用Java写一个词法分析器

好的，以下是一个简单的Java词法分析器的代码示例：

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

public class Lexer {
    private String input;
    private int currentPosition;
    private Token currentToken;

    public Lexer(String input) {
        this.input = input;
        this.currentPosition = 0;
        this.currentToken = null;
    }

    private static final Pattern IDENTIFIER_PATTERN = Pattern.compile("[a-zA-Z][a-zA-Z0-9]*");
    private static final Pattern NUMBER_PATTERN = Pattern.compile("[0-9]+");

    private void skipWhitespace() {
        while (currentPosition < input.length() && Character.isWhitespace(input.charAt(currentPosition))) {
            currentPosition++;
        }
    }

    private Token matchIdentifier() {
        Matcher matcher = IDENTIFIER_PATTERN.matcher(input.substring(currentPosition));
        if (matcher.find()) {
            String identifier = matcher.group();
            currentPosition += identifier.length();
            return new Token(TokenType.IDENTIFIER, identifier);
        } else {
            return null;
        }
    }

    private Token matchNumber() {
        Matcher matcher = NUMBER_PATTERN.matcher(input.substring(currentPosition));
        if (matcher.find()) {
            String number = matcher.group();
            currentPosition += number.length();
            return new Token(TokenType.NUMBER, number);
        } else {
            return null;
        }
    }

    public Token getNextToken() {
        skipWhitespace();
        if (currentPosition >= input.length()) {
            return null;
        }
        char currentChar = input.charAt(currentPosition);
        if (Character.isLetter(currentChar)) {
            return matchIdentifier();
        } else if (Character.isDigit(currentChar)) {
            return matchNumber();
        } else {
            currentPosition++;
            return new Token(TokenType.OPERATOR, Character.toString(currentChar));
        }
    }
}

enum TokenType {
    IDENTIFIER,
    NUMBER,
    OPERATOR
}

class Token {
    private TokenType type;
    private String value;

    public Token(TokenType type, String value) {
        this.type = type;
        this.value = value;
    }

    public TokenType getType() {
        return type;
    }

    public String getValue() {
        return value;
    }

    @Override
    public String toString() {
        return String.format("(%s, %s)", type, value);
    }
}

这个词法分析器可以识别标识符、数字和运算符。你可以使用它来解析简单的算术表达式，例如：

Lexer lexer = new Lexer("x = 42 + y");
Token token;
while ((token = lexer.getNextToken()) != null) {
    System.out.println(token);
}

这将输出：

(IDENTIFIER, x)
(OPERATOR, =)
(NUMBER, 42)
(OPERATOR, +)
(IDENTIFIER, y)