Java : 使用 SAX/XPATH 解析 xml 文件

Question

我有一个 xml 文件，如下所述：

<?xml version="1.0" encoding="UTF-8"?>
<Workbook>
    <ExcelWorkbook
    xmlns="urn:schemas-microsoft-com:office:excel"/>
        <Worksheet ss:Name="Table 1">
            <Table>
                <Row ss:Index="7" ss:AutoFitHeight="0" ss:Height="12">
                <Cell ss:Index="1" ss:StyleID="s05">
                    <ss:Data ss:Type="String"
                        xmlns="http://www.w3.org/TR/REC-html40">
                        <Font html:Size="9" html:Face="Times New Roman" x:Family="Roman" html:Color="#000000">
                        ABCD
                        </Font>
                    </ss:Data>
                </Cell>
            </Row>

如何在 Java 中使用 SAX 或 XPATH 提取数据，"ABCD"？

编辑 1：

这是XML-

<Table>
<Row ss:Index="74" ss:AutoFitHeight="0" ss:Height="14">
    <Cell ss:Index="1" ss:MergeAcross="3" ss:StyleID="s29">
        <ss:Data ss:Type="Number" xmlns="http://www.w3.org/TR/REC-html40">
        0.00
        </ss:Data>
    </Cell>
    <Cell ss:Index="15" ss:MergeAcross="5" ss:StyleID="s29">
        <ss:Data ss:Type="Number" xmlns="http://www.w3.org/TR/REC-html40">
        4.57
        </ss:Data>
    </Cell>
</Row>

Answer 1

解决方案假定问题是如何根据行号和列号获取任何单元格的文本。

由于在输入文档中使用了名称空间，我花了一段时间才得到解决方案。显然，如果没有名称空间处理器和一个 hsa 来实现用于此目的的接口（没有默认值？），xpath 无法解析合格的元素和属性，所以我找到了一个基于映射的实现 here 并使用了它。

因此，假设您的源代码树中有 link 中的 class，则以下代码有效。为了清楚起见，我将搜索模式分解为几个变量

public static String getCellValue(String filename, int rowIdx, int colIdx) {
    // search for Table element anywhere in the source
    String tableElementPattern = "//*[name()='Table']";
    // search for Row element with given number
    String rowPattern = String.format("/*[name()='Row' and @ss:Index='%d']", rowIdx) ;
    // search for Cell element with given column number
    String cellPattern = String.format("/*[name()='Cell' and @ss:Index='%d']", colIdx) ;  
    // search for element that has ss:Type="String" attribute, search for element with text under it and get text name
    String cellStringContent = "/*[@ss:Type='String']/*[text()]/text()";  
    String completePattern = tableElementPattern + rowPattern + cellPattern + cellStringContent;

    try (FileReader reader = new FileReader(filename)) {
        XPath xPath = getXpathProcessor();
        Node n = (Node)xPath.compile(completePattern)
        .evaluate(new InputSource(reader), XPathConstants.NODE);
        if (n.getNodeType() == Node.TEXT_NODE) {
            return n.getNodeValue().trim();
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
    return null;
}

private static XPath getXpathProcessor() {
    // this is where the custom implementation of NamespaceContext is used
    NamespaceContext context = new NamespaceContextMap(
        "html", "http://www.w3.org/TR/REC-html40", 
        "xsl", "http://www.w3.org/1999/XSL/Transform",
        "o", "urn:schemas-microsoft-com:office:office",
        "x", "urn:schemas-microsoft-com:office:excel",
        "ss", "urn:schemas-microsoft-com:office:spreadsheet");
    XPath xpath =  XPathFactory.newInstance().newXPath();
    xpath.setNamespaceContext(context);
    return xpath;
}

呼叫：

System.out.println(getCellValue("C://Temp/xx.xml", 7, 1));

生成所需的输出

Answer 2

下面是使用 vtd-xml...

查询您的 XML 的代码

import com.ximpleware.*;

public class queryXML{

 public static void main(String[] s) throws VTDException{

        VTDGen vg = new VTDGen();
        vg.selectLcDepth(5);
        if (!vg.parseFile("d:\xml\test11.xml", false))
            return;
        VTDNav vn = vg.getNav();
        AutoPilot ap = new AutoPilot(vn);
        ap.declareNameSpace("ss","urn:schemas-microsoft-com:office:spreadsheet");
              ap.selectXPath("/Workbook/ExcelWorkbook/Worksheet/Table/Cell/ss:data/font/text()");
int i=0;
while((i=ap.evalXPath())!=-1){
 System.out.println(" data content ==>"+vn.toString(i);
}


}


}

Java : 使用 SAX/XPATH 解析 xml 文件

Java : Parsing xml file using SAX/XPATH

java

xml

xpath

sax