图片文字自管理敏感词集成到文章审核中

1、在heima-leadnews-common中创建工具类，封装一下tess4j

package com.heima.common.tess4j;

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;

import java.awt.image.BufferedImage;

public class Tess4jClient {

    private String dataPath;
    private String language;

    public String doOCR(BufferedImage image) throws TesseractException {
        //创建Tesseract对象
        Tesseract tesseract = new Tesseract();
        //设置字体库路径
        tesseract.setDatapath(dataPath);
        //中文识别
        tesseract.setLanguage(language);
        //执行OCR识别
        String result = tesseract.doOCR(image);
        //替换回车和Tab键，使结果为一行
        result = result.replaceAll("\\r/\\n", "-").replaceAll(" ", "");
        return result;

    }
}

 

2、修改审核文章中的图片审核逻辑

将图片敏感词审核集成到图片审核中。

    try {
            for (String image : images) {
                byte[] bytes = fileStorageService.downLoadFile(image);
                //byte[] 转换为bufferedImage
                ByteArrayInputStream in = new ByteArrayInputStream(bytes);
                BufferedImage bufferedImage = ImageIO.read(in);
                //图片文字识别
                String result = tess4jClient.doOCR(bufferedImage);
                //过滤文字
                boolean isSensitive = handleSensitiveScan(result, wmNews);
                if(!isSensitive){
                    return isSensitive;
                }

                imageList.add(bytes);

            }
        }catch (Exception e){
            e.printStackTrace();
        }