为什么在 XML 中附加重复元素？

Question

我正在使用 Xerces API 在内存中创建 XML。我能够将重复的元素（相同的元素标签名称和属性）附加到元素节点。请建议我，如果 XML 元素已经作为元素节点的子元素存在，我该如何避免附加 XML 元素。

以下是创建的 XML（标签名为“Batch”的两个元素是重复的）：

<?xml version="1.0" encoding="UTF-8" standalone="no" ?>
<root>Text_root_01

  <Student>Text_Student_01
    <Batch ID="B01" Subject="Math">Ratnesh</Batch>Text_Student_02
    <Batch ID="B01" Subject="Math">Ratnesh</Batch>Text_Student_03
  </Student>Text_root_02

  <Othres Company="Airtel" NoOfEmployee="15">Text_Others</Othres>Text_root_03

</root>

以下是我用来创建此 XML 的 CPP 代码：

int main(int argc, char *argv[]) {

        //XMLCh temp_buff[64];

        XMLPlatformUtils::Initialize();

        DOMImplementation *p_domImpl = DOMImplementationRegistry::getDOMImplementation(XMLString::transcode("Core"));
        DOMDocument *p_domDoc = p_domImpl->createDocument(0, XMLString::transcode("root"), 0);

        DOMElement *p_root_elem = p_domDoc->getDocumentElement();
        DOMText *root_text_01 = p_domDoc->createTextNode(XMLString::transcode("Text_root_01"));
        p_root_elem->appendChild(root_text_01);

        DOMElement *root_child_student = p_domDoc->createElement(XMLString::transcode("Student"));
        p_root_elem->appendChild(root_child_student);
        DOMText* student_text_01 = p_domDoc->createTextNode(XMLString::transcode("Text_Student_01"));
        root_child_student->appendChild(student_text_01);


        DOMElement* student_child_batch = p_domDoc->createElement(XMLString::transcode("Batch"));
        student_child_batch->setAttribute(XMLString::transcode("Subject"), XMLString::transcode("Math"));
        student_child_batch->setAttribute(XMLString::transcode("ID"), XMLString::transcode("B01"));
        DOMText* batch_text = p_domDoc->createTextNode(XMLString::transcode("Ratnesh"));
        student_child_batch->appendChild(batch_text);
        root_child_student->appendChild(student_child_batch);

        DOMText* student_text_02 = p_domDoc->createTextNode(XMLString::transcode("Text_Student_02"));
        root_child_student->appendChild(student_text_02);

        student_child_batch = p_domDoc->createElement(XMLString::transcode("Batch"));
        student_child_batch->setAttribute(XMLString::transcode("Subject"), XMLString::transcode("Math"));
        student_child_batch->setAttribute(XMLString::transcode("ID"), XMLString::transcode("B01"));
        batch_text = p_domDoc->createTextNode(XMLString::transcode("Ratnesh"));
        student_child_batch->appendChild(batch_text);
        root_child_student->appendChild(student_child_batch);


        DOMText* student_text_03 = p_domDoc->createTextNode(XMLString::transcode("Text_Student_03"));
        root_child_student->appendChild(student_text_03);

        DOMText* root_text_02 = p_domDoc->createTextNode(XMLString::transcode("Text_root_02"));
        p_root_elem->appendChild(root_text_02);

        DOMElement *root_child_others = p_domDoc->createElement(XMLString::transcode("Othres"));
        root_child_others->setAttribute(XMLString::transcode("Company"), XMLString::transcode("Airtel"));
        root_child_others->setAttribute(XMLString::transcode("NoOfEmployee"), XMLString::transcode("15"));
        p_root_elem->appendChild(root_child_others);
        DOMText* others_text_01 = p_domDoc->createTextNode(XMLString::transcode("Text_Others"));
        root_child_others->appendChild(others_text_01);

        DOMText* root_text_03 = p_domDoc->createTextNode(XMLString::transcode("Text_root_03"));
        p_root_elem->appendChild(root_text_03);


        xml_output_to_stream(p_domDoc);

        p_domDoc->release();
        XMLPlatformUtils::Terminate();

        return 0;

}

Answer 1

我建议你：

用正确的术语说话：内存中的 XML 称为 DOM（文档对象模型）
XML 是文本文件中的最终文本表示形式。
构建一个对 xml 更友好的结构：
- 批量删除姓名，这是学生的姓名（我推测）并将其放入学生标签中。
- 不要在标签之间喷文字，使用标签（或 神奇之处在于解耦功能。

<root>

  <text>text_root1</text>

  <Student name="Ratnesh">
    <text>Text_Student_01</text>
    <Batch ID="B01" Subject="Math"></Batch>
    <Batch ID="B02" Subject="Geology"></Batch>
  </Student>

  <Student name="Mike">
    <text>Text_Student_02</text>
    <Batch ID="B01" Subject="Math"></Batch>
    <Batch ID="B03" Subject="Sport"></Batch>
  </Student>


  <Others Company="Airtel" NoOfEmployee="15">
    <text>Text for others...</text>
  </Others>

然后你可以构建方法或函数

Method (or function) insertStudent((NODE)parent, (string)text, (string)name) {
      > create a StudentNode <STUDENT> 
      > put attribute name="name" into StudenNode
      > create <TEXT> node
      > put sting(text) into <TEXT> node
      > put <TEXT>node into StudentNode
      > return StudentNode
  }




 Method (or function) insertBatch (StudentNode, batchId, batchName, (string) text) {
     > create a node <NodeBatch>
     > put him attribute Subject=string batchName
     > put him  attribute batchId=batchId
     > create a <TEXT> node, put him (string) text
     > put <TEXT> node in <NodeBatch>

 }




Method (or function) searchStudent  ((string)StudentName) {
   > use XPATH \ROOT\Student[name="StudentName"]
   > return a List of Node , or empty node if not found
 }




 Method (or function) searchBatchByName (NodeStudent, (string)batchName) {
   >  use XPATH Batch[subject="batchName"] starting at node NodeStudent
   >  return a List of Node , or empty node if not found
 }



 Method (or function) searchBatchById (nodeStudent, (string)batchId ) {
   >  use XPATH Batch[id="batchId"] starting at node nodeStudent
   >  return a List of Node , or empty node if not found
 }



 Method (or function) insertActivity ((string)studentName,(string)textStudent, (string)batchName , (string|int) batchID, (string)textBatch) {

   list = searchStudent (studentName)
   if (list).len>0 {
     nodeStudent=list[0]
   } else {
     nodeStudent=insertStudent(ROOT,textStudent,studentName)
   }

   listBatch=searchBatchByName(nodeStudent,batchName)) 
   *** OR list=searchBatchById (nodeStudent,batchId)) *** 

   if (listBatch.len>0) { skip } // already exist, do nothing
    else {
     insertBatch(listBatch[0],batchId, batchName, textBash)
    }

 }

并用

进行测试

 insertActivity ("Ratnesh","text student","Math","B01","text_bash")
   insertActivity ("Mike","text student","Sport","B03","text_bash")   
   insertActivity ("Ratnesh","text student","Geology","B02","text_bash")   
   insertActivity ("Mike","text student","Sport","B03","text_bash")   // oops duplicate entry