Compare commits

..
Author SHA1 Message Date
Niels Lohmann b0a4218e38 Report the same error position for bulk number runs as for byte-wise input
For contiguous input, the CBOR and MessagePack readers read the
scalars of an array in one loop, and the UBJSON/BJData readers the
numbers of an optimized array. These loops passed a value on before
they advanced the position and the last byte. With a number_float_t
narrower than the value (for example float), passing the value on
reports out_of_range.406, and SAX parse_error() then got a different
position and last token than for the same bytes read through a
non-contiguous adapter.

Advance before passing the value on in the CBOR and MessagePack loops.
The last byte is the head byte, as get_number() does not change it;
the MessagePack loop used the last byte of the value. In the typed
UBJSON/BJData loop, update the position per value only where passing
it on can report an error, which is decided at compile time and never
the case for the default number types, and do not change the last byte,
as reading the values one by one does not.

Instruction counts of SAX and DOM parsing of arrays of one million
numbers: CBOR -1 to -4 %, MessagePack -2 to -10 %, UBJSON/BJData typed
arrays -0.8 to +0.6 % (clang, -O2).

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-11-16 07:41:29 +01:00
9 changed files with 275 additions and 267 deletions

No files matched your search

@@ -100,8 +100,7 @@ points apply to every edit:
[`root()`](root.md). New values (and the element sequences of an edited array/object) go to storage owned by the
document, allocated on demand.
- **A view keeps referring to the same value.** After [`set`](set.md) replaces the value a view refers to, that view
sees the new value; a view of a value that a later edit replaces or drops keeps showing what it last held. Such a
view can still be edited: the edit changes only that detached value, never anything reachable from `root()`. An edit
sees the new value; a view of a value that a later edit replaces or drops keeps showing what it last held. An edit
of an array or object, however, **invalidates the iterators taken over it** (its members may now live in a
different sequence), and a string obtained with [`get_string()`](../basic_json_view/get_string.md) stays valid even
as further edits happen (earlier buffers of edited text are kept alive, not overwritten).
@@ -164,9 +164,7 @@ general.
The same switch happens, for the same reason, when overload 1. replaces a multi-node array/object value with a
scalar: the *parent's* element sequence is what has to switch to links, not `target` itself, because the parent
originally stepped over `target`'s whole subtree by its node count, which no longer applies once `target` is a
one-node scalar. This also holds when `target` is no longer part of the document (an edit erased or replaced it, or
a value that contains it): if the container that `target` was in still uses its parsed layout, it switches to links
(otherwise nothing steps over `target` any more), and only the dropped values change.
one-node scalar.
## Examples
+72 -43
View File
@@ -1927,6 +1927,21 @@ class binary_reader
return result;
}
/*!
@brief move past a value of @a size bytes, starting with @a head, that a
bulk run reads, as get() and get_number() would
Called before the value is passed on, so that an error reported while
passing it on (see @ref emit_float) has the position and the last byte
that reading the value byte by byte gives.
*/
void bulk_advance(const std::size_t size, const unsigned char head)
{
ia.bulk_skip(size);
chars_read += size;
current = head;
}
/*!
