Java、统计每个关键字的出现次数

 

package set;

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

public class Exercise21_10 {
    public static void main(String[] args) throws IOException {
        System.out.print("Enter a file: ");
        File file = new File(new Scanner(System.in).nextLine());

        if (!file.exists())
            System.out.println("File " + file + " does not exist");
        else if (!file.isFile())
            System.out.println("Not a file");
        else {
            int count = 0;
            Set<Map.Entry<String, Integer>> entrySet = countKeywords(file).entrySet();
            for (Map.Entry<String, Integer> entry: entrySet) {
                count += entry.getValue();
                System.out.println(String.format("%-10s%10d", entry.getKey(), entry.getValue()));
            }
            System.out.println("count = " + count);
        }
    }

    public static Map<String, Integer> countKeywords(File file) throws IOException {
        Set<String> keywordSet = getKeywordSet();
        Map<String, Integer> map = new TreeMap<>();

        try(Scanner input = new Scanner(file)) {
            while (input.hasNext()) {
                String word = input.next();

                if (word.contains("\"") && !word.matches(".*(\").*")) {
                    word = input.next();
                    while (input.hasNext() && !word.contains("\""))
                        word = input.next();
                    word = input.next();
                }
                if (word.contains("/*") && !word.matches("\".*/\\*\".*"))  {
                    word = input.next();
                    while (input.hasNext() && !word.contains("*/"))
                        word = input.next();
                    word = input.next();
                }
                if (word.contains("//")) {
                    input.nextLine();
                    if (input.hasNext())
                        word = input.next();
                }

                if (keywordSet.contains(word)) {
                    if (!map.containsKey(word))
                        map.put(word, 1);
                    else
                        map.put(word, map.get(word)+1);
                } else {
                    for (String s: keywordSet) {
                        for (String s1 : word.split("[ ().]"))
                            if (s1.matches(s)) {
                                if (!map.containsKey(s))
                                    map.put(s, 1);
                                else
                                    map.put(word, map.get(s) + 1);
                            }
                    }
                }
            }
        }

        return map;
    }

    /** 返回关键字集合 */
    public static Set<String> getKeywordSet() {
        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"};
        Set<String> keywordSet = new HashSet<>(Arrays.asList(keyWordString));
        return keywordSet;
    }
}