Java、统计Java源代码中的关键字

 

package set;

import java.io.File;
import java.io.IOException;
import java.util.*;

public class Exercise21_03 {
    public static void main(String[] args) throws IOException {
        if (args.length != 1) {
            System.out.println("Invalid length");
        } else {
            File file = new File(args[0]);
            if (!file.exists())
                System.out.println("File " + file + "does not exist");
            else
                System.out.println("The number of keywords in " + file + " is " + countKeywords(file));
        }
    }

    /** 统计关键字次数  false  boolean assert  */
    public static int countKeywords(File file) throws IOException {
        String[] keyWordString = {"abstract", "assert", "boolean", "break", "byte", "case", "catch",
                    "char", "class", "const", "continue", "default", "do", "double", "else", "enum",
                    "extends", "for", "final", "finally", "float", "goto", "if", "implements", "import",
                    "instanceof", "int", "interface", "long", "native", "new", "package", "private",
                    "protected", "public", "return", "short", "static", "strictfp", "super", "switch",
                    "synchronized", "this", "throw", "throws", "transient", "try", "void", "volatile",
                    "while", "true", "false", "null"};  //关键字数组
        Set<String> keywordSet = new HashSet<>(Arrays.asList(keyWordString));   //存放关键字集合
        int count = 0;  //次数

        try(Scanner input = new Scanner(file)) {
            while (input.hasNext()) {   //读入文本
                String word = input.next();     //false  boolean assert

                //字符串包含引号且不匹配转义字符引号
                if (word.contains("\"") && !word.matches(".*(\").*")) {
                    word = input.next();    //过滤第一个字符串
                    while (input.hasNext() && !word.contains("\"")) //过滤引号之间的字符串
                        word = input.next();
                    word = input.next();    //过滤第二个引号
                }

                //字符串包含段落注释且不匹配字符串形式字符
                if (word.contains("/*") && !word.matches("\".*/\\*\".*"))  {
                    word = input.next();
                    while (input.hasNext() && !word.contains("*/")) //过滤注释间的字符串
                        word = input.next();
                    word = input.next();    //跳过*/
                }

                //字符串包含行注释
                if (word.contains("//")) {
                    input.nextLine();   //跳过当前行
                    if (input.hasNext())
                        word = input.next();    //跳转到下一行
                }

                //关键字集合包含字符串
                if (keywordSet.contains(word)) {
                    count++;
                } else {
                    for (String s: keyWordString)   //检查字符串中的单词是否匹配关键字
                        for (String s1: word.split("[ ().]"))
                            if (s1.matches(s)) {
                                count++;
                            }
                }
            }
        }

        return count;
    }
}