Delete NestedJsonParsing.usql
This commit is contained in:
rukmanig
Родитель
9faa688f8b
Коммит
bf7738949b
|
|
@ -1,156 +0,0 @@
|
|||
/*
|
||||
This example illustrates processing a Json file containing nested nodes using the Json extractors and UDFs from Microsoft.Analytics.Samples.Formats.Json libraries.
|
||||
Download the Json extractors and UDFs from https://github.com/Azure/usql/tree/master/Examples/DataFormats
|
||||
|
||||
JSON file used in this example
|
||||
{
|
||||
"_comment": "Source - http://adobe.github.io/Spry/samples/data_region/JSONDataSetSample.html",
|
||||
"id": "0001",
|
||||
"type": "donut",
|
||||
"name": "Cake",
|
||||
"ppu": 0.55,
|
||||
"batters":
|
||||
{
|
||||
"batter":
|
||||
[
|
||||
{ "id": "1001", "type": "Regular" },
|
||||
{ "id": "1002", "type": "Chocolate" },
|
||||
{ "id": "1003", "type": "Blueberry" },
|
||||
{ "id": "1004", "type": "Devil's Food" }
|
||||
]
|
||||
},
|
||||
"topping":
|
||||
[
|
||||
{ "id": "5001", "type": "None" },
|
||||
{ "id": "5002", "type": "Glazed" },
|
||||
{ "id": "5005", "type": "Sugar" },
|
||||
{ "id": "5007", "type": "Powdered Sugar" },
|
||||
{ "id": "5006", "type": "Chocolate with Sprinkles" },
|
||||
{ "id": "5003", "type": "Chocolate" },
|
||||
{ "id": "5004", "type": "Maple" }
|
||||
]
|
||||
}
|
||||
|
||||
The U-SQL code parses the Json and generates a list of all possible combinations for donuts - with the possible batter and topping used in the donut.
|
||||
*/
|
||||
|
||||
CREATE ASSEMBLY IF NOT EXISTS [Newtonsoft.Json] FROM "assemblies/Newtonsoft.Json.dll";
|
||||
CREATE ASSEMBLY IF NOT EXISTS [Microsoft.Analytics.Samples.Formats] FROM "assemblies/Microsoft.Analytics.Samples.Formats.dll";
|
||||
|
||||
REFERENCE ASSEMBLY [Newtonsoft.Json];
|
||||
REFERENCE ASSEMBLY [Microsoft.Analytics.Samples.Formats];
|
||||
|
||||
DECLARE @INPUT_FILE string = @"/Samples/Data/json/donut.json";
|
||||
|
||||
|
||||
//Extract the different properties from the Json file using a JsonExtractor
|
||||
@json =
|
||||
EXTRACT id string, type string, name string, ppu string, batters string, topping string
|
||||
FROM @INPUT_FILE
|
||||
USING new Microsoft.Analytics.Samples.Formats.Json.JsonExtractor();
|
||||
|
||||
/*
|
||||
Batters and Toppings have nested Json in them, this script extracts the nested Json as SQL.MAPs
|
||||
*/
|
||||
@parsebatterandtopping =
|
||||
SELECT id,
|
||||
type ,
|
||||
name ,
|
||||
ppu ,
|
||||
Microsoft.Analytics.Samples.Formats.Json.JsonFunctions.JsonTuple(batters, "$..id") AS batter_id_map,
|
||||
Microsoft.Analytics.Samples.Formats.Json.JsonFunctions.JsonTuple(batters, "$..type") AS batter_type_map,
|
||||
Microsoft.Analytics.Samples.Formats.Json.JsonFunctions.JsonTuple(topping, "$..id") AS topping_id_map,
|
||||
Microsoft.Analytics.Samples.Formats.Json.JsonFunctions.JsonTuple(topping, "$..type") AS topping_type_map
|
||||
FROM @json;
|
||||
|
||||
/*
|
||||
Explode the batter map - this will result in a Cartesian product of the types and ids
|
||||
Result:
|
||||
batters.batter[0], 1001, batters.batter[0],Regular
|
||||
batters.batter[0], 1001, batters.batter[1],Chocolate
|
||||
...
