloger can only select executables and not distinguish if they are a go-compiled
-				// binary, we should not show warnings/logs in this case.
-				return nil, nil
-			}
-			// in this case we could not read the or parse the file, but not explicitly because it is not a
-			// go-compiled binary (though it still might be).
-			// TODO: We should change this back to "warn" eventually.
-			//  But right now it's catching too many cases where the reader IS NOT a Go binary at all.
-			//  It'd be great to see how we can get those cases to be detected and handled above before we get to
-			//  this point in execution.
-			log.Infof("golang cataloger: unable to read buildinfo (file=%q): %v", filename, err)
-			return nil, nil
+			log.WithFields("file", filename, "error", err).Warn("unable to read golang buildinfo")
+			continue
+		}
+		if bi == nil {
+			continue
 		}
-
 		builds = append(builds, bi)
 	}

@@ -46,3 +37,28 @@ func scanFile(reader unionreader.UnionReader, filename string) ([]*debug.BuildIn

 	return builds, archs
 }
+
+func getBuildInfo(r io.ReaderAt) (bi *debug.BuildInfo, err error) {
+	defer func() {
+		if r := recover(); r != nil {
+			// this can happen in cases where a malformed binary is passed in can be initially parsed, but not
+			// used without error later down the line. This is the case with :
+			// https://github.com/llvm/llvm-project/blob/llvmorg-15.0.6/llvm/test/Object/Inputs/macho-invalid-dysymtab-bad-size
+			err = fmt.Errorf("recovered from panic: %v", r)
+		}
+	}()
+	bi, err = buildinfo.Read(r)
+
+	// note: the stdlib does not export the error we need to check for
+	if err != nil {
+		if err.Error() == "not a Go executable" {
+			// since the cataloger can only select executables and not distinguish if they are a go-compiled
+			// binary, we should not show warnings/logs in this case.
+			return
+		}
+		// in this case we could not read the or parse the file, but not explicitly because it is not a
+		// go-compiled binary (though it still might be).
+		return
+	}
+	return
+}
@@ -0,0 +1,40 @@
+package golang
+
+import (
+	"fmt"
+	"io"
+	"runtime/debug"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_getBuildInfo(t *testing.T) {
+	type args struct {
+		r io.ReaderAt
+	}
+	tests := []struct {
+		name    string
+		args    args
+		wantBi  *debug.BuildInfo
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "recover from panic",
+			args: args{
+				r: nil, // trying to use a nil reader will cause a panic
+			},
+			wantBi:  nil, // we should not return anything useful
+			wantErr: assert.Error,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			gotBi, err := getBuildInfo(tt.args.r)
+			if !tt.wantErr(t, err, fmt.Sprintf("getBuildInfo(%v)", tt.args.r)) {
+				return
+			}
+			assert.Equalf(t, tt.wantBi, gotBi, "getBuildInfo(%v)", tt.args.r)
+		})
+	}
+}
@@ -4,7 +4,6 @@ Package javascript provides a concrete Cataloger implementation for JavaScript e
 package javascript

 import (
-	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 )

@@ -20,8 +19,3 @@ func NewJavascriptLockCataloger() *generic.Cataloger {
 		WithParserByGlobs(parseYarnLock, "**/yarn.lock").
 		WithParserByGlobs(parsePnpmLock, "**/pnpm-lock.yaml")
 }
-
-func NewNodeBinaryCataloger() *generic.Cataloger {
-	return generic.NewCataloger("node-binary-cataloger").
-		WithParserByMimeTypes(parseNodeBinary, internal.ExecutableMIMETypeSet.List()...)
-}
@@ -1,43 +0,0 @@
-package javascript
-
-import (
-	"regexp"
-
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/pkg"
-	"github.com/anchore/syft/syft/pkg/cataloger/generic"
-	"github.com/anchore/syft/syft/source"
-)
-
-var nodeClassifier = generic.Classifier{
-	Package: "node.js", // Note: this purposely matches the "node.js" string to aid nvd vuln matching
-	FilepathPatterns: []*regexp.Regexp{
-		// note: should we just parse all files resolved with executable mimetypes
-		// regexp that matches node binary
-		regexp.MustCompile(`(.*/|^)node$`),
-	},
-	EvidencePatterns: []*regexp.Regexp{
-		// regex that matches node.js/vx.y.z
-		regexp.MustCompile(`(?m)node\.js\/v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
-	},
-	CPEs: []pkg.CPE{
-		pkg.MustCPE("cpe:2.3:a:nodejs:node.js:*:*:*:*:*:*:*:*"),
-	},
-}
-
-func parseNodeBinary(_ source.FileResolver, _ *generic.Environment, reader source.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
-	p, _, err := nodeClassifier.Examine(reader)
-	if err != nil {
-		log.Trace("failed to find node.js package: %+v", err)
-		return nil, nil, nil // we can silently fail here to reduce warning noise
-	}
-
-	// TODO add node specific metadata to the packages to help with vulnerability matching
-	if p != nil {
-		p.Language = pkg.JavaScript
-		p.SetID()
-		return []pkg.Package{*p}, nil, nil
-	}
-	return nil, nil, nil
-}
@@ -0,0 +1,7 @@
+package pkg
+
+type FileMetadata struct {
+	Classifier  string `mapstructure:"Classifier" json:"classifier"`
+	RealPath    string `mapstructure:"RealPath" json:"realPath"`
+	VirtualPath string `mapstructure:"VirtualPath" json:"virtualPath"`
+}
@@ -25,6 +25,7 @@ const (
 	CPP             Language = "c++"
 	Haskell         Language = "haskell"
 	Binary          Language = "binary"
+	File            Language = "file"
 )

