bingyi/gf
1
0
Fork 0
mirror of https://gitee.com/johng/gf synced 2026-06-06 02:25:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

框架中增加字符集转换的标准库

Browse Source
This commit is contained in:
wenzi1
2019-06-11 17:25:30 +08:00
parent dd6152fe8a
commit d97fda794c
5 changed files with 256 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
g/encoding/gcharset/gcharset.go
View File

@ -12,95 +12,12 @@
package gcharset
import (
"bytes"
"errors"
"fmt"
"github.com/gogf/gf/g/container/gmap"
"github.com/gogf/gf/third/github.com/axgle/mahonia"
"github.com/gogf/gf/third/golang.org/x/text/encoding"
"github.com/gogf/gf/third/golang.org/x/text/encoding/japanese"
"github.com/gogf/gf/third/golang.org/x/text/encoding/korean"
"github.com/gogf/gf/third/golang.org/x/text/encoding/simplifiedchinese"
"github.com/gogf/gf/third/golang.org/x/text/encoding/traditionalchinese"
"github.com/gogf/gf/third/golang.org/x/text/transform"
"io/ioutil"
"strings"
"github.com/gogf/gf/g/encoding/internal"
)
var encodingMap *gmap.Map
func init() {
encodingMap = gmap.New()
encodingMap.Sets(
map[interface{}]interface{}{
"GBK": simplifiedchinese.GBK,
"GB18030": simplifiedchinese.GB18030,
"HZGB2312": simplifiedchinese.HZGB2312,
"GB2312": simplifiedchinese.HZGB2312,
"EUCJP": japanese.EUCJP,
"ISO2022JP": japanese.ISO2022JP,
"SHIFTJIS": japanese.ShiftJIS,
"EUCKR": korean.EUCKR,
"BIG5": traditionalchinese.Big5,
})
}
// 2个字符集之间的转换
func Convert(dstCharset string, srcCharset string, src string) (dst string, err error) {
srcCharsetUpper := strings.ToUpper(srcCharset)
dstCharsetUpper := strings.ToUpper(dstCharset)
if srcCharsetUpper == dstCharsetUpper {
return src, nil
}
s := new(mahonia.Charset)
d := new(mahonia.Charset)
srctmp := src
if srcCharset != "UTF-8" {
enc := encodingMap.Get(srcCharset)
if enc != nil {
tmp, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader([]byte(src)), enc.(encoding.Encoding).NewDecoder()))
if err != nil {
return "", fmt.Errorf("%s to utf8 failed. %v", srcCharset, err)
}
srctmp = string(tmp)
} else {
s = mahonia.GetCharset(srcCharsetUpper)
if s == nil {
return "", errors.New(fmt.Sprintf("not support charset:%s", srcCharset))
}
if s.Name != "UTF-8" {
srctmp = s.NewDecoder().ConvertString(srctmp)
}
}
}
dst = srctmp
if dstCharset != "UTF-8" {
enc := encodingMap.Get(dstCharset)
if enc != nil {
tmp, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader([]byte(srctmp)), enc.(encoding.Encoding).NewEncoder()))
if err != nil {
return "", fmt.Errorf("utf to %s failed. %v", dstCharset, err)
}
dst = string(tmp)
} else {
d = mahonia.GetCharset(dstCharsetUpper)
if d == nil {
return "", errors.New(fmt.Sprintf("not support charset:%s", dstCharset))
}
dst = srctmp
if d.Name != "UTF-8" {
dst = d.NewEncoder().ConvertString(dst)
}
}
}
return dst, nil
return internal.Convert(dstCharset, srcCharset, src)
}
// 指定字符集转UTF8

