How do I traverse through the JSON using a JSON path parser? - json

I have the following JSON response
'{ "person_list":
[
{
"id": "4",
"demographics": {
"address": {
"city": "Tokyo",
"country": "Japan",
"county_or_parish": "some county",
"postal_code": "98765",
"state_or_province": "some state",
"street_addresses": [
"123 Some Street"
]
},
"date_of_birth": "1964-01-30T00:00:00.000Z",
"date_of_death": "2013-01-30T00:00:00.000Z",
"deceased": true,
"emails": [],
"gender": "Male",
"full_name": "Yagami Light M",
"given_names": [
"Light",
"Maes"
],
"family_names": [
"Yagami",
"Hughes"
],
"prefix": "Dr.",
"suffix": "Jr.",
"telecoms": [],
"mrn_aliases": [],
"payer_info": [],
"person_benefit_coverages": []
},
"mara_risk_scores": [
{
"score": 10.0,
"model": "CXCONLAG0"
},
{
"score": 20.0,
"model": "CXCONLAG1"
},
{
"score": 30.0,
"model": "CXCONLAG2"
}
],
"dashboard": {},
"has_flagged_manual_data": true,
"record_ids": []
},
{
"id": "3",
"demographics": {
"emails": [],
"given_names": [],
"family_names": [],
"telecoms": [],
"mrn_aliases": [],
"payer_info": [],
"person_benefit_coverages": []
},
"mara_risk_scores": [],
"dashboard": {},
"has_flagged_manual_data": false,
"record_ids": []
}
]
}'
Now I want to get the demographics of the id's that are equal to the empi_id that I retrieved from another object..
I tried this..
JsonPath.read(jsonObject,"$.person_list[].demographics", filter(where("id").eq(cs.getEmpiId())))
It doesnt seem to work.. Could you please help me with that?


This JSONPath expression should help you get what you need:
$.person_list[?(#.id=='4')].demographics
Replace 4 with the id of the person you're interested in and it should do the trick.

Related

Cannot get jq to query json object [duplicate]

