I'm new to elasticsearch, managed to set it up and import recordset from my mongodb collection using the river plugin. For a start, I want to query against the "desc" field but just can't manage to get the query .. not sure if the problem is driven by the way index was defined.. can anyone help please?
Sample recordset in elastic search looks like this
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 107209,
"max_score": 1,
"hits": [
{
"_index": "shiv",
"_type": "shiv",
"_id": "iG1eIzN7RGO7hFfxTlnLuA",
"_score": 1,
"_source": {
"_id": {
"$oid": "50901d7f485bf7bd1c000021"
},
"brand": "",
"category": {
"$ref": "categories",
"$id": {
"$oid": "4fbd2221758cb11d14000174"
}
},
"comments": [],
"count_comment": 0,
"count_fav": 2,
"count_hotness": 1.46,
"count_rekick": 0,
"count_share": 0,
"country": {
"$ref": "countries",
"$id": {
"$oid": "4fec98f7758cb18c6e0002c9"
}
},
"currency": "pound",
"desc": "A men's automatic watch, this Seamaster Bond model features a Co-Axial escapement and date function. Its blue dial is teamed with a stainless steel case and bracelet for a look that's sporty and refined.",
"gender": "male",
"ident": "omega-seamaster-diver-bond-men-s-automatic-watch---ernest-jones-1351622015",
"img_url": "http://s7ondemand4.scene7.com/is/image/Signet/5735793?$detail$",
"lifestyles": [
{
"$ref": "lifestyles",
"$id": {
"$oid": "508ff6ca485bf73112000060"
}
}
],
"location": "United Kingdom",
"owner": {
"$ref": "accounts",
"$id": {
"$oid": "50742fd8485bf74b7a00213f"
}
},
"price": 2400,
"store": "ernestjones.co.uk",
"tags": [
"ernest-jones",
"bond"
],
"timestamp_creation": 1351622015,
"timestamp_exp": 1356825600,
"timestamp_update": 1351622015,
"title": "Omega Seamaster Diver Bond men's automatic watch - Ernest Jones",
"url": "http%3A%2F%2Fwww.ernestjones.co.uk%2Fwebstore%2Fd%2F5735793%2Fomega%20seamaster%20diver%20bond%20men%27s%20automatic%20watch%2F%3Futm_source%3Dgooglebase%26utm_medium%3Dfeedmanager%26cm_mmc%3DFroogle-_-CKB-_-nurses_fobs-_-watches%26cm_mmca1%3Domega%26cm_mmca2%3Dmale%26cm_mmca3%3Dadult"
}
}
]
}
}
The mapping of the index "shiv" looks like
{
"shiv": {
"properties": {
"$oid": {
"type": "string"
}
}
}
}
Thanks again
There are lots of ways to query, have you tried a match query?
Using curl or a rest client of your choice...
http://[host]:9200/[index_name]/[doc_type]/_search
{
"query" : {
"match" : {
"desc" : "some value you want to find in desc"
}
}
}
Related
I have multiple documents saved which look like the one shown below, how would I query against a nested object without the ID to receive the right document?
Here is what I current, but this doesnt work, as I dont have the ID at the start.
