Implementing lexer, next part 4.7

app/build.gradle.kts

@@ -34,7 +34,7 @@ java {
 
 application {
     // Define the main class for the application.
-    mainClass = "org.example.App"
+    mainClass = "org.tuxlanginterpreter.App"
 }
 
 tasks.named<Test>("test") {

app/src/main/java/org/example/App.java

@@ -1,14 +0,0 @@
-/*
- * This source file was generated by the Gradle 'init' task
- */
-package org.example;
-
-public class App {
-    public String getGreeting() {
-        return "Hello World!";
-    }
-
-    public static void main(String[] args) {
-        System.out.println(new App().getGreeting());
-    }
-}

app/src/main/java/org/tuxlanginterpreter/App.java

@@ -0,0 +1,64 @@
+package org.tuxlanginterpreter;
+
+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;
+import java.util.List;
+
+public class App {
+	static boolean hadError = false;
+
+	public static void main(String[] args) throws IOException {
+		if (args.length > 1) {
+			System.out.println("Usage: txli [script]");
+			System.exit(64); 
+		} else if (args.length == 1) {
+			run_file(args[0]);
+		} else {
+			run_prompt();
+		}
+    	}
+
+	private static void run_file(String path) throws IOException {
+		byte[] bytes = Files.readAllBytes(Paths.get(path));
+    		run(new String(bytes, Charset.defaultCharset()));
+
+		// Indicate an error in the exit code.
+		if (hadError) System.exit(65);
+  	}
+
+	private static void run_prompt() throws IOException {
+		InputStreamReader input = new InputStreamReader(System.in);
+		BufferedReader reader = new BufferedReader(input);
+
+		for (;;) { 
+			System.out.print("> ");
+			String line = reader.readLine();
+			if (line == null) break;
+			run(line);
+			hadError = false;
+		}
+  	}
+
+	private static void run(String source) {
+		Scanner scanner = new Scanner(source);
+		List<Token> tokens = scanner.scan_tokens();
+
+		// For now, just print the tokens.
+		for (Token token : tokens) {
+			System.out.println(token);
+		}
+	}
+
+	static void error(int line, String message) {
+		report(line, "", message);
+	}
+
+	private static void report(int line, String where, String message) {
+		System.err.println("[line " + line + "] Error" + where + ": " + message);
+		hadError = true;
+	}
+}

app/src/main/java/org/tuxlanginterpreter/Scanner.java

@@ -0,0 +1,154 @@
+package org.tuxlanginterpreter;
+
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+class Scanner {
+	private final String source;
+	private final List<Token> tokens = new ArrayList<>();
+	private int start = 0;
+	private int current = 0;
+	private int line = 1;
+
+	Scanner(String source) {
+		this.source = source;
+	}
+
+	private boolean is_at_end() {
+		return current >= source.length();
+	}
+
+	List<Token> scan_tokens() {
+		while (!is_at_end()) {
+			// We are at the beginning of the next lexeme.
+			start = current;
+			scan_token();
+		}
+
+		tokens.add(new Token(TokenType.EOF, "", null, line));
+		return tokens;
+  	}
+
+	private void scan_token() {
+		char c = advance();
+		switch (c) {
+			case '(': add_token(TokenType.LEFT_PAREN); break;
+			case ')': add_token(TokenType.RIGHT_PAREN); break;
+			case '{': add_token(TokenType.LEFT_BRACE); break;
+			case '}': add_token(TokenType.RIGHT_BRACE); break;
+      			case ',': add_token(TokenType.COMMA); break;
+      			case '.': add_token(TokenType.DOT); break;
+      			case '-': add_token(TokenType.MINUS); break;
+      			case '+': add_token(TokenType.PLUS); break;
+      			case ';': add_token(TokenType.SEMICOLON); break;
+      			case '*': add_token(TokenType.STAR); break; 
+			case '!':
+				add_token(match('=') ? TokenType.BANG_EQUAL : TokenType.BANG);
+				break;
+			case '=':
+				add_token(match('=') ? TokenType.EQUAL_EQUAL : TokenType.EQUAL);
+				break;
+			case '<':
+				add_token(match('=') ? TokenType.LESS_EQUAL : TokenType.LESS);
+				break;
+			case '>':
+				add_token(match('=') ? TokenType.GREATER_EQUAL : TokenType.GREATER);
+				break;
+			case '/':
+				if (match('/')) {
+					// A comment goes until the end of the line.
+					while (peek() != '\n' && !is_at_end()) advance();
+				} else {
+					add_token(TokenType.SLASH);
+				}
+				break;
+			case ' ':
+			case '\r':
+			case '\t':
+				// Ignore whitespace.
+				break;
+			case '\n':
+				line++;
+				break;
+			case '"': string(); break;
+
+			default:
+				if (is_digit(c)) {
+					number();
+				} else {
+					App.error(line, "Unexpected character.");
+				}
+				break;
+		}
+	}
+
+	private boolean is_digit(char c) {
+		return c >= '0' && c <= '9';
+	} 
+
+	private void number() {
+		while (is_digit(peek())) advance();
+
+		// Look for a fractional part.
+		if (peek() == '.' && is_digit(peek_next())) {
+			// Consume the "."
+			advance();
+
+			while (is_digit(peek())) advance();
+		}
+
+		add_token(TokenType.NUMBER, Double.parseDouble(source.substring(start, current)));
+	}
+
+	private void string() {
+		while (peek() != '"' && !is_at_end()) {
+			if (peek() == '\n') line++;
+			advance();
+		}
+
+		if (is_at_end()) {
+			App.error(line, "Unterminated string.");
+			return;
+		}
+
+		// The closing ".
+		advance();
+
+		// Trim the surrounding quotes.
+		String value = source.substring(start + 1, current - 1);
+		add_token(TokenType.STRING, value);
+	}
+
+	private char advance() {
+		return source.charAt(current++);
+	}
+
+	private char peek() {
+		if (is_at_end()) return '\0';
+		return source.charAt(current);
+	}
+
+	private char peek_next() {
+    		if (current + 1 >= source.length()) return '\0';
+    		return source.charAt(current + 1);
+	}
+
+	private boolean match(char expected) {
+		if (is_at_end()) return false;
+		if (source.charAt(current) != expected) return false;
+
+		current++;
+		return true;
+	}
+
+	private void add_token(TokenType type) {
+		add_token(type, null);
+	}
+
+	private void add_token(TokenType type, Object literal) {
+		String text = source.substring(start, current);
+		tokens.add(new Token(type, text, literal, line));
+	}
+}

app/src/main/java/org/tuxlanginterpreter/Token.java

@@ -0,0 +1,40 @@
+package org.tuxlanginterpreter;
+
+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
+}
+
+class Token {
+	final TokenType type;
+	final String lexeme;
+	final Object literal;
+	final int line; 
+
+	Token(TokenType type, String lexeme, Object literal, int line) {
+		this.type = type;
+		this.lexeme = lexeme;
+		this.literal = literal;
+		this.line = line;
+	}
+
+	public String toString() {
+		return type + " " + lexeme + " " + literal;
+	}
+}

app/src/test/java/org/tuxlanginterpreter/AppTest.java

@@ -1,14 +1,13 @@
-/*
- * This source file was generated by the Gradle 'init' task
- */
-package org.example;
+package org.tuxlanginterpreter;
 
 import org.junit.jupiter.api.Test;
 import static org.junit.jupiter.api.Assertions.*;
 
 class AppTest {
+	/*
     @Test void appHasAGreeting() {
         App classUnderTest = new App();
         assertNotNull(classUnderTest.getGreeting(), "app should have a greeting");
     }
+    */
 }