parse nested hash into RUBY to print output, without taking duplicate values - ruby

I have a nested hash and I am able to iterate it and print the section and the field values from the hash. I'm trying to iterate over this nested hash to create a steps guide, I want to create a file with the information and the output file to have the output written like:
steps_guide [section]elemento1 [section]elemento2 [section]elemento3
steps_guide [section]elemento2 [section]elemento3 [section]elemento4
....
steps_guide [section]radio [section]xenon [section]aluminio
steps_guide [section]xenon [section]aluminio [section]boro
If a section name is duplicated in other elementos I only need to print something like:
steps_guide expected_[section_duplicated]elemento1 [section]elemento2 [section]elemento3
and not print that section again and print the next element, and this for all the nested hash. Here is the source data.
_Data =[
{
"name": "script",
"elements": [
{
"name": "unknown group",
"headers": {
"map": {}
},
"agent": "",
"bottom_comments": [],
"checks": [
{
"title": "",
"field": "elemento1",
"section": "control_psd",
"value": "0",
},
{
"title": "",
"field": "elemento2",
"section": "control_psd",
"value": "0",
},
{
"title": "",
"field": "elemento3",
"section": "control_ptt",
"value": "0",
},
{
"title": "",
"field": "elemento4",
"section": "control_save",
"value": "0",
},
{
"title": "",
"section": "control_relay",
"field": "elemento5",
"value": "0",
},
{
"title": "",
"section": "control_relay",
"field": "elemento6",
"value": "1",
},
{
"title": "",
"section": "control_reply",
"field": "elemento7",
"value": "1",
},
{
"title": "",
"section": "plc_status",
"field": "elemento8",
"value": "1",
},
{
"title": "",
"section": "plc_status",
"field": "elemento9",
"value": "1",
},
{
"title": "",
"section": "plc_value",
"field": "elemento10",
"value": "0",
},
{
"type": "condiciones",
"elementos": [
{
"table": [
{
"title": "",
"section": "regresion",
"name": "radio",
},
{
"title": "",
"section": "regresion",
"name": "xenon",
},
{
"title": "",
"section": "update",
"name": "aluminio",
},
{
"title": "",
"section": "cont",
"name": "boro",
},
{
"title": "",
"section": "container",
"name": "oro",
},
{
"title": "",
"section": "after",
"name": "bromo",
},
{
"title": "",
"section": "after",
"name": "oxigeno",
}
]
}
]
}
]
}
]
}
]

