PdfExtractor pdfExtractor = container.getComponent("pdfExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/pdf", pdfExtractor);
                });
        pdfExtractor = container.getComponent("pdfExtractor");

                + "<field name=\"false\">false</field>\n"//
                + "</doc>";

        final ResponseData responseData = new ResponseData();
        responseData.setResponseBody(ResourceUtil.getResourceAsFile("html/test1.html"), false);
        responseData.setCharSet(Constants.UTF_8);
        final ResultData resultData = new ResultData();
        xpathTransformer.storeData(responseData, resultData);

			<artifactId>tika-parser-font-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-html-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-image-module</artifactId>

        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
        extensionMap.put("ods", "tsv");
        extensionMap.put("ots", "tsv");
        extensionMap.put("sxc", "tsv");
        extensionMap.put("xls", "tsv");

:!0,processData:!0,async:!0,contentType:"application/x-www-form-urlencoded; charset=UTF-8",accepts:{"*":pc,text:"text/plain",html:"text/html",xml:"application/xml, text/xml",json:"application/json, text/javascript"},contents:{xml:/xml/,html:/html/,json:/json/},responseFields:{xml:"responseXML",text:"responseText",json:"responseJSON"},converters:{"* text":String,"text html":!0,"text json":n.parseJSON,"text xml":n.parseXML},flatOptions:{url:!0,context:!0}},ajaxSetup:function(a,b){return b?tc(tc(a,...

     */
    protected String getFilePath(final String url) {
        return url.replaceAll("/+", "/")
                .replace("./", "")
                .replace("../", "")
                .replaceAll("/$", "/index.html")
                .replaceAll("\\?", questionStr)
                .replaceAll(":", colonStr)
                .replaceAll(";", semicolonStr)
                .replaceAll("&", ampersandStr);
    }

    /**

                    if (Part.ATTACHMENT.equalsIgnoreCase(bodyPart.getDisposition())) {
                        appendAttachment(buf, bodyPart);
                    } else if (bodyPart.isMimeType("text/plain") || bodyPart.isMimeType("text/html")) {
                        buf.append(bodyPart.getContent().toString()).append(' ');
                    } else if (bodyPart.isMimeType("multipart/alternative") && bodyPart.getContent() instanceof Multipart) {

        responseData1.setUrl("http://www.example.com/page");
        responseData1.setMimeType("text/html");
        assertTrue(conditionalRule.match(responseData1));

        // Test non-matching URL
        ResponseData responseData2 = new ResponseData();
        responseData2.setUrl("http://other.com/page");
        responseData2.setMimeType("text/html");
        assertFalse(conditionalRule.match(responseData2));

■特定商取引法に基づく表示
http://www.jp.playstation.com/R/aboutstore

■よくあるお問い合わせ（FAQ）
http://www.jp.playstation.com/support/

■株式会社ソニー・コンピュータエンタテインメントの個人情報保護方針
http://www.jp.playstation.com/about/privacy.html

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                })//
        ;

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

    public void test_getTika_text() {