FileDocCategorySizeDatePackage
AnalysisTest.javaAPI DocApache Lucene 2.1.02918Wed Feb 14 10:46:36 GMT 2007org.apache.lucene

AnalysisTest

public class AnalysisTest extends Object
Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You 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.

Fields Summary
Constructors Summary
Methods Summary
public static voidmain(java.lang.String[] args)

    try {
      test("This is a test", true);
      // FIXME: OG: what's with this hard-coded file name??
      test(new File("words.txt"), false);
    } catch (Exception e) {
      System.out.println(" caught a " + e.getClass() +
			 "\n with message: " + e.getMessage());
    }
  
static voidtest(java.io.File file, boolean verbose)

    long bytes = file.length();
    System.out.println(" Reading test file containing " + bytes + " bytes.");

    FileInputStream is = new FileInputStream(file);
    BufferedReader ir = new BufferedReader(new InputStreamReader(is));
    
    test(ir, verbose, bytes);

    ir.close();
  
static voidtest(java.lang.String text, boolean verbose)

    System.out.println(" Tokenizing string: " + text);
    test(new StringReader(text), verbose, text.length());
  
static voidtest(java.io.Reader reader, boolean verbose, long bytes)

    Analyzer analyzer = new SimpleAnalyzer();
    TokenStream stream = analyzer.tokenStream(null, reader);

    Date start = new Date();

    int count = 0;
    for (Token t = stream.next(); t!=null; t = stream.next()) {
      if (verbose) {
	System.out.println("Text=" + t.termText()
			   + " start=" + t.startOffset()
			   + " end=" + t.endOffset());
      }
      count++;
    }

    Date end = new Date();

    long time = end.getTime() - start.getTime();
    System.out.println(time + " milliseconds to extract " + count + " tokens");
    System.out.println((time*1000.0)/count + " microseconds/token");
    System.out.println((bytes * 1000.0 * 60.0 * 60.0)/(time * 1000000.0)
		       + " megabytes/hour");