This question already has answers here:
How to use jq when the variable has reserved characters?
(3 answers)
Closed 6 months ago.
I have a JSON file that I am trying to query with jq. I am unable to retrieve the observations. I am trying to retieve each of the "observations using the following command and not able to get to the result:
cat sample3.json | jq .dataSets[0].series.0:0:0:0:0.observations.0[0]
I am able to retieve up to the series using:
cat sample3.json | jq .dataSets[0].series
But once I try to drill down further I am getting a compile error:
$ cat sample3.json | jq .dataSets[0].series.0:0:0:0:0
jq: error: syntax error, unexpected LITERAL, expecting end of file (Unix shell quoting issues?) at <top-level>, line 1:
.dataSets[0].series.0:0:0:0:0
jq: 1 compile error
I am not sure what I am doing wrong here....
The input file is:
{
"header": {
"id": "b8be2cd5-33bf-4687-9e81-eb032f6f8a71",
"test": false,
"prepared": "2022-09-01T13:30:57.013+02:00",
"sender": {
"id": "ECB"
}
},
"dataSets": [
{
"action": "Replace",
"validFrom": "2022-09-01T13:30:57.013+02:00",
"series": {
"0:0:0:0:0": {
"attributes": [
0,
null,
0,
null,
null,
null,
null,
null,
null,
null,
null,
null,
0,
null,
0,
null,
0,
0,
0,
0
],
"observations": {
"0": [
1.4529,
0,
0,
null,
null
],
"1": [
1.4472,
0,
0,
null,
null
],
"2": [
1.4591,
0,
0,
null,
null
]
}
}
}
}
],
"structure": {
"links": [
{
"title": "Exchange Rates",
"rel": "dataflow",
"href": "https://sdw-wsrest.ecb.europa.eu:443/service/dataflow/ECB/EXR/1.0"
}
],
"name": "Exchange Rates",
"dimensions": {
"series": [
{
"id": "FREQ",
"name": "Frequency",
"values": [
{
"id": "D",
"name": "Daily"
}
]
},
{
"id": "CURRENCY",
"name": "Currency",
"values": [
{
"id": "AUD",
"name": "Australian dollar"
}
]
},
{
"id": "CURRENCY_DENOM",
"name": "Currency denominator",
"values": [
{
"id": "EUR",
"name": "Euro"
}
]
},
{
"id": "EXR_TYPE",
"name": "Exchange rate type",
"values": [
{
"id": "SP00",
"name": "Spot"
}
]
},
{
"id": "EXR_SUFFIX",
"name": "Series variation - EXR context",
"values": [
{
"id": "A",
"name": "Average"
}
]
}
],
"observation": [
{
"id": "TIME_PERIOD",
"name": "Time period or range",
"role": "time",
"values": [
{
"id": "2022-08-29",
"name": "2022-08-29",
"start": "2022-08-29T00:00:00.000+02:00",
"end": "2022-08-29T23:59:59.999+02:00"
},
{
"id": "2022-08-30",
"name": "2022-08-30",
"start": "2022-08-30T00:00:00.000+02:00",
"end": "2022-08-30T23:59:59.999+02:00"
},
{
"id": "2022-08-31",
"name": "2022-08-31",
"start": "2022-08-31T00:00:00.000+02:00",
"end": "2022-08-31T23:59:59.999+02:00"
}
]
}
]
},
"attributes": {
"series": [
{
"id": "TIME_FORMAT",
"name": "Time format code",
"values": [
{
"name": "P1D"
}
]
},
{
"id": "BREAKS",
"name": "Breaks",
"values": []
},
{
"id": "COLLECTION",
"name": "Collection indicator",
"values": [
{
"id": "A",
"name": "Average of observations through period"
}
]
},
{
"id": "COMPILING_ORG",
"name": "Compiling organisation",
"values": []
},
{
"id": "DISS_ORG",
"name": "Data dissemination organisation",
"values": []
},
{
"id": "DOM_SER_IDS",
"name": "Domestic series ids",
"values": []
},
{
"id": "PUBL_ECB",
"name": "Source publication (ECB only)",
"values": []
},
{
"id": "PUBL_MU",
"name": "Source publication (Euro area only)",
"values": []
},
{
"id": "PUBL_PUBLIC",
"name": "Source publication (public)",
"values": []
},
{
"id": "UNIT_INDEX_BASE",
"name": "Unit index base",
"values": []
},
{
"id": "COMPILATION",
"name": "Compilation",
"values": []
},
{
"id": "COVERAGE",
"name": "Coverage",
"values": []
},
{
"id": "DECIMALS",
"name": "Decimals",
"values": [
{
"id": "4",
"name": "Four"
}
]
},
{
"id": "NAT_TITLE",
"name": "National language title",
"values": []
},
{
"id": "SOURCE_AGENCY",
"name": "Source agency",
"values": [
{
"id": "4F0",
"name": "European Central Bank (ECB)"
}
]
},
{
"id": "SOURCE_PUB",
"name": "Publication source",
"values": []
},
{
"id": "TITLE",
"name": "Title",
"values": [
{
"name": "Australian dollar/Euro"
}
]
},
{
"id": "TITLE_COMPL",
"name": "Title complement",
"values": [
{
"name": "ECB reference exchange rate, Australian dollar/Euro, 2:15 pm (C.E.T.)"
}
]
},
{
"id": "UNIT",
"name": "Unit",
"values": [
{
"id": "AUD",
"name": "Australian dollar"
}
]
},
{
"id": "UNIT_MULT",
"name": "Unit multiplier",
"values": [
{
"id": "0",
"name": "Units"
}
]
}
],
"observation": [
{
"id": "OBS_STATUS",
"name": "Observation status",
"values": [
{
"id": "A",
"name": "Normal value"
}
]
},
{
"id": "OBS_CONF",
"name": "Observation confidentiality",
"values": [
{
"id": "F",
"name": "Free"
}
]
},
{
"id": "OBS_PRE_BREAK",
"name": "Pre-break observation value",
"values": []
},
{
"id": "OBS_COM",
"name": "Observation comment",
"values": []
}
]
}
}
}

The .foo syntax cannot be used if the key name has anything but alphanumeric characters or the underscore, or if the first character of the key name is numeric.
Assuming you are using a recent version of jq,
you can always use the form: ."foo", which is actually an abbreviation of the basic form, .["foo"].
So assuming you're using a sufficiently recent version of jq, your query could begin with:
.dataSets[0].series."0:0:0:0:0"
If you are presenting the jq query on a command line, then you may have to escape the double-quotes appropriately, e.g. in a bash shell, by enclosing the jq query in single-quotes.

