if (logger.isInfoEnabled()) {
                logger.info("Use a default encoding: " + encoding, e);
            }
        } finally {
            try {
                bis.reset();
            } catch (final IOException e) {
                throw new ExtractException(e);
            }
        }

        return encoding;
    }

    /**

            }
        }
        return requestDataList;
    }

    /**
     * Stores the response data content in the result data.
     *
     * @param responseData the response data containing the content
     * @param resultData the result data to store the content in
     * @throws CrawlerSystemException if storing data fails
     */

 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>
 *   <li>Text extraction from PDF pages</li>
 *   <li>Embedded document extraction</li>
 *   <li>Annotation extraction (file attachments)</li>
 *   <li>Metadata extraction</li>

            xpathEntityTransformer.setDataClass(TestEntity.class);
        }
    }

    public void test_storeData() throws Exception {
        final String result = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\"><list><item>タイトル</item></list></field>\n"//

        sitemapsLocal.set(sitemaps);
    }

    /**
     * Removes sitemaps from the thread-local storage and returns them.
     * @return An array of sitemap URLs, or null if none were present.
     */
    public String[] removeSitemaps() {
        final String[] sitemaps = sitemapsLocal.get();
        if (sitemaps != null) {
            sitemapsLocal.remove();
        }
        return sitemaps;

    <alias type="application/x-pdf"/>
    <acronym>PDF</acronym>
    <_comment>Portable Document Format</_comment>
    <tika:link>http://en.wikipedia.org/wiki/PDF</tika:link>
    <tika:link>http://www.adobe.com/devnet/pdf/pdf_reference_archive.html</tika:link>
    <tika:uti>com.adobe.pdf</tika:uti>
    <magic priority="50">
      <!-- Normally just %PDF- -->
      <match value="%PDF-" type="string" offset="0"/>

      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all

        protected T get() {
            return instance;
        }

        /**
         * Destroys the component by calling any @PreDestroy annotated methods
         * and the destroyer function if present.
         */
        protected void destroy() {
            final BeanDesc beanDesc = BeanDescFactory.getBeanDesc(instance.getClass());
            for (final String methodName : beanDesc.getMethodNames()) {

        ResponseData responseData = new ResponseData();
        responseData.setUrl("http://example.com");

        // Multiple calls should return same result
        boolean firstResult = rule.match(responseData);
        boolean secondResult = rule.match(responseData);
        boolean thirdResult = rule.match(responseData);

        assertEquals(firstResult, secondResult);

    }

    /**
     * Service for managing URL queues during crawling.
     */
    @Resource
    protected UrlQueueService<UrlQueue<?>> urlQueueService;

    /**
     * Service for managing access result data.
     */
    @Resource
    protected DataService<AccessResult<?>> dataService;

    /**
     * Container for managing crawler components.
     */
    @Resource