BSON reader: recover from the document size checks made on reading the size

Since #5930, a size below 5, a size that exceeds the enclosing document, and
a size too small for the document's content are reported before the document
is read. When recovering, such a document is now read up to its terminator,
within the enclosing document, and its size is not reported a second time.
BJData now checks an ndarray's type before the object that would hold it is
begun, so that test expects null.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.github/CONTRIBUTING.md

@@ -111,6 +111,8 @@ context which existing file needs to be extended, and only very few cases requir
 When fixing a bug, edit `unit-regression3.cpp` and add a section referencing the fixed issue.
 `unit-regression2.cpp` holds the older tests; the two files exist because a single one grew large enough for the
 MinGW linker to fail relocating it, so please keep adding to the smaller file rather than growing the larger one.
+Tests that call `sax_parse` go into `unit-sax_parse.cpp` rather than into a large test file: every call instantiates
+the parser and the binary reader that recover from errors, which grows a test file considerably.
 
 #### Exceptions
 

.github/workflows/cancel_closed_pr_runs.yml

@@ -24,7 +24,7 @@ jobs:
     permissions:
       actions: write
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     steps:
       - name: Harden Runner

.github/workflows/check_amalgamation.yml

@@ -19,7 +19,7 @@ permissions:
 jobs:
   save:
     if: github.event_name == 'pull_request'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/check_docs_links.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   check_docs_links:
     if: github.repository == 'nlohmann/json'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     timeout-minutes: 30
     steps:
       - name: Harden Runner

.github/workflows/comment_check_amalgamation.yml

@@ -12,7 +12,7 @@ jobs:
   comment:
     # 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
+    runs-on: ubuntu-26.04
     permissions:
       contents: read
       actions: read

.github/workflows/dependency-review.yml

@@ -18,7 +18,7 @@ permissions:
 
 jobs:
   dependency-review:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/flawfinder.yml

@@ -24,7 +24,7 @@ on:
 jobs:
   flawfinder:
     name: Flawfinder
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     permissions:
       actions: read
       contents: read

.github/workflows/labeler.yml

@@ -19,7 +19,7 @@ jobs:
       contents: read
       pull-requests: write
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     steps:
       - name: Harden Runner

.github/workflows/publish_documentation.yml

@@ -34,7 +34,7 @@ jobs:
       contents: write
 
     if: github.repository == 'nlohmann/json'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/scorecards.yml

@@ -24,7 +24,7 @@ permissions:
 jobs:
   analysis:
     name: Scorecard analysis
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     permissions:
       # Needed to upload the results to code-scanning dashboard.
       security-events: write

.github/workflows/stale.yml

@@ -8,7 +8,7 @@ permissions:
 
 jobs:
   stale:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     permissions:
       issues: write

.github/workflows/ubuntu.yml

@@ -18,7 +18,7 @@ concurrency:
 
 jobs:
   ci_test_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: gcc:latest
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -130,7 +130,7 @@ jobs:
         run: cmake --build build --target ${{ matrix.target }}
 
   ci_static_analysis_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: silkeh/clang:22
     strategy:
       matrix:
@@ -149,7 +149,7 @@ jobs:
         run: cmake --build build --target ${{ matrix.target }}
 
   ci_cmake_options:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: ubuntu:24.04
     strategy:
       matrix:
@@ -209,7 +209,7 @@ jobs:
           fail-on-error: false
 
   ci_test_compilers_gcc_old:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         compiler: ['4.8', '4.9', '5', '6']
@@ -251,7 +251,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_g++-${{ matrix.compiler }}
 
   ci_test_compilers_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         # older GCC docker images (4, 5, 6) fail to check out code
@@ -269,7 +269,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_default
 
   ci_test_compilers_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         compiler: ['3.4', '3.5', '3.6', '3.7', '3.8', '3.9', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14', '15-bullseye', '16', '17', '18', '19', '20', '21', '22', 'latest']
@@ -289,7 +289,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_default
 
   ci_test_standards_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: gcc:latest
     strategy:
       matrix:
@@ -306,7 +306,7 @@ jobs:
         run: cmake --build build --target ci_test_gcc_cxx${{ matrix.standard }}
 
   ci_test_standards_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: silkeh/clang:latest
     strategy:
       matrix:
@@ -330,7 +330,7 @@ jobs:
         if: ${{ matrix.stdlib == 'libstdcxx' }}
 
   ci_cuda_example:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       fail-fast: false
       matrix:
@@ -356,7 +356,7 @@ jobs:
     strategy:
       matrix:
         container: ['gcc:latest', 'silkeh/clang:latest']
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: ${{ matrix.container }}
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -383,7 +383,7 @@ jobs:
         run: cmake --build build --target ci_module_cpp20
 
   ci_icpc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     # Intel discontinued the classic icc/icpc compiler in oneAPI 2024.0; this is
     # Intel's own last officially published image that still includes it.
     container: intel/oneapi-hpckit:2023.2.1-devel-ubuntu22.04
@@ -402,7 +402,7 @@ jobs:
         run: cmake --build build --target ci_icpc
 
   ci_icpx:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: intel/oneapi-hpckit:latest
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -416,7 +416,7 @@ jobs:
         run: cmake --build build --target ci_icpx
 
   ci_nvhpc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: nvcr.io/nvidia/nvhpc:25.5-devel-cuda12.9-ubuntu22.04
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1

README.md

@@ -495,7 +495,7 @@ bool key(string_t& val);
 bool parse_error(std::size_t position, const std::string& last_token, const detail::exception& ex);
 ```
 
-The return value of each function determines whether parsing should proceed.
+The return value of each function determines whether parsing should proceed. For `parse_error`, returning `true` [recovers from the error](https://json.nlohmann.me/features/parsing/error_recovery/): the parser repairs the input and continues.
 
 To implement your own SAX handler, proceed as follows:
 
@@ -503,7 +503,7 @@ To implement your own SAX handler, proceed as follows:
 2. Create an object of your SAX interface class, e.g. `my_sax`.
 3. Call `bool json::sax_parse(input, &my_sax)`; where the first parameter can be any input like a string or an input stream and the second parameter is a pointer to your SAX interface.
 
-Note the `sax_parse` function only returns a `bool` indicating the result of the last executed SAX event. It does not return a  `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error -- it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file [`json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp).
+Note the `sax_parse` function only returns a `bool` indicating whether the input was parsed without errors and no SAX event returned `false`. It does not return a  `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error -- it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file [`json_sax.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/input/json_sax.hpp).
 
 ### STL-like access
 

cmake/ci.cmake

@@ -348,20 +348,20 @@ add_custom_target(ci_test_no_thread_local
 
 add_custom_target(ci_test_coverage
     COMMAND CXX=g++ ${CMAKE_COMMAND}
-        -DCMAKE_BUILD_TYPE=Debug -GNinja -DCMAKE_CXX_FLAGS="--coverage;-fprofile-arcs;-ftest-coverage;-fvar-tracking-assignments"
+        -DCMAKE_BUILD_TYPE=Debug -GNinja -DCMAKE_CXX_FLAGS="--coverage;-fprofile-arcs;-ftest-coverage"
         -DJSON_BuildTests=ON
         -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_coverage
     COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_coverage
     COMMAND cd ${PROJECT_BINARY_DIR}/build_coverage && ${CMAKE_CTEST_COMMAND} --parallel ${N} --output-on-failure
 
     COMMAND CXX=g++ ${CMAKE_COMMAND}
-        -DCMAKE_BUILD_TYPE=Debug -GNinja -DCMAKE_CXX_FLAGS="-m32;--coverage;-fprofile-arcs;-ftest-coverage;-fvar-tracking-assignments"
+        -DCMAKE_BUILD_TYPE=Debug -GNinja -DCMAKE_CXX_FLAGS="-m32;--coverage;-fprofile-arcs;-ftest-coverage"
         -DJSON_BuildTests=ON -DJSON_32bitTest=ONLY
         -S${PROJECT_SOURCE_DIR} -B${PROJECT_BINARY_DIR}/build_coverage32
     COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_coverage32
     COMMAND cd ${PROJECT_BINARY_DIR}/build_coverage32 && ${CMAKE_CTEST_COMMAND} --parallel ${N} --output-on-failure
 
-    COMMAND ${LCOV_TOOL} --directory . --capture --output-file json.info --rc branch_coverage=1 --ignore-errors mismatch --ignore-errors unused --ignore-errors inconsistent
+    COMMAND ${LCOV_TOOL} --directory . --capture --output-file json.info --rc branch_coverage=1 --rc geninfo_unexecuted_blocks=1 --ignore-errors mismatch --ignore-errors unused --ignore-errors inconsistent
     COMMAND ${LCOV_TOOL} -e json.info ${SRC_FILES} --output-file json.info.filtered --rc branch_coverage=1 --ignore-errors unused --ignore-errors inconsistent
     COMMAND ${CMAKE_SOURCE_DIR}/tests/thirdparty/imapdl/filterbr.py json.info.filtered > json.info.filtered.noexcept
     COMMAND ${GENHTML_TOOL} --title "JSON for Modern C++" --legend --demangle-cpp --output-directory html --show-details --branch-coverage --ignore-errors inconsistent json.info.filtered.noexcept

docs/mkdocs/docs/api/basic_json/sax_parse.md

@@ -104,7 +104,9 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index
 
 ## Return value
 
-return value of the last processed SAX event
+`#!cpp true` if the input was parsed without errors and no SAX event returned `#!cpp false`; `#!cpp false` otherwise.
+In particular, the result is `#!cpp false` for input with errors, even if the SAX parser recovered from all of them
+(see [error recovery](../../features/parsing/error_recovery.md)).
 
 ## Exception safety
 
@@ -163,6 +165,7 @@ use the same file with stdio functions, but it must not wait for another thread
 - Added `ignore_trailing_commas` in version 3.13.0.
 - Added `tag_handler` in version 3.13.0.
 - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
+- Recovering from parse errors (see [`parse_error`](../json_sax/parse_error.md)) added in version 3.13.0.
 - Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
 - `JSON_PRECISE_STREAM_POSITION` added in version 3.13.0 to optionally leave a `#!cpp std::istream` positioned right
   after the parsed value when `strict` is `#!cpp false`.

docs/mkdocs/docs/api/json_sax/index.md

@@ -7,7 +7,8 @@ struct json_sax;
 
 This class describes the SAX interface used by [sax_parse](../basic_json/sax_parse.md). Each function is called in
 different situations while the input is parsed. The boolean return value informs the parser whether to continue
-processing the input.
+processing the input; for [`parse_error`](parse_error.md), it decides whether to
+[recover from the error](../../features/parsing/error_recovery.md).
 
 For instance, parsing the JSON text `{"a": [1, true]}` triggers the following callbacks, in order:
 

docs/mkdocs/docs/api/json_sax/parse_error.md

@@ -21,11 +21,18 @@ A parse error occurred.
 
 ## Return value
 
-Whether parsing should proceed (**must return `#!cpp false`**).
+Whether to recover from the error:
+
+- `#!cpp false` stops parsing.
+- `#!cpp true` recovers from the error: the error is repaired and parsing continues. If that is not possible, which
+  happens in the binary formats when the end of the item with the error is unknown, the value read so far is completed
+  and parsing stops. See [error recovery](../../features/parsing/error_recovery.md) for how errors are repaired.
+
+Either way, [`sax_parse`](../basic_json/sax_parse.md) returns `#!cpp false`.
 
 ## Examples
 
-??? example
+??? example "Example: (1) the SAX interface"
 
     The example below shows how the SAX interface is used.
 
@@ -39,13 +46,30 @@ Whether parsing should proceed (**must return `#!cpp false`**).
     --8<-- "examples/sax_parse.output"
     ```
 
+??? example "Example: (2) recovering from errors"
+
+    The example below shows how a SAX parser recovers from errors.
+
+    ```cpp
+    --8<-- "examples/sax_parse__error_recovery.cpp"
+    ```
+    
+    Output:
+    
+    ```
+    --8<-- "examples/sax_parse__error_recovery.output"
+    ```
+
 ## See also
 
 - [`sax_parse`](../basic_json/sax_parse.md) - SAX parser
 - [Parsing and Exceptions](../../features/parsing/parse_exceptions.md) - the article on handling parse errors without
   exceptions
+- [Error Recovery](../../features/parsing/error_recovery.md) - the article on recovering from parse errors
 - [SAX Interface](../../features/parsing/sax_interface.md) - guide to event-based parsing
 
 ## Version history
 
 - Added in version 3.2.0.
+- Returning `#!cpp true` recovers from the error since version 3.13.0; before, parsing stopped, but the result of
+  [`sax_parse`](../basic_json/sax_parse.md) could be wrong.

docs/mkdocs/docs/examples/sax_parse__error_recovery.cpp

@@ -0,0 +1,43 @@
+#include <iostream>
+#include <iomanip>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+
+// a SAX parser that creates a JSON value like json::parse does, but that
+// recovers from parse errors instead of stopping at the first one
+class recovering_parser : public nlohmann::detail::json_sax_dom_parser<json>
+{
+  public:
+    explicit recovering_parser(json& result)
+        : nlohmann::detail::json_sax_dom_parser<json>(result, false)
+    {}
+
+    bool parse_error(std::size_t position,
+                     const std::string& /*last_token*/,
+                     const json::exception& ex)
+    {
+        std::cout << "byte " << position << ": " << ex.what() << '\n';
+
+        // repair the input and continue
+        return true;
+    }
+};
+
+int main()
+{
+    // JSON text with several mistakes that ends too early
+    const std::string text = R"({
+    "name": "Hello World",
+    "tags": ["a" "b",],
+    "valid": tru,
+    "size": 1.,
+    "nested": {"x": 1)";
+
+    json result;
+    recovering_parser sax(result);
+    const bool valid = json::sax_parse(text, &sax);
+
+    std::cout << "\nvalid JSON: " << std::boolalpha << valid << '\n'
+              << std::setw(4) << result << std::endl;
+}

docs/mkdocs/docs/examples/sax_parse__error_recovery.output

@@ -0,0 +1,19 @@
+byte 49: [json.exception.parse_error.101] parse error at line 3, column 20: syntax error while parsing array - unexpected string literal; expected ']'
+byte 51: [json.exception.parse_error.101] parse error at line 3, column 22: syntax error while parsing value - unexpected ']'; expected '[', '{', or a literal
+byte 70: [json.exception.parse_error.101] parse error at line 4, column 17: syntax error while parsing value - invalid literal; last read: '"valid": tru,'
+byte 86: [json.exception.parse_error.101] parse error at line 5, column 15: syntax error while parsing value - invalid number; expected digit after '.'; last read: '1.,'
+byte 109: [json.exception.parse_error.101] parse error at line 6, column 22: syntax error while parsing object - unexpected end of input; expected '}'
+
+valid JSON: false
+{
+    "name": "Hello World",
+    "nested": {
+        "x": 1
+    },
+    "size": 1,
+    "tags": [
+        "a",
+        "b"
+    ],
+    "valid": null
+}

docs/mkdocs/docs/features/parsing/error_recovery.md

@@ -0,0 +1,122 @@
+# Error Recovery
+
+By default, parsing stops at the first error. With the [SAX interface](sax_interface.md), you can instead ask the
+parser to *recover*: to repair the error and continue, so that you get as much as possible out of malformed input, for
+instance a file that was cut off, JSON edited by hand, or the output of a language model.
+
+## Recovering from errors
+
+The SAX parser's [`parse_error`](../../api/json_sax/parse_error.md) function is called for every error. Its return value
+decides what happens next:
+
+- `#!cpp false` stops parsing. This is what the SAX parsers of the library do, so [`parse`](../../api/basic_json/parse.md)
+  and [`accept`](../../api/basic_json/accept.md) never recover.
+- `#!cpp true` repairs the error and continues parsing.
+
+When recovering, the SAX parser still receives well-formed events: every `start_object` or `start_array` is followed by
+the matching `end_object` or `end_array`, and every `key` is followed by exactly one value. A SAX parser that creates a
+JSON value, such as the one in the example below, therefore gets a complete value. Parsing always ends, and
+[`sax_parse`](../../api/basic_json/sax_parse.md) returns `#!cpp false` for input that is not valid JSON, even if every
+error was repaired. Each token is reported at most once, and the SAX parser can stop at any error by returning
+`#!cpp false`.
+
+!!! example
+
+    The example below derives a SAX parser from the library's parser for `json` values (`json_sax_dom_parser`),
+    and recovers from all errors.
+
+    ```cpp
+    --8<-- "examples/sax_parse__error_recovery.cpp"
+    ```
+    
+    Output:
+    
+    ```
+    --8<-- "examples/sax_parse__error_recovery.output"
+    ```
+
+## How errors are repaired
+
+Each error is repaired with the smallest local edit: a missing separator is inserted, a stray token is removed, what can
+be read of a broken string or number is kept, and a value that cannot be read at all becomes `#!json null`.
+
+| Mistake                   | Repair                                                                         | Example                                  | Result                     |
+|---------------------------|--------------------------------------------------------------------------------|------------------------------------------|----------------------------|
+| missing `,` or `:`        | inserted                                                                       | `#!json [1 2]`, `#!json {"a" 1}`         | `[1,2]`, `{"a":1}`         |
+| missing value             | `#!json null` for an object key or between commas in an array                  | `#!json {"a":}`, `#!json [1,,2]`         | `{"a":null}`, `[1,null,2]` |
+| trailing comma            | removed                                                                        | `#!json [1,2,]`                          | `[1,2]`                    |
+| broken string             | invalid escapes and bytes are replaced (see below); a line break ends the string | `#!json ["a\qb"]`                        | `["aqb"]`                  |
+| broken number             | the longest valid beginning is kept                                            | `#!json [1., 2e+]`                       | `[1,2]`                    |
+| unreadable value          | `#!json null`                                                                  | `#!json [1, NaN, tru]`                   | `[1,null,null]`            |
+| number too large          | passed as infinity, together with its text                                     | `#!json [1e999]`                         | infinity (see below)       |
+| stray `:`                 | removed                                                                        | `#!json ["a":1]`                         | `["a",1]`                  |
+| member without a key      | skipped up to the next `,` or `}`                                              | `#!json {1:2, "b":3}`                    | `{"b":3}`                  |
+| wrong closing bracket     | closes the innermost array or object                                           | `#!json {"a":[1,2}, "b":3}`              | `{"a":[1,2],"b":3}`        |
+| input ends too early      | all open arrays and objects are closed                                         | `#!json {"a":[1,2`                       | `{"a":[1,2]}`              |
+| text before the value     | skipped                                                                        | `#!json )]}'{"a":1}`                     | `{"a":1}`                  |
+
+In a string, an unknown escape like `\q` stands for the escaped character (`q`), as in JavaScript. An invalid `\u`
+escape, a lone surrogate, and ill-formed UTF-8 are each replaced by U+FFFD (REPLACEMENT CHARACTER), and control
+characters are kept. A string without its closing quote ends at the next line break or at the end of the input.
+
+The input after the top-level value is not repaired: as without recovery, it is reported as an error, and parsing stops.
+
+## Binary formats
+
+The binary formats ([BJData](../binary_formats/bjdata.md), [BON8](../binary_formats/bon8.md),
+[BSON](../binary_formats/bson.md), [CBOR](../binary_formats/cbor.md), [MessagePack](../binary_formats/messagepack.md),
+and [UBJSON](../binary_formats/ubjson.md)) have no delimiters to find the next value by. So what can be repaired depends
+on whether the end of the item with the error is known, a distinction that
+[RFC 8949, Section 5.3](https://www.rfc-editor.org/rfc/rfc8949.html#section-5.3) makes for CBOR, too.
+
+If the item is complete, but cannot be passed on as it is, it is replaced, and parsing continues after it:
+
+| Mistake                                                             | Formats                 | Repair                                                                  |
+|---------------------------------------------------------------------|-------------------------|-------------------------------------------------------------------------|
+| tag, if `tag_handler` is `cbor_tag_handler_t::error` (the default)  | CBOR                    | ignored                                                                 |
+| simple value other than `false`, `true`, and `null`, like undefined | CBOR                    | `#!json null`                                                           |
+| number too large for a custom `number_float_t`, like `float`        | all                     | infinity                                                                |
+| character (`C`) that is not ASCII                                   | BJData, UBJSON          | U+FFFD                                                                  |
+| invalid high-precision number (`H`)                                 | BJData, UBJSON          | the longest valid beginning is kept, as for JSON text, or `#!json null` |
+| high-precision number too large                                     | BJData, UBJSON          | passed as infinity, together with its text                              |
+| object key that is not a string                                     | BON8, CBOR, MessagePack | the member is skipped                                                   |
+| element of a type the library does not read, like ObjectId or date  | BSON                    | `#!json null`                                                           |
+| string without its terminator                                       | BSON                    | kept                                                                    |
+| document whose size does not match its content                      | BSON                    | kept                                                                    |
+
+CBOR tags and simple values are repaired as [RFC 8949, Section 6.1](https://www.rfc-editor.org/rfc/rfc8949.html#section-6.1)
+suggests for converting CBOR to JSON. By default, [`sax_parse`](../../api/basic_json/sax_parse.md) reports every tag as
+an error; when recovering, tags are then ignored like with
+[`cbor_tag_handler_t::ignore`](../../api/basic_json/cbor_tag_handler_t.md). Strings that are not valid UTF-8 are no
+error: like [`from_cbor`](../../api/basic_json/from_cbor.md) and the other functions by default, `sax_parse` passes
+them on as they are.
+
+After any other error, the end of the item is unknown: the input ended, a byte is not a valid type marker, or a size
+cannot be right. Parsing then stops, and the value read so far is completed: a key that waits for its value gets
+`#!json null`, and all open arrays and objects are closed. This keeps everything before the error of an input that was
+cut off. The exception is BSON, which stores the size of every document: an element whose end is unknown gets
+`#!json null`, the rest of its document is skipped, and parsing continues after the document.
+
+## Limitations
+
+- A repair is a guess. For example, `#!json {"a" "b": 1}` could be meant as `#!json {"a": "b"}` or as
+  `#!json {"a": null, "b": 1}`; it is repaired to the former. Treat recovered values as a best effort, and check the
+  reported errors.
+- A closing bracket always closes the innermost array or object. If a bracket is missing rather than wrong, the
+  repair differs from the intention: `#!json {"a": {"b": [1, 2}, "c": 3}` is repaired to
+  `#!json {"a": {"b": [1, 2], "c": 3}}`, although `#!json {"a": {"b": [1, 2]}, "c": 3}` may have been meant.
+- Keys without quotes, and strings in single quotes, are not supported; such members are skipped.
+- In the binary formats, a member that is skipped because its key is not a string is lost, and so are the elements of a
+  BSON document after one whose end is unknown.
+- A number that is too large for `number_float_t` is passed as positive or negative infinity. The SAX parser's
+  `number_float` also gets the number's text, but a JSON value cannot store it, and
+  [`dump`](../../api/basic_json/dump.md) serializes infinity as `#!json null`.
+- When parsing is not strict (see [`sax_parse`](../../api/basic_json/sax_parse.md)), a repair may read parts of the
+  input after the value, for instance of the next value in a stream of concatenated values.
+
+## See also
+
+- [SAX interface](sax_interface.md) - implement a custom SAX handler
+- [`parse_error`](../../api/json_sax/parse_error.md) - the SAX event for parse errors
+- [`sax_parse`](../../api/basic_json/sax_parse.md) - generate SAX events
+- [parsing and exceptions](parse_exceptions.md) - control error handling

docs/mkdocs/docs/features/parsing/index.md

@@ -141,7 +141,7 @@ See [Zero-copy JSON views](../json_view.md) for the concept and the trade-offs.
 When the input is not valid JSON, the `parse` function throws an exception by default. If exceptions are undesired or
 unavailable, the parser can instead return a discarded value, or [`accept`](../../api/basic_json/accept.md) can be used
 to only check whether an input is valid JSON. See [parsing and exceptions](parse_exceptions.md) for the available
-options.
+options. To get as much as possible out of malformed input, a SAX parser can [recover from errors](error_recovery.md).
 
 ## See also
 
@@ -155,6 +155,7 @@ options.
 - [SAX interface](sax_interface.md) - implement a custom SAX handler
 - [Zero-copy JSON views](../json_view.md) - parse into a read-only document and read it through views
 - [parsing and exceptions](parse_exceptions.md) - control error handling
+- [error recovery](error_recovery.md) - get as much as possible out of malformed input
 - [parsing untrusted input](untrusted_input.md) - what to consider when parsing input from untrusted sources
 - [`operator>>`](../../api/operator_gtgt.md) - deserialize from stream
 - [`json_sax`](../../api/json_sax/index.md) - documentation of the SAX interface

docs/mkdocs/docs/features/parsing/parse_exceptions.md

@@ -68,7 +68,8 @@ bool parse_error(std::size_t position,
                  const json::exception& ex);
 ```
 
-The return value indicates whether the parsing should continue, so the function should usually return `#!cpp false`.
+The return value decides whether to stop parsing (`#!cpp false`) or to repair the error and continue
+(`#!cpp true`); see [error recovery](error_recovery.md) for the latter.
 
 ??? example "Example: report parse errors without exceptions"
 

