文件解析工具
前言
对Excel & CSV 文件解析
package com.wind.bird.Utils;
import com.opencsv.CSVReader;
import com.opencsv.CSVReaderBuilder;
import org.apache.commons.validator.Var;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.DateUtil;
import org.apache.poi.ss.util.NumberToTextConverter;
import org.apache.poi.xssf.usermodel.XSSFCell;
import org.apache.poi.xssf.usermodel.XSSFRow;
import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.web.multipart.MultipartFile;
import java.io.*;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
/**
* @Author windBird
* @Date 2023/11/25 21:28
* @ClassName FileParseUtil
* coding ^_^ every Day
* @Desc excel & csv parse
*/
public class FileParseUtil {
private static final Logger log = LoggerFactory.getLogger(FileParseUtil.class);
/**
* @param file
* @return
*/
public static List<Object[]> readFileToList(MultipartFile file) {
String fileName = file.getOriginalFilename();
String suffixName = fileName.substring(fileName.lastIndexOf("."));
try {
switch (suffixName) {
case FileTypeEnum.CSV:
return parseFileWithCsv(file);
case FileTypeEnum.XLS:
return readExcelWithXLs(file);
case FileTypeEnum.XLSX:
return parseExcelWithXlsx(file);
default:
return null;
}
} catch (IOException e) {
e.printStackTrace();
}
return new ArrayList<Object[]>();
}
private static List<Object[]> parseExcelWithXlsx(MultipartFile file) throws IOException {
XSSFWorkbook xssfWorkbook = null;
List<Object[]> list = new ArrayList<Object[]>();
InputStream inputStream = file.getInputStream();
try {
xssfWorkbook = new XSSFWorkbook(inputStream);
XSSFSheet xssfSheet = xssfWorkbook.getSheetAt(0);
XSSFRow xssfRow = null;
XSSFCell xssfCell = null;
Object cellValue = null;
for (int i = 1; i <= xssfSheet.getPhysicalNumberOfRows(); i++) {
xssfRow = xssfSheet.getRow(i);
if (null == xssfRow) {
continue;
}
Object[] values = new Object[xssfSheet.getRow(0).getLastCellNum()];
for (int j = 0; j <= xssfRow.getLastCellNum(); j++) {
xssfCell = xssfRow.getCell(j);
if (null == xssfCell) {
continue;
}
switch (xssfCell.getCellType()) {
case Cell.CELL_TYPE_STRING:
cellValue = xssfCell.getStringCellValue();
break;
case Cell.CELL_TYPE_NUMERIC:
if (DateUtil.isCellDateFormatted(xssfCell)) {
cellValue = DateUtil.getJavaDate(xssfCell.getNumericCellValue());
break;
} else {
cellValue = NumberToTextConverter.toText(xssfCell.getNumericCellValue());
break;
}
case Cell.CELL_TYPE_BOOLEAN:
cellValue = xssfCell.getBooleanCellValue();
break;
case Cell.CELL_TYPE_FORMULA:
cellValue = xssfCell.getCellFormula();
break;
case Cell.CELL_TYPE_BLANK:
cellValue = "";
break;
default:
cellValue = cellValue.toString();
}
values[j] = cellValue;
}
list.add(values);
}
return list;
} catch (Exception e) {
log.error("文件格式有误，请检查：{}", e);
return null;
} finally {
if (null != inputStream) inputStream.close();
if (null != xssfWorkbook) xssfWorkbook.close();
}
}
private static List<Object[]> readExcelWithXLs(MultipartFile file) throws IOException {
HSSFWorkbook hssfWorkbook = null;
List<Object[]> list = new ArrayList<Object[]>();
InputStream inputStream = file.getInputStream();
try {
hssfWorkbook = new HSSFWorkbook(inputStream);
HSSFSheet xssfSheet = hssfWorkbook.getSheetAt(0);
HSSFRow hssfRow = null;
HSSFCell hssfCell = null;
Object cellValue = null;
for (int i = 1; i <= xssfSheet.getPhysicalNumberOfRows(); i++) {
hssfRow = xssfSheet.getRow(i);
if (null == hssfRow) {
continue;
}
Object[] values = new Object[xssfSheet.getRow(0).getLastCellNum()];
for (int j = 0; j <= hssfRow.getLastCellNum(); j++) {
hssfCell = hssfRow.getCell(j);
if (null == hssfCell) {
continue;
}
switch (hssfCell.getCellType()) {
case Cell.CELL_TYPE_STRING:
cellValue = hssfCell.getStringCellValue();
break;
case Cell.CELL_TYPE_NUMERIC:
if (DateUtil.isCellDateFormatted(hssfCell)) {
cellValue = DateUtil.getJavaDate(hssfCell.getNumericCellValue());
break;
} else {
cellValue = NumberToTextConverter.toText(hssfCell.getNumericCellValue());
break;
}
case Cell.CELL_TYPE_FORMULA:
cellValue = hssfCell.getCellFormula();
break;
case Cell.CELL_TYPE_BOOLEAN:
cellValue = hssfCell.getBooleanCellValue();
break;
case Cell.CELL_TYPE_BLANK:
cellValue = "";
break;
default:
cellValue = cellValue.toString();
}
values[j] = cellValue;
}
list.add(values);
}
return list;
} catch (Exception e) {
log.error("文件格式有误，请检查：{}", e);
return null;
} finally {
if (null != inputStream) inputStream.close();
if (null != hssfWorkbook) hssfWorkbook.close();
}
}
private static List<Object[]> parseFileWithCsv(MultipartFile file) {
List<Object[]> list = new ArrayList<>();
int i = 0;
try {
CSVReader csvReader = new CSVReaderBuilder(
new BufferedReader(
new InputStreamReader(file.getInputStream()))).build();
Iterator<String[]> iterator = csvReader.iterator();
while (iterator.hasNext()) {
String[] next = iterator.next();
//去除第一行的表头，从第二行开始
if (i >= 1) {
list.add(next);
}
i++;
}
return list;
} catch (Exception e) {
log.error("CSV文件读取异常");
return list;
}
}
public interface FileTypeEnum {
String CSV = ".csv";
String XLS = ".xls";
String XLSX = ".xlsx";
}
}