switch from trigger-release target to release target (#1560)

Signed-off-by: Alex Goodman <alex.goodman@anchore.com>

.github/actions/bootstrap/action.yaml

@@ -4,7 +4,7 @@ inputs:
   go-version:
     description: "Go version to install"
     required: true
-    default: "1.18.x"
+    default: "1.19.x"
   use-go-cache:
     description: "Restore go cache"
     required: true

.github/scripts/ci-check.sh

@@ -6,6 +6,6 @@ normal=$(tput sgr0)
 
 # assert we are running in CI (or die!)
 if [[ -z "$CI" ]]; then
-    echo "${bold}${red}This script should ONLY be run in CI. Exiting...${normal}"
+    echo "${bold}${red}This step should ONLY be run in CI. Exiting...${normal}"
     exit 1
 fi

.github/scripts/go-mod-tidy-check.sh

@@ -4,7 +4,7 @@ set -eu
 ORIGINAL_STATE_DIR=$(mktemp -d "TEMP-original-state-XXXXXXXXX")
 TIDY_STATE_DIR=$(mktemp -d "TEMP-tidy-state-XXXXXXXXX")
 
-trap "cp ${ORIGINAL_STATE_DIR}/* ./ && rm -fR ${ORIGINAL_STATE_DIR} ${TIDY_STATE_DIR}" EXIT
+trap "cp -p ${ORIGINAL_STATE_DIR}/* ./ && git update-index -q --refresh && rm -fR ${ORIGINAL_STATE_DIR} ${TIDY_STATE_DIR}" EXIT
 
 # capturing original state of files...
 cp go.mod go.sum "${ORIGINAL_STATE_DIR}"

.github/scripts/json-schema-drift-check.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -u
+
+if ! git diff-index --quiet HEAD --; then
+  git diff-index HEAD --
+  git --no-pager diff
+  echo "there are uncommitted changes, please commit them before running this check"
+  exit 1
+fi
+
+success=true
+
+if ! make generate-json-schema; then
+  echo "Generating json schema failed"
+  success=false
+fi
+
+if ! git diff-index --quiet HEAD --; then
+  git diff-index HEAD --
+  git --no-pager diff
+  echo "JSON schema drift detected!"
+  success=false
+fi
+
+if ! $success; then
+  exit 1
+fi

.github/scripts/trigger-release.sh

@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+set -eu
+
+bold=$(tput bold)
+normal=$(tput sgr0)
+
+if ! [ -x "$(command -v gh)" ]; then
+    echo "The GitHub CLI could not be found. To continue follow the instructions at https://github.com/cli/cli#installation"
+    exit 1
+fi
+
+gh auth status
+
+# we need all of the git state to determine the next version. Since tagging is done by
+# the release pipeline it is possible to not have all of the tags from previous releases.
+git fetch --tags
+
+# populates the CHANGELOG.md and VERSION files
+echo "${bold}Generating changelog...${normal}"
+make changelog 2> /dev/null
+
+NEXT_VERSION=$(cat VERSION)
+
+if [[ "$NEXT_VERSION" == "" ||  "${NEXT_VERSION}" == "(Unreleased)" ]]; then
+    echo "Could not determine the next version to release. Exiting..."
+    exit 1
+fi
+
+while true; do
+    read -p "${bold}Do you want to trigger a release for version '${NEXT_VERSION}'?${normal} [y/n] " yn
+    case $yn in
+        [Yy]* ) echo; break;;
+        [Nn]* ) echo; echo "Cancelling release..."; exit;;
+        * ) echo "Please answer yes or no.";;
+    esac
+done
+
+echo "${bold}Kicking off release for ${NEXT_VERSION}${normal}..."
+echo
+gh workflow run release.yaml -f version=${NEXT_VERSION}
+
+echo
+echo "${bold}Waiting for release to start...${normal}"
+sleep 10
+
+set +e
+
+echo "${bold}Head to the release workflow to monitor the release:${normal} $(gh run list --workflow=release.yaml --limit=1 --json url --jq '.[].url')"
+id=$(gh run list --workflow=release.yaml --limit=1 --json databaseId --jq '.[].databaseId')
+gh run watch $id --exit-status || (echo ; echo "${bold}Logs of failed step:${normal}" && GH_PAGER="" gh run view $id --log-failed)

.github/workflows/release.yaml

@@ -1,15 +1,13 @@
 name: "Release"
 on:
-  push:
-    # take no actions on push to any branch...
-    branches-ignore:
-      - "**"
-    # ... only act on release tags
-    tags:
-      - "v*"
+  workflow_dispatch:
+    inputs:
+      version:
+        description: tag the latest commit on main with the given version (prefixed with v)
+        required: true
 
 env:
-  GO_VERSION: "1.18.x"
+  GO_VERSION: "1.19.x"
 
 jobs:
   quality-gate:
@@ -18,12 +16,11 @@ jobs:
     steps:
       - uses: actions/checkout@v3
 
-      # we don't want to release commits that have been pushed and tagged, but not necessarily merged onto main
-      - name: Ensure tagged commit is on main
+      - name: Check if tag already exists
+        # note: this will fail if the tag already exists
         run: |
-          echo "Tag: ${GITHUB_REF##*/}"
-          git fetch origin main
-          git merge-base --is-ancestor ${GITHUB_REF##*/} origin/main && echo "${GITHUB_REF##*/} is a commit on main!"
+          [[ "${{ github.event.inputs.version }}" == v* ]] || (echo "version '${{ github.event.inputs.version }}' does not have a 'v' prefix" && exit 1)
+          git tag ${{ github.event.inputs.version }}
 
       - name: Check static analysis results
         uses: fountainhead/action-wait-for-check@v1.1.0
@@ -120,8 +117,15 @@ jobs:
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
+      - name: Tag release
+        run: |
+          git tag ${{ github.event.inputs.version }}
+          git push origin --tags
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
       - name: Build & publish release artifacts
-        run: make release
+        run: make ci-release
         env:
           # for mac signing and notarization...
           QUILL_SIGN_P12: ${{ secrets.ANCHORE_APPLE_DEVELOPER_ID_CERT_CHAIN }}

.github/workflows/update-bootstrap-tools.yml

@@ -6,7 +6,7 @@ on:
   workflow_dispatch:
 
 env:
-  GO_VERSION: "1.18.x"
+  GO_VERSION: "1.19.x"
   GO_STABLE_VERSION: true
 
 jobs:
@@ -29,24 +29,27 @@ jobs:
           GOSIMPORTS_LATEST_VERSION=$(go list -m -json github.com/rinchsan/gosimports@latest 2>/dev/null | jq -r '.Version')
           YAJSV_LATEST_VERSION=$(go list -m -json github.com/neilpa/yajsv@latest 2>/dev/null | jq -r '.Version')
           COSIGN_LATEST_VERSION=$(go list -m -json github.com/sigstore/cosign@latest 2>/dev/null | jq -r '.Version')
+          GLOW_LATEST_VERSION=$(go list -m -json github.com/charmbracelet/glow@latest 2>/dev/null | jq -r '.Version')
           
           # update version variables in the Makefile
-          sed -r -i -e 's/^(GOLANGCILINT_VERSION = ).*/\1'${GOLANGCILINT_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(BOUNCER_VERSION = ).*/\1'${BOUNCER_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(CHRONICLE_VERSION = ).*/\1'${CHRONICLE_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(GORELEASER_VERSION = ).*/\1'${GORELEASER_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(GOSIMPORTS_VERSION = ).*/\1'${GOSIMPORTS_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(YAJSV_VERSION = ).*/\1'${YAJSV_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(COSIGN_VERSION = ).*/\1'${COSIGN_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(GOLANGCILINT_VERSION := ).*/\1'${GOLANGCILINT_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(BOUNCER_VERSION := ).*/\1'${BOUNCER_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(CHRONICLE_VERSION := ).*/\1'${CHRONICLE_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(GORELEASER_VERSION := ).*/\1'${GORELEASER_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(GOSIMPORTS_VERSION := ).*/\1'${GOSIMPORTS_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(YAJSV_VERSION := ).*/\1'${YAJSV_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(COSIGN_VERSION := ).*/\1'${COSIGN_LATEST_VERSION}'/' Makefile
+          sed -r -i -e 's/^(GLOW_VERSION := ).*/\1'${GLOW_LATEST_VERSION}'/' Makefile
           
           # export the versions for use with create-pull-request
-          echo "::set-output name=GOLANGCILINT::$GOLANGCILINT_LATEST_VERSION"
-          echo "::set-output name=BOUNCER::$BOUNCER_LATEST_VERSION"
-          echo "::set-output name=CHRONICLE::$CHRONICLE_LATEST_VERSION"
-          echo "::set-output name=GORELEASER::$GORELEASER_LATEST_VERSION"
-          echo "::set-output name=GOSIMPORTS::$GOSIMPORTS_LATEST_VERSION"
-          echo "::set-output name=YAJSV::$YAJSV_LATEST_VERSION"
-          echo "::set-output name=COSIGN::$COSIGN_LATEST_VERSION"
+          echo "GOLANGCILINT=$GOLANGCILINT_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "BOUNCER=$BOUNCER_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "CHRONICLE=$CHRONICLE_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "GORELEASER=$GORELEASER_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "GOSIMPORTS=$GOSIMPORTS_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "YAJSV=$YAJSV_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "COSIGN=$COSIGN_LATEST_VERSION" >> $GITHUB_OUTPUT
+          echo "GLOW=GLOW_LATEST_VERSION" >> $GITHUB_OUTPUT
         id: latest-versions
 
       - uses: tibdex/github-app-token@v1
@@ -71,5 +74,6 @@ jobs:
             - [gosimports ${{ steps.latest-versions.outputs.GOSIMPORTS }}](https://github.com/rinchsan/gosimports/releases/tag/${{ steps.latest-versions.outputs.GOSIMPORTS }})
             - [yajsv ${{ steps.latest-versions.outputs.YAJSV }}](https://github.com/neilpa/yajsv/releases/tag/${{ steps.latest-versions.outputs.YAJSV }})
             - [cosign ${{ steps.latest-versions.outputs.COSIGN }}](https://github.com/sigstore/cosign/releases/tag/${{ steps.latest-versions.outputs.COSIGN }})  
+            - [glow ${{ steps.latest-versions.outputs.GLOW }}](https://github.com/charmbracelet/glow/releases/tag/${{ steps.latest-versions.outputs.GLOW }})  
             This is an auto-generated pull request to update all of the bootstrap tools to the latest versions.
           token: ${{ steps.generate-token.outputs.token }}

.github/workflows/update-stereoscope-release.yml

@@ -6,7 +6,7 @@ on:
   workflow_dispatch:
 
 env:
-  GO_VERSION: "1.18.x"
+  GO_VERSION: "1.19.x"
   GO_STABLE_VERSION: true
 
 jobs:

.gitignore

@@ -1,4 +1,5 @@
 CHANGELOG.md
+VERSION
 /test/results
 /dist
 /snapshot

.golangci.yaml

@@ -6,7 +6,6 @@ issues:
 #  include:
 #    - EXC0002 # disable excluding of issues about comments from golint
 
-
 linters:
   # inverted configuration with `enable-all` and `disable` is not scalable during updates of golangci-lint
   disable-all: true
@@ -14,25 +13,24 @@ linters:
     - asciicheck
     - bodyclose
     - depguard
+    - dogsled
     - dupl
     - errcheck
-    - errorlint
     - exportloopref
-    - forcetypeassert
     - funlen
     - gocognit
     - goconst
     - gocritic
     - gocyclo
     - gofmt
-    - tparallel
-    - importas
+    - goimports
+    - goprintffuncname
     - gosec
     - gosimple
     - govet
     - ineffassign
     - misspell
-    - nolintlint
+    - nakedret
     - revive
     - staticcheck
     - stylecheck
@@ -41,6 +39,7 @@ linters:
     - unparam
     - unused
     - whitespace
+
 linters-settings:
   funlen:
     # Checks the number of lines in a function.
@@ -57,7 +56,7 @@ run:
   timeout: 10m
 
 # do not enable...
-#    - dogsled           # found to be to niche and ineffective
+#    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
 #    - goprintffuncname  # does not catch all cases and there are exceptions
 #    - nakedret          # does not catch all cases and should not fail a build
 #    - gochecknoglobals
@@ -73,7 +72,11 @@ run:
 #    - lll         # without a way to specify per-line exception cases, this is not usable
 #    - maligned    # this is an excellent linter, but tricky to optimize and we are not sensitive to memory layout optimizations
 #    - nestif
-#    - prealloc    # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
-#    - scopelint   # deprecated
+#    - nolintlint   # as of go1.19 this conflicts with the behavior of gofmt, which is a deal-breaker (lint-fix will still fail when running lint)
+#    - prealloc     # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
+#    - rowserrcheck # not in a repo with sql, so this is not useful
+#    - scopelint    # deprecated
+#    - structcheck  # The owner seems to have abandoned the linter. Replaced by "unused".
 #    - testpackage
-#    - wsl         # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)
+#    - varcheck     # The owner seems to have abandoned the linter. Replaced by "unused".
+#    - wsl          # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Contributing to Syft
+[#](#) Contributing to Syft
 
 If you are looking to contribute to this project and want to open a GitHub pull request ("PR"), there are a few guidelines of what we are looking for in patches. Make sure you go through this document and ensure that your code proposal is aligned.
 
@@ -10,7 +10,7 @@ Before you can contribute to Syft, you need to configure your development enviro
 
 You will need to install Go. The version on https://go.dev works best, using the system golang doesn't always work the way you might expect.
 
-At the time of writing, Go 1.19 does not work correctly with Syft. Please use Go 1.18 for now.
+Refer to the go.mod file in the root of this repo for the recommended version of Go to install.
 
 You will also need Docker. There's no reason the system packages shouldn't work, but we used the official Docker package. You can find instructions for installing Docker in Debian [here](https://docs.docker.com/engine/install/debian/).
 

DEVELOPING.md

@@ -118,45 +118,55 @@ sequenceDiagram
 
 Catalogers are the way in which syft is able to identify and construct packages given some amount of source metadata.
 For example, Syft can locate and process `package-lock.json` files when performing filesystem scans. 
-See: [how to specify file globs](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/javascript/cataloger.go#L16-L21)
-and an implementation of the [package-lock.json parser](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) fora quick review.
+See: [how to specify file globs](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21)
+and an implementation of the [package-lock.json parser](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) fora quick review.
 
 #### Building a new Cataloger
 
-Catalogers must fulfill the interface [found here](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger.go). 
+Catalogers must fulfill the interface [found here](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger.go). 
 This means that when building a new cataloger, the new struct must implement both method signatures of `Catalog` and `Name`.
 
-A top level view of the functions that construct all the catalogers can be found [here](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/cataloger.go).
+A top level view of the functions that construct all the catalogers can be found [here](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/cataloger.go).
 When an author has finished writing a new cataloger this is the spot to plug in the new catalog constructor.
 
-For a top level view of how the catalogers are used see [this function](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/catalog.go#L41-L100) as a reference. It ranges over all catalogers passed as an argument and invokes the `Catalog` method:
+For a top level view of how the catalogers are used see [this function](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/catalog.go#L41-L100) as a reference. It ranges over all catalogers passed as an argument and invokes the `Catalog` method:
 
 Each cataloger has its own `Catalog` method, but this does not mean that they are all vastly different.
-Take a look at the `apkdb` cataloger for alpine to see how it [constructs a generic.NewCataloger](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/apkdb/cataloger.go).
+Take a look at the `apkdb` cataloger for alpine to see how it [constructs a generic.NewCataloger](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/cataloger.go).
 
 `generic.NewCataloger` is an abstraction syft uses to make writing common components easier. First, it takes the `catalogerName` to identify the cataloger.
 On the other side of the call it uses two key pieces which inform the cataloger how to identify and return packages, the `globPatterns` and the `parseFunction`:
 - The first piece is a `parseByGlob` matching pattern used to identify the files that contain the package metadata.
-See [here for the APK example](https://github.com/anchore/syft/blob/main/syft/pkg/apk_metadata.go#L16-L41).
+See [here for the APK example](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/apk_metadata.go#L16-L41).
 - The other is a `parseFunction` which informs the cataloger what to do when it has found one of the above matches files.
-See this [link for an example](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102).
+See this [link for an example](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102).
 
 If you're unsure about using the `Generic Cataloger` and think the use case being filled requires something more custom
 just file an issue or ask in our slack, and we'd be more than happy to help on the design.
 
-Identified packages share a common struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/blob/main/syft/pkg/package.go#L16-L31).
+Identified packages share a common struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/package.go#L16-L31).
 
 Metadata Note: Identified packages are also assigned specific metadata that can be unique to their environment. 
-See [this folder](https://github.com/anchore/syft/tree/main/syft/pkg) for examples of the different metadata types.
+See [this folder](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg) for examples of the different metadata types.
 These are plugged into the `MetadataType` and `Metadata` fields in the above struct. `MetadataType` informs which type is being used. `Metadata` is an interface converted to that type.
 
 Finally, here is an example of where the package construction is done in the apk cataloger. The first link is where `newPackage` is called in the `parseFunction`. The second link shows the package construction:
-- [Call for new package](https://github.com/anchore/syft/blob/6a7d6e6071829c7ce2943266c0e187b27c0b325c/syft/pkg/cataloger/apkdb/parse_apk_db.go#L96-L99)
-- [APK Package Constructor](https://github.com/anchore/syft/blob/6a7d6e6071829c7ce2943266c0e187b27c0b325c/syft/pkg/cataloger/apkdb/package.go#L12-L27)
+- [Call for new package](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L106)
+- [APK Package Constructor](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/package.go#L12-L27)
 
 If you have more questions about implementing a cataloger or questions about one you might be currently working
 always feel free to file an issue or reach out to us [on slack](https://anchore.com/slack).
 
+#### Searching for files
+
+All catalogers are provided an instance of the [`source.FileResolver`](https://github.com/anchore/syft/blob/v0.70.0/syft/source/file_resolver.go#L8) to interface with the image and search for files. The implementations for these 
+abstractions leverage [`stereoscope`](https://github.com/anchore/stereoscope) in order to perform searching. Here is a 
+rough outline how that works:
+
+1. a stereoscope `file.Index` is searched based on the input given (a path, glob, or MIME type). The index is relatively fast to search, but requires results to be filtered down to the files that exist in the specific layer(s) of interest. This is done automatically by the `filetree.Searcher` abstraction. This abstraction will fallback to searching directly against the raw `filetree.FileTree` if the index does not contain the file(s) of interest. Note: the `filetree.Searcher` is used by the `source.FileResolver` abstraction.
+2. Once the set of files are returned from the `filetree.Searcher` the results are filtered down further to return the most unique file results. For example, you may have requested for files by a glob that returns multiple results. These results are filtered down to deduplicate by real files, so if a result contains two references to the same file, say one accessed via symlink and one accessed via the real path, then the real path reference is returned and the symlink reference is filtered out. If both were accessed by symlink then the first (by lexical order) is returned. This is done automatically by the `source.FileResolver` abstraction.
+3. By the time results reach the `pkg.Cataloger` you are guaranteed to have a set of unique files that exist in the layer(s) of interest (relative to what the resolver supports).
+
 ## Testing
 
 ### Levels of testing

Makefile

@@ -6,16 +6,19 @@ LINT_CMD := $(TEMP_DIR)/golangci-lint run --tests=false
 GOIMPORTS_CMD := $(TEMP_DIR)/gosimports -local github.com/anchore
 RELEASE_CMD := $(TEMP_DIR)/goreleaser release --rm-dist
 SNAPSHOT_CMD := $(RELEASE_CMD) --skip-publish --skip-sign --snapshot
+CHRONICLE_CMD = $(TEMP_DIR)/chronicle
+GLOW_CMD = $(TEMP_DIR)/glow
 
 # Tool versions #################################
-GOLANGCILINT_VERSION := v1.50.1
+GOLANGCILINT_VERSION := v1.51.1
 GOSIMPORTS_VERSION := v0.3.5
 BOUNCER_VERSION := v0.4.0
-CHRONICLE_VERSION := v0.4.2
-GORELEASER_VERSION := v1.14.1
+CHRONICLE_VERSION := v0.6.0
+GORELEASER_VERSION := v1.15.2
 YAJSV_VERSION := v1.4.1
 COSIGN_VERSION := v1.13.1
 QUILL_VERSION := v0.2.0
+GLOW_VERSION := v1.5.0
 
 # Formatting variables #################################
 BOLD := $(shell tput -T linux bold)
@@ -88,6 +91,7 @@ bootstrap-tools: $(TEMP_DIR)
 	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/rinchsan/gosimports/cmd/gosimports@$(GOSIMPORTS_VERSION)
 	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/neilpa/yajsv@$(YAJSV_VERSION)
 	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/sigstore/cosign/cmd/cosign@$(COSIGN_VERSION)
+	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/charmbracelet/glow@$(GLOW_VERSION)
 
 .PHONY: bootstrap-go
 bootstrap-go:
@@ -132,10 +136,7 @@ check-go-mod-tidy:
 
 check-json-schema-drift:
 	$(call title,Ensure there is no drift between the JSON schema and the code)
-	@git diff-index --quiet HEAD -- || (echo "there are uncommitted changes, please commit them before running this check" && false)
-	@make generate-json-schema || (echo "$(RED)$(BOLD)JSON schema drift detected!$(RESET)" && false)
-	@git diff-index --quiet HEAD -- || (echo "$(RED)$(BOLD)JSON schema drift detected!$(RESET)" && false)
-
+	@.github/scripts/json-schema-drift-check.sh
 
 ## Testing targets #################################
 
@@ -307,20 +308,20 @@ $(SNAPSHOT_DIR):  ## Build snapshot release binaries and packages
 	$(SNAPSHOT_CMD) --config $(TEMP_DIR)/goreleaser.yaml
 
 .PHONY: changelog
-changelog: clean-changelog $(CHANGELOG)  ## Generate and show the changelog for the current unreleased version
-	@docker run -it --rm \
-		-v $(shell pwd)/$(CHANGELOG):/$(CHANGELOG) \
-		rawkode/mdv \
-			-t 748.5989 \
-			/$(CHANGELOG)
+changelog: clean-changelog  ## Generate and show the changelog for the current unreleased version
+	$(CHRONICLE_CMD) -vvv -n --version-file VERSION > $(CHANGELOG)
+	@$(GLOW_CMD) $(CHANGELOG)
 
 $(CHANGELOG):
-	$(TEMP_DIR)/chronicle -vv > $(CHANGELOG)
+	$(CHRONICLE_CMD) -vvv > $(CHANGELOG)
 
 .PHONY: release
-release: clean-dist $(CHANGELOG)
+release:
+	@.github/scripts/trigger-release.sh
+
+.PHONY: ci-release
+ci-release: ci-check clean-dist $(CHANGELOG)
 	$(call title,Publishing release artifacts)
-	@.github/scripts/ci-check.sh
 
 	# create a config with the dist dir overridden
 	echo "dist: $(DIST_DIR)" > $(TEMP_DIR)/goreleaser.yaml
@@ -335,6 +336,10 @@ release: clean-dist $(CHANGELOG)
 	# upload the version file that supports the application version update check (excluding pre-releases)
 	.github/scripts/update-version-file.sh "$(DIST_DIR)" "$(VERSION)"
 
+.PHONY: ci-check
+ci-check:
+	@.github/scripts/ci-check.sh
+
 ## Cleanup targets #################################
 
 .PHONY: clean
@@ -353,7 +358,7 @@ clean-dist: clean-changelog
 
 .PHONY: clean-changelog
 clean-changelog:
-	rm -f $(CHANGELOG)
+	rm -f $(CHANGELOG) VERSION
 
 clean-test-image-cache: clean-test-image-tar-cache clean-test-image-docker-cache ## Clean test image cache
 

RELEASE.md

@@ -1,14 +1,49 @@
-# Release Process
+# Release
+
+## Creating a release
+
+This release process itself should be as automated as possible, and has only a few steps:
+
+1. **Trigger a new release with `make release`**. At this point you'll see a preview
+  changelog in the terminal. If you're happy with the changelog, press `y` to continue, otherwise
+  you can abort and adjust the labels on the PRs and issues to be included in the release and
+  re-run the release trigger command.
+
+1. A release admin must approve the release on the GitHub Actions release pipeline run page.
+   Once approved, the release pipeline will generate all assets and publish a GitHub Release.
+
+1. If there is a release Milestone, close it.
+
+Ideally releasing should be done often with small increments when possible. Unless a
+breaking change is blocking the release, or no fixes/features have been merged, a good
+target release cadence is between every 1 or 2 weeks.
+
+
+## Retracting a release
+
+If a release is found to be problematic, it can be retracted with the following steps:
+
+- Deleting the GitHub Release
+- Untag the docker images in the `ghcr.io` and `docker.io` registries
+- Revert the brew formula in [`anchore/homebrew-syft`](https://github.com/anchore/homebrew-syft) to point to the previous release
+- Add a new `retract` entry in the go.mod for the versioned release
+
+**Note**: do not delete release tags from the git repository since there may already be references to the release
+in the go proxy, which will cause confusion when trying to reuse the tag later (the H1 hash will not match and there
+will be a warning when users try to pull the new release).
+
+
+## Background
 
 A good release process has the following qualities:
 
 1. There is a way to plan what should be in a release
 1. There is a way to see what is actually in a release
-1. Allow for different kinds of releases (major breaking vs backwards compatible
-   enhancements vs patch updates)
+1. Allow for different kinds of releases (major breaking vs backwards compatible enhancements vs patch updates)
 1. Specify a repeatable way to build and publish software artifacts
 
-## Planning a release
+
+### Planning a release
 
 To indicate a set of features to be released together add each issue to an in-repository
 Milestone named with major-minor version to be released (e.g. `v0.1`). It is OK for other
@@ -21,15 +56,13 @@ completed, would allow the release to be considered complete. A Milestone is onl
 
 Not all releases need to be planned. For instance, patch releases for fixes should be
 released when they are ready and when releasing would not interfere with another current
-release (where some partial or breaking features have already been merged). Beta releases
-and release candidates should not be independently planned from the non-beta release. That
-is, the features for a `v0.1-beta.1` release should be planned under the `v0.1` Milestone,
-not under a separate `v0.1-beta.1` Milestone.
+release (where some partial or breaking features have already been merged).
 
 Unless necessary, feature releases should be small and frequent, which may obviate the
 need for regular release planning under a Milestone.
 
-## What is in a release
+
+### What is in a release
 
 Milestones are specifically for planning a release, not necessarily tracking all changes
 that a release may bring (and more importantly, not all releases are necessarily planned
@@ -42,9 +75,9 @@ Changelog line. Furthermore, there should be a place to see all released version
 release date for each release, the semantic version of the release, and the set of changes
 for each release.
 
-This project auto-generates the Changelog contents for each current release and posts the
-generated contents to the GitHub Release page. Leveraging the GitHub Releases feature
-allows GitHub to manage the Changelog on each release outside of the git repository while
+**This project auto-generates the Changelog contents for each current release and posts the
+generated contents to the GitHub Release page**. Leveraging the GitHub Releases feature
+allows GitHub to manage the Changelog on each release outside of the git source tree while
 still being hosted with the released assets.
 
 The Changelog is generated from the metadata from in-repository issues and PRs, using
@@ -60,45 +93,20 @@ The above suggestions imply that we should:
 - The appropriate label is applied to PRs and/or issues to drive specific change type
   sections (deprecated, breaking, security, bug, etc)
 
-With this approach as we cultivate good organization of PRs and issues we automatically
-get an equally good Changelog.
+**With this approach as we cultivate good organization of PRs and issues we automatically
+get an equally good Changelog.**
 
-## Major, minor, and patch releases
+
+### Major, minor, and patch releases
 
 The latest version of the tool is the only supported version, which implies that multiple
 parallel release branches will not be a regular process (if ever). Multiple releases can
 be planned in parallel, however, only one can be actively developed at a time. That is, if
 PRs attached to a release Milestone have been merged into the main branch, that release is
-now the "next" release. This implies that the source of truth for release lies with the
-git log and Changelog, not with the release Milestones (which are purely for planning and
+now the "next" release. **This implies that the source of truth for release lies with the
+git log and Changelog, not with the release Milestones** (which are purely for planning and
 tracking).
 
 Semantic versioning should be used to indicate breaking changes, new features, and fixes.
 The exception to this is `< 1.0`, where the major version is not bumped for breaking changes,
 instead the minor version indicates both new features and breaking changes.
-
-## Cutting a release
-
-Ideally releasing should be done often with small increments when possible. Unless a
-breaking change is blocking the release, or no fixes/features have been merged, a good
-target release cadence is between every 2 or 4 weeks.
-
-This release process itself should be as automated as possible, and have only a few steps:
-
-1. Tag the main branch with a full semantic-version, prefixed with a `v`. If there is a
-   milestone with a partial version, the full version should be used for the git tag (e.g.
-   with a Milestone of `v0.1` the tag should be `v0.1.0`). You can determine the changes going
-   into a release by running `make changelog-unreleased`. Use this change list to determine the 
-   release increment. After determining the release increment (major, minor, patch), create the tag.
-   Given the above example the command to create the tag would be `git tag v0.1.0`.
-
-1. Push the tag. Given the above example the command to push the tag would be `git push origin v0.1.0`.
-   
-1. A release admin must approve the release on the GitHub Actions release pipeline run page.
-   Once approved, the release pipeline will generate all assets and draft a GitHub Release.
-
-1. Navigate to the GitHub Release draft page to review the final changelog and publish the
-   release. Once published, a release-follow-up pipeline will publish derivative artifacts
-   (docker image to DockerHub, brew formula to the external homebrew git repo, etc).
-
-1. If there is a release Milestone, close it.

cmd/syft/cli/attest.go

@@ -20,8 +20,7 @@ const (
 	attestHelp       = attestExample + attestSchemeHelp
 )
 
-//nolint:dupl
-func Attest(v *viper.Viper, app *config.Application, ro *options.RootOptions, po *options.PackagesOptions) *cobra.Command {
+func Attest(v *viper.Viper, app *config.Application, ro *options.RootOptions, po *options.PackagesOptions, ao *options.AttestOptions) *cobra.Command {
 	cmd := &cobra.Command{
 		Use:   "attest --output [FORMAT] <IMAGE>",
 		Short: "Generate an SBOM as an attestation for the given [SOURCE] container image",
@@ -50,11 +49,17 @@ func Attest(v *viper.Viper, app *config.Application, ro *options.RootOptions, po
 		},
 	}
 
-	// syft attest is an enhancment of the packages command, so it should have the same flags
+	// syft attest is an enhancement of the packages command, so it should have the same flags
 	err := po.AddFlags(cmd, v)
 	if err != nil {
 		log.Fatal(err)
 	}
 
+	// syft attest has its own options not included as part of the packages command
+	err = ao.AddFlags(cmd, v)
+	if err != nil {
+		log.Fatal(err)
+	}
+
 	return cmd
 }

cmd/syft/cli/attest/attest.go

@@ -22,7 +22,6 @@ import (
 	"github.com/anchore/syft/syft/event/monitor"
 	"github.com/anchore/syft/syft/formats/syftjson"
 	"github.com/anchore/syft/syft/formats/table"
-	"github.com/anchore/syft/syft/formats/template"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
@@ -97,6 +96,7 @@ func buildSBOM(app *config.Application, si source.Input, writer sbom.Writer, err
 	return sBytes, nil
 }
 
+//nolint:funlen
 func execWorker(app *config.Application, si source.Input, writer sbom.Writer) <-chan error {
 	errs := make(chan error)
 	go func() {
@@ -130,10 +130,19 @@ func execWorker(app *config.Application, si source.Input, writer sbom.Writer) <-
 				return
 			}
 
-			args := []string{"attest", si.UserInput, "--type", "custom", "--predicate", f.Name()}
+			args := []string{"attest", si.UserInput, "--predicate", f.Name()}
+			if app.Attest.Key != "" {
+				args = append(args, "--key", app.Attest.Key)
+			}
+
 			execCmd := exec.Command(cmd, args...)
 			execCmd.Env = os.Environ()
-			execCmd.Env = append(execCmd.Env, "COSIGN_EXPERIMENTAL=1")
+			if app.Attest.Key != "" {
+				execCmd.Env = append(execCmd.Env, fmt.Sprintf("COSIGN_PASSWORD=%s", app.Attest.Password))
+			} else {
+				// no key provided, use cosign's keyless mode
+				execCmd.Env = append(execCmd.Env, "COSIGN_EXPERIMENTAL=1")
+			}
 
 			// bus adapter for ui to hook into stdout via an os pipe
 			r, w, err := os.Pipe()
@@ -166,16 +175,9 @@ func execWorker(app *config.Application, si source.Input, writer sbom.Writer) <-
 }
 
 func ValidateOutputOptions(app *config.Application) error {
-	var usesTemplateOutput bool
-	for _, o := range app.Outputs {
-		if o == template.ID.String() {
-			usesTemplateOutput = true
-			break
-		}
-	}
-
-	if usesTemplateOutput && app.OutputTemplatePath == "" {
-		return fmt.Errorf(`must specify path to template file when using "template" output format`)
+	err := packages.ValidateOutputOptions(app)
+	if err != nil {
+		return err
 	}
 
 	if len(app.Outputs) > 1 {

cmd/syft/cli/commands.go

@@ -45,12 +45,13 @@ func New() (*cobra.Command, error) {
 	// we also need the command to have information about the `root` options because of this alias
 	ro := &options.RootOptions{}
 	po := &options.PackagesOptions{}
+	ao := &options.AttestOptions{}
 	packagesCmd := Packages(v, app, ro, po)
 
 	// root options are also passed to the attestCmd so that a user provided config location can be discovered
 	poweruserCmd := PowerUser(v, app, ro)
 	convertCmd := Convert(v, app, ro, po)
-	attestCmd := Attest(v, app, ro, po)
+	attestCmd := Attest(v, app, ro, po, ao)
 
 	// rootCmd is currently an alias for the packages command
 	rootCmd := &cobra.Command{

cmd/syft/cli/convert/convert.go

@@ -8,12 +8,12 @@ import (
 	"github.com/anchore/syft/cmd/syft/cli/options"
 	"github.com/anchore/syft/internal/config"
 	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/formats"
 )
 
