Related
I have the following data frame, df1:
A B C
123 B1 C1
456 B2 C2
And data frame df2:
A
[
{
"id": "123",
"details": {
"id": "123",
"color": null,
"param_1": {
"name": "mike"
},
"location": "US",
"items": [
{
"item_1": "#227858",
"offer_id": null,
"item_details": {
"detials_1": [{ "notes": "other:", "quantity": 1 }]
}
}
],
"version": 1,
}
}
]
[
{
"id": "456",
"details": {
"id": "456",
"color": null,
"param_1": {
"name": "james"
},
"location": "KR",
"items": [
{
"item_1": "#2221",
"offer_id": null,
"item_details": {
"detials_1": [{ "notes": "other", "quantity": 1 }]
}
}
],
"version": 2,
}
}
]
I want to find all values in df1[A] inside the JSON found inside df2[A] under the first instance of the id parameter. Once found, I want to replace the NULL values inside the color parameter with the df1[B] and offer_id with df1[C].
The output should create a new column with the appended values:
df2[B]:
[
{
"id": "123",
"details": {
"id": "123",
"color": B1,
"param_1": {
"name": "mike"
},
"location": "US",
"items": [
{
"item_1": "#227858",
"offer_id": C1,
"item_details": {
"detials_1": [{ "notes": "other:", "quantity": 1 }]
}
}
],
"version": 1,
}
}
]
[
{
"id": "456",
"details": {
"id": "456",
"color": B2,
"param_1": {
"name": "james"
},
"location": "KR",
"items": [
{
"item_1": "#2221",
"offer_id": C2,
"item_details": {
"detials_1": [{ "notes": "other", "quantity": 1 }]
}
}
],
"version": 2,
}
}
]
I just started researching how to approach this, but I need guidance on the most efficient way. Any insight would be greatly appreciated.
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.
This is my first time to use JoltTransformationJson, so I have limited knowledge and experience on that. Please help me with this complicated project.
Request:
when the payment.code <> "paid", I have to do the following two things for the file.
to change the payment.code ="denied" and payment.text ="denied"
to add a JSON object to item.ADJ
When the payment.code =="paid", don't need to change anything.
Input :
{
"resourceType": "E",
"id": "11",
"identifier": [
{
"type": {
"coding": [
{
"system": "sys1",
"code": "aaa"
}
]
},
"value": "212"
},
{
"type": {
"coding": [
{
"system": "sys2",
"code": "RRR"
}
]
},
"value": "367"
}
],
"status": "active",
"created": "2021-08-05T02:43:48+00:00",
"outcome": "complete",
"item": [
{
"sequence": 1,
"product": {
"coding": [
{
"system": "example",
"code": "abc",
"display": "ABC"
}
],
"text": "ABC"
},
"servicedDate": "2021-08-04",
"quantity": {
"value": 60
},
"ADJ": [
{
"category": {
"coding": [
{
"system": "code1",
"code": "code1",
"display": "CODE1"
}
],
"text": "CODE1"
},
"amount": {
"value": 46.45,
"currency": "USD"
}
},
{
"category": {
"coding": [
{
"system": "code2",
"code": "code2",
"display": "CODE2"
}
],
"text": "CODE2"
},
"amount": {
"value": 12.04,
"currency": "USD"
}
}
]
}
],
"payment": {
"type": {
"coding": [
{
"system": "http://payment.com",
"code": "reversed/cancelled"
}
],
"text": "cancelled"
}
}
}
My Expected Output :
{
"resourceType": "E",
"id": "11",
"identifier": [
{
"type": {
"coding": [
{
"system": "sys1",
"code": "aaa"
}
]
},
"value": "212"
},
{
"type": {
"coding": [
{
"system": "sys2",
"code": "RRR"
}
]
},
"value": "367"
}
],
"status": "active",
"created": "2021-08-05T02:43:48+00:00",
"outcome": "complete",
"item": [
{
"sequence": 1,
"product": {
"coding": [
{
"system": "example",
"code": "abc",
"display": "ABC"
}
],
"text": "ABC"
},
"servicedDate": "2021-08-04",
"quantity": {
"value": 60
},
"ADJ": [
{
"category": {
"coding": [
{
"system": "code1",
"code": "code1",
"display": "CODE1"
}
],
"text": "CODE1"
},
"amount": {
"value": 46.45,
"currency": "USD"
}
},
{
"category": {
"coding": [
{
"system": "code2",
"code": "code2",
"display": "CODE2"
}
],
"text": "CODE2"
},
"amount": {
"value": 12.04,
"currency": "USD"
}
},
{// new object I want to insert into
"category": {
"coding": [
{
"system": "sys_denail",
"code": "denialreason"
}
],
"reason": {
"coding": [
{
"system": "https://example.com",
"code": "A1"
}
],
"text": "unknown"
}}
}
]
}
],
"payment": {
"type": {
"coding": [
{
"system": "http://payment.com",
"code": "denied" //change the value to denied
}
],
"text": "denied" //change the value to denied
}
}
}
Edit : I've tried to answer the second case by myself to be evaluated after the first case is answered
Welcome to SO, please ask minimal and reproducible questions, and show your effort tried for the future.
What you need is to use a conditional logic along with placeholder values with ampersand symbols depending on the levels of each key name within the tree.
