Speed up cataloging by replacing globs searching with index lookups (#…

…1510) * replace raw globs with index equivelent operations Signed-off-by: Alex Goodman <[email protected]> * add cataloger test for alpm cataloger Signed-off-by: Alex Goodman <[email protected]> * fix import sorting for binary cataloger Signed-off-by: Alex Goodman <[email protected]> * fix linting for mock resolver Signed-off-by: Alex Goodman <[email protected]> * separate portage cataloger parser impl from cataloger Signed-off-by: Alex Goodman <[email protected]> * enhance cataloger pkgtest utils to account for resolver responses Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for alpm cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for apkdb cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for dpkg cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for cpp cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for dart cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for dotnet cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for elixir cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for erlang cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for golang cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for haskell cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for java cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for javascript cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for php cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for portage cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for python cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for rpm cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for rust cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for sbom cataloger Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for swift cataloger Signed-off-by: Alex Goodman <[email protected]> * allow generic catloger to run all mimetype searches at once Signed-off-by: Alex Goodman <[email protected]> * remove stutter from php and javascript cataloger constructors Signed-off-by: Alex Goodman <[email protected]> * bump stereoscope Signed-off-by: Alex Goodman <[email protected]> * add tests for generic.Search Signed-off-by: Alex Goodman <[email protected]> * add exceptions for java archive git ignore entries Signed-off-by: Alex Goodman <[email protected]> * enhance basename and extension resolver methods to be variadic Signed-off-by: Alex Goodman <[email protected]> * dont allow * prefix on extension searches Signed-off-by: Alex Goodman <[email protected]> * add glob-based cataloger tests for ruby cataloger Signed-off-by: Alex Goodman <[email protected]> * remove unnecessary string casting Signed-off-by: Alex Goodman <[email protected]> * incorporate surfacing of leaf link resolitions from stereoscope results Signed-off-by: Alex Goodman <[email protected]> * [wip] switch to stereoscope file metadata Signed-off-by: Alex Goodman <[email protected]> * [wip + failing] revert to old globs but keep new resolvers Signed-off-by: Alex Goodman <[email protected]> * index files, links, and dirs within the directory resolver Signed-off-by: Alex Goodman <[email protected]> * fix several resolver bugs and inconsistencies Signed-off-by: Alex Goodman <[email protected]> * move format testutils to internal package Signed-off-by: Alex Goodman <[email protected]> * update syft json to account for file type string normalization Signed-off-by: Alex Goodman <[email protected]> * split up directory resolver from indexing Signed-off-by: Alex Goodman <[email protected]> * update docs to include details about searching Signed-off-by: Alex Goodman <[email protected]> * [wip] bump stereoscope to development version Signed-off-by: Alex Goodman <[email protected]> * fix linting Signed-off-by: Alex Goodman <[email protected]> * adjust symlinks fixture to be fixed to digest Signed-off-by: Alex Goodman <[email protected]> * fix all-locations resolver tests Signed-off-by: Alex Goodman <[email protected]> * fix test fixture reference Signed-off-by: Alex Goodman <[email protected]> * rename file.Type Signed-off-by: Alex Goodman <[email protected]> * bump stereoscope Signed-off-by: Alex Goodman <[email protected]> * fix PR comment to exclude extra * Signed-off-by: Alex Goodman <[email protected]> * bump to dev version of stereoscope Signed-off-by: Alex Goodman <[email protected]> * bump to final version of stereoscope Signed-off-by: Alex Goodman <[email protected]> * move observing resolver to pkgtest Signed-off-by: Alex Goodman <[email protected]> --------- Signed-off-by: Alex Goodman <[email protected]>
anchore · Feb 9, 2023 · 988041b · 988041b
1 parent 550e2fc
commit 988041b
Show file tree

Hide file tree

Showing 201 changed files with 4,162 additions and 1,366 deletions.
diff --git a/.golangci.yaml b/.golangci.yaml
@@ -6,33 +6,31 @@ issues:
 #  include:
 #    - EXC0002 # disable excluding of issues about comments from golint
 
-
 linters:
   # inverted configuration with `enable-all` and `disable` is not scalable during updates of golangci-lint
   disable-all: true
   enable:
     - asciicheck
     - bodyclose
     - depguard
+    - dogsled
     - dupl
     - errcheck
-    - errorlint
     - exportloopref
-    - forcetypeassert
     - funlen
     - gocognit
     - goconst
     - gocritic
     - gocyclo
     - gofmt
-    - tparallel
-    - importas
+    - goimports
+    - goprintffuncname
     - gosec
     - gosimple
     - govet
     - ineffassign
     - misspell
-    - nolintlint
+    - nakedret
     - revive
     - staticcheck
     - stylecheck
@@ -41,6 +39,7 @@ linters:
     - unparam
     - unused
     - whitespace
+
 linters-settings:
   funlen:
     # Checks the number of lines in a function.
@@ -57,7 +56,7 @@ run:
   timeout: 10m
 
 # do not enable...
-#    - dogsled           # found to be to niche and ineffective
+#    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
 #    - goprintffuncname  # does not catch all cases and there are exceptions
 #    - nakedret          # does not catch all cases and should not fail a build
 #    - gochecknoglobals
@@ -73,7 +72,11 @@ run:
 #    - lll         # without a way to specify per-line exception cases, this is not usable
 #    - maligned    # this is an excellent linter, but tricky to optimize and we are not sensitive to memory layout optimizations
 #    - nestif
-#    - prealloc    # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
-#    - scopelint   # deprecated
+#    - nolintlint   # as of go1.19 this conflicts with the behavior of gofmt, which is a deal-breaker (lint-fix will still fail when running lint)
+#    - prealloc     # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
+#    - rowserrcheck # not in a repo with sql, so this is not useful
+#    - scopelint    # deprecated
+#    - structcheck  # The owner seems to have abandoned the linter. Replaced by "unused".
 #    - testpackage
-#    - wsl         # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)
+#    - varcheck     # The owner seems to have abandoned the linter. Replaced by "unused".
+#    - wsl          # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)
diff --git a/DEVELOPING.md b/DEVELOPING.md
@@ -118,45 +118,55 @@ sequenceDiagram
 
 Catalogers are the way in which syft is able to identify and construct packages given some amount of source metadata.
 For example, Syft can locate and process `package-lock.json` files when performing filesystem scans. 
-See: [how to specify file globs](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/javascript/cataloger.go#L16-L21)
-and an implementation of the [package-lock.json parser](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) fora quick review.
+See: [how to specify file globs](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21)
+and an implementation of the [package-lock.json parser](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) fora quick review.
 
 #### Building a new Cataloger
 
-Catalogers must fulfill the interface [found here](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger.go). 
+Catalogers must fulfill the interface [found here](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger.go). 
 This means that when building a new cataloger, the new struct must implement both method signatures of `Catalog` and `Name`.
 
-A top level view of the functions that construct all the catalogers can be found [here](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/cataloger.go).
+A top level view of the functions that construct all the catalogers can be found [here](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/cataloger.go).
 When an author has finished writing a new cataloger this is the spot to plug in the new catalog constructor.
 
-For a top level view of how the catalogers are used see [this function](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/catalog.go#L41-L100) as a reference. It ranges over all catalogers passed as an argument and invokes the `Catalog` method:
+For a top level view of how the catalogers are used see [this function](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/catalog.go#L41-L100) as a reference. It ranges over all catalogers passed as an argument and invokes the `Catalog` method:
 
 Each cataloger has its own `Catalog` method, but this does not mean that they are all vastly different.
-Take a look at the `apkdb` cataloger for alpine to see how it [constructs a generic.NewCataloger](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/apkdb/cataloger.go).
+Take a look at the `apkdb` cataloger for alpine to see how it [constructs a generic.NewCataloger](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/cataloger.go).
 
 `generic.NewCataloger` is an abstraction syft uses to make writing common components easier. First, it takes the `catalogerName` to identify the cataloger.
 On the other side of the call it uses two key pieces which inform the cataloger how to identify and return packages, the `globPatterns` and the `parseFunction`:
 - The first piece is a `parseByGlob` matching pattern used to identify the files that contain the package metadata.
-See [here for the APK example](https://github.com/anchore/syft/blob/main/syft/pkg/apk_metadata.go#L16-L41).
+See [here for the APK example](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/apk_metadata.go#L16-L41).
 - The other is a `parseFunction` which informs the cataloger what to do when it has found one of the above matches files.
-See this [link for an example](https://github.com/anchore/syft/blob/main/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102).
+See this [link for an example](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102).
 
 If you're unsure about using the `Generic Cataloger` and think the use case being filled requires something more custom
 just file an issue or ask in our slack, and we'd be more than happy to help on the design.
 
-Identified packages share a common struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/blob/main/syft/pkg/package.go#L16-L31).
+Identified packages share a common struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/package.go#L16-L31).
 
 Metadata Note: Identified packages are also assigned specific metadata that can be unique to their environment. 
-See [this folder](https://github.com/anchore/syft/tree/main/syft/pkg) for examples of the different metadata types.
+See [this folder](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg) for examples of the different metadata types.
 These are plugged into the `MetadataType` and `Metadata` fields in the above struct. `MetadataType` informs which type is being used. `Metadata` is an interface converted to that type.
 
 Finally, here is an example of where the package construction is done in the apk cataloger. The first link is where `newPackage` is called in the `parseFunction`. The second link shows the package construction:
-- [Call for new package](https://github.com/anchore/syft/blob/6a7d6e6071829c7ce2943266c0e187b27c0b325c/syft/pkg/cataloger/apkdb/parse_apk_db.go#L96-L99)
-- [APK Package Constructor](https://github.com/anchore/syft/blob/6a7d6e6071829c7ce2943266c0e187b27c0b325c/syft/pkg/cataloger/apkdb/package.go#L12-L27)
+- [Call for new package](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L106)
+- [APK Package Constructor](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/package.go#L12-L27)
 
 If you have more questions about implementing a cataloger or questions about one you might be currently working
 always feel free to file an issue or reach out to us [on slack](https://anchore.com/slack).
 
+#### Searching for files
+
+All catalogers are provided an instance of the [`source.FileResolver`](https://github.com/anchore/syft/blob/v0.70.0/syft/source/file_resolver.go#L8) to interface with the image and search for files. The implementations for these 
+abstractions leverage [`stereoscope`](https://github.com/anchore/stereoscope) in order to perform searching. Here is a 
+rough outline how that works:
+
+1. a stereoscope `file.Index` is searched based on the input given (a path, glob, or MIME type). The index is relatively fast to search, but requires results to be filtered down to the files that exist in the specific layer(s) of interest. This is done automatically by the `filetree.Searcher` abstraction. This abstraction will fallback to searching directly against the raw `filetree.FileTree` if the index does not contain the file(s) of interest. Note: the `filetree.Searcher` is used by the `source.FileResolver` abstraction.
+2. Once the set of files are returned from the `filetree.Searcher` the results are filtered down further to return the most unique file results. For example, you may have requested for files by a glob that returns multiple results. These results are filtered down to deduplicate by real files, so if a result contains two references to the same file, say one accessed via symlink and one accessed via the real path, then the real path reference is returned and the symlink reference is filtered out. If both were accessed by symlink then the first (by lexical order) is returned. This is done automatically by the `source.FileResolver` abstraction.
+3. By the time results reach the `pkg.Cataloger` you are guaranteed to have a set of unique files that exist in the layer(s) of interest (relative to what the resolver supports).
+
 ## Testing
 
 ### Levels of testing

diff --git a/go.mod b/go.mod
@@ -52,15 +52,15 @@ require (
 	github.com/CycloneDX/cyclonedx-go v0.7.1-0.20221222100750-41a1ac565cce
 	github.com/Masterminds/sprig/v3 v3.2.3
 	github.com/anchore/go-logger v0.0.0-20220728155337-03b66a5207d8
-	github.com/anchore/stereoscope v0.0.0-20230203152723-c49244e4d66f
+	github.com/anchore/stereoscope v0.0.0-20230208154630-5a306f07f2e7
 	github.com/docker/docker v23.0.0+incompatible
 	github.com/google/go-containerregistry v0.13.0
 	github.com/invopop/jsonschema v0.7.0
 	github.com/knqyf263/go-rpmdb v0.0.0-20221030135625-4082a22221ce
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/sassoftware/go-rpmutils v0.2.0
 	github.com/vbatts/go-mtree v0.5.2
-	golang.org/x/exp v0.0.0-20220823124025-807a23277127
+	golang.org/x/exp v0.0.0-20230202163644-54bba9f4231b
 	gopkg.in/yaml.v3 v3.0.1
 )
 
