[wip] prototype binary relationships

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>
remove unreleated swift change
2026-10-13 14:47:22 +02:00 · 2024-03-13 18:09:19 -04:00 · 2024-03-13 17:09:08 -04:00 · 2024-03-13 17:07:52 -04:00 · 2024-03-13 17:05:56 -04:00 · 2024-03-13 16:44:05 -04:00
700 changed files with 41394 additions and 4174 deletions
@@ -1,4 +1,5 @@
 tools:
+  # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
  - name: binny
    version:
      want: v0.6.3
@@ -6,6 +7,15 @@ tools:
    with:
      repo: anchore/binny

+  # used to produce SBOMs during release
+  - name: syft
+    version:
+      want: latest
+    method: github-release
+    with:
+      repo: anchore/syft
+
+  # used to sign mac binaries at release
  - name: quill
    version:
      want: v0.4.1
@@ -13,13 +23,15 @@ tools:
    with:
      repo: anchore/quill

+  # used for linting
  - name: golangci-lint
    version:
-      want: v1.55.2
+      want: v1.56.2
    method: github-release
    with:
      repo: golangci/golangci-lint

+  # used for showing the changelog at release
  - name: glow
    version:
      want: v1.5.1
@@ -27,13 +39,15 @@ tools:
    with:
      repo: charmbracelet/glow

+  # used for signing the checksums file at release
  - name: cosign
    version:
-      want: v2.2.2
+      want: v2.2.3
    method: github-release
    with:
      repo: sigstore/cosign

+  # used in integration tests to verify JSON schemas
  - name: yajsv
    version:
      want: v1.4.1
@@ -41,13 +55,15 @@ tools:
    with:
      repo: neilpa/yajsv

+  # used to release all artifacts
  - name: goreleaser
    version:
-      want: v1.23.0
+      want: v1.24.0
    method: github-release
    with:
      repo: goreleaser/goreleaser

+  # used for organizing imports during static analysis
  - name: gosimports
    version:
      want: v0.3.8
@@ -55,6 +71,7 @@ tools:
    with:
      repo: rinchsan/gosimports

+  # used at release to generate the changelog
  - name: chronicle
    version:
      want: v0.8.0
@@ -62,6 +79,7 @@ tools:
    with:
      repo: anchore/chronicle

+  # used during static analysis for license compliance
  - name: bouncer
    version:
      want: v0.4.0
@@ -69,6 +87,7 @@ tools:
    with:
      repo: wagoodman/go-bouncer

+  # used for showing benchmark testing
  - name: benchstat
    version:
      want: latest
@@ -81,16 +100,18 @@ tools:
      entrypoint: cmd/benchstat
      module: golang.org/x/perf

+  # used for running all local and CI tasks
  - name: task
    version:
-      want: v3.33.1
+      want: v3.35.1
    method: github-release
    with:
      repo: go-task/task

+  # used for triggering a release
  - name: gh
    version:
-      want: v2.42.1
+      want: v2.45.0
    method: github-release
    with:
      repo: cli/cli
@@ -1,4 +1,4 @@
-enforce-v0: true # don't make breaking-change label bump major version before 1.0.
+enforce-v0: false
 title: ""

 github:
@@ -176,7 +176,8 @@ def filter_to_schema_files(list_of_files: list[str]) -> list[str]:

 def list_json_schema_files() -> list[str]:
    # list files in "schema/json" directory matching the pattern of "schema-*.json"
-    return sort_json_schema_files(list(glob.glob("schema/json/schema-*.json")))
+    # special case: always ignore the "latest" schema file
+    return sort_json_schema_files([f for f in glob.glob("schema/json/schema-*.json") if "latest" not in f])


 def run(command: str,  **kwargs) -> subprocess.CompletedProcess:
@@ -197,7 +198,7 @@ def sort_json_schema_files(files: list[str]) -> list[str]:
    # so that "schema/json/schema-1.2.1.json" comes before "schema/json/schema-1.12.1.json".
    versions = [get_semver(file) for file in files if file]
    
-    versions = sorted(versions, key=lambda s: [int(u) for u in s.split('.')])
+    versions = sorted(versions, key=lambda s: [int(u) for u in s.split('.') if "." in s])

    return [f"schema/json/schema-{version}.json" for version in versions]

@@ -60,6 +60,11 @@ class Labeler(unittest.TestCase):
        expected_sorted_files = ["schema/json/schema-1.2.1.json", "schema/json/schema-1.12.1.json"]
        self.assertEqual(labeler.sort_json_schema_files(files), expected_sorted_files)

+        # ensure that "latest" doesn't cause a problem and is ultimately ignored
+        files = ["schema/json/schema-1.12.1.json", "schema/json/schema-_bogus.json"]
+        expected_sorted_files = ["schema/json/schema-_bogus.json", "schema/json/schema-1.12.1.json"]
+        self.assertEqual(labeler.sort_json_schema_files(files), expected_sorted_files)
+

 if __name__ == "__main__":
    unittest.main()
@@ -17,13 +17,13 @@ jobs:
    # the job by event.
    steps:
      - name: Checkout code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+        uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 # v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap

      - name: Restore base benchmark result
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: test/results/benchmark-main.txt
          # use base sha for PR or new commit hash for main push in benchmark result key
@@ -39,13 +39,13 @@ jobs:
          OUTPUT="${OUTPUT//$'\r'/'%0D'}" # URL encode all '\r' characters
          echo "result=$OUTPUT" >> $GITHUB_OUTPUT

-      - uses: actions/upload-artifact@1eb3cb2b3e0f29609092a73eb033bb759a334595 # v4.1.0
+      - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4.3.1
        with:
          name: benchmark-test-results
          path: test/results/**/*

      - name: Update PR benchmark results comment
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
        continue-on-error: true
        with:
          header: benchmark
@@ -20,7 +20,7 @@ permissions:
 jobs:
  analyze:
    name: Analyze
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04-4core-16gb

    permissions:
      security-events: write
@@ -36,7 +36,7 @@ jobs:

    steps:
    - name: Checkout repository
-      uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

    - name: Install Go
      uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
@@ -45,7 +45,7 @@ jobs:

    # Initializes the CodeQL tools for scanning.
    - name: Initialize CodeQL
-      uses: github/codeql-action/init@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/init@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6
      with:
        languages: ${{ matrix.language }}
        # If you wish to specify custom queries, you can do so here or in a config file.
@@ -56,7 +56,7 @@ jobs:
    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
    # If this step fails, then you should remove it and run the build manually (see below)
    - name: Autobuild
-      uses: github/codeql-action/autobuild@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/autobuild@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6

    # ℹ️ Command-line programs to run using the OS shell.
    # 📚 https://git.io/JvXDl
@@ -70,4 +70,4 @@ jobs:
    #   make release

    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/analyze@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6
@@ -0,0 +1,10 @@
+name: Dependabot Automation
+on:
+  pull_request:
+
+permissions:
+  pull-requests: write
+
+jobs:
+  run:
+    uses: anchore/workflows/.github/workflows/dependabot-automation.yaml@main
@@ -30,7 +30,7 @@ jobs:
    runs-on: ubuntu-22.04
    steps:

-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - run: python .github/scripts/labeler.py
        env:
@@ -40,7 +40,7 @@ jobs:

      - name: Delete existing comment
        if: ${{ hashFiles( env.CI_COMMENT_FILE ) == '' }}
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
        with:
          header: ${{ env.COMMENT_HEADER }}
          hide: true
@@ -48,7 +48,7 @@ jobs:

      - name: Add comment
        if: ${{ hashFiles( env.CI_COMMENT_FILE ) != '' }}
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
        with:
          header: ${{ env.COMMENT_HEADER }}
          path: ${{ env.CI_COMMENT_FILE }}
@@ -11,7 +11,7 @@ jobs:
    runs-on: ubuntu-20.04
    steps:

-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
        with:
          # we need to be able to get the commit for a tag
          fetch-depth: 0
@@ -30,7 +30,7 @@ jobs:
          echo -n "commit=$(git rev-parse HEAD)" | tee -a $GITHUB_OUTPUT

      - name: Update Homebrew formula
-        uses: dawidd6/action-homebrew-bump-formula@75ed025ff3ad1d617862838b342b06d613a0ddf3 # v3.10.1
+        uses: dawidd6/action-homebrew-bump-formula@baf2b60c51fc1f8453c884b0c61052668a71bd1d # v3.11.0
        with:
          token: ${{ secrets.HOMEBREW_TOKEN }}
          org: anchore
@@ -38,7 +38,7 @@ jobs:
          tag: ${{ steps.release_info.outputs.tag_name }}
          revision: ${{ steps.git_info.outputs.commit }}

-      - uses: 8398a7/action-slack@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
        if: ${{ failure() }}
        with:
          status: ${{ job.status }}
@@ -15,7 +15,7 @@ jobs:
    environment: release
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Check if tag already exists
        # note: this will fail if the tag already exists
@@ -94,8 +94,10 @@ jobs:
    permissions:
      contents: write
      packages: write
+      # required for goreleaser signs section with cosign
+      id-token: write
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
        with:
          fetch-depth: 0

@@ -141,12 +143,12 @@ jobs:
          AWS_ACCESS_KEY_ID: ${{ secrets.TOOLBOX_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.TOOLBOX_AWS_SECRET_ACCESS_KEY }}

-      - uses: anchore/sbom-action@c7f031d9249a826a082ea14c79d3b686a51d485a #v0.15.3
+      - uses: anchore/sbom-action@9fece9e20048ca9590af301449208b2b8861333b #v0.15.9
        continue-on-error: true
        with:
          artifact-name: sbom.spdx.json

-      - uses: 8398a7/action-slack@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
        continue-on-error: true
        with:
          status: ${{ job.status }}
@@ -13,7 +13,7 @@ jobs:
    runs-on: ubuntu-latest
    if: github.repository == 'anchore/syft' # only run for main repo
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -50,7 +50,7 @@ jobs:
          app_id: ${{ secrets.TOKEN_APP_ID }}
          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}

-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
        with:
          signoff: true
          delete-branch: true
@@ -16,7 +16,7 @@ jobs:
    runs-on: ubuntu-latest
    if: github.repository == 'anchore/syft' # only run for main repo
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -33,7 +33,7 @@ jobs:
          app_id: ${{ secrets.TOKEN_APP_ID }}
          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}

-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
        with:
          signoff: true
          delete-branch: true
@@ -45,7 +45,7 @@ jobs:
            Update CPE dictionary index based on the latest available CPE dictionary
          token: ${{ steps.generate-token.outputs.token }}

-      - uses: 8398a7/action-slack@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
        with:
          status: ${{ job.status }}
          fields: workflow,eventName,job
@@ -17,7 +17,7 @@ jobs:
    runs-on: ubuntu-latest
    if: github.repository == 'anchore/syft' # only run for main repo
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
        with:
@@ -44,7 +44,7 @@ jobs:
          app_id: ${{ secrets.TOKEN_APP_ID }}
          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}

-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
        with:
          signoff: true
          delete-branch: true
@@ -17,7 +17,7 @@ jobs:
    name: "Static analysis"
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -31,37 +31,49 @@ jobs:
    name: "Unit tests"
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap

+      - name: Restore file executable test-fixture cache
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
+        with:
+          path: syft/file/cataloger/executable/test-fixtures/elf/bin
+          key: ${{ runner.os }}-unit-file-executable-elf-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint' ) }}
+
+      - name: Restore file executable shared-info test-fixture cache
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
+        with:
+          path: syft/file/cataloger/executable/test-fixtures/shared-info/bin
+          key: ${{ runner.os }}-unit-file-executable-shared-info-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint' ) }}
+
      - name: Restore Java test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: syft/pkg/cataloger/java/test-fixtures/java-builds/packages
          key: ${{ runner.os }}-unit-java-cache-${{ hashFiles( 'syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint' ) }}

      - name: Restore RPM test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: syft/pkg/cataloger/redhat/test-fixtures/rpms
          key: ${{ runner.os }}-unit-rpm-cache-${{ hashFiles( 'syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint' ) }}

      - name: Restore go binary test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: syft/pkg/cataloger/golang/test-fixtures/archs/binaries
          key: ${{ runner.os }}-unit-go-binaries-cache-${{ hashFiles( 'syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint' ) }}

      - name: Restore binary cataloger test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/bin
          key: ${{ runner.os }}-unit-binary-cataloger-cache-${{ hashFiles( 'syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint' ) }}

      - name: Restore Kernel test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: syft/pkg/cataloger/kernel/test-fixtures/cache
          key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
@@ -75,7 +87,7 @@ jobs:
    name: "Integration tests"
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -84,10 +96,10 @@ jobs:
        run: make validate-cyclonedx-schema

      - name: Restore integration test cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
-          path: ${{ github.workspace }}/test/integration/test-fixtures/cache
-          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('test/integration/test-fixtures/cache.fingerprint') }}
+          path: ${{ github.workspace }}/cmd/syft/internal/test/integration/test-fixtures/cache
+          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('/cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint') }}

      - name: Run integration tests
        run: make integration
@@ -97,7 +109,7 @@ jobs:
    name: "Build snapshot artifacts"
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -110,7 +122,7 @@ jobs:
      # why not use actions/upload-artifact? It is very slow (3 minutes to upload ~600MB of data, vs 10 seconds with this approach).
      # see https://github.com/actions/upload-artifact/issues/199 for more info
      - name: Upload snapshot artifacts
-        uses: actions/cache/save@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache/save@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          # we need to preserve the snapshot data itself as well as the task data that confirms if the
          # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
@@ -127,14 +139,14 @@ jobs:
    needs: [Build-Snapshot-Artifacts]
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap

      - name: Download snapshot build
        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: |
            snapshot
@@ -152,7 +164,7 @@ jobs:

      - name: Restore install.sh test image cache
        id: install-test-image-cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: ${{ github.workspace }}/test/install/cache
          key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
@@ -175,7 +187,7 @@ jobs:
    needs: [Build-Snapshot-Artifacts]
    runs-on: macos-latest
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap
@@ -187,7 +199,7 @@ jobs:

      - name: Download snapshot build
        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: |
            snapshot
@@ -202,7 +214,7 @@ jobs:

      - name: Restore docker image cache for compare testing
        id: mac-compare-testing-cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: image.tar
          key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
@@ -220,20 +232,20 @@ jobs:
    needs: [Build-Snapshot-Artifacts]
    runs-on: ubuntu-20.04
    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2

      - name: Bootstrap environment
        uses: ./.github/actions/bootstrap

      - name: Restore CLI test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: ${{ github.workspace }}/test/cli/test-fixtures/cache
          key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}

      - name: Download snapshot build
        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
        with:
          path: |
            snapshot
@@ -32,7 +32,6 @@ VERSION
 /test/results
 coverage.txt
 *.log
-test/integration/test-fixtures/**/go.sum

 # probable archives
 .images
@@ -247,3 +247,28 @@ docker_manifests:
      - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
      - ghcr.io/anchore/syft:{{.Tag}}-s390x
+
+sboms:
+  - artifacts: archive
+    # this is relative to the snapshot/dist directory, not the root of the repo
+    cmd: ../.tool/syft
+    documents:
+      - "{{ .Binary }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}.sbom"
+    args:
+      - "scan"
+      - "$artifact"
+      - "--output"
+      - "json=$document"
+
+signs:
+  - cmd: .tool/cosign
+    signature: "${artifact}.sig"
+    certificate: "${artifact}.pem"
+    args:
+      - "sign-blob"
+      - "--oidc-issuer=https://token.actions.githubusercontent.com"
+      - "--output-certificate=${certificate}"
+      - "--output-signature=${signature}"
+      - "${artifact}"
+      - "--yes"
+    artifacts: checksum
@@ -234,7 +234,7 @@ rough outline how that works:
  the `/test` directory. These tests should focus on correctness of functionality in depth. % test coverage metrics 
  only considers unit tests and no other forms of testing.

- `integration`: located within `test/integration`, these tests focus on the behavior surfaced by the common library 
+- `integration`: located within `cmd/syft/internal/test/integration`, these tests focus on the behavior surfaced by the common library 
  entrypoints from the `syft` package and make light assertions about the results surfaced. Additionally, these tests
  tend to make diversity assertions for enum-like objects, ensuring that as enum values are added to a definition
  that integration tests will automatically fail if no test attempts to use that enum value. For more details see 
@@ -54,6 +54,7 @@ For commercial support options with Syft or Grype, please [contact Anchore](http
 - Ruby (gem)
 - Rust (cargo.lock)
 - Swift (cocoapods, swift-package-manager)
+- Wordpress plugins

 ## Installation

@@ -121,7 +122,8 @@ syft <image> --scope all-layers

 ### Supported sources

-Syft can generate an SBOM from a variety of sources:
+Syft can generate an SBOM from a variety of sources including images, files, directories, and archives. Syft will attempt to
+determine the type of source based on provided input, for example:

 ```bash
 # catalog a container image archive (from the result of `docker image save ...`, `podman save ...`, or `skopeo copy` commands)
@@ -134,26 +136,24 @@ syft path/to/image.sif
 syft path/to/dir
 ```

-Sources can be explicitly provided with a scheme:
+To explicitly specify the source behavior, use the `--from` flag. Allowable options are:

 ```
-docker:yourrepo/yourimage:tag            use images from the Docker daemon
-podman:yourrepo/yourimage:tag            use images from the Podman daemon
-containerd:yourrepo/yourimage:tag        use images from the Containerd daemon
-docker-archive:path/to/yourimage.tar     use a tarball from disk for archives created from "docker save"
-oci-archive:path/to/yourimage.tar        use a tarball from disk for OCI archives (from Skopeo or otherwise)
-oci-dir:path/to/yourimage                read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
-singularity:path/to/yourimage.sif        read directly from a Singularity Image Format (SIF) container on disk
-dir:path/to/yourproject                  read directly from a path on disk (any directory)
-file:path/to/yourproject/file            read directly from a path on disk (any single file)
-registry:yourrepo/yourimage:tag          pull image directly from a registry (no container runtime required)
+docker             use images from the Docker daemon
+podman             use images from the Podman daemon
+containerd         use images from the Containerd daemon
+docker-archive     use a tarball from disk for archives created from "docker save"
+oci-archive        use a tarball from disk for OCI archives (from Skopeo or otherwise)
+oci-dir            read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
+singularity        read directly from a Singularity Image Format (SIF) container on disk
+dir                read directly from a path on disk (any directory)
+file               read directly from a path on disk (any single file)
+registry           pull image directly from a registry (no container runtime required)
 ```
+If a source is not provided and Syft identifies the input as a potential image reference, Syft will attempt to resolve it using:
+the Docker, Podman, and Containerd daemons followed by direct registry access, in that order.

-If an image source is not provided and cannot be detected from the given reference it is assumed the image should be pulled from the Docker daemon.
-If docker is not present, then the Podman daemon is attempted next, followed by reaching out directly to the image registry last.
-
-
-This default behavior can be overridden with the `default-image-pull-source` configuration option (See [Configuration](https://github.com/anchore/syft#configuration) for more details).
+This default behavior can be overridden with the `default-image-pull-source` configuration option (See [Configuration](#configuration) for more details).


 ### File selection
@@ -228,12 +228,12 @@ syft <a directory> --select-catalogers "python"

 Use the default set of catalogers and add a cataloger to the set:
 ```bash
-syft ... --catalogers "+sbom-cataloger"
+syft ... --select-catalogers "+sbom-cataloger"
 ```

 Use the default set of catalogers but remove any catalogers that deal with RPMs:
 ```bash
-syft ... --catalogers "-rpm"
+syft ... --select-catalogers "-rpm"
 ```

 Only scan with catalogers that:
@@ -305,7 +305,7 @@ Where the `formats` available are:

 ## Using templates

-Syft lets you define custom output formats, using [Go templates](https://pkg.go.dev/text/template). Here's how it works:
+Syft lets you define custom output formats, using [Go templates](https://pkg.go.dev/text/template) relative to the Syft JSON output. Here's how it works:

 - Define your format as a Go template, and save this template as a file.

@@ -319,9 +319,9 @@ Syft lets you define custom output formats, using [Go templates](https://pkg.go.

 Here's what the `csv.tmpl` file might look like:
 ```gotemplate
-"Package","Version Installed","Found by"
-{{- range .Artifacts}}
-"{{.Name}}","{{.Version}}","{{.FoundBy}}"
+"Package","Version Installed", "Found by"
+{{- range .artifacts}}
+"{{.name}}","{{.version}}","{{.foundBy}}"
 {{- end}}
 ```

@@ -338,6 +338,9 @@ Syft also includes a vast array of utility templating functions from [sprig](htt

 Lastly, Syft has custom templating functions defined in `./syft/format/template/encoder.go` to help parse the passed-in JSON structs.

+> [!NOTE]
+> If you have templates being used before Syft v0.102.0 that are no longer working. This is because templating keys were relative to the internal go structs before this version whereas now the keys are relative to the Syft JSON output. To get the legacy behavior back you can set the `format.template.legacy` option to `true` in your configuration.
+
 ## Multiple outputs

