Convert nested JSON to CSV

Question

I am converting a nested JSON object with more than 10 levels to CSV file in C# .NET.

I have been using JavaScriptSerializer().Deserialize(json)

Answer 1

I wrote this and it is working for me Here we save all breadcrumps of object tree in headers with format prop_prop And save jarray property objects in headers in format prop1

    public Dictionary<string, string> ComplexJsonToDictionary(JObject jObject, Dictionary<string, string> result, string field)
    {
        foreach (var property in jObject.Properties())
        {
            var endField = field + (string.IsNullOrEmpty(field) ? "" : "_") + property.Name;

            var innerDictionary = new Dictionary<string, string>();
            try
            {
                var innerValue = JObject.Parse(Convert.ToString(property.Value));


                result.AddOrOverride(ComplexJsonToDictionary(innerValue, innerDictionary, endField));
            }
            catch (Exception)
            {
                try
                {
                    var innerValues = JArray.Parse(Convert.ToString(property.Value));
                    try
                    {
                        var i = 0;
                        foreach (var token in innerValues)
                        {
                            var innerValue = JObject.Parse(Convert.ToString(token));

                            result.AddOrOverride(ComplexJsonToDictionary(innerValue, innerDictionary, endField+i++));
                        }
                    }
                    catch (Exception)
                    {
                        result.Add(endField, string.Join(",", innerValues.Values<string>()));
                    }
                }
                catch (Exception)
                {
                    result.Add(endField, property.Value.ToString());
                }
            }
        }
        return result;
    }

Thanks for atantion and please write review if appropriate.

Answer 2

There's an inconsistency in your request: you want a row to be generated for the root object, which has children, but you don't want a row to be generated for the "F3[2]" object, which also has children. So it sounds like your rule is, "print a row for an object with at least one primitive-value property, as long as that object is either the root object or does not have descendant objects with at a least one primitive-value property". That's a little tricky, but can be done with LINQ to JSON

        var obj = JObject.Parse(json);

        // Collect column titles: all property names whose values are of type JValue, distinct, in order of encountering them.
        var values = obj.DescendantsAndSelf()
            .OfType<JProperty>()
            .Where(p => p.Value is JValue)
            .GroupBy(p => p.Name)
            .ToList();

        var columns = values.Select(g => g.Key).ToArray();

        // Filter JObjects that have child objects that have values.
        var parentsWithChildren = values.SelectMany(g => g).SelectMany(v => v.AncestorsAndSelf().OfType<JObject>().Skip(1)).ToHashSet();

        // Collect all data rows: for every object, go through the column titles and get the value of that property in the closest ancestor or self that has a value of that name.
        var rows = obj
            .DescendantsAndSelf()
            .OfType<JObject>()
            .Where(o => o.PropertyValues().OfType<JValue>().Any())
            .Where(o => o == obj || !parentsWithChildren.Contains(o)) // Show a row for the root object + objects that have no children.
            .Select(o => columns.Select(c => o.AncestorsAndSelf()
                .OfType<JObject>()
                .Select(parent => parent[c])
                .Where(v => v is JValue)
                .Select(v => (string)v)
                .FirstOrDefault())
                .Reverse() // Trim trailing nulls
                .SkipWhile(s => s == null)
                .Reverse());

        // Convert to CSV
        var csvRows = new[] { columns }.Concat(rows).Select(r => string.Join(",", r));
        var csv = string.Join("\n", csvRows);

        Console.WriteLine(csv);

Using

public static class EnumerableExtensions
{
    // http://stackoverflow.com/questions/3471899/how-to-convert-linq-results-to-hashset-or-hashedset
    public static HashSet<T> ToHashSet<T>(this IEnumerable<T> source)
    {
        return new HashSet<T>(source);
    }
}

Which outputs:

F1,F2,E1,E2,D1,D2
1,2
1,2,3,4
1,2,5,6
1,2,7,8,9,10