feat: add IsGBK validator

go.mod

@@ -1,3 +1,5 @@
 module github.com/duke-git/lancet/v2
 
 go 1.18
+
+require golang.org/x/text v0.5.0

go.sum

@@ -0,0 +1,2 @@
+golang.org/x/text v0.5.0 h1:OLmvp0KP+FVG99Ct/qFiL/Fhk4zp4QQnZ7b2U+5piUM=
+golang.org/x/text v0.5.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=

validator/validator.go

@@ -274,3 +274,40 @@ func IsZeroValue(value any) bool {
 
 	return reflect.DeepEqual(rv.Interface(), reflect.Zero(rv.Type()).Interface())
 }
+
+// IsGBK check if data encoinge is gbk
+// Note: this function is implemented by whether double bytes fall within the encoding range of gbk,
+// while each byte of utf-8 encoding format falls within the encoding range of gbk.
+// Therefore, utf8.valid() should be called first to check whether it is not utf-8 encoding,
+// and then call IsGBK() to check gbk encoding. like below
+/**
+	data := []byte("你好")
+	if utf8.Valid(data) {
+		fmt.Println("data encoding is utf-8")
+	}else if(IsGBK(data)) {
+		fmt.Println("data encoding is GBK")
+	}
+	fmt.Println("data encoding is unknown")
+**/
+func IsGBK(data []byte) bool {
+	i := 0
+	for i < len(data) {
+		if data[i] <= 0xff {
+			i++
+			continue
+		} else {
+			if data[i] >= 0x81 &&
+				data[i] <= 0xfe &&
+				data[i+1] >= 0x40 &&
+				data[i+1] <= 0xfe &&
+				data[i+1] != 0xf7 {
+				i += 2
+				continue
+			} else {
+				return false
+			}
+		}
+	}
+
+	return true
+}

validator/validator_test.go

@@ -4,8 +4,10 @@ import (
 	"fmt"
 	"testing"
 	"time"
+	"unicode/utf8"
 
 	"github.com/duke-git/lancet/v2/internal"
+	"golang.org/x/text/encoding/simplifiedchinese"
 )
 
 func TestIsAllUpper(t *testing.T) {
@@ -388,3 +390,13 @@ func TestIsZeroValue(t *testing.T) {
 		assert.Equal(false, IsZeroValue(value))
 	}
 }
+
+func TestIsGBK(t *testing.T) {
+	assert := internal.NewAssert(t, "TestIsGBK")
+
+	str := "你好"
+	gbkData, _ := simplifiedchinese.GBK.NewEncoder().Bytes([]byte(str))
+
+	assert.Equal(true, IsGBK(gbkData))
+	assert.Equal(false, utf8.Valid(gbkData))
+}