testisolatin1accentfilter.java

来自「一套java版本的搜索引擎源码」· Java 代码 · 共 84 行

package org.apache.lucene.analysis;

import junit.framework.TestCase;

import java.io.StringReader;

public class TestISOLatin1AccentFilter extends TestCase {
  public void testU() throws Exception {
    TokenStream stream = new WhitespaceTokenizer(new StringReader("Des mot clés À LA CHAÎNE À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö Ø Œ Þ Ù Ú Û Ü Ý Ÿ à á â ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø œ ß þ ù ú û ü ý ÿ"));
    ISOLatin1AccentFilter filter = new ISOLatin1AccentFilter(stream);
    assertEquals("Des", filter.next().termText());
    assertEquals("mot", filter.next().termText());
    assertEquals("cles", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("LA", filter.next().termText());
    assertEquals("CHAINE", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("A", filter.next().termText());
    assertEquals("AE", filter.next().termText());
    assertEquals("C", filter.next().termText());
    assertEquals("E", filter.next().termText());
    assertEquals("E", filter.next().termText());
    assertEquals("E", filter.next().termText());
    assertEquals("E", filter.next().termText());
    assertEquals("I", filter.next().termText());
    assertEquals("I", filter.next().termText());
    assertEquals("I", filter.next().termText());
    assertEquals("I", filter.next().termText());
    assertEquals("D", filter.next().termText());
    assertEquals("N", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("O", filter.next().termText());
    assertEquals("OE", filter.next().termText());
    assertEquals("TH", filter.next().termText());
    assertEquals("U", filter.next().termText());
    assertEquals("U", filter.next().termText());
    assertEquals("U", filter.next().termText());
    assertEquals("U", filter.next().termText());
    assertEquals("Y", filter.next().termText());
    assertEquals("Y", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("a", filter.next().termText());
    assertEquals("ae", filter.next().termText());
    assertEquals("c", filter.next().termText());
    assertEquals("e", filter.next().termText());
    assertEquals("e", filter.next().termText());
    assertEquals("e", filter.next().termText());
    assertEquals("e", filter.next().termText());
    assertEquals("i", filter.next().termText());
    assertEquals("i", filter.next().termText());
    assertEquals("i", filter.next().termText());
    assertEquals("i", filter.next().termText());
    assertEquals("d", filter.next().termText());
    assertEquals("n", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("o", filter.next().termText());
    assertEquals("oe", filter.next().termText());
    assertEquals("ss", filter.next().termText());
    assertEquals("th", filter.next().termText());
    assertEquals("u", filter.next().termText());
    assertEquals("u", filter.next().termText());
    assertEquals("u", filter.next().termText());
    assertEquals("u", filter.next().termText());
    assertEquals("y", filter.next().termText());
    assertEquals("y", filter.next().termText());
    assertNull(filter.next());
  }
}