（3）ElasticSearch--全文检索
一、创建数据
1.创建索引
//PUT http://10.1.84.116:9200/school
{
"settings": {
"index": {
"number_of_shards": "1",
"number_of_replicas": "0"
}
},
"mappings": {
"person": {
"properties": {
"name": {
"type": "text"
},
"age": {
"type": "integer"
},
"mail": {
"type": "keyword"
},
"hobby": {
"type": "text",
"analyzer": "ik_max_word"
}
}
}
}
}
2.批量创建数据
{"index":{"_index":"school","_type":"person"}}
{"name":"张三","age": 20,"mail": "[email protected]","hobby":"羽毛球、乒乓球、足球"}
{"index":{"_index":"school","_type":"person"}}
{"name":"李四","age": 21,"mail": "[email protected]","hobby":"羽毛球、乒乓球、足球、篮球"}
{"index":{"_index":"school","_type":"person"}}
{"name":"王五","age": 22,"mail": "[email protected]","hobby":"羽毛球、篮球、游泳、听音乐"}
{"index":{"_index":"school","_type":"person"}}
{"name":"赵六","age": 23,"mail": "[email protected]","hobby":"跑步、游泳、篮球"}
{"index":{"_index":"school","_type":"person"}}
{"name":"孙七","age": 24,"mail": "[email protected]","hobby":"听音乐、看电影、羽毛球"}
3.单词搜索
搜索参数
//GET /school/person/_search
{
"query": {
"match": {
"hobby": "音乐"
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 118,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 0.81652206,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "k4Ndn3MB74wApIfXYeWI",
"_score": 0.81652206,
"_source": {
"name": "王五",
"age": 22,
"mail": "[email protected]",
"hobby": "羽毛球、篮球、游泳、听音乐"
},
"highlight": {
"hobby": [
"羽毛球、篮球、游泳、听音乐"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "mINhn3MB74wApIfXJeUx",
"_score": 0.81652206,
"_source": {
"name": "孙七",
"age": 24,
"mail": "[email protected]",
"hobby": "听音乐、看电影、羽毛球"
},
"highlight": {
"hobby": [
"听音乐、看电影、羽毛球"
]
}
}
]
}
}
4.多词搜索（或关系）
爱好包括音乐或游泳
搜索参数
//GET /school/person/_search
{
"query": {
"match": {
"hobby": "音乐 游泳"
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 11,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 3,
"max_score": 1.6330441,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "k4Ndn3MB74wApIfXYeWI",
"_score": 1.6330441,
"_source": {
"name": "王五",
"age": 22,
"mail": "[email protected]",
"hobby": "羽毛球、篮球、游泳、听音乐"
},
"highlight": {
"hobby": [
"羽毛球、篮球、游泳、听音乐"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "lINdn3MB74wApIfXcOWi",
"_score": 1.1349231,
"_source": {
"name": "赵六",
"age": 23,
"mail": "[email protected]",
"hobby": "跑步、游泳、篮球"
},
"highlight": {
"hobby": [
"跑步、游泳、篮球"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "mINhn3MB74wApIfXJeUx",
"_score": 0.81652206,
"_source": {
"name": "孙七",
"age": 24,
"mail": "[email protected]",
"hobby": "听音乐、看电影、羽毛球"
},
"highlight": {
"hobby": [
"听音乐、看电影、羽毛球"
]
}
}
]
}
}
5.多词搜索（与关系）
爱好既包括音乐也游泳
搜索参数
//GET /school/person/_search
{
"query": {
"match": {
"hobby": {
"query": "音乐 游泳",
"operator": "and"
}
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 1,
"max_score": 1.6330441,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "k4Ndn3MB74wApIfXYeWI",
"_score": 1.6330441,
"_source": {
"name": "王五",
"age": 22,
"mail": "[email protected]",
"hobby": "羽毛球、篮球、游泳、听音乐"
},
"highlight": {
"hobby": [
