Merge remote-tracking branch 'origin/develop' into claude/fix-issue-3989-db7e45

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

# Conflicts:
#	tests/src/unit-alt-string.cpp

BUILD.bazel

@@ -20,7 +20,6 @@ cc_library(
     hdrs = [
         "include/nlohmann/adl_serializer.hpp",
         "include/nlohmann/byte_container_with_subtype.hpp",
-        "include/nlohmann/detail/abi_config.hpp",
         "include/nlohmann/detail/abi_macros.hpp",
         "include/nlohmann/detail/bit_ops.hpp",
         "include/nlohmann/detail/conversions/from_json.hpp",
@@ -66,13 +65,6 @@ cc_library(
         "include/nlohmann/detail/string_escape.hpp",
         "include/nlohmann/detail/string_utils.hpp",
         "include/nlohmann/detail/value_t.hpp",
-        "include/nlohmann/detail/view/builder.hpp",
-        "include/nlohmann/detail/view/document_data.hpp",
-        "include/nlohmann/detail/view/macro_scope.hpp",
-        "include/nlohmann/detail/view/macro_unscope.hpp",
-        "include/nlohmann/detail/view/node.hpp",
-        "include/nlohmann/detail/view/scan.hpp",
-        "include/nlohmann/detail/view/string_ref.hpp",
         "include/nlohmann/json.hpp",
         "include/nlohmann/json_fwd.hpp",
         "include/nlohmann/json_literals.hpp",

README.md

@@ -496,7 +496,7 @@ 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:
 
@@ -504,7 +504,7 @@ 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
 
@@ -1395,7 +1395,7 @@ THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR I
 - The class contains a slightly modified version of the Grisu2 algorithm from Florian Loitsch which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above). Copyright © 2009 [Florian Loitsch](https://florian.loitsch.com/)
 - The class contains a copy of [Hedley](https://nemequ.github.io/hedley/) from Evan Nemerson which is licensed as [CC0-1.0](https://creativecommons.org/publicdomain/zero/1.0/).
 - The class contains parts of [Google Abseil](https://github.com/abseil/abseil-cpp) which is licensed under the [Apache 2.0 License](https://opensource.org/licenses/Apache-2.0).
-- The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors
+- The class contains an adapted version of the Eisel-Lemire algorithm and its table of powers of five from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors
 
 <img align="right" src="https://git.fsfe.org/reuse/reuse-ci/raw/branch/master/reuse-horizontal.png" alt="REUSE Software">
 

docs/mkdocs/docs/api/basic_json/number_float_t.md

@@ -23,10 +23,9 @@ type to use.
 ## Template parameters
 
 `NumberFloatType`
-:   the type to store floating-point numbers. The parser converts `#!cpp float`, `#!cpp double`, and a
-    `#!cpp long double` that is IEEE 754 binary64 itself and other `#!cpp long double` formats with
-    `#!cpp std::from_chars` or `#!cpp std::strtold`, and serialization falls back to `#!cpp std::snprintf`, so the
-    type must be `#!cpp float`, `#!cpp double`, or `#!cpp long double`. The
+:   the type to store floating-point numbers. Parsing and serialization are implemented in terms of
+    `#!cpp std::strtof`/`#!cpp std::strtod`/`#!cpp std::strtold` and `#!cpp std::snprintf`, so the type must be
+    `#!cpp float`, `#!cpp double`, or `#!cpp long double`. The
     [binary formats](../../features/binary_formats/index.md) additionally require `#!cpp float` or `#!cpp double`,
     because they have no encoding for `#!cpp long double`. See
     [Template Parameter Requirements](../../features/types/template_parameters.md#numberfloattype).

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

@@ -90,7 +90,9 @@ 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
 
@@ -138,6 +140,7 @@ A UTF-8 byte order mark is silently ignored.
 - Ignoring comments via `ignore_comments` added in version 3.9.0.
 - Added `ignore_trailing_commas` 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).
 
 ## Template parameters
 

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

@@ -21,7 +21,14 @@ 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
 
@@ -39,6 +46,22 @@ Whether parsing should proceed (**must return `#!cpp false`**).
     --8<-- "examples/sax_parse.output"
     ```
 
