Java 将 XML 拆分为单独的字符串

Question

我想将 XML 文件拆分为单独的 XML。通过阅读 和 标签。我已经使用 StringUtils.substringsBetween 分割了 XML。但是，我只能从文件中分割出两个 XML。第三个 XML 将附加到第二个 XML 中。

程序:

import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;

import org.apache.commons.lang3.StringUtils;

public class SBuff {

    private BufferedReader br;

    public SBuff() {
        // TODO Auto-generated constructor stub
    }

    public static void main(String[] args) throws IOException {

         String data = "<?xml version=\"1.0\"?>\r\n" + 
                "<company>\r\n" + 
                "    <staff>\r\n" + 
                "        <firstname>yong</firstname>\r\n" + 
                "        <lastname>mook kim</lastname>\r\n" + 
                "        <nickname>mkyong</nickname>\r\n" + 
                "        <salary>100000</salary>\r\n" + 
                "    </staff>\r\n" + 
                "    <staff>\r\n" + 
                "        <firstname>low</firstname>\r\n" + 
                "        <lastname>yin fong</lastname>\r\n" + 
                "        <nickname>fong fong</nickname>\r\n" + 
                "        <salary>200000</salary>\r\n" + 
                "    </staff>\r\n" + 
                "    <staff>\r\n" + 
                "        <firstname>low</firstname>\r\n" + 
                "        <lastname>yin fong</lastname>\r\n" + 
                "        <nickname>fong fong</nickname>\r\n" + 
                "        <salary>200000</salary>\r\n" + 
                "    </staff>\r\n" + 
                "</company>\r\n"+
                "</xml>";

        SBuff s = new SBuff();
        s.loadData(data);
    }

    public void loadData(String stream) throws IOException {
        String[] list = StringUtils.substringsBetween(stream,
                "<staff">", "</staff>");

        StringBuilder stringBuilder = new StringBuilder();
        for (String s : list) {

            stringBuilder.append("<staff>");
            stringBuilder.append(s);
            stringBuilder.append("</staff>");
            System.out.println("##################################");
            System.out.println(stringBuilder.toString());
            System.out.println("##################################");
        }

    }

    public void display(String data) {
        System.out.println("Buffer Data: " + data);
    }
}

输出:

Expected:

##################################
<staff> 
   <firstname>yong</firstname> 
   <lastname>mook kim</lastname>
   <nickname>mkyong</nickname> 
   <salary>100000</salary>
</staff>
##################################
<staff>
   <firstname>low</firstname> 
   <lastname>yin fong</lastname> 
   <nickname>fong fong</nickname> 
   <salary>200000</salary>
</staff>
##################################
<staff>
   <firstname>low</firstname> 
   <lastname>yin fong</lastname> 
   <nickname>fong fong</nickname> 
   <salary>200000</salary>
</staff>
##################################


Actual:

##################################
<staff> 
   <firstname>yong</firstname> 
   <lastname>mook kim</lastname>
   <nickname>mkyong</nickname> 
   <salary>100000</salary>
</staff>
##################################
<staff>
   <firstname>low</firstname> 
   <lastname>yin fong</lastname> 
   <nickname>fong fong</nickname> 
   <salary>200000</salary>
</staff><staff>
   <firstname>low</firstname> 
   <lastname>yin fong</lastname> 
   <nickname>fong fong</nickname> 
   <salary>200000</salary>
</staff>
##################################

我尝试了不同的方法。似乎没有人锻炼。 提前致谢。

Answer 1

您可以使用像 jsoup 这样的 XML 解析器。

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.12.1</version>
</dependency>

解析和分割:

 Document doc = Jsoup.parse(data, "", Parser.xmlParser());
 for(Element staffElement: doc.getElementsByTag("staff")) {
   System.out.println(staffElement);
   System.out.println("##################################");
 }