amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-06 22:47:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add images of json_documents: save() and load()

Browse Source 
An image is a document stored so that loading it needs no
parsing: save() writes the node index, the text and the decoded
strings; the static load() reads an image written by save().

load() takes a pointer and size, a borrowed vector, or an owned
rvalue vector; the nodes are copied so they are aligned and can
be edited, while the text and decoded strings stay in the image.

image_check controls how much load() trusts the input: full
checks structure, bounds, strings and numbers, the parser's own
guarantees; bounds checks structure and bounds only; none skips
all checks, for images from a trusted source.

Layout is little-endian only ("NJVI" header, nodes, text, decoded
strings), following the idea of zero-copy formats such as
FlatBuffers and YaFF; the check follows FlatBuffers' Verifier.

New errors: parse_error.116 for a malformed image or a failed
check, type_error.320 for a discarded document or a big-endian
target.

A dedicated fuzzer and 6,000 seeded corruptions, checked under
ASan/UBSan, found and fixed two gaps: unchecked reserved header
fields, and unbounded null/boolean offsets that could make
dump() throw std::length_error.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-06 10:48:07 +02:00
1 parent a0b98325cf
commit 9cb9f7fbad
27 files changed
+3064 -244
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/view/document_data.hpp
+3 -1
View File
@@ -10,7 +10,7 @@
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint32_t
#include <cstdint> // uint8_t, uint32_t
#include <cstring> // memcpy
#include <functional> // less
#include <map> // map
@@ -41,7 +41,9 @@ struct document_data
node* inline_tape = nullptr; ///< node array allocated together with this header
std::size_t inline_cap = 0;
std::string arena{}; ///< decoded strings that contained escapes // NOLINT(readability-redundant-member-init)
std::size_t arena_size = 0; ///< bytes of decoded strings at base[1] (the arena, or those of a loaded image)
std::string owned{}; ///< owned copy of the input, if any // NOLINT(readability-redundant-member-init)
std::vector<std::uint8_t> owned_image{}; ///< a loaded image the document owns (the text and the decoded strings point into it) // NOLINT(readability-redundant-member-init)
// hash indexes of large objects (see object_index.hpp)
static constexpr std::uint32_t index_min_members = 128;
include/nlohmann/detail/view/image.hpp
+602
View File
@@ -0,0 +1,602 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // int64_t, uint8_t, uint16_t, uint32_t, uint64_t
#include <cstring> // memcmp, memcpy
#include <limits> // numeric_limits
#include <string> // string
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
#include <nlohmann/detail/view/number.hpp>
#include <nlohmann/detail/view/object_index.hpp>
#include <nlohmann/detail/view/scan.hpp>
// Images: a document stored so that loading it needs no parsing.
//
// Layout (little-endian): a 64-byte header, the nodes, the text (the source,
// followed by the number tokens written by edits), a NUL, the decoded strings
// (followed by the strings written by edits), a NUL. The idea is that of
// zero-copy formats such as FlatBuffers (https://github.com/google/flatbuffers)
// and YaFF (https://github.com/yandex/yaff); no code is taken from them.
// check_image follows the idea of FlatBuffers' Verifier (bounds and
// structure) and also checks what the parser guarantees about strings and
// numbers, so that reading and serializing a checked image is safe and yields
// valid JSON.
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// how load() checks an image
enum class image_check
{
/// everything the parser guarantees: structure and bounds, strings (valid
/// UTF-8; source strings without quotes, backslashes, and control
/// characters), and numbers (well-formed, matching the stored values)
full,
/// structure and bounds only: reading and serializing are safe, but a
/// crafted image can yield invalid UTF-8, strings that serialize to
/// invalid JSON, or numbers that differ from their text
bounds,
/// none: for images from a trusted source only (a damaged image is
/// undefined behavior)
none,
};
struct image_header
{
std::array<char, 4> magic; ///< "NJVI"
std::uint32_t version; ///< 1
std::uint64_t node_count;
std::uint64_t text_size;
std::uint64_t arena_size;
std::array<std::uint64_t, 4> reserved; ///< zero (for later versions)
};
static_assert(sizeof(image_header) == 64, "the image header must be 64 bytes");
constexpr std::uint32_t image_version = 1;
/// the largest node count and text or string size of an image (as for parsed
/// documents, offsets and counts must fit 32 bits)
constexpr std::uint64_t image_limit = 0xFFFFFFF0u;
/// Copy the current structure of an edited document into nodes in document
/// order, as the parser would have written them. Text written by edits is
/// appended to text_tail (number tokens) and arena_tail (strings); floats that
/// are not finite become null, as dump() writes them.
