java有一个静态方法U.formatXml(string)。生活的例子

import com.github.underscore.U;

public class MyClass {
    public static void main(String args[]) {
        String xml = "<tag><nested>hello</nested></tag>";

        System.out.println(U.formatXml("<?xml version=\"1.0\" encoding=\"UTF-8\"?><root>" + xml + "</root>"));
    }
}

输出:

<?xml version="1.0" encoding="UTF-8"?>
<root>
   <tag>
      <nested>hello</nested>
   </tag>
</root>

在提出我自己的解决方案之前，我应该先看看这一页!不管怎样，我使用Java递归来解析xml页面。此代码是完全自包含的，不依赖于第三方库。也. .它使用递归!

// you call this method passing in the xml text
public static void prettyPrint(String text){
    prettyPrint(text, 0);
}

// "index" corresponds to the number of levels of nesting and/or the number of tabs to print before printing the tag
public static void prettyPrint(String xmlText, int index){
    boolean foundTagStart = false;
    StringBuilder tagChars = new StringBuilder();
    String startTag = "";
    String endTag = "";
    String[] chars = xmlText.split("");
    // find the next start tag
    for(String ch : chars){
        if(ch.equalsIgnoreCase("<")){
            tagChars.append(ch);
            foundTagStart = true;
        } else if(ch.equalsIgnoreCase(">") && foundTagStart){
            startTag = tagChars.append(ch).toString();
            String tempTag = startTag;
            endTag = (tempTag.contains("\"") ? (tempTag.split(" ")[0] + ">") : tempTag).replace("<", "</"); // <startTag attr1=1 attr2=2> => </startTag>
            break;
        } else if(foundTagStart){
            tagChars.append(ch);
        }
    }
    // once start and end tag are calculated, print start tag, then content, then end tag
    if(foundTagStart){
        int startIndex = xmlText.indexOf(startTag);
        int endIndex = xmlText.indexOf(endTag);
        // handle if matching tags NOT found
        if((startIndex < 0) || (endIndex < 0)){
            if(startIndex < 0) {
                // no start tag found
                return;
            } else {
                // start tag found, no end tag found (handles single tags aka "<mytag/>" or "<?xml ...>")
                printTabs(index);
                System.out.println(startTag);
                // move on to the next tag
                // NOTE: "index" (not index+1) because next tag is on same level as this one
                prettyPrint(xmlText.substring(startIndex+startTag.length(), xmlText.length()), index);
                return;
            }
        // handle when matching tags found
        } else {
            String content = xmlText.substring(startIndex+startTag.length(), endIndex);
            boolean isTagContainsTags = content.contains("<"); // content contains tags
            printTabs(index);
            if(isTagContainsTags){ // ie: <tag1><tag2>stuff</tag2></tag1>
                System.out.println(startTag);
                prettyPrint(content, index+1); // "index+1" because "content" is nested
                printTabs(index);
            } else {
                System.out.print(startTag); // ie: <tag1>stuff</tag1> or <tag1></tag1>
                System.out.print(content);
            }
            System.out.println(endTag);
            int nextIndex = endIndex + endTag.length();
            if(xmlText.length() > nextIndex){ // if there are more tags on this level, continue
                prettyPrint(xmlText.substring(nextIndex, xmlText.length()), index);
            }
        }
    } else {
        System.out.print(xmlText);
    }
}

private static void printTabs(int counter){
    while(counter-- > 0){ 
        System.out.print("\t");
    }
}

基于这个答案的一个更简单的解决方案:

public static String prettyFormat(String input, int indent) {
    try {
        Source xmlInput = new StreamSource(new StringReader(input));
        StringWriter stringWriter = new StringWriter();
        StreamResult xmlOutput = new StreamResult(stringWriter);
        TransformerFactory transformerFactory = TransformerFactory.newInstance();
        transformerFactory.setAttribute("indent-number", indent);
        transformerFactory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "");
        transformerFactory.setAttribute(XMLConstants.ACCESS_EXTERNAL_STYLESHEET, "");
        Transformer transformer = transformerFactory.newTransformer(); 
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        transformer.transform(xmlInput, xmlOutput);
        return xmlOutput.getWriter().toString();
    } catch (Exception e) {
        throw new RuntimeException(e); // simple exception handling, please review it
    }
}

public static String prettyFormat(String input) {
    return prettyFormat(input, 2);
}

testcase:

prettyFormat("<root><child>aaa</child><child/></root>");

返回:

