编译原理词法分析器-扫描器的设计与实现的代码Java实现

以下是使用Java实现的一个简单词法分析器：

import java.io.*;

// 定义Token的类型
enum TokenType {
    TOK_INT,    // 整数
    TOK_OP,     // 运算符
    TOK_EOF,    // 文件结束
}

// 定义Token的类
class Token {
    public TokenType type;  // Token类型
    public int value;       // Token的值

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

// 词法分析器的类
class Lexer {
    private BufferedReader reader;
    private int currentChar;

    public Lexer(String filename) throws FileNotFoundException {
        reader = new BufferedReader(new FileReader(filename));
        currentChar = getNextChar();
    }

    private int getNextChar() {
        try {
            return reader.read();
        } catch (IOException e) {
            e.printStackTrace();
            return -1;
        }
    }

    private void skipWhitespace() {
        while (Character.isWhitespace(currentChar)) {
            currentChar = getNextChar();
        }
    }

    private Token getIntToken() {
        int value = 0;
        while (Character.isDigit(currentChar)) {
            value = value * 10 + (currentChar - '0');
            currentChar = getNextChar();
        }
        return new Token(TokenType.TOK_INT, value);
    }

    private Token getOpToken() {
        Token token = new Token(TokenType.TOK_OP, currentChar);
        currentChar = getNextChar();
        return token;
    }

    public Token getNextToken() {
        while (currentChar != -1) {
            if (Character.isWhitespace(currentChar)) {
                skipWhitespace();
                continue;
            } else if (Character.isDigit(currentChar)) {
                return getIntToken();
            } else if (currentChar == '+' || currentChar == '-' || currentChar == '*' || currentChar == '/') {
                return getOpToken();
            } else {
                System.out.println("Unknown character: " + (char)currentChar);
                currentChar = getNextChar();
            }
        }
        return new Token(TokenType.TOK_EOF, 0);
    }
}

// 测试词法分析器的主函数
public class Main {
    public static void main(String[] args) throws FileNotFoundException {
        Lexer lexer = new Lexer("input.txt");
        Token token = lexer.getNextToken();
        while (token.type != TokenType.TOK_EOF) {
            if (token.type == TokenType.TOK_INT) {
                System.out.println("Integer: " + token.value);
            } else if (token.type == TokenType.TOK_OP) {
                System.out.println("Operator: " + (char)token.value);
            }
            token = lexer.getNextToken();
        }
    }
}

该词法分析器可以识别整数和四种基本运算符（加、减、乘、除）。它从文件中读取字符并逐个处理，将字符序列转换为一系列Token。