@brief read the integers, floats, booleans, and nulls that follow in a
definite-length array, without the per-element bookkeeping of
@@ -1952,71 +1967,70 @@ class binary_reader
{
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const unsigned char head = data[0];
std::size_t size = 0;
bool accepted = false;
switch (head)
{
case 0x18:
size = 2;
bulk_advance(2, head);
accepted = emit_unsigned(data[1]);
break;
case 0x19:
size = 3;
bulk_advance(3, head);
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
break;
case 0x1A:
size = 5;
bulk_advance(5, head);
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
break;
case 0x1B:
size = 9;
bulk_advance(9, head);
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
break;
case 0x38:
size = 2;
bulk_advance(2, head);
accepted = emit_cbor_negative_integer(data[1]);
break;
case 0x39:
size = 3;
bulk_advance(3, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint16_t>(data + 1));
break;
case 0x3A:
size = 5;
bulk_advance(5, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint32_t>(data + 1));
break;
case 0x3B:
size = 9;
bulk_advance(9, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint64_t>(data + 1));
break;
case 0xF4:
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(false);
break;
case 0xF5:
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(true);
break;
case 0xF6:
size = 1;
bulk_advance(1, head);
accepted = sax->null();
break;
case 0xFA:
size = 5;
bulk_advance(5, head);
accepted = emit_float(load_big_endian<float>(data + 1));
break;
case 0xFB:
size = 9;
bulk_advance(9, head);
accepted = emit_float(load_big_endian<double>(data + 1));
break;
default:
if (head <= 0x17)
{
size = 1;
bulk_advance(1, head);
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
}
else if (head >= 0x20 && head <= 0x37)
{
size = 1;
bulk_advance(1, head);
accepted = sax->number_integer(static_cast<std::int8_t>(0x20 - 1 - head));
}
else
@@ -2026,10 +2040,6 @@ class binary_reader
}
break;
}
// as if read by get() and get_number(): current is the head byte
ia.bulk_skip(size);
chars_read += size;
current = head;
--remaining;
if (JSON_HEDLEY_UNLIKELY(!accepted))
{
@@ -2867,73 +2877,72 @@ class binary_reader
{
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const unsigned char head = data[0];
std::size_t size = 0;
bool accepted = false;
switch (head)
{
case 0xC0: // nil
size = 1;
bulk_advance(1, head);
accepted = sax->null();
break;
case 0xC2: // false
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(false);
break;
case 0xC3: // true
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(true);
break;
case 0xCA: // float 32
size = 5;
bulk_advance(5, head);
accepted = emit_float(load_big_endian<float>(data + 1));
break;
case 0xCB: // float 64
size = 9;
bulk_advance(9, head);
accepted = emit_float(load_big_endian<double>(data + 1));
break;
case 0xCC: // uint 8
size = 2;
bulk_advance(2, head);
accepted = emit_unsigned(data[1]);
break;
case 0xCD: // uint 16
size = 3;
bulk_advance(3, head);
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
break;
case 0xCE: // uint 32
size = 5;
bulk_advance(5, head);
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
break;
case 0xCF: // uint 64
size = 9;
bulk_advance(9, head);
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
break;
case 0xD0: // int 8
size = 2;
bulk_advance(2, head);
accepted = emit_signed(static_cast<std::int8_t>(data[1]));
break;
case 0xD1: // int 16
size = 3;
bulk_advance(3, head);
accepted = emit_signed(load_big_endian<std::int16_t>(data + 1));
break;
case 0xD2: // int 32
size = 5;
bulk_advance(5, head);
accepted = emit_signed(load_big_endian<std::int32_t>(data + 1));
break;
case 0xD3: // int 64
size = 9;
bulk_advance(9, head);
accepted = emit_signed(load_big_endian<std::int64_t>(data + 1));
break;
default:
if (head <= 0x7F)
{
// positive fixint
size = 1;
bulk_advance(1, head);
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
}
else if (head >= 0xE0)
{
// negative fixint
size = 1;
bulk_advance(1, head);
accepted = sax->number_integer(static_cast<std::int8_t>(head));
}
else
@@ -2943,10 +2952,6 @@ class binary_reader
}
break;
}
// as if read by get() and get_number(): current is the last byte
ia.bulk_skip(size);
chars_read += size;
current = data[size - 1];
--remaining;
if (JSON_HEDLEY_UNLIKELY(!accepted))
{
@@ -3850,6 +3855,7 @@ class binary_reader
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
// UBJSON stores numbers big-endian, BJData little-endian
const bool swap = is_little_endian != (input_format == input_format_t::bjdata);
const std::size_t start = chars_read;
std::size_t read = 0;
bool accepted = true;
while (read < count && accepted)
@@ -3861,16 +3867,39 @@ class binary_reader
byte_swap(number);
}
++read;
// where passing the value on can report an error (see
// emit_float), the position is that after the value, as if it
// was read by get_number()
set_chars_read(start + (read * size), std::integral_constant<bool, may_overflow_number_float<NumberType>()> {});
accepted = emit_ubjson_number(number);
}
// as if read by get_number(): current is the last byte read
// get_number() does not change current
ia.bulk_skip(read * size);
chars_read += read * size;
current = data[(read * size) - 1];
chars_read = start + (read * size);
remaining -= read;
return accepted;
}
/*!
@brief whether a value of type @a NumberType can be finite and still
overflow number_float_t, which @ref emit_float reports as an error
False for the default number types, so that the loop in @ref
parse_ubjson_typed_run need not track the position per value.
*/
template<typename NumberType>
static constexpr bool may_overflow_number_float() noexcept
{
return static_cast<long double>((std::numeric_limits<number_float_t>::max)()) < static_cast<long double>((std::numeric_limits<NumberType>::max)());
}
void set_chars_read(const std::size_t position, std::true_type /*track*/) noexcept
{
chars_read = position;
}
void set_chars_read(const std::size_t /*position*/, std::false_type /*track*/) const noexcept {}
template<typename NumberType, enable_if_t<std::is_floating_point<NumberType>::value, int> = 0>
bool emit_ubjson_number(const NumberType number)
{
+2 -15
View File
@@ -384,22 +384,9 @@ class editor
// for the container is linear in the size of the document, so
// links (which are marked in the slot) avoid it.
node* const p = parent_known ? parent : find_parent(m_doc, slot);
if (p != nullptr)
if (p != nullptr && ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0))
{
if ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0)
{
block_of(m_doc, p, 0);
}
}
else
{
// the slot is no longer part of the document, but the
// (dropped) container it is in may still step over it
node* const q = find_layout_parent(m_doc, slot);
if (q != nullptr)
{
block_of(m_doc, q, 0);
}
block_of(m_doc, p, 0);
}
}
*slot = e.scalar;
+1 -38
View File
@@ -194,9 +194,7 @@ inline node* block_of(document_data& d, node* n, std::size_t extra)
h->len = n->len;
h->next = static_cast<std::uint32_t>(used);
node* o = h + 1;
// (the bound on o keeps the copy inside the block even if the elements
// disagreed with the element count)
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n), *const full = h + used; c != e && o != full;)
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n); c != e;)
{
if (object)
{
@@ -278,41 +276,6 @@ inline node* find_parent(const document_data& d, const node* target)
}
}
/// The container whose contiguous layout (in the parsed index, or in a new
/// value) steps over `target`, also when an edit dropped the container or a
/// value that encloses it; nullptr if there is none, or if the container no
/// longer walks that layout (its elements moved). An edit never gives a node a
/// larger extent than it was parsed or encoded with (a scalar is one node, an
/// assigned array/object keeps the extent of the slot), so the containers whose
/// extent covers `target` are its original ancestors: the nearest one before it
/// is its original parent. The root of a new value that is the element sequence
/// of another container is walked by that container (which find_parent() finds
/// while it still uses the sequence), not by itself.
inline node* find_layout_parent(const document_data& d, const node* target)
{
const std::less<const node*> lt{};
const node* lo = d.nodes;
if (lt(target, lo) || !lt(target, d.nodes + d.node_count))
{
auto it = d.edits->regions.upper_bound(target);
if (it == d.edits->regions.begin())
{
return nullptr; // LCOV_EXCL_LINE (an array/object with elements is in the index or a new value)
}
--it;
lo = it->second != nullptr ? it->first + 1 : it->first;
}
for (const node* c = target; c != lo;)
{
--c;
if (is_container(*c) && lt(target, c + c->next))
{
return (c->flags & node_flags::moved) == 0 ? const_cast<node*>(c) : nullptr; // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
}
}
return nullptr;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
+72 -43
View File
@@ -20605,6 +20605,21 @@ class binary_reader
return result;
}
/*!
@brief move past a value of @a size bytes, starting with @a head, that a
bulk run reads, as get() and get_number() would
Called before the value is passed on, so that an error reported while
passing it on (see @ref emit_float) has the position and the last byte
that reading the value byte by byte gives.
