keep file catalogers separate from file-related definitions

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

internal/archive/safe_copy.go

@@ -1,12 +1,14 @@
-package file
+package archive
 
 import (
 	"errors"
 	"fmt"
 	"io"
+
+	"github.com/anchore/syft/syft/file"
 )
 
-const perFileReadLimit = 2 * GB
+const perFileReadLimit = 2 * file.GB
 
 // safeCopy limits the copy from the reader. This is useful when extracting files from archives to
 // protect against decompression bomb attacks.

internal/archive/tar_file_traversal.go

@@ -1,38 +1,39 @@
-package file
+package archive
 
 import (
 	"fmt"
 	"io/ioutil"
 	"path/filepath"
 
+	"github.com/anchore/syft/syft/file"
 	"github.com/bmatcuk/doublestar/v4"
 	"github.com/mholt/archiver/v3"
 )
 
 // ExtractGlobsFromTarToUniqueTempFile extracts paths matching the given globs within the given archive to a temporary directory, returning file openers for each file extracted.
-func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...string) (map[string]Opener, error) {
-	results := make(map[string]Opener)
+func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...string) (map[string]file.Opener, error) {
+	results := make(map[string]file.Opener)
 
 	// don't allow for full traversal, only select traversal from given paths
 	if len(globs) == 0 {
 		return results, nil
 	}
 
-	visitor := func(file archiver.File) error {
-		defer file.Close()
+	visitor := func(f archiver.File) error {
+		defer f.Close()
 
 		// ignore directories
-		if file.FileInfo.IsDir() {
+		if f.FileInfo.IsDir() {
 			return nil
 		}
 
 		// ignore any filename that doesn't match the given globs...
-		if !matchesAnyGlob(file.Name(), globs...) {
+		if !matchesAnyGlob(f.Name(), globs...) {
 			return nil
 		}
 
 		// we have a file we want to extract....
-		tempfilePrefix := filepath.Base(filepath.Clean(file.Name())) + "-"
+		tempfilePrefix := filepath.Base(filepath.Clean(f.Name())) + "-"
 		tempFile, err := ioutil.TempFile(dir, tempfilePrefix)
 		if err != nil {
 			return fmt.Errorf("unable to create temp file: %w", err)
@@ -42,11 +43,11 @@ func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...strin
 		// provides a ReadCloser. It is up to the caller to handle closing the file explicitly.
 		defer tempFile.Close()
 
-		if err := safeCopy(tempFile, file.ReadCloser); err != nil {
-			return fmt.Errorf("unable to copy source=%q for tar=%q: %w", file.Name(), archivePath, err)
+		if err := safeCopy(tempFile, f.ReadCloser); err != nil {
+			return fmt.Errorf("unable to copy source=%q for tar=%q: %w", f.Name(), archivePath, err)
 		}
 
-		results[file.Name()] = Opener{path: tempFile.Name()}
+		results[f.Name()] = file.NewOpener(tempFile.Name())
 
 		return nil
 	}

internal/archive/zip_file_helpers_test.go

@@ -1,4 +1,4 @@
-package file
+package archive
 
 import (
 	"io/ioutil"

internal/archive/zip_file_manifest.go

@@ -1,7 +1,8 @@
-package file
+package archive
 
 import (
 	"fmt"
+	"github.com/anchore/syft/syft/file"
 	"os"
 	"sort"
 	"strings"
@@ -48,7 +49,7 @@ func (z ZipFileManifest) GlobMatch(patterns ...string) []string {
 			// so that glob logic is consistent inside and outside of ZIP archives
 			normalizedEntry := normalizeZipEntryName(entry)
 
-			if GlobMatch(pattern, normalizedEntry) {
+			if file.GlobMatch(pattern, normalizedEntry) {
 				uniqueMatches.Add(entry)
 			}
 		}

internal/archive/zip_file_manifest_test.go

@@ -1,7 +1,7 @@
 //go:build !windows
 // +build !windows
 
-package file
+package archive
 
 import (
 	"encoding/json"

internal/archive/zip_file_traversal.go

@@ -1,9 +1,10 @@
-package file
+package archive
 
 import (
 	"archive/zip"
 	"bytes"
 	"fmt"
+	"github.com/anchore/syft/syft/file"
 	"io/ioutil"
 	"os"
 	"path/filepath"
@@ -12,14 +13,6 @@ import (
 	"github.com/anchore/syft/internal/log"
 )
 
-const (
-	// represents the order of bytes
-	_  = iota
-	KB = 1 << (10 * iota)
-	MB
-	GB
-)
-
 type errZipSlipDetected struct {
 	Prefix   string
 	JoinArgs []string
@@ -71,16 +64,16 @@ func TraverseFilesInZip(archivePath string, visitor func(*zip.File) error, paths
 }
 
 // ExtractFromZipToUniqueTempFile extracts select paths for the given archive to a temporary directory, returning file openers for each file extracted.
-func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (map[string]Opener, error) {
-	results := make(map[string]Opener)
+func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (map[string]file.Opener, error) {
+	results := make(map[string]file.Opener)
 
 	// don't allow for full traversal, only select traversal from given paths
 	if len(paths) == 0 {
 		return results, nil
 	}
 
-	visitor := func(file *zip.File) error {
-		tempfilePrefix := filepath.Base(filepath.Clean(file.Name)) + "-"
+	visitor := func(f *zip.File) error {
+		tempfilePrefix := filepath.Base(filepath.Clean(f.Name)) + "-"
 
 		tempFile, err := ioutil.TempFile(dir, tempfilePrefix)
 		if err != nil {
@@ -91,26 +84,26 @@ func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (m
 		// provides a ReadCloser. It is up to the caller to handle closing the file explicitly.
 		defer tempFile.Close()
 
-		zippedFile, err := file.Open()
+		zippedFile, err := f.Open()
 		if err != nil {
-			return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to read file=%q from zip=%q: %w", f.Name, archivePath, err)
 		}
 		defer func() {
 			err := zippedFile.Close()
 			if err != nil {
-				log.Errorf("unable to close source file=%q from zip=%q: %+v", file.Name, archivePath, err)
+				log.Errorf("unable to close source file=%q from zip=%q: %+v", f.Name, archivePath, err)
 			}
 		}()
 
-		if file.FileInfo().IsDir() {
-			return fmt.Errorf("unable to extract directories, only files: %s", file.Name)
+		if f.FileInfo().IsDir() {
+			return fmt.Errorf("unable to extract directories, only files: %s", f.Name)
 		}
 
 		if err := safeCopy(tempFile, zippedFile); err != nil {
-			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", f.Name, archivePath, err)
 		}
 
