编译原理词法分析器Java

package word;

import java.io.File;
import java.io.FileReader;

/**

• 此程序是通过将文件的字符读取到字符数组中去，然后遍历数组，将读取的字符进行
• 分类并输出
• @author

*/

public class WordAnalyze {
// private String keyWord[] = {“break”,“include”,“begin”,“end”,“if”,“else”,“while”,“switch”};
private String keyWord[] = {“abstract”, “boolean”, “break”, “byte”,“case”, “catch”, “char”, “class”,
“continue”, “default”, “do”,“double”, “else”, “extends”, “final”, “finally”,
“float”, “for”,“if”, “implements”, “import”, “instanceof”, “int”, “interface”,
“long”, “native”, “new”, “package”, “private”, “protected”, “public”, “return”,
“short”, “static”, “super”, “switch”,“synchronized”, “this”, “throw”,“throws”,
“transient”, “try”,“void”,“volatile”,“while”,“strictfp”,
“enum”,“goto”,“const”,“assert”};
private char ch;
int KeeyWordNumber ;

//
// public static int printArray(int[] array,int value){
// for(int i = 0;i<array.length;i++){
// if(array[i]==value){
// return i;
// }
// }
// return -1;//当if条件不成立时，默认返回一个负数值-1
// }
//判断是否是关键字
int isKey(String str)
{
for(int i = 0;i < keyWord.length;i++)
{
if(keyWord[i].equals(str))
return i;

    }
    return -1;
}
//判断是否是字母
boolean isLetter(char letter)
{
    if((letter >= 'a' && letter <= 'z')||(letter >= 'A' && letter <= 'Z'))
        return true;
    else
        return false;
}
//判断是否是数字
boolean isDigit(char digit)
{
    if(digit >= '0' && digit <= '9')
        return true;
    else
        return false;
}
//词法分析
void analyze(char[] chars)
{
    String arr = "";
    for(int i = 0;i< chars.length;i++) {
        ch = chars[i];
        arr = "";
        if(ch == ' '||ch == '\t'||ch == '\n'||ch == '\r'){}
        else if(isLetter(ch)){
            while(isLetter(ch)||isDigit(ch)){    
                arr += ch;
                ch = chars[++i];
            }
            //回退一个字符
            i--;
            if(isKey(arr)!= -1){
                //关键字
                System.out.println(arr+"\t"+isKey(arr)+"\t关键字");
            }
            else{
                //标识符
                System.out.println(arr+"\t3"+"\t标识符");
            }
        }
        else if(isDigit(ch)||(ch == '.'))
        {
            while(isDigit(ch)||(ch == '.'&&isDigit(chars[++i])))
            {
                if(ch == '.') i--;
                arr = arr + ch;
                ch = chars[++i];
            }
            //属于无符号常数
            System.out.println(arr+"\t5"+"\t常数");
        }
        else switch(ch){
            //运算符
            case '+':System.out.println(ch+"\t2"+"\t运算符");break;
            case '-':System.out.println(ch+"\t2"+"\t运算符");break;
            case '*':System.out.println(ch+"\t2"+"\t运算符");break;
            case '/':System.out.println(ch+"\t2"+"\t运算符");break;
            //分界符
            case '(':System.out.println(ch+"\t3"+"\t分界符");break;
            case ')':System.out.println(ch+"\t3"+"\t分界符");break;
            case '[':System.out.println(ch+"\t3"+"\t分界符");break;
            case ']':System.out.println(ch+"\t3"+"\t分界符");break;
            case ';':System.out.println(ch+"\t3"+"\t分界符");break;
            case '{':System.out.println(ch+"\t3"+"\t分界符");break;
            case '}':System.out.println(ch+"\t3"+"\t分界符");break;
            //运算符
            case '=':{
                        ch = chars[++i];
                        if(ch == '=')System.out.println("=="+"\t2"+"\t运算符");
                        else {
                            System.out.println("="+"\t2"+"\t运算符");
                            i--;
                        }
                     }break;
            case ':':{
                        ch = chars[++i];
                        if(ch == '=')System.out.println(":="+"\t2"+"\t运算符");
                        else {
                            System.out.println(":"+"\t2"+"\t运算符");
                            i--;
                        }
                     }break;
            case '>':{
                        ch = chars[++i];
                        if(ch == '=')System.out.println(">="+"\t2"+"\t运算符");
                        else {
                            System.out.println(">"+"\t2"+"\t运算符");
                            i--;
                        }
                     }break;
            case '<':{
                        ch = chars[++i];
                        if(ch == '=')System.out.println("<="+"\t2"+"\t运算符");
                        else {
                            System.out.println("<"+"\t2"+"\t运算符");
                            i--;
                        }
                     }break;
            //无识别
            default: System.out.println(ch+"\t6"+"\t无识别符");
        }
    }
}

public static void main(String[] args) throws Exception {
File file = new File("./src/input.txt");//定义一个file对象，用来初始化FileReader
FileReader reader = new FileReader(file);//定义一个fileReader对象，用来初始化BufferedReader
int length = (int) file.length();
//这里定义字符数组的时候需要多定义一个,因为词法分析器会遇到超前读取一个字符的时候，如果是最后一个
//字符被读取，如果在读取下一个字符就会出现越界的异常
char buf[] = new char[length+1];
reader.read(buf);
reader.close();
new WordAnalyze().analyze(buf);

}
}

关键字可以自由修改添加，字符设置额外修整，整体框架已经给出