Related

Elastic search query - all objects of nested array should have specific value

I want to write Elasticsearch query where I am able to look into a nested array, and check a key for all those elements inside the array, if all of them have that value then the root document should be selected.
this is a sample data :
[
{
"_index": "allproperties",
"_type": "_doc",
"_id": "5241050",
"_score": 0.0,
"_source": {
"id": 5241050,
"type": "HOUSE",
"state": "NSW",
"agency": {
"id": 31,
"code": "AU_LNT",
"name": "Luthor Properties",
"config": "{}"
},
"branch": {
"id": 89,
"name": "Luthor Sales Unit Trust",
"tradingName": "Luthor Properties",
"internalCode": "AU_LNT_G"
},
"images": null,
"leases": [
{
"id": 26439,
"bond": 2000,
"leased": true,
"source": "PORTAL",
"status": "SIGNED",
"endDate": "2022-11-06T00:00:00",
"tenants": [
{
"id": 11106,
"role": "TENANT",
"user": {
"id": 38817,
"dob": "1900-01-01",
"name": "Liam",
"email": "tempo#tempo.com",
"phone": "+61400000000",
"surname": "Tempo",
"salutation": "Mr.",
"invitations": null,
"lastInAppActivity": null
},
"address": "45675 Bruce Hwy, Coolbie QLD 4850, Australia",
"extendedData": "{\"rentSplitAmount\":22.62}",
"roleAdjective": "PRIMARY",
"addressComponents": {
"state": "QLD",
"suburb": "Coolbie",
"country": "Australia",
"postcode": "4850",
"streetName": "Bruce Hwy",
"unitNumber": null,
"poboxNumber": null,
"streetNumber": "45675",
"addressComponentsUnavailable": null
}
}
],
"signDate": "2022-10-05T04:58:08.887",
"startDate": "2022-10-06T00:00:00",
"moveInDate": "2022-10-06T00:00:00",
"appointments": [
{
"id": 3506,
"type": "REMOTE",
"date_time": "2022-10-12T04:56:00+00:00",
"createdBy": "Lex Luthor",
"createdDate": "2022-10-05T04:56:52.936",
"lastModifiedBy": "Lex Luthor",
"lastModifiedDate": "2022-10-05T04:56:53.51"
}
],
"createdDate": "2022-10-05T04:55:42.247",
"rentalAmount": 500,
"dateAvailable": null,
"extendedData": {
"last_rent_adjustment_date": 1665014400000
},
"leaseDuration": 32,
"rentalFrequency": "2",
"signedManually": false
}
],
"refId": "b66326eb-a6b2-42b6-b058-b46847e13399",
"source": "PT",
"status": null,
"suburb": "Hurstville",
"address": "456 Forest Road Hurstville NSW AUSTRALIA 2220",
"country": "Australia",
"bedrooms": 3,
"category": null,
"pmsCode": "84c34d15-a0ab-4791-b9e3-1bdac215b99c",
"postcode": "2220",
"agencyId": 31,
"bathrooms": 3,
"branchId": 89,
"carspaces": 3,
"createdBy": "system",
"streetname": "Forest Road",
"unitnumber": null,
"description": null,
"createdDate": "2022-10-05T04:51:12.619",
"entitlements": [
{
"id": 3453799,
"role": "LANDLORD",
"user": {
"id": 22855,
"dob": null,
"name": "please enter ownership name",
"email": "mag.m#rr.com.au",
"phone": "0400000000",
"surname": "",
"salutation": null,
"lastInAppActivity": null
},
"company": {
"id": 137,
"abn": "",
"acn": "",
"phone": "0400000000",
"address": "1234 Park Avenue New York NY USA 10037-1702",
"companyName": "please enter ownership name",
"displayName": "please enter ownership name",
"email": "mag.m#rr.com.au"
},
"roleAdjective": "GROUP"
},
{
"id": 3453800,
"role": "AGENT",
"user": {
"id": 20054,
"dob": null,
"name": "Paul",
"email": "p.b#mr.com",
"phone": "+61403084232",
"surname": "Botti",
"salutation": null,
"lastInAppActivity": null
},
"company": null,
"roleAdjective": "MANAGING"
},
{
"id": 3453801,
"role": "AGENT",
"user": {
"id": 20054,
"dob": null,
"name": "Paul",
"email": "p.b#mr.com",
"phone": "+61403084232",
"surname": "Botti",
"salutation": null,
"lastInAppActivity": null
},
"company": null,
"roleAdjective": "LEASING"
}
],
"streetnumber": "456",
"advertised": false,
"commission_type": null,
"lastModifiedBy": "system",
"lastModifiedDate": "2022-10-05T04:58:09.043",
"_meta": {
"branches": {
"id": [
89
]
},
"agencies": {
"id": [
31
]
},
"user_property_entitlement": {
"id": [
3453799,
3453800,
3453801
]
},
"users": {
"id": [
20054,
22855,
38817
]
},
"companies": {
"id": [
137
]
},
"leases": {
"id": [
26439
]
},
"user_lease_entitlement": {
"id": [
11106
]
},
"appointments": {
"id": [
3506
]
}
}
},
"sort": [
1664945472619,
0.0
]
}
]
In this particular case, leases is a nested document, I want to select the documents where all the leases are in cancelled state or leases is null, i.e; either all of the objects inside leases should have status as CANCELLED or the leases key should be null.
Already went through this question, but did'nt quite get it as its an old answer from 2015 and methods used in this got deprecated.
Try this query:
GET idx_test/_search?filter_path=hits.hits
{
"query": {
"bool": {
"must_not": [
{
"nested": {
"path": "leases",
"query": {
"bool": {
"must_not": [
{
"bool": {
"should": [
{
"term": {
"leases.status.keyword": "CANCELLED"
}
},
{
"bool": {
"must_not": [
{
"exists": {
"field": "leases"
}
}
]
}
}
]
}
}
]
}
}
}
}
]
}
}
}

