6

我正在开发一个使用 Apache POI 读取 excel xlsb 文件的 Java 应用程序，但是在读取它时出现异常，我的代码如下：

import java.io.IOException;
import java.io.InputStream;

import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.Package;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
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.util.Iterator;

public class Prueba {

    public static void main (String [] args){

        String direccion = "C:/Documents and Settings/RSalasL/My Documents/New Folder/masstigeoct12.xlsb";

        Package pkg;
        try {
            pkg = Package.open(direccion);
            XSSFReader r = new XSSFReader(pkg);
            SharedStringsTable sst = r.getSharedStringsTable();

            XMLReader parser = fetchSheetParser(sst);

            Iterator<InputStream> sheets = r.getSheetsData();
            while(sheets.hasNext()) {
                System.out.println("Processing new sheet:\n");
                InputStream sheet = sheets.next();
                InputSource sheetSource = new InputSource(sheet);
                parser.parse(sheetSource);
                sheet.close();
                System.out.println("");
            }

        } catch (InvalidFormatException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (OpenXML4JException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (SAXException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

    }

    public void processAllSheets(String filename) throws Exception {
        Package pkg = Package.open(filename);
        XSSFReader r = new XSSFReader( pkg );
        SharedStringsTable sst = r.getSharedStringsTable();

        XMLReader parser = fetchSheetParser(sst);

        Iterator<InputStream> sheets = r.getSheetsData();
        while(sheets.hasNext()) {
            System.out.println("Processing new sheet:\n");
            InputStream sheet = sheets.next();
            InputSource sheetSource = new InputSource(sheet);
            parser.parse(sheetSource);
            sheet.close();
            System.out.println("");
        }
    }


    public static XMLReader fetchSheetParser(SharedStringsTable sst) throws SAXException {
        XMLReader parser =
            XMLReaderFactory.createXMLReader(
                    "org.apache.xerces.parsers.SAXParser"
            );
        ContentHandler handler = new SheetHandler(sst);
        parser.setContentHandler(handler);
        return parser;
    }

    private static class SheetHandler extends DefaultHandler {
        private SharedStringsTable sst;
        private String lastContents;
        private boolean nextIsString;

        private SheetHandler(SharedStringsTable sst) {
            this.sst = sst;
        }

        public void startElement(String uri, String localName, String name,
                Attributes attributes) throws SAXException {
            // c => cell
            if(name.equals("c")) {
                // Print the cell reference
                System.out.print(attributes.getValue("r") + " - ");
                // Figure out if the value is an index in the SST
                String cellType = attributes.getValue("t");
                if(cellType != null && cellType.equals("s")) {
                    nextIsString = true;
                } else {
                    nextIsString = false;
                }
            }
            // Clear contents cache
            lastContents = "";
        }

        public void endElement(String uri, String localName, String name)
                throws SAXException {
            // Process the last contents as required.
            // Do now, as characters() may be called more than once
            if(nextIsString) {
                int idx = Integer.parseInt(lastContents);
                lastContents = new XSSFRichTextString(sst.getEntryAt(idx)).toString();
            nextIsString = false;
            }

            // v => contents of a cell
            // Output after we've seen the string contents
            if(name.equals("v")) {
                System.out.println(lastContents);
            }
        }

        public void characters(char[] ch, int start, int length)
                throws SAXException {
            lastContents += new String(ch, start, length);
        }
    }