-func Run(ctx context.Context, app *config.Application, args []string) error {
+func Run(_ context.Context, app *config.Application, args []string) error {
 	log.Warn("convert is an experimental feature, run `syft convert -h` for help")
-	writer, err := options.MakeWriter(app.Outputs, app.File, "")
+	writer, err := options.MakeWriter(app.Outputs, app.File, app.OutputTemplatePath)
 	if err != nil {
 		return err
 	}
@@ -30,9 +30,11 @@ func Run(ctx context.Context, app *config.Application, args []string) error {
 	if err != nil {
 		return fmt.Errorf("failed to open SBOM file: %w", err)
 	}
-	defer f.Close()
+	defer func() {
+		_ = f.Close()
+	}()
 
-	sbom, _, err := syft.Decode(f)
+	sbom, _, err := formats.Decode(f)
 	if err != nil {
 		return fmt.Errorf("failed to decode SBOM: %w", err)
 	}

cmd/syft/cli/options/attest.go

@@ -0,0 +1,25 @@
+package options
+
+import (
+	"github.com/spf13/cobra"
+	"github.com/spf13/pflag"
+	"github.com/spf13/viper"
+)
+
+type AttestOptions struct {
+	Key string
+}
+
+var _ Interface = (*AttestOptions)(nil)
+
+func (o AttestOptions) AddFlags(cmd *cobra.Command, v *viper.Viper) error {
+	cmd.Flags().StringVarP(&o.Key, "key", "k", "", "the key to use for the attestation")
+	return bindAttestConfigOptions(cmd.Flags(), v)
+}
+
+func bindAttestConfigOptions(flags *pflag.FlagSet, v *viper.Viper) error {
+	if err := v.BindPFlag("attest.key", flags.Lookup("key")); err != nil {
+		return err
+	}
+	return nil
+}

cmd/syft/cli/options/format.go

@@ -1,39 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/syft/formats/cyclonedxjson"
-	"github.com/anchore/syft/syft/formats/cyclonedxxml"
-	"github.com/anchore/syft/syft/formats/github"
-	"github.com/anchore/syft/syft/formats/spdxjson"
-	"github.com/anchore/syft/syft/formats/spdxtagvalue"
-	"github.com/anchore/syft/syft/formats/syftjson"
-	"github.com/anchore/syft/syft/formats/table"
-	"github.com/anchore/syft/syft/formats/text"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-func FormatAliases(ids ...sbom.FormatID) (aliases []string) {
-	for _, id := range ids {
-		switch id {
-		case syftjson.ID:
-			aliases = append(aliases, "syft-json")
-		case text.ID:
-			aliases = append(aliases, "text")
-		case table.ID:
-			aliases = append(aliases, "table")
-		case spdxjson.ID:
-			aliases = append(aliases, "spdx-json")
-		case spdxtagvalue.ID:
-			aliases = append(aliases, "spdx-tag-value")
-		case cyclonedxxml.ID:
-			aliases = append(aliases, "cyclonedx-xml")
-		case cyclonedxjson.ID:
-			aliases = append(aliases, "cyclonedx-json")
-		case github.ID:
-			aliases = append(aliases, "github", "github-json")
-		default:
-			aliases = append(aliases, string(id))
-		}
-	}
-	return aliases
-}

cmd/syft/cli/options/packages.go

@@ -7,7 +7,7 @@ import (
 	"github.com/spf13/pflag"
 	"github.com/spf13/viper"
 
-	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/formats"
 	"github.com/anchore/syft/syft/formats/table"
 	"github.com/anchore/syft/syft/pkg/cataloger"
 	"github.com/anchore/syft/syft/source"
@@ -30,8 +30,8 @@ func (o *PackagesOptions) AddFlags(cmd *cobra.Command, v *viper.Viper) error {
 	cmd.Flags().StringVarP(&o.Scope, "scope", "s", cataloger.DefaultSearchConfig().Scope.String(),
 		fmt.Sprintf("selection of layers to catalog, options=%v", source.AllScopes))
 
-	cmd.Flags().StringArrayVarP(&o.Output, "output", "o", FormatAliases(table.ID),
-		fmt.Sprintf("report output format, options=%v", FormatAliases(syft.FormatIDs()...)))
+	cmd.Flags().StringArrayVarP(&o.Output, "output", "o", []string{string(table.ID)},
+		fmt.Sprintf("report output format, options=%v", formats.AllIDs()))
 
 	cmd.Flags().StringVarP(&o.File, "file", "", "",
 		"file to write the default report output to (default is STDOUT)")

cmd/syft/cli/options/writer.go

@@ -6,7 +6,7 @@ import (
 
 	"github.com/hashicorp/go-multierror"
 
-	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/formats"
 	"github.com/anchore/syft/syft/formats/table"
 	"github.com/anchore/syft/syft/formats/template"
 	"github.com/anchore/syft/syft/sbom"
@@ -32,7 +32,7 @@ func MakeWriter(outputs []string, defaultFile, templateFilePath string) (sbom.Wr
 func parseOutputs(outputs []string, defaultFile, templateFilePath string) (out []sbom.WriterOption, errs error) {
 	// always should have one option -- we generally get the default of "table", but just make sure
 	if len(outputs) == 0 {
-		outputs = append(outputs, string(table.ID))
+		outputs = append(outputs, table.ID.String())
 	}
 
 	for _, name := range outputs {
@@ -52,9 +52,9 @@ func parseOutputs(outputs []string, defaultFile, templateFilePath string) (out [
 			file = parts[1]
 		}
 
-		format := syft.FormatByName(name)
+		format := formats.ByName(name)
 		if format == nil {
-			errs = multierror.Append(errs, fmt.Errorf(`unsupported output format "%s", supported formats are: %+v`, name, FormatAliases(syft.FormatIDs()...)))
+			errs = multierror.Append(errs, fmt.Errorf(`unsupported output format "%s", supported formats are: %+v`, name, formats.AllIDs()))
 			continue
 		}
 

cmd/syft/cli/poweruser/poweruser.go

@@ -26,9 +26,10 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
-func Run(ctx context.Context, app *config.Application, args []string) error {
+func Run(_ context.Context, app *config.Application, args []string) error {
+	f := syftjson.Format()
 	writer, err := sbom.NewWriter(sbom.WriterOption{
-		Format: syftjson.Format(),
+		Format: f,
 		Path:   app.File,
 	})
 	if err != nil {

go.mod

@@ -1,6 +1,6 @@
 module github.com/anchore/syft
 
-go 1.18
+go 1.19
 
 require (
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d
@@ -11,7 +11,7 @@ require (
 	github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b
 	github.com/anchore/packageurl-go v0.1.1-0.20230104203445-02e0a6721501
 	github.com/bmatcuk/doublestar/v4 v4.6.0
-	github.com/dustin/go-humanize v1.0.0
+	github.com/dustin/go-humanize v1.0.1
 	github.com/facebookincubator/nvdtools v0.1.5
 	github.com/go-test/deep v1.1.0
 	github.com/google/go-cmp v0.5.9
@@ -31,7 +31,7 @@ require (
 	github.com/scylladb/go-set v1.0.3-0.20200225121959-cc7b2070d91e
 	github.com/sergi/go-diff v1.3.1
 	github.com/sirupsen/logrus v1.9.0
-	github.com/spdx/tools-golang v0.3.1-0.20221108182156-8a01147e6342
+	github.com/spdx/tools-golang v0.5.0-rc1
 	github.com/spf13/afero v1.9.3
 	github.com/spf13/cobra v1.6.1
 	github.com/spf13/pflag v1.0.5
@@ -42,33 +42,35 @@ require (
 	github.com/wagoodman/go-progress v0.0.0-20200731105512-1020f39e6240
 	github.com/wagoodman/jotframe v0.0.0-20211129225309-56b0d0a4aebb
 	github.com/xeipuuv/gojsonschema v1.2.0
-	golang.org/x/mod v0.6.0
-	golang.org/x/net v0.5.0
-	golang.org/x/term v0.4.0
+	golang.org/x/mod v0.8.0
+	golang.org/x/net v0.6.0
+	golang.org/x/term v0.5.0
 	gopkg.in/yaml.v2 v2.4.0
 )
 
 require (
 	github.com/CycloneDX/cyclonedx-go v0.7.1-0.20221222100750-41a1ac565cce
-	github.com/Masterminds/sprig/v3 v3.2.2
+	github.com/Masterminds/sprig/v3 v3.2.3
 	github.com/anchore/go-logger v0.0.0-20220728155337-03b66a5207d8
-	github.com/anchore/stereoscope v0.0.0-20221208011002-c5ff155d72f1
-	github.com/docker/docker v20.10.20+incompatible
-	github.com/google/go-containerregistry v0.12.1
+	github.com/anchore/stereoscope v0.0.0-20230208154630-5a306f07f2e7
+	github.com/docker/docker v23.0.0+incompatible
+	github.com/google/go-containerregistry v0.13.0
 	github.com/invopop/jsonschema v0.7.0
 	github.com/knqyf263/go-rpmdb v0.0.0-20221030135625-4082a22221ce
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/sassoftware/go-rpmutils v0.2.0
 	github.com/vbatts/go-mtree v0.5.2
-	golang.org/x/exp v0.0.0-20220823124025-807a23277127
+	golang.org/x/exp v0.0.0-20230202163644-54bba9f4231b
 	gopkg.in/yaml.v3 v3.0.1
 )
 
 require (
 	github.com/DataDog/zstd v1.4.5 // indirect
 	github.com/Masterminds/goutils v1.1.1 // indirect
-	github.com/Masterminds/semver/v3 v3.1.1 // indirect
+	github.com/Masterminds/semver/v3 v3.2.0 // indirect
 	github.com/Microsoft/go-winio v0.6.0 // indirect
+	github.com/anchore/go-struct-converter v0.0.0-20221118182256-c68fdcfa2092 // indirect
+	github.com/becheran/wildmatch-go v1.0.0 // indirect
 	github.com/containerd/containerd v1.6.12 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.12.1 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
@@ -86,7 +88,7 @@ require (
 	github.com/golang/snappy v0.0.4 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/hcl v1.0.0 // indirect
-	github.com/huandu/xstrings v1.3.2 // indirect
+	github.com/huandu/xstrings v1.3.3 // indirect
 	github.com/iancoleman/orderedmap v0.0.0-20190318233801-ac98e3ecb4b0 // indirect
 	github.com/imdario/mergo v0.3.12 // indirect
 	github.com/inconshreveable/mousetrap v1.0.1 // indirect
@@ -124,9 +126,9 @@ require (
 	github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 // indirect
 	github.com/xo/terminfo v0.0.0-20210125001918-ca9a967f8778 // indirect
 	golang.org/x/sync v0.1.0 // indirect
-	golang.org/x/sys v0.4.0 // indirect
-	golang.org/x/text v0.6.0 // indirect
-	golang.org/x/tools v0.1.12 // indirect
+	golang.org/x/sys v0.5.0 // indirect
+	golang.org/x/text v0.7.0 // indirect
+	golang.org/x/tools v0.2.0 // indirect
 	golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 // indirect
 	google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef // indirect
 	google.golang.org/grpc v1.52.0 // indirect
@@ -149,7 +151,7 @@ require (
 	// go: warning: github.com/andybalholm/brotli@v1.0.1: retracted by module author: occasional panics and data corruption
 	github.com/andybalholm/brotli v1.0.4 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
-	golang.org/x/crypto v0.1.0 // indirect
+	golang.org/x/crypto v0.3.0 // indirect
 )
 
 retract (

internal/config/application.go

@@ -47,6 +47,7 @@ type Application struct {
 	Log                logging            `yaml:"log" json:"log" mapstructure:"log"` // all logging-related options
 	Catalogers         []string           `yaml:"catalogers" json:"catalogers" mapstructure:"catalogers"`
 	Package            pkg                `yaml:"package" json:"package" mapstructure:"package"`
+	Attest             attest             `yaml:"attest" json:"attest" mapstructure:"attest"`
 	FileMetadata       FileMetadata       `yaml:"file-metadata" json:"file-metadata" mapstructure:"file-metadata"`
 	FileClassification fileClassification `yaml:"file-classification" json:"file-classification" mapstructure:"file-classification"`
 	FileContents       fileContents       `yaml:"file-contents" json:"file-contents" mapstructure:"file-contents"`

internal/config/attest.go

@@ -0,0 +1,14 @@
+package config
+
+import "github.com/spf13/viper"
+
+type attest struct {
+	// IMPORTANT: do not show the attestation key/password in any YAML/JSON output (sensitive information)
+	Key      string `yaml:"-" json:"-" mapstructure:"key"`
+	Password string `yaml:"-" json:"-" mapstructure:"password"`
+}
+
+func (cfg attest) loadDefaultValues(v *viper.Viper) {
+	v.SetDefault("attest.key", "")
+	v.SetDefault("attest.password", "")
+}

internal/file/zip_read_closer.go

@@ -146,9 +146,7 @@ func findArchiveStartOffset(r io.ReaderAt, size int64) (startOfArchive uint64, e
 		if err != nil {
 			return 0, err
 		}
-		startOfArchive = 0 // Prefixed data not supported
 	}
-
 	startOfArchive = uint64(directoryEndOffset) - d.directorySize - d.directoryOffset
 
 	// Make sure directoryOffset points to somewhere in our file.

internal/spdxlicense/license.go

@@ -12,9 +12,22 @@ import (
 // EX: gpl-2.0.0-only ---> GPL-2.0-only
 // See the debian link for more details on the spdx license differences
 
+const (
+	LicenseRefPrefix = "LicenseRef-" // prefix for non-standard licenses
+)
+
 //go:generate go run ./generate
 
-func ID(id string) (string, bool) {
-	value, exists := licenseIDs[strings.ToLower(id)]
-	return value, exists
+func ID(id string) (value, other string, exists bool) {
+	id = strings.TrimSpace(id)
+	// ignore blank strings or the joiner
+	if id == "" || id == "AND" {
+		return "", "", false
+	}
+	// first look for a canonical license
+	if value, exists := licenseIDs[strings.ToLower(id)]; exists {
+		return value, "", exists
+	}
+	// we did not find, so treat it as a separate license
+	return "", id, true
 }

internal/spdxlicense/license_test.go

@@ -9,52 +9,91 @@ import (
 func TestIDParse(t *testing.T) {
 	var tests = []struct {
 		shortName string
-		spdx      string
+		id        string
+		other     string
+		found     bool
 	}{
 		{
 			"GPL-1-only",
 			"GPL-1.0-only",
+			"",
+			true,
 		},
 		{
 			"GPL-2",
 			"GPL-2.0-only",
+			"",
+			true,
 		},
 		{
 			"GPL-2+",
 			"GPL-2.0-or-later",
+			"",
+			true,
 		},
 		{
 			"GPL-3.0.0-or-later",
 			"GPL-3.0-or-later",
+			"",
+			true,
 		},
 		{
 			"GPL-3-with-autoconf-exception",
 			"GPL-3.0-with-autoconf-exception",
+			"",
+			true,
 		},
 		{
 			"CC-by-nc-3-de",
 			"CC-BY-NC-3.0-DE",
+			"",
+			true,
 		},
 		// the below few cases are NOT expected, however, seem unavoidable given the current approach
 		{
 			"w3c-20150513.0.0",
 			"W3C-20150513",
+			"",
+			true,
 		},
 		{
 			"spencer-86.0.0",
 			"Spencer-86",
+			"",
+			true,
 		},
 		{
 			"unicode-dfs-2015.0.0",
 			"Unicode-DFS-2015",
+			"",
+			true,
+		},
+		{
+			"Unknown",
+			"",
+			"Unknown",
+			true,
+		},
+		{
+			"   ",
+			"",
+			"",
+			false,
+		},
+		{
+			"AND",
+			"",
+			"",
+			false,
 		},
 	}
 
 	for _, test := range tests {
 		t.Run(test.shortName, func(t *testing.T) {
-			got, exists := ID(test.shortName)
-			assert.True(t, exists)
-			assert.Equal(t, test.spdx, got)
+			value, other, exists := ID(test.shortName)
+			assert.Equal(t, test.found, exists)
+			assert.Equal(t, test.id, value)
+			assert.Equal(t, test.other, other)
 		})
 	}
 }

internal/string_helpers.go

@@ -28,3 +28,10 @@ func StringInSlice(a string, list []string) bool {
 	}
 	return false
 }
+
+func SplitAny(s string, seps string) []string {
+	splitter := func(r rune) bool {
+		return strings.ContainsRune(seps, r)
+	}
+	return strings.FieldsFunc(s, splitter)
+}

internal/string_helpers_test.go

@@ -104,3 +104,37 @@ func TestTruncateMiddleEllipsis(t *testing.T) {
 		})
 	}
 }
+
+func TestSplitAny(t *testing.T) {
+
+	tests := []struct {
+		name   string
+		input  string
+		fields string
+		want   []string
+	}{
+		{
+			name:   "simple",
+			input:  "a,b,c",
+			fields: ",",
+			want:   []string{"a", "b", "c"},
+		},
+		{
+			name:   "empty",
+			input:  "",
+			fields: ",",
+			want:   []string{},
+		},
+		{
+			name:   "multiple separators",
+			input:  "a,b\nc:d",
+			fields: ",:\n",
+			want:   []string{"a", "b", "c", "d"},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, SplitAny(tt.input, tt.fields))
+		})
+	}
+}

syft/file/all_regular_files.go

@@ -1,6 +1,7 @@
 package file
 
 import (
+	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/source"
 )
@@ -20,7 +21,7 @@ func allRegularFiles(resolver source.FileResolver) (locations []source.Location)
 				continue
 			}
 
