Java-XML

1. XML

<?xml version="1.0" encoding="UTF-8"?><bookstore>  <bookid="1">    <name>冰与火之歌</name>    <author>乔治马丁</author>    <year>2014</year>    <price>89</price>  </book>  <bookid="2">    <name>安徒生童话</name>    <year>2004</year>    <price>77</price>    <language>English</language>  </book></bookstore>

2. XML 解析

2.1. 应用 DOM 方式解析 XML

DocumentBuilderFactorydbf =DocumentBuilderFactory.newInstance();try {DocumentBuilderdb =dbf.newDocumentBuilder();Documentdocument =db.parse("src/main/resources/books.xml");// ...}catch (ParserConfigurationException |SAXException |IOExceptione) {e.printStackTrace();}

System.out.println("DOM解析开始");NodeListbookList =document.getElementsByTagName("book");for (inti =0;i <bookList.getLength();i++) {NodebookNode =bookList.item(i);NamedNodeMapattrs =bookNode.getAttributes();System.out.println("第" + (i +1) +"本书共有" +attrs.getLength() +"个属性");// ...NodeListchildList =bookNode.getChildNodes();System.out.println("第" + (i +1) +"本书共有" +childList.getLength() +"个子节点");// ...}System.out.println("DOM解析结束");

publicinterfaceNode {publicstaticfinalshortELEMENT_NODE              =1;publicstaticfinalshortATTRIBUTE_NODE            =2;publicstaticfinalshortTEXT_NODE                 =3;// ...}

for (intj =0;j <attrs.getLength();j++) {NodeattrNode =attrs.item(j);System.out.println("第" + (j +1) +"个属性的" +"属性名：" +attrNode.getNodeName()            +"，属性值：" +attrNode.getNodeValue());}

ElementbookElement = (Element)bookList.item(i);System.out.println("属性名：id，属性值：" +bookElement.getAttribute("id"));

for (intj =0;j <childList.getLength();j++) {NodechildNode =childList.item(j);if (childNode !=null &&childNode.getNodeType() ==Node.ELEMENT_NODE) {System.out.println("第" + (j +1) +"个子节点的" +"节点名：" +childNode.getNodeName()                +"，子节点值：" +childNode.getFirstChild().getNodeValue());    }}

DOM解析开始一共有2本书第1本书共有1个属性第1个属性的属性名：id，属性值：1属性名：id，属性值：1第1本书共有9个子节点第2个子节点的节点名：name，子节点值：冰与火之歌第4个子节点的节点名：author，子节点值：乔治马丁第6个子节点的节点名：year，子节点值：2014第8个子节点的节点名：price，子节点值：89第2本书共有1个属性第1个属性的属性名：id，属性值：2属性名：id，属性值：2第2本书共有9个子节点第2个子节点的节点名：name，子节点值：安徒生童话第4个子节点的节点名：year，子节点值：2004第6个子节点的节点名：price，子节点值：77第8个子节点的节点名：language，子节点值：EnglishDOM解析结束

2.2. 应用 SAX 方式解析 XML

2.2.1. 输出解析内容

SAXParserFactoryspf =SAXParserFactory.newInstance();try {SAXParsersaxParser =spf.newSAXParser();SaxParserHandlerhandler =newSaxParserHandler();saxParser.parse("src/main/resources/books.xml",handler);}catch (ParserConfigurationException |SAXException |IOExceptione) {e.printStackTrace();}

staticclassSaxParserHandlerextendsDefaultHandler {intbookstoreIndex =0;intbookIndex =0;intchildIndex =0;// ...}

@OverridepublicvoidstartDocument()throwsSAXException {super.startDocument();System.out.println("SAX解析开始");}@OverridepublicvoidendDocument()throwsSAXException {super.endDocument();System.out.println("SAX解析结束");}

@OverridepublicvoidstartElement(Stringuri,StringlocalName,StringqName,Attributesattributes)throwsSAXException {super.startElement(uri,localName,qName,attributes);if ("bookstore".equals(qName)) {bookstoreIndex++;bookIndex =0;    }elseif ("book".equals(qName)) {bookIndex++;childIndex =0;System.out.println("第" +bookIndex +"本书共有" +attributes.getLength() +"个属性");for (inti =0;i <attributes.getLength();i++) {System.out.println("第" + (i +1) +"个属性的" +"属性名：" +attributes.getQName(i)                    +"，属性值：" +attributes.getValue(i));        }System.out.println("属性名：id，属性值：" +attributes.getValue("id"));    }else {childIndex++;System.out.print("第" +childIndex +"个子节点名：" +qName);    }}