+??? example
+
+    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"
+    ```
+
 ## 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/api/operator_gtgt.md

@@ -18,10 +18,6 @@ Deserializes an input stream to a JSON value.
 
 the stream `i`
 
-## Exception safety
-
-Strong guarantee: if an exception is thrown, there are no changes in `j`.
-
 ## Exceptions
 
 - Throws [`parse_error.101`](../home/exceptions.md#jsonexceptionparse_error101) in case of an unexpected token, or if
@@ -129,5 +125,3 @@ being read.
   the stream; planned to become the default in version 4.0.0.
 - Fixed a null pointer dereference for an `std::istream` without a stream buffer (now throws `parse_error.101`), and a
   crash (`std::terminate`) when `i` has `eofbit` in its exception mask, in version 3.13.0.
-- Changed to the strong exception safety guarantee in version 3.13.0: `j` is no longer left with a partially parsed
-  value if parsing throws.

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 +1,121 @@
+# 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                                                                 | CBOR                                    | ignored                                                                 |
+| simple value other than `false`, `true`, and `null`, like undefined | CBOR                                    | `#!json null`                                                           |
+| negative integer below the range of `number_integer_t`              | CBOR                                    | the nearest floating-point number                                       |
+| string that is not valid UTF-8                                      | BJData, BSON, CBOR, MessagePack, UBJSON | each ill-formed sequence becomes U+FFFD                                 |
+| 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. Note that [`sax_parse`](../../api/basic_json/sax_parse.md) has no parameter for
+CBOR tags, so every tag is an error there; when recovering, tags are ignored like with
+[`cbor_tag_handler_t::ignore`](../../api/basic_json/cbor_tag_handler_t.md).
+
+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

@@ -65,7 +65,7 @@ You can influence a DOM parse without switching to the SAX interface by passing
 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
 
@@ -76,3 +76,4 @@ options.
 - [parser callbacks](parser_callbacks.md) - influence the parsing by a callback function
 - [SAX interface](sax_interface.md) - implement a custom SAX handler
 - [parsing and exceptions](parse_exceptions.md) - control error handling
+- [error recovery](error_recovery.md) - get as much as possible out of malformed input

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

@@ -64,7 +64,8 @@ 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
 

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

@@ -60,7 +60,8 @@ 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).
 
 To implement your own SAX handler, proceed as follows:
 
@@ -68,7 +69,7 @@ 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/docs/features/types/number_handling.md

@@ -71,11 +71,10 @@ otherwise, it uses unsigned integer storage.
 
     - Numbers with a decimal digit or scientific notation are always stored as `#!c double`.
     - The number types can be changed, see [Template number types](#template-number-types). 
-    - The library converts integers and floating-point numbers itself, independent of the locale. Floating-point
-      numbers are correctly rounded (to nearest, ties to even). Only a `#!c long double` that is not IEEE 754 binary64
-      (e.g., the 80-bit x87 format) is converted with `#!cpp std::from_chars` where available, or with
-      [`std::strtold`](https://en.cppreference.com/w/cpp/string/byte/strtof), which gets the decimal point of the
-      current locale, also one longer than one byte (e.g., in `fa_IR.UTF-8`).
+    - As of version 3.9.1, the conversion is realized by
+      [`std::strtoull`](https://en.cppreference.com/w/cpp/string/byte/strtoul),
+      [`std::strtoll`](https://en.cppreference.com/w/cpp/string/byte/strtol), and
+      [`std::strtod`](https://en.cppreference.com/w/cpp/string/byte/strtof), respectively.
 
 !!! example "Examples"
 
@@ -86,10 +85,10 @@ otherwise, it uses unsigned integer storage.
 ### Number limits
 
 - Any 64-bit signed or unsigned integer can be stored without loss of precision.
-- Numbers exceeding the limits of `#!c double` (i.e., numbers whose rounded value is not satisfying
+- Numbers exceeding the limits of `#!c double` (i.e., numbers that after conversion via
+[`std::strtod`](https://en.cppreference.com/w/cpp/string/byte/strtof) are not satisfying
 [`std::isfinite`](https://en.cppreference.com/w/cpp/numeric/math/isfinite) such as `#!c 1E400`) will throw exception
-[`json.exception.out_of_range.406`](../../home/exceptions.md#jsonexceptionout_of_range406) during parsing. Numbers too
-small for `#!c double` (such as `#!c 1E-400`) become zero, with the sign of the number.
+[`json.exception.out_of_range.406`](../../home/exceptions.md#jsonexceptionout_of_range406) during parsing.
 - Floating-point numbers are rounded to the next number representable as `double`. For instance
 `#!c 3.141592653589793238462643383279` is stored as [`0x400921fb54442d18`](https://float.exposed/0x400921fb54442d18).
 This is the same behavior as the code `#!c double x = 3.141592653589793238462643383279;`.

docs/mkdocs/docs/features/types/template_parameters.md

@@ -26,9 +26,8 @@ Requirements are split into two groups:
     diagnosed with dedicated error messages, and violating most of them results in a compiler error somewhere inside
     the library. Four violations are not caught at compile time at all:
 
-    - A [`StringType`](#stringtype) whose `data()` is not null-terminated compiles and silently misparses numbers
-      stored as a `#!cpp long double` that is not IEEE 754 binary64 (e.g., the 80-bit x87 format), because the lexer
-      hands the buffer to `#!cpp std::strtold`.
+    - A [`StringType`](#stringtype) whose `data()` is not null-terminated compiles and silently misparses numbers,
+      because the lexer hands the buffer to `#!cpp std::strtoull`/`#!cpp std::strtoll`/`#!cpp std::strtod`.
     - A stateful [`AllocatorType`](#allocatortype) compiles and silently ignores its state: allocation, deallocation,
       and [`get_allocator()`](../../api/basic_json/get_allocator.md) each use a different default-constructed instance.
     - The two [cross-specialization conversions](#cross-specialization-conversions) below. These abort on an assertion
@@ -390,7 +389,6 @@ using array_t = ArrayType<basic_json, AllocatorType<basic_json>>;
 | Functionality                                                                                                                     | Additional requirement                                                                                                                                                                       |
 |-----------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | [`diff`](../../api/basic_json/diff.md), [`items`](../../api/basic_json/items.md), [`std::hash`](../../api/basic_json/std_hash.md) | conversion of a `#!cpp std::size_t` to `StringType`: either assignability from the result of `#!cpp std::to_string`, or an ADL overload `#!cpp void int_to_string(StringType&, std::size_t)` |
-| [`operator/(std::size_t)`](../../api/json_pointer/operator_slash.md)                                                              | the same conversion of a `#!cpp std::size_t` to `StringType` as `diff`, `items`, and `std::hash` above                                                                                       |
 | [`std::hash<basic_json>`](../../api/basic_json/std_hash.md)                                                                       | additionally a specialization of `#!cpp std::hash<StringType>`                                                                                                                               |
 | [`to_bson`](../../api/basic_json/to_bson.md)                                                                                      | `find(value_type)` and `npos`                                                                                                                                                                |
 | [`parse`](../../api/basic_json/parse.md) from a `string_t`                                                                        | the input adapters must accept it; otherwise pass a character range                                                                                                                          |
@@ -536,10 +534,8 @@ therefore silently changes parse results rather than raising an error. See
 
 `NumberFloatType` must be one of `#!cpp float`, `#!cpp double`, or `#!cpp long double`:
 
-- The [parser](../parsing/index.md) converts number literals to `#!cpp float`, `#!cpp double`, and a
-  `#!cpp long double` that is IEEE 754 binary64 itself; other `#!cpp long double` formats are converted with
-  `#!cpp std::from_chars` where available, or with `#!cpp std::strtold`. The library provides overloads for exactly
-  these three types.
+- The [parser](../parsing/index.md) converts number literals with `#!cpp std::strtof`, `#!cpp std::strtod`, or
+  `#!cpp std::strtold`; the library provides overloads for exactly these three types.
 - [`dump`](../../api/basic_json/dump.md) falls back to `#!cpp std::snprintf` with the `%g` and `%Lg` conversion
   specifiers, for which the library likewise provides only `#!cpp double` and `#!cpp long double` overloads
   (`#!cpp float` is promoted to `#!cpp double`).

docs/mkdocs/docs/home/license.md

@@ -20,4 +20,4 @@ The class contains a slightly modified version of the Grisu2 algorithm from Flor
 
 The class contains a copy of [Hedley](https://nemequ.github.io/hedley/) from Evan Nemerson which is licensed as [CC0-1.0](https://creativecommons.org/publicdomain/zero/1.0/).
 
-The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors
+The class contains an adapted version of the Eisel-Lemire algorithm and its table of powers of five from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors

docs/mkdocs/mkdocs.yml

@@ -87,6 +87,7 @@ nav:
       - features/object_order.md
       - Parsing:
           - features/parsing/index.md
+          - features/parsing/error_recovery.md
           - features/parsing/json_lines.md
           - features/parsing/parse_exceptions.md
           - features/parsing/parser_callbacks.md

include/nlohmann/detail/abi_config.hpp

@@ -1,34 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <nlohmann/detail/abi_macros.hpp>
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-
-/*!
-@brief the configuration macros that change the library's behavior
-
-json.hpp undefines these macros at its end (see macro_unscope.hpp), so code
-that builds on the library after it (json_view.hpp) reads them here. Like the
-macros, they are part of the ABI namespace, so they always match the
-basic_json they are used with.
-*/
-struct abi_config
-{
-    /// JSON_STRICT_NUL_HANDLING: a null byte is an error, not the end of input
-    static constexpr bool strict_nul_handling = JSON_STRICT_NUL_HANDLING != 0;
-    /// JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
-    static constexpr bool legacy_discarded_value_comparison = JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON != 0;
-};
-
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/bit_ops.hpp

@@ -39,25 +39,6 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
 #endif
 }
 
-/// number of trailing zero bits of x (x != 0)
-inline int count_trailing_zeros(std::uint64_t x) noexcept
-{
-#if defined(__GNUC__) || defined(__clang__)
-    return __builtin_ctzll(x);
-#else
-    int n = 0;
-    for (int shift = 32; shift != 0; shift >>= 1)
-    {
-        if ((x << (64 - shift)) == 0)
-        {
-            n += shift;
-            x >>= shift;
-        }
-    }
-    return n;
-#endif
-}
-
 /// the 128-bit product of two 64-bit numbers
 struct uint128_parts
 {
@@ -87,19 +68,14 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
 
 /// eight bytes as a little-endian word (compilers fold this into one load on
 /// little-endian targets)
-inline std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
+inline std::uint64_t read_eight_bytes(const char* p) noexcept
 {
+    const auto* b = reinterpret_cast<const unsigned char*>(p); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
            | (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
            | (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
            | (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
 }
 
-/// eight bytes as a little-endian word
-inline std::uint64_t read_eight_bytes(const char* p) noexcept
-{
-    return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-}
-
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/input/json_sax.hpp

@@ -131,7 +131,9 @@ 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,
@@ -186,9 +188,12 @@ a pointer to the respective array or object for each recursion depth.
 After successful parsing, the value that is passed by reference to the
 constructor contains the parsed value.
 
-@tparam BasicJsonType  the JSON type
+@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
 */
-template<typename BasicJsonType, typename InputAdapterType>
+template<typename BasicJsonType, typename InputAdapterType = string_input_adapter_type>
 class json_sax_dom_parser
 {
   public:
@@ -505,7 +510,7 @@ class json_sax_dom_parser
     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:

include/nlohmann/detail/input/lexer.hpp

@@ -10,6 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint8_t
 #include <cstdio> // snprintf
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
@@ -219,44 +220,6 @@ class lexer : public lexer_base<BasicJsonType>
     // scan functions
     /////////////////////
 
-    /// contiguous input: try to decode the 4 hex digits following `\u`
-    /// directly from the input buffer via hex_codepoint(), instead of 4 calls
-    /// to get(). On success, advances the adapter and the position counters
-    /// exactly as those 4 get() calls would (a hex digit is never '\n', so
-    /// only the flat counters move) 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 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)
-    {
-        if (next_unget || ia.bulk_remaining() < 4)
-        {
-            return false;
-        }
-        const char_type* const raw = ia.bulk_data();
-        const int codepoint = hex_codepoint(reinterpret_cast<const unsigned char*>(raw));
-        if (codepoint < 0)
-        {
-            return false;
-        }
-        ia.bulk_skip(4);
-        // a hex digit is never a newline, so only the flat counters advance
-        position.chars_read_total += 4;
-        position.chars_read_current_line += 4;
-        current = char_traits<char_type>::to_int_type(raw[3]);
-        out = codepoint;
-        return true;
-    }
-
-    /// streaming input: no bulk fast path
-    bool get_codepoint_bulk(std::false_type /*bulk*/, int& /*out*/) const noexcept
-    {
-        return false;
-    }
-
     /*!
     @brief get codepoint from 4 hex characters following `\u`
 
@@ -276,14 +239,6 @@ class lexer : public lexer_base<BasicJsonType>
     {
         // this function only makes sense after reading `\u`
         JSON_ASSERT(current == 'u');
-
-        // contiguous input: decode all 4 hex digits directly from the buffer
-        int fast_codepoint = 0;
-        if (get_codepoint_bulk(std::integral_constant<bool, bulk_scan> {}, fast_codepoint))
-        {
-            return fast_codepoint;
-        }
-
         int codepoint = 0;
 
         const auto factors = { 12u, 8u, 4u, 0u };
@@ -483,8 +438,16 @@ 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";
+                                        string_error_resume = resume_kind::escaped_character;
+                                        return token_type::parse_error;
+                                    }
+
                                     const int codepoint2 = get_codepoint();
 
                                     if (JSON_HEDLEY_UNLIKELY(codepoint2 == -1))
@@ -509,7 +472,11 @@ class lexer : public lexer_base<BasicJsonType>
                                     }
                                     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";
+                                        string_error_resume = resume_kind::after_escape;
+                                        string_error_codepoint = codepoint2;
                                         return token_type::parse_error;
                                     }
                                 }
@@ -523,7 +490,9 @@ 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";
+                                    string_error_resume = resume_kind::after_escape;
                                     return token_type::parse_error;
                                 }
                             }
@@ -1105,11 +1074,9 @@ class lexer : public lexer_base<BasicJsonType>
             token_type::parse_error otherwise
 
     @note The scanner is independent of the current locale: token_buffer
-          always holds `.`. The conversion of float and double does not use
-          the locale either. Only the std::strtold fallback of
-          convert_number() for long double formats other than binary64
-          depends on it, and it looks up the decimal point right before
-          converting (see detail::convert_float_locale_aware()).
+          always holds `.`. Only the std::strtod fallback of convert_number()
+          depends on the locale, and it looks up the decimal point right
+          before converting (see detail::convert_float_locale_aware()).
     */
     token_type scan_number()  // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
     {
@@ -1122,7 +1089,7 @@ class lexer : public lexer_base<BasicJsonType>
 
         // offset just past the last mantissa byte in token_buffer (i.e. the
         // index of 'e'/'E', or the whole token when there is no exponent).
-        // convert_number() uses it to split the token; npos means
+        // convert_number() uses it to count significant digits; npos means
         // "not seen an exponent yet" and is resolved at scan_number_done
         std::size_t mantissa_end = std::string::npos;
 
@@ -1452,8 +1419,8 @@ scan_number_done:
     @param[in] mantissa_end  offset just past the last mantissa byte in
                              token_buffer (the index of 'e'/'E', or
                              token_buffer.size() when there is no exponent);
-                             with decimal_point_position, it locates the parts
-                             of a float token without scanning it again
+                             used to skip Clinger's fast path when it cannot
+                             possibly succeed - see detail::mantissa_fits_clinger()
     */
     token_type convert_number(token_type number_type, std::size_t mantissa_end)
     {
@@ -1522,11 +1489,10 @@ scan_number_done:
         }
 
         // this code is reached if we parse a floating-point number or if an
-        // integer conversion above overflowed. float and double (and long
-        // double where it is binary64) are converted by the library itself,
-        // correctly rounded and independent of the locale; other long double
-        // formats use std::from_chars when available, otherwise the
-        // locale-aware strtold.
+        // integer conversion above overflowed. Prefer std::from_chars
+        // (Eisel-Lemire, locale-independent, correctly rounded) when available;
+        // otherwise the exact Clinger fast path (double only); otherwise the
+        // locale-aware strtof/strtod/strtold.
         if (convert_float_fast(num_begin, num_end, decimal_point_position, mantissa_end, value_float))
         {
             return token_type::value_float;
@@ -2179,6 +2145,573 @@ scan_number_done:
         }
     }
 
+    /////////////////////
+    // 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 `\u` 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;
+
+        if (error_message_starts_with("invalid string"))
+        {
+            return recover_string(resume, codepoint);
+        }
+
+        if (error_message_starts_with("invalid number"))
+        {
+            return recover_number();
+        }
+
+        if (error_message_starts_with("invalid comment; missing"))
+        {
+            // the comment runs to the end of the input
+            return token_type::end_of_input;
+        }
+
+        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
+    };
+
+    /// whether error_message begins with @a prefix
+    bool error_message_starts_with(const char* prefix) const noexcept
+    {
+        const char* message = error_message;
+        while (*prefix != '\0')
+        {
+            if (*message++ != *prefix++)
+            {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    /// 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(0xEF);
+        add(0xBF);
+        add(0xBD);
+    }
+
+    /// 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);
+        const auto cp = static_cast<unsigned int>(codepoint);
+        if (cp < 0x80)
+        {
+            add(static_cast<char_int_type>(cp));
+        }
+        else if (cp <= 0x7FF)
+        {
+            add(static_cast<char_int_type>(0xC0u | (cp >> 6u)));
+            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
+        }
+        else if (cp <= 0xFFFF)
+        {
+            add(static_cast<char_int_type>(0xE0u | (cp >> 12u)));
+            add(static_cast<char_int_type>(0x80u | ((cp >> 6u) & 0x3Fu)));
+            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
+        }
+        else
+        {
+            add(static_cast<char_int_type>(0xF0u | (cp >> 18u)));
+            add(static_cast<char_int_type>(0x80u | ((cp >> 12u) & 0x3Fu)));
+            add(static_cast<char_int_type>(0x80u | ((cp >> 6u) & 0x3Fu)));
+            add(static_cast<char_int_type>(0x80u | (cp & 0x3Fu)));
+        }
+    }
+
+    /// append a code point read from a `\u` 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(static_cast<int>((static_cast<unsigned int>(high) << 10u)
+                                               + static_cast<unsigned int>(low) - 0x35FDC00u));
+                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] 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 resume_kind resume, const int codepoint)
+    {
+        // whether the next character must be read before it can be handled
+        bool fetch = false;
+
+        if (error_message_starts_with("invalid string: surrogate")
+                || error_message_starts_with("invalid string: '\\u'")
+                || (error_message_starts_with("invalid string: ill-formed UTF-8")
+                    && 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 adapter: the token string begins at current, which was consumed
+    void restart_token_string_impl(std::true_type /*lazy*/) noexcept
+    {
+        const std::size_t consumed = ia.get_consumed_count();
+        token_string_start = (consumed > 0 && current != char_traits<char_type>::eof()) ? consumed - 1 : consumed;
+    }
+
+    /// 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));
+        }
+    }
+
   private:
     /// input adapter
     InputAdapterType ia;
@@ -2219,6 +2752,13 @@ scan_number_done:
     /// a description of occurred lexer errors
     const char* error_message = "";
 
+    /// 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

@@ -98,7 +98,7 @@ class parser
         if (callback)
         {
             json_sax_dom_callback_parser<BasicJsonType, InputAdapterType> sdp(result, callback, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
+            sax_parse_internal<false>(&sdp);
 
             if (strict)
             {
@@ -135,7 +135,7 @@ class parser
         else
         {
             json_sax_dom_parser<BasicJsonType, InputAdapterType> sdp(result, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
+            sax_parse_internal<false>(&sdp);
 
             if (strict)
             {
@@ -173,26 +173,59 @@ 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)
+    {
+        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(sax);
+        const bool result = sax_parse_internal<AllowRecovery>(sax);
 
         if (result)
         {
             if (strict)
             {
-                // strict mode: next byte must be EOF
-                if (get_token() != token_type::end_of_input)
+                // 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)
                 {
-                    return sax->parse_error(m_lexer.get_position(),
-                                            m_lexer.get_token_string(),
-                                            parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
+                    // the value is complete, so there is nothing to recover
+                    static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr),
+                                                   std::integral_constant<bool, AllowRecovery> {}));
+                    return false;
                 }
             }
             else
@@ -203,14 +236,23 @@ class parser
             }
         }
 
-        return result;
+        return result && !error_reported;
     }
 
-  private:
-    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{};
+
         // stack to remember the hierarchy of structured values we are parsing
         // true = array; false = object
         std::vector<bool> states;
@@ -241,12 +283,18 @@ class parser
                             break;
                         }
 
-                        // parse key
+                        // remember we are now inside an object
+                        states.push_back(false);
+
+                        // 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 sax->parse_error(m_lexer.get_position(),
-                                                    m_lexer.get_token_string(),
-                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
+                            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())))
                         {
@@ -256,14 +304,13 @@ class parser
                         // parse separator (:)
                         if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
-                                                    m_lexer.get_token_string(),
-                                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
+                            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(false);
-
                         // parse values
                         get_token();
                         continue;
@@ -299,9 +346,11 @@ 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(406, 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, m_lexer.get_string())))
@@ -369,23 +418,63 @@ class parser
                     case token_type::parse_error:
                     {
                         // using "uninitialized" to avoid an "expected" message
-                        return sax->parse_error(m_lexer.get_position(),
-                                                m_lexer.get_token_string(),
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr));
+                        if (!report_error(sax, parse_error::create(101, 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();
+                        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())
+                            {
+                                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_position().chars_read_total == 1))
                         {
-                            return sax->parse_error(m_lexer.get_position(),
-                                                    m_lexer.get_token_string(),
-                                                    parse_error::create(101, m_lexer.get_position(),
-                                                            "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+                            // there is nothing to recover
+                            static_cast<void>(report_error(sax, parse_error::create(101, m_lexer.get_position(),
+                                                           "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr), allow_recovery));
+                            return false;
                         }
 
-                        return sax->parse_error(m_lexer.get_position(),
-                                                m_lexer.get_token_string(),
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
+                        if (!report_error(sax, parse_error::create(101, 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))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        m_lexer.unget_token();
