Java XMLStreamReader2.getText方法代码示例

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
public void testTextStreaming()
    throws IOException, XMLStreamException
{
    String CONTENT_IN =
        "Some content\nthat will be "
        +""streamed" & sliced"
        +" and\nprocessed...";
        ;
    String CONTENT_OUT = 
        "Some content\nthat will be "
        +"\"streamed\" & sliced"
        +" and\nprocessed...";
        ;
    /* Let's also add trailing CDATA, to ensure no coalescing is done
     * when not requested
     */
    String XML = "<root>" + CONTENT_IN + "<![CDATA[cdata]]></root>";
    XMLStreamReader2 sr = getReader(XML, false);
    assertTokenType(START_ELEMENT, sr.next());
    assertTokenType(CHARACTERS, sr.next());
    StringWriter sw = new StringWriter();
    sr.getText(sw, false);
    String act = sw.toString();
    if (!act.equals(CONTENT_OUT)) {
        if (CONTENT_OUT.startsWith(act)) {
            fail("Streaming text accessors returned partial match; first "
                 +act.length()+" chars of the expected "
                 +CONTENT_OUT.length()+" chars");
        }
        fail("Content accessed using streaming text accessor (len "
                 +act.length()+"; exp "+CONTENT_OUT.length()+" chars) wrong: "
             +"expected ["+CONTENT_OUT+"], got ["+act+"]");
    }

    // And should get the following CDATA, then:
    assertTokenType(CDATA, sr.next());
    // and then closing element; let's not check CDATA contents here
    assertTokenType(END_ELEMENT, sr.next());
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
public void testCDataStreaming()
    throws IOException, XMLStreamException
{
    String CONTENT_INOUT =
        "Some content\nthat will be stored in a\n"
        +"CDATA <yes!> Block <[*]>\n"
        +" yet not be split in any way...."
        ;
    /* Let's also add trailing text, to ensure no coalescing is done
     * when not requested
     */
    String XML = "<root><![CDATA[" + CONTENT_INOUT + "]]>some text!</root>";
    XMLStreamReader2 sr = getReader(XML, false);
    assertTokenType(START_ELEMENT, sr.next());
    assertTokenType(CDATA, sr.next());
    StringWriter sw = new StringWriter();
    sr.getText(sw, false);
    String act = sw.toString();
    if (!act.equals(CONTENT_INOUT)) {
        if (CONTENT_INOUT.startsWith(act)) {
            fail("Streaming text accessors returned partial match; first "
                 +act.length()+" chars of the expected "
                 +CONTENT_INOUT.length()+" chars");
        }
        fail("Content accessed using streaming text accessor (len "
                 +act.length()+"; exp "+CONTENT_INOUT.length()+" chars) wrong: "
             +"expected ["+CONTENT_INOUT+"], got ["+act+"]");
    }

    // And should get the following CHARACTERS then:
    assertTokenType(CHARACTERS, sr.next());
    // and then closing element; let's not check text contents here
    assertTokenType(END_ELEMENT, sr.next());
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
/**
 * Let's also ensure that coalescing still works ok with streaming
 * as well...
 */
public void testCoalescingStreaming()
    throws IOException, XMLStreamException
{
    String CONTENT_IN1 =
        "First text\n<![CDATA[ and ]]> cdata <![CDATA[]]><![CDATA[...]]>"
        ;
    String CONTENT_OUT1 = "First text\n and  cdata ...";
    String CONTENT_IN2 =
        "<![CDATA[Then CDATA]]> and text<![CDATA[...\n]]>neat-o<![CDATA[]]>!";
    ;
    String CONTENT_OUT2 = "Then CDATA and text...\nneat-o!";

    for (int i = 0; i < 2; ++i) {
        boolean first = (i == 0);
        String XML = "<root>" + (first ? CONTENT_IN1 : CONTENT_IN2) + "</root>";
        XMLStreamReader2 sr = getReader(XML, true);
        assertTokenType(START_ELEMENT, sr.next());
        assertTokenType(CHARACTERS, sr.next());
        StringWriter sw = new StringWriter();
        sr.getText(sw, false);
        String act = sw.toString();
        String exp = first ? CONTENT_OUT1 : CONTENT_OUT2;
        if (!act.equals(exp)) {
            if (exp.startsWith(act)) {
                fail("Streaming text accessors returned partial match; first "
                     +act.length()+" chars of the expected "
                     +exp.length()+" chars");
            }
            fail("Content accessed using streaming text accessor (len "
                 +act.length()+"; exp "+exp.length()+" chars) wrong: "
                 +"expected ["+exp+"], got ["+act+"]");
        }
        // and then closing element
        assertTokenType(END_ELEMENT, sr.next());
    }
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
private FeedContent parseContentElement(XMLStreamReader2 xmlReader) throws ParseFeedException, XMLStreamException {
	//in content element
	String encoding = xmlReader.getAttributeValue("", XML_CONTENT_ENCODING);
	while (xmlReader.hasNext()) {
		xmlReader.next();
		if (xmlReader.getEventType() == XMLStreamConstants.CHARACTERS || xmlReader.getEventType() == XMLStreamConstants.CDATA) {
			File temp = null;
			try {
				temp = File.createTempFile("constellio-feedprocessor", ".bin");
				FileOutputStream fos = null;
				try {
					fos = new FileOutputStream(temp);
					Writer writer = new OutputStreamWriter(new BufferedOutputStream(fos));
					xmlReader.getText(writer, false);
					writer.flush();
				} finally {
					IOUtils.closeQuietly(fos);
				}
				FeedContent content = new FeedContentImpl(temp, encoding);
				
