CustomAnalyzer.java

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.ArrayList;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Analyzer.TokenStreamComponents;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.ClassicTokenizer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.synonym.SolrSynonymParser;
import org.apache.lucene.analysis.synonym.SynonymFilter;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.analysis.util.ResourceLoader;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.Version;


public class CustomAnalyzer extends Analyzer {
  public static SynonymMap synmap;

	public CustomAnalyzer() throws IOException{
		ArrayList<String> list  = new ArrayList<String>();
		SynonymMap.Builder builder = new SynonymMap.Builder(true);
		  try (BufferedReader br = new BufferedReader(new FileReader("res/synonyms.txt")))
			{
				String sCurrentLine;
				while ((sCurrentLine = br.readLine()) != null) {
					list.add(sCurrentLine);
				}
			} catch (IOException e) {
				e.printStackTrace();
			}
		  int splitIndex = 0;
		  for(int i=0; i<list.size(); i++){ 
			  String s = list.get(i);
			  for(int j=0; j<s.length(); j++){
				   splitIndex = s.indexOf("=>");
			  }
			  if(splitIndex != -1){
				  String s1 = s.substring(0,splitIndex);
				  String s2 = s.substring(splitIndex, s.length());	
				  builder.add(new CharsRef(s1), new CharsRef(s2), true);
			  }
			 }
		  synmap = builder.build();
		  System.out.println("================ Custom analyzer built the synonym map =============== ");
	}
	@Override
	protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
	    Tokenizer source = new StandardTokenizer(Version.LUCENE_43, reader);
	    TokenStream filter = new StandardFilter(Version.LUCENE_43, source);
	    filter = new LowerCaseFilter(Version.LUCENE_43,filter);
	    filter = new SynonymFilter(filter, synmap, false);	
	    return new TokenStreamComponents(source, filter);
	}
}