-		results[file.Name] = Opener{path: tempFile.Name()}
+		results[f.Name] = file.NewOpener(tempFile.Name())
 
 		return nil
 	}

internal/archive/zip_file_traversal_test.go

@@ -1,7 +1,7 @@
 //go:build !windows
 // +build !windows
 
-package file
+package archive
 
 import (
 	"crypto/sha256"

internal/archive/zip_read_closer.go

@@ -1,4 +1,4 @@
-package file
+package archive
 
 import (
 	"archive/zip"

internal/archive/zip_read_closer_test.go

@@ -1,7 +1,7 @@
 //go:build !windows
 // +build !windows
 
-package file
+package archive
 
 import (
 	"os"

internal/config/application.go

@@ -45,7 +45,7 @@ type Application struct {
 	FileMetadata       FileMetadata       `yaml:"file-metadata" json:"file-metadata" mapstructure:"file-metadata"`
 	FileClassification fileClassification `yaml:"file-classification" json:"file-classification" mapstructure:"file-classification"`
 	FileContents       fileContents       `yaml:"file-contents" json:"file-contents" mapstructure:"file-contents"`
-	Secrets            secrets            `yaml:"secrets" json:"secrets" mapstructure:"secrets"`
+	Secrets            secretsCfg         `yaml:"secrets" json:"secrets" mapstructure:"secrets"`
 	Registry           registry           `yaml:"registry" json:"registry" mapstructure:"registry"`
 	Exclusions         []string           `yaml:"exclude" json:"exclude" mapstructure:"exclude"`
 	Attest             attest             `yaml:"attest" json:"attest" mapstructure:"attest"`

internal/config/file_contents.go

@@ -1,8 +1,8 @@
 package config
 
 import (
-	internalFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/file/cataloger/filecontents"
 	"github.com/anchore/syft/syft/source"
 	"github.com/spf13/viper"
 )
@@ -16,7 +16,7 @@ type fileContents struct {
 func (cfg fileContents) loadDefaultValues(v *viper.Viper) {
 	v.SetDefault("file-contents.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("file-contents.cataloger.scope", source.SquashedScope)
-	v.SetDefault("file-contents.skip-files-above-size", 1*internalFile.MB)
+	v.SetDefault("file-contents.skip-files-above-size", 1*file.MB)
 	v.SetDefault("file-contents.globs", []string{})
 }
 
@@ -24,8 +24,8 @@ func (cfg *fileContents) parseConfigValues() error {
 	return cfg.Cataloger.parseConfigValues()
 }
 
-func (cfg fileContents) ToConfig() file.ContentsCatalogerConfig {
-	return file.ContentsCatalogerConfig{
+func (cfg fileContents) ToConfig() filecontents.CatalogerConfig {
+	return filecontents.CatalogerConfig{
 		Globs:                     cfg.Globs,
 		SkipFilesAboveSizeInBytes: cfg.SkipFilesAboveSize,
 	}

internal/config/secrets.go

@@ -2,13 +2,13 @@ package config
 
 import (
 	"fmt"
-	internalFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/file/cataloger/secrets"
 	"github.com/anchore/syft/syft/source"
 	"github.com/spf13/viper"
 )
 
-type secrets struct {
+type secretsCfg struct {
 	Cataloger           catalogerOptions  `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
 	AdditionalPatterns  map[string]string `yaml:"additional-patterns" json:"additional-patterns" mapstructure:"additional-patterns"`
 	ExcludePatternNames []string          `yaml:"exclude-pattern-names" json:"exclude-pattern-names" mapstructure:"exclude-pattern-names"`
@@ -16,25 +16,25 @@ type secrets struct {
 	SkipFilesAboveSize  int64             `yaml:"skip-files-above-size" json:"skip-files-above-size" mapstructure:"skip-files-above-size"`
 }
 
-func (cfg secrets) loadDefaultValues(v *viper.Viper) {
+func (cfg secretsCfg) loadDefaultValues(v *viper.Viper) {
 	v.SetDefault("secrets.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("secrets.cataloger.scope", source.AllLayersScope)
 	v.SetDefault("secrets.reveal-values", false)
-	v.SetDefault("secrets.skip-files-above-size", 1*internalFile.MB)
+	v.SetDefault("secrets.skip-files-above-size", 1*file.MB)
 	v.SetDefault("secrets.additional-patterns", map[string]string{})
 	v.SetDefault("secrets.exclude-pattern-names", []string{})
 }
 
-func (cfg *secrets) parseConfigValues() error {
+func (cfg *secretsCfg) parseConfigValues() error {
 	return cfg.Cataloger.parseConfigValues()
 }
 
-func (cfg secrets) ToConfig() (*file.SecretsCatalogerConfig, error) {
-	patterns, err := file.GenerateSearchPatterns(file.DefaultSecretsPatterns, cfg.AdditionalPatterns, cfg.ExcludePatternNames)
+func (cfg secretsCfg) ToConfig() (*secrets.CatalogerConfig, error) {
+	patterns, err := file.GenerateSearchPatterns(secrets.DefaultSecretsPatterns, cfg.AdditionalPatterns, cfg.ExcludePatternNames)
 	if err != nil {
 		return nil, fmt.Errorf("unable to process secrets config patterns: %w", err)
 	}
-	return &file.SecretsCatalogerConfig{
+	return &secrets.CatalogerConfig{
 		Patterns:     patterns,
 		RevealValues: cfg.RevealValues,
 		MaxFileSize:  cfg.SkipFilesAboveSize,

syft/catalog.go

@@ -19,12 +19,12 @@ func Catalog(src *source.Source, options ...CatalogingOption) (*sbom.SBOM, error
 	var tasks []task
 
 	generators := []taskGenerator{
-		generateCatalogPackagesTask,
-		generateCatalogFileMetadataTask,
-		generateCatalogFileDigestsTask,
-		generateCatalogSecretsTask,
-		generateCatalogFileClassificationsTask,
-		generateCatalogContentsTask,
+		generatePackagesCatalogingTask,
+		generateFileMetadataCatalogingTask,
+		generateFileDigestsCatalogingTask,
+		generateSecretsCatalogingTask,
+		generateFileClassifierTask,
+		generateContentsCatalogingTask,
 	}
 
 	for _, generator := range generators {

syft/cataloging_config.go

@@ -2,6 +2,8 @@ package syft
 
 import (
 	"crypto"
+	"github.com/anchore/syft/syft/file/cataloger/filecontents"
+	"github.com/anchore/syft/syft/file/cataloger/secrets"
 
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/version"
@@ -25,13 +27,13 @@ type CatalogingConfig struct {
 	DigestHashes        []crypto.Hash
 	// secrets
 	CaptureSecrets bool
-	SecretsConfig  file.SecretsCatalogerConfig
+	SecretsConfig  secrets.CatalogerConfig
 	SecretsScope   source.Scope
 	// file classification
 	ClassifyFiles   bool
 	FileClassifiers []file.Classifier
 	// file contents
-	ContentsConfig file.ContentsCatalogerConfig
+	ContentsConfig filecontents.CatalogerConfig
 }
 
 func DefaultCatalogingConfig() CatalogingConfig {
@@ -40,8 +42,8 @@ func DefaultCatalogingConfig() CatalogingConfig {
 		ToolName:        internal.ApplicationName,
 		ToolVersion:     version.Guess(),
 		SecretsScope:    source.AllLayersScope,
-		SecretsConfig:   file.DefaultSecretsCatalogerConfig(),
+		SecretsConfig:   secrets.DefaultCatalogerConfig(),
 		FileClassifiers: file.DefaultClassifiers(),
-		ContentsConfig:  file.DefaultContentsCatalogerConfig(),
+		ContentsConfig:  filecontents.DefaultCatalogerConfig(),
 	}
 }

syft/cataloging_option.go

@@ -3,6 +3,7 @@ package syft
 import (
 	"crypto"
 	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/file/cataloger/secrets"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/packages"
 	"github.com/anchore/syft/syft/source"
@@ -82,7 +83,7 @@ func WithFileDigests(hashes ...crypto.Hash) CatalogingOption {
 	}
 }
 
-func WithSecrets(secretConfig *file.SecretsCatalogerConfig) CatalogingOption {
+func WithSecrets(secretConfig *secrets.CatalogerConfig) CatalogingOption {
 	return func(_ *source.Source, config *CatalogingConfig) error {
 		config.CaptureSecrets = true
 		if secretConfig != nil {

syft/file/byte_sizes.go

@@ -0,0 +1,9 @@
+package file
+
+const (
+	// represents the order of bytes
+	_  = iota
+	KB = 1 << (10 * iota)
+	MB
+	GB
+)

syft/file/cataloger/fileclassifier/cataloger.go

@@ -1,25 +1,26 @@
-package file
+package fileclassifier
 
 import (
 	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
 )
 
