Java CleanerProperties.setTransResCharsToNCR方法代码示例

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
private static HtmlCleaner createHtmlCleaner() {
    HtmlCleaner result = new HtmlCleaner();
    CleanerProperties cleanerProperties = result.getProperties();

    cleanerProperties.setAdvancedXmlEscape(true);

    cleanerProperties.setOmitXmlDeclaration(true);
    cleanerProperties.setOmitDoctypeDeclaration(false);

    cleanerProperties.setTranslateSpecialEntities(true);
    cleanerProperties.setTransResCharsToNCR(true);
    cleanerProperties.setRecognizeUnicodeChars(true);

    cleanerProperties.setIgnoreQuestAndExclam(true);
    cleanerProperties.setUseEmptyElementTags(false);

    cleanerProperties.setPruneTags("script,title");

    return result;
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
/**
 * To Output html Stream via Html Cleaner.
 * 
 * @param pathOfHOCRFile String
 * @param outputFilePath String
 * @throws IOException
 */
public static void htmlOutputStreamViaHtmlCleaner(String pathOfHOCRFile, String outputFilePath) throws IOException {
	CleanerProperties cleanerProps = new CleanerProperties();

	// set some properties to non-default values
	cleanerProps.setTransResCharsToNCR(true);
	cleanerProps.setTranslateSpecialEntities(true);
	cleanerProps.setOmitComments(true);
	cleanerProps.setOmitDoctypeDeclaration(true);
	cleanerProps.setOmitXmlDeclaration(false);
	HtmlCleaner cleaner = new HtmlCleaner(cleanerProps);

	// take default cleaner properties
	// CleanerProperties props = cleaner.getProperties();
	FileInputStream hOCRFileInputStream = new FileInputStream(pathOfHOCRFile);
	TagNode tagNode = cleaner.clean(hOCRFileInputStream, UTF_ENCODING);
	if (null != hOCRFileInputStream) {
		hOCRFileInputStream.close();
	}
	try {
		new PrettyHtmlSerializer(cleanerProps).writeToFile(tagNode, outputFilePath, UTF_ENCODING);
	} catch (Exception e) { // NOPMD.
	}
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
/**
 * This method extracts the text from html string.
 * @param htmlString {@link String}
 * @return {@link String}
 */
public static String getTextFromHtmlString(String htmlString) {
	String errorText = "";
	CleanerProperties cleanerProps = new CleanerProperties();
	// set some properties to non-default values
	cleanerProps.setTransResCharsToNCR(true);
	cleanerProps.setTranslateSpecialEntities(true);
	cleanerProps.setOmitComments(true);
	cleanerProps.setOmitDoctypeDeclaration(true);
	cleanerProps.setOmitXmlDeclaration(true);
	cleanerProps.setUseEmptyElementTags(true);

	HtmlCleaner cleaner = new HtmlCleaner(cleanerProps);
	TagNode tagNode = cleaner.clean(htmlString);
	Object[] rootNode = null;
	try {
		rootNode = tagNode.evaluateXPath("//table");
		if (null != rootNode && rootNode.length > 0) {
			TagNode[] textNode = ((TagNode) rootNode[rootNode.length - 1]).getElementsByName("td", true);
			for (TagNode tag : textNode) {
				if (tag != null && tag.getText() != null) {
					StringBuilder errorTextString = new StringBuilder();
					errorTextString.append(errorText);
					if (tag.getText().toString().trim().equals(" ")) {
						errorTextString.append(" ");
						errorText = errorTextString.toString();
					} else {
						errorTextString.append(tag.getText());
						errorText = errorTextString.toString();
					}
				}
			}
		}
	} catch (XPatherException e) {
		LOGGER.error("Error extracting table node from html." + e.getMessage());
	}
	return errorText;
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
private String html2xhtml(String html) {
	if (StringUtils.isEmpty(html)){
		return "";
	}
	
	// Garante tag raiz único para o HtmlCleaner 
	html = "<div>" + html + "</div>";
	
	CleanerProperties props = new CleanerProperties();
	 
	// set some properties to non-default values
	props.setTranslateSpecialEntities(true);
	props.setTransResCharsToNCR(true);
	props.setOmitXmlDeclaration(true);
	props.setOmitHtmlEnvelope(true);
	props.setOmitComments(true);
	 
	// do parsing
	TagNode tagNode = new HtmlCleaner(props).clean(html);
	 
	// serialize to xml file
	String ret;
	try {
		ret = new SimpleXmlSerializer(props).getAsString(tagNode);
	} catch (IOException e) {
		throw new RuntimeException(e.getMessage(), e);
	}

	// Remove tag raiz <div>
	ret = ret.substring(5, ret.length() - 6);
	
	return ret;
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
public void cleanHTML(String path, String out, String encoding) throws IOException {

	HtmlCleaner cleaner = new HtmlCleaner();

	CleanerProperties props = cleaner.getProperties();

	CleanerTransformations transformations = new CleanerTransformations();

	AttributeTransformationPatternImpl attPattern = new AttributeTransformationPatternImpl(
			Pattern.compile("^\\s*class", Pattern.CASE_INSENSITIVE), null,
			null);
	transformations.addGlobalTransformation(attPattern);

	AttributeTransformationPatternImpl attPattern2 = new AttributeTransformationPatternImpl(
			Pattern.compile("^\\s*id", Pattern.CASE_INSENSITIVE), null,
			null);
	transformations.addGlobalTransformation(attPattern2);

	props.setCleanerTransformations(transformations);

	// set some properties to non-default values
	props.setTranslateSpecialEntities(true);
	props.setTransResCharsToNCR(false);
	props.setOmitComments(true);
	props.setPruneTags("script,style,img,form");
	
	

	// do parsing
	TagNode tagNode = new HtmlCleaner(props)
			.clean(new File(path), encoding);

	tagNode.removeAttribute("class");

	// serialize to xml file
	new PrettyHtmlSerializer(props).writeToFile(tagNode,
			out, "utf-8");

}