taking into account word text statistics

git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@25 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
Alexander.A.Kuznetsov
2009-05-11 14:45:00 +00:00
parent c68fbb0827
commit ad97c3f275
11 changed files with 39705 additions and 7170 deletions

View File

@ -26,12 +26,12 @@ import java.io.InputStream;
import java.io.InputStreamReader;
public class SuffixEvristicsTest {
public class SuffixHeuristicTest {
@Test
public void testShouldDefineCorretCononicalWordForm() throws IOException {
SuffixHeuristic suffixHeuristic = new SuffixHeuristic();
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/suffix-evristics-test-data.txt");
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/suffix-heuristic-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
String s = bufferedReader.readLine();
while (s != null) {

View File

@ -4,4 +4,5 @@
победы победа
поэтическая поэтический
произошло произойти
test test
test test
ананасов ананас

View File

@ -9,7 +9,7 @@
заход
на
посадка
все
весь
нормальный
быть
рекомендовать
@ -25,7 +25,7 @@
новолазаревский
антарктида
совершаться
примерный
примерно
один
раз
в