使用Springboot+poi上传并处理百万级数据EXCEL

Z时代
2024-01-10
分类：综合

1 Excel上传

针对Excel的上传，采用的是比较常规的方法，其实和文件上传是相同的。具体源码如下：


  @PostMapping(value = "", consumes = "multipart/*", headers = "content-type=multipart/form-data")
  public Map<String, Object> addBlacklist(
      @RequestParam("file") MultipartFile multipartFile, HttpServletRequest request
  ) {
    //判断上传内容是否符合要求
    String fileName = multipartFile.getOriginalFilename();
    if (!fileName.matches("^.+\\.(?i)(xls)$") && !fileName.matches("^.+\\.(?i)(xlsx)$")) {
      return returnError(0,"上传的文件格式不正确");
    }
    String file = saveFile(multipartFile, request);
    int result = 0;
    try {
      result = blacklistServcice.addBlackLists(file);
    } catch (Exception e) {
      e.printStackTrace();
    }
    return returnData(result);
  }
  private String saveFile(MultipartFile multipartFile, HttpServletRequest request) {
    String path;
    String fileName = multipartFile.getOriginalFilename();
    // 判断文件类型
    String realPath = request.getSession().getServletContext().getRealPath("/");
    String trueFileName = fileName;
    // 设置存放Excel文件的路径
    path = realPath + trueFileName;
    File file = new File(path);
    if (file.exists() && file.isFile()) {
      file.delete();
    }
    try {
      multipartFile.transferTo(new File(path));
    } catch (IOException e) {
      e.printStackTrace();
    }
    return path;
  }

上面的源码我们可以看见有一个saveFile方法，这个方法是将文件存在服务器本地，这样方便后续文件内容的读取，用不着一次读取所有的内容从而导致消耗大量的内存。当然这里大家如果有更好的方法希望能留言告知哈。

2 Excel处理工具源码


import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.helpers.XMLReaderFactory;
import java.io.InputStream;
import java.sql.SQLException;
import java.util.*;
/**
 * XSSF and SAX (Event API)
 */
public abstract class XxlsAbstract extends DefaultHandler {
  private SharedStringsTable sst;
  private String lastContents;
  private int sheetIndex = -1;
  private List<String> rowlist = new ArrayList<>();
  public List<Map<String, Object>> dataMap = new LinkedList<>(); //即将进行批量插入的数据
  public int willSaveAmount; //将要插入的数据量
  public int totalSavedAmount; //总共插入了多少数据
  private int curRow = 0;    //当前行
  private int curCol = 0;    //当前列索引
  private int preCol = 0;    //上一列列索引
  private int titleRow = 0;  //标题行，一般情况下为0
  public int rowsize = 0;  //列数
  //excel记录行操作方法，以sheet索引，行索引和行元素列表为参数，对sheet的一行元素进行操作，元素为String类型
  public abstract void optRows(int sheetIndex, int curRow, List<String> rowlist) throws SQLException;
  //只遍历一个sheet，其中sheetId为要遍历的sheet索引，从1开始，1-3
  /**
   * @param filename
   * @param sheetId sheetId为要遍历的sheet索引，从1开始，1-3
   * @throws Exception
   */
  public void processOneSheet(String filename, int sheetId) throws Exception {
    OPCPackage pkg = OPCPackage.open(filename);
    XSSFReader r = new XSSFReader(pkg);
    SharedStringsTable sst = r.getSharedStringsTable();
    XMLReader parser = fetchSheetParser(sst);
    // rId2 found by processing the Workbook
    // 根据 rId# 或 rSheet# 查找sheet
    InputStream sheet2 = r.getSheet("rId" + sheetId);
    sheetIndex++;
    InputSource sheetSource = new InputSource(sheet2);
    parser.parse(sheetSource);
    sheet2.close();
  }
  public XMLReader fetchSheetParser(SharedStringsTable sst)
      throws SAXException {
    XMLReader parser = XMLReaderFactory.createXMLReader();
    this.sst = sst;
    parser.setContentHandler(this);
    return parser;
  }
  public void endElement(String uri, String localName, String name) {
    // 根据SST的索引值的到单元格的真正要存储的字符串
    try {
      int idx = Integer.parseInt(lastContents);
      lastContents = new XSSFRichTextString(sst.getEntryAt(idx))
          .toString();
    } catch (Exception e) {
    }
    // v => 单元格的值，如果单元格是字符串则v标签的值为该字符串在SST中的索引
    // 将单元格内容加入rowlist中，在这之前先去掉字符串前后的空白符
    if (name.equals("v")) {
      String value = lastContents.trim();
      value = value.equals("") ? " " : value;
      int cols = curCol - preCol;
      if (cols > 1) {
        for (int i = 0; i < cols - 1; i++) {
          rowlist.add(preCol, "");
        }
      }
      preCol = curCol;
      rowlist.add(curCol - 1, value);
    } else {
      //如果标签名称为 row ，这说明已到行尾，调用 optRows() 方法
      if (name.equals("row")) {
        int tmpCols = rowlist.size();
        if (curRow > this.titleRow && tmpCols < this.rowsize) {
          for (int i = 0; i < this.rowsize - tmpCols; i++) {
            rowlist.add(rowlist.size(), "");
          }
        }
        try {
          optRows(sheetIndex, curRow, rowlist);
        } catch (SQLException e) {
          e.printStackTrace();
        }
        if (curRow == this.titleRow) {
          this.rowsize = rowlist.size();
        }
        rowlist.clear();
        curRow++;
        curCol = 0;
        preCol = 0;
      }
    }
  }
}

