feat(04-02): implement DirSource with recursive walk, glob exclusion, and mmap

- Add DirSource with filepath.WalkDir recursive traversal
- Default exclusions for .git, node_modules, vendor, *.min.js, *.map
- Binary file detection via NUL byte sniff (first 512 bytes)
- mmap reads for files >= 10MB via golang.org/x/exp/mmap
- Deterministic sorted emission order for reproducible tests
- Refactor FileSource to share emitChunks/isBinary helpers and mmap large files

pkg/engine/sources/file.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"os"
 
+	"golang.org/x/exp/mmap"
+
 	"github.com/salvacybersec/keyhunter/pkg/types"
 )
 
@@ -11,6 +13,7 @@ const defaultChunkSize = 4096
 const chunkOverlap = 256 // overlap between chunks to avoid splitting keys at boundaries
 
 // FileSource reads a single file and emits overlapping chunks.
+// For files >= MmapThreshold it uses golang.org/x/exp/mmap for zero-copy reads.
 type FileSource struct {
 	Path      string
 	ChunkSize int
@@ -22,47 +25,36 @@ func NewFileSource(path string) *FileSource {
 }
 
 // Chunks reads the file in overlapping segments and sends each chunk to out.
-// Uses os.ReadFile for simplicity in Phase 1. mmap for files > 10MB is implemented
-// in Phase 4 (Input Sources) alongside all other source adapter enhancements.
+// Uses mmap for files >= MmapThreshold (10MB) and os.ReadFile for smaller files.
+// Binary files (NUL byte in the first 512 bytes) are skipped.
 func (f *FileSource) Chunks(ctx context.Context, out chan<- types.Chunk) error {
-	data, err := os.ReadFile(f.Path)
+	fi, err := os.Stat(f.Path)
 	if err != nil {
 		return err
 	}
-	size := f.ChunkSize
-	if size <= 0 {
-		size = defaultChunkSize
-	}
-	if len(data) <= size {
-		// File fits in one chunk
-		select {
-		case <-ctx.Done():
-			return ctx.Err()
-		case out <- types.Chunk{Data: data, Source: f.Path, Offset: 0}:
-		}
+	size := fi.Size()
+	if size == 0 {
 		return nil
 	}
-	// Emit overlapping chunks
-	var offset int64
-	for start := 0; start < len(data); start += size - chunkOverlap {
-		end := start + size
-		if end > len(data) {
-			end = len(data)
+	var data []byte
+	if size >= MmapThreshold {
+		ra, err := mmap.Open(f.Path)
+		if err != nil {
+			return err
 		}
-		chunk := types.Chunk{
-			Data:   data[start:end],
-			Source: f.Path,
-			Offset: offset,
+		defer ra.Close()
+		data = make([]byte, ra.Len())
+		if _, err := ra.ReadAt(data, 0); err != nil {
+			return err
 		}
-		select {
-		case <-ctx.Done():
-			return ctx.Err()
-		case out <- chunk:
-		}
-		offset += int64(end - start)
-		if end == len(data) {
-			break
+	} else {
+		data, err = os.ReadFile(f.Path)
+		if err != nil {
+			return err
 		}
 	}
-	return nil
+	if isBinary(data) {
+		return nil
+	}
+	return emitChunks(ctx, data, f.Path, f.ChunkSize, out)
 }