本篇笔记记录了在linux的CentOS7发行版下使用RPM包安装Elasticsearch，安装IK分词插件，创建索引设置和映射，以及使用Composer安装PHP的Elasticsearch包的过程；并实现了搜索和多维度聚合查询的实例。
安装Elasticsearch
下载RPM包并安装
wget https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-7.7.0-x86_64.rpm
wget https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-7.7.0-x86_64.rpm.sha512
shasum -a 512 -c elasticsearch-7.7.0-x86_64.rpm.sha512
sudo rpm --install elasticsearch-7.7.0-x86_64.rpm
设置开机自动启动
/bin/systemctl daemon-reload
/bin/systemctl enable elasticsearch.service
启动Elasticsearch
systemctl start elasticsearch
systemd查看Elasticsearch运行状态
systemctl status elasticsearch
curl查看Elasticsearch运行状态
curl http://localhost:9200
{
"name" : "localhost.localdomain",
"cluster_name" : "elasticsearch",
"cluster_uuid" : "RiSXKDmvQVCwljXTdXHFwA",
"version" : {
"number" : "7.7.0",
"build_flavor" : "default",
"build_type" : "rpm",
"build_hash" : "81a1e9eda8e6183f5237786246f6dced26a10eaf",
"build_date" : "2020-05-12T02:01:37.602180Z",
"build_snapshot" : false,
"lucene_version" : "8.5.1",
"minimum_wire_compatibility_version" : "6.8.0",
"minimum_index_compatibility_version" : "6.0.0-beta1"
},
"tagline" : "You Know, for Search"
}
安装IK分词插件
下载IK包
wget --no-check-certificate https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.7.0/elasticsearch-analysis-ik-7.7.0.zip
创建IK插件目录
cd /usr/share/elasticsearch/plugins/ && mkdir ik
解压IK包至ik目录
unzip /usr/local/elasticsearch-analysis-ik-7.7.0.zip -d /usr/share/elasticsearch/plugins/ik/
重启Elasticsearch
systemctl restart elasticsearch
测试IK分词
curl -XGET 'http://localhost:9200/_analyze?pretty=true' -H 'Content-Type:application/json' -d'{"analyzer":"ik_max_word","text":"我的学习笔记"}'
{
"tokens" : [
{
"token" : "我",
"start_offset" : 0,
"end_offset" : 1,
"type" : "CN_CHAR",
"position" : 0
},
{
"token" : "的",
"start_offset" : 1,
"end_offset" : 2,
"type" : "CN_CHAR",
"position" : 1
},
{
"token" : "学习",
"start_offset" : 2,
"end_offset" : 4,
"type" : "CN_WORD",
"position" : 2
},
{
"token" : "笔记",
"start_offset" : 4,
"end_offset" : 6,
"type" : "CN_WORD",
"position" : 3
}
]
}
创建索引
curl -X PUT http://localhost:9200/article -H 'Content-Type:application/json' -d'{
"settings": {
"number_of_shards": 3,
"number_of_replicas": 2
},
"mappings": {
"properties": {
"title": {
"type": "text",
"analyzer": "ik_max_word",
"search_analyzer": "ik_max_word"
},
"category": {
"type": "keyword"
},
"create_date": {
"type": "date",
"format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis"
},
"article_views": {
"type": "integer"
}
}
}
}'
查看索引信息
curl http://localhost:9200/article?pretty=true
{
"article": {
"aliases": {},
"mappings": {
"properties": {
"article_views": {
"type": "integer"
},
"category": {
"type": "keyword"
},
"create_date": {
"type": "date",
"format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis"
},
"title": {
"type": "text",
"analyzer": "ik_max_word"
}
}
},
"settings": {
"index": {
"creation_date": "1587886948979",