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                     case token_type::uninitialized:
                     case token_type::end_array:
@@ -395,9 +484,35 @@ class parser
                     case token_type::literal_or_value:
                     default: // the last token was unexpected
                     {
-                        return sax->parse_error(m_lexer.get_position(),
-                                                m_lexer.get_token_string(),
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
+                        if (!report_error(sax, parse_error::create(101, 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())
+                            {
+                                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))
+                        {
+                            return false;
+                        }
+                        // the state evaluation reads the token again
+                        m_lexer.unget_token();
+                        skip_to_state_evaluation = true;
+                        continue;
                     }
                 }
             }
@@ -447,9 +562,30 @@ class parser
                     continue;
                 }
 
-                return sax->parse_error(m_lexer.get_position(),
-                                        m_lexer.get_token_string(),
-                                        parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr));
+                if (!report_error(sax, parse_error::create(101, 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);
+                }
+                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
@@ -466,11 +602,12 @@ class parser
                     // parse key
                     if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
                     {
-                        return sax->parse_error(m_lexer.get_position(),
-                                                m_lexer.get_token_string(),
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
+                        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())))
                     {
                         return false;
@@ -479,9 +616,11 @@ class parser
                     // parse separator (:)
                     if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
                     {
-                        return sax->parse_error(m_lexer.get_position(),
-                                                m_lexer.get_token_string(),
-                                                parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
+                        if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
+                        {
+                            return false;
+                        }
+                        continue;
                     }
 
                     // parse values
@@ -508,12 +647,479 @@ class parser
                 continue;
             }
 
-            return sax->parse_error(m_lexer.get_position(),
-                                    m_lexer.get_token_string(),
-                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr));
+            if (!report_error(sax, parse_error::create(101, 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);
+            }
+            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
+    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())))
+        {
+            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, typename AllowRecovery>
+    bool overflow_error(SAX* sax, const number_float_t value, AllowRecovery allow_recovery)
+    {
+        if (!report_error(sax, out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr), allow_recovery))
+        {
+            return false;
+        }
+        return sax->number_float(value, m_lexer.get_string());
+    }
+
+    /*!
+    @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>
+    std::false_type key_error(SAX* sax, std::false_type allow_recovery, const bool key_read)
+    {
+        return report_error(sax, parse_error::create(101, 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(101, 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(101, 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>
+    std::false_type report_error(SAX* sax, const Exception& ex, std::false_type /*allow_recovery*/)
+    {
+        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*/)
+    {
+        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;
+    }
+
+    /// pass the end events of all open containers
+    template<typename SAX>
+    bool close_containers(SAX* sax, std::vector<bool>& states)
+    {
+        while (!states.empty())
+        {
+            const bool is_array = states.back();
+            states.pop_back();
+            if (JSON_HEDLEY_UNLIKELY(is_array ? !sax->end_array() : !sax->end_object()))
+            {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    /*!
+    @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()
+    {
+        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<bool>& states)
+    {
+        JSON_ASSERT(!states.empty());
+        if (!states.back() || 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>
+    std::false_type recover_member(SAX* /*sax*/, std::false_type /*allow_recovery*/) const noexcept
+    {
+        return {};
+    }
+
     /// get next token from lexer
     token_type get_token()
     {
@@ -560,6 +1166,12 @@ 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/input/string_scan.hpp

@@ -8,12 +8,10 @@
 
 #pragma once
 
-#include <array> // array
 #include <cstddef> // size_t
-#include <cstdint> // uint64_t, uint8_t
+#include <cstdint> // uint64_t
 #include <cstring> // memcpy
 
-#include <nlohmann/detail/bit_ops.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 
 // Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -71,12 +69,18 @@ inline std::size_t find_string_special(const unsigned char* data, std::size_t n)
     std::size_t i = 0;
     for (; i + 8 <= n; i += 8)
     {
-        const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
-        if (special != 0)
+        std::uint64_t word = 0;
+        std::memcpy(&word, data + i, sizeof(word));
+        if (swar_string_special(word) != 0)
         {
-            // the lowest flagged byte is the first special one: the borrows of
-            // the subtractions can only flag bytes above a true hit
-            return i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
+            // a special byte is in this word; locate it (endian-agnostic)
+            for (std::size_t j = 0; j < 8; ++j)
+            {
+                if (is_string_special(data[i + j]))
+                {
+                    return i + j;
+                }
+            }
         }
     }
     for (; i < n; ++i)
@@ -110,7 +114,8 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
     std::size_t i = 0;
     for (; i + 8 <= n; i += 8)
     {
-        const std::uint64_t v = read_eight_bytes(data + i);
+        std::uint64_t v = 0;
+        std::memcpy(&v, data + i, sizeof(v));
         const std::uint64_t q = v ^ 0x2222222222222222ull; // '"'  (0x22)
         const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\' (0x5C)
         const std::uint64_t d = v ^ 0x7F7F7F7F7F7F7F7Full; // DEL  (0x7F)
@@ -121,9 +126,7 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
                                    | (v & high);               // >= 0x80
         if (stop != 0)
         {
-            // the lowest flagged byte is the first one to stop at (see
-            // find_string_special())
-            return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
+            break;
         }
     }
     for (; i < n; ++i)
@@ -250,18 +253,12 @@ inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t
         {
             break; // end of buffer, or a quote/escape/control byte
         }
-        // a run of multi-byte sequences (e.g. CJK text) is validated sequence
-        // by sequence without searching for the next special byte in between
-        do
+        const std::size_t seq = validate_one_utf8(data + pos, n - pos);
+        if (seq == 0)
         {
-            const std::size_t seq = validate_one_utf8(data + pos, n - pos);
-            if (seq == 0)
-            {
-                return pos; // ill-formed or truncated: let the byte path diagnose it
-            }
-            pos += seq;
+            break; // ill-formed or truncated: let the byte path diagnose it
         }
-        while (pos < n && data[pos] >= 0x80u);
+        pos += seq;
     }
     return pos;
 }
@@ -276,7 +273,8 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
     std::size_t i = 0;
     for (; i + 8 <= n; i += 8)
     {
-        const std::uint64_t v = read_eight_bytes(data + i);
+        std::uint64_t v = 0;
+        std::memcpy(&v, data + i, sizeof(v));
         const std::uint64_t q = v ^ 0x2222222222222222ull;
         const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull;
         const std::uint64_t hit = ((q - ones) & ~q & high)
@@ -284,8 +282,14 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
                                   | ((v - 0x2020202020202020ull) & ~v & high);
         if (hit != 0)
         {
-            // the lowest flagged byte is the first delimiter (see find_string_special())
-            return i + (static_cast<std::size_t>(count_trailing_zeros(hit)) / 8);
+            for (std::size_t j = 0; j < 8; ++j)
+            {
+                const unsigned char c = data[i + j];
+                if (c == '\"' || c == '\\' || c < 0x20u)
+                {
+                    return i + j;
+                }
+            }
         }
     }
     for (; i < n; ++i)
@@ -316,50 +320,5 @@ inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noe
     return scalar_string_bulk_run(data, n);
 }
 
-// Decode the 4 hex digits at [data, data+4) - the digits following a `\u`
-// escape - into a codepoint 0x0000..0xFFFF via one table lookup per byte
-// (after yyjson's read_hex_u16), or return -1 if any of the 4 bytes is not a
-// hex digit ('0'..'9', 'A'..'F', 'a'..'f'). The caller must already have
-// checked that 4 bytes are available; used by lexer::get_codepoint()'s
-// contiguous fast path. On -1 it falls back to the byte-at-a-time loop, which
-// stops at the first invalid digit, so the reported error and position are
-// unaffected by this fast path.
-inline int hex_codepoint(const unsigned char* data) noexcept
-{
-    static const std::array<std::uint8_t, 256> hex_digit_table = // NOLINT(cppcoreguidelines-avoid-non-const-global-variables)
-    {
-        {
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 00..0F
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 10..1F
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 20..2F
-            0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 30..3F ('0'..'9')
-            0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 40..4F ('A'..'F')
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 50..5F
-            0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 60..6F ('a'..'f')
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 70..7F
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 80..8F
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 90..9F
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // A0..AF
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // B0..BF
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // C0..CF
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // D0..DF
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // E0..EF
-            0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF  // F0..FF
-        }
-    };
-
-    const std::uint8_t d0 = hex_digit_table[data[0]];
-    const std::uint8_t d1 = hex_digit_table[data[1]];
-    const std::uint8_t d2 = hex_digit_table[data[2]];
-    const std::uint8_t d3 = hex_digit_table[data[3]];
-    // every valid digit is <= 0xF; the combined OR only exceeds it if at
-    // least one of the four bytes was not a hex digit (looked up as 0xFF)
-    if ((d0 | d1 | d2 | d3) > 0x0F)
-    {
-        return -1;
-    }
-    return (d0 << 12) | (d1 << 8) | (d2 << 4) | d3;
-}
-
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/json_pointer.hpp

@@ -26,7 +26,6 @@
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/string_concat.hpp>
 #include <nlohmann/detail/string_escape.hpp>
-#include <nlohmann/detail/string_utils.hpp>
 #include <nlohmann/detail/value_t.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -117,7 +116,7 @@ class json_pointer
     /// @sa https://json.nlohmann.me/api/json_pointer/operator_slasheq/
     json_pointer& operator/=(std::size_t array_idx)
     {
-        return *this /= detail::to_string<string_t>(array_idx);
+        return *this /= std::to_string(array_idx);
     }
 
     /// @brief create a new JSON pointer by appending the right JSON pointer at the end of the left JSON pointer
@@ -753,7 +752,7 @@ class json_pointer
                         // would throw out_of_range.404 -- contains() must not throw (see #5395)
                         return false;
                     }
-                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() == 1 && !('0' <= reference_token[0] && reference_token[0] <= '9')))
+                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() == 1 && !("0" <= reference_token && reference_token <= "9")))
                     {
                         // invalid char
                         return false;
@@ -781,7 +780,7 @@ class json_pointer
                     // not throw (see #5395), so such a reference token is treated as "not found"
                     errno = 0; // strtoull() does not reset errno on success
                     char* p_end = nullptr; // NOLINT(misc-const-correctness)
-                    const unsigned long long magnitude = std::strtoull(reference_token.data(), &p_end, 10); // NOLINT(runtime/int)
+                    const unsigned long long magnitude = std::strtoull(reference_token.c_str(), &p_end, 10); // NOLINT(runtime/int)
                     if (JSON_HEDLEY_UNLIKELY(errno == ERANGE // the value exceeds ULLONG_MAX
                                              || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
                     {

include/nlohmann/detail/string_utils.hpp

@@ -12,6 +12,7 @@
 #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>
