Last active
October 27, 2022 10:58
-
-
Save amitavaghosh1/0f1dc0347b9f0cfe6f7a50b3f87eedc7 to your computer and use it in GitHub Desktop.
Encoder. Change \r to \n. Fucking microsoft
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package encoder | |
import ( | |
"io" | |
"io/ioutil" | |
"mime/multipart" | |
"github.com/dimchansky/utfbom" | |
"github.com/sirupsen/logrus" | |
"golang.org/x/net/html/charset" | |
"golang.org/x/text/transform" | |
) | |
type Normalize struct { | |
prev byte | |
} | |
func (n *Normalize) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) { | |
for nDst < len(dst) && nSrc < len(src) { | |
c := src[nSrc] | |
switch c { | |
case '\r': | |
dst[nDst] = '\n' | |
case '\n': | |
if n.prev == '\r' { | |
nSrc++ | |
n.prev = c | |
continue | |
} | |
dst[nDst] = '\n' | |
default: | |
dst[nDst] = c | |
} | |
n.prev = c | |
nDst++ | |
nSrc++ | |
} | |
if nSrc < len(src) { | |
err = transform.ErrShortDst | |
} | |
return | |
} | |
func (n *Normalize) Reset() { | |
n.prev = 0 | |
} | |
func EncodedReader(file multipart.File) (t io.Reader, err error) { | |
reader := utfbom.SkipOnly(file) | |
defer file.Seek(0, io.SeekStart) | |
b, err := ioutil.ReadAll(reader) | |
if err != nil { | |
return t, err | |
} | |
enc, nname, certain := charset.DetermineEncoding(b, "text/plain") | |
logrus.Println("[EncodedReader] enconding detected", nname, "certain: ", certain) | |
return transform.NewReader(enc.NewDecoder().Reader(reader), &Normalize{}), nil | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment