From ce6298f304ba722e5fdf9a20d261f5bce790dda9 Mon Sep 17 00:00:00 2001
From: salvacybersec <salva@opsecti.local>
Date: Sun, 5 Apr 2026 15:16:48 +0300
Subject: [PATCH] test(04-02): add failing tests for DirSource recursive walk
 and mmap

---
 pkg/engine/sources/dir_test.go | 146 +++++++++++++++++++++++++++++++++
 1 file changed, 146 insertions(+)
 create mode 100644 pkg/engine/sources/dir_test.go

diff --git a/pkg/engine/sources/dir_test.go b/pkg/engine/sources/dir_test.go
new file mode 100644
index 0000000..49759ec
--- /dev/null
+++ b/pkg/engine/sources/dir_test.go
@@ -0,0 +1,146 @@
+package sources
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/salvacybersec/keyhunter/pkg/types"
+)
+
+func drain(t *testing.T, src Source) []types.Chunk {
+	t.Helper()
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+	out := make(chan types.Chunk, 1024)
+	errCh := make(chan error, 1)
+	go func() { errCh <- src.Chunks(ctx, out); close(out) }()
+	var got []types.Chunk
+	for c := range out {
+		got = append(got, c)
+	}
+	require.NoError(t, <-errCh)
+	return got
+}
+
+func writeTestFile(t *testing.T, path, content string) {
+	t.Helper()
+	require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o755))
+	require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
+}
+
+func isSortedStrings(s []string) bool {
+	for i := 1; i < len(s); i++ {
+		if s[i-1] > s[i] {
+			return false
+		}
+	}
+	return true
+}
+
+func TestDirSource_RecursiveWalk(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "a.txt"), "alpha content")
+	writeTestFile(t, filepath.Join(root, "sub", "b.txt"), "bravo content")
+	writeTestFile(t, filepath.Join(root, "sub", "deep", "c.txt"), "charlie content")
+
+	chunks := drain(t, NewDirSourceRaw(root, nil))
+	require.Len(t, chunks, 3)
+
+	sources := make([]string, 0, len(chunks))
+	for _, c := range chunks {
+		sources = append(sources, c.Source)
+	}
+	require.True(t, isSortedStrings(sources), "emission order must be sorted, got %v", sources)
+}
+
+func TestDirSource_DefaultExcludes(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "keep.txt"), "keep me")
+	writeTestFile(t, filepath.Join(root, ".git", "config"), "[core]")
+	writeTestFile(t, filepath.Join(root, "node_modules", "foo.js"), "x")
+	writeTestFile(t, filepath.Join(root, "vendor", "bar.go"), "package x")
+	writeTestFile(t, filepath.Join(root, "app.min.js"), "y")
+	writeTestFile(t, filepath.Join(root, "app.js.map"), "{}")
+
+	chunks := drain(t, NewDirSource(root))
+	require.Len(t, chunks, 1)
+	require.Contains(t, chunks[0].Source, "keep.txt")
+}
+
+func TestDirSource_UserExclude(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "keep.txt"), "keep")
+	writeTestFile(t, filepath.Join(root, "drop.log"), "drop")
+
+	chunks := drain(t, NewDirSourceRaw(root, []string{"*.log"}))
+	require.Len(t, chunks, 1)
+	require.Contains(t, chunks[0].Source, "keep.txt")
+}
+
+func TestDirSource_BinarySkipped(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "text.txt"), "plain text content")
+	binPath := filepath.Join(root, "blob.bin")
+	require.NoError(t, os.WriteFile(binPath, []byte{0x7f, 'E', 'L', 'F', 0x00, 0x01, 0x02}, 0o644))
+
+	chunks := drain(t, NewDirSourceRaw(root, nil))
+	require.Len(t, chunks, 1)
+	require.Contains(t, chunks[0].Source, "text.txt")
+}
+
+func TestDirSource_MmapLargeFile(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping large file test in short mode")
+	}
+	root := t.TempDir()
+	big := filepath.Join(root, "big.txt")
+	payload := strings.Repeat("API_KEY=xxxxxxxxxxxxxxxxxxxx\n", (int(MmapThreshold)/28)+10)
+	require.NoError(t, os.WriteFile(big, []byte(payload), 0o644))
+
+	chunks := drain(t, NewDirSourceRaw(root, nil))
+	require.NotEmpty(t, chunks)
+	require.Equal(t, big, chunks[0].Source)
+}
+
+func TestDirSource_DeterministicOrdering(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "zeta.txt"), "z")
+	writeTestFile(t, filepath.Join(root, "alpha.txt"), "a")
+	writeTestFile(t, filepath.Join(root, "mike.txt"), "m")
+
+	run := func() []string {
+		chunks := drain(t, NewDirSourceRaw(root, nil))
+		srcs := make([]string, 0, len(chunks))
+		for _, c := range chunks {
+			srcs = append(srcs, c.Source)
+		}
+		return srcs
+	}
+	require.Equal(t, run(), run())
+}
+
+func TestDirSource_MissingRoot(t *testing.T) {
+	src := NewDirSourceRaw("/definitely/does/not/exist/keyhunter-xyz-zzz", nil)
+	ctx := context.Background()
+	out := make(chan types.Chunk, 1)
+	err := src.Chunks(ctx, out)
+	require.Error(t, err)
+}
+
+func TestDirSource_CtxCancellation(t *testing.T) {
+	root := t.TempDir()
+	for i := 0; i < 50; i++ {
+		writeTestFile(t, filepath.Join(root, "f", string(rune('a'+i%26))+"_"+string(rune('a'+i%26))+".txt"), "payload")
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel() // pre-cancelled
+	out := make(chan types.Chunk, 1024)
+	err := NewDirSourceRaw(root, nil).Chunks(ctx, out)
+	require.ErrorIs(t, err, context.Canceled)
+}