-			if metadata.Type != source.RegularFile {
+			if metadata.Type != file.TypeRegular {
 				continue
 			}
 			locations = append(locations, resolvedLocation)

syft/file/all_regular_files_test.go

@@ -3,6 +3,7 @@ package file
 import (
 	"testing"
 
+	"github.com/google/go-cmp/cmp"
 	"github.com/scylladb/go-set/strset"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -69,8 +70,8 @@ func Test_allRegularFiles(t *testing.T) {
 					virtualLocations.Add(l.VirtualPath)
 				}
 			}
-			assert.ElementsMatch(t, tt.wantRealPaths.List(), realLocations.List(), "mismatched real paths")
-			assert.ElementsMatch(t, tt.wantVirtualPaths.List(), virtualLocations.List(), "mismatched virtual paths")
+			assert.ElementsMatch(t, tt.wantRealPaths.List(), realLocations.List(), "real paths differ: "+cmp.Diff(tt.wantRealPaths.List(), realLocations.List()))
+			assert.ElementsMatch(t, tt.wantVirtualPaths.List(), virtualLocations.List(), "virtual paths differ: "+cmp.Diff(tt.wantVirtualPaths.List(), virtualLocations.List()))
 		})
 	}
 }

syft/file/digest_cataloger.go

@@ -11,6 +11,7 @@ import (
 	"github.com/wagoodman/go-partybus"
 	"github.com/wagoodman/go-progress"
 
+	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
@@ -65,7 +66,7 @@ func (i *DigestsCataloger) catalogLocation(resolver source.FileResolver, locatio
 	}
 
 	// we should only attempt to report digests for files that are regular files (don't attempt to resolve links)
-	if meta.Type != source.RegularFile {
+	if meta.Type != file.TypeRegular {
 		return nil, errUndigestableFile
 	}
 

syft/file/digest_cataloger_test.go

@@ -146,7 +146,7 @@ func TestDigestsCataloger_MixFileTypes(t *testing.T) {
 			if err != nil {
 				t.Fatalf("unable to get file=%q : %+v", test.path, err)
 			}
-			l := source.NewLocationFromImage(test.path, *ref, img)
+			l := source.NewLocationFromImage(test.path, *ref.Reference, img)
 
 			if len(actual[l.Coordinates]) == 0 {
 				if test.expected != "" {

syft/file/metadata_cataloger_test.go

@@ -6,6 +6,7 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 
 	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/stereoscope/pkg/imagetest"
@@ -50,8 +51,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/file-1.txt",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:     "/file-1.txt",
 				Mode:     0644,
-				Type:     "RegularFile",
+				Type:     file.TypeRegular,
 				UserID:   1,
 				GroupID:  2,
 				Size:     7,
@@ -62,8 +64,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/hardlink-1",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:            "/hardlink-1",
 				Mode:            0644,
-				Type:            "HardLink",
+				Type:            file.TypeHardLink,
 				LinkDestination: "file-1.txt",
 				UserID:          1,
 				GroupID:         2,
@@ -74,8 +77,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/symlink-1",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:            "/symlink-1",
 				Mode:            0777 | os.ModeSymlink,
-				Type:            "SymbolicLink",
+				Type:            file.TypeSymLink,
 				LinkDestination: "file-1.txt",
 				UserID:          0,
 				GroupID:         0,
@@ -86,8 +90,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/char-device-1",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:     "/char-device-1",
 				Mode:     0644 | os.ModeDevice | os.ModeCharDevice,
-				Type:     "CharacterDevice",
+				Type:     file.TypeCharacterDevice,
 				UserID:   0,
 				GroupID:  0,
 				MIMEType: "",
@@ -97,8 +102,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/block-device-1",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:     "/block-device-1",
 				Mode:     0644 | os.ModeDevice,
-				Type:     "BlockDevice",
+				Type:     file.TypeBlockDevice,
 				UserID:   0,
 				GroupID:  0,
 				MIMEType: "",
@@ -108,8 +114,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/fifo-1",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:     "/fifo-1",
 				Mode:     0644 | os.ModeNamedPipe,
-				Type:     "FIFONode",
+				Type:     file.TypeFIFO,
 				UserID:   0,
 				GroupID:  0,
 				MIMEType: "",
@@ -119,11 +126,13 @@ func TestFileMetadataCataloger(t *testing.T) {
 			path:   "/bin",
 			exists: true,
 			expected: source.FileMetadata{
+				Path:     "/bin",
 				Mode:     0755 | os.ModeDir,
-				Type:     "Directory",
+				Type:     file.TypeDirectory,
 				UserID:   0,
 				GroupID:  0,
 				MIMEType: "",
+				IsDir:    true,
 			},
 		},
 	}
@@ -131,11 +140,9 @@ func TestFileMetadataCataloger(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.path, func(t *testing.T) {
 			_, ref, err := img.SquashedTree().File(file.Path(test.path))
-			if err != nil {
-				t.Fatalf("unable to get file: %+v", err)
-			}
+			require.NoError(t, err)
 
-			l := source.NewLocationFromImage(test.path, *ref, img)
+			l := source.NewLocationFromImage(test.path, *ref.Reference, img)
 
 			assert.Equal(t, test.expected, actual[l.Coordinates], "mismatched metadata")
 

syft/formats.go

@@ -30,12 +30,12 @@ const (
 
 // TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func FormatIDs() (ids []sbom.FormatID) {
-	return formats.IDs()
+	return formats.AllIDs()
 }
 
 // TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func FormatByID(id sbom.FormatID) sbom.Format {
-	return formats.ByID(id)
+	return formats.ByNameAndVersion(string(id), "")
 }
 
 // TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0

syft/formats/common/cyclonedxhelpers/licenses.go

@@ -10,10 +10,11 @@ import (
 func encodeLicenses(p pkg.Package) *cyclonedx.Licenses {
 	lc := cyclonedx.Licenses{}
 	for _, licenseName := range p.Licenses {
-		if value, exists := spdxlicense.ID(licenseName); exists {
+		if value, other, exists := spdxlicense.ID(licenseName); exists {
 			lc = append(lc, cyclonedx.LicenseChoice{
 				License: &cyclonedx.License{
-					ID: value,
+					ID:   value,
+					Name: other,
 				},
 			})
 		}
@@ -28,7 +29,16 @@ func decodeLicenses(c *cyclonedx.Component) (out []string) {
 	if c.Licenses != nil {
 		for _, l := range *c.Licenses {
 			if l.License != nil {
-				out = append(out, l.License.ID)
+				var lic string
+				switch {
+				case l.License.ID != "":
+					lic = l.License.ID
+				case l.License.Name != "":
+					lic = l.License.Name
+				default:
+					continue
+				}
+				out = append(out, lic)
 			}
 		}
 	}

syft/formats/common/cyclonedxhelpers/licenses_test.go

@@ -27,7 +27,9 @@ func Test_encodeLicense(t *testing.T) {
 					"made-up",
 				},
 			},
-			expected: nil,
+			expected: &cyclonedx.Licenses{
+				{License: &cyclonedx.License{Name: "made-up"}},
+			},
 		},
 		{
 			name: "with SPDX license",

syft/formats/common/spdxhelpers/license.go

@@ -22,12 +22,7 @@ func License(p pkg.Package) string {
 	}
 
 	// take all licenses and assume an AND expression; for information about license expressions see https://spdx.github.io/spdx-spec/appendix-IV-SPDX-license-expressions/
-	var parsedLicenses []string
-	for _, l := range p.Licenses {
-		if value, exists := spdxlicense.ID(l); exists {
-			parsedLicenses = append(parsedLicenses, value)
-		}
-	}
+	parsedLicenses := parseLicenses(p.Licenses)
 
 	if len(parsedLicenses) == 0 {
 		return NOASSERTION
@@ -35,3 +30,16 @@ func License(p pkg.Package) string {
 
 	return strings.Join(parsedLicenses, " AND ")
 }
+
+func parseLicenses(raw []string) (parsedLicenses []string) {
+	for _, l := range raw {
+		if value, other, exists := spdxlicense.ID(l); exists {
+			parsed := value
+			if other != "" {
+				parsed = spdxlicense.LicenseRefPrefix + other
+			}
+			parsedLicenses = append(parsedLicenses, parsed)
+		}
+	}
+	return
+}

syft/formats/common/spdxhelpers/license_test.go

@@ -26,7 +26,7 @@ func Test_License(t *testing.T) {
 					"made-up",
 				},
 			},
-			expected: NOASSERTION,
+			expected: "LicenseRef-made-up",
 		},
 		{
 			name: "with SPDX license",

syft/formats/common/spdxhelpers/to_format_model.go

@@ -8,8 +8,7 @@ import (
 	"strings"
 	"time"
 
-	"github.com/spdx/tools-golang/spdx/common"
-	spdx "github.com/spdx/tools-golang/spdx/v2_3"
+	"github.com/spdx/tools-golang/spdx"
 
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
@@ -23,7 +22,6 @@ import (
 )
 
 const (
-	spdxVersion = "SPDX-2.3"
 	noAssertion = "NOASSERTION"
 )
 
@@ -40,11 +38,11 @@ func ToFormatModel(s sbom.SBOM) *spdx.Document {
 	// for the primary package purpose field:
 	// https://spdx.github.io/spdx-spec/v2.3/package-information/#724-primary-package-purpose-field
 	documentDescribesRelationship := &spdx.Relationship{
-		RefA: common.DocElementID{
+		RefA: spdx.DocElementID{
 			ElementRefID: "DOCUMENT",
 		},
 		Relationship: string(DescribesRelationship),
-		RefB: common.DocElementID{
+		RefB: spdx.DocElementID{
 			ElementRefID: "DOCUMENT",
 		},
 		RelationshipComment: "",
@@ -55,11 +53,11 @@ func ToFormatModel(s sbom.SBOM) *spdx.Document {
 	return &spdx.Document{
 		// 6.1: SPDX Version; should be in the format "SPDX-x.x"
 		// Cardinality: mandatory, one
-		SPDXVersion: spdxVersion,
+		SPDXVersion: spdx.Version,
 
 		// 6.2: Data License; should be "CC0-1.0"
 		// Cardinality: mandatory, one
-		DataLicense: "CC0-1.0",
+		DataLicense: spdx.DataLicense,
 
 		// 6.3: SPDX Identifier; should be "DOCUMENT" to represent mandatory identifier of SPDXRef-DOCUMENT
 		// Cardinality: mandatory, one
@@ -104,7 +102,7 @@ func ToFormatModel(s sbom.SBOM) *spdx.Document {
 			// 6.8: Creators: may have multiple keys for Person, Organization
 			//      and/or Tool
 			// Cardinality: mandatory, one or many
-			Creators: []common.Creator{
+			Creators: []spdx.Creator{
 				{
 					Creator:     "Anchore, Inc",
 					CreatorType: "Organization",
@@ -126,10 +124,11 @@ func ToFormatModel(s sbom.SBOM) *spdx.Document {
 		Packages:      toPackages(s.Artifacts.PackageCatalog, s),
 		Files:         toFiles(s),
 		Relationships: relationships,
+		OtherLicenses: toOtherLicenses(s.Artifacts.PackageCatalog),
 	}
 }
 
-func toSPDXID(identifiable artifact.Identifiable) common.ElementID {
+func toSPDXID(identifiable artifact.Identifiable) spdx.ElementID {
 	id := ""
 	if p, ok := identifiable.(pkg.Package); ok {
 		id = SanitizeElementID(fmt.Sprintf("Package-%+v-%s-%s", p.Type, p.Name, p.ID()))
@@ -137,7 +136,7 @@ func toSPDXID(identifiable artifact.Identifiable) common.ElementID {
 		id = string(identifiable.ID())
 	}
 	// NOTE: the spdx libraries prepend SPDXRef-, so we don't do it here
-	return common.ElementID(id)
+	return spdx.ElementID(id)
 }
 
 // packages populates all Package Information from the package Catalog (see https://spdx.github.io/spdx-spec/3-package-information/)
@@ -313,9 +312,9 @@ func toPackages(catalog *pkg.Catalog, sbom sbom.SBOM) (results []*spdx.Package)
 	return results
 }
 
-func toPackageChecksums(p pkg.Package) ([]common.Checksum, bool) {
+func toPackageChecksums(p pkg.Package) ([]spdx.Checksum, bool) {
 	filesAnalyzed := false
-	var checksums []common.Checksum
+	var checksums []spdx.Checksum
 	switch meta := p.Metadata.(type) {
 	// we generate digest for some Java packages
 	// spdx.github.io/spdx-spec/package-information/#710-package-checksum-field
@@ -325,8 +324,8 @@ func toPackageChecksums(p pkg.Package) ([]common.Checksum, bool) {
 			filesAnalyzed = true
 			for _, digest := range meta.ArchiveDigests {
 				algo := strings.ToUpper(digest.Algorithm)
-				checksums = append(checksums, common.Checksum{
-					Algorithm: common.ChecksumAlgorithm(algo),
+				checksums = append(checksums, spdx.Checksum{
+					Algorithm: spdx.ChecksumAlgorithm(algo),
 					Value:     digest.Value,
 				})
 			}
@@ -339,20 +338,20 @@ func toPackageChecksums(p pkg.Package) ([]common.Checksum, bool) {
 			break
 		}
 		algo = strings.ToUpper(algo)
-		checksums = append(checksums, common.Checksum{
-			Algorithm: common.ChecksumAlgorithm(algo),
+		checksums = append(checksums, spdx.Checksum{
+			Algorithm: spdx.ChecksumAlgorithm(algo),
 			Value:     hexStr,
 		})
 	}
 	return checksums, filesAnalyzed
 }
 
-func toPackageOriginator(p pkg.Package) *common.Originator {
+func toPackageOriginator(p pkg.Package) *spdx.Originator {
 	kind, originator := Originator(p)
 	if kind == "" || originator == "" {
 		return nil
 	}
-	return &common.Originator{
+	return &spdx.Originator{
 		Originator:     originator,
 		OriginatorType: kind,
 	}
@@ -386,11 +385,11 @@ func toRelationships(relationships []artifact.Relationship) (result []*spdx.Rela
 		}
 
 		result = append(result, &spdx.Relationship{
-			RefA: common.DocElementID{
+			RefA: spdx.DocElementID{
 				ElementRefID: toSPDXID(r.From),
 			},
 			Relationship: string(relationshipType),
-			RefB: common.DocElementID{
+			RefB: spdx.DocElementID{
 				ElementRefID: toSPDXID(r.To),
 			},
 			RelationshipComment: comment,
@@ -462,10 +461,10 @@ func toFiles(s sbom.SBOM) (results []*spdx.File) {
 	return results
 }
 
-func toFileChecksums(digests []file.Digest) (checksums []common.Checksum) {
-	checksums = make([]common.Checksum, 0, len(digests))
+func toFileChecksums(digests []file.Digest) (checksums []spdx.Checksum) {
+	checksums = make([]spdx.Checksum, 0, len(digests))
 	for _, digest := range digests {
-		checksums = append(checksums, common.Checksum{
+		checksums = append(checksums, spdx.Checksum{
 			Algorithm: toChecksumAlgorithm(digest.Algorithm),
 			Value:     digest.Value,
 		})
@@ -473,9 +472,9 @@ func toFileChecksums(digests []file.Digest) (checksums []common.Checksum) {
 	return checksums
 }
 
-func toChecksumAlgorithm(algorithm string) common.ChecksumAlgorithm {
+func toChecksumAlgorithm(algorithm string) spdx.ChecksumAlgorithm {
 	// this needs to be an uppercase version of our algorithm
-	return common.ChecksumAlgorithm(strings.ToUpper(algorithm))
+	return spdx.ChecksumAlgorithm(strings.ToUpper(algorithm))
 }
 
 func toFileTypes(metadata *source.FileMetadata) (ty []string) {
@@ -513,11 +512,33 @@ func toFileTypes(metadata *source.FileMetadata) (ty []string) {
 	return ty
 }
 
+func toOtherLicenses(catalog *pkg.Catalog) []*spdx.OtherLicense {
+	licenses := map[string]bool{}
+	for _, pkg := range catalog.Sorted() {
+		for _, license := range parseLicenses(pkg.Licenses) {
+			if strings.HasPrefix(license, spdxlicense.LicenseRefPrefix) {
+				licenses[license] = true
+			}
+		}
+	}
+	var result []*spdx.OtherLicense
+	for license := range licenses {
+		// separate the actual ID from the prefix
+		name := strings.TrimPrefix(license, spdxlicense.LicenseRefPrefix)
+		result = append(result, &spdx.OtherLicense{
+			LicenseIdentifier: license,
+			LicenseName:       name,
+			ExtractedText:     NONE, // we probably should have some extracted text here, but this is good enough for now
+		})
+	}
+	return result
+}
+
 // TODO: handle SPDX excludes file case
 // f file is an "excludes" file, skip it /* exclude SPDX analysis file(s) */
 // see: https://spdx.github.io/spdx-spec/v2.3/package-information/#79-package-verification-code-field
 // the above link contains the SPDX algorithm for a package verification code
-func newPackageVerificationCode(p pkg.Package, sbom sbom.SBOM) *common.PackageVerificationCode {
+func newPackageVerificationCode(p pkg.Package, sbom sbom.SBOM) *spdx.PackageVerificationCode {
 	// key off of the contains relationship;
 	// spdx validator will fail if a package claims to contain a file but no sha1 provided
 	// if a sha1 for a file is provided then the validator will fail if the package does not have
@@ -558,7 +579,7 @@ func newPackageVerificationCode(p pkg.Package, sbom sbom.SBOM) *common.PackageVe
 	//nolint:gosec
 	hasher := sha1.New()
 	_, _ = hasher.Write([]byte(b.String()))
-	return &common.PackageVerificationCode{
+	return &spdx.PackageVerificationCode{
 		// 7.9.1: Package Verification Code Value
 		// Cardinality: mandatory, one
 		Value: fmt.Sprintf("%+x", hasher.Sum(nil)),

syft/formats/common/spdxhelpers/to_format_model_test.go

@@ -4,8 +4,7 @@ import (
 	"fmt"
 	"testing"
 