|
||||
batters.batter[3], 1004, batters.batter[3], Devil's Food
|
||||
*/
|
||||
@batters =
|
||||
SELECT batter_id_name.Replace(".id", "") AS batter_id_name,
|
||||
batter_id_value,
|
||||
batter_type_name.Replace(".type", "") AS batter_type_name,
|
||||
batter_type_value
|
||||
FROM @parsebatterandtopping
|
||||
CROSS APPLY
|
||||
EXPLODE(batter_id_map) AS B(batter_id_name, batter_id_value)
|
||||
CROSS APPLY
|
||||
EXPLODE(batter_type_map) AS T(batter_type_name, batter_type_value);
|
||||
|
||||
/*
|
||||
Filter the complete Cartesian product to get the reduced map of the id and type values.
|
||||
Result:
|
||||
1001,Regular
|
||||
1002,Chocolate
|
||||
1003,Blueberry
|
||||
1004,Devil's Food
|
||||
*/
|
||||
@batters =
|
||||
SELECT batter_id_value,
|
||||
batter_type_value
|
||||
FROM @batters
|
||||
WHERE batter_id_name == batter_type_name;
|
||||
|
||||
OUTPUT @batters
|
||||
TO "/Samples/Output/batters.csv"
|
||||
USING Outputters.Csv(quoting:false);
|
||||
|
||||
/*
|
||||
Explode the topping map - this will result in a Cartesian product of the types and ids
|
||||
Result:
|
||||
toppings.topping[0], 5001, toppings.topping[0],None
|
||||
toppings.topping[0], 5001, toppings.topping[1],Glazed
|
||||
...
|
||||
toppings.topping[6], 5004, toppings.topping[6], Maple
|
||||
*/
|
||||
@toppings =
|
||||
SELECT topping_id_name.Replace(".id", "") AS topping_id_name,
|
||||
topping_id_value,
|
||||
topping_type_name.Replace(".type", "") AS topping_type_name,
|
||||
topping_type_value
|
||||
FROM @parsebatterandtopping
|
||||
CROSS APPLY
|
||||
EXPLODE(topping_id_map) AS B(topping_id_name, topping_id_value)
|
||||
CROSS APPLY
|
||||
EXPLODE(topping_type_map) AS T(topping_type_name, topping_type_value);
|
||||
/*
|
||||
Filter the complete Cartesian product to get the reduced map of the id and type values.
|
||||
Result:
|
||||
5001,None
|
||||
5002,Glazed
|
||||
5005,Sugar
|
||||
5007,Powdered Sugar
|
||||
5006,Chocolate with Sprinkles
|
||||
5003,Chocolate
|
||||
5004,Maple
|
||||
*/
|
||||
@toppings =
|
||||
SELECT topping_id_value,
|
||||
topping_type_value
|
||||
FROM @toppings
|
||||
WHERE topping_id_name == topping_type_name;
|
||||
|
||||
OUTPUT @toppings
|
||||
TO "/Samples/Output/toppings.csv"
|
||||
USING Outputters.Csv(quoting:false);
|
||||
|
||||
|
||||
/*
|
||||
Combine the batter and the topping types with the cake Id to generate the list of all the combinations available for donut.
|
||||
Result:
|
||||
5001,None
|
||||
5002,Glazed
|
||||
5005,Sugar
|
||||
5007,Powdered Sugar
|
||||
5006,Chocolate with Sprinkles
|
||||
5003,Chocolate
|
||||
5004,Maple
|
||||
*/
|
||||
@cake_types = SELECT id, type, name, batter_type_value, topping_type_value FROM @json CROSS JOIN @toppings CROSS JOIN @batters;
|
||||
|
||||
OUTPUT @cake_types TO "/Samples/Output/caketypes.csv" USING Outputters.Csv(quoting:false);
|
||||
Загрузка…
Ссылка в новой задаче