*/
void bulk_advance(const std::size_t size, const unsigned char head)
{
ia.bulk_skip(size);
chars_read += size;
current = head;
}
/*!
@brief read the integers, floats, booleans, and nulls that follow in a
definite-length array, without the per-element bookkeeping of
@@ -20630,71 +20645,70 @@ class binary_reader
{
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const unsigned char head = data[0];
std::size_t size = 0;
bool accepted = false;
switch (head)
{
case 0x18:
size = 2;
bulk_advance(2, head);
accepted = emit_unsigned(data[1]);
break;
case 0x19:
size = 3;
bulk_advance(3, head);
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
break;
case 0x1A:
size = 5;
bulk_advance(5, head);
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
break;
case 0x1B:
size = 9;
bulk_advance(9, head);
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
break;
case 0x38:
size = 2;
bulk_advance(2, head);
accepted = emit_cbor_negative_integer(data[1]);
break;
case 0x39:
size = 3;
bulk_advance(3, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint16_t>(data + 1));
break;
case 0x3A:
size = 5;
bulk_advance(5, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint32_t>(data + 1));
break;
case 0x3B:
size = 9;
bulk_advance(9, head);
accepted = emit_cbor_negative_integer(load_big_endian<std::uint64_t>(data + 1));
break;
case 0xF4:
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(false);
break;
case 0xF5:
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(true);
break;
case 0xF6:
size = 1;
bulk_advance(1, head);
accepted = sax->null();
break;
case 0xFA:
size = 5;
bulk_advance(5, head);
accepted = emit_float(load_big_endian<float>(data + 1));
break;
case 0xFB:
size = 9;
bulk_advance(9, head);
accepted = emit_float(load_big_endian<double>(data + 1));
break;
default:
if (head <= 0x17)
{
size = 1;
bulk_advance(1, head);
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
}
else if (head >= 0x20 && head <= 0x37)
{
size = 1;
bulk_advance(1, head);
accepted = sax->number_integer(static_cast<std::int8_t>(0x20 - 1 - head));
}
else
@@ -20704,10 +20718,6 @@ class binary_reader
}
break;
}
// as if read by get() and get_number(): current is the head byte
ia.bulk_skip(size);
chars_read += size;
current = head;
--remaining;
if (JSON_HEDLEY_UNLIKELY(!accepted))
{
@@ -21545,73 +21555,72 @@ class binary_reader
{
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const unsigned char head = data[0];
std::size_t size = 0;
bool accepted = false;
switch (head)
{
case 0xC0: // nil
size = 1;
bulk_advance(1, head);
accepted = sax->null();
break;
case 0xC2: // false
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(false);
break;
case 0xC3: // true
size = 1;
bulk_advance(1, head);
accepted = sax->boolean(true);
break;
case 0xCA: // float 32
size = 5;
bulk_advance(5, head);
accepted = emit_float(load_big_endian<float>(data + 1));
break;
case 0xCB: // float 64
size = 9;
bulk_advance(9, head);
accepted = emit_float(load_big_endian<double>(data + 1));
break;
case 0xCC: // uint 8
size = 2;
bulk_advance(2, head);
accepted = emit_unsigned(data[1]);
break;
case 0xCD: // uint 16
size = 3;
bulk_advance(3, head);
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
break;
case 0xCE: // uint 32
size = 5;
bulk_advance(5, head);
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
break;
case 0xCF: // uint 64
size = 9;
bulk_advance(9, head);
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
break;
case 0xD0: // int 8
size = 2;
bulk_advance(2, head);
accepted = emit_signed(static_cast<std::int8_t>(data[1]));
break;
case 0xD1: // int 16
size = 3;
bulk_advance(3, head);
accepted = emit_signed(load_big_endian<std::int16_t>(data + 1));
break;
case 0xD2: // int 32
size = 5;
bulk_advance(5, head);
accepted = emit_signed(load_big_endian<std::int32_t>(data + 1));
break;
case 0xD3: // int 64
size = 9;
bulk_advance(9, head);
accepted = emit_signed(load_big_endian<std::int64_t>(data + 1));
break;
default:
if (head <= 0x7F)
{
// positive fixint
size = 1;
bulk_advance(1, head);
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
}
else if (head >= 0xE0)
{
// negative fixint
size = 1;
bulk_advance(1, head);
accepted = sax->number_integer(static_cast<std::int8_t>(head));
}
else
@@ -21621,10 +21630,6 @@ class binary_reader
}
break;
}
