// sample-unicode-crlf.java: non-ASCII text, saved as UTF-8 (no BOM) with
// Windows (CRLF) line endings.
// Free sample from 99helpers.com/file-types/java
//
// javac reads CRLF and LF alike, and since Java 18 it reads source files
// as UTF-8 by default. On older Java, compile with
//     javac -encoding UTF-8 sample-unicode-crlf.java
// Don't save Java source with a byte order mark: javac stops with
// "illegal character: ''".
//
// Run it: java sample-unicode-crlf.java
// If letters show as "?", your terminal isn't set to UTF-8.

final class UnicodeSample {

    // 1. Identifiers may use letters from any script.
    static final String GRÜSSE = "Grüße aus Köln";

    public static void main(String[] args) {
        // 2. A Java String is a sequence of UTF-16 code units. length()
        //    counts those units; codePointCount() counts characters. They
        //    differ for emoji and other characters beyond U+FFFF.
        String[] samples = {
            "plain ASCII", GRÜSSE, "Ελληνικά", "日本語のテキスト", "مرحبا بالعالم", "emoji ☕🦀"
        };
        for (String text : samples) {
            System.out.printf("%2d units %2d chars %2d UTF-8 bytes  %s%n",
                    text.length(),
                    text.codePointCount(0, text.length()),
                    text.getBytes(java.nio.charset.StandardCharsets.UTF_8).length,
                    text);
        }

        // 3. A text block. Its CRLF line breaks are normalised to "\n", so
        //    the string is the same whichever line endings the file has.
        String poem = """
                first line
                second line""";
        System.out.println("text block contains \\r: " + poem.contains("\r"));

        // 4. Unicode escapes like é are translated before anything
        //    else, even inside comments, so a stray backslash-u followed by
        //    hex digits in a comment can break the build.
        String cafe = "café";
        System.out.println(cafe + " equals café: " + cafe.equals("café"));

        // 5. 🦀 needs two UTF-16 units (a surrogate pair), so charAt(0)
        //    returns half a character. Use codePointAt instead.
        String crab = "🦀";
        System.out.printf("U+%X, length %d, high surrogate: %b%n",
                crab.codePointAt(0), crab.length(), Character.isHighSurrogate(crab.charAt(0)));
    }
}