@@ -70,6 +70,7 @@ require (
 	github.com/Masterminds/semver/v3 v3.2.0 // indirect
 	github.com/Microsoft/go-winio v0.6.0 // indirect
 	github.com/anchore/go-struct-converter v0.0.0-20221118182256-c68fdcfa2092 // indirect
+	github.com/becheran/wildmatch-go v1.0.0 // indirect
 	github.com/containerd/containerd v1.6.12 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.12.1 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
@@ -127,7 +128,7 @@ require (
 	golang.org/x/sync v0.1.0 // indirect
 	golang.org/x/sys v0.5.0 // indirect
 	golang.org/x/text v0.7.0 // indirect
-	golang.org/x/tools v0.1.12 // indirect
+	golang.org/x/tools v0.2.0 // indirect
 	golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 // indirect
 	google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef // indirect
 	google.golang.org/grpc v1.52.0 // indirect

diff --git a/go.sum b/go.sum
@@ -90,8 +90,8 @@ github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b h1:e1bmaoJfZV
 github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b/go.mod h1:Bkc+JYWjMCF8OyZ340IMSIi2Ebf3uwByOk6ho4wne1E=
 github.com/anchore/packageurl-go v0.1.1-0.20230104203445-02e0a6721501 h1:AV7qjwMcM4r8wFhJq3jLRztew3ywIyPTRapl2T1s9o8=
 github.com/anchore/packageurl-go v0.1.1-0.20230104203445-02e0a6721501/go.mod h1:Blo6OgJNiYF41ufcgHKkbCKF2MDOMlrqhXv/ij6ocR4=
-github.com/anchore/stereoscope v0.0.0-20230203152723-c49244e4d66f h1:hyEFgDzqZRr/+q1cPfjgIKXWJ7lMHDHmDXAOrhKMhRA=
-github.com/anchore/stereoscope v0.0.0-20230203152723-c49244e4d66f/go.mod h1:YerDPu5voTWZUmjrAHhak7gGGdGLilqroEEFLA/PUHo=
+github.com/anchore/stereoscope v0.0.0-20230208154630-5a306f07f2e7 h1:PrdFBPMyika+AM1/AwDmYqrVeUATDU90wbrd81ugicU=
+github.com/anchore/stereoscope v0.0.0-20230208154630-5a306f07f2e7/go.mod h1:TUCfo52tEz7ahTUFtKN//wcB7kJzQs0Oifmnd4NkIXw=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
 github.com/andybalholm/brotli v1.0.4 h1:V7DdXeJtZscaqfNuAdSRuRFzuiKlHSC/Zh3zl9qY3JY=
@@ -102,6 +102,8 @@ github.com/armon/go-metrics v0.0.0-20180917152333-f0300d1749da/go.mod h1:Q73ZrmV
 github.com/armon/go-metrics v0.3.10/go.mod h1:4O98XIr/9W0sxpJ8UaYkvjk10Iff7SnFrb4QAOwNTFc=
 github.com/armon/go-radix v0.0.0-20180808171621-7fddfc383310/go.mod h1:ufUuZ+zHj4x4TnLV4JWEpy2hxWSpsRywHrMgIH9cCH8=
 github.com/armon/go-radix v1.0.0/go.mod h1:ufUuZ+zHj4x4TnLV4JWEpy2hxWSpsRywHrMgIH9cCH8=
+github.com/becheran/wildmatch-go v1.0.0 h1:mE3dGGkTmpKtT4Z+88t8RStG40yN9T+kFEGj2PZFSzA=
+github.com/becheran/wildmatch-go v1.0.0/go.mod h1:gbMvj0NtVdJ15Mg/mH9uxk2R1QCistMyU7d9KFzroX4=
 github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
 github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
@@ -637,8 +639,8 @@ golang.org/x/exp v0.0.0-20191227195350-da58074b4299/go.mod h1:2RIsYlXP63K8oxa1u0
 golang.org/x/exp v0.0.0-20200119233911-0405dc783f0a/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
 golang.org/x/exp v0.0.0-20200207192155-f17229e696bd/go.mod h1:J/WKrq2StrnmMY6+EHIKF9dgMWnmCNThgcyBT1FY9mM=
 golang.org/x/exp v0.0.0-20200224162631-6cc2880d07d6/go.mod h1:3jZMyOhIsHpP37uCMkUooju7aAi5cS1Q23tOzKc+0MU=
-golang.org/x/exp v0.0.0-20220823124025-807a23277127 h1:S4NrSKDfihhl3+4jSTgwoIevKxX9p7Iv9x++OEIptDo=
-golang.org/x/exp v0.0.0-20220823124025-807a23277127/go.mod h1:cyybsKvd6eL0RnXn6p/Grxp8F5bW7iYuBgsNCOHpMYE=
+golang.org/x/exp v0.0.0-20230202163644-54bba9f4231b h1:EqBVA+nNsObCwQoBEHy4wLU0pi7i8a4AL3pbItPdPkE=
+golang.org/x/exp v0.0.0-20230202163644-54bba9f4231b/go.mod h1:CxIveKay+FTh1D0yPZemJVgC/95VzuuOLq5Qi4xnoYc=
 golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
 golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
@@ -904,8 +906,9 @@ golang.org/x/tools v0.1.2/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.3/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.4/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.5/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
-golang.org/x/tools v0.1.12 h1:VveCTK38A2rkS8ZqFY25HIDFscX5X9OoEhJd3quQmXU=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/tools v0.2.0 h1:G6AHpWxTMGY1KyEYoAQ5WTtIekUUvDNjan3ugu60JvE=
+golang.org/x/tools v0.2.0/go.mod h1:y4OqIKeOV/fWJetJ8bXPU1sEVniLMIyDAZWeHdV+NTA=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