-	"github.com/spdx/tools-golang/spdx/common"
-	spdx "github.com/spdx/tools-golang/spdx/v2_3"
+	"github.com/spdx/tools-golang/spdx"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -21,7 +20,7 @@ func Test_toPackageChecksums(t *testing.T) {
 	tests := []struct {
 		name          string
 		pkg           pkg.Package
-		expected      []common.Checksum
+		expected      []spdx.Checksum
 		filesAnalyzed bool
 	}{
 		{
@@ -39,7 +38,7 @@ func Test_toPackageChecksums(t *testing.T) {
 					},
 				},
 			},
-			expected: []common.Checksum{
+			expected: []spdx.Checksum{
 				{
 					Algorithm: "SHA1",
 					Value:     "1234",
@@ -57,7 +56,7 @@ func Test_toPackageChecksums(t *testing.T) {
 					ArchiveDigests: []file.Digest{},
 				},
 			},
-			expected:      []common.Checksum{},
+			expected:      []spdx.Checksum{},
 			filesAnalyzed: false,
 		},
 		{
@@ -67,7 +66,7 @@ func Test_toPackageChecksums(t *testing.T) {
 				Version:  "1.0.0",
 				Language: pkg.Java,
 			},
-			expected:      []common.Checksum{},
+			expected:      []spdx.Checksum{},
 			filesAnalyzed: false,
 		},
 		{
@@ -81,7 +80,7 @@ func Test_toPackageChecksums(t *testing.T) {
 					H1Digest: "h1:9fHAtK0uDfpveeqqo1hkEZJcFvYXAiCN3UutL8F9xHw=",
 				},
 			},
-			expected: []common.Checksum{
+			expected: []spdx.Checksum{
 				{
 					Algorithm: "SHA256",
 					Value:     "f5f1c0b4ad2e0dfa6f79eaaaa3586411925c16f61702208ddd4bad2fc17dc47c",
@@ -97,7 +96,7 @@ func Test_toPackageChecksums(t *testing.T) {
 				Language: pkg.Java,
 				Metadata: struct{}{},
 			},
-			expected:      []common.Checksum{},
+			expected:      []spdx.Checksum{},
 			filesAnalyzed: false,
 		},
 	}
@@ -229,7 +228,7 @@ func Test_toFileChecksums(t *testing.T) {
 	tests := []struct {
 		name     string
 		digests  []file.Digest
-		expected []common.Checksum
+		expected []spdx.Checksum
 	}{
 		{
 			name: "empty",
@@ -246,7 +245,7 @@ func Test_toFileChecksums(t *testing.T) {
 					Value:     "meh",
 				},
 			},
-			expected: []common.Checksum{
+			expected: []spdx.Checksum{
 				{
 					Algorithm: "SHA256",
 					Value:     "deadbeefcafe",
@@ -275,8 +274,8 @@ func Test_fileIDsForPackage(t *testing.T) {
 		FileSystemID: "nowhere",
 	}
 
-	docElementId := func(identifiable artifact.Identifiable) common.DocElementID {
-		return common.DocElementID{
+	docElementId := func(identifiable artifact.Identifiable) spdx.DocElementID {
+		return spdx.DocElementID{
 			ElementRefID: toSPDXID(identifiable),
 		}
 	}

syft/formats/common/spdxhelpers/to_syft_model.go

@@ -6,7 +6,7 @@ import (
 	"strconv"
 	"strings"
 
-	spdx "github.com/spdx/tools-golang/spdx/v2_3"
+	"github.com/spdx/tools-golang/spdx"
 
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/internal/log"

syft/formats/common/spdxhelpers/to_syft_model_test.go

@@ -3,8 +3,7 @@ package spdxhelpers
 import (
 	"testing"
 
-	"github.com/spdx/tools-golang/spdx/common"
-	spdx "github.com/spdx/tools-golang/spdx/v2_3"
+	"github.com/spdx/tools-golang/spdx"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -246,9 +245,9 @@ func TestH1Digest(t *testing.T) {
 						RefType:  "purl",
 					},
 				},
-				PackageChecksums: []common.Checksum{
+				PackageChecksums: []spdx.Checksum{
 					{
-						Algorithm: common.SHA256,
+						Algorithm: spdx.SHA256,
 						Value:     "f5f1c0b4ad2e0dfa6f79eaaaa3586411925c16f61702208ddd4bad2fc17dc47c",
 					},
 				},
@@ -267,9 +266,9 @@ func TestH1Digest(t *testing.T) {
 						RefType:  "purl",
 					},
 				},
-				PackageChecksums: []common.Checksum{
+				PackageChecksums: []spdx.Checksum{
 					{
-						Algorithm: common.SHA1,
+						Algorithm: spdx.SHA1,
 						Value:     "f5f1c0b4ad2e0dfa6f79eaaaa3586411925c16f61702208ddd4bad2fc17dc47c",
 					},
 				},
@@ -288,9 +287,9 @@ func TestH1Digest(t *testing.T) {
 						RefType:  "purl",
 					},
 				},
-				PackageChecksums: []common.Checksum{
+				PackageChecksums: []spdx.Checksum{
 					{
-						Algorithm: common.SHA256,
+						Algorithm: spdx.SHA256,
 						Value:     "",
 					},
 				},

syft/formats/cyclonedxjson/encoder_test.go

@@ -5,7 +5,7 @@ import (
 	"regexp"
 	"testing"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateCycloneDx = flag.Bool("update-cyclonedx", false, "update the *.golden files for cyclone-dx encoders")

syft/formats/cyclonedxjson/format.go

@@ -7,13 +7,14 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "cyclonedx-1-json"
+const ID sbom.FormatID = "cyclonedx-json"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		sbom.AnyVersion,
 		encoder,
 		cyclonedxhelpers.GetDecoder(cyclonedx.BOMFileFormatJSON),
 		cyclonedxhelpers.GetValidator(cyclonedx.BOMFileFormatJSON),
+		ID,
 	)
 }

syft/formats/cyclonedxxml/encoder_test.go

@@ -5,7 +5,7 @@ import (
 	"regexp"
 	"testing"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateCycloneDx = flag.Bool("update-cyclonedx", false, "update the *.golden files for cyclone-dx encoders")

syft/formats/cyclonedxxml/format.go

@@ -7,13 +7,14 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "cyclonedx-1-xml"
+const ID sbom.FormatID = "cyclonedx-xml"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		sbom.AnyVersion,
 		encoder,
 		cyclonedxhelpers.GetDecoder(cyclonedx.BOMFileFormatXML),
 		cyclonedxhelpers.GetValidator(cyclonedx.BOMFileFormatXML),
+		ID, "cyclonedx", "cyclone",
 	)
 }

syft/formats/formats.go

@@ -5,8 +5,11 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"regexp"
 	"strings"
 
+	"golang.org/x/exp/slices"
+
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/formats/cyclonedxjson"
 	"github.com/anchore/syft/syft/formats/cyclonedxxml"
@@ -26,8 +29,11 @@ func Formats() []sbom.Format {
 		cyclonedxxml.Format(),
 		cyclonedxjson.Format(),
 		github.Format(),
-		spdxtagvalue.Format(),
-		spdxjson.Format(),
+		spdxtagvalue.Format2_1(),
+		spdxtagvalue.Format2_2(),
+		spdxtagvalue.Format2_3(),
+		spdxjson.Format2_2(),
+		spdxjson.Format2_3(),
 		table.Format(),
 		text.Format(),
 		template.Format(),
@@ -38,7 +44,7 @@ func Identify(by []byte) sbom.Format {
 	for _, f := range Formats() {
 		if err := f.Validate(bytes.NewReader(by)); err != nil {
 			if !errors.Is(err, sbom.ErrValidationNotSupported) {
-				log.Debugf("format %s returned err: %+v", f.ID(), err)
+				log.WithFields("error", err).Tracef("format validation for %s failed", f.ID())
 			}
 			continue
 		}
@@ -47,53 +53,51 @@ func Identify(by []byte) sbom.Format {
 	return nil
 }
 
+// ByName accepts a name@version string, such as:
+//
+//	spdx-json@2.1 or cyclonedx@2
 func ByName(name string) sbom.Format {
-	cleanName := cleanFormatName(name)
-	for _, f := range Formats() {
-		if cleanFormatName(string(f.ID())) == cleanName {
-			return f
-		}
+	parts := strings.SplitN(name, "@", 2)
+	version := sbom.AnyVersion
+	if len(parts) > 1 {
+		version = parts[1]
 	}
-
-	// handle any aliases for any supported format
-	switch cleanName {
-	case "json", "syftjson":
-		return ByID(syftjson.ID)
-	case "cyclonedx", "cyclone", "cyclonedxxml":
-		return ByID(cyclonedxxml.ID)
-	case "cyclonedxjson":
-		return ByID(cyclonedxjson.ID)
-	case "github", "githubjson":
-		return ByID(github.ID)
-	case "spdx", "spdxtv", "spdxtagvalue":
-		return ByID(spdxtagvalue.ID)
-	case "spdxjson":
-		return ByID(spdxjson.ID)
-	case "table":
-		return ByID(table.ID)
-	case "text":
-		return ByID(text.ID)
-	case "template":
-		ByID(template.ID)
-	}
-
-	return nil
+	return ByNameAndVersion(parts[0], version)
 }
 
-func IDs() (ids []sbom.FormatID) {
+func ByNameAndVersion(name string, version string) sbom.Format {
+	name = cleanFormatName(name)
+	var mostRecentFormat sbom.Format
 	for _, f := range Formats() {
-		ids = append(ids, f.ID())
-	}
-	return ids
-}
-
-func ByID(id sbom.FormatID) sbom.Format {
-	for _, f := range Formats() {
-		if f.ID() == id {
-			return f
+		for _, n := range f.IDs() {
+			if cleanFormatName(string(n)) == name && versionMatches(f.Version(), version) {
+				if mostRecentFormat == nil || f.Version() > mostRecentFormat.Version() {
+					mostRecentFormat = f
+				}
+			}
 		}
 	}
-	return nil
+	return mostRecentFormat
+}
+
+func versionMatches(version string, match string) bool {
+	if version == sbom.AnyVersion || match == sbom.AnyVersion {
+		return true
+	}
+
+	dots := strings.Count(match, ".")
+	if dots == 0 {
+		match += ".*"
+	}
+	match = strings.ReplaceAll(match, ".", "\\.")
+	match = strings.ReplaceAll(match, "*", ".*")
+	match = strings.ReplaceAll(match, "\\..*", "(\\..*)*")
+	match = fmt.Sprintf("^%s$", match)
+	matcher, err := regexp.Compile(match)
+	if err != nil {
+		return false
+	}
+	return matcher.MatchString(version)
 }
 
 func cleanFormatName(name string) string {
@@ -127,3 +131,13 @@ func Decode(reader io.Reader) (*sbom.SBOM, sbom.Format, error) {
 	s, err := f.Decode(bytes.NewReader(by))
 	return s, f, err
 }
+
+func AllIDs() (ids []sbom.FormatID) {
+	for _, f := range Formats() {
+		if slices.Contains(ids, f.ID()) {
+			continue
+		}
+		ids = append(ids, f.ID())
+	}
+	return ids
+}

syft/formats/formats_test.go

@@ -92,18 +92,6 @@ func TestByName(t *testing.T) {
 			name: "spdxtv", // clean variant
 			want: spdxtagvalue.ID,
 		},
-		{
-			name: "spdx-2-tag-value", // clean variant
-			want: spdxtagvalue.ID,
-		},
-		{
-			name: "spdx-2-tagvalue", // clean variant
-			want: spdxtagvalue.ID,
-		},
-		{
-			name: "spdx2-tagvalue", // clean variant
-			want: spdxtagvalue.ID,
-		},
 
 		// SPDX JSON
 		{
@@ -111,7 +99,7 @@ func TestByName(t *testing.T) {
 			want: spdxjson.ID,
 		},
 		{
-			name: "spdx-2-json",
+			name: "spdxjson", // clean variant
 			want: spdxjson.ID,
 		},
 
@@ -121,7 +109,7 @@ func TestByName(t *testing.T) {
 			want: cyclonedxjson.ID,
 		},
 		{
-			name: "cyclonedx-1-json",
+			name: "cyclonedxjson", // clean variant
 			want: cyclonedxjson.ID,
 		},
 
@@ -135,7 +123,7 @@ func TestByName(t *testing.T) {
 			want: cyclonedxxml.ID,
 		},
 		{
-			name: "cyclonedx-1-xml",
+			name: "cyclonedxxml", // clean variant
 			want: cyclonedxxml.ID,
 		},
 
@@ -144,7 +132,6 @@ func TestByName(t *testing.T) {
 			name: "table",
 			want: table.ID,
 		},
-
 		{
 			name: "syft-table",
 			want: table.ID,
@@ -155,7 +142,6 @@ func TestByName(t *testing.T) {
 			name: "text",
 			want: text.ID,
 		},
-
 		{
 			name: "syft-text",
 			want: text.ID,
@@ -166,23 +152,26 @@ func TestByName(t *testing.T) {
 			name: "json",
 			want: syftjson.ID,
 		},
-
 		{
 			name: "syft-json",
 			want: syftjson.ID,
 		},
+		{
+			name: "syftjson", // clean variant
+			want: syftjson.ID,
+		},
 
 		// GitHub JSON
 		{
 			name: "github",
 			want: github.ID,
 		},
-
 		{
 			name: "github-json",
 			want: github.ID,
 		},
 
+		// Syft template
 		{
 			name: "template",
 			want: template.ID,
@@ -200,3 +189,56 @@ func TestByName(t *testing.T) {
 		})
 	}
 }
+
+func Test_versionMatches(t *testing.T) {
+	tests := []struct {
+		name    string
+		version string
+		match   string
+		matches bool
+	}{
+		{
+			name:    "any version matches number",
+			version: string(sbom.AnyVersion),
+			match:   "6",
+			matches: true,
+		},
+		{
+			name:    "number matches any version",
+			version: "6",
+			match:   string(sbom.AnyVersion),
+			matches: true,
+		},
+		{
+			name:    "same number matches",
+			version: "3",
+			match:   "3",
+			matches: true,
+		},
+		{
+			name:    "same major number matches",
+			version: "3.1",
+			match:   "3",
+			matches: true,
+		},
+		{
+			name:    "same minor number matches",
+			version: "3.1",
+			match:   "3.1",
+			matches: true,
+		},
+		{
+			name:    "different number does not match",
+			version: "3",
+			match:   "4",
+			matches: false,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matches := versionMatches(test.version, test.match)
+			assert.Equal(t, test.matches, matches)
+		})
+	}
+}

syft/formats/github/format.go

@@ -7,11 +7,11 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "github-0-json"
+const ID sbom.FormatID = "github-json"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		sbom.AnyVersion,
 		func(writer io.Writer, sbom sbom.SBOM) error {
 			bom := toGithubModel(&sbom)
 
@@ -25,5 +25,6 @@ func Format() sbom.Format {
 		},
 		nil,
 		nil,
+		ID, "github",
 	)
 }

syft/formats/internal/testutils/utils.go

@@ -168,7 +168,7 @@ func populateImageCatalog(catalog *pkg.Catalog, img *image.Image) {
 		Name:    "package-1",
 		Version: "1.0.1",
 		Locations: source.NewLocationSet(
-			source.NewLocationFromImage(string(ref1.RealPath), *ref1, img),
+			source.NewLocationFromImage(string(ref1.RealPath), *ref1.Reference, img),
 		),
 		Type:         pkg.PythonPkg,
 		FoundBy:      "the-cataloger-1",
@@ -188,7 +188,7 @@ func populateImageCatalog(catalog *pkg.Catalog, img *image.Image) {
 		Name:    "package-2",
 		Version: "2.0.1",
 		Locations: source.NewLocationSet(
-			source.NewLocationFromImage(string(ref2.RealPath), *ref2, img),
+			source.NewLocationFromImage(string(ref2.RealPath), *ref2.Reference, img),
 		),
 		Type:         pkg.DebPkg,
 		FoundBy:      "the-cataloger-2",

syft/formats/spdxjson/decoder.go

@@ -4,14 +4,14 @@ import (
 	"fmt"
 	"io"
 
-	spdx "github.com/spdx/tools-golang/json"
+	"github.com/spdx/tools-golang/json"
 
 	"github.com/anchore/syft/syft/formats/common/spdxhelpers"
 	"github.com/anchore/syft/syft/sbom"
 )
 
 func decoder(reader io.Reader) (s *sbom.SBOM, err error) {
-	doc, err := spdx.Load2_3(reader)
+	doc, err := json.Read(reader)
 	if err != nil {
 		return nil, fmt.Errorf("unable to decode spdx-json: %w", err)
 	}

syft/formats/spdxjson/encoder.go

@@ -4,13 +4,31 @@ import (
 	"encoding/json"
 	"io"
 
