Apache POIを使用してExcelxlsbファイルを読み取るJavaアプリケーションを開発していますが、読み取り中に例外が発生しました。コードは次のとおりです。
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);
}
}
}
そして例外はこれです：
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)
ファイルには2つのシートがあります。1つは329行3列で、もう1つは566行3列です。ファイルを読み取って、2番目のシートに値があるかどうかを確認したいと思います。