I have partially answered, which will handle the bottom part of your question. Indeed the logic for the rest(inserting an object to the array will be similiar)
So, consider having a look at the following solution
[
{
"operation": "shift",
"spec": {
"*": "&",
"payment": {
"type": {
"coding": {
"*": {
"*": "&4.&3.&2[&1].&",
"code": {
"paid": {
"#1": "&6.&5.&4[&3].&2",
"#(4,text)": "&6.text"
},
"*": {
"#denied": "&6.&5.&4[&3].code",
"#(4,text)": {
"#denied": "&6.text"
}
}
}
}
}
}
}
}
}
]
Edit(for your own answer related to adding an object):
your current idea of using shift after default transformation spec is pretty good, you can rephrase like
[
{
"operation": "default",
"spec": {
"temp_deny": {
"denialreason": {
"category": {
"coding": [
{
"system": "sys_denail",
"code": "denialreason"
}
],
"reason": {
"coding": [
{
"system": "https://example.com",
"code": "A1"
}
],
"text": "unknown"
}
}
}
}
}
},
{
"operation": "shift",
"spec": {
"*": "&",
"item": {
"*": {
"*": "&2[&1].&",
"ADJ": {
"#": "&3[&2].&",
"#(4,temp_deny)": "&3[&2].&"
}
}
}
}
}
]
I have an elastic search index
like
{
"title": "A",
"comments": [
{
"id": "1"
},
{
"id": "2"
}
]
},
{
"title": "B",
"comments": [
{
"id": "1"
},
{
"id": "3"
}
]
},
{
"title": "C",
"comments": [
{
"id": "7"
},
{
"id": "3"
}
]
}
I want to collapse is the group by the nested object. In the above JSON, I want to group it by Id.
So the output will be like
hits:[{
"title": "A",
"comments": [
{
"id": "1"
},
{
"id": "2"
}
]
},
inner_hits {[
{
"title": "A",
"comments": [
{
"id": "1"
},
{
"id": "2"
}
]
},
{
"title": "B",
"comments": [
{
"id": "1"
},
{
"id": "3"
}
]
}
]}
}]
Baiscally I need collapse bases on the nested object property.
Tried this
/_search?track_total_hits=true
{
"collapse": {
"field": "comments.id",
"inner_hits": {
"name": "id",
"size": 10
},
"max_concurrent_group_searches": 3
}
}
But its always returing first object only in the inner hits
Within the mapping of the object comments , you should remove the nested type.
just checking before i build the wheel
I need a hackjob to present an api endpoint in a database. It doesn't need to do anything fancy, just convert what the rest api spits out into a single column of json. A new row at each iteration at the root/top level would be nice but a single varchar or whatever would be ok too
Does an ODBC wrapper exist out there anywhere? Googling just brings up hits for doing the opposite (exposing databases as an api). I'm not interested in the simba etc paid stuff. The consumer is SQL server so i can just use xp_cmdshell with curl as a last resort
so for instance the output of this : http://jsonapiplayground.reyesoft.com/v2/authors could come out as a table like so (a row for each author)
|data |
---------------------------------------------------
|{
"type": "authors",
"id": "1",
"attributes": {
"name": "Madge Mohr DVM 2",
"date_of_birth": "1977-08-21",
"date_of_death": "2009-09-14"
},
"relationships": {
"photos": {
"data": []
},
"books": {
"data": [
{
"type": "books",
"id": "41"
}
]
}
},
"links": {
"self": "/v2/authors/1"
}
} |
---------------------------------------------------
|{
"type": "authors",
"id": "3",
"attributes": {
"name": "Zelma Ortiz DDS",
"date_of_birth": "1992-09-06",
"date_of_death": "2000-12-19"
},
"relationships": {
"photos": {
"data": [
{
"type": "photos",
"id": "3"
}
]
},
"books": {
"data": [
{
"type": "books",
"id": "36"
},
{
"type": "books",
"id": "48"
}
]
}
},
"links": {
"self": "/v2/authors/3"
}
}|
----------
|{
"type": "authors",
"id": "4",
"attributes": {
"name": "Fermin Barrows Sr.",
"date_of_birth": "1991-03-18",
"date_of_death": "1975-11-07"
},
"relationships": {
"photos": {
"data": [
{
"type": "photos",
"id": "4"
}
]
},
"books": {
"data": [
{
"type": "books",
"id": "1"
},
{
"type": "books",
"id": "26"
},
{
"type": "books",
"id": "44"
},
{
"type": "books",
"id": "46"
}
]
}
},
"links": {
"self": "/v2/authors/4"
}
}|
----------
|{
"type": "authors",
"id": "5",
"attributes": {
"name": "Terry Durgan",
"date_of_birth": "2011-03-06",
"date_of_death": "2017-04-13"
},
"relationships": {
"photos": {
"data": [
{
"type": "photos",
"id": "5"
}
]
},
"books": {
"data": [
{
"type": "books",
"id": "6"
},
{
"type": "books",
"id": "16"
},
{
"type": "books",
"id": "50"
}
]
}
},
"links": {
"self": "/v2/authors/5"
}
}|
----------
|{
"type": "authors",
"id": "6",
"attributes": {
"name": "Annalise Walsh",
"date_of_birth": "2004-11-27",
"date_of_death": "1997-07-20"
},
"relationships": {
"photos": {
"data": [
{
"type": "photos",
"id": "6"
}
]
},
"books": {
"data": [
{
"type": "books",
"id": "4"
},
{
"type": "books",
"id": "5"
},
{
"type": "books",
"id": "21"
}
]
}
},
"links": {
"self": "/v2/authors/6"
}
}|
---------