+	"github.com/spdx/tools-golang/convert"
+	"github.com/spdx/tools-golang/spdx/v2/v2_2"
+
 	"github.com/anchore/syft/syft/formats/common/spdxhelpers"
 	"github.com/anchore/syft/syft/sbom"
 )
 
-func encoder(output io.Writer, s sbom.SBOM) error {
+func encoder2_3(output io.Writer, s sbom.SBOM) error {
+	doc := spdxhelpers.ToFormatModel(s)
+	return encodeJSON(output, doc)
+}
+
+func encoder2_2(output io.Writer, s sbom.SBOM) error {
 	doc := spdxhelpers.ToFormatModel(s)
 
+	var out v2_2.Document
+	err := convert.Document(doc, &out)
+	if err != nil {
+		return err
+	}
+
+	return encodeJSON(output, out)
+}
+
+func encodeJSON(output io.Writer, doc interface{}) error {
 	enc := json.NewEncoder(output)
 	// prevent > and < from being escaped in the payload
 	enc.SetEscapeHTML(false)

syft/formats/spdxjson/encoder_test.go

@@ -5,7 +5,7 @@ import (
 	"regexp"
 	"testing"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateSpdxJson = flag.Bool("update-spdx-json", false, "update the *.golden files for spdx-json encoders")
@@ -48,11 +48,11 @@ func TestSPDXRelationshipOrder(t *testing.T) {
 
 func spdxJsonRedactor(s []byte) []byte {
 	// each SBOM reports the time it was generated, which is not useful during snapshot testing
-	s = regexp.MustCompile(`"created":\s+"[^"]*",?`).ReplaceAll(s, []byte(""))
+	s = regexp.MustCompile(`"created":\s+"[^"]*"`).ReplaceAll(s, []byte(`"created":""`))
 
 	// each SBOM reports a unique documentNamespace when generated, this is not useful for snapshot testing
-	s = regexp.MustCompile(`"documentNamespace":\s+"[^"]*",?`).ReplaceAll(s, []byte(""))
+	s = regexp.MustCompile(`"documentNamespace":\s+"[^"]*"`).ReplaceAll(s, []byte(`"documentNamespace":""`))
 
 	// the license list will be updated periodically, the value here should not be directly tested in snapshot tests
-	return regexp.MustCompile(`"licenseListVersion":\s+"[^"]*",?`).ReplaceAll(s, []byte(""))
+	return regexp.MustCompile(`"licenseListVersion":\s+"[^"]*"`).ReplaceAll(s, []byte(`"licenseListVersion":""`))
 }

syft/formats/spdxjson/format.go

@@ -4,14 +4,30 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "spdx-2-json"
+const ID sbom.FormatID = "spdx-json"
+
+var IDs = []sbom.FormatID{ID}
 
 // note: this format is LOSSY relative to the syftjson format
-func Format() sbom.Format {
+
+func Format2_2() sbom.Format {
 	return sbom.NewFormat(
-		ID,
-		encoder,
+		"2.2",
+		encoder2_2,
 		decoder,
 		validator,
+		IDs...,
 	)
 }
+
+func Format2_3() sbom.Format {
+	return sbom.NewFormat(
+		"2.3",
+		encoder2_3,
+		decoder,
+		validator,
+		IDs...,
+	)
+}
+
+var Format = Format2_3

syft/formats/spdxjson/test-fixtures/snapshot/TestSPDXJSONDirectoryEncoder.golden

@@ -3,15 +3,14 @@
  "dataLicense": "CC0-1.0",
  "SPDXID": "SPDXRef-DOCUMENT",
  "name": "/some/path",
- "documentNamespace": "https://anchore.com/syft/dir/some/path-e13c8924-4bbc-42f8-bd30-4e1554472d62",
+ "documentNamespace": "https://anchore.com/syft/dir/some/path-1fe34646-a616-48c7-974b-3d1e27d406e3",
  "creationInfo": {
   "licenseListVersion": "3.19",
   "creators": [
    "Organization: Anchore, Inc",
    "Tool: syft-v0.42.0-bogus"
   ],
-  "created": "2022-12-22T23:33:52Z",
-  "comment": ""
+  "created": "2023-01-20T21:41:03Z"
  },
  "packages": [
   {
@@ -27,14 +26,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "a-purl-2",
-     "comment": ""
+     "referenceLocator": "a-purl-2"
     }
    ]
   },
@@ -51,14 +48,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "pkg:deb/debian/package-2@2.0.1",
-     "comment": ""
+     "referenceLocator": "pkg:deb/debian/package-2@2.0.1"
     }
    ]
   }

syft/formats/spdxjson/test-fixtures/snapshot/TestSPDXJSONImageEncoder.golden

@@ -3,15 +3,14 @@
  "dataLicense": "CC0-1.0",
  "SPDXID": "SPDXRef-DOCUMENT",
  "name": "user-image-input",
- "documentNamespace": "https://anchore.com/syft/image/user-image-input-a1cc9d58-830a-4a4b-9dcd-f41ea3001216",
+ "documentNamespace": "https://anchore.com/syft/image/user-image-input-33759ac3-6006-4f2c-bdc4-f40b9287a7f0",
  "creationInfo": {
   "licenseListVersion": "3.19",
   "creators": [
    "Organization: Anchore, Inc",
    "Tool: syft-v0.42.0-bogus"
   ],
-  "created": "2022-12-22T23:33:53Z",
-  "comment": ""
+  "created": "2023-01-20T21:41:03Z"
  },
  "packages": [
   {
@@ -27,14 +26,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:1:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:1:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "a-purl-1",
-     "comment": ""
+     "referenceLocator": "a-purl-1"
     }
    ]
   },
@@ -51,14 +48,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "pkg:deb/debian/package-2@2.0.1",
-     "comment": ""
+     "referenceLocator": "pkg:deb/debian/package-2@2.0.1"
     }
    ]
   }

syft/formats/spdxjson/test-fixtures/snapshot/TestSPDXRelationshipOrder.golden

@@ -3,15 +3,14 @@
  "dataLicense": "CC0-1.0",
  "SPDXID": "SPDXRef-DOCUMENT",
  "name": "user-image-input",
- "documentNamespace": "https://anchore.com/syft/image/user-image-input-fc663ee3-0f9b-402e-827f-3f29aeff164e",
+ "documentNamespace": "https://anchore.com/syft/image/user-image-input-ce98f51f-b483-4e93-9a15-5a8a16d35de6",
  "creationInfo": {
   "licenseListVersion": "3.19",
   "creators": [
    "Organization: Anchore, Inc",
    "Tool: syft-v0.42.0-bogus"
   ],
-  "created": "2022-12-22T23:33:53Z",
-  "comment": ""
+  "created": "2023-01-20T21:41:03Z"
  },
  "packages": [
   {
@@ -27,14 +26,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:1:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:1:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "a-purl-1",
-     "comment": ""
+     "referenceLocator": "a-purl-1"
     }
    ]
   },
@@ -51,14 +48,12 @@
     {
      "referenceCategory": "SECURITY",
      "referenceType": "cpe23Type",
-     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-     "comment": ""
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
     },
     {
      "referenceCategory": "PACKAGE-MANAGER",
      "referenceType": "purl",
-     "referenceLocator": "pkg:deb/debian/package-2@2.0.1",
-     "comment": ""
+     "referenceLocator": "pkg:deb/debian/package-2@2.0.1"
     }
    ]
   }

syft/formats/spdxtagvalue/decoder.go

@@ -4,14 +4,14 @@ import (
 	"fmt"
 	"io"
 
-	"github.com/spdx/tools-golang/tvloader"
+	"github.com/spdx/tools-golang/tagvalue"
 
 	"github.com/anchore/syft/syft/formats/common/spdxhelpers"
 	"github.com/anchore/syft/syft/sbom"
 )
 
 func decoder(reader io.Reader) (*sbom.SBOM, error) {
-	doc, err := tvloader.Load2_3(reader)
+	doc, err := tagvalue.Read(reader)
 	if err != nil {
 		return nil, fmt.Errorf("unable to decode spdx-tag-value: %w", err)
 	}

syft/formats/spdxtagvalue/encoder.go

@@ -3,13 +3,36 @@ package spdxtagvalue
 import (
 	"io"
 
-	"github.com/spdx/tools-golang/tvsaver"
+	"github.com/spdx/tools-golang/convert"
+	"github.com/spdx/tools-golang/spdx/v2/v2_1"
+	"github.com/spdx/tools-golang/spdx/v2/v2_2"
+	"github.com/spdx/tools-golang/tagvalue"
 
 	"github.com/anchore/syft/syft/formats/common/spdxhelpers"
 	"github.com/anchore/syft/syft/sbom"
 )
 
-func encoder(output io.Writer, s sbom.SBOM) error {
+func encoder2_3(output io.Writer, s sbom.SBOM) error {
 	model := spdxhelpers.ToFormatModel(s)
-	return tvsaver.Save2_3(model, output)
+	return tagvalue.Write(model, output)
+}
+
+func encoder2_2(output io.Writer, s sbom.SBOM) error {
+	model := spdxhelpers.ToFormatModel(s)
+	var out v2_2.Document
+	err := convert.Document(model, &out)
+	if err != nil {
+		return err
+	}
+	return tagvalue.Write(out, output)
+}
+
+func encoder2_1(output io.Writer, s sbom.SBOM) error {
+	model := spdxhelpers.ToFormatModel(s)
+	var out v2_1.Document
+	err := convert.Document(model, &out)
+	if err != nil {
+		return err
+	}
+	return tagvalue.Write(out, output)
 }

syft/formats/spdxtagvalue/encoder_test.go

@@ -5,7 +5,7 @@ import (
 	"regexp"
 	"testing"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"

syft/formats/spdxtagvalue/format.go

@@ -4,14 +4,39 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "spdx-2-tag-value"
+const ID sbom.FormatID = "spdx-tag-value"
 
-// note: this format is LOSSY relative to the syftjson formation, which means that decoding and validation is not supported at this time
-func Format() sbom.Format {
+var IDs = []sbom.FormatID{ID, "spdx", "spdx-tv"}
+
+// note: this format is LOSSY relative to the syftjson format
+func Format2_1() sbom.Format {
 	return sbom.NewFormat(
-		ID,
-		encoder,
+		"2.1",
+		encoder2_1,
 		decoder,
 		validator,
+		IDs...,
 	)
 }
+
+func Format2_2() sbom.Format {
+	return sbom.NewFormat(
+		"2.2",
+		encoder2_2,
+		decoder,
+		validator,
+		IDs...,
+	)
+}
+
+func Format2_3() sbom.Format {
+	return sbom.NewFormat(
+		"2.3",
+		encoder2_3,
+		decoder,
+		validator,
+		IDs...,
+	)
+}
+
+var Format = Format2_3

syft/formats/syftjson/decoder_test.go

@@ -8,7 +8,7 @@ import (
 	"github.com/go-test/deep"
 	"github.com/stretchr/testify/assert"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 func TestEncodeDecodeCycle(t *testing.T) {

syft/formats/syftjson/encoder_test.go

@@ -2,12 +2,14 @@ package syftjson
 
 import (
 	"flag"
+	"regexp"
 	"testing"
 
+	stereoFile "github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/file"
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 	"github.com/anchore/syft/syft/linux"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/sbom"
@@ -20,8 +22,9 @@ func TestDirectoryEncoder(t *testing.T) {
 	testutils.AssertEncoderAgainstGoldenSnapshot(t,
 		Format(),
 		testutils.DirectoryInput(t),
-		true,
 		*updateJson,
+		true,
+		schemaVersionRedactor,
 	)
 }
 
@@ -31,11 +34,18 @@ func TestImageEncoder(t *testing.T) {
 		Format(),
 		testutils.ImageInput(t, testImage, testutils.FromSnapshot()),
 		testImage,
-		true,
 		*updateJson,
+		true,
+		schemaVersionRedactor,
 	)
 }
 
+func schemaVersionRedactor(s []byte) []byte {
+	pattern := regexp.MustCompile(`,?\s*"schema":\s*\{[^}]*}`)
+	out := pattern.ReplaceAll(s, []byte(""))
+	return out
+}
+
 func TestEncodeFullJSONDocument(t *testing.T) {
 	catalog := pkg.NewCatalog()
 
@@ -98,26 +108,26 @@ func TestEncodeFullJSONDocument(t *testing.T) {
 			FileMetadata: map[source.Coordinates]source.FileMetadata{
 				source.NewLocation("/a/place").Coordinates: {
 					Mode:    0775,
-					Type:    "directory",
+					Type:    stereoFile.TypeDirectory,
 					UserID:  0,
 					GroupID: 0,
 				},
 				source.NewLocation("/a/place/a").Coordinates: {
 					Mode:    0775,
-					Type:    "regularFile",
+					Type:    stereoFile.TypeRegular,
 					UserID:  0,
 					GroupID: 0,
 				},
 				source.NewLocation("/b").Coordinates: {
 					Mode:            0775,
-					Type:            "symbolicLink",
+					Type:            stereoFile.TypeSymLink,
 					LinkDestination: "/c",
 					UserID:          0,
 					GroupID:         0,
 				},
 				source.NewLocation("/b/place/b").Coordinates: {
 					Mode:    0644,
-					Type:    "regularFile",
+					Type:    stereoFile.TypeRegular,
 					UserID:  1,
 					GroupID: 2,
 				},

syft/formats/syftjson/format.go

@@ -4,13 +4,14 @@ import (
 	"github.com/anchore/syft/syft/sbom"
 )
 
-const ID sbom.FormatID = "syft-6-json"
+const ID sbom.FormatID = "syft-json"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		"6",
 		encoder,
 		decoder,
 		validator,
+		ID, "json", "syft",
 	)
 }

syft/formats/syftjson/model/file.go

@@ -14,10 +14,10 @@ type File struct {
 }
 
 type FileMetadataEntry struct {
-	Mode            int             `json:"mode"`
-	Type            source.FileType `json:"type"`
-	LinkDestination string          `json:"linkDestination,omitempty"`
-	UserID          int             `json:"userID"`
-	GroupID         int             `json:"groupID"`
-	MIMEType        string          `json:"mimeType"`
+	Mode            int    `json:"mode"`
+	Type            string `json:"type"`
+	LinkDestination string `json:"linkDestination,omitempty"`
+	UserID          int    `json:"userID"`
+	GroupID         int    `json:"groupID"`
+	MIMEType        string `json:"mimeType"`
 }

syft/formats/syftjson/test-fixtures/snapshot/TestDirectoryEncoder.golden

@@ -89,7 +89,7 @@
   }
  },
  "schema": {
-  "version": "6.1.0",
-  "url": "https://raw.githubusercontent.com/anchore/syft/main/schema/json/schema-6.1.0.json"
+  "version": "6.2.0",
+  "url": "https://raw.githubusercontent.com/anchore/syft/main/schema/json/schema-6.2.0.json"
  }
 }

syft/formats/syftjson/test-fixtures/snapshot/TestEncodeFullJSONDocument.golden

@@ -78,7 +78,7 @@
    },
    "metadata": {
     "mode": 775,
-    "type": "directory",
+    "type": "Directory",
     "userID": 0,
     "groupID": 0,
     "mimeType": ""
@@ -91,7 +91,7 @@
    },
    "metadata": {
     "mode": 775,
-    "type": "regularFile",
+    "type": "RegularFile",
     "userID": 0,
     "groupID": 0,
     "mimeType": ""
@@ -111,7 +111,7 @@
    },
    "metadata": {
     "mode": 775,
-    "type": "symbolicLink",
+    "type": "SymbolicLink",
     "linkDestination": "/c",
     "userID": 0,
     "groupID": 0,
@@ -125,7 +125,7 @@
    },
    "metadata": {
     "mode": 644,
-    "type": "regularFile",
+    "type": "RegularFile",
     "userID": 1,
     "groupID": 2,
     "mimeType": ""