				return content;
			} catch (Exception e) {
				FileUtils.deleteQuietly(temp);
				e.printStackTrace();
			}
		} 
		if (xmlReader.getEventType() == XMLStreamConstants.END_ELEMENT) {
			if (XML_CONTENT.equals(xmlReader.getLocalName())) {
				break;
			}
		}
	}
	return null;
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
private String getText(XMLStreamReader2 reader) {
    String text = reader.getText();
    text = trim(text);
    return text;
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
/**
 * Get the oai:resumptionToken from the response
 * 
 * @return the oai:resumptionToken value
 * @throws TransformerException
 * @throws NoSuchFieldException
 */
public String getResumptionToken()
throws TransformerException, NoSuchFieldException, ParserConfigurationException, SAXException, IOException, XMLStreamException {
    String schemaLocation = getSchemaLocation();
    if (schemaLocation.indexOf(SCHEMA_LOCATION_V2_0) != -1) {
        if (hasDocument())
            return getSingleString("/oai20:OAI-PMH/oai20:ListRecords/oai20:resumptionToken");
        String token = null;
        XMLInputFactory2 xmlif = (XMLInputFactory2) XMLInputFactory2.newInstance();
        xmlif.configureForConvenience();
        XMLStreamReader2 xmlr = (XMLStreamReader2) xmlif.createXMLStreamReader(getStream());
        int state = 1; // 1:START 2:FOUND 0:STOP -1:ERROR
        while (state > 0) {
            int eventType = xmlr.getEventType();
            switch (state) {
                case 1://START
                    switch (eventType) {
                        case XMLEvent2.START_ELEMENT:
                            QName qn = xmlr.getName();
                            //logger.debug("finding token in the XML stream: node["+qn.getNamespaceURI()+"]["+qn.getLocalPart()+"]");
                            if (qn.getNamespaceURI().equals("http://www.openarchives.org/OAI/2.0/") && qn.getLocalPart().equals("resumptionToken"))
                                state = 2;//FOUND
                            break;
                    }
                    break;
                case 2://FOUND
                    switch (eventType) {
                        case XMLEvent2.CHARACTERS:
                            token = xmlr.getText();
                            state = 0;//STOP
                            break;
                        default:
                            state = -1;//ERROR
                            break;
                    }
                    break;
            }
            if (xmlr.hasNext())
                xmlr.next();
            else
                state = state == 1? 0: -1;// if START then STOP else ERROR
        }
        if (state < 0 || token == null) {
            logger.warn("couldn't find token in the XML stream!");
            return null;
        }
        logger.debug("found token["+token+"] in the XML stream!");
        return token;
    } else if (schemaLocation.indexOf(SCHEMA_LOCATION_V1_1_LIST_RECORDS) != -1) {
        return getSingleString("/oai11_ListRecords:ListRecords/oai11_ListRecords:resumptionToken");
    } else {
        throw new NoSuchFieldException(schemaLocation);
    }
}
 

import org.codehaus.stax2.XMLStreamReader2; //导入方法依赖的package包/类
@Override
 public void onCharacter(XMLStreamReader2 reader) {
     if (inSentence || inNamedEntity) {
         String text = reader.getText();
         //text = trim(text);
         if (isEmpty(text)) {
             return;
         }

List<String> tokens = null;
try {
	tokens = analyzer.tokenize(text, new Language(Language.FR, 1.0));
} catch(Exception e) {
	LOGGER.error("Tokenization failed", e);
}
if (tokens == null)
	return;
for(String token : tokens) {
	if (token.equals(" ") || token.equals("\t") || token.equals("\n") || token.equals("\r")) {
		continue;
	}
             if ((inNamedEntity) && (isNotEmpty(entityType))) {
                 sb.append(token).append("\t").append(translate(entityType, entitySubType));
                 /*if (isNotEmpty(entitySubType)) {
                     sb.append("\t").append(entitySubType);
                 }*/

                 if (isNotBlank(disambiguatedName)) {
                     sb.append("\t").append(disambiguatedName);
                 }

                 if (isNotBlank(uri)) {
                     sb.append("\t").append(uri);
                 }

                 sb.append("\n");
             } else {
                 sb.append(token).append("\t").append("O").append("\n");
             }
         }
     }


 }