SO-76690871

README.md

CSV to JSON

input.csv

main.go

package main

import (
	"encoding/csv"
	"encoding/json"
	"fmt"
	"os"
	"reflect"
	"sort"
)

type Topic struct {
	Label string `json:"label"`
	Query string `json:"query"`
}

type JSONObj struct {
	Operation string `json:"operation"`
	Topic     Topic  `json:"topic"`
}

func (o JSONObj) key() string { return o.Operation + "@@" + o.Topic.Label }

func main() {
	f, err := os.Open("input.csv")
	must(err)
	r := csv.NewReader(f)
	header, err := r.Read() // discard header
	if err != nil {
		panic(fmt.Errorf("unexpectedly done reading input.csv: %v", err))
	}
	if !reflect.DeepEqual(header, []string{"operation", "label", "query"}) {
		panic(fmt.Errorf("header %v != %v", header, []string{"operation", "label", "query"}))
	}
	records, err := r.ReadAll()
	must(err)

	objects := make([]JSONObj, 0)
	for _, record := range records {
		objects = append(objects, JSONObj{
			Operation: record[0],
			Topic:     Topic{Label: record[1], Query: record[2]},
		})
	}

	f, err = os.Create("output-flat.json")
	must(err)
	b, err := json.MarshalIndent(objects, "", "    ")
	must(err)
	f.Write(b)
	must(f.Close())

	sort.Slice(objects, func(i, j int) bool { return objects[i].key() < objects[j].key() })

	groupedObjs := make(map[string][]JSONObj)
	key := ""
	for _, obj := range objects {
		if obj.key() != key {
			key = obj.key()
			groupedObjs[key] = make([]JSONObj, 0)
		}
		groupedObjs[key] = append(groupedObjs[key], obj)
	}

	f, err = os.Create("output-grouped.json")
	must(err)
	b, err = json.MarshalIndent(groupedObjs, "", "    ")
	must(err)
	f.Write(b)
	must(f.Close())
}

func must(err error) {
	if err != nil {
		panic(err)
	}
}

main.py

import csv
import json

from typing import Any

Row = dict[str, str]
JSONObj = dict[str, Any]

with open("input.csv", newline="", encoding="utf-8") as f:
    reader = csv.DictReader(f)
    rows: list[Row] = list(reader)

print(rows)
# [
#     {"operation": "op1", "label": "label1", "query": "query1"},
#     {"operation": "op1", "label": "label1", "query": "query2"},
#     {"operation": "op1", "label": "label2", "query": "query3"},
#     {"operation": "op2", "label": "label3", "query": "query4"},
#     {"operation": "op2", "label": "label4", "query": "query5"},
#     {"operation": "op2", "label": "label3", "query": "query6"},
# ]

data_flat: list[JSONObj] = []
for row in rows:
    obj = {
        "operation": row["operation"],
        "topic": {
            "label": row["label"],
            "query": row["query"],
        },
    }

    data_flat.append(obj)

with open("output-flat.json", "w", encoding="utf-8") as f:
    json.dump(data_flat, f, indent=4)


from itertools import groupby


def key_func(row: Row):
    return (row["operation"], row["label"])


rows.sort(key=key_func)
grouped_iter = groupby(rows, key=key_func)

data_grouped: JSONObj = {}
for key, grouped_rows in grouped_iter:
    grouped_list: list[JSONObj] = []
    for row in grouped_rows:
        obj = {
            "operation": row["operation"],
            "topic": {
                "label": row["label"],
                "query": row["query"],
            },
        }

        grouped_list.append(obj)

    data_grouped["@@".join(key)] = grouped_list


with open("output-grouped.json", "w", encoding="utf-8") as f:
    json.dump(data_grouped, f, indent=4)

output-flat.json

[
    {
        "operation": "op1",
        "topic": {
            "label": "label1",
            "query": "query1"
        }
    },
    {
        "operation": "op1",
        "topic": {
            "label": "label1",
            "query": "query2"
        }
    },
    {
        "operation": "op1",
        "topic": {
            "label": "label2",
            "query": "query3"
        }
    },
    {
        "operation": "op2",
        "topic": {
            "label": "label3",
            "query": "query4"
        }
    },
    {
        "operation": "op2",
        "topic": {
            "label": "label4",
            "query": "query5"
        }
    },
    {
        "operation": "op2",
        "topic": {
            "label": "label3",
            "query": "query6"
        }
    }
]

output-grouped.json

{
    "op1@@label1": [
        {
            "operation": "op1",
            "topic": {
                "label": "label1",
                "query": "query1"
            }
        },
        {
            "operation": "op1",
            "topic": {
                "label": "label1",
                "query": "query2"
            }
        }
    ],
    "op1@@label2": [
        {
            "operation": "op1",
            "topic": {
                "label": "label2",
                "query": "query3"
            }
        }
    ],
    "op2@@label3": [
        {
            "operation": "op2",
            "topic": {
                "label": "label3",
                "query": "query4"
            }
        },
        {
            "operation": "op2",
            "topic": {
                "label": "label3",
                "query": "query6"
            }
        }
    ],
    "op2@@label4": [
        {
            "operation": "op2",
            "topic": {
                "label": "label4",
                "query": "query5"
            }
        }
    ]
}