凯文·哈肯森说: 但是，如果您知道您的XML字符串是有效的，并且您不想引起将字符串解析为DOM的内存开销，然后在DOM上运行转换以获得字符串—您可以通过字符解析进行一些老式的字符。在每个字符后插入换行符和空格，保持和缩进计数器(以确定空格的数量)，为每个<…>和递减你看到的每一个。”

同意了。这种方法要快得多，依赖关系也少得多。

示例解决方案:

/**
 * XML utils, including formatting.
 */
public class XmlUtils
{
  private static XmlFormatter formatter = new XmlFormatter(2, 80);

  public static String formatXml(String s)
  {
    return formatter.format(s, 0);
  }

  public static String formatXml(String s, int initialIndent)
  {
    return formatter.format(s, initialIndent);
  }

  private static class XmlFormatter
  {
    private int indentNumChars;
    private int lineLength;
    private boolean singleLine;

    public XmlFormatter(int indentNumChars, int lineLength)
    {
      this.indentNumChars = indentNumChars;
      this.lineLength = lineLength;
    }

    public synchronized String format(String s, int initialIndent)
    {
      int indent = initialIndent;
      StringBuilder sb = new StringBuilder();
      for (int i = 0; i < s.length(); i++)
      {
        char currentChar = s.charAt(i);
        if (currentChar == '<')
        {
          char nextChar = s.charAt(i + 1);
          if (nextChar == '/')
            indent -= indentNumChars;
          if (!singleLine)   // Don't indent before closing element if we're creating opening and closing elements on a single line.
            sb.append(buildWhitespace(indent));
          if (nextChar != '?' && nextChar != '!' && nextChar != '/')
            indent += indentNumChars;
          singleLine = false;  // Reset flag.
        }
        sb.append(currentChar);
        if (currentChar == '>')
        {
          if (s.charAt(i - 1) == '/')
          {
            indent -= indentNumChars;
            sb.append("\n");
          }
          else
          {
            int nextStartElementPos = s.indexOf('<', i);
            if (nextStartElementPos > i + 1)
            {
              String textBetweenElements = s.substring(i + 1, nextStartElementPos);

              // If the space between elements is solely newlines, let them through to preserve additional newlines in source document.
              if (textBetweenElements.replaceAll("\n", "").length() == 0)
              {
                sb.append(textBetweenElements + "\n");
              }
              // Put tags and text on a single line if the text is short.
              else if (textBetweenElements.length() <= lineLength * 0.5)
              {
                sb.append(textBetweenElements);
                singleLine = true;
              }
              // For larger amounts of text, wrap lines to a maximum line length.
              else
              {
                sb.append("\n" + lineWrap(textBetweenElements, lineLength, indent, null) + "\n");
              }
              i = nextStartElementPos - 1;
            }
            else
            {
              sb.append("\n");
            }
          }
        }
      }
      return sb.toString();
    }
  }

  private static String buildWhitespace(int numChars)
  {
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < numChars; i++)
      sb.append(" ");
    return sb.toString();
  }

  /**
   * Wraps the supplied text to the specified line length.
   * @lineLength the maximum length of each line in the returned string (not including indent if specified).
   * @indent optional number of whitespace characters to prepend to each line before the text.
   * @linePrefix optional string to append to the indent (before the text).
   * @returns the supplied text wrapped so that no line exceeds the specified line length + indent, optionally with
   * indent and prefix applied to each line.
   */
  private static String lineWrap(String s, int lineLength, Integer indent, String linePrefix)
  {
    if (s == null)
      return null;

    StringBuilder sb = new StringBuilder();
    int lineStartPos = 0;
    int lineEndPos;
    boolean firstLine = true;
    while(lineStartPos < s.length())
    {
      if (!firstLine)
        sb.append("\n");
      else
        firstLine = false;

      if (lineStartPos + lineLength > s.length())
        lineEndPos = s.length() - 1;
      else
      {
        lineEndPos = lineStartPos + lineLength - 1;
        while (lineEndPos > lineStartPos && (s.charAt(lineEndPos) != ' ' && s.charAt(lineEndPos) != '\t'))
          lineEndPos--;
      }
      sb.append(buildWhitespace(indent));
      if (linePrefix != null)
        sb.append(linePrefix);

      sb.append(s.substring(lineStartPos, lineEndPos + 1));
      lineStartPos = lineEndPos + 1;
    }
    return sb.toString();
  }

  // other utils removed for brevity
}

我过去使用org.dom4j.io.OutputFormat.createPrettyPrint()方法打印过

public String prettyPrint(final String xml){  

    if (StringUtils.isBlank(xml)) {
        throw new RuntimeException("xml was null or blank in prettyPrint()");
    }

    final StringWriter sw;

    try {
        final OutputFormat format = OutputFormat.createPrettyPrint();
        final org.dom4j.Document document = DocumentHelper.parseText(xml);
        sw = new StringWriter();
        final XMLWriter writer = new XMLWriter(sw, format);
        writer.write(document);
    }
    catch (Exception e) {
        throw new RuntimeException("Error pretty printing xml:\n" + xml, e);
    }
    return sw.toString();
}