inline void compact_nodes(const document_data& d, std::size_t arena_size, std::vector<node>& out, std::string& text_tail, std::string& arena_tail)
{
struct frame
{
const node* cur;
const node* end;
std::size_t index; ///< the container's node in out
std::uint32_t count;
bool object;
};
std::vector<frame> stack;
const auto string_node = [&](const node & s)
{
node r = s;
r.extra = 0;
r.flags = static_cast<std::uint8_t>(s.flags & node_flags::storage);
if (r.flags == node_flags::edited)
{
r.off = static_cast<std::uint32_t>(arena_size + arena_tail.size());
arena_tail.append(d.str(s), s.len);
r.flags = node_flags::escaped;
}
return r;
};
const auto emit = [&](const node * v)
{
node r = *v;
switch (static_cast<value_t>(v->kind))
{
case value_t::object:
case value_t::array:
r.flags = 0;
r.extra = 0;
r.off = (v->flags & (node_flags::moved | node_flags::is_new)) != 0 ? 0 : v->off;
r.len = 0; // counted below
r.next = 0; // set when the container is complete
stack.push_back(frame{d.first_child_edited(v), d.child_end_edited(v), out.size(), 0, v->kind == static_cast<std::uint8_t>(value_t::object)});
break;
case value_t::string:
r = string_node(*v);
break;
case value_t::number_integer:
case value_t::number_unsigned:
if ((v->flags & node_flags::storage) == node_flags::edited)
{
r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
text_tail.append(d.str(*v), number_length(*v));
}
r.flags = 0;
break;
case value_t::number_float:
if ((v->flags & node_flags::storage) == node_flags::edited)
{
const char* const t = d.str(*v);
if (t[0] == 'n' || t[0] == 'i' || (v->len > 1 && t[1] == 'i'))
{
r = node{}; // nan and infinity: null, as dump() writes them
r.kind = static_cast<std::uint8_t>(value_t::null);
break;
}
r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
text_tail.append(t, v->len);
r.extra = 0xFFFFu; // the digit layout is not recorded
}
r.flags = 0;
break;
case value_t::boolean:
r.flags = static_cast<std::uint8_t>(v->flags & node_flags::is_true);
break;
case value_t::null:
case value_t::binary:
case value_t::discarded:
default:
r.flags = 0;
break;
}
out.push_back(r);
};
emit(d.tape);
while (!stack.empty())
{
frame& top = stack.back();
if (top.cur == top.end)
{
node& c = out[top.index];
c.len = top.count;
c.next = static_cast<std::uint32_t>(out.size() - top.index);
stack.pop_back();
continue;
}
++top.count;
const node* v = nullptr;
if (top.object)
{
out.push_back(string_node(*top.cur));
v = document_data::deref(top.cur + 1);
top.cur = document_data::after(top.cur + 1);
}
else
{
v = document_data::deref(top.cur);
top.cur = document_data::after(top.cur);
}
emit(v); // may grow the stack (top is not used afterwards)
}
}
/// the document as an image
inline std::vector<std::uint8_t> save_image(const document_data& d)
{
#if !NLOHMANN_VIEW_LITTLE_ENDIAN
throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
#endif
const std::size_t arena_size = d.arena_size;
const node* nodes = d.tape;
std::size_t count = d.tape_size;
std::vector<node> compacted;
std::string text_tail;
std::string arena_tail;
if (d.edits)
{
compact_nodes(d, arena_size, compacted, text_tail, arena_tail);
nodes = compacted.data();
count = compacted.size();
}
const std::size_t text_size = d.size + text_tail.size();
const std::size_t total_arena = arena_size + arena_tail.size();
if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
{
// LCOV_EXCL_START (4 GiB)
throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
// LCOV_EXCL_STOP
}
image_header h{};
h.magic = {{'N', 'J', 'V', 'I'}};
h.version = image_version;
h.node_count = count;
h.text_size = text_size;
h.arena_size = total_arena;
std::vector<std::uint8_t> image(sizeof(h) + (count * sizeof(node)) + text_size + 1 + total_arena + 1);
std::uint8_t* o = image.data();
std::memcpy(o, &h, sizeof(h));
o += sizeof(h);
std::memcpy(o, nodes, count * sizeof(node));
// the hash indexes are rebuilt by load()
for (std::size_t i = 0; i < count; ++i)
{
if (nodes[i].kind == static_cast<std::uint8_t>(value_t::object) && nodes[i].extra != 0)
{
node n = nodes[i];
n.extra = 0;
std::memcpy(o + (i * sizeof(node)), &n, sizeof(node));
}
}
o += count * sizeof(node);
const auto append = [&o](const char* s, std::size_t n)
{
if (n != 0)
{
std::memcpy(o, s, n);
o += n;
}
};
append(d.src, d.size);
append(text_tail.data(), text_tail.size());
*o++ = 0;
append(d.base[1], arena_size);
append(arena_tail.data(), arena_tail.size());
*o = 0;
return image;
}
/// whether a number node matches its token the way the parser records it
/// (after the bounds check)
inline bool check_number(const node& n, const unsigned char* text)
{
const std::size_t len = number_length(n);
const unsigned char* const s = text + n.off;
const unsigned char* const e = s + len;
const unsigned char* p = s;
const bool negative = *p == '-';
p += negative ? 1 : 0;
const unsigned char* const int_start = p;
if (p == e)
{
return false;
}
if (*p == '0')
{
++p;
}
else if (*p >= '1' && *p <= '9')
{
while (p != e && is_digit(*p))
{
++p;
}
}
else
{
return false;
}
const auto int_digits = static_cast<std::size_t>(p - int_start);
std::size_t frac_digits = 0;
bool is_float = false;
if (p != e && *p == '.')
{
const unsigned char* const f0 = ++p;
while (p != e && is_digit(*p))
{
++p;
}
if (p == f0)
{
return false;
}
frac_digits = static_cast<std::size_t>(p - f0);
is_float = true;
}
std::int64_t exponent = 0;
if (p != e && (*p | 0x20u) == 'e')
{
++p;
const bool exp_negative = p != e && *p == '-';
p += (p != e && (*p == '+' || *p == '-')) ? 1 : 0;
if (p == e || !is_digit(*p))
{
return false;
}
while (p != e && is_digit(*p))
{
exponent = exponent < 100000 ? (exponent * 10) + (*p - '0') : exponent;
++p;
}
exponent = exp_negative ? -exponent : exponent;
is_float = true;
}
if (p != e)
{
return false;
}
if (n.kind == static_cast<std::uint8_t>(value_t::number_float))
{
// the digit layout the parser records (or "many", as compaction
// writes it), and a finite value
const auto layout = static_cast<std::uint16_t>((int_digits < 255 ? int_digits : 255) | ((frac_digits < 255 ? frac_digits : 255) << 8u));
if (n.extra != layout && n.extra != 0xFFFFu)
{
return false;
}
// parse() rejects floats that overflow; as there, only a number whose
// magnitude could reach 1e308 needs the conversion
if (static_cast<std::int64_t>(int_digits) + exponent > 300)
{
const auto v = float_value<double>(reinterpret_cast<const char*>(s), n); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
return v <= (std::numeric_limits<double>::max)() && v >= -(std::numeric_limits<double>::max)();
}
return true;
}
// integers: the token's value is the stored one; number_integer nodes of
// edits can be non-negative (as basic_json keeps the type of a value)
const bool integer = n.kind == static_cast<std::uint8_t>(value_t::number_integer);
if (is_float || int_digits > 20 || (negative && !integer))
{
return false;
}
// (at most 19 digits cannot overflow; 20 digits are compared with 2^64 - 1)
if (int_digits == 20 && std::memcmp(int_start, "18446744073709551615", 20) > 0)
{
return false;
}
std::uint64_t m = 0;
for (const unsigned char* d = int_start; d != int_start + int_digits; ++d)
{
m = (m * 10) + static_cast<std::uint64_t>(*d - '0');
}
if (integer && m > (negative ? std::uint64_t{1} << 63u : (std::uint64_t{1} << 63u) - 1))
{
return false;
}
return integer_bits(n) == (negative ? 0 - m : m);
}
/// Check the nodes of a loaded image against its text and decoded strings:
/// kinds, flags, and `extra`; extents and element counts of arrays and
/// objects; keys; bounds; string contents (source strings as the parser
/// leaves them: no quotes, backslashes, or control characters; all strings
/// valid UTF-8); and number tokens.