Error parsing a specific JSON file in Snowflake with File Format

I have created a Stage and File Format in Snowflake which works with all my other JSON files except this, which throws an error:
Error parsing JSON: misplaced { File 'rooms.json.gz', line 1,
character 2 Row 0, column $1
I am using the same query that I am using for other files.
SELECT $1
FROM #MySchema.MY_STAGE/rooms.json.gz
;
What is wrong with the structure of this specific JSON file?
{
"rooms": [
{
"area": 131.49,
"longDescription": "",
"dateCreated": 1589908063390,
"reservable": false,
"name": "E249",
"remoteInfo": "",
"description": "",
"id": 2,
"type": {
"hexColor": "c16058",
"contentFlag": 1,
"cost": 0.0,
"dateCreated": 1308610520717,
"color": {},
"name": "BREAK ROOM",
"occupiable": false,
"id": 120,
"parkingSpace": false,
"dateUpdated": 1591818585913,
"typeCode": ""
},
"floor": {
"area": 25312.9878,
"dateCreated": 1589907703870,
"drawingAvailable": true,
"interiorGross": 0.0,
"name": "2",
"leaseArea": 0.0,
"id": 12,
"building": {
"address": {
"country": {
"defaultSelected": true,
"subdivisionCategoryName": "state",
"alpha2Code": "US",
"isoCode": "US",
"name": "United States of America (the)",
"id": 223
},
"city": "Some City",
"street": "Some Drive",
"postalCode": "00000",
"state": {
"country": {
"defaultSelected": true,
"subdivisionCategoryName": "state",
"alpha2Code": "US",
"isoCode": "US",
"name": "United States of America (the)",
"id": 223
},
"defaultSelected": false,
"code": "XX",
"name": "Some State",
"id": 66,
"categoryName": "state"
}
},
"code": "B2",
"dateCreated": 1589907508020,
"metric": false,
"name": "Some name",
"location": {},
"revitLink": "",
"id": 45,
"dateUpdated": 1601315841453,
"costCenters": []
},
"dateUpdated": 1600441936663
},
"capacity": 0,
"dateUpdated": 1600441936960
}
]
}
Edit: Screenshot from Notepad++ with all characters enabled

Converting JSON Object to Flat Structure using Logic Apps

So I have been using this logic apps template to hit the Google Analytics API and the response is in this format
{
"reports": [
{
"columnHeader": {
"dimensions": [
"ga:date",
"ga:campaign",
"ga:country",
"ga:browser",
"ga:deviceCategory",
"ga:sourceMedium",
"ga:socialNetwork",
"ga:region"
],
"metricHeader": {
"metricHeaderEntries": [
{
"name": "ga:users",
"type": "INTEGER"
},
{
"name": "ga:sessions",
"type": "INTEGER"
},
{
"name": "ga:newUsers",
"type": "INTEGER"
},
{
"name": "ga:bounces",
"type": "INTEGER"
},
{
"name": "ga:pageviews",
"type": "INTEGER"
},
{
"name": "ga:sessionDuration",
"type": "TIME"
},
{
"name": "ga:hits",
"type": "INTEGER"
},
{
"name": "ga:goalCompletionsAll",
"type": "INTEGER"
},
{
"name": "ga:goalConversionRateAll",
"type": "PERCENT"
}
]
}
},
"data": {
"rows": [
{
"dimensions": [
"20200312",
"(not set)",
"India",
"Chrome",
"desktop",
"(direct) / (none)",
"(not set)",
"Tamil Nadu"
],
"metrics": [
{
"values": [
"4",
"4",
"4",
"0",
"111",
"5100.0",
"111",
"0",
"0.0"
]
}
]
},
{
"dimensions": [
"20200316",
"(not set)",
"India",
"Chrome",
"desktop",
"(direct) / (none)",
"(not set)",
"Tamil Nadu"
],
"metrics": [
{
"values": [
"1",
"1",
"0",
"0",
"6",
"266.0",
"6",
"0",
"0.0"
]
}
]
},
{
"dimensions": [
"20200318",
"(not set)",
"India",
"Chrome",
"desktop",
"(direct) / (none)",
"(not set)",
"Tamil Nadu"
],
"metrics": [
{
"values": [
"1",
"2",
"0",
"0",
"20",
"135.0",
"20",
"0",
"0.0"
]
}
]
}
],
"totals": [
{
"values": [
"6",
"7",
"4",
"0",
"137",
"5501.0",
"137",
"0",
"0.0"
]
}
],
"rowCount": 3,
"minimums": [
{
"values": [
"1",
"1",
"0",
"0",
"6",
"135.0",
"6",
"0",
"0.0"
]
}
],
"maximums": [
{
"values": [
"4",
"4",
"4",
"0",
"111",
"5100.0",
"111",
"0",
"0.0"
]
}
],
"isDataGolden": true
}
}
]
}
I Want to convert it and bring it in a form that the column header:dimensions and metric header entries name will become column names and their values,ie data.rows.dimensions and metrics.values become corresponding values
ga:date ga:campaign ga:country ga:browser ga:deviceCategory ga:sourceMedium ga:socialNetwork ga:region ga:users ga:sessions ga:newUsers : (column names)
20200316 (not set) India Chrome desktop (direct) / (none) (not set) Tamil Nadu 1 1 1 :(values)