docs/mkdocs/docs/features/parsing/sax_interface.md

@@ -62,7 +62,8 @@ bool key(string_t& val);
 bool parse_error(std::size_t position, const std::string& last_token, const json::exception& ex);
 ```
 
-The return value of each function determines whether parsing should proceed.
+The return value of each function determines whether parsing should proceed. For `parse_error`, returning
+`#!cpp true` [recovers from the error](error_recovery.md).
 
 Object keys are passed to `key` decoded and validated: escape sequences are already resolved, so different spellings of
 the same name yield the same string. See [`key`](../../api/json_sax/key.md#notes) for the exact guarantees.
@@ -101,7 +102,7 @@ To implement your own SAX handler, proceed as follows:
 2. Create an object of your SAX interface class, e.g. `my_sax`.
 3. Call `#!cpp bool json::sax_parse(input, &my_sax);` where the first parameter can be any input like a string or an input stream and the second parameter is a pointer to your SAX interface.
 
-Note the `sax_parse` function only returns a `#!cpp bool` indicating the result of the last executed SAX event. It does not return `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error - it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file `json_sax.hpp`.
+Note the `sax_parse` function only returns a `#!cpp bool` indicating whether the input was parsed without errors and no SAX event returned `#!cpp false`. It does not return `json` value - it is up to you to decide what to do with the SAX events. Furthermore, no exceptions are thrown in case of a parse error - it is up to you what to do with the exception object passed to your `parse_error` implementation. Internally, the SAX interface is used for the DOM parser (class `json_sax_dom_parser`) as well as the acceptor (`json_sax_acceptor`), see file `json_sax.hpp`.
 
 ## See also
 

docs/mkdocs/mkdocs.yml

@@ -142,6 +142,7 @@ nav:
       - features/performance.md
       - Parsing:
           - features/parsing/index.md
+          - features/parsing/error_recovery.md
           - features/parsing/json_lines.md
           - features/parsing/large_and_partial_input.md
           - features/parsing/parse_exceptions.md

include/nlohmann/detail/conversions/from_json.hpp

@@ -91,7 +91,7 @@ const typename BasicJsonType::binary_t& binary_value(const BasicJsonType& j)
 }
 
 template<typename View, enable_if_t<is_json_view<View>::value, int> = 0>
-typename View::basic_json_type::binary_t binary_value(const View& /*unused*/) // LCOV_EXCL_LINE
+typename View::basic_json_type::binary_t binary_value(const View& /*unused*/)
 {
     return {}; // LCOV_EXCL_LINE
 }

include/nlohmann/detail/input/input_adapters.hpp

@@ -545,9 +545,12 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character_slow()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // the get area is exhausted (get_character() handles the other case),
-        // so sbumpc() refills it
-        save_token_segment();
+        // sbumpc() refills the get area if it is exhausted
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            save_token_segment();
+        }
 #endif
 
         auto res = sb->sbumpc();
@@ -560,13 +563,17 @@ class input_stream_adapter
             is->clear(is->rdstate() | std::ios::eofbit);
         }
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        else
+        else if (JSON_HEDLEY_UNLIKELY(refill))
         {
             // the consumed character is at gptr() - 1, unless the streambuf
             // has no get area and returned it from uflow()
             const char* const next = streambuf_access::get_ptr(sb);
             after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
         }
+        else
+        {
+            current_in_get_area = true;
+        }
 #endif
         return res;
     }
@@ -789,17 +796,22 @@ class iterator_input_adapter
         return get_consumed_count() + eof_reads;
     }
 
-    // number of newlines in the consumed range [0, last_index); @a line_start
-    // is set to the index after the last of them (0 if there is none); only
-    // valid when supports_seek
-    std::size_t count_consumed_lines(std::size_t last_index, std::size_t& line_start) const
+    // number of newlines in the consumed range [first_index, last_index); if
+    // there is one, @a line_start is set to the index after the last of them,
+    // otherwise it is left unchanged; only valid when supports_seek
+    std::size_t count_consumed_lines(std::size_t first_index, std::size_t last_index, std::size_t& line_start) const
     {
-        const auto to = std::next(begin, static_cast<typename std::iterator_traits<IteratorType>::difference_type>(last_index));
+        using difference_type = typename std::iterator_traits<IteratorType>::difference_type;
+        const auto from = std::next(begin, static_cast<difference_type>(first_index));
+        const auto to = std::next(from, static_cast<difference_type>(last_index - first_index));
         const auto newline = char_traits<char_type>::to_char_type('\n');
         using reverse_it = std::reverse_iterator<IteratorType>;
-        const auto last_newline = std::find(reverse_it(to), reverse_it(begin), newline);
-        line_start = static_cast<std::size_t>(std::distance(begin, last_newline.base()));
-        return static_cast<std::size_t>(std::count(begin, last_newline.base(), newline));
+        const auto last_newline = std::find(reverse_it(to), reverse_it(from), newline);
+        if (last_newline.base() != from)
+        {
+            line_start = static_cast<std::size_t>(std::distance(begin, last_newline.base()));
+        }
+        return static_cast<std::size_t>(std::count(from, last_newline.base(), newline));
     }
 
     // append the already-consumed characters in the half-open range

include/nlohmann/detail/input/json_sax.hpp

@@ -138,7 +138,9 @@ struct json_sax
     @param[in] position    the position in the input where the error occurs
     @param[in] last_token  the last read token
     @param[in] ex          an exception object describing the error
-    @return whether parsing should proceed (must return false)
+    @return whether to recover from the error: false stops parsing; true
+            repairs the error and continues, or, if that is not possible,
+            stops after completing the value read so far
     */
     virtual bool parse_error(std::size_t position,
                              const std::string& last_token,
@@ -485,6 +487,9 @@ stored in place as it arrives, so after a parse error the value holds what was
 read up to it.
 
 @tparam BasicJsonType  the JSON type
+@tparam InputAdapterType  the input adapter of the lexer that can be passed to
+                          the constructor to record diagnostic positions; it
+                          does not matter if no lexer is passed
 @tparam Collect  whether to collect the values of containers of unknown size on
                  a stack (only for a caller that does not use the value after a
                  parse error)
@@ -493,7 +498,7 @@ read up to it.
                    it, so any type with its three functions works (as
                    materialize() of json_view uses it)
 */
-template<typename BasicJsonType, typename InputAdapterType, bool Collect = false, typename LexerType = lexer<BasicJsonType, InputAdapterType>>
+template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type, bool Collect = false, typename LexerType = lexer<BasicJsonType, InputAdapterType>>
 class json_sax_dom_parser : public json_sax_dom_error_state
 {
   public:
@@ -799,6 +804,8 @@ class json_sax_dom_parser : public json_sax_dom_error_state
         JSON_HEDLEY_NEVER_INLINE
         void grow()
         {
+            // the stack starts with local_capacity frames and only grows
+            JSON_ASSERT(capacity != 0);
             const std::size_t new_capacity = capacity * 2;
             std::unique_ptr<frame[]> new_heap(new frame[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
             for (std::size_t i = 0; i < count; ++i)
@@ -999,7 +1006,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
         ordered_data.members[f.ordered.dest_member].second = std::move(value);
     }
 
-    static void place_member(const frame& /*f*/, BasicJsonType&& /*value*/, std::false_type /*indexed*/) noexcept {} // LCOV_EXCL_LINE
+    static void place_member(const frame& /*f*/, BasicJsonType&& /*value*/, std::false_type /*indexed*/) noexcept {}
 
     /// store the members of a new object directly in it
     bool start_stored_object(std::size_t len)
@@ -1614,7 +1621,7 @@ class json_sax_dom_binary_parser : public json_sax_dom_error_state
     lexer_t* m_lexer_ref = nullptr;
 };
 
-template<typename BasicJsonType, typename InputAdapterType>
+template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
 class json_sax_dom_callback_parser : public json_sax_dom_error_state
 {
   public:
@@ -1737,7 +1744,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
         key_stack.push_back(val);
 
         // add discarded value at the given key and store the reference for later
-        if (keep)
+        if (keep && ref_stack.back())
         {
             auto& obj = *ref_stack.back()->m_data.m_value.object;
             // a single lookup: insert the placeholder, or find the existing member
@@ -1794,7 +1801,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
 
         const string_t object_key = pop_container();
 
-        if (!ref_stack.empty() && ref_stack.back())
+        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
         {
             // remove discarded value
             remove_discarded_value(*ref_stack.back(), object_key);
@@ -1960,7 +1967,8 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
     */
     string_t current_key() const
     {
-        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object())
+        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object()
+                && !key_stack.empty())
         {
             return key_stack.back();
         }

include/nlohmann/detail/input/lexer.hpp

@@ -10,7 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
-#include <cstdint> // uint32_t
+#include <cstdint> // uint8_t, uint32_t
 #include <cstdio> // snprintf
 #include <cstring> // memcmp
 #include <initializer_list> // initializer_list
@@ -300,16 +300,14 @@ class lexer : public lexer_base<BasicJsonType>
     /// calls would (including the position and token bookkeeping of a
     /// streaming adapter, see bulk_consume) and leaves @a current holding the last of
     /// the 4 digits, just as the last such get() would; the codepoint is
-    /// written to @a out. Makes no state change and returns false for fewer
-    /// than 4 remaining bytes or any of the 4 bytes not being a hex digit, so
-    /// the caller falls back unchanged to the per-character loop, which then
-    /// reports the same diagnostic (stopping at the first invalid digit) as
-    /// before this optimization.
+    /// written to @a out. Makes no state change and returns false for a
+    /// pending unget, fewer than 4 remaining bytes, or any of the 4 bytes not
+    /// being a hex digit, so the caller falls back unchanged to the
+    /// per-character loop, which then reports the same diagnostic (stopping
+    /// at the first invalid digit) as before this optimization.
     bool get_codepoint_bulk(std::true_type /*bulk*/, int& out)
     {
-        // no unget is pending inside a string (see get_after_string_run())
-        JSON_ASSERT(!next_unget);
-        if (ia.bulk_remaining() < 4)
+        if (next_unget || ia.bulk_remaining() < 4)
         {
             return false;
         }
@@ -387,6 +385,20 @@ class lexer : public lexer_base<BasicJsonType>
         return codepoint;
     }
 
+    /// the code point of the surrogate pair @a high (U+D800..U+DBFF) and @a low (U+DC00..U+DFFF)
+    static constexpr int combine_surrogates(const int high, const int low) noexcept
+    {
+        return static_cast<int>(
+                   // high surrogate occupies the most significant 22 bits
+                   (static_cast<unsigned int>(high) << 10u)
+                   // low surrogate occupies the least significant 15 bits
+                   + static_cast<unsigned int>(low)
+                   // there is still the 0xD800, 0xDC00, and 0x10000 noise
+                   // in the result, so we have to subtract with:
+                   // (0xD800 << 10) + DC00 - 0x10000 = 0x35FDC00
+                   - 0x35FDC00u);
+    }
+
     /*!
     @brief check if the next byte(s) are inside a given range
 
@@ -420,6 +432,7 @@ class lexer : public lexer_base<BasicJsonType>
             else
             {
                 error_message = "invalid string: ill-formed UTF-8 byte";
+                error_cause = error_kind::string_ill_formed_utf8;
                 return false;
             }
         }
@@ -439,10 +452,11 @@ class lexer : public lexer_base<BasicJsonType>
     template<bool Keep>
     char_int_type get_after_string_run(std::true_type /*bulk*/, std::integral_constant<bool, Keep> keep)
     {
-        // scan_string() is entered from scan_after_whitespace(), whose current
-        // was read by skip_whitespace() (its first get() clears a pending
-        // unget), and nothing in scan_string() calls unget()
-        JSON_ASSERT(!next_unget);
+        // a pending unget must be consumed through the normal path first
+        if (next_unget)
+        {
+            return get();
+        }
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
         {
@@ -542,6 +556,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case char_traits<char_type>::eof():
                 {
                     error_message = "invalid string: missing closing quote";
+                    error_cause = error_kind::string;
                     return token_type::parse_error;
                 }
 
@@ -598,6 +613,7 @@ class lexer : public lexer_base<BasicJsonType>
                             if (JSON_HEDLEY_UNLIKELY(codepoint1 == -1))
                             {
                                 error_message = "invalid string: '\\u' must be followed by 4 hex digits";
+                                error_cause = error_kind::string_invalid_escape;
                                 return token_type::parse_error;
                             }
 
@@ -605,13 +621,23 @@ class lexer : public lexer_base<BasicJsonType>
                             if (0xD800 <= codepoint1 && codepoint1 <= 0xDBFF)
                             {
                                 // expect next \uxxxx entry
-                                if (JSON_HEDLEY_LIKELY(get() == '\\' && get() == 'u'))
+                                if (JSON_HEDLEY_LIKELY(get() == '\\'))
                                 {
+                                    if (JSON_HEDLEY_UNLIKELY(get() != 'u'))
+                                    {
+                                        // current is the character escaped by the backslash
+                                        error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
+                                        error_cause = error_kind::string_invalid_escape;
+                                        string_error_resume = resume_kind::escaped_character;
+                                        return token_type::parse_error;
+                                    }
+
                                     const int codepoint2 = get_codepoint();
 
                                     if (JSON_HEDLEY_UNLIKELY(codepoint2 == -1))
                                     {
                                         error_message = "invalid string: '\\u' must be followed by 4 hex digits";
+                                        error_cause = error_kind::string_invalid_escape;
                                         return token_type::parse_error;
                                     }
 
@@ -619,25 +645,23 @@ class lexer : public lexer_base<BasicJsonType>
                                     if (JSON_HEDLEY_LIKELY(0xDC00 <= codepoint2 && codepoint2 <= 0xDFFF))
                                     {
                                         // overwrite codepoint
-                                        codepoint = static_cast<int>(
-                                                        // high surrogate occupies the most significant 22 bits
-                                                        (static_cast<unsigned int>(codepoint1) << 10u)
-                                                        // low surrogate occupies the least significant 15 bits
-                                                        + static_cast<unsigned int>(codepoint2)
-                                                        // there is still the 0xD800, 0xDC00, and 0x10000 noise
-                                                        // in the result, so we have to subtract with:
-                                                        // (0xD800 << 10) + DC00 - 0x10000 = 0x35FDC00
-                                                        - 0x35FDC00u);
+                                        codepoint = combine_surrogates(codepoint1, codepoint2);
                                     }
                                     else
                                     {
+                                        // the second escape was read completely and is a
+                                        // code point of its own
                                         error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
+                                        error_cause = error_kind::string_invalid_escape;
+                                        string_error_resume = resume_kind::after_escape;
+                                        string_error_codepoint = codepoint2;
                                         return token_type::parse_error;
                                     }
                                 }
                                 else
                                 {
                                     error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
+                                    error_cause = error_kind::string_invalid_escape;
                                     return token_type::parse_error;
                                 }
                             }
@@ -645,7 +669,10 @@ class lexer : public lexer_base<BasicJsonType>
                             {
                                 if (JSON_HEDLEY_UNLIKELY(0xDC00 <= codepoint1 && codepoint1 <= 0xDFFF))
                                 {
+                                    // the escape was read completely
                                     error_message = "invalid string: surrogate U+DC00..U+DFFF must follow U+D800..U+DBFF";
+                                    error_cause = error_kind::string_invalid_escape;
+                                    string_error_resume = resume_kind::after_escape;
                                     return token_type::parse_error;
                                 }
                             }
@@ -662,6 +689,7 @@ class lexer : public lexer_base<BasicJsonType>
                         // other characters after escape
                         default:
                             error_message = "invalid string: forbidden character after backslash";
+                            error_cause = error_kind::string;
                             return token_type::parse_error;
                     }
 
@@ -738,6 +766,7 @@ class lexer : public lexer_base<BasicJsonType>
                         }
                     };
                     error_message = control_character_messages[static_cast<std::size_t>(current)];
+                    error_cause = error_kind::string;
                     return token_type::parse_error;
                 }
 
@@ -960,6 +989,7 @@ class lexer : public lexer_base<BasicJsonType>
                 default:
                 {
                     error_message = "invalid string: ill-formed UTF-8 byte";
+                    error_cause = error_kind::string_ill_formed_utf8;
                     return token_type::parse_error;
                 }
             }
@@ -1015,6 +1045,7 @@ class lexer : public lexer_base<BasicJsonType>
                         case char_traits<char_type>::eof():
                         {
                             error_message = "invalid comment; missing closing '*/'";
+                            error_cause = error_kind::unclosed_comment;
                             return false;
                         }
 
@@ -1045,6 +1076,7 @@ class lexer : public lexer_base<BasicJsonType>
             default:
             {
                 error_message = "invalid comment; expecting '/' or '*' after '/'";
+                error_cause = error_kind::other;
                 return false;
             }
         }
@@ -1170,6 +1202,7 @@ scan_number_minus:
             default:
             {
                 error_message = "invalid number; expected digit after '-'";
+                error_cause = error_kind::number;
                 return token_type::parse_error;
             }
         }
@@ -1256,6 +1289,7 @@ scan_number_decimal1:
             default:
             {
                 error_message = "invalid number; expected digit after '.'";
+                error_cause = error_kind::number;
                 return token_type::parse_error;
             }
         }
@@ -1324,6 +1358,7 @@ scan_number_exponent:
             {
                 error_message =
                     "invalid number; expected '+', '-', or digit after exponent";
+                error_cause = error_kind::number;
                 return token_type::parse_error;
             }
         }
@@ -1350,6 +1385,7 @@ scan_number_sign:
             default:
             {
                 error_message = "invalid number; expected digit after exponent sign";
+                error_cause = error_kind::number;
                 return token_type::parse_error;
             }
         }
@@ -1411,7 +1447,7 @@ scan_number_done:
                 return token_type::value_unsigned;
             }
         }
-        else // value_integer (the callers handle value_float themselves)
+        else if (number_type == token_type::value_integer)
         {
             if (parse_integer_signed(first, last, value_integer))
             {
@@ -1517,9 +1553,11 @@ scan_number_done:
     */
     token_type scan_number_bulk_contiguous()
     {
-        // called right after scan_after_whitespace() read current (see
-        // get_after_string_run()), so no unget is pending
-        JSON_ASSERT(!next_unget);
+        // a pending unget offsets the buffer position from current; fall back
+        if (next_unget)
+        {
+            return token_type::uninitialized;
+        }
         const std::size_t rem = ia.bulk_remaining();
         if (rem == 0)
         {
@@ -1540,7 +1578,11 @@ scan_number_done:
         if (data[0] == '-')
         {
             number_type = token_type::value_integer;
-            i = 1; // avail >= 2: rem == 0 returned above
+            i = 1;
+            if (i >= avail)
+            {
+                return token_type::uninitialized;
+            }
         }
         const std::size_t integer_begin = i;
         if (data[i] == '0')
@@ -1771,6 +1813,7 @@ scan_number_done:
             if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != static_cast<char_type>(rest[i])))
             {
                 error_message = "invalid literal";
+                error_cause = error_kind::other;
                 return token_type::parse_error;
             }
         }
@@ -1782,10 +1825,7 @@ scan_number_done:
     /// the error at the right character
     JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
     {
-        // called right after scan_after_whitespace() read current (see
-        // get_after_string_run()), so no unget is pending
-        JSON_ASSERT(!next_unget);
-        if (ia.bulk_remaining() < length
+        if (next_unget || ia.bulk_remaining() < length
                 || std::memcmp(ia.bulk_data(), rest, length) != 0)
         {
             return false;
@@ -2192,17 +2232,25 @@ scan_number_done:
         return position.chars_read_total;
     }
 
-    /// seekable adapter: count the lines in the consumed input; O(input read
-    /// so far), but only called on errors
+    /// seekable adapter: count the lines in the consumed input. Only the
+    /// input consumed since the previous call is scanned, so a parse that
+    /// reports many errors (a SAX parser recovering from them) stays linear
+    /// in the input instead of rescanning it for every error.
     position_t get_position_impl(std::true_type /*lazy*/) const
     {
         position_t result;
         result.chars_read_total = get_chars_read_total();
         // reads at EOF count as characters but are not part of the input
         const std::size_t consumed = (std::min)(result.chars_read_total, ia.get_consumed_count());
-        std::size_t line_start = 0;
-        result.lines_read = ia.count_consumed_lines(consumed, line_start);
-        result.chars_read_current_line = result.chars_read_total - line_start;
+        if (JSON_HEDLEY_UNLIKELY(consumed < position_cache.consumed))
+        {
+            // the consumed input never shrinks; recount from the start if it did
+            position_cache = {};
+        }
+        position_cache.lines += ia.count_consumed_lines(position_cache.consumed, consumed, position_cache.line_start);
+        position_cache.consumed = consumed;
+        result.lines_read = position_cache.lines;
+        result.chars_read_current_line = result.chars_read_total - position_cache.line_start;
         return result;
     }
 
@@ -2386,6 +2434,7 @@ scan_number_done:
         if (get_chars_read_total() == 0 && !skip_bom())
         {
             error_message = "invalid BOM; must be 0xEF 0xBB 0xBF if given";
+            error_cause = error_kind::other;
             return token_type::parse_error;
         }
 
@@ -2495,10 +2544,583 @@ scan_number_done:
             // error
             default:
                 error_message = "invalid literal";
+                error_cause = error_kind::other;
                 return token_type::parse_error;
         }
     }
 
+  public:
+    /////////////////////
+    // error recovery
+    /////////////////////
+
+    /*!
+    @brief make the best of the token that scan() rejected
+
+    Called by the parser after scan() returned token_type::parse_error and the
+    SAX parser asked to recover from the error (see #3989). Keeps what can be
+    read of the token and skips the rest:
+
+    - A string keeps its characters. An unknown escape stands for the escaped
+      character itself (as in JavaScript), an invalid Unicode escape and ill-formed
+      UTF-8 become U+FFFD, and a control character is kept. A line break or the
+      end of the input ends a string that lacks its closing quote.
+    - A number keeps its longest valid prefix, e.g. `1` for `1.` or `1e+`.
+    - A block comment that is not closed runs to the end of the input.
+    - Anything else is skipped.
+
+    The rest of an invalid token is skipped up to the next delimiter
+    (whitespace, a structural character, or a quote). A delimiter that the
+    invalid token consumed is returned to the input, so that the next scan()
+    reads it.
+
+    @return token_type::value_string or a number token type if a string or a
+            number could be read, token_type::end_of_input for a block comment
+            that is not closed, token_type::uninitialized otherwise
+    */
+    token_type recover_token()
+    {
+        const resume_kind resume = string_error_resume;
+        const int codepoint = string_error_codepoint;
+        string_error_resume = resume_kind::character;
+        string_error_codepoint = -1;
+
+        const error_kind cause = error_cause;
+        error_cause = error_kind::other;
+
+        switch (cause)
+        {
+            case error_kind::string:
+            case error_kind::string_invalid_escape:
+            case error_kind::string_ill_formed_utf8:
+                return recover_string(cause, resume, codepoint);
+
+            case error_kind::number:
+                return recover_number();
+
+            case error_kind::unclosed_comment:
+                // the comment runs to the end of the input
+                return token_type::end_of_input;
+
+            case error_kind::other:
+            default:
+                skip_to_delimiter();
+                return token_type::uninitialized;
+        }
+    }
+
+    /*!
+    @brief return the token that scan() read last to the input, so that the
+           next scan() reads it again
+
+    Called by the parser when recovering from an error. The token must be a
+    single character (',', ':', '[', ']', '{', or '}') or the end of the
+    input, and scan() must have read it last.
+    */
+    void unget_token()
+    {
+        JSON_ASSERT(!next_unget);
+        unget();
+    }
+
+    /*!
+    @brief let the token string for the next error begin at the current character
+
+    The token string of an error reaches back to the beginning of the last
+    string or number. After an error, the parser calls this function so that
+    the next error does not report (and, with many errors, copy) everything
+    read since then.
+    */
+    void restart_token_string()
+    {
+        restart_token_string_impl(std::integral_constant<bool, lazy_token_string> {});
+    }
+
+  private:
+    /// how recover_string() continues after the error scan_string() reported
+    enum class resume_kind : std::uint8_t
+    {
+        /// current is the next character of the string (or the end of input)
+        character,
+        /// current is the character escaped by the preceding backslash
+        escaped_character,
+        /// current is the last character of a complete escape
+        after_escape
+    };
+
+    /// what kind of token scan() rejected, which decides how recover_token() repairs it
+    enum class error_kind : std::uint8_t
+    {
+        /// anything not listed below; skipped up to the next delimiter
+        other,
+        /// a string
+        string,
+        /// a string with an invalid Unicode escape, which becomes U+FFFD
+        string_invalid_escape,
+        /// a string with ill-formed UTF-8, which becomes U+FFFD
+        string_ill_formed_utf8,
+        /// a number
+        number,
+        /// a block comment that is not closed
+        unclosed_comment
+    };
+
+    /// whether current ends an invalid token (see recover_token())
+    bool current_is_delimiter() const noexcept
+    {
+        switch (current)
+        {
+            case ' ':
+            case '\t':
+            case '\n':
+            case '\r':
+            case '[':
+            case ']':
+            case '{':
+            case '}':
+            case ',':
+            case ':':
+            case '\"':
+#if !JSON_STRICT_NUL_HANDLING
+            case '\0':
+#endif
+            case char_traits<char_type>::eof():
+                return true;
+
+            case '/':
+                return ignore_comments;
+
+            default:
+                return false;
+        }
+    }
+
+    /// skip the rest of an invalid token and return its delimiter to the input
+    void skip_to_delimiter()
+    {
+        while (!current_is_delimiter())
+        {
+            get();
+        }
+
+        if (current != char_traits<char_type>::eof())
+        {
+            unget();
+        }
+    }
+
+    /// append U+FFFD REPLACEMENT CHARACTER to token_buffer
+    void add_replacement_character()
+    {
+        add_codepoint(0xFFFD);
+    }
+
+    /// append the UTF-8 encoding of @a codepoint (not a surrogate) to token_buffer
+    void add_codepoint(const int codepoint)
+    {
+        JSON_ASSERT(0x00 <= codepoint && codepoint <= 0x10FFFF);
+        encode_utf8(static_cast<std::uint32_t>(codepoint), [this](std::uint32_t byte)
+        {
+            add(static_cast<char_int_type>(byte));
+        });
+    }
+
+    /// append a code point read from a Unicode escape; a surrogate becomes U+FFFD
+    void add_escaped_codepoint(const int codepoint)
+    {
+        if (0xD800 <= codepoint && codepoint <= 0xDFFF)
+        {
+            add_replacement_character();
+        }
+        else
+        {
+            add_codepoint(codepoint);
+        }
+    }
+
+    /*!
+    @brief remove an incomplete UTF-8 sequence from the end of token_buffer
+
+    next_byte_in_range() adds the bytes of a sequence as it checks them, so
+    when it rejects a byte, the beginning of the sequence is already in
+    token_buffer, which otherwise holds only complete sequences.
+
+    @return whether an incomplete sequence was removed
+    */
+    bool remove_incomplete_utf8_sequence()
+    {
+        std::size_t lead = token_buffer.size();
+        std::size_t continuation_bytes = 0;
+        while (lead > 0 && continuation_bytes < 3
+                && (static_cast<unsigned char>(token_buffer[lead - 1]) & 0xC0u) == 0x80u)
+        {
+            --lead;
+            ++continuation_bytes;
+        }
+        if (lead == 0)
+        {
+            return false;
+        }
+
+        const auto lead_byte = static_cast<unsigned char>(token_buffer[lead - 1]);
+        std::size_t expected = 0;
+        if (lead_byte >= 0xF0)
+        {
+            expected = 3;
+        }
+        else if (lead_byte >= 0xE0)
+        {
+            expected = 2;
+        }
+        else if (lead_byte >= 0xC0)
+        {
+            expected = 1;
+        }
+        if (continuation_bytes >= expected)
+        {
+            return false;
+        }
+
+        token_buffer.resize(lead - 1);
+        return true;
+    }
+
+    /*!
+    @brief read the UTF-8 sequence that begins with current, which is not ASCII
+    @return whether the next character must be read; false if current still
+            needs to be handled, because it does not belong to the sequence
+    */
+    bool recover_utf8_sequence()
+    {
+        // the number of continuation bytes and the range of the first one;
+        // see the ranges in scan_string()
+        std::size_t count = 0;
+        char_int_type low = 0x80;
+        char_int_type high = 0xBF;
+        if (current >= 0xC2 && current <= 0xDF)
+        {
+            count = 1;
+        }
+        else if (current >= 0xE0 && current <= 0xEF)
+        {
+            count = 2;
+            low = (current == 0xE0) ? 0xA0 : 0x80;
+            high = (current == 0xED) ? 0x9F : 0xBF;
+        }
+        else if (current >= 0xF0 && current <= 0xF4)
+        {
+            count = 3;
+            low = (current == 0xF0) ? 0x90 : 0x80;
+            high = (current == 0xF4) ? 0x8F : 0xBF;
+        }
+        else
+        {
+            // an ill-formed byte
+            add_replacement_character();
+            return true;
+        }
+
+        const std::size_t start = token_buffer.size();
+        add(current);
+        for (std::size_t i = 0; i < count; ++i)
+        {
+            get();
+            if (current < low || current > high)
+            {
+                token_buffer.resize(start);
+                add_replacement_character();
+                return false;
+            }
+            add(current);
+            low = 0x80;
+            high = 0xBF;
+        }
+        return true;
+    }
+
+    /*!
+    @brief read the low surrogate that must follow the high surrogate @a high
+    @return whether the next character must be read; false if current still
+            needs to be handled
+    */
+    bool recover_low_surrogate(int high)
+    {
+        while (true)
+        {
+            if (get() != '\\')
+            {
+                add_replacement_character();
+                return false;
+            }
+            if (get() != 'u')
+            {
+                add_replacement_character();
+                // not 'u', so this does not come back here
+                return recover_escape();
+            }
+
+            const int low = get_codepoint();
+            if (low == -1)
+            {
+                add_replacement_character();
+                return false;
+            }
+            if (0xDC00 <= low && low <= 0xDFFF)
+            {
+                add_codepoint(combine_surrogates(high, low));
+                return true;
+            }
+
+            // high has no low surrogate
+            add_replacement_character();
+            if (low < 0xD800 || low > 0xDBFF)
+            {
+                add_codepoint(low);
+                return true;
+            }
+            // another high surrogate
+            high = low;
+        }
+    }
+
+    /*!
+    @brief read the escape whose backslash was read; current is the escaped character
+    @return whether the next character must be read; false if current still
+            needs to be handled
+    */
+    bool recover_escape()
+    {
+        switch (current)
+        {
+            case '\"':
+                add('\"');
+                return true;
+            case '\\':
+                add('\\');
+                return true;
+            case '/':
+                add('/');
+                return true;
+            case 'b':
+                add('\b');
+                return true;
+            case 'f':
+                add('\f');
+                return true;
+            case 'n':
+                add('\n');
+                return true;
+            case 'r':
+                add('\r');
+                return true;
+            case 't':
+                add('\t');
+                return true;
+
+            case 'u':
+            {
+                const int codepoint = get_codepoint();
+                if (codepoint == -1)
+                {
+                    add_replacement_character();
+                    return false;
+                }
+                if (0xD800 <= codepoint && codepoint <= 0xDBFF)
+                {
+                    return recover_low_surrogate(codepoint);
+                }
+                add_escaped_codepoint(codepoint);
+                return true;
+            }
+
+            // an unknown escape stands for the escaped character
+            default:
+                return false;
+        }
+    }
+
+    /*!
+    @brief read the rest of a string after scan_string() rejected it
+
+    token_buffer holds what scan_string() read before the error. See
+    recover_token() for how errors are repaired.
+
+    @param[in] cause      the kind of error scan_string() reported
+    @param[in] resume     how to continue, see resume_kind
+    @param[in] codepoint  for a high surrogate followed by an escape of another
+                          code point: that code point; -1 otherwise
+    */
+    token_type recover_string(const error_kind cause, const resume_kind resume, const int codepoint)
+    {
+        // whether the next character must be read before it can be handled
+        bool fetch = false;
+
+        if (cause == error_kind::string_invalid_escape
+                || (cause == error_kind::string_ill_formed_utf8 && remove_incomplete_utf8_sequence()))
+        {
+            add_replacement_character();
+        }
+
+        switch (resume)
+        {
+            case resume_kind::escaped_character:
+                fetch = recover_escape();
+                break;
+            case resume_kind::after_escape:
+                if (0xD800 <= codepoint && codepoint <= 0xDBFF)
+                {
+                    fetch = recover_low_surrogate(codepoint);
+                }
+                else
+                {
+                    if (codepoint != -1)
+                    {
+                        add_escaped_codepoint(codepoint);
+                    }
+                    fetch = true;
+                }
+                break;
+            case resume_kind::character:
+            default:
+                break;
+        }
+
+        while (true)
+        {
+            if (fetch)
+            {
+                get();
+            }
+            fetch = true;
+
+            switch (current)
+            {
+                case '\"':
+                // a line break or the end of the input ends a string that
+                // lacks its closing quote
+                case '\n':
+                case '\r':
+                case char_traits<char_type>::eof():
+                    return token_type::value_string;
+
+#if !JSON_STRICT_NUL_HANDLING
+                case '\0':
+                    // the end of the input, see scan()
+                    unget();
+                    return token_type::value_string;
+#endif
+
+                case '\\':
+                    get();
+                    fetch = recover_escape();
+                    break;
+
+                default:
+                    if (current < 0x80)
+                    {
+                        // including control characters
+                        add(current);
+                    }
+                    else
+                    {
+                        fetch = recover_utf8_sequence();
+                    }
+                    break;
+            }
+        }
+    }
+
+    /*!
+    @brief keep the longest valid prefix of a number that scan_number() rejected
+
+    token_buffer holds the characters scan_number() accepted before the error,
+    so the prefix ends at its last digit.
+    */
+    token_type recover_number()
+    {
+        // only size(), operator[], and resize() are used, which every string
+        // type the library supports provides
+        std::size_t length = token_buffer.size();
