How to solve large json file?

[napasa]

My json file has a array of approximately ten million data.
ucrtbased.dll!0f5160d0() Unknown
[Frames below may be incorrect and/or missing, no symbols loaded for ucrtbased.dll]
[External Code]

WenKuInfoProcess.exe!std::_Allocate(unsigned int _Count, unsigned int _Sz, bool _Try_aligned_allocation) Line 87 C++
WenKuInfoProcess.exe!std::allocatorstd::_Container_proxy::allocate(unsigned int _Count) Line 828 C++
WenKuInfoProcess.exe!std::_Wrap_alloc<std::allocatorstd::_Container_proxy >::allocate(unsigned int _Count) Line 1078 C++
WenKuInfoProcess.exe!std::_String_alloc<std::_String_base_types<char,std::allocator > >::_Alloc_proxy() Line 1776 C++
WenKuInfoProcess.exe!std::_String_alloc<std::_String_base_types<char,std::allocator > >::_String_alloc<std::_String_base_types<char,std::allocator > ><std::_Wrap_alloc<std::allocator >,void>(std::_Wrap_alloc<std::allocator > && _Al) Line 1731 C++
WenKuInfoProcess.exe!std::basic_string<char,std::char_traits,std::allocator >::basic_string<char,std::char_traits,std::allocator >(std::basic_string<char,std::char_traits,std::allocator > && _Right) Line 2055 C++
WenKuInfoProcess.exe!std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> ><std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer>,void,0>(std::basic_string<char,std::char_traits,std::allocator > && _Val1, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && _Val2) Line 188 C++
WenKuInfoProcess.exe!std::allocator<std::_Tree_node<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,void *> >::construct<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >(std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> > * _Ptr, std::basic_string<char,std::char_traits,std::allocator > && <_Args_0>, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && <_Args_1>) Line 840 C++
WenKuInfoProcess.exe!std::allocator_traits<std::allocator<std::_Tree_node<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,void *> > >::construct<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >(std::allocator<std::_Tree_node<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,void *> > & _Al, std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> > * _Ptr, std::basic_string<char,std::char_traits,std::allocator > && <_Args_0>, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && <_Args_1>) Line 960 C++
WenKuInfoProcess.exe!std::_Wrap_alloc<std::allocator<std::_Tree_node<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,void *> > >::construct<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >,std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >(std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> > * _Ptr, std::basic_string<char,std::char_traits,std::allocator > && <_Args_0>, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && <_Args_1>) Line 1096 C++
WenKuInfoProcess.exe!std::_Tree_comp_alloc<std::_Tmap_traits<std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer>,std::less<std::basic_string<char,std::char_traits,std::allocator > >,std::allocator<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> > >,0> >::_Buynode<std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >(std::basic_string<char,std::char_traits,std::allocator > && <_Val_0>, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && <_Val_1>) Line 902 C++
WenKuInfoProcess.exe!std::_Tree<std::_Tmap_traits<std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer>,std::less<std::basic_string<char,std::char_traits,std::allocator > >,std::allocator<std::pair<std::basic_string<char,std::char_traits,std::allocator > const ,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> > >,0> >::emplace<std::basic_string<char,std::char_traits,std::allocator >,nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >(std::basic_string<char,std::char_traits,std::allocator > && <_Val_0>, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> && <_Val_1>) Line 1084 C++
WenKuInfoProcess.exe!nlohmann::detail::parser<nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >::parse_internal(bool keep, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> & result) Line 3083 C++
WenKuInfoProcess.exe!nlohmann::detail::parser<nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >::parse_internal(bool keep, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> & result) Line 3150 C++
WenKuInfoProcess.exe!nlohmann::detail::parser<nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >::parse_internal(bool keep, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> & result) Line 3076 C++
WenKuInfoProcess.exe!nlohmann::detail::parser<nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> >::parse(const bool strict, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> & result) Line 2941 C++
WenKuInfoProcess.exe!nlohmann::operator>>(std::basic_istream<char,std::char_traits > & i, nlohmann::basic_json<std::map,std::vector,std::basic_string<char,std::char_traits,std::allocator >,bool,__int64,unsigned __int64,double,std::allocator,nlohmann::adl_serializer> & j) Line 13150 C++
WenKuInfoProcess.exe!main(int argc, char * * argv) Line 22 C++
[External Code]

[nlohmann]

Does this error message occur during parsing?

[napasa]

Yes~. Code is simple. std::fstream read file, pass data to json obj.

[nlohmann]

Right now, we only support DOM-like parsing to memory. There is an experimental SAX-like approach, but it has not been merged yet. With such an approach, you may parse and process the input without the need of converting each element to a JSON value and storing it.

Would it be possible to share your input so we could experiment whether the new approach would help?

[napasa]

Ok, Laterly I will upload data to Google Drive and paste link here. Finally I choose sed and grep to parse my data.

[nlohmann]

Thanks!

[napasa]

json data link: https://drive.google.com/file/d/15Ejx81HGCCPHUUPYXu-1rky2bayBnB5O/view?usp=sharing

[nlohmann]

Thanks. What did you want to do with the file after parsing? I am asking because it is possible to define a callback function to be called during parsing, see https://nlohmann.github.io/json/classnlohmann_1_1basic__json_ab4f78c5f9fd25172eeec84482e03f5b7.html#ab4f78c5f9fd25172eeec84482e03f5b7

With such a function, you can process the input during parsing without the need of actually storing all input data.

[nlohmann]

Example:

#include <iostream>
#include <fstream>
#include "json.hpp"

using json = nlohmann::json;

int main()
{
    std::size_t count = 0;
    
    auto x = [&count](int depth, json::parse_event_t event, json& parsed) {
        if (event == json::parse_event_t::object_end)
        {
            ++count;
            return false; // do not store the object value
        }
        else
        {
            return true;
        }
    };
    
    std::ifstream f("wk_file_list.json");
    json::parse(f, x);
    
    std::cerr << "file has " << count << " elements\n";
}

Output: file has 1992511 elements.

On my machine, this takes less than 3 MB of memory.

[JosephP91]

Hi @nlohmann ,
I think I have the same problem. I have to process a very big JSON file to store its content in a MongoDB database. I am talking about a 85 Mb on disk file. Can I use that function to avoid memory problems?

[nlohmann]

The code above is just an example how to cope with a single array of objects. You may need to adjust it to your needs. Please also have a look at the documentation.

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.