SpringBoot项目通过分词器生成词云

---

前言

公司项目涉及到员工任务管理，需要从员工任务中获取任务信息生成个人词云图，可以把员工任务中较为高频的词语突出展示。

---

一、词云是什么？

词云就是对文本中出现频率较高的“关键词”予以视觉上的突出，形成“关键词云层” 或“关键词渲染”，从而过滤掉大量的文本信息，使浏览网页者只要一眼扫过文本就可以领略文本的主旨。

二、使用步骤

1.引入依赖

<dependency>
    <groupId>cn.shenyanchao.ik-analyzergroupId>
    <artifactId>ik-analyzerartifactId>
    <version>9.0.0version>
dependency>


<dependency>
    <groupId>com.kennycasongroupId>
    <artifactId>kumo-coreartifactId>
    <version>1.28version>
dependency>

<dependency>
    <groupId>com.kennycasongroupId>
    <artifactId>kumo-tokenizersartifactId>
    <version>1.28version>
dependency>


<dependency>
    <groupId>org.springframework.bootgroupId>
    <artifactId>spring-boot-starter-webartifactId>
dependency>

<dependency>
    <groupId>org.projectlombokgroupId>
    <artifactId>lombokartifactId>
    <optional>trueoptional>
dependency>

2.application.yml

server:
  port: 8088

# 关闭日志输出 （可选）
logging:
  level:
    com.kennycason.kumo.WordCloud: OFF

3.Controller

import com.chendi.mydemo.utils.IkAnalyzerUtils;
import com.chendi.mydemo.utils.WorkCloudUtil;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

@RestController
public class TestController {

    @GetMapping("/")
    public void test() {
        List<String> list = new ArrayList<>();
        list.add("爱购物，爱手机，爱电脑，爱上网");
        list.add("爱学习，爱游戏，爱吃饭，爱睡觉");
        list.add("爱上班，爱下班，爱加班，爱翘班");
        list.add("爱上班，爱下班，爱加班，爱翘班");
        list.add("夏天的阳光明媚灿烂，\n" +
                "大自然万物生机盎然。\n" +
                "清晨的微风吹过花丛，\n" +
                "点缀着青草和蓝天。\n" +
                "\n" +
                "蝴蝶翩翩起舞在花间，\n" +
                "蜜蜂忙碌采集甘甜。\n" +
                "鸟儿欢快地歌唱着，\n" +
                "为夏日带来欢欣和欢愉。\n" +
                "\n" +
                "海浪轻拍沙滩起伏，\n" +
                "沙粒细腻温热宜走。\n" +
                "阳光透过水面璀璨，\n" +
                "让海洋如银河般流动。\n" +
                "\n" +
                "夏日的夜晚星空闪耀，\n" +
                "月亮洒下银色光晕。\n" +
                "夏虫的音符演奏着，\n" +
                "营造出夏夜的美妙。\n" +
                "\n" +
                "夏天啊，你是如此迷人，\n" +
                "给人们带来快乐和欢欣。\n" +
                "在你的怀抱里，我们尽情享受，\n" +
                "夏天，你是美丽的季节！");

        Map<String, Integer> wordMap = IkAnalyzerUtils.wordCloud(list, 0);
        WorkCloudUtil.generateWriteImage(wordMap);
    }

}

4.分词工具类

import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;

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

/**
 * 解析工具类
 */
public class IkAnalyzerUtils {

    /**
     * 拆分词云
     *
     * @param list     需要拆分的词云集合
     * @param quantity 结果集取的数量
     */
    public static String wordCloudParsing(List<String> list, Integer quantity) {
        Map<String,Integer> result = wordCloud(list,quantity);
        StringBuilder str = new StringBuilder();
        result.forEach((k, v) -> {
            String value = " " + k;
            str.append(value);
        });
        return str.toString().trim();
    }

    /**
     * 拆分词云
     *
     * @param list     需要拆分的词云集合
     * @param quantity 结果集取的数量
     */
    public static List<Map<String,Object>> wordCloudList(List<String> list, Integer quantity) {
        Map<String,Integer> result = wordCloud(list,quantity);
        List<Map<String,Object>> mapList = new LinkedList<>();
        result.forEach((k, v) -> {
            Map<String,Object> map = new HashMap<>(16);
            map.put("name",k);
            map.put("value",v);
            mapList.add(map);
        });
        Collections.reverse(mapList);
        return mapList;
    }