-type ClassificationCataloger struct {
-	classifiers []Classifier
+type Cataloger struct {
+	classifiers []file.Classifier
 }
 
-func NewClassificationCataloger(classifiers []Classifier) (*ClassificationCataloger, error) {
-	return &ClassificationCataloger{
+func NewCataloger(classifiers []file.Classifier) (*Cataloger, error) {
+	return &Cataloger{
 		classifiers: classifiers,
 	}, nil
 }
 
-func (i *ClassificationCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]Classification, error) {
-	results := make(map[source.Coordinates][]Classification)
+func (i *Cataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]file.Classification, error) {
+	results := make(map[source.Coordinates][]file.Classification)
 
 	numResults := 0
-	for _, location := range allRegularFiles(resolver) {
+	for _, location := range source.AllRegularFiles(resolver) {
 		for _, classifier := range i.classifiers {
 			result, err := classifier.Classify(resolver, location)
 			if err != nil {

syft/file/cataloger/fileclassifier/cataloger_test.go

@@ -1,9 +1,10 @@
-package file
+package fileclassifier
 
 import (
-	"github.com/anchore/stereoscope/pkg/imagetest"
 	"testing"
 
+	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
 	"github.com/stretchr/testify/assert"
 )
@@ -13,14 +14,14 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 		name        string
 		fixtureDir  string
 		location    string
-		expected    []Classification
+		expected    []file.Classification
 		expectedErr func(assert.TestingT, error, ...interface{}) bool
 	}{
 		{
 			name:       "positive-libpython3.7.so",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "libpython3.7.so",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "python-binary",
 					Metadata: map[string]string{
@@ -34,7 +35,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			name:       "positive-python3.6",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "python3.6",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "python-binary",
 					Metadata: map[string]string{
@@ -48,7 +49,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			name:       "positive-patchlevel.h",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "patchlevel.h",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "cpython-source",
 					Metadata: map[string]string{
@@ -62,7 +63,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			name:       "positive-go",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "go",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "go-binary",
 					Metadata: map[string]string{
@@ -76,7 +77,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			name:       "positive-go-hint",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "VERSION",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "go-binary-hint",
 					Metadata: map[string]string{
@@ -90,7 +91,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 			name:       "positive-busybox",
 			fixtureDir: "test-fixtures/classifiers/positive",
 			location:   "[", // note: busybox is a link to [
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "busybox-binary",
 					Metadata: map[string]string{
@@ -105,7 +106,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 
-			c, err := NewClassificationCataloger(DefaultClassifiers)
+			c, err := NewCataloger(file.DefaultClassifiers())
 			test.expectedErr(t, err)
 
 			src, err := source.NewFromDirectory(test.fixtureDir)
@@ -138,14 +139,14 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T
 		name         string
 		fixtureImage string
 		location     string
-		expected     []Classification
+		expected     []file.Classification
 		expectedErr  func(assert.TestingT, error, ...interface{}) bool
 	}{
 		{
 			name:         "busybox-regression",
 			fixtureImage: "image-busybox",
 			location:     "/bin/[",
-			expected: []Classification{
+			expected: []file.Classification{
 				{
 					Class: "busybox-binary",
 					Metadata: map[string]string{
@@ -160,7 +161,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 
-			c, err := NewClassificationCataloger(DefaultClassifiers)
+			c, err := NewCataloger(file.DefaultClassifiers())
 			test.expectedErr(t, err)
 
 			img := imagetest.GetFixtureImage(t, "docker-archive", test.fixtureImage)
@@ -191,7 +192,7 @@ func TestClassifierCataloger_DefaultClassifiers_PositiveCases_Image(t *testing.T
 
 func TestClassifierCataloger_DefaultClassifiers_NegativeCases(t *testing.T) {
 
-	c, err := NewClassificationCataloger(DefaultClassifiers)
+	c, err := NewCataloger(file.DefaultClassifiers())
 	assert.NoError(t, err)
 
 	src, err := source.NewFromDirectory("test-fixtures/classifiers/negative")

syft/file/cataloger/filecontents/cataloger.go

@@ -1,41 +1,40 @@
-package file
+package filecontents
 
 import (
 	"bytes"
 	"encoding/base64"
 	"fmt"
-	"github.com/anchore/syft/internal/file"
 	"io"
 
 	"github.com/anchore/syft/internal"
-
 	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
 )
 
-type ContentsCatalogerConfig struct {
+type CatalogerConfig struct {
 	Globs                     []string
 	SkipFilesAboveSizeInBytes int64
 }
 
-type ContentsCataloger struct {
-	config ContentsCatalogerConfig
+type Cataloger struct {
+	config CatalogerConfig
 }
 
-func DefaultContentsCatalogerConfig() ContentsCatalogerConfig {
-	return ContentsCatalogerConfig{
+func DefaultCatalogerConfig() CatalogerConfig {
+	return CatalogerConfig{
 		Globs:                     nil,
 		SkipFilesAboveSizeInBytes: 1 * file.MB,
 	}
 }
 
-func NewContentsCataloger(config ContentsCatalogerConfig) (*ContentsCataloger, error) {
-	return &ContentsCataloger{
+func NewCataloger(config CatalogerConfig) (*Cataloger, error) {
+	return &Cataloger{
 		config: config,
 	}, nil
 }
 
-func (i *ContentsCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates]string, error) {
+func (i *Cataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates]string, error) {
 	results := make(map[source.Coordinates]string)
 	var locations []source.Location
 
@@ -68,7 +67,7 @@ func (i *ContentsCataloger) Catalog(resolver source.FileResolver) (map[source.Co
 	return results, nil
 }
 
-func (i *ContentsCataloger) catalogLocation(resolver source.FileResolver, location source.Location) (string, error) {
+func (i *Cataloger) catalogLocation(resolver source.FileResolver, location source.Location) (string, error) {
 	contentReader, err := resolver.FileContentsByLocation(location)
 	if err != nil {
 		return "", err

syft/file/cataloger/filecontents/cataloger_test.go

@@ -1,4 +1,4 @@
-package file
+package filecontents
 
 import (
 	"testing"
@@ -66,7 +66,10 @@ func TestContentsCataloger(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
-			c, err := NewContentsCataloger(test.globs, test.maxSize)
+			c, err := NewCataloger(CatalogerConfig{
+				Globs:                     test.globs,
+				SkipFilesAboveSizeInBytes: test.maxSize,
+			})
 			assert.NoError(t, err)
 
 			resolver := source.NewMockResolverForPaths(test.files...)

syft/file/cataloger/filedigests/cataloger.go

@@ -1,37 +1,37 @@
-package file
+package filedigests
 
 import (
 	"crypto"
 	"errors"
 	"fmt"
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/syft/event"
-	"github.com/wagoodman/go-partybus"
-	"github.com/wagoodman/go-progress"
 	"hash"
 	"io"
 
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
-
+	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
+	"github.com/wagoodman/go-partybus"
+	"github.com/wagoodman/go-progress"
 )
 
 var errUndigestableFile = errors.New("undigestable file")
 
-type DigestsCataloger struct {
+type Cataloger struct {
 	hashes []crypto.Hash
 }
 
-func NewDigestsCataloger(hashes []crypto.Hash) (*DigestsCataloger, error) {
-	return &DigestsCataloger{
+func NewCataloger(hashes []crypto.Hash) (*Cataloger, error) {
+	return &Cataloger{
 		hashes: hashes,
 	}, nil
 }
 
-func (i *DigestsCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]Digest, error) {
-	results := make(map[source.Coordinates][]Digest)
-	locations := allRegularFiles(resolver)
+func (i *Cataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]file.Digest, error) {
+	results := make(map[source.Coordinates][]file.Digest)
+	locations := source.AllRegularFiles(resolver)
 	stage, prog := digestsCatalogingProgress(int64(len(locations)))
 	for _, location := range locations {
 		stage.Current = location.RealPath
@@ -57,7 +57,7 @@ func (i *DigestsCataloger) Catalog(resolver source.FileResolver) (map[source.Coo
 	return results, nil
 }
 