+        while (length != 0 && (token_buffer[length - 1] < '0' || token_buffer[length - 1] > '9'))
+        {
+            --length;
+        }
+        token_buffer.resize(length);
+
+        if (length == 0)
+        {
+            skip_to_delimiter();
+            return token_type::uninitialized;
+        }
+
+        if (decimal_point_position >= length)
+        {
+            decimal_point_position = std::string::npos;
+        }
+
+        std::size_t exponent = std::string::npos;
+        for (std::size_t i = 0; i < length; ++i)
+        {
+            if (token_buffer[i] == 'e' || token_buffer[i] == 'E')
+            {
+                exponent = i;
+                break;
+            }
+        }
+        const std::size_t mantissa_end = (exponent == std::string::npos) ? length : exponent;
+        token_type number_type = token_type::value_unsigned;
+        if (decimal_point_position != std::string::npos || exponent != std::string::npos)
+        {
+            number_type = token_type::value_float;
+        }
+        else if (token_buffer[0] == '-')
+        {
+            number_type = token_type::value_integer;
+        }
+
+        const token_type result = convert_number(number_type, mantissa_end);
+        skip_to_delimiter();
+        return result;
+    }
+
+    /// seekable or token-tracking adapter: the token string begins at current
+    void restart_token_string_impl(std::true_type /*lazy*/)
+    {
+        restart_token_string_lazy(std::integral_constant<bool, adapter_token> {});
+    }
+
+    /// seekable adapter: the token string begins at current, which was consumed
+    void restart_token_string_lazy(std::false_type /*adapter_token*/) noexcept
+    {
+        const std::size_t consumed = ia.get_consumed_count();
+        token_string_start = (consumed > 0 && current != char_traits<char_type>::eof()) ? consumed - 1 : consumed;
+    }
+
+    /// token-tracking adapter: the token begins with current, or with the next
+    /// character if current was put back or is the end of input
+    void restart_token_string_lazy(std::true_type /*adapter_token*/)
+    {
+        if (!next_unget && current != char_traits<char_type>::eof())
+        {
+            ia.mark_token_start(current);
+        }
+        else
+        {
+            ia.begin_token();
+        }
+    }
+
+    /// streaming adapter: the token string begins at current; a character
+    /// that was put back is copied again when it is read again
+    void restart_token_string_impl(std::false_type /*lazy*/)
+    {
+        token_string.clear();
+        if (!next_unget && current != char_traits<char_type>::eof())
+        {
+            token_string.push_back(char_traits<char_type>::to_char_type(current));
+        }
+    }
+
     /// input adapter
     InputAdapterType ia;
 
@@ -2523,6 +3145,19 @@ scan_number_done:
     /// that unget() can restore the column instead of leaving it at 0
     std::size_t chars_read_before_newline = 0;
 
+    /// seekable adapter: what get_position() counted last, so that the next
+    /// call only scans the input consumed since
+    struct position_cache_t
+    {
+        /// consumed characters scanned so far
+        std::size_t consumed = 0;
+        /// newlines among them
+        std::size_t lines = 0;
+        /// index after the last of these newlines
+        std::size_t line_start = 0;
+    };
+    mutable position_cache_t position_cache {};
+
     /// raw input token string for error messages; only populated for streaming
     /// adapters (seekable adapters reconstruct it lazily via token_string_start)
     std::vector<char_type> token_string {};
@@ -2543,6 +3178,15 @@ scan_number_done:
     /// a description of occurred lexer errors
     const char* error_message = "";
 
+    /// what kind of token scan() rejected; set together with error_message
+    error_kind error_cause = error_kind::other;
+    /// how recover_token() continues a string that scan_string() rejected;
+    /// set only on the error paths that need more than error_message
+    resume_kind string_error_resume = resume_kind::character;
+    /// the code point of the second escape when a high surrogate is followed
+    /// by an escape that is not a low surrogate; -1 otherwise
+    int string_error_codepoint = -1;
+
     // number values
     number_integer_t value_integer = 0;
     number_unsigned_t value_unsigned = 0;

include/nlohmann/detail/input/parser.hpp

@@ -152,25 +152,72 @@ class parser
     bool accept(const bool strict = true)
     {
         json_sax_acceptor<BasicJsonType> sax_acceptor;
-        return sax_parse(&sax_acceptor, strict);
+        return sax_parse_impl<false>(&sax_acceptor, strict);
     }
 
+    /*!
+    @brief public SAX interface
+
+    If the SAX parser's parse_error() returns true, the parser recovers from
+    the error: it repairs the input and continues (see #3989).
+
+    @param[in] sax     the SAX parser
+    @param[in] strict  whether to expect the last token to be EOF
+    @return whether the input was parsed without errors and no SAX event
+            returned false
+    */
     template<typename SAX>
     JSON_HEDLEY_NON_NULL(2)
     bool sax_parse(SAX* sax, const bool strict = true)
     {
-        (void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
-        const bool result = sax_parse_internal(sax);
-
-        if (result)
-        {
-            return finish_input(*sax, strict);
-        }
-
-        return false;
+        return sax_parse_impl<true>(sax, strict);
     }
 
   private:
+    /// what sax_parse_internal() does after an object key was expected
+    enum class next_step : std::uint8_t
+    {
+        /// stop parsing
+        stop,
+        /// parse a value that begins with last_token
+        parse_value,
+        /// evaluate the state of the innermost container, which reads
+        /// last_token again
+        evaluate_state
+    };
+
+    template<bool AllowRecovery, typename SAX>
+    JSON_HEDLEY_NON_NULL(2)
+    bool sax_parse_impl(SAX* sax, const bool strict)
+    {
+        (void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
+        const bool result = sax_parse_internal<AllowRecovery>(sax);
+
+        if (result)
+        {
+            if (strict)
+            {
+                // strict mode: next byte must be EOF; after recovering from an
+                // error, the end of the input may already have been read
+                if (last_token != token_type::end_of_input && get_token() != token_type::end_of_input)
+                {
+                    // the value is complete, so there is nothing to recover
+                    static_cast<void>(report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr),
+                                                   std::integral_constant<bool, AllowRecovery> {}));
+                    return false;
+                }
+            }
+            else
+            {
+                // the caller keeps using the input: position it right after
+                // the value by leaving the character that terminated it
+                m_lexer.release_lookahead();
+            }
+        }
+
+        return result && !error_reported;
+    }
+
     /// the text of the current float token for @a sax (see sax_ignores_number_text)
     template<typename SAX>
     const string_t& number_float_text(SAX* /*sax*/)
@@ -238,17 +285,26 @@ class parser
     template<typename DomSax>
     bool parse_dom(DomSax& sdp, const bool strict)
     {
-        sax_parse_internal(&sdp);
+        sax_parse_internal<false>(&sdp);
 
         static_cast<void>(finish_input(sdp, strict));
 
         return !sdp.is_errored();
     }
 
-    template<typename SAX>
+    /*!
+    @brief parse a JSON value and pass it to a SAX parser
+
+    @tparam AllowRecovery  whether to recover from an error if the SAX parser's
+                           parse_error() returns true; false for the SAX parsers
+                           of parse() and accept(), which never do, so that no
+                           code for recovering is generated for them
+    */
+    template<bool AllowRecovery, typename SAX>
     JSON_HEDLEY_NON_NULL(2)
     bool sax_parse_internal(SAX* sax)
     {
+        const std::integral_constant<bool, AllowRecovery> allow_recovery{};
         // value to avoid a goto (see comment where set to true)
         bool skip_to_state_evaluation = false;
 
@@ -287,10 +343,18 @@ class parser
                             break;
                         }
 
-                        // parse key
+                        // remember we are now inside an object
+                        states.push_back(0);
+
+                        // parse key (the steps of parse_key(), which are
+                        // repeated here and below for speed)
                         if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                         {
-                            return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
+                            if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
+                            {
+                                return false;
+                            }
+                            continue;
                         }
                         if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                         {
@@ -300,12 +364,13 @@ class parser
                         // parse separator (:)
                         if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                         {
-                            return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
+                            if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
+                            {
+                                return false;
+                            }
+                            continue;
                         }
 
-                        // remember we are now inside an object
-                        states.push_back(0);
-
                         // parse values
                         get_token();
                         continue;
@@ -341,9 +406,11 @@ class parser
 
                         if (JSON_HEDLEY_UNLIKELY(!std::isfinite(res)))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
-                                                    m_lexer.get_token_string(),
-                                                    out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
+                            if (!overflow_error(sax, res, allow_recovery))
+                            {
+                                return false;
+                            }
+                            break;
                         }
 
                         if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, number_float_text(sax))))
@@ -411,16 +478,63 @@ class parser
                     case token_type::parse_error:
                     {
                         // using "uninitialized" to avoid an "expected" message
-                        return syntax_error(*sax, exception_message(token_type::uninitialized, "value"));
+                        if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr), allow_recovery))
+                        {
+                            return false;
+                        }
+
+                        // recover: keep what can be read of the token
+                        recover_token(allow_recovery);
+                        if (last_token != token_type::uninitialized)
+                        {
+                            // a string or a number
+                            continue;
+                        }
+                        if (states.empty())
+                        {
+                            // look for the value after the garbage
+                            if (!skip_to_value(allow_recovery))
+                            {
+                                return false;
+                            }
+                            continue;
+                        }
+                        // nothing could be read
+                        if (JSON_HEDLEY_UNLIKELY(!sax->null()))
+                        {
+                            return false;
+                        }
+                        break;
                     }
                     case token_type::end_of_input:
                     {
                         if (JSON_HEDLEY_UNLIKELY(m_lexer.get_chars_read_total() == 1))
                         {
-                            return syntax_error(*sax, empty_input_message());
+                            // there is nothing to recover
+                            static_cast<void>(report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(),
+                                                           empty_input_message(), nullptr), allow_recovery));
+                            return false;
                         }
 
-                        return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
+                        if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
+                        {
+                            return false;
+                        }
+
+                        // recover: the input ends where a value is missing
+                        if (states.empty())
+                        {
+                            // there is no value
+                            return false;
+                        }
+                        if (!recover_missing_value(sax, states, allow_recovery))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        unget_token(allow_recovery);
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                     case token_type::uninitialized:
                     case token_type::end_array:
@@ -430,7 +544,35 @@ class parser
                     case token_type::literal_or_value:
                     default: // the last token was unexpected
                     {
-                        return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
+                        if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr), allow_recovery))
+                        {
+                            return false;
+                        }
+
+                        // recover
+                        if (states.empty())
+                        {
+                            // look for the value after the garbage
+                            if (!skip_to_value(allow_recovery))
+                            {
+                                return false;
+                            }
+                            continue;
+                        }
+                        if (last_token == token_type::name_separator)
+                        {
+                            // a stray ':'; the value may follow
+                            get_token();
+                            continue;
+                        }
+                        if (!recover_missing_value(sax, states, allow_recovery))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        unget_token(allow_recovery);
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                 }
             }
@@ -481,7 +623,30 @@ class parser
                     continue;
                 }
 
-                return syntax_error(*sax, exception_message(token_type::end_array, "array"));
+                if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr), allow_recovery))
+                {
+                    return false;
+                }
+
+                // recover
+                if (last_token == token_type::end_of_input)
+                {
+                    // the input ends inside the array
+                    return close_containers(sax, states, allow_recovery);
+                }
+                if (last_token == token_type::end_object)
+                {
+                    // a wrong closing bracket closes the innermost container
+                    if (JSON_HEDLEY_UNLIKELY(!sax->end_array()))
+                    {
+                        return false;
+                    }
+                    states.pop_back();
+                    skip_to_state_evaluation = true;
+                }
+                // otherwise, a missing ',' (or a stray ':', which value
+                // parsing drops): the next value begins here
+                continue;
             }
 
             // states.back() is false -> object
@@ -498,9 +663,12 @@ class parser
                     // parse key
                     if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                     {
-                        return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
+                        if (!continue_after(key_error(sax, allow_recovery, false), skip_to_state_evaluation))
+                        {
+                            return false;
+                        }
+                        continue;
                     }
-
                     if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
                     {
                         return false;
@@ -509,7 +677,11 @@ class parser
                     // parse separator (:)
                     if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                     {
-                        return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
+                        if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
+                        {
+                            return false;
+                        }
+                        continue;
                     }
 
                     // parse values
@@ -537,10 +709,546 @@ class parser
                 continue;
             }
 
-            return syntax_error(*sax, exception_message(token_type::end_object, "object"));
+            if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr), allow_recovery))
+            {
+                return false;
+            }
+
+            // recover
+            if (last_token == token_type::end_of_input)
+            {
+                // the input ends inside the object
+                return close_containers(sax, states, allow_recovery);
+            }
+            if (last_token == token_type::end_array)
+            {
+                // a wrong closing bracket closes the innermost container
+                if (JSON_HEDLEY_UNLIKELY(!sax->end_object()))
+                {
+                    return false;
+                }
+                states.pop_back();
+                skip_to_state_evaluation = true;
+                continue;
+            }
+            if (!continue_after(recover_member(sax, allow_recovery), skip_to_state_evaluation))
+            {
+                return false;
+            }
         }
     }
 
+    /*!
+    @brief continue sax_parse_internal() after a recovery
+    @return whether to continue parsing
+    */
+    bool continue_after(const next_step step, bool& skip_to_state_evaluation)
+    {
+        if (step == next_step::evaluate_state)
+        {
+            // the state evaluation reads the token again
+            m_lexer.unget_token();
+            skip_to_state_evaluation = true;
+        }
+        return step != next_step::stop;
+    }
+
+    /// the parser for parse() and accept() never recovers: stop parsing
+    JSON_INTERNAL_ALWAYS_INLINE
+    static std::false_type continue_after(std::false_type /*step*/, bool& /*skip_to_state_evaluation*/) noexcept
+    {
+        return {};
+    }
+
+    /*!
+    @brief parse an object key and the name separator (:) after it
+
+    last_token is the token where the key is expected. sax_parse_internal()
+    repeats these steps rather than calling this function, which is used
+    when recovering from an error.
+
+    @return next_step::parse_value if the value follows, with last_token its
+            first token; next_step::evaluate_state if the object's state is
+            to be evaluated after recovering from an error; next_step::stop
+            to stop parsing
+    */
+    template<typename SAX>
+    next_step parse_key(SAX* sax)
+    {
+        const std::true_type allow_recovery{};
+
+        if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
+        {
+            return key_error(sax, allow_recovery, false);
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string_token())))
+        {
+            return next_step::stop;
+        }
+
+        // parse separator (:)
+        if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
+        {
+            return key_error(sax, allow_recovery, true);
+        }
+
+        // the value begins with the next token
+        get_token();
+        return next_step::parse_value;
+    }
+
+    /*!
+    @brief report a number that is too large for number_float_t, and recover
+           from the error by passing the value on; the SAX parser gets the
+           number's text as well
+
+    This is a separate function, as reading other numbers is measurably
+    slower if the error is handled where they are read.
+
+    @param[in] sax    the SAX parser
+    @param[in] value  the value that is not finite
+    @return whether to continue parsing
+    */
+    template<typename SAX>
+    bool overflow_error(SAX* sax, const number_float_t value, std::true_type allow_recovery)
+    {
+        if (!report_error(sax, out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr), allow_recovery))
+        {
+            return false;
+        }
+        return sax->number_float(value, number_float_text(sax));
+    }
+
+    /// @copydoc overflow_error
+    template<typename SAX>
+    JSON_INTERNAL_ALWAYS_INLINE
+    std::false_type overflow_error(SAX* sax, const number_float_t /*value*/, std::false_type allow_recovery)
+    {
+        return report_error(sax, out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr), allow_recovery);
+    }
+
+    /*!
+    @brief report a missing key, or a missing name separator (:) after the
+           key; the parser for parse() and accept() never recovers
+
+    @param[in] key_read  whether the key was read, so that the name separator
+                         is missing
+    @return std::false_type, see report_error()
+    */
+    template<typename SAX>
+    JSON_INTERNAL_ALWAYS_INLINE
+    std::false_type key_error(SAX* sax, std::false_type allow_recovery, const bool key_read)
+    {
+        return report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), key_read
+                            ? exception_message(token_type::name_separator, "object separator")
+                            : exception_message(token_type::value_string, "object key"), nullptr), allow_recovery);
+    }
+
+    /*!
+    @brief report a missing key, or a missing name separator (:) after the
+           key, and recover from it
+
+    @param[in] key_read  whether the key was read, so that the name separator
+                         is missing
+    */
+    template<typename SAX>
+    next_step key_error(SAX* sax, std::true_type allow_recovery, const bool key_read)
+    {
+        if (!key_read)
+        {
+            if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr), allow_recovery))
+            {
+                return next_step::stop;
+            }
+            return recover_key(sax);
+        }
+
+        if (!report_error(sax, parse_error::create(exception_id::syntax_error, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr), allow_recovery))
+        {
+            return next_step::stop;
+        }
+        return recover_name_separator(sax);
+    }
+
+    /////////////////////
+    // error recovery
+    /////////////////////
+
+    /*
+    The functions below repair an error after the SAX parser's parse_error()
+    returned true (see #3989). Each mistake is repaired by the smallest local
+    edit: a missing ',' or ':' is inserted, a stray token is removed, what can
+    be read of an invalid string or number is kept (see
+    lexer::recover_token()), a missing value becomes null, a wrong closing
+    bracket closes the innermost container, and the end of the input closes
+    all of them. The events stay balanced, and every key() is followed by
+    exactly one value.
+
+    A repair hands a token to the state evaluation, by returning it to the
+    lexer (lexer::unget_token()) so that the state evaluation reads it again,
+    only if it is ',', ']', '}', or the end of the input. The state evaluation
+    hands a token to value or key parsing only if it is none of them, so a
+    token is never handed back and forth. Every other step reads a token or
+    closes a container, so parsing always ends.
+    */
+
+    /*!
+    @brief report an error to the SAX parser; the parser for parse() and
+           accept() never recovers
+
+    @return std::false_type rather than false: its value is known where the
+            function is called even if the call is not inlined, so the code
+            for recovering is not generated
+    */
+    template<typename SAX, typename Exception>
+    JSON_INTERNAL_ALWAYS_INLINE
+    std::false_type report_error(SAX* sax, const Exception& ex, std::false_type /*allow_recovery*/)
+    {
+        static_cast<void>(sax); // MSVC 2015 does not count calling a static parse_error() as using it
+        error_reported = true;
+        static_cast<void>(sax->parse_error(m_lexer.get_position(), m_lexer.get_token_string(), ex));
+        return {};
+    }
+
+    /*!
+    @brief report an error to the SAX parser
+    @return whether to recover from the error
+    */
+    template<typename SAX, typename Exception>
+    bool report_error(SAX* sax, const Exception& ex, std::true_type /*allow_recovery*/)
+    {
+        static_cast<void>(sax); // MSVC 2015 does not count calling a static parse_error() as using it
+        const std::size_t position = m_lexer.get_position().chars_read_total;
+        if (error_reported && position == last_error_position && last_token == last_error_token)
+        {
+            // a repair handed on the token of the error it repaired; the
+            // token was reported already, and the SAX parser asked to recover
+            return true;
+        }
+
+        error_reported = true;
+        last_error_position = position;
+        last_error_token = last_token;
+
+        if (!sax->parse_error(m_lexer.get_position(), m_lexer.get_token_string(), ex))
+        {
+            return false;
+        }
+
+        // the token string of the next error begins here
+        m_lexer.restart_token_string();
+        return true;
+    }
+
+    /*!
+    @brief keep what can be read of the token that the lexer rejected
+
+    The error was reported for the rejected token, so it is not reported again
+    for the token it is repaired to (see lexer::recover_token()).
+    */
+    token_type recover_token()
+    {
+        last_token = m_lexer.recover_token();
+        last_error_position = m_lexer.get_position().chars_read_total;
+        last_error_token = last_token;
+        return last_token;
+    }
+
+    // The functions below are called from sax_parse_internal() after an error
+    // was reported. The parser for parse() and accept() stopped there, so for
+    // it they are stubs: the code for recovering is then not even referenced,
+    // and unoptimized builds do not emit it either.
+
+    /// @copydoc recover_token()
+    JSON_INTERNAL_ALWAYS_INLINE
+    token_type recover_token(std::true_type /*allow_recovery*/)
+    {
+        return recover_token();
+    }
+
+    /// @copydoc recover_token()
+    JSON_INTERNAL_ALWAYS_INLINE
+    static std::false_type recover_token(std::false_type /*allow_recovery*/) noexcept
+    {
+        return {};
+    }
+
+    /// return the token that was read last to the lexer (see lexer::unget_token())
+    JSON_INTERNAL_ALWAYS_INLINE
+    void unget_token(std::true_type /*allow_recovery*/)
+    {
+        m_lexer.unget_token();
+    }
+
+    /// @copydoc unget_token(std::true_type)
+    JSON_INTERNAL_ALWAYS_INLINE
+    static void unget_token(std::false_type /*allow_recovery*/) noexcept {}
+
+    /// @copydoc skip_to_value
+    JSON_INTERNAL_ALWAYS_INLINE
+    static std::false_type skip_to_value(std::false_type /*allow_recovery*/) noexcept
+    {
+        return {};
+    }
+
+    /// @copydoc recover_missing_value
+    template<typename SAX>
+    JSON_INTERNAL_ALWAYS_INLINE
+    static std::false_type recover_missing_value(SAX* /*sax*/, const std::vector<std::uint8_t>& /*states*/, std::false_type /*allow_recovery*/) noexcept
+    {
+        return {};
+    }
+
+    /// pass the end events of all open containers
+    template<typename SAX>
+    bool close_containers(SAX* sax, std::vector<std::uint8_t>& states, std::true_type /*allow_recovery*/)
+    {
+        while (!states.empty())
+        {
+            const bool is_array = states.back() != 0;
+            states.pop_back();
+            if (JSON_HEDLEY_UNLIKELY(is_array ? !sax->end_array() : !sax->end_object()))
+            {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    /// @copydoc close_containers
+    template<typename SAX>
+    JSON_INTERNAL_ALWAYS_INLINE
+    static std::false_type close_containers(SAX* /*sax*/, std::vector<std::uint8_t>& /*states*/, std::false_type /*allow_recovery*/) noexcept
+    {
+        return {};
+    }
+
+    /*!
+    @brief read tokens until one begins a value, skipping everything before
+           the top-level value
+    @return whether a value begins with last_token
+    */
+    bool skip_to_value(std::true_type /*allow_recovery*/)
+    {
+        while (true)
+        {
+            switch (get_token())
+            {
+                case token_type::begin_array:
+                case token_type::begin_object:
+                case token_type::literal_false:
+                case token_type::literal_null:
+                case token_type::literal_true:
+                case token_type::value_float:
+                case token_type::value_integer:
+                case token_type::value_string:
+                case token_type::value_unsigned:
+                    return true;
+
+                case token_type::end_of_input:
+                    return false;
+
+                case token_type::parse_error:
+                    recover_token();
+                    if (last_token != token_type::uninitialized)
+                    {
+                        return true;
+                    }
+                    break;
+
+                case token_type::uninitialized:
+                case token_type::end_array:
+                case token_type::end_object:
+                case token_type::name_separator:
+                case token_type::value_separator:
+                case token_type::literal_or_value:
+                default:
+                    break;
+            }
+        }
+    }
+
+    /*!
+    @brief skip the rest of an object member that cannot be read
+
+    Reads tokens, beginning with last_token, until a ',', '}', or ']' that is
+    not inside a container that begins in the skipped tokens, or the end of
+    the input.
+    */
+    void skip_member()
+    {
+        std::size_t depth = 0;
+        while (true)
+        {
+            switch (last_token)
+            {
+                case token_type::begin_array:
+                case token_type::begin_object:
+                    ++depth;
+                    break;
+
+                case token_type::end_array:
+                case token_type::end_object:
+                    if (depth == 0)
+                    {
+                        return;
+                    }
+                    --depth;
+                    break;
+
+                case token_type::value_separator:
+                    if (depth == 0)
+                    {
+                        return;
+                    }
+                    break;
+
+                case token_type::end_of_input:
+                    return;
+
+                case token_type::parse_error:
+                    recover_token();
+                    break;
+
+                case token_type::uninitialized:
+                case token_type::literal_true:
+                case token_type::literal_false:
+                case token_type::literal_null:
+                case token_type::value_string:
+                case token_type::value_unsigned:
+                case token_type::value_integer:
+                case token_type::value_float:
+                case token_type::name_separator:
+                case token_type::literal_or_value:
+                default:
+                    break;
+            }
+            get_token();
+        }
+    }
+
+    /*!
+    @brief pass a value where it is missing
+
+    last_token is ',', ']', '}', or the end of the input, where a value was
+    expected. In an object, the key gets null; in an array, a ',' where a
+    value is missing stands for null (as in JavaScript), while an array that
+    ends there just ends.
+    */
+    template<typename SAX>
+    bool recover_missing_value(SAX* sax, const std::vector<std::uint8_t>& states, std::true_type /*allow_recovery*/)
+    {
+        JSON_ASSERT(!states.empty());
+        if (states.back() == 0 || last_token == token_type::value_separator)
+        {
+            return sax->null();
+        }
+        return true;
+    }
+
+    /// recover from a missing key; last_token is where it was expected
+    template<typename SAX>
+    next_step recover_key(SAX* sax)
+    {
+        switch (last_token)
+        {
+            case token_type::value_separator:
+            case token_type::end_object:
+            case token_type::end_array:
+            case token_type::end_of_input:
+                // no member: the object's state handles the token
+                return next_step::evaluate_state;
+
+            case token_type::parse_error:
+                recover_token();
+                if (last_token == token_type::value_string)
+                {
+                    // a key that could be repaired
+                    return parse_key(sax);
+                }
+                skip_member();
+                return next_step::evaluate_state;
+
+            case token_type::uninitialized:
+            case token_type::literal_true:
+            case token_type::literal_false:
+            case token_type::literal_null:
+            case token_type::value_string:
+            case token_type::value_unsigned:
+            case token_type::value_integer:
+            case token_type::value_float:
+            case token_type::begin_array:
+            case token_type::begin_object:
+            case token_type::name_separator:
+            case token_type::literal_or_value:
+            default:
+                // a member without a key
+                skip_member();
+                return next_step::evaluate_state;
+        }
+    }
+
+    /// recover from a missing name separator (:) after the key; last_token
+    /// is where it was expected
+    template<typename SAX>
+    next_step recover_name_separator(SAX* sax)
+    {
+        switch (last_token)
+        {
+            case token_type::value_separator:
+            case token_type::end_object:
+            case token_type::end_array:
+            case token_type::end_of_input:
+                // the value is missing as well
+                return sax->null() ? next_step::evaluate_state : next_step::stop;
+
+            case token_type::uninitialized:
+            case token_type::literal_true:
+            case token_type::literal_false:
+            case token_type::literal_null:
+            case token_type::value_string:
+            case token_type::value_unsigned:
+            case token_type::value_integer:
+            case token_type::value_float:
+            case token_type::begin_array:
+            case token_type::begin_object:
+            case token_type::name_separator:
+            case token_type::parse_error:
+            case token_type::literal_or_value:
+            default:
+                // a missing ':'; the value begins here
+                return next_step::parse_value;
+        }
+    }
+
+    /// recover from a token after an object member that is neither ',' nor
+    /// '}' (nor ']' or the end of the input, which the caller handles)
+    template<typename SAX>
+    next_step recover_member(SAX* sax, std::true_type /*allow_recovery*/)
+    {
+        if (last_token == token_type::parse_error)
+        {
+            recover_token();
+        }
+        if (last_token == token_type::value_string)
+        {
+            // a missing ','; the next key begins here
+            return parse_key(sax);
+        }
+        skip_member();
+        return next_step::evaluate_state;
+    }
+
+    /// the parser for parse() and accept() never recovers (and does not come
+    /// here, as report_error() returned false)
+    template<typename SAX>
+    JSON_INTERNAL_ALWAYS_INLINE
+    std::false_type recover_member(SAX* /*sax*/, std::false_type /*allow_recovery*/) const noexcept
+    {
+        return {};
+    }
+
     /// get next token from lexer
     token_type get_token()
     {
@@ -575,7 +1283,10 @@ class parser
     {
         std::string error_msg = "syntax error ";
 
-        error_msg += concat("while parsing ", context, ' ');
+        if (!context.empty())
+        {
+            error_msg += concat("while parsing ", context, ' ');
+        }
 
         error_msg += "- ";
 
@@ -595,7 +1306,7 @@ class parser
         }
 
         return error_msg;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
   private:
     /// callback function
@@ -608,6 +1319,12 @@ class parser
     const bool allow_exceptions = true;
     /// whether trailing commas in objects and arrays should be ignored (true) or signaled as errors (false)
     const bool ignore_trailing_commas = false;
+    /// whether an error was reported to the SAX parser
+    bool error_reported = false;
+    /// the position of the last reported error
+    std::size_t last_error_position = 0;
+    /// the token of the last reported error
+    token_type last_error_token = token_type::uninitialized;
 };
 
 }  // namespace detail

include/nlohmann/detail/iterators/iter_impl.hpp

@@ -108,9 +108,6 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        // m_it is already value-initialized, so this is not needed for
-        // correctness; it is kept because GCC generates faster loops with it
-        // (iterating a parsed document is 0.5-2.7 % slower without it, #6005)
         if (m_object->is_object())
         {
             m_it.object_iterator = typename object_t::iterator();

include/nlohmann/detail/json_pointer.hpp

@@ -304,7 +304,7 @@ class json_pointer
         result.reference_tokens.insert(result.reference_tokens.end(), lhs.reference_tokens.begin(), lhs.reference_tokens.end());
         result.reference_tokens.insert(result.reference_tokens.end(), rhs.reference_tokens.begin(), rhs.reference_tokens.end());
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /// @brief create a new JSON pointer by appending the unescaped token at the end of the JSON pointer
     /// @sa https://json.nlohmann.me/api/json_pointer/operator_slash/
@@ -315,7 +315,7 @@ class json_pointer
         result.reference_tokens.insert(result.reference_tokens.end(), lhs.reference_tokens.begin(), lhs.reference_tokens.end());
         result.reference_tokens.push_back(std::move(token));
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /// @brief create a new JSON pointer by appending the array-index-token at the end of the JSON pointer
     /// @sa https://json.nlohmann.me/api/json_pointer/operator_slash/
@@ -2180,7 +2180,7 @@ class json_pointer
                     {
                         // create an entry in the array
                         current = &current->operator[](array_index<BasicJsonType>(token));
-                        break; // LCOV_EXCL_LINE (needs an array index with 10 or more digits: more than 1e9 elements)
+                        break;
                     }
 
                     /*
@@ -2217,7 +2217,7 @@ class json_pointer
         json_pointer<string_t> result;
         result.reference_tokens = reference_tokens;
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     json_pointer<string_t> convert()&&
     {

include/nlohmann/detail/macro_scope.hpp

@@ -215,6 +215,17 @@
     #define JSON_NO_UNIQUE_ADDRESS
 #endif
 
+// Inlines small functions even in unoptimized builds, so that they are not
+// emitted. The parsers for parse(), accept(), and from_*() use it for the
+// functions that stand in for the code recovering from errors (see #3989).
+// MSVC is left to decide, as it warns (C4714) where it does not inline a
+// __forceinline function.
+#if defined(_MSC_VER) && !defined(__clang__)
+    #define JSON_INTERNAL_ALWAYS_INLINE
+#else
+    #define JSON_INTERNAL_ALWAYS_INLINE JSON_HEDLEY_ALWAYS_INLINE
+#endif
+
 // Clang targeting MinGW does not survive the thread_local storage the copy
 // constructor uses to bound its descent: every test that copies a value
 // segfaults with clang 11.0.1 and clang 18.1.8, while the same tests pass with

include/nlohmann/detail/macro_unscope.hpp

@@ -19,6 +19,7 @@
 #undef NLOHMANN_CAN_CALL_STD_FUNC_IMPL
 #undef JSON_INLINE_VARIABLE
 #undef JSON_NO_UNIQUE_ADDRESS
+#undef JSON_INTERNAL_ALWAYS_INLINE
 #undef JSON_DISABLE_ENUM_SERIALIZATION
 #undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
 #undef JSON_UNLOCKED_FILE_IO

include/nlohmann/detail/output/binary_writer.hpp

@@ -833,7 +833,7 @@ class binary_writer
         while (n != 0);
         std::reverse(result.begin(), result.end());
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /*!
     @brief the decimal digits of the integer @a n, with a leading '-' if it
@@ -860,7 +860,7 @@ class binary_writer
         }
         std::reverse(result.begin(), result.end());
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /*!
     @brief throws because the integer @a j is too large for @a format
@@ -1792,7 +1792,7 @@ class binary_writer
         std::memcpy(out, &n, sizeof(NumberType));
         if (!is_little_endian)
         {
-            std::reverse(out, out + sizeof(NumberType)); // LCOV_EXCL_LINE (big-endian hosts only)
+            std::reverse(out, out + sizeof(NumberType));
         }
     }
 
@@ -1921,7 +1921,7 @@ class binary_writer
             const string_t& value = *j.m_data.m_value.string;
             if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size() + 1ul)))
             {
-                return false; // LCOV_EXCL_LINE (a string of 2 GiB or more)
+                return false;
             }
             out[0] = to_char_type(0x02);
             store_little_endian<std::int32_t>(p, static_cast<std::int32_t>(value.size() + 1ul));
@@ -2378,7 +2378,7 @@ class binary_writer
         const std::size_t size = oa.written() - pos;
         if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(size)))
         {
-            return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
+            return false;
         }
         const auto le_size = static_cast<std::uint32_t>(size);
         oa.overwrite(pos, is_little_endian ? le_size : byteswap(le_size));
@@ -2507,7 +2507,7 @@ class binary_writer
                     {
                         if (JSON_HEDLEY_UNLIKELY(!close_bson_container(nested_size_pos)))
                         {
-                            return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
+                            return false;
                         }
                         continue;
                     }
@@ -2522,7 +2522,7 @@ class binary_writer
 
             if (JSON_HEDLEY_UNLIKELY(!close_bson_container(current.size_slot)))
             {
-                return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
+                return false;
             }
             if (parents.empty())
             {
@@ -2779,10 +2779,10 @@ class binary_writer
 
     Selected through masks rather than branches, as the type and the sign of
     the values in an array of mixed signs alternate unpredictably (non-negative
-    integers are number_unsigned after parsing). The sign is bit 63 of the
-    result (a narrower integer is sign-extended); computing it with masks keeps
-    GCC from branching on the type. Only called if @ref integers_fit_64_bits();
-    a wider number type is written with range checks on the whole value.
+    integers are number_unsigned after parsing). Up to 64 bits, the sign is bit
+    63 of the result (a narrower integer is sign-extended); computing it with
+    masks keeps GCC from branching on the type. A wider integer has to be
+    compared.
     */
     static std::uint64_t integer_bits(const BasicJsonType& j, std::uint64_t& sign_mask) noexcept
     {
@@ -2790,7 +2790,9 @@ class binary_writer
         const std::uint64_t raw = is_signed
                                   ? static_cast<std::uint64_t>(j.m_data.m_value.number_integer)
                                   : static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned);
-        sign_mask = (std::uint64_t{0} - static_cast<std::uint64_t>(is_signed)) & (std::uint64_t{0} - (raw >> 63u));
+        sign_mask = sizeof(typename BasicJsonType::number_integer_t) <= sizeof(std::uint64_t)
+                    ? (std::uint64_t{0} - static_cast<std::uint64_t>(is_signed)) & (std::uint64_t{0} - (raw >> 63u))
+                    : std::uint64_t{0} - static_cast<std::uint64_t>(is_signed && j.m_data.m_value.number_integer < 0);
         return raw;
     }
 
@@ -4157,34 +4159,57 @@ class binary_writer
     }
 
     /*!
-    @brief whether the BJData ND-array element @a el can be written with dtype 'd' (single precision)
-    @return whether @a el's value survives narrowing to float and back without any change
-            (so the ND-array round-trips exactly), or is infinite or NaN
+    @brief validate (dry_run) or write one BJData ND-array element of integer dtype @a T
+    @return whether @a el's value is in range of @a T; always true when @a dry_run is false
     */
-    static bool bjdata_ndarray_float_in_range(const BasicJsonType& el) noexcept
+    template<typename T>
+    bool write_bjdata_ndarray_element(const BasicJsonType& el, const bool dry_run)
+    {
+        if (dry_run)
+        {
+            return bjdata_ndarray_value_in_range<T>(el);
+        }
+        using storage_type = typename std::conditional<std::is_unsigned<T>::value, std::uint64_t, std::int64_t>::type;
+        write_number(static_cast<T>(el.template get<storage_type>()), true);
+        return true;
+    }
+
+    /*!
+    @brief validate (dry_run) or write one BJData ND-array element of dtype 'd' (single precision)
+    @return whether @a el's value survives narrowing to float and back without any change
+            (so the ND-array round-trips exactly), or is infinite or NaN; always true when
+            @a dry_run is false
+    */
+    bool write_bjdata_ndarray_float_element(const BasicJsonType& el, const bool dry_run)
     {
         const auto dval = static_cast<double>(el.m_data.m_value.number_float);
+        if (dry_run)
+        {
 #ifdef __GNUC__
-        JSON_HEDLEY_DIAGNOSTIC_PUSH
-        JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
+            JSON_HEDLEY_DIAGNOSTIC_PUSH
+            JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
-        // a value that would be rounded (rather than exactly represented) by the
-        // narrowing to float is treated like an out-of-range integer element; this
-        // is the same criterion write_compact_float() uses for CBOR/MessagePack
-        return std::isnan(dval) ||
-               (dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
-                dval <= static_cast<double>((std::numeric_limits<float>::max)()) &&
-                static_cast<double>(static_cast<float>(dval)) == dval) ||
-               std::isinf(dval);
+            // a value that would be rounded (rather than exactly represented) by the
+            // narrowing to float is treated like an out-of-range integer element; this
+            // is the same criterion write_compact_float() uses for CBOR/MessagePack
+            const bool in_range = std::isnan(dval) ||
+                                  (dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
+                                   dval <= static_cast<double>((std::numeric_limits<float>::max)()) &&
+                                   static_cast<double>(static_cast<float>(dval)) == dval) ||
+                                  std::isinf(dval);
 #ifdef __GNUC__
-        JSON_HEDLEY_DIAGNOSTIC_POP
+            JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
+            return in_range;
+        }
+        write_number(static_cast<float>(dval), true);
+        return true;
     }
 
     /*!
     @brief write the elements of an ND-array as the number kind @a dtype names
            (see @ref write_bjdata_ndarray), after they have been found to be
-           in range by @ref bjdata_ndarray_elements_in_range
+           in range by a dry run of @ref write_bjdata_ndarray_elements
 
     The elements are encoded in blocks into space reserved from the sink.
     */
@@ -4266,13 +4291,20 @@ class binary_writer
     }
 
     /*!
-    @brief whether every element of a BJData ND-array's `_ArrayData_` is in range for its dtype
+    @brief validate or write every element of a BJData ND-array's `_ArrayData_`
     @param[in] array_data  the `_ArrayData_` array
     @param[in] dtype       the ND-array dtype marker, as returned by bjdata_ndarray_type_marker()
-    @return whether every element is in range for @a dtype
+    @param[in] dry_run     true to only range-check each element, false to write it
+    @return whether every element is in range for @a dtype (always true when @a dry_run is false)
     */
-    static bool bjdata_ndarray_elements_in_range(const BasicJsonType& array_data, const CharType dtype)
+    bool write_bjdata_ndarray_elements(const BasicJsonType& array_data, const CharType dtype, const bool dry_run)
     {
+        if (!dry_run)
+        {
+            write_bjdata_ndarray_values(array_data, dtype);
+            return true;
+        }
+
         for (const auto& el : array_data)
         {
             bool ok = true;
@@ -4280,39 +4312,43 @@ class binary_writer
             {
                 case 'U':
                 case 'B':
-                    ok = bjdata_ndarray_value_in_range<std::uint8_t>(el);
+                    ok = write_bjdata_ndarray_element<std::uint8_t>(el, dry_run);
                     break;
                 case 'C':
                     // BJData limits a char to 0..127 (the intersection of the int8 and uint8 ranges)
                     ok = bjdata_ndarray_value_in_range<std::int8_t>(el) && bjdata_ndarray_value_in_range<std::uint8_t>(el);
                     break;
                 case 'i':
-                    ok = bjdata_ndarray_value_in_range<std::int8_t>(el);
+                    ok = write_bjdata_ndarray_element<std::int8_t>(el, dry_run);
                     break;
                 case 'u':
-                    ok = bjdata_ndarray_value_in_range<std::uint16_t>(el);
+                    ok = write_bjdata_ndarray_element<std::uint16_t>(el, dry_run);
                     break;
                 case 'I':
-                    ok = bjdata_ndarray_value_in_range<std::int16_t>(el);
+                    ok = write_bjdata_ndarray_element<std::int16_t>(el, dry_run);
                     break;
                 case 'm':
-                    ok = bjdata_ndarray_value_in_range<std::uint32_t>(el);
+                    ok = write_bjdata_ndarray_element<std::uint32_t>(el, dry_run);
                     break;
                 case 'l':
-                    ok = bjdata_ndarray_value_in_range<std::int32_t>(el);
+                    ok = write_bjdata_ndarray_element<std::int32_t>(el, dry_run);
                     break;
                 case 'M':
-                    ok = bjdata_ndarray_value_in_range<std::uint64_t>(el);
+                    ok = write_bjdata_ndarray_element<std::uint64_t>(el, dry_run);
                     break;
                 case 'L':
-                    ok = bjdata_ndarray_value_in_range<std::int64_t>(el);
+                    ok = write_bjdata_ndarray_element<std::int64_t>(el, dry_run);
                     break;
                 case 'd':
-                    ok = bjdata_ndarray_float_in_range(el);
+                    ok = write_bjdata_ndarray_float_element(el, dry_run);
                     break;
                 case 'D':
                 default:
                     // 'D' (double) already spans the full range of number_float_t
+                    if (!dry_run)
+                    {
+                        write_number(el.template get<double>(), true);
+                    }
                     break;
             }
             if (!ok)
@@ -4399,7 +4435,7 @@ class binary_writer
             const auto dim = el.template get<std::uint64_t>();
             if (!value_in_range_of<std::size_t>(dim))
             {
-                return true; // LCOV_EXCL_LINE (size_t is narrower than 64 bits)
+                return true;
             }
             const auto dim_size = static_cast<std::size_t>(dim);
 
@@ -4449,7 +4485,7 @@ class binary_writer
         // wrap (integers) or overflow to infinity (the "single" precision
         // float) instead of being reported, so such an object falls back to
         // a plain object encoding as well
-        if (!bjdata_ndarray_elements_in_range(array_data, dtype))
+        if (!write_bjdata_ndarray_elements(array_data, dtype, true))
         {
             return true;
         }
@@ -4461,7 +4497,7 @@ class binary_writer
 
         write_ubjson(array_size, use_count, use_type, true,  true, bjdata_version);
 
-        write_bjdata_ndarray_values(array_data, dtype);
+        write_bjdata_ndarray_elements(array_data, dtype, false);
         return false;
     }
 
@@ -4787,8 +4823,8 @@ class binary_writer
     run are encoded into space reserved from the sink, as in
     @ref write_array_elements; an integer that BON8 cannot write (an unsigned
     one above the int64 range, or one of a number type wider than 64 bits) throws
-    out_of_range.407, as write_bon8_value does. Kept out of line, like
-    @ref write_cbor_array.
+    from write_bon8_value, like any other value that is not a number. Kept out
+    of line, like @ref write_cbor_array.
     */
     template<typename ArrayType>
     JSON_HEDLEY_NEVER_INLINE
@@ -4838,10 +4874,10 @@ class binary_writer
                 string_open = false;
             }
 
-            if (JSON_HEDLEY_UNLIKELY(unencodable))
+            if (unencodable)
             {
-                // an integer beyond the int64 range, as write_bon8_value would report it
-                throw_integer_out_of_range(*it, input_format_t::bon8, "int64");
+                write_bon8_value(*it, string_open, depth + 1);
+                ++it;
             }
         }
     }
@@ -4876,13 +4912,14 @@ class binary_writer
                     break;
 
                 case value_t::number_integer:
-                    if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(value.m_data.m_value.number_integer)))
+                    if (JSON_HEDLEY_LIKELY(integer_fits<std::int64_t>(value.m_data.m_value.number_integer)))
                     {
-                        // beyond 64 bits (number types wider than that)
-                        throw_integer_out_of_range(value, input_format_t::bon8, "int64");
+                        write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_integer));
+                        string_open = false;
+                        break;
                     }
-                    write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_integer));
-                    string_open = false;
+                    // beyond 64 bits (number types wider than that): throws
+                    write_bon8_value(value, string_open, depth + 1);
                     break;
 
                 case value_t::number_float:
@@ -4891,13 +4928,14 @@ class binary_writer
                     break;
 
                 case value_t::number_unsigned:
-                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::int64_t>(value.m_data.m_value.number_unsigned)))
+                    if (JSON_HEDLEY_LIKELY(integer_fits_max<std::int64_t>(value.m_data.m_value.number_unsigned)))
                     {
-                        // too large for BON8
-                        throw_integer_out_of_range(value, input_format_t::bon8, "int64");
+                        write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_unsigned));
+                        string_open = false;
+                        break;
                     }
-                    write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_unsigned));
-                    string_open = false;
+                    // too large for BON8: throws
+                    write_bon8_value(value, string_open, depth + 1);
                     break;
 
                 case value_t::object:

include/nlohmann/detail/output/serializer.hpp

@@ -1113,21 +1113,36 @@ class serializer
                 {
                     // the code point is at least 0x60 (smaller ones are handled
                     // above) and is not printable ASCII (which the scanner
-                    // copies). Under EnsureAscii it is DEL (0x7F): every
-                    // well-formed multi-byte character is escaped by
-                    // write_u_escapes() above, so decode() only ever accepts a
-                    // single byte here, and nothing of it was buffered
+                    // copies): it is DEL (0x7F) under EnsureAscii or a non-ASCII
+                    // character
                     if (EnsureAscii)
                     {
-                        JSON_ASSERT(codepoint == 0x7F);
-                        JSON_ASSERT(bytes == bytes_after_last_accept);
-                        write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
+                        JSON_ASSERT(codepoint >= 0x7F);
+                        if (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));
+                        }
+                        else
+                        {
+                            write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
+                            write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
+                        }
                     }
                     else
                     {
                         // copy byte to buffer (all previous bytes of the
                         // sequence have been copied in the default case below)
-                        string_buffer[bytes++] = s[i]; // LCOV_EXCL_LINE (well-formed sequences are copied in runs)
+                        string_buffer[bytes++] = s[i];
                     }
 
                     reserve_string_buffer(bytes);

include/nlohmann/detail/string_concat.hpp

@@ -139,7 +139,7 @@ inline OutStringType concat(Args && ... args)
     str.reserve(concat_length(args...));
     concat_into(str, std::forward<Args>(args)...);
     return str;
-} // LCOV_EXCL_LINE (exception cleanup only)
+}
 
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/string_escape.hpp

@@ -83,6 +83,10 @@ template<typename StringType>
 inline void unescape(StringType& s)
 {
     auto pos = s.find_first_of('~', 0);
+    if (pos == StringType::npos)
+    {
+        return;
+    }
 
     StringType result;
     result.reserve(s.size());

include/nlohmann/detail/string_utils.hpp

@@ -13,6 +13,7 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint8_t, uint32_t
 #include <string> // string, to_string
+#include <utility> // move
 
 #include <nlohmann/detail/abi_macros.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
@@ -36,7 +37,7 @@ StringType to_string(std::size_t value)
     StringType result;
     int_to_string(result, value);
     return result;
-} // LCOV_EXCL_LINE (exception cleanup only)
+}
 
 /// @return a byte as two uppercase hexadecimal digits
 inline std::string hex_byte(const std::uint8_t byte)
@@ -46,7 +47,7 @@ inline std::string hex_byte(const std::uint8_t byte)
     result[0] = nibble_to_hex[byte / 16];
     result[1] = nibble_to_hex[byte % 16];
     return result;
-} // LCOV_EXCL_LINE (exception cleanup only)
+}
 
 /*!
 @brief write a UTF-16 code unit as four lowercase hexadecimal digits
@@ -390,7 +391,7 @@ inline StringType sanitize_utf8(const StringType& s, const error_handler_t error
     }
 
     return result;
-} // LCOV_EXCL_LINE (exception cleanup only)
+}
 
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/builder.hpp

@@ -1174,9 +1174,8 @@ indent_done:
             {
                 ++p;
             }
-            else if (!negative || NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            else if (NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
             {
-                // (without a sign, the dispatch saw a digit)
                 p = skip_digits(p + 1, e);
             }
             else

include/nlohmann/detail/view/compare.hpp

@@ -397,9 +397,9 @@ class view_side
         return m_view.size();
     }
 
-    string_view_t string() const noexcept
+    string_view_t string() const
     {
-        return {m_view.m_doc->str(*m_view.m_node), m_view.m_node->len};
+        return m_view.get_string();
     }
 
     bool boolean() const noexcept
@@ -428,19 +428,28 @@ class view_side
         return string_view_t(m_view.m_doc->str(*m_view.m_node), m_view.m_node->len);
     }
 
-    /// a number as a basic_json value (no allocation); only called for numbers
+    /// a number, boolean, or null as a basic_json value (no allocation)
     BasicJsonType scalar() const
     {
-        const value_t t = m_view.type();
-        if (t == value_t::number_integer)
+        switch (m_view.type())
         {
-            return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
+            case value_t::number_integer:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
+            case value_t::number_unsigned:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
+            case value_t::number_float:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
+            case value_t::boolean:
+                return BasicJsonType(m_view.template get<bool>());
+            case value_t::null:
+            case value_t::object:
+            case value_t::array:
+            case value_t::string:
+            case value_t::binary:
+            case value_t::discarded:
+            default:
+                return BasicJsonType(nullptr);
         }
-        if (t == value_t::number_unsigned)
-        {
-            return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
-        }
-        return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
     }
 
     /// start at the first element of this array
@@ -522,9 +531,9 @@ class json_side
         return m_json->size();
     }
 
-    string_view_t string() const noexcept
+    string_view_t string() const
     {
-        const auto& s = *m_json->template get_ptr<const typename BasicJsonType::string_t*>();
+        const auto& s = m_json->template get_ref<const typename BasicJsonType::string_t&>();
         return string_view_t(s.data(), s.size());
     }
 

include/nlohmann/detail/view/edit.hpp

@@ -96,11 +96,11 @@ NLOHMANN_VIEW_NOINLINE inline void check_utf8_scan(const unsigned char* p, std::
         }
         if (*q >= 0x80)
         {
-            break; // ill-formed UTF-8: reported below
+            check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
+            return; // not reached: the scan stopped at ill-formed UTF-8
         }
         ++q; // a quote, backslash, or control character
     }
-    check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
 }
 
 inline void check_utf8(const char* s, std::size_t n)

include/nlohmann/detail/view/edit_storage.hpp

@@ -158,7 +158,7 @@ inline void set_moved(document_data& d, node* n, node* seq, std::size_t cap)
         e.moved_cap[n->off] = cap;
         return;
     }
-    // every caller has called reserve_moved() (see above), so neither push_back() can throw
+    reserve_moved(d);
     e.moved.push_back(seq);
     e.moved_cap.push_back(cap);
     n->off = static_cast<std::uint32_t>(e.moved.size() - 1);
@@ -243,7 +243,7 @@ inline node* find_parent(const document_data& d, const node* target)
     }
     if (target == lo)
     {
-        return nullptr; // LCOV_EXCL_LINE (the root, or a new value's root, which is linked)
+        return nullptr;
     }
     for (;;)
     {

include/nlohmann/detail/view/errors.hpp

@@ -185,6 +185,10 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
         end = p.end;
         return;
     }
+    if ((n->flags & node_flags::is_new) != 0 || n->off >= d.size)
+    {
+        return;
+    }
     // the open brackets: n, then the last element as long as it is a non-empty container
     std::size_t closing = 0;
     std::size_t pos = std::string::npos;
@@ -416,12 +420,10 @@ struct throwing_sax
         return true;
     }
 
-    // LCOV_EXCL_START (throw_parse_failure parses JSON only)
     bool binary(binary_t& /*unused*/)
     {
         return true;
     }
-    // LCOV_EXCL_STOP
 
     bool start_object(std::size_t /*unused*/)
     {
@@ -450,11 +452,21 @@ struct throwing_sax
 
     /// (a template, as in json_sax_dom_parser: the parser passes the concrete
     /// exception type, which is thrown as is)
+    ///
+    /// It is not [[noreturn]]: sax_parse() recovers from an error if
+    /// parse_error() returns true, and MSVC reports that code as unreachable
+    /// (C4702) for a handler that never returns. The flag hides that from it.
     template<class Exception>
-    [[noreturn]] bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const Exception& ex)
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const Exception& ex)
     {
-        NLOHMANN_VIEW_THROW(ex);
+        if (throwing)
+        {
+            NLOHMANN_VIEW_THROW(ex);
+        }
+        return false; // LCOV_EXCL_LINE
     }
+
+    bool throwing = true;
 };
 
 /*!

include/nlohmann/detail/view/image.hpp

@@ -787,6 +787,10 @@ inline void load_image(document_data& d, const std::uint8_t* image, std::size_t
     d.edits.reset();
     d.base[2] = nullptr;
     d.owned.clear();
+    if (d.owned_image.empty() || image != d.owned_image.data())
+    {
+        d.owned_image.clear();
+    }
     d.arena.clear();
     d.indexes.clear();
     d.index_slots.clear();

include/nlohmann/detail/view/materialize.hpp

@@ -65,9 +65,14 @@ struct position_source
         return token{end - start};
     }
 
-    /// the range [first, last)
+    /// the range [first, last), or none if either is npos
     void set(std::size_t first, std::size_t last) noexcept
     {
+        if (first == std::string::npos || last == std::string::npos)
+        {
+            clear();
+            return;
+        }
         start = first;
         end = last;
     }
@@ -186,11 +191,11 @@ struct position_source
                 first = n.off;
                 last = n.off + 4u;
                 break;
-            case node_kind::object: // LCOV_EXCL_LINE
+            case node_kind::object:
             case node_kind::array:
             case node_kind::link:
             default:
-                break; // LCOV_EXCL_LINE
+                break;
         }
         // (a crafted image can point past the text)
         if (last == std::string::npos || last > d.size)

include/nlohmann/detail/view/serializer.hpp

@@ -641,7 +641,7 @@ class view_serializer
             {
                 invalid_utf8(s, n.len); // (the scan stopped at ill-formed UTF-8)
             }
-            write_escaped(s[i]); // a quote, a backslash, or a control character
+            write_codepoint<false>(s[i], s + i, 1); // a quote, a backslash, or a control character
             ++i;
         }
         m_out.put('"');
@@ -1389,10 +1389,20 @@ class view_serializer
     /// a float node as dump() writes it
     void write_float_node(const node& n)
     {
-        // (only for types other than double: doubles go through write_double_ahead())
+        write_float_node(n, fast_double {});
+    }
+
+    void write_float_node(const node& n, std::false_type /*other*/)
+    {
         write_float(float_value<number_float_t>(m_doc, n));
     }
 
+    void write_float_node(const node& n, std::true_type /*double*/)
+    {
+        m_out.reserve(64);
+        m_out.set_cursor(write_double_at(m_out.cursor(), n));
+    }
+
     /*!
     @brief (doubles) the float at n as dump() writes it, at w (64 bytes of room)
 
@@ -1487,11 +1497,10 @@ class view_serializer
     {
         const string_t dumped = BasicJsonType(string_t(reinterpret_cast<const char*>(s), n)).dump(); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
         static_cast<void>(dumped);
-    } // LCOV_EXCL_LINE (dump() throws: the callers pass only ill-formed UTF-8)
+    }
 
-    /// write the escape sequence of a quote, a backslash or a control
-    /// character (the only bytes a run of plain output stops at)
-    void write_escaped(std::uint32_t codepoint)
+    template<bool EnsureAscii>
+    void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
     {
         switch (codepoint)
         {
@@ -1519,7 +1528,20 @@ class view_serializer
             default:
                 break;
         }
-        write_u_escape(codepoint); // (a control character)
+        if (codepoint <= 0x1F || (EnsureAscii && codepoint >= 0x7F))
+        {
+            if (codepoint <= 0xFFFF)
+            {
+                write_u_escape(codepoint);
+            }
+            else
+            {
+                write_u_escape(0xD7C0u + (codepoint >> 10u));
+                write_u_escape(0xDC00u + (codepoint & 0x3FFu));
+            }
+            return;
+        }
+        m_out.put(reinterpret_cast<const char*>(bytes), len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) LCOV_EXCL_LINE (printable characters are copied in runs)
     }
 
     void write_u_escape(std::uint32_t u)

include/nlohmann/json.hpp

@@ -157,7 +157,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend class ::nlohmann::detail::iter_impl;
     template<typename BasicJsonType, typename CharType, typename OutputSinkType>
     friend class ::nlohmann::detail::binary_writer;
-    template<typename BasicJsonType, typename InputType, typename SAX>
+    template<typename BasicJsonType, typename InputType, typename SAX, bool AllowRecovery>
     friend class ::nlohmann::detail::binary_reader;
     template<typename BasicJsonType, typename InputAdapterType, bool Collect, typename LexerType>
     friend class ::nlohmann::detail::json_sax_dom_parser;
@@ -400,7 +400,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         result["compiler"] = {{"family", "clang"}, {"version", __clang_version__}};
 #elif defined(__GNUC__) || defined(__GNUG__)
         result["compiler"] = {{"family", "gcc"}, {"version", detail::concat<string_t>(
-                    detail::to_string<string_t>(static_cast<std::size_t>(__GNUC__)), '.', // LCOV_EXCL_LINE
+                    detail::to_string<string_t>(static_cast<std::size_t>(__GNUC__)), '.',
                     detail::to_string<string_t>(static_cast<std::size_t>(__GNUC_MINOR__)), '.',
                     detail::to_string<string_t>(static_cast<std::size_t>(__GNUC_PATCHLEVEL__)))
             }
@@ -672,14 +672,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 case value_t::binary:
                     binary = create<binary_t>();
                     break;
-                case value_t::null: // LCOV_EXCL_LINE
+                case value_t::null:
                 case value_t::boolean:
                 case value_t::number_integer:
                 case value_t::number_unsigned:
                 case value_t::number_float:
                 case value_t::discarded:
                 default:
-                    break; // LCOV_EXCL_LINE
+                    break;
             }
         }
 
@@ -1034,14 +1034,14 @@ public:
                     destroy_container(t);
                     break;
 
-                case value_t::null: // LCOV_EXCL_LINE
+                case value_t::null:
                 case value_t::boolean:
                 case value_t::number_integer:
                 case value_t::number_unsigned:
                 case value_t::number_float:
                 case value_t::discarded:
                 default:
-                    break; // LCOV_EXCL_LINE
+                    break;
             }
         }
     };
@@ -1214,9 +1214,9 @@ public:
         return is_array() ? array_capacity() : object_capacity();
     }
 #else
-    static constexpr std::size_t container_capacity() noexcept // LCOV_EXCL_LINE
+    static constexpr std::size_t container_capacity() noexcept
     {
-        return detail::unknown_size(); // LCOV_EXCL_LINE
+        return detail::unknown_size();
     }
 #endif
 
@@ -1402,7 +1402,7 @@ public:
     ///       into this switch is worth a few percent when copying a value made
     ///       mostly of numbers
     JSON_HEDLEY_ALWAYS_INLINE
-    static void copy_leaf_value(const basic_json& src, basic_json& dst) // LCOV_EXCL_LINE
+    static void copy_leaf_value(const basic_json& src, basic_json& dst)
     {
         switch (src.m_data.m_type)
         {
@@ -1576,7 +1576,7 @@ public:
         auto src_it = src_object.cbegin();
         for (auto& element : *dst.m_data.m_value.object)
         {
-            if (JSON_HEDLEY_LIKELY(copy_keys_equal(src_it->first, element.first)))
+            if (JSON_HEDLEY_LIKELY(src_it != src_object.cend() && copy_keys_equal(src_it->first, element.first)))
             {
                 copy_shallow(src_it->second, element.second, worklist);
                 ++src_it;
@@ -3134,7 +3134,8 @@ public:
         {
             return parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict);
         }
-        return detail::binary_reader<basic_json, InputAdapterType, SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
+        // the SAX parser may recover from errors (see parse_error())
+        return detail::binary_reader<basic_json, InputAdapterType, SAX, true>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 
     /// serialize @a j into a new vector; @a write receives the vector-backed writer
@@ -5353,7 +5354,8 @@ public:
     /// @name lexicographical comparison operators
     /// @{
 
-    // the same-type cases for non-owning scalars, used by JSON_IMPLEMENT_SCALAR_FAST
+    // the same-type cases for non-owning scalars, shared by JSON_IMPLEMENT_OPERATOR
+    // and JSON_IMPLEMENT_SCALAR_FAST
 #define JSON_IMPLEMENT_SCALAR_CASES(op, null_result)                                                     \
   case value_t::null:                                                                                  \
         return (null_result);                                                                            \
@@ -5375,7 +5377,7 @@ public:
     // because any negative signed value is smaller than any unsigned value.
     // Otherwise, the non-negative signed value is cast to unsigned before the
     // comparison to avoid wraparound.
-#define JSON_IMPLEMENT_OPERATOR(op, unordered_result, default_result, deep_result, may_descend)          \
+#define JSON_IMPLEMENT_OPERATOR(op, null_result, unordered_result, default_result, deep_result, may_descend) \
     const auto lhs_type = lhs.type();                                                                    \
     const auto rhs_type = rhs.type();                                                                    \
     \
@@ -5403,15 +5405,8 @@ public:
                 return (*lhs.m_data.m_value.object) op (*rhs.m_data.m_value.object);                                   \
             }                                                                                            \
             \
-                /* same-type scalars never get here: the inline fast path of the operator handles them */ \
-            case value_t::null:                                                                          \
-            case value_t::boolean:                                                                       \
-            case value_t::number_integer:                                                                \
-            case value_t::number_unsigned:                                                               \
-            case value_t::number_float:                                                                  \
-                JSON_ASSERT(false); /* NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) */ \
-                return (unordered_result);                                                               \
-                \
+            JSON_IMPLEMENT_SCALAR_CASES(op, null_result)                                                 \
+            \
             case value_t::string:                                                                        \
                 return (*lhs.m_data.m_value.string) op (*rhs.m_data.m_value.string);                                   \
                 \
@@ -5451,7 +5446,7 @@ public:
                ? (number_integer_t(-1) op number_integer_t(1))                                           \
                : (static_cast<number_unsigned_t>(lhs.m_data.m_value.number_integer) op rhs.m_data.m_value.number_unsigned); \
     }                                                                                             \
-    else if(lhs_type == value_t::discarded || rhs_type == value_t::discarded)\
+    else if(compares_unordered(lhs, rhs))\
     {\
         return (unordered_result);\
     }\
@@ -5519,7 +5514,7 @@ public:
         JSON_HEDLEY_DIAGNOSTIC_PUSH
         JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
-        JSON_IMPLEMENT_OPERATOR( ==, false, false,
+        JSON_IMPLEMENT_OPERATOR( ==, true, false, false,
                                  compare_iteratively<false>(lhs, rhs, false) == compare_result::equal, true)
 #ifdef __GNUC__
         JSON_HEDLEY_DIAGNOSTIC_POP
@@ -5533,6 +5528,7 @@ public:
         // default_result is used if we cannot compare values. In that case,
         // we compare types.
         JSON_IMPLEMENT_OPERATOR(<=>, // *NOPAD*
+                                std::partial_ordering::equivalent,
                                 std::partial_ordering::unordered,
                                 lhs_type <=> rhs_type, // *NOPAD*
                                 to_partial_ordering(compare_iteratively<true>(lhs, rhs, false)), true)
@@ -5544,7 +5540,7 @@ public:
         // default_result is used if we cannot compare values. In that case,
         // we compare types. Note we have to call the operator explicitly,
         // because MSVC has problems otherwise.
-        JSON_IMPLEMENT_OPERATOR( <, false, operator<(lhs_type, rhs_type),
+        JSON_IMPLEMENT_OPERATOR( <, false, false, operator<(lhs_type, rhs_type),
                                  compare_iteratively<true>(lhs, rhs, true) == compare_result::less, false)
     }
 #endif
@@ -5559,7 +5555,7 @@ public:
     ///       their inlined code at each call site small. Binary values are
     ///       rare and left to equal_general().
     JSON_HEDLEY_ALWAYS_INLINE
-    static int equal_leaf(const_reference lhs, const_reference rhs) noexcept // LCOV_EXCL_LINE
+    static int equal_leaf(const_reference lhs, const_reference rhs) noexcept
     {
 #ifdef __GNUC__
         JSON_HEDLEY_DIAGNOSTIC_PUSH
@@ -6868,7 +6864,7 @@ public:
         basic_json result(value_t::object);
         json_pointer::flatten("", *this, result);
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /// @brief unflatten a previously flattened JSON value
     /// @sa https://json.nlohmann.me/api/basic_json/unflatten/
@@ -7581,7 +7577,7 @@ public:
         result.append(path.data(), path.size());
         diff_append_key(result, key);
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /// @brief the path of the element @a index of the value at @a path
     static string_t diff_index_path(const string_t& path, const std::size_t index)
@@ -7591,7 +7587,7 @@ public:
         result.append(path.data(), path.size());
         diff_append_index(result, index);
         return result;
-    } // LCOV_EXCL_LINE (exception cleanup only)
+    }
 
     /// @brief append the "remove" operations for the elements of array
     ///        @a source from @a index on, and the "add" operations for the
@@ -7751,7 +7747,7 @@ public:
         // operations
         if (source == target)
         {
-            return false; // LCOV_EXCL_LINE (equal objects with the same members in the same order return early)
+            return false;
         }
 
         // slow path: the common keys are in a different relative

include/nlohmann/json_view.hpp

@@ -1705,11 +1705,9 @@ class basic_json_document
         {
             // (as before: the library's adapter decides what a null stream yields)
             detail::view::append_adapter(buf, detail::input_adapter(file));
+            return;
         }
-        else
-        {
-            detail::view::append_file(buf, file);
-        }
+        detail::view::append_file(buf, file);
     }
 #endif
 

single_include/nlohmann/json_view.hpp

@@ -2479,9 +2479,8 @@ indent_done:
             {
                 ++p;
             }
-            else if (!negative || NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            else if (NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
             {
-                // (without a sign, the dispatch saw a digit)
                 p = skip_digits(p + 1, e);
             }
             else
@@ -3550,9 +3549,9 @@ class view_side
         return m_view.size();
     }
 
-    string_view_t string() const noexcept
+    string_view_t string() const
     {
-        return {m_view.m_doc->str(*m_view.m_node), m_view.m_node->len};
+        return m_view.get_string();
     }
 
     bool boolean() const noexcept
@@ -3581,19 +3580,28 @@ class view_side
         return string_view_t(m_view.m_doc->str(*m_view.m_node), m_view.m_node->len);
     }
 
-    /// a number as a basic_json value (no allocation); only called for numbers
+    /// a number, boolean, or null as a basic_json value (no allocation)
     BasicJsonType scalar() const
     {
-        const value_t t = m_view.type();
-        if (t == value_t::number_integer)
+        switch (m_view.type())
         {
-            return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
+            case value_t::number_integer:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
+            case value_t::number_unsigned:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
+            case value_t::number_float:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
+            case value_t::boolean:
+                return BasicJsonType(m_view.template get<bool>());
+            case value_t::null:
+            case value_t::object:
+            case value_t::array:
+            case value_t::string:
+            case value_t::binary:
+            case value_t::discarded:
+            default:
+                return BasicJsonType(nullptr);
         }
-        if (t == value_t::number_unsigned)
