1、使用Elasticsearch API实现CRUD：
添加一个索引
PUT /lib/
{
"settings":{
"index":{
"number_of_shards":3, //分片
"number_of_replicas":0 //备份的数量
}
}
}
也可直接 PUT lib2
返回结果为：
{
"acknowledged": true,
"shards_acknowledged": true,
"index": "lib2"
}
即为创建索引成功
GET /lib/_settings 查看索引的配置
GET _all/_settings 查看所有索引的配置
增加：
在指定的索引中添加文档 使用PUT添加文档时需指定id
PUT /1ib/user/1
{ "first_ name" : "Jane",
"last_ name" : "Smith",
"age" : 32,
"about" :"I like to collect rock albums",
"interests": [ "music" ]
}
使用POST添加文档无需指定id将自动生成
POST /1ib/user/
{"first nane" : "Douglas",
"last_ name":"Fir",
"age" :23,
"about":"I like to build cabinets",
"interests": [ "forestry" ]
}
查询：
GET /1ib/user/1 查询lib索引下user类型id为1的文档
GET /1ib/user/nsrgZXABkJVXv6_Qvv_m 查询自动生成id的文档
GET /1ib/user/1?_source=age,about 查询指定字段的值
修改：
使用PUT用覆盖的方式进行更新
PUT /1ib/user/1
{ "first_ name" : "Jane",
"last_ name" : "Smith",
"age" : 36,
"about" :"I like to collect rock albums",
"interests": [ "music" ]
}
使用POST进行直接的修改
POST /lib/user/1/_update
{
"doc":{
"age":33
}
}
删除:
DELETE /lib/user/1 删除ID为1的文档
DELETE lib2 删除索引2、Filter查询
filter是不计算相关性的，同时可以cache，因此，filter速度要快于query
POST /lib4/items/_bulk
{"index":{"_id":1}}
{"price":40,"itemID":"ID100123"}
{"index":{"_id":2}}
{"price":50,"itemID":"ID100124"}
{"index":{"_id":3}}
{"price":25,"itemID":"ID100125"}
{"index":{"_id":4}}
{"price":30,"itemID":"ID100126"}
{"index":{"_id":5}}
{"price":null,"itemID":"ID100127"}
GET /lib4/items/_search
{
"query":{
"bool":{
"filter":[
{"term":{"price":25}}
]
}
}
}
GET /lib4/items/_search
{
"query":{
"bool":{
"filter":[
{"terms":{"price":[25,40]}}
]
}
}
}
以下查不出来 原因mapping的动态映射itermID是text 会进行分词 默认为小写
GET /lib4/items/_search
{
"query":{
"bool":{
"filter":[
{"terms":{"itemID":"ID100123"}}
]
}
}
}
GET lib4/_mapping
DELETE lib4
PUT lib4
{
"mappings":{
"items":{
"properties":{
"itemID":{
"type":"text",
"index":false
}
}
}
}
}
bool过滤查询
可以实现组合过滤查询
格式：
{"bool":{"must":[],"should":[],"must_not":[]}}
must必须满足的条件---and
should:可以满足也可以不满足的条件--or
must_not不需要满足的条件--not
GET /lib4/items/_search
{
"query":{
"bool":{
"should":[
{"term":{"price":25}},
{"term":{"itemID":"id100123"}}
],
"must_not":{
"term":{"price":30}
}
}
}
}
GET /lib4/items/_search
{
"query":{
"bool":{
"should": [
{"term":{"itemID": "id100123"}},
{
"bool":{
"must": [
{"term": {"itemID": "id100124"}},
{"term": {"price": 40}}
]
}
}
]
}
}
}
范围过滤
gt:>
lt:<
gte:>=
lte:<=
GET /lib4/items/_search
{
"query":{
"bool":{
"filter":{
"range":{
"price":{
"gt":25,
"lt":50
}
}
}
}
}
}
GET lib4/items/_search
{
"query":{
"bool":{
"filter":{
"exists": {
"field": "price"
}
}
}
}
