Last active
January 13, 2023 01:36
-
-
Save jschaf/bd600ce71ad3798af6c160d74904ac9c to your computer and use it in GitHub Desktop.
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
# We append the integers 1..50 to a base prefix. | |
# The problematic strings have the apostrophe \xe2 | |
# Andy’s liqour parent account | |
# Carr’s Bar N’ Grill | |
short dest error transforming unicode to ascii src_bytes="wind-Andy\xe2" src_bytes_read=10, dst_bytes="wind-And\x00\x00" dst_bytes_written=8: transform: short destination buffer | |
short dest error transforming unicode to ascii src_bytes="wind-Andy\xe21" src_bytes_read=11, dst_bytes="wind-And\x00\x00\x00" dst_bytes_written=8: transform: short destination buffer ... | |
... | |
short dest error transforming unicode to ascii src_bytes="wind-Andy\xe246" src_bytes_read=12, dst_bytes="wind-Andy\x00\x00\x00" dst_bytes_written=9: transform: short destination buffer | |
short dest error transforming unicode to ascii src_bytes="wind-Andy\xe247" src_bytes_read=12, dst_bytes="wind-Andy\x00\x00\x00" dst_bytes_written=9: transform: short destination buffer |
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
// normalize converts all unicode chars into ASCII. | |
func normalize(cs []byte) []byte { | |
if !hasUnicodeChars(cs) { | |
return cs | |
} | |
chars := make([]byte, len(cs)) | |
asciiTransformer := transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC) | |
nDst, nSrc, err := asciiTransformer.Transform(chars, cs, true) | |
if err != nil { | |
if errors.Is(err, transform.ErrShortDst) { | |
log.Global().Sugar().Errorf("short dest error transforming unicode to ascii src_bytes=%q src_bytes_read=%d, dst_bytes=%q dst_bytes_written=%d: %s", cs, nSrc, chars, nDst, err.Error()) | |
} else { | |
panic(fmt.Sprintf("transform unicode %q to ascii: %s", string(chars), err.Error())) | |
} | |
} | |
chars = chars[:nDst] | |
return chars | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment