edkuksa/russianmorphology
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding licence

Browse Source 
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@14 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov
2009-04-14 07:47:27 +00:00
parent fe855dfa51
commit 3f26888bde
23 changed files with 541 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
src/test/java/org/apache/lucene/russian/morphology/RussianSuffixDecoderEncoderTest.java
View File

@ -1,39 +1,54 @@
/**
* 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.russian.morphology;
import org.junit.Test;
import static org.junit.Assert.assertThat;
import static org.hamcrest.core.IsEqual.equalTo;
import org.apache.lucene.russian.morphology.SuffixToLongException;
import static org.junit.Assert.assertThat;
import org.junit.Test;
import java.io.InputStream;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
public class RussianSuffixDecoderEncoderTest {
@Test
public void testShouldCorretDecodeEncode() throws IOException {
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/decoder-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream,"UTF-8"));
String s = bufferedReader.readLine();
while(s != null){
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/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(" ");
Long ecodedSuffix = RussianSuffixDecoderEncoder.encode(qa[0]);
assertThat(RussianSuffixDecoderEncoder.decode(ecodedSuffix),equalTo(qa[1]));
assertThat(RussianSuffixDecoderEncoder.decode(ecodedSuffix), equalTo(qa[1]));
s = bufferedReader.readLine();
}
}
@Test(expected = SuffixToLongException.class)
public void shouldThrownExeptionIfSuffixToLong(){
RussianSuffixDecoderEncoder.encode("1234567890123");
public void shouldThrownExeptionIfSuffixToLong() {
RussianSuffixDecoderEncoder.encode("1234567890123");
}
@Test(expected = WrongCharaterException.class)
public void shouldThrownExeptionIfSuffixContainWrongCharater(){
RussianSuffixDecoderEncoder.encode("1");
}
public void shouldThrownExeptionIfSuffixContainWrongCharater() {
RussianSuffixDecoderEncoder.encode("1");
}
}

43
src/test/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzerTest.java
View File

@ -1,13 +1,28 @@
/**
* 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.russian.morphology.analayzer;
import junit.framework.TestCase;
import org.junit.Test;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.junit.Test;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.BufferedReader;
import java.io.InputStreamReader;
@ -17,24 +32,22 @@ public class RussianMorphlogyAnalayzerTest {
public void shouldCorrectProccessText() throws IOException {
RussianMorphlogyAnalayzer morphlogyAnalayzer = new RussianMorphlogyAnalayzer();
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/russian-text.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream,"UTF-8"));
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
final Token reusableToken = new Token();
Token nextToken;
Token nextToken;
TokenStream in = morphlogyAnalayzer.tokenStream(null, bufferedReader);
for (;;)
{
nextToken = in.next(reusableToken);
for (; ;) {
nextToken = in.next(reusableToken);
if (nextToken == null)
{
break;
}
if (nextToken == null) {
break;
}
System.out.println(nextToken.term());
System.out.println(nextToken.term());
// nextSampleToken = sample.next(reusableSampleToken);
// assertEquals(
// "Unicode",
@ -42,7 +55,7 @@ public class RussianMorphlogyAnalayzerTest {
// nextSampleToken == null
// ? null
// : nextSampleToken.term());
}
}
}
}

38
src/test/java/org/apache/lucene/russian/morphology/analayzer/SuffixEvristicsTest.java
View File

@ -1,24 +1,42 @@
/**
* 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.russian.morphology.analayzer;
import org.junit.Test;
import static org.junit.Assert.assertThat;
import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
import static org.hamcrest.core.IsEqual.equalTo;
import static org.junit.Assert.assertThat;
import org.junit.Test;
import java.io.*;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
public class SuffixEvristicsTest {
@Test
public void testShouldDefineCorretCononicalWordForm() throws IOException {
SuffixEvristics suffixEvristics = new SuffixEvristics();
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/suffix-evristics-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream,"UTF-8"));
String s = bufferedReader.readLine();
while(s != null){
SuffixEvristics suffixEvristics = new SuffixEvristics();
InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/suffix-evristics-test-data.txt");
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
String s = bufferedReader.readLine();
while (s != null) {
String[] qa = s.trim().split(" ");
assertThat(suffixEvristics.getCanonicalForm(qa[0]),equalTo(qa[1]));
assertThat(suffixEvristics.getCanonicalForm(qa[0]), equalTo(qa[1]));
s = bufferedReader.readLine();
}
}

8
src/test/resources/org/apache/lucene/russian/morphology/analayzer/russian-text.txt
View File

@ -1,5 +1,3 @@
В условиях нарастающей пурги было сделано 4 успешных захода на посадку. После завершения облета и демонтажа оборудования
Рубен Есаян дал устную оценку эксперимента:"Все нормально, будем рекомендовать систему к внедрению".
Летом - с ноября по март - рейсы из Кейптауна (ЮАР) на станцию "Новолазаревская" (Антарктида) совершаются
примерно один раз в две недели. Туда привозят людей, питание, оборудование, ГСМ и т.д.
что-то
В условиях нарастающей пурги было сделано 4 успешных захода на посадку. "Все нормально, будем рекомендовать систему к внедрению".
Рейсы из Кейптауна (ЮАР) на станцию "Новолазаревская" (Антарктида) совершаются
примерно один раз в две недели.