feat: honor ignore files and test exclusions

Author: aksOps

CHANGELOG.md

@@ -2,6 +2,9 @@
 
 ## Unreleased
 
+- Parse `.gitignore`, `.ignore`, and `.git/info/exclude` during working-tree scans.
+- Add `--exclude-tests` to skip well-known test-case paths from aggregate scan analysis.
+
 ## 0.0.1 - 2026-06-30
 
 - Initial public code-signal scanner.

README.md

@@ -52,6 +52,9 @@ scanner scan .
 # Emit aggregate JSON
 scanner scan . --json
 
+# Exclude well-known test files and test directories
+scanner scan . --exclude-tests
+
 # Detect languages and module roots
 scanner detect .
 
@@ -92,6 +95,14 @@ code-signal detects and analyzes these languages with built-in lexical/parser ch
 
 Detection uses extensions, shebangs, and common manifests such as `go.mod`, `package.json`, `pyproject.toml`, `Cargo.toml`, `pom.xml`, Gradle files, `.csproj`, `.sln`, `composer.json`, `Gemfile`, `Dockerfile`, `Containerfile`, and `*.dockerfile`.
 
+## Ignore files, test exclusion, and skip policy
+
+Working-tree scans parse `.gitignore`, `.ignore`, and `.git/info/exclude` using gitignore-style rules before reading candidate files.
+
+Pass `--exclude-tests` to `scan` or `diff` to skip well-known test-case paths from aggregate analysis. The built-in defaults cover common Go (`*_test.go`, `testdata`), Java (`src/test/**`, `*Test.java`, `*Tests.java`, `*IT.java`), Python (`tests/**`, `test_*.py`, `*_test.py`, `conftest.py`), TypeScript/JavaScript (`__tests__/**`, `*.test.*`, `*.spec.*`, `cypress/**`, `playwright/**`, `e2e/**`), and Rust (`tests/**`, `benches/**`, `*_test.rs`) conventions.
+
+Built-in skips still apply for common dependency, generated, build, coverage, and minified paths such as `node_modules`, `vendor`, `target`, `dist`, `build`, `.next`, `coverage`, `third_party`, `generated`, `gen`, `*.min.js`, `*.min.css`, `*.pb.go`, and `*_generated.go`.
+
 ## Configuration
 
 Configuration is optional. If present, `scanner.json` is loaded from the scanned repository root or from `--config`.
@@ -102,7 +113,8 @@ Configuration is optional. If present, `scanner.json` is loaded from the scanned
     "default_timeout_seconds": 30,
     "max_file_bytes": 1048576,
     "follow_symlinks": false,
-    "workers": 0
+    "workers": 0,
+    "exclude_tests": false
   },
   "score": {
     "fail_under": 75,

internal/cli/cli.go

@@ -23,6 +23,7 @@ const (
 
 	flagBase             = "--base"
 	flagConfig           = "--config"
+	flagExcludeTests     = "--exclude-tests"
 	flagFailOnRegression = "--fail-on-regression"
 	flagFailUnder        = "--fail-under"
 	flagHead             = "--head"
@@ -89,17 +90,19 @@ type diffArgs struct {
 	configPath       string
 	json             bool
 	failOnRegression bool
+	excludeTests     bool
 	timeout          time.Duration
 	timeoutSet       bool
 }
 
 type scanArgs struct {
-	path       string
-	configPath string
-	json       bool
-	failUnder  *int
-	timeout    time.Duration
-	timeoutSet bool
+	path         string
+	configPath   string
+	json         bool
+	failUnder    *int
+	excludeTests bool
+	timeout      time.Duration
+	timeoutSet   bool
 }
 
 type detectArgs struct {
@@ -129,6 +132,9 @@ func runDiff(ctx context.Context, args []string, stdout io.Writer) (int, error)
 	if err != nil {
 		return 2, err
 	}
+	if parsed.excludeTests {
+		cfg.Scan.ExcludeTests = true
+	}
 	diff, err := scan.Diff(ctx, parsed.repo, parsed.base, parsed.head, parsed.scopePath, scan.DiffOptions{Config: cfg})
 	if err != nil {
 		return 1, err
@@ -160,6 +166,9 @@ func runScan(ctx context.Context, args []string, stdout io.Writer) (int, error)
 	if err != nil {
 		return 2, err
 	}
+	if parsed.excludeTests {
+		cfg.Scan.ExcludeTests = true
+	}
 	scanReport, err := scan.ScanPath(ctx, parsed.path, scan.ScanOptions{Config: cfg})
 	if err != nil {
 		return 1, err
@@ -260,6 +269,9 @@ func parseDiffFlag(args []string, index int, parsed *diffArgs) (int, bool, error
 	case flagConfig:
 		next, err := assignFlagValue(args, index, flagConfig, &parsed.configPath)
 		return next, true, err
+	case flagExcludeTests:
+		parsed.excludeTests = true
+		return index, true, nil
 	case flagTimeout:
 		next, err := assignTimeoutValue(args, index, &parsed.timeout, &parsed.timeoutSet)
 		return next, true, err
@@ -303,6 +315,9 @@ func parseScanFlag(args []string, index int, parsed *scanArgs) (int, bool, error
 	case flagConfig:
 		next, err := assignFlagValue(args, index, flagConfig, &parsed.configPath)
 		return next, true, err
+	case flagExcludeTests:
+		parsed.excludeTests = true
+		return index, true, nil
 	case flagTimeout:
 		next, err := assignTimeoutValue(args, index, &parsed.timeout, &parsed.timeoutSet)
 		return next, true, err

