org.apache.poi.openxml4j.opc.OPCPackage Java Examples

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( String filename ) throws Exception {
	OPCPackage pkg = OPCPackage.open( filename );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

/**只遍历一个电子表格，其中sheetId为要遍历的sheet索引，从1开始，1-3
 * @param filename
 * @param sheetId
 * @throws Exception
 */
public void processOneSheet(String filename,int sheetId) throws Exception {
	OPCPackage pkg = OPCPackage.open(filename);
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	
	// 根据 rId# 或 rSheet# 查找sheet
	InputStream sheet2 = r.getSheet( "rId"+sheetId);
	sheetIndex++;
	InputSource sheetSource = new InputSource(sheet2);
	parser.parse(sheetSource);
	sheet2.close();
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( InputStream is ) throws Exception {
	OPCPackage pkg = OPCPackage.open( is );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( String filename ) throws Exception {
	OPCPackage pkg = OPCPackage.open( filename );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

void sanitize(BleachSession session, OPCPackage pkg, PackagePart part) {
  LOGGER.trace("Part name: {}", part.getPartName());

  String contentType = part.getContentType();
  LOGGER.debug("Content type: {} for part {}", contentType, part.getPartName());

  // Sample content types:
  // vnd.ms-word.vbaData+xml, vnd.ms-office.vbaProject
  // cf https://msdn.microsoft.com/fr-fr/library/aa338205(v=office.12).aspx
  ContentType type = part.getContentTypeDetails();
  if (isForbiddenType(type) || isStrangeContentType(type)) {
    LOGGER.debug(SUSPICIOUS_OOXML_FORMAT, contentType, part.getPartName(), part.getSize());
    deletePart(pkg, part.getPartName());

    Threat threat = Threat.builder()
        .type(ThreatType.ACTIVE_CONTENT)
        .severity(ThreatSeverity.HIGH)
        .action(ThreatAction.REMOVE)
        .location(part.getPartName().getName())
        .details("Forbidden content type: " + type)
        .build();

    session.recordThreat(threat);
  }
}
 

public void processAllSheets(String filename) throws Exception {
    OPCPackage pkg = OPCPackage.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("");
    }
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( String filename ) throws Exception {
	OPCPackage pkg = OPCPackage.open(filename);
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

@Test
public void Encryption() throws Exception {
    String file = TestFileUtil.getPath() + "large" + File.separator + "large07.xlsx";
    POIFSFileSystem fs = new POIFSFileSystem();
    EncryptionInfo info = new EncryptionInfo(EncryptionMode.agile);
    Encryptor enc = info.getEncryptor();
    enc.confirmPassword("foobaa");
    OPCPackage opc = OPCPackage.open(new File(file), PackageAccess.READ_WRITE);
    OutputStream os = enc.getDataStream(fs);
    opc.save(os);
    opc.close();

    // Write out the encrypted version
    FileOutputStream fos = new FileOutputStream("D:\\test\\99999999999.xlsx");
    fs.writeFilesystem(fos);
    fos.close();
    fs.close();

}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param is
 * @param fileKey 
 * @throws Exception
 */
public void process( InputStream is ) throws Exception {
	OPCPackage pkg = OPCPackage.open( is );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

/**
 * Gets the textual element of the .docx at the given {@link URI}.
 * 
 * @param uriConverter
 *            the {@link URIConverter}
 * @param uri
 *            the .docx {@link URI}
 * @return the textual element of the .docx at the given {@link URI}
 */
public static String getTextContent(URIConverter uriConverter, URI uri) {
    String result = "";

    try (InputStream is = uriConverter.createInputStream(uri);
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);
            XWPFWordExtractor ex = new XWPFWordExtractor(document);) {

        result += "===== Document Text ====\n";
        result += ex.getText();
        // CHECKSTYLE:OFF
    } catch (Throwable e) {
        // CHECKSTYLE:ON
        /*
         * if for some reason we can't use POI to get the text content then move along, we'll still get the XML and hashs
         */
    }
    return result;
}
 

public void parseXlsxFileAndWriteTmxBody(String fileName, AbstractWriter tmxWriter, IProgressMonitor monitor)
		throws ParserConfigurationException, SAXException, IOException, OpenXML4JException {
	this.tmxWriter = tmxWriter;
	this.monitor = monitor;
	File file = new File(fileName);
	long length = file.length();
	monitor.beginTask("", countTotal(length));
	OPCPackage p = OPCPackage.open(fileName, PackageAccess.READ);
	ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(p);
	XSSFReader xssfReader = new XSSFReader(p);
	XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
	try {
		while (iter.hasNext()) {
			InputStream stream = iter.next();
			parse(stream, strings, tmxWriter);
			stream.close();
			// 目前只处理第一个sheet
			break;
		}
	} finally {
		p.close();
	}

	monitor.done();
}
 

private POIFSFileSystem openFileSystemAndEncrypt(File file) throws Exception {
    POIFSFileSystem fileSystem = new POIFSFileSystem();
    Encryptor encryptor = new EncryptionInfo(EncryptionMode.standard).getEncryptor();
    encryptor.confirmPassword(writeWorkbookHolder.getPassword());
    OPCPackage opcPackage = null;
    try {
        opcPackage = OPCPackage.open(file, PackageAccess.READ_WRITE);
        OutputStream outputStream = encryptor.getDataStream(fileSystem);
        opcPackage.save(outputStream);
    } finally {
        if (opcPackage != null) {
            opcPackage.close();
        }
    }
    return fileSystem;
}
 

@Test
public void testNonEmptyDoc() throws InvalidFormatException, IOException {
    try (FileInputStream is = new FileInputStream("resources/document/notEmpty/notEmpty-template.docx");
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);) {
        TokenProvider iterator = new TokenProvider(document);
        XWPFRun run = iterator.next().getRun();
        assertEquals("P1Run1 ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P1Run2", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals(" P1Run3", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run1 ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run2", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals(" ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run3", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("", run.getText(run.getTextPosition()));
        assertTrue(!iterator.hasNext());
    }
}
 

@Test(expected = NoSuchElementException.class)
public void testAccessEmptyIterator() throws InvalidFormatException, IOException {
    try (FileInputStream is = new FileInputStream("resources/document/notEmpty/notEmpty-template.docx");
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);) {
        TokenProvider iterator = new TokenProvider(document);
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
        iterator.next().getRun();
    }
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param is
 * @param fileKey 
 * @throws Exception
 */
public void process( InputStream is ) throws Exception {
	OPCPackage pkg = OPCPackage.open( is );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( String filename ) throws Exception {
	OPCPackage pkg = OPCPackage.open(filename);
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

/**
 * 遍历工作簿中所有的电子表格
 * @param filename
 * @param fileKey 
 * @throws Exception
 */
public void process( String filename ) throws Exception {
	OPCPackage pkg = OPCPackage.open( filename );
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	Iterator<InputStream> sheets = r.getSheetsData();
	while (sheets.hasNext()) {
		curRow = 0;
		sheetIndex++;
		InputStream sheet = sheets.next();
		InputSource sheetSource = new InputSource(sheet);
		parser.parse( sheetSource );
		sheet.close();
	}
	//数据读取完成
}
 

@Test
public void testNextWitLookAhead() throws InvalidFormatException, IOException {
    try (FileInputStream is = new FileInputStream("resources/document/notEmpty/notEmpty-template.docx");
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);) {
        TokenProvider iterator = new TokenProvider(document);
        // CHECKSTYLE:OFF
        assertTrue(iterator.hasElements(7));
        // CHECKSTYLE:ON
        XWPFRun run;
        run = iterator.lookAhead(1).getRun();
        assertEquals("P1Run1 ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P1Run1 ", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(1).getRun();
        assertEquals("P1Run2", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(2).getRun();
        assertEquals(" P1Run3", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P1Run2", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals(" P1Run3", run.getText(run.getTextPosition()));
        assertTrue(iterator.hasElements(4));
    }
}
 

@Test
public void testNonEmptyDoc() throws InvalidFormatException, IOException {
    try (FileInputStream is = new FileInputStream("resources/document/notEmpty/notEmpty-template.docx");
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);) {
        TokenIterator iterator = new TokenIterator(document);
        XWPFRun run = iterator.next().getRun();
        assertEquals("P1Run1 ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P1Run2", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals(" P1Run3", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run1 ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run2", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals(" ", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("P2Run3", run.getText(run.getTextPosition()));
        run = iterator.next().getRun();
        assertEquals("", run.getText(run.getTextPosition()));
        assertTrue(!iterator.hasNext());
    }
}
 

/**
 * Opens the excel resource
 * @param resource the resource to open
 * @return an OPCPackage representing the excel resource
 * @throws IOException if an io problem occurs
 * @throws InvalidFormatException if the file has an incorrect format
 */
private OPCPackage open(Resource resource) throws IOException, InvalidFormatException {
    switch (resource.getType()) {
        case FILE: return OPCPackage.open(resource.asFile());
        case URL: return OPCPackage.open(resource.asURL().getPath());
        case INPUT_STREAM: return OPCPackage.open(resource.asInputStream());
        default: throw new DataFrameException("Unsupported resource specified in ExcelRequest: " + resource);
    }
}
 

public static OPCPackage readPackage(String path){
	try {
		OPCPackage pack = POIXMLDocument.openPackage(path);
		return pack;
	} catch (IOException e) {
		throw new RuntimeException("read word file["+path+"] error:"+e.getMessage());
	}
}
 

/**
 * Ensure that the validation generation produces a document with an warning.
 * 
 * @throws InvalidFormatException
 * @throws IOException
 * @throws DocumentParserException
 * @throws DocumentGenerationException
 */
@Test
public void testWarningGeneration()
        throws InvalidFormatException, IOException, DocumentParserException, DocumentGenerationException {
    IQueryEnvironment queryEnvironment = org.eclipse.acceleo.query.runtime.Query
            .newEnvironmentWithDefaultServices(null);
    final File tempFile = File.createTempFile("testParsingErrorSimpleTag", ".docx");

    try (DocumentTemplate documentTemplate = M2DocUtils.parse(URIConverter.INSTANCE,
            URI.createFileURI("resources/document/notEmpty/notEmpty-template.docx"), queryEnvironment,
            new ClassProvider(this.getClass().getClassLoader()), new BasicMonitor())) {
        final XWPFRun location = ((XWPFParagraph) documentTemplate.getDocument().getBodyElements().get(0)).getRuns()
                .get(0);
        documentTemplate.getBody().getValidationMessages().add(new TemplateValidationMessage(
                ValidationMessageLevel.WARNING, "XXXXXXXXXXXXXXXXXXXXXXXX", location));
        M2DocUtils.serializeValidatedDocumentTemplate(URIConverter.INSTANCE, documentTemplate,
                URI.createFileURI(tempFile.getAbsolutePath()));
    }
    assertTrue(new File(tempFile.getAbsolutePath()).exists());

    try (FileInputStream resIs = new FileInputStream(tempFile.getAbsolutePath());
            OPCPackage resOPackage = OPCPackage.open(resIs);
            XWPFDocument resDocument = new XWPFDocument(resOPackage);) {

        final XWPFRun messageRun = M2DocTestUtils.getRunContaining(resDocument, "XXXXXXXXXXXXXXXXXXXXXXXX");

        assertNotNull(messageRun);
        assertEquals("XXXXXXXXXXXXXXXXXXXXXXXX", messageRun.text());
        assertEquals("FFA500", messageRun.getColor());
    }

    tempFile.delete();
}
 

/**
 * Ensure that the validation generation produces a document with an error.
 * 
 * @throws InvalidFormatException
 * @throws IOException
 * @throws DocumentParserException
 * @throws DocumentGenerationException
 */
@Test
public void testErrorGeneration()
        throws InvalidFormatException, IOException, DocumentParserException, DocumentGenerationException {
    IQueryEnvironment queryEnvironment = org.eclipse.acceleo.query.runtime.Query
            .newEnvironmentWithDefaultServices(null);
    final File tempFile = File.createTempFile("testParsingErrorSimpleTag", ".docx");

    try (DocumentTemplate documentTemplate = M2DocUtils.parse(URIConverter.INSTANCE,
            URI.createFileURI("resources/document/notEmpty/notEmpty-template.docx"), queryEnvironment,
            new ClassProvider(this.getClass().getClassLoader()), new BasicMonitor())) {
        final XWPFRun location = ((XWPFParagraph) documentTemplate.getDocument().getBodyElements().get(0)).getRuns()
                .get(0);
        documentTemplate.getBody().getValidationMessages().add(
                new TemplateValidationMessage(ValidationMessageLevel.ERROR, "XXXXXXXXXXXXXXXXXXXXXXXX", location));
        M2DocUtils.serializeValidatedDocumentTemplate(URIConverter.INSTANCE, documentTemplate,
                URI.createFileURI(tempFile.getAbsolutePath()));
    }
    assertTrue(new File(tempFile.getAbsolutePath()).exists());

    try (FileInputStream resIs = new FileInputStream(tempFile.getAbsolutePath());
            OPCPackage resOPackage = OPCPackage.open(resIs);
            XWPFDocument resDocument = new XWPFDocument(resOPackage);) {

        final XWPFRun messageRun = M2DocTestUtils.getRunContaining(resDocument, "XXXXXXXXXXXXXXXXXXXXXXXX");

        assertNotNull(messageRun);
        assertEquals("XXXXXXXXXXXXXXXXXXXXXXXX", messageRun.text());
        assertEquals("FF0000", messageRun.getColor());
    }

    tempFile.delete();
}
 

@Test
public void testLookAhead() throws InvalidFormatException, IOException {
    try (FileInputStream is = new FileInputStream("resources/document/notEmpty/notEmpty-template.docx");
            OPCPackage oPackage = OPCPackage.open(is);
            XWPFDocument document = new XWPFDocument(oPackage);) {
        TokenProvider iterator = new TokenProvider(document);
        // CHECKSTYLE:OFF
        assertTrue(iterator.hasElements(7));
        XWPFRun run;
        run = iterator.lookAhead(1).getRun();
        assertEquals("P1Run1 ", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(2).getRun();
        assertEquals("P1Run2", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(3).getRun();
        assertEquals(" P1Run3", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(4).getRun();
        assertEquals("P2Run1 ", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(5).getRun();
        assertEquals("P2Run2", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(6).getRun();
        assertEquals(" ", run.getText(run.getTextPosition()));
        run = iterator.lookAhead(7).getRun();
        assertEquals("P2Run3", run.getText(run.getTextPosition()));
        assertTrue(iterator.hasElements(7));
        // CHECKSTYLE:ON
    }
}
 

/**
 * @param pkg          The {@link OPCPackage} to use as basis for the shared-strings table.
 * @param stringsCache stringsCache
 * @throws IOException  If reading the data from the package fails.
 * @throws SAXException if parsing the XML data fails.
 * @since POI 3.14-Beta3
 */
public ReadOnlySharedStringsTable(OPCPackage pkg, StringsCache stringsCache)
        throws IOException, SAXException {
    this.stringsCache = stringsCache;
    ArrayList<PackagePart> parts =
            pkg.getPartsByContentType(XSSFRelation.SHARED_STRINGS.getContentType());

    // Some workbooks have no shared strings table.
    if (parts.size() > 0) {
        PackagePart sstPart = parts.get(0);
        readFrom(sstPart.getInputStream());
    }
}
 

@Before
public void setUp() throws Exception {
    OPCPackage pkg = OPCPackage.open(StreamingSheetTest.class.getResourceAsStream("../dates.xlsx"));
    XSSFReader reader = new XSSFReader(pkg);

    ReadOnlySharedStringsTable sst = new ReadOnlySharedStringsTable(pkg);
    StylesTable styles = reader.getStylesTable();

    Iterator<InputStream> iter = reader.getSheetsData();
    XMLEventReader parser = XMLInputFactory.newInstance().createXMLEventReader(iter.next());
    final StreamingSheetReader streamingSheetReader = new StreamingSheetReader(sst, styles, parser, 10);
    streamingSheet = new StreamingSheet("name", streamingSheetReader);
}
 

/**
 * The dummy file tries to prevent Microsoft Office from crashing because they forgot a lot of "!=
 * null" while checking if a resource is valid.
 *
 * @param pkg Document to put the file in
 */
private void pushDummyFile(OPCPackage pkg) throws InvalidFormatException {

  try (ByteArrayOutputStream bos = new ByteArrayOutputStream()) {
    bos.write(DUMMY_FILE_CONTENT.getBytes());
    pkg.createPart(
        PackagingURIHelper.createPartName(DUMMY_FILE_PART_NAME), ContentTypes.TEXT_PLAIN, bos);
  } catch (IOException ex) {
    LOGGER.error(
        "Error occured while pushing the file in the document. But, it's not that critical so I'm gonna continue.",
        ex);
  }
}
 

public void sanitize(OPCPackage pkg, BleachSession session)
    throws BleachException, InvalidFormatException {
  LOGGER.trace("File opened");
  Iterator<PackagePart> it = getPartsIterator(pkg);

  pkg.ensureRelationships();

  sanitize(session, pkg, pkg.getRelationships());

  PackagePart part;
  while (it.hasNext()) {
    part = it.next();
    sanitize(session, pkg, part);

    OOXMLTagHelper.removeExternalDataTagAndDDE(session, part);

    if (!part.isRelationshipPart()) {
      sanitize(session, part, part.getRelationships());
    }

    if (part.isDeleted()) {
      continue;
    }

    remapContentType(session, part);
  }

  // If threats have been removed, then add the dummy file so the relationship
  // still refers to an existing dummy object.
  if (session.threatCount() > 0) {
    pushDummyFile(pkg);
  }
}
 

/**
 * Get OPCPackage from template file.
 * 
 * @param uriConverter
 *            the {@link URIConverter uri converter} to use.
 * @param templateURI
 *            the template {@link URI}
 * @return OPCPackage
 * @throws IOException
 *             IOException
 */
private OPCPackage getOPCPackage(URIConverter uriConverter, URI templateURI) throws IOException {
    OPCPackage oPackage;
    try (InputStream is = uriConverter.createInputStream(templateURI)) {
        try {
            oPackage = OPCPackage.open(is);

        } catch (InvalidFormatException e) {
            throw new IllegalArgumentException("Couldn't open template file", e);
        }
    }
    return oPackage;
}
 

/**只遍历一个电子表格，其中sheetId为要遍历的sheet索引，从1开始，1-3
 * @param filename
 * @param sheetId
 * @throws Exception
 */
public void processOneSheet(String filename,int sheetId) throws Exception {
	OPCPackage pkg = OPCPackage.open(filename);
	XSSFReader r = new XSSFReader(pkg);
	SharedStringsTable sst = r.getSharedStringsTable();
	XMLReader parser = fetchSheetParser(sst);
	
	// 根据 rId# 或 rSheet# 查找sheet
	InputStream sheet2 = r.getSheet("rId"+sheetId);
	sheetIndex++;
	InputSource sheetSource = new InputSource(sheet2);
	parser.parse(sheetSource);
	sheet2.close();
}