inline bool check_image(const node* nodes, std::size_t count, const unsigned char* text, std::size_t text_size,
const unsigned char* arena, std::size_t arena_size, bool full)
{
struct frame
{
std::size_t end;
std::uint32_t len;
std::uint32_t seen;
bool object;
bool expect_key;
};
std::vector<frame> stack;
const auto check_string = [&](const node & n) -> bool
{
if ((n.flags & ~node_flags::escaped) != 0 || n.extra != 0)
{
return false;
}
const bool decoded = (n.flags & node_flags::escaped) != 0;
const unsigned char* const base = decoded ? arena : text;
const std::size_t limit = decoded ? arena_size : text_size;
if (n.off > limit || n.len > limit - n.off)
{
return false;
}
if (!full)
{
return true;
}
const unsigned char* const b = base + n.off;
return decoded ? valid_utf8_prefix(b, n.len) == n.len : scan_string_run(b, b + n.len) == b + n.len;
};
// bounds of a number token; the recorded digit layout must lie within it
const auto number_in_bounds = [&](const node & n) -> bool
{
const std::size_t len = number_length(n);
if (len == 0 || n.off > text_size || len > text_size - n.off)
{
return false;
}
if (n.kind != static_cast<std::uint8_t>(value_t::number_float))
{
return (n.extra >> 8u) == 0;
}
// float_value() reads the sign, the integer digits, and the point and
// fraction digits the layout records (a layout of more than 19 digits
// means the general conversion, which stays within the token)
const std::size_t int_digits = n.extra & 0xFFu;
const std::size_t frac_digits = n.extra >> 8u;
const std::size_t need = (text[n.off] == '-' ? 1u : 0u) + int_digits + (frac_digits != 0 ? frac_digits + 1 : 0);
return int_digits + frac_digits > 19 || need <= len;
};
std::size_t i = 0;
for (;;)
{
// close finished arrays and objects
while (!stack.empty() && i == stack.back().end)
{
const frame f = stack.back();
if (f.seen != f.len || (f.object && !f.expect_key))
{
return false;
}
stack.pop_back();
if (!stack.empty())
{
++stack.back().seen;
stack.back().expect_key = true;
}
}
if (i == count)
{
return stack.empty();
}
if (i != 0 && stack.empty())
{
return false; // nodes after the root
}
const node& n = nodes[i];
if (!stack.empty() && stack.back().object && stack.back().expect_key)
{
if (n.kind != static_cast<std::uint8_t>(value_t::string) || !check_string(n))
{
return false;
}
stack.back().expect_key = false;
++i;
continue;
}
bool complete = true;
switch (static_cast<value_t>(n.kind))
{
case value_t::null:
// (the offset of a literal is read to size the output of dump())
if (n.flags != 0 || n.extra != 0 || n.off > text_size)
{
return false;
}
break;
case value_t::boolean:
if ((n.flags & ~node_flags::is_true) != 0 || n.extra != 0 || n.off > text_size)
{
return false;
}
break;
case value_t::string:
if (!check_string(n))
{
return false;
}
break;
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
if (n.flags != 0 || !number_in_bounds(n) || (full && !check_number(n, text)))
{
return false;
}
break;
case value_t::array:
case value_t::object:
{
const std::size_t limit = stack.empty() ? count : stack.back().end;
if (n.flags != 0 || n.extra != 0 || n.next == 0 || n.next > limit - i || n.off > text_size)
{
return false;
}
stack.push_back(frame{i + n.next, n.len, 0, n.kind == static_cast<std::uint8_t>(value_t::object), true});
complete = false;
break;
}
case value_t::binary:
case value_t::discarded:
default:
return false;
}
++i;
if (complete && !stack.empty())
{
++stack.back().seen;
stack.back().expect_key = true;
}
}
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
{
throw_parse_error(116, concat("invalid json_document image: ", what));
}
/// Read an image into d. The text and the decoded strings stay in the image;
/// the nodes are copied (so that they are aligned, and edits can change them).
inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
{
#if !NLOHMANN_VIEW_LITTLE_ENDIAN
throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
#endif
if (image == nullptr || size < sizeof(image_header))
{
throw_invalid_image("too short");
}
image_header h{};
std::memcpy(&h, image, sizeof(h));
// (the reserved fields are for later versions)
if (std::memcmp(h.magic.data(), "NJVI", 4) != 0 || h.version != image_version
|| (h.reserved[0] | h.reserved[1] | h.reserved[2] | h.reserved[3]) != 0)
{
throw_invalid_image("unknown format");
}
const std::size_t room = size - sizeof(h);
if (h.node_count == 0 || h.node_count > room / sizeof(node) || h.node_count >= image_limit || h.text_size >= image_limit || h.arena_size >= image_limit)
{
throw_invalid_image("sizes out of range");
}
const auto count = static_cast<std::size_t>(h.node_count);
const auto text_size = static_cast<std::size_t>(h.text_size);
const auto arena_size = static_cast<std::size_t>(h.arena_size);
const std::size_t text_at = sizeof(h) + (count * sizeof(node));
// the text, a NUL, the decoded strings, a NUL, and nothing after them
if (size - text_at < 2 || text_size > size - text_at - 2 || arena_size != size - text_at - text_size - 2
|| image[text_at + text_size] != 0 || image[size - 1] != 0)
{
throw_invalid_image("sizes out of range");
}
d.discarded = true;
d.edits.reset();
d.base[2] = nullptr;
d.owned.clear();
if (d.owned_image.empty() || image != d.owned_image.data())
{
d.owned_image.clear();
}
d.arena.clear();
d.indexes.clear();
d.index_slots.clear();
d.large_objects.clear();
d.tape_size = 0;
d.reserve(count);
std::memcpy(d.tape, image + sizeof(h), count * sizeof(node));
d.tape_size = count;
const std::uint8_t* const text = image + text_at;
const std::uint8_t* const arena = text + text_size + 1;
d.src = reinterpret_cast<const char*>(text); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
d.size = text_size;
d.base[0] = d.src;
d.base[1] = reinterpret_cast<const char*>(arena); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
d.arena_size = arena_size;
if (check != image_check::none && !check_image(d.tape, count, text, text_size, arena, arena_size, check == image_check::full))
{
throw_invalid_image("the check failed");
}
// the hash indexes of large objects, as after parsing
for (std::size_t i = 0; i < count; ++i)
{
node& n = d.tape[i];
if (n.kind == static_cast<std::uint8_t>(value_t::object))
{
n.extra = 0;
if (n.len >= document_data::index_min_members)
{
d.large_objects.push_back(static_cast<std::uint32_t>(i));
}
}
}
build_object_indexes(d);
d.discarded = false;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/number.hpp
+67 -30
View File
@@ -26,43 +26,76 @@ namespace detail
namespace view
{
/*!
@brief locate the decimal point and the end of the mantissa of a float token
Also checks that the token is a JSON number. Tokens of the parser and of edits
always are; an image loaded with image_check::bounds can hold any bytes, which
must not reach the conversion (it expects a well-formed token).
*/
inline bool float_token_layout(const char* first, const char* last, std::size_t& dot, std::size_t& mantissa_end) noexcept
{
const auto digit = [last](const char* q)
{
return q != last && is_digit(static_cast<unsigned char>(*q));
};
const char* p = first;
p += (p != last && *p == '-') ? 1 : 0;
if (!digit(p) || (*p == '0' && digit(p + 1)))
{
return false;
}
while (digit(p))
{
++p;
}
dot = std::string::npos;
if (p != last && *p == '.')
{
dot = static_cast<std::size_t>(p - first);
if (!digit(++p))
{
return false;
}
while (digit(p))
{
++p;
}
}
mantissa_end = static_cast<std::size_t>(p - first);
if (p != last && (*p == 'e' || *p == 'E'))
{
++p;
p += (p != last && (*p == '+' || *p == '-')) ? 1 : 0;
if (!digit(p))
{
return false;
}
while (digit(p))
{
++p;
}
}
return p == last;
}
/*!
@brief the value of the float token of a node, as parse() converts it
Uses the lexer's conversion (detail::convert_float), so that the values are
bit-identical to parse(): float and double are converted without allocation
and independent of the locale. The digit layout recorded while parsing locates
the decimal point and the exponent without scanning the token.
and independent of the locale. A token that is not a JSON number (only in a
damaged image loaded with image_check::bounds) yields 0.
*/
template<typename FloatType>
NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
{
const char* const last = first + n.len;
const std::size_t neg = first[0] == '-' ? 1 : 0;
const std::size_t int_digits = n.extra & 0xFFu;
const std::size_t frac_digits = n.extra >> 8u;
std::size_t dot = std::string::npos;
std::size_t mantissa_end = n.len;
if (int_digits != 255 && frac_digits != 255)
std::size_t dot = 0;
std::size_t mantissa_end = 0;
if (NLOHMANN_VIEW_UNLIKELY(!float_token_layout(first, last, dot, mantissa_end)))
{
dot = frac_digits != 0 ? neg + int_digits : std::string::npos;
mantissa_end = neg + int_digits + (frac_digits != 0 ? 1 + frac_digits : 0);
}
else
{
// more digits than the layout records: locate them
for (std::size_t i = 0; i < n.len; ++i)
{
if (first[i] == '.')
{
dot = i;
}
else if (first[i] == 'e' || first[i] == 'E')
{
mantissa_end = i;
break;
}
}
return FloatType{};
}
return convert_float<FloatType>(first, last, dot, mantissa_end);
}
@@ -93,16 +126,20 @@ NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char
}
if (p != e)
{
// [eE][+-]digits; huge exponents saturate (the parser rejected overflow)
// [eE][+-]digits; huge exponents saturate (the parser rejected
// overflow). The token is not read beyond e, and the digits are taken
// as unsigned, so that a token that is not well-formed (a damaged
// image loaded with image_check::bounds) yields a wrong value, but no
// overflow.
++p;
const bool exp_negative = *p == '-';
p += (*p == '-' || *p == '+') ? 1 : 0;
const bool exp_negative = p != e && *p == '-';
p += (p != e && (*p == '-' || *p == '+')) ? 1 : 0;
std::int64_t exp_value = 0;
for (; p != e; ++p)
{
if (exp_value < 0x10000000)
{
exp_value = (exp_value * 10) + (*p - '0');
exp_value = (exp_value * 10) + static_cast<unsigned char>(*p - '0');
}
}
q += exp_negative ? -exp_value : exp_value;
include/nlohmann/detail/view/serializer.hpp
+15 -5
View File
@@ -317,7 +317,9 @@ class view_serializer
m_out.put('"');
}
/// as serializer::dump_escaped() for valid UTF-8 (the view has no other)
/// as serializer::dump_escaped(); strings of a document are valid UTF-8,
/// except in a damaged image loaded with image_check::bounds, for which
/// this throws what basic_json::dump() throws for the string
template<bool EnsureAscii>
void write_escaped(const unsigned char* s, std::size_t n)
{
@@ -341,12 +343,13 @@ class view_serializer
}
std::uint32_t codepoint = s[i];
std::size_t len = 1;
if (codepoint >= 0xC0)
if (codepoint >= 0x80)
{
len = 2;
if (codepoint >= 0xE0)
len = validate_one_utf8(s + i, n - i);
if (NLOHMANN_VIEW_UNLIKELY(len == 0))
{
len = codepoint >= 0xF0 ? 4 : 3;
invalid_utf8(s, n);
return;
}
codepoint &= 0xFFu >> (len + 1);
for (std::size_t k = 1; k < len; ++k)
@@ -359,6 +362,13 @@ class view_serializer
}
}
/// throw what basic_json::dump() throws for a string that is not valid UTF-8
NLOHMANN_VIEW_NOINLINE static void invalid_utf8(const unsigned char* s, std::size_t n)
{
const string_t dumped = BasicJsonType(string_t(reinterpret_cast<const char*>(s), n)).dump(); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
static_cast<void>(dumped);
}
template<bool EnsureAscii>
void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
{
include/nlohmann/json_view.hpp
+63 -6
View File
@@ -25,7 +25,7 @@
#define INCLUDE_NLOHMANN_JSON_VIEW_HPP_
#include <cstddef> // size_t
#include <cstdint> // uint32_t
#include <cstdint> // uint8_t, uint32_t
#include <cstring> // memcpy, strlen
#include <iterator> // distance, input_iterator_tag, iterator_traits
#include <map> // map
@@ -53,6 +53,7 @@
#include <nlohmann/detail/view/edit.hpp>
#include <nlohmann/detail/view/edit_storage.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/image.hpp>
#include <nlohmann/detail/view/input.hpp>
#include <nlohmann/detail/view/iterator.hpp>
#include <nlohmann/detail/view/lookup.hpp>
@@ -934,7 +935,7 @@ class basic_json_document
/// whether the document holds its own copy of the text
bool owns_source() const noexcept
