feat: add --ignore-file filtering

CHANGELOG.md

@@ -12,6 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - KDL Document Language syntax validation (`.kdl`) via [sblinch/kdl-go](https://github.com/sblinch/kdl-go) (closes #463)
 - Documentation website at https://boeing.github.io/config-file-validator
 - `--reporter=github` option that emits validation errors as GitHub Actions workflow commands so they appear as inline PR annotations, without requiring the separate `validate-configs-action` wrapper (closes #459)
+- `--ignore-file` option for applying gitignore-style patterns from files like `.dockerignore` or `.prettierignore` during file discovery (closes #457)
 - Justfile syntax validation (`.just`, `justfile`, `Justfile`, `.justfile`) via embedded [go-just](https://github.com/Boeing/go-just) parser
 - Automatic file type detection from GitHub Linguist's `languages.yml` via `go generate`
 - ~90 known filenames auto-detected (`.babelrc`, `tsconfig.json`, `Pipfile`, `pom.xml`, `.gitconfig`, etc.)

cmd/validator/testdata/ignore_file.txtar

@@ -0,0 +1,58 @@
+# --ignore-file skips files matched by explicit ignore files without a git repo
+exec validator --ignore-file=.dockerignore project
+stdout '✓.*keep.json'
+! stdout 'ignored.json'
+! stdout 'build'
+
+# Multiple ignore files are additive
+exec validator --ignore-file=.dockerignore --ignore-file=.prettierignore multi
+stdout '✓.*keep.json'
+! stdout 'drop.json'
+! stdout 'skip.yaml'
+
+# Missing ignore files are skipped
+exec validator --ignore-file=missing.ignore project
+stdout 'keep.json'
+stdout 'ignored.json'
+
+# .cfv.toml ignore-files key works
+exec validator --config=cfv/.cfv.toml cfv
+stdout '✓.*app.json'
+! stdout 'out.json'
+
+# CFV_IGNORE_FILES env var works
+env CFV_IGNORE_FILES=.dockerignore,.prettierignore
+exec validator multi
+stdout '✓.*keep.json'
+! stdout 'drop.json'
+! stdout 'skip.yaml'
+
+-- project/.dockerignore --
+ignored.json
+build/
+-- project/keep.json --
+{"key": "value"}
+-- project/ignored.json --
+{"ignored": true}
+-- project/build/output.json --
+{"build": true}
+
+-- multi/.dockerignore --
+drop.json
+-- multi/.prettierignore --
+skip.yaml
+-- multi/keep.json --
+{"key": "value"}
+-- multi/drop.json --
+{"drop": true}
+-- multi/skip.yaml --
+skip: true
+
+-- cfv/.cfv.toml --
+ignore-files = [".dockerignore"]
+-- cfv/.dockerignore --
+gen/
+-- cfv/app.json --
+{"app": true}
+-- cfv/gen/out.json --
+{"gen": true}

cmd/validator/validator.go

@@ -80,6 +80,7 @@ type validatorConfig struct {
 	configPath       *string
 	noConfig         *bool
 	gitignore        *bool
+	ignoreFiles      ignoreFileFlags
 }
 
 type reporterFlags []string
@@ -120,6 +121,17 @@ func (sf *schemaMapFlags) Set(value string) error {
 	return nil
 }
 
+type ignoreFileFlags []string
+
+func (iff *ignoreFileFlags) String() string {
+	return fmt.Sprint(*iff)
+}
+
+func (iff *ignoreFileFlags) Set(value string) error {
+	*iff = append(*iff, value)
+	return nil
+}
+
 // Custom Usage function to cover. Uses the current flagSet when available.
 func validatorUsage() {
 	fmt.Println("Usage: validator [OPTIONS] [<search_path>...]")
@@ -241,13 +253,22 @@ func getFlags(args []string) (validatorConfig, error) {
 			"  --schema-map=\"**/config.xml:schemas/config.xsd\"",
 	)
 
+	ignoreFileConfigFlags := ignoreFileFlags{}
+	flagSet.Var(
+		&ignoreFileConfigFlags,
+		"ignore-file",
+		"Path to a gitignore-style file with patterns to skip during file discovery. "+
+			"Paths are relative to each search path. Can be specified multiple times.",
+	)
+
 	if err := flagSet.Parse(args); err != nil {
 		return validatorConfig{}, err
 	}
 
 	if err := applyDefaultFlagsFromEnv(); err != nil {
 		return validatorConfig{}, err
 	}
+	setIgnoreFilesFromEnvIfNotSet(&ignoreFileConfigFlags)
 
 	reporterConf, err := parseReporterFlags(reporterConfigFlags)
 	if err != nil {
@@ -287,6 +308,7 @@ func getFlags(args []string) (validatorConfig, error) {
 		configPathPtr,
 		noConfigPtr,
 		gitignorePtr,
+		ignoreFileConfigFlags,
 	}
 
 	return config, nil
@@ -500,6 +522,25 @@ func setFlagFromEnvIfNotSet(flagName string, envVar string) error {
 	return nil
 }
 