-        {
-            return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
-        }
-        return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
     }
 
     /// start at the first element of this array
@@ -3675,9 +3683,9 @@ class json_side
         return m_json->size();
     }
 
-    string_view_t string() const noexcept
+    string_view_t string() const
     {
-        const auto& s = *m_json->template get_ptr<const typename BasicJsonType::string_t*>();
+        const auto& s = m_json->template get_ref<const typename BasicJsonType::string_t&>();
         return string_view_t(s.data(), s.size());
     }
 
@@ -4470,9 +4478,14 @@ struct position_source
         return token{end - start};
     }
 
-    /// the range [first, last)
+    /// the range [first, last), or none if either is npos
     void set(std::size_t first, std::size_t last) noexcept
     {
+        if (first == std::string::npos || last == std::string::npos)
+        {
+            clear();
+            return;
+        }
         start = first;
         end = last;
     }
@@ -4591,11 +4604,11 @@ struct position_source
                 first = n.off;
                 last = n.off + 4u;
                 break;
-            case node_kind::object: // LCOV_EXCL_LINE
+            case node_kind::object:
             case node_kind::array:
             case node_kind::link:
             default:
-                break; // LCOV_EXCL_LINE
+                break;
         }
         // (a crafted image can point past the text)
         if (last == std::string::npos || last > d.size)
@@ -5014,6 +5027,10 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
         end = p.end;
         return;
     }
+    if ((n->flags & node_flags::is_new) != 0 || n->off >= d.size)
+    {
+        return;
+    }
     // the open brackets: n, then the last element as long as it is a non-empty container
     std::size_t closing = 0;
     std::size_t pos = std::string::npos;
@@ -5245,12 +5262,10 @@ struct throwing_sax
         return true;
     }
 
-    // LCOV_EXCL_START (throw_parse_failure parses JSON only)
     bool binary(binary_t& /*unused*/)
     {
         return true;
     }
-    // LCOV_EXCL_STOP
 
     bool start_object(std::size_t /*unused*/)
     {
@@ -5279,11 +5294,21 @@ struct throwing_sax
 
     /// (a template, as in json_sax_dom_parser: the parser passes the concrete
     /// exception type, which is thrown as is)
+    ///
+    /// It is not [[noreturn]]: sax_parse() recovers from an error if
+    /// parse_error() returns true, and MSVC reports that code as unreachable
+    /// (C4702) for a handler that never returns. The flag hides that from it.
     template<class Exception>
-    [[noreturn]] bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const Exception& ex)
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const Exception& ex)
     {
-        NLOHMANN_VIEW_THROW(ex);
+        if (throwing)
+        {
+            NLOHMANN_VIEW_THROW(ex);
+        }
+        return false; // LCOV_EXCL_LINE
     }
+
+    bool throwing = true;
 };
 
 /*!
@@ -5473,7 +5498,7 @@ inline void set_moved(document_data& d, node* n, node* seq, std::size_t cap)
         e.moved_cap[n->off] = cap;
         return;
     }
-    // every caller has called reserve_moved() (see above), so neither push_back() can throw
+    reserve_moved(d);
     e.moved.push_back(seq);
     e.moved_cap.push_back(cap);
     n->off = static_cast<std::uint32_t>(e.moved.size() - 1);
@@ -5558,7 +5583,7 @@ inline node* find_parent(const document_data& d, const node* target)
     }
     if (target == lo)
     {
-        return nullptr; // LCOV_EXCL_LINE (the root, or a new value's root, which is linked)
+        return nullptr;
     }
     for (;;)
     {
@@ -6179,11 +6204,11 @@ NLOHMANN_VIEW_NOINLINE inline void check_utf8_scan(const unsigned char* p, std::
         }
         if (*q >= 0x80)
         {
-            break; // ill-formed UTF-8: reported below
+            check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
+            return; // not reached: the scan stopped at ill-formed UTF-8
         }
         ++q; // a quote, backslash, or control character
     }
-    check_utf8_bytewise(p, n, static_cast<std::size_t>(q - p));
 }
 
 inline void check_utf8(const char* s, std::size_t n)
@@ -7777,6 +7802,10 @@ inline void load_image(document_data& d, const std::uint8_t* image, std::size_t
     d.edits.reset();
     d.base[2] = nullptr;
     d.owned.clear();
+    if (d.owned_image.empty() || image != d.owned_image.data())
+    {
+        d.owned_image.clear();
+    }
     d.arena.clear();
     d.indexes.clear();
     d.index_slots.clear();
@@ -9086,7 +9115,7 @@ class view_serializer
             {
                 invalid_utf8(s, n.len); // (the scan stopped at ill-formed UTF-8)
             }
-            write_escaped(s[i]); // a quote, a backslash, or a control character
+            write_codepoint<false>(s[i], s + i, 1); // a quote, a backslash, or a control character
             ++i;
         }
         m_out.put('"');
@@ -9834,10 +9863,20 @@ class view_serializer
     /// a float node as dump() writes it
     void write_float_node(const node& n)
     {
-        // (only for types other than double: doubles go through write_double_ahead())
+        write_float_node(n, fast_double {});
+    }
+
+    void write_float_node(const node& n, std::false_type /*other*/)
+    {
         write_float(float_value<number_float_t>(m_doc, n));
     }
 
+    void write_float_node(const node& n, std::true_type /*double*/)
+    {
+        m_out.reserve(64);
+        m_out.set_cursor(write_double_at(m_out.cursor(), n));
+    }
+
     /*!
     @brief (doubles) the float at n as dump() writes it, at w (64 bytes of room)
 
@@ -9932,11 +9971,10 @@ class view_serializer
     {
         const string_t dumped = BasicJsonType(string_t(reinterpret_cast<const char*>(s), n)).dump(); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
         static_cast<void>(dumped);
-    } // LCOV_EXCL_LINE (dump() throws: the callers pass only ill-formed UTF-8)
+    }
 
-    /// write the escape sequence of a quote, a backslash or a control
-    /// character (the only bytes a run of plain output stops at)
-    void write_escaped(std::uint32_t codepoint)
+    template<bool EnsureAscii>
+    void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
     {
         switch (codepoint)
         {
@@ -9964,7 +10002,20 @@ class view_serializer
             default:
                 break;
         }
-        write_u_escape(codepoint); // (a control character)
+        if (codepoint <= 0x1F || (EnsureAscii && codepoint >= 0x7F))
+        {
+            if (codepoint <= 0xFFFF)
+            {
+                write_u_escape(codepoint);
+            }
+            else
+            {
+                write_u_escape(0xD7C0u + (codepoint >> 10u));
+                write_u_escape(0xDC00u + (codepoint & 0x3FFu));
+            }
+            return;
+        }
+        m_out.put(reinterpret_cast<const char*>(bytes), len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) LCOV_EXCL_LINE (printable characters are copied in runs)
     }
 
     void write_u_escape(std::uint32_t u)
@@ -11758,11 +11809,9 @@ class basic_json_document
         {
             // (as before: the library's adapter decides what a null stream yields)
             detail::view::append_adapter(buf, detail::input_adapter(file));
+            return;
         }
-        else
-        {
-            detail::view::append_file(buf, file);
-        }
+        detail::view::append_file(buf, file);
     }
 #endif
 

tests/src/fuzzer-parse_bjdata.cpp

@@ -47,6 +47,10 @@ dumps is stable under exactly the same values that break operator==.
 The unit tests run the same checks on a fixed corpus (see the "BJData round-trip
 invariants" test case), so keep both in sync.
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_bjdata() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -57,6 +61,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -81,6 +86,9 @@ static bool is_value_stable(const json& lhs, const json& rhs)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bjdata).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -99,6 +107,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2.1: round trip without adding size annotations to container types
@@ -132,6 +143,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -142,6 +154,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-parse_bon8.cpp

@@ -17,6 +17,10 @@ array data, it performs the following steps:
 - j2 = from_bon8(vec)
 - assert(to_bon8(j2) == vec)
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_bon8() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -27,6 +31,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -44,6 +49,9 @@ struct read_bon8
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bon8).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -62,6 +70,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2: round trip
@@ -83,6 +94,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -93,6 +105,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-parse_bson.cpp

@@ -17,6 +17,10 @@ array data, it performs the following steps:
 - j2 = from_bson(vec)
 - assert(to_bson(j2) == vec)
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_bson() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -27,6 +31,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -44,6 +49,9 @@ struct read_bson
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::bson).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -62,6 +70,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2: round trip
@@ -83,6 +94,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -93,6 +105,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors can occur during parsing, too
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-parse_cbor.cpp

@@ -17,6 +17,10 @@ array data, it performs the following steps:
 - j2 = from_cbor(vec)
 - assert(to_cbor(j2) == vec)
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_cbor() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -27,6 +31,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -44,6 +49,9 @@ struct read_cbor
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::cbor).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -62,6 +70,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2: round trip
@@ -83,6 +94,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -93,6 +105,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors can occur during parsing, too
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-parse_json.cpp

@@ -24,11 +24,16 @@ array data, it performs the following steps:
 The pointer range takes the bulk fast paths, the other input adapters read byte
 by byte; see check_input_adapters().
 
+Furthermore, it parses data with a SAX parser that recovers from every error
+and checks that the events are balanced, that parsing ends, and that valid
+input is parsed without errors (see #3989).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -59,6 +64,13 @@ struct accept_json
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    {
+        const auto checker = check_recovering_parse(data, size, json::input_format_t::json);
+        assert(checker.events <= (4 * size) + 4);
+        assert((checker.errors == 0) == json::accept(data, data + size));
+    }
+
     // step 0: parse input without exceptions
     bool noexcept_threw = false;
     json const j_noexcept = parse_without_exceptions([&] { return json::parse(data, data + size, nullptr, false); }, noexcept_threw);

tests/src/fuzzer-parse_msgpack.cpp

@@ -17,6 +17,10 @@ array data, it performs the following steps:
 - j2 = from_msgpack(vec)
 - assert(to_msgpack(j2) == vec)
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_msgpack() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -27,6 +31,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -44,6 +49,9 @@ struct read_msgpack
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::msgpack).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -62,6 +70,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2: round trip
@@ -83,6 +94,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -93,6 +105,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-parse_ubjson.cpp

@@ -26,6 +26,10 @@ array data, it performs the following steps:
 The unit tests run the same checks on a fixed corpus (see the "UBJSON round-trip
 invariants" test case), so keep both in sync.
 
+Furthermore, it reads data with a SAX parser that recovers from every error
+and checks that the events are balanced, that reading ends, and that it
+reports an error exactly when from_ubjson() fails (see #3989).
+
 Finally, it reads the data from a stream, a non-contiguous iterator range, and
 a FILE*, which read byte by byte, and checks that each gives the same value or
 error (id, message, byte position) as the pointer range, which takes the bulk
@@ -36,6 +40,7 @@ drivers.
 */
 
 #include "fuzzer_common.hpp"
+#include "fuzzer-recovering_checker.hpp"
 
 namespace
 {
@@ -53,6 +58,9 @@ struct read_ubjson
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // recover from all errors, reading from memory and from a stream
+    const bool recovered_without_errors = check_recovering_parse(data, size, json::input_format_t::ubjson).errors == 0;
+
     std::vector<uint8_t> const vec1(data, data + size);
 
     // step 0: parse input without exceptions
@@ -71,6 +79,9 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // without exceptions, the same input must give the same value
         assert(!noexcept_threw && !j_noexcept.is_discarded() && same_value(j_noexcept, j1));
 
+        // the recovering parser must not have reported an error either
+        assert(recovered_without_errors);
+
         try
         {
             // step 2.1: round trip without adding size annotations to container types
@@ -102,6 +113,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // parse errors are ok, because input may be random bytes
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -112,6 +124,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     {
         // out of range errors may happen if provided sizes are excessive
         assert(parsed || noexcept_threw || j_noexcept.is_discarded());
+        assert(parsed || !recovered_without_errors);
     }
 
     // step 3: the other input adapters must read the data alike

tests/src/fuzzer-recovering_checker.hpp

@@ -0,0 +1,154 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+#pragma once
+
+#include <cassert>
+#include <cstddef>
+#include <cstdint>
+#include <sstream>
+#include <string>
+#include <vector>
+#include <nlohmann/json.hpp>
+
+namespace
+{
+// a SAX parser that recovers from every error and checks that the events are
+// balanced and that every key is followed by exactly one value
+class recovering_checker : public nlohmann::json_sax<nlohmann::json>
+{
+  public:
+    bool null() override
+    {
+        return value();
+    }
+
+    bool boolean(bool /*val*/) override
+    {
+        return value();
+    }
+
+    bool number_integer(number_integer_t /*val*/) override
+    {
+        return value();
+    }
+
+    bool number_unsigned(number_unsigned_t /*val*/) override
+    {
+        return value();
+    }
+
+    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
+    {
+        return value();
+    }
+
+    bool string(string_t& /*val*/) override
+    {
+        return value();
+    }
+
+    bool binary(binary_t& /*val*/) override
+    {
+        return value();
+    }
+
+    bool start_object(std::size_t /*elements*/) override
+    {
+        value();
+        stack.push_back('o');
+        return true;
+    }
+
+    bool key(string_t& /*val*/) override
+    {
+        ++events;
+        assert(!stack.empty() && stack.back() == 'o');
+        stack.back() = 'v';
+        return true;
+    }
+
+    bool end_object() override
+    {
+        ++events;
+        assert(!stack.empty() && stack.back() == 'o');
+        stack.pop_back();
+        return true;
+    }
+
+    bool start_array(std::size_t /*elements*/) override
+    {
+        value();
+        stack.push_back('a');
+        return true;
+    }
+
+    bool end_array() override
+    {
+        ++events;
+        assert(!stack.empty() && stack.back() == 'a');
+        stack.pop_back();
+        return true;
+    }
+
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const nlohmann::detail::exception& /*ex*/) override
+    {
+        ++errors;
+        return true;
+    }
+
+    bool complete() const
+    {
+        return stack.empty();
+    }
+
+    std::size_t events = 0;
+    std::size_t errors = 0;
+
+  private:
+    bool value()
+    {
+        ++events;
+        if (!stack.empty())
+        {
+            // an array element, or the value of a key
+            assert(stack.back() != 'o');
+            if (stack.back() == 'v')
+            {
+                stack.back() = 'o';
+            }
+        }
+        return true;
+    }
+
+    // 'a' for an array, 'o' for an object that expects a key, 'v' for an
+    // object that expects the value of a key
+    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
+};
+
+/// parses @a data with a recovering_checker from memory and from a stream,
+/// checks that both see the same, that the events are balanced, and that the
+/// number of errors is bounded, and returns the checker (see #3989)
+inline recovering_checker check_recovering_parse(const std::uint8_t* data, const std::size_t size, const nlohmann::json::input_format_t format)
+{
+    recovering_checker checker;
+    const bool ok = nlohmann::json::sax_parse(data, data + size, &checker, format);
+    assert(checker.complete());
+    assert(checker.errors <= size + 1);
+    assert(ok == (checker.errors == 0));
+
+    std::istringstream stream(std::string(reinterpret_cast<const char*>(data), size));
+    recovering_checker stream_checker;
+    assert(nlohmann::json::sax_parse(stream, &stream_checker, format) == ok);
+    assert(stream_checker.complete());
+    assert(stream_checker.events == checker.events);
+    assert(stream_checker.errors == checker.errors);
+
+    return checker;
+}
+} // namespace

tests/src/sax_event_loggers.hpp

@@ -131,11 +131,13 @@ struct SaxEventLogger : public nlohmann::json_sax<nlohmann::json>
     {
         errored = true;
         events.push_back("parse_error(" + std::to_string(position) + ")");
-        return false;
+        return recover;
     }
 
     std::vector<std::string> events {}; // NOLINT(readability-redundant-member-init)
     bool errored = false;
+    /// whether parse_error() asks the parser to recover from the error (see #3989)
+    bool recover = false;
 };
 
 struct SaxEventLoggerExitAfterStartObject : public SaxEventLogger

tests/src/unit-alt-string.cpp

@@ -432,6 +432,46 @@ TEST_CASE("alternative string type")
         CHECK(j2.dump() == R"({"/foo/0":"bar","/foo/1":"baz"})");
     }
 
+    SECTION("error recovery")
+    {
+        // a SAX parser that recovers from every error (see #3989)
+        struct recovering_parser : nlohmann::detail::json_sax_dom_parser<alt_json>
+        {
+            explicit recovering_parser(alt_json& j)
+                : nlohmann::detail::json_sax_dom_parser<alt_json>(j, false)
+            {}
+
+            // sax_parse() calls the SAX parser's own parse_error(), so hiding
+            // the one of the base class is what recovering takes
+            // NOLINTNEXTLINE(bugprone-derived-method-shadowing-base-method)
+            bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const nlohmann::detail::exception& /*unused*/)
+            {
+                ++errors;
+                return true;
+            }
+
+            std::size_t errors = 0;
+        };
+
+        alt_json j;
+        recovering_parser sax(j);
+        // not inside CHECK(): MSVC reads the escape in a stringized raw string
+        const std::string input = R"([1., "a\qb", tru, {"k" 2}])";
+        CHECK(!alt_json::sax_parse(input, &sax));
+        CHECK(sax.errors == 4);
+        CHECK(j.dump() == R"([1,"aqb",null,{"k":2}])");
+
+        // a UBJSON high-precision number, a CBOR key that is not a string
+        alt_json u;
+        recovering_parser ubjson_sax(u);
+        CHECK(!alt_json::sax_parse(std::vector<std::uint8_t> {'[', 'H', 'i', 2, '1', '.', ']'}, &ubjson_sax, alt_json::input_format_t::ubjson));
+        CHECK(u.dump() == "[1]");
+        alt_json c;
+        recovering_parser cbor_sax(c);
+        CHECK(!alt_json::sax_parse(std::vector<std::uint8_t> {0xA2, 0x01, 0x02, 0x61, 'a', 0x03}, &cbor_sax, alt_json::input_format_t::cbor));
+        CHECK(c.dump() == R"({"a":3})");
+    }
+
     SECTION("conversion between basic_json specializations (#2649)")
     {
         // explicit conversions are always possible

tests/src/unit-binary_writer_sinks.cpp

@@ -14,9 +14,7 @@ using nlohmann::json;
 #include <array>
 #include <cstdint>
 #include <limits>
-#include <memory>
 #include <sstream>
-#include <stdexcept>
 #include <string>
 #include <vector>
 
@@ -769,69 +767,3 @@ TEST_CASE("a write that throws leaves the same bytes in every kind of output")
     }
 }
 #endif
-
-#if !defined(JSON_NOEXCEPTION)
-namespace
-{
-
-// an adapter whose every write fails
-class failing_adapter : public nlohmann::detail::output_adapter_protocol<char>
-{
-  public:
-    [[noreturn]] void write_character(char /*c*/) override
-    {
-        throw std::runtime_error("write failed");
-    }
-
-    [[noreturn]] void write_characters(const char* /*s*/, std::size_t /*length*/) override
-    {
-        throw std::runtime_error("write failed");
-    }
-};
-
-} // namespace
-#endif
-
-TEST_CASE("output adapters")
-{
-    SECTION("writing a single character")
-    {
-        // the writers pass whole buffers on, but an adapter takes single
-        // characters as well
-        std::vector<char> as_vector;
-        nlohmann::detail::output_vector_adapter<char> vector_adapter(as_vector);
-        vector_adapter.write_character('a');
-        vector_adapter.write_character('b');
-        CHECK(as_vector == std::vector<char>({'a', 'b'}));
-
-        std::ostringstream as_stream;
-        nlohmann::detail::output_stream_adapter<char> stream_adapter(as_stream);
-        stream_adapter.write_character('c');
-        stream_adapter.write_character('d');
-        CHECK(as_stream.str() == "cd");
-
-        std::string as_string;
-        nlohmann::detail::output_string_adapter<char> string_adapter(as_string);
-        string_adapter.write_character('e');
-        string_adapter.write_character('f');
-        CHECK(as_string == "ef");
-    }
-
-#if !defined(JSON_NOEXCEPTION)
-    SECTION("a sink that is destroyed with characters left over")
-    {
-        // the destructor passes the pending characters on, as a write that
-        // threw leaves them there; the adapter failing then must not escape
-        {
-            nlohmann::detail::output_adapter_sink<char> sink(std::make_shared<failing_adapter>());
-            sink.write_character('x');
-        }
-
-        // while flush() reports the failure
-        nlohmann::detail::output_adapter_sink<char> sink(std::make_shared<failing_adapter>());
-        sink.write_character('x');
-        CHECK_THROWS_AS(sink.flush(), std::runtime_error&);
-        // (the character counts as written, so there is nothing left for the destructor)
-    }
-#endif
-}

tests/src/unit-bjdata.cpp

@@ -2312,23 +2312,6 @@ TEST_CASE("BJData")
             CHECK_FALSE(json::sax_parse(v, &scp, json::input_format_t::bjdata));
         }
 
-        SECTION("every event of an ndarray of chars")
-        {
-            // the elements of an ndarray of 'C' are read one by one
-            std::vector<uint8_t> const v = {'[', '$', 'C', '#', '[', '$', 'U', '#', 'U', 2, 2, 2, 'a', 'b', 'c', 'd'};
-            // start_object, key, string, key, start_array, 2 numbers, end_array,
-            // key, start_array, 4 chars, end_array, end_object
-            constexpr int events = 16;
-            for (int allowed = 0; allowed < events; ++allowed)
-            {
-                CAPTURE(allowed)
-                SaxCountdown scp(allowed);
-                CHECK_FALSE(json::sax_parse(v, &scp, json::input_format_t::bjdata));
-            }
-            SaxCountdown scp(events);
-            CHECK(json::sax_parse(v, &scp, json::input_format_t::bjdata));
-        }
-
         SECTION("start_array() in ndarray _ArrayData_")
         {
             std::vector<uint8_t> const v = {'[', '$', 'U', '#', '[', 'i', 2, 'i', 3, ']', 6, 5, 4, 3, 2, 1};
@@ -3112,15 +3095,6 @@ TEST_CASE("BJData")
                 json _;
                 CHECK_THROWS_WITH(_ = json::from_bjdata(v), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing BJData char: byte after 'C' must be in range 0x00..0x7F; last byte: 0x82");
             }
-
-            SECTION("ndarray of chars cut off by the end of the input")
-            {
-                // 2x2 chars announced, three present
-                std::vector<uint8_t> const v = {'[', '$', 'C', '#', '[', '$', 'U', '#', 'U', 2, 2, 2, 'a', 'b', 'c'};
-                json _;
-                CHECK_THROWS_WITH_AS(_ = json::from_bjdata(v), "[json.exception.parse_error.110] parse error at byte 16: syntax error while parsing BJData char: unexpected end of input", json::parse_error&);
-                CHECK(json::from_bjdata(v, true, false).is_discarded());
-            }
         }
 
         SECTION("byte")

tests/src/unit-bon8.cpp

@@ -329,9 +329,6 @@ TEST_CASE("BON8")
             check_bon8({false, nullptr, true}, {0x83, 0xF8, 0xFA, 0xF9});
             check_bon8({false, nullptr, true, 1.0}, {0x84, 0xF8, 0xFA, 0xF9, 0xFD});
             check_bon8({false, nullptr, true, 1.0, json::array(), 0.0}, {0x85, 0xF8, 0xFA, 0xF9, 0xFD, 0x80, 0xFC, 0xFE});
-            // an array that starts with a number: -1, 0, and 1 have bytes of their own
-            check_bon8({-1.0, 0.0, 1.0}, {0x83, 0xFB, 0xFC, 0xFD});
-            check_bon8({1.0, -1.0, -0.0}, {0x83, 0xFD, 0xFB, 0x8E, 0x80, 0x00, 0x00, 0x00});
             check_bon8({{{1}}}, {0x81, 0x81, 0x81, 0x91});
             check_bon8({{{"foo"}}}, {0x81, 0x81, 0x81, 'f', 'o', 'o', 0xFF});
             check_bon8({{{""}}}, {0x81, 0x81, 0x81, 0xFF});

tests/src/unit-bson.cpp

@@ -23,6 +23,7 @@ using nlohmann::json;
 #include <cstdint>
 #include <fstream>
 #include <limits>
+#include <list>
 #include <sstream>
 #include <vector>
 #include "make_test_data_available.hpp"
@@ -81,20 +82,8 @@ class huge_string_t : public std::string
         return result;
     }
 
-    // returns a copy of @a s whose size() pretends to be @a n
-    static huge_string_t as_size(const std::string& s, const size_type n)
-    {
-        huge_string_t result(s);
-        result.fake_size = n;
-        return result;
-    }
-
     size_type size() const noexcept
     {
-        if (fake_size != 0)
-        {
-            return fake_size;
-        }
         if (pretend_huge)
         {
             // one byte more than the BSON length field can represent
@@ -105,7 +94,6 @@ class huge_string_t : public std::string
 
   private:
     bool pretend_huge = false;
-    size_type fake_size = 0;
 };
 
 using huge_string_json = nlohmann::json::with_string_t<huge_string_t>;
@@ -280,17 +268,6 @@ TEST_CASE("BSON")
             CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
         }
 
-        SECTION("an array element that no longer fits the document")
-        {
-            // the string fits the length field, but not the document that
-            // holds it; nothing of it is written
-            const auto limit = static_cast<std::string::size_type>((std::numeric_limits<std::int32_t>::max)());
-            huge_string_json j;
-            j["a"] = huge_string_json::array({huge_string_t::as_size("value", limit - 8)});
-
-            CHECK_THROWS_AS(huge_string_json::to_bson(j), huge_string_json::out_of_range&);
-        }
-
         SECTION("document")
         {
             // an oversized string nested one level deep makes the
@@ -922,38 +899,6 @@ TEST_CASE("BSON")
             CHECK_THROWS_AS(_ = json::from_bson(input), json::parse_error&);
         }
 
-        SECTION("binary member with subtype 0x02 (old binary) with a truncated inner length")
-        {
-            // the inner length field is cut off by the end of the input
-            std::vector<std::uint8_t> const input =
-            {
-                0x0F, 0x00, 0x00, 0x00, // size (little endian)
-                0x05, 'a', 0x00, // entry: binary
-                0x08, 0x00, 0x00, 0x00, // size of binary (little endian)
-                0x02, // "old binary" subtype
-                0x01 // first byte of the inner length
-            };
-
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
-            CHECK(json::from_bson(input, true, false).is_discarded());
-        }
-
-        SECTION("string member that is cut off by the end of the input")
-        {
-            std::vector<std::uint8_t> const input =
-            {
-                0x0F, 0x00, 0x00, 0x00, // size (little endian)
-                0x02, 'a', 0x00, // entry: string
-                0x0A, 0x00, 0x00, 0x00, // size of the string (little endian)
-                'b', 'c' // the string ends early
-            };
-
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BSON string: unexpected end of input", json::parse_error&);
-            CHECK(json::from_bson(input, true, false).is_discarded());
-        }
-
         SECTION("Some more complex document")
         {
             json const j =
@@ -1255,6 +1200,31 @@ TEST_CASE("BSON keys from contiguous and stream input")
             from_stream = e.what();
         }
         CHECK(from_vector == from_stream);
+
+        // error_handler_t::strict checks the array element names in place on
+        // contiguous input and byte by byte otherwise; the names are
+        // well-formed, so both give the same value or error as above
+        std::string strict_from_vector;
+        std::string strict_from_list;
+        try
+        {
+            strict_from_vector = json::from_bson(input, true, true, json::error_handler_t::strict).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            strict_from_vector = e.what();
+        }
+        try
+        {
+            const std::list<std::uint8_t> list(input.begin(), input.end());
+            strict_from_list = json::from_bson(list.begin(), list.end(), true, true, json::error_handler_t::strict).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            strict_from_list = e.what();
+        }
+        CHECK(strict_from_vector == from_vector);
+        CHECK(strict_from_list == from_vector);
     }
 }
 
@@ -1283,6 +1253,18 @@ TEST_CASE("BSON array element names")
 
     std::istringstream stream(std::string(reinterpret_cast<const char*>(bson.data()), bson.size()));
     CHECK(json::from_bson(stream) == expected);
+
+    // input that is not contiguous reads the names byte by byte and must reject
+    // the same name
+    const std::list<std::uint8_t> list(bson.begin(), bson.end());
+    CHECK_THROWS_WITH_AS(_ = json::from_bson(list.begin(), list.end(), true, true, json::error_handler_t::strict), "[json.exception.parse_error.113] parse error at byte 14: syntax error while parsing BSON key: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+
+    // without exceptions, the rejected name ends the parse
+    CHECK(json::from_bson(bson, true, false, json::error_handler_t::strict).is_discarded());
+
+    // well-formed names pass the check without being stored
+    const json valid = {{"a", {true, false, {{"k", json::array({1, 2})}}}}};
+    CHECK(json::from_bson(json::to_bson(valid), true, true, json::error_handler_t::strict) == valid);
 }
 #endif
 
@@ -2192,25 +2174,6 @@ value = depth % 2 == 0 ? json{{"a", std::move(value)}, {"b", {1, "x"}}} :
         CHECK(output.empty());
     }
 
-#if !defined(JSON_NOEXCEPTION)
-    SECTION("U+0000 in a long key is found at any position")
-    {
-        // the key is searched eight characters at a time
-        for (const std::string& key :
-                {
-                    std::string("abc\0defghijkl", 12), std::string("abcdefgh\0ijkl", 13), std::string("abcdefghijklmnop\0", 17), std::string("\0abcdefghijkl", 13),
-                    std::string("abcdefghijklmno\0", 16)
-                })
-        {
-            CAPTURE(key)
-            const json value = json::object({{key, 1}});
-            std::vector<std::uint8_t> output;
-            CHECK_THROWS_AS(json::to_bson(value, output), json::out_of_range&);
-            CHECK(output.empty());
-        }
-    }
-#endif
-
     SECTION("a binary subtype that doesn't fit a byte is rejected before anything is written (#5675)")
     {
         // the offending value is nested, so this also covers that the check

tests/src/unit-cbor.cpp

@@ -1809,30 +1809,6 @@ TEST_CASE("CBOR")
             CHECK(json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01}), true, false).is_discarded());
         }
 
-        SECTION("tag in front of a key that is cut off by the end of the input")
-        {
-            // 0xD8: the tag number is in the next byte, which is missing
-            const std::vector<std::uint8_t> input = {0xA1, 0xD8};
-            json _;
-            for (const auto handler :
-                    {
-                        json::cbor_tag_handler_t::ignore, json::cbor_tag_handler_t::store
-                    })
-            {
-                CHECK_THROWS_WITH_AS(_ = json::from_cbor(input, true, true, handler), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
-                CHECK(json::from_cbor(input, true, false, handler).is_discarded());
-            }
-        }
-
-        SECTION("chunk of an indefinite-length string that is cut off by the end of the input")
-        {
-            // the second byte announces a chunk of three bytes, but two follow
-            const std::vector<std::uint8_t> input = {0x7F, 0x63, 'a', 'b'};
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
-            CHECK(json::from_cbor(input, true, false).is_discarded());
-        }
-
         SECTION("tag in front of a key")
         {
             const auto ignore = json::cbor_tag_handler_t::ignore;

tests/src/unit-class_lexer.cpp

@@ -2092,12 +2092,6 @@ TEST_CASE("UTF-8 validators accept the same sequences")
         }
     };
 
-    // an ASCII byte is a sequence of its own
-    for (unsigned lead = 0; lead < 0x80; ++lead)
-    {
-        CHECK(nlohmann::detail::utf8_shape(static_cast<std::uint8_t>(lead)).length == 1);
-    }
-
     for (unsigned lead = 0x80; lead <= 0xFF; ++lead)
     {
         const auto shape = nlohmann::detail::utf8_shape(static_cast<std::uint8_t>(lead));
@@ -2163,72 +2157,3 @@ TEST_CASE("UTF-8 validators accept the same sequences")
         }
     }
 }
-
-TEST_CASE("float_bigint")
-{
-    // the big integer of the exact comparison of a float token with the
-    // midpoint between two floats (digit_comparison())
-    using nlohmann::detail::float_bigint;
-
-    SECTION("zero")
-    {
-        // shifting zero keeps it zero, whatever the distance
-        float_bigint zero(0);
-        zero.shift_left(0);
-        zero.shift_left(5);
-        zero.shift_left(64);
-        CHECK(zero.compare(float_bigint(0)) == 0);
-        CHECK(zero.compare(float_bigint(1)) == -1);
-        CHECK(float_bigint(1).compare(zero) == 1);
-    }
-
-    SECTION("compare numbers of different lengths")
-    {
-        // the number with more 32-bit limbs is the greater one
-        const float_bigint small(0xFFFFFFFFu);
-        const float_bigint large(std::uint64_t{1} << 32u);
-        CHECK(small.compare(large) == -1);
-        CHECK(large.compare(small) == 1);
-        CHECK(large.compare(large) == 0);
-
-        // a shift can add a limb
-        float_bigint shifted(1);
-        shifted.shift_left(32);
-        CHECK(shifted.compare(large) == 0);
-        shifted.shift_left(1);
-        CHECK(shifted.compare(large) == 1);
-        CHECK(large.compare(shifted) == -1);
-    }
-
-    SECTION("compare numbers of the same length")
-    {
-        CHECK(float_bigint(2).compare(float_bigint(3)) == -1);
-        CHECK(float_bigint(3).compare(float_bigint(2)) == 1);
-        CHECK(float_bigint(3).compare(float_bigint(3)) == 0);
-        CHECK(float_bigint((std::uint64_t{3} << 32u) | 1u).compare(float_bigint((std::uint64_t{3} << 32u) | 2u)) == -1);
-    }
-}
-
-TEST_CASE("serialization of short strings")
-{
-    // the serializer takes strings of up to 32 characters that need no
-    // escaping by a table lookup of its own where the scan is not vectorized
-    // (this file is built that way, too, with JSON_NO_SIMD)
-    for (const std::string& s :
-            {
-                std::string(), std::string("a"), std::string("hello"), std::string("0123456789abcdef"), std::string("0123456789abcdef0123456789abcdef"),
-                std::string("0123456789abcdef0123456789abcdef0")
-            })
-    {
-        CAPTURE(s)
-        const json j = s;
-        CHECK(j.dump() == "\"" + s + "\"");
-        CHECK(j.dump(-1, ' ', true) == "\"" + s + "\"");
-        CHECK(json({{s, s}}).dump() == "{\"" + s + "\":\"" + s + "\"}");
-    }
-
-    // a character that needs an escape
-    CHECK(json("a\"b").dump() == "\"a\\\"b\"");
-    CHECK(json("caf\xC3\xA9").dump() == "\"caf\xC3\xA9\"");
-    CHECK(json("caf\xC3\xA9").dump(-1, ' ', true) == "\"caf\\u00e9\"");
-}

tests/src/unit-class_parser.cpp

@@ -2953,6 +2953,651 @@ TEST_CASE("diagnostic positions: value lifetime, input adapters, and SAX")
 }
 #endif
 
+namespace
+{
+/// builds a value like json::parse(), but asks the parser to recover from
+/// errors (see #3989), and checks that the events it receives are balanced
+class RecoveringDomParser
+{
+  public:
+    explicit RecoveringDomParser(json& j, std::size_t max_errors_ = static_cast<std::size_t>(-1))
+        : dom(j, false)
+        , max_errors(max_errors_)
+    {}
+
+    bool null()
+    {
+        value();
+        return dom.null();
+    }
+
+    bool boolean(bool val)
+    {
+        value();
+        return dom.boolean(val);
+    }
+
+    bool number_integer(json::number_integer_t val)
+    {
+        value();
+        return dom.number_integer(val);
+    }
+
+    bool number_unsigned(json::number_unsigned_t val)
+    {
+        value();
+        return dom.number_unsigned(val);
+    }
+
+    bool number_float(json::number_float_t val, const std::string& s)
+    {
+        value();
+        return dom.number_float(val, s);
+    }
+
+    bool string(std::string& val)
+    {
+        value();
+        return dom.string(val);
+    }
+
+    bool binary(json::binary_t& val)
+    {
+        value();
+        return dom.binary(val);
+    }
+
+    bool start_object(std::size_t elements)
+    {
+        value();
+        stack.push_back('o');
+        return dom.start_object(elements);
+    }
+
+    bool key(std::string& val)
+    {
+        ++events;
+        if (stack.empty() || stack.back() != 'o')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.back() = 'v';
+        return dom.key(val);
+    }
+
+    bool end_object()
+    {
+        ++events;
+        if (stack.empty() || stack.back() != 'o')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.pop_back();
+        return dom.end_object();
+    }
+
+    bool start_array(std::size_t elements)
+    {
+        value();
+        stack.push_back('a');
+        return dom.start_array(elements);
+    }
+
+    bool end_array()
+    {
+        ++events;
+        if (stack.empty() || stack.back() != 'a')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.pop_back();
+        return dom.end_array();
+    }
+
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& ex)
+    {
+        errors.emplace_back(ex.what());
+        return errors.size() < max_errors;
+    }
+
+    /// whether the events were balanced and every key was followed by a value
+    bool balanced() const
+    {
+        return well_formed && stack.empty();
+    }
+
+    /// builds the value
+    nlohmann::detail::json_sax_dom_parser<json> dom;
+    std::vector<std::string> errors {}; // NOLINT(readability-redundant-member-init)
+    std::size_t events = 0;
+    /// the open containers: 'a' for an array, 'o' for an object that expects
+    /// a key, 'v' for an object that expects the value of a key
+    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
+    bool well_formed = true;
+    std::size_t max_errors;
+
+  private:
+    /// a value is passed: it is an array element, or the value of a key
+    void value()
+    {
+        ++events;
+        if (!stack.empty())
+        {
+            if (stack.back() == 'v')
+            {
+                stack.back() = 'o';
+            }
+            else if (stack.back() == 'o')
+            {
+                // a value without a key
+                well_formed = false;
+            }
+        }
+    }
+
+};
+
+struct RecoveryResult
+{
+    json value;
+    std::vector<std::string> errors;
+    std::size_t events;
+    bool ok;
+    bool balanced;
+};
+
+template<typename InputType>
+RecoveryResult parse_recovering(InputType&& input, const bool strict = true,
+                                const bool ignore_comments = false, const bool ignore_trailing_commas = false)
+{
+    json j;
+    RecoveringDomParser sax(j);
+    const bool ok = json::sax_parse(std::forward<InputType>(input), &sax, json::input_format_t::json,
+                                    strict, ignore_comments, ignore_trailing_commas);