ruby extract data from nested array

How I can access to a depth key value from a nested hash?
I want to extract values inside of _Data, I want to extract the field and size inside data[], to be printed like fieldvalue_sizevalue
elemento3_3
I have this code but only get the all the data keys and values and i had some troubles making this iteration, I am new at ruby
_Data[0][:checks].each do |intera|
puts "#{itera[:data]}
end
this is the nested array
_Data =[
{
"agent": "",
"bottom_comments": [],
"checks": [
{
"title": "new",
"data": [{
"field": "elemento1",
"value": "0",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento2",
"value": "0",
"size":"4",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento3",
"value": "0",
"size":"3",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento4",
"value": "0",
"size":"17",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento5",
"value": "0",
"size":"12",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento6",
"value": "0",
"size":"19",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento7",
"value": "0",
"size":"9",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento8",
"value": "0",
"size":"10",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento11",
"value": "0",
"size":"14",
}
]
},
{
"title": "new",
"data": [{
"field": "elemento19",
"value": "0",
"size":"14",
}
]
},
{
"type": "condiciones",
"elementos": [
{
"table": [
{
"title": "",
"name": "radio",
},
{
"title": "",
"name": "xenon",
},
{
"title": "",
"name": "aluminio",
},
{
"title": "",
"name": "boro",
},
{
"title": "",
"name": "oro",
},
{
"title": "",
"name": "bromo",
},
{
"title": "",
"name": "oxigeno",
}
]
}
]
}
]
}
]
_Data[0][:checks].each do |intera|
intera[:data].each do |data|
puts "#{data[:filed]}_#{data[:value]}"
end
end
Hope this may help you.
Here is one line code to print the values if they exist. Let me know if any further details on any of the methods used will be helpful.
_Data[0][:checks].pluck(:data).flatten.compact.each{|i| puts "#{i[:field]}_#{i[:size]}" if i[:field] && i[:size]}

parse nested hash and iterate over to create a ruby file with output

so Im trying to iterate over this nested hash to create a steps guide, I want to create a file with the information and the output file to have the output written like:
steps_guide elemento1 elemento2 elemento3
steps_guide elemento2 elemento3 elemento4
steps_guide elemento3 elemento4 elemento5
steps_guide elemento4 elemento5 elemento6
steps_guide radio xenon aluminio
steps_guide xenon aluminio boro
is there a way to make this? i tried iterating over the hash but unsuccessfully and using each_cons to iterate but still the same
Can you help me? im really stuck on this
This is my nested hash
_Data =[
{
"name": "script",
"elements": [
{
"name": "unknown group",
"headers": {
"map": {}
},
"agent": "",
"bottom_comments": [],
"checks": [
{
"title": "",
"field": "elemento1",
"value": "0",
},
{
"title": "",
"field": "elemento2",
"value": "0",
},
{
"title": "",
"field": "elemento3",
"value": "0",
},
{
"title": "",
"field": "elemento4",
"value": "0",
},
{
"title": "",
"field": "elemento5",
"value": "0",
},
{
"title": "",
"field": "elemento6",
"value": "1",
},
{
"title": "",
"field": "elemento7",
"value": "1",
},
{
"title": "",
"field": "elemento8",
"value": "1",
},
{
"title": "",
"field": "elemento9",
"value": "1",
},
{
"title": "",
"field": "elemento10",
"value": "0",
},
{
"type": "condiciones",
"elementos": [
{
"table": [
{
"title": "",
"name": "radio",
},
{
"title": "",
"name": "xenon",
},
{
"title": "",
"name": "aluminio",
},
{
"title": "",
"name": "boro",
},
{
"title": "",
"name": "oro",
},
{
"title": "",
"name": "bromo",
},
{
"title": "",
"name": "oxigeno",
}
]
}
]
}
]
}
]
}
]
each_cons is the right thing to use. You're probably just having trouble because your data structure is so complicated. Part of the problem is that the last part of your table structure is its own special structure. Split them up to deal with them separately.
all_checks = data[0][:elements][0][:checks]
checks = all_checks[0...-1] # all but the last one
checks.each_cons(3).each do |a, b, c|
puts "steps_guide #{a[:field]} #{b[:field]} #{c[:field]}"
end
elementos = all_checks[-1][:elementos][0][:table]
elementos.each_cons(3).each do |a, b, c|
puts "steps_guide #{a[:name]} #{b[:name]} #{c[:name]}"
end
One thing that might be throwing you off is that "title": in a Ruby hash defines a symbol named :title, not a string as in JSON.

