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

update to Lucene 9.3

Browse Source
This commit is contained in:
Konstantin Perikov 2022-09-27 21:48:56 +01:00
parent 40fe59dd02
commit 1ecc7aaf9d
6 changed files with 21 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -1,6 +1,6 @@
# Russian Morphology for Apache Lucene
Russian and English morphology for Java and [Apache Lucene](http://lucene.apache.org) 8.7 framework based on open source dictionary from site [АОТ](http://aot.ru). It uses dictionary base morphology with some heuristics for unknown words. It supports a homonym for example for a Russian word "вина" it gives two variants "вино" and "вина".
Russian and English morphology for Java and [Apache Lucene](http://lucene.apache.org) 9.3 framework based on open source dictionary from site [АОТ](http://aot.ru). It uses dictionary base morphology with some heuristics for unknown words. It supports a homonym for example for a Russian word "вина" it gives two variants "вино" and "вина".
### How to use

4
dictionary-reader/src/test/java/org/apache/lucene/morphology/AnalyzersTest.java → dictionary-reader/src/test/java/org/apache/lucene/morphology/TestAnalyzers.java
View File

@ -16,7 +16,7 @@
package org.apache.lucene.morphology;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.TokenFilter;
@ -41,7 +41,7 @@ import java.util.*;
import static org.hamcrest.Matchers.equalTo;
public class AnalyzersTest extends BaseTokenStreamTestCase {
public class TestAnalyzers extends BaseTokenStreamTestCase {
@Test
public void shouldGiveCorrectWordsForEnglish() throws IOException {

2
dictionary-reader/src/test/java/org/apache/lucene/morphology/LuceneMorphTest.java → dictionary-reader/src/test/java/org/apache/lucene/morphology/TestLuceneMorph.java
View File

@ -33,7 +33,7 @@ import java.util.Set;
import static org.hamcrest.CoreMatchers.equalTo;
public class LuceneMorphTest {
public class TestLuceneMorph {
@Test
public void englishMorphologyShouldGetCorrectNormalForm() throws IOException {

4
pom.xml
View File

@ -16,7 +16,7 @@
</scm>
<properties>
<lucene.version>8.11.0</lucene.version>
<lucene.version>9.3.0</lucene.version>
<morphology.version>1.5</morphology.version>
<junit.version>4.13</junit.version>
</properties>
@ -56,7 +56,7 @@
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
<artifactId>lucene-analysis-common</artifactId>
<version>${lucene.version}</version>
</dependency>
</dependencies>

9
solr-morphology-analysis/src/main/java/org/apache/lucene/analysis/morphology/MorphologyFilterFactory.java
View File

@ -15,12 +15,13 @@
*/
package org.apache.lucene.analysis.morphology;
import org.apache.lucene.analysis.TokenFilterFactory;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.ResourceLoader;
import org.apache.lucene.analysis.util.ResourceLoaderAware;
import org.apache.lucene.analysis.util.TokenFilterFactory;
import org.apache.lucene.morphology.LuceneMorphology;
import org.apache.lucene.morphology.analyzer.MorphologyFilter;
import org.apache.lucene.util.ResourceLoader;
import org.apache.lucene.util.ResourceLoaderAware;
import java.util.Map;
@ -37,7 +38,7 @@ import java.util.Map;
* &lt;/analyzer&gt;
* &lt;/fieldType&gt;</pre>
*/
public class MorphologyFilterFactory extends TokenFilterFactory implements ResourceLoaderAware{
public class MorphologyFilterFactory extends TokenFilterFactory implements ResourceLoaderAware {
private static final String LANGUAGE_KEY = "language";

20
solr-morphology-analysis/src/test/java/org/apache/lucene/analysis/morphology/MorphologyFilterFactoryTest.java
View File

@ -1,12 +1,12 @@
/**
* Copyright 2009 Alexander Kuznetsov
*
* <p>
* 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
*
* <p>
* http://www.apache.org/licenses/LICENSE-2.0
* <p>
* 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.
@ -15,11 +15,11 @@
*/
package org.apache.lucene.analysis.morphology;
import org.apache.lucene.analysis.util.ClasspathResourceLoader;
import org.apache.lucene.analysis.util.ResourceLoader;
import org.apache.lucene.morphology.LuceneMorphology;
import org.apache.lucene.morphology.english.EnglishLuceneMorphology;
import org.apache.lucene.morphology.russian.RussianLuceneMorphology;
import org.apache.lucene.util.ClasspathResourceLoader;
import org.apache.lucene.util.ResourceLoader;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
@ -34,12 +34,12 @@ public class MorphologyFilterFactoryTest {
private Map<String, String> args;
@Before
public void setUp(){
public void setUp() {
args = new HashMap<>();
}
@Test
public void if_RussianLanguageKey_then_CreateRussianMorphologyFilter(){
public void if_RussianLanguageKey_then_CreateRussianMorphologyFilter() {
args.put(LANGUAGE_KEY, "Russian");
MorphologyFilterFactory morphologyFilterFactory = new MorphologyFilterFactory(args);
@ -51,7 +51,7 @@ public class MorphologyFilterFactoryTest {
}
@Test
public void if_EnglishLanguageKey_then_CreateEnglishMorphologyFilter(){
public void if_EnglishLanguageKey_then_CreateEnglishMorphologyFilter() {
args.put(LANGUAGE_KEY, "English");
MorphologyFilterFactory morphologyFilterFactory = new MorphologyFilterFactory(args);
@ -63,7 +63,7 @@ public class MorphologyFilterFactoryTest {
}
@Test
public void if_NoLanguageKey_then_CreateEnglishMorphologyFilter(){
public void if_NoLanguageKey_then_CreateEnglishMorphologyFilter() {
MorphologyFilterFactory morphologyFilterFactory = new MorphologyFilterFactory(args);
morphologyFilterFactory.inform(loader);