mirror of
https://github.com/nlohmann/json.git
synced 2026-10-01 12:10:32 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Niels Lohmann
|
11e75a5428 | ||
|
Niels Lohmann
|
e400780533 |
@@ -0,0 +1,53 @@
|
||||
name: "Cancel runs of closed pull requests"
|
||||
|
||||
# The concurrency groups of the other workflows cancel superseded runs when a
|
||||
# pull request gets new commits, but nothing stops the runs of its last commit
|
||||
# once the pull request is merged or closed. They then keep the runners busy
|
||||
# for hours while the queue of the open pull requests waits.
|
||||
#
|
||||
# pull_request_target is needed to get a token that can cancel runs for pull
|
||||
# requests from forks. This is safe because the workflow never checks out or
|
||||
# runs code from the pull request; it only calls the API.
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [closed]
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.run_id }}
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
cancel:
|
||||
permissions:
|
||||
actions: write
|
||||
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
- name: Cancel unfinished runs of the pull request's head commit
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
GH_REPO: ${{ github.repository }}
|
||||
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
|
||||
SELF: ${{ github.run_id }}
|
||||
# only runs triggered by the pull request: when a branch is pushed to
|
||||
# develop directly, its push runs share the head commit
|
||||
run: |
|
||||
gh api --paginate "repos/$GH_REPO/actions/runs?head_sha=$HEAD_SHA&per_page=100" \
|
||||
--jq ".workflow_runs[]
|
||||
| select(.status != \"completed\" and .id != $SELF)
|
||||
| select(.event == \"pull_request\" or .event == \"pull_request_target\")
|
||||
| \"\(.id) \(.name)\"" |
|
||||
while read -r id name; do
|
||||
echo "Cancelling run $id ($name)"
|
||||
# a run may finish between listing and cancelling; that is not an error
|
||||
gh run cancel "$id" || true
|
||||
done
|
||||
@@ -2,16 +2,23 @@ name: "Check amalgamation"
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
# also check develop itself: a PR can be merged before its own run of this
|
||||
# workflow completes (e.g. while it is still queued), leaving single_include
|
||||
# stale on develop without any failing check
|
||||
push:
|
||||
branches:
|
||||
- develop
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
|
||||
cancel-in-progress: true
|
||||
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
save:
|
||||
if: github.event_name == 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
@@ -43,11 +50,11 @@ jobs:
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
- name: Checkout pull request
|
||||
- name: Checkout pull request or pushed commit
|
||||
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
path: main
|
||||
ref: ${{ github.event.pull_request.head.sha }}
|
||||
ref: ${{ github.event.pull_request.head.sha || github.sha }}
|
||||
persist-credentials: false
|
||||
|
||||
- name: Checkout tools
|
||||
|
||||
@@ -10,7 +10,8 @@ permissions:
|
||||
|
||||
jobs:
|
||||
comment:
|
||||
if: ${{ github.event.workflow_run.conclusion == 'failure' }}
|
||||
# push runs on develop have no PR to comment on (and no "pr" artifact)
|
||||
if: ${{ github.event.workflow_run.conclusion == 'failure' && github.event.workflow_run.event == 'pull_request' }}
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
@@ -25,12 +25,10 @@ and `ensure_ascii` parameters.
|
||||
result consists of ASCII characters only.
|
||||
|
||||
`error_handler` (in)
|
||||
: how to react on decoding errors; there are four possible values (see [`error_handler_t`](error_handler_t.md):
|
||||
: how to react on decoding errors; there are three possible values (see [`error_handler_t`](error_handler_t.md):
|
||||
`strict` (throws an exception in case a decoding error occurs; default), `replace` (replace invalid UTF-8 sequences
|
||||
with U+FFFD), `ignore` (ignore invalid UTF-8 sequences during serialization; all valid bytes are copied to the
|
||||
output unchanged, and invalid bytes are dropped), and `keep` (write the ill-formed bytes to the output as is,
|
||||
without escaping them, even if `ensure_ascii` is `#!cpp true`; the result is then not valid UTF-8, but equals the
|
||||
input bytes exactly, and well-formed characters around the ill-formed bytes are still escaped as usual)).
|
||||
with U+FFFD), and `ignore` (ignore invalid UTF-8 sequences during serialization; all valid bytes are copied to the
|
||||
output unchanged, and invalid bytes are dropped)).
|
||||
|
||||
## Return value
|
||||
|
||||
@@ -96,4 +94,3 @@ Binary values are serialized as an object containing two keys:
|
||||
- Indentation character `indent_char`, option `ensure_ascii` and exceptions added in version 3.0.0.
|
||||
- Error handlers added in version 3.4.0.
|
||||
- Serialization of binary values added in version 3.8.0.
|
||||
- Error handler `keep` added in version 3.13.0.
|
||||
|
||||
@@ -4,30 +4,15 @@
|
||||
enum class error_handler_t {
|
||||
strict,
|
||||
replace,
|
||||
ignore,
|
||||
keep
|
||||
ignore
|
||||
};
|
||||
```
|
||||
|
||||
This enumeration is used to choose how to treat ill-formed UTF-8 in a string value or object key:
|
||||
|
||||
- [`dump`](dump.md) uses it while serializing a `basic_json` value to text.
|
||||
- [`to_cbor`](to_cbor.md), [`to_ubjson`](to_ubjson.md), [`to_bjdata`](to_bjdata.md), and [`to_bson`](to_bson.md) use it
|
||||
while serializing a `basic_json` value to that binary format; none of CBOR, UBJSON, BJData, or BSON requires a
|
||||
decoder to reject ill-formed UTF-8, so by default (`strict`) the library checks on write instead. `to_msgpack` and
|
||||
`to_bon8` do not take this parameter: MessagePack's specification explicitly allows a string to contain ill-formed
|
||||
UTF-8, so `to_msgpack` always passes it through, while BON8 always validates, since UTF-8 lead bytes are structural
|
||||
to that format.
|
||||
- [`from_cbor`](from_cbor.md), [`from_msgpack`](from_msgpack.md), [`from_ubjson`](from_ubjson.md),
|
||||
[`from_bjdata`](from_bjdata.md), and [`from_bson`](from_bson.md) use it while parsing that binary format, to decide
|
||||
whether to check a string value or object key for well-formed UTF-8 at all; by default (`keep`) they do not, as no
|
||||
binary reader did before this parameter was added. `from_bon8` does not take this parameter, for the same reason
|
||||
`to_bon8` does not.
|
||||
|
||||
Four values are differentiated:
|
||||
This enumeration is used in the [`dump`](dump.md) function to choose how to treat decoding errors while serializing a
|
||||
`basic_json` value. Three values are differentiated:
|
||||
|
||||
strict
|
||||
: throw a `type_error`/`parse_error` exception in case of invalid UTF-8
|
||||
: throw a `type_error` exception in case of invalid UTF-8
|
||||
|
||||
replace
|
||||
: replace invalid UTF-8 sequences with U+FFFD (� REPLACEMENT CHARACTER)
|
||||
@@ -35,12 +20,6 @@ replace
|
||||
ignore
|
||||
: ignore invalid UTF-8 sequences; all valid bytes are copied to the output unchanged, and invalid bytes are dropped
|
||||
|
||||
keep
|
||||
: keep invalid UTF-8 sequences unchanged; only meaningful for the binary formats mentioned above, since [`dump`]
|
||||
(dump.md) itself must produce text, and `keep` there writes the ill-formed bytes to the output as is, so the
|
||||
result is then not valid UTF-8 (but still equals the input bytes exactly, including around any well-formed
|
||||
characters, which are still escaped as usual)
|
||||
|
||||
## Examples
|
||||
|
||||
??? example
|
||||
@@ -61,5 +40,3 @@ keep
|
||||
## Version history
|
||||
|
||||
- Added in version 3.4.0.
|
||||
- Added `keep`, and made this enumeration apply to the binary readers and writers in addition to `dump`, in version
|
||||
3.13.0.
|
||||
|
||||
@@ -5,14 +5,12 @@
|
||||
template<typename InputType>
|
||||
static basic_json from_bjdata(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
// (2)
|
||||
template<typename IteratorType, typename SentinelType = IteratorType>
|
||||
static basic_json from_bjdata(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
```
|
||||
|
||||
Deserializes a given input to a JSON value using the BJData (Binary JData) serialization format.
|
||||
@@ -60,12 +58,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`allow_exceptions` (in)
|
||||
: whether to throw exceptions in case of a parse error (optional, `#!cpp true` by default)
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string value or object key that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
BJData does not require a decoder to reject ill-formed UTF-8, so checking is opt-in: the default, `keep`, does not
|
||||
check at all, as every binary reader did before this parameter was added; `strict` checks and throws;
|
||||
`replace`/`ignore` sanitize the string the same way [`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
deserialized JSON value; in case of a parse error and `allow_exceptions` set to `#!cpp false`, the return value will be
|
||||
@@ -81,7 +73,7 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
the end of the file was not reached when `strict` was set to true
|
||||
- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if a parse error occurs
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a string could not be parsed
|
||||
successfully, or if a string value or object key is not valid UTF-8 and `error_handler` is `strict`
|
||||
successfully
|
||||
- Throws [out_of_range.408](../../home/exceptions.md#jsonexceptionout_of_range408) if the size of an optimized container
|
||||
or n-dimensional array cannot be represented by `std::size_t`
|
||||
|
||||
@@ -119,4 +111,3 @@ Linear in the size of the input.
|
||||
- Added in version 3.11.0.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
@@ -5,14 +5,12 @@
|
||||
template<typename InputType>
|
||||
static basic_json from_bson(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
// (2)
|
||||
template<typename IteratorType, typename SentinelType = IteratorType>
|
||||
static basic_json from_bson(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
```
|
||||
|
||||
Deserializes a given input to a JSON value using the BSON (Binary JSON) serialization format.
|
||||
@@ -60,12 +58,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`allow_exceptions` (in)
|
||||
: whether to throw exceptions in case of a parse error (optional, `#!cpp true` by default)
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string value or object key that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
BSON does not require a decoder to reject ill-formed UTF-8, so checking is opt-in: the default, `keep`, does not
|
||||
check at all, as every binary reader did before this parameter was added; `strict` checks and throws;
|
||||
`replace`/`ignore` sanitize the string the same way [`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
deserialized JSON value; in case of a parse error and `allow_exceptions` set to `#!cpp false`, the return value will be
|
||||
@@ -83,8 +75,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
invalid string or byte array length)
|
||||
- Throws [`parse_error.114`](../../home/exceptions.md#jsonexceptionparse_error114) if an unsupported BSON record type is
|
||||
encountered
|
||||
- Throws [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) if a string value or object key is
|
||||
not valid UTF-8 and `error_handler` is `strict`
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -121,7 +111,6 @@ Linear in the size of the input.
|
||||
- Added in version 3.4.0.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -6,16 +6,14 @@ template<typename InputType>
|
||||
static basic_json from_cbor(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error);
|
||||
|
||||
// (2)
|
||||
template<typename IteratorType, typename SentinelType = IteratorType>
|
||||
static basic_json from_cbor(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error);
|
||||
```
|
||||
|
||||
Deserializes a given input to a JSON value using the CBOR (Concise Binary Object Representation) serialization format.
|
||||
@@ -67,12 +65,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
: how to treat CBOR tags (optional, `error` by default); see [`cbor_tag_handler_t`](cbor_tag_handler_t.md) for more
|
||||
information
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string value or object key that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
CBOR does not require a decoder to reject ill-formed UTF-8, so checking is opt-in: the default, `keep`, does not
|
||||
check at all, as every binary reader did before this parameter was added; `strict` checks and throws;
|
||||
`replace`/`ignore` sanitize the string the same way [`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
deserialized JSON value; in case of a parse error and `allow_exceptions` set to `#!cpp false`, the return value will be
|
||||
@@ -88,9 +80,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
the end of the file was not reached when `strict` was set to true
|
||||
- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if unsupported features from CBOR were
|
||||
used in the given input or if the input is not valid CBOR
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of
|
||||
other types are not supported, as JSON object keys are always strings), or if a string value or object key is not
|
||||
valid UTF-8 and `error_handler` is `strict`
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of other
|
||||
types are not supported, as JSON object keys are always strings) or a string is malformed
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -130,7 +121,6 @@ Linear in the size of the input.
|
||||
- Added `tag_handler` parameter in version 3.9.0.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -5,14 +5,12 @@
|
||||
template<typename InputType>
|
||||
static basic_json from_msgpack(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
// (2)
|
||||
template<typename IteratorType, typename SentinelType = IteratorType>
|
||||
static basic_json from_msgpack(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
```
|
||||
|
||||
Deserializes a given input to a JSON value using the MessagePack serialization format.
|
||||
@@ -60,12 +58,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`allow_exceptions` (in)
|
||||
: whether to throw exceptions in case of a parse error (optional, `#!cpp true` by default)
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string value or object key that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
MessagePack's specification explicitly allows ill-formed UTF-8, so checking is opt-in: the default, `keep`, does
|
||||
not check at all, as every binary reader did before this parameter was added; `strict` checks and throws;
|
||||
`replace`/`ignore` sanitize the string the same way [`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
deserialized JSON value; in case of a parse error and `allow_exceptions` set to `#!cpp false`, the return value will be
|
||||
@@ -81,9 +73,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
the end of the file was not reached when `strict` was set to true
|
||||
- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if unsupported features from
|
||||
MessagePack were used in the given input or if the input is not valid MessagePack
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of
|
||||
other types are not supported, as JSON object keys are always strings), or if a string value or object key is not
|
||||
valid UTF-8 and `error_handler` is `strict`
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of other
|
||||
types are not supported, as JSON object keys are always strings) or a string is malformed
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -122,7 +113,6 @@ Linear in the size of the input.
|
||||
- Added `allow_exceptions` parameter in version 3.2.0.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -5,14 +5,12 @@
|
||||
template<typename InputType>
|
||||
static basic_json from_ubjson(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
// (2)
|
||||
template<typename IteratorType, typename SentinelType = IteratorType>
|
||||
static basic_json from_ubjson(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep);
|
||||
const bool allow_exceptions = true);
|
||||
```
|
||||
|
||||
Deserializes a given input to a JSON value using the UBJSON (Universal Binary JSON) serialization format.
|
||||
@@ -60,12 +58,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`allow_exceptions` (in)
|
||||
: whether to throw exceptions in case of a parse error (optional, `#!cpp true` by default)
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string value or object key that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
UBJSON does not require a decoder to reject ill-formed UTF-8, so checking is opt-in: the default, `keep`, does not
|
||||
check at all, as every binary reader did before this parameter was added; `strict` checks and throws;
|
||||
`replace`/`ignore` sanitize the string the same way [`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
deserialized JSON value; in case of a parse error and `allow_exceptions` set to `#!cpp false`, the return value will be
|
||||
@@ -81,7 +73,7 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
the end of the file was not reached when `strict` was set to true
|
||||
- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if a parse error occurs
|
||||
- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a string could not be parsed
|
||||
successfully, or if a string value or object key is not valid UTF-8 and `error_handler` is `strict`
|
||||
successfully
|
||||
- Throws [out_of_range.408](../../home/exceptions.md#jsonexceptionout_of_range408) if the size of an optimized container
|
||||
or n-dimensional array cannot be represented by `std::size_t`
|
||||
|
||||
@@ -120,7 +112,6 @@ Linear in the size of the input.
|
||||
- Added `allow_exceptions` parameter in version 3.2.0.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -5,18 +5,15 @@
|
||||
static std::vector<std::uint8_t> to_bjdata(const basic_json& j,
|
||||
const bool use_size = false,
|
||||
const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bjdata_version_t version = bjdata_version_t::draft2);
|
||||
|
||||
// (2)
|
||||
static void to_bjdata(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bjdata_version_t version = bjdata_version_t::draft2);
|
||||
static void to_bjdata(const basic_json& j, detail::output_adapter<char> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bjdata_version_t version = bjdata_version_t::draft2);
|
||||
```
|
||||
|
||||
Serializes a given JSON value `j` to a byte vector using the BJData (Binary JData) serialization format. BJData aims to
|
||||
@@ -46,12 +43,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
: which version of BJData to use (see note on "Binary values" on [BJData](../../features/binary_formats/bjdata.md));
|
||||
optional, `#!cpp bjdata_version_t::draft2` by default.