+func setIgnoreFilesFromEnvIfNotSet(flags *ignoreFileFlags) {
+	if isFlagSet("ignore-file") {
+		return
+	}
+
+	envVarValue, ok := os.LookupEnv("CFV_IGNORE_FILES")
+	if !ok || envVarValue == "" {
+		return
+	}
+
+	for _, ignoreFile := range strings.Split(envVarValue, ",") {
+		ignoreFile = strings.TrimSpace(ignoreFile)
+		if ignoreFile == "" {
+			continue
+		}
+		*flags = append(*flags, ignoreFile)
+	}
+}
+
 // Return the reporter associated with the
 // reportType string
 func getReporter(reportType, outputDest string) reporter.Reporter {
@@ -761,6 +802,9 @@ func buildFinderOpts(cfg validatorConfig, excludeFileTypes []string, fileTypes [
 	if *cfg.gitignore {
 		fsOpts = append(fsOpts, finder.WithGitignore(true))
 	}
+	if len(cfg.ignoreFiles) > 0 {
+		fsOpts = append(fsOpts, finder.WithIgnoreFiles([]string(cfg.ignoreFiles)))
+	}
 
 	return fsOpts, nil
 }
@@ -918,6 +962,9 @@ func applyConfigFile(cfg *validatorConfig) (*configfile.ValidatorOptions, error)
 	if !isFlagSet("gitignore") && fileCfg.Gitignore != nil {
 		cfg.gitignore = fileCfg.Gitignore
 	}
+	if !isFlagSet("ignore-file") && len(fileCfg.IgnoreFiles) > 0 {
+		cfg.ignoreFiles = ignoreFileFlags(fileCfg.IgnoreFiles)
+	}
 	if len(cfg.schemaMap) == 0 && len(fileCfg.SchemaMap) > 0 {
 		for pattern, schema := range fileCfg.SchemaMap {
 			cfg.schemaMap = append(cfg.schemaMap, pattern+":"+schema)

cmd/validator/validator_test.go

@@ -1,6 +1,8 @@
 package main
 
 import (
+	"os"
+	"path/filepath"
 	"testing"
 
 	"github.com/stretchr/testify/require"
@@ -29,6 +31,8 @@ func Test_getFlags(t *testing.T) {
 		{"type-map", []string{"--type-map=**/inventory:ini", "."}, false},
 		{"multiple type-maps", []string{"--type-map=**/inventory:ini", "--type-map=**/configs/*:properties", "."}, false},
 		{"require-schema", []string{"--require-schema", "."}, false},
+		{"ignore-file", []string{"--ignore-file=.dockerignore", "."}, false},
+		{"multiple ignore-files", []string{"--ignore-file=.dockerignore", "--ignore-file=.prettierignore", "."}, false},
 
 		// Invalid flag combinations
 		{"negative depth", []string{"-depth=-1", "."}, true},
@@ -96,6 +100,42 @@ func Test_getFlagsRejectsDuplicateReporterOutputDest(t *testing.T) {
 	}
 }
 
+func Test_ignoreFilesEnvVar(t *testing.T) {
+	t.Setenv("CFV_IGNORE_FILES", ".dockerignore, .prettierignore")
+
+	cfg, err := getFlags([]string{"."})
+	require.NoError(t, err)
+	require.Equal(t, ignoreFileFlags{".dockerignore", ".prettierignore"}, cfg.ignoreFiles)
+}
+
+func Test_ignoreFilesConfigOverridesEnvVar(t *testing.T) {
+	dir := t.TempDir()
+	configPath := filepath.Join(dir, ".cfv.toml")
+	require.NoError(t, os.WriteFile(configPath, []byte(`ignore-files = ["config.ignore"]`), 0600))
+	t.Setenv("CFV_IGNORE_FILES", "env.ignore")
+
+	cfg, err := getFlags([]string{"--config=" + configPath, "."})
+	require.NoError(t, err)
+
+	_, err = applyConfigFile(&cfg)
+	require.NoError(t, err)
+	require.Equal(t, ignoreFileFlags{"config.ignore"}, cfg.ignoreFiles)
+}
+
+func Test_ignoreFilesFlagOverridesConfigAndEnv(t *testing.T) {
+	dir := t.TempDir()
+	configPath := filepath.Join(dir, ".cfv.toml")
+	require.NoError(t, os.WriteFile(configPath, []byte(`ignore-files = ["config.ignore"]`), 0600))
+	t.Setenv("CFV_IGNORE_FILES", "env.ignore")
+
+	cfg, err := getFlags([]string{"--config=" + configPath, "--ignore-file=cli.ignore", "."})
+	require.NoError(t, err)
+
+	_, err = applyConfigFile(&cfg)
+	require.NoError(t, err)
+	require.Equal(t, ignoreFileFlags{"cli.ignore"}, cfg.ignoreFiles)
+}
+
 func Test_getExcludeFileTypes(t *testing.T) {
 	cases := []struct {
 		name     string

