Examples with ExcelExtractor org.apache.poi.hssf.extractor.ExcelExtractor used on opensource projects

Example 6 with ExcelExtractor

use of org.apache.poi.hssf.extractor.ExcelExtractor in project poi by apache.

the class TestHPSFPropertiesExtractor method testConstructors.

public void testConstructors() throws IOException {
    POIFSFileSystem fs;
    HSSFWorkbook wb;
    try {
        fs = new POIFSFileSystem(_samples.openResourceAsStream("TestUnicode.xls"));
        wb = new HSSFWorkbook(fs);
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    ExcelExtractor excelExt = new ExcelExtractor(wb);
    final String fsText;
    HPSFPropertiesExtractor fsExt = new HPSFPropertiesExtractor(fs);
    // Don't close re-used test resources!
    fsExt.setFilesystem(null);
    try {
        fsText = fsExt.getText();
    } finally {
        fsExt.close();
    }
    final String hwText;
    HPSFPropertiesExtractor hwExt = new HPSFPropertiesExtractor(wb);
    // Don't close re-used test resources!
    hwExt.setFilesystem(null);
    try {
        hwText = hwExt.getText();
    } finally {
        hwExt.close();
    }
    final String eeText;
    HPSFPropertiesExtractor eeExt = new HPSFPropertiesExtractor(excelExt);
    // Don't close re-used test resources!
    eeExt.setFilesystem(null);
    try {
        eeText = eeExt.getText();
    } finally {
        eeExt.close();
        wb.close();
    }
    assertEquals(fsText, hwText);
    assertEquals(fsText, eeText);
    assertContains(fsText, "AUTHOR = marshall");
    assertContains(fsText, "TITLE = Titel: Äh");
}

Example 7 with ExcelExtractor

use of org.apache.poi.hssf.extractor.ExcelExtractor in project poi by apache.

the class TestCryptoAPI method validateContent.

private void validateContent(String wbFile, String password, String textExpected) throws IOException {
    Biff8EncryptionKey.setCurrentUserPassword(password);
    HSSFWorkbook wb = ssTests.openSampleWorkbook(wbFile);
    ExcelExtractor ee1 = new ExcelExtractor(wb);
    String textActual = ee1.getText();
    assertContains(textActual, textExpected);
    Biff8EncryptionKey.setCurrentUserPassword("bla");
    HSSFWorkbook wbBla = ssTests.writeOutAndReadBack(wb);
    ExcelExtractor ee2 = new ExcelExtractor(wbBla);
    textActual = ee2.getText();
    assertContains(textActual, textExpected);
    ee2.close();
    ee1.close();
    wbBla.close();
    wb.close();
}

Example 8 with ExcelExtractor

use of org.apache.poi.hssf.extractor.ExcelExtractor in project Gargoyle by callakrsos.

the class DocFileParser method DocFileContentParser.

public String DocFileContentParser(String fileName) {
    POIFSFileSystem fs = null;
    try {
        fs = new POIFSFileSystem(new FileInputStream(fileName));
        if (fileName.endsWith(".doc")) {
            HWPFDocument doc = new HWPFDocument(fs);
            WordExtractor we = new WordExtractor(doc);
            return we.getText();
        } else if (fileName.endsWith(".xls")) {
            ExcelExtractor ex = new ExcelExtractor(fs);
            ex.setFormulasNotResults(true);
            ex.setIncludeSheetNames(true);
            return ex.getText();
        } else if (fileName.endsWith(".ppt")) {
            PowerPointExtractor extractor = new PowerPointExtractor(fs);
            return extractor.getText();
        }
    } catch (Exception e) {
        LOGGER.debug("document file cant be indexed");
    }
    return "";
}

Example 9 with ExcelExtractor

use of org.apache.poi.hssf.extractor.ExcelExtractor in project carbon-apimgt by wso2.

the class DocumentIndexer method fetchDocumentContent.

