Implement the Scanner

jlox/build.gradle.kts

@@ -15,10 +15,20 @@ dependencies {
 }
 
 application {
-    mainClass.set("xyz.ctsk.jlox.Hello")
+    mainClass.set("xyz.ctsk.lox.Lox")
+}
+
+tasks.jar {
+    manifest {
+        attributes(mapOf("Main-Class" to "xyz.ctsk.lox.Lox"))
+    }
 }
 
 
 tasks.getByName<Test>("test") {
     useJUnitPlatform()
 }
+
+tasks.named<JavaExec>("run") {
+    standardInput = System.`in`
+}

jlox/src/main/java/xyz/ctsk/jlox/Hello.java

@@ -1,7 +0,0 @@
-package xyz.ctsk.jlox;
-
-public class Hello {
-    public static void main(String[] arg) {
-        System.out.println("Hello World");
-    }
-}

jlox/src/main/java/xyz/ctsk/lox/Lox.java

@@ -0,0 +1,62 @@
+package xyz.ctsk.lox;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.nio.charset.Charset;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+public class Lox {
+    private static boolean hadError = false;
+     private static void run(String source) {
+        var scanner = new Scanner(source);
+        scanner.scanTokens().forEach(System.out::println);
+    }
+
+    static void error(int line, String message) {
+         report(line, "", message);
+    }
+
+    private static void report(int line, String where, String message) {
+         System.err.printf("[line %d] Error %s: %s%n", line, where, message);
+         hadError = true;
+    }
+
+
+    private static void runPrompt() throws IOException {
+        var input = new InputStreamReader(System.in);
+        var reader = new BufferedReader(input);
+
+        while (true) {
+            System.out.println("> ");
+            String line = reader.readLine();
+            if (line == null) break;
+            run(line);
+            hadError = false;
+        }
+    };
+
+    private static void runFile(String path) throws IOException {
+        byte[] bytes = Files.readAllBytes(Paths.get(path));
+        run(new String(bytes, Charset.defaultCharset()));
+
+        if (hadError) {
+            System.exit(65);
+        }
+    }
+
+    private static void printUsage() {
+        System.out.println("Usage: jlox [script]");
+    }
+
+    public static void main(String[] args) throws IOException {
+        if (args.length == 0) {
+            runPrompt();
+        } else if (args.length == 1) {
+            runFile(args[0]);
+        } else {
+            printUsage();
+        }
+    }
+}