pkg/configfile/configfile.go

@@ -20,6 +20,7 @@ const FileName = ".cfv.toml"
 type Config struct {
 	ExcludeDirs      []string          `toml:"exclude-dirs"`
 	ExcludeFileTypes []string          `toml:"exclude-file-types"`
+	IgnoreFiles      []string          `toml:"ignore-files"`
 	FileTypes        []string          `toml:"file-types"`
 	Depth            *int              `toml:"depth"`
 	Reporter         []string          `toml:"reporter"`

pkg/configfile/configfile_test.go

@@ -14,6 +14,7 @@ func TestLoadValid(t *testing.T) {
 	writeConfig(t, dir, `
 exclude-dirs = ["node_modules", ".git"]
 exclude-file-types = ["csv"]
+ignore-files = [".dockerignore", ".prettierignore"]
 depth = 2
 quiet = true
 schemastore = true
@@ -29,6 +30,7 @@ schemastore = true
 	require.NoError(t, err)
 	require.Equal(t, []string{"node_modules", ".git"}, cfg.ExcludeDirs)
 	require.Equal(t, []string{"csv"}, cfg.ExcludeFileTypes)
+	require.Equal(t, []string{".dockerignore", ".prettierignore"}, cfg.IgnoreFiles)
 	require.Equal(t, 2, *cfg.Depth)
 	require.True(t, *cfg.Quiet)
 	require.True(t, *cfg.SchemaStore)

pkg/configfile/schema.json

@@ -14,6 +14,11 @@
       "items": { "type": "string" },
       "description": "File types to ignore"
     },
+    "ignore-files": {
+      "type": "array",
+      "items": { "type": "string" },
+      "description": "Gitignore-style pattern files to apply during file discovery"
+    },
     "file-types": {
       "type": "array",
       "items": { "type": "string" },

pkg/finder/finder_test.go

@@ -678,6 +678,57 @@ func Test_fsFinderGitignoreDisabled(t *testing.T) {
 	require.Len(t, files, 2, "without WithGitignore, .gitignore should have no effect")
 }
 
+func Test_fsFinderIgnoreFiles(t *testing.T) {
+	dir := t.TempDir()
+	testhelper.WriteFile(t, dir, "keep.json", testhelper.ValidContent["json"])
+	testhelper.WriteFile(t, dir, "drop.json", testhelper.ValidContent["json"])
+	build := testhelper.CreateSubdir(t, dir, "build")
+	testhelper.WriteFile(t, build, "skip.yaml", testhelper.ValidContent["yaml"])
+	testhelper.WriteFile(t, dir, ".dockerignore", "drop.json\nbuild/\n")
+
+	fsFinder := FileSystemFinderInit(
+		WithPathRoots(dir),
+		WithIgnoreFiles([]string{"missing.ignore", ".dockerignore"}),
+	)
+	files, err := fsFinder.Find()
+	require.NoError(t, err)
+	require.ElementsMatch(t, []string{"keep.json"}, fileNames(files))
+}
+
+func Test_fsFinderMultipleIgnoreFiles(t *testing.T) {
+	dir := t.TempDir()
+	testhelper.WriteFile(t, dir, "keep.json", testhelper.ValidContent["json"])
+	testhelper.WriteFile(t, dir, "drop.json", testhelper.ValidContent["json"])
+	testhelper.WriteFile(t, dir, "skip.yaml", testhelper.ValidContent["yaml"])
+	testhelper.WriteFile(t, dir, ".dockerignore", "drop.json\n")
+	testhelper.WriteFile(t, dir, ".prettierignore", "skip.yaml\n")
+
+	fsFinder := FileSystemFinderInit(
+		WithPathRoots(dir),
+		WithIgnoreFiles([]string{".dockerignore", ".prettierignore"}),
+	)
+	files, err := fsFinder.Find()
+	require.NoError(t, err)
+	require.ElementsMatch(t, []string{"keep.json"}, fileNames(files))
+}
+
+func Test_fsFinderSubdirectoryIgnoreFile(t *testing.T) {
+	dir := t.TempDir()
+	testhelper.WriteFile(t, dir, "foo.json", testhelper.ValidContent["json"])
+	sub := testhelper.CreateSubdir(t, dir, "subdir")
+	testhelper.WriteFile(t, sub, "foo.json", testhelper.ValidContent["json"])
+	testhelper.WriteFile(t, sub, ".dockerignore", "foo.json\n")
+
+	fsFinder := FileSystemFinderInit(
+		WithPathRoots(dir),
+		WithIgnoreFiles([]string{filepath.Join("subdir", ".dockerignore")}),
+	)
+	files, err := fsFinder.Find()
+	require.NoError(t, err)
+	require.ElementsMatch(t, []string{"foo.json"}, fileNames(files))
+	require.Equal(t, filepath.Join(dir, "foo.json"), files[0].Path)
+}
+
 // Test_fsFinderExtensionCacheNoPoison verifies that an unrecognized
 // extensionless file (e.g. LICENSE) does not poison the extension
 // cache and prevent subsequent extensionless known files from being found.