-func (i *DigestsCataloger) catalogLocation(resolver source.FileResolver, location source.Location) ([]Digest, error) {
+func (i *Cataloger) catalogLocation(resolver source.FileResolver, location source.Location) ([]file.Digest, error) {
 	meta, err := resolver.FileMetadataByLocation(location)
 	if err != nil {
 		return nil, err
@@ -88,16 +88,16 @@ func (i *DigestsCataloger) catalogLocation(resolver source.FileResolver, locatio
 	}
 
 	if size == 0 {
-		return make([]Digest, 0), nil
+		return make([]file.Digest, 0), nil
 	}
 
-	result := make([]Digest, len(i.hashes))
+	result := make([]file.Digest, len(i.hashes))
 	// only capture digests when there is content. It is important to do this based on SIZE and not
 	// FILE TYPE. The reasoning is that it is possible for a tar to be crafted with a header-only
 	// file type but a body is still allowed.
 	for idx, hasher := range hashers {
-		result[idx] = Digest{
-			Algorithm: DigestAlgorithmName(i.hashes[idx]),
+		result[idx] = file.Digest{
+			Algorithm: file.DigestAlgorithmName(i.hashes[idx]),
 			Value:     fmt.Sprintf("%+x", hasher.Sum(nil)),
 		}
 	}

syft/file/cataloger/filedigests/cataloger_test.go

@@ -1,25 +1,23 @@
-package file
+package filedigests
 
 import (
 	"crypto"
 	"fmt"
-	"github.com/stretchr/testify/require"
 	"io/ioutil"
 	"os"
 	"path/filepath"
 	"testing"
 
-	"github.com/anchore/stereoscope/pkg/file"
-
+	stereoscopeFile "github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/stereoscope/pkg/imagetest"
-
-	"github.com/stretchr/testify/assert"
-
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 )
 
-func testDigests(t testing.TB, root string, files []string, hashes ...crypto.Hash) map[source.Coordinates][]Digest {
-	digests := make(map[source.Coordinates][]Digest)
+func testDigests(t testing.TB, root string, files []string, hashes ...crypto.Hash) map[source.Coordinates][]file.Digest {
+	digests := make(map[source.Coordinates][]file.Digest)
 
 	for _, f := range files {
 		fh, err := os.Open(filepath.Join(root, f))
@@ -33,15 +31,15 @@ func testDigests(t testing.TB, root string, files []string, hashes ...crypto.Has
 
 		if len(b) == 0 {
 			// we don't keep digests for empty files
-			digests[source.NewLocation(f).Coordinates] = []Digest{}
+			digests[source.NewLocation(f).Coordinates] = []file.Digest{}
 			continue
 		}
 
 		for _, hash := range hashes {
 			h := hash.New()
 			h.Write(b)
-			digests[source.NewLocation(f).Coordinates] = append(digests[source.NewLocation(f).Coordinates], Digest{
-				Algorithm: CleanDigestAlgorithmName(hash.String()),
+			digests[source.NewLocation(f).Coordinates] = append(digests[source.NewLocation(f).Coordinates], file.Digest{
+				Algorithm: file.CleanDigestAlgorithmName(hash.String()),
 				Value:     fmt.Sprintf("%x", h.Sum(nil)),
 			})
 		}
@@ -56,7 +54,7 @@ func TestDigestsCataloger(t *testing.T) {
 		name     string
 		digests  []crypto.Hash
 		files    []string
-		expected map[source.Coordinates][]Digest
+		expected map[source.Coordinates][]file.Digest
 	}{
 		{
 			name:     "md5",
@@ -74,7 +72,7 @@ func TestDigestsCataloger(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
-			c, err := NewDigestsCataloger(test.digests)
+			c, err := NewCataloger(test.digests)
 			require.NoError(t, err)
 
 			src, err := source.NewFromDirectory("test-fixtures/last/")
@@ -92,14 +90,7 @@ func TestDigestsCataloger(t *testing.T) {
 }
 
 func TestDigestsCataloger_MixFileTypes(t *testing.T) {
-	testImage := "image-file-type-mix"
-
-	if *updateImageGoldenFiles {
-		imagetest.UpdateGoldenFixtureImage(t, testImage)
-	}
-
-	img := imagetest.GetGoldenFixtureImage(t, testImage)
-
+	img := imagetest.GetFixtureImage(t, "docker-archive", "image-file-type-mix")
 	src, err := source.NewFromImage(img, "---")
 	if err != nil {
 		t.Fatalf("could not create source: %+v", err)
@@ -140,7 +131,7 @@ func TestDigestsCataloger_MixFileTypes(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.path, func(t *testing.T) {
-			c, err := NewDigestsCataloger([]crypto.Hash{crypto.MD5})
+			c, err := NewCataloger([]crypto.Hash{crypto.MD5})
 			if err != nil {
 				t.Fatalf("unable to get cataloger: %+v", err)
 			}
@@ -150,7 +141,7 @@ func TestDigestsCataloger_MixFileTypes(t *testing.T) {
 				t.Fatalf("could not catalog: %+v", err)
 			}
 
-			_, ref, err := img.SquashedTree().File(file.Path(test.path))
+			_, ref, err := img.SquashedTree().File(stereoscopeFile.Path(test.path))
 			if err != nil {
 				t.Fatalf("unable to get file=%q : %+v", test.path, err)
 			}

syft/file/cataloger/filedigests/test-fixtures/image-file-type-mix/Dockerfile

@@ -4,7 +4,6 @@ ADD file-1.txt .
 RUN chmod 644 file-1.txt
 RUN chown 1:2 file-1.txt
 RUN ln -s file-1.txt symlink-1
-# note: hard links may behave inconsistently, this should be a golden image
 RUN ln file-1.txt hardlink-1
 RUN mknod char-device-1 c 89 1
 RUN mknod block-device-1 b 0 1

syft/file/cataloger/filedigests/test-fixtures/last/path.txt

@@ -0,0 +1 @@
+test-fixtures/last/path.txt file contents!

syft/file/cataloger/filemetadata/cataloger.go

@@ -1,4 +1,4 @@
-package file
+package filemetadata
 
 import (
 	"github.com/anchore/syft/internal/bus"
@@ -9,14 +9,14 @@ import (
 	"github.com/wagoodman/go-progress"
 )
 
-type MetadataCataloger struct {
+type Cataloger struct {
 }
 
-func NewMetadataCataloger() *MetadataCataloger {
-	return &MetadataCataloger{}
+func NewCataloger() *Cataloger {
+	return &Cataloger{}
 }
 
-func (i *MetadataCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates]source.FileMetadata, error) {
+func (i *Cataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates]source.FileMetadata, error) {
 	results := make(map[source.Coordinates]source.FileMetadata)
 	var locations []source.Location
 	for location := range resolver.AllLocations() {

syft/file/cataloger/filemetadata/cataloger_test.go

@@ -1,7 +1,6 @@
-package file
+package filemetadata
 
 import (
-	"flag"
 	"os"
 	"testing"
 
@@ -11,18 +10,10 @@ import (
 	"github.com/stretchr/testify/assert"
 )
 
-var updateImageGoldenFiles = flag.Bool("update-image", false, "update the golden fixture images used for testing")
-
 func TestFileMetadataCataloger(t *testing.T) {
-	testImage := "image-file-type-mix"
+	img := imagetest.GetFixtureImage(t, "docker-archive", "image-file-type-mix")
 
-	if *updateImageGoldenFiles {
-		imagetest.UpdateGoldenFixtureImage(t, testImage)
-	}
-
-	img := imagetest.GetGoldenFixtureImage(t, testImage)
-
-	c := NewMetadataCataloger()
+	c := NewCataloger()
 
 	src, err := source.NewFromImage(img, "---")
 	if err != nil {

syft/file/cataloger/filemetadata/test-fixtures/image-file-type-mix/Dockerfile

@@ -0,0 +1,12 @@
+FROM busybox:latest
+
+ADD file-1.txt .
+RUN chmod 644 file-1.txt
+RUN chown 1:2 file-1.txt
+RUN ln -s file-1.txt symlink-1
+RUN ln file-1.txt hardlink-1
+RUN mknod char-device-1 c 89 1
+RUN mknod block-device-1 b 0 1
+RUN mknod fifo-1 p
+RUN mkdir /dir
+RUN rm -rf home etc/group etc/localtime etc/mtab etc/network etc/passwd etc/shadow var usr bin/*

syft/file/cataloger/filemetadata/test-fixtures/image-file-type-mix/file-1.txt

@@ -0,0 +1 @@
+file 1!

syft/file/cataloger/secrets/cataloger.go

@@ -1,23 +1,22 @@
-package file
+package secrets
 
 import (
 	"bytes"
 	"fmt"
-	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/syft/event"
-	"github.com/anchore/syft/syft/event/monitor"
-	"github.com/wagoodman/go-partybus"
-	"github.com/wagoodman/go-progress"
 	"io"
 	"io/ioutil"
 	"regexp"
 	"sort"
 
 	"github.com/anchore/syft/internal"
-
+	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/event/monitor"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
+	"github.com/wagoodman/go-partybus"
+	"github.com/wagoodman/go-progress"
 )
 
 var DefaultSecretsPatterns = map[string]string{
@@ -28,38 +27,38 @@ var DefaultSecretsPatterns = map[string]string{
 	"generic-api-key":    `(?i)api(-|_)?key["'=:\s]*?(?P<value>[A-Z0-9]{20,60})["']?(\s|$)`,
 }
 
-type SecretsCatalogerConfig struct {
+type CatalogerConfig struct {
 	Patterns     map[string]*regexp.Regexp
 	RevealValues bool
 	MaxFileSize  int64
 }
 
-type SecretsCataloger struct {
-	config SecretsCatalogerConfig
+type Cataloger struct {
+	config CatalogerConfig
 }
 
-func DefaultSecretsCatalogerConfig() SecretsCatalogerConfig {
-	patterns, err := GenerateSearchPatterns(DefaultSecretsPatterns, nil, nil)
+func DefaultCatalogerConfig() CatalogerConfig {
+	patterns, err := file.GenerateSearchPatterns(DefaultSecretsPatterns, nil, nil)
 	if err != nil {
 		patterns = make(map[string]*regexp.Regexp)
 		log.Errorf("unable to create default secrets config: %w", err)
 	}
-	return SecretsCatalogerConfig{
+	return CatalogerConfig{
 		Patterns:     patterns,
 		RevealValues: false,
 		MaxFileSize:  1 * file.MB,
 	}
 }
 
-func NewSecretsCataloger(config SecretsCatalogerConfig) (*SecretsCataloger, error) {
-	return &SecretsCataloger{
+func NewCataloger(config CatalogerConfig) (*Cataloger, error) {
+	return &Cataloger{
 		config: config,
 	}, nil
 }
 
-func (i *SecretsCataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]SearchResult, error) {
-	results := make(map[source.Coordinates][]SearchResult)
-	locations := allRegularFiles(resolver)
+func (i *Cataloger) Catalog(resolver source.FileResolver) (map[source.Coordinates][]file.SearchResult, error) {
+	results := make(map[source.Coordinates][]file.SearchResult)
+	locations := source.AllRegularFiles(resolver)
 	stage, prog, secretsDiscovered := newSecretsCatalogerMonitor(int64(len(locations)))
 	for _, location := range locations {
 		stage.Current = location.RealPath
@@ -83,7 +82,7 @@ func (i *SecretsCataloger) Catalog(resolver source.FileResolver) (map[source.Coo
 	return results, nil
 }
 
-func (i *SecretsCataloger) catalogLocation(resolver source.FileResolver, location source.Location) ([]SearchResult, error) {
+func (i *Cataloger) catalogLocation(resolver source.FileResolver, location source.Location) ([]file.SearchResult, error) {
 	metadata, err := resolver.FileMetadataByLocation(location)
 	if err != nil {
 		return nil, err

syft/file/cataloger/secrets/cataloger_test.go

@@ -1,13 +1,11 @@
-package file
+package secrets
 
 import (
 	"regexp"
 	"testing"
 
-	"github.com/anchore/syft/internal/file"
-
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/source"
-
 	"github.com/stretchr/testify/assert"
 )
 
@@ -18,7 +16,7 @@ func TestSecretsCataloger(t *testing.T) {
 		reveal         bool
 		maxSize        int64
 		patterns       map[string]string
-		expected       []SearchResult
+		expected       []file.SearchResult
 		constructorErr bool
 		catalogErr     bool
 	}{
@@ -29,7 +27,7 @@ func TestSecretsCataloger(t *testing.T) {
 			patterns: map[string]string{
 				"simple-secret-key": `^secret_key=.*`,
 			},
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "simple-secret-key",
 					LineNumber:     2,
@@ -47,7 +45,7 @@ func TestSecretsCataloger(t *testing.T) {
 			patterns: map[string]string{
 				"simple-secret-key": `^secret_key=.*`,
 			},
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "simple-secret-key",
 					LineNumber:     2,
@@ -65,7 +63,7 @@ func TestSecretsCataloger(t *testing.T) {
 			patterns: map[string]string{
 				"simple-secret-key": `^secret_key=(?P<value>.*)`,
 			},
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "simple-secret-key",
 					LineNumber:     2,
@@ -83,7 +81,7 @@ func TestSecretsCataloger(t *testing.T) {
 			patterns: map[string]string{
 				"simple-secret-key": `secret_key=.*`,
 			},
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "simple-secret-key",
 					LineNumber:     1,
@@ -126,7 +124,7 @@ func TestSecretsCataloger(t *testing.T) {
 			patterns: map[string]string{
 				"simple-secret-key": `secret_key=(?P<value>.*)`,
 			},
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "simple-secret-key",
 					LineNumber:     1,
@@ -177,7 +175,11 @@ func TestSecretsCataloger(t *testing.T) {
 				regexObjs[name] = obj
 			}
 
-			c, err := NewSecretsCataloger(regexObjs, test.reveal, test.maxSize)
+			c, err := NewCataloger(CatalogerConfig{
+				Patterns:     regexObjs,
+				RevealValues: test.reveal,
+				MaxFileSize:  test.maxSize,
+			})
 			if err != nil && !test.constructorErr {
 				t.Fatalf("could not create cataloger (but should have been able to): %+v", err)
 			} else if err == nil && test.constructorErr {
@@ -208,18 +210,18 @@ func TestSecretsCataloger(t *testing.T) {
 }
 
 func TestSecretsCataloger_DefaultSecrets(t *testing.T) {
-	regexObjs, err := GenerateSearchPatterns(DefaultSecretsPatterns, nil, nil)
+	regexObjs, err := file.GenerateSearchPatterns(DefaultSecretsPatterns, nil, nil)
 	if err != nil {
 		t.Fatalf("unable to get patterns: %+v", err)
 	}
 