db.collection.find({
"details.hardware.id": 5,
})
This is what ive tested and know works but I dont know the ID -
db.collection.find({
"100201.details.hardware.id": 5,
})
Document example -
[
{
"_id": {
"$oid": "6338b69062433c04642d26ca"
},
"100201": {
"broken": true,
"details": {
"build": {
"id": 1018458,
},
"hardware": {
"id": 5,
"model": {
"id": 131,
},
},
"id": 2811302,
"view": {
"id": 781,
}
},
"id": "100201",
"links": [
{
"details": {
"id": 7832,
},
"id": 15012,
},
{
"description": null,
"details": {
"id": 6528,
"model": {
"id": 530
}
},
"id": 15076,
}
],
"ref": false,
}
}
]
any help would be appreciated
I have my json object like this
{
"_id": "5c2e811154855c0012308f00",
"__pclass": "QXRzXFByb2plY3RcTW9kZWxcUHJvamVjdA==",
"id": 44328,
"name": "Test project via postman2//2",
"address": "some random address",
"area": null,
"bidDate": null,
"building": {
"name": "Health Care Facilities",
"type": "Dental Clinic"
},
"collaborators": [],
"createdBy": {
"user": {
"id": 7662036,
"name": "Someone Here"
},
"firm": {
"id": 2520967,
"type": "ATS"
}
},
"createdDate": "2019-01-03T21:39:29Z",
"customers": [],
"doneBy": null,
"file": null,
"firm": {
"id": 1,
"name": "MyFirm"
},
"leadSource": {
"name": "dontknow",
"number": "93794497"
},
"location": {
"id": null,
"city": {
"id": 567,
"name": "Bahamas"
},
"country": {
"id": 38,
"name": "Canada"
},
"province": {
"id": 7,
"name": "British Columbia"
}
},
"modifiedBy": null,
"modifiedDate": null,
"projectPhase": {
"id": 1,
"name": "pre-design"
},
"quotes": [{
"id": 19,
"opportunityValues": {
"Key1": 100,
"Key2 Key2": 100,
"Key3 Key3 Key3": 200,
}
}],
"specForecast": [],
"specIds": [],
"tags": [],
"valuation": "something"
}
I am trying to aggregate using this query in MongoDB. My aggregation key is 4 level deep and also contains spaces. On all online examples shows me the aggregation at the first level. Looking to the online codes, I tried to re-iterate the same with my 4th level deep key.
db.mydata.aggregate([
{$match: {"id": 44328 } } ,
{$group: { _id: "$quotes.id",
totalKey2:{ $sum: "$quotes.opportunityValues.Key2 Key2"},
totalKey3:{ $sum: "$quotes.opportunityValues.Key3 Key3 Key3"}
}
}
]);
This should return
_id totalKey2 totalKey3
0 19 100 300
But it is returning
_id totalKey2 totalKey3
0 19 0 0
What am I doing Wrong?
Although it's not recommended to use space in field names in Mongo, it works as expected.
The problem with your query is that "quotes" is an array and you should first unwind it before grouping it.
This works as expected:
db.mydata.aggregate([
{ $match: { "id": 44328 } } ,
{ $unwind: "$quotes" },
{ $group: { _id: "$quotes.id",
totalKey2:{ $sum: "$quotes.opportunityValues.Key2 Key2" },
totalKey3:{ $sum: "$quotes.opportunityValues.Key3 Key3 Key3" } }
}
]);
{
"_id": {
"$oid": "5a99553c1b4a1b0922039e73"
},
"date_added": {
"$date": "2018-03-02T13:42:36.684Z"
},
"title": "Black Panther",
"__v": 14,
"alls": [
{
"name": "Mbezi",
"geocoordinates": "-6.8140361,39.2775983",
"region": "Dar es salaam",
"times": "",
"_id": {
"$oid": "5a9c74885980731a35a013b2"
}
},
{
"name": "DFM",
"geocoordinates": "-6.7726935,39.2196418",
"region": "Dar es salaam",
"times": "",
"_id": {
"$oid": "5a9c7f61bb57291a81d8309e"
}
}
]
}
How can i find alls name equals to "Mbezi" and update times to a certain value? Any links that can help me will be appreciated..
My document looks like:
"hits": {
"total": 4,
"max_score": 1,
"hits": [
{
"_index": "test_db2",
"_type": "test",
"_id": "1",
"_score": 1,
"_source": {
"name": "very cool shoes",
"price": 26
}
},
{
"_index": "test_db2",
"_type": "test",
"_id": "2",
"_score": 1,
"_source": {
"name": "great shampoo",
"price": 15
}
},
{
"_index": "test_db2",
"_type": "test",
"_id": "3",
"_score": 1,
"_source": {
"name": "shirt",
"price": 25
}
}
]
}
How to create autocomplete in elasticsearch like for example:
I put in input word "sh" , after that I should see result
shoes
shampoo
shirt
.....