If you can use an Integration account, I suggest to create a flat file schema with the desired structure, and in the logic app you can convert in xml and then apply the Flat File Encoding.
Otherwise a function app should resolve your issue

Jsonpath syntax to extract specific parent keys with specific child keys

Is it possible to filter json by jsonpath query to get specific keys of parents AND specific keys of childs?
Here is the json:
{
"data": {
"paymentProviders": [
{
"currency": "USD",
"supported": true,
"providers": [
{
"fields": [],
"key": "paypal",
"maintenance": false,
"settings": [
{
"max": 10000,
"min": 100
}
],
"withdrawalFields": []
},
{
"fields": [],
"key": "moneta",
"maintenance": false,
"settings": [
{
"key": "deposits",
"max": 10000,
"min": 100
}
],
"withdrawalFields": []
}
]
},
{
"currency": "GBP",
"supported": true,
"providers": [
{
"fields": [],
"key": "directTransfer",
"maintenance": false,
"settings": [
{
"key": "deposits",
"max": 0,
"min": 100
}
],
"withdrawalFields": []
}
]
},
{
"currency": "EUR",
"supported": true,
"providers": [
{
"fields": [],
"key": "paypal",
"maintenance": false,
"settings": [
{
"key": "deposits",
"max": 10000,
"min": 100
}
],
"withdrawalFields": []
}
]
}
]
}
}
I want to get only 'currency', 'providers.key' and 'providers.maintenance' from it, like this:
{
"data": {
"paymentProviders": [
{
"currency": "USD",
"providers": [
{
"key": "paypal",
"maintenance": false,
},
{
"key": "moneta",
"maintenance": false,
}
]
},
{
"currency": "GBP",
"providers": [
{
"key": "directTransfer",
"maintenance": false,
}
]
},
{
"currency": "EUR",
"providers": [
{
"key": "paypal",
"maintenance": false,
}
]
}
]
}
}
If I use something like
$..['key', 'maintenance']
I'll lose that 'currency' property.
Basically, I want to use 'Union operator' pattern inside another 'Union operator' pattern, idea is this:
$..["currency","providers.['key', 'maintenance']"]

Try
$..['currency','key','maintenance']
You should get
[
"USD",
"paypal",
false,
"moneta",
false,
"deposits",
"GBP",
"directTransfer",
false,
"deposits",
"EUR",
"paypal",
false,
"deposits"
]
Compare with Goessner
Note that the jsonpath union operator will only give you a list of values, without the contextual elements that you have in your desired results.