/**
 * Write document content to document artifact as its raw content
 *
 * @param registry
 * @param documentResource
 * @return
 * @throws RegistryException
 * @throws IOException
 * @throws APIManagementException
 */
private String fetchDocumentContent(Registry registry, Resource documentResource) throws RegistryException, IOException, APIManagementException {
    GenericArtifactManager docArtifactManager = APIUtil.getArtifactManager(registry, APIConstants.DOCUMENTATION_KEY);
    GenericArtifact documentArtifact = docArtifactManager.getGenericArtifact(documentResource.getUUID());
    String sourceType = documentArtifact.getAttribute(APIConstants.DOC_SOURCE_TYPE);
    String contentString = null;
    if (Documentation.DocumentSourceType.FILE.name().equals(sourceType)) {
        String path = documentArtifact.getAttribute(APIConstants.DOC_FILE_PATH);
        int indexOfApimgt = path.indexOf(APIConstants.APIMGT_REGISTRY_LOCATION);
        String filepath = path.substring(indexOfApimgt);
        Resource contentResource = registry.get(filepath);
        int indexOfFiles = filepath.indexOf(APIConstants.DOCUMENT_FILE_DIR) + APIConstants.DOCUMENT_FILE_DIR.length() + 1;
        String fileName = filepath.substring(indexOfFiles);
        String extension = FilenameUtils.getExtension(fileName);
        InputStream inputStream = null;
        try {
            inputStream = contentResource.getContentStream();
            switch(extension) {
                case APIConstants.PDF_EXTENSION:
                    PDFParser pdfParser = new PDFParser(new RandomAccessBufferedFileInputStream(inputStream));
                    pdfParser.parse();
                    COSDocument cosDocument = pdfParser.getDocument();
                    PDFTextStripper stripper = new PDFTextStripper();
                    contentString = stripper.getText(new PDDocument(cosDocument));
                    break;
                case APIConstants.DOC_EXTENSION:
                    {
                        POIFSFileSystem pfs = new POIFSFileSystem(inputStream);
                        WordExtractor msWord2003Extractor = new WordExtractor(pfs);
                        contentString = msWord2003Extractor.getText();
                        break;
                    }
                case APIConstants.DOCX_EXTENSION:
                    XWPFDocument doc = new XWPFDocument(inputStream);
                    XWPFWordExtractor msWord2007Extractor = new XWPFWordExtractor(doc);
                    contentString = msWord2007Extractor.getText();
                    break;
                case APIConstants.XLS_EXTENSION:
                    {
                        POIFSFileSystem pfs = new POIFSFileSystem(inputStream);
                        ExcelExtractor extractor = new ExcelExtractor(pfs);
                        contentString = extractor.getText();
                        break;
                    }
                case APIConstants.XLSX_EXTENSION:
                    XSSFWorkbook xssfSheets = new XSSFWorkbook(inputStream);
                    XSSFExcelExtractor xssfExcelExtractor = new XSSFExcelExtractor(xssfSheets);
                    contentString = xssfExcelExtractor.getText();
                    break;
                case APIConstants.PPT_EXTENSION:
                    {
                        POIFSFileSystem fs = new POIFSFileSystem(inputStream);
                        PowerPointExtractor extractor = new PowerPointExtractor(fs);
                        contentString = extractor.getText();
                        break;
                    }
                case APIConstants.PPTX_EXTENSION:
                    XMLSlideShow xmlSlideShow = new XMLSlideShow(inputStream);
                    XSLFPowerPointExtractor xslfPowerPointExtractor = new XSLFPowerPointExtractor(xmlSlideShow);
                    contentString = xslfPowerPointExtractor.getText();
                    break;
                case APIConstants.TXT_EXTENSION:
                case APIConstants.WSDL_EXTENSION:
                case APIConstants.XML_DOC_EXTENSION:
                    BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
                    String line;
                    StringBuilder contentBuilder = new StringBuilder();
                    while ((line = reader.readLine()) != null) {
                        contentBuilder.append(line);
                    }
                    contentString = contentBuilder.toString();
                    break;
            }
        } finally {
            IOUtils.closeQuietly(inputStream);
        }
    } else if (Documentation.DocumentSourceType.INLINE.name().equals(sourceType)) {
        String fileName = ((ResourceImpl) documentResource).getName();
        String pathToDocFile = documentResource.getPath();
        String pathToContent = pathToDocFile.substring(0, pathToDocFile.lastIndexOf(fileName)) + APIConstants.INLINE_DOCUMENT_CONTENT_DIR + RegistryConstants.PATH_SEPARATOR + fileName;
        if (registry.resourceExists(pathToContent)) {
            Resource contentResource = registry.get(pathToContent);
            InputStream instream = null;
            BufferedReader reader = null;
            String line;
            try {
                instream = contentResource.getContentStream();
                reader = new BufferedReader(new InputStreamReader(instream));
                StringBuilder contentBuilder = new StringBuilder();
                while ((line = reader.readLine()) != null) {
                    contentBuilder.append(line);
                }
                contentString = contentBuilder.toString();
            } finally {
                if (reader != null) {
                    IOUtils.closeQuietly(reader);
                }
            }
        }
    }
    return contentString;
}

Example 10 with ExcelExtractor

use of org.apache.poi.hssf.extractor.ExcelExtractor in project poi by apache.

the class OLE2ExtractorFactory method getEmbededDocsTextExtractors.

/**
     * Returns an array of text extractors, one for each of
     *  the embedded documents in the file (if there are any).
     * If there are no embedded documents, you'll get back an
     *  empty array. Otherwise, you'll get one open
     *  {@link POITextExtractor} for each embedded file.
     */
public static POITextExtractor[] getEmbededDocsTextExtractors(POIOLE2TextExtractor ext) throws IOException {
    // All the embedded directories we spotted
    List<Entry> dirs = new ArrayList<Entry>();
    // For anything else not directly held in as a POIFS directory
    List<InputStream> nonPOIFS = new ArrayList<InputStream>();
    // Find all the embedded directories
    DirectoryEntry root = ext.getRoot();
    if (root == null) {
        throw new IllegalStateException("The extractor didn't know which POIFS it came from!");
    }
    if (ext instanceof ExcelExtractor) {
        // These are in MBD... under the root
        Iterator<Entry> it = root.getEntries();
        while (it.hasNext()) {
            Entry entry = it.next();
            if (entry.getName().startsWith("MBD")) {
                dirs.add(entry);
            }
        }
    } else {
        // Ask Scratchpad, or fail trying
        Class<?> cls = getScratchpadClass();
        try {
            Method m = cls.getDeclaredMethod("identifyEmbeddedResources", POIOLE2TextExtractor.class, List.class, List.class);
            m.invoke(null, ext, dirs, nonPOIFS);
        } catch (Exception e) {
            throw new IllegalArgumentException("Error checking for Scratchpad embedded resources", e);
        }
    }
    // Create the extractors
    if (dirs.size() == 0 && nonPOIFS.size() == 0) {
        return new POITextExtractor[0];
    }
    ArrayList<POITextExtractor> e = new ArrayList<POITextExtractor>();
    for (Entry dir : dirs) {
        e.add(createExtractor((DirectoryNode) dir));
    }
    for (InputStream nonPOIF : nonPOIFS) {
        try {
            e.add(createExtractor(nonPOIF));
        } catch (IllegalArgumentException ie) {
            // Ignore, just means it didn't contain
            //  a format we support as yet
            LOGGER.log(POILogger.WARN, ie);
        } catch (Exception xe) {
            // Ignore, invalid format
            LOGGER.log(POILogger.WARN, xe);
        }
    }
    return e.toArray(new POITextExtractor[e.size()]);
}