How to concatenate multiple string fields into single field using MongoDB Aggregation? - python

Let's suppose I have an incoming data in the following format:
{
"Name": "Test"
"Location": "Whatever",
"customerServices": [
{
"id": "test",
"cusId": "test",
"adr": "Adr 1",
"serviceCounty": "Center",
"area": "village"
},
{
"id": "test",
"cusId": "test",
"adr": "adr2",
"serviceCounty": "West",
"area": "city"
},
{
"id": "test",
"cusId": "test",
"adr": "test",
"serviceCounty": "West",
"area": "test"
}
]
}
Any ideas, how to write an aggregation query which would:
Create a new field called 'serviceAreas'. Type: list
For each item in the 'customerServices'. It would select: adr, serviceCounty and area fields.
Append them together into a single string and add to the newly created serviceAreas field.
It would select and do the operation only for distinct serviceCounty items
So the end result would be like this:
{
"Name": "Test"
"Location": "Whatever",
"customerServices": [
{
"id": "test",
"cusId": "test",
"adr": "Adr 1",
"serviceCounty": "Center",
"area": "village"
},
{
"id": "test",
"cusId": "test",
"adr": "adr2",
"serviceCounty": "West",
"area": "city"
},
{
"id": "test",
"cusId": "test",
"adr": "test",
"serviceCounty": "West",
"area": "test"
}
],
"serviceAreas": [
"Adr 1, Center, village", "adr2, West, city"
]
}
Any help is appreciated!
Here is what I have tried, but it didn't work out:
'serviceAreas': {
'$reduce': {
'input': '$serviceImpactHistory.event.services',
'initialValue': [],
'in': {
'$setUnion': [
'$$value', {'$concat': ['$$this.serviceCounty', '$$this.adr', '$$this.area']}
]
}
}
},

You don't need to use $setUnion, just create your string with $concat
db.collection.aggregate([
{
$addFields: {
serviceAreas: {
"$reduce": {
"input": "$customerServices",
"initialValue": "",
"in": {
"$concat": [
"$$value",
"$$this.serviceCounty",
", ",
"$$this.adr",
", ",
"$$this.area",
", "
]
}
}
}
}
}
])
Try it here

Related

Modify the value of a field of a specific nested object (its index) depending on a condition

I would like to modify the value of a field on a specific index of a nested type depending on another value of the same nested object or a field outside of the nested object.
As example, I have the current mapping of my index feed:
{
"feed": {
"mappings": {
"properties": {
"attacks_ids": {
"type": "keyword"
},
"created_by": {
"type": "keyword"
},
"date": {
"type": "date"
},
"groups_related": {
"type": "keyword"
},
"indicators": {
"type": "nested",
"properties": {
"date": {
"type": "date"
},
"description": {
"type": "text"
},
"role": {
"type": "keyword"
},
"type": {
"type": "keyword"
},
"value": {
"type": "keyword"
}
}
},
"malware_families": {
"type": "keyword"
},
"published": {
"type": "boolean"
},
"references": {
"type": "keyword"
},
"tags": {
"type": "keyword"
},
"targeted_countries": {
"type": "keyword"
},
"title": {
"type": "text"
},
"tlp": {
"type": "keyword"
}
}
}
}
}
Take the following document as example:
{
"took": 194,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 1,
"hits": [
{
"_index": "feed",
"_type": "_doc",
"_id": "W3CS7IABovFpcGfZjfyu",
"_score": 1,
"_source": {
"title": "Test",
"date": "2022-05-22T16:21:09.159711",
"created_by": "finch",
"tlp": "white",
"published": true,
"references": [
"test",
"test"
],
"tags": [
"tag1",
"tag2"
],
"targeted_countries": [
"Italy",
"Germany"
],
"malware_families": [
"family1",
"family2"
],
"groups_related": [
"group1",
"griup2"
],
"attacks_ids": [
""
],
"indicators": [
{
"value": "testest",
"description": "This is a test",
"type": "sha256",
"role": "file",
"date": "2022-05-22T16:21:09.159560"
},
{
"value": "testest2",
"description": "This is a test 2",
"type": "ipv4",
"role": "c2",
"date": "2022-05-22T16:21:09.159699"
}
]
}
}
]
}
}
I would like to make this update: indicators[0].value = 'changed'
if _id == 'W3CS7IABovFpcGfZjfyu'
or if title == 'some_title'
or if indicators[0].role == 'c2'
I already tried with a script, but it seems I can't manage to get it work, I hope the explanation is clear, ask any question if not, thank you.
Edit 1:
I managed to make it work, however it needs the _id, still looking for a way to do that without it.
My partial solution:
update = Pulse.get(id="XHCz7IABovFpcGfZWfz9") #Pulse is my document
update.update(script="for (indicator in ctx._source.indicators) {if (indicator.value=='changed2') {indicator.value='changed3'}}")
# Modify depending on the value of a field inside the same nested object

Elasticsearch DSL, filter list of objects with in list of values

my data looks like this:
[
{
"id": "00f0bbe514dcaf262c8a",
"status": "CL",
"type": "opportunity",
"locations": [
{
"name": "New York, USA",
"lat": 99.0853,
"lng": 99.7818,
"id": "456",
"type": "CI"
},
{
"name": "Boston, USA",
"lat": 80.0853,
"lng": 80.7818,
"id": "555",
"type": "CI"
},
{
"name": "London, UK",
"lat": 10.0853,
"lng": 10.7818,
"id": "999",
"type": "CI"
}
]
},
{
"id": "sadl9asod01",
"status": "CL",
"type": "opportunity",
"locations": [
{
"name": "Boston, USA",
"lat": 80.0853,
"lng": 80.7818,
"id": "555",
"type": "CI"
},
]
},
{
"id": "13094ulk",
"status": "CL",
"type": "project", # has right location but not type
"locations": [
{
"name": "Boston, USA",
"lat": 80.0853,
"lng": 80.7818,
"id": "555",
"type": "CI"
},
]
}
]
I want to build a query that the type must be opportunity:
type_q = ElasticQ('bool', must=[ElasticQ('match', type='opportunity')])
query = self.index.search().query(type_q)
I know how to build an "in" query with the dsl, for example:
excluded_ids = self._excluded_jobs() # list
query = query.exclude('terms', id=excluded_ids)
but, how can I add to the query what in SQL I would do like this:
WHERE type='opportunity'
AND
location.id in (1, 2, 3)
location represents here object inside the locations array of the doc
Something like:
type_q = ElasticQ('bool', must=[
ElasticQ('match', type='opportunity'),
ElasticQ('terms', id=excluded_ids),
])
Or, if you actually wanted to exclude those IDs:
type_q = ElasticQ('bool',
must=[ElasticQ('match', type='opportunity')]
must_not=[ElasticQ('terms', id=excluded_ids)]
)

Best way to parse a JSON to store in SQL database (SQL stored procedure/Python)

