构建词云图

构建词云图

1、配置项

2、常量信息

3、依赖包

4、实现过程

package top.cfl.cflwork.common.utils;

import com.chenlb.mmseg4j.*;
import com.chenlb.mmseg4j.Dictionary;
import com.google.common.collect.Lists;
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.LinearGradientColorPalette;
import org.apache.commons.lang.time.DateFormatUtils;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.context.annotation.Configuration;
import top.cfl.cflwork.common.Constants;
import top.cfl.cflwork.config.ArchivesConfig;

import java.awt.*;
import java.io.File;
import java.io.IOException;
import java.io.StringReader;
import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.util.*;
import java.util.List;

import static top.cfl.cflwork.common.Constants.JPG;

/**
 * 词云图
 *
 * @author linc
 */
@Configuration
public class WordCloudUtils {
    @Autowired
    private ArchivesConfig archivesConfig;

    /**
     * 庖丁分词器
     *
     * @throws UnsupportedEncodingException
     */
    public String mMSeg(String txt) throws UnsupportedEncodingException {
        StringReader input = new StringReader(txt);
        Dictionary dic = Dictionary.getInstance();
        Seg seg = new ComplexSeg(dic);//Complex分词
        //seg = new SimpleSeg(dic);//Simple分词
        MMSeg mmSeg = new MMSeg(input, seg);
        Word word;
        String wordCloudFilePath = "";
        List<String> wordList = Lists.newArrayList();
        try {
            while ((word = mmSeg.next()) != null) {
                //word是单个分出的词，先放到List里下面统一按竖线拼接词打印出来
                wordList.add(word.getString());
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            input.close();
        }
        if (wordList.size() > 0) {
            wordCloudFilePath = wordCloud(wordList);
        }
        return wordCloudFilePath;
    }

    /**
     * 词云
     *
     * @param wordList
     * @return path
     * @throws UnsupportedEncodingException
     */
    public String wordCloud(List<String> wordList) throws UnsupportedEncodingException {
        FrequencyAnalyzer frequencyAnalyzer = new FrequencyAnalyzer();
        frequencyAnalyzer.setWordFrequenciesToReturn(600);
        frequencyAnalyzer.setMinWordLength(2);
        frequencyAnalyzer.setWordTokenizer(new ChineseWordTokenizer());
        // 可以直接从文件中读取
        //List<WordFrequency> wordFrequencies = frequencyAnalyzer.load(getInputStream("WordList.txt"));
        List<WordFrequency> wordFrequencies = new ArrayList<>();

        // 用词语来随机生成词云
        String strValue = frequencyOfListW(wordList).toString();
        String replace = strValue.replace("{", "");
        String strValueNew = replace.replace("}", "");
        //以逗号为分割号
        String[] strSplit = strValueNew.split(", ");
        String word = "";
        int count = 0;

        for (int i = 0; i < strSplit.length; i++) {
            String[] wordInfo = strSplit[i].split("=");
            word = wordInfo[0];
            count = Integer.valueOf(wordInfo[1]);
            wordFrequencies.add(new WordFrequency(word, count));
        }

        //加入分词并随机生成权重，每次生成得图片都不一样
//        wordList.stream().forEach(e -> wordFrequencies.add(new WordFrequency(e, new Random().nextInt(wordList.size()))));
        //此处不设置会出现中文乱码
        java.awt.Font font = new java.awt.Font("STSong-Light", 2, 18);
        //设置图片分辨率
        Dimension dimension = new Dimension(500, 500);
        //此处的设置采用内置常量即可，生成词云对象
        WordCloud wordCloud = new WordCloud(dimension, CollisionMode.PIXEL_PERFECT);
        //设置边界及字体
        wordCloud.setPadding(2);
        //因为我这边是生成一个圆形,这边设置圆的半径
        wordCloud.setBackground(new CircleBackground(255));
        wordCloud.setFontScalar(new SqrtFontScalar(12, 42));
        //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 LinearGradientColorPalette(Color.RED, Color.BLUE, Color.GREEN, 30, 30));
        wordCloud.setKumoFont(new KumoFont(font));
        wordCloud.setBackgroundColor(new Color(255, 255, 255, 0));
        //因为我这边是生成一个圆形,这边设置圆的半径
        wordCloud.setBackground(new CircleBackground(255));
        wordCloud.build(wordFrequencies);
        //生成词云图路径
        System.out.println(archivesConfig.getProfile() + "+路径");
        String filePath = URLDecoder.decode(archivesConfig.getProfile(), "UTF-8");//如果路径中带有中文会被URLEncoder,因此这里需要解码
        System.out.println(filePath);
        String fileName = "/wordCloud" + getDate() + ".png";
        String filePath1 = filePath + fileName;
        wordCloud.writeToFile(filePath1);
        String wordCloudFilePath = Constants.RESOURCE_PREFIX + fileName;
        return wordCloudFilePath;
    }

    /**
     * 获取当天日期
     * @return
     */
    public String getDate() {
        Date now = new Date(); // 创建一个Date对象，获取当前时间
        String strDateFormat = "yyyyMMdd";
        return DateFormatUtils.format(now, strDateFormat);
    }

    /**
     * 判断文件是否存在
     * @return
     */
    public boolean isExist() {
        File file = new File(getCurrentDayWordCloudPath());
        boolean exists = file.exists();
        return exists;
    }

    /**
     * 获取问卷地址
     * @return
     */
    public String getCurrentDayWordCloudPath() {
        String folder = System.getProperty("user.dir") + "\\" + archivesConfig.getProfile();
        String fileName = "/wordCloud" + getDate() + JPG;
        String absolutePath = folder + "\\" + fileName;
        return absolutePath;
    }

    /**
     * 适用于 jdk 1.8及以下，统计List集合中每个元素出现的次数
     * 例如frequencyOfListElements(["111","111","222"])
     * ->
     * 则返回Map {"111"=2,"222"=1}
     *
     * @param items
     * @return Map<String, Integer>
     * @author wuqx
     */
    public Map<String, Integer> frequencyOfListW(List<String> items) {
        Map<String, Integer> map = new HashMap<>();
        if (items == null || items.size() == 0) {
            return map;
        }
        for (String k : items) {
            Integer counts = map.get(k);
            map.put(k, (counts == null) ? 1 : ++counts);
        }
        int sum = 0;
        int total = 0;
        Collection values = map.values();
        for (Object object : values) {
            total = total + Integer.parseInt(object.toString());
            sum += 1;
        }
        int avg = total / sum;
        Iterator<Map.Entry<String, Integer>> it = map.entrySet().iterator();
        while (it.hasNext()) {
            Map.Entry<String, Integer> entry = it.next();
            if (entry.getValue() < avg)
                it.remove();//使用迭代器的remove()方法删除元素
        }
        return map;
    }

}