Java中的词法分析器

Question

我一直在尝试用java编写一个简单的词法分析器。

File Token.java如下：

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

public enum Token {

    TK_MINUS ("-"), 
    TK_PLUS ("\\+"), 
    TK_MUL ("\\*"), 
    TK_DIV ("/"), 
    TK_NOT ("~"), 
    TK_AND ("&"),  
    TK_OR ("\\|"),  
    TK_LESS ("<"),
    TK_LEG ("<="),
    TK_GT (">"),
    TK_GEQ (">="), 
    TK_EQ ("=="),
    TK_ASSIGN ("="),
    TK_OPEN ("\\("),
    TK_CLOSE ("\\)"), 
    TK_SEMI (";"), 
    TK_COMMA (","), 
    TK_KEY_DEFINE ("define"), 
    TK_KEY_AS ("as"),
    TK_KEY_IS ("is"),
    TK_KEY_IF ("if"), 
    TK_KEY_THEN ("then"), 
    TK_KEY_ELSE ("else"), 
    TK_KEY_ENDIF ("endif"),
    OPEN_BRACKET ("\\{"),
    CLOSE_BRACKET ("\\}"),
    DIFFERENT ("<>"),

    STRING ("\"[^\"]+\""),
    INTEGER ("\\d"), 
    IDENTIFIER ("\\w+");

    private final Pattern pattern;

    Token(String regex) {
        pattern = Pattern.compile("^" + regex);
    }

    int endOfMatch(String s) {
        Matcher m = pattern.matcher(s);

        if (m.find()) {
            return m.end();
        }
        return -1;
    }
}

Lexer如下：Lexer。JAVA

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.HashSet;
import java.util.Set;
import java.util.stream.Stream;

public class Lexer {
    private StringBuilder input = new StringBuilder();
    private Token token;
    private String lexema;
    private boolean exausthed = false;
    private String errorMessage = "";
    private Set<Character> blankChars = new HashSet<Character>();

    public Lexer(String filePath) {
        try (Stream<String> st = Files.lines(Paths.get(filePath))) {
            st.forEach(input::append);
        } catch (IOException ex) {
            exausthed = true;
            errorMessage = "Could not read file: " + filePath;
            return;
        }

        blankChars.add('\r');
        blankChars.add('\n');
        blankChars.add((char) 8);
        blankChars.add((char) 9);
        blankChars.add((char) 11);
        blankChars.add((char) 12);
        blankChars.add((char) 32);

        moveAhead();
    }

    public void moveAhead() {
        if (exausthed) {
            return;
        }

        if (input.length() == 0) {
            exausthed = true;
            return;
        }

        ignoreWhiteSpaces();

        if (findNextToken()) {
            return;
        }

        exausthed = true;

        if (input.length() > 0) {
            errorMessage = "Unexpected symbol: '" + input.charAt(0) + "'";
        }
    }

    private void ignoreWhiteSpaces() {
        int charsToDelete = 0;

        while (blankChars.contains(input.charAt(charsToDelete))) {
            charsToDelete++;
        }

        if (charsToDelete > 0) {
            input.delete(0, charsToDelete);
        }
    }

    private boolean findNextToken() {
        for (Token t : Token.values()) {
            int end = t.endOfMatch(input.toString());

            if (end != -1) {
                token = t;
                lexema = input.substring(0, end);
                input.delete(0, end);
                return true;
            }
        }

        return false;
    }

    public Token currentToken() {
        return token;
    }

    public String currentLexema() {
        return lexema;
    }

    public boolean isSuccessful() {
        return errorMessage.isEmpty();
    }

    public String errorMessage() {
        return errorMessage;
    }

    public boolean isExausthed() {
        return exausthed;
    }
}

并且可以用Try.java测试如下：

public class Try {

    public static void main(String[] args) {

        Lexer lexer = new Lexer("C:/Users/Input.txt");

        System.out.println("Lexical Analysis");
        System.out.println("-----------------");
        while (!lexer.isExausthed()) {
            System.out.printf("%-18s :  %s \n",lexer.currentLexema() , lexer.currentToken());
            lexer.moveAhead();
        }

        if (lexer.isSuccessful()) {
            System.out.println("Ok! :D");
        } else {
            System.out.println(lexer.errorMessage());
        }
    }
}

说出输入。txt有

define mine 
a=1000;
b=23.5;

我期望的输出是

define : TK_KEYWORD
mine : IDENTIFIER
a : IDENTIFIER
= : TK_ASSIGN
1000 : INTEGER
; : TK_SEMI
b : IDENTIFIER
= : TK_ASSIGN
23.5 : REAL

但我面临的问题是：它把每个数字都当作

1 INTEGER
0 INTEGER
0 INTEGER
0 INTEGER

而且它不能识别实数。我得到：

意外符号：'.'

为了达到预期的效果，需要做哪些改变？

Answer 1

匹配整数的模式是：

INTEGER ("\\d"), 

正好匹配一个数字。

如果你想要一个以上，去

INTEGER ("\\d+"), 

例如

为了完成，浮点数缺失的另一个模式可能看起来像

REAL ("(\\d+)\\.\\d+")

正如评论指出的那样。或

REAL ("(\\d*)\\.\\d+")

使允许

.23

太-如果这是你正在寻找的！