From 92a970456baf20ca5d41c85bb568d36f850c434c Mon Sep 17 00:00:00 2001
From: Hikmatulloh Hari Mukti <muktihaz@gmail.com>
Date: Tue, 17 Sep 2024 08:30:55 +0700
Subject: [PATCH] chore: proto.UnmarshalValue simplify utf8 string decoding

---
 proto/value_unmarshal.go               | 19 ++++--------
 proto/value_unmarshal_internal_test.go | 41 ++++----------------------
 2 files changed, 11 insertions(+), 49 deletions(-)

diff --git a/proto/value_unmarshal.go b/proto/value_unmarshal.go
index d384aed0..e2284bc2 100755
--- a/proto/value_unmarshal.go
+++ b/proto/value_unmarshal.go
@@ -224,31 +224,22 @@ func UnmarshalValue(b []byte, arch byte, baseType basetype.BaseType, profileType
 			}
 			return SliceString(vals), nil
 		}
-		b = trimRightZero(b)
 		return String(utf8String(b)), nil
 	}
 
 	return Value{}, fmt.Errorf("type %s(%d) is not supported: %w", baseType, baseType, ErrTypeNotSupported)
 }
 
-// trimRightZero returns a subslice of b up to the null-terminated
-// string ('\x00') and discard the remaining bytes, as these are likely
-// padding bytes used to meet the desired length.
-func trimRightZero(b []byte) []byte {
-	for i := range b {
-		if b[i] == 0 {
-			return b[:i]
-		}
-	}
-	return b
-}
-
 // utf8String converts b into a valid UTF-8 string. If it encounters
-// utf8.RuneError character, it will discard that character.
+// utf8.RuneError character it will discard it. It stops when all bytes
+// have been successfully decoded or reach a null-terminated string '\x00'.
 func utf8String(b []byte) string {
 	buf := make([]byte, 0, 255)
 	for len(b) > 0 {
 		r, size := utf8.DecodeRune(b)
+		if r == 0 {
+			break
+		}
 		if r != utf8.RuneError {
 			buf = utf8.AppendRune(buf, r)
 		}
diff --git a/proto/value_unmarshal_internal_test.go b/proto/value_unmarshal_internal_test.go
index 680d2601..ccd2cf18 100644
--- a/proto/value_unmarshal_internal_test.go
+++ b/proto/value_unmarshal_internal_test.go
@@ -9,47 +9,18 @@ import (
 	"testing"
 )
 
-func TestTrimRightZero(t *testing.T) {
-	tt := []struct {
-		str      string
-		expected string
-	}{
-		{str: "", expected: ""},
-		{str: "\x00", expected: ""},
-		{str: "Open Water", expected: "Open Water"},
-		{str: "Open Water\x00", expected: "Open Water"},
-		{str: "Open Water\x00\x00", expected: "Open Water"},
-		{str: "Walk or jog lightly.\x00��", expected: "Walk or jog lightly."},
-		{str: "Walk or jog lightly.��", expected: "Walk or jog lightly.��"},
-	}
-
-	for _, tc := range tt {
-		t.Run(tc.str, func(t *testing.T) {
-			res := trimRightZero([]byte(tc.str))
-			if string(res) != tc.expected {
-				t.Fatalf("expected: %s, got: %s", tc.expected, res)
-			}
-		})
-	}
-}
-
-func BenchmarkTrimRightZero(b *testing.B) {
-	for i := 0; i < b.N; i++ {
-		_ = trimRightZero([]byte(""))
-		_ = trimRightZero([]byte("\x00"))
-		_ = trimRightZero([]byte("Open Water"))
-		_ = trimRightZero([]byte("Open Water\x00"))
-		_ = trimRightZero([]byte("Open Water\x00\x00"))
-		_ = trimRightZero([]byte("Walk or jog lightly.\x00��"))
-	}
-}
-
 func TestUTF8String(t *testing.T) {
 	tt := []struct {
 		in  []byte
 		out string
 	}{
+		{in: []byte(""), out: ""},
+		{in: []byte("\x00"), out: ""},
+		{in: []byte("Open Water"), out: "Open Water"},
+		{in: []byte("Open Water\x00"), out: "Open Water"},
+		{in: []byte("Open Water\x00\x00"), out: "Open Water"},
 		{in: []byte("Walk or jog lightly.��"), out: "Walk or jog lightly."},
+		{in: []byte("Walk or jog lightly.\x00��"), out: "Walk or jog lightly."},
 		{in: []byte("0000000000000�0000000"), out: "00000000000000000000"},
 		{in: []byte("0000000000000\xe80000000"), out: "00000000000000000000"},
 	}