Console.java

// Kimberley Ni and Eylul Oktay

import java.util.ArrayList;
import java.util.Scanner;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Console {
	private static Scanner in;

	public static void main(String[] args) {
		in = new Scanner(System.in);

		Lexer lexer = new Lexer();
		Parser parser = new Parser();

		String input = cleanConsoleInput(); // see comment

		while (!input.equalsIgnoreCase("exit")) {

			ArrayList<String> tokens = lexer.tokenize(input);
			tokens = Parser.preparser(tokens);

			if (tokens.size() > 0) {
				String output = "";

				try {
					Expression exp = parser.parse(tokens);
					if (tokens.contains("=")) {
						output = Parser.lastVariableAssignResult();
					} else {
						output = exp.toString();
					}
				} catch (Exception e) {
					System.out.println("Unparsable expression, input was: \"" + input + "\"");
					e.printStackTrace();
					input = cleanConsoleInput();
					continue;
				}
				
				System.out.println(output);
			}

			input = cleanConsoleInput();
		}
		System.out.println("Goodbye!");
	}

	/*
	 * Collects user input, and ...
	 * ... does a bit of raw string processing to (1) strip away comments,
	 * (2) remove the BOM character that appears in unicode strings in Windows,
	 * (3) turn all weird whitespace characters into spaces,
	 * and (4) replace all λs with backslashes.
	 */

	private static String cleanConsoleInput() {
		System.out.print("> ");
		String raw = in.nextLine();
		String deBOMified = raw.replaceAll("\uFEFF", ""); // remove Byte Order Marker from UTF

		String clean = removeWeirdWhitespace(deBOMified);

		return clean.replaceAll("λ", "\\\\");
	}

	public static String removeWeirdWhitespace(String input) {
		String whitespace_chars = "" // dummy empty string for homogeneity
				+ "\\u0009" // CHARACTER TABULATION
				+ "\\u000A" // LINE FEED (LF)
				+ "\\u000B" // LINE TABULATION
				+ "\\u000C" // FORM FEED (FF)
				+ "\\u000D" // CARRIAGE RETURN (CR)
				+ "\\u0020" // SPACE
				+ "\\u0085" // NEXT LINE (NEL)
				+ "\\u00A0" // NO-BREAK SPACE
				+ "\\u1680" // OGHAM SPACE MARK
				+ "\\u180E" // MONGOLIAN VOWEL SEPARATOR
				+ "\\u2000" // EN QUAD
				+ "\\u2001" // EM QUAD
				+ "\\u2002" // EN SPACE
				+ "\\u2003" // EM SPACE
				+ "\\u2004" // THREE-PER-EM SPACE
				+ "\\u2005" // FOUR-PER-EM SPACE
				+ "\\u2006" // SIX-PER-EM SPACE
				+ "\\u2007" // FIGURE SPACE
				+ "\\u2008" // PUNCTUATION SPACE
				+ "\\u2009" // THIN SPACE
				+ "\\u200A" // HAIR SPACE
				+ "\\u2028" // LINE SEPARATOR
				+ "\\u2029" // PARAGRAPH SEPARATOR
				+ "\\u202F" // NARROW NO-BREAK SPACE
				+ "\\u205F" // MEDIUM MATHEMATICAL SPACE
				+ "\\u3000"; // IDEOGRAPHIC SPACE
		Pattern whitespace = Pattern.compile(whitespace_chars);
		Matcher matcher = whitespace.matcher(input);
		String result = input;
		if (matcher.find()) {
			result = matcher.replaceAll(" ");
		}

		return result;
	}

}