Java ContentNode类代码示例

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private void handleContent(SpannableStringBuilder builder, Object node,
                           SpanStack stack, CancellationCallback cancellationCallback ) {

    checkForCancellation(cancellationCallback);

    ContentNode contentNode = (ContentNode) node;

    String text = TextUtil.replaceHtmlEntities(
            contentNode.getContent().toString(), false);

    if ( isStripExtraWhiteSpace() ) {
        //Replace unicode non-breaking space with normal space.
        text = text.replace( '\u00A0', ' ' );
    }

    if ( text.trim().length() > 0 ) {
        builder.append(text);
    }
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private void getPlainText(StringBuffer buffer, Object node) {
	if (node instanceof ContentNode) {

		ContentNode contentNode = (ContentNode) node;
		String text = TextUtil.replaceHtmlEntities(contentNode.getContent()
				.toString(), true);

		buffer.append(text);

	} else if (node instanceof TagNode) {
		TagNode tagNode = (TagNode) node;
		for (Object child : tagNode.getAllChildren()) {
			getPlainText(buffer, child);
		}
	}
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
@Override
public void handleTagNode(TagNode node, SpannableStringBuilder builder, int start, int end, SpanStack spanStack) {

    if ( getSpanner().isAllowStyling() ) {

        if ( node.getAllChildren().size() == 1 ) {
            Object childNode = node.getAllChildren().get(0);

            if ( childNode instanceof ContentNode ) {
                parseCSSFromText( ( (ContentNode) childNode ).getContent(),
                        spanStack );
            }
        }
    }

}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
final private void checkStyleCSS(TagNode node)
		throws ClientProtocolException, IllegalStateException, IOException, SearchLibException, URISyntaxException {
	if (!("style".equalsIgnoreCase(node.getName())))
		return;
	String attr = node.getAttributeByName("type");
	if (!StringUtils.isEmpty(attr) && !"text/css".equalsIgnoreCase(attr))
		return;
	attr = node.getAttributeByName("media");
	if (!StringUtils.isEmpty(attr) && !"screen".equalsIgnoreCase(attr) && !"all".equalsIgnoreCase(attr))
		return;
	StringBuilder builder = (StringBuilder) node.getText();
	if (builder == null)
		return;
	String content = builder.toString();
	String newContent = StringEscapeUtils.unescapeXml(content);
	StringBuffer sb = checkCSSContent(baseUrl, newContent);
	if (sb != null)
		newContent = sb.toString();
	if (newContent.equals(content))
		return;
	node.removeAllChildren();
	node.addChild(new ContentNode(newContent));
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
final private void checkScriptContent(TagNode node, Set<TagNode> disableScriptNodeSet) {
	if (!("script".equalsIgnoreCase(node.getName())))
		return;
	if (disableScriptNodeSet != null && hasAncestorXPath(disableScriptNodeSet, node)) {
		node.removeFromTree();
		return;
	}
	StringBuilder builder = (StringBuilder) node.getText();
	if (builder == null)
		return;
	String content = builder.toString();
	if (content == null)
		return;
	String newContent = StringEscapeUtils.unescapeXml(content);
	if (newContent.equals(content))
		return;
	node.removeAllChildren();
	node.addChild(new ContentNode(newContent));
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private void getPlainText(StringBuffer buffer, Object node) {
    if (node instanceof ContentNode) {
        ContentNode contentNode = (ContentNode) node;
        String text = contentNode.getContent().toString();
        buffer.append(text);
    } else if (node instanceof TagNode) {
        TagNode tagNode = (TagNode) node;
        for (Object child : tagNode.getChildren()) {
            this.getPlainText(buffer, child);
        }
    }
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private void applySpan(SpannableStringBuilder builder, TagNode node, SpanStack stack,
                       CancellationCallback cancellationCallback) {

    checkForCancellation(cancellationCallback);

    TagNodeHandler handler = this.handlers.get(node.getName());

    if ( handler == null ) {
        handler = new StyledTextHandler();
        handler.setSpanner(this);
    }

    int lengthBefore = builder.length();

    handler.beforeChildren(node, builder, stack);

    if ( !handler.rendersContent() ) {

        for (Object childNode : node.getAllChildren()) {

            if ( childNode instanceof ContentNode ) {
                handleContent( builder, childNode, stack, cancellationCallback );
            } else if ( childNode instanceof TagNode ) {
                applySpan( builder, (TagNode) childNode, stack, cancellationCallback );
            }
        }
    }

    int lengthAfter = builder.length();
    handler.handleTagNode(node, builder, lengthBefore, lengthAfter, stack);
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private boolean satisfy(TagNode tagNode, boolean override) {
    String name = tagNode.getName();
    TagInfo tagInfo = tagInfoProvider.getTagInfo(name);
    //Only _block_ elements can match.
    if (tagInfo != null && !hasIdAttributeSet(tagNode) && none != tagInfo.getDisplay() && !tagInfo.isEmptyTag() && (override || !unsafeBlockElements.contains(name))) {
        CharSequence contentString = tagNode.getText();
        if(isEmptyString(contentString)) {
            // even though there may be no text need to make sure all children are empty or can be pruned
            if (tagNode.isEmpty()) {
                return true;
            } else {
                for(Object child: tagNode.getAllChildren()) {
                    // TODO : similar check as in tagNode.isEmpty() argues for a visitor pattern
                    // but allow empty td, ths to be pruned.
                    if ( child instanceof TagNode) {
                        if (!satisfy((TagNode)child, true)) {
                            return false;
                        }
                    } else if (child instanceof ContentNode ) {
                        if ( !((ContentNode)child).isBlank()) {
                            return false;
                        }
                    } else {
                        return false;
                    }
                }
                return true;
            }
        }
    }
    return false;
}
 

import org.htmlcleaner.ContentNode; //导入依赖的package包/类
private boolean satisfy(TagNode tagNode, boolean override) {
    String name = tagNode.getName();
    TagInfo tagInfo = tagInfoProvider.getTagInfo(name);
    //Only _block_ elements can match.
    if (tagInfo != null && !hasIdAttributeSet(tagNode) && none != tagInfo.getDisplay() && !tagInfo.isEmptyTag() && (override || !unsafeBlockElements.contains(name))) {
        CharSequence contentString = tagNode.getText();
        if (isEmptyString(contentString)) {
            // even though there may be no text need to make sure all children are empty or can be pruned
            if (tagNode.isEmpty()) {
                return true;
            } else {
                for (Object child : tagNode.getAllChildren()) {
                    // TODO : similar check as in tagNode.isEmpty() argues for a visitor pattern
                    // but allow empty td, ths to be pruned.
                    if (child instanceof TagNode) {
                        if (!satisfy((TagNode) child, true)) {
                            return false;
                        }
                    } else if (child instanceof ContentNode) {
                        if (!((ContentNode) child).isBlank()) {
                            return false;
                        }
                    } else {
                        return false;
                    }
                }
                return true;
            }
        }
    }
    return false;
}