Introduce trufflehog:ignore tag feature (#1433)

* init ignore

* cleanup and add test

* update readme

README.md

@@ -151,6 +151,8 @@ trufflehog docker --image trufflesecurity/secrets --only-verified
   + Unauthenticated GitHub scans have rate limits. To improve your rate limits, include the `--token` flag with a personal access token
 + It says a private key was verified, what does that mean?
   + Check out our Driftwood blog post to learn how to do this, in short we've confirmed the key can be used live for SSH or SSL [Blog post](https://trufflesecurity.com/blog/driftwood-know-if-private-keys-are-sensitive/)
++ Is there an easy way to ignore specific secrets?
+  + If the scanned source [supports line numbers](https://github.com/trufflesecurity/trufflehog/blob/d6375ba92172fd830abb4247cca15e3176448c5d/pkg/engine/engine.go#L358-L365), then you can add a `trufflehog:ignore` comment on the line containing the secret to ignore that secrets. 
 
 
 # :newspaper: What's new in v3?

pkg/engine/engine.go

@@ -53,6 +53,8 @@ func WithConcurrency(concurrency int) EngineOption {
 	}
 }
 
+const ignoreTag = "trufflehog:ignore"
+
 func WithDetectors(verify bool, d ...detectors.Detector) EngineOption {
 	return func(e *Engine) {
 		if e.detectors == nil {
@@ -315,16 +317,20 @@ func (e *Engine) detectorWorker(ctx context.Context) {
 						}
 						for _, result := range results {
 							resultChunk := chunk
+							ignoreLinePresent := false
 							if SupportsLineNumbers(chunk.SourceType) {
 								copyChunk := *chunk
 								copyMetaDataClone := proto.Clone(chunk.SourceMetadata)
 								if copyMetaData, ok := copyMetaDataClone.(*source_metadatapb.MetaData); ok {
 									copyChunk.SourceMetadata = copyMetaData
 								}
 								fragStart, mdLine := FragmentFirstLine(&copyChunk)
-								SetResultLineNumber(&copyChunk, &result, fragStart, mdLine)
+								ignoreLinePresent = SetResultLineNumber(&copyChunk, &result, fragStart, mdLine)
 								resultChunk = &copyChunk
 							}
+							if ignoreLinePresent {
+								continue
+							}
 							result.DecoderType = decoderType
 							e.results <- detectors.CopyMetadata(resultChunk, result)
 
@@ -377,14 +383,18 @@ func SupportsLineNumbers(sourceType sourcespb.SourceType) bool {
 }
 
 // FragmentLineOffset sets the line number for a provided source chunk with a given detector result.
-func FragmentLineOffset(chunk *sources.Chunk, result *detectors.Result) int64 {
+func FragmentLineOffset(chunk *sources.Chunk, result *detectors.Result) (int64, bool) {
 	lines := bytes.Split(chunk.Data, []byte("\n"))
 	for i, line := range lines {
 		if bytes.Contains(line, result.Raw) {
-			return int64(i)
+			// if the line contains the ignore tag, we should ignore the result
+			if bytes.Contains(line, []byte(ignoreTag)) {
+				return int64(i), true
+			}
+			return int64(i), false
 		}
 	}
-	return 0
+	return 0, false
 }
 
 // FragmentFirstLine returns the first line number of a fragment along with a pointer to the value to update in the
@@ -411,7 +421,8 @@ func FragmentFirstLine(chunk *sources.Chunk) (int64, *int64) {
 }
 
 // SetResultLineNumber sets the line number in the provided result.
-func SetResultLineNumber(chunk *sources.Chunk, result *detectors.Result, fragStart int64, mdLine *int64) {
-	offset := FragmentLineOffset(chunk, result)
+func SetResultLineNumber(chunk *sources.Chunk, result *detectors.Result, fragStart int64, mdLine *int64) bool {
+	offset, skip := FragmentLineOffset(chunk, result)
 	*mdLine = fragStart + offset
+	return skip
 }

pkg/engine/engine_test.go

@@ -0,0 +1,64 @@
+package engine
+
+import (
+	"testing"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
+)
+
+func TestFragmentLineOffset(t *testing.T) {
+	tests := []struct {
+		name         string
+		chunk        *sources.Chunk
+		result       *detectors.Result
+		expectedLine int64
+		ignore       bool
+	}{
+		{
+			name: "ignore found on same line",
+			chunk: &sources.Chunk{
+				Data: []byte("line1\nline2\nsecret here trufflehog:ignore\nline4"),
+			},
+			result: &detectors.Result{
+				Raw: []byte("secret here"),
+			},
+			expectedLine: 2,
+			ignore:       true,
+		},
+		{
+			name: "no ignore",
+			chunk: &sources.Chunk{
+				Data: []byte("line1\nline2\nsecret here\nline4"),
+			},
+			result: &detectors.Result{
+				Raw: []byte("secret here"),
+			},
+			expectedLine: 2,
+			ignore:       false,
+		},
+		{
+			name: "ignore on different line",
+			chunk: &sources.Chunk{
+				Data: []byte("line1\nline2\ntrufflehog:ignore\nline4\nsecret here\nline6"),
+			},
+			result: &detectors.Result{
+				Raw: []byte("secret here"),
+			},
+			expectedLine: 4,
+			ignore:       false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			lineOffset, isIgnored := FragmentLineOffset(tt.chunk, tt.result)
+			if lineOffset != tt.expectedLine {
+				t.Errorf("Expected line offset to be %d, got %d", tt.expectedLine, lineOffset)
+			}
+			if isIgnored != tt.ignore {
+				t.Errorf("Expected isIgnored to be %v, got %v", tt.ignore, isIgnored)
+			}
+		})
+	}
+}