adding some test create a full pacage for morphology

git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@52 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov 2009-10-04 09:23:40 +00:00
parent fed6cd480a
commit b95e7f59d5
5 changed files with 1607117 additions and 31 deletions

View File

@ -34,7 +34,7 @@ public class HeuristicBuilder {
RussianLetterDecoderEncoder decoderEncoder = new RussianLetterDecoderEncoder();
StatiticsCollector statiticsCollector = new StatiticsCollector(grammaInfo, decoderEncoder);
dictonaryReader.proccess(statiticsCollector);
statiticsCollector.saveHeuristic();
statiticsCollector.saveHeuristic("russian/src/main/resources/org/apache/lucene/morphology/russian/morph.info");
}
}

File diff suppressed because it is too large Load Diff

View File

@ -1,11 +1,26 @@
/**
* 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;
/**
* Created by IntelliJ IDEA.
* User: akuznetsov
* Date: 03/10/2009
* Time: 3:52:43 PM
* To change this template use File | Settings | File Templates.
*/
import org.junit.Test;
public class AnalayzerTest {
@Test
public void shoudGetCorrentTokens() {
}
}

View File

@ -1,30 +1,73 @@
/**
* 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 junit.framework.TestCase;
import org.apache.lucene.morphology.SuffixToLongException;
import org.apache.lucene.morphology.WrongCharaterException;
import static org.hamcrest.core.IsEqual.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;
public class RussianLetterDecoderEncoderTest extends TestCase {
public void testEncode() {
// Add your code here
public class RussianLetterDecoderEncoderTest {
private RussianLetterDecoderEncoder decoderEncoder;
@Before
public void setUp() {
decoderEncoder = new RussianLetterDecoderEncoder();
}
public void testEncodeToArray() {
// Add your code here
@Test
public void testShouldCorretDecodeEncode() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/decoder-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
Integer ecodedSuffix = decoderEncoder.encode(qa[0]);
assertThat(decoderEncoder.decode(ecodedSuffix), equalTo(qa[1]));
s = bufferedReader.readLine();
}
}
public void testDecodeArray() {
// Add your code here
@Test
public void testShouldCorretDecodeEncodeStringToArray() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/morphology/russian/decoder-test-data-for-array.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
int[] ecodedSuffix = decoderEncoder.encodeToArray(qa[0]);
assertThat(decoderEncoder.decodeArray(ecodedSuffix), equalTo(qa[1]));
s = bufferedReader.readLine();
}
}
public void testDecode() {
// Add your code here
@Test(expected = SuffixToLongException.class)
public void shouldThrownExeptionIfSuffixToLong() {
decoderEncoder.encode("1234567890123");
}
public void testCheckCharacter() {
// Add your code here
}
public void testCleanString() {
// Add your code here
@Test(expected = WrongCharaterException.class)
public void shouldThrownExeptionIfSuffixContainWrongCharater() {
decoderEncoder.encode("1");
}
}

View File

@ -1,11 +1,26 @@
/**
* 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;
/**
* Created by IntelliJ IDEA.
* User: akuznetsov
* Date: 03/10/2009
* Time: 3:52:18 PM
* To change this template use File | Settings | File Templates.
*/
import org.junit.Test;
public class RussianMorphTest {
@Test
public void shoudGetCorrentMorphInfo() {
}
}