}3、mapping和查询：
GET /1ib/user/_mapping 获取mapping
mapping作用：定义字段的属性，定义字段是否分词
属性：
"store":false//是否单独设置此字段的是否存储而从_source字段中分离，默认是false，只能搜索，不能获取值
"index":true//分词，不分词是:false,设置成false，字段将不会被索引
"analyzer":"ik"//指定分词器，默认分词器为standard analyer
"boost":123//字段级别的分数加权，默认值是1.0
"doc_value":false//对not_analyzed字段，默认都是开启，分词字段不能使用，对排序和聚合能提升较大性能，节约内存
"fielddata":{"format":"disabled"}//针对分词字段，参与排序或聚合时能提高性能，不分词字段统一建议使用doc_value
"fields":{"raw":{"type":"string","index":"not_analyzed"}}//可以对一个字段提供多种索引模式，同一个字段的值，一个分词，一个分词
"ignore_above":100//超过100个字符的文本，将会被忽略，不被索引
"include_in_all":true//设置是否此字段包含在_all字段中，默认时true,除非index设置成no选项
"index_options":"docs"//4个可选参数docs(索引文档号)，freqs(文档号+词项)，positions（文档号+词频+位置，通常用来距离查询）,offsets(文档号+词频
+位置+偏移量，通常被使用在高亮字段)分词字段默认是position，其他的默认是docs
"norms":{"eanbale":true,";loading":"lazy"}//分词字段默认配置，不分词字段：默认（"enable":false）,存储长度因子和索引时boost,建议对需要参与评分
字段使用，会额外增加内存消耗量
"null_value":"NULL"//设置一些缺失字段的初始化值，只有string可以使用，分词字段的null值也会被分词
"position_increament_gap":0//影响距离查询或近似查询，可以设置在多值字段的数据上或分词字段上，查询时可指定slop间隔，默认值是100
"search_analyzer":"ik"//设置搜索时的分词器，默认跟ananlyzer是一致的，比如index时用standard+naram,搜索是用standard用来完成自动提示功能
"similarity":"BM25"//默认不储存向量信息，支持参数yes(term储存),with_position(term+位置),with_offsets(term+偏移量)，
with_positions_offsets(term+位置+偏移量)对快射高亮fast vector highlighter能提供性能,但开启又会加大索引体积，不适合大数据量用
//创建数据
PUT /myindex/articel/1
{
"post_date":"2018-05-10",
"title":"Java",
"content":"java is the best language",
"author_id":119
}
PUT /myindex/articel/2
{
"post_date":"2018-05-12",
"title":"html",
"content":"I like html",
"author_id":120
}
PUT /myindex/articel/3
{
"post_date":"2018-05-16",
"title":"es",
"content":"Es is disbuted document store",
"author_id":110
}
查询数据：
GET myindex/articel/_search
#查不出来
GET myindex/articel/_search?q=post_date:2018
#查出来了
GET myindex/articel/_search?q=post_date:2018-05-16
GET myindex/articel/_search?q=content:is4、match查询：
match query知道分词器的存在，会对filed进行分词操作，然后再查询
GET /lib3/user/_search
{
"query":{
"match":{
"name":"zhaoliu zhaoming"
}
}
}
GET lib3/user/_search
{
"query":{
"match":{
"age":20
}
}
}
match_all:查询所有文档
GET /lib3/user/_search
{
"query":{
"match_all": {}
}
}
GET /lib3/user/_search
{
"query":{
"match_all": {}
}
, "_source": {
"includes": ["name","address"],
"excludes": ["age","brithday"]
}
}
通配符：
GET /lib3/user/_search
{
"query":{
"match_all": {}
}
, "_source": {
"includes": ["addr*"],
"excludes": ["age","bri*"]
}
}
排序：
GET /lib3/user/_search
{
"query":{
"match_all": {}
},
"sort": [
{
"age": {
"order": "desc"
}
}
]
}
multi_match:可以指定多个字段
GET lib3/user/_search
{
"query":{
"multi_match": {
