Adding index to mappings in MongoDB - node.js

Hey I have a problem with my mongoDb search. I need to add one more index to my search for better result. But since its not in mappings whenever i perform my search as following it returns me nothing.
`
embeddedDocument: {
path: 'produces',
operator: {
compound: {
"must": [
{
autocomplete: {
"path": "produces.name",
"query": val,
"fuzzy": {
"maxEdits": 2,
"prefixLength": 3
}
}
},
{
equals: { path: 'produces.deleted', value: false }
}
],
}
}
}
and here is my index definition
{
"mappings": {
"dynamic": false,
"fields": {
"companyName": [
{
"analyzer": "lucene.standard",
"type": "string"
},
{
"foldDiacritics": true,
"maxGrams": 6,
"minGrams": 2,
"tokenization": "edgeGram",
"type": "autocomplete"
}
],
"produces": {
"type": "embeddedDocuments",
"fields": {
"name": [
{
"analyzer": "lucene.standard",
"type": "string"
},
{
"foldDiacritics": true,
"maxGrams": 6,
"minGrams": 2,
"tokenization": "edgeGram",
"type": "autocomplete"
}
]
}
},
"status": {
"type": "string"
}
}
}
}
So i need to update my index definition as following.
{
"mappings": {
"dynamic": false,
"fields": {
"companyName": [
{
"analyzer": "lucene.standard",
"type": "string"
},
{
"foldDiacritics": true,
"maxGrams": 6,
"minGrams": 2,
"tokenization": "edgeGram",
"type": "autocomplete"
}
],
"produces": {
"type": "embeddedDocuments",
"fields": {
"deleted": {
"type": "boolean"
},
"name": [
{
"analyzer": "lucene.standard",
"type": "string"
},
{
"foldDiacritics": true,
"maxGrams": 6,
"minGrams": 2,
"tokenization": "edgeGram",
"type": "autocomplete"
}
]
}
},
"status": {
"type": "string"
}
}
}
}
`
But my problem is i dont know where to add this index definition on the mongoDB side so i can filter with deleted false criteria.
I tried to add index to mongoDB to produces collection but it doesnt work and i still get empty result.

Related

How to add multiple conditions in JSON schema?

I have the below JSON schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "array",
"items": {
"type": "object",
"properties": {
"op": {
"type": "string",
"minLength": 1,
"enum": [
"add",
"remove",
"replace"
]
},
"path": {
"type": "string",
"minLength": 1,
"enum": [
"/name",
"/description",
"/prefix"
]
},
"value": {
"type": "string",
"minLength": 1
}
},
"additionalProperties": false,
"required": [
"op",
"path",
"value"
],
"minItems": 1,
"allOf": [
{
"if" : {
"properties": {
"path" : {
"const": "/name"
}
}
},
"then": {
"properties": {
"op": {
"const": "replace"
}
}
}
},
{
"if" : {
"properties": {
"path" : {
"const": "/description"
}
}
},
"then": {
"properties": {
"op": {
"const": "replace"
}
}
}
}
]
}
}
As above we can see , if name and description are there ,then op will be replace and for path prefix I have all the operations i.e add , remove and replace , but i want a special condition to be applied for remove operation
Like if path is xFix and op is remove then required parameters should not contain value attrribute , so only op and path.
I think you'll want to turn the logic of that around. Do not include "value" in the "required" list. Instead, add a condition that says, basically, "if op is not 'remove', then value is required".
{
"if" : {
"not": {
"properties": {
"op" : {
"const": "remove"
}
}
}
},
"then": {
"required": ["value"]
}
}

Using JSON descriptors how to define an array in gRPC?

I'm using JSON descriptors instead of proto format. Everithing works, unless the array of Todo. I need an array of Todos.
How define that? I put the "type": "array", but always return the error:
'Error: no such Type or Enum 'array' in Type .Todos'
My json file is like this:
const todo = {
"nested": {
"Services": {
"methods": {
"createTodo": {
"requestType": "Todo",
"requestStream": false,
"responseType": "Todo",
"responseStream": false
},
"readTodos": {
"requestType": "voidNoParam",
"requestStream": false,
"responseType": "Todos",
"responseStream": false
},
"readTodosStream": {
"requestType": "voidNoParam",
"requestStream": false,
"responseType": "Todo",
"responseStream": true
}
}
},
"Todo": {
"fields": {
"id": {
"type": "int32",
"id": 1
},
"text": {
"type": "string",
"id": 2
}
}
},
"Todos": {
"fields": {
"items": {
"type": "array",
"id": 1
}
}
},
"voidNoParam": {
"fields": {}
}
}
}
module.exports = todo
I found the problem, really simple.
"Todos": {
"fields": {
"items": {
"rule": "repeated",
"type": "Todo",
"id": 1
}
}
},

How to apply filter on geo coordinates in elasticsearch?