有一个非常好的命令行XML实用程序叫做xmlstarlet(http://xmlstar.sourceforge.net/)，它可以做很多事情，很多人都在使用它。

您可以使用Runtime以编程方式执行此程序。然后读入格式化的输出文件。它具有比几行Java代码所能提供的更多选项和更好的错误报告。

下载xmlstarlet: http://sourceforge.net/project/showfiles.php?group_id=66612&package_id=64589

下面的代码工作得很好

import javax.xml.transform.OutputKeys;
import javax.xml.transform.Source;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.stream.StreamResult;
import javax.xml.transform.stream.StreamSource;

String formattedXml1 = prettyFormat("<root><child>aaa</child><child/></root>");

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

public static String prettyFormat(String input, String indent) {
    Source xmlInput = new StreamSource(new StringReader(input));
    StringWriter stringWriter = new StringWriter();
    try {
        TransformerFactory transformerFactory = TransformerFactory.newInstance();
        Transformer transformer = transformerFactory.newTransformer();
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", indent);
        transformer.transform(xmlInput, new StreamResult(stringWriter));

        String pretty = stringWriter.toString();
        pretty = pretty.replace("\r\n", "\n");
        return pretty;              
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

对于那些寻找快速和肮脏的解决方案的人——它不需要XML是100%有效的。例如，在REST / SOAP日志的情况下(你永远不知道其他人发送了什么;-))

我发现并改进了一个我在网上找到的代码剪辑，我认为这仍然是一个有效的可能的方法:

public static String prettyPrintXMLAsString(String xmlString) {
    /* Remove new lines */
    final String LINE_BREAK = "\n";
    xmlString = xmlString.replaceAll(LINE_BREAK, "");
    StringBuffer prettyPrintXml = new StringBuffer();
    /* Group the xml tags */
    Pattern pattern = Pattern.compile("(<[^/][^>]+>)?([^<]*)(</[^>]+>)?(<[^/][^>]+/>)?");
    Matcher matcher = pattern.matcher(xmlString);
    int tabCount = 0;
    while (matcher.find()) {
        String str1 = (null == matcher.group(1) || "null".equals(matcher.group())) ? "" : matcher.group(1);
        String str2 = (null == matcher.group(2) || "null".equals(matcher.group())) ? "" : matcher.group(2);
        String str3 = (null == matcher.group(3) || "null".equals(matcher.group())) ? "" : matcher.group(3);
        String str4 = (null == matcher.group(4) || "null".equals(matcher.group())) ? "" : matcher.group(4);

        if (matcher.group() != null && !matcher.group().trim().equals("")) {
            printTabs(tabCount, prettyPrintXml);
            if (!str1.equals("") && str3.equals("")) {
                ++tabCount;
            }
            if (str1.equals("") && !str3.equals("")) {
                --tabCount;
                prettyPrintXml.deleteCharAt(prettyPrintXml.length() - 1);
            }

            prettyPrintXml.append(str1);
            prettyPrintXml.append(str2);
            prettyPrintXml.append(str3);
            if (!str4.equals("")) {
                prettyPrintXml.append(LINE_BREAK);
                printTabs(tabCount, prettyPrintXml);
                prettyPrintXml.append(str4);
            }
            prettyPrintXml.append(LINE_BREAK);
        }
    }
    return prettyPrintXml.toString();
}

private static void printTabs(int count, StringBuffer stringBuffer) {
    for (int i = 0; i < count; i++) {
        stringBuffer.append("\t");
    }
}

public static void main(String[] args) {
    String x = new String(
            "<soap:Envelope xmlns:soap=\"http://schemas.xmlsoap.org/soap/envelope/\"><soap:Body><soap:Fault><faultcode>soap:Client</faultcode><faultstring>INVALID_MESSAGE</faultstring><detail><ns3:XcbSoapFault xmlns=\"\" xmlns:ns3=\"http://www.someapp.eu/xcb/types/xcb/v1\"><CauseCode>20007</CauseCode><CauseText>INVALID_MESSAGE</CauseText><DebugInfo>Problems creating SAAJ object model</DebugInfo></ns3:XcbSoapFault></detail></soap:Fault></soap:Body></soap:Envelope>");
    System.out.println(prettyPrintXMLAsString(x));
}

输出如下:

<soap:Envelope xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/">
  <soap:Body>
    <soap:Fault>
        <faultcode>soap:Client</faultcode>
        <faultstring>INVALID_MESSAGE</faultstring>
        <detail>
            <ns3:XcbSoapFault xmlns="" xmlns:ns3="http://www.someapp.eu/xcb/types/xcb/v1">
                <CauseCode>20007</CauseCode>
                <CauseText>INVALID_MESSAGE</CauseText>
                <DebugInfo>Problems creating SAAJ object model</DebugInfo>
            </ns3:XcbSoapFault>
        </detail>
    </soap:Fault>
  </soap:Body>
</soap:Envelope>

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");
    }
}