java实现词法分析器

实现词法分析器

实验内容要求

一、实验目的加深对词法分析器的工作过程的理解；加强对词法分析方法的掌握；能够采用一种编程语言实现简单的词法分析程序；能够使用自己编写的分析程序对简单的程序段进行词法分析。

二、实验内容自定义一种程序设计语言，或者选择已有的一种高级语言，编制它的词法分析程序。词法分析程序的实现可以采用任何一种编程语言和编程工具。从输入的源程序中，识别出各个具有独立意义的单词，即关键字、标识符、常数、运算符、界符。并依次输出各个单词的内部编码及单词符号自身值。（遇到错误时可显示“Error”，然后跳过错误部分继续显示）

三、实验要求： 1. 对单词的构词规则有明确的定义； 2. 编写的分析程序能够正确识别源程序中的单词符号； 3. 识别出的单词以<种别码，值>的形式保存在符号表中，正确设计和维护符号表； 4. 对于源程序中的词法错误，能够做出简单的错误处理，给出简单的错误提示，保证顺利完成整个源程序的词法分析；

四、实验步骤 1. 定义目标语言的可用符号表和构词规则； 2. 依次读入源程序符号，对源程序进行单词切分和识别，直到源程序结束； 3. 对正确的单词，按照它的种别以<种别码，值>的形式保存在符号表中； 4. 对不正确的单词，做出错误处理。

实验方法

根据对应的状态转换图完成编码就可以了，内容我不详细多说，下面的图可以作为参照，实际上还需要自己去思考更多，我的代码还是存在一点小问题的，仅供大家参考。

状态转换图

import java.io.File; import java.io.FileNotFoundException; import java.util.*; public class LexicalAnalyzer { 
    /* * 1表示关键字 * 2表示标识符 * 3表示常数 * 4表示运算符 * 5表示界符 * 6表示字符串 * */ //关键字 static String []keyWord={ 
   "private","protected","public","abstract","class","extends","final","implements", "interface","native","new","static","strictfp","break","continue","return","do","while","if","else","for", "instanceof","switch","case","default","boolean","byte","char","double","float","int","long","short", "String","null","true","false","void","this","goto"}; //运算符 static String []operation={ 
   "+","-","*","/","%","++","--","-=","*=","/=","&","|","^","~","<<",">>",">>>","==","!=", ">","<","=",">=","<=","&&","||","!","."}; //界符 static String []symbol={ 
   ",",";",":","(",")","{","}"}; static ArrayList<String> keyWords=null; static ArrayList<String> operations=null; static ArrayList<String> symbols=null; //指向当前所读到字符串的位置的指针 static int p,lines; public static void main(String []args) throws FileNotFoundException { 
    init(); File file=new File("E:\\code\\bytest\\test11\\test2.txt"); lines=1; try(Scanner input=new Scanner(file)) { 
    while (input.hasNextLine()){ 
    String str=input.nextLine(); analyze(str); lines++; } } } //初始化把数组转换为ArrayList public static void init(){ 
    keyWords=new ArrayList<>(); operations=new ArrayList<>(); symbols=new ArrayList<>(); Collections.addAll(keyWords, keyWord); Collections.addAll(operations, operation); Collections.addAll(symbols, symbol); } public static void analyze(String str){ 
    p=0; char ch; str=str.trim(); for (;p<str.length();p++){ 
    ch=str.charAt(p); if (Character.isDigit(ch)){ 
    digitCheck(str); }else if (Character.isLetter(ch)||ch=='_'){ 
    letterCheck(str); }else if (ch=='"'){ 
    stringCheck(str); } else if (ch==' '){ 
    continue; }else { 
    symbolCheck(str); } } } /*数字的识别 * 1、识别退出： * 1.1、遇到空格符 * 1.2、遇到运算符或者界符 * 2、错误情况： * 2.1、两个及以上小数点 * 2.2、掺杂字母 * */ public static void digitCheck(String str){ 
    String token= String.valueOf(str.charAt(p++)); //判断数字的小数点是否有且是否大于1 int flag=0; boolean err=false; char ch; for (;p<str.length();p++) { 
    ch = str.charAt(p); if (ch==' '||(!Character.isLetterOrDigit(ch)&&ch!='.')) { 
    break; }else if (err){ 
    token+=ch; } else { 
    token+=ch; if (ch == '.') { 
    if (flag == 1) { 
    err = true; } else { 
    flag++; } }else if (Character.isLetter(ch)){ 
    err=true; } } } if (token.charAt(token.length()-1)=='.'){ 
    err=true; } if (err){ 
    System.out.println(lines+"line"+": "+token+" is wrong"); }else { 
    System.out.println("("+3+","+token+")"); } if (p!=str.length()-1||(p==str.length()-1&&!Character.isDigit(str.charAt(p)))){ 
    p--; } } //标识符，关键字的识别 public static void letterCheck(String str){ 
    String token= String.valueOf(str.charAt(p++)); char ch; for (;p<str.length();p++){ 
    ch=str.charAt(p); if (!Character.isLetterOrDigit(ch)&&ch!='_'){ 
    break; }else{ 
    token+=ch; } } if (keyWords.contains(token)){ 
    System.out.println("("+1+","+token+")"); }else { 
    System.out.println("("+2+","+token+")"); } if (p!=str.length()-1||(p==str.length()-1&&(!Character.isLetterOrDigit(str.charAt(p))&&str.charAt(p)!='_'))){ 
    p--; } } //符号的识别 public static void symbolCheck(String str){ 
    String token= String.valueOf(str.charAt(p++)); char ch; if (symbols.contains(token)){ 
    System.out.println("("+5+","+token+")"); p--; }else { 
    if (operations.contains(token)){ 
    if (p<str.length()){ 
    ch=str.charAt(p); if (operations.contains(token+ch)){ 
    token+=ch; p++; if (p<str.length()){ 
    ch=str.charAt(p); if (operations.contains(token+ch)){ 
    token+=ch; System.out.println("("+4+","+token+")"); }else{ 
    p--; System.out.println("("+4+","+token+")"); } }else{ 
    System.out.println("("+4+","+token+")"); } }else { 
    p--; System.out.println("("+4+","+token+")"); } } }else { 
    p--; System.out.println(lines+"line"+": "+token+" is wrong"); } } } //字符串检查 public static void stringCheck(String str){ 
    String token= String.valueOf(str.charAt(p++)); char ch; for (;p<str.length();p++){ 
    ch=str.charAt(p); token+=ch; if (ch=='"'){ 
    break; } } if (token.charAt(token.length()-1)!='"'){ 
    System.out.println(lines+"line"+": "+token+" is wrong"); }else { 
    System.out.println("("+6+","+token+")"); } } }

实验结果

1、对于正确的输入：

 public static void test(){ 
    int a=10; double b=20.2; double c=a+b; }

测试一结果
2、有不正确的输入：

public static double test(){ 
    double a=20.3.2.1; int 1111bbbb=10; System.out.println(a+b); String str="helloWorld"; double c=124.、 a++; return a+b+c; }