 // AllLanguages is a set of all programming languages detected by syft.
@@ -18,13 +18,12 @@ type SBOM struct {
 }

 type Artifacts struct {
-	PackageCatalog      *pkg.Catalog
-	FileMetadata        map[source.Coordinates]source.FileMetadata
-	FileDigests         map[source.Coordinates][]file.Digest
-	FileClassifications map[source.Coordinates][]file.Classification
-	FileContents        map[source.Coordinates]string
-	Secrets             map[source.Coordinates][]file.SearchResult
-	LinuxDistribution   *linux.Release
+	PackageCatalog    *pkg.Catalog
+	FileMetadata      map[source.Coordinates]source.FileMetadata
+	FileDigests       map[source.Coordinates][]file.Digest
+	FileContents      map[source.Coordinates]string
+	Secrets           map[source.Coordinates][]file.SearchResult
+	LinuxDistribution *linux.Release
 }

 type Descriptor struct {
@@ -55,9 +54,6 @@ func (s SBOM) AllCoordinates() []source.Coordinates {
 	for coordinates := range s.Artifacts.FileContents {
 		set.Add(coordinates)
 	}
-	for coordinates := range s.Artifacts.FileClassifications {
-		set.Add(coordinates)
-	}
 	for coordinates := range s.Artifacts.FileDigests {
 		set.Add(coordinates)
 	}
@@ -1,5 +1,5 @@
 # LAYER 0:
-FROM busybox:latest
+FROM busybox:1.34.0

 # LAYER 1:
 ADD file-1.txt .
@@ -105,7 +105,7 @@ func TestPackagesCmdFlags(t *testing.T) {
 			name: "squashed-scope-flag-hidden-packages",
 			args: []string{"packages", "-o", "json", "-s", "squashed", hiddenPackagesImage},
 			assertions: []traitAssertion{
-				assertPackageCount(162),
+				assertPackageCount(163),
 				assertNotInOutput("vsftpd"), // hidden package
 				assertSuccessfulReturnCode,
 			},
@@ -114,7 +114,7 @@ func TestPackagesCmdFlags(t *testing.T) {
 			name: "all-layers-scope-flag",
 			args: []string{"packages", "-o", "json", "-s", "all-layers", hiddenPackagesImage},
 			assertions: []traitAssertion{
-				assertPackageCount(163), // packages are now deduplicated for this case
+				assertPackageCount(164), // packages are now deduplicated for this case
 				assertInOutput("all-layers"),
 				assertInOutput("vsftpd"), // hidden package
 				assertSuccessfulReturnCode,
@@ -127,7 +127,7 @@ func TestPackagesCmdFlags(t *testing.T) {
 				"SYFT_PACKAGE_CATALOGER_SCOPE": "all-layers",
 			},
 			assertions: []traitAssertion{
-				assertPackageCount(163), // packages are now deduplicated for this case
+				assertPackageCount(164), // packages are now deduplicated for this case
 				assertInOutput("all-layers"),
 				assertInOutput("vsftpd"), // hidden package
 				assertSuccessfulReturnCode,
@@ -9,6 +9,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"

