com.jaeksoft.searchlib.parser.htmlParser.DomHtmlNode Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of opensearchserver Show documentation
Show all versions of opensearchserver Show documentation
OpenSearchServer is a powerful, enterprise-class, search engine program. Using the web user interface, the crawlers (web, file, database, ...) and the REST/RESTFul API you will be able to integrate quickly and easily advanced full-text search capabilities in your application. OpenSearchServer runs on Windows and Linux/Unix/BSD.
The newest version!
/**
* License Agreement for OpenSearchServer
*
* Copyright (C) 2012-2013 Emmanuel Keller / Jaeksoft
*
* http://www.open-search-server.com
*
* This file is part of OpenSearchServer.
*
* OpenSearchServer is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* OpenSearchServer is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with OpenSearchServer.
* If not, see .
**/
package com.jaeksoft.searchlib.parser.htmlParser;
import java.util.Collection;
import java.util.List;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpressionException;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import com.jaeksoft.searchlib.util.DomUtils;
import com.jaeksoft.searchlib.util.XPathParser;
public class DomHtmlNode extends HtmlNodeAbstract implements
HtmlDocumentProvider.XPath {
private XPathParser xPathParser = null;
public DomHtmlNode(Node node) {
super(node);
}
@Override
final public int countElements() {
return DomUtils.countElements(node);
}
@Override
public String getFirstTextNode(String... path) {
return DomUtils.getFirstTextNode(node, path);
}
@Override
public String getText() {
return DomUtils.getText(node);
}
@Override
public String getAttributeText(String name) {
return DomUtils.getAttributeText(node, name);
}
@Override
public void getNodes(List> nodes, String... path) {
List nodeList = DomUtils.getNodes(node, path);
for (Node node : nodeList)
nodes.add(new DomHtmlNode(node));
}
@Override
public List> getAllNodes(String... tags) {
List> nodes = getNewNodeList();
List nodeList = DomUtils.getAllNodes(node, tags);
for (Node node : nodeList)
nodes.add(new DomHtmlNode(node));
return nodes;
}
@Override
protected List> getNewChildNodes() {
List> nodes = getNewNodeList();
NodeList nodeList = node.getChildNodes();
int l = nodeList.getLength();
for (int i = 0; i < l; i++)
nodes.add(new DomHtmlNode(nodeList.item(i)));
return nodes;
}
@Override
public boolean isComment() {
return node.getNodeType() == Node.COMMENT_NODE;
}
@Override
public boolean isTextNode() {
return node.getNodeType() == Node.TEXT_NODE;
}
@Override
public String getNodeName() {
return node.getNodeName();
}
@Override
public String getAttribute(String name) {
return DomUtils.getAttributeText(node, name);
}
@Override
public void xPath(String xPath, Collection