diff --git a/internal/string_helpers.go b/internal/string_helpers.go
@@ -28,3 +28,10 @@ func StringInSlice(a string, list []string) bool {
 	}
 	return false
 }
+
+func SplitAny(s string, seps string) []string {
+	splitter := func(r rune) bool {
+		return strings.ContainsRune(seps, r)
+	}
+	return strings.FieldsFunc(s, splitter)
+}
diff --git a/internal/string_helpers_test.go b/internal/string_helpers_test.go
@@ -104,3 +104,37 @@ func TestTruncateMiddleEllipsis(t *testing.T) {
 		})
 	}
 }
+
+func TestSplitAny(t *testing.T) {
+
+	tests := []struct {
+		name   string
+		input  string
+		fields string
+		want   []string
+	}{
+		{
+			name:   "simple",
+			input:  "a,b,c",
+			fields: ",",
+			want:   []string{"a", "b", "c"},
+		},
+		{
+			name:   "empty",
+			input:  "",
+			fields: ",",
+			want:   []string{},
+		},
+		{
+			name:   "multiple separators",
+			input:  "a,b\nc:d",
+			fields: ",:\n",
+			want:   []string{"a", "b", "c", "d"},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, SplitAny(tt.input, tt.fields))
+		})
+	}
+}
diff --git a/syft/file/all_regular_files.go b/syft/file/all_regular_files.go
@@ -1,6 +1,7 @@
 package file
 
 import (
+	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/source"
 )
@@ -20,7 +21,7 @@ func allRegularFiles(resolver source.FileResolver) (locations []source.Location)
 				continue
 			}
 
-			if metadata.Type != source.RegularFile {
+			if metadata.Type != file.TypeRegular {
 				continue
 			}
 			locations = append(locations, resolvedLocation)

diff --git a/syft/file/all_regular_files_test.go b/syft/file/all_regular_files_test.go
@@ -3,6 +3,7 @@ package file
 import (
 	"testing"
 
+	"github.com/google/go-cmp/cmp"
 	"github.com/scylladb/go-set/strset"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -69,8 +70,8 @@ func Test_allRegularFiles(t *testing.T) {
 					virtualLocations.Add(l.VirtualPath)
 				}
 			}
-			assert.ElementsMatch(t, tt.wantRealPaths.List(), realLocations.List(), "mismatched real paths")
-			assert.ElementsMatch(t, tt.wantVirtualPaths.List(), virtualLocations.List(), "mismatched virtual paths")
+			assert.ElementsMatch(t, tt.wantRealPaths.List(), realLocations.List(), "real paths differ: "+cmp.Diff(tt.wantRealPaths.List(), realLocations.List()))
+			assert.ElementsMatch(t, tt.wantVirtualPaths.List(), virtualLocations.List(), "virtual paths differ: "+cmp.Diff(tt.wantVirtualPaths.List(), virtualLocations.List()))
 		})
 	}
 }
diff --git a/syft/file/digest_cataloger.go b/syft/file/digest_cataloger.go
@@ -11,6 +11,7 @@ import (
 	"github.com/wagoodman/go-partybus"
 	"github.com/wagoodman/go-progress"
 
+	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
@@ -65,7 +66,7 @@ func (i *DigestsCataloger) catalogLocation(resolver source.FileResolver, locatio
 	}
 
 	// we should only attempt to report digests for files that are regular files (don't attempt to resolve links)
-	if meta.Type != source.RegularFile {
+	if meta.Type != file.TypeRegular {
 		return nil, errUndigestableFile
 	}
 

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