import java.lang.reflect.Field;
import org.openjdk.jol.info.ClassLayout;
import org.openjdk.jol.info.GraphLayout;
import org.openjdk.jol.vm.VM;

/**
 * What one String really costs: the String object, the byte[] it points to, and the coder byte that says how to read it.
 * Measured with JOL (org.openjdk.jol:jol-core). Run by run.sh under several JVM flag sets.
 */
public class StringLayout {

    static byte coder(String s) throws Exception {
        Field f = String.class.getDeclaredField("coder");
        f.setAccessible(true);                       // needs --add-opens java.base/java.lang=ALL-UNNAMED
        return f.getByte(s);
    }

    static byte[] value(String s) throws Exception {
        Field f = String.class.getDeclaredField("value");
        f.setAccessible(true);
        return (byte[]) f.get(s);
    }

    static String repeat(char c, int n) { return String.valueOf(c).repeat(n); }

    public static void main(String[] args) throws Exception {
        System.out.println("java.version = " + System.getProperty("java.version"));
        System.out.println("vm.flags     = " + String.join(" ", java.lang.management.ManagementFactory.getRuntimeMXBean().getInputArguments()
                .stream().filter(a -> a.startsWith("-XX")).toList()));
        System.out.println(VM.current().details().lines().filter(l -> l.startsWith("# Objects are 8 bytes") || l.startsWith("# Field sizes")
                || l.contains("Array element") || l.contains("compressed")).reduce("", (a, b) -> a + b + "\n"));

        System.out.println("=== java.lang.String, the class");
        System.out.println(ClassLayout.parseClass(String.class).toPrintable());

        System.out.println("=== one Latin-1 string and one UTF-16 string, field by field");
        System.out.println(ClassLayout.parseInstance("hello").toPrintable());
        System.out.println(ClassLayout.parseInstance("h\u20ACllo").toPrintable());

        System.out.println("=== the byte[] behind each");
        System.out.println(ClassLayout.parseInstance(value("hello")).toPrintable());
        System.out.println(ClassLayout.parseInstance(value("h\u20ACllo")).toPrintable());

        System.out.println("=== footprint by length (String object + its byte[], via GraphLayout)");
        System.out.println("chars  content   coder  byte[].length  String  byte[]  total");
        for (int n : new int[] {0, 1, 5, 10, 20, 40, 100, 1000}) {
            for (char c : new char[] {'a', '\u00E9', '\u20AC'}) {          // a = ASCII, e-acute = Latin-1 supplement, euro = needs UTF-16
                String s = new String(repeat(c, n).toCharArray());           // a fresh object, never the interned literal
                long total = GraphLayout.parseInstance(s).totalSize();
                long str = ClassLayout.parseInstance(s).instanceSize();
                long arr = ClassLayout.parseInstance(value(s)).instanceSize();
                System.out.printf("%5d  %-8s  %5d  %13d  %6d  %6d  %5d%n", n,
                        c == 'a' ? "ASCII" : c == '\u00E9' ? "U+00E9" : "U+20AC", coder(s), value(s).length, str, arr, total);
            }
        }
    }
}