}

例外是：

java.io.CharConversionException: Characters larger than 4 bytes are not supported: byte 0x83 implies a length of more than 4 bytes
    at org.apache.xmlbeans.impl.piccolo.xml.UTF8XMLDecoder.decode(UTF8XMLDecoder.java:162)
    at org.apache.xmlbeans.impl.piccolo.xml.XMLStreamReader$FastStreamDecoder.read(XMLStreamReader.java:762)
    at org.apache.xmlbeans.impl.piccolo.xml.XMLStreamReader.read(XMLStreamReader.java:162)
    at org.apache.xmlbeans.impl.piccolo.xml.PiccoloLexer.yy_refill(PiccoloLexer.java:3474)
    at org.apache.xmlbeans.impl.piccolo.xml.PiccoloLexer.yylex(PiccoloLexer.java:3958)
    at org.apache.xmlbeans.impl.piccolo.xml.Piccolo.yylex(Piccolo.java:1290)
    at org.apache.xmlbeans.impl.piccolo.xml.Piccolo.yyparse(Piccolo.java:1400)
    at org.apache.xmlbeans.impl.piccolo.xml.Piccolo.parse(Piccolo.java:714)
    at org.apache.xmlbeans.impl.store.Locale$SaxLoader.load(Locale.java:3439)
    at org.apache.xmlbeans.impl.store.Locale.parseToXmlObject(Locale.java:1270)
    at org.apache.xmlbeans.impl.store.Locale.parseToXmlObject(Locale.java:1257)
    at org.apache.xmlbeans.impl.schema.SchemaTypeLoaderBase.parse(SchemaTypeLoaderBase.java:345)
    at org.openxmlformats.schemas.spreadsheetml.x2006.main.WorkbookDocument$Factory.parse(Unknown Source)
    at org.apache.poi.xssf.eventusermodel.XSSFReader$SheetIterator.<init>(XSSFReader.java:207)
    at org.apache.poi.xssf.eventusermodel.XSSFReader$SheetIterator.<init>(XSSFReader.java:166)
    at org.apache.poi.xssf.eventusermodel.XSSFReader.getSheetsData(XSSFReader.java:160)
    at EDManager.Prueba.main(Prueba.java:36)

该文件有 2 张，一张 329 行 3 列，另一张 566 行 3 列，我只想读取文件以查找第二张表中是否有值。

4

3 回答 3

13

Apache POI 不支持将 .xlsb 文件格式用于文本提取以外的任何内容。Apache POI 很乐意提供完整的读取或写入支持 .xls 文件（通过 HSSF）和 .xlsx 文件（通过 XSSF），或两者（通过通用 SS UserModel 接口）。

但是，生成操作不支持 .xlsb 格式 - 这是两者之间非常奇怪的混合体，涉及的大量工作意味着没有人愿意自愿/赞助所需的工作。

从 Apache POI 3.15 beta3 / 3.16 开始，Apache POI 为 .xlsb 提供的是.xlsb 文件的文本提取器 - XSSFBEventBasedExcelExtractor。您可以使用它从文件中获取文本，或者通过一些调整将其转换为 CSV 之类的内容

要获得完整的读/写支持，您需要将文件转换为 .xls（如果它没有非常多的行/列）或 .xlsx（如果有）。如果您真的很想提供帮助，您可以查看XSSFBEventBasedExcelExtractor 的源代码，然后尝试贡献补丁以添加对 POI 的全面支持！

（此外，我认为您的特定 .xlsb 文件部分损坏的例外情况，但即使不是，Apache POI 仍然不支持除文本提取之外的任何其他内容，抱歉）

于 2013-01-11T20:27:15.937 回答
3

我曾尝试使用 Apache POI 读取 XLSB 文件，它是成功的。下面是我使用的代码片段。

import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.ss.usermodel.DataFormatter;
import org.apache.poi.xssf.binary.XSSFBSharedStringsTable;
import org.apache.poi.xssf.binary.XSSFBSheetHandler;
import org.apache.poi.xssf.binary.XSSFBStylesTable;
import org.apache.poi.xssf.eventusermodel.XSSFBReader;
import org.xml.sax.SAXException;

import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;

public class ApachePoiXLSB {

    public static void main (String [] args){

        String xlsbFileName = "test.xlsb";

        OPCPackage pkg;

        try {
            pkg = OPCPackage.open(xlsbFileName);
            XSSFBReader r = new XSSFBReader(pkg);
            XSSFBSharedStringsTable sst = new XSSFBSharedStringsTable(pkg);
            XSSFBStylesTable xssfbStylesTable = r.getXSSFBStylesTable();
            XSSFBReader.SheetIterator it = (XSSFBReader.SheetIterator) r.getSheetsData();