// as if read by get() and get_number(): current is the last byte
ia.bulk_skip(size);
chars_read += size;
current = data[size - 1];
--remaining;
if (JSON_HEDLEY_UNLIKELY(!accepted))
{
@@ -22528,6 +22533,7 @@ class binary_reader
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
// UBJSON stores numbers big-endian, BJData little-endian
const bool swap = is_little_endian != (input_format == input_format_t::bjdata);
const std::size_t start = chars_read;
std::size_t read = 0;
bool accepted = true;
while (read < count && accepted)
@@ -22539,16 +22545,39 @@ class binary_reader
byte_swap(number);
}
++read;
// where passing the value on can report an error (see
// emit_float), the position is that after the value, as if it
// was read by get_number()
set_chars_read(start + (read * size), std::integral_constant<bool, may_overflow_number_float<NumberType>()> {});
accepted = emit_ubjson_number(number);
}
// as if read by get_number(): current is the last byte read
// get_number() does not change current
ia.bulk_skip(read * size);
chars_read += read * size;
current = data[(read * size) - 1];
chars_read = start + (read * size);
remaining -= read;
return accepted;
}
/*!
@brief whether a value of type @a NumberType can be finite and still
overflow number_float_t, which @ref emit_float reports as an error
False for the default number types, so that the loop in @ref
parse_ubjson_typed_run need not track the position per value.
*/
template<typename NumberType>
static constexpr bool may_overflow_number_float() noexcept
{
return static_cast<long double>((std::numeric_limits<number_float_t>::max)()) < static_cast<long double>((std::numeric_limits<NumberType>::max)());
}
void set_chars_read(const std::size_t position, std::true_type /*track*/) noexcept
{
chars_read = position;
}
void set_chars_read(const std::size_t /*position*/, std::false_type /*track*/) const noexcept {}
template<typename NumberType, enable_if_t<std::is_floating_point<NumberType>::value, int> = 0>
bool emit_ubjson_number(const NumberType number)
{
+3 -53
View File
@@ -5564,9 +5564,7 @@ inline node* block_of(document_data& d, node* n, std::size_t extra)
h->len = n->len;
h->next = static_cast<std::uint32_t>(used);
node* o = h + 1;
// (the bound on o keeps the copy inside the block even if the elements
// disagreed with the element count)
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n), *const full = h + used; c != e && o != full;)
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n); c != e;)
{
if (object)
{
@@ -5648,41 +5646,6 @@ inline node* find_parent(const document_data& d, const node* target)
}
}
/// The container whose contiguous layout (in the parsed index, or in a new
/// value) steps over `target`, also when an edit dropped the container or a
/// value that encloses it; nullptr if there is none, or if the container no
/// longer walks that layout (its elements moved). An edit never gives a node a
/// larger extent than it was parsed or encoded with (a scalar is one node, an
/// assigned array/object keeps the extent of the slot), so the containers whose
/// extent covers `target` are its original ancestors: the nearest one before it
/// is its original parent. The root of a new value that is the element sequence
/// of another container is walked by that container (which find_parent() finds
/// while it still uses the sequence), not by itself.
inline node* find_layout_parent(const document_data& d, const node* target)
{
const std::less<const node*> lt{};
const node* lo = d.nodes;
if (lt(target, lo) || !lt(target, d.nodes + d.node_count))
{
auto it = d.edits->regions.upper_bound(target);
if (it == d.edits->regions.begin())
{
return nullptr; // LCOV_EXCL_LINE (an array/object with elements is in the index or a new value)
}
--it;
lo = it->second != nullptr ? it->first + 1 : it->first;
}
for (const node* c = target; c != lo;)
{
--c;
if (is_container(*c) && lt(target, c + c->next))
{
return (c->flags & node_flags::moved) == 0 ? const_cast<node*>(c) : nullptr; // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
}
}
return nullptr;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
@@ -6559,22 +6522,9 @@ class editor
// for the container is linear in the size of the document, so
// links (which are marked in the slot) avoid it.