@OverridepublicvoidendElement(Stringuri,StringlocalName,StringqName)throwsSAXException {super.endElement(uri,localName,qName);if ("bookstore".equals(qName)) {System.out.println("一共有" +bookIndex +"本书");    }elseif ("book".equals(qName)) {System.out.println("第" +bookIndex +"本书共有" +childIndex +"个子节点");    }}

@Overridepublicvoidcharacters(char[]ch,intstart,intlength)throwsSAXException {super.characters(ch,start,length);Stringvalue =newString(ch,start,length);if (!"".equals(value.trim())) {System.out.println("，节点值：" +value);    }}

SAX解析开始第1本书共有1个属性第1个属性的属性名：id，属性值：1属性名：id，属性值：1第1个子节点的节点名：name，节点值：冰与火之歌第2个子节点的节点名：author，节点值：乔治马丁第3个子节点的节点名：year，节点值：2014第4个子节点的节点名：price，节点值：89第1本书共有4个子节点第2本书共有1个属性第1个属性的属性名：id，属性值：2属性名：id，属性值：2第1个子节点的节点名：name，节点值：安徒生童话第2个子节点的节点名：year，节点值：2004第3个子节点的节点名：price，节点值：77第4个子节点的节点名：language，节点值：English第2本书共有4个子节点一共有2本书SAX解析结束

2.2.2. 使用 Java 对象保存

publicclassBook {privateStringid;privateStringname;privateStringauthor;privateStringyear;privateStringprice;privateStringlanguage;// ...}

staticclassSaxParserHandlerextendsDefaultHandler {List<Book>bookList =newArrayList<>();intbookIndex =0;Bookbook =null;StringcurrentValue =null;// ...}

@OverridepublicvoidstartElement(Stringuri,StringlocalName,StringqName,Attributesattributes)throwsSAXException {super.startElement(uri,localName,qName,attributes);if ("book".equals(qName)) {bookIndex++;book =newBook();for (inti =0;i <attributes.getLength();i++) {if ("id".equals(attributes.getQName(i))) {book.setId(attributes.getValue(i));            }        }    }}

@OverridepublicvoidendElement(Stringuri,StringlocalName,StringqName)throwsSAXException {super.endElement(uri,localName,qName);if ("book".equals(qName)) {bookList.add(book);book =null;    }elseif ("name".equals(qName)) {book.setName(currentValue);    }elseif ("author".equals(qName)) {book.setAuthor(currentValue);    }elseif ("year".equals(qName)) {book.setYear(currentValue);    }elseif ("price".equals(qName)) {book.setPrice(currentValue);    }elseif ("language".equals(qName)) {book.setLanguage(currentValue);    }}

@Overridepublicvoidcharacters(char[]ch,intstart,intlength)throwsSAXException {super.characters(ch,start,length);currentValue =newString(ch,start,length);}

Book{id='1',name='冰与火之歌',author='乔治马丁',year='2014',price='89',language='null'}Book{id='2',name='安徒生童话',author='null',year='2004',price='77',language='English'}

2.3. 应用 DOM4J 及 JDOM 方式解析 XML

2.3.1. 应用 JDOM 方式解析

SAXBuildersaxBuilder =newSAXBuilder();InputStreamin;try {in =newFileInputStream("src/main/resources/books.xml");InputStreamReaderisr =newInputStreamReader(in,StandardCharsets.UTF_8);Documentdocument =saxBuilder.build(isr);ElementrootElement =document.getRootElement();List<Element>bookList =rootElement.getChildren();// ...}catch (JDOMException |IOExceptione) {e.printStackTrace();}

System.out.println("JDOM解析开始");System.out.println("一共有" +bookList.size() +"本书");for (Elementbook :bookList) {List<Attribute>attributeList =book.getAttributes();System.out.println("第" + (bookList.indexOf(book) +1) +"本书共有"            +attributeList.size() +"个属性");// ...List<Element>childList =book.getChildren();System.out.println("第" + (bookList.indexOf(book) +1) +"本书共有"            +childList.size() +"个子节点");// ...}System.out.println("JDOM解析结束");

List<Attribute>attributeList =book.getAttributes();System.out.println("第" + (bookList.indexOf(book) +1) +"本书共有"        +attributeList.size() +"个属性");for (Attributeattr :attributeList) {System.out.println("第" + (attributeList.indexOf(attr) +1) +"个属性的" +"属性名：" +attr.getName()            +"，属性值：" +attr.getValue());}

