import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {

        item.setTimestamp(ZonedDateTime.now());

        String bulkLine = SuggestUtil.createBulkLine("test_index", "_doc", item);
        assertNotNull(bulkLine);
        assertTrue(bulkLine.contains("test_index"));
        assertTrue(bulkLine.contains("_doc"));
        assertTrue(bulkLine.contains("test text"));
        assertTrue(bulkLine.contains("reading1"));

        msWordExtractor = container.getComponent("msWordExtractor");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc");
        final String content = msWordExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

                Map<String, Object> doc = documentReader.read();
                while (doc != null) {
                    if (Thread.currentThread().isInterrupted()) {
                        break;
                    }
                    docs.add(doc);
                    doc = documentReader.read();
                    if (doc == null || docs.size() >= docPerReq) {

     * Returns the result data header.
     * @return The result data header.
     */
    protected String getResultDataHeader() {
        // TODO: Support other XML header types
        return "<?xml version=\"1.0\"?>\n<doc>\n";
    }

    /**
     * Returns the result data body for a single value.
     * @param name The name of the field.
     * @param value The value of the field.
     * @return The result data body.
     */

    // public ResponseData call() throws Exception {
    // String[] urls =
    // new String[] {
    // "http://.../",
    // "http://.../test.pdf",
    // "http://.../test.doc",
    // "http://.../test.xls",
    // "http://.../test.ppt",
    // "http://.../test.txt", };
    // for (String url : urls) {
    // ResponseData responseData = httpClient.doGet(url);

        // Text Formats
        extensionMap.put("odt", "txt");
        extensionMap.put("ott", "txt");
        extensionMap.put("sxw", "txt");
        extensionMap.put("rtf", "txt");
        extensionMap.put("doc", "txt");
        extensionMap.put("docx", "txt");
        extensionMap.put("wpd", "txt");
        extensionMap.put("txt", "txt");
        extensionMap.put("html", "txt");
        // Spreadsheet Formats

    /** Field name for field analyzer mapping. */
    public static final String FIELD_ANALYZER_MAPPING = "fieldAnalyzerMapping";

    /** Document type name. */
    public static final String DOC_TYPE_NAME = "_doc";

    /** OpenSearch client. */
    protected final Client client;
    /** Analyzer settings index name. */
    protected final String analyzerSettingsIndexName;
    private final SuggestSettings settings;

				"application/vnd.epson.quickanime",
				"application/vnd.epson.salt",
				"application/vnd.epson.ssf",
				"application/vnd.ericsson.quickcall",
				"application/vnd.eszigno3+xml",
				"application/vnd.etsi.aoc+xml",
				"application/vnd.etsi.cug+xml",
				"application/vnd.etsi.iptvcommand+xml",
				"application/vnd.etsi.iptvdiscovery+xml",
				"application/vnd.etsi.iptvprofile+xml",
				"application/vnd.etsi.iptvsad-bc+xml",

    /**
     * Field name for creation time timestamp.
     */
    protected static final String CREATE_TIME = "createTime";

    /**
     * Document type.
     */
    protected static final String _DOC = "_doc";

    /**
     * Fields that store timestamps.
     */
    protected static final String[] timestampFields = { LAST_MODIFIED, CREATE_TIME };

    /**
     * Hash function for generating IDs.