splitter: exposed MaxSegmentSize() for splitters

repo/splitter/splitter.go

@@ -13,6 +13,7 @@
 // It must return true if the object should be split after byte b is processed.
 type Splitter interface {
 	ShouldSplit(b byte) bool
+	MaxSegmentSize() int
 	Reset()
 	Close()
 }

repo/splitter/splitter_buzhash32.go

@@ -39,6 +39,10 @@ func (rs *buzhash32Splitter) ShouldSplit(b byte) bool {
 	return false
 }
 
+func (rs *buzhash32Splitter) MaxSegmentSize() int {
+	return rs.maxSize
+}
+
 func newBuzHash32SplitterFactory(avgSize int) Factory {
 	// avgSize must be a power of two, so 0b000001000...0000
 	// it just so happens that mask is avgSize-1 :)

repo/splitter/splitter_fixed.go

@@ -23,6 +23,10 @@ func (s *fixedSplitter) ShouldSplit(b byte) bool {
 	return false
 }
 
+func (s *fixedSplitter) MaxSegmentSize() int {
+	return s.chunkLength
+}
+
 // Fixed returns a factory that creates splitters with fixed chunk length.
 func Fixed(length int) Factory {
 	return func() Splitter {

repo/splitter/splitter_rabinkarp64.go

@@ -39,6 +39,10 @@ func (rs *rabinKarp64Splitter) ShouldSplit(b byte) bool {
 	return false
 }
 
+func (rs *rabinKarp64Splitter) MaxSegmentSize() int {
+	return rs.maxSize
+}
+
 func newRabinKarp64SplitterFactory(avgSize int) Factory {
 	mask := uint64(avgSize - 1)
 	minSize, maxSize := avgSize/2, avgSize*2 //nolint:gomnd

repo/splitter/splitter_test.go

@@ -69,6 +69,10 @@ func TestSplitterStability(t *testing.T) {
 		minSplit := int(math.MaxInt32)
 		count := 0
 
+		if got, want := s.MaxSegmentSize(), tc.maxSplit; got != want {
+			t.Errorf("unexpected max segment size: %v, want %v", got, want)
+		}
+
 		for i, p := range rnd {
 			if !s.ShouldSplit(p) {
 				continue