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string or object key in `j` that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
The default, `strict`, throws; `keep` writes the ill-formed bytes to the output as is, as every version of
|
||||
`to_bjdata` did before this parameter was added; `replace`/`ignore` sanitize it the same way
|
||||
[`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
1. BJData serialization as byte vector
|
||||
@@ -65,8 +56,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
|
||||
- Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
|
||||
is false.
|
||||
- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
|
||||
not valid UTF-8 and `error_handler` is `strict` (the default)
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -100,6 +89,4 @@ Linear in the size of the JSON value `j`.
|
||||
## Version history
|
||||
|
||||
- Added in version 3.11.0.
|
||||
- BJData version parameter (for draft3 binary encoding) added in version 3.12.0.
|
||||
- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
- BJData version parameter (for draft3 binary encoding) added in version 3.12.0.
|
||||
@@ -2,14 +2,11 @@
|
||||
|
||||
```cpp
|
||||
// (1)
|
||||
static std::vector<std::uint8_t> to_bson(const basic_json& j,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static std::vector<std::uint8_t> to_bson(const basic_json& j);
|
||||
|
||||
// (2)
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<char> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o);
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<char> o);
|
||||
```
|
||||
|
||||
BSON (Binary JSON) is a binary format in which zero or more ordered key/value pairs are stored as a single entity (a
|
||||
@@ -28,12 +25,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`o` (in)
|
||||
: output adapter to write serialization to
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string or object key in `j` that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
The default, `strict`, throws; `keep` writes the ill-formed bytes to the output as is, as every version of
|
||||
`to_bson` did before this parameter was added; `replace`/`ignore` sanitize it the same way
|
||||
[`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
1. BSON serialization as a byte vector
|
||||
@@ -55,8 +46,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
- Throws [`out_of_range.415`](../../home/exceptions.md#jsonexceptionout_of_range415) if the subtype of a binary value
|
||||
exceeds 255, the maximum of the BSON binary subtype; example:
|
||||
`"subtype 70000 is too large for the BSON binary subtype (max 255)"`
|
||||
- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key is
|
||||
not valid UTF-8 and `error_handler` is `strict` (the default)
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -93,6 +82,3 @@ pass before anything is written.
|
||||
- Added in version 3.4.0.
|
||||
- Linear in the size of `j`, and no longer limited by the call stack for deeply nested values, since version 3.13.0.
|
||||
- `out_of_range.415` is now detected before anything is written, like the other exceptions above, since version 3.13.0.
|
||||
- Throwing `type_error.316` for a string value or object key that is not valid UTF-8, detected before anything is
|
||||
written, added in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
@@ -2,14 +2,11 @@
|
||||
|
||||
```cpp
|
||||
// (1)
|
||||
static std::vector<std::uint8_t> to_cbor(const basic_json& j,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static std::vector<std::uint8_t> to_cbor(const basic_json& j);
|
||||
|
||||
// (2)
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<char> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o);
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<char> o);
|
||||
```
|
||||
|
||||
Serializes a given JSON value `j` to a byte vector using the CBOR (Concise Binary Object Representation) serialization
|
||||
@@ -29,12 +26,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
`o` (in)
|
||||
: output adapter to write serialization to
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string or object key in `j` that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
The default, `strict`, throws; `keep` writes the ill-formed bytes to the output as is, as every version of
|
||||
`to_cbor` did before this parameter was added; `replace`/`ignore` sanitize it the same way
|
||||
[`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
1. CBOR serialization as a byte vector
|
||||
@@ -44,11 +35,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
|
||||
Strong guarantee: if an exception is thrown, there are no changes in the JSON value.
|
||||
|
||||
## Exceptions
|
||||
|
||||
- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
|
||||
not valid UTF-8 and `error_handler` is `strict` (the default)
|
||||
|
||||
## Complexity
|
||||
|
||||
Linear in the size of the JSON value `j`.
|
||||
@@ -82,5 +68,3 @@ Linear in the size of the JSON value `j`.
|
||||
|
||||
- Added in version 2.0.9.
|
||||
- Compact representation of floating-point numbers added in version 3.8.0.
|
||||
- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
@@ -4,16 +4,13 @@
|
||||
// (1)
|
||||
static std::vector<std::uint8_t> to_ubjson(const basic_json& j,
|
||||
const bool use_size = false,
|
||||
const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bool use_type = false);
|
||||
|
||||
// (2)
|
||||
static void to_ubjson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bool use_size = false, const bool use_type = false);
|
||||
static void to_ubjson(const basic_json& j, detail::output_adapter<char> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict);
|
||||
const bool use_size = false, const bool use_type = false);
|
||||
```
|
||||
|
||||
Serializes a given JSON value `j` to a byte vector using the UBJSON (Universal Binary JSON) serialization format. UBJSON
|
||||
@@ -39,12 +36,6 @@ The exact mapping and its limitations are described on a [dedicated page](../../
|
||||
: whether to add type annotations to container types (must be combined with `#!cpp use_size = true`); optional,
|
||||
`#!cpp false` by default.
|
||||
|
||||
`error_handler` (in)
|
||||
: how to treat a string or object key in `j` that is not valid UTF-8; see [`error_handler_t`](error_handler_t.md).
|
||||
The default, `strict`, throws; `keep` writes the ill-formed bytes to the output as is, as every version of
|
||||
`to_ubjson` did before this parameter was added; `replace`/`ignore` sanitize it the same way
|
||||
[`dump`](dump.md) would
|
||||
|
||||
## Return value
|
||||
|
||||
1. UBJSON serialization as a byte vector
|
||||
@@ -58,8 +49,6 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
|
||||
- Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
|
||||
is false.
|
||||
- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
|
||||
not valid UTF-8 and `error_handler` is `strict` (the default)
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -93,5 +82,3 @@ Linear in the size of the JSON value `j`.
|
||||
## Version history
|
||||
|
||||
- Added in version 3.1.0.
|
||||
- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
|
||||
@@ -20,6 +20,5 @@ int main()
|
||||
<< j_invalid.dump(-1, ' ', false, json::error_handler_t::replace)
|
||||
<< "\nstring with ignored invalid characters: "
|
||||
<< j_invalid.dump(-1, ' ', false, json::error_handler_t::ignore)
|
||||
<< "\nstring with the invalid byte kept as is (" << j_invalid.dump(-1, ' ', false, json::error_handler_t::keep).size()
|
||||
<< " bytes, not valid UTF-8 itself)\n";
|
||||
<< '\n';
|
||||
}
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9
|
||||
string with replaced invalid characters: "ä�ü"
|
||||
string with ignored invalid characters: "äü"
|
||||
string with the invalid byte kept as is (7 bytes, not valid UTF-8 itself)
|
||||
|
||||
@@ -63,12 +63,6 @@ The library uses the following mapping from JSON values types to BJData types ac
|
||||
|
||||
- strings with more than 18446744073709551615 bytes, i.e., 2<sup>64</sup>-1 bytes (theoretical)
|
||||
|
||||
!!! warning "UTF-8 validation of string values and object keys"
|
||||
|
||||
BJData strings must use UTF-8 encoding. `to_bjdata()` validates the bytes of every string value and object key
|
||||
and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for ill-formed UTF-8, so a
|
||||
value with such a string cannot be serialized in the first place.
|
||||
|
||||
!!! info "Unused BJData markers"
|
||||
|
||||
The following markers are not used in the conversion:
|
||||
@@ -214,20 +208,6 @@ The library maps BJData types to JSON value types as follows:
|
||||
|
||||
The mapping is **complete** in the sense that any BJData value can be converted to a JSON value.
|
||||
|
||||
!!! warning "Ill-formed UTF-8 in string values and object keys"
|
||||
|
||||
BJData strings must use UTF-8 encoding, but checking it on read is opt-in: with the
|
||||
[`error_handler`](../../api/basic_json/from_bjdata.md) parameter left at `keep` (the default), `from_bjdata()`
|
||||
accepts a string value or object key whose bytes are not valid UTF-8 and hands them back unchanged. Passing
|
||||
`error_handler_t::strict` makes `from_bjdata()` check and throw
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) for ill-formed UTF-8, and
|
||||
`replace`/`ignore` sanitize the string instead of keeping it. However,
|
||||
[`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
|
||||
[`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for a value read with the default
|
||||
`keep` handler, unless an error handler is passed that replaces or ignores the ill-formed bytes. `to_bjdata()`'s
|
||||
own `error_handler` parameter defaults to `strict` (see above), so a value read this way cannot be written back
|
||||
to BJData unless a non-strict handler is passed there too.
|
||||
|
||||
!!! info "Round trips"
|
||||
|
||||
A value returned by [`from_bjdata`](../../api/basic_json/from_bjdata.md) can be serialized with
|
||||
|
||||
@@ -109,22 +109,14 @@ The library maps BSON record types to JSON value types as follows:
|
||||
If BSON input must be validated for strict specification compliance, validate it separately before passing it to
|
||||
`from_bson()`.
|
||||
|
||||
!!! warning "Ill-formed UTF-8 in string values"
|
||||
!!! warning "UTF-8 validation of string values"
|
||||
|
||||
The BSON specification requires `string` values (type `0x02`) to be valid UTF-8, but this is not required of a
|
||||
decoder, so checking is opt-in: with the [`error_handler`](../../api/basic_json/from_bson.md) parameter left at
|
||||
`keep` (the default), `from_bson()` accepts a `string` value whose bytes are not valid UTF-8 and hands them back
|
||||
unchanged. Passing `error_handler_t::strict` makes `from_bson()` check and throw
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) for ill-formed UTF-8, and
|
||||
`replace`/`ignore` sanitize the string instead of keeping it. However, [`dump()`](../../api/basic_json/dump.md)
|
||||
still requires valid UTF-8 and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316)
|
||||
for a value read with the default `keep` handler, unless an error handler is passed that replaces or ignores
|
||||
the ill-formed bytes. `to_bson()`'s own `error_handler` parameter defaults to `strict` and throws the same
|
||||
exception for a string value or element (key) name that is not valid UTF-8, so an object with such a key or
|
||||
value cannot be produced in the first place unless a non-strict handler is passed there, even though
|
||||
`from_bson()` would accept it from another source with the default `keep` handler. Element (key) names are
|
||||
never validated on read, since they are read byte-by-byte as a C string. `binary` values (type `0x05`) are
|
||||
unaffected, since they are not required to hold text.
|
||||
The BSON specification requires `string` values (type `0x02`) to be valid UTF-8. This library validates the
|
||||
bytes of every such string at decode time and rejects ill-formed UTF-8 with a
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with `allow_exceptions`
|
||||
set to `false`, a discarded value), rather than only failing later when the resulting value is dumped. Element
|
||||
(key) names and `binary` values (type `0x05`) are unaffected and are never validated, since they are read
|
||||
byte-by-byte as a C string, or are not required to hold text, respectively.
|
||||
|
||||
??? example
|
||||
|
||||
|
||||
@@ -189,21 +189,15 @@ The library maps CBOR types to JSON value types as follows:
|
||||
([RFC 8392](https://www.rfc-editor.org/rfc/rfc8392.html)), cannot be read with this library and need a
|
||||
general-purpose CBOR library instead.
|
||||
|
||||
!!! warning "Ill-formed UTF-8 in text strings"
|
||||
!!! warning "UTF-8 validation of text strings"
|
||||
|
||||
[RFC 8949, Section 3.1](https://www.rfc-editor.org/rfc/rfc8949.html#section-3.1) requires CBOR text strings
|
||||
(major type 3) to be valid UTF-8, but leaves it up to the decoder whether to enforce this, so checking is
|
||||
opt-in: with the [`error_handler`](../../api/basic_json/from_cbor.md) parameter left at `keep` (the default),
|
||||
`from_cbor()` accepts a text string (object keys included) whose bytes are not valid UTF-8 and hands them back
|
||||
unchanged. Passing `error_handler_t::strict` makes `from_cbor()` check and throw
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) for ill-formed UTF-8, and
|
||||
`replace`/`ignore` sanitize the string instead of keeping it. However, [`dump()`](../../api/basic_json/dump.md)
|
||||
still requires valid UTF-8 and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316)
|
||||
for a value read with the default `keep` handler, unless an error handler is passed that replaces or ignores
|
||||
the ill-formed bytes. `to_cbor()`'s own [`error_handler`](../../api/basic_json/to_cbor.md) parameter defaults
|
||||
to `strict` and throws the same exception for a string value or object key that is not valid UTF-8, so such a
|
||||
value cannot be written back to CBOR unless a non-strict handler is passed there too. Byte strings (major
|
||||
type 2) are unaffected, since they are not required to hold text.
|
||||
(major type 3) to be valid UTF-8. This library validates the bytes of every text string (object keys included) at
|
||||
decode time and rejects ill-formed UTF-8 with a
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with
|
||||
`allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting value is
|
||||
dumped. Byte strings (major type 2) are unaffected and are never validated, since they are not required to hold
|
||||
text.
|
||||
|
||||
!!! warning "Tagged items"
|
||||
|
||||
|
||||
@@ -153,21 +153,14 @@ The library maps MessagePack types to JSON value types as follows:
|
||||
This applies to the [SAX interface](../parsing/sax_interface.md) as well, as the key is read before it is passed
|
||||
on. Such input needs a general-purpose MessagePack library instead.
