Last active
February 20, 2020 14:38
-
-
Save bdarfler/d080cf34f35df6c687cd5ee5a3c899f4 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
import io.Codec | |
import java.nio.ByteBuffer | |
val UTF8 = “UTF-8” | |
val ISO8859 = “ISO-8859–1” | |
val REPLACEMENT_CHAR = ‘\uFFFD’ | |
def bytesToString(bytes: Array[Byte], encoding: String) = { | |
val upper = encoding.toUpperCase | |
val codec = if (ISO8859 == upper) Codec.ISO8859 else Codec.UTF8 | |
val decoded = codec.decode(ByteBuffer.wrap(bytes)).toString | |
if (!decoded.contains(REPLACEMENT_CHAR)) { | |
decoded | |
} else { | |
val otherCodec = if (ISO8859 == upper) Codec.UTF8 else Codec.ISO8859 | |
val otherDecoded = otherCodec.decode(ByteBuffer.wrap(bytes)).toString | |
if (!otherDecoded.contains(REPLACEMENT_CHAR)) { | |
otherDecoded | |
} else { | |
val utf8 = if (ISO8859 == upper) otherDecoded else decoded | |
utf8.replace(REPLACEMENT_CHAR, ‘?’) | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment