ElasticSearch/Kibana fields on update of document - elasticsearch

I'm very new to ES. I'm using https://github.com/dariusk/corpora/blob/master/data/humans/us_presidents.json as a learning set.
At first I entered this in Dev Tools tab in Kibana:
POST /presidents/president/1
{ "bo" :
{
"website":"",
"startdate":"2009-01-20",
"role_type_label":"President",
"enddate":"2013-01-20",
"description":"President",
"district":null,
"phone":null,
"title":"President",
"congress_numbers":[
111,
112,
113
],
"title_long":"President",
"current":false,
"person":{
"name":"President Barack Obama [D]",
"firstname":"Barack",
"twitterid":null,
"middlename":"",
"gender":"male",
"bioguideid":"O000167",
"namemod":"",
"birthday":"1961-08-04",
"link":"https://www.govtrack.us/congress/members/barack_obama/400629",
"youtubeid":null,
"sortname":"Obama, Barack (President) [D]",
"lastname":"Obama",
"gender_label":"Male",
"osid":"N00009638",
"pvsid":"9490",
"nickname":"",
"id":400629,
"cspanid":null
}
...
}
}
Then I realized that if I want add more data about individual presidents, I should rather do this:
POST /presidents/president/1
{
"website":"",
"startdate":"2009-01-20",
"role_type_label":"President",
"enddate":"2013-01-20",
"description":"President",
"district":null,
"phone":null,
"title":"President",
"congress_numbers":[
111,
112,
113
],
"title_long":"President",
"current":false,
"person":{
"name":"President Barack Obama [D]",
"firstname":"Barack",
"twitterid":null,
"middlename":"",
"gender":"male",
"bioguideid":"O000167",
"namemod":"",
"birthday":"1961-08-04",
"link":"https://www.govtrack.us/congress/members/barack_obama/400629",
"youtubeid":null,
"sortname":"Obama, Barack (President) [D]",
"lastname":"Obama",
"gender_label":"Male",
"osid":"N00009638",
"pvsid":"9490",
"nickname":"",
"id":400629,
"cspanid":null
}
}
OK, so ES accepted the update fine.
But now, when I go to Management / Index Patterns in Kibana, I see both person.lastname and bo.person.lastname as fields.
Why the previous field remained? Is this normal for ES to retain fields that are no longer in the updated document?
And obviously, apart from exceptionally funny ones, please no quips about today's election results.

This is normal, expected, behaviour for Elasticsearch.
ES, by default, will dynamically map the data you are inserting. When you index multiple objects under the same type in an index, all of these objects share the same mapping. The intention is to allow objects to be inserted that do not necessarily carry all of the potential fields of its type, and be inserted into the index anyways.
You can define a mapping yourself, either upon index creation, or by defining a new type for an index. Mappings can also be updated, with some caveats.
To see the mapping of the type in your index, execute the following:
GET /tk_file.2016/TK_FILE/_mapping
Your response will look like this:
{
"presidents": {
"mappings": {
"president": {
"properties": {
"bo": {
"properties": {
"congress_numbers": {
"type": "long"
},
"current": {
"type": "boolean"
},
"description": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"enddate": {
"type": "date"
},
"person": {
"properties": {
"bioguideid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"birthday": {
"type": "date"
},
"firstname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender_label": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "long"
},
"lastname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"middlename": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"namemod": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"nickname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"osid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"pvsid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"sortname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"role_type_label": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"startdate": {
"type": "date"
},
"title": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"title_long": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"website": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"congress_numbers": {
"type": "long"
},
"current": {
"type": "boolean"
},
"description": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"enddate": {
"type": "date"
},
"person": {
"properties": {
"bioguideid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"birthday": {
"type": "date"
},
"firstname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender_label": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "long"
},
"lastname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"middlename": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"namemod": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"nickname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"osid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"pvsid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"sortname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"role_type_label": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"startdate": {
"type": "date"
},
"title": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"title_long": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"website": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
}
}
}
Notice here that you have a set of mappings for the bo object and its related sub-fields, as well as having a mapping for each field of your subsequent document. This is the effect of the dynamic mapping.
To disable this mapping flexibility, you can disable dynamic mappings explicitly, and defining the structure of the document yourself, including its datatypes. Perhaps you want the bioguideid to be an integer instead of text, as it is defined in the current mapping? I direct you to the Mappings API.

Related

results not showing during indexing elastic search

I am performing elastic search full indexing using Bulk request. I have an issue during the indexing the results are coming as empty. As I am deleting the index during the full index, How I can handle this situation.
I have done the these steps:
delete index
Create index
Create Mapping
bulk request
Index properties and Mapping:
{
"products": {
"aliases": {},
"mappings": {
"properties": {
"assemblyrequired": {
"type": "boolean"
},
"australianmade": {
"type": "boolean"
},
"australiasellable": {
"type": "boolean"
},
"avgRating": {
"type": "float"
},
"category": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"categorylevel1": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"categorylevel2": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"categorylevel3": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"categoryname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"categoryname_old": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"clearance": {
"type": "boolean"
},
"commercialuse": {
"type": "boolean"
},
"customisable": {
"type": "boolean"
},
"depth": {
"type": "float"
},
"freedelivery": {
"type": "boolean"
},
"genericcolourcode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"height": {
"type": "float"
},
"hideprice": {
"type": "boolean"
},
"listprice": {
"type": "float"
},
"materialcode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"moneybackguarantee": {
"type": "boolean"
},
"newrelease": {
"type": "boolean"
},
"numberOfRating": {
"type": "long"
},
"online": {
"type": "boolean"
},
"outdooruse": {
"type": "boolean"
},
"predictivecategorydata": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"pricematchguarantee": {
"type": "boolean"
},
"productcode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"productid": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"productimageurl": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"productname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"producttypecode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"promotedprice": {
"type": "float"
},
"sale": {
"type": "integer"
},
"saleprice": {
"type": "float"
},
"sellable": {
"type": "boolean"
},
"sellercode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"shortdescription": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"sku": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"sortweight": {
"type": "long"
},
"state": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"stylecode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"warrantycode": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"weight": {
"type": "float"
},
"width": {
"type": "float"
}
}
},
"settings": {
"index": {
"number_of_shards": "1",
"provided_name": "products",
"max_result_window": "500000",
"creation_date": "1595814303422",
"number_of_replicas": "1",
"uuid": "sGJxwr73Rkyu7-JekWFYsw",
"version": {
"created": "7060199"
}
}
}
}
}
I have around 75k documents.
Thanks,
Sree.
If you want the full index to be available during the reindex, your only option is to not delete the original index until after the indexing is done. In that case, I would probably work with aliases. For example, let's assume products-2020.07.28 was your current index, you would then create a new index for today and change the alias as soon as the indexing is done.
Create Index
PUT /products-2020.07.28
{
"settings": {
... your settings ...
},
"mappings": {
... your mappings ...
}
}
Bulk Index Request
Change Alias to new Index
POST /_aliases
{
"actions" : [
{ "remove" : { "index" : "products-2020.07.27", "alias" : "products" } },
{ "add" : { "index" : "products-2020.07.28", "alias" : "products" } }
]
}
Delete old Index
DELETE /products-2020.07.27
Any requests can then go directly to the alias, instead of the index.
GET /products/_search
That way you can reindex without the user noticing anything.