 Syft can also output _multiple_ files in differing formats by appending
@@ -502,19 +505,20 @@ Configuration options (example values are the default):

 ```yaml
 # the output format(s) of the SBOM report (options: syft-table, syft-text, syft-json, spdx-json, ...)
-# same as -o, --output, and SYFT_OUTPUT env var
 # to specify multiple output files in differing formats, use a list:
 # output:
 #   - "syft-json=<syft-json-output-file>"
 #   - "spdx-json=<spdx-json-output-file>"
-output: "syft-table"
+# SYFT_OUTPUT env var / -o, --output flags
+output: 
+  - "syft-table"

 # suppress all output (except for the SBOM report)
-# same as -q ; SYFT_QUIET env var
+# SYFT_QUIET env var / -q flag
 quiet: false

 # enable/disable checking for application updates on startup
-# same as SYFT_CHECK_FOR_APP_UPDATE env var
+# SYFT_CHECK_FOR_APP_UPDATE env var 
 check-for-app-update: true

 # maximum number of workers used to process the list of package catalogers in parallel
@@ -524,15 +528,11 @@ parallelism: 1
 # exclude:
 #   - "/etc/**"
 #   - "./out/**/*.json"
-# same as --exclude ; SYFT_EXCLUDE env var
+# SYFT_EXCLUDE env var / --exclude flag
 exclude: []

-# allows users to exclude synthetic binary packages from the sbom
-# these packages are removed if an overlap with a non-synthetic package is found
-exclude-binary-overlap-by-ownership: true
-
 # os and/or architecture to use when referencing container images (e.g. "windows/armv6" or "arm64")
-# same as --platform; SYFT_PLATFORM env var
+# SYFT_PLATFORM env var / --platform flag
 platform: ""

 # the search space to look for file and package data (options: all-layers, squashed)
@@ -541,48 +541,24 @@ scope: "squashed"

 # set the list of package catalogers to use when generating the SBOM
 # default = empty (cataloger set determined automatically by the source type [image or file/directory])
-# catalogers:
-#   - alpm-db-cataloger
-#   - apkdb-cataloger
-#   - binary-cataloger
-#   - cargo-auditable-binary-cataloger
-#   - cocoapods-cataloger
-#   - conan-cataloger
-#   - dartlang-lock-cataloger
-#   - dotnet-deps-cataloger
-#   - dotnet-portable-executable-cataloger
-#   - dpkg-db-cataloger
-#   - elixir-mix-lock-cataloger
-#   - erlang-rebar-lock-cataloger
-#   - go-module-file-cataloger
-#   - go-module-binary-cataloger
-#   - graalvm-native-image-cataloger
-#   - haskell-cataloger
-#   - java-cataloger
-#   - java-gradle-lockfile-cataloger
-#   - java-pom-cataloger
-#   - javascript-lock-cataloger
-#   - javascript-package-cataloger
-#   - linux-kernel-cataloger
-#   - nix-store-cataloger
-#   - php-composer-installed-cataloger
-#   - php-composer-lock-cataloger
-#   - portage-cataloger
-#   - python-package-cataloger
-#   - python-installed-package-cataloger
-#   - rpm-db-cataloger
-#   - rpm-archive-cataloger
-#   - ruby-gemfile-cataloger
-#   - ruby-installed-gemspec-cataloger
-#   - rust-cargo-lock-cataloger
-#   - sbom-cataloger
-#   - spm-cataloger
+# Use `syft cataloger list` for a list of catalogers you can specify
+# DEPRECATED: please use default-catalogers and select-catalogers configuration options instead
+# SYFT_CATALOGERS env var / --catalogers flag
 catalogers:

+# set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)
+# SYFT_DEFAULT_CATALOGERS env var / --override-default-catalogers flag
+default-catalogers: []
+
+# add, remove, and filter the catalogers to be used
+# SYFT_SELECT_CATALOGERS env var / --select-catalogers flag;
+select-catalogers: []
+
 # all format configuration
 format:
 
  # default value for all formats that support the "pretty" option (default is unset)
+  # SYFT_FORMAT_PRETTY env var
  pretty: 

  # all syft-json format options
@@ -590,6 +566,7 @@ format:

    # include space indention and newlines (inherits default value from 'format.pretty' or 'false' if parent is unset)
    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+    # SYFT_FORMAT_JSON_PRETTY env var
    pretty: false
    
    # transform any syft-json output to conform to an approximation of the v11.0.1 schema. This includes:
@@ -599,21 +576,30 @@ format:
    # that output might not strictly be json schema v11 compliant, however, for consumers that require time to port
    # over to the final syft 1.0 json output this option can be used to ease the transition.
    #
-    # Note: long term support for this option is not guaranteed.
+    # Note: long term support for this option is not guaranteed (it may change or break at any time).
+    # SYFT_FORMAT_JSON_LEGACY env var
    legacy: false

  # all template format options
  template:
    # path to the template file to use when rendering the output with the `template` output format. 
    # Note that all template paths are based on the current syft-json schema.
-    # same as -t ; SYFT_TEMPLATE_PATH env var
+    # SYFT_FORMAT_TEMPLATE_PATH env var / -t flag 
    path: ""
+    
+    # if true, uses the go structs for the syft-json format for templating. 
+    # if false, uses the syft-json output for templating (which follows the syft JSON schema exactly).
+    #
+    # Note: long term support for this option is not guaranteed (it may change or break at any time).
+    # SYFT_FORMAT_TEMPLATE_LEGACY env var
+    legacy: false

  # all spdx-json format options
  spdx-json:

    # include space indention and newlines
    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+    # SYFT_FORMAT_SPDX_JSON_PRETTY env var
    pretty: false

  # all cyclonedx-json format options
@@ -621,6 +607,7 @@ format:

     # include space indention and newlines
     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+     # SYFT_FORMAT_CYCLONEDX_JSON_PRETTY env var
     pretty: false

  # all cyclonedx-xml format options
@@ -628,6 +615,7 @@ format:

     # include space indention
     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+     # SYFT_FORMAT_CYCLONEDX_XML_PRETTY env var
     pretty: false


@@ -636,16 +624,17 @@ file:
   metadata: 
      # select which files should be captured by the file-metadata cataloger and included in the SBOM. 
      # Options include:
-      #  - "all-files": capture all files from the search space
-      #  - "owned-files": capture only files owned by packages
-      #  - "unowned-files": capture only files not owned by packages
-      #  - "no-files", "": do not capture any files
+      #  - "all": capture all files from the search space
+      #  - "owned-by-package": capture only files owned by packages
+      #  - "none", "": do not capture any files
      # SYFT_FILE_METADATA_SELECTION env var
-      selection: "owned-files"
+      selection: "owned-by-package"

      # the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
      # SYFT_FILE_METADATA_DIGESTS env var
-      digests: ["sha256"]
+      digests:
+      - "sha256"
+      - "sha1"

   # capture the contents of select files in the SBOM
   content:
@@ -674,6 +663,7 @@ package:

  # allows users to exclude synthetic binary packages from the sbom
  # these packages are removed if an overlap with a non-synthetic package is found
+  # SYFT_PACKAGE_EXCLUDE_BINARY_OVERLAP_BY_OWNERSHIP env var
  exclude-binary-overlap-by-ownership: true


@@ -701,6 +691,24 @@ golang:
   # SYFT_GOLANG_NOPROXY env var
   no-proxy: ""
  
+   # the go main module version discovered from binaries built with the go compiler will
+   # always show (devel) as the version. Use these options to control heuristics to guess
+   # a more accurate version from the binary.
+   main-module-version:
+      
+      # look for LD flags that appear to be setting a version (e.g. -X main.version=1.0.0)
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_LD_FLAGS env var
+      from-ld-flags: true
+      
+      # use the build settings (e.g. vcs.version & vcs.time) to craft a v0 pseudo version 
+      # (e.g. v0.0.0-20220308212642-53e6d0aaf6fb) when a more accurate version cannot be found otherwise.
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_BUILD_SETTINGS env var
+      from-build-settings: true
+      
+      # search for semver-like strings in the binary contents.
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_CONTENTS env var
+      from-contents: true
+  
 java:
   maven-url: "https://repo1.maven.org/maven2"
   max-parent-recursive-depth: 5
@@ -732,17 +740,23 @@ javascript:
 # configuration for the source that the SBOM is generated from (e.g. a file, directory, or container image)
 source:
  # alias name for the source
-  # SYFT_SOURCE_NAME env var; --source-name flag
+  # SYFT_SOURCE_NAME env var / --source-name flag
  name: ""
   
  # alias version for the source
-  # SYFT_SOURCE_VERSION env var; --source-version flag
+  # SYFT_SOURCE_VERSION env var / --source-version flag
  version: ""
-   
-  # options affecting the file source type
+
+  # base directory for scanning, no links will be followed above this directory, and all paths will be 
+  # reported relative to this directory
+  # SYFT_SOURCE_BASE_PATH env var
+  base-path: ''
+
+   # options affecting the file source type
  file:
    # the file digest algorithms to use on the scanned file (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-    digests: ["sha256"]
+    digests: 
+     - "sha256"

  image:
     
@@ -804,15 +818,15 @@ attest:

 log:
  # use structured logging
-  # same as SYFT_LOG_STRUCTURED env var
+  # SYFT_LOG_STRUCTURED env var
  structured: false

  # the log level; note: detailed logging suppress the ETUI
-  # same as SYFT_LOG_LEVEL env var
+  # SYFT_LOG_LEVEL env var
  level: "error"

  # location to write the log file (default is not to have a log file)
-  # same as SYFT_LOG_FILE env var
+  # SYFT_LOG_FILE env var
  file: ""
 ```

@@ -185,7 +185,7 @@ tasks:
      - fixtures
    vars:
      TEST_PKGS:
-        sh: "go list ./... | grep -v {{ .OWNER }}/{{ .PROJECT }}/test | tr '\n' ' '"
+        sh: "go list ./... | grep -v {{ .OWNER }}/{{ .PROJECT }}/test | grep -v {{ .OWNER }}/{{ .PROJECT }}/cmd/syft/internal/test | tr '\n' ' '"

      # unit test coverage threshold (in % coverage)
      COVERAGE_THRESHOLD: 62
@@ -197,7 +197,7 @@ tasks:
  integration:
    desc: Run integration tests
    cmds:
-      - "go test -v ./test/integration"
+      - "go test -v ./cmd/syft/internal/test/integration"
      # exercise most of the CLI with the data race detector
      - "go run -race cmd/syft/main.go alpine:latest"

@@ -265,7 +265,9 @@ tasks:
  fingerprints:
    desc: Generate test fixture fingerprints
    generates:
-      - test/integration/test-fixtures/cache.fingerprint
+      - cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint
+      - syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint
+      - syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint
      - syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint
      - syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint
      - syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint
@@ -274,19 +276,22 @@ tasks:
      - test/install/cache.fingerprint
      - test/cli/test-fixtures/cache.fingerprint
    cmds:
+      # for EXECUTABLE unit test fixtures
+      - "cd syft/file/cataloger/executable/test-fixtures/elf && make cache.fingerprint"
+      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make cache.fingerprint"
      # for IMAGE integration test fixtures
-      - "cd test/integration/test-fixtures && make cache.fingerprint"
-      # for BINARY test fixtures
+      - "cd cmd/syft/internal/test/integration/test-fixtures && make cache.fingerprint"
+      # for BINARY unit test fixtures
      - "cd syft/pkg/cataloger/binary/test-fixtures && make cache.fingerprint"
-      # for JAVA BUILD test fixtures
+      # for JAVA BUILD unit test fixtures
      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make cache.fingerprint"
-      # for GO BINARY test fixtures
+      # for GO BINARY unit test fixtures
      - "cd syft/pkg/cataloger/golang/test-fixtures/archs && make binaries.fingerprint"
-      # for RPM test fixtures
+      # for RPM unit test fixtures
      - "cd syft/pkg/cataloger/redhat/test-fixtures && make rpms.fingerprint"
-      # for Kernel test fixtures
+      # for Kernel unit test fixtures
      - "cd syft/pkg/cataloger/kernel/test-fixtures && make cache.fingerprint"
-      # for INSTALL integration test fixtures
+      # for INSTALL test fixtures
      - "cd test/install && make cache.fingerprint"
      # for CLI test fixtures
      - "cd test/cli/test-fixtures && make cache.fingerprint"
@@ -294,6 +299,8 @@ tasks:
  fixtures:
    desc: Generate test fixtures
    cmds:
+      - "cd syft/file/cataloger/executable/test-fixtures/elf && make"
+      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make"
      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make"
      - "cd syft/pkg/cataloger/redhat/test-fixtures && make"
      - "cd syft/pkg/cataloger/binary/test-fixtures && make"
@@ -8,13 +8,8 @@ import (
 	"github.com/spf13/cobra"

 	"github.com/anchore/clio"
-	"github.com/anchore/stereoscope"
-	"github.com/anchore/syft/cmd/syft/cli/commands"
-	handler "github.com/anchore/syft/cmd/syft/cli/ui"
-	"github.com/anchore/syft/cmd/syft/internal/ui"
-	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/internal/redact"
+	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/commands"
 )

 // Application constructs the `syft packages` command and aliases the root command to `syft packages`.
@@ -34,44 +29,7 @@ func Command(id clio.Identification) *cobra.Command {
 }

 func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Command) {
-	clioCfg := clio.NewSetupConfig(id).
-		WithGlobalConfigFlag().   // add persistent -c <path> for reading an application config from
-		WithGlobalLoggingFlags(). // add persistent -v and -q flags tied to the logging config
-		WithConfigInRootHelp().   // --help on the root command renders the full application config in the help text
-		WithUIConstructor(
-			// select a UI based on the logging configuration and state of stdin (if stdin is a tty)
-			func(cfg clio.Config) ([]clio.UI, error) {
-				noUI := ui.None(out, cfg.Log.Quiet)
-				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
-					return []clio.UI{noUI}, nil
-				}
-
-				return []clio.UI{
-					ui.New(out, cfg.Log.Quiet,
-						handler.New(handler.DefaultHandlerConfig()),
-					),
-					noUI,
-				}, nil
-			},
-		).
-		WithInitializers(
-			func(state *clio.State) error {
-				// clio is setting up and providing the bus, redact store, and logger to the application. Once loaded,
-				// we can hoist them into the internal packages for global use.
-				stereoscope.SetBus(state.Bus)
-				bus.Set(state.Bus)
-
-				redact.Set(state.RedactStore)
-
-				log.Set(state.Logger)
-				stereoscope.SetLogger(state.Logger)
-
-				return nil
-			},
-		).
-		WithPostRuns(func(state *clio.State, err error) {
-			stereoscope.Cleanup()
-		})
+	clioCfg := internal.AppClioSetupConfig(id, out)

 	app := clio.New(*clioCfg)