"query": "lvyou",
"fields": ["interests","name"]
}
}
}
match_phrase：短语匹配查询
ElasticSearch引擎首先分析(analyze)查询字符串，从分析后的文本中构建短语查询，这意味着必须匹配短语中的所有分词，并且保证各个分词的相对位置不变
GET lib3/user/_search
{
"query":{
"match_phrase": {
"interests": "duanlian,lvyou"
}
}
}
指定返回的字段：
GET lib3/user/_search
{
"_source": ["address","name"],
"query":{
"match":{
"interests":"changge"
}
}
}
前缀匹配查询
GET lib3/user/_search
{
"_source": ["address","name"],
"query":{
"match_phrase_prefix":{
"name":{
"query":"zhao"
}
}
}
}
范围查询：
GET lib3/user/_search
{
"query":{
"range":{
"brithday":{
"from":"1990-10-10",
"to":"2018-05-01"
}
}
}
}
GET lib3/user/_search
{
"query":{
"range":{
"age":{
"from":"20",
"to":"25",
"include_lower":true,
"include_upper":false
}
}
}
}
wildcard查询：
允许使用通配符*和？来进行查询
*代表0个或多个字符
？代表任意一个字符
GET /lib3/user/_search
{
"query":{
"wildcard": {
"name": "zhao*"
}
}
}
GET /lib3/user/_search
{
"query":{
"wildcard": {
"name": "li?i"
}
}
}
fuzzy实现模糊查询
value：查询的关键字
boost:查询的权值，默认值是：1.0
min_similarity:设置匹配的最小相似度，默认值为0.5，对于字符串，取值为0-1（包括0和1）：对于数值，取值可能大于1；对于日期取值为1d，1m等，1d就代表1天
prefix_length:指明区分词项的共同前缀长度，默认是0
max_expansions:查询中的词项可以扩展的数目，默认可以无限大
GET /lib3/user/_search
{
"query":{
"fuzzy":{
"interests":"changge"
}
}
}
GET /lib3/user/_search
{
"query":{
"fuzzy":{
"interests":{
"value": "changge"
}
}
}
}
高亮搜索结果：（加个标签做强调）
GET /lib3/user/_search
{
"query":{
"match": {
"interests": "changge"
}
},
"highlight":{
"fields": {
"interests": {}
}
}
}5、Multi Get API批量获取文档：
获取指定字段的文档：
GET /_mget
{
"docs":[
{
"_index": "1ib",
"_type": "user",
"_id": 1,
"_source": "interests"
},
{
"_index": "1ib",
"_type": "user",
"_id": 2,
"_source": "interests"
}
]
}
获取相同索引和类型下的文档：
GET /1ib/user/_mget
{
"docs":[
{
"_id":1
},
{
"_type": "user",
"_id": 2
}
]
}
简化：
GET /1ib/user/_mget
{
"ids":["1","2","3"]
}
6、query查询：
数据准备：
PUT /lib3
{
"Settings":{
"number_of_shards":3,
"number_of_replicas":0
},
"mappings":{
"user":{
"properties":{
"name":{"type":"text"},
"address":{"type":"text"},
"age":{"type":"integer"},
"interests":{"type":"text"},
"brithday":{"type":"date"}
}
}
}
}
PUT /lib3/user/1
{
"name":"zhaoliu",
"address":"hei long jiang sheng tie ling shi",
"age":50,
"brithday":"1970-12-12",
"interests":"xi huan hejiu,duanlian,lvyou"
}
PUT /lib3/user/2
{
"name":"zhaoming",
"address":"bei jing hai dian qu qing he zhen",
"age":20,
"brithday":"1998-12-12",
"interests":"xi huan hejiu,duanlian,changge"
}
PUT /lib3/user/3
{
"name":"lisi",
"address":"bei jing hai dian qu qing he zhen",
"age":23,
"brithday":"1998-12-12",
"interests":"xi huan hejiu,duanlian,changge"
}
PUT /lib3/user/4