syft/formats/syftjson/test-fixtures/snapshot/TestImageEncoder.golden

@@ -9,7 +9,7 @@
    "locations": [
     {
      "path": "/somefile-1.txt",
-     "layerID": "sha256:6afd1cb55939d87ba4c298907d0a53059bb3742c2d65314643e2464071cf0a2d"
+     "layerID": "sha256:fb6beecb75b39f4bb813dbf177e501edd5ddb3e69bb45cedeb78c676ee1b7a59"
     }
    ],
    "licenses": [
@@ -40,7 +40,7 @@
    "locations": [
     {
      "path": "/somefile-2.txt",
-     "layerID": "sha256:657997cff9a836139186239bdfe77250239a700d0ed97d57e101c295e8244319"
+     "layerID": "sha256:319b588ce64253a87b533c8ed01cf0025e0eac98e7b516e12532957e1244fdec"
     }
    ],
    "licenses": [],
@@ -64,11 +64,11 @@
  ],
  "artifactRelationships": [],
  "source": {
-  "id": "c85f7ae1b0ac38342c1cf1a6f7ea2b4b1ddc49cd1b24219ebd05dc10b3303491",
+  "id": "1a678f111c8ddc66fd82687bb024e0dd6af61314404937a80e810c0cf317b796",
   "type": "image",
   "target": {
    "userInput": "user-image-input",
-   "imageID": "sha256:b5c0bfa8bcf70c75d92ebebbf76af667906d56e6fad50c37e7f93df824a64b79",
+   "imageID": "sha256:3c51b06feb0cda8ee62d0e3755ef2a8496a6b71f8a55b245f07f31c4bb813d31",
    "manifestDigest": "sha256:2731251dc34951c0e50fcc643b4c5f74922dad1a5d98f302b504cf46cd5d9368",
    "mediaType": "application/vnd.docker.distribution.manifest.v2+json",
    "tags": [
@@ -78,17 +78,17 @@
    "layers": [
     {
      "mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
-     "digest": "sha256:6afd1cb55939d87ba4c298907d0a53059bb3742c2d65314643e2464071cf0a2d",
+     "digest": "sha256:fb6beecb75b39f4bb813dbf177e501edd5ddb3e69bb45cedeb78c676ee1b7a59",
      "size": 22
     },
     {
      "mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
-     "digest": "sha256:657997cff9a836139186239bdfe77250239a700d0ed97d57e101c295e8244319",
+     "digest": "sha256:319b588ce64253a87b533c8ed01cf0025e0eac98e7b516e12532957e1244fdec",
      "size": 16
     }
    ],
-   "manifest": "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",
-   "config": "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",
+   "manifest": "eyJzY2hlbWFWZXJzaW9uIjoyLCJtZWRpYVR5cGUiOiJhcHBsaWNhdGlvbi92bmQuZG9ja2VyLmRpc3RyaWJ1dGlvbi5tYW5pZmVzdC52Mitqc29uIiwiY29uZmlnIjp7Im1lZGlhVHlwZSI6ImFwcGxpY2F0aW9uL3ZuZC5kb2NrZXIuY29udGFpbmVyLmltYWdlLnYxK2pzb24iLCJzaXplIjo2NzMsImRpZ2VzdCI6InNoYTI1NjozYzUxYjA2ZmViMGNkYThlZTYyZDBlMzc1NWVmMmE4NDk2YTZiNzFmOGE1NWIyNDVmMDdmMzFjNGJiODEzZDMxIn0sImxheWVycyI6W3sibWVkaWFUeXBlIjoiYXBwbGljYXRpb24vdm5kLmRvY2tlci5pbWFnZS5yb290ZnMuZGlmZi50YXIuZ3ppcCIsInNpemUiOjIwNDgsImRpZ2VzdCI6InNoYTI1NjpmYjZiZWVjYjc1YjM5ZjRiYjgxM2RiZjE3N2U1MDFlZGQ1ZGRiM2U2OWJiNDVjZWRlYjc4YzY3NmVlMWI3YTU5In0seyJtZWRpYVR5cGUiOiJhcHBsaWNhdGlvbi92bmQuZG9ja2VyLmltYWdlLnJvb3Rmcy5kaWZmLnRhci5nemlwIiwic2l6ZSI6MjA0OCwiZGlnZXN0Ijoic2hhMjU2OjMxOWI1ODhjZTY0MjUzYTg3YjUzM2M4ZWQwMWNmMDAyNWUwZWFjOThlN2I1MTZlMTI1MzI5NTdlMTI0NGZkZWMifV19",
+   "config": "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",
    "repoDigests": [],
    "architecture": "",
    "os": ""
@@ -112,7 +112,7 @@
   }
  },
  "schema": {
-  "version": "6.1.0",
-  "url": "https://raw.githubusercontent.com/anchore/syft/main/schema/json/schema-6.1.0.json"
+  "version": "6.2.0",
+  "url": "https://raw.githubusercontent.com/anchore/syft/main/schema/json/schema-6.2.0.json"
  }
 }

syft/formats/syftjson/to_format_model.go

@@ -5,6 +5,7 @@ import (
 	"sort"
 	"strconv"
 
+	stereoscopeFile "github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
@@ -137,7 +138,7 @@ func toFileMetadataEntry(coordinates source.Coordinates, metadata *source.FileMe
 
 	return &model.FileMetadataEntry{
 		Mode:            mode,
-		Type:            metadata.Type,
+		Type:            toFileType(metadata.Type),
 		LinkDestination: metadata.LinkDestination,
 		UserID:          metadata.UserID,
 		GroupID:         metadata.GroupID,
@@ -145,6 +146,31 @@ func toFileMetadataEntry(coordinates source.Coordinates, metadata *source.FileMe
 	}
 }
 
+func toFileType(ty stereoscopeFile.Type) string {
+	switch ty {
+	case stereoscopeFile.TypeSymLink:
+		return "SymbolicLink"
+	case stereoscopeFile.TypeHardLink:
+		return "HardLink"
+	case stereoscopeFile.TypeDirectory:
+		return "Directory"
+	case stereoscopeFile.TypeSocket:
+		return "Socket"
+	case stereoscopeFile.TypeBlockDevice:
+		return "BlockDevice"
+	case stereoscopeFile.TypeCharacterDevice:
+		return "CharacterDevice"
+	case stereoscopeFile.TypeFIFO:
+		return "FIFONode"
+	case stereoscopeFile.TypeRegular:
+		return "RegularFile"
+	case stereoscopeFile.TypeIrregular:
+		return "IrregularFile"
+	default:
+		return "Unknown"
+	}
+}
+
 func toPackageModels(catalog *pkg.Catalog) []model.Package {
 	artifacts := make([]model.Package, 0)
 	if catalog == nil {

syft/formats/syftjson/to_format_model_test.go

@@ -8,6 +8,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/syft/formats/syftjson/model"
 	"github.com/anchore/syft/syft/source"
@@ -15,8 +16,7 @@ import (
 
 func Test_SyftJsonID_Compatibility(t *testing.T) {
 	jsonMajorVersion := strings.Split(internal.JSONSchemaVersion, ".")[0]
-	syftJsonIDVersion := strings.Split(string(ID), "-")[1]
-	assert.Equal(t, jsonMajorVersion, syftJsonIDVersion)
+	assert.Equal(t, jsonMajorVersion, string(Format().Version()))
 }
 
 func Test_toSourceModel(t *testing.T) {
@@ -98,3 +98,64 @@ func Test_toSourceModel(t *testing.T) {
 	// assert all possible schemes were under test
 	assert.ElementsMatch(t, allSchemes.List(), testedSchemes.List(), "not all source.Schemes are under test")
 }
+
+func Test_toFileType(t *testing.T) {
+
+	badType := file.Type(0x1337)
+	var allTypesTested []file.Type
+	tests := []struct {
+		ty   file.Type
+		name string
+	}{
+		{
+			ty:   file.TypeRegular,
+			name: "RegularFile",
+		},
+		{
+			ty:   file.TypeDirectory,
+			name: "Directory",
+		},
+		{
+			ty:   file.TypeSymLink,
+			name: "SymbolicLink",
+		},
+		{
+			ty:   file.TypeHardLink,
+			name: "HardLink",
+		},
+		{
+			ty:   file.TypeSocket,
+			name: "Socket",
+		},
+		{
+			ty:   file.TypeCharacterDevice,
+			name: "CharacterDevice",
+		},
+		{
+			ty:   file.TypeBlockDevice,
+			name: "BlockDevice",
+		},
+		{
+			ty:   file.TypeFIFO,
+			name: "FIFONode",
+		},
+		{
+			ty:   file.TypeIrregular,
+			name: "IrregularFile",
+		},
+		{
+			ty:   badType,
+			name: "Unknown",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equalf(t, tt.name, toFileType(tt.ty), "toFileType(%v)", tt.ty)
+			if tt.ty != badType {
+				allTypesTested = append(allTypesTested, tt.ty)
+			}
+		})
+	}
+
+	assert.ElementsMatch(t, allTypesTested, file.AllTypes(), "not all file.Types are under test")
+}

syft/formats/table/encoder_test.go

@@ -6,7 +6,7 @@ import (
 
 	"github.com/go-test/deep"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateTableGoldenFiles = flag.Bool("update-table", false, "update the *.golden files for table format")
@@ -15,8 +15,8 @@ func TestTableEncoder(t *testing.T) {
 	testutils.AssertEncoderAgainstGoldenSnapshot(t,
 		Format(),
 		testutils.DirectoryInput(t),
-		false,
 		*updateTableGoldenFiles,
+		false,
 	)
 }
 

syft/formats/table/format.go

@@ -8,9 +8,10 @@ const ID sbom.FormatID = "syft-table"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		sbom.AnyVersion,
 		encoder,
 		nil,
 		nil,
+		ID, "table",
 	)
 }

syft/formats/template/encoder_test.go

@@ -6,7 +6,7 @@ import (
 
 	"github.com/stretchr/testify/assert"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateTmpl = flag.Bool("update-tmpl", false, "update the *.golden files for json encoders")

syft/formats/template/format.go

@@ -1,6 +1,7 @@
 package template
 
 import (
+	"fmt"
 	"io"
 
 	"github.com/anchore/syft/syft/formats/syftjson"
@@ -23,7 +24,19 @@ func (f OutputFormat) ID() sbom.FormatID {
 	return ID
 }
 
-func (f OutputFormat) Decode(reader io.Reader) (*sbom.SBOM, error) {
+func (f OutputFormat) IDs() []sbom.FormatID {
+	return []sbom.FormatID{ID}
+}
+
+func (f OutputFormat) Version() string {
+	return sbom.AnyVersion
+}
+
+func (f OutputFormat) String() string {
+	return fmt.Sprintf("template: " + f.templateFilePath)
+}
+
+func (f OutputFormat) Decode(_ io.Reader) (*sbom.SBOM, error) {
 	return nil, sbom.ErrDecodingNotSupported
 }
 
@@ -37,7 +50,7 @@ func (f OutputFormat) Encode(output io.Writer, s sbom.SBOM) error {
 	return tmpl.Execute(output, doc)
 }
 
-func (f OutputFormat) Validate(reader io.Reader) error {
+func (f OutputFormat) Validate(_ io.Reader) error {
 	return sbom.ErrValidationNotSupported
 }
 
@@ -45,3 +58,5 @@ func (f OutputFormat) Validate(reader io.Reader) error {
 func (f *OutputFormat) SetTemplatePath(filePath string) {
 	f.templateFilePath = filePath
 }
+
+var _ sbom.Format = (*OutputFormat)(nil)

syft/formats/text/encoder_test.go

@@ -4,7 +4,7 @@ import (
 	"flag"
 	"testing"
 
-	"github.com/anchore/syft/syft/formats/common/testutils"
+	"github.com/anchore/syft/syft/formats/internal/testutils"
 )
 
 var updateTextEncoderGoldenFiles = flag.Bool("update-text", false, "update the *.golden files for text encoder")

syft/formats/text/format.go

@@ -8,9 +8,10 @@ const ID sbom.FormatID = "syft-text"
 
 func Format() sbom.Format {
 	return sbom.NewFormat(
-		ID,
+		sbom.AnyVersion,
 		encoder,
 		nil,
 		nil,
+		ID, "text",
 	)
 }

syft/pkg/cataloger/alpm/cataloger_test.go

@@ -0,0 +1,209 @@
+package alpm
+
+import (
+	"testing"
+
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"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/pkgtest"
+	"github.com/anchore/syft/syft/source"
+)
+
+func TestAlpmCataloger(t *testing.T) {
+
+	expectedPkgs := []pkg.Package{
+		{
+			Name:         "gmp",
+			Version:      "6.2.1-2",
+			Type:         pkg.AlpmPkg,
+			FoundBy:      "alpmdb-cataloger",
+			Licenses:     []string{"LGPL3", "GPL"},
+			Locations:    source.NewLocationSet(source.NewLocation("var/lib/pacman/local/gmp-6.2.1-2/desc")),
+			CPEs:         nil,
+			PURL:         "",
+			MetadataType: "AlpmMetadata",
+			Metadata: pkg.AlpmMetadata{
+				BasePackage:  "gmp",
+				Package:      "gmp",
+				Version:      "6.2.1-2",
+				Description:  "A free library for arbitrary precision arithmetic",
+				Architecture: "x86_64",
+				Size:         1044438,
+				Packager:     "Antonio Rojas <arojas@archlinux.org>",
+				License:      "LGPL3\nGPL",
+				URL:          "https://gmplib.org/",
+				Validation:   "pgp",
+				Reason:       1,
+				Files: []pkg.AlpmFileRecord{
+					{
+						Path:    "/usr",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path:    "/usr/include",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path: "/usr/include/gmp.h",
+						Size: "84140",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "76595f70565c72550eb520809bf86856"},
+							{Algorithm: "sha256", Value: "91a614b9202453153fe3b7512d15e89659108b93ce8841c8e13789eb85da9e3a"},
+						},
+					},
+					{
+						Path: "/usr/include/gmpxx.h",
+						Size: "129113",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "ea3d21de4bcf7c696799c5c55dd3655b"},
+							{Algorithm: "sha256", Value: "0011ae411a0bc1030e07d968b32fdc1343f5ac2a17b7d28f493e7976dde2ac82"},
+						},
+					},
+					{
+						Path:    "/usr/lib",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path:    "/usr/lib/libgmp.so",
+						Type:    "link",
+						Link:    "libgmp.so.10.4.1",
+						Digests: []file.Digest{},
+					},
+					{
+						Path:    "/usr/lib/libgmp.so.10",
+						Type:    "link",
+						Link:    "libgmp.so.10.4.1",
+						Digests: []file.Digest{},
+					},
+					{
+						Path: "/usr/lib/libgmp.so.10.4.1",
+						Size: "663224",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "d6d03eadacdd9048d5b2adf577e9d722"},
+							{Algorithm: "sha256", Value: "39898bd3d8d6785222432fa8b8aef7ce3b7e5bbfc66a52b7c0da09bed4adbe6a"},
+						},
+					},
+					{
+						Path:    "/usr/lib/libgmpxx.so",
+						Type:    "link",
+						Link:    "libgmpxx.so.4.6.1",
+						Digests: []file.Digest{},
+					},
+					{
+						Path:    "/usr/lib/libgmpxx.so.4",
+						Type:    "link",
+						Link:    "libgmpxx.so.4.6.1",
+						Digests: []file.Digest{},
+					},
+					{
+						Path: "/usr/lib/libgmpxx.so.4.6.1",
+						Size: "30680",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "dd5f0c4d635fa599fa7f4339c0e8814d"},
+							{Algorithm: "sha256", Value: "0ef67cbde4841f58d2e4b41f59425eb87c9eeaf4e649c060b326342c53bedbec"},
+						},
+					},
+					{
+						Path:    "/usr/lib/pkgconfig",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path: "/usr/lib/pkgconfig/gmp.pc",
+						Size: "245",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "a91a9f1b66218cb77b9cd2cdf341756d"},
+							{Algorithm: "sha256", Value: "4e9de547a48c4e443781e9fa702a1ec5a23ee28b4bc520306cff2541a855be37"},
+						},
+					},
+					{
+						Path: "/usr/lib/pkgconfig/gmpxx.pc",
+						Size: "280",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "8c0f54e987934352177a6a30a811b001"},
+							{Algorithm: "sha256", Value: "fc5dbfbe75977057ba50953d94b9daecf696c9fdfe5b94692b832b44ecca871b"},
+						},
+					},
+					{
+						Path:    "/usr/share",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path:    "/usr/share/info",
+						Type:    "dir",
+						Digests: []file.Digest{},
+					},
+					{
+						Path: "/usr/share/info/gmp.info-1.gz",
+						Size: "85892",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "63304d4d2f0247fb8a999fae66a81c19"},
+							{Algorithm: "sha256", Value: "86288c1531a2789db5da8b9838b5cde4db07bda230ae11eba23a1f33698bd14e"},
+						},
+					},
+					{
+						Path: "/usr/share/info/gmp.info-2.gz",
+						Size: "48484",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "4bb0dadec416d305232cac6eae712ff7"},
+							{Algorithm: "sha256", Value: "b7443c1b529588d98a074266087f79b595657ac7274191c34b10a9ceedfa950e"},
+						},
+					},
+					{
+						Path: "/usr/share/info/gmp.info.gz",
+						Size: "2380",
+						Digests: []file.Digest{
+							{Algorithm: "md5", Value: "cf6880fb0d862ee1da0d13c3831b5720"},
+							{Algorithm: "sha256", Value: "a13c8eecda3f3e5ad1e09773e47a9686f07d9d494eaddf326f3696bbef1548fd"},
+						},
+					},
+				},
+				Backup: []pkg.AlpmFileRecord{},
+			},
+		},
+	}
+
+	// TODO: relationships are not under test yet
+	var expectedRelationships []artifact.Relationship
+
+	pkgtest.NewCatalogTester().
+		FromDirectory(t, "test-fixtures/gmp-fixture").
+		WithCompareOptions(cmpopts.IgnoreFields(pkg.AlpmFileRecord{}, "Time")).
+		Expects(expectedPkgs, expectedRelationships).
+		TestCataloger(t, NewAlpmdbCataloger())
+
+}
+
+func TestCataloger_Globs(t *testing.T) {
+	tests := []struct {
+		name     string
+		fixture  string
+		expected []string
+	}{
+		{
+			name:    "obtain description files",
+			fixture: "test-fixtures/glob-paths",
+			expected: []string{
+				"var/lib/pacman/local/base-1.0/desc",
+				"var/lib/pacman/local/dive-0.10.0/desc",
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, test.fixture).
+				ExpectsResolverContentQueries(test.expected).
+				IgnoreUnfulfilledPathResponses("var/lib/pacman/local/base-1.0/mtree", "var/lib/pacman/local/dive-0.10.0/mtree").
+				TestCataloger(t, NewAlpmdbCataloger())
+		})
+	}
+}

syft/pkg/cataloger/alpm/package.go

@@ -1,9 +1,8 @@
 package alpm
 
 import (
-	"strings"
-
 	"github.com/anchore/packageurl-go"
+	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/syft/linux"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
@@ -15,7 +14,7 @@ func newPackage(m pkg.AlpmMetadata, release *linux.Release, locations ...source.
 		Version:      m.Version,
 		Locations:    source.NewLocationSet(locations...),
 		Type:         pkg.AlpmPkg,
-		Licenses:     strings.Split(m.License, " "),
+		Licenses:     internal.SplitAny(m.License, " \n"),
 		PURL:         packageURL(m, release),
 		MetadataType: pkg.AlpmMetadataType,
 		Metadata:     m,

syft/pkg/cataloger/alpm/parse_alpm_db.go

@@ -65,6 +65,10 @@ func parseAlpmDB(resolver source.FileResolver, env *generic.Environment, reader
 		metadata.Backup = filesMetadata.Backup
 	}
 
