Elasticsearch docker安装ik插件及预设分词器

2018-06-15

Elasticsearch

> 在使用Elasticsearch时处理中文内容时，需要安装额外的解析器来处理中文分词。

# 制作带分词插件的镜像

以ik为例：

```Dockerfile
ARG ELK_VERSION=6.2.2
FROM docker.elastic.co/elasticsearch/elasticsearch-oss:$ELK_VERSION

ARG ELK_VERSION
RUN ./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v$ELK_VERSION/elasticsearch-analysis-ik-$ELK_VERSION.zip
```

# 使用template设置index的默认mapping

```
PUT /_template/template_1
{
 "index_patterns" : ["*"],
 "settings": {
 "analysis": {
 "analyzer": {
 "my_custom_analyzer": {
 "type": "custom",
 "tokenizer": "ik_max_word",
 "char_filter": [
 "html_strip"
 ],
 "filter": [
 "lowercase",
 "asciifolding"
 ]
 }
 }
 }
 },
 "mappings": {
 "doc": {
 "properties": {
 "content": { 
 "type": "text",
 "fields": {
 "keyword": {
 "type": "keyword",
 "ignore_above": 256
 }
 },
 "analyzer": "my_custom_analyzer"
 },
 "title": { 
 "type": "text",
 "fields": {
 "keyword": {
 "type": "keyword",
 "ignore_above": 256
 }
 },
 "analyzer": "my_custom_analyzer"
 },
 "description": { 
 "type": "text",
 "fields": {
 "keyword": {
 "type": "keyword",
 "ignore_above": 256
 }
 },
 "analyzer": "my_custom_analyzer"
 }
 }
 }
 }
}
```

# 使用reindex功能重新索引数据

如果配置之前数据已经存在elasticsearch中，则可以用reindex功能来重新索引数据

1. 

```
POST _reindex
{
 "source": {
 "index": "origin_index"
 },
 "dest": {
 "index": "new_index"
 }
}
```

2. 

```
delete origin_index
```

3.

```
POST _reindex
{
 "source": {
 "index": "new_index"
 },
 "dest": {
 "index": "origin_index"
 }
}
```

# 使用template查询

```
GET origin_index/_search/template
{
 "source" : {
 "_source": ["title", "meta"],
 "query": {
 "multi_match" : {
 "query": "{{keyword}}",
 "fields": [ "title", "content", "description" ] 
 }
 },
 "highlight" : {
 "number_of_fragments" : 3,
 "fragment_size" : 150,
 "fields" : {
 "content" : {"pre_tags" : [""], "post_tags" : [""]},
 "description" : {"pre_tags" : [""], "post_tags" : [""]},
 "title" : {"pre_tags" : [""], "post_tags" : [""]}
 }
 }
 },
 "params" : {
 "keyword" : "手机"
 }
}
```

# 参考：

* [Reindex API](https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-reindex.html)
* [IK Analysis for Elasticsearch](https://github.com/medcl/elasticsearch-analysis-ik)
* [Search Template](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-template.html)
* [Index Template](https://www.elastic.co/guide/en/elasticsearch/reference/current/indices-templates.html)

本文为博主原创，如需转载，请注明出处：http://www.supperxin.com

返回博客列表