I am using elasticsearch with mongoosastic npm module. I am trying to apply filter on geo coordinates having following model structure
geoLocation: {
type: {
type: String,
default: 'Point'
},
coordinates: [Number] //orders should be lat,lng
}
with the mapping as follows
{
"events": {
"settings": {
"analysis": {
"filter": {
"edgeNGram_filter": {
"type": "edgeNGram",
"min_gram": 1,
"max_gram": 50,
"side": "front"
}
},
"analyzer": {
"edge_nGram_analyzer": {
"type": "custom",
"tokenizer": "edge_ngram_tokenizer",
"filter": [
"lowercase",
"asciifolding",
"edgeNGram_filter"
]
},
"whitespace_analyzer": {
"type": "custom",
"tokenizer": "whitespace",
"filter": [
"lowercase",
"asciifolding"
]
}
},
"tokenizer": {
"edge_ngram_tokenizer": {
"type": "edgeNGram",
"min_gram": "1",
"max_gram": "50",
"token_chars": [
"letter",
"digit"
]
}
}
}
},
"mappings": {
"event": {
"_all": {
"index_analyzer": "nGram_analyzer",
"search_analyzer": "whitespace_analyzer"
},
"properties": {
"title": {
"type": "string",
"index": "not_analyzed"
},
"geoLocation": {
"index": "not_analyzed",
"type": "geo_point"
}
}
}
}
}
}
Query
{
"query": {
"multi_match": {
"query": "the",
"fields": ["title", ]
}
},
"filter" : {
"geo_distance" : {
"distance" : "200km",
"geoLocation.coordinates" : {
"lat" : 19.007452,
"lon" : 72.831556
}
}
}
}
I am unable to create indexing on the geo coordinates with the following model structure, I dont understand if it is not possible to index geo coordinates with the above model structure because in my case the coordinates has order as lat,long and I have found somewhere that elasticsearch expects coordinates order as long,lat.
Error
Error: SearchPhaseExecutionException[Failed to execute phase [query],
all shards failed; shardFailures {[CDHdgtJnTbeu8tl2mDfllg][events][0]:
SearchParseException[[events][0]: from[-1],size[-1]: Parse Failure
[Failed to parse source
curl -XGET localhost:9200/events
{
"events": {
"aliases": {},
"mappings": {
"1": {
"properties": {
"location": {
"type": "double"
},
"text": {
"type": "string"
}
}
},
"event": {
"properties": {
"city": {
"type": "string"
},
"endTime": {
"type": "date",
"format": "dateOptionalTime"
},
"geo_with_lat_lon": {
"type": "geo_point",
"lat_lon": true
},
"isActive": {
"type": "boolean"
},
"isRecommended": {
"type": "boolean"
},
"location": {
"type": "string"
},
"title": {
"type": "string"
}
}
}
},
"settings": {
"index": {
"creation_date": "1461675012489",
"uuid": "FT-xVUdPQtyuKFm4J4Rd7g",
"number_of_replicas": "1",
"number_of_shards": "5",
"events": {
"mappings": {
"event": {
"_all": {
"enabled": "false",
"search_analyzer": "whitespace_analyzer",
"index_analyzer": "nGram_analyzer"
},
"properties": {
"geoLocation": {
"coordinates": {
"type": "geo_shape",
"index": "not_analyzed"
}
},
"location": {
"type": "string",
"index": "not_analyzed"
},
"title": {
"type": "string",
"index": "not_analyzed"
},
"geo_with_lat_lon": {
"type": "geo_point",
"lat_lon": "true",
"index": "not_analyzed"
}
}
}
},
"settings": {
"analysis": {
"analyzer": {
"edge_nGram_analyzer": {
"type": "custom",
"filter": [
"lowercase",
"asciifolding",
"edgeNGram_filter"
],
"tokenizer": "edge_ngram_tokenizer"
},
"whitespace_analyzer": {
"type": "custom",
"filter": [
"lowercase",
"asciifolding"
],
"tokenizer": "whitespace"
}
},
"filter": {
"edgeNGram_filter": {
"max_gram": "50",
"type": "edgeNGram",
"min_gram": "1",
"side": "front"
}
},
"tokenizer": {
"edge_ngram_tokenizer": {
"max_gram": "50",
"type": "edgeNGram",
"min_gram": "1",
"token_chars": [
"letter",
"digit"
]
}
}
}
}
},
"version": {
"created": "1070099"
}
}
},
"warmers": {}
}
}
I got a solution for my question
Mapping
PUT /geo_test
{
"mappings": {
"type_test": {
"properties": {
"name": {
"type": "string"
},
"geoLocation": {
"type": "nested",
"properties": {
"coordinates": {
"type": "geo_point",
"lat_lon": true
}
}
}
}
}
}
}
Query
POST /geo_test/type_test/_search
{
"query": {
"filtered": {
"filter": {
"nested": {
"path": "geoLocation",
"query": {
"filtered": {
"filter": {
"geo_distance": {
"distance": 5,
"distance_unit": "km",
"geoLocation.coordinates": {
"lat": 41.12,
"lon": -71.34
}
}
}
}
}
}
}
}
}
}

mapper_parsing_exception in new elasticsearch 2.1.1 version

Problem : I have created mapping and its working fine in elasticsearch
1.7.1 but after updating to 2.1.1 it will give me exception
EXCEPTION
response: '{"error":{"root_cause":[{"type":"mapper_parsing_exception","reason"
:"analyzer on field [_all] must be set when search_analyzer is set"}],"type":"ma
pper_parsing_exception","reason":"Failed to parse mapping [movie]: analyzer on f
ield [_all] must be set when search_analyzer is set","caused_by":{"type":"mapper
_parsing_exception","reason":"analyzer on field [_all] must be set when search_a
nalyzer is set"}},"status":400}',
toString: [Function],
toJSON: [Function] }
{
"settings": {
"number_of_shards": 1,
"number_of_replicas": 0,
"analysis": {
"filter": {
"nGram_filter": {
"type": "nGram",
"min_gram": 2,
"max_gram": 20,
"token_chars": [
"letter",
"digit",
"punctuation",
"symbol"
]
}
},
"analyzer": {
"nGram_analyzer": {
"type": "custom",
"tokenizer": "whitespace",
"filter": [
"lowercase",
"asciifolding",
"nGram_filter"
]
},
"whitespace_analyzer": {
"type": "custom",
"tokenizer": "whitespace",
"filter": [
"lowercase",
"asciifolding"
]
}
}
}
},
"mappings": {
"movie": {
"_all": {
"index_analyzer": "nGram_analyzer",
"search_analyzer": "whitespace_analyzer"
},
"properties": {
"movieName": {
"type": "string",
"index": "not_analyzed"
},
"movieYear": {
"type": "double"
},
"imageUrl": {
"type": "string"
},
"genre": {
"type": "string"
},
"director": {
"type": "string"
},
"producer": {
"type": "string"
},
"cast": {
"type": "String"
},
"writer": {
"type": "string"
},
"synopsis": {
"type": "string"
},
"rating": {
"type": "double"
},
"price": {
"type": "double"
},
"format": {
"type": "string"
},
"offer": {
"type": "double"
},
"offerString": {
"type": "string"
},
"language": {
"type": "string"
}
}
}
}
}
The error is quite clear if you ask me, you need to specify analyzer for _all in your movie mapping. Setting index_analyzer was removed in Elasticsearch 2.0.
"_all": {
"analyzer": "nGram_analyzer",
"search_analyzer": "whitespace_analyzer"
},

ElasticSearch query stops working with big amount of data

The problem: I have 2 identical in terms of settings and mappings indexes.
The first index contains only 1 document.
The second index contains the same document + 16M of others.
When I'm running the query on the first index it returns the document, but when I do the same query on the second — I receive nothing.
Indexes settings:
{
"tasks_test": {
"settings": {
"index": {
"analysis": {
"analyzer": {
"tag_analyzer": {
"filter": [
"lowercase",
"tag_filter"
],
"tokenizer": "whitespace",
"type": "custom"
}
},
"filter": {
"tag_filter": {
"type": "word_delimiter",
"type_table": "# => ALPHA"
}
}
},
"creation_date": "1444127141035",
"number_of_replicas": "2",
"number_of_shards": "5",
"uuid": "wTe6WVtLRTq0XwmaLb7BLg",
"version": {
"created": "1050199"
}
}
}
}
}
Mappings:
{
"tasks_test": {
"mappings": {
"Task": {
"dynamic": "false",
"properties": {
"format": "dateOptionalTime",
"include_in_all": false,
"type": "date"
},
"is_private": {
"type": "boolean"
},
"last_timestamp": {
"type": "integer"
},
"name": {
"analyzer": "tag_analyzer",
"type": "string"
},
"project_id": {
"include_in_all": false,
"type": "integer"
},
"user_id": {
"include_in_all": false,
"type": "integer"
}
}
}
}
}
The document:
{
"_index": "tasks_test",
"_type": "Task",
"_id": "1",
"_source": {
"is_private": false,
"name": "135548- test with number",
"project_id": 2,
"user_id": 1
}
}
The query:
{
"query": {
"filtered": {
"query": {
"bool": {
"must": [
[
{
"match": {
"_all": {
"query": "135548",
"type": "phrase_prefix"
}
}
}
]
]
}
},
"filter": {
"bool": {
"must": [
{
"term": {
"is_private": false
}
},
{
"terms": {
"project_id": [
2
]
}
},
{
"terms": {
"user_id": [
1
]
}
}
]
}
}
}
}
}
Also, some findings:
if I replace _all with name everything works
if I replace match_phrase_prefix with match_phrase works too
ES version: 1.5.1
So, the question is: how to make the query work for the second index without mentioned hacks?

Resources