unique records in elastic search

how to find all the unique records in elastic search based on an attribute in it..
Is there a way?
GET questiondetails/question/_search
{
"size": 0,
"aggs" : {
"Name" : {
"terms" : {
"field" : "owner.user_id.keyword"
}
}
}
}
I tried this way.. But I want it to give all the docs wherever user id is present in the whole record.
Whether it is in inner loop also....
Is there a way to get this in a single query instead of making in multiple queries..
Here is my sample record.
{
"_index": "questiondetails",
"_type": "question",
"_id": "BOktPnABW1evGoA0CqDZ",
"_score": 1,
"_source": {
"tags": [
"android",
"kotlin"
],
"owner": {
"user_id": "10633771"
},
"reply_count": "1",
"reply": [
{
"owner": {
"user_id": "12632101",
"user_type": "registered",
}
}
]
}
}
Index
{
"questiondetails": {
"aliases": {},
"mappings": {
"question": {
"properties": {
"accepted_answer_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"answer_count": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"answers": {
"properties": {
"answer_id": {
"type": "long"
},
"body": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"body_markdown": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"comment_count": {
"type": "long"
},
"comments": {
"properties": {
"comment_id": {
"type": "long"
},
"creation_date": {
"type": "long"
},
"edited": {
"type": "boolean"
},
"owner": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"post_id": {
"type": "long"
},
"reply_to_user": {
"properties": {
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"score": {
"type": "long"
}
}
},
"creation_date": {
"type": "long"
},
"down_vote_count": {
"type": "long"
},
"is_accepted": {
"type": "boolean"
},
"last_activity_date": {
"type": "long"
},
"last_edit_date": {
"type": "long"
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"owner": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"question_id": {
"type": "long"
},
"score": {
"type": "long"
},
"share_link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"title": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"up_vote_count": {
"type": "long"
}
}
},
"body": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"body_markdown": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"close_vote_count": {
"type": "long"
},
"comment_count": {
"type": "long"
},
"comments": {
"properties": {
"body": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"body_markdown": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"comment_id": {
"type": "long"
},
"creation_date": {
"type": "long"
},
"edited": {
"type": "boolean"
},
"owner": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"post_id": {
"type": "long"
},
"reply_to_user": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"score": {
"type": "long"
}
}
},
"creation_date": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"delete_vote_count": {
"type": "long"
},
"down_vote_count": {
"type": "long"
},
"is_answered": {
"type": "boolean"
},
"last_activity_date": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"last_edit_date": {
"type": "long"
},
"last_editor": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"owner": {
"properties": {
"accept_rate": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"display_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_image": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reputation": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"question_id": {
"type": "long"
},
"reopen_vote_count": {
"type": "long"
},
"score": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"share_link": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"tags": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"title": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"up_vote_count": {
"type": "long"
},
"view_count": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
},
"settings": {
"index": {
"creation_date": "1581585452123",
"number_of_shards": "5",
"number_of_replicas": "1",
"uuid": "_nvo_G7ZRvqMIwLmddUXPw",
"version": {
"created": "6020399"
},
"provided_name": "questiondetails"
}
}
}
}
You can achieve what you want with a scripted terms aggregation, like this:
POST questions/_search
{
"size": 0,
"aggs": {
"ids": {
"terms": {
"script": "[doc['owner.user_id.keyword'].value, doc['reply.owner.user_id.keyword'].value]",
"size": 10
}
}
}
}

Unable to search by word "company"

Both the below questions are related to same index
1) I am using Elastic search. My text contains word "companies"
For example: John has worked with companies like Bharat Electronics
and Gillette in senior management positions, wherein he has  set up
new units, managed talent acquisition, systems, processes and laying
out SOP for Human Resources
When I search using following query, I don't find any result however it should have returned data:
{
"query": {
"bool": {
"should": [
{ "match":
{
"fields.bio": "company"
}
}
]
}
}
}
I get zero records however it should have found above record.
2) While creating an index I used english stop words but it still returns records bases on words like an.
The code I used to create an index:
{
"settings": {
"analysis": {
"filter": {
"my_stop": {
"type": "stop",
"stopwords": "_english_"
}
}
}
}
}
So, it should not return any record even though the text contain an word But in reality it is returning records if it finds an word in records.
The index mapping is as follows:
{
"experts": {
"mappings": {
"properties": {
"categories": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"expertise": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"fields": {
"properties": {
"annual_income": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"avg_rating": {
"type": "long"
},
"bio": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"calls": {
"type": "long"
},
"current_company": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"current_country_id": {
"type": "long"
},
"current_position": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"email": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "long"
},
"linkedin_url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"mobileno": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"profile_photo_url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"review_count": {
"type": "long"
},
"total_experience": {
"type": "long"
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"users": {
"type": "long"
}
}
},
"functions": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"industries": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"qualifications": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
}
}
Kindly help.

Elasticsearch - using nested object value in Function Score

I currently have a nested object interest_scores in ES that looks like this:
[{
username: 'Somebody',
interest_scores: [
{ name: 'Running', score: 10 }
{ name: 'Food and drinks', score: 21 }
]
},
{
username: 'SomebodyElse',
interest_scores: [
{ name: 'Running', score: 7 }
{ name: 'Food and drinks', score: 29 }
]
}]
When I enter the search term Running I would like the user with the highest score for Running to get returned first.
I know the way to do this is to use a Function Score Query but I am not sure how to use the matching search term in the function / script. What I think is that the query will return all documents that have the interest "Running" and then I could use something like interest_scores.{match}.score to add to or multiply by the document score.
Any help with this would be greatly appreciated!
As requested, here is the mapping:
{
"influencers": {
"mappings": {
"influencer": {
"properties": {
"email": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"geo": {
"type": "geo_point"
},
"hashtags": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"interest_scores": {
"type": "nested",
"properties": {
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"score": {
"type": "long"
}
}
},
"interests": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"language": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"location": {
"properties": {
"city": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"country": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"country_code": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"lat": {
"type": "float"
},
"lng": {
"type": "float"
},
"state_code": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"subdivision": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"network_data": {
"properties": {
"facebook": {
"properties": {
"url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"instagram": {
"properties": {
"bio": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"engagement": {
"type": "float"
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"picture": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reach": {
"type": "long"
},
"url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"pinterest": {
"properties": {
"url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"twitter": {
"properties": {
"bio": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"engagement": {
"type": "float"
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"picture": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reach": {
"type": "long"
},
"url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"youtube": {
"properties": {
"bio": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"engagement": {
"type": "float"
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"picture": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"reach": {
"type": "long"
},
"url": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"videos": {
"type": "long"
},
"views": {
"type": "long"
},
"views_per_video": {
"type": "float"
}
}
}
}
},
"networks": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"picture": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"total_reach": {
"type": "long"
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
}
}
}
I do not have a function score query yet, I am only testing in the Dev Tools of Kibana - I do have all of the other filters working correctly though. I am just looking to say "If the search term matches a interest_scores.name then sort the hits by the interest_scores.score of that interest_scores.name
Update
The following seems to be working when I test it in Kibana dev tools:
{
"query": {
"nested": {
"path": "interest_scores",
"score_mode": "sum",
"query": {
"function_score": {
"query": {
"match": { "interest_scores.name": "Running" }
},
"script_score": {
"script": "_score + doc['interest_scores.score'].value"
}
}
}
}
}
}
I have tested it with a few different search terms and it always returns the highest score first, but what is weird is that I get the same results when I remove the script_score function. Can anyone tell me if this is a good solution, or why it works without the script_score?
As described here, you can sort by nested fields:
{
"_source": false, # for inner hits - you can remove it
"query": {
"nested": {
"path": "interest_scores",
"filter": {
"range": {
"interest_scores.score": {
"gte": "0"
}
}
},
"inner_hits": {} # for inner hits - you can remove it
}
},
"sort": {
"interest_scores.score": {
"order": "desc",
"mode": "max",
"nested_filter": {
"range": {
"interest_scores.score": {
"gte": "0"
}
}
}
}
}
}
*Pay attention that, you can use the inner_hits ability to show only relevant nested documents. If all inner hits documents are relevant - please remove the marked lines.
**Use the filter on score field or on any other field (e.g: name you would like to filter by).
EDIT 1:
If you want to get the sorted scores of specific name, try:
{
"_source": false,
"query": {
"nested": {
"path": "interest_scores",
"filter": {
"term": {
"interest_scores.name": "SCORE_NAME"
}
},
"inner_hits": {}
}
},
"sort": {
"interest_scores.score": {
"order": "desc",
"mode": "max",
"nested_filter": {
"range": {
"interest_scores.score": {
"gte": "0"
}
}
}
}
}
}
Put the desired score name instead SCORE_NAME.