Example of what I need
Take a look at ngrams. Or actually, edge ngrams are probably all you need.
Qbox has a couple of blog posts about setting up autocomplete with ngrams, so for a more in-depth discussion I would refer you to these:
https://qbox.io/blog/an-introduction-to-ngrams-in-elasticsearch
https://qbox.io/blog/multi-field-partial-word-autocomplete-in-elasticsearch-using-ngrams
But just very quickly, this should get you started.
First I set up the index:
PUT /test_index
{
"settings": {
"analysis": {
"analyzer": {
"autocomplete": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"standard",
"stop",
"kstem",
"edgengram_filter"
]
}
},
"filter": {
"edgengram_filter": {
"type": "edgeNGram",
"min_gram": 2,
"max_gram": 15
}
}
}
},
"mappings": {
"doc": {
"properties": {
"name": {
"type": "string",
"index_analyzer": "autocomplete",
"search_analyzer": "standard"
},
"price":{
"type": "integer"
}
}
}
}
}
Then I indexed your documents:
POST /test_index/doc/_bulk
{"index":{"_id":1}}
{"name": "very cool shoes","price": 26}
{"index":{"_id":2}}
{"name": "great shampoo","price": 15}
{"index":{"_id":3}}
{"name": "shirt","price": 25}
Now I can get autocomplete results with a simple match query:
POST /test_index/_search
{
"query": {
"match": {
"name": "sh"
}
}
}
which returns:
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 3,
"max_score": 0.30685282,
"hits": [
{
"_index": "test_index",
"_type": "doc",
"_id": "3",
"_score": 0.30685282,
"_source": {
"name": "shirt",
"price": 25
}
},
{
"_index": "test_index",
"_type": "doc",
"_id": "2",
"_score": 0.19178301,
"_source": {
"name": "great shampoo",
"price": 15
}
},
{
"_index": "test_index",
"_type": "doc",
"_id": "1",
"_score": 0.15342641,
"_source": {
"name": "very cool shoes",
"price": 26
}
}
]
}
}
Here's the code I used to test it:
http://sense.qbox.io/gist/0886488ddfb045c69eed67b15e9734187c8b2491
Building my first RESTful api, and thought I'd try elasticsearch for a base. Is there a way customize the API in Elasticsearch to only return certain fields from results of a query. For instance if I have data with fname, lname, city, state, zip, email and I only want to return a list of fnames and cities for every query matching the city field. So something like this:
curl -XPOST "http://localhost:9200/custom_call/_search" -d'
{
"query": {
"query_string": {
"query": "Toronto",
"fields": ["city"]
}
}
}'
Would ideally return something like:
{"took": 52, "timed_out": false, "_shards": {
"total": 35,
"successful": 35,
"failed": 0
}, "hits": {
"total": 1,
"max_score": 0.375,
"hits": [
{
"_index": "persons",
"_type": "person",
"_id": "6",
"_score": 0.375,
"_source": {
"fname": "Bob",
"city": "Toronto",
}
},
{
"_index": "persons",
"_type": "person",
"_id": "13",
"_score": 0.375,
"_source": {
"fname": "Sue",
"city": "Toronto",
}
},
{
"_index": "persons",
"_type": "person",
"_id": "21",
"_score": 0.375,
"_source": {
"fname": "Jose",
"city": "Toronto",
}
}
]
}}
Not sure if Elasticsearch is set up to do this or even if you would want it to. My first foray into building a RESTful API. I figure if NPR StackOverflow like it, its worth a shot! Thanks for the help.
Yes you can, I think you haven't tried to find out on your own.
Here is how to do that,
POST localhost:9200/index/type/_search
{
"query": {
"query_string": {
"query": "Toronto",
"fields": ["city"]
}
},
"_source" :["fields_you_want_to_get"]
}
The term you are looking is source filtering.