@@ -1,129 +0,0 @@
-package options
-
-import (
-	"fmt"
-
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/syft/syft/format/cyclonedxjson"
-	"github.com/anchore/syft/syft/format/cyclonedxxml"
-	"github.com/anchore/syft/syft/format/github"
-	"github.com/anchore/syft/syft/format/spdxjson"
-	"github.com/anchore/syft/syft/format/spdxtagvalue"
-	"github.com/anchore/syft/syft/format/syftjson"
-	"github.com/anchore/syft/syft/format/table"
-	"github.com/anchore/syft/syft/format/template"
-	"github.com/anchore/syft/syft/format/text"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-var _ clio.PostLoader = (*Format)(nil)
-
-// Format contains all user configuration for output formatting.
-type Format struct {
-	Pretty        *bool               `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-	Template      FormatTemplate      `yaml:"template" json:"template" mapstructure:"template"`
-	SyftJSON      FormatSyftJSON      `yaml:"json" json:"json" mapstructure:"json"`
-	SPDXJSON      FormatSPDXJSON      `yaml:"spdx-json" json:"spdx-json" mapstructure:"spdx-json"`
-	CyclonedxJSON FormatCyclonedxJSON `yaml:"cyclonedx-json" json:"cyclonedx-json" mapstructure:"cyclonedx-json"`
-	CyclonedxXML  FormatCyclonedxXML  `yaml:"cyclonedx-xml" json:"cyclonedx-xml" mapstructure:"cyclonedx-xml"`
-}
-
-func (o *Format) PostLoad() error {
-	o.SyftJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SyftJSON.Pretty)
-	o.SPDXJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SPDXJSON.Pretty)
-	o.CyclonedxJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxJSON.Pretty)
-	o.CyclonedxXML.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxXML.Pretty)
-
-	return nil
-}
-
-func DefaultFormat() Format {
-	return Format{
-		Template:      DefaultFormatTemplate(),
-		SyftJSON:      DefaultFormatJSON(),
-		SPDXJSON:      DefaultFormatSPDXJSON(),
-		CyclonedxJSON: DefaultFormatCyclonedxJSON(),
-		CyclonedxXML:  DefaultFormatCyclonedxXML(),
-	}
-}
-
-func (o *Format) Encoders() ([]sbom.FormatEncoder, error) {
-	// setup all encoders based on the configuration
-	var list encoderList
-
-	// in the future there will be application configuration options that can be used to set the default output format
-	list.addWithErr(template.ID)(o.Template.formatEncoders())
-	list.addWithErr(syftjson.ID)(o.SyftJSON.formatEncoders())
-	list.add(table.ID)(table.NewFormatEncoder())
-	list.add(text.ID)(text.NewFormatEncoder())
-	list.add(github.ID)(github.NewFormatEncoder())
-	list.addWithErr(cyclonedxxml.ID)(o.CyclonedxXML.formatEncoders())
-	list.addWithErr(cyclonedxjson.ID)(o.CyclonedxJSON.formatEncoders())
-	list.addWithErr(spdxjson.ID)(o.SPDXJSON.formatEncoders())
-	list.addWithErr(spdxtagvalue.ID)(spdxTagValueEncoders())
-
-	return list.encoders, list.err
-}
-
-// TODO: when application configuration is made for this format then this should be ported to the options object
-// that is created for that configuration (as done with the template output option)
-func spdxTagValueEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range spdxtagvalue.SupportedVersions() {
-		enc, err := spdxtagvalue.NewFormatEncoderWithConfig(spdxtagvalue.EncoderConfig{Version: v})
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-type encoderList struct {
-	encoders []sbom.FormatEncoder
-	err      error
-}
-
-func (l *encoderList) addWithErr(name sbom.FormatID) func([]sbom.FormatEncoder, error) {
-	return func(encs []sbom.FormatEncoder, err error) {
-		if err != nil {
-			l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: %w", name, err))
-			return
-		}
-		for _, enc := range encs {
-			if enc == nil {
-				l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: nil encoder returned", name))
-				continue
-			}
-			l.encoders = append(l.encoders, enc)
-		}
-	}
-}
-
-func (l *encoderList) add(name sbom.FormatID) func(...sbom.FormatEncoder) {
-	return func(encs ...sbom.FormatEncoder) {
-		for _, enc := range encs {
-			if enc == nil {
-				l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: nil encoder returned", name))
-				continue
-			}
-			l.encoders = append(l.encoders, enc)
-		}
-	}
-}
-
-func multiLevelOption[T any](defaultValue T, option ...*T) *T {
-	result := defaultValue
-	for _, opt := range option {
-		if opt != nil {
-			result = *opt
-		}
-	}
-	return &result
-}
@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/cyclonedxjson"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatCyclonedxJSON struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatCyclonedxJSON() FormatCyclonedxJSON {
-	return FormatCyclonedxJSON{}
-}
-
-func (o FormatCyclonedxJSON) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range cyclonedxjson.SupportedVersions() {
-		enc, err := cyclonedxjson.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatCyclonedxJSON) buildConfig(version string) cyclonedxjson.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return cyclonedxjson.EncoderConfig{
-		Version: version,
-		Pretty:  pretty,
-	}
-}
@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/cyclonedxxml"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatCyclonedxXML struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatCyclonedxXML() FormatCyclonedxXML {
-	return FormatCyclonedxXML{}
-}
-
-func (o FormatCyclonedxXML) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range cyclonedxxml.SupportedVersions() {
-		enc, err := cyclonedxxml.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatCyclonedxXML) buildConfig(version string) cyclonedxxml.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return cyclonedxxml.EncoderConfig{
-		Version: version,
-		Pretty:  pretty,
-	}
-}
@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/spdxjson"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatSPDXJSON struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatSPDXJSON() FormatSPDXJSON {
-	return FormatSPDXJSON{}
-}
-
-func (o FormatSPDXJSON) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range spdxjson.SupportedVersions() {
-		enc, err := spdxjson.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatSPDXJSON) buildConfig(v string) spdxjson.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return spdxjson.EncoderConfig{
-		Version: v,
-		Pretty:  pretty,
-	}
-}
@@ -1,9 +0,0 @@
-package options
-
-type golangConfig struct {
-	SearchLocalModCacheLicenses bool   `json:"search-local-mod-cache-licenses" yaml:"search-local-mod-cache-licenses" mapstructure:"search-local-mod-cache-licenses"`
-	LocalModCacheDir            string `json:"local-mod-cache-dir" yaml:"local-mod-cache-dir" mapstructure:"local-mod-cache-dir"`
-	SearchRemoteLicenses        bool   `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
-	Proxy                       string `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
-	NoProxy                     string `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
-}
@@ -0,0 +1,55 @@
+package internal
+
+import (
+	"io"
+	"os"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/stereoscope"
+	ui2 "github.com/anchore/syft/cmd/syft/cli/ui"
+	"github.com/anchore/syft/cmd/syft/internal/ui"
+	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/redact"
+)
+
+func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig {
+	clioCfg := clio.NewSetupConfig(id).
+		WithGlobalConfigFlag().   // add persistent -c <path> for reading an application config from
+		WithGlobalLoggingFlags(). // add persistent -v and -q flags tied to the logging config
+		WithConfigInRootHelp().   // --help on the root command renders the full application config in the help text
+		WithUIConstructor(
+			// select a UI based on the logging configuration and state of stdin (if stdin is a tty)
+			func(cfg clio.Config) ([]clio.UI, error) {
+				noUI := ui.None(out, cfg.Log.Quiet)
+				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
+					return []clio.UI{noUI}, nil
+				}
+
+				return []clio.UI{
+					ui.New(out, cfg.Log.Quiet,
+						ui2.New(ui2.DefaultHandlerConfig()),
+					),
+					noUI,
+				}, nil
+			},
+		).
+		WithInitializers(
+			func(state *clio.State) error {
+				// clio is setting up and providing the bus, redact store, and logger to the application. Once loaded,
+				// we can hoist them into the internal packages for global use.
+				stereoscope.SetBus(state.Bus)
+				bus.Set(state.Bus)
+
+				redact.Set(state.RedactStore)
+
+				log.Set(state.Logger)
+				stereoscope.SetLogger(state.Logger)
+				return nil
+			},
+		).
+		WithPostRuns(func(_ *clio.State, _ error) {
+			stereoscope.Cleanup()
+		})
+	return clioCfg
+}
@@ -13,7 +13,8 @@ import (
 	"github.com/wagoodman/go-progress"

 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/stereoscope"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/bus"
@@ -26,7 +27,6 @@ import (
 	"github.com/anchore/syft/syft/format/spdxtagvalue"
 	"github.com/anchore/syft/syft/format/syftjson"
 	"github.com/anchore/syft/syft/sbom"
-	"github.com/anchore/syft/syft/source"
 )

 const (
@@ -42,7 +42,7 @@ type attestOptions struct {
 	options.Output      `yaml:",inline" mapstructure:",squash"`
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 	options.Catalog     `yaml:",inline" mapstructure:",squash"`
-	options.Attest      `yaml:",inline" mapstructure:",squash"`
+	Attest              options.Attest `yaml:"attest" mapstructure:"attest"`
 }

 func Attest(app clio.Application) *cobra.Command {
@@ -247,7 +247,11 @@ func predicateType(outputName string) string {
 }

 func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opts *options.Catalog, userInput string) (*sbom.SBOM, error) {
-	src, err := getSource(opts, userInput, onlyContainerImages)
+	if len(opts.From) > 1 || (len(opts.From) == 1 && opts.From[0] != stereoscope.RegistryTag) {
+		return nil, fmt.Errorf("attest requires use of an OCI registry directly, one or more of the specified sources is unsupported: %v", opts.From)
+	}
+
+	src, err := getSource(ctx, opts, userInput, stereoscope.RegistryTag)

 	if err != nil {
 		return nil, err
@@ -273,13 +277,6 @@ func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opt
 	return s, nil
 }

-func onlyContainerImages(d *source.Detection) error {
-	if !d.IsContainerImage() {
-		return fmt.Errorf("attestations are only supported for oci images at this time")
-	}
-	return nil
-}
-
 func commandExists(cmd string) bool {
 	_, err := exec.LookPath(cmd)
 	return err == nil
@@ -4,17 +4,22 @@ import (
 	"bytes"
 	"context"
 	"fmt"
+	"io"
 	"os/exec"
 	"regexp"
 	"strings"
 	"testing"

+	"github.com/google/go-cmp/cmp"
 	"github.com/scylladb/go-set/strset"
+	"github.com/spf13/cobra"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"

 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/clio/cliotestutils"
+	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
@@ -267,3 +272,60 @@ func Test_buildSBOMForAttestation(t *testing.T) {
 		})
 	}
 }
+
+func Test_attestCLIWiring(t *testing.T) {
+	id := clio.Identification{
+		Name:    "syft",
+		Version: "testing",
+	}
+	cfg := internal.AppClioSetupConfig(id, io.Discard)
+	tests := []struct {
+		name          string
+		assertionFunc func(*testing.T, *cobra.Command, []string, ...any)
+		wantOpts      attestOptions
+		args          []string
+		env           map[string]string
+	}{
+		{
+			name:          "key flag is accepted",
+			args:          []string{"some-image:some-tag", "--key", "some-cosign-key.key"},
+			assertionFunc: hasAttestOpts(options.Attest{Key: "some-cosign-key.key"}),
+		},
+		{
+			name: "key password is read from env",
+			args: []string{"some-image:some-tag", "--key", "cosign.key"},
+			env: map[string]string{
+				"SYFT_ATTEST_PASSWORD": "some-password",
+			},
+			assertionFunc: hasAttestOpts(options.Attest{
+				Key:      "cosign.key",
+				Password: "some-password",
+			}),
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.env != nil {
+				for k, v := range tt.env {
+					t.Setenv(k, v)
+				}
+			}
+			app := cliotestutils.NewApplication(t, cfg, tt.assertionFunc)
+			cmd := Attest(app)
+			cmd.SetArgs(tt.args)
+			err := cmd.Execute()
+			assert.NoError(t, err)
+		})
+	}
+}
+
+func hasAttestOpts(wantOpts options.Attest) cliotestutils.AssertionFunc {
+	return func(t *testing.T, _ *cobra.Command, _ []string, cfgs ...any) {
+		assert.Equal(t, len(cfgs), 1)
+		attestOpts, ok := cfgs[0].(*attestOptions)
+		require.True(t, ok)
+		if d := cmp.Diff(wantOpts, attestOpts.Attest); d != "" {
+			t.Errorf("mismatched attest options (-want +got):\n%s", d)
+		}
+	}
+}
@@ -46,7 +46,7 @@ func CatalogerList(app clio.Application) *cobra.Command {
 	return app.SetupCommand(&cobra.Command{
 		Use:   "list [OPTIONS]",
 		Short: "List available catalogers",
-		RunE: func(cmd *cobra.Command, args []string) error {
+		RunE: func(_ *cobra.Command, _ []string) error {
 			return runCatalogerList(opts)
 		},
 	}, opts)
@@ -0,0 +1,20 @@
+package commands
+
+import (
+	"os"
+	"testing"
+
+	gologgerredact "github.com/anchore/go-logger/adapter/redact"
+	"github.com/anchore/syft/internal/redact"
+)
+
+func TestMain(m *testing.M) {
+	// Initialize global state needed to test clio/cobra commands directly
+	// Should be kept minimal.
+
+	// Initialize redact store once for all tests in the commands package
+	// Redact store must be wired up here because syft will panic unless
+	// a redact store is wired up exactly once
+	redact.Set(gologgerredact.NewStore())
+	os.Exit(m.Run())
+}
@@ -8,7 +8,7 @@ import (
 	"github.com/spf13/cobra"

 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
@@ -47,7 +47,7 @@ func Convert(app clio.Application) *cobra.Command {
 		}),
 		Args:    validateConvertArgs,
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(cmd *cobra.Command, args []string) error {
+		RunE: func(_ *cobra.Command, args []string) error {
 			restoreStdout := ui.CaptureStdoutToTraceLog()
 			defer restoreStdout()

@@ -13,8 +13,10 @@ import (
 	"gopkg.in/yaml.v3"

 	"github.com/anchore/clio"
+	"github.com/anchore/go-collections"
+	"github.com/anchore/stereoscope"
 	"github.com/anchore/stereoscope/pkg/image"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/bus"
@@ -24,6 +26,7 @@ import (
 	"github.com/anchore/syft/syft"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
+	"github.com/anchore/syft/syft/source/sourceproviders"
 )

 const (
@@ -132,7 +135,7 @@ func (o *scanOptions) validateLegacyOptionsNotUsed() error {
 	}

 	if legacy.ExcludeBinaryOverlapByOwnership != nil {
-		return fmt.Errorf("the config file option 'exclude-binary-overlap-by-ownership' has been removed, please use 'relationships.exclude-binary-packages-with-file-ownership-overlap' instead")
+		return fmt.Errorf("the config file option 'exclude-binary-overlap-by-ownership' has been removed, please use 'package.exclude-binary-overlap-by-ownership' instead")
 	}

 	if legacy.BasePath != nil {
@@ -162,14 +165,23 @@ func validateArgs(cmd *cobra.Command, args []string, error string) error {
 	return cobra.MaximumNArgs(1)(cmd, args)
 }

