Java Unicode System

// char holds a single Unicode character:
char letter = 'A';          // U+0041 — Latin capital A
char digit  = '5';          // U+0035
char space  = ' ';          // U+0020
char newline = '
';        // U+000A — escape sequence

// Unicode escape sequences — \uXXXX (4 hex digits):
char omega = 'Ω';      // Ω — Greek capital Omega
char rupee = '₹';      // ₹ — Indian Rupee sign
char snowman = '☃';    // ☃

// char is numerically a 16-bit integer:
char c = 'A';
int code = c;               // code = 65 (Unicode code point for 'A')
char next = (char)(c + 1);  // next = 'B'

// Printing Unicode:
System.out.println('Ω');   // prints: Ω
System.out.println('₹');   // prints: ₹

// char arithmetic:
for (char ch = 'A'; ch <= 'Z'; ch++) {
    System.out.print(ch);       // prints: ABCDEFGHIJKLMNOPQRSTUVWXYZ
}

// In string literals:
String greeting = "中文";    // 中文 — Chinese characters
String hello = "Hello";  // "Hello"

// In char literals:
char euro = '€';     // €
char pi = 'π';       // π

// In identifiers (unusual but valid):
int Age = 25;        // same as: int Age = 25;

// Unicode escapes are processed BEFORE compilation:
// This means 
 (newline) in source code is a real newline:
// System.out.println("line1
line2");  // same as 


// Common Unicode escapes worth knowing:
// 	 — horizontal tab (same as 	)
// 
 — line feed / newline (same as 
)
// 
 — carriage return (same as 
)
// " — double quote (same as ")
// ' — single quote (same as ')
// \ — backslash (same as \)

// String length returns the number of char values, not visual characters:
String s = "Hello";
System.out.println(s.length());   // 5 — as expected

// Emoji are supplementary characters — stored as surrogate pairs:
String emoji = "😀";
System.out.println(emoji.length());         // 2 — two char values!
System.out.println(emoji.codePointCount(0, emoji.length()));  // 1 — one character

// Safe iteration over code points (handles surrogates correctly):
String text = "Hello 😀";
text.codePoints().forEach(cp -> {
    System.out.println(Character.toString(cp));  // correctly handles emoji
});

// String.chars() returns char values — may split surrogate pairs:
// String.codePoints() returns code points — handles supplementary characters
String mixed = "A😀B";   // A + 😀 (surrogate pair) + B
System.out.println(mixed.length());              // 4 (A + 2 surrogates + B)
System.out.println(mixed.codePointCount(0, 4));  // 3 (A + 😀 + B)

import java.io.*;
import java.nio.charset.StandardCharsets;
import java.nio.file.*;

// ALWAYS specify charset explicitly — never rely on the default:

// Writing UTF-8 file:
Path path = Path.of("output.txt");
Files.writeString(path, "Hello 世界 🌍", StandardCharsets.UTF_8);

// Reading UTF-8 file:
String content = Files.readString(path, StandardCharsets.UTF_8);

// PrintWriter with explicit encoding:
PrintWriter writer = new PrintWriter(
    new OutputStreamWriter(
        new FileOutputStream("file.txt"), StandardCharsets.UTF_8));

// BufferedReader with explicit encoding:
BufferedReader reader = new BufferedReader(
    new InputStreamReader(
        new FileInputStream("file.txt"), StandardCharsets.UTF_8));

// Java 18+ — UTF-8 is the default charset (finally!)
// Before Java 18: the default was platform-dependent (Cp1252 on Windows, UTF-8 on Linux)
// Best practice: still specify StandardCharsets.UTF_8 explicitly for clarity

// Testing character categories:
Character.isLetter('A')          // true
Character.isLetter('5')          // false
Character.isDigit('7')           // true
Character.isLetterOrDigit('_')   // false
Character.isWhitespace(' ')      // true
Character.isUpperCase('A')       // true
Character.isLowerCase('a')       // true

// Unicode-aware:
Character.isLetter('α')          // true — Greek alpha
Character.isLetter('中')          // true — Chinese character

// Case conversion:
Character.toUpperCase('a')       // 'A'
Character.toLowerCase('Ω')      // 'ω'

// Supplementary character support (code point versions):
int codePoint = "😀".codePointAt(0);
Character.isLetterOrDigit(codePoint)     // false — emoji is not a letter
Character.getType(codePoint)             // 28 = OTHER_SYMBOL

// Get Unicode block and category:
Character.UnicodeBlock block = Character.UnicodeBlock.of('α');
// block = Character.UnicodeBlock.GREEK