Apache POI SAX XSSFReader 读取错误的日期格式

Question

Apache POI SAX 阅读器实现类似于这个众所周知的例子https://github.com/pjfanning/poi-shared-strings-sample/blob/master/src/main/java/com/github/pjfanning/poi/sample/XLSX2CSV .java读取一些日期值，而不是它们在 excel 中显示的那样，尽管它应该读取“格式化值”。

Excel 文件中的值： 1/1/2019 ，阅读器读取的“格式化值”： 1/1/19 。

知道为什么会有区别吗？

Apache POI 版本 3.17

读者代码：

package com.lopuch.sk.lita.is.importer;

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import javax.xml.parsers.ParserConfigurationException;

import org.apache.log4j.Logger;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.util.ZipSecureFile;
import org.apache.poi.ss.usermodel.DataFormatter;
import org.apache.poi.ss.util.CellAddress;
import org.apache.poi.ss.util.CellReference;
import org.apache.poi.util.SAXHelper;
import org.apache.poi.xssf.eventusermodel.ReadOnlySharedStringsTable;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.eventusermodel.XSSFSheetXMLHandler;
import org.apache.poi.xssf.eventusermodel.XSSFSheetXMLHandler.SheetContentsHandler;
import org.apache.poi.xssf.model.StylesTable;
import org.apache.poi.xssf.usermodel.XSSFComment;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;

import com.lopuch.sk.lita.is.importer.fileImport.ExcelRowReadListener;

public class ExcelSaxImporter {

    private static final Logger logger = Logger.getLogger(ExcelSaxImporter.class);

    private ExcelRowReadListener listener;

    public void setOnRowRead(ExcelRowReadListener listener) {
        this.listener = listener;
    }

    public ExcelRowReadListener getListener() {
        return listener;
    };

    public void process(byte[] fileByteArray)
            throws IOException, OpenXML4JException, ParserConfigurationException, SAXException {
        ZipSecureFile.setMinInflateRatio(0.0d);
        OPCPackage opcpPackage = OPCPackage.open(new ByteArrayInputStream(fileByteArray));
        ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(opcpPackage);
        XSSFReader xssfReader = new XSSFReader(opcpPackage);
        StylesTable styles = xssfReader.getStylesTable();
        XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();

        while (iter.hasNext()) {
            InputStream stream = iter.next();
            processSheet(styles, strings, getHandler(), stream);
            stream.close();
        }
    }

    private SheetContentsHandler getHandler() {
        return new SheetContentsHandler() {

            private boolean firstCellOfRow = false;
            private int currentRow = -1;
            private int currentCol = -1;

            // Maps column Letter name to its value.
            // Does not contain key-value pair if cell value is null for
            // currently
            // processed column and row.
            private Map<String, String> rowValues;

            @Override
            public void startRow(int rowNum) {
                // Prepare for this row
                firstCellOfRow = true;
                currentRow = rowNum;
                currentCol = -1;
                rowValues = new HashMap<String, String>();
            }

            @Override
            public void endRow(int rowNum) {
                if (rowValues.keySet().size() == 0) {
                    logger.trace("Skipping calling rowRead() because of empty row");
                } else {
                    ExcelSaxImporter.this.getListener().rowRead(rowValues);
                }
            }

            @Override
            public void cell(String cellReference, String formattedValue, XSSFComment comment) {
                if (firstCellOfRow) {
                    firstCellOfRow = false;
                }

                // gracefully handle missing CellRef here in a similar way
                // as XSSFCell does
                if (cellReference == null) {
                    cellReference = new CellAddress(currentRow, currentCol).formatAsString();
                }

                // Did we miss any cells?
                int thisCol = (new CellReference(cellReference)).getCol();
                currentCol = thisCol;

                cellReference = cellReference.replaceAll("\\d","");
                rowValues.put(cellReference, formattedValue);

            }

            @Override
            public void headerFooter(String text, boolean isHeader, String tagName) {
            }
        };
    }

    /**
     * Parses and shows the content of one sheet using the specified styles and
     * shared-strings tables.
     *
     * @param styles
     * @param strings
     * @param sheetInputStream
     */
    public void processSheet(StylesTable styles, ReadOnlySharedStringsTable strings, SheetContentsHandler sheetHandler,
            InputStream sheetInputStream) throws IOException, ParserConfigurationException, SAXException {
        DataFormatter formatter = new DataFormatter();
        InputSource sheetSource = new InputSource(sheetInputStream);
        try {
            XMLReader sheetParser = SAXHelper.newXMLReader();
            ContentHandler handler = new XSSFSheetXMLHandler(styles, null, strings, sheetHandler, formatter, false);
            sheetParser.setContentHandler(handler);
            sheetParser.parse(sheetSource);
        } catch (ParserConfigurationException e) {
            throw new RuntimeException("SAX parser appears to be broken - " + e.getMessage());
        }
    }
}

Answer 1

excel 显示的值与 Apache POI 读取的值之间的差异来自于对用户语言设置做出反应的日期格式。 来自 Excel：

以星号 (*) 开头的日期格式响应为操作系统指定的区域日期和时间设置的更改。

Apache POI DataFormatter 会忽略这些特定于语言环境的格式并返回默认的美国格式日期。 来自 Apache POI DataFormatter 文档：

某些格式会被 Excel 自动“本地化”，例如在某些区域设置中加载到 Excel 时显示为 mm/dd/yyyy，但在其他区域设置中显示为 dd/mm/yyyy。 这些始终以存储在文件中的“默认”（美国）格式返回。

要解决此问题，请参阅Java 的答案：excel to csv date conversion issue with Apache Poi