Question

我不确定如何在Stax中关闭此行为。当我解析文档时，我希望在解析它时捕获原始xml。

编辑以添加工作代码。

import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.io.Reader;

import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.events.Characters;
import javax.xml.stream.events.XMLEvent;

import org.apache.commons.lang.StringEscapeUtils;



public class Tester {
public static void main(String[] args) {


boolean output = false;


boolean pubDateMonthFlg = false;

boolean createDateFlg = false;
boolean createDateYrFlg = false;

String pubDateYear ="";
String pubDateMonth ="";
String createDateYear="";

StringBuilder k = new StringBuilder();
String file = "c:\\a.xml";
try{
    XMLInputFactory inputFactory = XMLInputFactory.newInstance();
    inputFactory.setProperty(XMLInputFactory.IS_COALESCING, Boolean.TRUE);
    inputFactory.setProperty(XMLInputFactory.IS_REPLACING_ENTITY_REFERENCES, Boolean.FALSE);
    inputFactory.setProperty(XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, Boolean.FALSE);

    Reader rd = new InputStreamReader(new FileInputStream(file),"UTF-8");   
    XMLEventReader reader = inputFactory.createXMLEventReader(rd);

    long start = 0;
    StringBuffer temp = new StringBuffer();
    while (reader.hasNext()) {
        XMLEvent event = (XMLEvent) reader.next();

        //makes sure the xml is welformed
        if (output == true) {
            if (isIgnoreEvent(event)) {
                //k.append(event.toString());
                k.append(event.toString());
            } else {
                k.append(StringEscapeUtils.escapeXml(event.toString()));
            }
        }






        if (event.getEventType() == event.START_ELEMENT) {
            if (event.asStartElement().getName().getLocalPart().equalsIgnoreCase("xml")) {
                k.append(event.toString());
                output = true;
            }

            if (event.asStartElement().getName().getLocalPart().equalsIgnoreCase("node")) {
                pubDateMonthFlg = true; 
            }
        }
        if (event.getEventType() == event.END_ELEMENT) {
            if (event.asEndElement().getName().getLocalPart().equalsIgnoreCase("xml")) {

                // the collected xml 
                System.out.println(k.toString());


                //reset  
                k.delete(0, k.length());

                output = false;
                createDateFlg = false;

            }
        }

        if (event.isCharacters()) {
            Characters characters = (Characters) event;
            if (!characters.isIgnorableWhiteSpace()&& !characters.isWhiteSpace()) {
                    //set the parent pubDateFlg to false 
                    if(pubDateMonthFlg){
                          pubDateMonthFlg = false;

                    }

                    //piiFlg = false;
                    output = true;
                }
            }

    }
    reader.close();


}
 catch (Exception e){
  e.printStackTrace();
 }

}

/**
* Ignore Start , End and comment Events
* @param event
* @return
*/
protected static boolean isIgnoreEvent(XMLEvent event){
   return (event.isStartElement() || event.isEndElement() || event.getEventType() == event.COMMENT) ? Boolean.TRUE : Boolean.FALSE;

}



}

这就是我用作样本

<xml>
   <node category="conclusion" value="reviewer's reason">blah blah blah!! </node>
</xml>

生成Stax

<xml>
   <node category='conclusion' value='reviewer's reason'>blah blah blah!! </node>
</xml>

结果当你尝试另一个解析器尝试摄取输出时，它就变成了一个非常好的文档。

任何帮助表示赞赏感谢

Answer 1

我不太明白你要做什么......但考虑使用XMLEventWriter而不是StringBuilder和toString。

为什么stax取代＆＃34;到＆＃39;在开始元素标签中

1 个答案: