JAVA API 正则表达式常用方式

获取所有的 group 内容

将帖子/博文中的 #xxx 内容都提取出来。

package cn.mrcode;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.CountDownLatch;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import lombok.extern.slf4j.Slf4j;
/**
 * 帖子 tag 处理
 *
 * @author mrcode
 * @date 2022/6/23 17:05
 */
@Service
@Slf4j
public class HashtagTask {
    final static Pattern pattern = Pattern.compile("(#.+?)(?=#| )");
    /**
     * 提取 tag
     * @param body
     * @return
     */
    public static List<String> extractHashTags(String body) {
        final Matcher matcher = pattern.matcher(body);
        List<String> array = new ArrayList<>();
        while (matcher.find()) {
            array.add(matcher.group());
        }
        return array;
    }
    public static void main(String[] args) {
        String body = "#KalAdvisory#KalAdvisory #Kal #Shark #vacuum #cleaning #PowerFins #housecleaning #antihairwrap #duoclean #Petcare #TruePet https://t.co/T3ffrOG6JZ\n" +
                "i got a robot shark vacuum\n" +
                "ive named him bruce\n" +
                "and i've taped a shark fin into him\n" +
                "not to be dramatic but i'd die for him? lol\n" +
                "Our first DuoClean vacuum! It got all of the dirt that our vacuum missed.";
        final List<String> tags = extractHashTags(body);
        // 输出值 [#KalAdvisory , #Kal , #Shark , #vacuum , #cleaning , #PowerFins , #housecleaning , #antihairwrap , #duoclean , #Petcare , #TruePet ]
        System.out.println(tags);
    }
}