從父和子節點的XPath選擇屬性值

Question

以下是我的XML文件：

<?xml version="1.0" encoding="UTF-8"?> 
    <query xmlns:yahoo="http://www.yahooapis.com/v1/base.rng" yahoo:lang="en-GB"> 
     <results> 

     <sector sectorid="1" sectorname="Basic Materials"> 
      <industry id="112" name="Agricultural Chemicals"/> 
      <industry id="132" name="Aluminum"/> 
      <industry id="110" name="Chemicals - Major Diversified"/> 
      <industry id="131" name="Copper"/> 
      <industry id="134" name="Gold"/> 
      <industry id="121" name="Independent Oil and Gas"/> 
      <industry id="120" name="Major Integrated Oil and Gas"/> 
     </sector> 

     <sector sectorid="2" sectorname="Conglomerates"> 
      <industry id="210" name="Conglomerates"/> 
     </sector> 

     <sector sectorid="7" sectorname="Services"> 
      <industry id="720" name="Advertising Agencies"/> 
      <industry id="773" name="Air Delivery and Freight Services"/> 
      <industry id="772" name="Air Services and Others"/> 
      <industry id="730" name="Apparel Stores"/> 
      <industry id="744" name="Auto Dealerships"/> 
     </sector> 

    </results> 
    </query> 

從上面的XML文件，我要找存儲屬性的值：sectorid，id，並在適當的name變量（我正在使用Java）。我一直在尋找不同的XPath表達式，並且提出了以下代碼，但是，當存儲值id屬性時，會引發java.lang.NumberFormatException: For input string: ""異常。這裏是我的代碼：

public class XMLToDatabase { 

    private static int __SectorID; 
    private static int __IndustryID; 
    private static String __IndustryName; 

    public static void main(String[] args) throws SQLException, UnsupportedEncodingException, ParserConfigurationException, SAXException, IOException, XPathExpressionException { 

     try {    
      File _XMLFile = new File("SectorsAndIndustries.xml"); 

      DocumentBuilderFactory _DocumentBuilderFactory = DocumentBuilderFactory.newInstance(); 
      _DocumentBuilderFactory.setNamespaceAware(true); 

      DocumentBuilder _DocumentBuilder = _DocumentBuilderFactory.newDocumentBuilder(); 
      Document _Document = _DocumentBuilder.parse(_XMLFile); 

      _Document.getDocumentElement().normalize(); 

      XPath _XPath = XPathFactory.newInstance().newXPath(); 

      XPathExpression _XPathExpression = _XPath.compile("//sector | //industry"); 

      NodeList _NodeList = (NodeList) _XPathExpression.evaluate(_Document, XPathConstants.NODESET); 


      for (int i = 0; i < _NodeList.getLength(); i++) { 
       Node _Node = _NodeList.item(i); 

       if(_Node.getNodeType() == Node.ELEMENT_NODE) { 
        Element _Element = (Element) _Node; 

        __SectorID = Integer.parseInt(_Element.getAttribute("sectorid")); 
        __IndustryID = Integer.parseInt(_Element.getAttribute("id")); 
        __IndustryName = _Element.getAttribute("name"); 
       } 

      System.out.println(__SectorID + ", " + __IndustryID + ", " + __IndustryName); 
      } 
     } catch (Exception e) { 
      e.printStackTrace(); 
     } 

    } 

} 

可能有人請幫助我確定它是否是XPath Expression，我犯了一個錯誤使用，或者如果路上我儲存的第二個變量__IndustryID？因爲第一個變量__SectorID正確存儲值1，但引發上述__IndustryID的異常。理想情況下，每次執行for循環時，我都希望存儲所有3個屬性的值，以將它們保存到數據庫表中。請讓我知道是否需要更多信息。

Answer 1

馬蒂亞斯曾建議正確的方法，我都拿出了它的解決方案稍作修改：

public class XMLToDatabase { 

    private static int __SectorID; 
    private static int __IndustryID; 
    private static String __IndustryName; 

    public static void main(String[] args) throws SQLException, 
      UnsupportedEncodingException, ParserConfigurationException, 
      SAXException, IOException, XPathExpressionException { 

     try { 
      File _XMLFile = new File("C:/Users/Sachin/Desktop/SectorsAndIndustries.xml"); 
      DocumentBuilderFactory _DocumentBuilderFactory = DocumentBuilderFactory.newInstance(); 
      DocumentBuilder _DocumentBuilder = _DocumentBuilderFactory.newDocumentBuilder(); 
      Document _Document = _DocumentBuilder.parse(_XMLFile); 
      _Document.getDocumentElement().normalize(); 

      XPath _XPath = XPathFactory.newInstance().newXPath(); 

      NodeList _NodeList1 = (NodeList) _XPath.evaluate("/results/sector", _Document, XPathConstants.NODESET); 

      for (int i = 0; i < _NodeList1.getLength(); i++) { 
       Element _Element1 = (Element) _NodeList1.item(i); 

       __SectorID = Integer.parseInt(_Element1.getAttribute("sectorid")); 

       NodeList _NodeList2 = (NodeList) _XPath.evaluate("industry", _Element1, XPathConstants.NODESET); 

       for (int k=0; k < _NodeList2.getLength(); k++) { 
        __IndustryID = Integer.parseInt(_XPath.evaluate("industry[position()=" + (k + 1) + "]/@id", _Element1)); 
        __IndustryName = _XPath.evaluate("industry[position()=" + (k + 1) + "]/@name", _Element1); 

        System.out.println(__SectorID + ", " + __IndustryID + ", " + __IndustryName); 
       } 
       System.out.println("\n-----------\n"); 
      } 

     } catch (Exception e) { 
      e.printStackTrace(); 
     } 
    } 
} 

Answer 2

就我所見，您正在編譯一個節點列表，其節點爲sector或industry元素。對於其中的每一個，您都希望檢索sectorid和id屬性 - 但顯然，沒有元素具有這兩個屬性。

一個更好的辦法是

• 找到所有sector元素，併爲每個打印出的扇區ID
• 每個sector元素經過所謂industry所有的子元素（這需要應用第二個XPath表達式爲每個sector元素，但它是一個簡單的："industry"）
• 並輸出每個industry的ID屬性