用java写一个词法分析的代码

以下是一个简单的 Java 词法分析器代码，它可以将输入的代码分解为单个标识符，关键字和运算符。

import java.util.HashMap;

public class Lexer {
    private String input;
    private int position;
    private int charPosition;
    private HashMap<String, TokenType> keywords;

    public Lexer(String input) {
        this.input = input;
        this.position = 0;
        this.charPosition = 1;

        // 初始化关键字
        keywords = new HashMap<>();
        keywords.put("if", TokenType.IF);
        keywords.put("else", TokenType.ELSE);
        keywords.put("while", TokenType.WHILE);
        keywords.put("do", TokenType.DO);
        keywords.put("int", TokenType.INT);
        keywords.put("float", TokenType.FLOAT);
        keywords.put("bool", TokenType.BOOL);
        keywords.put("true", TokenType.TRUE);
        keywords.put("false", TokenType.FALSE);
    }

    private char currentChar() {
        if (position >= input.length()) {
            return '\0';
        }
        return input.charAt(position);
    }

    private void advance() {
        position++;
        charPosition++;
    }

    private void skipWhitespace() {
        while (currentChar() == ' ' || currentChar() == '\t' || currentChar() == '\n') {
            advance();
        }
    }

    private String readIdentifier() {
        StringBuilder identifier = new StringBuilder();
        while (Character.isLetterOrDigit(currentChar()) || currentChar() == '_') {
            identifier.append(currentChar());
            advance();
        }
        return identifier.toString();
    }

    private String readNumber() {
        StringBuilder number = new StringBuilder();
        while (Character.isDigit(currentChar())) {
            number.append(currentChar());
            advance();
        }
        if (currentChar() == '.') {
            number.append(currentChar());
            advance();
            while (Character.isDigit(currentChar())) {
                number.append(currentChar());
                advance();
            }
            return number.toString();
        } else {
            return number.toString();
        }
    }

    private Token readOperator() {
        switch (currentChar()) {
            case '=':
                if (peek() == '=') {
                    advance();
                    advance();
                    return new Token(TokenType.EQUALS, "==");
                } else {
                    advance();
                    return new Token(TokenType.ASSIGN, "=");
                }
            case '+':
                advance();
                return new Token(TokenType.PLUS, "+");
            case '-':
                advance();
                return new Token(TokenType.MINUS, "-");
            case '*':
                advance();
                return new Token(TokenType.MULTIPLY, "*");
            case '/':
                advance();
                return new Token(TokenType.DIVIDE, "/");
            case '<':
                advance();
                return new Token(TokenType.LESS_THAN, "<");
            case '>':
                advance();
                return new Token(TokenType.GREATER_THAN, ">");
            default:
                return null;
        }
    }

    private char peek() {
        if (position + 1 >= input.length()) {
            return '\0';
        }
        return input.charAt(position + 1);
    }

    public Token getNextToken() {
        while (currentChar() != '\0') {
            if (currentChar() == ' ' || currentChar() == '\t' || currentChar() == '\n') {
                skipWhitespace();
                continue;
            }
            if (Character.isLetter(currentChar()) || currentChar() == '_') {
                String identifier = readIdentifier();
                TokenType tokenType = keywords.getOrDefault(identifier, TokenType.IDENTIFIER);
                return new Token(tokenType, identifier);
            }
            if (Character.isDigit(currentChar())) {
                String number = readNumber();
                return new Token(TokenType.NUMBER, number);
            }
            Token operator = readOperator();
            if (operator != null) {
                return operator;
            }
            throw new RuntimeException("Invalid character: " + currentChar());
        }
        return new Token(TokenType.EOF, "");
    }
}

该代码通过 `getNextToken()` 方法逐个读取输入代码中的标识符、关键字和运算符，并返回相应的 Token 类型。Token 类型由 `TokenType` 枚举类表示，其中包含了所有可识别的类型。