            List<String> sheetTexts = new ArrayList<>();
            while (it.hasNext()) {
                InputStream is = it.next();
                String name = it.getSheetName();
                TestSheetHandler testSheetHandler = new TestSheetHandler();
                testSheetHandler.startSheet(name);
                XSSFBSheetHandler sheetHandler = new XSSFBSheetHandler(is,
                        xssfbStylesTable,
                        it.getXSSFBSheetComments(),
                        sst, testSheetHandler,
                        new DataFormatter(),
                        false);
                sheetHandler.parse();
                testSheetHandler.endSheet();
                sheetTexts.add(testSheetHandler.toString());
            }
            System.out.println("output text:"+sheetTexts);

        } catch (InvalidFormatException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (OpenXML4JException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (SAXException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
}


import org.apache.poi.xssf.eventusermodel.XSSFSheetXMLHandler;
import org.apache.poi.xssf.usermodel.XSSFComment;

class TestSheetHandler implements XSSFSheetXMLHandler.SheetContentsHandler {

        private final StringBuilder sb = new StringBuilder();

        public void startSheet(String sheetName) {
            sb.append("<sheet name=\"").append(sheetName).append(">");
        }

        public void endSheet() {
            sb.append("</sheet>");
        }

        @Override
        public void startRow(int rowNum) {
            sb.append("\n<tr num=\"").append(rowNum).append(">");
        }

        @Override
        public void endRow(int rowNum) {
            sb.append("\n</tr num=\"").append(rowNum).append(">");
        }

        @Override
        public void cell(String cellReference, String formattedValue, XSSFComment comment) {
            formattedValue = (formattedValue == null) ? "" : formattedValue;
            if (comment == null) {
                sb.append("\n\t<td ref=\"").append(cellReference).append("\">").append(formattedValue).append("</td>");
            } else {
                sb.append("\n\t<td ref=\"").append(cellReference).append("\">")
                        .append(formattedValue)
                        .append("<span type=\"comment\" author=\"")
                        .append(comment.getAuthor()).append("\">")
                        .append(comment.getString().toString().trim()).append("</span>")
                        .append("</td>");
            }
        }

        @Override
        public void headerFooter(String text, boolean isHeader, String tagName) {
            if (isHeader) {
                sb.append("<header tagName=\"").append(tagName).append("\">").append(text).append("</header>");
            } else {
                sb.append("<footer tagName=\"").append(tagName).append("\">").append(text).append("</footer>");

            }
        }

        @Override
        public String toString() {
            return sb.toString();
        }
    }
于 2019-08-13T12:46:48.967 回答
-2

我有一个使用smartxls的实现，我的代码首先将 xlsb 转换为 xlsx，之后可以使用 ApachePoi。下一个方法接收 java.io.File 并验证其扩展名是否为 xlsb 并将其转换为 xlsx 并将文件替换为新文件。这对我有用。

private void processXLSBFile(File file) {
    WorkBook workBook = new WorkBook();
    String filePath = file.getAbsolutePath();
    if (FilenameUtils.getExtension(filePath).equalsIgnoreCase((Static.XLSB_EXT))) {
        try {
            workBook.readXLSB(new java.io.FileInputStream(filePath));
            filePath = filePath.replaceAll("(?i)".concat(Static.XLSB),
                    Static.XLSX_EXT.toLowerCase());
            workBook.writeXLSX(new java.io.FileOutputStream(filePath));
            final File xlsb = new File(filePath);
            file = xlsb;
        } catch (Exception e) {
            logger.error(e.getMessage(), e);
            MensajesJSFUtil
                    .mostrarMensajeNegocio(new GTMException(e, ClaveMensaje.COMANDAS_ADJUNTAR_XLSBFILE_READERROR));
        }
    }
}
于 2017-11-30T15:56:08.903 回答