Skip to content
Snippets Groups Projects
json.hpp 624 KiB
Newer Older
3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000
        {
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_any1;
            }

            case '.':
            {
                add(decimal_point_char);
                goto scan_number_decimal1;
            }

            case 'e':
            case 'E':
            {
                add(current);
                goto scan_number_exponent;
            }

            default:
                goto scan_number_done;
        }

scan_number_decimal1:
        // state: we just parsed a decimal point
        number_type = token_type::value_float;
        switch (get())
        {
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_decimal2;
            }

            default:
            {
                error_message = "invalid number; expected digit after '.'";
                return token_type::parse_error;
            }
        }

scan_number_decimal2:
        // we just parsed at least one number after a decimal point
        switch (get())
        {
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_decimal2;
            }

            case 'e':
            case 'E':
            {
                add(current);
                goto scan_number_exponent;
            }

            default:
                goto scan_number_done;
        }

scan_number_exponent:
        // we just parsed an exponent
        number_type = token_type::value_float;
        switch (get())
        {
            case '+':
            case '-':
            {
                add(current);
                goto scan_number_sign;
            }

            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_any2;
            }

            default:
            {
                error_message =
                    "invalid number; expected '+', '-', or digit after exponent";
                return token_type::parse_error;
            }
        }

scan_number_sign:
        // we just parsed an exponent sign
        switch (get())
        {
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_any2;
            }

            default:
            {
                error_message = "invalid number; expected digit after exponent sign";
                return token_type::parse_error;
            }
        }

scan_number_any2:
        // we just parsed a number after the exponent or exponent sign
        switch (get())
        {
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            {
                add(current);
                goto scan_number_any2;
            }

            default:
                goto scan_number_done;
        }

scan_number_done:
        // unget the character after the number (we only read it to know that
        // we are done scanning a number)
        unget();

        char* endptr = nullptr;
        errno = 0;

        // try to parse integers first and fall back to floats
        if (number_type == token_type::value_unsigned)
        {
            const auto x = std::strtoull(token_buffer.data(), &endptr, 10);

            // we checked the number format before
            assert(endptr == token_buffer.data() + token_buffer.size());

            if (errno == 0)
            {
                value_unsigned = static_cast<number_unsigned_t>(x);
                if (value_unsigned == x)
                {
                    return token_type::value_unsigned;
                }
            }
        }
        else if (number_type == token_type::value_integer)
        {
            const auto x = std::strtoll(token_buffer.data(), &endptr, 10);

            // we checked the number format before
            assert(endptr == token_buffer.data() + token_buffer.size());

            if (errno == 0)
            {
                value_integer = static_cast<number_integer_t>(x);
                if (value_integer == x)
                {
                    return token_type::value_integer;
                }
            }
        }

        // this code is reached if we parse a floating-point number or if an
        // integer conversion above failed
        strtof(value_float, token_buffer.data(), &endptr);

        // we checked the number format before
        assert(endptr == token_buffer.data() + token_buffer.size());

        return token_type::value_float;
    }

    /*!
    @param[in] literal_text  the literal text to expect
    @param[in] length        the length of the passed literal text
    @param[in] return_type   the token type to return on success
    */
    token_type scan_literal(const char* literal_text, const std::size_t length,
                            token_type return_type)
    {
        assert(current == literal_text[0]);
        for (std::size_t i = 1; i < length; ++i)
        {
            if (JSON_UNLIKELY(get() != literal_text[i]))
            {
                error_message = "invalid literal";
                return token_type::parse_error;
            }
        }
        return return_type;
    }

    /////////////////////
    // input management
    /////////////////////

    /// reset token_buffer; current character is beginning of token
    void reset() noexcept
    {
        token_buffer.clear();
        token_string.clear();
        token_string.push_back(std::char_traits<char>::to_char_type(current));
    }

    /*
    @brief get next character from the input

    This function provides the interface to the used input adapter. It does
    not throw in case the input reached EOF, but returns a
    `std::char_traits<char>::eof()` in that case.  Stores the scanned characters
    for use in error messages.