 	tests := []struct {
 		fixture  string
-		expected []SearchResult
+		expected []file.SearchResult
 	}{
 		{
 			fixture: "test-fixtures/secrets/default/aws.env",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "aws-access-key",
 					LineNumber:     2,
@@ -240,7 +242,7 @@ func TestSecretsCataloger_DefaultSecrets(t *testing.T) {
 		},
 		{
 			fixture: "test-fixtures/secrets/default/aws.ini",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "aws-access-key",
 					LineNumber:     3,
@@ -261,7 +263,7 @@ func TestSecretsCataloger_DefaultSecrets(t *testing.T) {
 		},
 		{
 			fixture: "test-fixtures/secrets/default/private-key.pem",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "pem-private-key",
 					LineNumber:     2,
@@ -281,7 +283,7 @@ z3P668YfhUbKdRF6S42Cg6zn
 		},
 		{
 			fixture: "test-fixtures/secrets/default/private-key-openssl.pem",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "pem-private-key",
 					LineNumber:     2,
@@ -303,7 +305,7 @@ z3P668YfhUbKdRF6S42Cg6zn
 			// note: this test proves that the PEM regex matches the smallest possible match
 			// since the test catches two adjacent secrets
 			fixture: "test-fixtures/secrets/default/private-keys.pem",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "pem-private-key",
 					LineNumber:     1,
@@ -346,7 +348,7 @@ j4f668YfhUbKdRF6S6734856
 			// 2. a named capture group with the correct line number and line offset case
 			// 3. the named capture group is in a different line than the match start, and both the match start and the capture group have different line offsets
 			fixture: "test-fixtures/secrets/default/docker-config.json",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "docker-config-auth",
 					LineNumber:     5,
@@ -363,7 +365,7 @@ j4f668YfhUbKdRF6S6734856
 		},
 		{
 			fixture: "test-fixtures/secrets/default/api-key.txt",
-			expected: []SearchResult{
+			expected: []file.SearchResult{
 				{
 					Classification: "generic-api-key",
 					LineNumber:     2,
@@ -419,7 +421,11 @@ j4f668YfhUbKdRF6S6734856
 	for _, test := range tests {
 		t.Run(test.fixture, func(t *testing.T) {
 
-			c, err := NewSecretsCataloger(regexObjs, true, 10*file.MB)
+			c, err := NewCataloger(CatalogerConfig{
+				Patterns:     regexObjs,
+				RevealValues: true,
+				MaxFileSize:  10 * file.MB,
+			})
 			if err != nil {
 				t.Fatalf("could not create cataloger: %+v", err)
 			}

syft/file/cataloger/secrets/newline_counter.go

@@ -1,4 +1,4 @@
-package file
+package secrets
 
 import "io"
 

syft/file/cataloger/secrets/newline_counter_test.go

@@ -1,4 +1,4 @@
-package file
+package secrets
 
 import (
 	"bufio"

syft/file/cataloger/secrets/secrets_search_by_line_strategy.go

@@ -1,9 +1,10 @@
-package file
+package secrets
 
 import (
 	"bufio"
 	"errors"
 	"fmt"
+	"github.com/anchore/syft/syft/file"
 	"io"
 	"io/ioutil"
 	"regexp"
@@ -13,7 +14,7 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
-func catalogLocationByLine(resolver source.FileResolver, location source.Location, patterns map[string]*regexp.Regexp) ([]SearchResult, error) {
+func catalogLocationByLine(resolver source.FileResolver, location source.Location, patterns map[string]*regexp.Regexp) ([]file.SearchResult, error) {
 	readCloser, err := resolver.FileContentsByLocation(location)
 	if err != nil {
 		return nil, fmt.Errorf("unable to fetch reader for location=%q : %w", location, err)
@@ -22,7 +23,7 @@ func catalogLocationByLine(resolver source.FileResolver, location source.Locatio
 
 	var scanner = bufio.NewReader(readCloser)
 	var position int64
-	var allSecrets []SearchResult
+	var allSecrets []file.SearchResult
 	var lineNo int64
 	var readErr error
 	for !errors.Is(readErr, io.EOF) {
@@ -45,8 +46,8 @@ func catalogLocationByLine(resolver source.FileResolver, location source.Locatio
 	return allSecrets, nil
 }
 
-func searchForSecretsWithinLine(resolver source.FileResolver, location source.Location, patterns map[string]*regexp.Regexp, line []byte, lineNo int64, position int64) ([]SearchResult, error) {
-	var secrets []SearchResult
+func searchForSecretsWithinLine(resolver source.FileResolver, location source.Location, patterns map[string]*regexp.Regexp, line []byte, lineNo int64, position int64) ([]file.SearchResult, error) {
+	var secrets []file.SearchResult
 	for name, pattern := range patterns {
 		matches := pattern.FindAllIndex(line, -1)
 		for i, match := range matches {
@@ -91,7 +92,7 @@ func readerAtPosition(resolver source.FileResolver, location source.Location, se
 	return readCloser, nil
 }
 
-func extractSecretFromPosition(readCloser io.ReadCloser, name string, pattern *regexp.Regexp, lineNo, lineOffset, seekPosition int64) *SearchResult {
+func extractSecretFromPosition(readCloser io.ReadCloser, name string, pattern *regexp.Regexp, lineNo, lineOffset, seekPosition int64) *file.SearchResult {
 	reader := &newlineCounter{RuneReader: bufio.NewReader(readCloser)}
 	positions := pattern.FindReaderSubmatchIndex(reader)
 	if len(positions) == 0 {
@@ -127,7 +128,7 @@ func extractSecretFromPosition(readCloser io.ReadCloser, name string, pattern *r
 		lineOffsetOfSecret += lineOffset
 	}
 
-	return &SearchResult{
+	return &file.SearchResult{
 		Classification: name,
 		SeekPosition:   start + seekPosition,
 		Length:         stop - start,

syft/file/classification.go

@@ -0,0 +1,6 @@
+package file
+
+type Classification struct {
+	Class    string            `json:"class"`
+	Metadata map[string]string `json:"metadata"`
+}

syft/file/classifier.go

@@ -11,6 +11,12 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
+type Classifier struct {
+	Class                    string
+	FilepathPatterns         []*regexp.Regexp
+	EvidencePatternTemplates []string
+}
+
 func DefaultClassifiers() []Classifier {
 	return []Classifier{
 		{
@@ -62,17 +68,6 @@ func DefaultClassifiers() []Classifier {
 	}
 }
 
-type Classifier struct {
-	Class                    string
-	FilepathPatterns         []*regexp.Regexp
-	EvidencePatternTemplates []string
-}
-
-type Classification struct {
-	Class    string            `json:"class"`
-	Metadata map[string]string `json:"metadata"`
-}
-
 func (c Classifier) Classify(resolver source.FileResolver, location source.Location) (*Classification, error) {
 	doesFilepathMatch, filepathNamedGroupValues := filepathMatches(c.FilepathPatterns, location)
 	if !doesFilepathMatch {

syft/file/opener.go

@@ -10,6 +10,12 @@ type Opener struct {
 	path string
 }
 
+func NewOpener(path string) Opener {
+	return Opener{
+		path: path,
+	}
+}
+
 // Open the stored path as a io.ReadCloser.
 func (o Opener) Open() (io.ReadCloser, error) {
 	return os.Open(o.path)

syft/file/test-fixtures/symlinked-root/nested/link-root

@@ -1 +0,0 @@
-../real-root

syft/file/test-fixtures/symlinked-root/real-root/file1.txt

@@ -1 +0,0 @@
-contents!

syft/file/test-fixtures/symlinked-root/real-root/nested/file2.txt

@@ -1 +0,0 @@
-more contents!

syft/file/test-fixtures/symlinked-root/real-root/nested/linked-file1.txt

@@ -1 +0,0 @@
-../file1.txt

syft/pkg/cataloger/java/archive_parser.go

@@ -2,15 +2,16 @@ package java
 
 import (
 	"fmt"
-	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+	"github.com/anchore/syft/internal/archive"
 	"io"
 	"path"
 	"strings"
 
