Question

我必须在odt文件中更新文件content.xml。我想获取相同的文件内容，没有元素空格和没有换行符。

我尝试在Java中使用带有Transformer对象的xsl转换，它部分有效。例如，有一个简单的odt，content.xml如下：

<?xml version="1.0" encoding="utf-8" ?>
<office:document-content xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0" xmlns:script="urn:oasis:names:tc:opendocument:xmlns:script:1.0" xmlns:ooo="http://openoffice.org/2004/office" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:xforms="http://www.w3.org/2002/xforms" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" office:version="1.2">
    <office:font-face-decls>
        <style:font-face style:name="Courier New" style:font-family-generic="modern" style:font-pitch="fixed" svg:font-family="'Courier New'" />
    </office:font-face-decls>
    <office:automatic-styles>

    </office:automatic-styles>
    <office:body>
        <office:text>
            <text:p text:style-name="Title">TODO supply a title</text:p>
            <text:p text:style-name="Text_20_body">TODO write content</text:p>
            <text:h text:style-name="Heading_20_1" text:outline-level="1">My First Heading</text:h>
            <text:p text:style-name="First_20_paragraph">My first paragraph.</text:p>
        </office:text>
    </office:body>
</office:document-content>

我写了这个xsl文件来删除所有换行符，元素之间的空格，所以我想在一行中获得相同的XML内容序列化。

<?xml version="1.0" encoding="ISO-8859-15" ?>
<xsl:stylesheet version="1.0"
                xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
                xmlns:xalan="http://xml.apache.org/xslt"
                xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" 
                xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" 
                xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" 
                xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" 
                xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0"
                xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" 
                xmlns:xlink="http://www.w3.org/1999/xlink" 
                xmlns:dc="http://purl.org/dc/elements/1.1/" 
                xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" 
                xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" 
                xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" 
                xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" 
                xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" 
                xmlns:math="http://www.w3.org/1998/Math/MathML" 
                xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0" 
                xmlns:script="urn:oasis:names:tc:opendocument:xmlns:script:1.0" 
                xmlns:ooo="http://openoffice.org/2004/office" 
                xmlns:ooow="http://openoffice.org/2004/writer" 
                xmlns:oooc="http://openoffice.org/2004/calc" 
                xmlns:dom="http://www.w3.org/2001/xml-events"
                xmlns:xforms="http://www.w3.org/2002/xforms" 
                xmlns:xsd="http://www.w3.org/2001/XMLSchema" 
                xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
                xmlns="urn:oasis:names:tc:opendocument:xmlns:office:1.0"
                extension-element-prefixes="office style text"
>
    <xsl:output method="xml" encoding="ISO-8859-15" indent="no"/>
    <xsl:strip-space elements="*" />


    <xsl:template match="@*|node()|comment()|processing-instruction()|text()">
        <xsl:copy>
            <xsl:apply-templates select="@*|node()|comment()|processing-instruction()|text()" />
        </xsl:copy>
    </xsl:template>

</xsl:stylesheet>

我使用了缩进=＆＃34;没有＆＃34;和条形空间元素=＆＃34; *＆＃34;没有标识，但现在我的问题是名称空间。我使用这个xsl获得的XML如下：

<?xml version="1.0" encoding="ISO-8859-15"?><document-content xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:ooo="http://openoffice.org/2004/office" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:script="urn:oasis:names:tc:opendocument:xmlns:script:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:xforms="http://www.w3.org/2002/xforms" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" office:version="1.2"><font-face-decls><font-face style:font-family-generic="modern" style:font-pitch="fixed" style:name="Courier New" svg:font-family="'Courier New'"/></font-face-decls><automatic-styles/><body><text><p text:style-name="Title">TODO supply a title</p><p text:style-name="Text_20_body">TODO write content</p><h text:outline-level="1" text:style-name="Heading_20_1">My First Heading</h><p text:style-name="First_20_paragraph">My first paragraph.</p></text></body></document-content>

它按照我的意愿排在一行，但元素没有名称空间前缀。请注意，对于具有正确名称空间的属性，它不会发生。

在我指定匹配节点，注释和属性的xsl中，<xsl:stylesheet>元素中的命名空间和传递允许命名空间列表的extension-element-prefixs。如果我删除了extension-element-prefix，则没有任何改变。

使用Transformer对象的Java代码如下：

 public void serializeXML(String filePath, String destinationPath) throws Exception {
    File xmlFile = new File(filePath);
    DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
    DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
    Document doc = dBuilder.parse(xmlFile);
    doc.normalizeDocument();

    DOMSource domSource = new DOMSource(doc);
    TransformerFactory transformerFactory = TransformerFactory.newInstance();

    InputStream is = XMLSerializer.class.getClassLoader().getResourceAsStream("identer.xsl");

    Transformer transformer = transformerFactory.newTransformer(new StreamSource(is));

    StringWriter sw = new StringWriter();
    StreamResult sr = new StreamResult(sw);
    transformer.transform(domSource, sr);

    Result result = new StreamResult(new FileOutputStream(new File(destinationPath)));

    transformer.transform(domSource, result);

    LOGGER.info(sw.toString());
}

我声明了Transformer对象，并向其传递了xsl文件的inputStream。我没有设置任何属性，因为我在xsl文件中声明了所有（在我看来）是必要的，之后我转换文档，将结果保存到文件中并用记录器打印。

有人可以帮助我吗？

谢谢。

Answer 1

我解决了，感谢回答我问题的用户。

我修改了我的代码，所以xsl现在是：

<xsl:output method="xml" encoding="ISO-8859-15" indent="no"/>
<xsl:strip-space elements="*" />

<xsl:template match="@*|node()">
    <xsl:copy>
        <xsl:apply-templates select="@*|node()"/>
    </xsl:copy>
</xsl:template>

然后我简化了使用Transformer的Java代码：

 public void serializeXML(String filePath, String destinationPath) throws Exception {

        TransformerFactory factory = TransformerFactory.newInstance();
        InputStream is = XMLSerializer.class.getClassLoader().getResourceAsStream("identer.xsl");
        Source xslt = new StreamSource(is);
        Transformer transformer = factory.newTransformer(xslt);

        Source text = new StreamSource(new File(filePath));
        transformer.transform(text, new StreamResult(new File(destinationPath)));

    }

XSL转换不会在元素之前写入命名空间

1 个答案: