@Override
        public boolean removeRule(Rule rule) {
            return rules.remove(rule);
        }

        @Override
        public boolean hasRule(Rule rule) {
            return rules.contains(rule);
        }

        public List<Rule> getRules() {
            return new ArrayList<>(rules);
        }

        public void clearRules() {
            rules.clear();
        }
    }

            return keywords;
        }
        for (final TermQuery tq : termQueryList) {
            final String text = tq.getTerm().text();
            if (0 == text.length() || keywords.contains(text)) {
                continue;
            }
            keywords.add(text);
        }
        return keywords;
    }

    /**

                                org.codelibs.jcifs.smb.impl.SID.SID_FLAG_RESOLVE_SIDS);
                for (final SID child : children) {
                    if (!sidSet.contains(child)) {
                        processAllowedSIDs(file, child, sidSet);
                    }
                }
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {

                } catch (OpenSearchStatusException | IllegalStateException e) {
                    final String msg = e.getMessage();
                    if (StringUtil.isNotEmpty(msg) || msg.contains("index.analyze.max_token_count")) {
                        logger.warn("Failed to parse document. ", e);
                        return Stream.empty();
                    }
                    throw e;

        } else {
            hostUrl = url;
        }
        final String robotTxtUrl = hostUrl + "/robots.txt";

        // check url
        if (crawlerContext.getRobotsTxtUrlSet().contains(robotTxtUrl)) {
            if (logger.isDebugEnabled()) {
                logger.debug("{} is already visited.", robotTxtUrl);
            }
            return;
        }

        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.
     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.
     * @return An ExtractData object containing the filename as content.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

        String text = "ひらがな";
        String field = "content";

        List<String> results = converter.convert(text, field, "ja");

        assertNotNull(results);
        // Results should contain Katakana conversion
    }

    @Test
    public void testLangAnalyzerConverterInit() throws IOException {
        // Test inner class LangAnalyzerConverter init

     *
     * @param sourceMap The source map containing the date field.
     * @param name The name of the date field.
     * @return The Date object, or null if the field doesn't contain a valid date.
     */
    protected Date getDateFromSource(final Map<String, Object> sourceMap, final String name) {
        final Object obj = sourceMap.get(name);
        if (obj instanceof Date) {

   * Highly specific magic matches get a high priority
   * General magic matches which could trigger a false-positive need
     a low one
   * The priority for containers normally need to be higher than for
     the things they contain, so they don't accidently get detected
     as what's in them
   * For logic too complex to be expressed in a magic match, do the best
     you can here, then provide a Custom Detector for the rest
-->