SearchFormatter.java

Go to the documentation of this file.

/*
 * Turró i Cutiller Foundation. License notice.
 * Copyright (C) 2011 Lluis Turró Cutiller <http://www.turro.org/>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program 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 Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
package org.turro.elephant.search;
 
import java.util.Stack;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class SearchFormatter {
  protected Stack lines;
  protected String query, reQuery;
  protected Pattern pat;
  protected int count, found = 0;
  protected boolean ignoreCase;
  
  public SearchFormatter(String query, boolean ignoreCase) {
    this.query = query;
    this.ignoreCase = ignoreCase;
    lines = new Stack();
    reQuery = queryToRegExp(query);
    pat = Pattern.compile(reQuery);    
  }
  
  public void processLine(String line) {
    if(line == null) return;
    line = removeHTMLTag(line, "script");
    line = removeHTMLTag(line, "style");
    line = removeHTML(line);
    line = removeMacros(line);
    Matcher mat = pat.matcher(line);
    int lfound = 0;
    while(mat.find()) {
      lfound++;
    }
    if(lfound > 0) {
      line = line.replaceAll("(" + reQuery + ")", "<span class='found'>$1</span>");
      lines.push(line);
      found += lfound;
    }
  }
  
  public boolean wasFound() {
    return lines.size() > 0;
  }
  
  public String getResult() {
    String result = "";
    for(int i = 0; i < lines.size(); i++) {
      result += lines.get(i) + "<br/>";
    }
    return result;
  }
  
  public int getFound() {
    return found;
  }
 
  public String queryToRegExp(String query) {
    if(query == null) return "";
    String[] values = query.split("\\s+");
    count = values.length;
    String result = "(", sep = "";
    for(int i = 0; i < count; i++) {
      result += sep + "(" + values[i] + ")";
      sep = "|";
    }
    return (ignoreCase ? "(?i)" : "") + result + ")";
  }
  
  public static String queryToSQL(String field, String query, boolean ignoreCase) {
    String[] values = query.split("\\s+");
    String result = "(", sep = "";
    for(int i = 0; i < values.length; i++) {
      if(ignoreCase) {
        result += sep + "UCASE(" + field + ") LIKE '%" + values[i].toUpperCase() + "%' ";
      }
      else {
        result += sep + field + " LIKE '%" + values[i] + "%' ";
      }
      sep = "OR ";
    }
    return result + ")";
  }
  
  public static String removeHTML(String line) {
    return line.replaceAll("\\<\\/?[\\?a-zA-Z\\-\\:\\_0-9]+\\ ?.*?\\>", "");
  }
 
  public static String removeHTMLTag(String line, String string) {
    return line.replaceAll("\\<" + string + " .*?\\<\\/" + string + "\\>", "");
  }
 
  private static String removeMacros(String line) {
    return line.replaceAll("\\{\\@[\\?\\&a-zA-Z\\-\\:\\_0-9\\ \\.]+\\}", "");
  }
 
}