"羽毛球、篮球、游泳、听音乐"
]
}
}
]
}
}
6.多词搜索（相似度）
搜索参数
//GET /school/person/_search
{
"query": {
"match": {
"hobby": {
"query": "游泳 羽毛球",
"minimum_should_match": "80%"
}
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 10,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 4,
"max_score": 1.621458,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "k4Ndn3MB74wApIfXYeWI",
"_score": 1.621458,
"_source": {
"name": "王五",
"age": 22,
"mail": "[email protected]",
"hobby": "羽毛球、篮球、游泳、听音乐"
},
"highlight": {
"hobby": [
"羽毛球、篮球、游泳、听音乐"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "kYNdn3MB74wApIfXNeXo",
"_score": 0.9608413,
"_source": {
"name": "张三",
"age": 20,
"mail": "[email protected]",
"hobby": "羽毛球、乒乓球、足球"
},
"highlight": {
"hobby": [
"羽毛球、乒乓球、足球"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "koNdn3MB74wApIfXTuVV",
"_score": 0.91348255,
"_source": {
"name": "李四",
"age": 21,
"mail": "[email protected]",
"hobby": "羽毛球、乒乓球、足球、篮球"
},
"highlight": {
"hobby": [
"羽毛球、乒乓球、足球、篮球"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "mINhn3MB74wApIfXJeUx",
"_score": 0.80493605,
"_source": {
"name": "孙七",
"age": 24,
"mail": "[email protected]",
"hobby": "听音乐、看电影、羽毛球"
},
"highlight": {
"hobby": [
"听音乐、看电影、羽毛球"
]
}
}
]
}
}
7.组合搜索
搜索结果中必须包含篮球，不能包含音乐，如果包含了游泳，那么它的相似度更高。
搜索参数
//GET /school/person/_search
{
"query": {
"bool": {
"must": {
"match": {
"hobby": "篮球"
}
},
"must_not": {
"match": {
"hobby": "音乐"
}
},
"should": [
{
"match": {
"hobby": "游泳"
}
}
]
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 7,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 1.8336569,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "lINdn3MB74wApIfXcOWi",
"_score": 1.8336569,
"_source": {
"name": "赵六",
"age": 23,
"mail": "[email protected]",
"hobby": "跑步、游泳、篮球"
},
"highlight": {
"hobby": [
"跑步、游泳、篮球"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "koNdn3MB74wApIfXTuVV",
"_score": 0.50270504,
"_source": {
"name": "李四",
"age": 21,
"mail": "[email protected]",
"hobby": "羽毛球、乒乓球、足球、篮球"
},
"highlight": {
"hobby": [
"羽毛球、乒乓球、足球、篮球"
]
}
}
]
}
}
8.权重
有些时候，我们可能需要对某些词增加权重来影响该条数据的得分。如下：搜索关键字为“游泳篮球”，如果结果中包含了“音乐”权重为10，包含了“跑步”权重为2
搜索参数
//GET /school/person/_search
{
"query": {
"bool": {
"must": {
"match": {
"hobby": {
"query": "游泳篮球",
"operator": "and"
}
}
},
"should": [
{
"match": {
"hobby": {
"query": "音乐",
"boost": 10
}
}
},
{
"match": {
"hobby": {
"query": "跑步",
"boost": 2
}
}
}
]
}
},
"highlight": {
"fields": {
"hobby": {}
}
}
}
搜索结果
{
"took": 5,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 9.484448,
"hits": [
{
"_index": "school",
"_type": "person",
"_id": "k4Ndn3MB74wApIfXYeWI",
"_score": 9.484448,
"_source": {
"name": "王五",
"age": 22,
"mail": "[email protected]",
"hobby": "羽毛球、篮球、游泳、听音乐"
},
"highlight": {
"hobby": [
"羽毛球、篮球、游泳、听音乐"
]
}
},
{
"_index": "school",
"_type": "person",
"_id": "lINdn3MB74wApIfXcOWi",
"_score": 5.4279313,
"_source": {
"name": "赵六",
"age": 23,
"mail": "[email protected]",
"hobby": "跑步、游泳、篮球"
},
"highlight": {
"hobby": [
"跑步、游泳、篮球"
]
}
}
]
}
}