This is an automated email from the ASF dual-hosted git repository.
mawiesne pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/opennlp-addons.git
The following commit(s) were added to refs/heads/main by this push:
new 0327b14 Bump org.apache.lucene:lucene-core from 6.0.0 to 7.7.3 (#83)
0327b14 is described below
commit 0327b142296379739fd3da5c2a692bd4e3cf8f0c
Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
AuthorDate: Mon May 26 12:05:01 2025 +0200
Bump org.apache.lucene:lucene-core from 6.0.0 to 7.7.3 (#83)
* Bump org.apache.lucene:lucene-core from 6.0.0 to 7.7.3
- bumps org.apache.lucene:lucene-core from 6.0.0 to 7.7.3.
- fixes compile errors due to package relocation since Lucene 7.x for
`CharArraySet` class
- introduces common Lucene property in geoentitylinker-addon's `pom.xml`
- optimizes imports in `GazetteerIndexer` and `GazetteerSearcher`
---
updated-dependencies:
- dependency-name: org.apache.lucene:lucene-core
dependency-version: 7.7.3
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <[email protected]>
* - fixes compile errors due to package relocation since Lucene 7.x for
CharArraySet class
- introduces common Lucene property in geoentitylinker-addon's pom.xml
- optimizes imports in GazetteerIndexer and GazetteerSearcher
---------
Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot]
<49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Martin Wiesner <[email protected]>
---
geoentitylinker-addon/pom.xml | 17 ++++++----
.../addons/geoentitylinker/GazetteerSearcher.java | 11 ++++---
.../geoentitylinker/indexing/GazetteerIndexer.java | 38 ++++++++++------------
3 files changed, 33 insertions(+), 33 deletions(-)
diff --git a/geoentitylinker-addon/pom.xml b/geoentitylinker-addon/pom.xml
index 35fc56c..ae0da35 100644
--- a/geoentitylinker-addon/pom.xml
+++ b/geoentitylinker-addon/pom.xml
@@ -33,6 +33,11 @@
<packaging>jar</packaging>
<name>Apache OpenNLP GeoentityLinker Addon</name>
+ <properties>
+ <lucene.version>7.7.3</lucene.version>
+ <spatial4j.version>0.5</spatial4j.version>
+ </properties>
+
<dependencies>
<dependency>
<groupId>org.apache.opennlp</groupId>
@@ -42,35 +47,33 @@
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
- <version>6.0.0</version>
+ <version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
- <version>6.0.0</version>
+ <version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
- <version>6.0.0</version>
+ <version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>com.spatial4j</groupId>
<artifactId>spatial4j</artifactId>
- <version>0.5</version>
- <type>jar</type>
+ <version>${spatial4j.version}</version>
</dependency>
+ <!-- TEST scope -->
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-api</artifactId>
</dependency>
-
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-engine</artifactId>
</dependency>
-
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-params</artifactId>
diff --git
a/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/GazetteerSearcher.java
b/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/GazetteerSearcher.java
index 804432a..19ebf4f 100644
---
a/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/GazetteerSearcher.java
+++
b/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/GazetteerSearcher.java
@@ -23,27 +23,28 @@ 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.CharArraySet;
+import org.apache.lucene.analysis.core.KeywordAnalyzer;
+import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.queryparser.classic.ParseException;
-
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.MMapDirectory;
-import opennlp.tools.entitylinker.EntityLinkerProperties;
-import org.apache.lucene.analysis.core.KeywordAnalyzer;
-import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
-import org.apache.lucene.analysis.util.CharArraySet;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
+import opennlp.tools.entitylinker.EntityLinkerProperties;
+
/**
*
* Searches Gazetteers stored in a MMapDirectory Lucene index. The structure of
diff --git
a/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/indexing/GazetteerIndexer.java
b/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/indexing/GazetteerIndexer.java
index a640c5d..394da00 100644
---
a/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/indexing/GazetteerIndexer.java
+++
b/geoentitylinker-addon/src/main/java/opennlp/addons/geoentitylinker/indexing/GazetteerIndexer.java
@@ -21,21 +21,24 @@ import java.io.FileWriter;
import java.io.IOException;
import java.nio.file.Paths;
import java.util.ArrayList;
-import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
-import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.MMapDirectory;
+import opennlp.addons.geoentitylinker.GeoEntityLinker;
+
/**
- * Creates two lucene indexes, geonames and usgs for use in GeoEntityLinker.
+ * Creates two lucene indexes, geonames and usgs for use in {@link
GeoEntityLinker}.
+ *
+ * @see GeoEntityLinker
*/
public class GazetteerIndexer {
@@ -143,16 +146,15 @@ public class GazetteerIndexer {
String indexloc = outputIndexDir.getPath() +
"/opennlp_geoentitylinker_gazetteer";
Directory index = new MMapDirectory(Paths.get(indexloc));
Analyzer a = new StandardAnalyzer(new CharArraySet(new ArrayList<>(),
true));
- Map<String, Analyzer> analyMap = new HashMap<>();
-
- analyMap.put("countrycode", new KeywordAnalyzer());
- analyMap.put("admincode", new KeywordAnalyzer());
- analyMap.put("loctype", new KeywordAnalyzer());
- analyMap.put("countycode", new KeywordAnalyzer());
- analyMap.put("gazsource", new KeywordAnalyzer());
-
- PerFieldAnalyzerWrapper aWrapper = new PerFieldAnalyzerWrapper(a,
analyMap);
- IndexWriterConfig config = new IndexWriterConfig(aWrapper);
+ Map<String, Analyzer> analyMap = Map.of(
+ "countcode", new KeywordAnalyzer(),
+ "admincode", new KeywordAnalyzer(),
+ "loctype", new KeywordAnalyzer(),
+ "countycode", new KeywordAnalyzer(),
+ "gazsource", new KeywordAnalyzer());
+
+ final PerFieldAnalyzerWrapper aWrapper = new PerFieldAnalyzerWrapper(a,
analyMap);
+ final IndexWriterConfig config = new IndexWriterConfig(aWrapper);
try (IndexWriter w = new IndexWriter(index, config)) {
//write the column headers for the countryContextFile
try (FileWriter writer = new FileWriter(outputCountryContextFile,
false)) {
@@ -192,14 +194,8 @@ public class GazetteerIndexer {
try {
GazetteerIndexer i = new GazetteerIndexer();
- i.index(geonamesData,
- geoNamesCountryInfo,
- geonamesAdmin1CodesASCII,
- usgsDataFile,
- usgsGovUnitsFile,
- outputIndexDir,
- outputCountryContextFile,
- regionsFile);
+ i.index(geonamesData, geoNamesCountryInfo, geonamesAdmin1CodesASCII,
+ usgsDataFile, usgsGovUnitsFile, outputIndexDir,
outputCountryContextFile, regionsFile);
} catch (Exception ex) {
ex.printStackTrace();
}
