PHP与Elasticsearch整合教程 使用PHP实现高效全文搜索的完整方案

composer require elasticsearch/elasticsearch

<?php

require 'vendor/autoload.php'; // 确保autoload文件已引入

use Elasticsearch\ClientBuilder;

$hosts = [
    'localhost:9200', // 你的Elasticsearch主机地址和端口
    // 'anotherhost:9200', // 如果有多个节点，可以配置多个
];

$client = ClientBuilder::create()
            ->setHosts($hosts)
            ->build();

// 现在 $client 对象就可以用来与Elasticsearch交互了

<?php
// ... $client 实例化代码

$params = [
    'index' => 'my_documents', // 索引名称
    'id'    => '1',            // 文档ID，可以是你的数据库ID
    'body'  => [
        'title'   => 'PHP与Elasticsearch整合实践',
        'content' => '这是一篇关于如何使用PHP和Elasticsearch构建高效全文搜索的文章，涵盖了数据索引和查询技巧。',
        'author'  => '张三',
        'tags'    => ['PHP', 'Elasticsearch', '搜索'],
        'created_at' => date('Y-m-d H:i:s')
    ]
];

try {
    $response = $client->index($params);
    print_r($response);
} catch (Exception $e) {
    echo "索引文档失败: " . $e->getMessage();
}

// 批量索引通常更高效
$bulkParams = ['body' => []];
for ($i = 2; $i <= 10; $i++) {
    $bulkParams['body'][] = [
        'index' => [
            '_index' => 'my_documents',
            '_id'    => $i
        ]
    ];
    $bulkParams['body'][] = [
        'title'   => '文档标题 ' . $i,
        'content' => '这是第 ' . $i . ' 篇测试文档的内容，用来演示批量索引。',
        'author'  => '李四',
        'tags'    => ['测试', '批量'],
        'created_at' => date('Y-m-d H:i:s', strtotime("-$i days"))
    ];
}

try {
    $response = $client->bulk($bulkParams);
    print_r($response);
} catch (Exception $e) {
    echo "批量索引失败: " . $e->getMessage();
}

<?php
// ... $client 实例化代码

// 简单搜索
$searchParams = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'match' => [
                'content' => '全文搜索' // 搜索content字段中包含“全文搜索”的文档
            ]
        ]
    ]
];

try {
    $response = $client->search($searchParams);
    echo "搜索结果：\n";
    foreach ($response['hits']['hits'] as $hit) {
        echo "ID: " . $hit['_id'] . ", 标题: " . $hit['_source']['title'] . "\n";
    }
} catch (Exception $e) {
    echo "搜索失败: " . $e->getMessage();
}

// 复杂查询示例：同时搜索标题和内容，并按时间排序
$complexSearchParams = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'multi_match' => [
                'query'  => 'PHP 搜索',
                'fields' => ['title', 'content'] // 在多个字段中搜索
            ]
        ],
        'sort' => [
            'created_at' => [
                'order' => 'desc' // 按创建时间降序排序
            ]
        ],
        'from' => 0,  // 分页：从第0条开始
        'size' => 10  // 分页：每页10条
    ]
];

try {
    $response = $client->search($complexSearchParams);
    echo "\n复杂搜索结果：\n";
    foreach ($response['hits']['hits'] as $hit) {
        echo "ID: " . $hit['_id'] . ", 标题: " . $hit['_source']['title'] . ", 创建时间: " . $hit['_source']['created_at'] . "\n";
    }
} catch (Exception $e) {
    echo "复杂搜索失败: " . $e->getMessage();
}

PUT /my_documents
{
  "settings": {
    "number_of_shards": 1,
    "number_of_replicas": 0,
    "analysis": {
      "analyzer": {
        "ik_smart_analyzer": {
          "type": "custom",
          "tokenizer": "ik_smart"
        },
        "ik_max_word_analyzer": {
          "type": "custom",
          "tokenizer": "ik_max_word"
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "title": {
        "type": "text",
        "analyzer": "ik_max_word_analyzer"
      },
      "content": {
        "type": "text",
        "analyzer": "ik_smart_analyzer"
      },
      "author": {
        "type": "keyword"
      },
      "tags": {
        "type": "keyword"
      },
      "created_at": {
        "type": "date",
        "format": "yyyy-MM-dd HH:mm:ss"
      },
      "comments": {
        "type": "nested",
        "properties": {
          "user": { "type": "keyword" },
          "text": { "type": "text", "analyzer": "ik_smart_analyzer" },
          "timestamp": { "type": "date" }
        }
      }
    }
  }
}

bool

$params = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'bool' => [
                'must' => [
                    [ 'multi_match' => [ 'query' => 'PHP', 'fields' => ['title', 'content'] ] ]
                ],
                'filter' => [
                    [ 'term' => [ 'author.keyword' => '张三' ] ] // keyword类型用于精确匹配
                ],
                'must_not' => [
                    [ 'term' => [ 'tags.keyword' => '旧数据' ] ]
                ]
            ]
        ]
    ]
];
$response = $client->search($params);
// ... 处理结果

range

$params = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'range' => [
                'created_at' => [
                    'gte' => '2023-01-01', // 大于等于
                    'lt'  => '2024-01-01'  // 小于
                ]
            ]
        ]
    ]
];
$response = $client->search($params);
// ... 处理结果

fuzzy

// 模糊查询：允许少量编辑距离
$params = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'fuzzy' => [
                'title' => [
                    'value'    => 'PHp', // 用户可能输错大小写
                    'fuzziness' => 'AUTO' // 自动根据词长判断允许的编辑距离
                ]
            ]
        ]
    ]
];

// 前缀查询：搜索以特定字符串开头的词
$params = [
    'index' => 'my_documents',
    'body'  => [
        'query' => [
            'prefix' => [
                'title.keyword' => 'PHP与' // 搜索标题以“PHP与”开头的文档
            ]
        ]
    ]
];
$response = $client->search($params);
// ... 处理结果

$params = [
    'index' => 'my_documents',
    'body'  => [
        'size' => 0, // 不返回文档，只返回聚合结果
        'aggs' => [
            'authors_count' => [ // 聚合名称
                'terms' => [
                    'field' => 'author.keyword', // 基于哪个字段进行分组
                    'size'  => 10 // 返回前10个作者
                ]
            ]
        ]
    ]
];
$response = $client->search($params);

echo "作者文章数量统计：\n";
foreach ($response['aggregations']['authors_count']['buckets'] as $bucket) {
    echo "作者: " . $bucket['key'] . ", 文章数: " . $bucket['doc_count'] . "\n";
}

match_phrase

query_string

geo_distance