|
||||
|
||||
!!! warning "Ill-formed UTF-8 in string values"
|
||||
!!! warning "UTF-8 validation of string values"
|
||||
|
||||
The MessagePack specification explicitly allows a `str` value (`fixstr`, `str 8`, `str 16`, `str 32`) to contain
|
||||
a byte sequence that is not valid UTF-8, and expects a deserializer to hand the original bytes back unchanged.
|
||||
This library follows that by default: with its
|
||||
[`error_handler`](../../api/basic_json/from_msgpack.md) parameter left at `keep` (the default),
|
||||
`from_msgpack()` reads `str` bytes (object keys included) as-is, without validating them, so such a value
|
||||
round-trips through `from_msgpack(to_msgpack(j))` byte for byte. Passing `error_handler_t::strict` makes
|
||||
`from_msgpack()` check anyway and throw
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) for ill-formed UTF-8, and
|
||||
`replace`/`ignore` sanitize the string instead of keeping it. `to_msgpack()` itself has no `error_handler`
|
||||
parameter and always writes `str` bytes as-is, since the specification permits it. However,
|
||||
[`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
|
||||
[`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for a value read this way with the
|
||||
default `keep` handler, unless an error handler is passed that replaces or ignores the ill-formed bytes.
|
||||
The MessagePack specification requires `str` values (`fixstr`, `str 8`, `str 16`, `str 32`) to be valid UTF-8.
|
||||
This library validates the bytes of every such string (object keys included) at decode time and rejects
|
||||
ill-formed UTF-8 with a [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or,
|
||||
with `allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting
|
||||
value is dumped. `bin`/`ext`/`fixext` values are unaffected and are never validated, since they are not required
|
||||
to hold text.
|
||||
|
||||
??? example
|
||||
|
||||
|
||||
@@ -47,12 +47,6 @@ The library uses the following mapping from JSON values types to UBJSON types ac
|
||||
|
||||
- strings with more than 9223372036854775807 bytes (theoretical)
|
||||
|
||||
!!! warning "UTF-8 validation of string values and object keys"
|
||||
|
||||
UBJSON's required string encoding is UTF-8. `to_ubjson()` validates the bytes of every string value and object
|
||||
key and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for ill-formed UTF-8, so
|
||||
a value with such a string cannot be serialized in the first place.
|
||||
|
||||
!!! info "Unused UBJSON markers"
|
||||
|
||||
The following markers are not used in the conversion:
|
||||
@@ -126,20 +120,6 @@ The library maps UBJSON types to JSON value types as follows:
|
||||
|
||||
The mapping is **complete** in the sense that any UBJSON value can be converted to a JSON value.
|
||||
|
||||
!!! warning "Ill-formed UTF-8 in string values and object keys"
|
||||
|
||||
UBJSON's required string encoding is UTF-8, but checking it on read is opt-in: with the
|
||||
[`error_handler`](../../api/basic_json/from_ubjson.md) parameter left at `keep` (the default), `from_ubjson()`
|
||||
accepts a string value or object key whose bytes are not valid UTF-8 and hands them back unchanged. Passing
|
||||
`error_handler_t::strict` makes `from_ubjson()` check and throw
|
||||
[`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) for ill-formed UTF-8, and
|
||||
`replace`/`ignore` sanitize the string instead of keeping it. However,
|
||||
[`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
|
||||
[`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for a value read with the default
|
||||
`keep` handler, unless an error handler is passed that replaces or ignores the ill-formed bytes. `to_ubjson()`'s
|
||||
own `error_handler` parameter defaults to `strict` (see above), so a value read this way cannot be written back
|
||||
to UBJSON unless a non-strict handler is passed there too.
|
||||
|
||||
??? example
|
||||
|
||||
```cpp
|
||||
|
||||
@@ -341,10 +341,7 @@ An unexpected byte was read in a [binary format](../features/binary_formats/inde
|
||||
|
||||
A string could not be read from a [binary format](../features/binary_formats/index.md): either a value that is not a
|
||||
string was read where one was required (for instance as a map key), the string's length specification is invalid, or
|
||||
the string's bytes are not valid UTF-8 and the `error_handler` parameter of the corresponding `from_*` function is
|
||||
set to `strict`. By default (`error_handler_t::keep`), the bytes of a string are not checked for valid UTF-8 on read;
|
||||
see the ill-formed UTF-8 notes on the individual [binary format](../features/binary_formats/index.md) pages for how
|
||||
such a string is handled depending on `error_handler`.
|
||||
the string's bytes are not valid UTF-8.
|
||||
|
||||
CBOR and MessagePack allow map keys of any type, but JSON object keys are always strings. Maps with keys of any other
|
||||
type (for instance integers or `null`) are therefore not supported; see the notes on
|
||||
|
||||
@@ -31,7 +31,6 @@
|
||||
#include <nlohmann/detail/macro_scope.hpp>
|
||||
#include <nlohmann/detail/meta/is_sax.hpp>
|
||||
#include <nlohmann/detail/meta/type_traits.hpp>
|
||||
#include <nlohmann/detail/output/error_handler.hpp>
|
||||
#include <nlohmann/detail/string_concat.hpp>
|
||||
#include <nlohmann/detail/string_utils.hpp>
|
||||
#include <nlohmann/detail/value_t.hpp>
|
||||
@@ -109,16 +108,8 @@ class binary_reader
|
||||
@brief create a binary reader
|
||||
|
||||
@param[in] adapter input adapter to read from
|
||||
@param[in] format the binary format to parse
|
||||
@param[in] error_handler how to treat text strings and object keys that
|
||||
are not well-formed UTF-8; none of the supported formats
|
||||
requires a decoder to reject those, so the default is to
|
||||
@ref error_handler_t::keep them unchanged, as every binary
|
||||
reader did before this parameter existed
|
||||
*/
|
||||
explicit binary_reader(InputAdapterType&& adapter, const input_format_t format = input_format_t::json,
|
||||
const error_handler_t error_handler = error_handler_t::keep) noexcept
|
||||
: ia(std::move(adapter)), input_format(format), error_handler(error_handler)
|
||||
explicit binary_reader(InputAdapterType&& adapter, const input_format_t format = input_format_t::json) noexcept : ia(std::move(adapter)), input_format(format)
|
||||
{
|
||||
(void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
|
||||
}
|
||||
@@ -437,7 +428,7 @@ class binary_reader
|
||||
{
|
||||
if (get_bson_cstr_bulk(result, std::integral_constant<bool, bulk_scan> {}))
|
||||
{
|
||||
return check_string_utf8(result, "key");
|
||||
return true;
|
||||
}
|
||||
|
||||
auto out = std::back_inserter(result);
|
||||
@@ -450,7 +441,7 @@ class binary_reader
|
||||
}
|
||||
if (current == 0x00)
|
||||
{
|
||||
return check_string_utf8(result, "key");
|
||||
return true;
|
||||
}
|
||||
*out++ = static_cast<typename string_t::value_type>(current);
|
||||
}
|
||||
@@ -531,7 +522,7 @@ class binary_reader
|
||||
"string"), nullptr));
|
||||
}
|
||||
|
||||
return check_string_utf8(result, "string");
|
||||
return true;
|
||||
}
|
||||
|
||||
/*!
|
||||
@@ -1158,7 +1149,7 @@ class binary_reader
|
||||
|
||||
@return whether string creation completed
|
||||
*/
|
||||
bool get_cbor_string(string_t& result, const char* context = "string")
|
||||
bool get_cbor_string(string_t& result)
|
||||
{
|
||||
// number of indefinite-length strings that have been opened and not
|
||||
// closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
|
||||
@@ -1188,7 +1179,7 @@ class binary_reader
|
||||
{
|
||||
if (--open == 0)
|
||||
{
|
||||
return check_string_utf8(result, context);
|
||||
return true;
|
||||
}
|
||||
get();
|
||||
continue;
|
||||
@@ -1201,7 +1192,7 @@ class binary_reader
|
||||
|
||||
if (open == 0)
|
||||
{
|
||||
return check_string_utf8(result, context);
|
||||
return true;
|
||||
}
|
||||
|
||||
get();
|
||||
@@ -1225,7 +1216,7 @@ class binary_reader
|
||||
// EOF and major type 3 (text string) are left to get_cbor_string
|
||||
if (current == char_traits<char_type>::eof() || (static_cast<unsigned int>(current) & 0xE0u) == 0x60u)
|
||||
{
|
||||
return get_cbor_string(result, "key");
|
||||
return get_cbor_string(result);
|
||||
}
|
||||
|
||||
const char* found = nullptr;
|
||||
@@ -2013,7 +2004,7 @@ class binary_reader
|
||||
|
||||
@return whether string creation completed
|
||||
*/
|
||||
bool get_msgpack_string(string_t& result, const char* context = "string")
|
||||
bool get_msgpack_string(string_t& result)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::msgpack, "string")))
|
||||
{
|
||||
@@ -2056,25 +2047,25 @@ class binary_reader
|
||||
case 0xBE:
|
||||
case 0xBF:
|
||||
{
|
||||
return get_string(input_format_t::msgpack, static_cast<unsigned int>(current) & 0x1Fu, result) && check_string_utf8(result, context);
|
||||
return get_string(input_format_t::msgpack, static_cast<unsigned int>(current) & 0x1Fu, result);
|
||||
}
|
||||
|
||||
case 0xD9: // str 8
|
||||
{
|
||||
std::uint8_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
|
||||
}
|
||||
|
||||
case 0xDA: // str 16
|
||||
{
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
|
||||
}
|
||||
|
||||
case 0xDB: // str 32
|
||||
{
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
|
||||
}
|
||||
|
||||
default:
|
||||
@@ -2152,7 +2143,7 @@ class binary_reader
|
||||
// byte 0xC1 are left to get_msgpack_string
|
||||
if (current == char_traits<char_type>::eof())
|
||||
{
|
||||
return get_msgpack_string(result, "key");
|
||||
return get_msgpack_string(result);
|
||||
}
|
||||
if (current <= 0x7F || current >= 0xE0)
|
||||
{
|
||||
@@ -2168,7 +2159,7 @@ class binary_reader
|
||||
}
|
||||
else
|
||||
{
|
||||
return get_msgpack_string(result, "key");
|
||||
return get_msgpack_string(result);
|
||||
}
|
||||
break;
|
||||
}
|
||||
@@ -2414,7 +2405,7 @@ class binary_reader
|
||||
if (top.is_object)
|
||||
{
|
||||
key.clear();
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, true, "key") || !sax->key(key)))
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
@@ -2436,7 +2427,7 @@ class binary_reader
|
||||
if (top.is_object)
|
||||
{
|
||||
key.clear();
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, false, "key") || !sax->key(key)))
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, false) || !sax->key(key)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
@@ -2504,7 +2495,7 @@ class binary_reader
|
||||
|
||||
@return whether string creation completed
|
||||
*/
|
||||
bool get_ubjson_string(string_t& result, const bool get_char = true, const char* context = "string")
|
||||
bool get_ubjson_string(string_t& result, const bool get_char = true)
|
||||
{
|
||||
if (get_char)
|
||||
{
|
||||
@@ -2525,31 +2516,31 @@ class binary_reader
|
||||
case 'U':
|
||||
{
|
||||
std::uint8_t len{};
|
||||
return get_number(input_format, len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'i':
|
||||
{
|
||||
std::int8_t len{};
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'I':
|
||||
{
|
||||
std::int16_t len{};
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'l':
|
||||
{
|
||||
std::int32_t len{};
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'L':
|
||||
{
|
||||
std::int64_t len{};
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'u':
|
||||
@@ -2559,7 +2550,7 @@ class binary_reader
|
||||
break;
|
||||
}
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format, len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'm':
|
||||
@@ -2569,7 +2560,7 @@ class binary_reader
|
||||
break;
|
||||
}
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format, len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
case 'M':
|
||||
@@ -2579,7 +2570,7 @@ class binary_reader
|
||||
break;
|
||||
}
|
||||
std::uint64_t len{};
|
||||
return get_number(input_format, len) && get_string(input_format, len, result) && check_string_utf8(result, context);
|
||||
return get_number(input_format, len) && get_string(input_format, len, result);
|
||||
}
|
||||
|
||||
default:
|
||||
@@ -4040,50 +4031,27 @@ class binary_reader
|
||||
const NumberType len,
|
||||
string_t& result)
|
||||
{
|
||||
// Strings are taken as is by default: none of CBOR (RFC 8949 §3.1
|
||||
// leaves the choice to the decoder), MessagePack (whose spec
|
||||
// explicitly allows a str object to contain an invalid byte
|
||||
// sequence), UBJSON, BJData, or BSON requires a decoder to reject
|
||||
// ill-formed UTF-8. Checking (and, with @ref error_handler_t::strict,
|
||||
// rejecting, or with `replace`/`ignore`, sanitizing) is opt-in via
|
||||
// @ref error_handler, applied once the whole string (all chunks of
|
||||
// an indefinite-length CBOR string included) has been assembled, by
|
||||
// @ref check_string_utf8 at the call site.
|
||||
return get_bytes(format, len, "string", result);
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief validate a decoded text string (value or object key) against @ref error_handler
|
||||
|
||||
None of the binary formats requires a decoder to reject ill-formed UTF-8
|
||||
in a text string (see @ref get_string), so by default
|
||||
(@ref error_handler_t::keep) this does nothing. A stricter
|
||||
@ref error_handler opts into the same well-formedness check @ref
|
||||
serializer::dump_escaped_impl applies when dumping a string:
|
||||
@ref error_handler_t::strict rejects ill-formed input with
|
||||
parse_error.113 (honoring `allow_exceptions` via @a sax), while
|
||||
@ref error_handler_t::replace / @ref error_handler_t::ignore sanitize
|
||||
@a result in place, using the exact same rules.
|
||||
|
||||
@param[in,out] result the already assembled string to check
|
||||
@param[in] context further context information (for diagnostics)
|
||||
@return whether @a result is acceptable (always true for `keep`)
|
||||
*/
|
||||
bool check_string_utf8(string_t& result, const char* context)
|
||||
{
|
||||
if (error_handler == error_handler_t::keep || is_valid_utf8(result))
|
||||
// get_bytes() appends to result, and CBOR indefinite-length strings
|
||||
// collect all their chunks in the same result; validating only the
|
||||
// newly read bytes keeps the check linear in the input size
|
||||
const std::size_t old_size = result.size();
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_bytes(format, len, "string", result)))
|
||||
{
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
if (error_handler == error_handler_t::strict)
|
||||
// RFC 8949 (CBOR) §3.1 and the MessagePack/BSON/UBJSON specifications
|
||||
// all require text strings to be valid UTF-8; reject anything else
|
||||
// right here so malformed input is caught at decode time instead of
|
||||
// only surfacing later as a type_error.316 when the value is dumped
|
||||
// (which would defeat allow_exceptions=false / strict discarding).
