#2282 fast detection of utf-8

This commit is contained in:
Unknwon 2015-12-27 17:02:36 -05:00
parent 240fe07287
commit 44637f03cc
4 changed files with 10 additions and 5 deletions

View file

@ -17,7 +17,7 @@ import (
"github.com/gogits/gogs/modules/setting"
)
const APP_VER = "0.8.13.1225"
const APP_VER = "0.8.13.1227"
func init() {
runtime.GOMAXPROCS(runtime.NumCPU())

View file

@ -18,6 +18,7 @@ import (
"regexp"
"strings"
"time"
"unicode/utf8"
"github.com/Unknwon/com"
"github.com/Unknwon/i18n"
@ -53,6 +54,11 @@ func ShortSha(sha1 string) string {
}
func DetectEncoding(content []byte) string {
if utf8.Valid(content[:1024]) {
log.Debug("Detected encoding: utf-8 (fast)")
return "utf-8"
}
_, name, certain := charset.DetermineEncoding(content, "")
if name != "utf-8" && len(setting.Repository.AnsiCharset) > 0 {
log.Debug("Using default AnsiCharset: %s", setting.Repository.AnsiCharset)

View file

@ -12,7 +12,6 @@ import (
"runtime"
"strings"
"time"
"unicode/utf8"
"golang.org/x/net/html/charset"
"golang.org/x/text/transform"
@ -131,11 +130,11 @@ func Sha1(str string) string {
}
func ToUtf8WithErr(content []byte) (error, string) {
if utf8.Valid(content[:1024]) {
charsetLabel := base.DetectEncoding(content)
if charsetLabel == "utf-8" {
return nil, string(content)
}
charsetLabel := base.DetectEncoding(content)
encoding, _ := charset.Lookup(charsetLabel)
if encoding == nil {
return fmt.Errorf("Unknown encoding: %s", charsetLabel), string(content)

View file

@ -1 +1 @@
0.8.13.1225
0.8.13.1227