I have a table of overly complex JSON files I'm trying to convert to tabular format to store in a SQL database. I'm pulling the JSONs from the quickbooks online API, and the format is messy to say the least.. (We're talking 7x nested JSONs for some bits of it..
The format resembles the code snippet down below. Currently I am using a bunch of OpenJSON's + Cross applys to dig down to the innermost ColData then work my way up but it looks like some of the ColData's get skipped over doing that.
Are there any better ways, using either Python (since I pull the JSON initially in Python before sending the JSON to a SQL database to parse) or SQL to convert it to tabular format besides manually trying to use OpenJSON with Cross applys?
The goal is to get all of the ColData's into a SQL table...
Thanks!
{
"Header": {
"ReportName": "BalanceSheet",
"Option": [
{
"Name": "AccountingStandard",
"Value": "GAAP"
},
{
"Name": "NoReportData",
"Value": "false"
}
],
"DateMacro": "this calendar year-to-date",
"ReportBasis": "Accrual",
"StartPeriod": "2016-01-01",
"Currency": "USD",
"EndPeriod": "2016-10-31",
"Time": "2016-10-31T09:42:21-07:00",
"SummarizeColumnsBy": "Total"
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "ASSETS"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Current Assets"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Bank Accounts"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "35",
"value": "Checking"
},
{
"value": "1350.55"
}
],
"type": "Data"
},
{
"ColData": [
{
"id": "36",
"value": "Savings"
},
{
"value": "800.00"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "BankAccounts",
"Summary": {
"ColData": [
{
"value": "Total Bank Accounts"
},
{
"value": "2150.55"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Accounts Receivable"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "84",
"value": "Accounts Receivable (A/R)"
},
{
"value": "6383.12"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "AR",
"Summary": {
"ColData": [
{
"value": "Total Accounts Receivable"
},
{
"value": "6383.12"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Other current assets"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "81",
"value": "Inventory Asset"
},
{
"value": "596.25"
}
],
"type": "Data"
},
{
"ColData": [
{
"id": "4",
"value": "Undeposited Funds"
},
{
"value": "2117.52"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "OtherCurrentAssets",
"Summary": {
"ColData": [
{
"value": "Total Other current assets"
},
{
"value": "2713.77"
}
]
}
}
]
},
"type": "Section",
"group": "CurrentAssets",
"Summary": {
"ColData": [
{
"value": "Total Current Assets"
},
{
"value": "11247.44"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Fixed Assets"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"id": "37",
"value": "Truck"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "38",
"value": "Original Cost"
},
{
"value": "13495.00"
}
],
"type": "Data"
}
]
},
"type": "Section",
"Summary": {
"ColData": [
{
"value": "Total Truck"
},
{
"value": "13495.00"
}
]
}
}
]
},
"type": "Section",
"group": "FixedAssets",
"Summary": {
"ColData": [
{
"value": "Total Fixed Assets"
},
{
"value": "13495.00"
}
]
}
}
]
},
"type": "Section",
"group": "TotalAssets",
"Summary": {
"ColData": [
{
"value": "TOTAL ASSETS"
},
{
"value": "24742.44"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "LIABILITIES AND EQUITY"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Liabilities"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Current Liabilities"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Accounts Payable"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "33",
"value": "Accounts Payable (A/P)"
},
{
"value": "1984.17"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "AP",
"Summary": {
"ColData": [
{
"value": "Total Accounts Payable"
},
{
"value": "1984.17"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Credit Cards"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "41",
"value": "Mastercard"
},
{
"value": "157.72"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "CreditCards",
"Summary": {
"ColData": [
{
"value": "Total Credit Cards"
},
{
"value": "157.72"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Other Current Liabilities"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "89",
"value": "Arizona Dept. of Revenue Payable"
},
{
"value": "4.55"
}
],
"type": "Data"
},
{
"ColData": [
