/*
* Copyright 2013 Eolya Consulting - http://www.eolya.fr/
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package fr.eolya.extraction.htmlformater;
import org.jsoup.Jsoup;
import org.jsoup.helper.StringUtil;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
/**
* HTML to plain-text formatter.
* This simple implementation demonstrates the use of jsoup to convert HTML input to lightly-formatted
* plain-text.
* <p/>
*
* @author Eolya Consulting - http://www.eolya.fr/
*/
public class HtmlToPlaintTextSimple implements IHtmlFormater {
/**
* {@inheritDoc}
*/
public String getPlainText(String html) {
Document doc = Jsoup.parse(html);
if (doc==null) return null;
FormattingVisitor formatter = new FormattingVisitor();
NodeTraversor traversor = new NodeTraversor(formatter);
traversor.traverse(doc); // walk the DOM, and call .head() and .tail() for each node
return formatter.toString();
}
// the formatting rules, implemented in a breadth-first DOM traverse
private class FormattingVisitor implements NodeVisitor {
private static final int maxWidth = 80;
private int width = 0;
private StringBuilder accum = new StringBuilder(); // holds the accumulated text
// hit when the node is first seen
public void head(Node node, int depth) {
String name = node.nodeName();
if (node instanceof TextNode)
append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
else if (name.equals("li"))
append("\n * ");
}
// hit when all of the node's children (if any) have been visited
public void tail(Node node, int depth) {
String name = node.nodeName();
if (name.equals("br"))
append("\n");
else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5"))
append("\n\n");
else if (name.equals("a"))
append(String.format(" <%s>", node.absUrl("href")));
}
// appends text to the string builder with a simple word wrap method
private void append(String text) {
if (text.startsWith("\n"))
width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
if (text.equals(" ") &&
(accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
return; // don't accumulate long runs of empty spaces
if (text.length() + width > maxWidth) { // won't fit, needs to wrap
String words[] = text.split("\\s+");
for (int i = 0; i < words.length; i++) {
String word = words[i];
boolean last = i == words.length - 1;
if (!last) // insert a space if not the last word
word = word + " ";
if (word.length() + width > maxWidth) { // wrap and reset counter
accum.append("\n").append(word);
width = word.length();
} else {
accum.append(word);
width += word.length();
}
}
} else { // fits as is, without need to wrap text
accum.append(text);
width += text.length();
}
}
public String toString() {
return accum.toString();
}
}
}