|
||||
if (JSON_HEDLEY_UNLIKELY(!is_valid_utf8(result, old_size)))
|
||||
{
|
||||
auto last_token = get_token_string();
|
||||
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
|
||||
exception_message(input_format, "invalid string: ill-formed UTF-8 byte", context), nullptr));
|
||||
return sax->parse_error(chars_read, get_token_string(),
|
||||
parse_error::create(113, chars_read,
|
||||
exception_message(format, "invalid string: ill-formed UTF-8 byte", "string"), nullptr));
|
||||
}
|
||||
|
||||
result = sanitize_utf8(result, error_handler);
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -4258,9 +4226,6 @@ class binary_reader
|
||||
/// input format
|
||||
const input_format_t input_format = input_format_t::json;
|
||||
|
||||
/// how to treat text strings/object keys that are not well-formed UTF-8
|
||||
const error_handler_t error_handler = error_handler_t::keep;
|
||||
|
||||
/// the SAX parser
|
||||
json_sax_t* sax = nullptr;
|
||||
|
||||
|
||||
@@ -26,7 +26,6 @@
|
||||
#include <nlohmann/detail/input/binary_reader.hpp>
|
||||
#include <nlohmann/detail/input/string_scan.hpp>
|
||||
#include <nlohmann/detail/macro_scope.hpp>
|
||||
#include <nlohmann/detail/output/error_handler.hpp>
|
||||
#include <nlohmann/detail/output/output_adapters.hpp>
|
||||
#include <nlohmann/detail/string_concat.hpp>
|
||||
#include <nlohmann/detail/string_utils.hpp>
|
||||
@@ -94,12 +93,8 @@ class binary_writer
|
||||
@param[in] sink output sink to write to (a value-type sink such as
|
||||
output_vector_sink, or output_adapter_sink wrapping a
|
||||
type-erased output adapter)
|
||||
@param[in] error_handler_ how to treat a string value or object key that
|
||||
is not valid UTF-8 (CBOR, UBJSON, BJData, and BSON only; never
|
||||
consulted by @ref write_msgpack or @ref write_bon8)
|
||||
*/
|
||||
explicit binary_writer(OutputSinkType sink, const error_handler_t error_handler_ = error_handler_t::strict)
|
||||
: oa(std::move(sink)), error_handler(error_handler_)
|
||||
explicit binary_writer(OutputSinkType sink) : oa(std::move(sink))
|
||||
{}
|
||||
|
||||
/*!
|
||||
@@ -112,20 +107,14 @@ class binary_writer
|
||||
from one.
|
||||
|
||||
@param[in] adapter output adapter to write to
|
||||
@param[in] error_handler_ how to treat a string value or object key that
|
||||
is not valid UTF-8 (CBOR, UBJSON, BJData, and BSON only; never
|
||||
consulted by @ref write_msgpack or @ref write_bon8)
|
||||
*/
|
||||
template < typename SinkType = OutputSinkType,
|
||||
typename std::enable_if < std::is_constructible<SinkType, output_adapter_t<CharType>>::value, int >::type = 0 >
|
||||
explicit binary_writer(output_adapter_t<CharType> adapter, const error_handler_t error_handler_ = error_handler_t::strict)
|
||||
: oa(SinkType(std::move(adapter))), error_handler(error_handler_)
|
||||
explicit binary_writer(output_adapter_t<CharType> adapter) : oa(SinkType(std::move(adapter)))
|
||||
{}
|
||||
|
||||
/*!
|
||||
@param[in] j JSON value to serialize
|
||||
@throw type_error.316 if a string value or an object key is not valid
|
||||
UTF-8
|
||||
@throw type_error.317 if @a j is not an object
|
||||
*/
|
||||
void write_bson(const BasicJsonType& j)
|
||||
@@ -156,8 +145,6 @@ class binary_writer
|
||||
|
||||
/*!
|
||||
@param[in] j JSON value to serialize
|
||||
@throw type_error.316 if a string value or an object key is not valid
|
||||
UTF-8
|
||||
*/
|
||||
void write_cbor(const BasicJsonType& j)
|
||||
{
|
||||
@@ -224,16 +211,13 @@ class binary_writer
|
||||
|
||||
case value_t::string:
|
||||
{
|
||||
string_t storage;
|
||||
const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
|
||||
|
||||
// step 1: write control byte and the string length
|
||||
write_cbor_head(0x60, value.size());
|
||||
write_cbor_head(0x60, j.m_data.m_value.string->size());
|
||||
|
||||
// step 2: write the string
|
||||
oa.write_characters(
|
||||
reinterpret_cast<const CharType*>(value.data()),
|
||||
value.size());
|
||||
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
|
||||
j.m_data.m_value.string->size());
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -303,17 +287,6 @@ class binary_writer
|
||||
// step 2: write each element
|
||||
for (const auto& el : *j.m_data.m_value.object)
|
||||
{
|
||||
// el.first is checked here, against the object as
|
||||
// diagnostics context, because write_cbor(el.first)
|
||||
// converts it to a temporary basic_json that would be
|
||||
// used as the context instead; for error_handler_t::keep
|
||||
// and ::replace/::ignore the recursive write_cbor(el.first)
|
||||
// call below handles the key like any other string, so no
|
||||
// separate check is needed here for those
|
||||
if (error_handler == error_handler_t::strict)
|
||||
{
|
||||
check_utf8(el.first, j);
|
||||
}
|
||||
write_cbor(el.first);
|
||||
write_cbor(el.second);
|
||||
}
|
||||
@@ -656,8 +629,6 @@ class binary_writer
|
||||
@param[in] add_prefix whether prefixes need to be used for this value
|
||||
@param[in] use_bjdata whether write in BJData format, default is false
|
||||
@param[in] bjdata_version which BJData version to use, default is draft2
|
||||
@throw type_error.316 if a string value or an object key is not valid
|
||||
UTF-8
|
||||
*/
|
||||
void write_ubjson(const BasicJsonType& j, const bool use_count,
|
||||
const bool use_type, const bool add_prefix = true,
|
||||
@@ -707,17 +678,14 @@ class binary_writer
|
||||
|
||||
case value_t::string:
|
||||
{
|
||||
string_t storage;
|
||||
const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
|
||||
|
||||
if (add_prefix)
|
||||
{
|
||||
oa.write_character(to_char_type('S'));
|
||||
}
|
||||
write_number_with_ubjson_prefix(value.size(), true, use_bjdata);
|
||||
write_number_with_ubjson_prefix(j.m_data.m_value.string->size(), true, use_bjdata);
|
||||
oa.write_characters(
|
||||
reinterpret_cast<const CharType*>(value.data()),
|
||||
value.size());
|
||||
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
|
||||
j.m_data.m_value.string->size());
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -872,12 +840,10 @@ class binary_writer
|
||||
|
||||
for (const auto& el : *j.m_data.m_value.object)
|
||||
{
|
||||
string_t storage;
|
||||
const string_t& key = sanitize_utf8_for_write(el.first, j, storage);
|
||||
write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
|
||||
write_number_with_ubjson_prefix(el.first.size(), true, use_bjdata);
|
||||
oa.write_characters(
|
||||
reinterpret_cast<const CharType*>(key.data()),
|
||||
key.size());
|
||||
reinterpret_cast<const CharType*>(el.first.data()),
|
||||
el.first.size());
|
||||
write_ubjson(el.second, use_count, use_type, prefix_required, use_bjdata, bjdata_version);
|
||||
}
|
||||
|
||||
@@ -918,12 +884,8 @@ class binary_writer
|
||||
/*!
|
||||
@return The size of a BSON document entry header, including the id marker
|
||||
and the entry name size (and its null-terminator).
|
||||
@throw out_of_range.409 if @a name contains U+0000, before anything is
|
||||
written
|
||||
@throw type_error.316 if @a name is not valid UTF-8, before anything is
|
||||
written
|
||||
*/
|
||||
std::size_t calc_bson_entry_header_size(const string_t& name, const BasicJsonType& j)
|
||||
static std::size_t calc_bson_entry_header_size(const string_t& name, const BasicJsonType& j)
|
||||
{
|
||||
const auto it = name.find(static_cast<typename string_t::value_type>(0));
|
||||
if (JSON_HEDLEY_UNLIKELY(it != BasicJsonType::string_t::npos))
|
||||
@@ -931,10 +893,8 @@ class binary_writer
|
||||
JSON_THROW(out_of_range::create(409, concat("BSON key cannot contain code point U+0000 (at byte ", std::to_string(it), ")"), &j));
|
||||
}
|
||||
|
||||
string_t storage;
|
||||
const string_t& sanitized = sanitize_utf8_for_write(name, j, storage);
|
||||
|
||||
return /*id*/ 1ul + sanitized.size() + /*zero-terminator*/1u;
|
||||
static_cast<void>(j);
|
||||
return /*id*/ 1ul + name.size() + /*zero-terminator*/1u;
|
||||
}
|
||||
|
||||
/*!
|
||||
@@ -954,28 +914,14 @@ class binary_writer
|
||||
|
||||
/*!
|
||||
@brief Writes the given @a element_type and @a name to the output adapter
|
||||
|
||||
@a name has already been validated (and, for @ref error_handler_t::strict,
|
||||
found well-formed) by @ref calc_bson_entry_header_size during the earlier
|
||||
size pass, so only @ref error_handler_t::replace / @ref
|
||||
error_handler_t::ignore need to sanitize it again here, to actually write
|
||||
the bytes that size was computed from.
|
||||
*/
|
||||
void write_bson_entry_header(const string_t& name,
|
||||
const std::uint8_t element_type)
|
||||
{
|
||||
oa.write_character(to_char_type(element_type));
|
||||
|
||||
if (error_handler == error_handler_t::keep || error_handler == error_handler_t::strict || is_valid_utf8(name))
|
||||
{
|
||||
oa.write_characters(reinterpret_cast<const CharType*>(name.data()), name.size());
|
||||
}
|
||||
else
|
||||
{
|
||||
const string_t sanitized = sanitize_utf8(name, error_handler);
|
||||
oa.write_characters(reinterpret_cast<const CharType*>(sanitized.data()), sanitized.size());
|
||||
}
|
||||
|
||||
oa.write_characters(
|
||||
reinterpret_cast<const CharType*>(name.data()),
|
||||
name.size());
|
||||
// the terminating null byte is written explicitly rather than taken
|
||||
// from the buffer, so that string_t::data() need not be null-terminated
|
||||
oa.write_character(to_char_type(0x00));
|
||||
@@ -1003,50 +949,24 @@ class binary_writer
|
||||
|
||||
/*!
|
||||
@return The size of the BSON-encoded string in @a value
|
||||
@throw type_error.316 if @a value is not valid UTF-8, before anything is
|
||||
written
|
||||
|
||||
@note The UTF-8 check is skipped if @a value is already too long for the
|
||||
32-bit BSON length field (@ref to_bson_length rejects it later, once
|
||||
the size of the whole document is known); this also keeps the check
|
||||
from reading past a StringType that reports a size larger than what
|
||||
it actually holds.
|
||||
*/
|
||||
std::size_t calc_bson_string_size(const string_t& value, const BasicJsonType& j)
|
||||
static std::size_t calc_bson_string_size(const string_t& value)
|
||||
{
|
||||
if (JSON_HEDLEY_LIKELY(value_in_range_of<std::int32_t>(value.size())))
|
||||
{
|
||||
string_t storage;
|
||||
const string_t& sanitized = sanitize_utf8_for_write(value, j, storage);
|
||||
return sizeof(std::int32_t) + sanitized.size() + 1ul;
|
||||
}
|
||||
return sizeof(std::int32_t) + value.size() + 1ul;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief Writes a BSON element with key @a name and string value @a value
|
||||
|
||||
@a value has already been validated (and, for @ref error_handler_t::strict,
|
||||
found well-formed) by @ref calc_bson_string_size during the earlier size
|
||||
pass, so only @ref error_handler_t::replace / @ref error_handler_t::ignore
|
||||
need to sanitize it again here, to actually write the bytes that size was
|
||||
computed from.
|
||||
*/
|
||||
void write_bson_string(const string_t& name,
|
||||
const string_t& value)
|
||||
{
|
||||
write_bson_entry_header(name, 0x02);
|
||||
|
||||
const bool sanitize = error_handler != error_handler_t::keep
|
||||
&& error_handler != error_handler_t::strict
|
||||
&& !is_valid_utf8(value);
|
||||
const string_t sanitized = sanitize ? sanitize_utf8(value, error_handler) : string_t{};
|
||||
const string_t& written = sanitize ? sanitized : value;
|
||||
|
||||
write_number<std::int32_t>(to_bson_length(written.size() + 1ul), true);
|
||||
write_number<std::int32_t>(to_bson_length(value.size() + 1ul), true);
|
||||
oa.write_characters(
|
||||
reinterpret_cast<const CharType*>(written.data()),
|
||||
written.size());
|
||||
reinterpret_cast<const CharType*>(value.data()),
|
||||
value.size());
|
||||
// the terminating null byte is written explicitly rather than taken
|
||||
// from the buffer, so that string_t::data() need not be null-terminated
|
||||
oa.write_character(to_char_type(0x00));
|
||||
@@ -1160,10 +1080,8 @@ class binary_writer
|
||||
is neither an object nor an array
|
||||
@throw out_of_range.415 if @a j is binary with a subtype that does not fit
|
||||
into a byte, before anything is written
|
||||
@throw type_error.316 if @a j is a string that is not valid UTF-8, before
|
||||
anything is written
|
||||
*/
|
||||
std::size_t calc_bson_value_size(const BasicJsonType& j)
|
||||
static std::size_t calc_bson_value_size(const BasicJsonType& j)
|
||||
{
|
||||
switch (j.type())
|
||||
{
|
||||
@@ -1183,7 +1101,7 @@ class binary_writer
|
||||
return calc_bson_unsigned_size(j.m_data.m_value.number_unsigned);
|
||||
|
||||
case value_t::string:
|
||||
return calc_bson_string_size(*j.m_data.m_value.string, j);
|
||||
return calc_bson_string_size(*j.m_data.m_value.string);
|
||||
|
||||
case value_t::null:
|
||||
return 0ul;
|
||||
@@ -1296,10 +1214,8 @@ class binary_writer
|
||||
written
|
||||
@throw out_of_range.415 if a binary value's subtype does not fit into a
|
||||
byte, before anything is written
|
||||
@throw type_error.316 if a string value or a key is not valid UTF-8,
|
||||
before anything is written
|
||||
*/
|
||||
std::size_t calc_bson_sizes(const BasicJsonType& document, std::vector<std::size_t>& nested_sizes)
|
||||
static std::size_t calc_bson_sizes(const BasicJsonType& document, std::vector<std::size_t>& nested_sizes)
|
||||
{
|
||||
// the object or array whose entries are being sized, and the ones it
|
||||
// is in; nothing is allocated unless the document nests
|
||||
@@ -2176,7 +2092,7 @@ class binary_writer
|
||||
*/
|
||||
void write_bon8_string(const string_t& s, bool& string_open, const BasicJsonType& context)
|
||||
{
|
||||
check_utf8(s, context);
|
||||
check_bon8_utf8(s, context);
|
||||
|
||||
// a string that follows another string terminates it
|
||||
if (string_open)
|
||||
@@ -2206,7 +2122,7 @@ class binary_writer
|
||||
@throw type_error.316 if @a s is not valid UTF-8; the message names the
|
||||
first byte of the first invalid or incomplete sequence
|
||||
*/
|
||||
static void check_utf8(const string_t& s, const BasicJsonType& context)
|
||||
static void check_bon8_utf8(const string_t& s, const BasicJsonType& context)
|
||||
{
|
||||
static_cast<void>(context); // only used when exceptions are enabled
|
||||
const auto* data = reinterpret_cast<const unsigned char*>(s.data());
|
||||
@@ -2217,59 +2133,6 @@ class binary_writer
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief return @a s as it should be written, honoring @ref error_handler
|
||||
|
||||
Used by @ref write_cbor, @ref write_ubjson (and so @ref write_bjdata), and
|
||||
the BSON writing functions for string values and object keys; never by
|
||||
@ref write_msgpack or @ref write_bon8, which do not take an @ref
|
||||
error_handler (MessagePack's spec allows a str object to contain
|
||||
ill-formed UTF-8, and BON8 always validates, since UTF-8 lead bytes are
|
||||
structural there).
|
||||
|
||||
- @ref error_handler_t::keep: @a s is returned unchanged, without even
|
||||
checking it (the behavior of release 3.12.0 and earlier).
|
||||
- @ref error_handler_t::strict: @ref check_utf8 is called, which throws
|
||||
type_error.316 if @a s is not valid UTF-8.
|
||||
- @ref error_handler_t::replace / @ref error_handler_t::ignore: @a s is
|
||||
sanitized into @a storage with exactly the rules @ref
|
||||
serializer::dump_escaped_impl uses, so that parsing what @ref
|
||||
basic_json::dump produces for the same string and the same handler
|
||||
yields the same result.
|
||||
|
||||
Well-formed input is never copied: this returns a reference to @a s
|
||||
itself in every case but a sanitized `replace`/`ignore` one, so @a
|
||||
storage must outlive the returned reference only then.
|
||||
|
||||
@param[in] s the string (value or object key) to write
|
||||
@param[in] context the value @a s belongs to (for diagnostics)
|
||||
@param[out] storage backing storage for a sanitized copy
|
||||
|
||||
@return a reference to @a s, or to @a storage once it holds a sanitized copy
|
||||
*/
|
||||
const string_t& sanitize_utf8_for_write(const string_t& s, const BasicJsonType& context, string_t& storage) const
|
||||
{
|
||||
switch (error_handler)
|
||||
{
|
||||
case error_handler_t::keep:
|
||||
return s;
|
||||
|
||||
case error_handler_t::strict:
|
||||
check_utf8(s, context);
|
||||
return s;
|
||||
|
||||
case error_handler_t::replace:
|
||||
case error_handler_t::ignore:
|
||||
default:
|
||||
if (is_valid_utf8(s))
|
||||
{
|
||||
return s;
|
||||
}
|
||||
storage = sanitize_utf8(s, error_handler);
|
||||
return storage;
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief write an integer in the shortest encoding
|
||||
|
||||
@@ -2598,10 +2461,6 @@ class binary_writer
|
||||
|
||||
/// the output
|
||||
OutputSinkType oa;
|
||||
|
||||
/// how to treat a string value or object key that is not valid UTF-8
|
||||
/// (CBOR, UBJSON, BJData, and BSON only)
|
||||
const error_handler_t error_handler = error_handler_t::strict;
|
||||
};
|
||||
|
||||
} // namespace detail
|
||||
|
||||
@@ -1,38 +0,0 @@
|
||||
// __ _____ _____ _____
|
||||
// __| | __| | | | 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 <nlohmann/detail/abi_macros.hpp>
|
||||
|
||||
NLOHMANN_JSON_NAMESPACE_BEGIN
|
||||
namespace detail
|
||||
{
|
||||
|
||||
/// how to treat decoding errors
|
||||
///
|
||||
/// @ref basic_json::dump uses this to decide what to do with ill-formed
|
||||
/// UTF-8 while escaping a string, and the binary writers (@ref
|
||||
/// basic_json::to_cbor, @ref basic_json::to_ubjson, @ref
|
||||
/// basic_json::to_bjdata, @ref basic_json::to_bson) use it the same way for
|
||||
/// string values and object keys. The binary readers (@ref
|
||||
/// basic_json::from_cbor, @ref basic_json::from_msgpack, @ref
|
||||
/// basic_json::from_ubjson, @ref basic_json::from_bjdata, @ref
|
||||
/// basic_json::from_bson) use it to decide whether to check text strings
|
||||
/// and object keys for well-formed UTF-8 at all, since none of those
|
||||
/// formats requires a decoder to do so.
|
||||
enum class error_handler_t
|
||||
{
|
||||
strict, ///< throw a type_error/parse_error exception in case of invalid UTF-8
|
||||
replace, ///< replace invalid UTF-8 sequences with U+FFFD
|
||||
ignore, ///< ignore invalid UTF-8 sequences
|
||||
keep ///< keep invalid UTF-8 sequences unchanged
|
||||
};
|
||||
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
@@ -27,7 +27,6 @@
|
||||
#include <nlohmann/detail/input/string_scan.hpp>
|
||||
#include <nlohmann/detail/macro_scope.hpp>
|
||||
#include <nlohmann/detail/meta/cpp_future.hpp>
|
||||
#include <nlohmann/detail/output/error_handler.hpp>
|
||||
#include <nlohmann/detail/output/output_adapters.hpp>
|
||||
#include <nlohmann/detail/recursion_depth_limit.hpp>
|
||||
#include <nlohmann/detail/string_concat.hpp>
|
||||
@@ -42,6 +41,14 @@ namespace detail
|
||||
// serialization //
|
||||
///////////////////
|
||||
|
||||
/// how to treat decoding errors
|
||||
enum class error_handler_t
|
||||
{
|
||||
strict, ///< throw a type_error exception in case of invalid UTF-8
|
||||
replace, ///< replace invalid UTF-8 sequences with U+FFFD
|
||||
ignore ///< ignore invalid UTF-8 sequences
|
||||
};
|
||||
|
||||
template<typename BasicJsonType>
|
||||
class serializer
|
||||
{
|
||||
@@ -832,16 +839,6 @@ class serializer
|
||||
// EnsureAscii parameter is used, non-ASCII characters
|
||||
if ((codepoint <= 0x1F) || (EnsureAscii && (codepoint >= 0x7F)))
|
||||
{
|
||||
if (EnsureAscii && error_handler == error_handler_t::keep)
|
||||
{
|
||||
// this character was buffered as raw bytes
|
||||
// below in case it turned out to be part of
|
||||
// an ill-formed sequence (which is kept as
|
||||
// is); now that it decoded to a well-formed
|
||||
// code point, undo that and \u-escape it
|
||||
// like any other character instead
|
||||
bytes = bytes_after_last_accept;
|
||||
}
|
||||
if (codepoint <= 0xFFFF)
|
||||
{
|
||||
write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
|
||||
@@ -940,44 +937,6 @@ class serializer
|
||||
break;
|
||||
}
|
||||
|
||||
case error_handler_t::keep:
|
||||
{
|
||||
// the bytes of this (now abandoned) ill-formed
|
||||
// sequence seen so far are already buffered below
|
||||
// and are kept unchanged in the output
|
||||
if (undumped_chars > 0)
|
||||
{
|
||||
// the byte that ended the sequence may be OK
|
||||
// for itself (e.g., a quote that must still be
|
||||
// escaped, or the lead byte of a well-formed
|
||||
// code point), so read it again
|
||||
--i;
|
||||
}
|
||||
else
|
||||
{
|
||||
// a byte that cannot start a sequence (e.g.,
|
||||
// 0xFF or a stray continuation byte) is kept
|
||||
// as well
|
||||
string_buffer[bytes++] = s[i];
|
||||
}
|
||||
|
||||
// write buffer and reset index; there must be 13 bytes
|
||||
// left, as this is the maximal number of bytes to be
|
||||
// written ("\uxxxx\uxxxx\0") for one code point
|
||||
if (string_buffer.size() - bytes < 13)
|
||||
{
|
||||
put_buffer(string_buffer, bytes);
|
||||
bytes = 0;
|
||||
}
|
||||
|
||||
bytes_after_last_accept = bytes;
|
||||
undumped_chars = 0;
|
||||
|
||||
// continue processing the string
|
||||
state = UTF8_ACCEPT;
|
||||
break;
|
||||
}
|
||||
|
||||
default: // LCOV_EXCL_LINE
|
||||
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
|
||||
}
|
||||
@@ -986,12 +945,9 @@ class serializer
|
||||
|
||||
default: // decode found yet incomplete multibyte code point
|
||||
{
|
||||
if (!EnsureAscii || error_handler == error_handler_t::keep)
|
||||
if (!EnsureAscii)
|
||||
{
|
||||
// code point will not be escaped (or will be kept as
|
||||
// is if it turns out to be ill-formed) - copy byte to
|
||||
// buffer; dropped again above if it decodes to a
|
||||
// well-formed code point that needs \u-escaping
|
||||
// code point will not be escaped - copy byte to buffer
|
||||
string_buffer[bytes++] = s[i];
|
||||
}
|
||||
++undumped_chars;
|
||||
@@ -1042,14 +998,6 @@ class serializer
|
||||
break;
|
||||
}
|
||||
|
||||
case error_handler_t::keep:
|
||||
{
|
||||
// write the ill-formed trailing bytes as is; they were
|
||||
// buffered above regardless of EnsureAscii
|
||||
put_buffer(string_buffer, bytes);
|
||||
break;
|
||||
}
|
||||
|
||||
default: // LCOV_EXCL_LINE
|
||||
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
|
||||
}
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
|
||||
#include <nlohmann/detail/abi_macros.hpp>
|
||||
#include <nlohmann/detail/macro_scope.hpp>
|
||||
#include <nlohmann/detail/output/error_handler.hpp>
|
||||
|
||||
NLOHMANN_JSON_NAMESPACE_BEGIN
|
||||
namespace detail
|
||||
@@ -118,14 +117,13 @@ This is a single-byte step of a "shift-based" UTF-8 decoder originally
|
||||
written by Björn Hoehrmann. See
|
||||
http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
|
||||
|
||||
The library checks UTF-8 well-formedness (RFC 3629, section 4) in three
|
||||
The library checks UTF-8 well-formedness (RFC 3629, section 4) in four
|
||||
places, which differ in speed, diagnostics, and how they read the input:
|
||||
|
||||
- decode() below: the serializer, to escape and, in strict mode, reject
|
||||
ill-formed UTF-8 when dumping a string. The CBOR, MessagePack, BSON,
|
||||
UBJSON and BJData readers do not use it: none of those specs requires a
|
||||
decoder to reject ill-formed UTF-8 in text strings, so the readers keep
|
||||
the bytes as is and leave the check to dump() and the binary writers.
|
||||
- decode() and @ref is_valid_utf8 below: the serializer (to escape and, in
|
||||
strict mode, reject ill-formed UTF-8 when dumping a string) and the CBOR,
|
||||
MessagePack, BSON, UBJSON and BJData readers (to reject ill-formed UTF-8 in
|
||||
text strings at decode time).
|
||||
- the per-lead-byte switch in lexer::scan_string(): JSON text, with a
|
||||
diagnostic for each kind of error.
|
||||
- validate_one_utf8() and valid_utf8_prefix() in string_scan.hpp: the lexer's
|
||||
@@ -181,19 +179,19 @@ inline std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std:
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief check a string for well-formed UTF-8 (RFC 3629, section 4)
|
||||
@brief check whether a string consists solely of valid UTF-8
|
||||
|
||||
Used by the binary readers (CBOR, MessagePack, UBJSON, BJData, BSON) when an
|
||||
@ref error_handler_t other than `keep` is requested for a text string value
|
||||
or object key: none of those formats requires a decoder to reject ill-formed
|
||||
UTF-8 on its own, so the check is opt-in there, unlike the JSON lexer and the
|
||||
serializer's @ref decode -based escaping, which always run it.
|
||||
Used by the CBOR/MessagePack/BSON/UBJSON binary readers to reject text
|
||||
strings that are not valid UTF-8 at decode time (RFC 8949 §3.1 and the
|
||||
MessagePack/BSON specifications all require text strings to be UTF-8), so
|
||||
that malformed input is caught immediately instead of only surfacing later
|
||||
as a type_error.316 when the resulting value is dumped.
|
||||
|
||||
@param[in] s the string to check
|
||||
@param[in] first the index to start checking at
|
||||
@return whether `s.substr(first)` is well-formed UTF-8
|
||||
|
||||
@sa @ref decode
|
||||
@param[in] first index of the first byte to check; the bytes before it are
|
||||
assumed to have been validated already and to end on a
|
||||
code point boundary
|
||||
@return whether @a s (from index @a first on) is valid UTF-8
|
||||
*/
|
||||
template<typename StringType>
|
||||
inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noexcept
|
||||
@@ -213,101 +211,5 @@ inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noex
|
||||
return state == UTF8_ACCEPT;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief sanitize a string with ill-formed UTF-8 for @ref error_handler_t::replace or @ref error_handler_t::ignore
|
||||
|
||||
Replaces every maximal ill-formed subsequence with U+FFFD (`replace`) or
|
||||
drops it (`ignore`), using exactly the same boundaries @ref
|
||||
serializer::dump_escaped_impl uses while escaping a string: a byte that does
|
||||
not extend the sequence started by the previous byte(s) is reread as the
|
||||
start of a new one, instead of being swallowed along with them.
|
||||
|
||||
@pre @a error_handler is @ref error_handler_t::replace or @ref error_handler_t::ignore
|
||||
@note Well-formed input is copied through unchanged, including bytes (e.g.
|
||||
control characters or quotes) that @ref serializer::dump_escaped_impl
|
||||
would itself escape; this function only concerns itself with
|
||||
well-formedness, not with producing valid JSON text.