{
"id": "90",
"value": "Board of Equalization Payable"
},
{
"value": "401.98"
}
],
"type": "Data"
},
{
"ColData": [
{
"id": "43",
"value": "Loan Payable"
},
{
"value": "4000.00"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "OtherCurrentLiabilities",
"Summary": {
"ColData": [
{
"value": "Total Other Current Liabilities"
},
{
"value": "4406.53"
}
]
}
}
]
},
"type": "Section",
"group": "CurrentLiabilities",
"Summary": {
"ColData": [
{
"value": "Total Current Liabilities"
},
{
"value": "6548.42"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Long-Term Liabilities"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "44",
"value": "Notes Payable"
},
{
"value": "25000.00"
}
],
"type": "Data"
}
]
},
"type": "Section",
"group": "LongTermLiabilities",
"Summary": {
"ColData": [
{
"value": "Total Long-Term Liabilities"
},
{
"value": "25000.00"
}
]
}
}
]
},
"type": "Section",
"group": "Liabilities",
"Summary": {
"ColData": [
{
"value": "Total Liabilities"
},
{
"value": "31548.42"
}
]
}
},
{
"Header": {
"ColData": [
{
"value": "Equity"
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"id": "34",
"value": "Opening Balance Equity"
},
{
"value": "-9337.50"
}
],
"type": "Data"
},
{
"ColData": [
{
"id": "2",
"value": "Retained Earnings"
},
{
"value": "91.25"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Net Income"
},
{
"value": "2440.27"
}
],
"type": "Data",
"group": "NetIncome"
}
]
},
"type": "Section",
"group": "Equity",
"Summary": {
"ColData": [
{
"value": "Total Equity"
},
{
"value": "-6805.98"
}
]
}
}
]
},
"type": "Section",
"group": "TotalLiabilitiesAndEquity",
"Summary": {
"ColData": [
{
"value": "TOTAL LIABILITIES AND EQUITY"
},
{
"value": "24742.44"
}
]
}
}
]
},
"Columns": {
"Column": [
{
"ColType": "Account",
"ColTitle": "",
"MetaData": [
{
"Name": "ColKey",
"Value": "account"
}
]
},
{
"ColType": "Money",
"ColTitle": "Total",
"MetaData": [
{
"Name": "ColKey",
"Value": "total"
}
]
}
]
}
}
Here is what I tried to get the ColData (unsuccessfully I might add), I think it might be a little too contrived to do in SQL but I'm not sure if I should continue trying this way or if there's a better way in Python:
declare #json nvarchar(max)
SELECT #json = json FROM QboApiRawJSONData WHERE ID = 2
--Outer layer of JSON breaks into 3 parts - header, columns, rows
SELECT * FROM OPENJSON(#json)
WITH
(
Rows nvarchar(max) AS JSON
) as MainLayer
CROSS APPLY OPENJSON (MainLayer.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as SecondaryLayer
CROSS APPLY OPENJSON (SecondaryLayer.Row)
WITH
(
Rows nvarchar(max) AS JSON
) As ThirdLayer
CROSS APPLY OPENJSON (ThirdLayer.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as FourthLayer
CROSS APPLY OPENJSON (FourthLayer.Row)
WITH
(
Rows nvarchar(max) AS JSON
) as FifthLayer
CROSS APPLY OPENJSON (FifthLayer.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as SixthLayer
CROSS APPLY OPENJSON (SixthLayer.Row)
WITH
(
Rows nvarchar(max) AS JSON
) as SeventhLayer
CROSS APPLY OPENJSON (SeventhLayer.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as EighthLayer
CROSS APPLY OPENJSON (EighthLayer.Row)
WITH
(
Rows nvarchar(max) AS JSON
) as LayerNine
---Things get funky here
CROSS APPLY OPENJSON (LayerNine.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as LayerTen
CROSS APPLY OPENJSON (LayerTen.Row)
WITH
(
Rows nvarchar(max) AS JSON
) as LayerEleven
CROSS APPLY OPENJSON (LayerEleven.Rows)
WITH
(
Row nvarchar(max) AS JSON
) as LayerTwelve
--21 items in last col
There is JSON support for sql-server:
https://learn.microsoft.com/en-us/sql/relational-databases/json/json-data-sql-server?view=sql-server-ver15
There is a JSON storage method here: https://learn.microsoft.com/en-us/sql/relational-databases/json/store-json-documents-in-sql-tables?view=sql-server-ver15. Although it will be fairly complex here I recommend storing the JSON data as a Logs table and then following the tutorial above to see if that solves your issue.
Use Quickbooks API to get the JSON, then refer to this guide:
https://learn.microsoft.com/en-us/sql/relational-databases/json/json-data-sql-server?view=sql-server-ver15
and this guide:
https://learn.microsoft.com/en-us/sql/relational-databases/json/convert-json-data-to-rows-and-columns-with-openjson-sql-server?view=sql-server-ver15
You can also consider setting something like AWS Lambda or Google Cloud Functions if you need something more automated.

Python Script to convert multiple json files in to single csv

{
"type": "Data",
"version": "1.0",
"box": {
"identifier": "abcdef",
"serial": "12345678"
},
"payload": {
"Type": "EL",
"Version": "1",
"Result": "Successful",
"Reference": null,
"Box": {
"Identifier": "abcdef",
"Serial": "12345678"
},
"Configuration": {
"EL": "1"
},
"vent": [
{
"ventType": "Arm",
"Timestamp": "2020-03-18T12:17:04+10:00",
"Parameters": [
{
"Name": "Arm",
"Value": "LT"
},
{
"Name": "Status",
"Value": "LD"
}
]
},
{
"ventType": "Arm",
"Timestamp": "2020-03-18T12:17:24+10:00",
"Parameters": [
{
"Name": "Arm",
"Value": "LT"
},
{
"Name": "Status",
"Value": "LD"
}
]
},
{
"EventType": "TimeUpdateCompleted",
"Timestamp": "2020-03-18T02:23:21.2979668Z",
"Parameters": [
{
"Name": "ActualAdjustment",
"Value": "PT0S"
},
{
"Name": "CorrectionOffset",
"Value": "PT0S"
},
{
"Name": "Latency",
"Value": "PT0.2423996S"
}
]
}
]
}
}
If you're looking to transfer information from a JSON file to a CSV, then you can use the following code to read in a JSON file into a dictionary in Python:
import json
with open('data.txt') as json_file:
data_dict = json.load(json_file)
You could then convert this dictionary into a list with either data_dict.items() or data_dict.values().
Then you just need to write this list to a CSV file which you can easily do by just looping through the list.

Adding an adaptive card to bot framework with python

I am playing a little bit with the samples of the bot framework in python from here https://github.com/Microsoft/botbuilder-python
Now I want to add a simple adaptive card to the response which I believe it is the part where it says await context.send_activity(response) but I can not attach the card. I grabbed the card from the docs sample:
{
"$schema": "http://adaptivecards.io/schemas/adaptive-card.json",
"type": "AdaptiveCard",
"version": "1.0",
"body": [
{
"type": "Container",
"items": [
{
"type": "TextBlock",
"text": "Publish Adaptive Card schema",
"weight": "bolder",
"size": "medium"
},
{
"type": "ColumnSet",
"columns": [
{
"type": "Column",
"width": "auto",
"items": [
{
"type": "Image",
"url": "https://pbs.twimg.com/profile_images/3647943215/d7f12830b3c17a5a9e4afcc370e3a37e_400x400.jpeg",
"size": "small",
"style": "person"
}
]
},
{
"type": "Column",
"width": "stretch",
"items": [
{
"type": "TextBlock",
"text": "Matt Hidinger",
"weight": "bolder",
"wrap": true
},
{
"type": "TextBlock",
"spacing": "none",
"text": "Created {{DATE(2017-02-14T06:08:39Z, SHORT)}}",
"isSubtle": true,
"wrap": true
}
]
}
]
}
]
},
{
"type": "Container",
"items": [
{
"type": "TextBlock",
"text": "Now that we have defined the main rules and features of the format, we need to produce a schema and publish it to GitHub. The schema will be the starting point of our reference documentation.",
"wrap": true
},
{
"type": "FactSet",
"facts": [
{
"title": "Board:",
"value": "Adaptive Card"
},
{
"title": "List:",
"value": "Backlog"
},
{
"title": "Assigned to:",
"value": "Matt Hidinger"
},
{
"title": "Due date:",
"value": "Not set"
}
]
}
]
}
],
"actions": [
{
"type": "Action.ShowCard",
"title": "Set due date",
"card": {
"type": "AdaptiveCard",
"body": [
{
"type": "Input.Date",
"id": "dueDate"
}
],
"actions": [
{
"type": "Action.Submit",
"title": "OK"
}
]
}
},
{
"type": "Action.ShowCard",
"title": "Comment",
"card": {
"type": "AdaptiveCard",
"body": [
{
"type": "Input.Text",
"id": "comment",
"isMultiline": true,
"placeholder": "Enter your comment"
}
],
"actions": [
{
"type": "Action.Submit",
"title": "OK"
}
]
}
}
]}
I can not find a way to attach the card to the python response.
You need to create the Attachment for the activity that is sent to the user:
ADAPTIVE_CARD_ATTACHMENT = Attachment(content_type='application/vnd.microsoft.card.adaptive',
content=ADAPTIVE_CARD)
After this, you can attach it to your response activity like this:
response.attachments = [ADAPTIVE_CARD_ATTACHMENT]
Or you could add it when you create the response:
response = Activity(type='message', attachments=[ADAPTIVE_CARD_ATTACHMENT])
Note: I left out the additional code needed to create a valid activity for brevity, you still need to add the fields such as channel_id, recipient and from_property, etc.

Categories

Resources