使用jq将JSON行转换为JSON数组

von4xj4u  于 2023-05-19  发布在  其他
关注(0)|答案(4)|浏览(253)

首先，我是新的jq，像1天新，我也是新的JSON，我是一个SQL的家伙，所以我学得很快，但不能让我的头周围…所以请耐心点
我运行Windows，在PowerShell上使用jq v1.5。
我下载了多个JSON文件，它们看起来像这样：

{"Header":{"AssetClass":"Commodities","InstrumentType":"Forward","UseCase":"Forward","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"EUR","ExpiryDate":"2018-01-01","ReturnorPayoutTrigger":"Contract for Difference (CFD)","DeliveryType":"CASH","BaseProduct":"AGRI","TransactionType":"FUTR","FinalPriceType":"ARGM","ReferenceRate":"10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN","SubProduct":"GROS","AdditionalSubProduct":"FWHT"},"ISIN":{"ISIN":"EZX27M86B860","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Agriculture","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Forward AGRI GROS FWHT EUR 20180101","ShortName":"NA/Fwd AGRI FWHT EUR 20180101","ClassificationType":"JTAXCC"}}
{"Header":{"AssetClass":"Commodities","InstrumentType":"Swap","UseCase":"Basis_Swap","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"SOS","ExpiryDate":"2208-12-10","ReturnorPayoutTrigger":"Total Return","DeliveryType":"OPTL","TransactionType":"ORIT","FinalPriceType":"IHSM","ReferenceRate":"NATURAL GAS-MONTHLY INDEX S. TEXAS (TETCO)-GAS DAILY PRICE GUIDE","OtherReferenceRate":"NATURAL GAS-MONTHLY INDEX W. LOUISIANA (TETCO)-GAS DAILY PRICE GUIDE","BaseProduct":"OTHR","OtherBaseProduct":"OTHR","SubProduct":"","AdditionalSubProduct":"","OtherSubProduct":"","OtherAdditionalSubProduct":""},"ISIN":{"ISIN":"EZBBH1XR9GV6","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Multi Commodity","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Swap Basis_Swap OTHR   OTHR   SOS 22081210","ShortName":"NA/Swap OTHR   SOS 22081210","ClassificationType":"STQTXE"}}
{"Header":{"AssetClass":"Commodities","InstrumentType":"Swap","UseCase":"Multi_Exotic_Swap","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"LRD","ExpiryDate":"2200-01-31","ReturnorPayoutTrigger":"Contract for Difference (CFD)","DeliveryType":"CASH","TransactionType":"TAPO","FinalPriceType":"EXOF","UnderlyingInstrumentIndex":["BCOMF6","BCOMNG3"]},"ISIN":{"ISIN":"EZ286HJVY4Q2","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"UnderlyingAssetType":"Multi Commodity","BaseProduct":"MCEX","SubProduct":"","AdditionalSubProduct":"","FullName":"Commodities Multi_Exotic_Swap MCEX LRD 22000131","ShortName":"NA/Swap MCEX LRD 22000131","ClassificationType":"STQCXC"}}
{"Header":{"AssetClass":"Commodities","InstrumentType":"Option","UseCase":"Option","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"TND","ExpiryDate":"2209-10-18","OptionType":"OPTL","OptionExerciseStyle":"AMER","ValuationMethodorTrigger":"Asian","DeliveryType":"CASH","TransactionType":"OTHR","FinalPriceType":"IHSM","ReferenceRate":"NATURAL GAS-NGPL (NICOR, NIPSCO, PGLC CITYGATE), NBPL-NICOR-ICE/10X MONTHLY","BaseProduct":"OTHR","SubProduct":"","AdditionalSubProduct":""},"ISIN":{"ISIN":"EZ2TK5CWL9Y4","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Other","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Option OTHR   TND 22091018","ShortName":"NA/O OTHR  OPTL TND 22091018","ClassificationType":"HTMHAC"}}
{"Header":{"AssetClass":"Commodities","InstrumentType":"Option","UseCase":"Multi_Exotic_Option","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"SOS","ExpiryDate":"2209-10-18","UnderlyingInstrumentIndex":["BCOMSI2","BCOMPR3T"],"OptionType":"CALL","OptionExerciseStyle":"AMER","ValuationMethodorTrigger":"Other Path Dependent","DeliveryType":"CASH","TransactionType":"ORIT","FinalPriceType":"BLTC"},"ISIN":{"ISIN":"EZ82L36B6225","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"UnderlyingAssetType":"Multi Commodity","BaseProduct":"MCEX","SubProduct":"","AdditionalSubProduct":"","FullName":"Commodities Multi_Exotic_Option MCEX SOS 22091018","ShortName":"NA/O MCEX Call SOS 22091018","ClassificationType":"HTQBPC"}}

文件的大小可以超过1 GB。
为了有效地使用这些，我需要将JSON行转换为JSON数组， Package 文件，前置“[”并追加“]”，并为每行使用逗号（，）分隔。
使文件看起来像这样（理论上）：

[
{
"Header": {
  "AssetClass": "Commodities",
  "InstrumentType": "Swap",
  "UseCase": "Basis_Swap",
  "Level": "InstRefDataReporting"
},
"Attributes": {
  "NotionalCurrency": "EUR",
  "ExpiryDate": "2017-08-31",
  "ReturnorPayoutTrigger": "Contract for Difference (CFD)",
  "DeliveryType": "CASH",
  "BaseProduct": "AGRI",
  "OtherBaseProduct": "AGRI",
  "TransactionType": "FUTR",
  "FinalPriceType": "ARGM",
  "ReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "OtherReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "SubProduct": "GROS",
  "AdditionalSubProduct": "FWHT",
  "OtherSubProduct": "GROS",
  "OtherAdditionalSubProduct": "FWHT"
},
"ISIN": {
  "ISIN": "EZ68CZDRFYY7",
  "Status": "New"
},
"TemplateVersion": 1,
"Derived": {
  "CommodityDerivativeIndicator": "TRUE",
  "UnderlyingAssetType": "Multi Commodity",
  "IssuerorOperatoroftheTradingVenueIdentifier": "NA",
  "PriceMultiplier": 1,
  "FullName": "Commodities Swap Basis_Swap AGRI GROS FWHT AGRI GROS FWHT EUR 20170831",
  "ShortName": "NA/Swap AGRI FWHT FWHT EUR 20170831",
  "ClassificationType": "STQCXC"
  }
},
{
"Header": {
  "AssetClass": "Commodities",
  "InstrumentType": "Swap",
  "UseCase": "Basis_Swap",
  "Level": "InstRefDataReporting"
},
"Attributes": {
  "NotionalCurrency": "EUR",
  "ExpiryDate": "2017-08-31",
  "ReturnorPayoutTrigger": "Contract for Difference (CFD)",
  "DeliveryType": "CASH",
  "BaseProduct": "AGRI",
  "OtherBaseProduct": "AGRI",
  "TransactionType": "FUTR",
  "FinalPriceType": "ARGM",
  "ReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "OtherReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "SubProduct": "GROS",
  "AdditionalSubProduct": "FWHT",
  "OtherSubProduct": "GROS",
  "OtherAdditionalSubProduct": "FWHT"
},
"ISIN": {
  "ISIN": "EZ68CZDRFYY7",
  "Status": "New"
},
"TemplateVersion": 1,
"Derived": {
  "CommodityDerivativeIndicator": "TRUE",
  "UnderlyingAssetType": "Multi Commodity",
  "IssuerorOperatoroftheTradingVenueIdentifier": "NA",
  "PriceMultiplier": 1,
  "FullName": "Commodities Swap Basis_Swap AGRI GROS FWHT AGRI GROS FWHT EUR 20170831",
  "ShortName": "NA/Swap AGRI FWHT FWHT EUR 20170831",
  "ClassificationType": "STQCXC"
}
}
]

所以我找到了jq，根据我的理解，我可以运行这个

jq --slurp 'map(select(. >= 2))' Inputfile.json > OutputFile.json

这是可行的，但当运行大于200 MB的文件时，我会出现“系统内存不足”错误（如果我使用伊势），如果我使用标准的Powershell或CMD，则需要很长时间。分钟（5+）
如果我把--slurp从命令中去掉，它会工作，它会更快，但结果看起来像这样：

[
{
"Header": {
  "AssetClass": "Commodities",
  "InstrumentType": "Swap",
  "UseCase": "Basis_Swap",
  "Level": "InstRefDataReporting"
},
"Attributes": {
  "NotionalCurrency": "EUR",
  "ExpiryDate": "2017-08-31",
  "ReturnorPayoutTrigger": "Contract for Difference (CFD)",
  "DeliveryType": "CASH",
  "BaseProduct": "AGRI",
  "OtherBaseProduct": "AGRI",
  "TransactionType": "FUTR",
  "FinalPriceType": "ARGM",
  "ReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "OtherReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "SubProduct": "GROS",
  "AdditionalSubProduct": "FWHT",
  "OtherSubProduct": "GROS",
  "OtherAdditionalSubProduct": "FWHT"
},
"ISIN": {
  "ISIN": "EZ68CZDRFYY7",
  "Status": "New"
},
"TemplateVersion": 1,
"Derived": {
  "CommodityDerivativeIndicator": "TRUE",
  "UnderlyingAssetType": "Multi Commodity",
  "IssuerorOperatoroftheTradingVenueIdentifier": "NA",
  "PriceMultiplier": 1,
  "FullName": "Commodities Swap Basis_Swap AGRI GROS FWHT AGRI GROS FWHT EUR 20170831",
  "ShortName": "NA/Swap AGRI FWHT FWHT EUR 20170831",
  "ClassificationType": "STQCXC"
  }
}]
[{
"Header": {
  "AssetClass": "Commodities",
  "InstrumentType": "Swap",
  "UseCase": "Basis_Swap",
  "Level": "InstRefDataReporting"
},
"Attributes": {
  "NotionalCurrency": "EUR",
  "ExpiryDate": "2017-08-31",
  "ReturnorPayoutTrigger": "Contract for Difference (CFD)",
  "DeliveryType": "CASH",
  "BaseProduct": "AGRI",
  "OtherBaseProduct": "AGRI",
  "TransactionType": "FUTR",
  "FinalPriceType": "ARGM",
  "ReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "OtherReferenceRate": "10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN",
  "SubProduct": "GROS",
  "AdditionalSubProduct": "FWHT",
  "OtherSubProduct": "GROS",
  "OtherAdditionalSubProduct": "FWHT"
},
"ISIN": {
  "ISIN": "EZ68CZDRFYY7",
  "Status": "New"
},
"TemplateVersion": 1,
"Derived": {
  "CommodityDerivativeIndicator": "TRUE",
  "UnderlyingAssetType": "Multi Commodity",
  "IssuerorOperatoroftheTradingVenueIdentifier": "NA",
  "PriceMultiplier": 1,
  "FullName": "Commodities Swap Basis_Swap AGRI GROS FWHT AGRI GROS FWHT EUR 20170831",
  "ShortName": "NA/Swap AGRI FWHT FWHT EUR 20170831",
  "ClassificationType": "STQCXC"
}
}
]

它为每一行创建一个数组，但数组不是逗号分隔的，这不是我想要的。
那么，如何处理包含多个JSON行的大文件，并为作为逗号分隔的单个数组生成的输入文件创建一个文件，而不使用slurp呢？
我读过有关输入的内容，但不确定这是否与我需要做的事情相关？

JSON

4条答案

按热度按时间
e1xvtsh3

e1xvtsh31#

也许我迟到了，但这就是你要找的！

jq -s '.' in.json > out.json
赞(0）分享  回复(0）举报  2023-05-19
r8uurelv

r8uurelv2#

看起来inputs和slurp有同样的问题。我不知道如何在大文件上使用jq来实现这一点，但sed可以做到：

sed '1s/^/[/; $!s/$/,/; $s/$/]/' in.json > out.json

输出：

[{"Header":{"AssetClass":"Commodities","InstrumentType":"Forward","UseCase":"Forward","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"EUR","ExpiryDate":"2018-01-01","ReturnorPayoutTrigger":"Contract for Difference (CFD)","DeliveryType":"CASH","BaseProduct":"AGRI","TransactionType":"FUTR","FinalPriceType":"ARGM","ReferenceRate":"10PPM ULTRA LOW SULPHUR DIESEL-CARGOES CIF NWE/BASIS ARA-PLATTS EUROPEAN","SubProduct":"GROS","AdditionalSubProduct":"FWHT"},"ISIN":{"ISIN":"EZX27M86B860","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Agriculture","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Forward AGRI GROS FWHT EUR 20180101","ShortName":"NA/Fwd AGRI FWHT EUR 20180101","ClassificationType":"JTAXCC"}},
{"Header":{"AssetClass":"Commodities","InstrumentType":"Swap","UseCase":"Basis_Swap","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"SOS","ExpiryDate":"2208-12-10","ReturnorPayoutTrigger":"Total Return","DeliveryType":"OPTL","TransactionType":"ORIT","FinalPriceType":"IHSM","ReferenceRate":"NATURAL GAS-MONTHLY INDEX S. TEXAS (TETCO)-GAS DAILY PRICE GUIDE","OtherReferenceRate":"NATURAL GAS-MONTHLY INDEX W. LOUISIANA (TETCO)-GAS DAILY PRICE GUIDE","BaseProduct":"OTHR","OtherBaseProduct":"OTHR","SubProduct":"","AdditionalSubProduct":"","OtherSubProduct":"","OtherAdditionalSubProduct":""},"ISIN":{"ISIN":"EZBBH1XR9GV6","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Multi Commodity","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Swap Basis_Swap OTHR   OTHR   SOS 22081210","ShortName":"NA/Swap OTHR   SOS 22081210","ClassificationType":"STQTXE"}},
{"Header":{"AssetClass":"Commodities","InstrumentType":"Swap","UseCase":"Multi_Exotic_Swap","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"LRD","ExpiryDate":"2200-01-31","ReturnorPayoutTrigger":"Contract for Difference (CFD)","DeliveryType":"CASH","TransactionType":"TAPO","FinalPriceType":"EXOF","UnderlyingInstrumentIndex":["BCOMF6","BCOMNG3"]},"ISIN":{"ISIN":"EZ286HJVY4Q2","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"UnderlyingAssetType":"Multi Commodity","BaseProduct":"MCEX","SubProduct":"","AdditionalSubProduct":"","FullName":"Commodities Multi_Exotic_Swap MCEX LRD 22000131","ShortName":"NA/Swap MCEX LRD 22000131","ClassificationType":"STQCXC"}},
{"Header":{"AssetClass":"Commodities","InstrumentType":"Option","UseCase":"Option","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"TND","ExpiryDate":"2209-10-18","OptionType":"OPTL","OptionExerciseStyle":"AMER","ValuationMethodorTrigger":"Asian","DeliveryType":"CASH","TransactionType":"OTHR","FinalPriceType":"IHSM","ReferenceRate":"NATURAL GAS-NGPL (NICOR, NIPSCO, PGLC CITYGATE), NBPL-NICOR-ICE/10X MONTHLY","BaseProduct":"OTHR","SubProduct":"","AdditionalSubProduct":""},"ISIN":{"ISIN":"EZ2TK5CWL9Y4","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","UnderlyingAssetType":"Other","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"FullName":"Commodities Option OTHR   TND 22091018","ShortName":"NA/O OTHR  OPTL TND 22091018","ClassificationType":"HTMHAC"}},
{"Header":{"AssetClass":"Commodities","InstrumentType":"Option","UseCase":"Multi_Exotic_Option","Level":"InstRefDataReporting"},"Attributes":{"NotionalCurrency":"SOS","ExpiryDate":"2209-10-18","UnderlyingInstrumentIndex":["BCOMSI2","BCOMPR3T"],"OptionType":"CALL","OptionExerciseStyle":"AMER","ValuationMethodorTrigger":"Other Path Dependent","DeliveryType":"CASH","TransactionType":"ORIT","FinalPriceType":"BLTC"},"ISIN":{"ISIN":"EZ82L36B6225","Status":"New"},"TemplateVersion":1,"Derived":{"CommodityDerivativeIndicator":"TRUE","IssuerorOperatoroftheTradingVenueIdentifier":"NA","PriceMultiplier":1,"UnderlyingAssetType":"Multi Commodity","BaseProduct":"MCEX","SubProduct":"","AdditionalSubProduct":"","FullName":"Commodities Multi_Exotic_Option MCEX SOS 22091018","ShortName":"NA/O MCEX Call SOS 22091018","ClassificationType":"HTQBPC"}}]

