用java写一个词法分析

好的，下面是一个简单的 Java 词法分析器的示例代码：

import java.util.ArrayList;
import java.util.List;

public class Lexer {
    
    private final String input;
    private int position;
    private final List<Token> tokens;
    
    public Lexer(String input) {
        this.input = input;
        this.position = 0;
        this.tokens = new ArrayList<>();
    }
    
    public List<Token> tokenize() {
        while (position < input.length()) {
            char currentChar = input.charAt(position);
            if (Character.isDigit(currentChar)) {
                tokenizeNumber();
            } else if (Character.isLetter(currentChar)) {
                tokenizeIdentifier();
            } else if (currentChar == '+') {
                tokens.add(new Token(TokenType.PLUS, "+"));
                position++;
            } else if (currentChar == '-') {
                tokens.add(new Token(TokenType.MINUS, "-"));
                position++;
            } else if (currentChar == '*') {
                tokens.add(new Token(TokenType.ASTERISK, "*"));
                position++;
            } else if (currentChar == '/') {
                tokens.add(new Token(TokenType.SLASH, "/"));
                position++;
            } else if (currentChar == '(') {
                tokens.add(new Token(TokenType.LEFT_PAREN, "("));
                position++;
            } else if (currentChar == ')') {
                tokens.add(new Token(TokenType.RIGHT_PAREN, ")"));
                position++;
            } else {
                throw new RuntimeException("Invalid character: " + currentChar);
            }
        }
        return tokens;
    }
    
    private void tokenizeNumber() {
        StringBuilder sb = new StringBuilder();
        while (position < input.length() && Character.isDigit(input.charAt(position))) {
            sb.append(input.charAt(position));
            position++;
        }
        tokens.add(new Token(TokenType.NUMBER, sb.toString()));
    }
    
    private void tokenizeIdentifier() {
        StringBuilder sb = new StringBuilder();
        while (position < input.length() && Character.isLetter(input.charAt(position))) {
            sb.append(input.charAt(position));
            position++;
        }
        tokens.add(new Token(TokenType.IDENTIFIER, sb.toString()));
    }
    
}

这个词法分析器可以识别简单的加减乘除表达式和标识符，它将输入字符串转换为一系列的 Token 对象。Token 类型定义如下：

public enum TokenType {
    NUMBER,
    IDENTIFIER,
    PLUS,
    MINUS,
    ASTERISK,
    SLASH,
    LEFT_PAREN,
    RIGHT_PAREN
}

Token 类定义如下：

public class Token {
    
    private final TokenType type;
    private final 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);
    }
    
}

下面是一个简单的测试程序：

public class Main {
    
    public static void main(String[] args) {
        Lexer lexer = new Lexer("1+2*3");
        List<Token> tokens = lexer.tokenize();
        System.out.println(tokens);
    }
    
}

输出结果为：

[(NUMBER, 1), (PLUS, +), (NUMBER, 2), (ASTERISK, *), (NUMBER, 3)]