1
0
mirror of https://github.com/duke-git/lancet.git synced 2026-02-04 12:52:28 +08:00

feat: add IsGBK

This commit is contained in:
dudaodong
2022-12-15 16:21:09 +08:00
parent fb3de03f37
commit 0a99492cf6
6 changed files with 134 additions and 4 deletions

View File

@@ -47,7 +47,7 @@ import (
- [IsUrl](#IsUrl)
- [IsWeakPassword](#IsWeakPassword)
- [IsZeroValue](#IsZeroValue)
- [IsGBK](#IsGBK)
<div STYLE="page-break-after: always;"></div>
@@ -819,7 +819,34 @@ 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/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")
}
```

View File

@@ -47,7 +47,7 @@ import (
- [IsUrl](#IsUrl)
- [IsWeakPassword](#IsWeakPassword)
- [IsZeroValue](#IsZeroValue)
- [IsGBK](#IsGBK)
<div STYLE="page-break-after: always;"></div>
@@ -821,6 +821,33 @@ 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/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")
}
```

2
go.mod
View File

@@ -1,3 +1,5 @@
module github.com/duke-git/lancet
go 1.16
require golang.org/x/text v0.5.0 // indirect

25
go.sum Normal file
View File

@@ -0,0 +1,25 @@
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
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=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

View File

@@ -288,3 +288,40 @@ func IsZeroValue(value interface{}) 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
}

View File

@@ -4,8 +4,10 @@ import (
"fmt"
"testing"
"time"
"unicode/utf8"
"github.com/duke-git/lancet/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))
}