整体思路:Sax解析是将xml文档按Stream读入,一点一点的解析,不像Dom解析那样把文档全部加载到内存中,因此更适合实际情况的使用。Sax解析需要继承DefaultHandler,重写其4个方法(startDocument、startElement、endElement、characters),分别用于处理xml的ElementNode(<>或</>)和TextNode(字符)。下面看一个例子:此程序将原本的xml文件中各个元素标签解析成对应的TagBean实例,每对标签会被解析成一个实例,并且按树状存储标签之间的关系。因为我的目的是要解析Spring IoC的配置信息,所以4个方法的处理都是基于Spring IoC配置规则而实现的,当你们解析特定的xml文档时,只要修改这4个方法的解析规则即可。
TagBean的代码:
1 public class TagBean { 2 private String name; 3 private Map<String,String> attrList = null; 4 private ArrayList<TagBean> childList = new ArrayList<TagBean>(); 5 6 public void print(int count){ 7 for(int i = 0; i < count; i++){ 8 System.out.print(" "); 9 } 10 System.out.print(name+":"); 11 if(attrList != null){ 12 Iterator<String> keySetItr = attrList.keySet().iterator(); 13 while(keySetItr.hasNext()){ 14 String key = keySetItr.next(); 15 System.out.print(key +"--"+attrList.get(key)+"\t"); 16 } 17 System.out.println(); 18 }else{ 19 System.out.println(); 20 } 21 if(childList.size() > 0){ 22 int newCount = ++count; 23 for(TagBean temp : childList){ 24 temp.print(newCount); 25 } 26 }else{ 27 return; 28 } 29 } 30 31 public String getName() { 32 return name; 33 } 34 public void setName(String name) { 35 this.name = name; 36 } 37 public Map<String, String> getAttrList() { 38 if(attrList == null){ 39 attrList = new HashMap<String,String>(); 40 } 41 return attrList; 42 } 43 public void setAttrList(Map<String, String> attrList) { 44 this.attrList = attrList; 45 } 46 public ArrayList<TagBean> getChildList() { 47 return childList; 48 } 49 public void setChildList(TagBean childTag){ 50 this.childList.add(childTag); 51 } 52 53 }
解析服务的代码:
1 public class SaxParsingService extends DefaultHandler{ 2 private ArrayList<TagBean> tagList = null; 3 private TagBean tag = null; 5 private Stack<String> tagNameStack = null;//标记当前在处理的tag的隶属关系,遇到<>时入栈,遇到 </>时出栈 6 private Stack<TagBean> tagBeanStack = null; 7 private TagBean rootTag = null; 8 9 public TagBean getRootTag(InputStream xmlStream) throws Exception{ 10 //获取sax分析器 11 SAXParserFactory factory = SAXParserFactory.newInstance(); 12 SAXParser parser = factory.newSAXParser(); 13 //根据具体程序要求进行分析 14 SaxParsingService handler = new SaxParsingService(); 15 parser.parse(xmlStream, handler); //给分析器传入文件路径和分析规则 16 return handler.getRootTag(); //分析结束,获得信息 17 } 18 19 public ArrayList<TagBean> getTagList(){ 20 return tagList; 21 } 22 23 @Override //当文件解析开始时,会调用此函数 24 public void startDocument() throws SAXException { 25 tagList = new ArrayList<TagBean>(); 26 tagNameStack = new Stack<String>(); 27 tagBeanStack = new Stack<TagBean>(); 28 } 29 30 @Override //当碰到ElementNode时(如<books>),会调用此方法 31 public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException { 32 //System.out.println(qName+" start"); 33 tagNameStack.push(qName); 34 35 tag = new TagBean(); 36 tag.setName(qName); 37 38 //存储标签的属性信息 39 int index = attributes.getLength(); 40 if(index > 0){ 41 Map<String,String> attrList = new HashMap<String,String>(); 42 for(int i = 0 ; i < index ; i++ ){ 43 attrList.put(attributes.getQName(i),attributes.getValue(i)); 44 } 45 tag.setAttrList(attrList); 46 } 47 48 //将正在解析的节点名称赋给preTag 49 //preTag = qName; 50 51 //处理子标签问题 52 tagBeanStack.push(tag); 53 54 //保存beans的引用 55 if("beans".equals(qName)){ 56 rootTag = tag; 57 } 58 } 59 60 @Override //当遇到</>时调用此方法 61 public void endElement(String uri, String localName, String qName) throws SAXException { 62 //System.out.println(qName+" end"); 63 64 //处理了</>后,需要弹栈,并且构建子标签与父标签的关系 65 tagNameStack.pop(); 66 tag = tagBeanStack.pop(); 67 if(!tag.getName().equals("beans")){ 68 tagBeanStack.peek().setChildList(tag); 69 } 70 71 //preTag = null; 72 } 73 74 @Override //当遇到TextNode时调用,比如空格、值 75 public void characters(char[] ch, int start, int length) throws SAXException { 76 //System.out.println("char here"); 77 String content = new String(ch,start,length); 78 content = content.trim(); 79 80 if(content.length() > 0){ 81 tagNameStack.peek(); 82 tag = tagBeanStack.peek(); 83 tag.getAttrList().put(tagNameStack.peek(), content); 84 } 85 86 } 87 88 public TagBean getRootTag(){ 89 return this.rootTag; 90 } 91 }