-// nolint:funlen
 func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, userInput string) error {
 	writer, err := opts.SBOMWriter()
 	if err != nil {
 		return err
 	}

-	src, err := getSource(&opts.Catalog, userInput)
+	sources := opts.From
+	if len(sources) == 0 {
+		// extract a scheme if it matches any provider tag; this is a holdover for compatibility, using the --from flag is recommended
+		explicitSource, newUserInput := stereoscope.ExtractSchemeSource(userInput, allSourceProviderTags()...)
+		if explicitSource != "" {
+			sources = append(sources, explicitSource)
+			userInput = newUserInput
+		}
+	}
+
+	src, err := getSource(ctx, &opts.Catalog, userInput, sources...)

 	if err != nil {
 		return err
@@ -199,23 +211,21 @@ func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, use
 	return nil
 }

-func getSource(opts *options.Catalog, userInput string, filters ...func(*source.Detection) error) (source.Source, error) {
-	detection, err := source.Detect(
-		userInput,
-		source.DetectConfig{
-			DefaultImageSource: opts.Source.Image.DefaultPullSource,
-		},
-	)
-	if err != nil {
-		return nil, fmt.Errorf("could not deteremine source: %w", err)
-	}
-
-	for _, filter := range filters {
-		if err := filter(detection); err != nil {
-			return nil, err
-		}
-	}
+func getSource(ctx context.Context, opts *options.Catalog, userInput string, sources ...string) (source.Source, error) {
+	cfg := syft.DefaultGetSourceConfig().
+		WithRegistryOptions(opts.Registry.ToOptions()).
+		WithAlias(source.Alias{
+			Name:    opts.Source.Name,
+			Version: opts.Source.Version,
+		}).
+		WithExcludeConfig(source.ExcludeConfig{
+			Paths: opts.Exclusions,
+		}).
+		WithBasePath(opts.Source.BasePath).
+		WithSources(sources...).
+		WithDefaultImagePullSource(opts.Source.Image.DefaultPullSource)

+	var err error
 	var platform *image.Platform

 	if opts.Platform != "" {
@@ -223,29 +233,22 @@ func getSource(opts *options.Catalog, userInput string, filters ...func(*source.
 		if err != nil {
 			return nil, fmt.Errorf("invalid platform: %w", err)
 		}
+		cfg = cfg.WithPlatform(platform)
 	}

-	hashers, err := file.Hashers(opts.Source.File.Digests...)
+	if opts.Source.File.Digests != nil {
+		hashers, err := file.Hashers(opts.Source.File.Digests...)
+		if err != nil {
+			return nil, fmt.Errorf("invalid hash algorithm: %w", err)
+		}
+		cfg = cfg.WithDigestAlgorithms(hashers...)
+	}
+
+	src, err := syft.GetSource(ctx, userInput, cfg)
 	if err != nil {
-		return nil, fmt.Errorf("invalid hash algorithm: %w", err)
+		return nil, fmt.Errorf("could not determine source: %w", err)
 	}

-	src, err := detection.NewSource(
-		source.DetectionSourceConfig{
-			Alias: source.Alias{
-				Name:    opts.Source.Name,
-				Version: opts.Source.Version,
-			},
-			RegistryOptions: opts.Registry.ToOptions(),
-			Platform:        platform,
-			Exclude: source.ExcludeConfig{
-				Paths: opts.Exclusions,
-			},
-			DigestAlgorithms: hashers,
-			BasePath:         opts.Source.BasePath,
-		},
-	)
-
 	if err != nil {
 		if userInput == "power-user" {
 			bus.Notify("Note: the 'power-user' command has been removed.")
@@ -445,3 +448,7 @@ func getHintPhrase(expErr task.ErrInvalidExpression) string {
 func trimOperation(x string) string {
 	return strings.TrimLeft(x, "+-")
 }
+
+func allSourceProviderTags() []string {
+	return collections.TaggedValueSet[source.Provider]{}.Join(sourceproviders.All("", nil)...).Tags()
+}
@@ -5,7 +5,7 @@ import (

 	"github.com/stretchr/testify/assert"

-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 )

 func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
@@ -29,7 +29,7 @@ func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
 		{
 			name:    "config file with exclude-binary-overlap-by-ownership legacy option",
 			cfg:     "test-fixtures/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
-			wantErr: assertErrorContains("relationships.exclude-binary-packages-with-file-ownership-overlap"),
+			wantErr: assertErrorContains("package.exclude-binary-overlap-by-ownership"),
 		},
 		{
 			name:    "config file with file string legacy option",
@@ -11,8 +11,8 @@ import (

 	"github.com/anchore/clio"
 	hashiVersion "github.com/anchore/go-version"
-	"github.com/anchore/syft/cmd/syft/cli/options"
 	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/event"
@@ -28,7 +28,7 @@ var latestAppVersionURL = struct {
 }

 func applicationUpdateCheck(id clio.Identification, check *options.UpdateCheck) func(cmd *cobra.Command, args []string) error {
-	return func(cmd *cobra.Command, args []string) error {
+	return func(_ *cobra.Command, _ []string) error {
 		if check.CheckForAppUpdate {
 			checkForApplicationUpdate(id)
 		}
@@ -4,6 +4,8 @@ import (
 	"github.com/anchore/clio"
 )

+var _ clio.FlagAdder = (*Attest)(nil)
+
 type Attest struct {
 	// IMPORTANT: do not show the attestation key/password in any YAML/JSON output (sensitive information)
 	Key      secret `yaml:"key" json:"key" mapstructure:"key"`
@@ -12,6 +14,6 @@ type Attest struct {

 var _ clio.FlagAdder = (*Attest)(nil)

-func (o Attest) AddFlags(flags clio.FlagSet) {
+func (o *Attest) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP((*string)(&o.Key), "key", "k", "the key to use for the attestation")
 }
@@ -15,6 +15,7 @@ import (
 	"github.com/anchore/syft/syft/cataloging"
 	"github.com/anchore/syft/syft/cataloging/filecataloging"
 	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
+	"github.com/anchore/syft/syft/file/cataloger/executable"
 	"github.com/anchore/syft/syft/file/cataloger/filecontent"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
 	"github.com/anchore/syft/syft/pkg/cataloger/golang"
@@ -45,8 +46,8 @@ type Catalog struct {

 	// configuration for the source (the subject being analyzed)
 	Registry   registryConfig `yaml:"registry" json:"registry" mapstructure:"registry"`
+	From       []string       `yaml:"from" json:"from" mapstructure:"from"`
 	Platform   string         `yaml:"platform" json:"platform" mapstructure:"platform"`
-	Name       string         `yaml:"name" json:"name" mapstructure:"name"` // deprecated
 	Source     sourceConfig   `yaml:"source" json:"source" mapstructure:"source"`
 	Exclusions []string       `yaml:"exclude" json:"exclude" mapstructure:"exclude"`
 }
@@ -62,6 +63,7 @@ func DefaultCatalog() Catalog {
 		Scope:         source.SquashedScope.String(),
 		Package:       defaultPackageConfig(),
 		LinuxKernel:   defaultLinuxKernelConfig(),
+		Golang:        defaultGolangConfig(),
 		File:          defaultFileConfig(),
 		Relationships: defaultRelationshipsConfig(),
 		Source:        defaultSourceConfig(),
@@ -112,6 +114,10 @@ func (cfg Catalog) ToFilesConfig() filecataloging.Config {
 			Globs:              cfg.File.Content.Globs,
 			SkipFilesAboveSize: cfg.File.Content.SkipFilesAboveSize,
 		},
+		Executable: executable.Config{
+			MIMETypes: executable.DefaultConfig().MIMETypes,
+			Globs:     cfg.File.Executable.Globs,
+		},
 	}
 }

@@ -121,13 +127,19 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 		IncludeUnindexedArchives: cfg.Package.SearchUnindexedArchives,
 	}
 	return pkgcataloging.Config{
-		Binary: binary.DefaultCatalogerConfig(),
+		Binary: binary.DefaultClassifierCatalogerConfig(),
 		Golang: golang.DefaultCatalogerConfig().
 			WithSearchLocalModCacheLicenses(cfg.Golang.SearchLocalModCacheLicenses).
 			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
 			WithSearchRemoteLicenses(cfg.Golang.SearchRemoteLicenses).
 			WithProxy(cfg.Golang.Proxy).
-			WithNoProxy(cfg.Golang.NoProxy),
+			WithNoProxy(cfg.Golang.NoProxy).
+			WithMainModuleVersion(
+				golang.DefaultMainModuleVersionConfig().
+					WithFromContents(cfg.Golang.MainModuleVersion.FromContents).
+					WithFromBuildSettings(cfg.Golang.MainModuleVersion.FromBuildSettings).
+					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
+			),
 		JavaScript: javascript.DefaultCatalogerConfig().
 			WithSearchRemoteLicenses(cfg.JavaScript.SearchRemoteLicenses).
 			WithNpmBaseURL(cfg.JavaScript.NpmBaseURL),
@@ -152,6 +164,9 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP(&cfg.Scope, "scope", "s",
 		fmt.Sprintf("selection of layers to catalog, options=%v", validScopeValues))

+	flags.StringArrayVarP(&cfg.From, "from", "",
+		"specify the source behavior to use (e.g. docker, registry, oci-dir, ...)")
+
 	flags.StringVarP(&cfg.Platform, "platform", "",
 		"an optional platform specifier for container image sources (e.g. 'linux/arm64', 'linux/arm64/v8', 'arm64', 'linux')")

@@ -175,14 +190,6 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringArrayVarP(&cfg.SelectCatalogers, "select-catalogers", "",
 		"add, remove, and filter the catalogers to be used")

-	flags.StringVarP(&cfg.Source.Name, "name", "",
-		"set the name of the target being analyzed")
-
-	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
-		flagSet := pfp.PFlagSet()
-		flagSet.Lookup("name").Deprecated = "use: source-name"
-	}
-
 	flags.StringVarP(&cfg.Source.Name, "source-name", "",
 		"set the name of the target being analyzed")

@@ -198,13 +205,6 @@ func (cfg *Catalog) DescribeFields(descriptions fangs.FieldDescriptionSet) {
 }

 func (cfg *Catalog) PostLoad() error {
-	if cfg.Name != "" {
-		log.Warnf("name parameter is deprecated. please use: source-name. name will be removed in a future version")
-		if cfg.Source.Name == "" {
-			cfg.Source.Name = cfg.Name
-		}
-	}
-
 	usingLegacyCatalogers := len(cfg.Catalogers) > 0
 	usingNewCatalogers := len(cfg.DefaultCatalogers) > 0 || len(cfg.SelectCatalogers) > 0

@@ -224,6 +224,8 @@ func (cfg *Catalog) PostLoad() error {
 		return out
 	}

+	cfg.From = flatten(cfg.From)
+
 	cfg.Catalogers = flatten(cfg.Catalogers)
 	cfg.DefaultCatalogers = flatten(cfg.DefaultCatalogers)
 	cfg.SelectCatalogers = flatten(cfg.SelectCatalogers)
@@ -2,14 +2,18 @@ package options

 import (
 	"fmt"
+	"sort"
+
+	"github.com/scylladb/go-set/strset"

 	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/syft/file"
 )

 type fileConfig struct {
-	Metadata fileMetadata `yaml:"metadata" json:"metadata" mapstructure:"metadata"`
-	Content  fileContent  `yaml:"content" json:"content" mapstructure:"content"`
+	Metadata   fileMetadata   `yaml:"metadata" json:"metadata" mapstructure:"metadata"`
+	Content    fileContent    `yaml:"content" json:"content" mapstructure:"content"`
+	Executable fileExecutable `yaml:"executable" json:"executable" mapstructure:"executable"`
 }

 type fileMetadata struct {
@@ -22,6 +26,10 @@ type fileContent struct {
 	Globs              []string `yaml:"globs" json:"globs" mapstructure:"globs"`
 }

+type fileExecutable struct {
+	Globs []string `yaml:"globs" json:"globs" mapstructure:"globs"`
+}
+
 func defaultFileConfig() fileConfig {
 	return fileConfig{
 		Metadata: fileMetadata{
@@ -31,10 +39,17 @@ func defaultFileConfig() fileConfig {
 		Content: fileContent{
 			SkipFilesAboveSize: 250 * intFile.KB,
 		},
+		Executable: fileExecutable{
+			Globs: nil,
+		},
 	}
 }

 func (c *fileConfig) PostLoad() error {
+	digests := strset.New(c.Metadata.Digests...).List()
+	sort.Strings(digests)
+	c.Metadata.Digests = digests
+
 	switch c.Metadata.Selection {
 	case file.NoFilesSelection, file.FilesOwnedByPackageSelection, file.AllFilesSelection:
 		return nil
@@ -0,0 +1,56 @@
+package options
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/anchore/syft/syft/file"
+)
+
+func Test_fileConfig_PostLoad(t *testing.T) {
+	tests := []struct {
+		name    string
+		cfg     fileConfig
+		assert  func(t *testing.T, cfg fileConfig)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "deduplicate digests",
+			cfg: fileConfig{
+				Metadata: fileMetadata{
+					Selection: file.NoFilesSelection,
+					Digests:   []string{"sha1", "sha1"},
+				},
+			},
+			assert: func(t *testing.T, cfg fileConfig) {
+				assert.Equal(t, []string{"sha1"}, cfg.Metadata.Digests)
+			},
+		},
+		{
+			name: "error on invalid selection",
+			cfg: fileConfig{
+				Metadata: fileMetadata{
+					Selection: file.Selection("invalid"),
+				},
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name:    "error on empty selection",
+			cfg:     fileConfig{},
+			wantErr: assert.Error,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.cfg.PostLoad())
+			if tt.assert != nil {
+				tt.assert(t, tt.cfg)
+			}
+		})
+	}
+}
@@ -0,0 +1,60 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/spdxtagvalue"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+var _ clio.PostLoader = (*Format)(nil)
+
+// Format contains all user configuration for output formatting.
+type Format struct {
+	Pretty        *bool               `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+	Template      FormatTemplate      `yaml:"template" json:"template" mapstructure:"template"`
+	SyftJSON      FormatSyftJSON      `yaml:"json" json:"json" mapstructure:"json"`
+	SPDXJSON      FormatSPDXJSON      `yaml:"spdx-json" json:"spdx-json" mapstructure:"spdx-json"`
+	CyclonedxJSON FormatCyclonedxJSON `yaml:"cyclonedx-json" json:"cyclonedx-json" mapstructure:"cyclonedx-json"`
+	CyclonedxXML  FormatCyclonedxXML  `yaml:"cyclonedx-xml" json:"cyclonedx-xml" mapstructure:"cyclonedx-xml"`
+}
+
+func (o *Format) PostLoad() error {
+	o.SyftJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SyftJSON.Pretty)
+	o.SPDXJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SPDXJSON.Pretty)
+	o.CyclonedxJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxJSON.Pretty)
+	o.CyclonedxXML.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxXML.Pretty)
+
+	return nil
+}
+
+func DefaultFormat() Format {
+	return Format{
+		Template:      DefaultFormatTemplate(),
+		SyftJSON:      DefaultFormatJSON(),
+		SPDXJSON:      DefaultFormatSPDXJSON(),
+		CyclonedxJSON: DefaultFormatCyclonedxJSON(),
+		CyclonedxXML:  DefaultFormatCyclonedxXML(),
+	}
+}
+
+func (o Format) Encoders() ([]sbom.FormatEncoder, error) {
+	return format.EncodersConfig{
+		Template:      o.Template.config(),
+		SyftJSON:      o.SyftJSON.config(),
+		SPDXJSON:      o.SPDXJSON.config(format.AllVersions),                   // we support multiple versions, not just a single version
+		SPDXTagValue:  spdxtagvalue.EncoderConfig{Version: format.AllVersions}, // we support multiple versions, not just a single version
+		CyclonedxJSON: o.CyclonedxJSON.config(format.AllVersions),              // we support multiple versions, not just a single version
+		CyclonedxXML:  o.CyclonedxXML.config(format.AllVersions),               // we support multiple versions, not just a single version
+	}.Encoders()
+}
+
+func multiLevelOption[T any](defaultValue T, option ...*T) *T {
+	result := defaultValue
+	for _, opt := range option {
+		if opt != nil {
+			result = *opt
+		}
+	}
+	return &result
+}
@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/cyclonedxjson"
+)
+
+type FormatCyclonedxJSON struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatCyclonedxJSON() FormatCyclonedxJSON {
+	return FormatCyclonedxJSON{}
+}
+
+func (o FormatCyclonedxJSON) config(version string) cyclonedxjson.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return cyclonedxjson.EncoderConfig{
+		Version: version,
+		Pretty:  pretty,
+	}
+}
@@ -13,7 +13,7 @@ func TestFormatCyclonedxJSON_buildConfig(t *testing.T) {
 	ft := &FormatCyclonedxJSON{}
 	ft = setAllToNonZero(t, ft).(*FormatCyclonedxJSON)

-	subject := ft.buildConfig("Version")
+	subject := ft.config("Version")
 	assertExpectedValue(t, subject)
 }

@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/cyclonedxxml"
+)
+
+type FormatCyclonedxXML struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatCyclonedxXML() FormatCyclonedxXML {
+	return FormatCyclonedxXML{}
+}
+
+func (o FormatCyclonedxXML) config(version string) cyclonedxxml.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return cyclonedxxml.EncoderConfig{
+		Version: version,
+		Pretty:  pretty,
+	}
+}
@@ -10,6 +10,6 @@ func TestFormatCyclonedxXML_buildConfig(t *testing.T) {
 	ft := FormatCyclonedxXML{}
 	ftp := setAllToNonZero(t, &ft).(*FormatCyclonedxXML)

-	subject := ftp.buildConfig("Version")
+	subject := ftp.config("Version")
 	assertExpectedValue(t, subject)
 }
@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/spdxjson"
+)
+
+type FormatSPDXJSON struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatSPDXJSON() FormatSPDXJSON {
+	return FormatSPDXJSON{}
+}
+
+func (o FormatSPDXJSON) config(v string) spdxjson.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return spdxjson.EncoderConfig{
+		Version: v,
+		Pretty:  pretty,
+	}
+}
@@ -10,6 +10,6 @@ func TestFormatSPDXJSON_buildConfig(t *testing.T) {
 	ft := &FormatSPDXJSON{}
 	ft = setAllToNonZero(t, ft).(*FormatSPDXJSON)

-	subject := ft.buildConfig("Version")
+	subject := ft.config("Version")
 	assertExpectedValue(t, subject)
 }
@@ -2,7 +2,6 @@ package options

 import (
 	"github.com/anchore/syft/syft/format/syftjson"
-	"github.com/anchore/syft/syft/sbom"
 )

 type FormatSyftJSON struct {
@@ -16,12 +15,7 @@ func DefaultFormatJSON() FormatSyftJSON {
 	}
 }

-func (o FormatSyftJSON) formatEncoders() ([]sbom.FormatEncoder, error) {
-	enc, err := syftjson.NewFormatEncoderWithConfig(o.buildConfig())
-	return []sbom.FormatEncoder{enc}, err
-}
-
-func (o FormatSyftJSON) buildConfig() syftjson.EncoderConfig {
+func (o FormatSyftJSON) config() syftjson.EncoderConfig {
 	var pretty bool
 	if o.Pretty != nil {
 		pretty = *o.Pretty
@@ -10,6 +10,6 @@ func TestFormatSyftJSON_buildConfig(t *testing.T) {
 	ft := &FormatSyftJSON{}
 	ft = setAllToNonZero(t, ft).(*FormatSyftJSON)

-	subject := ft.buildConfig()
+	subject := ft.config()
 	assertExpectedValue(t, subject)
 }
@@ -3,7 +3,6 @@ package options
 import (
 	"github.com/anchore/clio"
 	"github.com/anchore/syft/syft/format/template"
-	"github.com/anchore/syft/syft/sbom"
 )

 var _ clio.FlagAdder = (*FormatTemplate)(nil)
@@ -11,6 +10,7 @@ var _ clio.FlagAdder = (*FormatTemplate)(nil)
 type FormatTemplate struct {
 	Enabled bool   `yaml:"-" json:"-" mapstructure:"-"`
 	Path    string `yaml:"path" json:"path" mapstructure:"path"` // -t template file to use for output
+	Legacy  bool   `yaml:"legacy" json:"legacy" mapstructure:"legacy"`
 }

 func DefaultFormatTemplate() FormatTemplate {
@@ -26,12 +26,9 @@ func (o *FormatTemplate) AddFlags(flags clio.FlagSet) {
 	}
 }

-func (o FormatTemplate) formatEncoders() ([]sbom.FormatEncoder, error) {
-	if !o.Enabled {
-		return nil, nil
-	}
-	enc, err := template.NewFormatEncoder(template.EncoderConfig{
+func (o FormatTemplate) config() template.EncoderConfig {
+	return template.EncoderConfig{
 		TemplatePath: o.Path,
-	})
-	return []sbom.FormatEncoder{enc}, err
+		Legacy:       o.Legacy,
+	}
 }
@@ -0,0 +1,38 @@
+package options
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg/cataloger/golang"
+)
+
+type golangConfig struct {
+	SearchLocalModCacheLicenses bool                          `json:"search-local-mod-cache-licenses" yaml:"search-local-mod-cache-licenses" mapstructure:"search-local-mod-cache-licenses"`
+	LocalModCacheDir            string                        `json:"local-mod-cache-dir" yaml:"local-mod-cache-dir" mapstructure:"local-mod-cache-dir"`
+	SearchRemoteLicenses        bool                          `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	Proxy                       string                        `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
+	NoProxy                     string                        `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
+	MainModuleVersion           golangMainModuleVersionConfig `json:"main-module-version" yaml:"main-module-version" mapstructure:"main-module-version"`
+}
+
+type golangMainModuleVersionConfig struct {
+	FromLDFlags       bool `json:"from-ld-flags" yaml:"from-ld-flags" mapstructure:"from-ld-flags"`
+	FromContents      bool `json:"from-contents" yaml:"from-contents" mapstructure:"from-contents"`
+	FromBuildSettings bool `json:"from-build-settings" yaml:"from-build-settings" mapstructure:"from-build-settings"`
+}
+
+func defaultGolangConfig() golangConfig {
+	def := golang.DefaultCatalogerConfig()
+	return golangConfig{
+		SearchLocalModCacheLicenses: def.SearchLocalModCacheLicenses,
+		LocalModCacheDir:            def.LocalModCacheDir,
+		SearchRemoteLicenses:        def.SearchRemoteLicenses,
+		Proxy:                       strings.Join(def.Proxies, ","),
+		NoProxy:                     strings.Join(def.NoProxy, ","),
+		MainModuleVersion: golangMainModuleVersionConfig{
+			FromLDFlags:       def.MainModuleVersion.FromLDFlags,
+			FromContents:      def.MainModuleVersion.FromContents,
+			FromBuildSettings: def.MainModuleVersion.FromBuildSettings,
+		},
+	}
+}
@@ -2,9 +2,12 @@ package options

 import (
 	"fmt"
+	"sort"
 	"strings"

 	"github.com/scylladb/go-set/strset"
+
+	"github.com/anchore/syft/syft/source/sourceproviders"
 )

 type sourceConfig struct {
@@ -24,16 +27,24 @@ type imageSource struct {
 }

 func defaultSourceConfig() sourceConfig {
+	var digests []string
+	for _, alg := range sourceproviders.DefaultConfig().DigestAlgorithms {
+		digests = append(digests, alg.String())
+	}
 	return sourceConfig{
 		File: fileSource{
-			Digests: []string{"sha256"},
-		},
-		Image: imageSource{
-			DefaultPullSource: "",
+			Digests: digests,
 		},
 	}
 }

+func (c *fileSource) PostLoad() error {
+	digests := strset.New(c.Digests...).List()
+	sort.Strings(digests)
+	c.Digests = digests
+	return nil
+}
+
 func (c imageSource) PostLoad() error {
 	return checkDefaultSourceValues(c.DefaultPullSource)
 }
@@ -0,0 +1,37 @@
+package options
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_fileSource_PostLoad(t *testing.T) {
+	tests := []struct {
+		name    string
+		cfg     fileSource
+		assert  func(t *testing.T, cfg fileSource)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "deduplicate digests",
+			cfg: fileSource{
+				Digests: []string{"sha1", "sha1"},
+			},
+			assert: func(t *testing.T, cfg fileSource) {
+				assert.Equal(t, []string{"sha1"}, cfg.Digests)
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.cfg.PostLoad())
+			if tt.assert != nil {
+				tt.assert(t, tt.cfg)
+			}
+		})
+	}
+}
@@ -368,6 +368,14 @@ var dirOnlyTestCases = []testCase{
 			"unicode_util_compat": "0.7.0",
 		},
 	},
+	{
+		name:        "find ErLang OTP applications",
+		pkgType:     pkg.ErlangOTPPkg,
+		pkgLanguage: pkg.Erlang,
+		pkgInfo: map[string]string{
+			"accept": "0.3.5",
+		},
+	},
 	{
 		name:        "find swift package manager packages",
 		pkgType:     pkg.SwiftPkg,
@@ -444,4 +452,12 @@ var commonTestCases = []testCase{
 			"glibc": "2.34-210",
 		},
 	},
+	{
+		name:        "find wordpress plugins",
+		pkgType:     pkg.WordpressPluginPkg,
+		pkgLanguage: pkg.PHP,
+		pkgInfo: map[string]string{
+			"Akismet Anti-spam: Spam Protection": "5.3",
+		},
+	},
 }
@@ -22,15 +22,11 @@ func BenchmarkImagePackageCatalogers(b *testing.B) {
 	tarPath := imagetest.GetFixtureImageTarPath(b, fixtureImageName)