System.out.println("属性名：id，属性值：" +book.getAttributeValue("id"));

for (Elementchild :childList) {System.out.println("第" + (childList.indexOf(child) +1) +"个子节点的" +"节点名：" +child.getName()            +"，子节点值：" +child.getValue());}

JDOM解析开始一共有2本书第1本书共有1个属性第1个属性的属性名：id，属性值：1属性名：id，属性值：1第1本书共有4个子节点第1个子节点的节点名：name，子节点值：冰与火之歌第2个子节点的节点名：author，子节点值：乔治马丁第3个子节点的节点名：year，子节点值：2014第4个子节点的节点名：price，子节点值：89第2本书共有1个属性第1个属性的属性名：id，属性值：2属性名：id，属性值：2第2本书共有4个子节点第1个子节点的节点名：name，子节点值：安徒生童话第2个子节点的节点名：year，子节点值：2004第3个子节点的节点名：price，子节点值：77第4个子节点的节点名：language，子节点值：EnglishJDOM解析结束

2.3.2. 使用 Java 对象保存

SAXBuildersaxBuilder =newSAXBuilder();InputStreamin;List<Book>bookEntityList =newArrayList<>();BookbookEntity =null;try {in =newFileInputStream("src/main/resources/books.xml");Documentdocument =saxBuilder.build(in);ElementrootElement =document.getRootElement();List<Element>bookList =rootElement.getChildren();for (Elementbook :bookList) {bookEntity =newBook();List<Attribute>attributeList =book.getAttributes();for (Attributeattr :attributeList) {if ("id".equals(attr.getName())) {bookEntity.setId(attr.getValue());            }        }List<Element>childList =book.getChildren();for (Elementchild :childList) {if ("name".equals(child.getName())) {bookEntity.setName(child.getValue());            }elseif ("author".equals(child.getName())) {bookEntity.setAuthor(child.getValue());            }elseif ("year".equals(child.getName())) {bookEntity.setYear(child.getValue());            }elseif ("price".equals(child.getName())) {bookEntity.setPrice(child.getValue());            }elseif ("language".equals(child.getName())) {bookEntity.setLanguage(child.getValue());            }        }bookEntityList.add(bookEntity);    }}catch (JDOMException |IOExceptione) {e.printStackTrace();}for (Bookbook :bookEntityList) {System.out.println(book);}

2.3.3. 乱码问题解决

<?xml version="1.0" encoding="ISO-8859-1"?><bookstore>  <bookid="1">    <name>冰与火之歌</name>    <author>乔治马丁</author>    <year>2014</year>    <price>89</price>  </book>  <bookid="2">    <name>安徒生童话</name>    <year>2004</year>    <price>77</price>    <language>English</language>  </book></bookstore>

in =newFileInputStream("src/main/resources/books2.xml");InputStreamReaderisr =newInputStreamReader(in,StandardCharsets.UTF_8);Documentdocument =saxBuilder.build(isr);

2.3.4. 应用 DOM4J 方式解析

SAXReaderreader =newSAXReader();intbookIndex =0;intattributeIndex;intchildIndex;try {Documentdocument =reader.read(newFile("src/main/resources/books.xml"));ElementbookStore =document.getRootElement();Iteratoriterator =bookStore.elementIterator();// ...}catch (DocumentExceptione) {e.printStackTrace();}

System.out.println("DOM4J解析开始");while (iterator.hasNext()) {bookIndex++;attributeIndex =0;childIndex =0;Elementbook = (Element)iterator.next();List<Attribute>bookAttrs =book.attributes();// ...System.out.println("第" +bookIndex +"本书共有" +attributeIndex +"个属性");Iteratoriterator2 =book.elementIterator();// ...System.out.println("第" +bookIndex +"本书共有" +childIndex +"个子节点");}System.out.println("一共有" +bookIndex +"本书");System.out.println("DOM4J解析结束");

for (Attributeattr :bookAttrs) {attributeIndex++;System.out.println("属性名：" +attr.getName()            +"，属性值：" +attr.getValue());}

while (iterator2.hasNext()) {childIndex++;ElementbookChild = (Element)iterator2.next();System.out.println("节点名：" +bookChild.getName()            +"，节点值：" +bookChild.getStringValue());}

DOM4J解析开始属性名：id，属性值：1第1本书共有1个属性节点名：name，节点值：冰与火之歌节点名：author，节点值：乔治马丁节点名：year，节点值：2014节点名：price，节点值：89第1本书共有4个子节点属性名：id，属性值：2第2本书共有1个属性节点名：name，节点值：安徒生童话节点名：year，节点值：2004节点名：price，节点值：77节点名：language，节点值：English第2本书共有4个子节点一共有2本书DOM4J解析结束