"number_of_shards": "3",
"number_of_replicas": "2",
"uuid": "pkEmM36VT9KHjVGYxfqXJA",
"version": {
"created": "7070099"
},
"provided_name": "article"
}
}
}
}
settings:
number_of_shards主分片数
number_of_replicas副本数
mappings:
title文章标题，启用ik_max_word分词模式
category文章分类
article_views文章浏览量
create_date文章创建时间
修改配置文件
vim /etc/elasticsearch/elasticsearch.yml
配置
network.host: 0.0.0.0
cluster.initial_master_nodes: ["node-1", "node-2"]
重启Elasticsearch
systemctl restart elasticsearch
如果重启失败，查看log
tail -f /var/log/elasticsearch/elasticsearch.log
安装PHP的Elasticsearch包
本实例基于yii2框架，但不过多使用yii2特性，主要演示Elasticsearch
Elasticsearch包运行要求
- PHP 7.1.0或更高版本
- Composer
- PHP的Libcurl扩展
安装
composer require elasticsearch/elasticsearch ~7.0
引入Elasticsearch包
我这里没有
require 'vendor/autoload.php';是因为yii的index.php入口文件已经帮我做了这件事
use Elasticsearch\ClientBuilder;
测试一下，查看索引的字段映射信息
public function actionTest()
{
$hosts = [
'192.168.75.237:9200', // IP + Port
];
$client = ClientBuilder::create() // Instantiate a new ClientBuilder
->setHosts($hosts) // Set the hosts
->build();
$params = [
'index' => 'article',
];
$result = $client->indices()->getMapping($params);
print_r($result);
}
执行结果
创建索引
mysql部分略过......
public function actionCreateIndex()
{
$hosts = [
'192.168.75.237:9200', // IP + Port
];
$client = ClientBuilder::create() // Instantiate a new ClientBuilder
->setHosts($hosts) // Set the hosts
->build();
$article = Article::find()->where(['article_status' => 1])->all();
foreach ($article as $row) {
$params = [
'index' => 'article',
'id' => $row->id,
'body' => [
'title' => $row->article_title,
'category' => $row->category->category_name,
'article_views' => $row->article_views,
'create_date' => $row->create_date,
]
];
$response = $client->index($params);
var_dump($response['_shards']['successful']);
}
}
执行结果
Elasticsearch支持使用$client->bulk($params);方法批量创建索引，详情请查阅官方资料
搜索数据
public function actionResult()
{
$keyword = Yii::$app->request->get('keyword', '');
$hosts = [
'192.168.75.237:9200', // IP + Port
];
$client = ClientBuilder::create() // Instantiate a new ClientBuilder
->setHosts($hosts) // Set the hosts
->build();
$params = [
'index' => 'article',
'body' => [
//查询
'query' => [
//匹配搜索
'match' => [
'title' => $keyword
]
],
//高亮
'highlight' => [
//自定义高亮起始标签，默认em
'pre_tags' => ['<span class="red">'],
//自定义高亮结束标签，默认em
'post_tags' => ['</span>'],
//高亮字段
'fields' => [
'title' => new \stdClass(),
]
]
]
];
$results = $client->search($params);
print_r($results);
exit();
}
搜索结果
搜索数据，并进行多维度聚合
public function actionResult()
{
$keyword = Yii::$app->request->get('keyword', '');
$hosts = [
'192.168.75.237:9200', // IP + Port
];
$client = ClientBuilder::create() // Instantiate a new ClientBuilder
->setHosts($hosts) // Set the hosts
->build();
$params = [
'index' => 'article',
'body' => [
'from' => 0,
'size' => 10,
//查询
'query' => [
//匹配搜索
'match' => [
'title' => $keyword
]
],
//高亮
'highlight' => [
//自定义高亮起始标签，默认em