3 解析成功后的数据处理

首先我们将源码展示出来，然后再具体说明


public int addBlackLists(String file) throws ExecutionException, InterruptedException {
    ArrayList<Future<Integer>> resultList = new ArrayList<>();
    XxlsAbstract xxlsAbstract = new XxlsAbstract() {
      //针对数据的具体处理
      @Override
      public void optRows(int sheetIndex, int curRow, List<String> rowlist) {
        /**
         * 判断即将插入的数据是否已经到达8000，如果到达8000，
         * 进行数据插入
         */
        if (this.willSaveAmount == 5000) {
          //插入数据
          List<Map<String, Object>> list = new LinkedList<>(this.dataMap);
          Callable<Integer> callable = () -> {
            int count = blacklistMasterDao.addBlackLists(list);
            blacklistRecordMasterDao.addBlackListRecords(list);
            return count;
          };
          this.willSaveAmount = 0;
          this.dataMap = new LinkedList<>();
          Future<Integer> future = executor.submit(callable);
          resultList.add(future);
        }
        //汇总数据
        Map<String, Object> map = new HashMap<>();
        map.put("uid", rowlist.get(0));
        map.put("createTime", rowlist.get(1));
        map.put("regGame", rowlist.get(2));
          map.put("banGame", rowlist.get(2));
        this.dataMap.add(map);
        this.willSaveAmount++;
        this.totalSavedAmount++;
      }
    };
    try {
      xxlsAbstract.processOneSheet(file, 1);
    } catch (Exception e) {
      e.printStackTrace();
    }
    //针对没有存入的数据进行处理
    if(xxlsAbstract.willSaveAmount != 0){
      List<Map<String, Object>> list = new LinkedList<>(xxlsAbstract.dataMap);
      Callable<Integer> callable = () -> {
        int count = blacklistMasterDao.addBlackLists(list);
        blacklistRecordMasterDao.addBlackListRecords(list);
        return count;
      };
      Future<Integer> future = executor.submit(callable);
      resultList.add(future);
    }
    executor.shutdown();
    int total = 0;
    for (Future<Integer> future : resultList) {
      while (true) {
        if (future.isDone() && !future.isCancelled()) {
          int sum = future.get();
          total += sum;
          break;
        } else {
          Thread.sleep(100);
        }
      }
    }
    return total;
  }