-	"github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 )
 
 // integrity check
@@ -35,7 +36,7 @@ var archiveFormatGlobs = []string{
 }
 
 type archiveParser struct {
-	fileManifest file.ZipFileManifest
+	fileManifest archive.ZipFileManifest
 	virtualPath  string
 	archivePath  string
 	contentPath  string
@@ -74,7 +75,7 @@ func newJavaArchiveParser(virtualPath string, reader io.Reader, detectNested boo
 		return nil, cleanupFn, fmt.Errorf("unable to process java archive: %w", err)
 	}
 
-	fileManifest, err := file.NewZipFileManifest(archivePath)
+	fileManifest, err := archive.NewZipFileManifest(archivePath)
 	if err != nil {
 		return nil, cleanupFn, fmt.Errorf("unable to read files from java archive: %w", err)
 	}
@@ -144,7 +145,7 @@ func (j *archiveParser) discoverMainPackage() (*pkg.Package, error) {
 	}
 
 	// fetch the manifest file
-	contents, err := file.ContentsFromZip(j.archivePath, manifestMatches...)
+	contents, err := archive.ContentsFromZip(j.archivePath, manifestMatches...)
 	if err != nil {
 		return nil, fmt.Errorf("unable to extract java manifests (%s): %w", j.virtualPath, err)
 	}
@@ -213,9 +214,9 @@ func (j *archiveParser) discoverPkgsFromNestedArchives(parentPkg *pkg.Package) (
 
 // discoverPkgsFromZip finds Java archives within Java archives, returning all listed Java packages found and
 // associating each discovered package to the given parent package.
-func discoverPkgsFromZip(virtualPath, archivePath, contentPath string, fileManifest file.ZipFileManifest, parentPkg *pkg.Package) ([]*pkg.Package, []artifact.Relationship, error) {
+func discoverPkgsFromZip(virtualPath, archivePath, contentPath string, fileManifest archive.ZipFileManifest, parentPkg *pkg.Package) ([]*pkg.Package, []artifact.Relationship, error) {
 	// search and parse pom.properties files & fetch the contents
-	openers, err := file.ExtractFromZipToUniqueTempFile(archivePath, contentPath, fileManifest.GlobMatch(archiveFormatGlobs...)...)
+	openers, err := archive.ExtractFromZipToUniqueTempFile(archivePath, contentPath, fileManifest.GlobMatch(archiveFormatGlobs...)...)
 	if err != nil {
 		return nil, nil, fmt.Errorf("unable to extract files from zip: %w", err)
 	}
@@ -274,7 +275,7 @@ func discoverPkgsFromOpener(virtualPath, pathWithinArchive string, archiveOpener
 }
 
 func pomPropertiesByParentPath(archivePath string, extractPaths []string, virtualPath string) (map[string]pkg.PomProperties, error) {
-	contentsOfMavenPropertiesFiles, err := file.ContentsFromZip(archivePath, extractPaths...)
+	contentsOfMavenPropertiesFiles, err := archive.ContentsFromZip(archivePath, extractPaths...)
 	if err != nil {
 		return nil, fmt.Errorf("unable to extract maven files: %w", err)
 	}
@@ -302,7 +303,7 @@ func pomPropertiesByParentPath(archivePath string, extractPaths []string, virtua
 }
 
 func pomProjectByParentPath(archivePath string, extractPaths []string, virtualPath string) (map[string]pkg.PomProject, error) {
-	contentsOfMavenProjectFiles, err := file.ContentsFromZip(archivePath, extractPaths...)
+	contentsOfMavenProjectFiles, err := archive.ContentsFromZip(archivePath, extractPaths...)
 	if err != nil {
 		return nil, fmt.Errorf("unable to extract maven files: %w", err)
 	}

syft/pkg/cataloger/java/tar_wrapped_archive_parser.go

@@ -2,11 +2,10 @@ package java
 
 import (
 	"fmt"
+	"github.com/anchore/syft/internal/archive"
 	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 	"io"
 
-	"github.com/anchore/syft/internal/file"
-
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/pkg"
 )
@@ -59,7 +58,7 @@ func parseTarWrappedJavaArchive(virtualPath string, reader io.Reader) ([]*pkg.Pa
 }
 
 func discoverPkgsFromTar(virtualPath, archivePath, contentPath string) ([]*pkg.Package, []artifact.Relationship, error) {
-	openers, err := file.ExtractGlobsFromTarToUniqueTempFile(archivePath, contentPath, archiveFormatGlobs...)
+	openers, err := archive.ExtractGlobsFromTarToUniqueTempFile(archivePath, contentPath, archiveFormatGlobs...)
 	if err != nil {
 		return nil, nil, fmt.Errorf("unable to extract files from tar: %w", err)
 	}

syft/pkg/cataloger/java/zip_wrapped_archive_parser.go

@@ -2,11 +2,10 @@ package java
 
 import (
 	"fmt"
+	"github.com/anchore/syft/internal/archive"
 	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 	"io"
 
-	"github.com/anchore/syft/internal/file"
-
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/pkg"
 )
@@ -33,7 +32,7 @@ func parseZipWrappedJavaArchive(virtualPath string, reader io.Reader) ([]*pkg.Pa
 	// functions support zips with shell scripts prepended to the file. Specifically, the helpers use the central
 	// header at the end of the file to determine where the beginning of the zip payload is (unlike the standard lib
 	// or archiver).
-	fileManifest, err := file.NewZipFileManifest(archivePath)
+	fileManifest, err := archive.NewZipFileManifest(archivePath)
 	if err != nil {
 		return nil, nil, fmt.Errorf("unable to read files from java archive: %w", err)
 	}

syft/pkg/cataloger/python/parse_wheel_egg_metadata.go

@@ -3,11 +3,11 @@ package python
 import (
 	"bufio"
 	"fmt"
+	"github.com/anchore/syft/syft/file"
 	"io"
 	"path/filepath"
 	"strings"
 
-	"github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/log"
 
 	"github.com/mitchellh/mapstructure"

syft/source/all_regular_files.go

@@ -1,11 +1,10 @@
-package file
+package source
 
 import (
 	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/source"
 )
 
-func allRegularFiles(resolver source.FileResolver) (locations []source.Location) {
+func AllRegularFiles(resolver FileResolver) (locations []Location) {
 	for location := range resolver.AllLocations() {
 		resolvedLocations, err := resolver.FilesByPath(location.RealPath)
 		if err != nil {
@@ -20,7 +19,7 @@ func allRegularFiles(resolver source.FileResolver) (locations []source.Location)
 				continue
 			}
 
-			if metadata.Type != source.RegularFile {
+			if metadata.Type != RegularFile {
 				continue
 			}
 			locations = append(locations, resolvedLocation)

syft/source/all_regular_files_test.go

@@ -1,8 +1,7 @@
-package file
+package source
 
 import (
 	"github.com/anchore/stereoscope/pkg/imagetest"
-	"github.com/anchore/syft/syft/source"
 	"github.com/scylladb/go-set/strset"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -16,25 +15,19 @@ func Test_allRegularFiles(t *testing.T) {
 	}
 	tests := []struct {
 		name             string
-		setup            func() source.FileResolver
+		setup            func() FileResolver
 		wantRealPaths    *strset.Set
 		wantVirtualPaths *strset.Set
 	}{
 		{
 			name: "image",
-			setup: func() source.FileResolver {
-				testImage := "image-file-type-mix"
+			setup: func() FileResolver {
+				img := imagetest.GetFixtureImage(t, "docker-archive", "image-file-type-mix")
 