rethinkdb, How could I pluck the result by a value in particular "array index"?

sample data
[
{
"createdDate": 1508588333821,
"data": {
"image_extension": "png",
"name": "Golden",
"qty": 1,
"remark": "#296-2",
"status": "RETURN",
"owner": [
{
"name": "app1emaker",
"location": 1
},
{
"name": "simss92_lmao",
"location": 31
}
]
},
"deleted": false,
"docId": 307,
"docType": "product",
"id": "db0131f9-9359-4aa3-b6ed-cd9f3ff4aa3e",
"updatedDate": 1553155281691
},
{
"createdDate": 1508588333324,
"data": {
"image_extension": "png",
"name": "Golden",
"qty": 1,
"remark": "#296-2",
"status": "DISCARD",
"owner": [
{
"name": "At533",
"location": 7
},
{
"name": "madsimon",
"location": 64
},
{
"name": "boyboy96",
"location": 1
},
{
"name": "xinfengCN",
"location": 5
}
]
},
"deleted": false,
"docId": 308,
"docType": "product",
"id": "3790bdaa-5347-4ab0-8149-37332c23c6ea",
"updatedDate": 1554555231691
},
...
...
]
And said that, I would like to select the data.owner on array index 0 only (or I should say data.owner[0]), which are
{
"name": "app1emaker",
"location": 1
}
and
{
"name": "At533",
"location": 7
}
in this case. I have a failed code below.
r.db('carbon').table("items").pluck(['id', 'docId', 'createdDate',{data:{name: true, owner:[0]}}])
I saw that for some functions like orderBy, rethinkdb allowed to use orderBy(r.row('data')('owner')(0)('name')) for access nested object, but I have no idea how to do this for pluck? could anyone give me some hints?
Thanks a lot
pluck can not do that, but you can fall back to use the map:
r.db("carbon").table("items").map(function(doc){
return {
"id": doc("id"),
"docId": doc("docId"),
"createdDate": doc("createdDate"),
"data": {
"name": doc("data")("name"),
"owner": doc("data")("owner")(0)
}
}
})