Convert json to include name and children values to feed D3

I am trying to get json converted from:
{
"Devices": [
{
"Udid": "7a2b0e6c928f2321a75e423ba23ae93d",
"SerialNumber": "RF1D232ZLEE",
"MacAddress": "40F232726FC8",
"Imei": "3576342323280150",
"EasId": "SEC1BC252327E92B",
"AssetNumber": "7a2b0e23223928f2321a75e423ba23ae93d",
"DeviceFriendlyName": "gel1 Android Android 5.0.1 ZLEE ",
"LocationGroupId": {
"Id": {
"Value": 19529
},
"Name": "Group Express"
},
"LocationGroupName": "Group Express",
"UserId": {
"Name": ""
},
"UserName": "",
"UserEmailAddress": "",
"Ownership": "S",
"PlatformId": {
"Id": {
"Value": 5
},
"Name": "Android"
},
"Platform": "Android",
"ModelId": {
"Id": {
"Value": 5
},
"Name": "samsung GT-I9505"
},
"Model": "samsung GT-I9505",
"OperatingSystem": "5.0.1",
"PhoneNumber": "+447881867010",
"LastSeen": "2016-07-06T14:01:03.590",
"EnrollmentStatus": "Unenrolled",
"ComplianceStatus": "NotAvailable",
"CompromisedStatus": false,
"LastEnrolledOn": "2016-06-15T16:01:38.763",
"LastComplianceCheckOn": "0001-01-01T00:00:00.000",
"LastCompromisedCheckOn": "2016-07-06T13:58:26.183",
"IsSupervised": false,
"DeviceMCC": {
"SIMMCC": "234",
"CurrentMCC": "234"
},
"AcLineStatus": 0,
"VirtualMemory": 0,
"Id": {
"Value": 23459
}
},
{
"Udid": "c5f94db71d406dae7f881d3edf059e",
"SerialNumber": "",
"MacAddress": "000C300F9108",
"Imei": "",
"EasId": "D80DB85EC411C8E9B28BC292A603F05C2C0EEEC8",
"AssetNumber": "c592f93db71d406dae7f881d3edf059e",
"DeviceFriendlyName": "user Windows 10 WinRT 10.0.10240 ",
"LocationGroupId": {
"Id": {
"Value": 18498
},
"Name": "Business Solutions"
},
"LocationGroupName": "Business Solutions",
"UserId": {
"Name": ""
},
"UserName": "",
"UserEmailAddress": "",
"Ownership": "C",
"PlatformId": {
"Id": {
"Value": 12
},
"Name": "WinRT"
},
"Platform": "WinRT",
"ModelId": {
"Id": {
"Value": 50
},
"Name": "Windows 10"
},
"Model": "Windows 10",
"OperatingSystem": "10.0.10240",
"PhoneNumber": "",
"LastSeen": "2016-05-03T10:54:07.650",
"EnrollmentStatus": "Unenrolled",
"ComplianceStatus": "NotAvailable",
"CompromisedStatus": false,
"LastEnrolledOn": "2016-01-29T16:41:57.760",
"LastComplianceCheckOn": "0001-01-01T00:00:00.000",
"LastCompromisedCheckOn": "0001-01-01T00:00:00.000",
"IsSupervised": false,
"DeviceMCC": {
"SIMMCC": "",
"CurrentMCC": ""
},
"AcLineStatus": 0,
"VirtualMemory": 0,
"Id": {
"Value": 23545
}
}
],
"Page": 0,
"PageSize": 500,
"Total": 13}
To something like:
{"name": "Devices",
"children": [
{"name":"Udid", "size":"7f0dsda63274692ea4f0b66fec67a020158"},
{"name":"SerialNumber", "size":"P988KJSPQF938"},
{"name":"MacAddress", "size":"1HJUSUD031C4"},
{"name":"Imei", "size":""},
{"name":"EasId", "size":"ApKJSPQF193"},
{"name":"AssetNumber", "size":"7f0cda636b3305fea4f0b66fec9997267a020158"},
{"name":"DeviceFriendlyName", "size":"TMcKenz iPad iOS 7.1.4 F193 "},
{"name":"LocationGroupId",
"children": [
{"name":"Id","size":7488},
{"name":"Name","size":"MCM"}
]
},
{"name":"UserId",
"children": [
{"name":"Id","size":6418},
{"name":"Name","size":"Tom McKenz"}
]
},
{"name":"UserName", "size":"TMcKenz"},
{"name":"UserEmailAddress", "size":"TMcKenz#awaw.com"}
]
}
Not sure what is the best practice here: is it possible to use D3.nest or do you need to iterate through all the nodes and change to 'name' and 'children' accordingly.