Docker容器部署Elasticsearch并配置分词器的方法实现

# 拉取指定版本（建议使用7.x或8.x稳定版）
docker pull elasticsearch:7.17.20
# 验证镜像
docker images | grep elasticsearch

# 创建数据、配置、插件、日志目录
mkdir -p /opt/es/{data,config,plugins,logs}
# 设置权限（ES容器以uid:1000用户运行）
chown -R 1000:1000 /opt/es

cluster.name: "docker-cluster"
network.host: 0.0.0.0
http.port: 9200
discovery.type: single-node
xpack.security.enabled: false
http.cors.enabled: true
http.cors.allow-origin: "*"

docker run -d \
  --name elasticsearch \
  -p 9200:9200 \
  -p 9300:9300 \
  -e "discovery.type=single-node" \
  -e "ES_JAVA_OPTS=-Xms512m -Xmx512m" \
  -v /opt/es/config/elasticsearch.yml:/usr/share/elasticsearch/config/elasticsearch.yml \
  -v /opt/es/data:/usr/share/elasticsearch/data \
  -v /opt/es/plugins:/usr/share/elasticsearch/plugins \
  -v /opt/es/logs:/usr/share/elasticsearch/logs \
  --restart=unless-stopped \
  elasticsearch:7.17.20

# 检查容器状态
docker ps | grep elasticsearch
# 测试ES服务
curl http://localhost:9200

{
  "name" : "node-1",
  "cluster_name" : "docker-cluster",
  "version" : { "number" : "7.17.20" }
}

# 进入容器
docker exec -it elasticsearch /bin/bash
# 在线安装IK（版本需与ES完全一致）
./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.17.20/elasticsearch-analysis-ik-7.17.20.zip
# 退出并重启
exit
docker restart elasticsearch

# 1. 下载对应版本的IK插件包
cd /opt/es/plugins
wget https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.17.20/elasticsearch-analysis-ik-7.17.20.zip

# 2. 解压到ik目录
unzip elasticsearch-analysis-ik-7.17.20.zip -d ik
rm -f elasticsearch-analysis-ik-7.17.20.zip

# 3. 设置权限
chown -R 1000:1000 /opt/es/plugins/ik

# 4. 重启容器
docker restart elasticsearch

FROM elasticsearch:7.17.20
COPY elasticsearch-analysis-ik-7.17.20.zip /tmp/
RUN ./bin/elasticsearch-plugin install -b file:///tmp/elasticsearch-analysis-ik-7.17.20.zip

docker build -t elasticsearch-with-ik:7.17.20 .
docker run -d --name elasticsearch -p 9200:9200 elasticsearch-with-ik:7.17.20

docker exec -it elasticsearch ./bin/elasticsearch-plugin list

curl -X POST "http://localhost:9200/_analyze" -H "Content-Type: application/json" -d'
{
  "analyzer": "ik_max_word",
  "text": "中华人民共和国国徽"
}'

{
  "tokens": [
    {"token": "中华人民共和国", "position": 0},
    {"token": "中华人民", "position": 1},
    {"token": "中华", "position": 2},
    {"token": "华人", "position": 3},
    {"token": "人民共和国", "position": 4},
    {"token": "人民", "position": 5},
    {"token": "共和国", "position": 6},
    {"token": "共和", "position": 7},
    {"token": "国", "position": 8},
    {"token": "国徽", "position": 9}
  ]
}

# 测试ik_smart（最少切分）
curl -X POST "http://localhost:9200/_analyze" -H "Content-Type: application/json" -d'
{
  "analyzer": "ik_smart",
  "text": "中华人民共和国国徽"
}'

# 查看插件目录挂载位置
docker inspect elasticsearch | grep -A 10 "Mounts"

# 进入容器
docker exec -it elasticsearch /bin/bash
# 编辑配置文件
vi /usr/share/elasticsearch/config/analysis-ik/IKAnalyzer.cfg.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
    <comment>IK Analyzer 扩展配置</comment>
    <!-- 自定义扩展词典 -->
    <entry key="ext_dict">ext_dict.dic</entry>
    <!-- 自定义停用词词典 -->
    <entry key="ext_stopwords">stopword.dic</entry>
</properties>

# 进入配置目录
cd /usr/share/elasticsearch/config/analysis-ik/
# 创建扩展词典（每行一个词）
echo "传智播客" >> ext_dict.dic
echo "奥力给" >> ext_dict.dic
echo "人工智能" >> ext_dict.dic
# 创建停用词词典
echo "的" >> stopword.dic
echo "了" >> stopword.dic
echo "呢" >> stopword.dic
# 退出容器
exit
# 重启ES
docker restart elasticsearch

# 1. 从容器复制默认配置到宿主机
docker cp elasticsearch:/usr/share/elasticsearch/config/analysis-ik ./analysis-ik-config
# 2. 修改宿主机上的配置文件
vi ./analysis-ik-config/IKAnalyzer.cfg.xml
echo "自定义词汇" >> ./analysis-ik-config/ext_dict.dic
# 3. 重新挂载启动（挂载配置目录）
docker run -d \
  --name elasticsearch \
  -p 9200:9200 \
  -v /opt/es/config/elasticsearch.yml:/usr/share/elasticsearch/config/elasticsearch.yml \
  -v /opt/es/data:/usr/share/elasticsearch/data \
  -v /opt/es/plugins:/usr/share/elasticsearch/plugins \
  -v /opt/es/logs:/usr/share/elasticsearch/logs \
  -v $(pwd)/analysis-ik-config:/usr/share/elasticsearch/config/analysis-ik \
  elasticsearch:7.17.20

curl -X POST "http://localhost:9200/_analyze" -H "Content-Type: application/json" -d'
{
  "analyzer": "ik_max_word",
  "text": "传智播客Java就业率超过95%,奥力给！"
}'

# 查看错误日志
docker logs elasticsearch
# 常见原因：
# 1. IK版本与ES版本不匹配 → 重新下载匹配版本
# 2. 插件目录权限不足 → chown -R 1000:1000 /opt/es/plugins
# 3. 内存不足 → 调整ES_JAVA_OPTS=-Xms256m -Xmx256m

# 检查插件是否安装成功
docker exec -it elasticsearch ./bin/elasticsearch-plugin list

# 检查文件编码（必须是UTF-8，无BOM）
file -bi /opt/es/plugins/ik/config/*.dic

# 查看ES日志确认词典加载
docker logs elasticsearch 2>&1 | grep -i "dic"
# 预期输出：
# [INFO] loading ext_dict.dic
# [INFO] loading stopword.dic