    @return character read from the input
    */
    std::char_traits<char>::int_type get()
    {
        ++chars_read;
        if (next_unget)
        {
            // just reset the next_unget variable and work with current
            next_unget = false;
        }
        else
        {
            current = ia->get_character();
        }

        if (JSON_LIKELY(current != std::char_traits<char>::eof()))
        {
            token_string.push_back(std::char_traits<char>::to_char_type(current));
        }
        return current;
    }

    /*!
    @brief unget current character (read it again on next get)

    We implement unget by setting variable next_unget to true. The input is not
    changed - we just simulate ungetting by modifying chars_read and
    token_string. The next call to get() will behave as if the unget character
    is read again.
    */
    void unget()
    {
        next_unget = true;
        --chars_read;
        if (JSON_LIKELY(current != std::char_traits<char>::eof()))
        {
            assert(token_string.size() != 0);
            token_string.pop_back();
        }
    }

    /// add a character to token_buffer
    void add(int c)
    {
        token_buffer.push_back(std::char_traits<char>::to_char_type(c));
    }

  public:
    /////////////////////
    // value getters
    /////////////////////

    /// return integer value
    constexpr number_integer_t get_number_integer() const noexcept
    {
        return value_integer;
    }

    /// return unsigned integer value
    constexpr number_unsigned_t get_number_unsigned() const noexcept
    {
        return value_unsigned;
    }

    /// return floating-point value
    constexpr number_float_t get_number_float() const noexcept
    {
        return value_float;
    }

    /// return current string value (implicitly resets the token; useful only once)
    string_t& get_string()
    {
        return token_buffer;
    }

    /////////////////////
    // diagnostics
    /////////////////////

    /// return position of last read token
    constexpr std::size_t get_position() const noexcept
    {
        return chars_read;
    }

    /// return the last read token (for errors only).  Will never contain EOF
    /// (an arbitrary value that is not a valid char value, often -1), because
    /// 255 may legitimately occur.  May contain NUL, which should be escaped.
    std::string get_token_string() const
    {
        // escape control characters
        std::string result;
        for (const auto c : token_string)
        {
            if ('\x00' <= c and c <= '\x1F')
            {
                // escape control characters
                char cs[9];
                snprintf(cs, 9, "<U+%.4hhX>", static_cast<unsigned char>(c));
                result += cs;
            }
            else
            {
                // add character as is
                result.push_back(c);
            }
        }

        return result;
    }

    /// return syntax error message
    constexpr const char* get_error_message() const noexcept
    {
        return error_message;
    }

    /////////////////////
    // actual scanner
    /////////////////////

    /*!
    @brief skip the UTF-8 byte order mark
    @return true iff there is no BOM or the correct BOM has been skipped
    */
    bool skip_bom()
    {
        if (get() == 0xEF)
        {
            if (get() == 0xBB and get() == 0xBF)
            {
                // we completely parsed the BOM
                return true;
            }
            else
            {
                // after reading 0xEF, an unexpected character followed
                return false;
            }
        }
        else
        {
            // the first character is not the beginning of the BOM; unget it to
            // process is later
            unget();
            return true;
        }
    }

    token_type scan()
    {
        // initially, skip the BOM
        if (chars_read == 0 and not skip_bom())
        {
            error_message = "invalid BOM; must be 0xEF 0xBB 0xBF if given";
            return token_type::parse_error;
        }

        // read next character and ignore whitespace
        do
        {
            get();
        }
        while (current == ' ' or current == '\t' or current == '\n' or current == '\r');

        switch (current)
        {
            // structural characters
            case '[':
                return token_type::begin_array;
            case ']':
                return token_type::end_array;
            case '{':
                return token_type::begin_object;
            case '}':
                return token_type::end_object;
            case ':':
                return token_type::name_separator;
            case ',':
                return token_type::value_separator;

            // literals
            case 't':
                return scan_literal("true", 4, token_type::literal_true);
            case 'f':
                return scan_literal("false", 5, token_type::literal_false);
            case 'n':
                return scan_literal("null", 4, token_type::literal_null);

            // string
            case '\"':
                return scan_string();

            // number
            case '-':
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
                return scan_number();

            // end of input (the null byte is needed when parsing from
            // string literals)
            case '\0':
            case std::char_traits<char>::eof():
                return token_type::end_of_input;

            // error
            default:
                error_message = "invalid literal";
                return token_type::parse_error;
        }
    }

  private:
    /// input adapter
    detail::input_adapter_t ia = nullptr;

