php使用Elasticsearch之批量操作（bulk）

Elasticsearch的批量操作就像 mget 允许我们一次性检索多个文档一样， bulk API允许我们使用单一请求来实现多个文档的 create 、 index 、 update 或 delete 。这对索引类似于日志活动这样的数据流非常有用，它们可以以成百上千的数据为一 个批次按序进行索引。

批量操作的行为(action)必须是以下几种：

行为	解释
create	当文档不存在时创建之。
index	创建新文档或替换已有文档。
update	局部更新文档。
delete	删除一个文档。

注意： 在索引、创建、更新或删除时必须指定文档的 _index 、 _type 、 _id 、（如果设置了routing，也必须指定）这些元数据

创建一个例子索引的mapping如下：

$mapping = [
    'index' => 'my_index',
    'body' => [
        'mappings' => [
            'my_type' => [
                '_all' => [
                    'enabled' => 'false'
                ],
                '_routing' => [   #设置routing（分片路由）
                    'required' => 'true'
                ],
                'properties' => [
                    'name' => [
                        'type' => 'string',
                    ],
                    'age' => [
                        'type' => 'integer'
                    ]
                ]
            ]
        ]
    ]
];
$client = Elasticsearch\ClientBuilder::create()->setHosts(['127.0.0.1:9200'])->build();
$res = $client->indices()->create($mapping);

批量执行创建文档例子

$params['body'] = [];
$nameArr = ['赵','钱','孙','李','周','吴','郑','王'];
for ($i = 1; $i <= 100; $i++) {
    $params['body'][] = [
        'create' => [   #创建
            '_index' => 'my_index',
            '_type' => 'my_type',
            '_id' => $i,
            '_routing' => mt_rand(1,100),
        ]
    ];
    $params['body'][] = [
        'name' => $nameArr[mt_rand(0,7)],
        'age' => mt_rand(18,60)
    ];
}
$client = Elasticsearch\ClientBuilder::create()->setHosts(['127.0.0.1:9200'])->build();
$res = $client->bulk($params);

批量执行更新文档操作例子

//查找指定文档
$client = Elasticsearch\ClientBuilder::create()->setHosts(['127.0.0.1:9200'])->build();
$params = [
	'index' => 'my_index',
	'type' => 'my_type',
	'body' => [
	    'query' => [
	        'bool' => [
	            'must' => [
	                'range' => [
	                    'age' => [
	                        'gt' => '25',
	                        'lt' => '40'
	                    ]
	                ]
	            ]
	        ]
	    ],
	    'from' => 0,
	    'size' => 100,
	    'sort' => [
	    	'age' => 'desc'
	    ]
	]
];
$info = $client->search($params);
$data = $info['hits']['hits'];

// 批量执行更新文档
$params['body'] = [];
$nameArr = ['赵','钱','孙','李','周','吴','郑','王'];
foreach ($data as $key => $value) {
	$params['body'][] = [
        'update' => [   #更新文档
            '_index' => $value['_index'],
            '_type' => $value['_type'],
            '_id' => $value['_id'],
            '_routing' => $value['_routing'],
        ]
    ];
    $params['body'][] = [
    	'doc' => [  #更新指定的字段值
        	'name' => $nameArr[mt_rand(0,7)].$nameArr[mt_rand(0,7)]
        ]
    ];
}
$res = $client->bulk($params);

增删改批量执行操作例子

$params['body'] = [];

//创建或替换文档操作
$params['body'][] = [
    'index' => [   #创建或替换
        '_index' => 'my_index',
        '_type' => 'my_type',
        '_id' => 1,
        '_routing' => 1,
    ]
];
$params['body'][] = [
    'name' => '杨',
    'age' => 23
];

//创建文档操作
$params['body'][] = [
    'create' => [   #创建
        '_index' => 'my_index',
        '_type' => 'my_type',
        '_id' => 2,
        '_routing' => 2,
    ]
];
$params['body'][] = [
    'name' => '郭',
    'age' => 19
];

//局部更新文档操作
$params['body'][] = [
    'update' => [   #局部更新
        '_index' => 'my_index',
        '_type' => 'my_type',
        '_id' => 3,
        '_routing' => 3,
    ]
];
$params['body'][] = [
	'doc' => [
    	'age' => 19
    ]
];

//删除文档操作
$params['body'][] = [
    'delete' => [   #删除
        '_index' => 'my_index',
        '_type' => 'my_type',
        '_id' => 4,
        '_routing' => 4,
    ]
];
$client = Elasticsearch\ClientBuilder::create()->setHosts(['127.0.0.1:9200'])->build();
$res = $client->bulk($params);