elasticsearch-script-painless
为了举例说明Painless是如何工作的，让我们加载一些曲棍球统计数据到ElasticSearch的索引中。
PUT hockey/_bulk?refresh
{"index":{"_id":1}}
{"first":"johnny","last":"gaudreau","goals":[9,27,1],"assists":[17,46,0],"gp":[26,82,1],"born":"1993/08/13"}
{"index":{"_id":2}}
{"first":"sean","last":"monohan","goals":[7,54,26],"assists":[11,26,13],"gp":[26,82,82],"born":"1994/10/12"}
{"index":{"_id":3}}
{"first":"jiri","last":"hudler","goals":[5,34,36],"assists":[11,62,42],"gp":[24,80,79],"born":"1984/01/04"}
{"index":{"_id":4}}
{"first":"micheal","last":"frolik","goals":[4,6,15],"assists":[8,23,15],"gp":[26,82,82],"born":"1988/02/17"}
{"index":{"_id":5}}
{"first":"sam","last":"bennett","goals":[5,0,0],"assists":[8,1,0],"gp":[26,1,0],"born":"1996/06/20"}
{"index":{"_id":6}}
{"first":"dennis","last":"wideman","goals":[0,26,15],"assists":[11,30,24],"gp":[26,81,82],"born":"1983/03/20"}
{"index":{"_id":7}}
{"first":"david","last":"jones","goals":[7,19,5],"assists":[3,17,4],"gp":[26,45,34],"born":"1984/08/10"}
{"index":{"_id":8}}
{"first":"tj","last":"brodie","goals":[2,14,7],"assists":[8,42,30],"gp":[26,82,82],"born":"1990/06/07"}
{"index":{"_id":39}}
{"first":"mark","last":"giordano","goals":[6,30,15],"assists":[3,30,24],"gp":[26,60,63],"born":"1983/10/03"}
{"index":{"_id":10}}
{"first":"mikael","last":"backlund","goals":[3,15,13],"assists":[6,24,18],"gp":[26,82,82],"born":"1989/03/17"}
{"index":{"_id":11}}
{"first":"joe","last":"colborne","goals":[3,18,13],"assists":[6,20,24],"gp":[26,67,82],"born":"1990/01/30"}
文档值可以从一个名称为doc的Map中获取
举例说明，下面的脚本计算一个球员的总进球数，这个例子使用了int强类型和for循环。
## 自定义评分计算方式,数组求和,值返回到_score上
GET hockey/_search
{
"query": {
"function_score": {
"script_score": {
"script": {
"lang": "painless",
"source": """
int total = 0;
for(int i = 0; i < doc['goals'].length; ++i){
total += doc['goals'][i];
}
return total;
"""
}
}
}
}
, "size": 2
}
结果
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 12,
"relation" : "eq"
},
"max_score" : 87.0,
"hits" : [
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "2",
"_score" : 87.0,
"_source" : {
"first" : "sean",
"last" : "monohan",
"goals" : [
7,
54,
26
],
"assists" : [
11,
26,
13
],
"gp" : [
26,
82,
82
],
"born" : "1994/10/12"
}
},
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "3",
"_score" : 75.0,
"_source" : {
"first" : "jiri",
"last" : "hudler",
"goals" : [
5,
34,
36
],
"assists" : [
11,
62,
42
],
"gp" : [
24,
80,
79
],
"born" : "1984/01/04"
}
}
]
}
}
或者，你可以使用脚本字段完成同样的事情而不是一个function score
## 返回添加一个字段total_goals,数组求和,返回数组
GET hockey/_search
{
"_source": true,
"script_fields": {
"total_goals": {
"script": {
"lang": "painless",
"source": """
int total = 0;
for(int i = 0; i < doc['goals'].length; ++i){
total += doc['goals'][i];
}
return total;
"""
}
}
}
, "size": 2
}
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 12,
"relation" : "eq"
},
"max_score" : 1.0,
"hits" : [
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"first" : "johnny",
"last" : "gaudreau",
"goals" : [
9,
27,
1
],
"assists" : [
17,
46,
0
],
"gp" : [
26,
82,
1
],
"born" : "1993/08/13"
},
"fields" : {
"total_goals" : [
37
]
}
},
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"first" : "sean",
"last" : "monohan",
"goals" : [
7,
54,
26
],
"assists" : [
11,
26,
13
],
"gp" : [
26,
82,
82
],
"born" : "1994/10/12"
},
"fields" : {
"total_goals" : [
87
]
}
}
]
}
}
如果要拼接的字段不存在，将抛出异常：A document doesn't have a value for a field! Use doc[<field>].size()==0 to check if a document is missing a field!