    /// the current character
    std::char_traits<char>::int_type current = std::char_traits<char>::eof();

    /// whether the next get() call should just return current
    bool next_unget = false;

    /// the number of characters read
    std::size_t chars_read = 0;

    /// raw input token string (for error messages)
    std::vector<char> token_string {};

    /// buffer for variable-length tokens (numbers, strings)
    string_t token_buffer {};

    /// a description of occurred lexer errors
    const char* error_message = "";

    // number values
    number_integer_t value_integer = 0;
    number_unsigned_t value_unsigned = 0;
    number_float_t value_float = 0;

    /// the decimal point
    const char decimal_point_char = '.';
};
}
}

// #include <nlohmann/detail/input/parser.hpp>


#include <cassert> // assert
#include <cmath> // isfinite
#include <cstdint> // uint8_t
#include <functional> // function
#include <string> // string
#include <utility> // move

// #include <nlohmann/detail/exceptions.hpp>

// #include <nlohmann/detail/macro_scope.hpp>

// #include <nlohmann/detail/input/input_adapters.hpp>

// #include <nlohmann/detail/input/json_sax.hpp>


#include <cstddef>
#include <string>
#include <vector>

// #include <nlohmann/detail/input/parser.hpp>

// #include <nlohmann/detail/exceptions.hpp>


namespace nlohmann
{

/*!
@brief SAX interface
*/
template<typename BasicJsonType>
struct json_sax
{
    /// type for (signed) integers
    using number_integer_t = typename BasicJsonType::number_integer_t;
    /// type for unsigned integers
    using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
    /// type for floating-point numbers
    using number_float_t = typename BasicJsonType::number_float_t;
    /// type for strings
    using string_t = typename BasicJsonType::string_t;

    /// constant to indicate that no size limit is given for array or object
    static constexpr auto no_limit = std::size_t(-1);

    /*!
    @brief a null value was read
    @return whether parsing should proceed
    */
    virtual bool null() = 0;

    /*!
    @brief a boolean value was read
    @param[in] val  boolean value
    @return whether parsing should proceed
    */
    virtual bool boolean(bool val) = 0;

    /*!
    @brief an integer number was read
    @param[in] val  integer value
    @return whether parsing should proceed
    */
    virtual bool number_integer(number_integer_t val) = 0;

    /*!
    @brief an unsigned integer number was read
    @param[in] val  unsigned integer value
    @return whether parsing should proceed
    */
    virtual bool number_unsigned(number_unsigned_t val) = 0;

    /*!
    @brief an floating-point number was read
    @param[in] val  floating-point value
    @param[in] s    raw token value
    @return whether parsing should proceed
    */
    virtual bool number_float(number_float_t val, const string_t& s) = 0;

    /*!
    @brief a string was read
    @param[in] val  string value
    @return whether parsing should proceed
    */
    virtual bool string(string_t& val) = 0;

    /*!
    @brief the beginning of an object was read
    @param[in] elements  number of object elements or no_limit if unknown
    @return whether parsing should proceed
    @note binary formats may report the number of elements
    */
    virtual bool start_object(std::size_t elements = no_limit) = 0;

    /*!
    @brief an object key was read
    @param[in] val  object key
    @return whether parsing should proceed
    */
    virtual bool key(string_t& val) = 0;

    /*!
    @brief the end of an object was read
    @return whether parsing should proceed
    */
    virtual bool end_object() = 0;

    /*!
    @brief the beginning of an array was read
    @param[in] elements  number of array elements or no_limit if unknown
    @return whether parsing should proceed
    @note binary formats may report the number of elements
    */
    virtual bool start_array(std::size_t elements = no_limit) = 0;

    /*!
    @brief the end of an array was read
    @return whether parsing should proceed
    */
    virtual bool end_array() = 0;

    /*!
    @brief a parse error occurred
    @param[in] position    the position in the input where the error occurs
    @param[in] last_token  the last read token
    @param[in] error_msg   a detailed error message
    @return whether parsing should proceed (must return false)
    */
    virtual bool parse_error(std::size_t position,
                             const std::string& last_token,
                             const detail::exception& ex) = 0;

    virtual ~json_sax() = default;
};


namespace detail
{
/*!
@brief SAX implementation to create a JSON value from SAX events

This class implements the @ref json_sax interface and processes the SAX events
to create a JSON value which makes it basically a DOM parser. The structure or
hierarchy of the JSON value is managed by the stack `ref_stack` which contains
a pointer to the respective array or object for each recursion depth.