@@ -133,5 +134,78 @@ inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noex
     return state == UTF8_ACCEPT;
 }
 
+/*!
+@brief append U+FFFD REPLACEMENT CHARACTER, encoded in UTF-8
+@param[in,out] s  the string to append to
+*/
+template<typename StringType>
+inline void append_replacement_character(StringType& s)
+{
+    s.push_back(static_cast<typename StringType::value_type>(0xEFu));
+    s.push_back(static_cast<typename StringType::value_type>(0xBFu));
+    s.push_back(static_cast<typename StringType::value_type>(0xBDu));
+}
+
+/*!
+@brief replace ill-formed UTF-8 with U+FFFD REPLACEMENT CHARACTER
+
+Each maximal subpart of an ill-formed sequence becomes one U+FFFD, as the
+Unicode Standard recommends (Section 3.9, "U+FFFD Substitution of Maximal
+Subparts"), and as the parser for JSON text does when it recovers from errors.
+
+@param[in,out] s  the string to repair
+@param[in] first  index of the first byte to repair; the bytes before it are
+                  assumed to be valid UTF-8 that ends on a code point boundary
+*/
+template<typename StringType>
+inline void replace_invalid_utf8(StringType& s, const std::size_t first = 0)
+{
+    StringType result = s;
+    result.resize(first);
+
+    std::uint8_t state = UTF8_ACCEPT;
+    std::uint32_t codepoint = 0;
+    // the first byte of the sequence being decoded
+    std::size_t sequence_start = first;
+
+    std::size_t i = first;
+    while (i < s.size())
+    {
+        switch (decode(state, codepoint, static_cast<std::uint8_t>(s[i])))
+        {
+            case UTF8_ACCEPT:
+                for (++i; sequence_start < i; ++sequence_start)
+                {
+                    result.push_back(s[sequence_start]);
+                }
+                break;
+
+            case UTF8_REJECT:
+                append_replacement_character(result);
+                // the byte that made the sequence ill-formed begins the next
+                // one, unless it began this one
+                if (i == sequence_start)
+                {
+                    ++i;
+                }
+                state = UTF8_ACCEPT;
+                sequence_start = i;
+                break;
+
+            default: // in the middle of a sequence
+                ++i;
+                break;
+        }
+    }
+
+    // a sequence that the string ends in the middle of
+    if (state != UTF8_ACCEPT)
+    {
+        append_replacement_character(result);
+    }
+
+    s = std::move(result);
+}
+
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/document_data.hpp

@@ -1,130 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <array> // array
-#include <cstddef> // size_t
-#include <cstring> // memcpy
-#include <new> // operator new, placement new
-#include <string> // string
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/macro_scope.hpp>
-#include <nlohmann/detail/view/node.hpp>
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-namespace view
-{
-
-/// storage of a parsed document; heap-allocated (header and an initial node
-/// array in one block) so that views survive moves of the owning document
-struct document_data
-{
-    const char* src = nullptr;
-    std::size_t size = 0;
-    node* tape = nullptr;
-    std::size_t tape_size = 0;
-    std::size_t tape_cap = 0;
-    node* inline_tape = nullptr; ///< node array allocated together with this header
-    std::size_t inline_cap = 0;
-    std::string arena{}; ///< decoded strings that contained escapes // NOLINT(readability-redundant-member-init)
-    std::string owned{}; ///< owned copy of the input, if any // NOLINT(readability-redundant-member-init)
-    std::array<const char*, 4> base = {{nullptr, nullptr, nullptr, nullptr}}; ///< string bases: source, arena (indexed by flags & node_flags::storage)
-    bool discarded = true;
-
-    /// one allocation for the header and room for `nodes` nodes; large
-    /// documents get a separate node array instead (so it can be trimmed)
-    static document_data* create(std::size_t nodes)
-    {
-        nodes = nodes <= 256 ? nodes : 0;
-        void* mem = ::operator new (sizeof(document_data) + (nodes * sizeof(node)));
-        auto* d = new (mem) document_data(); // NOLINT(cppcoreguidelines-owning-memory): owned by the returned pointer, freed by deleter
-        // (aligned: sizeof is a multiple of the alignment; through void*, as GCC's -Wcast-align wants)
-        d->inline_tape = static_cast<node*>(static_cast<void*>(static_cast<char*>(mem) + sizeof(document_data))); // NOLINT(bugprone-casting-through-void)
-        d->inline_cap = nodes;
-        d->tape = d->inline_tape;
-        d->tape_cap = nodes;
-        return d;
-    }
-
-    struct deleter
-    {
-        void operator()(document_data* d) const noexcept
-        {
-            d->~document_data();
-            ::operator delete (d);
-        }
-    };
-
-    document_data() noexcept = default;
-    document_data(const document_data&) = delete;
-    document_data(document_data&&) = delete;
-    document_data& operator=(const document_data&) = delete;
-    document_data& operator=(document_data&&) = delete;
-    ~document_data()
-    {
-        release();
-    }
-
-    void release() noexcept
-    {
-        if (tape != inline_tape)
-        {
-            ::operator delete (tape);
-        }
-        tape = inline_tape;
-        tape_cap = inline_cap;
-    }
-
-    /// make room for n nodes; keeps the first tape_size nodes
-    void reserve(std::size_t n)
-    {
-        if (n <= tape_cap)
-        {
-            return;
-        }
-        node* fresh = static_cast<node*>(::operator new (n * sizeof(node)));
-        if (tape_size != 0)
-        {
-            std::memcpy(fresh, tape, tape_size * sizeof(node));
-        }
-        release();
-        tape = fresh;
-        tape_cap = n;
-    }
-
-    const char* str(const node& n) const noexcept
-    {
-        return base[n.flags & node_flags::storage] + n.off;
-    }
-
-    /// the node after n's subtree (containers span `next` nodes, scalars one)
-    static NLOHMANN_VIEW_ALWAYS_INLINE const node* after(const node* n) noexcept
-    {
-        return n + (is_container(*n) ? n->next : 1u);
-    }
-
-    /// first element (array) or first key (object) of a container
-    static NLOHMANN_VIEW_ALWAYS_INLINE const node* first_child(const node* n) noexcept
-    {
-        return n + 1;
-    }
-
-    /// end of the elements of a container
-    static NLOHMANN_VIEW_ALWAYS_INLINE const node* child_end(const node* n) noexcept
-    {
-        return n + n->next;
-    }
-};
-
-}  // namespace view
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/macro_scope.hpp

@@ -1,63 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-// Macros of json_view.hpp and its detail headers. json.hpp undefines its own
-// macros at its end (macro_unscope.hpp), so the view defines the few it needs
-// under its own prefix; json_view.hpp undefines them all at its end
-// (detail/view/macro_unscope.hpp). Configuration that json.hpp undefines is
-// read from detail::abi_config instead.
-
-#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_MSVC_LANG) && _MSVC_LANG >= 201703L)
-    #define NLOHMANN_VIEW_HAS_CPP_17 1
-#else
-    #define NLOHMANN_VIEW_HAS_CPP_17 0
-#endif
-
-#if defined(__GNUC__) || defined(__clang__)
-    #define NLOHMANN_VIEW_LIKELY(x) __builtin_expect(!!(x), 1)
-    #define NLOHMANN_VIEW_UNLIKELY(x) __builtin_expect(!!(x), 0)
-    #define NLOHMANN_VIEW_ALWAYS_INLINE inline __attribute__((always_inline))
-    #define NLOHMANN_VIEW_NOINLINE __attribute__((noinline))
-#elif defined(_MSC_VER)
-    #define NLOHMANN_VIEW_LIKELY(x) (x)
-    #define NLOHMANN_VIEW_UNLIKELY(x) (x)
-    #define NLOHMANN_VIEW_ALWAYS_INLINE __forceinline
-    #define NLOHMANN_VIEW_NOINLINE __declspec(noinline)
-#else
-    #define NLOHMANN_VIEW_LIKELY(x) (x)
-    #define NLOHMANN_VIEW_UNLIKELY(x) (x)
-    #define NLOHMANN_VIEW_ALWAYS_INLINE inline
-    #define NLOHMANN_VIEW_NOINLINE
-#endif
-
-// exceptions as in json.hpp (JSON_NOEXCEPTION, JSON_THROW_USER)
-#if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
-    #define NLOHMANN_VIEW_THROW(exception) throw exception
-#else
-    #include <cstdlib>
-    // (the exception is built first, so that the arguments of the throwing
-    // helpers count as used; the program ends anyway)
-    #define NLOHMANN_VIEW_THROW(exception) (static_cast<void>(exception), std::abort())
-#endif
-#if defined(JSON_THROW_USER)
-    #undef NLOHMANN_VIEW_THROW
-    #define NLOHMANN_VIEW_THROW JSON_THROW_USER
-#endif
-
-// the parser stores a node's first word at once where the layout of `node` is
-// known to be little-endian (MSVC targets are); elsewhere field by field
-#if (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__) || defined(_MSC_VER)
-    #define NLOHMANN_VIEW_LITTLE_ENDIAN 1
-#else
-    #define NLOHMANN_VIEW_LITTLE_ENDIAN 0
-#endif
-
-/// sixteen checks at fixed offsets 0..15
-#define NLOHMANN_VIEW_REPEAT16(X) X(0) X(1) X(2) X(3) X(4) X(5) X(6) X(7) X(8) X(9) X(10) X(11) X(12) X(13) X(14) X(15)

include/nlohmann/detail/view/macro_unscope.hpp

@@ -1,20 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-// undefine the macros of detail/view/macro_scope.hpp (at the end of json_view.hpp)
-
-#undef NLOHMANN_VIEW_HAS_CPP_17
-#undef NLOHMANN_VIEW_LIKELY
-#undef NLOHMANN_VIEW_UNLIKELY
-#undef NLOHMANN_VIEW_ALWAYS_INLINE
-#undef NLOHMANN_VIEW_NOINLINE
-#undef NLOHMANN_VIEW_THROW
-#undef NLOHMANN_VIEW_LITTLE_ENDIAN
-#undef NLOHMANN_VIEW_REPEAT16

include/nlohmann/detail/view/node.hpp

@@ -1,97 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <cstddef> // size_t
-#include <cstdint> // uint8_t, uint16_t, uint32_t, uint64_t
-#include <cstring> // memcpy
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/macro_scope.hpp>
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-namespace view
-{
-
-// the node kinds are value_t values; the tests of is_container() and of the
-// number kinds depend on this numbering
-static_assert(static_cast<std::uint8_t>(value_t::null) == 0 && static_cast<std::uint8_t>(value_t::object) == 1
-              && static_cast<std::uint8_t>(value_t::array) == 2 && static_cast<std::uint8_t>(value_t::string) == 3
-              && static_cast<std::uint8_t>(value_t::boolean) == 4 && static_cast<std::uint8_t>(value_t::number_integer) == 5
-              && static_cast<std::uint8_t>(value_t::number_unsigned) == 6 && static_cast<std::uint8_t>(value_t::number_float) == 7,
-              "the node format depends on the numbering of value_t");
-
-/// node flags
-struct node_flags
-{
-    static constexpr std::uint8_t escaped = 1; ///< string payload lives in the decode arena, not the source
-    static constexpr std::uint8_t storage = 3; ///< mask: where a string or number token lives (index into document_data::base)
-    static constexpr std::uint8_t is_true = 4; ///< boolean value
-};
-
-/// One entry of the flat index, in document order. An object's members are
-/// stored as key node followed by the value's subtree. Integers keep their
-/// converted 64-bit value in the len/next bytes (the node after a scalar is
-/// always the next one, and the token length follows from `extra`).
-struct node
-{
-    std::uint8_t kind;   ///< value_t
-    std::uint8_t flags;  ///< node_flags
-    std::uint16_t extra; ///< numbers: integer digits (low byte) and fraction digits (high byte), 255 = "many"; otherwise 0
-    std::uint32_t off;   ///< source offset (string content, number token, literal, bracket); arena offset if node_flags::escaped
-    std::uint32_t len;   ///< string: decoded bytes; float: token bytes; array/object: element count
-    std::uint32_t next;  ///< array/object: number of nodes of the subtree (its extent in the enclosing sequence)
-};
-static_assert(sizeof(node) == 16, "node must stay 16 bytes");
-
-NLOHMANN_VIEW_ALWAYS_INLINE bool is_container(const node& n) noexcept
-{
-    return static_cast<unsigned>(n.kind) - 1u <= 1u;
-}
-
-/// the converted value of an integer node (stored in len/next)
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t integer_bits(const node& n) noexcept
-{
-    std::uint64_t v = 0;
-    std::memcpy(&v, reinterpret_cast<const unsigned char*>(&n) + 8, 8); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    return v;
-}
-
-NLOHMANN_VIEW_ALWAYS_INLINE void set_integer_bits(node& n, std::uint64_t v) noexcept
-{
-    std::memcpy(reinterpret_cast<unsigned char*>(&n) + 8, &v, 8); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-}
-
-/// token length of a number node
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint32_t number_length(const node& n) noexcept
-{
-    return n.kind == static_cast<std::uint8_t>(value_t::number_float) ? n.len
-           : (n.extra & 0xFFu) + (n.kind == static_cast<std::uint8_t>(value_t::number_integer) ? 1u : 0u);
-}
-
-/// estimated number of nodes for an input of `size` bytes (one node per ~12
-/// bytes covers typical documents without regrowth)
-inline std::size_t estimate_nodes(std::size_t size) noexcept
-{
-    return (size / 12) + 16;
-}
-
-/// estimated number of nodes for the input [src, src + size): pretty-printed
-/// input (whitespace after the first byte) needs about a node per 12 bytes,
-/// minified input up to one per 4 (yyjson tells the two apart the same way)
-inline std::size_t estimate_nodes(const char* src, std::size_t size) noexcept
-{
-    return size >= 2 && (src[1] == ' ' || src[1] == '\n' || src[1] == '\r' || src[1] == '\t') ? estimate_nodes(size) : (size / 4) + 16;
-}
-
-}  // namespace view
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/scan.hpp

@@ -1,189 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-FileCopyrightText: 2020 YaoYuan <https://github.com/ibireme/yyjson>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <array> // array
-#include <cstddef> // size_t
-#include <cstdint> // uint8_t, uint16_t, uint64_t
-#include <cstring> // memcpy
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/macro_scope.hpp>
-
-// Scanning primitives of the view's parser. The unrolled checks at fixed
-// offsets follow yyjson (https://github.com/ibireme/yyjson, MIT license): the
-// loads do not depend on each other, so the CPU can run ahead. Words are read
-// with read_eight_bytes(), so nothing here depends on the byte order.
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-namespace view
-{
-
-/// 1 for bytes that may appear verbatim in a string: 0x20..0x7F except '"' and '\\'
-inline const std::uint8_t* string_plain() noexcept
-{
-    static const std::array<std::uint8_t, 256> table =
-    {
-        {
-            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x00..0x1F
-            1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x20..0x3F ('"')
-            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, // 0x40..0x5F ('\\')
-            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x60..0x7F
-            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x80..0x9F
-            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xA0..0xBF
-            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xC0..0xDF
-            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xE0..0xFF
-        }
-    };
-    return table.data();
-}
-
-NLOHMANN_VIEW_ALWAYS_INLINE bool is_digit(unsigned char c) noexcept
-{
-    return static_cast<unsigned char>(c - '0') <= 9;
-}
-
-/// two bytes as they are in memory (only compared with byte-symmetric patterns)
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint16_t load16(const unsigned char* p) noexcept
-{
-    std::uint16_t w = 0;
-    std::memcpy(&w, p, 2);
-    return w;
-}
-
-/// Advance over plain string bytes and well-formed UTF-8. Stops at a quote,
-/// a backslash, a control character, ill-formed UTF-8, or the end. The first
-/// 16 bytes are checked one by one, so that the position advances by
-/// constants in predicted branches (most strings are short); longer runs
-/// continue eight bytes at a time.
-NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* scan_string_run(const unsigned char* p, const unsigned char* e) noexcept
-{
-    const std::uint8_t* plain = string_plain();
-    for (;;)
-    {
-        if (e - p >= 16)
-        {
-#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(plain[p[i]] != 0)) {} else { p += (i); goto stop; }
-            NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
-#undef NLOHMANN_VIEW_STEP
-            p += 16;
-            while (e - p >= 8)
-            {
-                const std::uint64_t special = swar_string_special(read_eight_bytes(p));
-                if (special != 0)
-                {
-                    p += count_trailing_zeros(special) / 8;
-                    goto stop;
-                }
-                p += 8;
-            }
-            continue;
-        }
-        while (p != e && plain[*p] != 0)
-        {
-            ++p;
-        }
-        if (p == e)
-        {
-            return p;
-        }
-stop:
-        if (*p < 0x80)
-        {
-            return p; // quote, backslash, or control character
-        }
-        // non-ASCII: a run of well-formed sequences (the library's check, so
-        // that exactly what json::parse accepts is accepted)
-        do
-        {
-            const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
-            if (n == 0)
-            {
-                return p;
-            }
-            p += n;
-        }
-        while (p != e && *p >= 0x80);
-    }
-}
-
-/// advance over ASCII digits
-NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* skip_digits(const unsigned char* p, const unsigned char* e) noexcept
-{
-    while (e - p >= 16)
-    {
-#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(is_digit(p[i]))) {} else { return p + (i); }
-        NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
-#undef NLOHMANN_VIEW_STEP
-        p += 16;
-    }
-    while (p != e && is_digit(*p))
-    {
-        ++p;
-    }
-    return p;
-}
-
-/// powers of ten up to 10^19 as integers
-inline std::uint64_t int_pow10(unsigned k) noexcept
-{
-    static const std::array<std::uint64_t, 20> table =
-    {
-        {
-            1u, 10u, 100u, 1000u, 10000u, 100000u, 1000000u, 10000000u, 100000000u, 1000000000u,
-            10000000000u, 100000000000u, 1000000000000u, 10000000000000u, 100000000000000u, 1000000000000000u,
-            10000000000000000u, 100000000000000000u, 1000000000000000000u, 10000000000000000000u
-        }
-    };
-    return table[k];
-}
-
-/// value of 0 < k < 8 digits at p in one step if [p, p + 8) lies below
-/// limit, else one digit at a time (whole blocks of eight digits are read by
-/// parse_upto19() directly)
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t parse_upto8(const unsigned char* p, unsigned k, const unsigned char* limit) noexcept
-{
-    if (NLOHMANN_VIEW_LIKELY(limit - p >= 8))
-    {
-        // move the k digits to the top and pad the vacated low bytes with '0'
-        const unsigned shift = 8 * (8 - k);
-        return parse_eight_digits((read_eight_bytes(p) << shift) | (0x3030303030303030u >> (8 * k)));
-    }
-    std::uint64_t v = 0;
-    for (unsigned i = 0; i < k; ++i)
-    {
-        v = (v * 10) + static_cast<std::uint64_t>(p[i] - '0');
-    }
-    return v;
-}
-
-/// value of k <= 19 digits at p
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t parse_upto19(const unsigned char* p, unsigned k, const unsigned char* limit) noexcept
-{
-    std::uint64_t w = 0;
-    while (k >= 8)
-    {
-        // (eight digits of the token: they lie below limit)
-        w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
-        p += 8;
-        k -= 8;
-    }
-    if (k != 0)
-    {
-        w = (w * int_pow10(k)) + parse_upto8(p, k, limit);
-    }
-    return w;
-}
-
-}  // namespace view
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/string_ref.hpp

@@ -1,111 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#pragma once
-
-#include <algorithm> // min
-#include <cstddef> // size_t
-#include <cstring> // memcmp, strlen
-#include <string> // basic_string
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/macro_scope.hpp>
-
-#if NLOHMANN_VIEW_HAS_CPP_17
-    #include <string_view> // string_view
-#endif
-#ifndef JSON_NO_IO
-    #include <ostream> // ostream
-#endif
-
-NLOHMANN_JSON_NAMESPACE_BEGIN
-namespace detail
-{
-namespace view
-{
-
-#if NLOHMANN_VIEW_HAS_CPP_17
-using string_ref = std::string_view;
-#else
-/// minimal C++11 stand-in for std::string_view
-class string_ref
-{
-  public:
-    using size_type = std::size_t;
-    using const_iterator = const char*;
-
-    string_ref() noexcept = default;
-    string_ref(const char* s) : m_data(s), m_size(std::strlen(s)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
-    string_ref(const char* s, std::size_t n) noexcept : m_data(s), m_size(n) {}
-    template<typename Traits, typename Alloc>
-    string_ref(const std::basic_string<char, Traits, Alloc>& s) noexcept : m_data(s.data()), m_size(s.size()) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
-
-    const char* data() const noexcept
-    {
-        return m_data;
-    }
-    std::size_t size() const noexcept
-    {
-        return m_size;
-    }
-    std::size_t length() const noexcept
-    {
-        return m_size;
-    }
-    bool empty() const noexcept
-    {
-        return m_size == 0;
-    }
-    const char* begin() const noexcept
-    {
-        return m_data;
-    }
-    const char* end() const noexcept
-    {
-        return m_data + m_size;
-    }
-    char operator[](std::size_t i) const noexcept
-    {
-        return m_data[i];
-    }
-
-    template<typename Traits, typename Alloc>
-    explicit operator std::basic_string<char, Traits, Alloc>() const
-    {
-        return std::basic_string<char, Traits, Alloc>(m_data, m_size);
-    }
-
-    friend bool operator==(string_ref a, string_ref b) noexcept
-    {
-        return a.m_size == b.m_size && (a.m_size == 0 || std::memcmp(a.m_data, b.m_data, a.m_size) == 0);
-    }
-    friend bool operator!=(string_ref a, string_ref b) noexcept
-    {
-        return !(a == b);
-    }
-    friend bool operator<(string_ref a, string_ref b) noexcept
-    {
-        const int c = std::memcmp(a.m_data, b.m_data, (std::min)(a.m_size, b.m_size));
-        return c != 0 ? c < 0 : a.m_size < b.m_size;
-    }
-#ifndef JSON_NO_IO
-    friend std::ostream& operator<<(std::ostream& o, string_ref s)
-    {
-        return o.write(s.m_data, static_cast<std::streamsize>(s.m_size));
-    }
-#endif
-
-  private:
-    const char* m_data = "";
-    std::size_t m_size = 0;
-};
-#endif
-
-}  // namespace view
-}  // namespace detail
-NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json.hpp

@@ -45,7 +45,6 @@
 
 #include <nlohmann/adl_serializer.hpp>
 #include <nlohmann/byte_container_with_subtype.hpp>
-#include <nlohmann/detail/abi_config.hpp>
 #include <nlohmann/detail/conversions/from_json.hpp>
 #include <nlohmann/detail/conversions/to_json.hpp>
 #include <nlohmann/detail/exceptions.hpp>
@@ -146,7 +145,7 @@ 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>
     friend class ::nlohmann::detail::json_sax_dom_parser;
@@ -5035,7 +5034,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
     }
 
     /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -5052,7 +5051,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
     }
 
     /// @brief generate SAX events
@@ -5074,7 +5073,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX, true>(std::move(ia), format).sax_parse(format, sax, strict);
     }
 #ifndef JSON_NO_IO
     /// @brief deserialize from stream
@@ -5093,10 +5092,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @sa https://json.nlohmann.me/api/basic_json/operator_gtgt/
     friend std::istream& operator>>(std::istream& i, basic_json& j)
     {
-        // parse into a temporary so that j is left unchanged if parsing fails
-        basic_json result;
-        parser(detail::input_adapter(i)).parse(false, result);
-        j = std::move(result);
+        parser(detail::input_adapter(i)).parse(false, j);
         return i;
     }
 #endif  // JSON_NO_IO

src/modules/json.cppm

@@ -47,6 +47,7 @@ inline namespace json_literals
 namespace detail
 {
     using NLOHMANN_JSON_NAMESPACE::detail::json_sax_dom_callback_parser;
+    using NLOHMANN_JSON_NAMESPACE::detail::json_sax_dom_parser;
     using NLOHMANN_JSON_NAMESPACE::detail::unknown_size;
 } // namespace detail
 

tests/CMakeLists.txt

@@ -279,10 +279,6 @@ if(json_32bit_test_only)
 elseif(NOT json_32bit_test)
     list(FILTER files EXCLUDE REGEX src/unit-32bit.cpp)
 endif()
-if(NOT JSON_MultipleHeaders)
-    # the internal headers of json_view are not part of a single header yet
-    list(FILTER files EXCLUDE REGEX src/unit-json_view_builder.cpp)
-endif()
 
 foreach(file ${files})
     json_test_add_test_for(${file} MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force})

tests/src/float_hard_cases.hpp

@@ -1,599 +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
-
-#pragma once
-
-#include <array> // array
-#include <cstdint> // uint32_t, uint64_t
-
-// Number tokens that are hard to round correctly, with the IEEE-754 binary64
-// and binary32 bits of their correctly rounded values (ties to even; infinity
-// for an overflow, a signed zero for an underflow).
-//
-// For doubles and floats around 0, the smallest normal number, 1, 2^24, 2^53,
-// 0.1, and the largest finite number, and for random ones, the exact midpoint
-// m to the next number gives: m, m with one unit more and less in the last
-// digit, m with "01" and "0...01" appended, m with trailing zeros, and m cut
-// after 17 to 30 digits (rounded down and up, so that the rounding is decided
-// after the 19th digit), in fixed and exponent notation, 30% of them negative.
-// Tokens longer than 80 characters are left out, except for four of 700 digits
-// and more. Zeros, underflow, overflow, huge exponents, and integers beyond 64
-// bits complete the set. Of the 508 tokens, 134 (as double) and 150 (as
-// float) need the exact comparison with the midpoint (detail::digit_comparison()).
-//
-// The expected bits were computed with exact rational arithmetic in Python
-// (fractions.Fraction) and cross-checked with Python's float(); strtod_l and
-// strtof_l of Apple's libc and of glibc agree. Generated by
-// compact_hard_cases.py 5 (with hard_cases.py), see the pull request that
-// added this file.
-
-namespace float_hard_cases
-{
-
-struct hard_case
-{
-    const char* token;
-    std::uint64_t bits64;
-    std::uint32_t bits32;
-};
-
-inline const std::array<hard_case, 508>& cases()
-{
-    static const std::array<hard_case, 508> table =
-    {
-        {
-            {"-2.4703282292062327e-324", 0x8000000000000000u, 0x80000000u},
-            {"24703282292062328e-340", 0x0000000000000001u, 0x00000000u},
-            {"247032822920623272e-341", 0x0000000000000000u, 0x00000000u},
-            {"-0.2470328229206232721e-323", 0x8000000000000001u, 0x80000000u},
-            {"-0.24703282292062327208e-323", 0x8000000000000000u, 0x80000000u},
-            {"-2.4703282292062327209e-324", 0x8000000000000001u, 0x80000000u},
-            {"2.47032822920623272088e-324", 0x0000000000000000u, 0x00000000u},
-            {"247032822920623272089e-344", 0x0000000000000001u, 0x00000000u},
-            {"-247032822920623272088284396434e-353", 0x8000000000000000u, 0x80000000u},
-            {"0.247032822920623272088284396435e-323", 0x0000000000000001u, 0x00000000u},
-            {"-74109846876186981e-340", 0x8000000000000001u, 0x80000000u},
-            {"0.74109846876186982e-323", 0x0000000000000002u, 0x00000000u},
-            {"-0.7410984687618698162e-323", 0x8000000000000001u, 0x80000000u},
-            {"-7.410984687618698163e-324", 0x8000000000000002u, 0x80000000u},
-            {"7.4109846876186981626e-324", 0x0000000000000001u, 0x00000000u},
-            {"-74109846876186981627e-343", 0x8000000000000002u, 0x80000000u},
-            {"-741098468761869816264e-344", 0x8000000000000001u, 0x80000000u},
-            {"0.741098468761869816265e-323", 0x0000000000000002u, 0x00000000u},
-            {"0.741098468761869816264853189302e-323", 0x0000000000000001u, 0x00000000u},
-            {"-7.41098468761869816264853189303e-324", 0x8000000000000002u, 0x80000000u},
-            {"0.22250738585072006e-307", 0x000FFFFFFFFFFFFEu, 0x00000000u},
-            {"2.2250738585072007e-308", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"2.225073858507200641e-308", 0x000FFFFFFFFFFFFEu, 0x00000000u},
-            {"-2225073858507200642e-326", 0x800FFFFFFFFFFFFFu, 0x80000000u},
-            {"22250738585072006419e-327", 0x000FFFFFFFFFFFFEu, 0x00000000u},
-            {"0.2225073858507200642e-307", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"0.222507385850720064199e-307", 0x000FFFFFFFFFFFFEu, 0x00000000u},
-            {"2.225073858507200642e-308", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"-2.22507385850720064199176395546e-308", 0x800FFFFFFFFFFFFEu, 0x80000000u},
-            {"222507385850720064199176395547e-337", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"-2.2250738585072011e-308", 0x800FFFFFFFFFFFFFu, 0x80000000u},
-            {"-22250738585072012e-324", 0x8010000000000000u, 0x80000000u},
-            {"-2225073858507201136e-326", 0x800FFFFFFFFFFFFFu, 0x80000000u},
-            {"0.2225073858507201137e-307", 0x0010000000000000u, 0x00000000u},
-            {"0.2225073858507201136e-307", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"-2.2250738585072011361e-308", 0x8010000000000000u, 0x80000000u},
-            {"2.22507385850720113605e-308", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"222507385850720113606e-328", 0x0010000000000000u, 0x00000000u},
-            {"22250738585072011360574097967e-336", 0x000FFFFFFFFFFFFFu, 0x00000000u},
-            {"0.222507385850720113605740979671e-307", 0x0010000000000000u, 0x00000000u},
-            {"22250738585072016e-324", 0x0010000000000000u, 0x00000000u},
-            {"0.22250738585072017e-307", 0x0010000000000001u, 0x00000000u},
-            {"0.222507385850720163e-307", 0x0010000000000000u, 0x00000000u},
-            {"2.225073858507201631e-308", 0x0010000000000001u, 0x00000000u},
-            {"-2.2250738585072016301e-308", 0x8010000000000000u, 0x80000000u},
-            {"22250738585072016302e-327", 0x0010000000000001u, 0x00000000u},
-            {"-222507385850720163012e-328", 0x8010000000000000u, 0x80000000u},
-            {"0.222507385850720163013e-307", 0x0010000000000001u, 0x00000000u},
-            {"0.222507385850720163012305563795e-307", 0x0010000000000000u, 0x00000000u},
-            {"-2.22507385850720163012305563796e-308", 0x8010000000000001u, 0x80000000u},
-            {"0.17976931348623156E+309", 0x7FEFFFFFFFFFFFFEu, 0x7F800000u},
-            {"1.7976931348623157e308", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"1.797693134862315608e308", 0x7FEFFFFFFFFFFFFEu, 0x7F800000u},
-            {"-1797693134862315609e290", 0xFFEFFFFFFFFFFFFFu, 0xFF800000u},
-            {"-17976931348623156083e289", 0xFFEFFFFFFFFFFFFEu, 0xFF800000u},
-            {"-0.17976931348623156084E+309", 0xFFEFFFFFFFFFFFFFu, 0xFF800000u},
-            {"0.179769313486231560835E+309", 0x7FEFFFFFFFFFFFFEu, 0x7F800000u},
-            {"-1.79769313486231560836e308", 0xFFEFFFFFFFFFFFFFu, 0xFF800000u},
-            {"1.79769313486231560835325876058e308", 0x7FEFFFFFFFFFFFFEu, 0x7F800000u},
-            {"179769313486231560835325876059e279", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"1.7976931348623158e308", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"17976931348623159e292", 0x7FF0000000000000u, 0x7F800000u},
-            {"1797693134862315807e290", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"0.1797693134862315808E+309", 0x7FF0000000000000u, 0x7F800000u},
-            {"0.17976931348623158079E+309", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"-1.797693134862315808e308", 0xFFF0000000000000u, 0xFF800000u},
-            {"1.79769313486231580793e308", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"179769313486231580794e288", 0x7FF0000000000000u, 0x7F800000u},
-            {"179769313486231580793728971405e279", 0x7FEFFFFFFFFFFFFFu, 0x7F800000u},
-            {"-0.179769313486231580793728971406E+309", 0xFFF0000000000000u, 0xFF800000u},
-            {"100000000000000011102230246251565404236316680908203125e-53", 0x3FF0000000000000u, 0x3F800000u},
-            {"-1.00000000000000011102230246251565404236316680908203126", 0xBFF0000000000001u, 0xBF800000u},
-            {"1.00000000000000011102230246251565404236316680908203124e0", 0x3FF0000000000000u, 0x3F800000u},
-            {"10000000000000001110223024625156540423631668090820312501e-55", 0x3FF0000000000001u, 0x3F800000u},
-            {"1.00000000000000011102230246251565404236316680908203125000000000000000000001", 0x3FF0000000000001u, 0x3F800000u},
-            {"10000000000000001e-16", 0x3FF0000000000000u, 0x3F800000u},
-            {"1.0000000000000002", 0x3FF0000000000001u, 0x3F800000u},
-            {"1.000000000000000111", 0x3FF0000000000000u, 0x3F800000u},
-            {"1.000000000000000112e0", 0x3FF0000000000001u, 0x3F800000u},
-            {"1.000000000000000111e0", 0x3FF0000000000000u, 0x3F800000u},
-            {"-10000000000000001111e-19", 0xBFF0000000000001u, 0xBF800000u},
-            {"-100000000000000011102e-20", 0xBFF0000000000000u, 0xBF800000u},
-            {"-1.00000000000000011103", 0xBFF0000000000001u, 0xBF800000u},
-            {"1.00000000000000011102230246251", 0x3FF0000000000000u, 0x3F800000u},
-            {"1.00000000000000011102230246252e0", 0x3FF0000000000001u, 0x3F800000u},
-            {"-0.999999999999999944488848768742172978818416595458984375", 0xBFF0000000000000u, 0xBF800000u},
-            {"-9.99999999999999944488848768742172978818416595458984376e-1", 0xBFF0000000000000u, 0xBF800000u},
-            {"999999999999999944488848768742172978818416595458984374e-54", 0x3FEFFFFFFFFFFFFFu, 0x3F800000u},
-            {"0.99999999999999994448884876874217297881841659545898437501", 0x3FF0000000000000u, 0x3F800000u},
-            {"9.99999999999999944488848768742172978818416595458984375000000000000000000001e-1", 0x3FF0000000000000u, 0x3F800000u},
-            {"-0.99999999999999994", 0xBFEFFFFFFFFFFFFFu, 0xBF800000u},
-            {"9.9999999999999995e-1", 0x3FF0000000000000u, 0x3F800000u},
-            {"9.999999999999999444e-1", 0x3FEFFFFFFFFFFFFFu, 0x3F800000u},
-            {"9999999999999999445e-19", 0x3FF0000000000000u, 0x3F800000u},
-            {"99999999999999994448e-20", 0x3FEFFFFFFFFFFFFFu, 0x3F800000u},
-            {"-0.99999999999999994449", 0xBFF0000000000000u, 0xBF800000u},
-            {"0.999999999999999944488", 0x3FEFFFFFFFFFFFFFu, 0x3F800000u},
-            {"-9.99999999999999944489e-1", 0xBFF0000000000000u, 0xBF800000u},
-            {"9.99999999999999944488848768742e-1", 0x3FEFFFFFFFFFFFFFu, 0x3F800000u},
-            {"999999999999999944488848768743e-30", 0x3FF0000000000000u, 0x3F800000u},
-            {"-9.007199254740993e15", 0xC340000000000000u, 0xDA000000u},
-            {"9007199254740994e0", 0x4340000000000001u, 0x5A000000u},
-            {"9007199254740992", 0x4340000000000000u, 0x5A000000u},
-            {"9.00719925474099301e15", 0x4340000000000001u, 0x5A000000u},
-            {"9007199254740993000000000000000000001e-21", 0x4340000000000001u, 0x5A000000u},
-            {"-9007199254740993.000000000000000000000000000000", 0xC340000000000000u, 0xDA000000u},
-            {"90071992547409915e-1", 0x4340000000000000u, 0x5A000000u},
-            {"-9007199254740991.6", 0xC340000000000000u, 0xDA000000u},
-            {"9.0071992547409914e15", 0x433FFFFFFFFFFFFFu, 0x5A000000u},
-            {"-9007199254740991501e-3", 0xC340000000000000u, 0xDA000000u},
-            {"9007199254740991.5000000000000000000001", 0x4340000000000000u, 0x5A000000u},
-            {"9.0071992547409915000000000000000000000000000000e15", 0x4340000000000000u, 0x5A000000u},
-            {"0.100000000000000012490009027033011079765856266021728515625", 0x3FB999999999999Au, 0x3DCCCCCDu},
-            {"1.00000000000000012490009027033011079765856266021728515626e-1", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"100000000000000012490009027033011079765856266021728515624e-57", 0x3FB999999999999Au, 0x3DCCCCCDu},
-            {"0.10000000000000001249000902703301107976585626602172851562501", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"0.10000000000000001", 0x3FB999999999999Au, 0x3DCCCCCDu},
-            {"1.0000000000000002e-1", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"-1.000000000000000124e-1", 0xBFB999999999999Au, 0xBDCCCCCDu},
-            {"1000000000000000125e-19", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"-10000000000000001249e-20", 0xBFB999999999999Au, 0xBDCCCCCDu},
-            {"0.1000000000000000125", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"0.10000000000000001249", 0x3FB999999999999Au, 0x3DCCCCCDu},
-            {"1.00000000000000012491e-1", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"1.00000000000000012490009027033e-1", 0x3FB999999999999Au, 0x3DCCCCCDu},
-            {"100000000000000012490009027034e-30", 0x3FB999999999999Bu, 0x3DCCCCCDu},
-            {"2.45134755833537796875e14", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"-245134755833537796876e-6", 0xC2EBDE5C4164D83Au, 0xD75EF2E2u},
-            {"-245134755833537.796874", 0xC2EBDE5C4164D839u, 0xD75EF2E2u},
-            {"2.4513475583353779687501e14", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"245134755833537796875000000000000000000001e-27", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"245134755833537.796875000000000000000000000000000000", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"2.4513475583353779e14", 0x42EBDE5C4164D839u, 0x575EF2E2u},
-            {"2451347558335378e-1", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"2451347558335377968e-4", 0x42EBDE5C4164D839u, 0x575EF2E2u},
-            {"245134755833537.7969", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"245134755833537.79687", 0x42EBDE5C4164D839u, 0x575EF2E2u},
-            {"2.4513475583353779688e14", 0x42EBDE5C4164D83Au, 0x575EF2E2u},
-            {"181510327827821147441864013671875e-23", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"-1815103278.27821147441864013671876", 0xC1DB0C11CB91CE38u, 0xCED8608Eu},
-            {"1.81510327827821147441864013671874e9", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"18151032782782114744186401367187501e-25", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"1815103278.27821147441864013671875000000000000000000001", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"-1.81510327827821147441864013671875000000000000000000000000000000e9", 0xC1DB0C11CB91CE38u, 0xCED8608Eu},
-            {"18151032782782114e-7", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"1815103278.2782115", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"1815103278.278211474", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"-1.815103278278211475e9", 0xC1DB0C11CB91CE38u, 0xCED8608Eu},
-            {"1.8151032782782114744e9", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"-18151032782782114745e-10", 0xC1DB0C11CB91CE38u, 0xCED8608Eu},
-            {"181510327827821147441e-11", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"1815103278.27821147442", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"1815103278.27821147441864013671", 0x41DB0C11CB91CE37u, 0x4ED8608Eu},
-            {"1.81510327827821147441864013672e9", 0x41DB0C11CB91CE38u, 0x4ED8608Eu},
-            {"3809325632181785344", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"3.809325632181785345e18", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"3809325632181785343e0", 0x43CA6EB8BD69FE29u, 0x5E5375C6u},
-            {"3809325632181785344.01", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"3.809325632181785344000000000000000000001e18", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"3809325632181785344000000000000000000000000000000e-30", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"3809325632181785300", 0x43CA6EB8BD69FE29u, 0x5E5375C6u},
-            {"3.8093256321817854e18", 0x43CA6EB8BD69FE2Au, 0x5E5375C6u},
-            {"4.046966549916366943359375e12", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"4046966549916366943359376e-12", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"4046966549916.366943359374", 0x428D7210076CE2EFu, 0x546B9080u},
-            {"4.04696654991636694335937501e12", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"4046966549916366943359375000000000000000000001e-33", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"-4046966549916.366943359375000000000000000000000000000000", 0xC28D7210076CE2F0u, 0xD46B9080u},
-            {"4.0469665499163669e12", 0x428D7210076CE2EFu, 0x546B9080u},
-            {"4046966549916367e-3", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"4046966549916366943e-6", 0x428D7210076CE2EFu, 0x546B9080u},
-            {"4046966549916.366944", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"4046966549916.3669433", 0x428D7210076CE2EFu, 0x546B9080u},
-            {"4.0469665499163669434e12", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"-4.04696654991636694335e12", 0xC28D7210076CE2EFu, 0xD46B9080u},
-            {"404696654991636694336e-8", 0x428D7210076CE2F0u, 0x546B9080u},
-            {"28093802557000874e154", 0x63529C3B77330BDBu, 0x7F800000u},
-            {"0.28093802557000875E+171", 0x63529C3B77330BDCu, 0x7F800000u},
-            {"0.2809380255700087447E+171", 0x63529C3B77330BDBu, 0x7F800000u},
-            {"2.809380255700087448e170", 0x63529C3B77330BDCu, 0x7F800000u},
-            {"2.8093802557000874472e170", 0x63529C3B77330BDBu, 0x7F800000u},
-            {"28093802557000874473e151", 0x63529C3B77330BDCu, 0x7F800000u},
-            {"280938025570008744728e150", 0x63529C3B77330BDBu, 0x7F800000u},
-            {"-0.280938025570008744729E+171", 0xE3529C3B77330BDCu, 0xFF800000u},
-            {"-0.280938025570008744728403667979E+171", 0xE3529C3B77330BDBu, 0xFF800000u},
-            {"2.8093802557000874472840366798e170", 0x63529C3B77330BDCu, 0x7F800000u},
-            {"0.39523280297734525e-154", 0x1FE0F51BF17FD374u, 0x00000000u},
-            {"-3.9523280297734526e-155", 0x9FE0F51BF17FD375u, 0x80000000u},
-            {"3.952328029773452547e-155", 0x1FE0F51BF17FD374u, 0x00000000u},
-            {"3952328029773452548e-173", 0x1FE0F51BF17FD375u, 0x00000000u},
-            {"-39523280297734525478e-174", 0x9FE0F51BF17FD374u, 0x80000000u},
-            {"0.39523280297734525479e-154", 0x1FE0F51BF17FD375u, 0x00000000u},
-            {"-0.395232802977345254787e-154", 0x9FE0F51BF17FD374u, 0x80000000u},
-            {"-3.95232802977345254788e-155", 0x9FE0F51BF17FD375u, 0x80000000u},
-            {"-3.95232802977345254787245825501e-155", 0x9FE0F51BF17FD374u, 0x80000000u},
-            {"395232802977345254787245825502e-184", 0x1FE0F51BF17FD375u, 0x00000000u},
-            {"-1.0790205420931879e-276", 0x86A3209CA6233255u, 0x80000000u},
-            {"-1079020542093188e-291", 0x86A3209CA6233256u, 0x80000000u},
-            {"-1079020542093187947e-294", 0x86A3209CA6233255u, 0x80000000u},
-            {"0.1079020542093187948e-275", 0x06A3209CA6233256u, 0x00000000u},
-            {"0.1079020542093187947e-275", 0x06A3209CA6233255u, 0x00000000u},
-            {"1.0790205420931879471e-276", 0x06A3209CA6233256u, 0x00000000u},
-            {"1.07902054209318794701e-276", 0x06A3209CA6233255u, 0x00000000u},
-            {"-107902054209318794702e-296", 0x86A3209CA6233256u, 0x80000000u},