'pre_tags' => ['<span class="red">'],
//自定义高亮结束标签，默认em
'post_tags' => ['</span>'],
//高亮字段
'fields' => [
'title' => new \stdClass(),
]
],
//聚合
'aggs' => [
//按分类聚合
'group_category' => [
'terms' => ['field' => 'category'],
],
//按创建时间聚合，步长按月，最小数量设置1，过滤掉0的数据
'group_create_date' => [
'date_histogram' => [
'field' => 'create_date',
'interval' => 'month',
'format' => 'yyyy-MM',
'min_doc_count' => 1,
],
],
//按访问量区间聚合，步长500
'interval_article_views' => [
'histogram' => [
'field' => 'article_views',
'interval' => 500,
],
],
],
]
];
$results = $client->search($params);
print_r($results);
exit();
}
搜索结果
Array
(
[took] => 12
[timed_out] =>
[_shards] => Array
(
[total] => 3
[successful] => 3
[skipped] => 0
[failed] => 0
)
[hits] => Array
(
[total] => Array
(
[value] => 13
[relation] => eq
)
[max_score] => 8.7013235
[hits] => Array
(
[0] => Array
(
[_index] => article
[_type] => _doc
[_id] => 850
[_score] => 8.7013235
[_source] => Array
(
[title] => Redis Cluster集群搭建
[category] => nosql笔记
[article_views] => 25
[create_date] => 2020-05-26 12:45:44
)
[highlight] => Array
(
[title] => Array
(
[0] => <span class="red">Redis</span> Cluster<span class="red">集群</span><span class="red">搭建</span>
)
)
)
[1] => Array
(
[_index] => article
[_type] => _doc
[_id] => 851
[_score] => 3.7347772
[_source] => Array
(
[title] => Redis Cluster集群新增、删除节点以及重新分配hash slot哈希槽
[category] => nosql笔记
[article_views] => 15
[create_date] => 2020-05-27 15:42:21
)
[highlight] => Array
(
[title] => Array
(
[0] => <span class="red">Redis</span> Cluster<span class="red">集群</span>新增、删除节点以及重新分配hash slot哈希槽
)
)
)
............
[9] => Array
(
[_index] => article
[_type] => _doc
[_id] => 601
[_score] => 1.3900613
[_source] => Array
(
[title] => PHP使用Redis的Transaction(事务)命令
[category] => nosql笔记
[article_views] => 463
[create_date] => 2019-01-24 22:34:56
)
[highlight] => Array
(
[title] => Array
(
[0] => PHP使用<span class="red">Redis</span>的Transaction(事务)命令
)
)
)
)
)
[aggregations] => Array
(
[group_category] => Array
(
[doc_count_error_upper_bound] => 0
[sum_other_doc_count] => 0
[buckets] => Array
(
[0] => Array
(
[key] => nosql笔记
[doc_count] => 11
)
[1] => Array
(
[key] => git笔记
[doc_count] => 1
)
[2] => Array
(
[key] => 消息队列
[doc_count] => 1
)
)
)
[group_create_date] => Array
(
[buckets] => Array
(
[0] => Array
(
[key_as_string] => 2018-12
[key] => 1543622400000
[doc_count] => 2
)
[1] => Array
(
[key_as_string] => 2019-01
[key] => 1546300800000
[doc_count] => 6
)
[2] => Array
(
[key_as_string] => 2019-03
[key] => 1551398400000
[doc_count] => 1
)
[3] => Array
(
[key_as_string] => 2020-05
[key] => 1588291200000
[doc_count] => 4
)
)
)
[interval_article_views] => Array
(
[buckets] => Array
(
[0] => Array
(
[key] => 0
[doc_count] => 9
)
[1] => Array
(
[key] => 500
[doc_count] => 4
)
)
)
)
)
搜索结果页面展示(模版部分略过......)
主要实现了以下功能：
- ik分词搜索
- 搜索结果高亮
- 按分类聚合：搜索命中的数据的分类和对应的数量
- 按发布时间聚合：搜索命中的数据的发布月份和对应的数量
- 按浏览量聚合：搜索命中的数据的浏览量区间和对应的数量
再现理想