1.统计字符串字母个数(并且保持字母顺序)
比如: aabbbbbbbba喔喔bcab cdabc deaaa
目前我做知道的有5种方式,如果你还有更好的,欢迎赐教
要求:统计字符串的字符个数,最好按顺序输出每个字符的个数
- //方式1
- public static void letterCount1(String s) {
- s=s.replaceAll(" +", "");
- //1,转换成字符数组
- char c[]=s.toCharArray();
- Map<Character, Integer> tree=new TreeMap<Character, Integer>();
- for (int i = 0; i < c.length; i++) {
- //第一次:a,1
- //第二次:a,2
- //2,获取键所对应的值
- Integer value=tree.get(c[i]);
- //3,存储判断
- tree.put(c[i], value==null? 1:value+1);
- }
- System.out.println(tree);
- }
- //方式2 使用流
- //这个在测试特殊字符,比如\ \n时,他的顺序会不对,这个是Map造成的
- //解决办法使用TreeMap
- public static void letterCount2(String s) {
- s=s.replaceAll(" +", "");
- TreeMap<String, Long> result = Arrays.stream(s.split(""))
- .sorted()
- // .collect(Collectors.groupingBy(Function.identity(),Collectors.counting()));
- .collect(Collectors.groupingBy(Function.identity(),TreeMap::new,Collectors.counting()));
- System.out.println(result);
- }
- //或者
- public static void letterCount2_1(String s) throws Exception {
- s=s.replaceAll(" +", "");
- Stream<String> words = Arrays.stream(s.split(""));
- Map<String, Integer> wordsCount = words.collect(Collectors.toMap(k -> k, v -> 1,
- (i, j) -> i + j));
- System.out.println(wordsCount);
- }
- //方式3 使用Collections.frequency
- //其实就是字符串变成集合存每个字串,把每个字串循环跟集合比较
- public static void letterCount3(String s) {
- s=s.replaceAll(" +", "");
- List<String> list=Arrays.asList(s.split(""));
- Map<String,Integer> map=new TreeMap<String, Integer>();
- for (String str : list) {
- map.put(str, Collections.frequency(list, str));
- }
- System.out.println(map);
- }
- //方式4
- public static void letterCount4(String s) {
- s=s.replaceAll(" +", "");
- String[] strs = s.split("");
- Map<String,Integer> map=new TreeMap<String, Integer>();
- for (String str : strs) {
- map.put(str, stringCount(s, str));
- }
- System.out.println(map);
- }
- //方式5
- public static void letterCount5(String s) {
- s=s.replaceAll(" +", "");
- String[] strs = s.split("");
- Map<String,Integer> map=new TreeMap<String, Integer>();
- for (String str : strs) {
- map.put(str, stringCount2(s, str));
- }
- System.out.println(map);
- }
- //巧用split
- public static int stringCount(String maxstr, String substr) {
- // 注意
- // 1.比如qqqq,没有找到,则直接返回这个字符串
- // 2.比如qqqjava,末尾没有其他字符,这时也不会分割,所以可以添加一个空格
- // 3.java11开头没有字符,没有关系,自动空填充
- // 4.对于特殊字符,要注意使用转义符
- int count = (maxstr + " ").split(substr).length - 1;
- // System.out.println("\"" + minstr + "\"" + "字符串出现次数:" + count);
- return count;
- }
- //如果要不区分大小写,则compile(minstr,CASE_INSENSITIVE)
- public static int stringCount2(String maxstr, String substr) {
- int count = 0;
- Matcher m = Pattern.compile(substr).matcher(maxstr);
- while (m.find()) {
- count++;
- }
- return count;
- }
2.统计字符串的单词个数
这个其实跟上面一样的,下面只写一个简洁的方法
- public static void wordStringCount(String s) {
- //这里开始是字符串,分割后变成字符串流
- Map<String, Long> result = Arrays.stream(s.split("\\s+"))
- .map(word -> word.replaceAll("[^a-zA-Z]", ""))
- .collect(Collectors.groupingBy(Function.identity(),Collectors.counting()));
- System.out.println(result);
- }
3.统计文本单词个数
- //统计一个文本中单词的个数
- public static void wordFileCount(String path) throws IOException{
- //这里一开始字符串流
- //先分割
- //在变成字符流
- //在筛选
- Map<String, Long> result = Files.lines(Paths.get(path),Charset.defaultCharset())
- .parallel()
- //字符串流--分割--字符串流
- .flatMap(str->Arrays.stream(str.split(" +")))
- .map(word -> word.replaceAll("[^a-zA-Z]", ""))
- //去掉空
- .filter(word->word.length()>0)
- .collect(Collectors.groupingBy(Function.identity(),Collectors.counting()));
- System.out.println(result);
- }
- //优化:更精确的是根据非单词来分组
- public static void wordFileCount0(String path) throws IOException{
- Map<String, Long> result = Files.lines(Paths.get(path),Charset.defaultCharset())
- .parallel()
- //字符串流--分割--字符串流
- .flatMap(str->Arrays.stream(str.split("[^a-zA-Z]+")))
- //去掉\n
- .filter(word->word.length()>0)
- .collect(Collectors.groupingBy(Function.identity(),Collectors.counting()));
- System.out.println(result);
- }