快捷導(dǎo)航

SpringBoot項(xiàng)目實(shí)現(xiàn)通過分詞器生成詞云

更新時(shí)間：2026年05月08日 09:41:18 作者：無(wú)敵小肥007

本文介紹了如何在SpringBoot項(xiàng)目中利用IK分詞器和Kumo庫(kù)生成員工任務(wù)的詞云圖,展示了從引入依賴、配置YAML到Controller中處理文本并生成詞云的詳細(xì)步驟以及處理中文文本的注意事項(xiàng),希望對(duì)大家有所幫助

前言

公司項(xiàng)目涉及到員工任務(wù)管理，需要從員工任務(wù)中獲取任務(wù)信息生成個(gè)人詞云圖，可以把員工任務(wù)中較為高頻的詞語(yǔ)突出展示。

一、詞云是什么

詞云就是對(duì)文本中出現(xiàn)頻率較高的“關(guān)鍵詞”予以視覺上的突出，形成“關(guān)鍵詞云層” 或“關(guān)鍵詞渲染”，從而過濾掉大量的文本信息，使瀏覽網(wǎng)頁(yè)者只要一眼掃過文本就可以領(lǐng)略文本的主旨。

二、使用步驟

1.引入依賴

<!--   IK分詞器    -->
<dependency>
    <groupId>cn.shenyanchao.ik-analyzer</groupId>
    <artifactId>ik-analyzer</artifactId>
    <version>9.0.0</version>
</dependency>
<!--    詞雲(yún)    -->
<dependency>
    <groupId>com.kennycason</groupId>
    <artifactId>kumo-core</artifactId>
    <version>1.28</version>
</dependency>
<dependency>
    <groupId>com.kennycason</groupId>
    <artifactId>kumo-tokenizers</artifactId>
    <version>1.28</version>
</dependency>
<!--    web    -->
<dependency>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
    <groupId>org.projectlombok</groupId>
    <artifactId>lombok</artifactId>
    <optional>true</optional>
</dependency>

2.application.yml

server:
  port: 8088
# 關(guān)閉日志輸出 （可選）
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("愛購(gòu)物，愛手機(jī)，愛電腦，愛上網(wǎng)");
        list.add("愛學(xué)習(xí)，愛游戲，愛吃飯，愛睡覺");
        list.add("愛上班，愛下班，愛加班，愛翹班");
        list.add("愛上班，愛下班，愛加班，愛翹班");
        list.add("夏天的陽(yáng)光明媚燦爛，\n" +
                "大自然萬(wàn)物生機(jī)盎然。\n" +
                "清晨的微風(fēng)吹過花叢，\n" +
                "點(diǎn)綴著青草和藍(lán)天。\n" +
                "\n" +
                "蝴蝶翩翩起舞在花間，\n" +
                "蜜蜂忙碌采集甘甜。\n" +
                "鳥兒歡快地歌唱著，\n" +
                "為夏日帶來(lái)歡欣和歡愉。\n" +
                "\n" +
                "海浪輕拍沙灘起伏，\n" +
                "沙粒細(xì)膩溫?zé)嵋俗?。\n" +
                "陽(yáng)光透過水面璀璨，\n" +
                "讓海洋如銀河般流動(dòng)。\n" +
                "\n" +
                "夏日的夜晚星空閃耀，\n" +
                "月亮灑下銀色光暈。\n" +
                "夏蟲的音符演奏著，\n" +
                "營(yíng)造出夏夜的美妙。\n" +
                "\n" +
                "夏天啊，你是如此迷人，\n" +
                "給人們帶來(lái)快樂和歡欣。\n" +
                "在你的懷抱里，我們盡情享受，\n" +
                "夏天，你是美麗的季節(jié)！");

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

}

4.分詞工具類

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

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

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

    /**
     * 拆分詞云
     *
     * @param list     需要拆分的詞云集合
     * @param quantity 結(jié)果集取的數(shù)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();
    }

    /**
     * 拆分詞云
     *
     * @param list     需要拆分的詞云集合
     * @param quantity 結(jié)果集取的數(shù)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;
    }

    /**
     * 拆分詞云
     *
     * @param list     需要拆分的詞云集合
     * @param quantity 結(jié)果集取的數(shù)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;
    }
}

5.詞云生成工具類、支持輸出文件和字節(jié)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);
        //輸出字節(jié)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");
        //設(shè)置圖片分辨率
        final Dimension dimension = new Dimension(400, 400);
        //此處的設(shè)置采用內(nèi)置常量即可，生成詞云對(duì)象
        final WordCloud wordCloud = new WordCloud(dimension, CollisionMode.PIXEL_PERFECT);
        //設(shè)置邊界及字體
        wordCloud.setPadding(2);
        wordCloud.setBackgroundColor(Color.WHITE);
        //設(shè)置背景圖層為圓形，設(shè)置圓形的大小
        wordCloud.setBackground(new CircleBackground(200));
        //設(shè)置詞云顯示的三種顏色，越靠前設(shè)置表示詞頻越高的詞語(yǔ)的顏色
        wordCloud.setColorPalette(new ColorPalette(new Color(0x4055F1), new Color(0x408DF1), new Color(0x40AAF1), new Color(0x40C5F1), new Color(0x40D3F1), new Color(0xFFFFFF)));
        //設(shè)置字體的大小
        wordCloud.setFontScalar(new SqrtFontScalar(10, 40));
        wordCloud.setKumoFont(new KumoFont(font));
        wordCloud.build(wordFrequencies);
        //設(shè)置背景圖片，如果想要固定的形狀，就插入這個(gè)形狀的圖片
        //wordCloud.setBackground(new PixelBoundryBackground("E:\\星星/star.jpg"));
        return wordCloud;
    }

}

FontUtil

import org.springframework.core.io.ClassPathResource;
import org.springframework.util.StringUtils;

import java.awt.*;
import java.io.InputStream;

public class FontUtil {

    public static Font loadFont(InputStream inputStream  , float fontSize) {
        try {
        Font dynamicFont = Font.createFont(Font.TRUETYPE_FONT, inputStream);
        Font dynamicFontPt = dynamicFont.deriveFont(fontSize);
        inputStream.close();
        return dynamicFontPt;
        } catch (Exception e){
            return new Font("微軟雅黑", Font.PLAIN, 18);
        }
    }

    public static Font getFont(String path) {
        if(StringUtils.isEmpty(path)){
            return new Font("微軟雅黑", Font.PLAIN, 18);
        }
        //獲取字體文件
        ClassPathResource classPathResource = new ClassPathResource(path);
        InputStream inputStream;
        try {
            inputStream = classPathResource.getInputStream();
        } catch (Exception e) {
            return new Font("微軟雅黑", Font.PLAIN, 18);
        }
        return FontUtil.loadFont(inputStream, 18);

    }
}