+    return {j, sax.errors, sax.events, ok, sax.balanced()};
+}
+
+/// stops after a number of events, but recovers from errors
+class RecoveringCountdown
+{
+  public:
+    explicit RecoveringCountdown(const int count)
+        : countdown(count)
+    {}
+
+    bool null()
+    {
+        return countdown.null();
+    }
+
+    bool boolean(bool val)
+    {
+        return countdown.boolean(val);
+    }
+
+    bool number_integer(json::number_integer_t val)
+    {
+        return countdown.number_integer(val);
+    }
+
+    bool number_unsigned(json::number_unsigned_t val)
+    {
+        return countdown.number_unsigned(val);
+    }
+
+    bool number_float(json::number_float_t val, const std::string& s)
+    {
+        return countdown.number_float(val, s);
+    }
+
+    bool string(std::string& val)
+    {
+        return countdown.string(val);
+    }
+
+    bool binary(json::binary_t& val)
+    {
+        return countdown.binary(val);
+    }
+
+    bool start_object(std::size_t elements)
+    {
+        return countdown.start_object(elements);
+    }
+
+    bool key(std::string& val)
+    {
+        return countdown.key(val);
+    }
+
+    bool end_object()
+    {
+        return countdown.end_object();
+    }
+
+    bool start_array(std::size_t elements)
+    {
+        return countdown.start_array(elements);
+    }
+
+    bool end_array()
+    {
+        return countdown.end_array();
+    }
+
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return true;
+    }
+
+  private:
+    SaxCountdown countdown;
+};
+
+/// a repaired input: the value it is repaired to, and the number of errors
+struct Repair
+{
+    const char* input;
+    const char* expected;
+    std::size_t errors;
+};
+} // namespace
+
+TEST_CASE("parser error recovery (#3989)")
+{
+    SECTION("repairs")
+    {
+        const std::vector<Repair> repairs =
+        {
+            // a missing separator is inserted
+            {"[1 2]", "[1,2]", 1},
+            {R"({"a":1 "b":2})", R"({"a":1,"b":2})", 1},
+            {R"({"a" 1})", R"({"a":1})", 1},
+            {"[1 tru 2]", "[1,null,2]", 2},
+            {R"({"a" "b": 1})", R"({"a":"b"})", 2},
+
+            // a missing value is null in an object; in an array, a ',' stands
+            // for null, while an array that ends there just ends
+            {R"({"a":})", R"({"a":null})", 1},
+            {R"({"a"})", R"({"a":null})", 1},
+            {R"({"a","b":1})", R"({"a":null,"b":1})", 1},
+            {"[1,,2]", "[1,null,2]", 1},
+            {"[,1]", "[null,1]", 1},
+            {"[1,]", "[1]", 1},
+            {"[1,2,3,]", "[1,2,3]", 1},
+            {R"({"a":1,})", R"({"a":1})", 1},
+
+            // a broken string keeps what can be read
+            {R"(["a\qb"])", R"(["aqb"])", 1},
+            {R"({"na\me":1})", R"({"name":1})", 1},
+            {"[\"\xFF\"]", R"(["\uFFFD"])", 1},
+            {"[\"a\xC3(\"]", R"(["a\uFFFD("])", 1},
+            {"[\"\xE2\x82\"]", R"(["\uFFFD"])", 1},
+            {"[\"\xC3\\\\\", 1]", R"(["\uFFFD\\",1])", 1},
+            {R"(["\u12"])", R"(["\uFFFD"])", 1},
+            {R"(["\u12G4"])", R"(["\uFFFDG4"])", 1},
+            {R"(["\uDC00x"])", R"(["\uFFFDx"])", 1},
+            {R"(["\uD800x"])", R"(["\uFFFDx"])", 1},
+            {R"(["\uD800\u0041"])", R"(["\uFFFDA"])", 1},
+            {R"(["\uD800\uD800\uDC00"])", R"(["\uFFFD\uD800\uDC00"])", 1},
+            {R"(["\uD800\uD800\uD800x"])", R"(["\uFFFD\uFFFD\uFFFDx"])", 1},
+            {
+                R"(["\uD800\"x", 1])", R"(["\uFFFD\"x",1])", 1
+            },
+            {R"(["\uD800\q"])", R"(["\uFFFDq"])", 1},
+            {"[\"a\tb\"]", R"(["a\tb"])", 1},
+            {R"(["a\qb\u0041\x"])", R"(["aqbAx"])", 1},
+
+            // a broken number keeps its longest valid prefix
+            {"[1.]", "[1]", 1},
+            {"[-2.]", "[-2]", 1},
+            {"[1.5e]", "[1.5]", 1},
+            {"[1e+]", "[1]", 1},
+            {"[1.x2, 3]", "[1,3]", 1},
+
+            // what cannot be read at all is null
+            {"[1,NaN,3]", "[1,null,3]", 1},
+            {"[tru]", "[null]", 1},
+            {"[-]", "[null]", 1},
+            {R"({"a":Infinity})", R"({"a":null})", 1},
+
+            // a stray token is dropped
+            {"[:1]", "[1]", 1},
+            {R"(["a":1])", R"(["a",1])", 1},
+            {R"({"a"::1})", R"({"a":1})", 1},
+
+            // a member that cannot be read is skipped
+            {R"({1:2,"b":3})", R"({"b":3})", 1},
+            {R"({"a":1 2})", R"({"a":1})", 1},
+            {R"({,"a":1})", R"({"a":1})", 1},
+            {R"({"a":1,,"b":2})", R"({"a":1,"b":2})", 1},
+            {"{a:1}", "{}", 1},
+            {R"({"a":1 [1,{"b":2}], "c":3})", R"({"a":1,"c":3})", 1},
+            {R"([{1}, "a"])", R"([{},"a"])", 1},
+
+            // a wrong closing bracket closes the innermost container
+            {R"({"a":[1,2}, "b":3})", R"({"a":[1,2],"b":3})", 1},
+            {R"([{"a":1], 2])", R"([{"a":1},2])", 1},
+            {"{]", "{}", 1},
+            {"[}", "[]", 1},
+
+            // the end of the input closes all containers
+            {R"({"a":[1,2)", R"({"a":[1,2]})", 1},
+            {"[", "[]", 1},
+            {"{", "{}", 1},
+            {R"({"a")", R"({"a":null})", 1},
+            {R"({"a":)", R"({"a":null})", 1},
+            {"[1,", "[1]", 1},
+            {"[[[1", "[[[1]]]", 1},
+            {
+                R"(["abc)", R"(["abc"])", 2
+            },
+            {"[1,tr", "[1,null]", 2},
+            {"\"abc", "\"abc\"", 1},
+            {"[\"ab\ncd\"]", R"(["ab",null,"]"])", 4},
+
+            // what comes before the top-level value is skipped
+            {")]}'\n{\"a\":1}", R"({"a":1})", 1},
+            {R"(data: {"a":1})", R"({"a":1})", 1},
+            {"\xEF\xBB[1]", "[1]", 1},
+
+            // what comes after it is an error that ends parsing
+            {R"({"a":1}})", R"({"a":1})", 1},
+            {"[1}]", "[1]", 2},
+            {"[1] [2]", "[1]", 1},
+        };
+
+        for (const auto& repair : repairs)
+        {
+            CAPTURE(repair.input)
+            const auto result = parse_recovering(std::string(repair.input));
+            CHECK(!result.ok);
+            CHECK(result.balanced);
+            CHECK(result.value == json::parse(repair.expected));
+            CHECK(result.errors.size() == repair.errors);
+        }
+    }
+
+    SECTION("number overflow")
+    {
+        const auto result = parse_recovering(std::string("[1e999,-1e999]"));
+        CHECK(!result.ok);
+        CHECK(result.balanced);
+        CHECK(result.errors.size() == 2);
+        CHECK(result.errors[0] == "[json.exception.out_of_range.406] number overflow parsing '1e999'");
+        REQUIRE(result.value.size() == 2);
+        CHECK(result.value[0].is_number_float());
+        CHECK(result.value[0].get<double>() == std::numeric_limits<double>::infinity());
+        CHECK(result.value[1].get<double>() == -std::numeric_limits<double>::infinity());
+
+        // the SAX parser gets the number's text
+        SaxEventLogger logger;
+        logger.recover = true;
+        CHECK(!json::sax_parse("1e999", &logger));
+        CHECK(logger.events == std::vector<std::string>({"parse_error(5)", "number_float(1e999)"}));
+    }
+
+    SECTION("nothing to recover")
+    {
+        for (const std::string s :
+                {
+                    "", "   ", "]", "tru", "NaN", ",:", "/* comment"
+                })
+        {
+            CAPTURE(s)
+            const auto result = parse_recovering(s, true, true);
+            CHECK(!result.ok);
+            CHECK(result.balanced);
+            CHECK(result.events == 0);
+            CHECK(result.value == nullptr);
+            CHECK(result.errors.size() == 1);
+        }
+    }
+
+    SECTION("error messages")
+    {
+        // the first error is reported as without recovery
+        for (const std::string s :
+                {
+                    "[1 2]", R"({"a":1 "b":2})", R"({"a" 1})", R"({"a":})", "[1,]", "[1.]",
+                    R"(["a\qb"])", "[1e999]", "{1:2}", R"({"a":[1,2}})", "[1,", "[1] [2]", "{a:1}"
+                })
+        {
+            CAPTURE(s)
+            const auto result = parse_recovering(s);
+            REQUIRE(!result.errors.empty());
+            json _;
+            CHECK_THROWS_WITH_STD_STR(_ = json::parse(s), result.errors.front());
+        }
+
+        // the token of an error begins where the previous error was
+        const auto result = parse_recovering(std::string("[tru, fals, nul]"));
+        CHECK(result.errors == std::vector<std::string>(
+        {
+            "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: '[tru,'",
+            "[json.exception.parse_error.101] parse error at line 1, column 11: syntax error while parsing value - invalid literal; last read: ', fals,'",
+            "[json.exception.parse_error.101] parse error at line 1, column 16: syntax error while parsing value - invalid literal; last read: ', nul]'"
+        }));
+        CHECK(result.value == json::parse("[null,null,null]"));
+    }
+
+    SECTION("events")
+    {
+        // see #4522
+        SaxEventLogger logger;
+        logger.recover = true;
+        CHECK(!json::sax_parse(R"([{1}, "a"])", &logger));
+        CHECK(logger.events == std::vector<std::string>(
+        {
+            "start_array()", "start_object()", "parse_error(3)", "end_object()", "string(a)", "end_array()"
+        }));
+    }
+
+    SECTION("options")
+    {
+        SECTION("strict")
+        {
+            const auto result = parse_recovering(std::string("[1 2] [3]"), false);
+            CHECK(!result.ok);
+            CHECK(result.value == json::parse("[1,2]"));
+            CHECK(result.errors.size() == 1);
+        }
+
+        SECTION("ignore_trailing_commas")
+        {
+            for (const std::string s :
+                    {
+                        "[1,]", R"({"a":1,})", "[[1,],]"
+                    })
+            {
+                CAPTURE(s)
+                const auto result = parse_recovering(s, true, false, true);
+                CHECK(result.ok);
+                CHECK(result.errors.empty());
+            }
+
+            auto result = parse_recovering(std::string("[1,,]"), true, false, true);
+            CHECK(result.value == json::parse("[1,null]"));
+            CHECK(result.errors.size() == 1);
+
+            result = parse_recovering(std::string(R"({"a":1,,})"), true, false, true);
+            CHECK(result.value == json::parse(R"({"a":1})"));
+            CHECK(result.errors.size() == 1);
+        }
+
+        SECTION("ignore_comments")
+        {
+            auto result = parse_recovering(std::string("[1 /* one */ 2]"), true, true);
+            CHECK(result.value == json::parse("[1,2]"));
+            CHECK(result.errors.size() == 1);
+
+            // a comment that is not closed runs to the end of the input, which
+            // is not reported again
+            result = parse_recovering(std::string("[1, 2 /* unterminated"), true, true);
+            CHECK(result.balanced);
+            CHECK(result.value == json::parse("[1,2]"));
+            CHECK(result.errors.size() == 1);
+
+            // a '/' that does not begin a comment is garbage
+            result = parse_recovering(std::string("[1, /x, 2]"), true, true);
+            CHECK(result.balanced);
+            CHECK(result.value == json::parse("[1,null,2]"));
+            CHECK(result.errors.size() == 1);
+        }
+    }
+
+    SECTION("null bytes")
+    {
+        // a null byte ends the input, unless JSON_STRICT_NUL_HANDLING is set
+        const auto result = parse_recovering(std::string("[1,\0x", 5));
+        CHECK(result.balanced);
+        CHECK(!result.ok);
+#ifdef JSON_TEST_STRICT_NUL_HANDLING_ENABLED
+        CHECK(result.value == json::parse("[1,null]"));
+#else
+        CHECK(result.value == json::parse("[1]"));
+        CHECK(result.errors.size() == 1);
+#endif
+
+        const auto in_string = parse_recovering(std::string("[\"a\0b\"]", 7));
+        CHECK(in_string.balanced);
+#ifdef JSON_TEST_STRICT_NUL_HANDLING_ENABLED
+        CHECK(in_string.value == json::array({std::string("a\0b", 3)}));
+#else
+        CHECK(in_string.value == json::parse(R"(["a"])"));
+#endif
+    }
+
+    SECTION("the SAX parser stops recovering")
+    {
+        json j;
+        RecoveringDomParser sax(j, 2);
+        CHECK(!json::sax_parse("[1 2 3 4 5]", &sax));
+        CHECK(sax.errors.size() == 2);
+
+        // an error at a delimiter that an invalid token consumed is reported
+        // to the SAX parser, too
+        json j2;
+        RecoveringDomParser sax2(j2, 2);
+        CHECK(!json::sax_parse("[tru}, 1]", &sax2));
+        CHECK(sax2.errors.size() == 2);
+    }
+
+    SECTION("an event stops parsing during a repair")
+    {
+        // start_object() and key() are passed, then null() for the missing
+        // value returns false
+        RecoveringCountdown countdown(2);
+        CHECK(!json::sax_parse(R"({"a":})", &countdown));
+
+        // the end of the input: end_array() for the second array returns false
+        RecoveringCountdown countdown2(4);
+        CHECK(!json::sax_parse("[[1", &countdown2));
+    }
+
+    SECTION("input adapters")
+    {
+        // the lexer reads contiguous and streaming input differently, and it
+        // puts back a character that ended an invalid token
+        for (const std::string s :
+                {
+                    "[1 2]", "[tru}, 1]", R"({"a" "b\q", "c":[1.x, 2}})", "[\"\xFF\xC3(\", -, 1e+]", "{a:1,\"b\":2", ")]}' [1]"
+                })
+        {
+            CAPTURE(s)
+            const auto reference = parse_recovering(s);
+            CHECK(reference.balanced);
+
+            const auto from_c_string = parse_recovering(s.c_str());
+            CHECK(from_c_string.value == reference.value);
+            CHECK(from_c_string.errors == reference.errors);
+
+            const std::list<char> l(s.begin(), s.end());
+            json j;
+            RecoveringDomParser sax(j);
+            CHECK(!json::sax_parse(l.begin(), l.end(), &sax));
+            CHECK(j == reference.value);
+            CHECK(sax.errors == reference.errors);
+
+            std::istringstream ss(s);
+            const auto from_stream = parse_recovering(ss);
+            CHECK(from_stream.value == reference.value);
+            CHECK(from_stream.errors == reference.errors);
+        }
+    }
+
+    SECTION("long runs of errors")
+    {
+        // no error may copy all the input read before it
+        const auto closing = parse_recovering("[" + std::string(100000, '}'));
+        CHECK(closing.balanced);
+        CHECK(closing.value == json::array());
+
+        const auto garbage = parse_recovering("[" + std::string(100000, 'x') + "]");
+        CHECK(garbage.balanced);
+        CHECK(garbage.errors.size() == 1);
+
+        const auto commas = parse_recovering("{" + std::string(100000, ',') + "}");
+        CHECK(commas.balanced);
+        CHECK(commas.value == json::object());
+    }
+
+    SECTION("mutations of valid input")
+    {
+        // whatever the input, the events are balanced, every error is reported
+        // at most once, and valid input is parsed as usual
+        const std::vector<std::string> documents =
+        {
+            R"({"name": "value", "list": [1, -2.5, true, null, {"x": [[]]}], "e": "\u00e9"})",
+            R"([{"a": [1, 2, {"b": "c"}]}, [], {}, "\ud83d\ude00", 1e10])",
+            "{\"\xC3\xA9\": \"\xF0\x9F\x98\x80\"}",
+            R"(  {"k" : [ "v" , 0 ] }  )",
+        };
+        // each character that can be inserted, including a null byte
+        const std::string insertions("[]{},:\"x\\\0\xFF", 11);
+
+        std::vector<std::string> inputs;
+        for (const auto& doc : documents)
+        {
+            for (std::size_t i = 0; i <= doc.size(); ++i)
+            {
+                inputs.push_back(doc.substr(0, i));
+                if (i < doc.size())
+                {
+                    inputs.push_back(doc.substr(0, i) + doc.substr(i + 1));
+                }
+                for (const char c : insertions)
+                {
+                    inputs.push_back(doc.substr(0, i) + c + doc.substr(i));
+                }
+            }
+        }
+
+        for (const auto& s : inputs)
+        {
+            CAPTURE(s)
+            const auto result = parse_recovering(s);
+            CHECK(result.balanced);
+            CHECK(result.errors.size() <= s.size() + 1);
+            CHECK(result.events <= (4 * s.size()) + 4);
+            if (json::accept(s))
+            {
+                CHECK(result.ok);
+                CHECK(result.errors.empty());
+                CHECK(result.value == json::parse(s));
+            }
+            else
+            {
+                CHECK(!result.ok);
+                CHECK(!result.errors.empty());
+            }
+        }
+    }
+}
+
 TEST_CASE("accept() agrees with parse() on floats around the overflow limit")
 {
     // accept() does not convert a float that cannot overflow; the tokens

tests/src/unit-custom-array-type.cpp

@@ -210,23 +210,3 @@ TEST_CASE("regression test #5476 - array type without reserve()")
         CHECK(json::from_cbor(truncated, true, false).is_discarded());
     }
 }
-
-TEST_CASE("array type with std::deque nested beyond the recursion limit")
-{
-    // the binary writers finish a value nested deeper than
-    // recursion_depth_limit() with an explicit stack of frames; with the
-    // iterators of std::deque, these frames are copied and moved through
-    // their own special members
-    deque_json j = 1;
-    for (int i = 0; i < 200; ++i)
-    {
-        deque_json outer = deque_json::array();
-        outer.push_back(std::move(j));
-        j = std::move(outer);
-    }
-
-    // 200 arrays of one element each (0x81) around the integer 1
-    std::vector<std::uint8_t> expected(200, 0x81);
-    expected.push_back(0x01);
-    CHECK(deque_json::to_cbor(j) == expected);
-}

tests/src/unit-custom-key-type-full.cpp

@@ -49,24 +49,3 @@ TEST_CASE("custom object key types: MessagePack (json_full)")
 {
     custom_key_test::test_msgpack<json_full>();
 }
-
-TEST_CASE("custom object key types: patch (json_full)")
-{
-    // the members of a patch are found by lookup, as their keys are not std::string
-    const json_full j = json_full::parse(R"({"a":1,"b":[1,2],"c":{"d":2}})");
-    const json_full patch = json_full::parse(R"([
-        {"op": "add", "path": "/e", "value": 5},
-        {"op": "remove", "path": "/a"},
-        {"op": "replace", "path": "/c/d", "value": 3},
-        {"op": "test", "path": "/c/d", "value": 3},
-        {"op": "move", "from": "/e", "path": "/f"},
-        {"op": "copy", "from": "/f", "path": "/g"},
-        {"op": "add", "path": "/b/-", "value": 7}
-    ])");
-
-    CHECK(j.patch(patch).dump() == R"({"b":[1,2,7],"c":{"d":3},"f":5,"g":5})");
-
-    // a patch with a missing member is rejected
-    CHECK_THROWS_AS(j.patch(json_full::parse(R"([{"op": "add", "path": "/e"}])")), json_full::parse_error&);
-    CHECK_THROWS_AS(j.patch(json_full::parse(R"([{"op": "test", "path": "/a", "value": 2}])")), json_full::other_error&);
-}

tests/src/unit-custom-number-types.cpp

@@ -337,52 +337,6 @@ TEST_CASE("custom number types: integers beyond 64 bits")
         CHECK(wide_json::to_bson(fit_members) == nlohmann::json::to_bson(fit_members64));
     }
 
-    SECTION("MessagePack integers of every width")
-    {
-        // an integer of a number type wider than 64 bits is written with the
-        // smallest MessagePack integer that holds it, as for 64-bit types
-        const wide_json widths = wide_json::array(
-        {
-            make_int(-33), make_int(-100), make_int(-128), make_int(-129), make_int(-32768), make_int(-32769), make_int(-2147483648LL), make_int(-2147483649LL),
-            make_int(128), make_int(255), make_int(256), make_int(300), make_int(65535), make_int(65536), make_int(70000), make_int(4294967295LL), make_int(4294967296LL),
-            make_uint(128), make_uint(255), make_uint(256), make_uint(300), make_uint(65535), make_uint(65536), make_uint(70000), make_uint(4294967295ULL), make_uint(4294967296ULL)
-        });
-        const nlohmann::json widths64 = nlohmann::json::array(
-        {
-            -33, -100, -128, -129, -32768, -32769, -2147483648LL, -2147483649LL,
-            128, 255, 256, 300, 65535, 65536, 70000, 4294967295LL, 4294967296LL,
-            128u, 255u, 256u, 300u, 65535u, 65536u, 70000u, 4294967295ULL, 4294967296ULL
-        });
-        CHECK(wide_json::to_msgpack(widths) == nlohmann::json::to_msgpack(widths64));
-
-        // as single values, too
-        CHECK(wide_json::to_msgpack(make_int(-100)) == std::vector<std::uint8_t>({0xD0, 0x9C}));
-        CHECK(wide_json::to_msgpack(make_int(300)) == std::vector<std::uint8_t>({0xCD, 0x01, 0x2C}));
-        CHECK(wide_json::to_msgpack(make_int(70000)) == std::vector<std::uint8_t>({0xCE, 0x00, 0x01, 0x11, 0x70}));
-        CHECK(wide_json::to_msgpack(make_uint(300)) == std::vector<std::uint8_t>({0xCD, 0x01, 0x2C}));
-        CHECK(wide_json::to_msgpack(make_uint(70000)) == std::vector<std::uint8_t>({0xCE, 0x00, 0x01, 0x11, 0x70}));
-    }
-
-    SECTION("dump")
-    {
-        // beyond 64 bits, the digits are counted before they are written
-        CHECK(make_int(0).dump() == "0");
-        CHECK(make_int(two_64).dump() == "18446744073709551616");
-        CHECK(make_int(-two_64).dump() == "-18446744073709551616");
-        CHECK(make_int(two_100).dump() == "1267650600228229401496703205376");
-        CHECK(make_int(-two_100).dump() == "-1267650600228229401496703205376");
-        // powers of ten, where the count of digits ends on a single digit or two
-        const int128 ten_20 = static_cast<int128>(100000000000ULL) * static_cast<int128>(1000000000ULL);
-        CHECK(make_int(ten_20).dump() == "100000000000000000000");
-        CHECK(make_int(-ten_20).dump() == "-100000000000000000000");
-        CHECK(make_int(ten_20 * 10).dump() == "1000000000000000000000");
-        CHECK(make_int(ten_20 * 100).dump() == "10000000000000000000000");
-        CHECK(make_int(ten_20 * 1000).dump() == "100000000000000000000000");
-        CHECK(make_uint(static_cast<uint128>(ten_20) * 10u).dump() == "1000000000000000000000");
-        CHECK(make_uint((std::numeric_limits<uint128>::max)()).dump() == "340282366920938463463374607431768211455");
-        CHECK(make_int((std::numeric_limits<int128>::min)()).dump() == "-170141183460469231731687303715884105728");
-    }
-
     SECTION("BJData ND-array")
     {
         // an ND-array element beyond 64 bits does not fit any dtype, so the
@@ -463,23 +417,3 @@ TEST_CASE("custom number types")
     }
 
 }
-
-TEST_CASE("custom number types: 32-bit integers in the binary formats")
-{
-    // integers narrower than 64 bits are widened (a signed one with its sign)
-    // before the CBOR, MessagePack, and UBJSON writers pick their encoding
-    using json32 = nlohmann::json::with_integers_t<std::int32_t, std::uint32_t>;
-    json32 values = json32::array();
-    values.push_back(std::uint32_t{0});
-    values.push_back(std::uint32_t{200});
-    values.push_back(std::uint32_t{4294967295u});
-    values.push_back(std::int32_t{-1});
-    values.push_back(std::int32_t{-2147483647 - 1});
-    REQUIRE(values[2].is_number_unsigned());
-    REQUIRE(values[4].is_number_integer());
-
-    const nlohmann::json values64 = {0u, 200u, 4294967295u, -1, -2147483648LL};
-    CHECK(json32::to_cbor(values) == nlohmann::json::to_cbor(values64));
-    CHECK(json32::to_msgpack(values) == nlohmann::json::to_msgpack(values64));
-    CHECK(json32::to_ubjson(values) == nlohmann::json::to_ubjson(values64));
-}

tests/src/unit-custom-object-key-type.cpp

@@ -11,13 +11,8 @@
 #include <nlohmann/json.hpp>
 
 #include <cstddef>
-#include <cstdint>
-#include <map>
-#include <memory>
 #include <string>
-#include <type_traits>
 #include <utility>
-#include <vector>
 
 #include "custom_object_key_type.hpp"
 
@@ -130,161 +125,3 @@ TEST_CASE("MessagePack supports custom object key types nested deeper than the r
     CHECK(encoded == nlohmann::json::to_msgpack(expected));
     CHECK(nlohmann::json::from_msgpack(encoded) == expected);
 }
-
-namespace
-{
-// A key type that cannot be constructed from a std::string, so that a value
-// with such keys cannot be converted from a nlohmann::json by the range
-// constructor of its object type: the serializer converts the object instead.
-class strict_key
-{
-  public:
-    strict_key(const char* value)
-        : m_value(value)
-    {}
-
-    strict_key(const std::string& /*value*/) = delete;
-
-#if JSON_DIAGNOSTICS
-    // Required by JSON_DIAGNOSTICS, which reads object keys through data()
-    // when building the path of an exception.
-    const char* data() const noexcept
-    {
-        return m_value.data();
-    }
-#endif
-
-    friend bool operator<(const strict_key& lhs, const strict_key& rhs)
-    {
-        return lhs.m_value < rhs.m_value;
-    }
-
-  private:
-    std::string m_value{};
-};
-
-strict_key make_strict_key(const std::string& key)
-{
-    return strict_key(key.c_str());
-}
-
-template<class Key, class Value, class Compare, class Allocator>
-class strict_object
-    : public std::map <
-      strict_key,
-      Value,
-      std::less<strict_key>, // NOLINT(modernize-use-transparent-functors)
-      typename std::allocator_traits<Allocator>::template rebind_alloc <
-          std::pair<const strict_key, Value >>>
-{
-  public:
-    strict_object() = default;
-};
-
-template<typename T, typename = void>
-struct strict_serializer : nlohmann::adl_serializer<T> {};
-
-using strict_json = nlohmann::basic_json < strict_object, std::vector, std::string, bool, std::int64_t,
-      std::uint64_t, double, std::allocator, strict_serializer, std::vector<std::uint8_t >>;
-
-// the members of an object are converted one by one, their keys by make_strict_key()
-template<>
-struct strict_serializer<nlohmann::json::object_t, void>
-{
-    static void to_json(strict_json& j, const nlohmann::json::object_t& object)
-    {
-        strict_json::object_t converted;
-        for (const auto& member : object)
-        {
-            converted.emplace(make_strict_key(member.first), strict_json(member.second));
-        }
-        j = strict_json(std::move(converted));
-    }
-};
-} // namespace
-
-TEST_CASE("converting a value with keys that cannot be made from a std::string nested deeper than the recursion depth limit")
-{
-    static_assert(!std::is_constructible<strict_key, const std::string&>::value, "the keys cannot be made from a std::string");
-
-    // below detail::recursion_depth_limit(), objects and arrays are converted
-    // by the serializers instead of the range constructors
-    const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 10;
-
-    nlohmann::json value = 1;
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        if (i % 2 == 0)
-        {
-            value = nlohmann::json::object({{"a", std::move(value)}, {"b", true}});
-        }
-        else
-        {
-            value = nlohmann::json::array({std::move(value), "sibling"});
-        }
-    }
-
-    const strict_json converted = value;
-
-    // at() needs to make a std::string of a key for its error message
-    const auto member = [](const strict_json & object, const char* name) -> const strict_json &
-    {
-        const auto it = object.find(strict_key(name));
-        REQUIRE(it != object.end());
-        return *it;
-    };
-
-    // walk down the nesting levels without recursion
-    const strict_json* current = &converted;
-    for (std::size_t i = depth; i > 0; --i)
-    {
-        if (i % 2 == 1)
-        {
-            REQUIRE(current->is_object());
-            CHECK(current->size() == 2);
-            CHECK(member(*current, "b").get<bool>());
-            current = &member(*current, "a");
-        }
-        else
-        {
-            REQUIRE(current->is_array());
-            CHECK(current->size() == 2);
-            CHECK(current->at(1).get<std::string>() == "sibling");
-            current = &current->at(0);
-        }
-    }
-    CHECK(current->get<int>() == 1);
-}
-
-namespace
-{
-// shorter keys come first
-struct shortlex_less
-{
-    bool operator()(const std::string& lhs, const std::string& rhs) const
-    {
-        return lhs.size() != rhs.size() ? lhs.size() < rhs.size() : lhs < rhs;
-    }
-};
-
-template<class Key, class Value, class Compare, class Allocator>
-using shortlex_map = std::map<Key, Value, shortlex_less, Allocator>;
-
-using shortlex_json = nlohmann::json::with_object_t<shortlex_map>;
-} // namespace
-
-TEST_CASE("unflatten with an object type that does not sort the keys alphabetically")
-{
-    // the keys of /a come before and after one of /b: unlike in an object
-    // sorted alphabetically, the values below a prefix are not found one
-    // after the other, so the value of /a must be looked up again
-    shortlex_json flat = shortlex_json::object();
-    flat["/a/p"] = 1;
-    flat["/b/qq"] = 2;
-    flat["/a/pqr"] = 3;
-    REQUIRE(flat.begin().key() == "/a/p");
-    REQUIRE((++flat.begin()).key() == "/b/qq");
-
-    CHECK(flat.unflatten().dump() == R"({"a":{"p":1,"pqr":3},"b":{"qq":2}})");
-    CHECK(flat.unflatten().flatten() == flat);
-}

tests/src/unit-deserialization.cpp

@@ -1195,28 +1195,6 @@ TEST_CASE("deserialization")
 #endif
 }
 
-#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-TEST_CASE("deserialization from a pointer and a length (deprecated)")
-{
-    // the unit test build disables -Wdeprecated-declarations (see
-    // cmake/clang_flags.cmake)
-    const std::string text = R"({"foo": [1, 2, 3]})";
-    const std::string invalid = R"({"foo": )";
-
-    SECTION("parse")
-    {
-        const json j = json::parse({text.data(), text.size()});
-        CHECK(j == json({{"foo", {1, 2, 3}}}));
-    }
-
-    SECTION("accept")
-    {
-        CHECK(json::accept({text.data(), text.size()}));
-        CHECK_FALSE(json::accept({invalid.data(), invalid.size()}));
-    }
-}
-#endif
-
 // select the types to test - char8_t is only available since C++20 if and only
 // if __cpp_char8_t is defined.
 #define TYPE_LIST(...) __VA_ARGS__

tests/src/unit-diagnostics.cpp

@@ -868,23 +868,3 @@ TEST_CASE("Parent pointers stay consistent for object types not known to keep th
     obj["1"].push_back(42);
     CHECK_THROWS_WITH_AS(obj["1"].at(5), "[json.exception.out_of_range.401] (/1) array index 5 is out of range", relocating_json::out_of_range&);
 }
-
-TEST_CASE("patch_inplace() with a patch that is stored inside the patched value")
-{
-    // the patch is modified-while-iterated if it is not copied first: it is a
-    // descendant of the value it is applied to, which only the parent pointers
-    // (JSON_DIAGNOSTICS) reveal
-    json j =
-    {
-        {"patch", {{{"op", "add"}, {"path", "/x"}, {"value", 1}}, {{"op", "remove"}, {"path", "/patch/0"}}}},
-        {"y", 2}
-    };
-
-    j.patch_inplace(j["patch"]);
-
-    CHECK(j.size() == 3);
-    CHECK(j["x"] == 1);
-    CHECK(j["y"] == 2);
-    CHECK(j["patch"].size() == 1);
-    CHECK(j["patch"][0]["op"] == "remove");
-}

tests/src/unit-iterators2.cpp

@@ -18,8 +18,6 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
-#include <iterator>
-
 #if JSON_HAS_RANGES
     #include <algorithm>
     #include <ranges>
@@ -667,23 +665,6 @@ TEST_CASE("iterators 2")
         }
     }
 
-    SECTION("reverse iterators of a const value")
-    {
-        const json j_array = {1, 2, 3};
-        const json j_object = {{"one", 1}, {"two", 2}};
-
-        // rbegin() and rend() of a const value are crbegin() and crend()
-        CHECK(j_array.rbegin() == j_array.crbegin());
-        CHECK(j_array.rend() == j_array.crend());
-        CHECK(*j_array.rbegin() == 3);
-        CHECK(std::distance(j_array.rbegin(), j_array.rend()) == 3);
-
-        CHECK(j_object.rbegin() == j_object.crbegin());
-        CHECK(j_object.rend() == j_object.crend());
-        CHECK(j_object.rbegin().key() == "two");
-        CHECK(std::distance(j_object.rbegin(), j_object.rend()) == 2);
-    }
-
     SECTION("reverse iterator arithmetic")
     {
         json j_object = {{"one", 1}, {"two", 2}, {"three", 3}};

tests/src/unit-json_patch.cpp

@@ -14,11 +14,9 @@ using nlohmann::json;
     using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
 #endif
 
-#include <cstddef>
 #include <fstream>
 #include <limits>
 #include <string>
-#include <utility>
 #include <vector>
 #include "make_test_data_available.hpp"
 
@@ -2455,99 +2453,3 @@ TEST_CASE("JSON patch - diff behavior documented in the API reference")
         CHECK(json::diff(json(nullptr), json::array()) == R"([{"op": "replace", "path": "", "value": []}])"_json);
     }
 }
-
-TEST_CASE("JSON patch - operations that are left to json_pointer")
-{
-    // the usual operations on a plain pointer are applied without building a
-    // json_pointer; the following are not plain, and some are errors
-    SECTION("a path without a slash")
-    {
-        const json j = {{"a", 1}};
-
-        CHECK_THROWS_AS(j.patch(R"([{"op": "add", "path": "abc", "value": 1}])"_json), json::parse_error&);
-        CHECK_THROWS_AS(j.patch(R"([{"op": "remove", "path": "abc"}])"_json), json::parse_error&);
-    }
-
-    SECTION("remove with an escaped reference token")
-    {
-        const json j = {{"a/b", 1}, {"c~d", 2}, {"e", 3}};
-
-        CHECK(j.patch(R"([{"op": "remove", "path": "/a~1b"}])"_json) == json({{"c~d", 2}, {"e", 3}}));
-        CHECK(j.patch(R"([{"op": "remove", "path": "/c~0d"}])"_json) == json({{"a/b", 1}, {"e", 3}}));
-        CHECK_THROWS_AS(j.patch(R"([{"op": "remove", "path": "/missing~1key"}])"_json), json::out_of_range&);
-    }
-
-    SECTION("a path through a primitive value")
-    {
-        const json j = {{"a", 1}};
-
-        CHECK_THROWS_AS(j.patch(R"([{"op": "test", "path": "/a/b", "value": 1}])"_json), json::other_error&);
-        CHECK_THROWS_AS(j.patch(R"([{"op": "replace", "path": "/a/b", "value": 1}])"_json), json::out_of_range&);
-    }
-}
-
-TEST_CASE("JSON patch - diff of objects with many members")
-{
-    // more members than diff() keeps without allocating
-    for (const std::size_t members :
-            {
-                16u, 17u, 40u
-            })
-    {
-        CAPTURE(members)
-
-        json source = json::object();
-        json target = json::object();
-        for (std::size_t i = 0; i < members; ++i)
-        {
-            const std::string key = "key" + std::to_string(i);
-            source[key] = i;
-            // every third member differs
-            target[key] = (i % 3 == 0) ? i + 1 : i;
-        }
-        // the same keys, a removed and an added one
-        source["removed"] = true;
-        target["added"] = false;
-
-        const json patch = json::diff(source, target);
-        CHECK(source.patch(patch) == target);
-        CHECK(patch.size() == ((members + 2) / 3) + 2);
-
-        const nlohmann::ordered_json ordered_source = source;
-        const nlohmann::ordered_json ordered_target = target;
-        CHECK(ordered_source.patch(nlohmann::ordered_json::diff(ordered_source, ordered_target)) == ordered_target);
-    }
-}
-
-TEST_CASE("JSON patch - diff of leaf values below the bound of the recursive descent")
-{
-    // the values at the innermost level are diffed without recursion: equal
-    // leaves yield nothing, leaves of different types and different leaves
-    // are replaced
-    const std::size_t depth = 200;
-
-    json source = {1, "text", 3, {{"x", 1}, {"y", 2}}, true, nullptr};
-    json target = {1, 2, 4, {{"x", 1}, {"y", 3}}, true, nullptr};
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        source = json::array({std::move(source)});
-        target = json::array({std::move(target)});
-    }
-
-    const json patch = json::diff(source, target);
-    CHECK(patch.size() == 3);
-    CHECK(source.patch(patch) == target);
-
-    // the same with objects as the outer levels
-    json object_source = {{"equal", 1}, {"type", "text"}, {"value", 3}};
-    json object_target = {{"equal", 1}, {"type", 2}, {"value", 4}};
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        object_source = json::object({{"a", std::move(object_source)}});
-        object_target = json::object({{"a", std::move(object_target)}});
-    }
-
-    const json object_patch = json::diff(object_source, object_target);
-    CHECK(object_patch.size() == 2);
-    CHECK(object_source.patch(object_patch) == object_target);
-}

tests/src/unit-json_pointer.cpp

@@ -106,12 +106,6 @@ TEST_CASE("JSON pointers")
         CHECK_THROWS_WITH_AS(p.pop_back(),
                              "[json.exception.out_of_range.405] JSON pointer has no parent", json::out_of_range&);
 
-        // the top of a pointer is its first reference token
-        const json::json_pointer nonempty("/foo/bar/0");
-        CHECK(nonempty.top() == json::json_pointer("/foo"));
-        CHECK(nonempty.top().to_string() == "/foo");
-        CHECK(json::json_pointer("/a~1b").top() == json::json_pointer("/a~1b"));
-
         SECTION("array index error")
         {
             json v = {1, 2, 3, 4};
@@ -703,16 +697,6 @@ TEST_CASE("JSON pointers")
         CHECK_THROWS_WITH_AS(j_error.unflatten(),
                              "[json.exception.type_error.313] invalid value to unflatten", json::type_error&);
 
-        // error for an invalid escape sequence in a key
-        CHECK_THROWS_WITH_AS(json({{"/a~2", 1}}).unflatten(),
-        "[json.exception.parse_error.108] parse error: escape character '~' must be followed with '0' or '1'", json::parse_error&);
-        CHECK_THROWS_WITH_AS(json({{"/a/b", 1}, {"/c~", 1}}).unflatten(),
-        "[json.exception.parse_error.108] parse error: escape character '~' must be followed with '0' or '1'", json::parse_error&);
-
-        // error for an element of an array that is also a container
-        CHECK_THROWS_WITH_AS(json({{"/a/0", 1}, {"/a/0/x", 2}}).unflatten(),
-        "[json.exception.type_error.313] invalid value to unflatten", json::type_error&);
-
         // explicit roundtrip check
         CHECK(j.flatten().unflatten() == j);
 

tests/src/unit-json_view.cpp

@@ -31,11 +31,9 @@ using json_view_test::has_duplicate_keys;
 #include <ios>
 #include <istream>
 #include <iterator>
-#include <functional>
 #include <limits>
 #include <list>
 #include <map>
-#include <new>
 #include <random>
 #include <sstream>
 #include <string>
@@ -100,37 +98,6 @@ template<typename View>
 using bool_conversion_t = decltype(static_cast<bool>(std::declval<View>()));
 
 #if !defined(JSON_NOEXCEPTION)
-// an allocator that never has room
-template<typename T>
-struct failing_allocator
-{
-    using value_type = T;
-
-    failing_allocator() = default;
-
-    template<typename U>
-    explicit failing_allocator(const failing_allocator<U>& /*other*/) noexcept {}
-
-    T* allocate(std::size_t /*n*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        throw std::bad_alloc();
-    }
-
-    void deallocate(T* /*p*/, std::size_t /*n*/) noexcept {} // NOLINT(readability-convert-member-functions-to-static)
-
-    template<typename U>
-    bool operator==(const failing_allocator<U>& /*other*/) const noexcept
-    {
-        return true;
-    }
-
-    template<typename U>
-    bool operator!=(const failing_allocator<U>& /*other*/) const noexcept
-    {
-        return false;
-    }
-};
-
 // the exception parse() throws for a text, or "" if it accepts it
 std::string parse_exception(const std::string& text, bool comments = false, bool trailing_commas = false)
 {
@@ -268,9 +235,7 @@ TEST_CASE("json_view")
                 {
                     "", " ", "[", "]", "{", "[1,]", "{\"a\":1,}", "[1 2]", "{\"a\" 1}", "{1:2}", "tru", "nul", "fals", "truex", "-", "01", "1.", ".5", "1e",
                     "\"", "\"abc", "\"\\x\"", "\"\\u12\"", "\"\\ud800\"", "\"\\udc00\"", "\"\x01\"", "\"\xff\"", "\"\xc3\"", "[1]x", "/", "/*", "[\n  1,\n  x\n]", // NOLINT(modernize-raw-string-literal)
-                    "1e400", "-1e400", "[1.7976931348623159e308]", "{\"a\":\n{\"b\": [1, 2,\n 3 x]}}",
-                    // (an error after every kind of value: the error is found by replaying the parser)
-                    "[null, true, -1, 1, 1.5, \"s\", {\"a\": 1} 2]", "{\"a\": null, \"b\": -1, \"c\": 1.5, \"d\": \"s\", \"e\": {}, 1}"
+                    "1e400", "-1e400", "[1.7976931348623159e308]", "{\"a\":\n{\"b\": [1, 2,\n 3 x]}}"
                 })
         {
             CAPTURE(text)
@@ -403,10 +368,6 @@ TEST_CASE("json_view")
         CHECK(from_stream.root().materialize() == expected);
         const std::list<char> list(text.begin(), text.end());
         CHECK(json_document::parse(list.begin(), list.end()).owns_source());
-        // (an input that is not valid)
-        const std::list<char> bad_list{'[', '1', ','};
-        json_document from_bad_list;
-        CHECK_THROWS_AS(from_bad_list = json_document::parse(bad_list.begin(), bad_list.end()), json::parse_error&);
         CHECK(materialized<json_document>(list.begin(), list.end()) == expected);
 
         // iterator pairs: pointers are borrowed, and so are contiguous library
@@ -1550,17 +1511,6 @@ TEST_CASE("json_view values")
         const json_document dup = json_document::parse(R"({"a":1,"a":2})");
         CHECK((dup.root().get<std::map<std::string, int>>() == std::map<std::string, int> {{"a", 2}}));
 
-        // a map of views from something that is not an object
-        using view_map = std::map<std::string, json_view>;
-        const json_document not_an_object = json_document::parse("[1,2]");
-        CHECK_THROWS_WITH_AS(not_an_object.root().get<view_map>(), json_view_test::message("type_error.302", "", 0, 5, "type must be object, but is array").c_str(), json::type_error&);
-#if !defined(JSON_NOEXCEPTION)
-        // (and one that cannot allocate its nodes)
-        using failing_map = std::map<std::string, json_view, std::less<std::string>, failing_allocator<std::pair<const std::string, json_view>>>;
-        const json_document one_member = json_document::parse(R"({"a":1})");
-        CHECK_THROWS_AS(one_member.root().get<failing_map>(), std::bad_alloc&);
-#endif
-
         const json_view invalid{};
         CHECK_THROWS_WITH_AS(invalid.get<int>(), "[json.exception.type_error.302] type must be number, but is discarded", json::type_error&);
         CHECK(invalid.get<json>().is_discarded());

tests/src/unit-json_view_builder.cpp

@@ -692,7 +692,7 @@ TEST_CASE("json_view builder: fraction digits")
             check_same(number);
             check_same("[" + number + "]");
             std::string pair;
-            pair.reserve(number.size() * 2 + 3);
+            pair.reserve((number.size() * 2) + 3);
             pair += '[';
             pair += number;
             pair += ',';

tests/src/unit-json_view_compare_values.cpp

@@ -1,83 +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_view.hpp>
-using nlohmann::json;
-using nlohmann::json_document;
-
-#include <functional>
-#include <map>
-#include <string>
-
-// These tests were split off unit-json_view_compare.cpp, whose object file got
-// too large for the MinGW assembler ("file too big").
-
-namespace
-{
-// an object type that does not enumerate its members in ascending order of keys
-template<typename Key, typename Value, typename /*Compare*/, typename Allocator>
-using descending_object = std::map<Key, Value, std::greater<Key>, Allocator>;
-} // namespace
-
-TEST_CASE("json_view comparison of differing values")
-{
-    SECTION("values that differ in their first bytes, or are written differently")
-    {
-        const auto same = [](const char* x, const char* y)
-        {
-            const json_document dx = json_document::parse(x);
-            const json_document dy = json_document::parse(y);
-            const bool equal = dx.root() == dy.root();
-            CHECK(equal == (json::parse(x) == json::parse(y)));
-            CHECK(equal == (dx.root() == json::parse(y)));
-            const nlohmann::json_editable_document ex = nlohmann::json_editable_document::parse(x);
-            CHECK(equal == (ex.root() == dy.root()));
-            return equal;
-        };
-        // booleans
-        CHECK(!same("true", "false"));
-        CHECK(!same("[true]", "[false]"));
-        CHECK(!same(R"({"a":false,"b":[1]})", R"({"a":true,"b":[1]})"));
-        CHECK(same(R"({"a":true,"b":[1]})", R"({"a":true,"b":[1]})"));
-        // strings and keys of equal length that differ in the first eight bytes (they are compared in words)
-        CHECK(!same(R"("abcdefghijklmnopqrstuvwxyz")", R"("Xbcdefghijklmnopqrstuvwxyz")"));
-        CHECK(!same(R"(["abcdefghijklmnopq",1])", R"(["abcdefghXjklmnopq",1])"));
-        CHECK(!same(R"({"abcdefghijklmnopq":1})", R"({"Xbcdefghijklmnopq":1})"));
-        CHECK(!same(R"({"abcdefghijklmnopq":[1]})", R"({"abcdefghijklmnopX":[1]})"));
-        // floats of one layout and different tokens are the same value
-        CHECK(same("[1.5e0, 2]", "[1.5E0, 2]"));
-        CHECK(same("[1.5e0, 2]", "[1.5e+0, 2]"));
-        CHECK(same("[1.50, 2]", "[1.5, 2]"));
-        CHECK(!same("[1.5e0, 2]", "[1.6e0, 2]"));
-        CHECK(!same("[1.5e0, 2]", "[1.5E1, 2]"));
-        CHECK(same(R"({"a":1.25e0,"b":[3]})", R"({"a":1.25E0,"b":[3]})"));
-    }
-
-    SECTION("a basic_json whose members are not sorted")
-    {
-        // (an object type that is not an ordered map, and does not keep its members sorted either)
-        using descending_json = nlohmann::basic_json<descending_object>;
-        using descending_document = nlohmann::basic_json_document<descending_json>;
-        std::string text = "{";
-        for (char key = 'a'; key <= 'p'; ++key)
-        {
-            text += (key != 'a' ? ",\"" : "\"") + std::string(1, key) + "\":[" + std::to_string(key) + "]";
-        }
-        text += "}";
-        const descending_json j = descending_json::parse(text);
-        const descending_document d = descending_document::parse(text);
-        CHECK(d.root() == j);
-        CHECK(j == d.root());
-        descending_json other = j;
-        other["k"] = 0;
-        CHECK(d.root() != other);
-        CHECK(other != d.root());
-    }
-}

tests/src/unit-json_view_dump.cpp

@@ -101,10 +101,6 @@ TEST_CASE("json_view dump")
         CHECK(d.root().dump(0, ' ', false, json_view::number_format::source) == "[\n1.50,\n1E2,\n-0,\n-0.0,\n123456789012345678901234567890,\n18446744073709551615,\n-9223372036854775808,\n0.1,\n1e-7,\n5e-324\n]");
         CHECK(d.root().dump(-1, ' ', true, json_view::number_format::source) == "[1.50,1E2,-0,-0.0,123456789012345678901234567890,18446744073709551615,-9223372036854775808,0.1,1e-7,5e-324]");
 
-        CHECK(d.root().dump(0, ' ', true, json_view::number_format::source) == d.root().dump(0, ' ', false, json_view::number_format::source));
-        const json_document escaped = json_document::parse("[\"\xC3\xA9\", 1.50, {\"\xF0\x9F\x98\x80\": 1E2}]");
-        CHECK(escaped.root().dump(1, ' ', true, json_view::number_format::source) == "[\n \"\\u00e9\",\n 1.50,\n {\n  \"\\ud83d\\ude00\": 1E2\n }\n]");
-
         // float tokens of up to 17 significant digits in every spelling: those
         // of at most 15 digits are written from their digits, the others
         // through the conversion; both as dump() writes them
@@ -236,29 +232,6 @@ TEST_CASE("json_view dump")
             CHECK(editable.root().dump() == expected.dump());
         }
 
-        // tokens of 16 and 17 digits with few digits after the point, and with a value of 0, which are
-        // converted by the general algorithm; padded, as a token near the end of the text is not read in this way
-        {
-            const std::string padding(40, ' ');
-            for (const char* token :
-                    {
-                        "123456789012.3456", "-123456789012.3456", "1234567890123.456", "12345678901234.56", "123456789012345.6", "1234567890123456.0",
-                        "0.0000000000000000", "-0.0000000000000000", "0.000000000000000", "1234567890123.4567", "99999999999999.999"
-                    })
-            {
-                CAPTURE(token)
-                const std::string padded = std::string("[") + token + padding + "]";
-                const json_document padded_document = json_document::parse(padded);
-                const json padded_json = json::parse(padded);
-                CHECK(padded_document.root()[0].get<double>() == padded_json[0].get<double>());
-                CHECK(padded_document.root().dump() == padded_json.dump());
-                // a float document converts the tokens as well
-                using json_float = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
-                const nlohmann::basic_json_document<json_float> float_doc = nlohmann::basic_json_document<json_float>::parse(padded);
-                CHECK(float_doc.root()[0].get<float>() == json_float::parse(padded)[0].get<float>());
-            }
-        }
-
         // random doubles, written as parse() and dump() would
         std::mt19937_64 rng(1170); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
         std::string many = "[";

tests/src/unit-json_view_dump_escape.cpp

@@ -214,24 +214,6 @@ TEST_CASE("json_view dump: escaping, nesting, and output buffers")
         CHECK(d.root()["a"].dump(-1, ' ', true).size() == 2 + (5000 * 6));
     }
 
-    SECTION("the estimate for a value that is followed by many decoded strings")
-    {
-        // (the end of the value in the source is not known when the nodes after it have decoded strings)
-        std::string text = "[7";
-        for (int i = 0; i < 20; ++i)
-        {
-            text += R"(,"\n")";
-        }
-        text += ",8]";
-        const json_document d = json_document::parse(text);
-        CHECK(d.root()[0].dump() == "7");
-        CHECK(d.root()[1].dump() == R"("\n")");
-        CHECK(d.root().dump() == json::parse(text).dump());
-        // the same with a container
-        const json_document nested = json_document::parse(R"([[7],)" + text.substr(3));
-        CHECK(nested.root()[0].dump() == "[7]");
-    }
-
     SECTION("ensure_ascii with strings of the source, decoded strings, and edited strings")
     {
         // plain ASCII, non-ASCII, escaped (decoded), and mixed strings, as values and as keys;
@@ -277,28 +259,6 @@ TEST_CASE("json_view dump: escaping, nesting, and output buffers")
         }
     }
 
-    SECTION("the length of the run that ensure_ascii copies")
-    {
-        // (dump() only asks for strings with a byte to escape, so a run that ends the string is checked here)
-        for (const std::size_t length :
-                {
-                    std::size_t{0}, std::size_t{1}, std::size_t{15}, std::size_t{16}, std::size_t{17}, std::size_t{31}, std::size_t{32}, std::size_t{48}, std::size_t{50}
-                })
-        {
-            CAPTURE(length)
-            // a run of printable characters, followed by a byte that is not copied and more text
-            std::string text(length, 'a');
-            text += "\"abcdefghijklmnopqrstuvwxyz";
-            const auto* const bytes = reinterpret_cast<const unsigned char*>(text.data()); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-            const auto* const end = bytes + text.size();
-            CHECK(nlohmann::detail::view::ascii_copyable_run(bytes, length, end) == length);
-            CHECK(nlohmann::detail::view::ascii_copyable_run(bytes, length + 1, end) == length);
-            CHECK(nlohmann::detail::view::ascii_copyable_run(bytes, length + 5, end) == length);
-            // the end of the buffer right after the run
-            CHECK(nlohmann::detail::view::ascii_copyable_run(bytes, length, bytes + length) == length);
-        }
-    }
-
     SECTION("ensure_ascii with DEL or a non-ASCII character at every position")
     {
         // the check whether a string of the source has no byte >= 0x7F reads

tests/src/unit-json_view_edit.cpp

@@ -547,10 +547,6 @@ TEST_CASE("json_view edits: errors")
     CHECK_THROWS_WITH_AS(d.set(json::json_pointer("/a/01"), 1), "[json.exception.parse_error.106] parse error: array index '01' must not begin with '0'", json::parse_error&);
     CHECK_THROWS_WITH_AS(d.set(root, json_editable_view()), "[json.exception.type_error.302] type must be a value, but is discarded", json::type_error&);
     CHECK_THROWS_WITH_AS(d.set(root, json::binary({1, 2})), "[json.exception.type_error.319] cannot store a binary value in a json_document", json::type_error&);
-    CHECK_THROWS_WITH_AS(d.set(root, json(json::value_t::discarded)), "[json.exception.type_error.302] type must be a value, but is discarded", json::type_error&);
-    // (an index that does not fit the document, in a null: basic_json would pad it with 4 Gi nulls)
-    CHECK_THROWS_AS(d.set(json::json_pointer("/z/4294967295"), 1), json::out_of_range&);
-    CHECK(root["z"].is_null());
 
 #if !defined(JSON_NOEXCEPTION)
     // invalid UTF-8 is rejected when it enters the document, with the error
@@ -576,19 +572,6 @@ TEST_CASE("json_view edits: errors")
     static_cast<void>(other);
 }
 
-TEST_CASE("json_view edits: a container that was added is replaced by a scalar")
-{
-    // the view of an element that push_back() added is that of the new value itself, not of
-    // the slot that links to it: replacing it by a scalar has to find the container it is in
-    json_editable_document d = json_editable_document::parse(R"({"a": [1]})");
-    d.push_back(d.root()["a"], json::array({2, 3}));
-    d.push_back(d.root()["a"], json::object({{"k", json::array({4, 5})}}));
-    d.set(d.root()["a"][1], 6);
-    d.set(d.root()["a"][2]["k"], "s");
-    CHECK(d.root().dump() == R"({"a":[1,6,{"k":"s"}]})");
-    CHECK(d.root().materialize() == json::parse(R"({"a":[1,6,{"k":"s"}]})"));
-}
-
 #if !defined(JSON_NOEXCEPTION)
 TEST_CASE("json_view edits: the size of a text arena")
 {

tests/src/unit-json_view_from_json.cpp

@@ -277,17 +277,6 @@ TEST_CASE("json_view from_json")
         CHECK(true);
     }
 
-    SECTION("a map with enum keys from a view that is not an object")
-    {
-        // an object is read with the keys as the enum's names; any other
-        // value is read as an array of pairs, like a map of any other key type
-        const json_document d = json_document::parse(R"({"pairs": [["red", 1], ["green", 2]], "number": 1})");
-        const json j = d.root().materialize();
-        const json_view v = d.root();
-        CHECK(same<std::map<color, int>>(v, j, "pairs"));
-        CHECK((v["pairs"].get<std::map<color, int>>() == std::map<color, int> {{color::red, 1}, {color::green, 2}}));
-    }
-
     SECTION("std types: the same values as from the materialized value")
     {
         const json_document d = json_document::parse(R"({"ints": [3, 1, 2, 1], "strings": ["b", "a", "b"], "pairs": [[1, "x"], [2, "y"]],

tests/src/unit-json_view_image.cpp

@@ -819,13 +819,6 @@ TEST_CASE("json_view images: errors")
             static_cast<void>(d);
         }) == prefix + "too short");
 
-        // an image that is moved into the document is checked as well
-        CHECK(exception_of([&]
-        {
-            const json_document d = json_document::load(std::vector<std::uint8_t>(10, 0));
-            static_cast<void>(d);
-        }) == prefix + "too short");
-
         std::vector<std::uint8_t> bad = image;
         bad[0] = 'X';
         CHECK(load_result(bad, image_check::full) == prefix + "unknown format");

tests/src/unit-json_view_large.cpp

@@ -333,62 +333,6 @@ TEST_CASE("json_view large objects")
         CHECK(without_collisions.memory_usage() >= with_collisions.memory_usage() + (table_size * sizeof(std::uint32_t)));
     }
 
-    SECTION("a lookup of a missing key stops at the end of the probe window")
-    {
-        // Every slot of the first half of the table holds a key, each at its home slot, so
-        // that the table is built; a key that is not in the object but whose home slot is
-        // the first slot finds a full window of slots with other keys.
-        constexpr std::size_t members = 128;
-        constexpr std::size_t table_size = 256; // the table size for 128 members: the next power of two >= 256
-        for (const std::size_t prefix_length :
-                {
-                    std::size_t{0}, std::size_t{20}
-                })
-        {
-            CAPTURE(prefix_length)
-            std::vector<std::string> keys(members);
-            std::vector<bool> taken(members, false);
-            std::string missing;
-            std::size_t found = 0;
-            for (std::uint64_t counter = 0; found < members || missing.empty(); ++counter)
-            {
-                std::string key(prefix_length, 'p');
-                std::uint64_t x = counter;
-                for (std::size_t i = 0; i < 8; ++i, x /= 26)
-                {
-                    key += static_cast<char>('a' + (x % 26));
-                }
-                const std::size_t slot = nlohmann::detail::conditional_static_cast<std::size_t>(nlohmann::detail::view::key_hash(key.data(), key.size())) & (table_size - 1);
-                if (slot < members && !taken[slot])
-                {
-                    taken[slot] = true;
-                    keys[slot] = key;
-                    ++found;
-                }
-                else if (slot == 0 && missing.empty())
-                {
-                    missing = key;
-                }
-            }
-            std::string text = "{";
-            for (std::size_t i = 0; i < members; ++i)
-            {
-                text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i);
-            }
-            text += "}";
-            const json_document d = json_document::parse(text);
-            const json_view v = d.root();
-            for (std::size_t i = 0; i < members; ++i)
-            {
-                CAPTURE(i)
-                CHECK(v[keys[i]].get<std::size_t>() == i);
-            }
-            CHECK(!v.contains(missing));
-            CHECK(v.find(missing) == v.end());
-            CHECK(v.count(missing) == 0);
-        }
-    }
-
     SECTION("keys that differ in their last bytes are spread over the table")
     {
         // The hash must spread the usual families of keys (numbered names, hex

tests/src/unit-json_view_positions.cpp

@@ -20,7 +20,6 @@ using nlohmann::ordered_json;
 using nlohmann::json_document;
 using nlohmann::json_editable_document;
 
-#include <algorithm>
 #include <cstdint>
 #include <cstring>
 #include <fstream>
@@ -428,31 +427,6 @@ TEST_CASE("json_view materialize() source positions")
             CHECK(same_positions(m[std::string("a") + '\n'][2], j[std::string("a") + '\n'][2]));
         }
 
-        SECTION("a damaged text: the end of a container is not found")
-        {
-            // (the text of an image is not checked with image_check::none)
-            const std::string array_text = "[1,2]";
-            const std::vector<std::uint8_t> original = json_document::parse(array_text).save();
-            const auto at = std::search(original.begin(), original.end(), array_text.begin(), array_text.end());
-            REQUIRE(at != original.end());
-            const auto closing = static_cast<std::size_t>(at - original.begin()) + array_text.size() - 1;
-            // not a closing bracket, a slash that starts no comment, and the end of the text
-            for (const char replacement :
-                    {
-                        'x', '/', ' '
-                    })
-            {
-                CAPTURE(replacement)
-                std::vector<std::uint8_t> damaged = original;
-                damaged[closing] = static_cast<std::uint8_t>(replacement);
-                const json_document d = json_document::load(damaged, json_document::image_check::none);
-                const json m = d.root().materialize();
-                CHECK(range(m) == "none");
-                CHECK(range(m[0]) == "1-2");
-                CHECK(range(m[1]) == "3-4");
-            }
-        }
-
 #if !defined(JSON_NOEXCEPTION)
         SECTION("a decoded string's position must be within the text")
         {
@@ -487,7 +461,6 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         {
             "null", "true", "42", "\"s\"", "[]", "{}", "[1, [2, [3, []]]]", R"({"a": {"b": [1, {"c": null}]}, "d": "e"})",
             R"({"a/b": {"~": [1]}, "\u0041\n": {"x": "\t"}, "": [{}]})",
-            R"({"a\u0000b": [1, "x"], "c": {"d\u0000": 2}})", // (the path of a key ends at a null byte, as in basic_json)
             R"([1 /* ] */, {"a": [] // }
 , "b": {} } , ])",
             "\n\t[\r\n  1 ,\n  {\n    \"a\" : [ ]\n  }\n]\n",
@@ -539,49 +512,6 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         CHECK(exception_of_call([&] { static_cast<void>(d.root()["a"][2]["n"][0].get<int>()); }) == expected);
     }
 
-    SECTION("views of values that are no longer part of the document, and of no value")
-    {
-        const std::string expected_string = "[json.exception.type_error.302] type must be number, but is string";
-        static_cast<void>(expected_string);
-        // (a value that is not found has no path, and with it no bytes)
-        {
-            json_editable_document d = json_editable_document::parse(R"(["x", ["y"]])");
-            const auto removed = d.root()[0];
-            d.erase(d.root(), 0);
-#if JSON_DIAGNOSTICS
-            CHECK(exception_of_call([&] { static_cast<void>(removed.get<int>()); }) == expected_string);
-#endif
-            // (the root is a scalar now: the value cannot be in it)
-            d.set(d.root(), 5);
-#if JSON_DIAGNOSTICS
-            CHECK(exception_of_call([&] { static_cast<void>(removed.get<int>()); }) == expected_string);
-#endif
-            CHECK(d.root().get<int>() == 5);
-        }
-        {
-            json_editable_document d = json_editable_document::parse(R"(["x"])");
-            const auto removed = d.root()[0];
-            d.set(d.root(), 5);
-#if JSON_DIAGNOSTICS
-            CHECK(exception_of_call([&] { static_cast<void>(removed.get<int>()); }) == expected_string);
-#endif
-        }
-        // a view of no value has no context
-        CHECK(exception_of_call([&] { static_cast<void>(nlohmann::json_view().get<int>()); }) == "[json.exception.type_error.302] type must be number, but is discarded");
-    }
-
-    SECTION("an array whose last element was replaced by a new container has no bytes")
-    {
-        json_editable_document d = json_editable_document::parse(R"({"a": [1, [2]], "b": 1})");
-        d.set(d.root()["a"][1], json::array({3}));
-        std::string expected = "[json.exception.type_error.302] ";
-#if JSON_DIAGNOSTICS
-        expected += "(/a) ";
-#endif
-        expected += "type must be number, but is array";
-        CHECK(exception_of_call([&] { static_cast<void>(d.root()["a"].get<int>()); }) == expected);
-    }
-
     SECTION("deep documents with siblings after every nested container")
     {
         // the search for the path pushes and pops one frame per level (the
@@ -591,7 +521,8 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         std::string text = "7";
         for (int level = 0; level < 40; ++level)
         {
-            text = R"([[1, [2]], )" + text + R"(, {"k": [3, {"l": [4]}]}, [5, [6, [7]]]])";
+            text.insert(0, R"([[1, [2]], )");
+            text += R"(, {"k": [3, {"l": [4]}]}, [5, [6, [7]]]])";
         }
         CAPTURE(text)
         const json j = json::parse(text);

tests/src/unit-large_json.cpp

@@ -12,10 +12,7 @@
 using nlohmann::json;
 
 #include <algorithm>
-#include <cstddef>
-#include <cstdint>
 #include <string>
-#include <utility>
 
 TEST_CASE("tests on very large JSONs")
 {
@@ -143,56 +140,6 @@ TEST_CASE("tests on deeply nested JSONs")
             }
         }
 
-        SECTION("leaf values of every type below the bound of the recursive descent")
-        {
-            // the elements and members of the containers below the bound are
-            // copied one by one, whatever their type
-            const json leaves = json::array(
-            {
-                nullptr, true, false, -1, std::uint64_t{1}, 1.5, "text", json::binary({1, 2, 3})
-            });
-            const json members =
-            {
-                {"null", nullptr}, {"boolean", true}, {"integer", -1}, {"unsigned", std::uint64_t{1}},
-                {"float", 1.5}, {"string", "text"}, {"binary", json::binary({1, 2, 3})}
-            };
-
-            for (const bool objects :
-                    {
-                        false, true
-                    })
-            {
-                CAPTURE(objects)
-
-                json j = objects ? members : leaves;
-                for (std::size_t i = 0; i < 300; ++i)
-                {
-                    json wrapper = objects ? json::object() : json::array();
-                    if (objects)
-                    {
-                        wrapper["a"] = std::move(j);
-                    }
-                    else
-                    {
-                        wrapper.push_back(std::move(j));
-                    }
-                    j = std::move(wrapper);
-                }
-
-                const json copy(j); // NOLINT(performance-unnecessary-copy-initialization): the copy is what is tested
-
-                const json* current = &copy;
-                for (std::size_t i = 0; i < 300; ++i)
-                {
-                    current = objects ? &current->at("a") : &current->front();
-                }
-
-                // the innermost value is shallow: it is safe to compare
-                CHECK(*current == (objects ? members : leaves));
-                CHECK(current->size() == (objects ? members.size() : leaves.size()));
-            }
-        }
-
         SECTION("a value that is deep in one place only")
         {
             json j = json::object();

tests/src/unit-locale-cpp.cpp

@@ -495,206 +495,3 @@ TEST_CASE("locale changes during a single dump() (#5709 item 3)")
     // fix #5597 made on the parser side
     CHECK(buf.data == "[\"" + padding + "\",1234.5]");
 }
-
-namespace
-{
-// a token whose first data() call switches LC_NUMERIC, so that the locale
-// changes between convert_float_locale_aware() looking up the decimal point
-// and strtod reading the token (the race of #5198, made deterministic)
-struct locale_switching_token
-{
-    using value_type = char;
-
-    locale_switching_token(std::string text_, const char* switch_to_)
-        : text(std::move(text_)), switch_to(switch_to_)
-    {}
-
-    std::size_t size() const
-    {
-        return text.size();
-    }
-
-    char& operator[](std::size_t i)
-    {
-        return text[i];
-    }
-
-    char* data()
-    {
-        if (!switched)
-        {
-            switched = std::setlocale(LC_NUMERIC, switch_to) != nullptr;
-        }
-        return &text[0];
-    }
-
-    std::string text;
-    const char* switch_to;
-    bool switched = false;
-};
-
-// set LC_NUMERIC to the first of @a names that is usable and has a decimal
-// point of @a min_size bytes at least (and at most @a max_size)
-bool use_decimal_point_locale(const std::vector<const char*>& names, std::size_t min_size, std::size_t max_size, const char*& used)
-{
-    for (const char* name : names)
-    {
-        if (std::setlocale(LC_NUMERIC, name) == nullptr)
-        {
-            continue;
-        }
-        const std::size_t size = std::string(std::localeconv()->decimal_point).size();
-        if (size >= min_size && size <= max_size)
-        {
-            used = name;
-            return true;
-        }
-    }
-    return false;
-}
-
-// convert a token with convert_float_locale_aware(); the token must be given
-// back as it was
-template<typename FloatType>
-FloatType convert_locale_aware(const std::string& text)
-{
-    std::string token = text;
-    const std::size_t dot = token.find('.');
-    FloatType value{};
-    nlohmann::detail::convert_float_locale_aware(token, dot, value);
-    CHECK(token == text);
-    return value;
-}
-
-template<typename FloatType>
-void check_locale_aware_conversions()
-{
-    CHECK(convert_locale_aware<FloatType>("3.5") == FloatType(3.5));
-    CHECK(convert_locale_aware<FloatType>("-0.25") == FloatType(-0.25));
-    CHECK(convert_locale_aware<FloatType>("1.25e2") == FloatType(125));
-    // no decimal point at all
-    CHECK(convert_locale_aware<FloatType>("12e1") == FloatType(120));
-    CHECK(convert_locale_aware<FloatType>("7") == FloatType(7));
-}
-} // namespace
-
-TEST_CASE("convert_float_locale_aware")
-{
-    const std::vector<const char*> single_byte_names = {"de_DE.UTF-8", "de_DE", "fr_FR.UTF-8", "fr_FR", "ru_RU.UTF-8"};
-    const std::vector<const char*> multi_byte_names = {"ar_EG.UTF-8", "ar_SA.UTF-8", "fa_IR.UTF-8", "ps_AF.UTF-8", "ar_EG", "fa_IR"};
-    const char* used = nullptr;
-
-    SECTION("decimal point '.'")
-    {
-        REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-        check_locale_aware_conversions<float>();
-        check_locale_aware_conversions<double>();
-        check_locale_aware_conversions<long double>();
-    }
-
-    SECTION("single-byte decimal point other than '.'")
-    {
-        if (use_decimal_point_locale(single_byte_names, 1, 1, used) && std::localeconv()->decimal_point[0] != '.')
-        {
-            CAPTURE(used)
-            check_locale_aware_conversions<float>();
-            check_locale_aware_conversions<double>();
-            check_locale_aware_conversions<long double>();
-        }
-        else
-        {
-            MESSAGE("no locale with a single-byte decimal point other than '.' is usable");
-        }
-    }
-
-    SECTION("multi-byte decimal point")
-    {
-        if (use_decimal_point_locale(multi_byte_names, 2, 8, used))
-        {
-            CAPTURE(used)
-            check_locale_aware_conversions<float>();
-            check_locale_aware_conversions<double>();
-            check_locale_aware_conversions<long double>();
-        }
-        else
-        {
-            MESSAGE("no locale with a multi-byte decimal point is usable");
-        }
-    }
-
-    SECTION("a token that is not converted completely")
-    {
-        // the locale does not change, so there is nothing to retry: the
-        // value up to the garbage is kept
-        REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-        std::string token = "1.5x";
-        double value = 0;
-        nlohmann::detail::convert_float_locale_aware(token, token.find('.'), value);
-        CHECK(value == 1.5);
-        CHECK(token == "1.5x");
-    }
-
-    SECTION("the locale changes before the conversion")
-    {
-        if (!use_decimal_point_locale(single_byte_names, 1, 1, used) || std::localeconv()->decimal_point[0] == '.')
-        {
-            MESSAGE("no locale with a single-byte decimal point other than '.' is usable");
-        }
-        else
-        {
-            const std::string comma_locale = used;
-            REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-
-            // "C" -> comma locale: strtod stops at the '.', so the conversion is repeated
-            {
-                locale_switching_token token("1.5", comma_locale.c_str());
-                double value = 0;
-                nlohmann::detail::convert_float_locale_aware(token, 1, value);
-                if (token.switched)
-                {
-                    CHECK(value == 1.5);
-                    CHECK(token.text == "1.5");
-                }
-            }
-
-            // the same for the other floating-point types
-            REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-            {
-                locale_switching_token token("2.25", comma_locale.c_str());
-                float value = 0;
-                nlohmann::detail::convert_float_locale_aware(token, 1, value);
-                if (token.switched)
-                {
-                    CHECK(value == 2.25f);
-                }
-            }
-            REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-            {
-                locale_switching_token token("2.25", comma_locale.c_str());
-                long double value = 0;
-                nlohmann::detail::convert_float_locale_aware(token, 1, value);
-                if (token.switched)
-                {
-                    CHECK(value == 2.25L);
-                }
-            }
-
-            // comma locale -> multi-byte decimal point
-            const char* multi_byte = nullptr;
-            if (use_decimal_point_locale(multi_byte_names, 2, 8, multi_byte))
-            {
-                REQUIRE(std::setlocale(LC_NUMERIC, comma_locale.c_str()) != nullptr);
-                locale_switching_token token("1.5", multi_byte);
-                double value = 0;
-                nlohmann::detail::convert_float_locale_aware(token, 1, value);
-                if (token.switched)
-                {
-                    CHECK(value == 1.5);
-                    CHECK(token.text == "1.5");
-                }
-            }
-        }
-    }
-
-    CHECK(std::setlocale(LC_NUMERIC, "C") != nullptr);
-}

tests/src/unit-msgpack-cpp17.cpp

@@ -18,7 +18,6 @@ using nlohmann::json;
 
 #ifdef JSON_HAS_CPP_17
 #include <cstddef>
-#include <string>
 #include <vector>
 
 // Test suite for verifying MessagePack handling with std::byte input
@@ -97,33 +96,4 @@ TEST_CASE("MessagePack with std::byte")
         }
     }
 }
-
-// JSON text (not MessagePack) as std::byte input: the error position is
-// computed from the bytes consumed so far
-TEST_CASE("JSON text with std::byte")
-{
-    const auto to_bytes = [](const std::string & text)
-    {
-        std::vector<std::byte> bytes;
-        for (const char c : text)
-        {
-            bytes.push_back(static_cast<std::byte>(c));
-        }
-        return bytes;
-    };
-
-    SECTION("valid text")
-    {
-        const json j = json::parse(to_bytes("[1,\n2]"));
-        CHECK(j == json({1, 2}));
-        CHECK(json::accept(to_bytes("[1,\n2]")));
-    }
-
-    SECTION("invalid text")
-    {
-        CHECK_FALSE(json::accept(to_bytes("[1,\n2,")));
-        CHECK_THROWS_WITH_AS(json::parse(to_bytes("[1,\n2,")),
-                             "[json.exception.parse_error.101] parse error at line 2, column 3: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal", json::parse_error&);
-    }
-}
 #endif

tests/src/unit-msgpack.cpp

@@ -1648,30 +1648,6 @@ TEST_CASE("MessagePack")
             }
         }
     }
-
-    SECTION("SAX aborts")
-    {
-        SECTION("start_array(len)")
-        {
-            std::vector<uint8_t> const v = {0x93, 0x01, 0x02, 0x03};
-            SaxCountdown scp(0);
-            CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
-        }
-
-        SECTION("start_object(len)")
-        {
-            std::vector<uint8_t> const v = {0x81, 0xa3, 0x66, 0x6F, 0x6F, 0xc2};
-            SaxCountdown scp(0);
-            CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
-        }
-
-        SECTION("key()")
-        {
-            std::vector<uint8_t> const v = {0x81, 0xa3, 0x66, 0x6F, 0x6F, 0xc2};
-            SaxCountdown scp(1);
-            CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
-        }
-    }
 }
 
 TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
@@ -1742,21 +1718,6 @@ TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
             CHECK(json::from_msgpack(packed) == j);
         }
     }
-
-    SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
-    {
-        // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
-        // a custom SAX consumer that does not touch a DOM array sees identical events
-        json j = json::array();
-        for (int i = 0; i < 100; ++i)
-        {
-            j.push_back(i);
-        }
-        const auto packed = json::to_msgpack(j);
-
-        SaxCountdown scp(1000000); // large enough to never trigger an abort
-        CHECK(json::sax_parse(packed, &scp, json::input_format_t::msgpack));
-    }
 }
 
 TEST_CASE("regression test - MessagePack ext type rejects a subtype that doesn't fit a single byte")
@@ -1795,15 +1756,6 @@ TEST_CASE("MessagePack nesting does not consume the call stack")
         CHECK(json::from_msgpack(input, true, false).is_discarded());
     }
 
-    SECTION("a well-formed deep value is read through the SAX interface")
-    {
-        std::vector<uint8_t> input(300000, 0x91);
-        input.push_back(0x01); // innermost value
-
-        SaxCountdown accept_all(600001);
-        CHECK(json::sax_parse(input, &accept_all, json::input_format_t::msgpack));
-    }
-
     SECTION("a well-formed deep value is read into a value")
     {
         const std::size_t depth = 10000;
@@ -1851,31 +1803,6 @@ TEST_CASE("MessagePack input that cannot be read is discarded by every overload"
 #endif
 }
 
-TEST_CASE("MessagePack SAX parsing stops at every event")
-{
-    // Containers are opened and closed by the loop that reads them; a SAX
-    // handler that rejects any event - including the end of a nested
-    // container - must stop the parse right there.
-    const auto count_events = [](const std::vector<std::uint8_t>& input)
-    {
-        int events = 0;
-        while (true)
-        {
-            SaxCountdown scp(events);
-            if (json::sax_parse(input, &scp, json::input_format_t::msgpack))
-            {
-                return events;
-            }
-            ++events;
-            REQUIRE(events < 1000);
-        }
-    };
-
-    // 20 events: every container kind closes inside another one
-    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
-    CHECK(count_events(json::to_msgpack(j)) == 20);
-}
-
 TEST_CASE("single MessagePack roundtrip")
 {
     SECTION("sample.json")

tests/src/unit-ordered_json.cpp

@@ -16,7 +16,6 @@ using nlohmann::ordered_json;
 #include <cstddef>
 #include <cstdint>
 #include <string>
-#include <vector>
 
 TEST_CASE("ordered_json")
 {
@@ -516,87 +515,3 @@ TEST_CASE("parsing random trees of arrays and objects")
         CHECK(json::parse(text).dump() == expected.dump());
     }
 }
-
-TEST_CASE("object_key_index")
-{
-    // the hash table of the DOM parser finds the position of a key in an
-    // ordered_json object; the parser creates it for exactly 64 elements, but
-    // it is correct for any number of elements it is given
-    using nlohmann::detail::object_key_index;
-    const std::size_t not_found = object_key_index::npos;
-
-    for (const std::size_t initial :
-            {
-                std::size_t{0}, std::size_t{10}, std::size_t{64}, std::size_t{65}, std::size_t{300}
-            })
-    {
-        CAPTURE(initial)
-
-        // the hashes are not distinct on purpose: elements with the same
-        // hash are told apart by the caller
-        const auto hash_of = [](std::size_t position)
-        {
-            return (position % 50) * 0x9E3779B97F4A7C15ull;
-        };
-
-        std::vector<std::size_t> hashes;
-        for (std::size_t i = 0; i < initial; ++i)
-        {
-            hashes.push_back(hash_of(i));
-        }
-        object_key_index index(std::move(hashes));
-
-        // the elements that are there
-        for (std::size_t i = 0; i < initial; ++i)
-        {
-            CHECK(index.find(hash_of(i), [i](std::size_t position)
-            {
-                return position == i;
-            }) == i);
-        }
-        CHECK(index.find(hash_of(1), [](std::size_t /*position*/)
-        {
-            return false;
-        }) == not_found);
-
-        // elements that are added later, until the table grows
-        for (std::size_t i = initial; i < initial + 600; ++i)
-        {
-            index.add(hash_of(i));
-            CHECK(index.find(hash_of(i), [i](std::size_t position)
-            {
-                return position == i;
-            }) == i);
-        }
-        CHECK(index.find(hash_of(initial), [initial](std::size_t position)
-        {
-            return position == initial;
-        }) == initial);
-    }
-}
-
-TEST_CASE("JSON pointers on ordered_json")
-{
-    using pointer = ordered_json::json_pointer;
-
-    SECTION("operator[] inserts a missing key at the end")
-    {
-        ordered_json j = {{"z", 1}, {"x", {{"y", 2}}}};
-
-        j[pointer("/a")] = 3;
-        j[pointer("/x/b")] = 4;
-
-        CHECK(j == ordered_json({{"z", 1}, {"x", {{"y", 2}, {"b", 4}}}, {"a", 3}}));
-        CHECK(j.dump() == R"({"z":1,"x":{"y":2,"b":4},"a":3})");
-    }
-
-    SECTION("unflatten of a flattened object whose keys are not sorted")
-    {
-        // the prefixes /a and /c denote arrays; a key of /a follows one of /c
-        const ordered_json flat = {{"/a/0/p", 1}, {"/c/0/x", 2}, {"/a/0/q", 3}, {"/a/1/p", 4}};
-        const ordered_json expected = {{"a", {{{"p", 1}, {"q", 3}}, {{"p", 4}}}}, {"c", {{{"x", 2}}}}};
-
-        CHECK(flat.unflatten() == expected);
-        CHECK(expected.flatten().unflatten() == expected);
-    }
-}

tests/src/unit-regression1.cpp

@@ -23,13 +23,11 @@ using nlohmann::json;
     using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
 #endif
 
-#include <array>
 #include <fstream>
 #include <sstream>
 #include <list>
 #include <limits>
 #include <cstdio>
-#include <utility>
 #include "make_test_data_available.hpp"
 #include "test_utils.hpp"
 
@@ -1521,75 +1519,6 @@ TEST_CASE("regression tests 1")
         }
     }
 
-    SECTION("operator[](json_pointer) continues with the member that emplace() found")
-    {
-        // see the section above: the lookup does not find "k", but emplace()
-        // finds "x" and the pointer continues with the member of "x". Here
-        // the member is a container, so the pointer can go on below it. Only
-        // the outermost object may be a copy (with restarted timestamps): the
-        // value of "x" is moved in, so that its own lookups work.
-        const my_json orig = my_json::parse(R"({"x":null})");
-        const auto make = [&orig]()
-        {
-            my_json::object_t top = orig.get_ref<const my_json::object_t&>();
-            top.at("x") = my_json::parse(R"({"a":{"b":1},"n":null,"arr":[10,20],"objs":[{"m":5},{"m":6}]})");
-            return my_json(std::move(top));
-        };
-
-        SECTION("existing members")
-        {
-            // emplace() registers the key "k" in the object, so that every
-            // pointer needs a new object to reach the member of "x" again
-            const std::array<std::pair<const char*, const char*>, 4> pointers = {{{"/k/a/b", "1"}, {"/k/arr/1", "20"}, {"/k/n", "null"}, {"/k/objs/1/m", "6"}}};
-            for (const auto& pointer : pointers)
-            {
-                CAPTURE(pointer.first)
-                my_json j = make();
-                CHECK(j[my_json::json_pointer(pointer.first)].dump() == pointer.second);
-                CHECK(j.size() == 1);
-                CHECK(j["x"].size() == 4);
-            }
-        }
-
-        SECTION("a missing member of an object")
-        {
-            my_json j = make();
-#ifdef JSON_NO_THREAD_LOCAL
-            // the objects below the outermost one are not copied by their
-            // object_t here, but member by member, which keeps their
-            // timestamps correct: "c" is not mistaken for "b" and is inserted
-            CHECK(j[my_json::json_pointer("/k/a/c/d")].is_null());
-            CHECK(j["x"]["a"].dump() == R"({"b":1,"c":{"d":null}})");
