com.flamenk.article.Article Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of flamenk Show documentation
Flamenk is an srticle extractor, extracts the article present in a web page.
The newest version!
/*
 * Copyright 2013 Torindo Nesci.
 *
 * 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 com.flamenk.article;

import com.google.common.base.Optional;
import com.google.common.base.Preconditions;
import java.net.URL;

/**
 *
 * The article extracted from the html page.
 *
 * 

This implementation is Thread Safe.
 *
 * @author Torindo Nesci
 */
public class Article {
  
  private volatile String mTitle;
  private volatile String mImageUrl;
  private volatile String mBody;
  private final URL mUrl;
  private volatile long mProcessingTime;
  
  Article(URL url) {
    Preconditions.checkNotNull(url);
    
    this.mUrl = url;
  }
  
  void setProcessingTime(long time) {
    Preconditions.checkArgument(time >= 0);
    
    this.mProcessingTime = time;
  }
  
  /**
   * Returns the processing time in milliseconds taken to extract this article.
   * In this time is excluded:
   * 
   *  the time to pull the html from the network.
   *  the time to parse the html page.
   * 
   *
   * @return The processing time.
   */
  public long getProcessingTime() {
    return this.mProcessingTime;
  }
  
  /**
   * Returns the url.
   *
   * @return The url.
   */
  public URL getUrl() {
    return this.mUrl;
  }
  
  /**
   * Returns the document body, it can have html tokens.
   *
   * @return The document body.
   */
  public Optional getBody() {
    return optionalOf(this.mBody);
  }
  
  /**
   * Sets the article body, it can have html tokens.
   *
   * @param body The article body.
   */
  void setBody(String body) {
    Preconditions.checkNotNull(body);
    
    this.mBody = body;
  }
  
  /**
   * Sets the article title, it cannot have html tags.
   *
   * @param title The article title
   */
  void setTitle(String title) {
    Preconditions.checkNotNull(title);
    
    this.mTitle = title;
  }
  
  /**
   * Returns the article title, it cannot have html tags.
   *
   * @return The article title.
   */
  public Optional getTitle() {
    return optionalOf(this.mTitle);
  }
  
  /**
   * Sets the article main image url.
   *
   * @param url The article main image url.
   */
  void setMainImageUrl(String url) {
    Preconditions.checkNotNull(url);
    
    this.mImageUrl = url;
  }
  
  /**
   * Returns the article main image url.
   *
   * @return The article main image url.
   */
  public Optional getMainImageUrl() {
    return optionalOf(this.mImageUrl);
  }
  
  private  Optional optionalOf(T obj) {
    if (isNullOrEmpty(obj)) {
      return Optional.absent();
    }
    
    return Optional.of(obj);
  }
  
  private boolean isNullOrEmpty(Object obj) {
    if (obj == null) {
      return true;
    }
    if (obj instanceof String) {
      return ((String) obj).isEmpty();
    }
    return false;
  }
  
}