After successful parsing, the value that is passed by reference to the
constructor contains the parsed value.

@tparam BasicJsonType  the JSON type
*/
template<typename BasicJsonType>
class json_sax_dom_parser : public json_sax<BasicJsonType>
{
  public:
    using number_integer_t = typename BasicJsonType::number_integer_t;
    using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
    using number_float_t = typename BasicJsonType::number_float_t;
    using string_t = typename BasicJsonType::string_t;

    /*!
    @param[in, out] r  reference to a JSON value that is manipulated while
                       parsing
    @param[in] allow_exceptions_  whether parse errors yield exceptions
    */
    json_sax_dom_parser(BasicJsonType& r, const bool allow_exceptions_ = true)
        : root(r), allow_exceptions(allow_exceptions_)
    {}

    bool null() override
    {
        handle_value(nullptr);
        return true;
    }

    bool boolean(bool val) override
    {
        handle_value(val);
        return true;
    }

    bool number_integer(number_integer_t val) override
    {
        handle_value(val);
        return true;
    }

    bool number_unsigned(number_unsigned_t val) override
    {
        handle_value(val);
        return true;
    }

    bool number_float(number_float_t val, const string_t&) override
    {
        handle_value(val);
        return true;
    }

    bool string(string_t& val) override
    {
        handle_value(val);
        return true;
    }

    bool start_object(std::size_t len) override
    {
        ref_stack.push_back(handle_value(BasicJsonType::value_t::object));

        if (JSON_UNLIKELY(len != json_sax<BasicJsonType>::no_limit and len > ref_stack.back()->max_size()))
        {
            JSON_THROW(out_of_range::create(408,
                                            "excessive object size: " + std::to_string(len)));
        }

        return true;
    }

    bool key(string_t& val) override
    {
        // add null at given key and store the reference for later
        object_element = &(ref_stack.back()->m_value.object->operator[](val));
        return true;
    }

    bool end_object() override
    {
        ref_stack.pop_back();
        return true;
    }

    bool start_array(std::size_t len) override
    {
        ref_stack.push_back(handle_value(BasicJsonType::value_t::array));

        if (JSON_UNLIKELY(len != json_sax<BasicJsonType>::no_limit and len > ref_stack.back()->max_size()))
        {
            JSON_THROW(out_of_range::create(408,
                                            "excessive array size: " + std::to_string(len)));
        }

        return true;
    }

    bool end_array() override
    {
        ref_stack.pop_back();
        return true;
    }

    bool parse_error(std::size_t, const std::string&,
                     const detail::exception& ex) override
    {
        errored = true;
        if (allow_exceptions)
        {
            // determine the proper exception type from the id
            switch ((ex.id / 100) % 100)
            {
                case 1:
                    JSON_THROW(*reinterpret_cast<const detail::parse_error*>(&ex));
                case 2:
                    JSON_THROW(*reinterpret_cast<const detail::invalid_iterator*>(&ex));  // LCOV_EXCL_LINE
                case 3:
                    JSON_THROW(*reinterpret_cast<const detail::type_error*>(&ex));  // LCOV_EXCL_LINE
                case 4:
                    JSON_THROW(*reinterpret_cast<const detail::out_of_range*>(&ex));
                case 5:
                    JSON_THROW(*reinterpret_cast<const detail::other_error*>(&ex));  // LCOV_EXCL_LINE
                default:
                    assert(false);  // LCOV_EXCL_LINE
            }
        }
        return false;
    }

    constexpr bool is_errored() const
    {
        return errored;
    }

  private:
    /*!
    @invariant If the ref stack is empty, then the passed value will be the new
               root.
    @invariant If the ref stack contains a value, then it is an array or an
               object to which we can add elements
    */
    template<typename Value>
    BasicJsonType* handle_value(Value&& v)
    {
        if (ref_stack.empty())
        {
            root = BasicJsonType(std::forward<Value>(v));
            return &root;
        }
        else
        {
            assert(ref_stack.back()->is_array() or ref_stack.back()->is_object());
            if (ref_stack.back()->is_array())
            {
                ref_stack.back()->m_value.array->emplace_back(std::forward<Value>(v));
                return &(ref_stack.back()->m_value.array->back());
            }
            else
            {
                assert(object_element);
                *object_element = BasicJsonType(std::forward<Value>(v));
                return object_element;
            }
        }
    }

    /// the parsed JSON value
    BasicJsonType& root;
    /// stack to model hierarchy of values
    std::vector<BasicJsonType*> ref_stack;
    /// helper to hold the reference for the next object element
    BasicJsonType* object_element = nullptr;
    /// whether a syntax error occurred
    bool errored = false;
    /// whether to throw exceptions in case of errors
    const bool allow_exceptions = true;
};

template<typename BasicJsonType>
class json_sax_dom_callback_parser : public json_sax<BasicJsonType>
{
  public:
    using number_integer_t = typename BasicJsonType::number_integer_t;
    using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
    using number_float_t = typename BasicJsonType::number_float_t;
    using string_t = typename BasicJsonType::string_t;
    using parser_callback_t = typename BasicJsonType::parser_callback_t;
    using parse_event_t = typename BasicJsonType::parse_event_t;

    json_sax_dom_callback_parser(BasicJsonType& r,
                                 const parser_callback_t cb,
                                 const bool allow_exceptions_ = true)
        : root(r), callback(cb), allow_exceptions(allow_exceptions_)
    {
        keep_stack.push_back(true);
    }

    bool null() override
    {
        handle_value(nullptr);
        return true;
    }

    bool boolean(bool val) override
    {
        handle_value(val);
        return true;
    }

    bool number_integer(number_integer_t val) override
    {
        handle_value(val);
        return true;
    }

    bool number_unsigned(number_unsigned_t val) override
    {
        handle_value(val);
        return true;
    }

    bool number_float(number_float_t val, const string_t&) override
    {
        handle_value(val);
        return true;
    }

    bool string(string_t& val) override
    {
        handle_value(val);
        return true;
    }

    bool start_object(std::size_t len) override
    {
        // check callback for object start
        const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::object_start, discarded);
        keep_stack.push_back(keep);

        auto val = handle_value(BasicJsonType::value_t::object, true);
        ref_stack.push_back(val.second);

        // check object limit
        if (ref_stack.back())
        {
            if (JSON_UNLIKELY(len != json_sax<BasicJsonType>::no_limit and len > ref_stack.back()->max_size()))
            {
                JSON_THROW(out_of_range::create(408,
                                                "excessive object size: " + std::to_string(len)));
            }
        }

        return true;
    }

    bool key(string_t& val) override
    {
        BasicJsonType k = BasicJsonType(val);

        // check callback for key
        const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::key, k);
        key_keep_stack.push_back(keep);

        // add discarded value at given key and store the reference for later
        if (keep and ref_stack.back())
        {
            object_element = &(ref_stack.back()->m_value.object->operator[](val) = discarded);
        }

        return true;
    }

    bool end_object() override
    {
        if (ref_stack.back())
        {
            if (not callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::object_end, *ref_stack.back()))
            {
                // discard object
                *ref_stack.back() = discarded;
            }
        }

        assert(not ref_stack.empty());
        assert(not keep_stack.empty());
        ref_stack.pop_back();
        keep_stack.pop_back();

        if (not ref_stack.empty() and ref_stack.back())
        {
            // remove discarded value
            if (ref_stack.back()->is_object())
            {
                for (auto it = ref_stack.back()->begin(); it != ref_stack.back()->end(); ++it)
                {
                    if (it->is_discarded())
                    {
                        ref_stack.back()->erase(it);
                        break;
                    }
                }
            }
        }

        return true;
    }

    bool start_array(std::size_t len) override
    {
        const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::array_start, discarded);
        keep_stack.push_back(keep);

        auto val = handle_value(BasicJsonType::value_t::array, true);
        ref_stack.push_back(val.second);

        // check array limit
        if (ref_stack.back())
        {
            if (JSON_UNLIKELY(len != json_sax<BasicJsonType>::no_limit and len > ref_stack.back()->max_size()))
            {
                JSON_THROW(out_of_range::create(408,
                                                "excessive array size: " + std::to_string(len)));
            }
        }

        return true;
    }