 	// get the source object for the image
-	userInput := "docker-archive:" + tarPath
-	detection, err := source.Detect(userInput, source.DefaultDetectConfig())
-	require.NoError(b, err)
-
-	theSource, err := detection.NewSource(source.DefaultDetectionSourceConfig())
+	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(b, err)

 	b.Cleanup(func() {
-		theSource.Close()
+		require.NoError(b, theSource.Close())
 	})

 	// build the SBOM
@@ -57,8 +53,8 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedLanguages.Remove(pkg.Swift.String())
 	definedLanguages.Remove(pkg.CPP.String())
 	definedLanguages.Remove(pkg.Haskell.String())
-	definedLanguages.Remove(pkg.Erlang.String())
 	definedLanguages.Remove(pkg.Elixir.String())
+	definedLanguages.Remove(pkg.Erlang.String())

 	observedPkgs := strset.New()
 	definedPkgs := strset.New()
@@ -71,6 +67,7 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedPkgs.Remove(string(pkg.GoModulePkg))
 	definedPkgs.Remove(string(pkg.RustPkg))
 	definedPkgs.Remove(string(pkg.DartPubPkg))
+	definedPkgs.Remove(string(pkg.ErlangOTPPkg))
 	definedPkgs.Remove(string(pkg.CocoapodsPkg))
 	definedPkgs.Remove(string(pkg.ConanPkg))
 	definedPkgs.Remove(string(pkg.HackagePkg))
@@ -122,7 +119,6 @@ func TestPkgCoverageImage(t *testing.T) {
 				}
 				t.Fatalf("unexpected package count: %d!=%d", pkgCount, len(c.pkgInfo))
 			}
-
 		})
 	}

@@ -210,7 +206,6 @@ func TestPkgCoverageDirectory(t *testing.T) {
 				}
 				t.Fatalf("unexpected package count: %d!=%d", actualPkgCount, len(test.pkgInfo))
 			}
-
 		})
 	}

@@ -248,7 +243,6 @@ func TestPkgCoverageImage_HasEvidence(t *testing.T) {

 	for _, c := range cases {
 		t.Run(c.name, func(t *testing.T) {
-
 			for a := range sbom.Artifacts.Packages.Enumerate(c.pkgType) {
 				assert.NotEmpty(t, a.Locations.ToSlice(), "package %q has no locations (type=%q)", a.Name, a.Type)
 				for _, l := range a.Locations.ToSlice() {
@@ -258,7 +252,6 @@ func TestPkgCoverageImage_HasEvidence(t *testing.T) {
 					}
 				}
 			}
-
 		})
 	}

@@ -278,7 +271,6 @@ func TestPkgCoverageDirectory_HasEvidence(t *testing.T) {

 	for _, c := range cases {
 		t.Run(c.name, func(t *testing.T) {
-
 			for a := range sbom.Artifacts.Packages.Enumerate(c.pkgType) {
 				assert.NotEmpty(t, a.Locations.ToSlice(), "package %q has no locations (type=%q)", a.Name, a.Type)
 				for _, l := range a.Locations.ToSlice() {
@@ -288,7 +280,6 @@ func TestPkgCoverageDirectory_HasEvidence(t *testing.T) {
 					}
 				}
 			}
-
 		})
 	}

@@ -10,7 +10,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"

-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/syft/format"
 	"github.com/anchore/syft/syft/format/cyclonedxjson"
 	"github.com/anchore/syft/syft/format/cyclonedxxml"
@@ -12,7 +12,7 @@ import (

 	"github.com/anchore/clio"
 	stereoscopeFile "github.com/anchore/stereoscope/pkg/file"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/syft/cataloging/filecataloging"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/file/cataloger/filecontent"
@@ -19,7 +19,7 @@ func TestGolangCompilerDetection(t *testing.T) {
 			name:              "syft can detect a single golang compiler given the golang base image",
 			image:             "image-golang-compiler",
 			expectedCompilers: []string{"go1.18.10"},
-			expectedCPE:       []cpe.CPE{cpe.Must("cpe:2.3:a:golang:go:1.18.10:-:*:*:*:*:*:*")},
+			expectedCPE:       []cpe.CPE{cpe.Must("cpe:2.3:a:golang:go:1.18.10:-:*:*:*:*:*:*", cpe.GeneratedSource)},
 			expectedPURL:      []string{"pkg:golang/stdlib@1.18.10"},
 		},
 	}
@@ -51,7 +51,6 @@ var noAssertion = map[string]string{
 	"/packages/TwilioNotifier.hpi:WEB-INF/lib/sdk-3.0.jar":                                           "pkg:maven/sdk/sdk@3.0",

