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

Merge pull request #28 from MysterionRise/master

Browse Source 
update to Lucene 9.3
This commit is contained in:
Alexander Kuznetsov 2022-09-28 15:03:55 +03:00 committed by GitHub
commit 71af7f6f9d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 17 additions and 16 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 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 ### 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; package org.apache.lucene.morphology;
import org.apache.lucene.analysis.Analyzer; 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.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter; import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.TokenFilter; import org.apache.lucene.analysis.TokenFilter;
@ -41,7 +41,7 @@ import java.util.*;
import static org.hamcrest.Matchers.equalTo; import static org.hamcrest.Matchers.equalTo;
public class AnalyzersTest extends BaseTokenStreamTestCase { public class TestAnalyzers extends BaseTokenStreamTestCase {
@Test @Test
public void shouldGiveCorrectWordsForEnglish() throws IOException { 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; import static org.hamcrest.CoreMatchers.equalTo;
public class LuceneMorphTest { public class TestLuceneMorph {
@Test @Test
public void englishMorphologyShouldGetCorrectNormalForm() throws IOException { public void englishMorphologyShouldGetCorrectNormalForm() throws IOException {

4
pom.xml
View File

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

7
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; package org.apache.lucene.analysis.morphology;
import org.apache.lucene.analysis.TokenFilterFactory;
import org.apache.lucene.analysis.TokenStream; 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.LuceneMorphology;
import org.apache.lucene.morphology.analyzer.MorphologyFilter; import org.apache.lucene.morphology.analyzer.MorphologyFilter;
import org.apache.lucene.util.ResourceLoader;
import org.apache.lucene.util.ResourceLoaderAware;
import java.util.Map; import java.util.Map;

4
solr-morphology-analysis/src/test/java/org/apache/lucene/analysis/morphology/MorphologyFilterFactoryTest.java
View File

@ -15,11 +15,11 @@
*/ */
package org.apache.lucene.analysis.morphology; 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.LuceneMorphology;
import org.apache.lucene.morphology.english.EnglishLuceneMorphology; import org.apache.lucene.morphology.english.EnglishLuceneMorphology;
import org.apache.lucene.morphology.russian.RussianLuceneMorphology; 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.Assert;
import org.junit.Before; import org.junit.Before;
import org.junit.Test; import org.junit.Test;