本文整理汇总了Java中org.htmlcleaner.PrettyXmlSerializer类的典型用法代码示例。如果您正苦于以下问题：Java PrettyXmlSerializer类的具体用法？Java PrettyXmlSerializer怎么用？Java PrettyXmlSerializer使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
PrettyXmlSerializer类属于org.htmlcleaner包，在下文中一共展示了PrettyXmlSerializer类的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: toHTML
import org.htmlcleaner.PrettyXmlSerializer; //导入依赖的package包/类
/**
* Converts a given xml to HTML String
* @param htmlIn - xml in String
* @return String - in HTML format
*/
public static String toHTML( String htmlIn )
{
try
{
HtmlCleaner cleaner = new HtmlCleaner();
cleaner.getProperties().setNamespacesAware( true );
XmlSerializer xmlSerializer = new PrettyXmlSerializer( cleaner.getProperties(), " " );
String htmlData = xmlSerializer.getAsString( htmlIn );
htmlData = escapeXML( htmlData.replaceAll("(?m)^[ \t]*\r?\n", "") );
return htmlData;
}
catch( Exception e )
{
e.printStackTrace();
return null;
}
}
示例2: toXML
import org.htmlcleaner.PrettyXmlSerializer; //导入依赖的package包/类
/**
* htmlcleaner로 html string을 xml string으로 바꿔주는 메소드.
* @param source
* @return
*/
private String toXML(String source){
try {
CleanerProperties props = new CleanerProperties();
props.setTranslateSpecialEntities(true);
props.setOmitComments(true);
props.setPruneTags("script,style");
// namespace를 무시한다.
props.setNamespacesAware(false);
props.setAdvancedXmlEscape(true);
props.setTranslateSpecialEntities(true);
HtmlCleaner cl = new HtmlCleaner(props);
TagNode tagNode = cl.clean(source);
source = new PrettyXmlSerializer(props).getXmlAsString(tagNode);
} catch (IOException e) {
logger.error("",e);
}
return source;
}
示例3: getHTML
import org.htmlcleaner.PrettyXmlSerializer; //导入依赖的package包/类
public byte[] getHTML(HSSFWorkbook book) throws IOException {
double width = 21.0;
double height = 29.7;
if (isLandscape()) {
width += height;
height = width - height;
width = width - height;
}
byte[] html = convert(book, width, height).getBytes();
ByteArrayInputStream in = new ByteArrayInputStream(html);
// Clean up the HTML to be well formed
HtmlCleaner cleaner = new HtmlCleaner();
CleanerProperties props = cleaner.getProperties();
TagNode node = cleaner.clean(in, "UTF-8");
// ByteArrayOutputStream out = new ByteArrayOutputStream();
// Instead of writing to System.out we now write to the ByteArray buffer
// return new PrettyXmlSerializer(props).getAsString(node, "UTF-8").getBytes();
ByteArrayOutputStream out = new ByteArrayOutputStream();
// Instead of writing to System.out we now write to the ByteArray buffer
new PrettyXmlSerializer(props).writeToStream(node, out);
return out.toByteArray();
}
示例4: toHTML
import org.htmlcleaner.PrettyXmlSerializer; //导入依赖的package包/类
/**
* Converts a given xml to HTML String
* @param htmlIn - xml in String
* @return String - in HTML format
*/
public InputStream toHTML( InputStream htmlIn )
{
try
{
byte[] buffer = new byte[ 512 ];
int bytesRead = 0;
StringBuilder sB = new StringBuilder();
while ( (bytesRead = htmlIn.read( buffer ) ) != -1 )
{
sB.append( new String( buffer, 0, bytesRead ) );
}
if ( sB.indexOf( "html" ) != -1 )
{
HtmlCleaner cleaner = new HtmlCleaner();
cleaner.getProperties().setNamespacesAware( true );
XmlSerializer xmlSerializer = new PrettyXmlSerializer( cleaner.getProperties(), " " );
String htmlData = xmlSerializer.getAsString( sB.toString() );
htmlData = escapeXML( htmlData.replaceAll("(?m)^[ \t]*\r?\n", "") );
htmlData = htmlData.replace( "<!DOCTYPE HTML PUBLIC \"-//IETF//DTD HTML 2.0//EN\">", "" );
return new ByteArrayInputStream( htmlData.getBytes() );
}
else
return null;
}
catch( Exception e )
{
return null;
}
}
示例5: getCleanHtml
import org.htmlcleaner.PrettyXmlSerializer; //导入依赖的package包/类
/**
* Clean HTML document and return XML as byte array
*
* @param resourceMap map of resources
* @param resID unique ID of resource
* @return clean XHTML document as {@code byte[]}
* @throws IOException
*/
private byte[] getCleanHtml(PandaSettings pandaSettings, String resID) throws IOException {
byte[] doc = null;
// Get local path to file, if null the URL field will be used to
// retrieve resource
ResourceInfo resInfo = pandaSettings.getResourceMap().getMap().get(resID);
String filePath = resInfo.getFilePath();
// properties for HTML cleaning
CleanerProperties props = new CleanerProperties();
// preserve namespace prefixes
props.setNamespacesAware(true);
// remove <?TAGNAME....> or <!TAGNAME....>
props.setIgnoreQuestAndExclam(true);
// do not split attributes with multiple words
props.setAllowMultiWordAttributes(true);
// omits <html> tag
// props.setOmitHtmlEnvelope(true);
// omit DTD
props.setOmitDoctypeDeclaration(true);
// omit xml declaration
props.setOmitXmlDeclaration(true);
// omit comments
props.setOmitComments(true);
// omit deprecated tags like <font...>
props.setOmitDeprecatedTags(true);
// treat script and style tag contents as CDATA
props.setUseCdataForScriptAndStyle(true);
// replace html character in form &#XXXX with real unicode characters
props.setRecognizeUnicodeChars(true);
// replace special entities with unicode character
props.setTranslateSpecialEntities(true);
// if true do not escape valid xml character sequences
props.setAdvancedXmlEscape(true);
// get HTML document, parse HTML
TagNode tagNode = null;
if (filePath != null) {
tagNode = new HtmlCleaner(props).clean(new File(filePath));
} else {
// Get online resource
URL resURL = pandaSettings.getResourceMap().getMap().get(resID).getURL();
InputStream htmlDoc = getOnlineResource(resURL);
tagNode = new HtmlCleaner(props).clean(htmlDoc);
}
PrettyXmlSerializer pXmlS = new PrettyXmlSerializer(props);
doc = pXmlS.getAsString(tagNode).getBytes();
return doc;
}