How can I use/map the field 'geoip.locations' in my index for Kibana which is looking for type 'geo_point'?

I have a log that returns a field called 'ip' from a parsed json field called 'message'.
I've set up my logstash.conf file as so:
filter {
json {
source => "message"
}
geoip {
source => "ip"
target => "geoip"
#add_field => [ "[geoip][coordinates]", "%{[geoip][longitude]}" ]
#add_field => [ "[geoip][coordinates]", "%{[geoip][latitude]}" ]
}
#mutate {
# convert => [ "[geoip][coordinates]", "float"]
#}
}
However, I'm not seeing anything I can use in my index pattern to create a map. Kibana gives me the error:
The "myindex*" index pattern does not contain any of the following field types: geo_point
What am I doing wrong here?
EDIT: results of curl on /_mapping
{
"<my index>": {
"mappings": {
"%{[#metadata][type]}": {
"properties": {
"#timestamp": {
"type": "date"
},
"#version": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"host": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"message": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"tracking log": {
"properties": {
"#timestamp": {
"type": "date"
},
"#version": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"accept_language": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"agent": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"beat": {
"properties": {
"hostname": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"version": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"context": {
"properties": {
"course_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"course_user_tags": {
"type": "object"
},
"org_id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"path": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"user_id": {
"type": "long"
}
}
},
"event": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"event_source": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"event_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"geoip": {
"properties": {
"city_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"continent_code": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"coordinates": {
"type": "float"
},
"country_code2": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"country_code3": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"country_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"dma_code": {
"type": "long"
},
"ip": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"latitude": {
"type": "float"
},
"location": {
"type": "float"
},
"longitude": {
"type": "float"
},
"postal_code": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"region_code": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"region_name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"timezone": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"host": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"input_type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"ip": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"message": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"offset": {
"type": "long"
},
"page": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"referer": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"session": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"source": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"tags": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"time": {
"type": "date"
},
"type": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"username": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
}
}
}
I used this command to execute the map:
curl -XPOST -u elastic 'localhost:9200/_template/<my index>' -H 'Content-Type: application/json' -d'
{"order": 0, "template": "<my index>*","mappings": {"_default_": {"dynamic_templates": [{"location_fields": {"mapping": {"type": "geo_point"},"match": "geoip"}}]}}}
'
You don't need the add_field lines or the mutate/convert. What you do need is to properly map the geoip field as a geo_point in elasticsearch.
Generally you'd do this with an index template -- this mapps any field named geoip to a geo_point -- you can be more specific with your templates though.
POST /_template/myindex
{
"order": 0,
"template": "myindex*",
"mappings": {
"_default_": {
"dynamic_templates": [
{
"location_fields": {
"mapping": {
"type": "geo_point"
},
"match": "location"
}
}
]
}
}
}
In any event, you'll need to re-index your data to get the mapping right and then tell kibana to reload your index mappings (under settings).
Ok - I solved this with the help of #Alcanzar. Apparently, as he said, it is impossible to change a the type of a field once data has been sent to it -- essentially, once you've started logstash and started using it.
So -- to map geoip.location to type geo_point -- here it what I did:
Steps:
1) I stopped logstash.
2) Deleted my index using 'DELETE /"
3) Created a new index with the name I wanted using 'PUT /' in the Kibana dev console.
4) Applied the mapping #Alcanzar contributed above using 'geoip.location' instead of 'location'
5) Restarted logstash.
Now geoip.location is of type geo_point.
It might be obvious that these are the steps to take for some of you experienced ES users, but it wasn't to me. I hope this helps someone else.

Resources