    /**
     * 拆分词云
     *
     * @param list     需要拆分的词云集合
     * @param quantity 结果集取的数量
     */
    public static Map<String,Integer> wordCloud(List<String> list, Integer quantity) {
        StringReader reader = new StringReader(String.join(",", list));
        IKSegmenter ikSegmenter = new IKSegmenter(reader, true);
        Map<String, Integer> map = null;
        try {
            Lexeme lexeme;
            map = new HashMap<>(16);
            while ((lexeme = ikSegmenter.next()) != null) {
                String str = lexeme.getLexemeText();
                Integer num = map.get(str);
                if (num != null && num > 0) {
                    map.put(str, num + 1);
                } else {
                    map.put(str, 1);
                }
            }
            reader.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        Map<String, Integer> result = new LinkedHashMap<>();
        if (quantity != null && quantity > 0) {
            map.entrySet().stream().sorted(Map.Entry.comparingByValue()).limit(quantity)
                    .forEachOrdered(item -> result.put(item.getKey(), item.getValue()));
        } else {
            map.entrySet().stream().sorted(Map.Entry.comparingByValue())
                    .forEachOrdered(item -> result.put(item.getKey(), item.getValue()));
        }
        return result;
    }
}

4.词云生成工具类、支持输出文件和字节流

import com.kennycason.kumo.CollisionMode;
import com.kennycason.kumo.WordCloud;
import com.kennycason.kumo.WordFrequency;
import com.kennycason.kumo.bg.CircleBackground;
import com.kennycason.kumo.font.KumoFont;
import com.kennycason.kumo.font.scale.SqrtFontScalar;
import com.kennycason.kumo.nlp.FrequencyAnalyzer;
import com.kennycason.kumo.nlp.tokenizers.ChineseWordTokenizer;
import com.kennycason.kumo.palette.ColorPalette;
import lombok.SneakyThrows;

import java.awt.*;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

public class WorkCloudUtil {

    @SneakyThrows
    public static InputStream generateImageStream(Map<String, Integer> wordMap) {
        WordCloud wordCloud = generateWordCloud(wordMap);
        //输出字节流
        ByteArrayOutputStream out =new ByteArrayOutputStream();
        wordCloud.writeToStreamAsPNG(out);
        return new ByteArrayInputStream(out.toByteArray());
    }


    @SneakyThrows
    public static void generateWriteImage(Map<String, Integer> wordMap) {
        WordCloud wordCloud = generateWordCloud(wordMap);
        wordCloud.writeToFile("D:\\chendi\\cd.png");
    }

    public static WordCloud generateWordCloud(Map<String, Integer> wordMap){
        if (wordMap == null || wordMap.size() == 0) {
            return null;
        }
        final FrequencyAnalyzer frequencyAnalyzer = new FrequencyAnalyzer();
        frequencyAnalyzer.setWordFrequenciesToReturn(600);
        frequencyAnalyzer.setMinWordLength(2);
        frequencyAnalyzer.setWordTokenizer(new ChineseWordTokenizer());
        final List<WordFrequency> wordFrequencies = new ArrayList<>();
        for (Map.Entry<String, Integer> entry : wordMap.entrySet()) {
            wordFrequencies.add(new WordFrequency(entry.getKey(), entry.getValue()));
        }
        Font font = FontUtil.getFont("/static/fonts/QingNiaoHuaGuangJianMeiHei-2.ttf");
        //设置图片分辨率
        final Dimension dimension = new Dimension(400, 400);
        //此处的设置采用内置常量即可，生成词云对象
        final WordCloud wordCloud = new WordCloud(dimension, CollisionMode.PIXEL_PERFECT);
        //设置边界及字体
        wordCloud.setPadding(2);
        wordCloud.setBackgroundColor(Color.WHITE);
        //设置背景图层为圆形，设置圆形的大小
        wordCloud.setBackground(new CircleBackground(200));
        //设置词云显示的三种颜色，越靠前设置表示词频越高的词语的颜色
        wordCloud.setColorPalette(new ColorPalette(new Color(0x4055F1), new Color(0x408DF1), new Color(0x40AAF1), new Color(0x40C5F1), new Color(0x40D3F1), new Color(0xFFFFFF)));
        //设置字体的大小
        wordCloud.setFontScalar(new SqrtFontScalar(10, 40));
        wordCloud.setKumoFont(new KumoFont(font));
        wordCloud.build(wordFrequencies);
        //设置背景图片，如果想要固定的形状，就插入这个形状的图片
        //wordCloud.setBackground(new PixelBoundryBackground("E:\\星星/star.jpg"));
        return wordCloud;
    }

}

---

注意

处理中文需要宿主机有中文字体包、如果宿主机不支持中文，请下载一个中文字体包

本文指定使用的就是QingNiaoHuaGuangJianMeiHei-2.ttf字体

百度一下、找不到私信我发你QingNiaoHuaGuangJianMeiHei-2.ttf字体包