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

@@ -21,7 +22,7 @@ func TestPackageDeduplication(t *testing.T) {
 	}{
 		{
 			scope:        source.AllLayersScope,
-			packageCount: 172, // without deduplication this would be 618
+			packageCount: 173, // without deduplication this would be 618
 			instanceCount: map[string]int{
 				"basesystem": 1,
 				"wget":       1,
@@ -40,7 +41,7 @@ func TestPackageDeduplication(t *testing.T) {
 		},
 		{
 			scope:        source.SquashedScope,
-			packageCount: 170,
+			packageCount: 171,
 			instanceCount: map[string]int{
 				"basesystem": 1,
 				"wget":       1,
@@ -62,6 +63,12 @@ func TestPackageDeduplication(t *testing.T) {
 		t.Run(string(tt.scope), func(t *testing.T) {
 			sbom, _ := catalogFixtureImage(t, "image-vertical-package-dups", tt.scope, nil)

+			for _, p := range sbom.Artifacts.PackageCatalog.Sorted() {
+				if p.Type == pkg.BinaryPkg {
+					assert.NotEmpty(t, p.Name)
+				}
+			}
+
 			assert.Equal(t, tt.packageCount, sbom.Artifacts.PackageCatalog.PackageCount())
 			for name, expectedInstanceCount := range tt.instanceCount {
 				pkgs := sbom.Artifacts.PackageCatalog.PackagesByName(name)
Author	SHA1	Message	Date
Christopher Angelo Phillips	23a3173c9f	feat: add catalog delete (#1377 )	2022-12-12 12:55:12 -05:00
Keith Zantow	17aa8287e6	docs: remove file classifier (#1397 )	2022-12-08 16:50:29 +00:00
Christopher Angelo Phillips	730d3e3187	chore: update latest cyclonedx library (#1390 )	2022-12-08 11:36:08 -05:00
Keith Zantow	997fbdfcf3	feat: Add Java binary catalogers (#1392 )	2022-12-08 10:50:28 -05:00
Marc-Etienne Vargenau	13ceed9336	chore: Update SPDX license list to 3.19 (#1389 )	2022-12-08 10:29:27 -05:00
Chapman Pendery	668f102340	fix: add manual vendor/product removal to fix false flags (#1070 ) Closes https://github.com/anchore/syft/issues/1066 Closes https://github.com/anchore/grype/issues/800 Closes https://github.com/anchore/grype/issues/491	2022-12-08 09:57:42 -05:00
anchore-actions-token-generator[bot]	f1a124209a	Update Stereoscope to c5ff155d72f166e2332e160a75c3ff2b8e9c7e2e (#1395 ) Signed-off-by: GitHub <noreply@github.com>	2022-12-08 08:32:49 +00:00
Keith Zantow	5dbb3fc41d	chore: fix test busybox image sha (#1393 )	2022-12-07 20:15:39 -05:00
Keith Zantow	614ea00905	fix: go version not properly identified in binary (#1384 )	2022-12-02 13:24:36 -05:00
anchore-actions-token-generator[bot]andwagoodman	247b054ab5	Update Stereoscope to 3b80d983223f6e6fc2d33b0ffa003d30268418e9 (#1376 ) Signed-off-by: GitHub <noreply@github.com> Signed-off-by: GitHub <noreply@github.com> Co-authored-by: wagoodman <wagoodman@users.noreply.github.com>	2022-11-30 16:11:57 +00:00
Keith Zantow	9e43725951	fix: Update node binary package name (#1375 )	2022-11-30 10:30:57 -05:00
Keith Zantow	4f39287216	feat: Generic Binary Cataloger (#1336 )	2022-11-29 18:28:10 -05:00
Alex Goodman	7a69e2129b	recover from bad parsing of golang binary (#1371 ) Signed-off-by: Alex Goodman <alex.goodman@anchore.com> Signed-off-by: Alex Goodman <alex.goodman@anchore.com>	2022-11-29 15:56:46 +00:00
Dan Luhring	f6996f7b9a	Fix parsing of apk databases with large entries (#1365 ) Closes https://github.com/anchore/syft/issues/1354	2022-11-29 10:16:36 -05:00
anchore-actions-token-generator[bot]andspiffcs	bd523bdb5d	Update syft bootstrap tools to latest versions. (#1369 ) Co-authored-by: spiffcs <spiffcs@users.noreply.github.com>	2022-11-29 10:13:00 -05:00