程序入口,Main类:
1 public class Main { 2 public void testSAX() throws Throwable{ 3 SaxParsingService sax; 4 InputStream input = null; 5 try { 6 sax = new SaxParsingService(); 7 input = this.getClass().getClassLoader().getResourceAsStream(“test.xml”); 8 9 //解析input的xml文件,存储成树结构的tag链 10 TagBean rootTag = sax.getRootTag(input); 11 12 //输出解析后存储的标签树结构 13 rootTag.print(0); 14 } catch (Exception e) { 15 e.printStackTrace(); 16 } finally{ 17 input.close(); 18 } 19 } 20 public static void main(String[] args) throws Throwable { 21 new Main().testSAX(); 22 } 23 }
需要解析的文档:
1 <?xml version="1.0" encoding="UTF-8"?> 2 <beans 3 xmlns="http://www.springframework.org/schema/beans" 4 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" 5 xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-3.2.xsd"> 6 <bean id = "beanB" class = "org.beans.BeanB"> 7 <property name = "ba"> 8 <ref bean = "beanA"/> 9 </property> 10 <property name = "content"> 11 <value>There is no problem!</value> 12 </property> 13 <property name="bc" ref="beanC"/> 14 <property name="listRef"> 15 <list> 16 <value>First</value> 17 <value>Second</value> 18 </list> 19 </property> 20 <property name="listBeanRef"> 21 <list> 22 <ref bean = "beanA1"/> 23 <ref bean = "beanA2"/> 24 </list> 25 </property> 26 <property name="max" value="15" /> 27 <property name = "valueProps"> 28 <props> 29 <prop key = "strValueKey1">something1</prop> 30 <prop key = "strValueKey2">something2</prop> 31 </props> 32 </property> 33 <property name="mapRef"> 34 <map> 35 <entry> 36 <key> 37 <value>key1</value> 38 </key> 39 <value>v1</value> 40 </entry> 41 <entry key="key2"> 42 <value>v2</value> 43 </entry> 44 <entry key="key3" value="v3"/> 45 </map> 46 </property> 47 </bean> 48 <bean id = "beanA" class = "org.beans.BeanA"/> 49 <bean id = "beanC" class = "org.beans.BeanC"> 50 <constructor-arg > 51 <value>11</value> 52 </constructor-arg> 53 <constructor-arg> 54 <ref bean = "beanA3"/> 55 </constructor-arg> 56 </bean> 57 <bean id = "beanA1" class = "org.beans.BeanA"> 58 <constructor-arg index = "1" value = "22"/> 59 <constructor-arg index = "0" ref = "beanA4"/> 60 </bean> 61 <bean id = "beanA2" class = "org.beans.BeanA"> 62 <constructor-arg index = "1" > 63 <value>33</value> 64 </constructor-arg> 65 <constructor-arg ref = "beanA4"/> 66 <constructor-arg> 67 <value>44</value> 68 </constructor-arg> 69 <constructor-arg index = "0" value = "55"/> 70 </bean> 71 </beans>
解析后,调用rootTag的print方法,打印的树状数据结构:
beans:xmlns:xsi--http://www.w3.org/2001/XMLSchema-instance xmlns--http://www.springframework.org/schema/beans xsi:schemaLocation--http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-3.2.xsd
bean:id--beanB class--org.beans.BeanB
property:name--ba
ref:bean--beanA
property:name--content
value:value--There is no problem!
property:ref--beanC name--bc
property:name--listRef
list:
value:value--First
value:value--Second
property:name--listBeanRef
list:
ref:bean--beanA1
ref:bean--beanA2
property:name--max value--15
property:name--valueProps
props:
prop:prop--something1 key--strValueKey1
prop:prop--something2 key--strValueKey2
property:name--mapRef
map:
entry:
key:
value:value--key1
value:value--v1
entry:key--key2
value:value--v2
entry:value--v3 key--key3
bean:id--beanA class--org.beans.BeanA
bean:id--beanC class--org.beans.BeanC
constructor-arg:
value:value--11
constructor-arg:
ref:bean--beanA3
bean:id--beanA1 class--org.beans.BeanA
constructor-arg:index--1 value--22
constructor-arg:ref--beanA4 index--0
bean:id--beanA2 class--org.beans.BeanA
constructor-arg:index--1
value:value--33
constructor-arg:ref--beanA4
constructor-arg:
value:value--44
constructor-arg:index--0 value--55
如有疑问,可留言沟通~