doc: add doc for IsGBK'

docs/system.md

@@ -211,7 +211,7 @@ func main() {
 
 
 ### <span id="ExecCommand">CompareOsEnv</span>
-<p>Use shell /bin/bash -c(linux) or cmd (windows) to execute command.</p>
+<p>Execute shell command, return the stdout and stderr string of command, and error if error occur. param `command` is a complete command string, like, ls -a (linux), dir(windows), ping 127.0.0.1. In linux, use /bin/bash -c to execute command, In windows, use powershell.exe to execute command.</p>
 
 <b>Signature:</b>
 
@@ -227,10 +227,24 @@ import (
 )
 
 func main() {
-	out, errout, err := system.ExecCommand("ls")
+	// linux or mac
-	fmt.Println(out)
+	stdout, stderr, err := system.ExecCommand("ls")
-	fmt.Println(errout)
+	fmt.Println("std out: ", stdout)
-	fmt.Println(err)
+	fmt.Println("std err: ", stderr)
+	assert.Equal("", stderr)
+
+	// windows
+	stdout, stderr, err = system.ExecCommand("dir")
+	fmt.Println("std out: ", stdout)
+	fmt.Println("std err: ", stderr)
+
+	// error command
+	stdout, stderr, err = system.ExecCommand("abc")
+	fmt.Println("std out: ", stdout)
+	fmt.Println("std err: ", stderr)
+	if err != nil {
+		fmt.Println(err.Error())
+	}
 }
 ```
 

docs/system_zh-CN.md

@@ -212,7 +212,7 @@ func main() {
 
 
 ### <span id="ExecCommand">ExecCommand</span>
-<p>使用shell /bin/bash -c(linux) 或 cmd (windows) 执行shell命令</p>
+<p>执行shell命令，返回命令的stdout和stderr字符串，如果出现错误，则返回错误。参数`command`是一个完整的命令字符串，如ls-a（linux），dir（windows），ping 127.0.0.1。在linux中，使用/bin/bash-c执行命令，在windows中，使用powershell.exe执行命令。</p>
 
 <b>Signature:</b>
 
@@ -228,10 +228,24 @@ import (
 )
 
 func main() {
-	out, errout, err := system.ExecCommand("ls")
+	// linux or mac
-	fmt.Println(out)
+	stdout, stderr, err := system.ExecCommand("ls")
-	fmt.Println(errout)
+	fmt.Println("std out: ", stdout)
-	fmt.Println(err)
+	fmt.Println("std err: ", stderr)
+	assert.Equal("", stderr)
+
+	// windows
+	stdout, stderr, err = system.ExecCommand("dir")
+	fmt.Println("std out: ", stdout)
+	fmt.Println("std err: ", stderr)
+
+	// error command
+	stdout, stderr, err = system.ExecCommand("abc")
+	fmt.Println("std out: ", stdout)
+	fmt.Println("std err: ", stderr)
+	if err != nil {
+		fmt.Println(err.Error())
+	}
 }
 ```
 

docs/validator.md

@@ -47,6 +47,7 @@ import (
 - [IsUrl](#IsUrl)
 - [IsWeakPassword](#IsWeakPassword)
 - [IsZeroValue](#IsZeroValue)
+- [IsGBK](#IsGBK)
   
 
 <div STYLE="page-break-after: always;"></div>
@@ -821,7 +822,34 @@ func main() {
 ```
 
 
-
+### <span id="IsGBK">IsGBK</span>
+<p>Checks if data encoding is gbk(Chinese character internal code extension specification). 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 the example.</p>
+
+<b>Signature:</b>
+
+```go
+func IsGBK(data []byte) bool
+```
+<b>Example:</b>
+
+```go
+import (
+	"fmt"
+	"github.com/duke-git/lancet/v2/validator"
+)
+
+func main() {
+	data := []byte("你好")
+	
+	// check utf8 first
+	if utf8.Valid(data) {
+		fmt.Println("data encoding is utf-8")
+	}else if(validator.IsGBK(data)) {
+		fmt.Println("data encoding is GBK")
+	}
+	fmt.Println("data encoding is unknown")
+}
+```
 
 
 

docs/validator_zh-CN.md

@@ -47,6 +47,7 @@ import (
 - [IsUrl](#IsUrl)
 - [IsWeakPassword](#IsWeakPassword)
 - [IsZeroValue](#IsZeroValue)
+- [IsGBK](#IsGBK)
   
 
 <div STYLE="page-break-after: always;"></div>
@@ -820,3 +821,31 @@ func main() {
 }
 ```
 
+### <span id="IsGBK">IsGBK</span>
+<p>检查数据编码是否为gbk（汉字内部代码扩展规范）。该函数的实现取决于双字节是否在gbk的编码范围内，而utf-8编码格式的每个字节都在gbk编码范围内。因此，应该首先调用utf8.valid检查它是否是utf-8编码，然后调用IsGBK检查gbk编码。如示例所示。</p>
+
+<b>函数签名:</b>
+
+```go
+func IsGBK(data []byte) bool
+```
+<b>例子:</b>
+
+```go
+import (
+	"fmt"
+	"github.com/duke-git/lancet/v2/validator"
+)
+
+func main() {
+	data := []byte("你好")
+	
+	// 先检查utf8编码
+	if utf8.Valid(data) {
+		fmt.Println("data encoding is utf-8")
+	}else if(validator.IsGBK(data)) {
+		fmt.Println("data encoding is GBK")
+	}
+	fmt.Println("data encoding is unknown")
+}
+```