-				if *updateImageGoldenFiles {
-					imagetest.UpdateGoldenFixtureImage(t, testImage)
-				}
-
-				img := imagetest.GetGoldenFixtureImage(t, testImage)
-
-				s, err := source.NewFromImage(img, "---")
+				s, err := NewFromImage(img, "---")
 				require.NoError(t, err)
 
-				r, err := s.FileResolver(source.SquashedScope)
+				r, err := s.FileResolver(SquashedScope)
 				require.NoError(t, err)
 
 				return r
@@ -44,10 +37,10 @@ func Test_allRegularFiles(t *testing.T) {
 		},
 		{
 			name: "directory",
-			setup: func() source.FileResolver {
-				s, err := source.NewFromDirectory("test-fixtures/symlinked-root/nested/link-root")
+			setup: func() FileResolver {
+				s, err := NewFromDirectory("test-fixtures/symlinked-root/nested/link-root")
 				require.NoError(t, err)
-				r, err := s.FileResolver(source.SquashedScope)
+				r, err := s.FileResolver(SquashedScope)
 				require.NoError(t, err)
 				return r
 			},
@@ -58,7 +51,7 @@ func Test_allRegularFiles(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			resolver := tt.setup()
-			locations := allRegularFiles(resolver)
+			locations := AllRegularFiles(resolver)
 			realLocations := strset.New()
 			virtualLocations := strset.New()
 			for _, l := range locations {

syft/source/test-fixtures/image-file-type-mix/Dockerfile

@@ -0,0 +1,12 @@
+FROM busybox:latest
+
+ADD file-1.txt .
+RUN chmod 644 file-1.txt
+RUN chown 1:2 file-1.txt
+RUN ln -s file-1.txt symlink-1
+RUN ln file-1.txt hardlink-1
+RUN mknod char-device-1 c 89 1
+RUN mknod block-device-1 b 0 1
+RUN mknod fifo-1 p
+RUN mkdir /dir
+RUN rm -rf home etc/group etc/localtime etc/mtab etc/network etc/passwd etc/shadow var usr bin/*

syft/source/test-fixtures/image-file-type-mix/file-1.txt

@@ -0,0 +1 @@
+file 1!

syft/tasks.go

@@ -3,7 +3,11 @@ package syft
 import (
 	"fmt"
 	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/file/cataloger/fileclassifier"
+	"github.com/anchore/syft/syft/file/cataloger/filecontents"
+	"github.com/anchore/syft/syft/file/cataloger/filedigests"
+	"github.com/anchore/syft/syft/file/cataloger/filemetadata"
+	"github.com/anchore/syft/syft/file/cataloger/secrets"
 	"github.com/anchore/syft/syft/linux"
 	"github.com/anchore/syft/syft/pkg/cataloger/packages"
 	"github.com/anchore/syft/syft/sbom"
@@ -13,7 +17,7 @@ import (
 type task func(*sbom.Artifacts, *source.Source) ([]artifact.Relationship, error)
 type taskGenerator func(CatalogingConfig) (task, error)
 
-func generateCatalogPackagesTask(config CatalogingConfig) (task, error) {
+func generatePackagesCatalogingTask(config CatalogingConfig) (task, error) {
 	if len(config.PackageCatalogers) == 0 {
 		return nil, nil
 	}
@@ -38,12 +42,12 @@ func generateCatalogPackagesTask(config CatalogingConfig) (task, error) {
 	}, nil
 }
 
-func generateCatalogFileMetadataTask(config CatalogingConfig) (task, error) {
+func generateFileMetadataCatalogingTask(config CatalogingConfig) (task, error) {
 	if !config.CaptureFileMetadata {
 		return nil, nil
 	}
 
-	metadataCataloger := file.NewMetadataCataloger()
+	cataloger := filemetadata.NewCataloger()
 
 	return func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(config.Scope)
@@ -51,7 +55,7 @@ func generateCatalogFileMetadataTask(config CatalogingConfig) (task, error) {
 			return nil, err
 		}
 
-		result, err := metadataCataloger.Catalog(resolver)
+		result, err := cataloger.Catalog(resolver)
 		if err != nil {
 			return nil, err
 		}
@@ -61,12 +65,12 @@ func generateCatalogFileMetadataTask(config CatalogingConfig) (task, error) {
 
 }
 
-func generateCatalogFileDigestsTask(config CatalogingConfig) (task, error) {
+func generateFileDigestsCatalogingTask(config CatalogingConfig) (task, error) {
 	if len(config.DigestHashes) == 0 {
 		return nil, nil
 	}
 
-	digestsCataloger, err := file.NewDigestsCataloger(config.DigestHashes)
+	cataloger, err := filedigests.NewCataloger(config.DigestHashes)
 	if err != nil {
 		return nil, err
 	}
@@ -77,7 +81,7 @@ func generateCatalogFileDigestsTask(config CatalogingConfig) (task, error) {
 			return nil, err
 		}
 
-		result, err := digestsCataloger.Catalog(resolver)
+		result, err := cataloger.Catalog(resolver)
 		if err != nil {
 			return nil, err
 		}
@@ -87,12 +91,12 @@ func generateCatalogFileDigestsTask(config CatalogingConfig) (task, error) {
 
 }
 
-func generateCatalogContentsTask(config CatalogingConfig) (task, error) {
-	if len(config.ContentsConfig.Globs) > 0 {
+func generateContentsCatalogingTask(config CatalogingConfig) (task, error) {
+	if len(config.ContentsConfig.Globs) == 0 {
 		return nil, nil
 	}
 
-	contentsCataloger, err := file.NewContentsCataloger(config.ContentsConfig)
+	cataloger, err := filecontents.NewCataloger(config.ContentsConfig)
 	if err != nil {
 		return nil, err
 	}
@@ -103,7 +107,7 @@ func generateCatalogContentsTask(config CatalogingConfig) (task, error) {
 			return nil, err
 		}
 
-		result, err := contentsCataloger.Catalog(resolver)
+		result, err := cataloger.Catalog(resolver)
 		if err != nil {
 			return nil, err
 		}
@@ -112,12 +116,12 @@ func generateCatalogContentsTask(config CatalogingConfig) (task, error) {
 	}, nil
 }
 
-func generateCatalogSecretsTask(config CatalogingConfig) (task, error) {
+func generateSecretsCatalogingTask(config CatalogingConfig) (task, error) {
 	if !config.CaptureSecrets {
 		return nil, nil
 	}
 
-	secretsCataloger, err := file.NewSecretsCataloger(config.SecretsConfig)
+	cataloger, err := secrets.NewCataloger(config.SecretsConfig)
 	if err != nil {
 		return nil, err
 	}
@@ -128,7 +132,7 @@ func generateCatalogSecretsTask(config CatalogingConfig) (task, error) {
 			return nil, err
 		}
 
-		result, err := secretsCataloger.Catalog(resolver)
+		result, err := cataloger.Catalog(resolver)
 		if err != nil {
 			return nil, err
 		}
@@ -138,12 +142,12 @@ func generateCatalogSecretsTask(config CatalogingConfig) (task, error) {
 
 }
 
-func generateCatalogFileClassificationsTask(config CatalogingConfig) (task, error) {
+func generateFileClassifierTask(config CatalogingConfig) (task, error) {
 	if !config.ClassifyFiles {
 		return nil, nil
 	}
 
-	classifierCataloger, err := file.NewClassificationCataloger(config.FileClassifiers)
+	cataloger, err := fileclassifier.NewCataloger(config.FileClassifiers)
 	if err != nil {
 		return nil, err
 	}
@@ -154,7 +158,7 @@ func generateCatalogFileClassificationsTask(config CatalogingConfig) (task, erro
 			return nil, err
 		}
 
-		result, err := classifierCataloger.Catalog(resolver)
+		result, err := cataloger.Catalog(resolver)
 		if err != nil {
 			return nil, err
 		}