{
"name":"wangwu",
"address":"bei jing hai dian qu qing he zhen",
"age":26,
"brithday":"1998-12-12",
"interests":"xi huan hejiu,duanlian,changge"
}
PUT /lib3/user/5
{
"name":"zhangsan",
"address":"bei jing hai dian qu qing he zhen",
"age":29,
"brithday":"1998-12-12",
"interests":"xi huan hejiu,duanlian,changge,tiaowu"
}
查询：
#max_score:和当前搜索相关度的匹配分数
GET /lib3/user/_search?q=name:lisi
查询interests为changge且按age倒序排序
GET /lib3/user/_search?q=interests:changge&sort=age:desc
term查询和terms查询
term query会去倒排索引中寻找确切的term，它并不知道分词器的存在。这种查询适合keyword、numeric、date。
term:查询某个字段里含有某个关键词的文档
GET /lib3/user/_search/
{
"query":{"term":{"interests":"changge"}}
}
控制查询返回的数量：
from:从哪一个文档开始size:需要的个数
GET /lib3/user/_search
{
"from":0,"size":2,"query":{"terms": {
"interests": [
"hejiu",
"changge"
]
}}
}
返回版本号：
GET /lib3/user/_search
{
"from":0,"size":2,
"version":true,
"query":{"terms": {
"interests": [
"hejiu",
"changge"
]
}}
}
7、版本控制_并发问题：
每次进行增删改操作时，version会加一
PUT /1ib/user/4?version=2
{ "first_ name" : "Jane",
"last_ name" : "Smith",
"age" : 38,
"about" :"I like to collect rock albums",
"interests": [ "music" ]
}
外部版本控制：version的值需大于当前版本的值
PUT /1ib/user/4?version=4&version_type=external
{ "first_ name" : "Jane",
"last_ name" : "Smith",
"age" : 37,
"about" :"I like to collect rock albums",
"interests": [ "music" ]
}8、多index，多type查询：
多index，多type查询
GET /lib/user/4
GET _search
GET /lib/_search
GET /lib,lib3/_search
GET /*3,*4/_search
GET /lib/user/_search
GET /lib,lib4/user,items/_search
GET /_all/_search
GET /_all/user,items/_search9、分页查询：
from 从第几个文档开始查询
size 查询的数据量
GET /lib/user/_search?from=0&size=310、复合查询：
GET /lib3/user/_search
{
"query":{
"bool":{
"must":{"match":{"interests":"changge"}},
"must_not":{"match":{"interests":"lvyou"}},
"should": [
{"match": {
"address": "bei jing"
}},
{"range":{"brithday": {
"gte": "1996-01-01"
}}}
]
}
}
}
GET /lib3/user/_search
{
"query":{
"bool":{
"must":{"match":{"interests":"changge"}},
"must_not":{"match":{"interests":"lvyou"}},
"should": [
{"match": {
"address": "bei jing"
}}
],
"filter": {
"range": {"brithday": {
"gte": "1996-01-01"
}}
}
}
}
}
GET /lib3/user/_search
{
"query":{
"bool":{
"must":{"match":{"interests":"changge"}},
"must_not":{"match":{"interests":"lvyou"}},
"should": [
{"match": {
"address": "bei jing"
}}
],
"filter": {
"bool":{
"must":[
{"range":{"brithday":{"gte":"1990-01-01"}}},
{"range":{"age":{"lte":30}}}
],
"must_not":[
{"term":{"age":"29"}}
]
}
}
}
}
}
constant_score查询
它将一个不变的常量评分应用于所有匹配的文档，它被经常用于你只需执行一个filter而没有其它查询（例如，评分查询）的情况下
GET /lib3/user/_search
{
"query":{
"constant_score": {
"filter": {
"term":{"interests":"changge"}
}
}
}
}
term查询被放置在contant_score中，转成不评分的filter，这种方式可以取代只有filter语句的bool查询11、基于groovy脚本执行partial update：
GET /lib/user/4
GET /lib/user/4/_update
{
"script":"ctx_source.age+=1"
}
GET /lib/user/4/_update
{
"script":"ctx_source.last_name+='hehe'"
}
GET /lib/user/4/_update
{
"script":{
"source":"ctx_source.interests.add(params.tag)",
"params":{
"tag":"football"
}
}
}
GET /lib/user/4/_update
{
"script":{
"source":"ctx_source.interests.remove(ctx._source.interests.indexof(params.tag))",
"params":{
"tag":"football"
}
}
}
删除文档
GET /lib/user/4/_update
{
"script":{
"source":"ctx_op=ctx._source.age==params.count?'delete':'none'",
"params":{
"count":"22"
}
}
}
upset操作：如果该文档不存在会进行初始化，如果存在执行"script":"ctx._source.age+=1",
GET /lib/user/4/_update
{
"script":"ctx_source.age+=1"
"upset":{
"first_name":"Jame",
"last_name":"Lucy",
"age":20,
"about":"I like to collect rock albums",
"interests":[
"music"
]
}
}12、聚合查询：
所有商品价格的总和
GET /lib4/items/_search
{
"size":0,
"aggs":{
"price_of_sum":{
"sum":{
"field":"price"
}
}
}
所有商品价格的最小值
GET /lib4/items/_search
{
"size":0,
"aggs":{
"price_of_sum":{
"min":{
"field":"price"
}
}
}
}
所有商品价格的平均值
GET /lib4/items/_search
{
"size":0,
"aggs":{
"price_of_sum":{
"avg":{
"field":"price"
}
}
}
}
所有商品价格的奇数列值
GET /lib4/items/_search
{
"size":0,
"aggs":{
"price_of_sum":{
"cardinality":{
"field":"price"
}
}
}
}
所有商品价格分组
GET /lib4/items/_search
{
"size":0,
"aggs":{
"price_of_group":{
"terms":{
"field":"price"
}
}
}
}
对那些有唱歌兴趣的用户按年龄分组
GET /lib3/user/_search
{
"size": 0,
"query":{
"match": {
"interests": "changge"
}
},
"aggs":{
"age_of_group":{
"terms":{
"field":"age"
, "order": {
"age_of_avg": "desc"
}
},
"aggs":{
"age_of_avg":{
"avg": {
"field": "age"
}
}
}
}
}
}
13、使用Bulk API实现批量操作：
bulk的格式
{action:{metadata}}\n
{requestbody}\n
action:(行为)
create:文档不存在时创建
update:更新文档
index:创建新文档或替换已有文档
delete:删除一个文档
metadata:_index,_type,_id
create和index的区别：
如果数据存在，使用create操作失败，会提示文档已经存在，使用index则可以成功执行
列如：
{"delete":{"_index":"1ib","_type":"user","_id":"1"}}
批量添加：
POST /lib2/books/_bulk
{"index":{"_id":1}}
{"title":"java","price":55}
{"index":{"_id":2}}
{"title":"Html5","price":45}
{"index":{"_id":3}}
{"title":"Php","price":35}
{"index":{"_id":4}}
{"title":"Python","price":50}
查询：
GET /lib2/books/_mget
{
"ids":["1","2","3","4"]
}
批量操作：
POST /lib2/books/_bulk
{"delete":{"_index":"lib2","_type":"books","_id":4}}
{"create":{"_index":"tt","_type":"ttt","_id":"100"}}
{"name":"lisi"}
{"update":{"_index":"lib2","_type":"books","_id":"3"}}
{"doc":{"price":58}}