使用 XPathFactory、SAXParserFactory 和 StAX (JSR-173) 读取 XML 文件。
使用 XPath 获取节点及其子数据。
public static void main(String[] args) {
String xml = "<soapenv:Body xmlns:soapenv='http://schemas.xmlsoap.org/soap/envelope/'>"
+ "<Yash:Data xmlns:Yash='http://Yash.stackoverflow.com/Services/Yash'>"
+ "<Yash:Tags>Java</Yash:Tags><Yash:Tags>Javascript</Yash:Tags><Yash:Tags>Selenium</Yash:Tags>"
+ "<Yash:Top>javascript</Yash:Top><Yash:User>Yash-777</Yash:User>"
+ "</Yash:Data></soapenv:Body>";
String jsonNameSpaces = "{'soapenv':'http://schemas.xmlsoap.org/soap/envelope/',"
+ "'Yash':'http://Yash.stackoverflow.com/Services/Yash'}";
String xpathExpression = "//Yash:Data";
Document doc1 = getDocument(false, "fileName", xml);
getNodesFromXpath(doc1, xpathExpression, jsonNameSpaces);
System.out.println("\n===== ***** =====");
Document doc2 = getDocument(true, "./books.xml", xml);
getNodesFromXpath(doc2, "//person", "{}");
}
static Document getDocument( boolean isFileName, String fileName, String xml ) {
Document doc = null;
try {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setValidating(false);
factory.setNamespaceAware(true);
factory.setIgnoringComments(true);
factory.setIgnoringElementContentWhitespace(true);
DocumentBuilder builder = factory.newDocumentBuilder();
if( isFileName ) {
File file = new File( fileName );
FileInputStream stream = new FileInputStream( file );
doc = builder.parse( stream );
} else {
doc = builder.parse( string2Source( xml ) );
}
} catch (SAXException | IOException e) {
e.printStackTrace();
} catch (ParserConfigurationException e) {
e.printStackTrace();
}
return doc;
}
/**
* ELEMENT_NODE[1],ATTRIBUTE_NODE[2],TEXT_NODE[3],CDATA_SECTION_NODE[4],
* ENTITY_REFERENCE_NODE[5],ENTITY_NODE[6],PROCESSING_INSTRUCTION_NODE[7],
* COMMENT_NODE[8],DOCUMENT_NODE[9],DOCUMENT_TYPE_NODE[10],DOCUMENT_FRAGMENT_NODE[11],NOTATION_NODE[12]
*/
public static void getNodesFromXpath( Document doc, String xpathExpression, String jsonNameSpaces ) {
try {
XPathFactory xpf = XPathFactory.newInstance();
XPath xpath = xpf.newXPath();
JSONObject namespaces = getJSONObjectNameSpaces(jsonNameSpaces);
if ( namespaces.size() > 0 ) {
NamespaceContextImpl nsContext = new NamespaceContextImpl();
Iterator<?> key = namespaces.keySet().iterator();
while (key.hasNext()) { // Apache WebServices Common Utilities
String pPrefix = key.next().toString();
String pURI = namespaces.get(pPrefix).toString();
nsContext.startPrefixMapping(pPrefix, pURI);
}
xpath.setNamespaceContext(nsContext );
}
XPathExpression compile = xpath.compile(xpathExpression);
NodeList nodeList = (NodeList) compile.evaluate(doc, XPathConstants.NODESET);
displayNodeList(nodeList);
} catch (XPathExpressionException e) {
e.printStackTrace();
}
}
static void displayNodeList( NodeList nodeList ) {
for (int i = 0; i < nodeList.getLength(); i++) {
Node node = nodeList.item(i);
String NodeName = node.getNodeName();
NodeList childNodes = node.getChildNodes();
if ( childNodes.getLength() > 1 ) {
for (int j = 0; j < childNodes.getLength(); j++) {
Node child = childNodes.item(j);
short nodeType = child.getNodeType();
if ( nodeType == 1 ) {
System.out.format( "\n\t Node Name:[%s], Text[%s] ", child.getNodeName(), child.getTextContent() );
}
}
} else {
System.out.format( "\n Node Name:[%s], Text[%s] ", NodeName, node.getTextContent() );
}
}
}
static InputSource string2Source( String str ) {
InputSource inputSource = new InputSource( new StringReader( str ) );
return inputSource;
}
static JSONObject getJSONObjectNameSpaces( String jsonNameSpaces ) {
if(jsonNameSpaces.indexOf("'") > -1) jsonNameSpaces = jsonNameSpaces.replace("'", "\"");
JSONParser parser = new JSONParser();
JSONObject namespaces = null;
try {
namespaces = (JSONObject) parser.parse(jsonNameSpaces);
} catch (ParseException e) {
e.printStackTrace();
}
return namespaces;
}
XML 文档
<?xml version="1.0" encoding="UTF-8"?>
<book>
<person>
<first>Yash</first>
<last>M</last>
<age>22</age>
</person>
<person>
<first>Bill</first>
<last>Gates</last>
<age>46</age>
</person>
<person>
<first>Steve</first>
<last>Jobs</last>
<age>40</age>
</person>
</book>
给定 XPathExpression 的输出：
String xpathExpression = "//person/first";
/*OutPut:
Node Name:[first], Text[Yash]
Node Name:[first], Text[Bill]
Node Name:[first], Text[Steve] */
String xpathExpression = "//person";
/*OutPut:
Node Name:[first], Text[Yash]
Node Name:[last], Text[M]
Node Name:[age], Text[22]
Node Name:[first], Text[Bill]
Node Name:[last], Text[Gates]
Node Name:[age], Text[46]
Node Name:[first], Text[Steve]
Node Name:[last], Text[Jobs]
Node Name:[age], Text[40] */
String xpathExpression = "//Yash:Data";
/*OutPut:
Node Name:[Yash:Tags], Text[Java]
Node Name:[Yash:Tags], Text[Javascript]
Node Name:[Yash:Tags], Text[Selenium]
Node Name:[Yash:Top], Text[javascript]
Node Name:[Yash:User], Text[Yash-777] */
See this link 用于我们自己实现的NamespaceContext