2.4. 四种 XML 解析方式比较

2.4.1. DOM

2.4.2. SAX

2.4.3. JDOM

2.4.4. DOM4J

3. XML 生成

3.1. 通过 DOM 方式生成 XML 文档

DocumentBuildergetDocumentBuilder() {DocumentBuilderFactorydbf =DocumentBuilderFactory.newInstance();DocumentBuilderdb =null;try {db =dbf.newDocumentBuilder();    }catch (ParserConfigurationExceptione) {e.printStackTrace();    }returndb;}

TransformergetTransformer() {TransformerFactorytff =TransformerFactory.newInstance();Transformertf =null;try {tf =tff.newTransformer();tf.setOutputProperty(OutputKeys.INDENT,"yes");    }catch (TransformerConfigurationExceptione) {e.printStackTrace();    }returntf;}

publicvoidcreateXml() {Documentdocument =getDocumentBuilder().newDocument();document.setXmlStandalone(true);Elementbookstore =document.createElement("bookstore");Elementbook =document.createElement("book");book.setAttribute("id","1");Elementname =document.createElement("name");name.setTextContent("小王子");book.appendChild(name);bookstore.appendChild(book);document.appendChild(bookstore);Transformertf =getTransformer();try {tf.transform(newDOMSource(document),newStreamResult(newFile("src/main/resources/books3.xml")        ));    }catch (TransformerExceptione) {e.printStackTrace();    }}

3.2. 通过 SAX 方式生成 XML 文档

TransformerHandlergetTransformerHandler() {SAXTransformerFactorytff = (SAXTransformerFactory)SAXTransformerFactory.newInstance();TransformerHandlerhandler =null;try {handler =tff.newTransformerHandler();    }catch (TransformerConfigurationExceptione) {e.printStackTrace();    }returnhandler;}

List<Book>bookList =parseXml();TransformerHandlerhandler =getTransformerHandler();Transformertf =handler.getTransformer();tf.setOutputProperty(OutputKeys.ENCODING,"UTF-8");tf.setOutputProperty(OutputKeys.INDENT,"yes");try {Filef =newFile("src/main/resources/books4.xml");if (!f.exists()) {f.createNewFile();    }Resultresult =newStreamResult(newFileOutputStream(f));handler.setResult(result);handler.startDocument();AttributesImplattr =newAttributesImpl();handler.startElement("","","bookstore",attr);for (Bookbook :bookList) {attr.clear();attr.addAttribute("","","id","","1");handler.startElement("","","book",attr);// ...handler.endElement("","","book");    }handler.endElement("","","bookstore");handler.endDocument();}catch (SAXException |IOExceptione) {e.printStackTrace();}

if (book.getAuthor() !=null && !"".equals(book.getAuthor().trim())) {attr.clear();handler.startElement("","","author",attr);handler.characters(book.getAuthor().toCharArray(),0,book.getAuthor().length());handler.endElement("","","author");}

3.3. 通过 JDOM 方式生成 XML 文档

Elementrss =newElement("rss");rss.setAttribute("version","2.0");Documentdocument =newDocument(rss);Elementchannel =newElement("channel");rss.addContent(channel);Elementtitle =newElement("title");title.setText("国内最新新闻");channel.addContent(title);Elementtitle2 =newElement("title2");title2.setText("<尖括号会自动转义>");channel.addContent(title2);Formatformat =Format.getCompactFormat();format.setIndent("");format.setEncoding("GBK");XMLOutputteroutput =newXMLOutputter(format);try {output.output(document,newFileOutputStream("src/main/resources/rssNews1.xml"));}catch (IOExceptione) {e.printStackTrace();}

3.4. 通过 DOM4J 方式生成 XML 文档

Documentdocument =DocumentHelper.createDocument();Elementrss =document.addElement("rss");rss.addAttribute("version","2.0");Elementchannel =rss.addElement("channel");Elementtitle =channel.addElement("title");title.setText("国内最新新闻");Elementtitle2 =channel.addElement("title2");title2.setText("<尖括号不会自动转义>");OutputFormatformat =OutputFormat.createPrettyPrint();format.setEncoding("GBK");Filefile =newFile("src/main/resources/rssNews2.xml");try {XMLWriterwriter =newXMLWriter(newFileOutputStream(file),format);writer.setEscapeText(false);writer.write(document);writer.close();}catch (IOExceptione) {e.printStackTrace();}

3.5. 四种 XML 生成方式比较