说明

sed脚本由三个独立的替换组成。下面是它们在不同的行上：

赞(0）分享  回复(0）举报  2023-05-19
tpgth1q7

tpgth1q73#

也许awk对眼睛更容易：

awk '
  BEGIN{print "["} 
  length(last)>0 {print last ","} {last=$0}
  END {print last, "]"}
'

为了记录在案，这里有一个使用input的jq版本的无slurp解决方案：

jq -nr '"[", try (input|tojson, repeat(",\n\(input|tojson)")), "]"'
赞(0）分享  回复(0）举报  2023-05-19
s4chpxco

s4chpxco4#

我使用了一行node调用：

$ cat input.ndjson | node -e 'const rl = readline.createInterface({ input: process.stdin }); !async function () { let idx = 0; for await (const line of rl) { process.stdout.write((++idx === 1 ? "[" : "\n,") + JSON.stringify(JSON.parse(line))); } process.stdout.write("]"); }()' | tee output.json | jq 'length'
16814

说明：

$ cat input.ndjson |      # pipe the ndjson input, can be a file or any stream
  node -e '
    const rl = readline.createInterface({ input: process.stdin });
    !async function () {  // to be able to use await, this function has to be async, and then `!` is to be able call it right away;
      let idx = 0;
      for await (const line of rl) {
        process.stdout.write((++idx === 1 ? "[" : "\n,") + JSON.stringify(JSON.parse(line)));
      }
      process.stdout.write("]");
    }()
  ' | tee output.json     # save the output json file
    | jq 'length'         # call jq to calculate a length, also validate it, to make sure it's a valid single json file, this optional

Node的readline是一个很好的逐行读取流的方法，它是asyncIterable，可以使用（await... of）获取每一行，然后调用JSON.parse以确保验证每一行是有效的json，然后调用JSON.stringify将每一行转换回缩小的JSON;
当然，你可以改为本地的const arr = [];，并将每行的obj推送到t中，然后在最后使用JSON.stringify，以获得最小化的JSON，
但我喜欢这种几乎缩小的格式，即每一行的obj都缩小了，但仍逐行保留外部数组，以便我可以轻松地通过wc -l计数其行数来获得其总数

[{...minified line1obj with no spaces...}
,{...minified line2obj}
,{...minified line3obj}
,...
,{...minified lineNobj}]
赞(0）分享  回复(0）举报  2023-05-19
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com