Data commit

Task/String-length/Java/string-length-1.java

@@ -0,0 +1,4 @@
+String s = "Hello, world!";
+int byteCountUTF16 = s.getBytes("UTF-16").length; // Incorrect: it yields 28 (that is with the BOM)
+int byteCountUTF16LE = s.getBytes("UTF-16LE").length; // Correct: it yields 26
+int byteCountUTF8  = s.getBytes("UTF-8").length; // yields 13

Task/String-length/Java/string-length-2.java

@@ -0,0 +1,2 @@
+String s = "Hello, world!";
+int not_really_the_length = s.length(); // XXX: does not (always) count Unicode characters (code points)!

Task/String-length/Java/string-length-3.java

@@ -0,0 +1,3 @@
+String str = "\uD834\uDD2A"; //U+1D12A
+int not_really__the_length = str.length(); // value is 2, which is not the length in characters
+int actual_length = str.codePointCount(0, str.length()); // value is 1, which is the length in characters

Task/String-length/Java/string-length-4.java

@@ -0,0 +1,19 @@
+import java.text.BreakIterator;
+
+public class Grapheme {
+  public static void main(String[] args) {
+    printLength("møøse");
+    printLength("𝔘𝔫𝔦𝔠𝔬𝔡𝔢");
+    printLength("J̲o̲s̲é̲");
+  }
+
+  public static void printLength(String s) {
+    BreakIterator it = BreakIterator.getCharacterInstance();
+    it.setText(s);
+    int count = 0;
+    while (it.next() != BreakIterator.DONE) {
+      count++;
+    }
+    System.out.println("Grapheme length: " + count+ " " + s);
+  }
+}