Shinsuke Sugaya <******@****.***> 1444529815 +0900

Shinsuke Sugaya <******@****.***> 1444529815 +0900

        private final Node doc;

        public DefaultNamespaceContext(final Node doc) {
            this.doc = doc;
        }

        @Override
        public String getNamespaceURI(final String prefix) {
            return getNamespaceForPrefix(prefix, doc);
        }

        final String value = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\">タイトル</field>\n"//
                + "<field name=\"body\">第一章 第一節 ほげほげふがふが LINK 第2章 第2節</field>\n"//
                + "<field name=\"list\"><list><item>リスト1</item><item>リスト2</item><item>リスト3</item></list></field>\n"//
                + "</doc>";

        final String value = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\">タイトル</field>\n"//
                + "<field name=\"body\">第一章 第一節 ほげほげふがふが LINK 第2章 第2節</field>\n"//
                + "<field name=\"list\"><list><item>リスト1</item><item>リスト2</item><item>リスト3</item></list></field>\n"//
                + "</doc>";

            final PDDocument doc = document;
            final Set<Exception> exceptionSet = new HashSet<>();
            final Thread task = new Thread(() -> {
                try {
                    stripper.writeText(doc, writer);
                    extractEmbeddedDocuments(doc, writer);
                    extractAnnotations(doc, writer);
                } catch (final Exception e) {

    }

    public void test_getText_msword() {
        InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc");
        Map<String, String> params = new HashMap<String, String>();
        params.put("resourceName", "test.doc");
        ExtractData extractData = jodExtractor.getText(in, params);
        String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);

        assertContentType("text/html", "html/test1.shtml", "hoge.shtml");

        assertContentType("application/msword", "test/text1.txt", "hoge.doc");
        assertContentType("application/msword", "extractor/msoffice/test.doc", "hoge.doc");
        assertContentType("application/vnd.ms-excel", "test/text1.txt", "hoge.xls");
        assertContentType("application/vnd.ms-excel", "extractor/msoffice/test.xls", "hoge.xls");

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() {

        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"));
    }