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=

system/os.go

@@ -9,6 +9,10 @@ import (
 	"os"
 	"os/exec"
 	"runtime"
+	"unicode/utf8"
+
+	"github.com/duke-git/lancet/v2/validator"
+	"golang.org/x/text/encoding/simplifiedchinese"
 )
 
 // IsWindows check if current os is windows
@@ -50,27 +54,61 @@ func CompareOsEnv(key, comparedEnv string) bool {
 	return env == comparedEnv
 }
 
-// ExecCommand use shell /bin/bash -c to execute command
+// ExecCommand execute command, return the stdout and stderr string of command, and error if error occur
+// param `command` is a complete command string, like, ls -a (linux), dir(windows), ping 127.0.0.1
+// in linux,  use /bin/bash -c to execute command
+// in windows, use powershell.exe to execute command
 func ExecCommand(command string) (stdout, stderr string, err error) {
 	var out bytes.Buffer
-	var errout bytes.Buffer
+	var errOut bytes.Buffer
 
 	cmd := exec.Command("/bin/bash", "-c", command)
 	if IsWindows() {
-		cmd = exec.Command("cmd")
+		cmd = exec.Command("powershell.exe", command)
 	}
 	cmd.Stdout = &out
-	cmd.Stderr = &errout
+	cmd.Stderr = &errOut
+
 	err = cmd.Run()
 
 	if err != nil {
-		stderr = string(errout.Bytes())
+		if utf8.Valid(errOut.Bytes()) {
+			stderr = byteToString(errOut.Bytes(), "UTF8")
+		} else if validator.IsGBK(errOut.Bytes()) {
+			stderr = byteToString(errOut.Bytes(), "GBK")
+		}
+		return
+	}
+
+	data := out.Bytes()
+	if utf8.Valid(data) {
+		stdout = byteToString(data, "UTF8")
+	} else if validator.IsGBK(data) {
+		stdout = byteToString(data, "GBK")
 	}
-	stdout = string(out.Bytes())
 
 	return
 }
 
+func byteToString(data []byte, charset string) string {
+	var result string
+
+	switch charset {
+	case "GBK":
+		decodeBytes, _ := simplifiedchinese.GBK.NewDecoder().Bytes(data)
+		result = string(decodeBytes)
+	case "GB18030":
+		decodeBytes, _ := simplifiedchinese.GB18030.NewDecoder().Bytes(data)
+		result = string(decodeBytes)
+	case "UTF8":
+		fallthrough
+	default:
+		result = string(data)
+	}
+
+	return result
+}
+
 // GetOsBits get this system bits 32bit or 64bit
 // return bit int (32/64)
 func GetOsBits() int {

system/os_test.go

@@ -11,10 +11,10 @@ func TestOsDetection(t *testing.T) {
 	assert := internal.NewAssert(t, "TestOsJudgment")
 
 	osType, _, _ := ExecCommand("echo $OSTYPE")
-	if strings.Index(osType, "linux") != -1 {
+	if strings.Contains(osType, "linux") {
 		assert.Equal(true, IsLinux())
 	}
-	if strings.Index(osType, "darwin") != -1 {
+	if strings.Contains(osType, "darwin") {
 		assert.Equal(true, IsMac())
 	}
 }
@@ -44,21 +44,27 @@ func TestOsEnvOperation(t *testing.T) {
 func TestExecCommand(t *testing.T) {
 	assert := internal.NewAssert(t, "TestExecCommand")
 
-	out, errout, err := ExecCommand("ls")
+	// linux or mac
-	t.Log("std out: ", out)
+	stdout, stderr, err := ExecCommand("ls")
-	t.Log("std err: ", errout)
+	t.Log("std out: ", stdout)
+	t.Log("std err: ", stderr)
+	assert.Equal("", stderr)
 	assert.IsNil(err)
 
-	out, errout, err = ExecCommand("abc")
+	// windows
-	t.Log("std out: ", out)
+	stdout, stderr, err = ExecCommand("dir")
-	t.Log("std err: ", errout)
+	t.Log("std out: ", stdout)
-	if err != nil {
+	t.Log("std err: ", stderr)
-		t.Logf("error: %v\n", err)
+	assert.IsNil(err)
-	}
 
-	if !IsWindows() {
+	// error command
-		assert.IsNotNil(err)
+	stdout, stderr, err = ExecCommand("abc")
-	}
+	t.Log("std out: ", stdout)
+	t.Log("std err: ", stderr)
+	// if err != nil {
+	// 	t.Log(err.Error())
+	// }
+	assert.IsNotNil(err)
 }
 
 func TestGetOsBits(t *testing.T) {

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 encoding 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))
+}