序

本文主要讲述一下如何使用apache collections4的bag以及guava的multiset的数据结构来统计单词次数。

maven

        <dependency>
            <groupId>com.google.guava</groupId>
            <artifactId>guava</artifactId>
            <version>22.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-collections4</artifactId>
            <version>4.1</version>
        </dependency>

bag

    @Test
    public void testBag(){
        Bag<String> bag = new HashBag<>();
        String content = "She is beautiful and she is my angel";
        Arrays.stream(content.split(" ")).forEach(word -> {
            bag.add(word);bag.add(word);
        });
        //get unique key
        Set<String> set = bag.uniqueSet();
        set.stream().forEach(word -> {
            System.out.println(word + "-->" + bag.getCount(word));
        });
    }

multiset

    @Test
    public void testMultiSet(){
        String content = "She is beautiful and she is my angel";
        Multiset<String> set = HashMultiset.create();
        Arrays.stream(content.split(" ")).forEach(word -> {
            set.add(word);
        });
        set.stream().distinct().forEach(e -> {
            System.out.println(e + "-->" + set.count(e));
        });
    }

小结

经过封装后的数据结构，用起来非常简洁。