|
||||
|
||||
@param[in] s the string to sanitize
|
||||
@param[in] error_handler @ref error_handler_t::replace or @ref error_handler_t::ignore
|
||||
|
||||
@return @a s with every ill-formed subsequence replaced or removed
|
||||
|
||||
@sa @ref decode
|
||||
*/
|
||||
template<typename StringType>
|
||||
inline StringType sanitize_utf8(const StringType& s, const error_handler_t error_handler)
|
||||
{
|
||||
JSON_ASSERT(error_handler == error_handler_t::replace || error_handler == error_handler_t::ignore);
|
||||
|
||||
StringType result;
|
||||
result.reserve(s.size());
|
||||
|
||||
std::uint32_t codepoint = 0;
|
||||
std::uint8_t state = UTF8_ACCEPT;
|
||||
// length of result after the last accepted code point
|
||||
std::size_t result_len_after_last_accept = 0;
|
||||
// whether bytes of an as yet unresolved sequence were already appended
|
||||
bool pending = false;
|
||||
|
||||
for (std::size_t i = 0; i < s.size(); ++i)
|
||||
{
|
||||
switch (decode(state, codepoint, static_cast<std::uint8_t>(s[i])))
|
||||
{
|
||||
case UTF8_ACCEPT: // decode found a well-formed code point
|
||||
{
|
||||
result.push_back(s[i]);
|
||||
result_len_after_last_accept = result.size();
|
||||
pending = false;
|
||||
break;
|
||||
}
|
||||
|
||||
case UTF8_REJECT: // decode found an ill-formed byte
|
||||
{
|
||||
// in case we saw this byte for the first time, read it again,
|
||||
// because it may be fine for itself, just not for the
|
||||
// sequence that came before it
|
||||
if (pending)
|
||||
{
|
||||
--i;
|
||||
}
|
||||
|
||||
// drop the bytes of the ill-formed sequence buffered below
|
||||
result.resize(result_len_after_last_accept);
|
||||
|
||||
if (error_handler == error_handler_t::replace)
|
||||
{
|
||||
result.append("\xEF\xBF\xBD");
|
||||
result_len_after_last_accept = result.size();
|
||||
}
|
||||
|
||||
pending = false;
|
||||
state = UTF8_ACCEPT;
|
||||
break;
|
||||
}
|
||||
|
||||
default: // decode found yet incomplete multibyte code point
|
||||
{
|
||||
result.push_back(s[i]);
|
||||
pending = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// the string ended with an incomplete sequence
|
||||
if (state != UTF8_ACCEPT)
|
||||
{
|
||||
result.resize(result_len_after_last_accept);
|
||||
|
||||
if (error_handler == error_handler_t::replace)
|
||||
{
|
||||
result.append("\xEF\xBF\xBD");
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
|
||||
+46
-69
@@ -201,10 +201,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
// used by the vector-returning to_* overloads
|
||||
template<typename CharType> using vector_binary_writer =
|
||||
::nlohmann::detail::binary_writer<basic_json, CharType, ::nlohmann::detail::output_vector_sink<CharType>>;
|
||||
template<typename CharType> static vector_binary_writer<CharType> vector_writer(
|
||||
std::vector<CharType>& v, const ::nlohmann::detail::error_handler_t error_handler = ::nlohmann::detail::error_handler_t::strict)
|
||||
template<typename CharType> static vector_binary_writer<CharType> vector_writer(std::vector<CharType>& v)
|
||||
{
|
||||
return vector_binary_writer<CharType>(::nlohmann::detail::output_vector_sink<CharType>(v), error_handler);
|
||||
return vector_binary_writer<CharType>(::nlohmann::detail::output_vector_sink<CharType>(v));
|
||||
}
|
||||
|
||||
JSON_PRIVATE_UNLESS_TESTED:
|
||||
@@ -5446,29 +5445,26 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
public:
|
||||
/// @brief create a CBOR serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_cbor/
|
||||
static std::vector<std::uint8_t> to_cbor(const basic_json& j,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static std::vector<std::uint8_t> to_cbor(const basic_json& j)
|
||||
{
|
||||
std::vector<std::uint8_t> result;
|
||||
result.reserve(detail::binary_reserve_hint(j));
|
||||
vector_writer(result, error_handler).write_cbor(j);
|
||||
vector_writer(result).write_cbor(j);
|
||||
return result;
|
||||
}
|
||||
|
||||
/// @brief create a CBOR serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_cbor/
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o)
|
||||
{
|
||||
binary_writer<std::uint8_t>(o, error_handler).write_cbor(j);
|
||||
binary_writer<std::uint8_t>(o).write_cbor(j);
|
||||
}
|
||||
|
||||
/// @brief create a CBOR serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_cbor/
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<char> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static void to_cbor(const basic_json& j, detail::output_adapter<char> o)
|
||||
{
|
||||
binary_writer<char>(o, error_handler).write_cbor(j);
|
||||
binary_writer<char>(o).write_cbor(j);
|
||||
}
|
||||
|
||||
/// @brief create a MessagePack serialization of a given JSON value
|
||||
@@ -5499,31 +5495,28 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_ubjson/
|
||||
static std::vector<std::uint8_t> to_ubjson(const basic_json& j,
|
||||
const bool use_size = false,
|
||||
const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bool use_type = false)
|
||||
{
|
||||
std::vector<std::uint8_t> result;
|
||||
result.reserve(detail::binary_reserve_hint(j));
|
||||
vector_writer(result, error_handler).write_ubjson(j, use_size, use_type);
|
||||
vector_writer(result).write_ubjson(j, use_size, use_type);
|
||||
return result;
|
||||
}
|
||||
|
||||
/// @brief create a UBJSON serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_ubjson/
|
||||
static void to_ubjson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bool use_size = false, const bool use_type = false)
|
||||
{
|
||||
binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type);
|
||||
binary_writer<std::uint8_t>(o).write_ubjson(j, use_size, use_type);
|
||||
}
|
||||
|
||||
/// @brief create a UBJSON serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_ubjson/
|
||||
static void to_ubjson(const basic_json& j, detail::output_adapter<char> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bool use_size = false, const bool use_type = false)
|
||||
{
|
||||
binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type);
|
||||
binary_writer<char>(o).write_ubjson(j, use_size, use_type);
|
||||
}
|
||||
|
||||
/// @brief create a BJData serialization of a given JSON value
|
||||
@@ -5531,12 +5524,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
static std::vector<std::uint8_t> to_bjdata(const basic_json& j,
|
||||
const bool use_size = false,
|
||||
const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bjdata_version_t version = bjdata_version_t::draft2)
|
||||
{
|
||||
std::vector<std::uint8_t> result;
|
||||
result.reserve(detail::binary_reserve_hint(j));
|
||||
vector_writer(result, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
vector_writer(result).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
return result;
|
||||
}
|
||||
|
||||
@@ -5544,47 +5536,42 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_bjdata/
|
||||
static void to_bjdata(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bjdata_version_t version = bjdata_version_t::draft2)
|
||||
{
|
||||
binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
binary_writer<std::uint8_t>(o).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
}
|
||||
|
||||
/// @brief create a BJData serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_bjdata/
|
||||
static void to_bjdata(const basic_json& j, detail::output_adapter<char> o,
|
||||
const bool use_size = false, const bool use_type = false,
|
||||
const bjdata_version_t version = bjdata_version_t::draft2,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
const bjdata_version_t version = bjdata_version_t::draft2)
|
||||
{
|
||||
binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
binary_writer<char>(o).write_ubjson(j, use_size, use_type, true, true, version);
|
||||
}
|
||||
|
||||
/// @brief create a BSON serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_bson/
|
||||
static std::vector<std::uint8_t> to_bson(const basic_json& j,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static std::vector<std::uint8_t> to_bson(const basic_json& j)
|
||||
{
|
||||
std::vector<std::uint8_t> result;
|
||||
result.reserve(detail::binary_reserve_hint(j));
|
||||
vector_writer(result, error_handler).write_bson(j);
|
||||
vector_writer(result).write_bson(j);
|
||||
return result;
|
||||
}
|
||||
|
||||
/// @brief create a BSON serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_bson/
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o)
|
||||
{
|
||||
binary_writer<std::uint8_t>(o, error_handler).write_bson(j);
|
||||
binary_writer<std::uint8_t>(o).write_bson(j);
|
||||
}
|
||||
|
||||
/// @brief create a BSON serialization of a given JSON value
|
||||
/// @sa https://json.nlohmann.me/api/basic_json/to_bson/
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<char> o,
|
||||
const error_handler_t error_handler = error_handler_t::strict)
|
||||
static void to_bson(const basic_json& j, detail::output_adapter<char> o)
|
||||
{
|
||||
binary_writer<char>(o, error_handler).write_bson(j);
|
||||
binary_writer<char>(o).write_bson(j);
|
||||
}
|
||||
|
||||
/// @brief create a BON8 serialization of a given JSON value
|
||||
@@ -5618,13 +5605,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
static basic_json from_cbor(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor, error_handler).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5639,13 +5625,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
static basic_json from_cbor(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor, error_handler).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5687,13 +5672,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_msgpack(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5707,13 +5691,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_msgpack(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5753,13 +5736,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_ubjson(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5773,13 +5755,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_ubjson(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5819,13 +5800,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_bjdata(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5839,13 +5819,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_bjdata(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5895,13 +5874,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_bson(InputType&& i,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::forward<InputType>(i));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
@@ -5915,13 +5893,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
static basic_json from_bson(IteratorType first, SentinelType last,
|
||||
const bool strict = true,
|
||||
const bool allow_exceptions = true,
|
||||
const error_handler_t error_handler = error_handler_t::keep)
|
||||
const bool allow_exceptions = true)
|
||||
{
|
||||
basic_json result;
|
||||
auto ia = detail::input_adapter(std::move(first), std::move(last));
|
||||
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson, error_handler).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
|
||||
+138
-530
File diff suppressed because it is too large
Load Diff
@@ -1,346 +0,0 @@
|
||||
// __ _____ _____ _____
|
||||
// __| | __| | | | JSON for Modern C++ (supporting code)
|
||||
// | | |__ | | | | | | version 3.12.0
|
||||
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
|
||||
//
|
||||
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
|
||||
// SPDX-License-Identifier: MIT
|
||||
|
||||
#include "doctest_compatibility.h"
|
||||
|
||||
#include <nlohmann/json.hpp>
|
||||
using nlohmann::json;
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
struct ill_formed_case
|
||||
{
|
||||
const char* name;
|
||||
std::string bytes;
|
||||
};
|
||||
|
||||
// RFC 3629 ill-formed sequences used throughout this file, plus one
|
||||
// well-formed sequence for contrast
|
||||
const std::vector<ill_formed_case> ill_formed_cases =
|
||||
{
|
||||
{"overlong", "\xC0\xAE"},
|
||||
{"lone_0xFF", "\xFF"},
|
||||
{"truncated", "\xE2\x82"},
|
||||
{"surrogate", "\xED\xA0\x80"},
|
||||
};
|
||||
|
||||
const std::string valid_sequence = "\xC3\xA9"; // U+00E9, "é"
|
||||
|
||||
using eh = json::error_handler_t;
|
||||
const std::vector<eh> all_handlers = {eh::strict, eh::replace, eh::ignore, eh::keep};
|
||||
|
||||
// what dump()+parse() produces for a sanitizing error_handler; this is the
|
||||
// ground truth every binary writer/reader is checked against
|
||||
std::string dump_and_parse(const std::string& raw, eh error_handler)
|
||||
{
|
||||
return json::parse(json(raw).dump(-1, ' ', false, error_handler)).get<std::string>();
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
TEST_CASE("UTF-8 error_handler for the binary readers and writers")
|
||||
{
|
||||
SECTION("writers: string value")
|
||||
{
|
||||
for (const auto& c : ill_formed_cases)
|
||||
{
|
||||
CAPTURE(c.name);
|
||||
const json jval = c.bytes;
|
||||
|
||||
CHECK_THROWS_AS(json::to_cbor(jval, eh::strict), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_ubjson(jval, false, false, eh::strict), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_bjdata(jval, false, false, json::bjdata_version_t::draft2, eh::strict), json::type_error&);
|
||||
{
|
||||
json jobj;
|
||||
jobj["k"] = jval;
|
||||
CHECK_THROWS_AS(json::to_bson(jobj, eh::strict), json::type_error&);
|
||||
}
|
||||
|
||||
for (const auto h :
|
||||
{
|
||||
eh::replace, eh::ignore
|
||||
})
|
||||
{
|
||||
CAPTURE(static_cast<int>(h));
|
||||
const std::string expected = dump_and_parse(c.bytes, h);
|
||||
|
||||
CHECK(json::from_cbor(json::to_cbor(jval, h)).get<std::string>() == expected);
|
||||
CHECK(json::from_ubjson(json::to_ubjson(jval, false, false, h)).get<std::string>() == expected);
|
||||
CHECK(json::from_bjdata(json::to_bjdata(jval, false, false, json::bjdata_version_t::draft2, h)).get<std::string>() == expected);
|
||||
{
|
||||
json jobj;
|
||||
jobj["k"] = jval;
|
||||
const auto bytes = json::to_bson(jobj, h);
|
||||
CHECK(json::from_bson(bytes)["k"].get<std::string>() == expected);
|
||||
}
|
||||
}
|
||||
|
||||
// keep: the writer passes the ill-formed bytes through unchanged,
|
||||
// exactly as every binary writer did before this parameter existed
|
||||
CHECK(json::from_cbor(json::to_cbor(jval, eh::keep)).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_ubjson(json::to_ubjson(jval, false, false, eh::keep)).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_bjdata(json::to_bjdata(jval, false, false, json::bjdata_version_t::draft2, eh::keep)).get<std::string>() == c.bytes);
|
||||
{
|
||||
json jobj;
|
||||
jobj["k"] = jval;
|
||||
const auto bytes = json::to_bson(jobj, eh::keep);
|
||||
CHECK(json::from_bson(bytes)["k"].get<std::string>() == c.bytes);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("writers: object key")
|
||||
{
|
||||
for (const auto& c : ill_formed_cases)
|
||||
{
|
||||
CAPTURE(c.name);
|
||||
json jobj;
|
||||
jobj[c.bytes] = 1;
|
||||
|
||||
CHECK_THROWS_AS(json::to_cbor(jobj, eh::strict), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_ubjson(jobj, false, false, eh::strict), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_bjdata(jobj, false, false, json::bjdata_version_t::draft2, eh::strict), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_bson(jobj, eh::strict), json::type_error&);
|
||||
|
||||
for (const auto h :
|
||||
{
|
||||
eh::replace, eh::ignore
|
||||
})
|
||||
{
|
||||
CAPTURE(static_cast<int>(h));
|
||||
const std::string expected = dump_and_parse(c.bytes, h);
|
||||
|
||||
CHECK(json::from_cbor(json::to_cbor(jobj, h)).begin().key() == expected);
|
||||
CHECK(json::from_ubjson(json::to_ubjson(jobj, false, false, h)).begin().key() == expected);
|
||||
CHECK(json::from_bjdata(json::to_bjdata(jobj, false, false, json::bjdata_version_t::draft2, h)).begin().key() == expected);
|
||||
CHECK(json::from_bson(json::to_bson(jobj, h)).begin().key() == expected);
|
||||
}
|
||||
|
||||
// keep: object keys round-trip unchanged too
|
||||
CHECK(json::from_cbor(json::to_cbor(jobj, eh::keep)).begin().key() == c.bytes);
|
||||
CHECK(json::from_ubjson(json::to_ubjson(jobj, false, false, eh::keep)).begin().key() == c.bytes);
|
||||
CHECK(json::from_bjdata(json::to_bjdata(jobj, false, false, json::bjdata_version_t::draft2, eh::keep)).begin().key() == c.bytes);
|
||||
CHECK(json::from_bson(json::to_bson(jobj, eh::keep)).begin().key() == c.bytes);
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("readers: string value")
|
||||
{
|
||||
for (const auto& c : ill_formed_cases)
|
||||
{
|
||||
CAPTURE(c.name);
|
||||
|
||||
// bytes produced the lenient (keep) way, as any binary reader
|
||||
// accepted them before this parameter existed
|
||||
const auto cbor_bytes = json::to_cbor(json(c.bytes), eh::keep);
|
||||
const auto msgpack_bytes = json::to_msgpack(json(c.bytes)); // to_msgpack has no error_handler; always pass-through
|
||||
const auto ubjson_bytes = json::to_ubjson(json(c.bytes), false, false, eh::keep);
|
||||
const auto bjdata_bytes = json::to_bjdata(json(c.bytes), false, false, json::bjdata_version_t::draft2, eh::keep);
|
||||
const auto bson_bytes = [&c]
|
||||
{
|
||||
json jobj;
|
||||
jobj["k"] = c.bytes;
|
||||
return json::to_bson(jobj, eh::keep);
|
||||
}();
|
||||
|
||||
// keep (the default): bytes are kept unchanged
|
||||
CHECK(json::from_cbor(cbor_bytes).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_msgpack(msgpack_bytes).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_ubjson(ubjson_bytes).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_bjdata(bjdata_bytes).get<std::string>() == c.bytes);
|
||||
CHECK(json::from_bson(bson_bytes)["k"].get<std::string>() == c.bytes);
|
||||
|
||||
// strict: parse_error.113, discarded (not thrown) when allow_exceptions is false
|
||||
CHECK_THROWS_AS(json::from_cbor(cbor_bytes, true, true, json::cbor_tag_handler_t::error, eh::strict), json::parse_error&);
|
||||
CHECK(json::from_cbor(cbor_bytes, true, false, json::cbor_tag_handler_t::error, eh::strict).is_discarded());
|
||||
CHECK_THROWS_AS(json::from_msgpack(msgpack_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK(json::from_msgpack(msgpack_bytes, true, false, eh::strict).is_discarded());
|
||||
CHECK_THROWS_AS(json::from_ubjson(ubjson_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK(json::from_ubjson(ubjson_bytes, true, false, eh::strict).is_discarded());
|
||||
CHECK_THROWS_AS(json::from_bjdata(bjdata_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK(json::from_bjdata(bjdata_bytes, true, false, eh::strict).is_discarded());
|
||||
CHECK_THROWS_AS(json::from_bson(bson_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK(json::from_bson(bson_bytes, true, false, eh::strict).is_discarded());
|
||||
|
||||
// replace / ignore: match what dump() would have sanitized the same bytes to
|
||||
for (const auto h :
|
||||
{
|
||||
eh::replace, eh::ignore
|
||||
})
|
||||
{
|
||||
CAPTURE(static_cast<int>(h));
|
||||
const std::string expected = dump_and_parse(c.bytes, h);
|
||||
|
||||
CHECK(json::from_cbor(cbor_bytes, true, true, json::cbor_tag_handler_t::error, h).get<std::string>() == expected);
|
||||
CHECK(json::from_msgpack(msgpack_bytes, true, true, h).get<std::string>() == expected);
|
||||
CHECK(json::from_ubjson(ubjson_bytes, true, true, h).get<std::string>() == expected);
|
||||
CHECK(json::from_bjdata(bjdata_bytes, true, true, h).get<std::string>() == expected);
|
||||
CHECK(json::from_bson(bson_bytes, true, true, h)["k"].get<std::string>() == expected);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("readers: object key")
|
||||
{
|
||||
for (const auto& c : ill_formed_cases)
|
||||
{
|
||||
CAPTURE(c.name);
|
||||
|
||||
json jobj;
|
||||
jobj[c.bytes] = 1;
|
||||
const auto cbor_bytes = json::to_cbor(jobj, eh::keep);
|
||||
const auto msgpack_bytes = json::to_msgpack(jobj);
|
||||
const auto ubjson_bytes = json::to_ubjson(jobj, false, false, eh::keep);
|
||||
const auto bjdata_bytes = json::to_bjdata(jobj, false, false, json::bjdata_version_t::draft2, eh::keep);
|
||||
const auto bson_bytes = json::to_bson(jobj, eh::keep);
|
||||
|
||||
CHECK(json::from_cbor(cbor_bytes).begin().key() == c.bytes);
|
||||
CHECK(json::from_msgpack(msgpack_bytes).begin().key() == c.bytes);
|
||||
CHECK(json::from_ubjson(ubjson_bytes).begin().key() == c.bytes);
|
||||
CHECK(json::from_bjdata(bjdata_bytes).begin().key() == c.bytes);
|
||||
CHECK(json::from_bson(bson_bytes).begin().key() == c.bytes);
|
||||
|
||||
CHECK_THROWS_AS(json::from_cbor(cbor_bytes, true, true, json::cbor_tag_handler_t::error, eh::strict), json::parse_error&);
|
||||
CHECK_THROWS_AS(json::from_msgpack(msgpack_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK_THROWS_AS(json::from_ubjson(ubjson_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK_THROWS_AS(json::from_bjdata(bjdata_bytes, true, true, eh::strict), json::parse_error&);
|
||||
CHECK_THROWS_AS(json::from_bson(bson_bytes, true, true, eh::strict), json::parse_error&);
|
||||
|
||||
for (const auto h :
|
||||
{
|
||||
eh::replace, eh::ignore
|
||||
})
|
||||
{
|
||||
CAPTURE(static_cast<int>(h));
|
||||
const std::string expected = dump_and_parse(c.bytes, h);
|
||||
|
||||
CHECK(json::from_cbor(cbor_bytes, true, true, json::cbor_tag_handler_t::error, h).begin().key() == expected);
|
||||
CHECK(json::from_msgpack(msgpack_bytes, true, true, h).begin().key() == expected);
|
||||
CHECK(json::from_ubjson(ubjson_bytes, true, true, h).begin().key() == expected);
|
||||
CHECK(json::from_bjdata(bjdata_bytes, true, true, h).begin().key() == expected);
|
||||
CHECK(json::from_bson(bson_bytes, true, true, h).begin().key() == expected);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("well-formed UTF-8 is unaffected by error_handler")
|
||||
{
|
||||
const json jval = valid_sequence;
|
||||
json jobj;
|
||||
jobj[valid_sequence] = valid_sequence;
|
||||
|
||||
for (const auto h : all_handlers)
|
||||
{
|
||||
CAPTURE(static_cast<int>(h));
|
||||
|
||||
CHECK(json::from_cbor(json::to_cbor(jval, h)).get<std::string>() == valid_sequence);
|
||||
CHECK(json::from_ubjson(json::to_ubjson(jval, false, false, h)).get<std::string>() == valid_sequence);
|
||||
CHECK(json::from_bjdata(json::to_bjdata(jval, false, false, json::bjdata_version_t::draft2, h)).get<std::string>() == valid_sequence);
|
||||
CHECK(json::from_bson(json::to_bson(jobj, h)).begin().key() == valid_sequence);
|
||||
|
||||
CHECK(json::from_cbor(json::to_cbor(jval, eh::keep), true, true, json::cbor_tag_handler_t::error, h).get<std::string>() == valid_sequence);
|
||||
CHECK(json::from_msgpack(json::to_msgpack(jval), true, true, h).get<std::string>() == valid_sequence);
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("dump() with error_handler_t::keep writes raw bytes as is")
|
||||
{
|
||||
for (const auto& c : ill_formed_cases)
|
||||
{
|
||||
CAPTURE(c.name);
|
||||
|
||||
const json jval = c.bytes;
|
||||
const std::string dumped = jval.dump(-1, ' ', false, eh::keep);
|
||||
CHECK(dumped.find(c.bytes) != std::string::npos);
|
||||
|
||||
// even with ensure_ascii, the ill-formed bytes are written as is
|
||||
const std::string dumped_ascii = jval.dump(-1, ' ', true, eh::keep);
|
||||
CHECK(dumped_ascii.find(c.bytes) != std::string::npos);
|
||||
}
|
||||
|
||||
// well-formed characters around an ill-formed sequence are still
|
||||
// escaped as usual under ensure_ascii
|
||||
const json mixed = valid_sequence + ill_formed_cases[1].bytes; // "é" + lone 0xFF
|
||||
const std::string dumped_mixed = mixed.dump(-1, ' ', true, eh::keep);
|
||||
CHECK(dumped_mixed.find("\\u00e9") != std::string::npos);
|
||||
CHECK(dumped_mixed.find(ill_formed_cases[1].bytes) != std::string::npos);
|
||||
|
||||
// the byte that ends an ill-formed sequence is read again, so a quote,
|
||||
// a backslash, or a control character after it is still escaped, and
|
||||
// a well-formed code point after it is escaped under ensure_ascii
|
||||
for (const bool ensure_ascii :
|
||||
{
|
||||
false, true
|
||||
})
|
||||
{
|
||||
CAPTURE(ensure_ascii);
|
||||
CHECK(json("\xC3\"").dump(-1, ' ', ensure_ascii, eh::keep) == "\"\xC3\\\"\"");
|
||||
CHECK(json("\xC3\\").dump(-1, ' ', ensure_ascii, eh::keep) == "\"\xC3\\\\\"");
|
||||
CHECK(json("\xC3\n").dump(-1, ' ', ensure_ascii, eh::keep) == "\"\xC3\\n\"");
|
||||
CHECK(json("\xE2\x82\"").dump(-1, ' ', ensure_ascii, eh::keep) == "\"\xE2\x82\\\"\"");
|
||||
CHECK(json("\xFF\"").dump(-1, ' ', ensure_ascii, eh::keep) == "\"\xFF\\\"\"");
|
||||
CHECK(json("a\xE2\x82").dump(-1, ' ', ensure_ascii, eh::keep) == "\"a\xE2\x82\"");
|
||||
}
|
||||
CHECK(json("\xC3\xC3\xA9").dump(-1, ' ', false, eh::keep) == "\"\xC3\xC3\xA9\"");
|
||||
CHECK(json("\xC3\xC3\xA9").dump(-1, ' ', true, eh::keep) == "\"\xC3\\u00e9\"");
|
||||
}
|
||||
|
||||
SECTION("to_msgpack and to_bon8 are not affected by error_handler")
|
||||
{
|
||||
const json jval = ill_formed_cases[1].bytes; // lone 0xFF
|
||||
|
||||
// to_msgpack has no error_handler parameter; the bytes are always
|
||||
// passed through, as MessagePack's spec allows
|
||||
CHECK(json::from_msgpack(json::to_msgpack(jval)).get<std::string>() == ill_formed_cases[1].bytes);
|
||||
|
||||
// to_bon8 has no error_handler parameter either; UTF-8 is structural
|
||||
// for BON8, so it always rejects ill-formed input
|
||||
CHECK_THROWS_AS(json::to_bon8(jval), json::type_error&);
|
||||
}
|
||||
|
||||
SECTION("allow_exceptions=false with error_handler_t::strict discards the value")
|
||||
{
|
||||
const auto bytes = json::to_cbor(json(ill_formed_cases[0].bytes), eh::keep);
|
||||
const json result = json::from_cbor(bytes, true, false, json::cbor_tag_handler_t::error, eh::strict);
|
||||
CHECK(result.is_discarded());
|
||||
}
|
||||
|
||||
SECTION("default parameters are unchanged")
|
||||
{
|
||||
const json jval = ill_formed_cases[0].bytes;
|
||||
|
||||
// to_*: the default error_handler is strict, so ill-formed input still throws
|
||||
CHECK_THROWS_AS(json::to_cbor(jval), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_ubjson(jval), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_bjdata(jval), json::type_error&);
|
||||
{
|
||||
json jobj;
|
||||
jobj["k"] = jval;
|
||||
CHECK_THROWS_AS(json::to_bson(jobj), json::type_error&);
|
||||
}
|
||||
|
||||
// from_*: the default error_handler is keep, so ill-formed bytes are
|
||||
// still accepted unchanged, exactly as in release 3.12.0
|
||||
const auto cbor_bytes = json::to_cbor(jval, eh::keep);
|
||||
CHECK(json::from_cbor(cbor_bytes).get<std::string>() == ill_formed_cases[0].bytes);
|
||||
const auto ubjson_bytes = json::to_ubjson(jval, false, false, eh::keep);
|
||||
CHECK(json::from_ubjson(ubjson_bytes).get<std::string>() == ill_formed_cases[0].bytes);
|
||||
const auto bjdata_bytes = json::to_bjdata(jval, false, false, json::bjdata_version_t::draft2, eh::keep);
|
||||
CHECK(json::from_bjdata(bjdata_bytes).get<std::string>() == ill_formed_cases[0].bytes);
|
||||
const auto msgpack_bytes = json::to_msgpack(jval);
|
||||
CHECK(json::from_msgpack(msgpack_bytes).get<std::string>() == ill_formed_cases[0].bytes);
|
||||
json bson_obj;
|
||||
bson_obj["k"] = jval;
|
||||
const auto bson_bytes = json::to_bson(bson_obj, eh::keep);
|
||||
CHECK(json::from_bson(bson_bytes)["k"].get<std::string>() == ill_formed_cases[0].bytes);
|
||||
}
|
||||
}
|
||||
@@ -3907,41 +3907,6 @@ TEST_CASE("Universal Binary JSON Specification Examples 1")
|
||||
CHECK(json::to_bjdata(j) == v);
|
||||
CHECK(json::from_bjdata(v) == j);
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 (see #5529, #5651)")
|
||||
{
|
||||
// none of the binary format specs requires a decoder to reject
|
||||
// ill-formed UTF-8 in a text string, so a value whose bytes are
|
||||
// not valid UTF-8 (0xC0 0xAE is an overlong encoding of '.')
