UTF-8 encode and decode: Difference between revisions

Content added Content deleted
Line 854: Line 854:
}</lang>
}</lang>
=== Functional solution===
=== Functional solution===
<lang scala>object UTF8EncodeAndDecode extends App {
<lang scala>import java.nio.charset.StandardCharsets

object UTF8EncodeAndDecode extends App {


val codePoints = Seq(0x0041, 0x00F6, 0x0416, 0x20AC, 0x1D11E)
val codePoints = Seq(0x0041, 0x00F6, 0x0416, 0x20AC, 0x1D11E)
Line 865: Line 867:


println("Char Name Unicode UTF-8 Decoded")
println("Char Name Unicode UTF-8 Decoded")
for (codePoint <- codePoints) {
codePoints.foreach{ codePoint =>
val w = if (Character.isBmpCodePoint(codePoint)) 4 else 5 // Compute spacing
val w = if (Character.isBmpCodePoint(codePoint)) 4 else 5 // Compute spacing
val bytes = utf8Encode(codePoint)
val bytes = utf8Encode(codePoint)
Line 874: Line 876:


printf(s"%-${w}c %-36s %-7s %-${16 - w}s%c%n",
printf(s"%-${w}c %-36s %-7s %-${16 - w}s%c%n",
codePoint, Character.getName(codePoint), leftAlignedHex, utf, utf8Decode(bytes))
codePoint, Character.getName(codePoint), leftAlignedHex, utf, utf8Decode(bytes)) }
⚫
}


println(s"\nSuccessfully completed without errors. [total ${scala.compat.Platform.currentTime - executionStart} ms]")
println(s"\nSuccessfully completed without errors. [total ${scala.compat.Platform.currentTime - executionStart} ms]")
}</lang>
}</lang>
=== Composable and testable solution===
<lang scala>package example

object UTF8EncodeAndDecode extends TheMeat with App {
val codePoints = Seq(0x0041, 0x00F6, 0x0416, 0x20AC, 0x1D11E)

println("Char Name Unicode UTF-8 Decoded")
codePoints.foreach { codepoint => print(composeString(codepoint)) }

println(s"\nSuccessfully completed without errors. [total ${scala.compat.Platform.currentTime - executionStart} ms]")
}

trait TheMeat {
import java.nio.charset.StandardCharsets

def composeString(codePoint: Int): String = {
val w = if (Character.isBmpCodePoint(codePoint)) 4 else 5 // Compute spacing
val bytes = utf8Encode(codePoint)

def leftAlignedHex: String = f"U+${codePoint}%04X"

def utf: String = bytes.foldLeft("")(_ + "%02X ".format(_))

s"%-${w}c %-36s %-7s %-${16 - w}s%c%n"
.format(codePoint, Character.getName(codePoint), leftAlignedHex, utf, utf8Decode(bytes))
⚫
}

def utf8Encode(codepoint: Int): Array[Byte] =
new String(Array[Int](codepoint), 0, 1).getBytes(StandardCharsets.UTF_8)

def utf8Decode(bytes: Array[Byte]): Int =
new String(bytes, StandardCharsets.UTF_8).codePointAt(0)

}
</lang>


=={{header|Sidef}}==
=={{header|Sidef}}==
Retrieved from "https://rosettacode.org/wiki/UTF-8_encode_and_decode"