iSharkFly-Docs
/
java-tutorials
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #5068 from Doha2012/master 

lucene analyzers
This commit is contained in:
Loredana Crusoveanu 2018-08-26 10:16:31 +03:00 committed by GitHub
parent 5c6ebc0f46 1613d21656
commit 24b6f662d8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 183 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lucene/pom.xml
View File

@ -23,6 +23,12 @@
<artifactId>lucene-queryparser</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
<version>${lucene.version}</version>
</dependency>
</dependencies>
<properties>
@ -32,7 +38,7 @@
<hibernate-jpa-2.1-api.version>1.0.0.Final</hibernate-jpa-2.1-api.version>
<!-- delombok maven plugin -->
<delombok-maven-plugin.version>1.16.10.0</delombok-maven-plugin.version>
<lucene.version>7.1.0</lucene.version>
<lucene.version>7.4.0</lucene.version>
</properties>
</project>

6
lucene/src/main/java/com/baeldung/lucene/InMemoryLuceneIndex.java
View File

@ -4,7 +4,7 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.SortedDocValuesField;
@ -27,9 +27,9 @@ import org.apache.lucene.util.BytesRef;
public class InMemoryLuceneIndex {
private Directory memoryIndex;
private StandardAnalyzer analyzer;
private Analyzer analyzer;
public InMemoryLuceneIndex(Directory memoryIndex, StandardAnalyzer analyzer) {
public InMemoryLuceneIndex(Directory memoryIndex, Analyzer analyzer) {
super();
this.memoryIndex = memoryIndex;
this.analyzer = analyzer;

26
lucene/src/main/java/com/baeldung/lucene/MyCustomAnalyzer.java Normal file
View File

@ -0,0 +1,26 @@
package com.baeldung.lucene;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.miscellaneous.CapitalizationFilter;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
public class MyCustomAnalyzer extends Analyzer{
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final StandardTokenizer src = new StandardTokenizer();
TokenStream result = new StandardFilter(src);
result = new LowerCaseFilter(result);
result = new StopFilter(result, StandardAnalyzer.STOP_WORDS_SET);
result = new PorterStemFilter(result);
result = new CapitalizationFilter(result);
return new TokenStreamComponents(src, result);
}
}

147
lucene/src/test/java/com/baeldung/lucene/LuceneAnalyzerIntegrationTest.java Normal file
View File

@ -0,0 +1,147 @@
package com.baeldung.lucene;
import static org.hamcrest.MatcherAssert.assertThat;
import static org.hamcrest.collection.IsIterableContainingInOrder.contains;
import static org.junit.Assert.assertEquals;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.custom.CustomAnalyzer;
import org.apache.lucene.analysis.en.EnglishAnalyzer;
import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.RAMDirectory;
import org.junit.Test;
public class LuceneAnalyzerIntegrationTest {
private static final String SAMPLE_TEXT = "This is baeldung.com Lucene Analyzers test";
private static final String FIELD_NAME = "sampleName";
@Test
public void whenUseStandardAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new StandardAnalyzer());
assertThat(result, contains("baeldung.com", "lucene", "analyzers", "test"));
}
@Test
public void whenUseStopAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new StopAnalyzer());
assertThat(result, contains("baeldung", "com", "lucene", "analyzers", "test"));
}
@Test
public void whenUseSimpleAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new SimpleAnalyzer());
assertThat(result, contains("this", "is", "baeldung", "com", "lucene", "analyzers", "test"));
}
@Test
public void whenUseWhiteSpaceAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new WhitespaceAnalyzer());
assertThat(result, contains("This", "is", "baeldung.com", "Lucene", "Analyzers", "test"));
}
@Test
public void whenUseKeywordAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new KeywordAnalyzer());
assertThat(result, contains("This is baeldung.com Lucene Analyzers test"));
}
@Test
public void whenUseEnglishAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new EnglishAnalyzer());
assertThat(result, contains("baeldung.com", "lucen", "analyz", "test"));
}
@Test
public void whenUseCustomAnalyzerBuilder_thenAnalyzed() throws IOException {
Analyzer analyzer = CustomAnalyzer.builder()
.withTokenizer("standard")
.addTokenFilter("lowercase")
.addTokenFilter("stop")
.addTokenFilter("porterstem")
.addTokenFilter("capitalization")
.build();
List<String> result = analyze(SAMPLE_TEXT, analyzer);
assertThat(result, contains("Baeldung.com", "Lucen", "Analyz", "Test"));
}
@Test
public void whenUseCustomAnalyzer_thenAnalyzed() throws IOException {
List<String> result = analyze(SAMPLE_TEXT, new MyCustomAnalyzer());
assertThat(result, contains("Baeldung.com", "Lucen", "Analyz", "Test"));
}
// ================= usage example
@Test
public void givenTermQuery_whenUseCustomAnalyzer_thenCorrect() {
InMemoryLuceneIndex luceneIndex = new InMemoryLuceneIndex(new RAMDirectory(), new MyCustomAnalyzer());
luceneIndex.indexDocument("introduction", "introduction to lucene");
luceneIndex.indexDocument("analyzers", "guide to lucene analyzers");
Query query = new TermQuery(new Term("body", "Introduct"));
List<Document> documents = luceneIndex.searchIndex(query);
assertEquals(1, documents.size());
}
@Test
public void givenTermQuery_whenUsePerFieldAnalyzerWrapper_thenCorrect() {
Map<String,Analyzer> analyzerMap = new HashMap<>();
analyzerMap.put("title", new MyCustomAnalyzer());
analyzerMap.put("body", new EnglishAnalyzer());
PerFieldAnalyzerWrapper wrapper =
new PerFieldAnalyzerWrapper(new StandardAnalyzer(), analyzerMap);
InMemoryLuceneIndex luceneIndex = new InMemoryLuceneIndex(new RAMDirectory(), wrapper);
luceneIndex.indexDocument("introduction", "introduction to lucene");
luceneIndex.indexDocument("analyzers", "guide to lucene analyzers");
Query query = new TermQuery(new Term("body", "introduct"));
List<Document> documents = luceneIndex.searchIndex(query);
assertEquals(1, documents.size());
query = new TermQuery(new Term("title", "Introduct"));
documents = luceneIndex.searchIndex(query);
assertEquals(1, documents.size());
}
// ===================================================================
public List<String> analyze(String text, Analyzer analyzer) throws IOException {
List<String> result = new ArrayList<String>();
TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, text);
CharTermAttribute attr = tokenStream.addAttribute(CharTermAttribute.class);
tokenStream.reset();
while (tokenStream.incrementToken()) {
result.add(attr.toString());
}
return result;
}
}