Java Tidy.setNumEntities方法代碼示例

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
public void tidy_init() {
	long bgn = System_.Ticks();
	wtr = new ByteArrayOutputStream();
	System.setProperty("line.separator", "\n");
	tidy = new Tidy(); // obtain a new Tidy instance
	tidy.setInputEncoding("utf-8");			// -utf8
	tidy.setOutputEncoding("utf-8");		// -utf8
	tidy.setDocType("\"\"");				// --doctype \"\"; set to empty else some wikis will show paragraph text with little vertical gap; PAGE:tr.b:
	tidy.setForceOutput(true);				// --force-output y 
	tidy.setQuiet(true);					// --quiet y
	tidy.setTidyMark(false);				// --tidy-mark n
	tidy.setWraplen(0);						// --wrap 0
	tidy.setIndentContent(true);			// --indent y; NOTE: true indents all content in edit box
	tidy.setQuoteNbsp(true);				// --quote-nbsp y
	tidy.setLiteralAttribs(true);			// --literal-attributes y
	tidy.setWrapAttVals(false);				// --wrap-attributes n
	tidy.setFixUri(false);					// --fix-url n
	tidy.setFixBackslash(false);			// --fix-backslash n
	tidy.setEncloseBlockText(true);			// --enclose-block-text y; NOTE: true creates extra <p>; very noticeable in sidebar
	tidy.setNumEntities(false);				// NOTE: true will convert all UTF-8 chars to &#val; which ruins readability
	tidy.setTrimEmptyElements(true);		// NOTE: tidy always trims (not even an option)
	tidy.setShowWarnings(false);			// NOTE: otherwise warnings printed to output window
	tidy.setShowErrors(0);					// NOTE: otherwise errors printed to output window; EX: Error: <time> is not recognized!
	app.Usr_dlg().Log_many("", "", "jtidy.init; elapsed=~{0}", System_.Ticks__elapsed_in_frac(bgn));
}
 

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
private String cleanupHtml(String story) {
    Tidy tidy = new Tidy();
    tidy.setInputEncoding(ENCODING);
    tidy.setOutputEncoding(ENCODING);
    tidy.setPrintBodyOnly(true);
    tidy.setXmlOut(true);
    tidy.setSmartIndent(false);
    tidy.setBreakBeforeBR(false);
    tidy.setMakeBare(true);
    tidy.setMakeClean(true);
    tidy.setNumEntities(true);
    tidy.setWraplen(0);

    StringWriter writer = new StringWriter();
    StringReader reader = new StringReader(story);
    tidy.parse(reader, writer);
    return writer.toString();
}
 

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
public void ConverterXhtml(String fileHtml, String fileXhtmlAux) throws Exception {

        Tidy tidy = new Tidy();

        FileInputStream in = new FileInputStream(fileHtml);
        FileOutputStream out = new FileOutputStream(fileXhtmlAux);

        tidy.setTidyMark(false);
        tidy.setDocType("omit");
        tidy.setAltText("");
        tidy.setFixBackslash(true);
        tidy.setFixComments(true);
        tidy.setXmlPi(true);
        tidy.setQuoteAmpersand(true);
        tidy.setQuoteNbsp(true);
        tidy.setNumEntities(true);
        tidy.setXmlOut(true);
        tidy.setWraplen(999);
        tidy.setWriteback(true);
        tidy.setQuoteMarks(true);
        tidy.setLogicalEmphasis(true);
        tidy.setEncloseText(true);
        tidy.setHideEndTags(true);
        tidy.setShowWarnings(false);
        tidy.setQuiet(true);
        tidy.setXHTML(true);
        tidy.parse(in, out);

        in.close();
        out.close();


    }
 

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
/**
 * Method used to transform the data from the html file given as parameter to 
 * xhtml format file which will be stored in the second file given.
 * @param fileHtml input html file path.
 * @param fileXhtmlAux output xhtml file path.
 * @throws Exception if the files can not be read or written.
 */
public void ConverterXhtml(String fileHtml, String fileXhtmlAux) throws Exception {

    Tidy tidy = new Tidy();

    FileInputStream in = new FileInputStream(fileHtml);
    FileOutputStream out = new FileOutputStream(fileXhtmlAux);

    tidy.setTidyMark(false);
    tidy.setDocType("omit");
    tidy.setAltText("");
    tidy.setFixBackslash(true);
    tidy.setFixComments(true);
    tidy.setXmlPi(true);
    tidy.setQuoteAmpersand(true);
    tidy.setQuoteNbsp(true);
    tidy.setNumEntities(true);
    tidy.setXmlOut(true);
    tidy.setWraplen(999);
    tidy.setWriteback(true);
    tidy.setQuoteMarks(true);
    tidy.setLogicalEmphasis(true);
    tidy.setEncloseText(true);
    tidy.setHideEndTags(true);
    tidy.setShowWarnings(false);
    tidy.setQuiet(true);
    tidy.setXHTML(true);
    tidy.parse(in, out);

    in.close();
    out.close();


}
 

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
private String getXHTML( String _html ){
	Tidy tidy = new Tidy();
	tidy.setQuiet( true );
	tidy.setNumEntities( true );
	tidy.setShowWarnings( false );
	StringWriter result = new StringWriter();
	tidy.setMakeClean( true );
	tidy.setXHTML( true );
	tidy.parse( new StringReader( _html ), result );

	return result.toString();
}
 

import org.w3c.tidy.Tidy; //導入方法依賴的package包/類
private static String tidyHTML(String content)
								throws IOException{
	Tidy tidy = new Tidy();
	
	// set configuration values
	tidy.setDropEmptyParas(false); // drop empty P elements
	tidy.setDocType("omit"); // omit the doctype
	tidy.setEncloseBlockText(true); // wrap blocks of text in P elements
	tidy.setEncloseText(true); // wrap text right under BODY element in P elements
	tidy.setHideEndTags(false); // force optional end tags
	tidy.setIndentContent(false); // indent content for easy reading
	tidy.setLiteralAttribs(false); // no new lines in attributes
	tidy.setLogicalEmphasis(false); // replace i and b by em and strong, respectively
	tidy.setMakeClean(false); // strip presentational cruft
	tidy.setNumEntities(true); // convert entities to their numeric form
	tidy.setWord2000(true); // strip Word 2000 cruft
	tidy.setXHTML(true); // output XHTML
	tidy.setXmlPi(true); // add <?xml?> processing instruction
	
	// parse
	StringReader in = new StringReader(content);
	StringWriter out = new StringWriter();
	tidy.parse(in, out);
	in.close();
	out.close();
	String results = out.toString();
	
	// remove the XML namespace declaration,
	// since it makes trouble for us in the XPath
	// evaluator
	// FIXME: this is ghetto and needs to be fixed
	// with a namespace evaluator in the XPath section,
	// but namespace evaluators are a pain in the butt
	// to get working
	
	// String.replace() does not work on 1.4 JVMs when compiled
	// with 1.5 JVMs, even with target="1.4" (this is a known Java
	// bug). Using workaround instead. -- Brad Neuberg
	//results = results.replace("xmlns=\"http://www.w3.org/1999/xhtml\"", "");
	
	StringBuffer buffer = new StringBuffer(results);
	int startCut = buffer.indexOf("xmlns=\"http://www.w3.org/1999/xhtml\"");
	if(startCut != -1){
		buffer.replace(startCut, 
						startCut + "xmlns=\"http://www.w3.org/1999/xhtml\"".length(), 
						"");
		results = buffer.toString();
	}
	
	//System.out.println("tidied results="+results);
			
	return results;
}