REQL to match string expression

I have the following json:
{
"release": {
"genres": {
"genre": "Electronic"
},
"identifiers": {
"identifier": [
{
"description": "Text",
"value": "5 709498 101026",
"type": "Barcode"
},
{
"description": "String",
"value": 5709498101026,
"type": "Barcode"
}
]
},
"status": "Accepted",
"videos": {
"video": [
{
"title": "Future 3 - Renaldo",
"duration": 446,
"description": "Future 3 - Renaldo",
"src": "http://www.youtube.com/watch?v=hpc9aQpnUjc",
"embed": true
},
{
"title": "Future 3 - Silver M from album We are the Future / 1995 Denmark / Archivos de Kraftwerkmusik",
"duration": 461,
"description": "Future 3 - Silver M from album We are the Future / 1995 Denmark / Archivos de Kraftwerkmusik",
"src": "http://www.youtube.com/watch?v=nlcHRI8iV4g",
"embed": true
},
{
"title": "Future 3 - Bubbles At Dawn",
"duration": 710,
"description": "Future 3 - Bubbles At Dawn",
"src": "http://www.youtube.com/watch?v=ABBCyvGMOFw",
"embed": true
}
]
},
"labels": {
"label": {
"catno": "APR 010CD",
"name": "April Records"
}
},
"companies": {
"company": {
"id": 26184,
"catno": "",
"name": "Voices Of Wonder",
"entity_type_name": "Published By",
"resource_url": "http://api.discogs.com/labels/26184",
"entity_type": 21
}
},
"styles": {
"style": [
"Abstract",
"IDM",
"Downtempo"
]
},
"formats": {
"format": {
"text": "",
"name": "CD",
"qty": 1,
"descriptions": {
"description": "Album"
}
}
},
"country": "Denmark",
"id": 5375,
"released": "1995-00-00",
"artists": {
"artist": {
"id": 5139,
"anv": "",
"name": "Future 3",
"role": "",
"tracks": "",
"join": ""
}
},
"title": "We Are The Future 3",
"master_id": 638422,
"tracklist": {
"track": [
{
"position": 1,
"duration": "8:04",
"title": "Future 3"
},
{
"position": 2,
"duration": "7:38",
"title": "Silver M"
},
{
"position": 3,
"duration": "7:27",
"title": "Renaldo"
},
{
"position": 4,
"duration": "6:04",
"title": "B.O.Y.D."
},
{
"position": 5,
"duration": "6:12",
"title": "Fumble"
},
{
"position": 6,
"duration": "6:12",
"title": "Dawn"
},
{
"position": 7,
"duration": "11:54",
"title": "Bubbles At Dawn"
},
{
"position": 8,
"duration": "6:03",
"title": "D.A.W.N. At 6"
},
{
"position": 9,
"duration": "8:50",
"title": 4684351684651
}
]
},
"data_quality": "Needs Vote",
"extraartists": {
"artist": [
{
"id": 2647642,
"anv": "",
"name": "Danesadwork",
"role": "Cover",
"tracks": "",
"join": ""
},
{
"id": 2647647,
"anv": "",
"name": "Djon Edvard Petersen",
"role": "Photography By",
"tracks": "",
"join": ""
},
{
"id": 114164,
"anv": "",
"name": "Anders Remmer",
"role": "Written-By",
"tracks": "",
"join": ""
},
{
"id": 435979,
"anv": "",
"name": "Jesper Skaaning",
"role": "Written-By",
"tracks": "",
"join": ""
},
{
"id": 15691,
"anv": "",
"name": "Thomas Knak",
"role": "Written-By",
"tracks": "",
"join": ""
}
]
},
"notes": "© 1995 April Records APS ℗ 1995 April Records APS"
}
}
I am trying to get those titles which end with 'At Dawn'.
I am using the following command
r.db("discogs1").table("releases").filter(function(doc){ return doc('release')('title').match('At Dawn$')})
But I get errors as follows:
RqlRuntimeError: Expected type STRING but found NUMBER in:r.db("discogs1").table("releases").filter(function(var_24) { return var_24("release")("title").match("At Dawn$"); })
I tried different combinations but I can't seem to get it to work
It seems that some of your documents don't have a row('release')('title') property that is a string. Some of them are numbers, so when you try to call .match on them, they throw an error because .match only works on strings.
To see if this is true, try the following:
r.db("discogs1").table("releases")
.filter(r.row('release')('title').typeOf().ne('STRING'))
.count()
Ideally, the result of this should be 0, since no document should have a title property that's not a string. If it's higher than 0, that's why you're getting an error.
If you want to only get documents where the title is a string, you can do the following:
r.db("discogs1").table("releases")
.filter(r.row('release')('title').typeOf().eq('STRING'))
.filter(function(doc){ return doc('release')('title').match('At Dawn$')})
This query will work, because it will filter our all documents where the title is not a string.
If you want to coerce all title into strings, you can do the following:
r.db("discogs1").table("releases")
.filter(r.row('release')('title').typeOf().ne('STRING'))
.merge(function (row) {
return {
'title': row('title').coerceTo('string')
}
})
If you want to delete all documents where the title is not a string, you can do this:
r.db("discogs1").table("releases")
.filter(r.row('release')('title').typeOf().ne('STRING'))
.delete()

Resources