-#else
-            // the timestamp of "c" is that of "b" again, so that emplace()
-            // finds the member "b", a number, which has no member "d"
-            CHECK_THROWS_AS(j[my_json::json_pointer("/k/a/c/d")], my_json::out_of_range&);
-            CHECK(j["x"]["a"].dump() == R"({"b":1})");
-#endif
-        }
-
-        SECTION("a null value is converted to an object")
-        {
-            my_json j = make();
-            j[my_json::json_pointer("/k/n/c")] = 3;
-            CHECK(j["x"]["n"].dump() == R"({"c":3})");
-        }
-
-        SECTION("the end of an array")
-        {
-            my_json j = make();
-            j[my_json::json_pointer("/k/arr/-")] = 30;
-            CHECK(j["x"]["arr"].dump() == "[10,20,30]");
-        }
-
-        SECTION("an index past the end of an array")
-        {
-            my_json j = make();
-            j[my_json::json_pointer("/k/arr/3")] = 40;
-            CHECK(j["x"]["arr"].dump() == "[10,20,null,40]");
-        }
-    }
-
     SECTION("issue #977 - Assigning between different json types")
     {
         foo_json lj = ns::foo{3};

tests/src/unit-regression2.cpp

@@ -441,10 +441,6 @@ TEST_CASE("regression tests 2")
 
         float_json j2 = {1000.0, 2000.0, 3000.0};
         CHECK(float_json::from_ubjson(float_json::to_ubjson(j2, true, true)) == j2);
-
-        // half-precision floats of both signs are converted to the float type
-        CHECK(float_json::from_cbor(std::vector<std::uint8_t> {0xF9, 0xC0, 0x00}) == -2.0f);
-        CHECK(float_json::from_cbor(std::vector<std::uint8_t> {0xF9, 0x3C, 0x00}) == 1.0f);
     }
 
     SECTION("issue #1045 - Using STL algorithms with JSON containers with expected results?")

tests/src/unit-regression3.cpp

@@ -22,14 +22,6 @@
 // scoped enum, so get<std::byte>() (needed below to get<std::vector<std::byte>>()
 // from a plain JSON array, not just from an already-binary value) relies on
 // enum serialization being enabled
-// capture whether JSON_DELETE_DEPRECATED_FUNCTIONS was enabled on the command
-// line *before* including json.hpp, since the library #undefs it once the header
-// has been fully processed (see include/nlohmann/detail/macro_unscope.hpp); the
-// tests of deprecated functions are skipped if these functions are deleted
-#if defined(JSON_DELETE_DEPRECATED_FUNCTIONS) && (JSON_DELETE_DEPRECATED_FUNCTIONS == 1)
-    #define JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-#endif
-
 #if defined(JSON_DISABLE_ENUM_SERIALIZATION) && (JSON_DISABLE_ENUM_SERIALIZATION == 1)
     #define SKIP_TESTS_FOR_ENUM_SERIALIZATION
 #endif
@@ -810,50 +802,6 @@ TEST_CASE("issue #5338 - truncated CBOR tagged binary subtype is rejected")
     }
 }
 
-TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
-{
-    const json expected = json::binary({1, 2, 3}, 42);
-    const auto cbor = json::to_cbor(expected);
-
-    nlohmann::detail::json_sax_acceptor<json> acceptor;
-    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
-    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
-                                true, false, false, json::cbor_tag_handler_t::error));
-
-    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::ignore));
-
-    json parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
-    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(parsed == expected);
-
-    json iterator_parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
-    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(iterator_parsed == expected);
-
-#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-    json span_parsed;
-    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
-    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
-                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(span_parsed == expected);
-#endif
-
-    const std::string text = "null";
-    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
-                          true, false, false, json::cbor_tag_handler_t::store));
-    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
-                          true, false, false, json::cbor_tag_handler_t::store));
-#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
-    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
-                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
-#endif
-}
-
 TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with an object")
 {
     json t = {{"k", 1}};

tests/src/unit-sax_parse.cpp

@@ -0,0 +1,781 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+/////////////////////////////////////////////////////////////////////
+// Tests that call basic_json::sax_parse have a file of their own: every
+// sax_parse call instantiates the parser and binary reader that recover from
+// errors (see #3989), and in unit-regression2.cpp, unit-regression3.cpp, and
+// unit-msgpack.cpp this made the objects too large for the MinGW linker to
+// relocate (see #5511).
+/////////////////////////////////////////////////////////////////////
+
+#include "doctest_compatibility.h"
+
+// capture whether JSON_DELETE_DEPRECATED_FUNCTIONS was enabled on the command
+// line *before* including json.hpp, since the library #undefs it once the header
+// has been fully processed (see include/nlohmann/detail/macro_unscope.hpp); the
+// tests of deprecated functions are skipped if these functions are deleted
+#if defined(JSON_DELETE_DEPRECATED_FUNCTIONS) && (JSON_DELETE_DEPRECATED_FUNCTIONS == 1)
+    #define JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+#endif
+
+#include <nlohmann/json.hpp>
+using json = nlohmann::json;
+
+#include <cmath>
+#include <cstddef>
+#include <cstdint>
+#include <initializer_list>
+#include <map>
+#include <string>
+#include <utility>
+#include <vector>
+
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
+
+// a narrow number_float_t, so that a double read from binary input can
+// overflow it
+using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
+
+DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
+DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
+
+namespace
+{
+/// builds a value from SAX events, asks the parser to recover from its first
+/// 100 errors, and checks that the events are balanced (see #3989)
+template<typename BasicJsonType>
+class BasicRecoveringParser
+{
+  public:
+    explicit BasicRecoveringParser(BasicJsonType& j)
+        : dom(j, false)
+    {}
+
+    bool null()
+    {
+        value();
+        return dom.null();
+    }
+
+    bool boolean(bool val)
+    {
+        value();
+        return dom.boolean(val);
+    }
+
+    bool number_integer(typename BasicJsonType::number_integer_t val)
+    {
+        value();
+        return dom.number_integer(val);
+    }
+
+    bool number_unsigned(typename BasicJsonType::number_unsigned_t val)
+    {
+        value();
+        return dom.number_unsigned(val);
+    }
+
+    bool number_float(typename BasicJsonType::number_float_t val, const std::string& s)
+    {
+        value();
+        return dom.number_float(val, s);
+    }
+
+    bool string(std::string& val)
+    {
+        value();
+        return dom.string(val);
+    }
+
+    bool binary(typename BasicJsonType::binary_t& val)
+    {
+        value();
+        return dom.binary(val);
+    }
+
+    bool start_object(std::size_t elements)
+    {
+        value();
+        stack.push_back('o');
+        return dom.start_object(elements);
+    }
+
+    bool key(std::string& val)
+    {
+        if (stack.empty() || stack.back() != 'o')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.back() = 'v';
+        return dom.key(val);
+    }
+
+    bool end_object()
+    {
+        if (stack.empty() || stack.back() != 'o')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.pop_back();
+        return dom.end_object();
+    }
+
+    bool start_array(std::size_t elements)
+    {
+        value();
+        stack.push_back('a');
+        return dom.start_array(elements);
+    }
+
+    bool end_array()
+    {
+        if (stack.empty() || stack.back() != 'a')
+        {
+            well_formed = false;
+            return false;
+        }
+        stack.pop_back();
+        return dom.end_array();
+    }
+
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& ex)
+    {
+        messages.emplace_back(ex.what());
+        // a limit, so that a reader that does not stop fails the test
+        // instead of making it hang
+        return ++errors < 100;
+    }
+
+    /// whether the events were balanced and every key was followed by a value
+    bool balanced() const
+    {
+        return well_formed && stack.empty();
+    }
+
+    /// builds the value
+    nlohmann::detail::json_sax_dom_parser<BasicJsonType> dom;
+    std::size_t errors = 0;
+    std::vector<std::string> messages {}; // NOLINT(readability-redundant-member-init)
+    std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
+    bool well_formed = true;
+
+  private:
+    void value()
+    {
+        if (!stack.empty())
+        {
+            if (stack.back() == 'v')
+            {
+                stack.back() = 'o';
+            }
+            else if (stack.back() == 'o')
+            {
+                well_formed = false;
+            }
+        }
+    }
+
+};
+
+using RecoveringParser = BasicRecoveringParser<json>;
+
+struct BinaryParseResult
+{
+    json value;
+    std::size_t errors;
+    std::vector<std::string> messages;
+    bool ok;
+    bool balanced;
+};
+
+BinaryParseResult parse_binary_recovering(const std::vector<std::uint8_t>& input, const json::input_format_t format)
+{
+    json j;
+    RecoveringParser sax(j);
+    const bool ok = json::sax_parse(input, &sax, format);
+    return {j, sax.errors, sax.messages, ok, sax.balanced()};
+}
+
+#if !defined(JSON_NOEXCEPTION)
+/// the message of the exception that reading @a input into a JSON value
+/// throws, or an empty string if reading succeeds
+std::string binary_error_message(const std::vector<std::uint8_t>& input, const json::input_format_t format)
+{
+    try
+    {
+        json _;
+        switch (format)
+        {
+            case json::input_format_t::cbor:
+                _ = json::from_cbor(input);
+                break;
+            case json::input_format_t::msgpack:
+                _ = json::from_msgpack(input);
+                break;
+            case json::input_format_t::ubjson:
+                _ = json::from_ubjson(input);
+                break;
+            case json::input_format_t::bjdata:
+                _ = json::from_bjdata(input);
+                break;
+            case json::input_format_t::bson:
+                _ = json::from_bson(input);
+                break;
+            case json::input_format_t::bon8:
+                _ = json::from_bon8(input);
+                break;
+            case json::input_format_t::json:
+            default:
+                break;
+        }
+    }
+    catch (const json::exception& e)
+    {
+        return e.what();
+    }
+    return "";
+}
+#endif
+
+/// a BSON element: its type, its name, and its value
+std::vector<std::uint8_t> bson_element(const std::uint8_t type, const std::string& name, const std::vector<std::uint8_t>& value)
+{
+    std::vector<std::uint8_t> result = {type};
+    result.insert(result.end(), name.begin(), name.end());
+    result.push_back(0x00);
+    result.insert(result.end(), value.begin(), value.end());
+    return result;
+}
+
+/// a BSON document of the given elements; @a size_offset is added to the
+/// size it declares
+std::vector<std::uint8_t> bson_document(const std::vector<std::vector<std::uint8_t>>& elements, const int size_offset = 0)
+{
+    std::vector<std::uint8_t> body;
+    for (const auto& element : elements)
+    {
+        body.insert(body.end(), element.begin(), element.end());
+    }
+    const auto size = static_cast<std::uint32_t>(static_cast<int>(body.size()) + 5 + size_offset);
+    std::vector<std::uint8_t> result = {static_cast<std::uint8_t>(size & 0xFFu), static_cast<std::uint8_t>((size >> 8u) & 0xFFu),
+                                        static_cast<std::uint8_t>((size >> 16u) & 0xFFu), static_cast<std::uint8_t>((size >> 24u) & 0xFFu)
+                                       };
+    result.insert(result.end(), body.begin(), body.end());
+    result.push_back(0x00);
+    return result;
+}
+
+/// a BSON int32 value
+std::vector<std::uint8_t> bson_int32(const std::int32_t value)
+{
+    const auto u = static_cast<std::uint32_t>(value);
+    return {static_cast<std::uint8_t>(u & 0xFFu), static_cast<std::uint8_t>((u >> 8u) & 0xFFu),
+            static_cast<std::uint8_t>((u >> 16u) & 0xFFu), static_cast<std::uint8_t>((u >> 24u) & 0xFFu)};
+}
+
+/// a BSON string value, whose length is @a length_offset off
+std::vector<std::uint8_t> bson_string(const std::string& value, const std::int32_t length_offset = 0)
+{
+    auto result = bson_int32(static_cast<std::int32_t>(value.size() + 1) + length_offset);
+    result.insert(result.end(), value.begin(), value.end());
+    result.push_back(0x00);
+    return result;
+}
+
+/// @a count bytes of value 0xAB
+std::vector<std::uint8_t> bytes(const std::size_t count)
+{
+    return std::vector<std::uint8_t>(count, 0xAB);
+}
+
+/// the bytes of @a parts, one after the other
+std::vector<std::uint8_t> concatenated(std::initializer_list<std::vector<std::uint8_t>> parts)
+{
+    std::vector<std::uint8_t> result;
+    for (const auto& part : parts)
+    {
+        result.insert(result.end(), part.begin(), part.end());
+    }
+    return result;
+}
+
+/// U+FFFD REPLACEMENT CHARACTER
+std::string replacement_character()
+{
+    return "\xEF\xBF\xBD";
+}
+}  // namespace
+
+TEST_CASE("regression test - #3989 SAX parse_error() returning true")
+{
+    SECTION("binary formats complete what was read before the input ends")
+    {
+        const json j = {{"a", {1, -2, {{"b", "c"}}, json::array()}}, {"d", {{"e", nullptr}, {"f", true}}}, {"g", 1.5}, {"h", json::binary({1, 2, 3})}};
+
+        const std::vector<std::pair<json::input_format_t, std::vector<std::uint8_t>>> encodings =
+        {
+            {json::input_format_t::cbor, json::to_cbor(j)},
+            {json::input_format_t::msgpack, json::to_msgpack(j)},
+            {json::input_format_t::ubjson, json::to_ubjson(j)},
+            {json::input_format_t::ubjson, json::to_ubjson(j, true, true)},
+            {json::input_format_t::bjdata, json::to_bjdata(j)},
+            {json::input_format_t::bjdata, json::to_bjdata(j, true, true)},
+            {json::input_format_t::bson, json::to_bson(j)},
+            {json::input_format_t::bon8, json::to_bon8(j)},
+        };
+
+        for (const auto& encoding : encodings)
+        {
+            const auto format = encoding.first;
+            const auto& bytes = encoding.second;
+            CAPTURE(format)
+
+            // every prefix is truncated input
+            for (std::size_t length = 0; length < bytes.size(); ++length)
+            {
+                CAPTURE(length)
+                const auto result = parse_binary_recovering(std::vector<std::uint8_t>(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length)), format);
+                CHECK(!result.ok);
+                CHECK(result.errors == 1);
+                CHECK(result.balanced);
+            }
+
+            // the complete input is read as usual (binary values do not
+            // round-trip through every format, so compare with a plain parse)
+            json expected;
+            nlohmann::detail::json_sax_dom_parser<json> dom(expected);
+            CHECK(json::sax_parse(bytes, &dom, format));
+            const auto complete = parse_binary_recovering(bytes, format);
+            CHECK(complete.ok);
+            CHECK(complete.errors == 0);
+            CHECK(complete.value == expected);
+
+            // a byte after the value
+            auto trailing_bytes = bytes;
+            trailing_bytes.push_back(0x01);
+            const auto trailing = parse_binary_recovering(trailing_bytes, format);
+            CHECK(!trailing.ok);
+            CHECK(trailing.errors == 1);
+            CHECK(trailing.value == expected);
+        }
+    }
+
+    SECTION("containers without an end")
+    {
+        // these made the readers loop, or read on, after the error
+        const auto cbor_array = parse_binary_recovering({0x9F}, json::input_format_t::cbor);
+        CHECK(cbor_array.errors == 1);
+        CHECK(cbor_array.value == json::array());
+
+        const auto cbor_map = parse_binary_recovering({0xBF, 0x61, 'a'}, json::input_format_t::cbor);
+        CHECK(cbor_map.errors == 1);
+        CHECK(cbor_map.value == json({{"a", nullptr}}));
+
+        const auto msgpack_array = parse_binary_recovering({0xDD, 0xFF, 0xFF, 0xFF, 0xFF}, json::input_format_t::msgpack);
+        CHECK(msgpack_array.errors == 1);
+        CHECK(msgpack_array.value == json::array());
+
+        const auto msgpack_map = parse_binary_recovering({0x81, 0xA1, 'a', 0x92, 0x01}, json::input_format_t::msgpack);
+        CHECK(msgpack_map.errors == 1);
+        CHECK(msgpack_map.value == json({{"a", {1}}}));
+    }
+
+    SECTION("BJData ndarray")
+    {
+        // a 2x3 int8 array with two of its six elements; the annotated array
+        // format opens an object and two arrays of its own
+        const auto result = parse_binary_recovering({'[', '$', 'i', '#', '[', '$', 'i', '#', 'i', 2, 2, 3, 1, 2}, json::input_format_t::bjdata);
+        CHECK(result.errors == 1);
+        CHECK(result.balanced);
+        CHECK(result.value == json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2}}}));
+    }
+
+    SECTION("binary formats repair items whose end is known")
+    {
+        struct Repair
+        {
+            json::input_format_t format;
+            std::vector<std::uint8_t> input;
+            json expected;
+            std::size_t errors;
+        };
+
+        const std::vector<Repair> repairs =
+        {
+            // CBOR: tags are ignored (here tag 1 and the self-describe tag 55799)
+            {json::input_format_t::cbor, {0x82, 0xC1, 0x05, 0xD9, 0xD9, 0xF7, 0x06}, {5, 6}, 2},
+            // CBOR: undefined and other simple values become null
+            {json::input_format_t::cbor, {0x84, 0xF7, 0xE0, 0xF8, 0x20, 0x01}, {nullptr, nullptr, nullptr, 1}, 3},
+            // CBOR: members whose key is not a string are skipped, whatever their key and value
+            {json::input_format_t::cbor, {0xA4, 0x01, 0x02, 0x82, 0x01, 0x02, 0xA1, 0x61, 'x', 0x9F, 0xFF, 0xC1, 0x01, 0x5F, 0x41, 0x00, 0xFF, 0x61, 'a', 0x03}, {{"a", 3}}, 3},
+            {json::input_format_t::cbor, {0xBF, 0xF5, 0xBF, 0x61, 'x', 0x7F, 0x61, 'y', 0xFF, 0xFF, 0x61, 'a', 0x03, 0xFF}, {{"a", 3}}, 1},
+            // MessagePack: members whose key is not a string are skipped
+            {json::input_format_t::msgpack, {0x84, 0x01, 0x02, 0x81, 0xA1, 'x', 0x01, 0x92, 0x01, 0x02, 0xD4, 0x01, 0x02, 0xC0, 0xA1, 'a', 0x04}, {{"a", 4}}, 3},
+            // UBJSON: a char that is not ASCII becomes U+FFFD
+            {json::input_format_t::ubjson, {'[', 'C', 0x80, 'C', 'A', ']'}, {replacement_character(), "A"}, 1},
+            // UBJSON: the longest beginning of a high-precision number is kept
+            {json::input_format_t::ubjson, {'[', 'H', 'i', 5, '1', '2', 'a', 'b', 'c', 'H', 'i', 2, '1', '.', 'H', 'i', 3, 'a', 'b', 'c', 'H', 'i', 3, '4', '.', '5', ']'}, {12, 1, nullptr, 4.5}, 3},
+            // BJData, too
+            {json::input_format_t::bjdata, {'[', 'C', 0xFF, 'H', 'i', 2, '-', '1', 'H', 'i', 2, '-', 'x', ']'}, {replacement_character(), -1, nullptr}, 2},
+            // a NUL ends a high-precision number, as it ends JSON text
+            {json::input_format_t::ubjson, {'[', 'H', 'i', 4, '1', '2', 0, '9', 'H', 'i', 2, 0, '1', 'i', 3, ']'}, {12, nullptr, 3}, 2},
+            // BON8: members whose key is not a string are skipped
+            {json::input_format_t::bon8, {0x89, 0x91, 0x92, 0xC9, 0x40, 0x82, 0x91, 0x92, 0x61, 0x93}, {{"a", 3}}, 2},
+            {json::input_format_t::bon8, {0x8B, 0x91, 0x85, 0x91, 0xFE, 0xFA, 0x8B, 'x', 0x91, 0xFE, 0x61, 0x93, 0xFE}, {{"a", 3}}, 2},
+            // BSON: elements of types the library does not read become null
+            {
+                json::input_format_t::bson, bson_document(
+                {
+                    bson_element(0x07, "_id", bytes(12)),                         // ObjectId
+                    bson_element(0x09, "date", bytes(8)),                         // UTC datetime
+                    bson_element(0x13, "decimal", bytes(16)),                     // 128-bit decimal
+                    bson_element(0x0B, "regex", {'a', '+', 0, 'i', 0}),           // regular expression
+                    bson_element(0x0D, "code", bson_string("f()")),               // JavaScript code
+                    bson_element(0x0E, "symbol", bson_string("s")),               // symbol
+                    bson_element(0x0C, "pointer", concatenated({bson_string("c"), bytes(12)})), // DBPointer
+                    bson_element(0x0F, "scope", concatenated({bson_int32(15), bson_string("g"), bson_document({})})), // code with scope
+                    bson_element(0x06, "undefined", {}),                          // undefined
+                    bson_element(0xFF, "min", {}),                                // min key
+                    bson_element(0x7F, "max", {}),                                // max key
+                    bson_element(0x10, "z", bson_int32(7)),
+                }),
+                {{"_id", nullptr}, {"date", nullptr}, {"decimal", nullptr}, {"regex", nullptr}, {"code", nullptr}, {"symbol", nullptr}, {"pointer", nullptr}, {"scope", nullptr}, {"undefined", nullptr}, {"min", nullptr}, {"max", nullptr}, {"z", 7}},
+                11
+            },
+            // BSON: an element of an unknown type becomes null, and the rest of its document is skipped
+            {
+                json::input_format_t::bson, bson_document(
+                {
+                    bson_element(0x03, "inner", bson_document({bson_element(0x10, "a", bson_int32(1)), bson_element(0x42, "x", bytes(3)), bson_element(0x10, "b", bson_int32(2))})),
+                    bson_element(0x04, "array", bson_document({bson_element(0x10, "0", bson_int32(1)), bson_element(0x42, "1", bytes(3))})),
+                    bson_element(0x10, "after", bson_int32(3)),
+                }),
+                {{"inner", {{"a", 1}, {"x", nullptr}}}, {"array", {1, nullptr}}, {"after", 3}},
+                2
+            },
+            // BSON: so does a string or byte array whose length cannot be right
+            {
+                json::input_format_t::bson, bson_document(
+                {
+                    bson_element(0x03, "inner", bson_document({bson_element(0x02, "s", bson_string("abc", -10)), bson_element(0x10, "b", bson_int32(2))})),
+                    bson_element(0x03, "bin", bson_document({bson_element(0x05, "b", concatenated({bson_int32(-1), bytes(1)})), bson_element(0x10, "b", bson_int32(2))})),
+                    bson_element(0x10, "after", bson_int32(3)),
+                }),
+                {{"inner", {{"s", nullptr}}}, {"bin", {{"b", nullptr}}}, {"after", 3}},
+                2
+            },
+            // BSON: a string without its terminator, and a document whose size does not match, are kept
+            {
+                json::input_format_t::bson, bson_document(
+                {
+                    bson_element(0x02, "s", {2, 0, 0, 0, 'a', 'X'}),
+                    bson_element(0x03, "inner", bson_document({bson_element(0x10, "a", bson_int32(1))}, 1)),
+                }),
+                {{"s", "a"}, {"inner", {{"a", 1}}}},
+                2
+            },
+            // BSON: so is a document whose size is too small for its content,
+            // which is read up to its terminator
+            {
+                json::input_format_t::bson, bson_document(
+                {
+                    bson_element(0x03, "inner", bson_document({bson_element(0x10, "a", bson_int32(1)), bson_element(0x10, "b", bson_int32(2))}, -7)),
+                    bson_element(0x10, "after", bson_int32(3)),
+                }),
+                {{"inner", {{"a", 1}, {"b", 2}}}, {"after", 3}},
+                1
+            },
+        };
+
+        for (const auto& repair : repairs)
+        {
+            CAPTURE(repair.format)
+            CAPTURE(repair.input)
+            const auto result = parse_binary_recovering(repair.input, repair.format);
+            CHECK(!result.ok);
+            CHECK(result.balanced);
+            CHECK(result.errors == repair.errors);
+            CHECK(result.value == repair.expected);
+            REQUIRE(!result.messages.empty());
+#if !defined(JSON_NOEXCEPTION)
+            // the first error is the one reported without recovering; under
+            // JSON_NOEXCEPTION, reading without recovering aborts instead of
+            // throwing, so there is no message to compare with
+            CHECK(result.messages.front() == binary_error_message(repair.input, repair.format));
+#endif
+        }
+    }
+
+    SECTION("binary formats repair numbers that are out of range")
+    {
+        // CBOR: a double too large for a float number_float_t
+        float_json cbor;
+        BasicRecoveringParser<float_json> sax(cbor);
+        const std::vector<std::uint8_t> cbor_input = {0x82, 0xFB, 0x7E, 0x37, 0xE4, 0x3C, 0x88, 0x00, 0x75, 0x9C, 0x01}; // [1e300, 1]
+        CHECK(!float_json::sax_parse(cbor_input, &sax, float_json::input_format_t::cbor));
+        CHECK(sax.errors == 1);
+        CHECK(sax.messages.front() == "[json.exception.out_of_range.406] syntax error while parsing CBOR value: number overflow");
+        REQUIRE(cbor.size() == 2);
+        CHECK(std::isinf(cbor[0].get<float>()));
+        CHECK(cbor[1] == 1);
+
+        // UBJSON: a high-precision number too large for number_float_t
+        const auto ubjson = parse_binary_recovering({'H', 'i', 5, '1', 'e', '9', '9', '9'}, json::input_format_t::ubjson);
+        CHECK(ubjson.errors == 1);
+        CHECK(ubjson.value.is_number_float());
+        CHECK(std::isinf(ubjson.value.get<double>()));
+    }
+
+    SECTION("binary formats stop where the end of an item is not known")
+    {
+        // a byte that begins no item
+        const auto cbor = parse_binary_recovering({0x82, 0x01, 0x1C, 0x02}, json::input_format_t::cbor);
+        CHECK(cbor.errors == 1);
+        CHECK(cbor.value == json({1}));
+
+        // a key that is no item: the unused MessagePack byte, a CBOR break
+        // in a map of known size, and the end of a BON8 container
+        const auto msgpack = parse_binary_recovering({0x82, 0xA1, 'a', 0x01, 0xC1, 0x02}, json::input_format_t::msgpack);
+        CHECK(msgpack.errors == 1);
+        CHECK(msgpack.value == json({{"a", 1}}));
+        const auto cbor_break = parse_binary_recovering({0xA2, 0x61, 'a', 0x01, 0xFF, 0x02}, json::input_format_t::cbor);
+        CHECK(cbor_break.errors == 1);
+        CHECK(cbor_break.value == json({{"a", 1}}));
+        const auto bon8 = parse_binary_recovering({0x88, 0x61, 0x91, 0xFE}, json::input_format_t::bon8);
+        CHECK(bon8.errors == 1);
+        CHECK(bon8.value == json({{"a", 1}}));
+
+        // an indefinite-length string inside an indefinite-length string
+        const auto nested = parse_binary_recovering({0x82, 0x01, 0x7F, 0x7F, 0x61, 'a', 0xFF, 0xFF}, json::input_format_t::cbor);
+        CHECK(nested.errors == 1);
+        CHECK(nested.value == json({1}));
+
+        // a BJData ndarray whose element type is not valid: the type is
+        // checked before the object that would hold the ndarray is begun
+        const auto ndarray = parse_binary_recovering({'[', '$', 0x01, '#', '[', '$', 'i', '#', 'i', 2, 2, 3}, json::input_format_t::bjdata);
+        CHECK(ndarray.errors == 1);
+        CHECK(ndarray.balanced);
+        CHECK(ndarray.value == nullptr);
+
+        // a skipped member that the input ends in
+        const auto truncated = parse_binary_recovering({0xA2, 0x01, 0x82, 0x01}, json::input_format_t::cbor);
+        CHECK(truncated.errors == 2);
+        CHECK(truncated.balanced);
+        CHECK(truncated.value == json::object());
+
+        // a BSON element of an unknown type in a document whose size cannot be
+        // right: the size is reported when it is read, and the element ends
+        // the document, as its end is not known
+        const auto bson = parse_binary_recovering(bson_document({bson_element(0x10, "a", bson_int32(1)), bson_element(0x42, "x", bytes(3))}, -10), json::input_format_t::bson);
+        CHECK(bson.errors == 2);
+        CHECK(bson.value == json({{"a", 1}, {"x", nullptr}}));
+    }
+
+    SECTION("changed bytes in binary input")
+    {
+        const json j = {{"a", {1, -2, {{"b", "c"}}, json::array()}}, {"d", {{"e", nullptr}, {"f", true}}}, {"g", 1.5}, {"h", json::binary({1, 2, 3})}, {"i", "\xC3\xA4"}};
+
+        const std::vector<std::pair<json::input_format_t, std::vector<std::uint8_t>>> encodings =
+        {
+            {json::input_format_t::cbor, json::to_cbor(j)},
+            {json::input_format_t::msgpack, json::to_msgpack(j)},
+            {json::input_format_t::ubjson, json::to_ubjson(j)},
+            {json::input_format_t::ubjson, json::to_ubjson(j, true, true)},
+            {json::input_format_t::bjdata, json::to_bjdata(j)},
+            {json::input_format_t::bjdata, json::to_bjdata(j, true, true)},
+            {json::input_format_t::bson, json::to_bson(j)},
+            {json::input_format_t::bon8, json::to_bon8(j)},
+        };
+        const std::vector<std::uint8_t> replacements = {0x00, 0x01, 0x7F, 0x80, 0xC1, 0xD9, 0xE0, 0xF7, 0xFE, 0xFF};
+
+        for (const auto& encoding : encodings)
+        {
+            const auto format = encoding.first;
+            const auto& original = encoding.second;
+            CAPTURE(format)
+
+            std::vector<std::vector<std::uint8_t>> inputs;
+            for (std::size_t position = 0; position < original.size(); ++position)
+            {
+                for (const auto replacement : replacements)
+                {
+                    auto changed = original;
+                    changed[position] = replacement;
+                    inputs.push_back(changed);
+                }
+                auto removed = original;
+                removed.erase(removed.begin() + static_cast<std::ptrdiff_t>(position));
+                inputs.push_back(removed);
+            }
+
+            for (const auto& input : inputs)
+            {
+                CAPTURE(input)
+                const auto result = parse_binary_recovering(input, format);
+                CHECK(result.balanced);
+                CHECK(result.errors <= input.size() + 1);
+#if !defined(JSON_NOEXCEPTION)
+                // an error is reported exactly if reading into a JSON value
+                // fails, and the first one is the same (under JSON_NOEXCEPTION,
+                // that reading aborts instead of throwing)
+                const auto message = binary_error_message(input, format);
+                CHECK(result.ok == message.empty());
+                if (!result.ok && result.errors < 100)
+                {
+                    CHECK(result.messages.front() == message);
+                }
+#endif
+            }
+        }
+    }
+
+    SECTION("JSON text")
+    {
+        // the parser stopped, but reported success
+        json j;
+        RecoveringParser sax(j);
+        CHECK(!json::sax_parse("[1,2,3,]", &sax));
+        CHECK(sax.errors == 1);
+        CHECK(j == json({1, 2, 3}));
+    }
+
+    SECTION("the SAX parsers of the library stop")
+    {
+        json _;
+        CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9F}, true, false).is_discarded());
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t> {0x9F}), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
+        CHECK(json::parse("[1,2,3,]", nullptr, false).is_discarded());
+        CHECK(!json::accept("[1,2,3,]"));
+    }
+}
+
+
+TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
+{
+    const json expected = json::binary({1, 2, 3}, 42);
+    const auto cbor = json::to_cbor(expected);
+
+    nlohmann::detail::json_sax_acceptor<json> acceptor;
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                                true, false, false, json::cbor_tag_handler_t::error));
+
+    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::ignore));
+
+    json parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
+    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(parsed == expected);
+
+    json iterator_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
+    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(iterator_parsed == expected);
+
+#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+    json span_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
+                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(span_parsed == expected);
+#endif
+
+    const std::string text = "null";
+    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
+                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
+#endif
+}
+
+
+TEST_CASE("MessagePack SAX aborts")
+{
+    SECTION("start_array(len)")
+    {
+        std::vector<uint8_t> const v = {0x93, 0x01, 0x02, 0x03};
+        SaxCountdown scp(0);
+        CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
+    }
+
+    SECTION("start_object(len)")
+    {
+        std::vector<uint8_t> const v = {0x81, 0xa3, 0x66, 0x6F, 0x6F, 0xc2};
+        SaxCountdown scp(0);
+        CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
+    }
+
+    SECTION("key()")
+    {
+        std::vector<uint8_t> const v = {0x81, 0xa3, 0x66, 0x6F, 0x6F, 0xc2};
+        SaxCountdown scp(1);
+        CHECK(!json::sax_parse(v, &scp, json::input_format_t::msgpack));
+    }
+}
+
+TEST_CASE("issue #5405 - a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
+{
+    // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
+    // a custom SAX consumer that does not touch a DOM array sees identical events
+    json j = json::array();
+    for (int i = 0; i < 100; ++i)
+    {
+        j.push_back(i);
+    }
+    const auto packed = json::to_msgpack(j);
+
+    SaxCountdown scp(1000000); // large enough to never trigger an abort
+    CHECK(json::sax_parse(packed, &scp, json::input_format_t::msgpack));
+}
+
+TEST_CASE("MessagePack nesting does not consume the call stack - SAX interface")
+{
+    // see the test case of the same name in unit-msgpack.cpp (#5104)
+    std::vector<uint8_t> input(300000, 0x91);
+    input.push_back(0x01); // innermost value
+
+    SaxCountdown accept_all(600001);
+    CHECK(json::sax_parse(input, &accept_all, json::input_format_t::msgpack));
+}
+
+TEST_CASE("MessagePack SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::msgpack))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_msgpack(j)) == 20);
+}
+
+DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-stream-bulk-scan.cpp

@@ -19,13 +19,11 @@
 using nlohmann::json;
 
 #include <algorithm>
-#include <array>
 #include <cstddef>
 #include <cstdint>
 #include <cstdio>
 #include <fstream>
 #include <istream>
-#include <limits>
 #include <random>
 #include <sstream>
 #include <streambuf>
@@ -95,33 +93,6 @@ class chunked_streambuf : public std::streambuf
     std::size_t m_unbuffered;
 };
 
-#if TEST_STREAM_BULK_SCAN
-// A streambuf that claims a get area of several gigabytes, of which only the
-// first bytes exist. It is only used to move the read position of the adapter,
-// never to read beyond them, so that skipping more than gbump() can bump at
-// once can be tested without allocating that much.
-class oversized_get_area_streambuf : public std::streambuf
-{
-  public:
-    explicit oversized_get_area_streambuf(std::size_t claimed_size)
-    {
-        // NOLINTNEXTLINE(cppcoreguidelines-pro-bounds-pointer-arithmetic)
-        setg(m_data.data(), m_data.data(), m_data.data() + claimed_size);
-    }
-
-    // Give the get area back its real size, so that the adapter may read the
-    // character at the read position when it is destroyed (with
-    // JSON_PRECISE_STREAM_POSITION, it consumes the last character returned).
-    void restore_get_area()
-    {
-        setg(m_data.data(), m_data.data(), m_data.data() + m_data.size());
-    }
-
-  private:
-    std::array<char, 8> m_data{{'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'}};
-};
-#endif
-
 // how a test reads from the stream
 enum class read_mode
 {
@@ -462,35 +433,6 @@ TEST_CASE("parsing from a std::istream scans the get area in bulk")
         ia.copy_token(token, false);
         CHECK(token.empty());
     }
-
-    SECTION("skipping more characters than gbump() takes at once")
-    {
-        // gbump() takes an int, but a get area can be larger
-        const std::size_t claimed = sizeof(std::size_t) < 8 ? 0 : std::size_t{3} << 30u;
-        oversized_get_area_streambuf buf(claimed);
-        if (claimed == 0 || static_cast<std::size_t>(buf.in_avail()) != claimed)
-        {
-            // a 32-bit size_t, or a standard library whose streambuf stores
-            // the size of the get area in an int (MSVC)
-            MESSAGE("a get area larger than an int is not supported");
-        }
-        else
-        {
-            std::istream is(&buf);
-            nlohmann::detail::input_stream_adapter ia(is);
-            CHECK(ia.get_character() == 'a');
-            CHECK(ia.bulk_remaining() == claimed - 1);
-
-            const std::size_t skipped = static_cast<std::size_t>((std::numeric_limits<int>::max)()) + 10;
-            ia.bulk_skip(skipped);
-            CHECK(ia.bulk_remaining() == claimed - 1 - skipped);
-
-            ia.bulk_skip(ia.bulk_remaining());
-            CHECK(ia.bulk_remaining() == 0);
-
-            buf.restore_get_area();
-        }
-    }
 #endif
 
     SECTION("SAX parsing from a stream")

tests/src/unit-to_chars.cpp

@@ -928,49 +928,3 @@ TEST_CASE("short decimals")
         }
     }
 }
-
-TEST_CASE("decimals of up to 17 digits")
-{
-    // write_decimal() lays out digits * 10^exp as format_buffer() does; to_chars()
-    // calls it for the doubles whose digits write_shortest() does not convert at
-    // once, and the digits may be as many as 17
-    const auto written = [](std::uint64_t digits, int exp) -> std::string
-    {
-        std::array<char, 64> buf{}; // (up to 41 bytes are written)
-        char* const end = nlohmann::detail::dtoa_impl::write_decimal(buf.data(), digits, exp);
-        return {buf.data(), end};
-    };
-
-    SECTION("fixed notation")
-    {
-        CHECK(written(1, 0) == "1.0");
-        CHECK(written(1234, -2) == "12.34");
-        CHECK(written(123, 2) == "12300.0");
-        CHECK(written(50000000000u, -1) == "5000000000.0");
-        CHECK(written(100000000u, -8) == "1.0");
-        CHECK(written(12345678u, -12) == "1.2345678e-05");
-        CHECK(written(1234, 11) == "123400000000000.0");
-        // the point moves left of the first digit
-        CHECK(written(5, -3) == "0.005");
-        CHECK(written(12345678901234567u, -20) == "0.00012345678901234567");
-    }
-
-    SECTION("exponent notation")
-    {
-        CHECK(written(5, -5) == "5e-05");
-        CHECK(written(1234, 12) == "1.234e+15");
-        CHECK(written(5, -324) == "5e-324");
-    }
-
-    SECTION("17 digits")
-    {
-        CHECK(written(12345678901234567u, -16) == "1.2345678901234567");
-        CHECK(written(12345678901234567u, -19) == "0.0012345678901234567");
-        CHECK(written(12345678901234567u, 5) == "1.2345678901234567e+21");
-        CHECK(written(99999999999999999u, -17) == "0.99999999999999999");
-        CHECK(written(10000000000000001u, -16) == "1.0000000000000001");
-        // trailing zeros are not written
-        CHECK(written(10000000000000000u, -17) == "0.1");
-        CHECK(written(12000000000000000u, -15) == "12.0");
-    }
-}

tests/src/unit-ubjson.cpp

@@ -1673,31 +1673,6 @@ TEST_CASE("UBJSON")
                     return true;
                 });
                 CHECK_THROWS_AS(scp2.start_array((std::numeric_limits<std::size_t>::max)() - 1), json::out_of_range&);
-
-                // without exceptions, the error is reported to the caller
-                json l;
-                nlohmann::detail::json_sax_dom_callback_parser<json, decltype(nlohmann::detail::input_adapter(v_ubjson))> scp3(l, [](int /*unused*/, json::parse_event_t /*unused*/, const json& /*unused*/) noexcept
-                {
-                    return true;
-                }, false);
-                CHECK_FALSE(scp3.start_array((std::numeric_limits<std::size_t>::max)() - 1));
-                CHECK(scp3.is_errored());
-            }
-
-            SECTION("array with a known size, read without exceptions")
-            {
-                std::vector<uint8_t> const v_ubjson = {'[', '#', 'i', 2, 'i', 1, 'i', 2};
-                json j;
-                nlohmann::detail::json_sax_dom_parser<json, decltype(nlohmann::detail::input_adapter(v_ubjson))> sax(j, false);
-                CHECK(json::sax_parse(v_ubjson, &sax, json::input_format_t::ubjson));
-                CHECK(j == json({1, 2}));
-
-                // the readers reject a size this large before they announce
-                // it, so it can only reach start_array() directly
-                json k;
-                nlohmann::detail::json_sax_dom_parser<json, decltype(nlohmann::detail::input_adapter(v_ubjson))> sax2(k, false);
-                CHECK_FALSE(sax2.start_array((std::numeric_limits<std::size_t>::max)() - 1));
-                CHECK(sax2.is_errored());
             }
         }
     }