如果使用doc['last'].value, 将抛异常：Fielddata is disabled on text fields by default. Set fielddata=true on [last] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory. Alternatively use a keyword field instead.
GET hockey/_search
{
"size": 2,
"_source": true,
"script_fields": {
"fullname": {
"script": {
"lang": "painless",
"source": """
if(doc['last.keyword'].size()==0 || doc['first.keyword'].size()==0){
return "";
} else {
return doc['first.keyword'].value +' '+ doc['last.keyword'].value;
}
"""
}
}
}
}
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 12,
"relation" : "eq"
},
"max_score" : 1.0,
"hits" : [
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"first" : "johnny",
"last" : "gaudreau",
"goals" : [
9,
27,
1
],
"assists" : [
17,
46,
0
],
"gp" : [
26,
82,
1
],
"born" : "1993/08/13"
},
"fields" : {
"fullname" : [
"johnny gaudreau"
]
}
},
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"first" : "sean",
"last" : "monohan",
"goals" : [
7,
54,
26
],
"assists" : [
11,
26,
13
],
"gp" : [
26,
82,
82
],
"born" : "1994/10/12"
},
"fields" : {
"fullname" : [
"sean monohan"
]
}
}
]
}
}
你可以非常容易的更新字段值，你可以使用ctx._source.<field-name>获取原始字段。
把球员_id=1的last name改为hockey
POST hockey/_update/1
{
"script": {
"lang": "painless",
"source": "ctx._source.last = params.last",
"params": {
"last": "hockey"
}
}
}
结果
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "1",
"_version" : 2,
"result" : "updated",
"_shards" : {
"total" : 2,
"successful" : 2,
"failed" : 0
},
"_seq_no" : 14,
"_primary_term" : 1
}
新增球员昵称字段nick
POST hockey/_update/1
{
"script": {
"lang": "painless",
"source": """
ctx._source.last = params.last;
ctx._source.nick = params.nick
""",
"params": {
"last": "gaudreau",
"nick": "hockey"
}
}
}
结果
{
"_index" : "hockey",
"_type" : "_doc",
"_id" : "1",
"_version" : 3,
"result" : "updated",
"_shards" : {
"total" : 2,
"successful" : 2,
"failed" : 0
},
"_seq_no" : 15,
"_primary_term" : 1
}
date字段被解释为ZonedDateTime类，所以它支持像getYear，getDayOfWeek或者getMillis。为了在脚本中使用它们，去掉get前缀并且继续小写其余的方法名称，比如下面的例子
## 从出生日期中获取年份
GET hockey/_search
{
"script_fields": {
"birth_year": {
"script": {
"source": "doc.born.value.year"
}
}
}
}
## 从出生日期中获取月份
GET hockey/_search
{
"_source": ["born"],
"script_fields": {
"birth_year": {
"script": {
"source": "doc.born.value.monthValue"
}
}
}
}
## 从出生日期中获取日
GET hockey/_search
{
"_source": ["born"],
"script_fields": {
"birth_day": {
"script": {
"source": "doc.born.value.dayOfMonth"
}
}
}
}
Painless原生就支持拥有语法结构的正则表达式：
-
\pattern\ -
=~: 这个查找操作返回的是boolean值，如果文本的一个字序列匹配上了就返回true，否则返回false -
==~: 这个匹配操作返回的是boolean值，如果文本匹配上返回true，否则返回false
示例1:
POST hockey/_update_by_query
{
"script": {
"lang": "painless",
"source": """
if (ctx._source.last =~ /b/) {
ctx._source.last += "matched";
} else {
ctx.op = "noop";
}
"""
}
}
示例2：
POST hockey/_update_by_query
{
"script": {
"lang": "painless",
"source": """
if (ctx._source.last ==~ /[^aeiou].*[aeiou]/) {
ctx._source.last += "matched";
} else {
ctx.op = "noop";
}
"""
}
}
