org.apache.poi.hwpf.extractor.WordExtractor Java Examples

private static String readDoc (String filePath, InputStream is) throws Exception {
    String text= "";
    is = FileMagic.prepareToCheckMagic(is);
    try {
        if (FileMagic.valueOf(is) == FileMagic.OLE2) {
            WordExtractor ex = new WordExtractor(is);
            text = ex.getText();
            ex.close();
        } else if(FileMagic.valueOf(is) == FileMagic.OOXML) {
            XWPFDocument doc = new XWPFDocument(is);
            XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
            text = extractor.getText();
            extractor.close();
        }
    } catch (OfficeXmlFileException e) {
        logger.error(filePath, e);
    } finally {
        if (is != null) {
            is.close();
        }
    }
    return text;
}
 

private String microsoftWordDocumentToString(InputStream inputStream) throws IOException {
    String strRet;

    try (InputStream wordStream = new BufferedInputStream(inputStream)) {
        if (POIFSFileSystem.hasPOIFSHeader(wordStream)) {
            WordExtractor wordExtractor = new WordExtractor(wordStream);
            strRet = wordExtractor.getText();
            wordExtractor.close();
        } else {
            XWPFWordExtractor wordXExtractor = new XWPFWordExtractor(new XWPFDocument(wordStream));
            strRet = wordXExtractor.getText();
            wordXExtractor.close();
        }
    }

    return strRet;
}
 

public static String word2Text(File f) throws Exception {
    FileInputStream in = new FileInputStream (f);
    WordExtractor extractor = new WordExtractor(in);
    String str = extractor.getText();
    System.out.println("the result length is"+str.length());
    return str;
}
 

public static String Parse03(String FilePath) throws IOException{
    String text2003=null;
    InputStream is = null;
    try {
        is = new FileInputStream(new File(FilePath));
        WordExtractor ex = new WordExtractor(is);
        text2003 = ex.getText();

    } catch (Exception e) {
        e.printStackTrace();
    }finally{
        is.close();
    }
    return text2003;
}
 

/**
 * {@inheritDoc} Returns an empty reader if an error occured extracting text from
 * the word document.
 */
public String extractText(InputStream stream, String type, String encoding) throws IOException {
	try {
		return new WordExtractor(stream).getText();
	} catch (Exception e) {
		logger.warn("Failed to extract Word text content", e);
		throw new IOException(e.getMessage(), e);
	} finally {
		stream.close();
	}
}
 

@Override
public void readContent(ClassifiableContentIF cc, TextHandlerIF handler) {
  try {
    WordExtractor extractor = new WordExtractor(new BufferedInputStream(new ByteArrayInputStream(cc.getContent())));
    String s = extractor.getText();
    char[] c = s.toCharArray();
    handler.startRegion("document");
    handler.text(c, 0, c.length);
    handler.endRegion();
  } catch (Exception e) {
    throw new OntopiaRuntimeException(e);
  }    
}
 

/**
 * Extract metadata from Office Word
 */
public static OfficeMetadata officeExtractor(InputStream is, String mimeType) throws IOException {
	POIFSFileSystem fs = new POIFSFileSystem(is);
	OfficeMetadata md = new OfficeMetadata();
	SummaryInformation si = null;

	if (MimeTypeConfig.MIME_MS_WORD.equals(mimeType)) {
		si = new WordExtractor(fs).getSummaryInformation();
	} else if (MimeTypeConfig.MIME_MS_EXCEL.equals(mimeType)) {
		si = new ExcelExtractor(fs).getSummaryInformation();
	} else if (MimeTypeConfig.MIME_MS_POWERPOINT.equals(mimeType)) {
		si = new PowerPointExtractor(fs).getSummaryInformation();
	}

	if (si != null) {
		md.setTitle(si.getTitle());
		md.setSubject(si.getSubject());
		md.setAuthor(si.getAuthor());
		md.setLastAuthor(si.getLastAuthor());
		md.setKeywords(si.getKeywords());
		md.setComments(si.getComments());
		md.setTemplate(si.getTemplate());
		md.setRevNumber(si.getRevNumber());
		md.setApplicationName(si.getApplicationName());
		md.setEditTime(si.getEditTime());
		md.setPageCount(si.getPageCount());
		md.setWordCount(si.getWordCount());
		md.setCharCount(si.getCharCount());
		md.setSecurity(si.getSecurity());

		Calendar createDateTime = Calendar.getInstance();
		createDateTime.setTime(si.getCreateDateTime());
		md.setCreateDateTime(createDateTime);

		Calendar lastSaveDateTime = Calendar.getInstance();
		lastSaveDateTime.setTime(si.getLastSaveDateTime());
		md.setLastSaveDateTime(lastSaveDateTime);

		Calendar lastPrinted = Calendar.getInstance();
		lastPrinted.setTime(si.getLastPrinted());
		md.setLastPrinted(lastPrinted);
	}

	log.info("officeExtractor: {}", md);
	return md;
}
 

@Test
public void testShouldReturnIndexedDocumentWhenParameterCorrect() throws Exception {
    POIFSFileSystem poiFS = Mockito.mock(POIFSFileSystem.class);
    WordExtractor wordExtractor = Mockito.mock(WordExtractor.class);
    XWPFWordExtractor xwpfExtractor = Mockito.mock(XWPFWordExtractor.class);
    XWPFDocument xwpfDocument = Mockito.mock(XWPFDocument.class);
    PowerMockito.whenNew(POIFSFileSystem.class).withParameterTypes(InputStream.class)
            .withArguments(Mockito.any(InputStream.class))
            .thenThrow(OfficeXmlFileException.class)
            .thenReturn(poiFS)
            .thenThrow(APIManagementException.class);
    PowerMockito.whenNew(WordExtractor.class).withArguments(poiFS).thenReturn(wordExtractor);
    PowerMockito.whenNew(XWPFDocument.class).withParameterTypes(InputStream.class)
            .withArguments(Mockito.any())
            .thenReturn(xwpfDocument);
    PowerMockito.whenNew(XWPFWordExtractor.class).withArguments(xwpfDocument).thenReturn(xwpfExtractor);
    Mockito.when(wordExtractor.getText()).thenReturn("");
    Mockito.when(xwpfExtractor.getText()).thenReturn("");
    MSWordIndexer indexer = new MSWordIndexer();

    IndexDocument wordDoc = indexer.getIndexedDocument(file2Index);

    // should return the default media type when media type is not defined in file2Index
    if (!"application/pdf".equals(wordDoc.getFields().get(IndexingConstants.FIELD_MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

    // should return the media type we have set in the file2Index
    file2Index.mediaType = "text/html";
    wordDoc = indexer.getIndexedDocument(file2Index);
    if (!"text/html".equals(wordDoc.getFields().get(IndexingConstants.FIELD_MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

    // should return the media type we have set in the file2Index even if exception occurred while reading the file
    file2Index.mediaType = "text/html";
    wordDoc = indexer.getIndexedDocument(file2Index);
    if (!"text/html".equals(wordDoc.getFields().get(IndexingConstants.FIELD_MEDIA_TYPE).get(0))) {
        Assert.fail();
    }
}