首页 > elasticsearch创建索引时的一些选项问题

elasticsearch创建索引时的一些选项问题

我想用elasticsearch为博客的文章做站内搜索,后台用的php。

文章表articles的全部字段如下:

id     title     content     user_id    created_at     updated_at

现在我想为文章表的title字段、content字段、updated_at字段,共三个字段创建索引。

下面是我参照elasticsearch-php客户端的官方文档写的创建索引blog和创建类型article的demo,分词用到了ik分词。

其中有些选项不太清楚什么意思,具体问题在下面代码中(有4个),请大神帮解答一下,谢谢。

官方文档链接:https://www.elastic.co/guide/en/elasticsearch/client/php-api/current/_index_management_operations.html#_create_an_index_advanced_example

        $params = [
            'index' => 'blog',
            'body' => [
                'settings' => [
                    'number_of_shards' => 1,
                    'number_of_replicas' => 0,
                    'analysis' => [
                        'filter' => [
                            //1、这里的两个shingle应该改成article吗?
                            'shingle' => [
                                'type' => 'shingle'
                            ]
                        ],

                        //2、char_filter里面内容表示什么意思?包括pre_negs和post_negs。
                        'char_filter' => [

                            'pre_negs' => [
                                'type' => 'pattern_replace',
                                'pattern' => '(\\w+)\\s+((?i:never|no|nothing|nowhere|noone|none|not|havent|hasnt|hadnt|cant|couldnt|shouldnt|wont|wouldnt|dont|doesnt|didnt|isnt|arent|aint))\\b',
                                'replacement' => '~$1 $2'
                            ],
                            'post_negs' => [
                                'type' => 'pattern_replace',
                                'pattern' => '\\b((?i:never|no|nothing|nowhere|noone|none|not|havent|hasnt|hadnt|cant|couldnt|shouldnt|wont|wouldnt|dont|doesnt|didnt|isnt|arent|aint))\\s+(\\w+)',
                                'replacement' => '$1 ~$2'
                            ]
                        ],

                        //3、analyzer的内容需要怎么修改吗?
                        'analyzer' => [
                            'blog' => [
                                'type' => 'custom',
                                'tokenizer' => 'standard',
                                'filter' => ['lowercase', 'stop', 'kstem']
                            ]
                        ]
                    ]
                ],
                'mappings' => [
                    'article' => [
                        "_all" => [
                            "analyzer" => "ik_max_word",
                            "search_analyzer" => "ik_max_word",
                            "term_vector" => "no",
                            "store" => "false"
                        ],
                        'properties' => [
                            'title' => [
                                'type' => 'string',
                                'store' => 'no',
                                'term_vector' => 'with_positions_offsets',
                                'analyzer' => 'ik_max_word',
                                'search_analyzer' => 'ik_max_word',
                                'include_in_all' => 'true',
                                'boost' => 9
                            ],
                            'content' => [
                                'type' => 'string',
                                'store' => 'no',
                                'term_vector' => 'with_positions_offsets',
                                'analyzer' => 'ik_max_word',
                                'search_analyzer' => 'ik_max_word',
                                'include_in_all' => 'true',
                                'boost' => 8
                            ],
                            //4、时间只是用来在搜索的时候排序使用,下面的选项该怎么填写?
                            'updated_at' => [
                                'type' => '',
                                'store' => '',
                                'term_vector' => '',
                                'analyzer' => '',
                                'search_analyzer' => '',
                                'include_in_all' => '',
                                'boost' => 
                            ]
                        ]
                    ]


                ]
            ]
        ];
        $client->indices()->create($params);
【热门文章】
【热门文章】