jlox/src/main/java/xyz/ctsk/lox/Scanner.java

@@ -0,0 +1,203 @@
+package xyz.ctsk.lox;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+import static java.util.Map.entry;
+import static xyz.ctsk.lox.TokenType.*;
+
+public class Scanner {
+    private static final Map<String, TokenType> keywords =
+            Map.ofEntries(
+                    entry("and", AND),
+                    entry("class", CLASS),
+                    entry("else", ELSE),
+                    entry("false", FALSE),
+                    entry("for", FOR),
+                    entry("fun", FUN),
+                    entry("if", IF),
+                    entry("nil", NIL),
+                    entry("or", OR),
+                    entry("print", PRINT),
+                    entry("return", RETURN),
+                    entry("super", SUPER),
+                    entry("this", THIS),
+                    entry("true", TRUE),
+                    entry("var", VAR),
+                    entry("while", WHILE)
+            );
+
+    private final String source;
+    private final List<Token> tokens = new ArrayList<>();
+
+    private int start = 0;
+    private int current = 0;
+    private int line = 1;
+
+    public Scanner(String source) {
+        this.source = source;
+    }
+
+    private String currentMatch() {
+        return source.substring(start, current);
+    }
+
+    private void addToken(TokenType type, Object literal) {
+        tokens.add(new Token(type, currentMatch(), literal, line));
+    }
+
+    private void addToken(TokenType type) {
+        addToken(type, null);
+    }
+
+
+    private boolean isAtEnd() {
+        return current >= source.length();
+    }
+    private char advance() {
+        return source.charAt(current++);
+    }
+    private char peek() {
+        return isAtEnd() ? '\0' : source.charAt(current);
+    }
+    private boolean match(char expected) {
+        if (isAtEnd()) {
+            return false;
+        }
+
+        if (source.charAt(current) != expected) {
+            return false;
+        }
+
+        current++;
+        return true;
+    }
+
+    private void string() {
+        while (peek() != '"' && !isAtEnd()) {
+            if (peek() == '\n') line++;
+            advance();
+        }
+
+        if (isAtEnd()) {
+            Lox.error(line, "Unterminated string.");
+            return;
+        }
+
+        advance();
+
+        String value = source.substring(start + 1, current - 1);
+        addToken(STRING, value);
+    }
+
+    private char peekNext() {
+        if (current + 1 >= source.length()) return '\0';
+        return source.charAt(current + 1);
+    }
+
+    private static boolean isDigit(char c) {
+        return '0' <= c && c <= '9';
+    }
+
+    private static boolean isAlpha(char c) {
+        return ('a' <= c && c <= 'z') ||
+                ('A' <= c && c <= 'Z') ||
+                c == '_';
+    }
+
+    private static boolean isAlphaNumeric(char c) {
+        return isDigit(c) || isAlpha(c);
+    }
+
+    private static boolean isKeyword(String s) {
+        return keywords.containsKey(s);
+    }
+
+    private void number() {
+        while (isDigit(peek())) advance();
+
+        // Look for a fractional part.
+        if (peek() == '.' && isDigit(peekNext())) {
+            // Consume the "."
+            advance();
+
+            while (isDigit(peek())) advance();
+        }
+
+        // Enhancement: Do not allow Letters in numbers
+        if (isAlpha(peek())) {
+            Lox.error(line, "Unexpected character in number.");
+            return;
+        }
+
+        addToken(NUMBER,
+                Double.parseDouble(currentMatch()));
+    }
+
+
+    private void identifier() {
+        while (isAlphaNumeric(peek())) advance();
+
+        var text = currentMatch();
+        if (isKeyword(text)) {
+            addToken(keywords.get(text));
+        } else {
+            addToken(IDENTIFIER);
+        }
+    }
+
+    private void scanToken() {
+        var c = advance();
+        switch (c) {
+            case '(' -> addToken(LEFT_PAREN);
+            case ')' -> addToken(RIGHT_PAREN);
+            case '{' -> addToken(LEFT_BRACE);
+            case '}' -> addToken(RIGHT_BRACE);
+            case ',' -> addToken(COMMA);
+            case '.' -> addToken(DOT);
+            case '-' -> addToken(MINUS);
+            case '+' -> addToken(PLUS);
+            case ';' -> addToken(SEMICOLON);
+            case '*' -> addToken(STAR);
+
+            case '!' -> addToken(match('=') ? BANG_EQUAL : BANG);
+            case '=' -> addToken(match('=') ? EQUAL_EQUAL : EQUAL);
+            case '<' -> addToken(match('=') ? LESS_EQUAL : LESS);
+            case '>' -> addToken(match('=') ? GREATER_EQUAL : GREATER);
+
+            case '/' -> {
+                if (match('/')) {
+                    while (peek() != '\n' && !isAtEnd()) advance();
+                } else {
+                    addToken(SLASH);
+                }
+            }
+
+            case ' ', '\r', '\t' -> {}
+            case '\n' -> line++;
+
+            case '"' -> string();
+
+            default -> {
+                if (isDigit(c)) {
+                    number();
+                } else if (isAlpha(c)) {
+                    identifier();
+                } else {
+                    Lox.error(line, "Unexpected character.");
+                }
+            }
+        }
+    }
+
+    List<Token> scanTokens() {
+        while (!isAtEnd()) {
+            start = current;
+            scanToken();
+        }
+
+        tokens.add(new Token(EOF, "", line));
+        return tokens;
+    }
+}

jlox/src/main/java/xyz/ctsk/lox/Token.java

@@ -0,0 +1,16 @@
+package xyz.ctsk.lox;
+
+public record Token(TokenType type, String lexeme, Object literal, int line) {
+    public Token(TokenType type, String lexeme, int line) {
+        this(type, lexeme, null, line);
+    }
+
+    @Override
+    public String toString() {
+        if (literal == null) {
+            return "%s %s".formatted(type, lexeme);
+        } else {
+            return "%s %s %s".formatted(type, lexeme, literal);
+        }
+    }
+};

jlox/src/main/java/xyz/ctsk/lox/TokenType.java

@@ -0,0 +1,22 @@
+package xyz.ctsk.lox;
+
+public enum TokenType {
+    // Single-character tokens
+    LEFT_PAREN, RIGHT_PAREN, LEFT_BRACE, RIGHT_BRACE,
+    COMMA, DOT, MINUS, PLUS, SEMICOLON, SLASH, STAR,
+
+    // One or two character tokens
+    BANG, BANG_EQUAL,
+    EQUAL, EQUAL_EQUAL,
+    GREATER, GREATER_EQUAL,
+    LESS, LESS_EQUAL,
+
+    // Literals
+    IDENTIFIER, STRING, NUMBER,
+
+    // Keywords
+    AND, CLASS, ELSE, FALSE, FUN, FOR, IF, NIL, OR,
+    PRINT, RETURN, SUPER, THIS, TRUE, VAR, WHILE,
+
+    EOF
+}