<?xml version="1.0" encoding="UTF-8"?>
<root>
  <child>aaa</child>
  <child/>
</root>

//忽略:原始编辑只需要在代码中的类名中缺少s。为了在SO上获得超过6个字符的验证，添加了多余的6个字符

除了max、codeskrap、David Easley和milosmns给出的答案外，还可以看看我的轻量级、高性能漂亮打印机库:xml-formatter

// construct lightweight, threadsafe, instance
PrettyPrinter prettyPrinter = PrettyPrinterBuilder.newPrettyPrinter().build();

StringBuilder buffer = new StringBuilder();
String xml = ..; // also works with char[] or Reader

if(prettyPrinter.process(xml, buffer)) {
     // valid XML, print buffer
} else {
     // invalid XML, print xml
}

有时，就像直接从文件运行模拟SOAP服务时，有一个漂亮的打印机也能处理已经打印好的XML是很好的:

PrettyPrinter prettyPrinter = PrettyPrinterBuilder.newPrettyPrinter().ignoreWhitespace().build();

正如一些人评论的那样，漂亮打印只是一种以更适合人类阅读的形式表示XML的方法——严格来说，XML数据中不应该有空格。

该库用于日志记录的漂亮打印，还包括用于过滤(子树移除/匿名化)和漂亮打印CDATA和Text节点中的XML的函数。

我用Scala看到了一个答案，所以这里有另一个用Groovy的答案，以防有人觉得有趣。默认缩进为2步，XmlNodePrinter构造函数也可以传递另一个值。

def xml = "<tag><nested>hello</nested></tag>"
def stringWriter = new StringWriter()
def node = new XmlParser().parseText(xml);
new XmlNodePrinter(new PrintWriter(stringWriter)).print(node)
println stringWriter.toString()

如果groovy jar在类路径中，则使用Java

  String xml = "<tag><nested>hello</nested></tag>";
  StringWriter stringWriter = new StringWriter();
  Node node = new XmlParser().parseText(xml);
  new XmlNodePrinter(new PrintWriter(stringWriter)).print(node);
  System.out.println(stringWriter.toString());

我在这里找到的针对Java 1.6+的解决方案不会重新格式化已经格式化的代码。对我有效的方法(重新格式化已经格式化的代码)如下。

import org.apache.xml.security.c14n.CanonicalizationException;
import org.apache.xml.security.c14n.Canonicalizer;
import org.apache.xml.security.c14n.InvalidCanonicalizerException;
import org.w3c.dom.Element;
import org.w3c.dom.bootstrap.DOMImplementationRegistry;
import org.w3c.dom.ls.DOMImplementationLS;
import org.w3c.dom.ls.LSSerializer;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerException;
import java.io.IOException;
import java.io.StringReader;

public class XmlUtils {
    public static String toCanonicalXml(String xml) throws InvalidCanonicalizerException, ParserConfigurationException, SAXException, CanonicalizationException, IOException {
        Canonicalizer canon = Canonicalizer.getInstance(Canonicalizer.ALGO_ID_C14N_OMIT_COMMENTS);
        byte canonXmlBytes[] = canon.canonicalize(xml.getBytes());
        return new String(canonXmlBytes);
    }

    public static String prettyFormat(String input) throws TransformerException, ParserConfigurationException, IOException, SAXException, InstantiationException, IllegalAccessException, ClassNotFoundException {
        InputSource src = new InputSource(new StringReader(input));
        Element document = DocumentBuilderFactory.newInstance().newDocumentBuilder().parse(src).getDocumentElement();
        Boolean keepDeclaration = input.startsWith("<?xml");
        DOMImplementationRegistry registry = DOMImplementationRegistry.newInstance();
        DOMImplementationLS impl = (DOMImplementationLS) registry.getDOMImplementation("LS");
        LSSerializer writer = impl.createLSSerializer();
        writer.getDomConfig().setParameter("format-pretty-print", Boolean.TRUE);
        writer.getDomConfig().setParameter("xml-declaration", keepDeclaration);
        return writer.writeToString(document);
    }
}

它是在单元测试中比较全字符串xml的好工具。

private void assertXMLEqual(String expected, String actual) throws ParserConfigurationException, IOException, SAXException, CanonicalizationException, InvalidCanonicalizerException, TransformerException, IllegalAccessException, ClassNotFoundException, InstantiationException {
    String canonicalExpected = prettyFormat(toCanonicalXml(expected));
    String canonicalActual = prettyFormat(toCanonicalXml(actual));
    assertEquals(canonicalExpected, canonicalActual);
}