fixing some spelling errors
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@100 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
@ -1,59 +0,0 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.
|
||||
*/
|
||||
package org.apache.lucene.morphology.russian;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
|
||||
import static org.hamcrest.Matchers.equalTo;
|
||||
import static org.junit.Assert.assertThat;
|
||||
import org.junit.Test;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.util.Arrays;
|
||||
import java.util.HashSet;
|
||||
|
||||
|
||||
public class RussianAnalayzerTest {
|
||||
|
||||
@Test
|
||||
public void shoudGiveCorretWords() throws IOException {
|
||||
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/russian-analayzer-answer.txt");
|
||||
BufferedReader breader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
|
||||
String[] strings = breader.readLine().replaceAll(" +", " ").trim().split(" ");
|
||||
HashSet<String> answer = new HashSet<String>(Arrays.asList(strings));
|
||||
stream.close();
|
||||
|
||||
RussianAnalyzer morphlogyAnalyzer = new RussianAnalyzer();
|
||||
stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/russian-analayzer-data.txt");
|
||||
|
||||
InputStreamReader reader = new InputStreamReader(stream, "UTF-8");
|
||||
|
||||
TokenStream tokenStream = morphlogyAnalyzer.tokenStream(null, reader);
|
||||
HashSet<String> result = new HashSet<String>();
|
||||
while (tokenStream.incrementToken()) {
|
||||
TermAttribute attribute1 = tokenStream.getAttribute(TermAttribute.class);
|
||||
result.add(attribute1.term());
|
||||
}
|
||||
|
||||
stream.close();
|
||||
|
||||
assertThat(result, equalTo(answer));
|
||||
}
|
||||
}
|
||||
|
@ -1,55 +0,0 @@
|
||||
/**
|
||||
* Copyright 2009 Alexander Kuznetsov
|
||||
*
|
||||
* Licensed 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.
|
||||
*/
|
||||
package org.apache.lucene.morphology.russian;
|
||||
|
||||
import org.apache.lucene.morphology.LuceneMorphology;
|
||||
import static org.hamcrest.Matchers.equalTo;
|
||||
import static org.junit.Assert.assertThat;
|
||||
import org.junit.Before;
|
||||
import org.junit.Test;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.util.HashSet;
|
||||
import java.util.Set;
|
||||
|
||||
public class RussianLuceneMorphTest {
|
||||
private LuceneMorphology luceneMorph;
|
||||
|
||||
@Before
|
||||
public void setUp() throws IOException {
|
||||
luceneMorph = new LuceneMorphology(this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/morph.info"), new RussianLetterDecoderEncoder());
|
||||
}
|
||||
|
||||
@Test
|
||||
public void shoudGetCorrentMorphInfo() throws IOException {
|
||||
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/russian-morphology-test.txt");
|
||||
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
|
||||
String s = bufferedReader.readLine();
|
||||
while (s != null) {
|
||||
String[] qa = s.trim().split(" ");
|
||||
Set<String> result = new HashSet<String>();
|
||||
for (int i = 1; i < qa.length; i++) {
|
||||
result.add(qa[i]);
|
||||
}
|
||||
Set<String> stringList = new HashSet<String>(luceneMorph.getNormalForms(qa[0]));
|
||||
assertThat(stringList, equalTo(result));
|
||||
s = bufferedReader.readLine();
|
||||
}
|
||||
}
|
||||
}
|
@ -1 +0,0 @@
|
||||
в результат крушение погибнуть командир отряд специальный назначение пря при переть гувд ростовский область полковник милиция михаил перов и предприниматель
|
@ -1 +0,0 @@
|
||||
В результате крушения погибли командир отряда специального назначения при ГУВД Ростовской области полковник милиции Михаил Перов и предприниматель
|
@ -1,19 +0,0 @@
|
||||
еду еда ехать
|
||||
тестов тест
|
||||
вина вино вина
|
||||
вино вино
|
||||
ехать ехать
|
||||
ананасов ананас ананасовый
|
||||
сухой сухой
|
||||
дураков дурак
|
||||
пушка пушка пушок
|
||||
пушок пушок
|
||||
пушек пушка
|
||||
козлов козлов козловый козел
|
||||
жуков жуков жук
|
||||
красив красить красивый
|
||||
красивая красивый
|
||||
тосклив тоскливый
|
||||
лучший хороший
|
||||
на на
|
||||
тест тест тесто
|
Reference in New Issue
Block a user