}

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

        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");
        fileTransformer.setChildUrlRuleMap(childUrlRuleMap);
    }

    protected void setBaseDir() throws IOException {
        fileTransformer.baseDir = File.createTempFile("crawler-", "");
        fileTransformer.baseDir.delete();

        for (int i = 0; i < readings.length; i++) {
            secondLine.put("reading_" + i, readings[i]);
        }

        secondLine.put("fields", item.getFields());
        secondLine.put("queryFreq", item.getQueryFreq());
        secondLine.put("docFreq", item.getDocFreq());
        secondLine.put("userBoost", item.getUserBoost());
        secondLine.put("score", (item.getQueryFreq() + item.getDocFreq()) * item.getUserBoost());

                .put("number_of_shards", 1)
                .put("number_of_replicas", 0)
                .put("analysis.analyzer.test_reading_analyzer.type", "custom")
                .put("analysis.analyzer.test_reading_analyzer.tokenizer", "standard")
                .put("analysis.analyzer.test_reading_term_analyzer.type", "custom")

         * args = new HashMap<>(); args.put("mode", "normal"); args.put("discardPunctuation", "false"); if
         * (Strings.isNullOrEmpty(path)) { args.put("userDictionary", path); } if (Strings.isNullOrEmpty(encoding)) {
         * args.put("userDictionaryEncoding", encoding); } final JapaneseTokenizerFactory japaneseTokenizerFactory = new

        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");
        htmlTransformer.setChildUrlRuleMap(childUrlRuleMap);
    }

    public void test_name() {
        assertEquals("htmlTransformer", htmlTransformer.getName());
    }

    public void test_transform() {

        java.util.Map<CrawlerStatus, String> statusMap = new java.util.HashMap<>();

        // Add entries
        statusMap.put(CrawlerStatus.INITIALIZING, "Starting up");
        statusMap.put(CrawlerStatus.RUNNING, "In progress");
        statusMap.put(CrawlerStatus.DONE, "Completed");

        // Verify entries
        assertEquals(3, statusMap.size());

        Map<String, String> analyzerMapping = new HashMap<>();
        analyzerMapping.put(FieldNames.ANALYZER_SETTINGS_TYPE, AnalyzerSettings.FIELD_ANALYZER_MAPPING);
        analyzerMapping.put(FieldNames.ANALYZER_SETTINGS_FIELD_NAME, field);
        analyzerMapping.put(FieldNames.ANALYZER_SETTINGS_CONTENTS_ANALYZER, "title_contents_analyzer");
        analyzerMapping.put(FieldNames.ANALYZER_SETTINGS_CONTENTS_READING_ANALYZER, "");
        runner.client()

        assertEquals("$INPUT_FILE", list.get(1));
        assertEquals("$OUTPUT_FILE", list.get(2));

        cmd = "test.sh $INPUT_FILE $OUTPUT_FILE";
        params.clear();
        params.put("$INPUT_FILE", "A");
        params.put("$OUTPUT_FILE", "B");
        list = extractor.parseCommand(cmd, params);
        assertEquals(3, list.size());
        assertEquals("test.sh", list.get(0));
        assertEquals("A", list.get(1));

        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        final Map<String, String> propertyMap = newHashMap();
        final Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");
        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");