+	if metadata.Package == "" {
+		return nil, nil, nil
+	}
+
 	return []pkg.Package{
 		newPackage(*metadata, env.LinuxRelease, reader.Location),
 	}, nil, nil

syft/pkg/cataloger/alpm/parse_alpm_db_test.go

@@ -16,10 +16,12 @@ import (
 func TestDatabaseParser(t *testing.T) {
 	tests := []struct {
 		name     string
+		fixture  string
 		expected pkg.AlpmMetadata
 	}{
 		{
-			name: "test alpm database parsing",
+			name:    "test alpm database parsing",
+			fixture: "test-fixtures/files",
 			expected: pkg.AlpmMetadata{
 				Backup: []pkg.AlpmFileRecord{
 					{
@@ -90,7 +92,7 @@ func TestDatabaseParser(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
-			f, err := os.Open("test-fixtures/files")
+			f, err := os.Open(test.fixture)
 			require.NoError(t, err)
 			t.Cleanup(func() { require.NoError(t, f.Close()) })
 

syft/pkg/cataloger/alpm/test-fixtures/glob-paths/var/lib/pacman/local/base-1.0/desc

@@ -0,0 +1 @@
+bogus desc file

syft/pkg/cataloger/alpm/test-fixtures/glob-paths/var/lib/pacman/local/base-1.0/files

@@ -0,0 +1 @@
+bogus files

syft/pkg/cataloger/alpm/test-fixtures/glob-paths/var/lib/pacman/local/dive-0.10.0/desc

@@ -0,0 +1 @@
+bogus desc file

syft/pkg/cataloger/alpm/test-fixtures/gmp-fixture/var/lib/pacman/local/gmp-6.2.1-2/desc

@@ -0,0 +1,44 @@
+%NAME%
+gmp
+
+%VERSION%
+6.2.1-2
+
+%BASE%
+gmp
+
+%DESC%
+A free library for arbitrary precision arithmetic
+
+%URL%
+https://gmplib.org/
+
+%ARCH%
+x86_64
+
+%BUILDDATE%
+1653121258
+
+%INSTALLDATE%
+1665878640
+
+%PACKAGER%
+Antonio Rojas <arojas@archlinux.org>
+
+%SIZE%
+1044438
+
+%REASON%
+1
+
+%LICENSE%
+LGPL3
+GPL
+
+%VALIDATION%
+pgp
+
+%DEPENDS%
+gcc-libs
+sh
+

syft/pkg/cataloger/alpm/test-fixtures/gmp-fixture/var/lib/pacman/local/gmp-6.2.1-2/files

@@ -0,0 +1,21 @@
+%FILES%
+usr/
+usr/include/
+usr/include/gmp.h
+usr/include/gmpxx.h
+usr/lib/
+usr/lib/libgmp.so
+usr/lib/libgmp.so.10
+usr/lib/libgmp.so.10.4.1
+usr/lib/libgmpxx.so
+usr/lib/libgmpxx.so.4
+usr/lib/libgmpxx.so.4.6.1
+usr/lib/pkgconfig/
+usr/lib/pkgconfig/gmp.pc
+usr/lib/pkgconfig/gmpxx.pc
+usr/share/
+usr/share/info/
+usr/share/info/gmp.info-1.gz
+usr/share/info/gmp.info-2.gz
+usr/share/info/gmp.info.gz
+

syft/pkg/cataloger/apkdb/cataloger_test.go

@@ -0,0 +1,30 @@
+package apkdb
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/pkgtest"
+)
+
+func TestCataloger_Globs(t *testing.T) {
+	tests := []struct {
+		name     string
+		fixture  string
+		expected []string
+	}{
+		{
+			name:     "obtain DB files",
+			fixture:  "test-fixtures/glob-paths",
+			expected: []string{"lib/apk/db/installed"},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, test.fixture).
+				ExpectsResolverContentQueries(test.expected).
+				TestCataloger(t, NewApkdbCataloger())
+		})
+	}
+}

syft/pkg/cataloger/apkdb/parse_apk_db.go

@@ -7,6 +7,7 @@ import (
 	"strconv"
 	"strings"
 
+	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
@@ -350,19 +351,12 @@ func discoverPackageDependencies(pkgs []pkg.Package) (relationships []artifact.R
 	return relationships
 }
 
-func splitAny(s string, seps string) []string {
-	splitter := func(r rune) bool {
-		return strings.ContainsRune(seps, r)
-	}
-	return strings.FieldsFunc(s, splitter)
-}
-
 func stripVersionSpecifier(s string) string {
 	// examples:
 	// musl>=1                 --> musl
 	// cmd:scanelf=1.3.4-r0    --> cmd:scanelf
 
-	items := splitAny(s, "<>=")
+	items := internal.SplitAny(s, "<>=")
 	if len(items) == 0 {
 		return s
 	}

syft/pkg/cataloger/apkdb/test-fixtures/glob-paths/lib/apk/db/installed

@@ -0,0 +1 @@
+bogus db contents

syft/pkg/cataloger/binary/cataloger.go

@@ -32,6 +32,7 @@ func (c Cataloger) Catalog(resolver source.FileResolver) ([]pkg.Package, []artif
 	var relationships []artifact.Relationship
 
 	for _, cls := range defaultClassifiers {
+		log.WithFields("classifier", cls.Class).Trace("cataloging binaries")
 		pkgs, err := catalog(resolver, cls)
 		if err != nil {
 			log.WithFields("error", err, "classifier", cls.Class).Warn("unable to catalog binary package: %w", err)

syft/pkg/cataloger/binary/cataloger_test.go

@@ -13,12 +13,96 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
-func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
+func Test_Cataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 	tests := []struct {
 		name       string
 		fixtureDir string
 		expected   pkg.Package
 	}{
+		{
+			name:       "positive-postgresql-15beta4",
+			fixtureDir: "test-fixtures/classifiers/positive/postgresql-15beta4",
+			expected: pkg.Package{
+				Name:      "postgresql",
+				Version:   "15beta4",
+				Type:      "binary",
+				PURL:      "pkg:generic/postgresql@15beta4",
+				Locations: singleLocation("postgres"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "postgresql-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-postgresql-15.1",
+			fixtureDir: "test-fixtures/classifiers/positive/postgresql-15.1",
+			expected: pkg.Package{
+				Name:      "postgresql",
+				Version:   "15.1",
+				Type:      "binary",
+				PURL:      "pkg:generic/postgresql@15.1",
+				Locations: singleLocation("postgres"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "postgresql-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-postgresql-9.6.24",
+			fixtureDir: "test-fixtures/classifiers/positive/postgresql-9.6.24",
+			expected: pkg.Package{
+				Name:      "postgresql",
+				Version:   "9.6.24",
+				Type:      "binary",
+				PURL:      "pkg:generic/postgresql@9.6.24",
+				Locations: singleLocation("postgres"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "postgresql-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-postgresql-9.5alpha1",
+			fixtureDir: "test-fixtures/classifiers/positive/postgresql-9.5alpha1",
+			expected: pkg.Package{
+				Name:      "postgresql",
+				Version:   "9.5alpha1",
+				Type:      "binary",
+				PURL:      "pkg:generic/postgresql@9.5alpha1",
+				Locations: singleLocation("postgres"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "postgresql-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-traefik-2.9.6",
+			fixtureDir: "test-fixtures/classifiers/positive/traefik-2.9.6",
+			expected: pkg.Package{
+				Name:      "traefik",
+				Version:   "2.9.6",
+				Type:      "binary",
+				PURL:      "pkg:generic/traefik@2.9.6",
+				Locations: singleLocation("traefik"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "traefik-binary",
+				},
+			},
+		},
+		{
+			name:       "positive-traefik-1.7.34",
+			fixtureDir: "test-fixtures/classifiers/positive/traefik-1.7.34",
+			expected: pkg.Package{
+				Name:      "traefik",
+				Version:   "1.7.34",
+				Type:      "binary",
+				PURL:      "pkg:generic/traefik@1.7.34",
+				Locations: singleLocation("traefik"),
+				Metadata: pkg.BinaryMetadata{
+					Classifier: "traefik-binary",
+				},
+			},
+		},
 		{
 			name:       "positive-memcached-1.6.18",
 			fixtureDir: "test-fixtures/classifiers/positive/memcached-1.6.18",
@@ -356,7 +440,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 	}
 }
 
-func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T) {
+func Test_Cataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T) {
 	tests := []struct {
 		name         string
 		fixtureImage string
@@ -437,39 +521,57 @@ func assertPackagesAreEqual(t *testing.T, expected pkg.Package, p pkg.Package) {
 }
 
 type panicyResolver struct {
-	globCalled bool
+	searchCalled bool
 }
 
-func (p panicyResolver) FileContentsByLocation(location source.Location) (io.ReadCloser, error) {
+func (p *panicyResolver) FilesByExtension(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
 	return nil, errors.New("not implemented")
 }
 
-func (p panicyResolver) HasPath(s string) bool {
+func (p *panicyResolver) FilesByBasename(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
+	return nil, errors.New("not implemented")
+}
+
+func (p *panicyResolver) FilesByBasenameGlob(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
+	return nil, errors.New("not implemented")
+}
+
+func (p *panicyResolver) FileContentsByLocation(_ source.Location) (io.ReadCloser, error) {
+	p.searchCalled = true
+	return nil, errors.New("not implemented")
+}
+
+func (p *panicyResolver) HasPath(s string) bool {
 	return true
 }
 
-func (p panicyResolver) FilesByPath(paths ...string) ([]source.Location, error) {
+func (p *panicyResolver) FilesByPath(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
 	return nil, errors.New("not implemented")
 }
 
-func (p *panicyResolver) FilesByGlob(patterns ...string) ([]source.Location, error) {
-	p.globCalled = true
+func (p *panicyResolver) FilesByGlob(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
 	return nil, errors.New("not implemented")
 }
 
-func (p panicyResolver) FilesByMIMEType(types ...string) ([]source.Location, error) {
+func (p *panicyResolver) FilesByMIMEType(_ ...string) ([]source.Location, error) {
+	p.searchCalled = true
 	return nil, errors.New("not implemented")
 }
 
-func (p panicyResolver) RelativeFileByPath(_ source.Location, path string) *source.Location {
+func (p *panicyResolver) RelativeFileByPath(_ source.Location, _ string) *source.Location {
 	return nil
 }
 
-func (p panicyResolver) AllLocations() <-chan source.Location {
+func (p *panicyResolver) AllLocations() <-chan source.Location {
 	return nil
 }
 
-func (p panicyResolver) FileMetadataByLocation(location source.Location) (source.FileMetadata, error) {
+func (p *panicyResolver) FileMetadataByLocation(_ source.Location) (source.FileMetadata, error) {
 	return source.FileMetadata{}, errors.New("not implemented")
 }
 
@@ -479,5 +581,5 @@ func Test_Cataloger_ResilientToErrors(t *testing.T) {
 	resolver := &panicyResolver{}
 	_, _, err := c.Catalog(resolver)
 	assert.NoError(t, err)
-	assert.True(t, resolver.globCalled)
+	assert.True(t, resolver.searchCalled)
 }

syft/pkg/cataloger/binary/classifier_test.go

@@ -21,7 +21,7 @@ func Test_ClassifierCPEs(t *testing.T) {
 			fixture: "test-fixtures/version.txt",
 			classifier: classifier{
 				Package:         "some-app",
-				FileGlob:        ".*/version.txt",
+				FileGlob:        "**/version.txt",
 				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
 				CPEs:            []cpe.CPE{},
 			},
@@ -32,7 +32,7 @@ func Test_ClassifierCPEs(t *testing.T) {
 			fixture: "test-fixtures/version.txt",
 			classifier: classifier{
 				Package:         "some-app",
-				FileGlob:        ".*/version.txt",
+				FileGlob:        "**/version.txt",
 				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
 				CPEs: []cpe.CPE{
 					cpe.Must("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*"),
@@ -47,7 +47,7 @@ func Test_ClassifierCPEs(t *testing.T) {
 			fixture: "test-fixtures/version.txt",
 			classifier: classifier{
 				Package:         "some-app",
-				FileGlob:        ".*/version.txt",
+				FileGlob:        "**/version.txt",
 				EvidenceMatcher: fileContentsVersionMatcher(`(?m)my-verison:(?P<version>[0-9.]+)`),
 				CPEs: []cpe.CPE{
 					cpe.Must("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*"),

syft/pkg/cataloger/binary/default_classifiers.go

@@ -1,6 +1,9 @@
 package binary
 
-import "github.com/anchore/syft/syft/pkg"
+import (
+	"github.com/anchore/syft/syft/cpe"
+	"github.com/anchore/syft/syft/pkg"
+)
 
 var defaultClassifiers = []classifier{
 	{
@@ -11,6 +14,10 @@ var defaultClassifiers = []classifier{
 			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
 		Package: "python",
 		PURL:    mustPURL("pkg:generic/python@version"),
+		CPEs: []cpe.CPE{
+			cpe.Must("cpe:2.3:a:python_software_foundation:python:*:*:*:*:*:*:*:*"),
+			cpe.Must("cpe:2.3:a:python:python:*:*:*:*:*:*:*:*"),
+		},
 	},
 	{
 		Class:    "python-binary-lib",
@@ -20,6 +27,10 @@ var defaultClassifiers = []classifier{
 			`(?m)(?P<version>{{ .version }}\.[0-9]+[-_a-zA-Z0-9]*)`),
 		Package: "python",
 		PURL:    mustPURL("pkg:generic/python@version"),
+		CPEs: []cpe.CPE{
+			cpe.Must("cpe:2.3:a:python_software_foundation:python:*:*:*:*:*:*:*:*"),
+			cpe.Must("cpe:2.3:a:python:python:*:*:*:*:*:*:*:*"),
+		},
 	},
 	{
 		Class:    "cpython-source",
@@ -28,6 +39,10 @@ var defaultClassifiers = []classifier{
 			`(?m)#define\s+PY_VERSION\s+"?(?P<version>[0-9\.\-_a-zA-Z]+)"?`),
 		Package: "python",
 		PURL:    mustPURL("pkg:generic/python@version"),
+		CPEs: []cpe.CPE{
+			cpe.Must("cpe:2.3:a:python_software_foundation:python:*:*:*:*:*:*:*:*"),
+			cpe.Must("cpe:2.3:a:python:python:*:*:*:*:*:*:*:*"),
+		},
 	},
 	{
 		Class:    "go-binary",
@@ -103,6 +118,7 @@ var defaultClassifiers = []classifier{
 		EvidenceMatcher: fileContentsVersionMatcher(
 			`(?m)BusyBox\s+v(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
 		Package: "busybox",
+		CPEs:    singleCPE("cpe:2.3:a:busybox:busybox:*:*:*:*:*:*:*:*"),
 	},
 	{
 		Class:    "php-cli-binary",
@@ -149,4 +165,26 @@ var defaultClassifiers = []classifier{
 		Package: "memcached",
 		PURL:    mustPURL("pkg:generic/memcached@version"),
 	},
+	{
+		Class:    "traefik-binary",
+		FileGlob: "**/traefik",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			// [NUL]v1.7.34[NUL]
+			// [NUL]2.9.6[NUL]
+			`(?m)\x00v?(?P<version>[0-9]+\.[0-9]+\.[0-9]+(-alpha[0-9]|-beta[0-9]|-rc[0-9])?)\x00`),
+		Package: "traefik",
+		PURL:    mustPURL("pkg:generic/traefik@version"),
+	},
+	{
+		Class:    "postgresql-binary",
+		FileGlob: "**/postgres",
+		EvidenceMatcher: fileContentsVersionMatcher(
+			// [NUL]PostgreSQL 15beta4
+			// [NUL]PostgreSQL 15.1
+			// [NUL]PostgreSQL 9.6.24
+			// ?PostgreSQL 9.5alpha1
+			`(?m)(\x00|\?)PostgreSQL (?P<version>[0-9]+(\.[0-9]+)?(\.[0-9]+)?(alpha[0-9]|beta[0-9]|rc[0-9])?)`),
+		Package: "postgresql",
+		PURL:    mustPURL("pkg:generic/postgresql@version"),
+	},
 }