安装es
docker pull elasticsearch:7.14.0 docker run --name es -p 9200:9200 -p 9300:9300 -e "discovery.type=single-node" -e ES_JAVA_OPTS="-Xms256m -Xmx256m" --network mynetwork --ip 172.18.0.7 -v /d/docker/docker-php/elasticsearch/data:/usr/share/elasticsearch/data -d elasticsearch:7.14.0 #discovery.type=single-node表示单节点
下载IK中文分词插件
curl -L -o ik.zip https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.14.0/elasticsearch-analysis-ik-7.14.0.zip 或者将zip文件下载到宿主机，通过copy命令拷贝到es容器中 #https://github.com/medcl/elasticsearch-analysis-ik/releases #https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.14.0/elasticsearch-analysis-ik-7.14.0.zip docker cp C:\Users\Administrator\Desktop\docker\elasticsearch-analysis-ik-7.14.0.zip es:/usr/share/elasticsearch/plugins docker exec -it es bash cd /usr/share/elasticsearch/plugins unzip elasticsearch-analysis-ik-7.14.0.zip -d ./ik rm elasticsearch-analysis-ik-7.14.0.zip elasticsearch-plugin list
配置es，让其可以被head插件访问到
cd /usr/share/elasticsearch/config vi elasticsearch.yml http.cors.enabled: true http.cors.allow-origin: "*"
如果我们不小心把配置文件改错了，启动失败进不了容器中，我们可以把配置文件copy出来修改
docker cp es:/usr/share/elasticsearch/config/elasticsearch.yml C:\Users\Administrator\Desktop\elasticsearch.yml docker cp C:\Users\Administrator\Desktop\elasticsearch.yml es:/usr/share/elasticsearch/config/elasticsearch.yml docker restart es
安装head插件
docker pull mobz/elasticsearch-head:5 docker run -d --name es_head -p 9100:9100 --network mynetwork --ip 172.18.0.8 mobz/elasticsearch-head:5 docker ps
http://localhost:9100/
解决head插件406：Content-Type header [application/x-www-form-urlencoded] is not supported
docker cp es_head:/usr/src/app/_site/vendor.js C:\Users\Administrator\Desktop\docker #6886行：application/x-www-form-urlencoded改为application/json;charset=UTF-8 #7573行：application/x-www-form-urlencoded改为application/json;charset=UTF-8 docker cp C:\Users\Administrator\Desktop\vendor.js es_head:/usr/src/app/_site/vendor.js
复合查询
http://localhost:9200/_analyze POST
{
"analyzer": "ik_max_word",
"text": [
"我是中国人"
]
}
自定义词组
我们先来看看关键词 周廷泽 的检索结果
cd /usr/share/elasticsearch/plugins/ik/config mkdir custom touch single_word.dic vi single_word.dic >周廷泽 >周泽 cd /usr/share/elasticsearch/plugins/ik/config vi 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> <!--用户可以在这里配置自己的扩展字典 --> <entry key="ext_dict">custom/single_word.dic</entry> <!--用户可以在这里配置自己的扩展停止词字典--> <entry key="ext_stopwords"></entry> <!--用户可以在这里配置远程扩展字典 --> <!-- <entry key="remote_ext_dict">words_location</entry> --> <!--用户可以在这里配置远程扩展停止词字典--> <!-- <entry key="remote_ext_stopwords">words_location</entry> --> </properties> docker restart es
安装拼音分词
https://github.com/medcl/elasticsearch-analysis-pinyin/tags
安装方式跟IK分词一样
<?php
/**
* https://www.elastic.co/guide/en/elasticsearch/client/php-api/current/index_management.html
* https://open.163.com/newview/movie/free?pid=XGG8PCIUJ&mid=HGG8PFDRB
*/
use Elasticsearch\ClientBuilder;
require './vendor/autoload.php';
/**
* @param $num 生成汉字的数量
* @return string
*/
function getChar($num)
{
$b = '';
for ($i = 0; $i < $num; $i++) {
// 使用chr()函数拼接双字节汉字，前一个chr()为高位字节，后一个为低位字节
$a = chr(mt_rand(0xB0, 0xD0)) . chr(mt_rand(0xA1, 0xF0));
// 转码
$b .= iconv('GB2312', 'UTF-8', $a);
}
return $b;
}
$client = ClientBuilder::create()
->setHosts(['127.0.0.1:9200'])
->setRetries(2)
->build();
$index = [
'index' => 'shop',
'body' => [
'settings' => [
'number_of_shards' => 5,
'number_of_replicas' => 0,
'analysis' => [
'analyzer' => [
'text_analyzer' => [
'tokenizer' => 'ik_max_word',
'filter' => 'py'
],
'completion_analyzer' => [
'tokenizer' => 'keyword',
'filter' => 'py'
]
],
'filter' => [
'py' => [
"type"=> "pinyin",
"keep_full_pinyin"=> false,
"keep_joined_full_pinyin"=> true,
"keep_original" => true,
"limit_first_letter_length" => 16,
"none_chinese_pinyin_tokenize"=> false,
"remove_duplicated_term"=> true
]
]
]
],
'mappings' => [
'_source' => [
'enabled' => true
],
'properties' => [
'article_id' => [
'type' => 'integer' // long
],
'title' => [
'type' => 'text',
'analyzer' => 'text_analyzer',
'search_analyzer' => 'ik_smart',
],
'title_completion' => [
'type' => 'completion',
'analyzer' => 'completion_analyzer',
// 'search_analyzer' => 'ik_smart', // 狮子 虱子 search：我掉到了狮子笼里怎么办
],
'content' => [
'type' => 'text',
'analyzer' => 'text_analyzer',
'search_analyzer' => 'ik_smart',
]
]
]
]
];
//$response = $client->indices()->create($index);
//print_r($response);
//exit;
$doc = [
'index' => 'shop',
'id' => 1,
'body' => [
'article_id' => 1,
'title' => '人民日报再次点名阿里，不要妄想大而不倒',
//'title_completion' => '人民日报再次点名阿里，不要妄想大而不倒',// 这里也可以设置成数组，词条
'title_completion' => ['人民日报', '阿里', '点名', '妄想', '不倒'],
'content' => '据吉林省委政法委官方微信公众号“平安吉林”消息：8月31日，省委召开省委政法委员会干部会议，宣布省委政法委主要领导任职决定。省委副书记高广滨，省委常委、省委政法委书记范锐平出席会议并讲话。省委常委、省委组织部部长张恩惠主持会议并宣布决定。副省长、省公安厅厅长刘金波，省法院院长徐家新，省检察院检察长尹伊君，省武警总队司令员赵洪炜出席会议。'
]
];
//$client->index($doc);
//exit;
// 搜索建议，前缀检索
$params = [
'index' => 'shop',
'body' => [
'suggest' => [
'my-suggest' => [
'text' => '人民',
'completion' => [
'field' => 'title_completion',
'skip_duplicates' => true,
'size' => 5
],
]
],
]
];
$result = $client->search($params);
var_dump($result);
echo "<hr/>";
//exit;
$params = [
'index' => 'shop',
'body' => [
'query' => [
'match' => [
'title' => '阿里'
]
],
// 'stored_fields' => ['title']
]
];
/* select * from article where title like '%国际%' or title like '%test%'*/
$result = $client->search($params);
var_dump($result);
fffffasdfasdfasdfasdfas;kdfjlaskl;dfjaskl;dfjakls;dfjkal;sfdjlaks;df als;dfj awkls;dfj asl;dfj aslk;dfjaskl;dfjas;ldf
访客评论