node* const p = parent_known ? parent : find_parent(m_doc, slot);
if (p != nullptr)
if (p != nullptr && ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0))
{
if ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0)
{
block_of(m_doc, p, 0);
}
}
else
{
// the slot is no longer part of the document, but the
// (dropped) container it is in may still step over it
node* const q = find_layout_parent(m_doc, slot);
if (q != nullptr)
{
block_of(m_doc, q, 0);
}
block_of(m_doc, p, 0);
}
}
*slot = e.scalar;
+123
View File
@@ -14,6 +14,7 @@ using nlohmann::json;
#include <cmath>
#include <fstream>
#include <limits>
#include <list>
#include <map>
#include <string>
#include <vector>
@@ -367,3 +368,125 @@ TEST_CASE("Binary formats with narrow number types")
CHECK(format.decode(format.encode(json(1e300)), false).is_discarded());
}
}
namespace
{
// records the SAX events of narrow_json, including the arguments of parse_error
struct narrow_event_recorder
{
using number_integer_t = narrow_json::number_integer_t;
using number_unsigned_t = narrow_json::number_unsigned_t;
using number_float_t = narrow_json::number_float_t;
using string_t = narrow_json::string_t;
using binary_t = narrow_json::binary_t;
bool null()
{
events.emplace_back("null");
return true;
}
bool boolean(bool val)
{
events.emplace_back(val ? "true" : "false");
return true;
}
bool number_integer(number_integer_t val)
{
events.push_back(std::to_string(val));
return true;
}
bool number_unsigned(number_unsigned_t val)
{
events.push_back(std::to_string(val));
return true;
}
bool number_float(number_float_t val, const string_t& /*unused*/)
{
events.push_back(std::to_string(val));
return true;
}
bool string(string_t& val)
{
events.push_back(val);
return true;
}
bool binary(binary_t& /*unused*/)
{
events.emplace_back("binary");
return true;
}
bool start_object(std::size_t /*unused*/)
{
events.emplace_back("{");
return true;
}
bool key(string_t& val)
{
events.push_back(val);
return true;
}
bool end_object()
{
events.emplace_back("}");
return true;
}
bool start_array(std::size_t /*unused*/)
{
events.emplace_back("[");
return true;
}
bool end_array()
{
events.emplace_back("]");
return true;
}
bool parse_error(std::size_t position, const std::string& last_token, const nlohmann::detail::exception& ex)
{
events.push_back("parse_error(" + std::to_string(position) + ", " + last_token + ", " + ex.what() + ")");
return false;
}
std::vector<std::string> events {}; // NOLINT(readability-redundant-member-init)
};
} // namespace
TEST_CASE("Binary formats with narrow number types from contiguous and non-contiguous input")
{
// contiguous input reads runs of numbers in one loop; a number that
// overflows number_float_t must be reported with the same position and
// last byte as when the input is read byte by byte
const json values = {1, 70000, -70000, 1.5, 2.5, 1e300, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5};
const json doubles = {1.5, 2.5, 3.5, 1e300, 4.5, 5.5, 6.5, 7.5, 8.5};
struct binary_input
{
const char* name;
json::input_format_t format;
bytes data;
};
const std::vector<binary_input> inputs =
{
{"CBOR", json::input_format_t::cbor, json::to_cbor(values)},
{"CBOR doubles", json::input_format_t::cbor, json::to_cbor(doubles)},
{"MessagePack", json::input_format_t::msgpack, json::to_msgpack(values)},
{"MessagePack doubles", json::input_format_t::msgpack, json::to_msgpack(doubles)},
{"UBJSON", json::input_format_t::ubjson, json::to_ubjson(values, true)},
{"UBJSON typed doubles", json::input_format_t::ubjson, json::to_ubjson(doubles, true, true)},
{"BJData", json::input_format_t::bjdata, json::to_bjdata(values, true)},
{"BJData typed doubles", json::input_format_t::bjdata, json::to_bjdata(doubles, true, true)},
};
for (const auto& input : inputs)
{
const std::string name = input.name;
CAPTURE(name)
const std::list<std::uint8_t> bytewise(input.data.begin(), input.data.end());
narrow_event_recorder from_contiguous;
narrow_event_recorder from_bytewise;
CHECK_FALSE(narrow_json::sax_parse(input.data, &from_contiguous, input.format));
CHECK_FALSE(narrow_json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, input.format));
CHECK(from_contiguous.events == from_bytewise.events);
REQUIRE(!from_contiguous.events.empty());
CHECK(from_contiguous.events.back().find("out_of_range.406") != std::string::npos);
}
}
-70
View File
@@ -589,76 +589,6 @@ TEST_CASE("json_view edits: a container that was added is replaced by a scalar")
CHECK(d.root().materialize() == json::parse(R"({"a":[1,6,{"k":"s"}]})"));
}
TEST_CASE("json_view edits: a scalar replaces an array or object that is no longer part of the document")
{
// the dropped container that the array/object is in still steps over its
// parsed extent: that container switches to links first, as a live one does
SECTION("members of an erased object")
{
json_editable_document d = json_editable_document::parse(R"({"p": {"a": [1, [2]], "b": 3, "e": []}, "q": 0})");
const json_editable_view p = d.root()["p"];
const json_editable_view a = p["a"];
d.erase(d.root(), "p");
d.set(a[1], 5);
CHECK(p.dump() == R"({"a":[1,5],"b":3,"e":[]})");
d.set(a, 5);
CHECK(p.size() == 3);
CHECK(p.dump() == R"({"a":5,"b":3,"e":[]})");
d.push_back(p["e"], 6);
CHECK(p.dump() == R"({"a":5,"b":3,"e":[6]})");
CHECK(d.root().dump() == R"({"q":0})");
}
SECTION("an array whose elements moved")
{
json_editable_document d = json_editable_document::parse(R"({"p": {"a": [1, 2], "b": 3}, "q": 0})");
const json_editable_view p = d.root()["p"];
const json_editable_view a = p["a"];
d.erase(d.root(), "p");
d.push_back(a, 4); // (the extent of a stays)
d.set(a, 5);
CHECK(p.dump() == R"({"a":5,"b":3})");
CHECK(d.root().dump() == R"({"q":0})");
}
SECTION("an element of an erased array, which grows afterwards")
{
json_editable_document d = json_editable_document::parse(R"({"p": [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], "q": 0})");
const json_editable_view p = d.root()["p"];
d.erase(d.root(), "p");
d.set(p[0], 5);
d.push_back(p, 1);
CHECK(p.dump() == "[5,1]");
CHECK(d.root().dump() == R"({"q":0})");
}
SECTION("values in an erased new value")
{
json_editable_document d = json_editable_document::parse("[0]");
const json_editable_view x = d.push_back(d.root(), json::parse("[[[1, 2]], 3]"));
const json_editable_view y = x[0];
d.erase(d.root(), 1);
d.set(y[0], 5);
CHECK(x.dump() == "[[5],3]");
d.set(y, 5);
CHECK(x.dump() == "[5,3]");
CHECK(d.root().dump() == "[0]");
}
SECTION("values in the elements that an array had before it was replaced")
{
json_editable_document d = json_editable_document::parse("[0]");
d.set(d.root()[0], json::parse("[[[1, 2]]]"));
const json_editable_view y = d.root()[0][0];
d.set(d.root()[0], json::array({3}));
d.set(y[0], 5);
CHECK(y.dump() == "[5]");
d.set(y, 5);
CHECK(y.dump() == "5");
CHECK(d.root().dump() == "[[3]]");
}
}
#if !defined(JSON_NOEXCEPTION)
TEST_CASE("json_view edits: the size of a text arena")
{