Sync

Task/Character-codes/Befunge/character-codes.bf

@@ -1 +1 @@
-"A".  88*1+,
+"a". 99*44*+, @

Task/Character-codes/Bracmat/character-codes.bracmat

@@ -0,0 +1,21 @@
+( put
+$ ( str
+  $ ( "\nLatin a
+        ISO-9959-1: "
+      asc$a
+      " = "
+      chr$97
+      "
+             UTF-8: "
+      utf$a
+      " = "
+      chu$97
+      \n
+      "Cyrillic а (UTF-8): "
+      utf$а
+      " = "
+      chu$1072
+      \n
+    )
+  )
+)

Task/Character-codes/Component-Pascal/character-codes.component

@@ -0,0 +1,9 @@
+PROCEDURE CharCodes*;
+VAR
+	c : CHAR;
+BEGIN
+	c := 'A';
+	StdLog.Char(c);StdLog.String(":> ");StdLog.Int(ORD(c));StdLog.Ln;
+	c := CHR(3A9H);
+	StdLog.Char(c);StdLog.String(":> ");StdLog.Int(ORD(c));StdLog.Ln
+END CharCodes;

Task/Character-codes/Scala/character-codes-1.scala

@@ -1,5 +1,11 @@
 scala> 'a' toInt
-res9: Int = 97
+res2: Int = 97
 
 scala> 97 toChar
-res10: Char = a
+res3: Char = a
+
+scala> '\u0061'
+res4: Char = a
+
+scala> "\uD869\uDEA5"
+res5: String = 𪚥

Task/Character-codes/Scala/character-codes-2.scala

@@ -1,7 +1,43 @@
-def charToInt(c: Char, next: Char): Option[Int] = (c, next) match {
-  case _ if (c.isHighSurrogate && next.isLowSurrogate) => Some(java.lang.Character.toCodePoint(c, next))
-  case _ if (c.isLowSurrogate) => None
-  case _ => Some(c.toInt)
-}
+import java.lang.Character._; import scala.annotation.tailrec
 
-def intToChars(n: Int): Array[Char] = java.lang.Character.toChars(n)
+object CharacterCode extends App {
+  def intToChars(n: Int): Array[Char] = java.lang.Character.toChars(n)
+
+  def UnicodeToList(UTFstring: String) = {
+    @tailrec
+    def inner(str: List[Char], acc: List[String], surrogateHalf: Option[Char]): List[String] = {
+      (str, surrogateHalf) match {
+        case (Nil, _) => acc
+        case (ch :: rest, None) => if (ch.isSurrogate) inner(rest, acc, Some(ch))
+        else inner(rest, acc :+ ch.toString, None)
+        case (ch :: rest, Some(f)) => inner(rest, (acc :+ (f.toString + ch)), None)
+      }
+    }
+    inner(UTFstring.toList, Nil, None)
+  }
+
+  def UnicodeToInt(utf: String) = {
+    def charToInt(high: Char, low: Char) =
+      { if (isSurrogatePair(high, low)) toCodePoint(high, low) else high.toInt }
+    charToInt(utf(0), if (utf.size > 1) utf(1) else 0)
+  }
+
+  def UTFtoHexString(utf: String) = { utf.map(ch => f"${ch.toInt}%04X").mkString("\"\\u", "\\u", "\"") }
+
+  def flags(ch: String) = { // Testing Unicode character properties
+    (if (ch matches "\\p{M}") "Y" else "N") + (if (ch matches "\\p{Mn}") "Y" else "N")
+  }
+
+  val str = '\uFEFF' /*big-endian BOM*/ + "\u0301a" +
+    "$áabcde¢£¤¥©ÇßIJijŁłʒλπक्तु•₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵℃←→⇒∙⌘☃☹☺☻ア字文𠀀" + intToChars(173733).mkString
+
+  println(s"Example string: $str")
+  println("""    | Chr C/C++/Java source  Code Point Hex      Dec Mn Name
+		  	!----+ --- ------------------------- ------- -------- -- """.stripMargin('!') + "-" * 27)
+
+  (UnicodeToList(str)).zipWithIndex.map {
+    case (coll, nr) =>
+      f"$nr%4d: $coll\t${UTFtoHexString(coll)}%27s U+${UnicodeToInt(coll)}%05X" +
+        f"${"(" + UnicodeToInt(coll).toString}%8s) ${flags(coll)}  ${getName(coll(0).toInt)} "
+  }.foreach(println)
+}