|
||||
// round-trips byte for byte as a string value; to_bjdata() is
|
||||
// strict, so such a value cannot be written back
|
||||
const std::vector<uint8_t> v = {'S', 'i', 2, 0xc0, 0xae};
|
||||
json j;
|
||||
CHECK_NOTHROW(j = json::from_bjdata(v));
|
||||
REQUIRE(j.is_string());
|
||||
CHECK(j.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
|
||||
CHECK_THROWS_AS(j.dump(), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_bjdata(j), json::type_error&);
|
||||
|
||||
// the same bytes as an object key round-trip as well
|
||||
const std::vector<uint8_t> v_key = {'{', 'i', 2, 0xc0, 0xae, 'i', 1, '}'};
|
||||
json j_key;
|
||||
CHECK_NOTHROW(j_key = json::from_bjdata(v_key));
|
||||
REQUIRE(j_key.is_object());
|
||||
CHECK(j_key.contains(std::string("\xc0\xae")));
|
||||
CHECK_THROWS_AS(json::to_bjdata(j_key), json::type_error&);
|
||||
|
||||
CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xFF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
// a truncated multi-byte sequence
|
||||
CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xC3")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
|
||||
// an encoded surrogate half (U+D800)
|
||||
CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xED\xA0\x80")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
|
||||
// an overlong encoding of '.'
|
||||
CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xC0\xAF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
|
||||
|
||||
// an object key with ill-formed UTF-8 is rejected the same way
|
||||
CHECK_THROWS_WITH_AS(json::to_bjdata(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("Array Type")
|
||||
|
||||
@@ -154,51 +154,6 @@ TEST_CASE("BSON")
|
||||
#endif
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 (see #5529, #5651)")
|
||||
{
|
||||
// a BSON document {"s": "\xC0\xAE"} (0xC0 0xAE is an overlong
|
||||
// encoding of '.'); the BSON spec does not require a decoder to
|
||||
// reject ill-formed UTF-8 in a string value, so the reader hands the
|
||||
// bytes back unchanged
|
||||
const std::vector<uint8_t> v =
|
||||
{
|
||||
0x0F, 0x00, 0x00, 0x00, // document length
|
||||
0x02, 's', 0x00, // type 0x02 (string), key "s"
|
||||
0x03, 0x00, 0x00, 0x00, // string length (including null)
|
||||
0xc0, 0xae, 0x00, // string content and its null terminator
|
||||
0x00 // document terminator
|
||||
};
|
||||
json j;
|
||||
CHECK_NOTHROW(j = json::from_bson(v));
|
||||
REQUIRE(j.is_object());
|
||||
REQUIRE(j.contains("s"));
|
||||
CHECK(j["s"].get_ref<const json::string_t&>() == std::string("\xc0\xae"));
|
||||
// dump() still requires valid UTF-8 and throws for such a value
|
||||
CHECK_THROWS_AS(j.dump(), json::type_error&);
|
||||
// to_bson() is strict as well, so the value cannot be written back
|
||||
CHECK_THROWS_AS(json::to_bson(j), json::type_error&);
|
||||
|
||||
// to_bson() rejects the same kind of ill-formed string value, before
|
||||
// any bytes reach the output adapter (the BSON document length
|
||||
// prefix must be known up front, so nothing is written incrementally)
|
||||
std::vector<std::uint8_t> out{0x42}; // a sentinel byte the writer must not touch
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xFF"}}, nlohmann::detail::output_adapter<std::uint8_t>(out)), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
CHECK(out == std::vector<std::uint8_t> {0x42});
|
||||
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xFF"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
// a truncated multi-byte sequence
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xC3"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
|
||||
// an encoded surrogate half (U+D800)
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xED\xA0\x80"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
|
||||
// an overlong encoding of '.'
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xC0\xAF"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
|
||||
|
||||
// an object key with ill-formed UTF-8 is rejected as well; unlike
|
||||
// the reader (which never validates element names), the writer
|
||||
// checks both string values and object keys
|
||||
CHECK_THROWS_WITH_AS(json::to_bson(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
}
|
||||
|
||||
SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
|
||||
{
|
||||
// out_of_range.412 is thrown from a single shared helper
|
||||
|
||||
+18
-65
@@ -1801,40 +1801,19 @@ TEST_CASE("CBOR")
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x7C, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C", json::parse_error&);
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 in string (see #5529, #5651)")
|
||||
SECTION("invalid UTF-8 in string (see #5529)")
|
||||
{
|
||||
// RFC 8949 §3.1 leaves it up to the decoder whether to reject
|
||||
// ill-formed UTF-8 in a text string; this library does not, and
|
||||
// hands the original bytes back unchanged, matching the
|
||||
// MessagePack reader and the behavior before #5185/#5531 (not in
|
||||
// any release)
|
||||
|
||||
// a two-character text string (major type 3) whose bytes are not
|
||||
// valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') round-trips
|
||||
// byte for byte as a string value
|
||||
const std::vector<uint8_t> ill_formed_value = {0x62, 0xc0, 0xae};
|
||||
json j_value;
|
||||
CHECK_NOTHROW(j_value = json::from_cbor(ill_formed_value));
|
||||
REQUIRE(j_value.is_string());
|
||||
CHECK(j_value.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
|
||||
// dump() still requires valid UTF-8 and throws for such a value,
|
||||
// unless an error handler that replaces or ignores the bytes is
|
||||
// passed
|
||||
CHECK_THROWS_AS(j_value.dump(), json::type_error&);
|
||||
// to_cbor() is strict as well, so the value cannot be written back
|
||||
CHECK_THROWS_AS(json::to_cbor(j_value), json::type_error&);
|
||||
|
||||
// the same bytes as an object key round-trip as well
|
||||
const std::vector<uint8_t> ill_formed_key = {0xa1, 0x62, 0xc0, 0xae, 0x01};
|
||||
json j_key;
|
||||
CHECK_NOTHROW(j_key = json::from_cbor(ill_formed_key));
|
||||
REQUIRE(j_key.is_object());
|
||||
CHECK(j_key.contains(std::string("\xc0\xae")));
|
||||
CHECK_THROWS_AS(json::to_cbor(j_key), json::type_error&);
|
||||
// valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') must be
|
||||
// rejected at decode time, matching every other kind of
|
||||
// malformed binary input, rather than only failing later when
|
||||
// the resulting value is dumped
|
||||
json _;
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae}), true, false).is_discarded());
|
||||
|
||||
// a CBOR byte string (major type 2) with the very same bytes is
|
||||
// NOT text and must still be accepted as-is
|
||||
json _;
|
||||
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x42, 0xc0, 0xae})));
|
||||
CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
|
||||
|
||||
@@ -1843,46 +1822,17 @@ TEST_CASE("CBOR")
|
||||
CHECK(json::from_cbor(json::to_cbor(j)) == j);
|
||||
}
|
||||
|
||||
SECTION("to_cbor rejects ill-formed UTF-8 (see #5651)")
|
||||
{
|
||||
// to_cbor() must reject the same ill-formed strings from_cbor()
|
||||
// rejects, so a value it accepts can always be read back
|
||||
CHECK_THROWS_WITH_AS(json::to_cbor(json("\xFF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
// a truncated multi-byte sequence
|
||||
CHECK_THROWS_WITH_AS(json::to_cbor(json("\xC3")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
|
||||
// an encoded surrogate half (U+D800)
|
||||
CHECK_THROWS_WITH_AS(json::to_cbor(json("\xED\xA0\x80")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
|
||||
// an overlong encoding of '.'
|
||||
CHECK_THROWS_WITH_AS(json::to_cbor(json("\xC0\xAF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
|
||||
|
||||
// an object key with ill-formed UTF-8 is rejected the same way
|
||||
CHECK_THROWS_WITH_AS(json::to_cbor(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
|
||||
// binary values are not text and are unaffected
|
||||
CHECK_NOTHROW(json::to_cbor(json::binary(std::vector<std::uint8_t>({0xFF}))));
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 in indefinite-length string")
|
||||
SECTION("invalid UTF-8 in indefinite-length string")
|
||||
{
|
||||
json _;
|
||||
|
||||
// the chunks are concatenated as is, without checking that each
|
||||
// chunk is valid UTF-8 on its own (RFC 8949, Section 3.2.3), so
|
||||
// a code point split across two chunks yields a valid string
|
||||
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})));
|
||||
CHECK(_ == "\xc3\xa9");
|
||||
CHECK(_.dump() == "\"\xc3\xa9\"");
|
||||
// every chunk must be valid UTF-8 on its own (RFC 8949, Section
|
||||
// 3.2.3), so a code point split across two chunks is rejected
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff}), true, false).is_discarded());
|
||||
|
||||
// a truncated code point is kept as is
|
||||
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0xff})));
|
||||
CHECK(_ == "\xc3");
|
||||
CHECK_THROWS_AS(_.dump(), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_cbor(_), json::type_error&);
|
||||
|
||||
// an ill-formed later chunk is kept after valid ones
|
||||
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})));
|
||||
CHECK(_ == "\xc3\xa9\xc0\xae");
|
||||
CHECK_THROWS_AS(_.dump(), json::type_error&);
|
||||
// an ill-formed later chunk is rejected after valid ones
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
|
||||
|
||||
// valid multi-byte chunks are accepted
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc3, 0xb6, 0xff})) == "\xc3\xa9\xc3\xb6");
|
||||
@@ -1890,6 +1840,9 @@ TEST_CASE("CBOR")
|
||||
|
||||
SECTION("many chunks in indefinite-length string")
|
||||
{
|
||||
// only the newly read chunk is validated, not the whole string
|
||||
// collected so far; validating the latter made this input take
|
||||
// quadratic time (about ten seconds for 100000 chunks)
|
||||
constexpr std::size_t chunks = 100000;
|
||||
std::vector<uint8_t> v{0x7f};
|
||||
for (std::size_t i = 0; i < chunks; ++i)
|
||||
|
||||
@@ -1540,39 +1540,19 @@ TEST_CASE("MessagePack")
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing MessagePack string: unexpected end of input", json::parse_error&);
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 in string (see #5529, #5651)")
|
||||
SECTION("invalid UTF-8 in string (see #5529)")
|
||||
{
|
||||
// the MessagePack specification explicitly allows a str object to
|
||||
// contain a byte sequence that is not valid UTF-8 and expects a
|
||||
// deserializer to hand the original bytes back unchanged; this
|
||||
// library follows that, unlike CBOR/UBJSON/BJData/BSON, whose
|
||||
// specifications require text strings to be valid UTF-8
|
||||
|
||||
// a fixstr of length 2 (0xA0 | 2) whose bytes are not valid UTF-8
|
||||
// (0xC0 0xAE is an overlong encoding of '.') round-trips byte for
|
||||
// byte as a string value
|
||||
const std::vector<uint8_t> ill_formed_value = {0xa2, 0xc0, 0xae};
|
||||
json j_value;
|
||||
CHECK_NOTHROW(j_value = json::from_msgpack(ill_formed_value));
|
||||
REQUIRE(j_value.is_string());
|
||||
CHECK(j_value.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
|
||||
CHECK(json::from_msgpack(json::to_msgpack(j_value)) == j_value);
|
||||
// dump() still requires valid UTF-8 and throws for such a value,
|
||||
// unless an error handler that replaces or ignores the bytes is
|
||||
// passed
|
||||
CHECK_THROWS_AS(j_value.dump(), json::type_error&);
|
||||
|
||||
// the same bytes as an object key round-trip as well
|
||||
const std::vector<uint8_t> ill_formed_key = {0x81, 0xa2, 0xc0, 0xae, 0x01};
|
||||
json j_key;
|
||||
CHECK_NOTHROW(j_key = json::from_msgpack(ill_formed_key));
|
||||
REQUIRE(j_key.is_object());
|
||||
CHECK(j_key.contains(std::string("\xc0\xae")));
|
||||
CHECK(json::from_msgpack(json::to_msgpack(j_key)) == j_key);
|
||||
// (0xC0 0xAE is an overlong encoding of '.') must be rejected at
|
||||
// decode time, matching every other kind of malformed binary
|
||||
// input, rather than only failing later when the resulting
|
||||
// value is dumped
|
||||
json _;
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing MessagePack string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae}), true, false).is_discarded());
|
||||
|
||||
// a MessagePack bin8 blob with the very same bytes is NOT text
|
||||
// and must still be accepted as-is
|
||||
json _;
|
||||
CHECK_NOTHROW(_ = json::from_msgpack(std::vector<uint8_t>({0xc4, 0x02, 0xc0, 0xae})));
|
||||
CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
|
||||
|
||||
|
||||
@@ -2505,41 +2505,6 @@ TEST_CASE("Universal Binary JSON Specification Examples 1")
|
||||
CHECK(json::to_ubjson(j) == v);
|
||||
CHECK(json::from_ubjson(v) == j);
|
||||
}
|
||||
|
||||
SECTION("ill-formed UTF-8 (see #5529, #5651)")
|
||||
{
|
||||
// none of the binary format specs requires a decoder to reject
|
||||
// ill-formed UTF-8 in a text string, so a value whose bytes are
|
||||
// not valid UTF-8 (0xC0 0xAE is an overlong encoding of '.')
|
||||
// round-trips byte for byte as a string value; to_ubjson() is
|
||||
// strict, so such a value cannot be written back
|
||||
const std::vector<uint8_t> v = {'S', 'i', 2, 0xc0, 0xae};
|
||||
json j;
|
||||
CHECK_NOTHROW(j = json::from_ubjson(v));
|
||||
REQUIRE(j.is_string());
|
||||
CHECK(j.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
|
||||
CHECK_THROWS_AS(j.dump(), json::type_error&);
|
||||
CHECK_THROWS_AS(json::to_ubjson(j), json::type_error&);
|
||||
|
||||
// the same bytes as an object key round-trip as well
|
||||
const std::vector<uint8_t> v_key = {'{', 'i', 2, 0xc0, 0xae, 'i', 1, '}'};
|
||||
json j_key;
|
||||
CHECK_NOTHROW(j_key = json::from_ubjson(v_key));
|
||||
REQUIRE(j_key.is_object());
|
||||
CHECK(j_key.contains(std::string("\xc0\xae")));
|
||||
CHECK_THROWS_AS(json::to_ubjson(j_key), json::type_error&);
|
||||
|
||||
CHECK_THROWS_WITH_AS(json::to_ubjson(json("\xFF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
// a truncated multi-byte sequence
|
||||
CHECK_THROWS_WITH_AS(json::to_ubjson(json("\xC3")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
|
||||
// an encoded surrogate half (U+D800)
|
||||
CHECK_THROWS_WITH_AS(json::to_ubjson(json("\xED\xA0\x80")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
|
||||
// an overlong encoding of '.'
|
||||
CHECK_THROWS_WITH_AS(json::to_ubjson(json("\xC0\xAF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
|
||||
|
||||
// an object key with ill-formed UTF-8 is rejected the same way
|
||||
CHECK_THROWS_WITH_AS(json::to_ubjson(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("Array Type")
|
||||
|
||||
Reference in New Issue
Block a user