15
g/encoding/gxml/gxml.go
View File

@ -9,8 +9,8 @@ package gxml
import (
"fmt"
"github.com/gogf/gf/g/encoding/internal"
"github.com/gogf/gf/g/text/gregex"
"github.com/gogf/gf/third/github.com/axgle/mahonia"
"github.com/gogf/gf/third/github.com/clbanning/mxj"
"strings"
)
@ -60,16 +60,21 @@ func convert(xml []byte) (res []byte, err error) {
if len(matchStr) == 2 {
xmlEncode = matchStr[1]
}
s := mahonia.GetCharset(xmlEncode)
if s == nil {
xmlEncode = strings.ToUpper(xmlEncode)
s := internal.GetCharset(xmlEncode)
if s == false {
return nil, fmt.Errorf("not support charset:%s\n", xmlEncode)
}
res, err = gregex.Replace(patten, []byte(""), xml)
if err != nil {
return nil, err
}
if !strings.EqualFold(s.Name, "UTF-8") {
res = []byte(s.NewDecoder().ConvertString(string(res)))
if xmlEncode != "UTF-8" && xmlEncode != "UTF8" {
dst, err := internal.Convert("UTF-8", xmlEncode, string(res))
if err != nil {
return nil, err
}
res = []byte(dst)
}
return res, nil
}

6
g/encoding/gxml/gxml_test.go
View File

@ -112,7 +112,7 @@ func Test_Encode(t *testing.T) {
if err != nil {
t.Errorf("encode error.")
}
t.Logf("%s\n", string(xmlStr))
//t.Logf("%s\n", string(xmlStr))
res := `<root><bool>true</bool><float>100.92</float><int>123</int><string>hello world</string></root>`
if string(xmlStr) != res {
@ -130,11 +130,11 @@ func Test_EncodeIndent(t *testing.T) {
}
m["root"] = interface{}(v)
xmlStr, err := gxml.EncodeWithIndent(m, "xml")
_, err := gxml.EncodeWithIndent(m, "xml")
if err != nil {
t.Errorf("encodeWithIndent error.")
}
t.Logf("%s\n", string(xmlStr))
//t.Logf("%s\n", string(xmlStr))
}

114
g/encoding/internal/gcharsetconvert.go Normal file
View File

@ -0,0 +1,114 @@
// Copyright 2018 gf Author(https://github.com/gogf/gf). All Rights Reserved.
//
// This Source Code Form is subject to the terms of the MIT License.
// If a copy of the MIT was not distributed with this file,
// You can obtain one at https://github.com/gogf/gf.
// @author wenzi1
// @date 20180604
// Package gcharset provides converting string to requested character encoding.
//
// 字符集转换方法,
package internal
import (
"bytes"
"errors"
"fmt"
"github.com/gogf/gf/g/container/gmap"
"github.com/gogf/gf/third/github.com/axgle/mahonia"
"github.com/gogf/gf/third/golang.org/x/text/encoding"
"github.com/gogf/gf/third/golang.org/x/text/encoding/japanese"
"github.com/gogf/gf/third/golang.org/x/text/encoding/korean"
"github.com/gogf/gf/third/golang.org/x/text/encoding/simplifiedchinese"
"github.com/gogf/gf/third/golang.org/x/text/encoding/traditionalchinese"
"github.com/gogf/gf/third/golang.org/x/text/transform"
"io/ioutil"
"strings"
)
var encodingMap *gmap.Map
func init() {
encodingMap = gmap.New()
encodingMap.Sets(
map[interface{}]interface{}{
"GBK": simplifiedchinese.GBK,
"GB18030": simplifiedchinese.GB18030,
"HZGB2312": simplifiedchinese.HZGB2312,
"GB2312": simplifiedchinese.HZGB2312,
"EUCJP": japanese.EUCJP,
"ISO2022JP": japanese.ISO2022JP,
"SHIFTJIS": japanese.ShiftJIS,
"EUCKR": korean.EUCKR,
"BIG5": traditionalchinese.Big5,
})
}
func GetCharset(charset string) bool {
c := strings.ToUpper(charset)
if encodingMap.Contains(c) == false {
if mahonia.GetCharset(c) == nil {
return false
}
}
return true
}
// 2个字符集之间的转换
func Convert(dstCharset string, srcCharset string, src string) (dst string, err error) {
srcCharsetUpper := strings.ToUpper(srcCharset)
dstCharsetUpper := strings.ToUpper(dstCharset)
if srcCharsetUpper == dstCharsetUpper {
return src, nil
}
s := new(mahonia.Charset)
d := new(mahonia.Charset)
srctmp := src
if srcCharset != "UTF-8" {
enc := encodingMap.Get(srcCharset)
if enc != nil {
tmp, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader([]byte(src)), enc.(encoding.Encoding).NewDecoder()))
if err != nil {
return "", fmt.Errorf("%s to utf8 failed. %v", srcCharset, err)
}
srctmp = string(tmp)
} else {
s = mahonia.GetCharset(srcCharsetUpper)
if s == nil {
return "", errors.New(fmt.Sprintf("not support charset:%s", srcCharset))
}
if s.Name != "UTF-8" {
srctmp = s.NewDecoder().ConvertString(srctmp)
}
}
}
dst = srctmp
if dstCharset != "UTF-8" {
enc := encodingMap.Get(dstCharset)
if enc != nil {
tmp, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader([]byte(srctmp)), enc.(encoding.Encoding).NewEncoder()))
if err != nil {
return "", fmt.Errorf("utf to %s failed. %v", dstCharset, err)
}
dst = string(tmp)
} else {
d = mahonia.GetCharset(dstCharsetUpper)
if d == nil {
return "", errors.New(fmt.Sprintf("not support charset:%s", dstCharset))
}
dst = srctmp
if d.Name != "UTF-8" {
dst = d.NewEncoder().ConvertString(dst)
}
}
}
return dst, nil
}

127
g/encoding/internal/gcharsetconvert_test.go Normal file
View File

@ -0,0 +1,127 @@
// Copyright 2018 gf Author(https://github.com/gogf/gf). All Rights Reserved.
//
// This Source Code Form is subject to the terms of the MIT License.
// If a copy of the MIT was not distributed with this file,
// You can obtain one at https://github.com/gogf/gf.
package internal_test
import (
"github.com/gogf/gf/g/encoding/internal"
"github.com/gogf/gf/g/test/gtest"
"testing"
)
var testData = []struct {
utf8, other, otherEncoding string
}{
{"Résumé", "Résumé", "utf8"},
{"Résumé", "R\xe9sum\xe9", "latin-1"},
{"これは漢字です。", "S0\x8c0o0\"oW[g0Y0\x020", "UTF-16LE"},
{"これは漢字です。", "0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16BE"},
{"これは漢字です。", "\xfe\xff0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16"},
{"𝄢𝄞𝄪𝄫", "\xfe\xff\xd8\x34\xdd\x22\xd8\x34\xdd\x1e\xd8\x34\xdd\x2a\xd8\x34\xdd\x2b", "UTF-16"},
{"Hello, world", "Hello, world", "ASCII"},
{"Gdańsk", "Gda\xf1sk", "ISO-8859-2"},
{"Ââ Čč Đđ Ŋŋ Õõ Šš Žž Åå Ää", "\xc2\xe2 \xc8\xe8 \xa9\xb9 \xaf\xbf \xd5\xf5 \xaa\xba \xac\xbc \xc5\xe5 \xc4\xe4", "ISO-8859-10"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "ISO-8859-11"},
{"latviešu", "latvie\xf0u", "ISO-8859-13"},
{"Seònaid", "Se\xf2naid", "ISO-8859-14"},
{"€1 is cheap", "\xa41 is cheap", "ISO-8859-15"},
{"românește", "rom\xe2ne\xbate", "ISO-8859-16"},
{"nutraĵo", "nutra\xbco", "ISO-8859-3"},
{"Kalâdlit", "Kal\xe2dlit", "ISO-8859-4"},
{"русский", "\xe0\xe3\xe1\xe1\xda\xd8\xd9", "ISO-8859-5"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "ISO-8859-7"},
{"Kağan", "Ka\xf0an", "ISO-8859-9"},
{"Résumé", "R\x8esum\x8e", "macintosh"},
{"Gdańsk", "Gda\xf1sk", "windows-1250"},
{"русский", "\xf0\xf3\xf1\xf1\xea\xe8\xe9", "windows-1251"},
{"Résumé", "R\xe9sum\xe9", "windows-1252"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "windows-1253"},
{"Kağan", "Ka\xf0an", "windows-1254"},
{"עִבְרִית", "\xf2\xc4\xe1\xc0\xf8\xc4\xe9\xfa", "windows-1255"},
{"العربية", "\xc7\xe1\xda\xd1\xc8\xed\xc9", "windows-1256"},
{"latviešu", "latvie\xf0u", "windows-1257"},
{"Việt", "Vi\xea\xf2t", "windows-1258"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "windows-874"},
{"русский", "\xd2\xd5\xd3\xd3\xcb\xc9\xca", "KOI8-R"},
{"українська", "\xd5\xcb\xd2\xc1\xa7\xce\xd3\xd8\xcb\xc1", "KOI8-U"},
{"Hello 常用國字標準字體表", "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed", "big5"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gbk"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gb18030"},
{"花间一壶酒，独酌无相亲。", "~{;(<dR;:x>F#,6@WCN^O`GW!#", "GB2312"},
{"花间一壶酒，独酌无相亲。", "~{;(<dR;:x>F#,6@WCN^O`GW!#", "HZGB2312"},
{"עִבְרִית", "\x81\x30\xfb\x30\x81\x30\xf6\x34\x81\x30\xf9\x33\x81\x30\xf6\x30\x81\x30\xfb\x36\x81\x30\xf6\x34\x81\x30\xfa\x31\x81\x30\xfb\x38", "gb18030"},
{"㧯", "\x82\x31\x89\x38", "gb18030"},
{"㧯", "㧯", "UTF-8"},
{"これは漢字です。", "\x82\xb1\x82\xea\x82\xcd\x8a\xbf\x8e\x9a\x82\xc5\x82\xb7\x81B", "SJIS"},
{"これは漢字です。", "\xa4\xb3\xa4\xec\xa4\u03f4\xc1\xbb\xfa\xa4\u01e4\xb9\xa1\xa3", "EUC-JP"},
}
func TestDecode(t *testing.T) {
for _, data := range testData {
str := ""
str, err := internal.Convert("UTF-8", data.otherEncoding, data.other)
if err != nil {
t.Errorf("Could not create decoder for %v", err)
continue
}
if str != data.utf8 {
t.Errorf("Unexpected value: %#v (expected %#v) %v", str, data.utf8, data.otherEncoding)
}
}
}
func TestEncode(t *testing.T) {
for _, data := range testData {
str := ""
str, err := internal.Convert(data.otherEncoding, "UTF-8", data.utf8)
if err != nil {
t.Errorf("Could not create decoder for %v", err)
continue
}
if str != data.other {
t.Errorf("Unexpected value: %#v (expected %#v)", str, data.other)
}
}
}
func TestConvert(t *testing.T) {
srcCharset := "big5"
src := "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed"
dstCharset := "gbk"
dst := "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed"
str, err := internal.Convert(dstCharset, srcCharset, src)
if err != nil {
t.Errorf("convert error. %v", err)
return
}
if str != dst {
t.Errorf("unexpected value:%#v (expected %#v)", str, dst)
}
}
func TestGetCharset(t *testing.T) {
gtest.Case(t, func() {
if internal.GetCharset("XX") {
t.Errorf("unexpected value:%v (expected %v)", true, false)
}
})
gtest.Case(t, func() {
if internal.GetCharset("UTF-8") == false {
t.Errorf("unexpected value:%v (expected %v)", false, true)
}
})
gtest.Case(t, func() {
if internal.GetCharset("gbk") == false {
t.Errorf("unexpected value:%v (expected %v)", false, true)
}
})
}