使用Apache POI API将xlsx转换为csv

java apache-poi

2022-09-03 01:50:59

我正在尝试将.xlsx文件转换为.csv，正在进行转换，但数据格式不正确。请在下面找到代码，并建议对代码进行更改。

在这里，我试图读取一个.xlsx文件并将其写入csv文件，即将xlsx转换为csv，但我没有以正确的格式获得.csv文件，所有数据都显示在单个文件中，但它必须像Excel中的行一样显示。

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.util.Iterator;

import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;

public class XlsxtoCSV {

    static void xlsx(File inputFile, File outputFile) {
        // For storing data into CSV files
        StringBuffer data = new StringBuffer();

        try {
            FileOutputStream fos = new FileOutputStream(outputFile);
            // Get the workbook object for XLSX file
            XSSFWorkbook wBook = new XSSFWorkbook(new FileInputStream(inputFile));
            // Get first sheet from the workbook
            XSSFSheet sheet = wBook.getSheetAt(0);
            Row row;
            Cell cell;
            // Iterate through each rows from first sheet
            Iterator<Row> rowIterator = sheet.iterator();

            while (rowIterator.hasNext()) {
                row = rowIterator.next();

                // For each row, iterate through each columns
                Iterator<Cell> cellIterator = row.cellIterator();
                while (cellIterator.hasNext()) {

                    cell = cellIterator.next();

                    switch (cell.getCellType()) {
                        case Cell.CELL_TYPE_BOOLEAN:
                            data.append(cell.getBooleanCellValue() + ",");

                            break;
                        case Cell.CELL_TYPE_NUMERIC:
                            data.append(cell.getNumericCellValue() + ",");

                            break;
                        case Cell.CELL_TYPE_STRING:
                            data.append(cell.getStringCellValue() + ",");
                            break;

                        case Cell.CELL_TYPE_BLANK:
                            data.append("" + ",");
                            break;
                        default:
                            data.append(cell + ",");

                    }
                }
            }

            fos.write(data.toString().getBytes());
            fos.close();

        } catch (Exception ioe) {
            ioe.printStackTrace();
        }
    }
    //testing the application 

    public static void main(String[] args) {
        //reading file from desktop
        File inputFile = new File("C:\\Users\\user69\\Desktop\\test.xlsx");
        //writing excel data to csv 
        File outputFile = new File("C:\\Users\\user69\\Desktop\\test1.csv");
        xlsx(inputFile, outputFile);
    }
}

答案 1

这是感谢@Swapnil！

data.append("\r\n"); // After the columns have been appended.

以下内容由@Abdullah编辑（添加）我上面的原始答案并没有太大的影响，但阿卜杜拉的编辑显示了很多努力，所以我把它留给那些遇到这个问题的人。

public class App {

    public void convertExcelToCSV(Sheet sheet, String sheetName) {
        StringBuilder data = new StringBuilder();
        try {
            Iterator<Row> rowIterator = sheet.iterator();
            while (rowIterator.hasNext()) {
                Row row = rowIterator.next();
                Iterator<Cell> cellIterator = row.cellIterator();
                while (cellIterator.hasNext()) {
                    Cell cell = cellIterator.next();

                    CellType type = cell.getCellTypeEnum();
                    if (type == CellType.BOOLEAN) {
                        data.append(cell.getBooleanCellValue());
                    } else if (type == CellType.NUMERIC) {
                        data.append(cell.getNumericCellValue());
                    } else if (type == CellType.STRING) {
                        String cellValue = cell.getStringCellValue();
                        if(!cellValue.isEmpty()) {
                            cellValue = cellValue.replaceAll("\"", "\"\"");
                            data.append("\"").append(cellValue).append("\"");
                        }
                    } else if (type == CellType.BLANK) {
                    } else {
                        data.append(cell + "");
                    }
                    if(cell.getColumnIndex() != row.getLastCellNum()-1) {
                        data.append(",");
                    }
                }
                data.append('\n');
            }
            Files.write(Paths.get("C:\\Users\\" + sheetName + ".csv"),
                data.toString().getBytes("UTF-8"));
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String [] args)
    {
        App app = new App();
        String path =  "C:\\Users\\myFile.xlsx";
        try (InputStream inp = new FileInputStream(path)) {
            Workbook wb = WorkbookFactory.create(inp);

            for (int i = 0; i < wb.getNumberOfSheets(); i++) {
                System.out.println(wb.getSheetAt(i).getSheetName());
                app.convertExcelToCSV(wb.getSheetAt(i), wb.getSheetAt(i).getSheetName());
            }
        } catch (Exception ex) {
            System.out.println(ex.getMessage());
        } 
    }
}

答案 2

使用Commons CSV对单元格值进行编码，这更加强大。不幸的是，仍然需要一些额外的代码来迭代Sheet by Row/Cell，并在每个单元格上调用Commons CSV（XSSF没有提供），但至少实际写入的单元格值保证是标准的CSV（即你不需要担心自己转义字符或添加逗号）。

Maven add for Commons CSV：

<dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-csv</artifactId>
            <version>1.5</version>
        </dependency>

共享资源 CSV 可用后，这是将工作簿导出为 CSV 的代码。此示例写入输出流，但文件输出也很容易。

// Convert an XSSFWorkbook to CSV and write to provided OutputStream
private void writeWorkbookAsCSVToOutputStream(XSSFWorkbook workbook, OutputStream out) {        
    CSVPrinter csvPrinter = null;       
    try {       
        csvPrinter = new CSVPrinter(new OutputStreamWriter(out), CSVFormat.DEFAULT);                

        if (workbook != null) {
            XSSFSheet sheet = workbook.getSheetAt(0); // Sheet #0 in this example
            Iterator<Row> rowIterator = sheet.rowIterator();
            while (rowIterator.hasNext()) {               
                Row row = rowIterator.next();
                Iterator<Cell> cellIterator = row.cellIterator();
                while (cellIterator.hasNext()) {
                    Cell cell = cellIterator.next();
                    csvPrinter.print(cell.getStringCellValue());
                }                   
                csvPrinter.println(); // Newline after each row
            }               
        }

    }
    catch (Exception e) {
        log.error("Failed to write CSV file to output stream", e);
    }
    finally {
        try {
            if (csvPrinter != null) {
                csvPrinter.flush(); // Flush and close CSVPrinter
                csvPrinter.close();
            }
        }
        catch (IOException ioe) {
            log.error("Error when closing CSV Printer", ioe);
        }           
    }
}