Created
February 3, 2017 07:13
-
-
Save opencubicles/ccb65849b426235feb14e5e3de44cd91 to your computer and use it in GitHub Desktop.
elastic search - hunspell example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
require 'vendor/autoload.php'; | |
use Elasticsearch; | |
use Elasticsearch\ClientBuilder; | |
use Elasticsearch\Connections\Connection; | |
use Faker; | |
$client = Elasticsearch\ClientBuilder::create()->setHosts(['http://ec2-35-154-104-170.ap-south-1.compute.amazonaws.com:9200'])->build(); | |
$faker = Faker\Factory::create(); | |
$deleteParams = [ | |
'index' => 'my_index2' | |
]; | |
$response = $client->indices()->delete($deleteParams); | |
$params = [ | |
'index' => 'my_index2', | |
'body' => [ | |
'mappings' => [ | |
'my_type2' => [ | |
'_source' => [ | |
'enabled' => true | |
], | |
'_all' => ['analyzer' => "my_analyzer"], | |
'properties' => [ | |
'cliptexts' => [ | |
'type' => 'nested', | |
"include_in_parent" => true, | |
'properties' => [ | |
'content' => ['type' => 'string', "analyzer" => "my_analyzer"], | |
'cliptextid' => ['type' => 'string'] | |
] | |
], | |
'uid' => [ | |
'type' => 'integer' | |
], | |
'text' => [ | |
"type" => "string", "analyzer" => "my_analyzer" | |
] | |
] | |
] | |
], | |
"settings"=> [ | |
"analysis"=> [ | |
"analyzer"=> [ | |
"my_analyzer"=> [ | |
"type"=> "custom", | |
"tokenizer"=> "standard", | |
"filter"=> ["lowercase", "en_US", "my_stopwords"] | |
] | |
], | |
"filter"=> [ | |
"my_stopwords"=> [ | |
"type"=> "stop", | |
"stopwords"=> "they,this,to,was,will,with" | |
] | |
] | |
] | |
] | |
] | |
]; | |
// Create the index with mappings and settings now | |
$response = $client->indices()->create($params); | |
for ($j=0; $j < 100; $j++) { | |
$uids = array(27, 29, 31, 12, 19); | |
$uid = $uids[array_rand($uids,1)]; | |
$id = $j; | |
$params = [ | |
'index' => 'my_index2', | |
'type' => 'my_type2', | |
'id' => 'my_id'.$id, | |
'body' => ['uid' => $uid ] | |
]; | |
$rand1 = rand(1,14); | |
$rand2 = rand(1,14); | |
for ($i=0; $i < 15; $i++) { | |
$content = $faker->sentence(12, true); | |
if($i == $rand1) | |
$content = $content." carry eat"; | |
if($i == $rand2 && $rand1 != $rand2) | |
$content = $content." carries meeeet eat "; | |
$cliptextid = $i; | |
$params['body']['cliptexts'][$i] = array('content' => $content." women", 'cliptextid' => $cliptextid ); | |
} | |
$params['body']['text'] = $content." women"; | |
$response = $client->index($params); | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment