[WIP]

.tool-versions

@@ -0,0 +1,3 @@
+elasticsearch 7.17.18
+java openjdk-17.0.2
+maven 3.9.0

Dockerfile

@@ -0,0 +1,13 @@
+ARG ES_VERSION=8.6.2
+FROM docker.elastic.co/elasticsearch/elasticsearch:${ES_VERSION}
+
+ARG ES_VERSION
+COPY --chown=elasticsearch:elasticsearch ./target/releases/elasticsearch-analysis-lemmagen-${ES_VERSION}-plugin.zip /tmp/elasticsearch-analysis-lemmagen-${ES_VERSION}-plugin.zip
+
+USER elasticsearch
+
+RUN elasticsearch-plugin install file:///tmp/elasticsearch-analysis-lemmagen-${ES_VERSION}-plugin.zip
+
+RUN mkdir -p /usr/share/elasticsearch/config/lemmagen && \
+    cd /usr/share/elasticsearch/config/lemmagen && \
+    curl -L https://github.com/vhyza/lemmagen-lexicons/raw/master/free/lexicons/en.lem -o en.lem

docker-compose.yml

@@ -0,0 +1,23 @@
+services:
+  elasticsearch:
+    # image: docker.elastic.co/elasticsearch/elasticsearch:8.6.2
+    build:
+      context: .
+      platforms:
+        - linux/amd64
+      args:
+        - ES_VERSION=8.6.2
+    ports:
+      - 9200:9200
+    environment:
+      - cluster.name=lemmagen-test
+      - bootstrap.memory_lock=true
+      - xpack.security.enabled=false
+      - xpack.security.http.ssl.enabled=false
+      - xpack.security.transport.ssl.enabled=false
+      - network.host=0.0.0.0
+      - discovery.type=single-node
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1

plugin-descriptor.properties

@@ -1,6 +1,6 @@
 description=Lemmatizer token filter
-version=${elasticsearch.version}
+version=${project.version}
 name=elasticsearch-analysis-lemmagen
 classname=org.elasticsearch.plugin.analysis.lemmagen.AnalysisLemmagenPlugin
 java.version=1.8
-elasticsearch.version=${plugin.version}
+elasticsearch.version=${elasticsearch.version}

pom.xml

@@ -7,12 +7,11 @@
   <modelVersion>4.0.0</modelVersion>
   <groupId>org.elasticsearch</groupId>
   <artifactId>elasticsearch-analysis-lemmagen</artifactId>
-  <version>8.6.1</version>
+  <version>8.6.2</version>
   <packaging>jar</packaging>
   <properties>
-    <plugin.version>8.6.1</plugin.version>
-    <lucene.version>9.4.2</lucene.version>
-    <elasticsearch.version>8.6.1</elasticsearch.version>
+    <elasticsearch.version>8.6.2</elasticsearch.version>
+    <plugin.version>${elasticsearch.version}</plugin.version>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
   </properties>
   <dependencies>
@@ -37,12 +36,6 @@
       <artifactId>slf4j-simple</artifactId>
       <version>1.6.2</version>
     </dependency>
-    <dependency>
-      <groupId>org.apache.lucene</groupId>
-      <artifactId>lucene-test-framework</artifactId>
-      <version>${lucene.version}</version>
-      <scope>test</scope>
-    </dependency>
     <dependency>
       <groupId>org.hamcrest</groupId>
       <artifactId>hamcrest-core</artifactId>
@@ -86,13 +79,13 @@
     <dependency>
       <groupId>org.apache.logging.log4j</groupId>
       <artifactId>log4j-core</artifactId>
-      <version>[2.16.0,)</version>
+      <version>2.23.1</version>
       <scope>test</scope>
     </dependency>
     <dependency>
       <groupId>org.apache.logging.log4j</groupId>
       <artifactId>log4j-api</artifactId>
-      <version>[2.16.0,)</version>
+      <version>2.23.1</version>
       <scope>test</scope>
     </dependency>
   </dependencies>
@@ -133,7 +126,7 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-surefire-plugin</artifactId>
-        <version>2.14</version>
+        <version>3.2.2</version>
         <configuration>
           <!-- disable security manager for tests -->
           <argLine>-Dtests.security.manager=false</argLine>

test.sh

@@ -0,0 +1,75 @@
+#!/bin/bash
+
+set -e
+
+# To clear possible old index
+curl -s -H "Content-Type: application/json" -X DELETE "http://localhost:9200/lemmagen-test" > /dev/null
+
+echo -e "--------------- CREATE INDEX ---------------\n"
+curl -f -H "Content-Type: application/json" -X PUT "http://localhost:9200/lemmagen-test" -d '{
+ "settings": {
+   "index": {
+     "analysis": {
+       "filter": {
+         "lemmagen_filter_en": {
+           "type": "lemmagen",
+           "lexicon": "en"
+         }
+       },
+       "analyzer": {
+         "lemmagen_en": {
+           "type": "custom",
+           "tokenizer": "uax_url_email",
+           "filter": [
+             "lemmagen_filter_en"
+           ]
+         }
+       }
+     }
+   }
+ },
+ "mappings": {
+   "properties": {
+     "text": {
+       "type": "text",
+       "analyzer": "lemmagen_en"
+     }
+   }
+ }
+}'
+
+echo -e "\n"
+echo -e "--------------- ANALYZE TEXT ---------------\n"
+curl -f -H "Content-Type: application/json" -X GET "http://localhost:9200/lemmagen-test/_analyze" -d '
+{
+  "text": "I am late.",
+  "analyzer": "lemmagen_en"
+}'
+
+echo -e "\n"
+echo -e "--------------- INDEX DOCUMENT ---------------\n"
+curl -f -H "Content-Type: application/json" -X PUT "http://localhost:9200/lemmagen-test/_doc/1?refresh=wait_for" -d '
+{
+  "user": "tester",
+  "published_at": "2013-11-15T14:12:12",
+  "text": "I am late."
+}'
+
+
+echo -e "\n"
+echo -e "--------------- SEARCH DOCUMENT ---------------\n"
+curl -f -H "Content-Type: application/json" -X GET "http://localhost:9200/lemmagen-test/_search" -d '
+{
+  "query": {
+    "match": {
+      "text": "is"
+    }
+  }
+}'
+
+echo -e "\n"
+echo -e "--------------- DELETE INDEX ---------------\n"
+curl -f -H "Content-Type: application/json" -X DELETE "http://localhost:9200/lemmagen-test"
+
+echo -e "\n"
+echo -e "👍 ALL DONE 👍\n"