 	// syft generates incorrect purls
-	"/packages/kafka_2.13-3.2.2.jar":                             "pkg:maven/org.apache.kafka/kafka_2.13@3.2.2",
 	"/packages/akka-actor_2.13-2.6.6.jar":                        "pkg:maven/com.typesafe.akka/akka-actor_2.13@2.6.6",
 	"/packages/akka-management-cluster-bootstrap_2.13-1.2.0.jar": "pkg:maven/com.lightbend.akka.management/akka-management-cluster-bootstrap_2.13@1.2.0",
 	"/packages/hudson.war:WEB-INF/lib/asm-2.2.3.jar":             "pkg:maven/asm/asm@2.2.3",
@@ -366,10 +365,10 @@ var expectedPURLs = map[string]string{
 	"/packages/jruby-stdlib-9.1.15.0.jar:META-INF/jruby.home/lib/ruby/stdlib/org/yaml/snakeyaml/1.18/snakeyaml-1.18.jar":                   "pkg:maven/org.yaml/snakeyaml@1.18",
 	"/packages/jruby-stdlib-9.1.15.0.jar:META-INF/jruby.home/lib/ruby/stdlib/readline.jar:jline:jline":                                     "pkg:maven/jline/jline@2.11",
 	"/packages/jruby-stdlib-9.1.15.0.jar:META-INF/jruby.home/lib/ruby/stdlib/readline.jar:rubygems:jruby-readline":                         "pkg:maven/rubygems/jruby-readline@1.2.0",
-	"/packages/jruby-stdlib-9.1.15.0.jar": "pkg:maven/org.jruby/jruby-stdlib@9.1.15.0",
-	"/packages/jsch-0.1.55.jar":           "pkg:maven/com.jcraft/jsch@0.1.55",
-	"/packages/junit-4.13.1.jar":          "pkg:maven/junit/junit@4.13.1",
-	// "/packages/kafka_2.13-3.2.2.jar":                                                                                                       "pkg:maven/org.apache.kafka/kafka_2.13@3.2.2",
+	"/packages/jruby-stdlib-9.1.15.0.jar":                                                          "pkg:maven/org.jruby/jruby-stdlib@9.1.15.0",
+	"/packages/jsch-0.1.55.jar":                                                                    "pkg:maven/com.jcraft/jsch@0.1.55",
+	"/packages/junit-4.13.1.jar":                                                                   "pkg:maven/junit/junit@4.13.1",
+	"/packages/kafka_2.13-3.2.2.jar":                                                               "pkg:maven/org.apache.kafka/kafka_2.13@3.2.2",
 	"/packages/keycloak-core-22.0.2.jar":                                                           "pkg:maven/org.keycloak/keycloak-core@22.0.2",
 	"/packages/log4j-1.2.16.jar":                                                                   "pkg:maven/log4j/log4j@1.2.16",
 	"/packages/log4j-core-2.17.0.jar":                                                              "pkg:maven/org.apache.logging.log4j/log4j-core@2.17.0",
@@ -0,0 +1,352 @@
+package integration
+
+import (
+	"fmt"
+	"go/ast"
+	"go/parser"
+	"go/token"
+	"go/types"
+	"os"
+	"path/filepath"
+	"reflect"
+	"strings"
+	"testing"
+
+	"github.com/bmatcuk/doublestar/v4"
+	"github.com/scylladb/go-set/strset"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func Test_packageCatalogerExports(t *testing.T) {
+	// sanity check that we are actually finding exports
+
+	exports := packageCatalogerExports(t)
+	require.NotEmpty(t, exports)
+
+	expectAtLeast := map[string]*strset.Set{
+		"golang": strset.New("NewGoModuleFileCataloger", "NewGoModuleBinaryCataloger", "CatalogerConfig", "DefaultCatalogerConfig"),
+	}
+
+	for pkg, expected := range expectAtLeast {
+		actual, ok := exports[pkg]
+		require.True(t, ok, pkg)
+		if !assert.True(t, actual.Names().IsSubset(expected), pkg) {
+			t.Logf("missing: %s", strset.SymmetricDifference(expected, actual.Names()))
+		}
+	}
+
+}
+
+func Test_validatePackageCatalogerExport(t *testing.T) {
+	cases := []struct {
+		name    string
+		export  exportToken
+		wantErr assert.ErrorAssertionFunc
+	}{
+		// valid...
+		{
+			name: "valid constructor",
+			export: exportToken{
+				Name:          "NewFooCataloger",
+				Type:          "*ast.FuncType",
+				SignatureSize: 1,
+				ReturnTypeNames: []string{
+					"pkg.Cataloger",
+				},
+			},
+		},
+		{
+			name: "valid default config",
+			export: exportToken{
+				Name:          "DefaultFooConfig",
+				Type:          "*ast.FuncType",
+				SignatureSize: 0,
+			},
+		},
+		{
+			name: "valid config",
+			export: exportToken{
+				Name: "FooConfig",
+				Type: "*ast.StructType",
+			},
+		},
+		// invalid...
+		{
+			name: "constructor that returns a concrete type",
+			export: exportToken{
+				Name:          "NewFooCataloger",
+				Type:          "*ast.FuncType",
+				SignatureSize: 1,
+				ReturnTypeNames: []string{
+					"*generic.Cataloger",
+				},
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "struct with constructor name",
+			export: exportToken{
+				Name: "NewFooCataloger",
+				Type: "*ast.StructType",
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "struct with default config fn name",
+			export: exportToken{
+				Name: "DefaultFooConfig",
+				Type: "*ast.StructType",
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "fn with struct name",
+			export: exportToken{
+				Name: "FooConfig",
+				Type: "*ast.FuncType",
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "default config with parameters",
+			export: exportToken{
+				Name:          "DefaultFooConfig",
+				Type:          "*ast.FuncType",
+				SignatureSize: 1,
+			},
+			wantErr: assert.Error,
+		},
+	}
+
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			if c.wantErr == nil {
+				c.wantErr = assert.NoError
+			}
+			err := validatePackageCatalogerExport(t, "test", c.export)
+			c.wantErr(t, err)
+		})
+	}
+}
+
+func Test_PackageCatalogerConventions(t *testing.T) {
+	// look at each package in syft/pkg/cataloger...
+	// we want to make certain that only the following things are exported from the package:
+	// - function matching New*Cataloger (e.g. NewAptCataloger)
+	// - function matching Default*Config
+	// - struct matching *Config
+	//
+	// anything else that is exported should result in the test failing.
+	// note: this is meant to apply to things in static space, not methods on structs or within interfaces.
+	//
+	// this additionally ensures that:
+	// - any config struct has a Default*Config function to pair with it.
+	// - all cataloger constructors return pkg.Cataloger interface instead of a concrete type
+
+	exportsPerPackage := packageCatalogerExports(t)
+
+	//for debugging purposes...
+	//for pkg, exports := range exportsPerPackage {
+	//	t.Log(pkg)
+	//	for _, export := range exports {
+	//		t.Logf("  %#v", export)
+	//	}
+	//}
+
+	for pkg, exports := range exportsPerPackage {
+		for _, export := range exports.List() {
+			// assert the export name is valid...
+			assert.NoError(t, validatePackageCatalogerExport(t, pkg, export))
+
+			// assert that config structs have a Default*Config functions to pair with them...
+			if strings.Contains(export.Name, "Config") && !strings.Contains(export.Name, "Default") {
+				// this is a config struct, make certain there is a pairing with a Default*Config function
+				assert.True(t, exports.Has("Default"+export.Name), "cataloger config struct %q in pkg %q must have a 'Default%s' function", export.Name, pkg, export.Name)
+			}
+		}
+	}
+}
+
+func validatePackageCatalogerExport(t *testing.T, pkg string, export exportToken) error {
+
+	constructorMatches, err := doublestar.Match("New*Cataloger", export.Name)
+	require.NoError(t, err)
+
+	defaultConfigMatches, err := doublestar.Match("Default*Config", export.Name)
+	require.NoError(t, err)
+
+	configMatches, err := doublestar.Match("*Config", export.Name)
+	require.NoError(t, err)
+
+	switch {
+	case constructorMatches:
+		if !export.isFunction() {
+			return fmt.Errorf("constructor convention used for non-function in pkg=%q: %#v", pkg, export)
+		}
+
+		returnTypes := strset.New(export.ReturnTypeNames...)
+		if !returnTypes.Has("pkg.Cataloger") {
+			return fmt.Errorf("constructor convention is to return pkg.Cataloger and not concrete types. pkg=%q constructor=%q types=%+v", pkg, export.Name, strings.Join(export.ReturnTypeNames, ","))
+		}
+
+	case defaultConfigMatches:
+		if !export.isFunction() {
+			return fmt.Errorf("default config convention used for non-function in pkg=%q: %#v", pkg, export)
+		}
+		if export.SignatureSize != 0 {
+			return fmt.Errorf("default config convention used for non-zero signature size in pkg=%q: %#v", pkg, export)
+		}
+	case configMatches:
+		if !export.isStruct() {
+			return fmt.Errorf("config convention used for non-struct in pkg=%q: %#v", pkg, export)
+		}
+	default:
+		return fmt.Errorf("unexpected export in pkg=%q: %#v", pkg, export)
+	}
+	return nil
+}
+
+type exportToken struct {
+	Name            string
+	Type            string
+	SignatureSize   int
+	ReturnTypeNames []string
+}
+
+func (e exportToken) isFunction() bool {
+	return strings.Contains(e.Type, "ast.FuncType")
+}
+
+func (e exportToken) isStruct() bool {
+	return strings.Contains(e.Type, "ast.StructType")
+}
+
+type exportTokenSet map[string]exportToken
+
+func (s exportTokenSet) Names() *strset.Set {
+	set := strset.New()
+	for k := range s {
+		set.Add(k)
+	}
+	return set
+}
+
+func (s exportTokenSet) Has(name string) bool {
+	_, ok := s[name]
+	return ok
+}
+
+func (s exportTokenSet) Add(tokens ...exportToken) {
+	for _, t := range tokens {
+		if _, ok := s[t.Name]; ok {
+			panic("duplicate token name: " + t.Name)
+		}
+		s[t.Name] = t
+	}
+}
+
+func (s exportTokenSet) Remove(names ...string) {
+	for _, name := range names {
+		delete(s, name)
+	}
+}
+
+func (s exportTokenSet) List() []exportToken {
+	var tokens []exportToken
+	for _, t := range s {
+		tokens = append(tokens, t)
+	}
+	return tokens
+}
+
+func packageCatalogerExports(t *testing.T) map[string]exportTokenSet {
+	t.Helper()
+
+	catalogerPath := filepath.Join(repoRoot(t), "syft", "pkg", "cataloger")
+
+	ignorePaths := []string{
+		filepath.Join(catalogerPath, "common"),
+		filepath.Join(catalogerPath, "generic"),
+	}
+
+	exportsPerPackage := make(map[string]exportTokenSet)
+
+	err := filepath.Walk(catalogerPath, func(path string, info os.FileInfo, err error) error {
+		require.NoError(t, err)
+
+		if info.IsDir() ||
+			!strings.HasSuffix(info.Name(), ".go") ||
+			strings.HasSuffix(info.Name(), "_test.go") ||
+			strings.Contains(path, "test-fixtures") ||
+			strings.Contains(path, "internal") {
+			return nil
+		}
+
+		for _, ignorePath := range ignorePaths {
+			if strings.Contains(path, ignorePath) {
+				return nil
+			}
+		}
+
+		fset := token.NewFileSet()
+		node, err := parser.ParseFile(fset, path, nil, parser.ParseComments)
+		require.NoError(t, err)
+
+		pkg := node.Name.Name
+		for _, f := range node.Decls {
+			switch decl := f.(type) {
+			case *ast.GenDecl:
+				for _, spec := range decl.Specs {
+					switch spec := spec.(type) {
+					case *ast.TypeSpec:
+						if spec.Name.IsExported() {
+							if _, ok := exportsPerPackage[pkg]; !ok {
+								exportsPerPackage[pkg] = make(exportTokenSet)
+							}
+							exportsPerPackage[pkg].Add(exportToken{
+								Name: spec.Name.Name,
+								Type: reflect.TypeOf(spec.Type).String(),
+							})
+						}
+					}
+				}
+			case *ast.FuncDecl:
+				if decl.Recv == nil && decl.Name.IsExported() {
+					var returnTypes []string
+					if decl.Type.Results != nil {
+						for _, field := range decl.Type.Results.List {
+							// TODO: there is probably a better way to extract the specific type name
+							//ty := strings.Join(strings.Split(fmt.Sprint(field.Type), " "), ".")
+							ty := types.ExprString(field.Type)
+
+							returnTypes = append(returnTypes, ty)
+						}
+					}
+
+					if _, ok := exportsPerPackage[pkg]; !ok {
+						exportsPerPackage[pkg] = make(exportTokenSet)
+					}
+					exportsPerPackage[pkg].Add(exportToken{
+						Name:            decl.Name.Name,
+						Type:            reflect.TypeOf(decl.Type).String(),
+						SignatureSize:   len(decl.Type.Params.List),
+						ReturnTypeNames: returnTypes,
+					})
+				}
+			}
+		}
+
+		return nil
+	})
+
+	require.NoError(t, err)
+
+	// remove exceptions
+	// these are known violations to the common convention that are allowed.
+	if vs, ok := exportsPerPackage["binary"]; ok {
+		vs.Remove("Classifier", "EvidenceMatcher", "FileContentsVersionMatcher", "DefaultClassifiers")
+	}
+
+	return exportsPerPackage
+}
@@ -0,0 +1,204 @@
+package integration
+
+import (
+	"bytes"
+	"go/ast"
+	"go/parser"
+	"go/token"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/scylladb/go-set/strset"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/internal/task"
+	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
+)
+
+func TestAllPackageCatalogersReachableInTasks(t *testing.T) {
+	// we want to see if we can get a task for all package catalogers. This is a bit tricky since we
+	// don't have a nice way to find all cataloger names in the codebase. Instead, we'll look at the
+	// count of unique task names from the package task factory set and compare that with the known constructors
+	// from a source analysis... they should match.
+
+	// additionally, at this time they should either have a "directory" or "image" tag as well. If there is no tag
+	// on a cataloger task then the test should fail.
+
+	taskFactories := task.DefaultPackageTaskFactories()
+	taskTagsByName := make(map[string][]string)
+	for _, factory := range taskFactories {
+		tsk := factory(task.DefaultCatalogingFactoryConfig())
+		if taskTagsByName[tsk.Name()] != nil {
+			t.Fatalf("duplicate task name: %q", tsk.Name())
+		}
+
+		require.NotNil(t, tsk)
+		if sel, ok := tsk.(task.Selector); ok {
+			taskTagsByName[tsk.Name()] = sel.Selectors()
+		} else {
+			taskTagsByName[tsk.Name()] = []string{}
+		}
+	}
+
+	var constructorCount int
+	constructorsPerPackage := getCatalogerConstructors(t)
+	for _, constructors := range constructorsPerPackage {
+		constructorCount += constructors.Size()
+	}
+
+	assert.Equal(t, len(taskTagsByName), constructorCount, "mismatch in number of cataloger constructors and task names")
+
+	for taskName, tags := range taskTagsByName {
+		if taskName == "sbom-cataloger" {
+			continue // this is a special case
+		}
+		if !strset.New(tags...).HasAny(pkgcataloging.ImageTag, pkgcataloging.DirectoryTag) {
+			t.Errorf("task %q is missing 'directory' or 'image' a tag", taskName)
+		}
+	}
+
+}
+
+func TestAllPackageCatalogersRepresentedInSource(t *testing.T) {
+	// find all functions in syft/pkg/cataloger/** that either:
+	// - match the name glob "New*Cataloger"
+	// - are in cataloger.go and match the name glob "New*"
+	//
+	// Then:
+	// - keep track of all packages with cataloger constructors
+	// - keep track of all constructors
+	constructorsPerPackage := getCatalogerConstructors(t)
+
+	// look at the source file in internal/task/package_tasks.go:
+	// - ensure all go packages that have constructors are imported
+	// - ensure there is a reference to all package constructors
+	assertAllPackageCatalogersRepresented(t, constructorsPerPackage)
+}
+
+func getCatalogerConstructors(t *testing.T) map[string]*strset.Set {
+	t.Helper()
+	root := repoRoot(t)
+	catalogerPath := filepath.Join(root, "syft", "pkg", "cataloger")
+
+	constructorsPerPackage := make(map[string]*strset.Set)
+
+	err := filepath.Walk(catalogerPath, func(path string, info os.FileInfo, err error) error {
+		require.NoError(t, err)
+
+		// ignore directories and test files...
+		if info.IsDir() || strings.HasSuffix(info.Name(), "_test.go") {
+			return nil
+		}
+
+		partialResults := getConstructorsFromExpectedFile(t, path, info)
+
+		constructorsPerPackage = mergeConstructors(constructorsPerPackage, partialResults)
+
+		partialResults = getCatalogerConstructorsFromPackage(t, path, info)
+
+		constructorsPerPackage = mergeConstructors(constructorsPerPackage, partialResults)
+
+		return nil
+	})
+
+	require.NoError(t, err)
+
+	// remove some exceptions
+	delete(constructorsPerPackage, "generic") // this is not an actual cataloger
+
+	return constructorsPerPackage
+}
+
+func getConstructorsFromExpectedFile(t *testing.T, path string, info os.FileInfo) map[string][]string {
+	constructorsPerPackage := make(map[string][]string)
+
+	if !strings.HasSuffix(info.Name(), "cataloger.go") && !strings.HasSuffix(info.Name(), "catalogers.go") {
+		return nil
+	}
+
+	fset := token.NewFileSet()
+	node, err := parser.ParseFile(fset, path, nil, parser.ParseComments)
+	require.NoError(t, err)
+
+	for _, f := range node.Decls {
+		fn, ok := f.(*ast.FuncDecl)
+		if !ok || fn.Recv != nil || !strings.HasPrefix(fn.Name.Name, "New") {
+			continue
+		}
+
+		pkg := node.Name.Name
+		constructorsPerPackage[pkg] = append(constructorsPerPackage[pkg], fn.Name.Name)
+	}
+
+	return constructorsPerPackage
+}
+
+func getCatalogerConstructorsFromPackage(t *testing.T, path string, info os.FileInfo) map[string][]string {
+	constructorsPerPackage := make(map[string][]string)
+
+	if info.IsDir() || !strings.HasSuffix(info.Name(), ".go") {
+		return nil
+	}
+
+	fset := token.NewFileSet()
+	node, err := parser.ParseFile(fset, path, nil, parser.ParseComments)
+	require.NoError(t, err)
+
+	for _, f := range node.Decls {
+		fn, ok := f.(*ast.FuncDecl)
+		if !ok || fn.Recv != nil || !strings.HasPrefix(fn.Name.Name, "New") || !strings.HasSuffix(fn.Name.Name, "Cataloger") {
+			continue
+		}
+
+		pkg := node.Name.Name
+		constructorsPerPackage[pkg] = append(constructorsPerPackage[pkg], fn.Name.Name)
+	}
+
+	return constructorsPerPackage
+}
+
+func assertAllPackageCatalogersRepresented(t *testing.T, constructorsPerPackage map[string]*strset.Set) {
+	t.Helper()
+
+	contents, err := os.ReadFile(filepath.Join(repoRoot(t), "internal", "task", "package_tasks.go"))
+	require.NoError(t, err)
+
+	// ensure all packages (keys) are represented in the package_tasks.go file
+	for pkg, constructors := range constructorsPerPackage {
+		if !assert.True(t, bytes.Contains(contents, []byte(pkg)), "missing package %q", pkg) {
+			continue
+		}
+		for _, constructor := range constructors.List() {
+			assert.True(t, bytes.Contains(contents, []byte(constructor)), "missing constructor %q for package %q", constructor, pkg)
+		}
+	}
+
+}
+
+func repoRoot(t testing.TB) string {
+	t.Helper()
+	root, err := exec.Command("git", "rev-parse", "--show-toplevel").Output()
+	if err != nil {
+		t.Fatalf("unable to find repo root dir: %+v", err)
+	}
+	absRepoRoot, err := filepath.Abs(strings.TrimSpace(string(root)))
+	if err != nil {
+		t.Fatal("unable to get abs path to repo root:", err)
+	}
+	return absRepoRoot
+}
+
+func mergeConstructors(constructorsPerPackage map[string]*strset.Set, partialResults map[string][]string) map[string]*strset.Set {
+	for pkg, constructors := range partialResults {
+		if _, ok := constructorsPerPackage[pkg]; !ok {
+			constructorsPerPackage[pkg] = strset.New()
+		}
+		constructorsPerPackage[pkg].Add(constructors...)
+	}
+
+	return constructorsPerPackage
+}
--- a/Show More
+++ b/Show More