{
return m_data && !m_data->owned.empty() && m_data->src == m_data->owned.data();
return m_data && ((!m_data->owned.empty() && m_data->src == m_data->owned.data()) || !m_data->owned_image.empty());
}
/// number of index nodes (values plus object keys)
@@ -943,7 +944,7 @@ class basic_json_document
return m_data ? m_data->tape_size : 0;
}
/// bytes held by the document (index, decoded strings, owned text)
/// bytes held by the document (index, decoded strings, owned text or image)
std::size_t memory_usage() const noexcept
{
if (!m_data)
@@ -952,7 +953,7 @@ class basic_json_document
}
return sizeof(document_data) + (m_data->inline_cap * sizeof(detail::view::node))
+ (m_data->tape != m_data->inline_tape ? m_data->tape_cap * sizeof(detail::view::node) : 0)
+ m_data->arena.capacity() + m_data->owned.capacity()
+ m_data->arena.capacity() + m_data->owned.capacity() + m_data->owned_image.capacity()
+ (m_data->indexes.capacity() * sizeof(document_data::object_index)) + (m_data->index_slots.capacity() * sizeof(std::uint32_t))
+ (m_data->large_objects.capacity() * sizeof(std::uint32_t))
+ (m_data->edits != nullptr ? m_data->edits->bytes : 0);
@@ -972,8 +973,10 @@ class basic_json_document
// allocate everything first, so that an exception leaves the document
// unchanged
// (the decoded strings of a loaded image stay in the image)
const bool arena_in_use = d.base[1] == d.arena.data();
const bool shrink_arena = d.arena.capacity() > d.arena.size();
std::string arena(shrink_arena ? d.arena : std::string());
std::string arena(shrink_arena && arena_in_use ? d.arena : std::string());
// (edits link to the nodes of the index, which then stays in place)
const bool shrink_tape = d.tape != d.inline_tape && d.tape_size != d.tape_cap && d.edits == nullptr;
const bool into_header = d.tape_size <= d.inline_cap;
@@ -989,10 +992,62 @@ class basic_json_document
if (shrink_arena)
{
d.arena.swap(arena);
d.base[1] = d.arena.data();
if (arena_in_use)
{
d.base[1] = d.arena.data();
}
}
}
////////////
// images //
////////////
/// how load() checks an image (full, bounds, or none)
using image_check = detail::view::image_check;
/// The document as an image that load() reads without parsing: the node
/// index, the text, and the decoded strings. An edited document is
/// written in its current state (floats that are not finite become null,
/// as in dump()).
std::vector<std::uint8_t> save() const
{
if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
{
detail::view::throw_type_error(320, "cannot save a discarded json_document");
}
return detail::view::save_image(*m_data);
}
/// Read an image written by save(). The image is borrowed: it must stay
/// alive and unchanged while the document is used.
NLOHMANN_VIEW_NODISCARD
static basic_json_document load(const std::uint8_t* image, std::size_t size, const image_check check = image_check::full)
{
basic_json_document d;
d.ensure_data(nullptr, 0);
detail::view::load_image(*d.m_data, image, size, check);
return d;
}
/// read an image (borrowed)
NLOHMANN_VIEW_NODISCARD
static basic_json_document load(const std::vector<std::uint8_t>& image, const image_check check = image_check::full)
{
return load(image.data(), image.size(), check);
}
/// read an image and keep it (no copy)
NLOHMANN_VIEW_NODISCARD
static basic_json_document load(std::vector<std::uint8_t>&& image, const image_check check = image_check::full)
{
basic_json_document d;
d.ensure_data(nullptr, 0);
d.m_data->owned_image = std::move(image);
detail::view::load_image(*d.m_data, d.m_data->owned_image.data(), d.m_data->owned_image.size(), check);
return d;
}
///////////
// edits //
///////////
@@ -1176,6 +1231,7 @@ class basic_json_document
{
d.owned.clear();
}
d.owned_image.clear();
d.src = src;
d.size = size;
d.tape_size = 0;
@@ -1200,6 +1256,7 @@ class basic_json_document
{
d.base[0] = d.src;
d.base[1] = d.arena.data();
d.arena_size = d.arena.size();
detail::view::build_object_indexes(d);
d.discarded = false;
return;