异常读取XLSB文件Apache POI java.io.CharConversionException

Question

我正在开发一个使用Apache POI读取excel xlsb文件的Java应用程序,但是在读取它时遇到异常,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);
        }
    }

}

例外是这样的:

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,一张有329行和3列,另一张有566行和3列,我只是想读取文件以查找值是否在第二张表中.

Answer 1

除了文本提取之外,Apache POI不支持.xlsb文件格式.Apache POI将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(通过公共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,并且涉及的大量工作意味着没有人愿意自愿/赞助所需的工作.

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

要获得完整的读/写支持,您需要将文件转换为.xls(如果它没有非常大的行/列)或.xlsx(如果有).如果你真的非常渴望提供帮助,你可以查看XSSFBEventBasedExcelExtractor的源代码,然后继续提供补丁,为它添加对POI的全面支持!

(另外,我认为从您的特定.xlsb文件部分损坏的例外情况来看,但即使它不是,它仍然不会被Apache POI支持除文本提取以外的任何内容,抱歉)