java 使用 opencsv 封装csv导入导出工具 中文乱码

Posted 2021-07-07 BBinChina

场景

业务开放过程中， 经常需要使用到csv导入导出的功能，我们可以使用opencsv库封装工具类。

pom引入：

        <!--        csv-->
        <dependency>
            <groupId>com.opencsv</groupId>
            <artifactId>opencsv</artifactId>
            <version>5.2</version>
        </dependency>

工具类封装：

package com.digquant.util;

import com.opencsv.CSVWriter;
import com.opencsv.bean.StatefulBeanToCsv;
import com.opencsv.bean.StatefulBeanToCsvBuilder;
import com.opencsv.exceptions.CsvDataTypeMismatchException;
import com.opencsv.exceptions.CsvRequiredFieldEmptyException;
import lombok.extern.slf4j.Slf4j;
import org.springframework.stereotype.Component;

import javax.servlet.http.HttpServletResponse;
import java.io.*;
import java.util.List;

@Slf4j
public class CsvUtil<T> {
    public void generateCsvFile(List<T> exportResults, String fileName, String[] header) throws IOException, CsvDataTypeMismatchException, CsvRequiredFieldEmptyException {
        Writer writer = new FileWriter(fileName);
        //utf-8  bom
        writer.write(new String(new byte[] { (byte) 0xEF, (byte) 0xBB,(byte) 0xBF }));
        // 写表头
        CSVWriter csvWriter = new CSVWriter(writer, CSVWriter.DEFAULT_SEPARATOR, CSVWriter.NO_QUOTE_CHARACTER, CSVWriter.NO_ESCAPE_CHARACTER, CSVWriter.DEFAULT_LINE_END);
        csvWriter.writeNext(header);
        //写内容
        StatefulBeanToCsv beanToCsv = new StatefulBeanToCsvBuilder(writer).build();
        beanToCsv.write(exportResults);
        csvWriter.close();
        writer.close();
    }

    /**
     * 读取csv文件流返回前端下载
     * @param fileName
     * @param response
     * @throws UnsupportedEncodingException
     */
    public void readCsvFileStream(String fileName, HttpServletResponse response) throws UnsupportedEncodingException {
        String myFileName = new String(fileName.getBytes("utf-8"), "gbk");
        File file = new File(myFileName);
        if (file.exists()) {
            response.setContentType("application/force-download");// 设置强制下载不打开
            response.addHeader("Content-Disposition", "attachment;fileName=" + myFileName);// 设置文件名
            byte[] buffer = new byte[1024];
            FileInputStream fis = null;
            BufferedInputStream bis = null;
            try {
                fis = new FileInputStream(file);
                bis = new BufferedInputStream(fis);
                OutputStream os = response.getOutputStream();
                int i = bis.read(buffer);
                while (i != -1) {
                    os.write(buffer, 0, i);
                    i = bis.read(buffer);
                }
            } catch (Exception e) {
                e.printStackTrace();
            } finally {
                if (bis != null) {
                    try {
                        bis.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                if (fis != null) {
                    try {
                        fis.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
            }
        }
        if(file.delete()){
            log.error(file.getName() + " 文件已被删除！");
        }else{
            log.error("文件删除失败！");
        }
    }
}

在使用csv过程中， 常见的问题有 csv的中文乱码问题，在写csv文件时，微软的csv采用的utf-8 bom的编码格式，因此我们可以在文件头3字节写入utf-8 bom说明文件格式

//utf-8  bom
        writer.write(new String(new byte[] { (byte) 0xEF, (byte) 0xBB,(byte) 0xBF }));

说到编码集，我们同样可以读取文件的前三个字节，关于一下代码，你是否有些许问题呢？评论交流吧

    public static String GetFileCharset(InputStream ins) {
        BufferedInputStream bin = new BufferedInputStream(ins);
        int p = 0;
        try {
            p = (bin.read() << 8) + bin.read();
        } catch (IOException e) {
            e.printStackTrace();
            return "";
        }
        String code = null;

        switch (p) {
            case 0xefbb:
                code = "UTF-8";
                break;
            case 0xfffe:
                code = "Unicode";
                break;
            case 0xfeff:
                code = "UTF-16BE";
                break;
            default:
                code = "GBK";
        }
        return code;
    }