internal/cli/cli_test.go

@@ -3,6 +3,7 @@ package cli
 import (
 	"bytes"
 	"context"
+	"encoding/json"
 	"errors"
 	"os"
 	"path/filepath"
@@ -72,6 +73,44 @@ func TestScanCommandKeepsZeroExitForLowScore(t *testing.T) {
 		t.Fatalf("stdout = %q, want score output", stdout.String())
 	}
 }
+func TestScanCommandExcludeTestsUsesDefaultPatterns(t *testing.T) {
+	root := t.TempDir()
+	writeCLITestFile(t, root, "cmd/main.go", "package main\n")
+	longLine := "// " + strings.Repeat("x", 140) + "\n"
+	for _, name := range []string{
+		"cmd/main_test.go",
+		"testdata/golden.go",
+		"src/test/java/AppTest.java",
+		"tests/test_app.py",
+		"web/src/app.spec.ts",
+		"web/src/__tests__/app.test.js",
+		"crates/core/tests/integration.rs",
+	} {
+		writeCLITestFile(t, root, name, longLine)
+	}
+
+	var stdout, stderr bytes.Buffer
+	code := Run(context.Background(), []string{"scan", "--exclude-tests", "--json", root}, &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("code = %d stdout = %q stderr = %q, want 0", code, stdout.String(), stderr.String())
+	}
+	var decoded struct {
+		Totals struct {
+			FilesScanned int `json:"files_scanned"`
+			FilesSkipped int `json:"files_skipped"`
+			Warnings     int `json:"warnings"`
+		} `json:"totals"`
+	}
+	if err := json.Unmarshal(stdout.Bytes(), &decoded); err != nil {
+		t.Fatalf("unmarshal scan JSON: %v\n%s", err, stdout.String())
+	}
+	if decoded.Totals.FilesScanned != 1 || decoded.Totals.FilesSkipped != 7 {
+		t.Fatalf("totals = %#v, want one source file scanned and seven test files skipped", decoded.Totals)
+	}
+	if decoded.Totals.Warnings != 0 {
+		t.Fatalf("warnings = %d, want ignored test long lines excluded", decoded.Totals.Warnings)
+	}
+}
 
 func TestUnknownCommandReturnsCLIError(t *testing.T) {
 	var stdout, stderr bytes.Buffer
@@ -134,6 +173,17 @@ func TestRunReturnsOneForRuntimeInputErrors(t *testing.T) {
 	}
 }
 
+func writeCLITestFile(t *testing.T, root, name, content string) {
+	t.Helper()
+	path := filepath.Join(root, filepath.FromSlash(name))
+	if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+		t.Fatalf("mkdir %s: %v", filepath.Dir(path), err)
+	}
+	if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+		t.Fatalf("write %s: %v", name, err)
+	}
+}
+
 var errFailingWrite = errors.New("write failed")
 
 type failingWriter struct{}

internal/config/config.go

@@ -22,6 +22,7 @@ type ScanConfig struct {
 	MaxFileBytes          int64 `json:"max_file_bytes"`
 	FollowSymlinks        bool  `json:"follow_symlinks"`
 	Workers               int   `json:"workers"`
+	ExcludeTests          bool  `json:"exclude_tests"`
 }
 
 // ScoreConfig controls aggregate score deductions.
@@ -50,6 +51,7 @@ type scanFile struct {
 	MaxFileBytes          *int64 `json:"max_file_bytes"`
 	FollowSymlinks        *bool  `json:"follow_symlinks"`
 	Workers               *int   `json:"workers"`
+	ExcludeTests          *bool  `json:"exclude_tests"`
 }
 
 type scoreFile struct {
@@ -151,6 +153,9 @@ func mergeScanConfig(cfg *ScanConfig, file *scanFile) {
 	if file.Workers != nil {
 		cfg.Workers = *file.Workers
 	}
+	if file.ExcludeTests != nil {
+		cfg.ExcludeTests = *file.ExcludeTests
+	}
 }
 
 func mergeScoreConfig(cfg *ScoreConfig, file *scoreFile) {

internal/config/config_test.go

@@ -41,7 +41,8 @@ func TestLoadMergesScannerJSONScanAndScoreOverrides(t *testing.T) {
 			"default_timeout_seconds": 7,
 			"max_file_bytes": 2048,
 			"follow_symlinks": true,
-			"workers": 3
+			"workers": 3,
+			"exclude_tests": true
 		},
 		"score": {
 			"fail_under": 91,
@@ -70,6 +71,9 @@ func TestLoadMergesScannerJSONScanAndScoreOverrides(t *testing.T) {
 	if cfg.Scan.Workers != 3 {
 		t.Fatalf("Workers = %d, want 3", cfg.Scan.Workers)
 	}
+	if !cfg.Scan.ExcludeTests {
+		t.Fatalf("ExcludeTests = false, want true")
+	}
 	if cfg.Score.FailUnder != 91 || cfg.Score.Error != 15 || cfg.Score.Warning != 5 || cfg.Score.Info != 2 {
 		t.Fatalf("Score = %#v, want overridden values", cfg.Score)
 	}