-            {"107902054209318794701153285302e-305", 0x06A3209CA6233255u, 0x00000000u},
-            {"-0.107902054209318794701153285303e-275", 0x86A3209CA6233256u, 0x80000000u},
-            {"58530471071351308e-228", 0x1413B446E6A16A3Bu, 0x00000000u},
-            {"-0.58530471071351309e-211", 0x9413B446E6A16A3Cu, 0x80000000u},
-            {"0.5853047107135130893e-211", 0x1413B446E6A16A3Bu, 0x00000000u},
-            {"-5.853047107135130894e-212", 0x9413B446E6A16A3Cu, 0x80000000u},
-            {"5.853047107135130893e-212", 0x1413B446E6A16A3Bu, 0x00000000u},
-            {"58530471071351308931e-231", 0x1413B446E6A16A3Cu, 0x00000000u},
-            {"-585304710713513089304e-232", 0x9413B446E6A16A3Bu, 0x80000000u},
-            {"0.585304710713513089305e-211", 0x1413B446E6A16A3Cu, 0x00000000u},
-            {"-0.585304710713513089304248824438e-211", 0x9413B446E6A16A3Bu, 0x80000000u},
-            {"5.85304710713513089304248824439e-212", 0x1413B446E6A16A3Cu, 0x00000000u},
-            {"0.19334214893983531e-78", 0x2F96ECBF1CFB10F6u, 0x00000000u},
-            {"1.9334214893983532e-79", 0x2F96ECBF1CFB10F7u, 0x00000000u},
-            {"1.933421489398353102e-79", 0x2F96ECBF1CFB10F6u, 0x00000000u},
-            {"1933421489398353103e-97", 0x2F96ECBF1CFB10F7u, 0x00000000u},
-            {"19334214893983531023e-98", 0x2F96ECBF1CFB10F6u, 0x00000000u},
-            {"0.19334214893983531024e-78", 0x2F96ECBF1CFB10F7u, 0x00000000u},
-            {"0.193342148939835310231e-78", 0x2F96ECBF1CFB10F6u, 0x00000000u},
-            {"1.93342148939835310232e-79", 0x2F96ECBF1CFB10F7u, 0x00000000u},
-            {"-1.93342148939835310231359014704e-79", 0xAF96ECBF1CFB10F6u, 0x80000000u},
-            {"193342148939835310231359014705e-108", 0x2F96ECBF1CFB10F7u, 0x00000000u},
-            {"2.9873358928024455e227", 0x6F2938807814E8A2u, 0x7F800000u},
-            {"29873358928024456e211", 0x6F2938807814E8A3u, 0x7F800000u},
-            {"298733589280244551e210", 0x6F2938807814E8A2u, 0x7F800000u},
-            {"0.2987335892802445511E+228", 0x6F2938807814E8A3u, 0x7F800000u},
-            {"0.29873358928024455109E+228", 0x6F2938807814E8A2u, 0x7F800000u},
-            {"2.987335892802445511e227", 0x6F2938807814E8A3u, 0x7F800000u},
-            {"-2.98733589280244551098e227", 0xEF2938807814E8A2u, 0xFF800000u},
-            {"-298733589280244551099e207", 0xEF2938807814E8A3u, 0xFF800000u},
-            {"298733589280244551098081559931e198", 0x6F2938807814E8A2u, 0x7F800000u},
-            {"0.298733589280244551098081559932E+228", 0x6F2938807814E8A3u, 0x7F800000u},
-            {"7.0064923216240853e-46", 0x3690000000000000u, 0x00000000u},
-            {"70064923216240854e-62", 0x3690000000000000u, 0x00000001u},
-            {"7006492321624085354e-64", 0x3690000000000000u, 0x00000000u},
-            {"-0.7006492321624085355e-45", 0xB690000000000000u, 0x80000001u},
-            {"0.70064923216240853546e-45", 0x3690000000000000u, 0x00000000u},
-            {"7.0064923216240853547e-46", 0x3690000000000000u, 0x00000001u},
-            {"7.00649232162408535461e-46", 0x3690000000000000u, 0x00000000u},
-            {"-700649232162408535462e-66", 0xB690000000000000u, 0x80000001u},
-            {"-700649232162408535461864791644e-75", 0xB690000000000000u, 0x80000000u},
-            {"0.700649232162408535461864791645e-45", 0x3690000000000000u, 0x00000001u},
-            {"21019476964872256e-61", 0x36A8000000000000u, 0x00000001u},
-            {"0.21019476964872257e-44", 0x36A8000000000000u, 0x00000002u},
-            {"-0.2101947696487225606e-44", 0xB6A8000000000000u, 0x80000001u},
-            {"-2.101947696487225607e-45", 0xB6A8000000000000u, 0x80000002u},
-            {"2.1019476964872256063e-45", 0x36A8000000000000u, 0x00000001u},
-            {"21019476964872256064e-64", 0x36A8000000000000u, 0x00000002u},
-            {"-210194769648722560638e-65", 0xB6A8000000000000u, 0x80000001u},
-            {"-0.210194769648722560639e-44", 0xB6A8000000000000u, 0x80000002u},
-            {"-0.210194769648722560638559437493e-44", 0xB6A8000000000000u, 0x80000001u},
-            {"2.10194769648722560638559437494e-45", 0x36A8000000000000u, 0x00000002u},
-            {"0.11754941406275178e-37", 0x380FFFFFA0000000u, 0x007FFFFEu},
-            {"1.1754941406275179e-38", 0x380FFFFFA0000000u, 0x007FFFFFu},
-            {"-1.175494140627517859e-38", 0xB80FFFFFA0000000u, 0x807FFFFEu},
-            {"117549414062751786e-55", 0x380FFFFFA0000000u, 0x007FFFFFu},
-            {"-11754941406275178592e-57", 0xB80FFFFFA0000000u, 0x807FFFFEu},
-            {"0.11754941406275178593e-37", 0x380FFFFFA0000000u, 0x007FFFFFu},
-            {"0.117549414062751785924e-37", 0x380FFFFFA0000000u, 0x007FFFFEu},
-            {"1.17549414062751785925e-38", 0x380FFFFFA0000000u, 0x007FFFFFu},
-            {"-1.17549414062751785924617589866e-38", 0xB80FFFFFA0000000u, 0x807FFFFEu},
-            {"117549414062751785924617589867e-67", 0x380FFFFFA0000000u, 0x007FFFFFu},
-            {"1.1754942807573642e-38", 0x380FFFFFDFFFFFFFu, 0x007FFFFFu},
-            {"11754942807573643e-54", 0x380FFFFFE0000000u, 0x00800000u},
-            {"1175494280757364291e-56", 0x380FFFFFE0000000u, 0x007FFFFFu},
-            {"0.1175494280757364292e-37", 0x380FFFFFE0000000u, 0x00800000u},
-            {"0.11754942807573642917e-37", 0x380FFFFFE0000000u, 0x007FFFFFu},
-            {"-1.1754942807573642918e-38", 0xB80FFFFFE0000000u, 0x80800000u},
-            {"-1.17549428075736429172e-38", 0xB80FFFFFE0000000u, 0x807FFFFFu},
-            {"-117549428075736429173e-58", 0xB80FFFFFE0000000u, 0x80800000u},
-            {"117549428075736429172788299103e-67", 0x380FFFFFE0000000u, 0x007FFFFFu},
-            {"0.117549428075736429172788299104e-37", 0x380FFFFFE0000000u, 0x00800000u},
-            {"11754944208872107e-54", 0x3810000010000000u, 0x00800000u},
-            {"-0.11754944208872108e-37", 0xB810000010000000u, 0x80800001u},
-            {"0.1175494420887210724e-37", 0x3810000010000000u, 0x00800000u},
-            {"1.175494420887210725e-38", 0x3810000010000000u, 0x00800001u},
-            {"1.1754944208872107242e-38", 0x3810000010000000u, 0x00800000u},
-            {"-11754944208872107243e-57", 0xB810000010000000u, 0x80800001u},
-            {"-11754944208872107242e-57", 0xB810000010000000u, 0x80800000u},
-            {"0.117549442088721072421e-37", 0x3810000010000000u, 0x00800001u},
-            {"0.11754944208872107242095900834e-37", 0x3810000010000000u, 0x00800000u},
-            {"-1.17549442088721072420959008341e-38", 0xB810000010000000u, 0x80800001u},
-            {"340282336497324057985868971510891282432", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"-3.40282336497324057985868971510891282433e38", 0xC7EFFFFFD0000000u, 0xFF7FFFFFu},
-            {"340282336497324057985868971510891282431e0", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"340282336497324057985868971510891282432.01", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"3.40282336497324057985868971510891282432000000000000000000001e38", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"340282336497324057985868971510891282432000000000000000000000000000000e-30", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"340282336497324050000000000000000000000", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"3.4028233649732406e38", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"3.402823364973240579e38", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"340282336497324058e21", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"34028233649732405798e19", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"340282336497324057990000000000000000000", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"340282336497324057985000000000000000000", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"3.40282336497324057986e38", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"3.4028233649732405798586897151e38", 0x47EFFFFFD0000000u, 0x7F7FFFFEu},
-            {"340282336497324057985868971511e9", 0x47EFFFFFD0000000u, 0x7F7FFFFFu},
-            {"3.40282356779733661637539395458142568448e38", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"-340282356779733661637539395458142568449e0", 0xC7EFFFFFF0000000u, 0xFF800000u},
-            {"340282356779733661637539395458142568447", 0x47EFFFFFF0000000u, 0x7F7FFFFFu},
-            {"3.4028235677973366163753939545814256844801e38", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"340282356779733661637539395458142568448000000000000000000001e-21", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"340282356779733661637539395458142568448.000000000000000000000000000000", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"3.4028235677973366e38", 0x47EFFFFFF0000000u, 0x7F7FFFFFu},
-            {"-34028235677973367e22", 0xC7EFFFFFF0000000u, 0xFF800000u},
-            {"3402823567797336616e20", 0x47EFFFFFF0000000u, 0x7F7FFFFFu},
-            {"340282356779733661700000000000000000000", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"340282356779733661630000000000000000000", 0x47EFFFFFF0000000u, 0x7F7FFFFFu},
-            {"3.4028235677973366164e38", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"3.40282356779733661637e38", 0x47EFFFFFF0000000u, 0x7F7FFFFFu},
-            {"340282356779733661638e18", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"-340282356779733661637539395458e9", 0xC7EFFFFFF0000000u, 0xFF7FFFFFu},
-            {"340282356779733661637539395459000000000", 0x47EFFFFFF0000000u, 0x7F800000u},
-            {"-1000000059604644775390625e-24", 0xBFF0000010000000u, 0xBF800000u},
-            {"-1.000000059604644775390626", 0xBFF0000010000000u, 0xBF800001u},
-            {"-1.000000059604644775390624e0", 0xBFF0000010000000u, 0xBF800000u},
-            {"100000005960464477539062501e-26", 0x3FF0000010000000u, 0x3F800001u},
-            {"1.000000059604644775390625000000000000000000001", 0x3FF0000010000000u, 0x3F800001u},
-            {"1.000000059604644775390625000000000000000000000000000000e0", 0x3FF0000010000000u, 0x3F800000u},
-            {"-10000000596046447e-16", 0xBFF0000010000000u, 0xBF800000u},
-            {"1.0000000596046448", 0x3FF0000010000000u, 0x3F800001u},
-            {"1.000000059604644775", 0x3FF0000010000000u, 0x3F800000u},
-            {"-1.000000059604644776e0", 0xBFF0000010000000u, 0xBF800001u},
-            {"-1.0000000596046447753e0", 0xBFF0000010000000u, 0xBF800000u},
-            {"10000000596046447754e-19", 0x3FF0000010000000u, 0x3F800001u},
-            {"100000005960464477539e-20", 0x3FF0000010000000u, 0x3F800000u},
-            {"-1.0000000596046447754", 0xBFF0000010000000u, 0xBF800001u},
-            {"0.9999999701976776123046875", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"9.999999701976776123046876e-1", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"9999999701976776123046874e-25", 0x3FEFFFFFF0000000u, 0x3F7FFFFFu},
-            {"0.999999970197677612304687501", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"-9.999999701976776123046875000000000000000000001e-1", 0xBFEFFFFFF0000000u, 0xBF800000u},
-            {"-9999999701976776123046875000000000000000000000000000000e-55", 0xBFEFFFFFF0000000u, 0xBF800000u},
-            {"0.99999997019767761", 0x3FEFFFFFF0000000u, 0x3F7FFFFFu},
-            {"-9.9999997019767762e-1", 0xBFEFFFFFF0000000u, 0xBF800000u},
-            {"-9.999999701976776123e-1", 0xBFEFFFFFF0000000u, 0xBF7FFFFFu},
-            {"9999999701976776124e-19", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"9999999701976776123e-19", 0x3FEFFFFFF0000000u, 0x3F7FFFFFu},
-            {"0.99999997019767761231", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"-0.999999970197677612304", 0xBFEFFFFFF0000000u, 0xBF7FFFFFu},
-            {"9.99999970197677612305e-1", 0x3FEFFFFFF0000000u, 0x3F800000u},
-            {"-1.6777217e7", 0xC170000010000000u, 0xCB800000u},
-            {"16777218e0", 0x4170000020000000u, 0x4B800001u},
-            {"16777216", 0x4170000000000000u, 0x4B800000u},
-            {"-1.677721701e7", 0xC17000001028F5C3u, 0xCB800001u},
-            {"-16777217000000000000000000001e-21", 0xC170000010000000u, 0xCB800001u},
-            {"16777217.000000000000000000000000000000", 0x4170000010000000u, 0x4B800000u},
-            {"167772155e-1", 0x416FFFFFF0000000u, 0x4B800000u},
-            {"16777215.6", 0x416FFFFFF3333333u, 0x4B800000u},
-            {"1.67772154e7", 0x416FFFFFECCCCCCDu, 0x4B7FFFFFu},
-            {"16777215501e-3", 0x416FFFFFF0083127u, 0x4B800000u},
-            {"-16777215.5000000000000000000001", 0xC16FFFFFF0000000u, 0xCB800000u},
-            {"-1.67772155000000000000000000000000000000e7", 0xC16FFFFFF0000000u, 0xCB800000u},
-            {"0.1000000052154064178466796875", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"1.000000052154064178466796876e-1", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"-1000000052154064178466796874e-28", 0xBFB99999B0000000u, 0xBDCCCCCDu},
-            {"0.100000005215406417846679687501", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"1.000000052154064178466796875000000000000000000001e-1", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"-1000000052154064178466796875000000000000000000000000000000e-58", 0xBFB99999B0000000u, 0xBDCCCCCEu},
-            {"-0.10000000521540641", 0xBFB99999AFFFFFFFu, 0xBDCCCCCDu},
-            {"-1.0000000521540642e-1", 0xBFB99999B0000000u, 0xBDCCCCCEu},
-            {"1.000000052154064178e-1", 0x3FB99999B0000000u, 0x3DCCCCCDu},
-            {"-1000000052154064179e-19", 0xBFB99999B0000000u, 0xBDCCCCCEu},
-            {"10000000521540641784e-20", 0x3FB99999B0000000u, 0x3DCCCCCDu},
-            {"0.10000000521540641785", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"0.100000005215406417846", 0x3FB99999B0000000u, 0x3DCCCCCDu},
-            {"1.00000005215406417847e-1", 0x3FB99999B0000000u, 0x3DCCCCCEu},
-            {"5.429001220703125e3", 0x40B5350050000000u, 0x45A9A802u},
-            {"-5429001220703126e-12", 0xC0B5350050000001u, 0xC5A9A803u},
-            {"-5429.001220703124", 0xC0B535004FFFFFFFu, 0xC5A9A802u},
-            {"5.42900122070312501e3", 0x40B5350050000000u, 0x45A9A803u},
-            {"5429001220703125000000000000000000001e-33", 0x40B5350050000000u, 0x45A9A803u},
-            {"-5429.001220703125000000000000000000000000000000", 0xC0B5350050000000u, 0xC5A9A802u},
-            {"503719056e0", 0x41BE062490000000u, 0x4DF03124u},
-            {"503719057", 0x41BE062491000000u, 0x4DF03125u},
-            {"5.03719055e8", 0x41BE06248F000000u, 0x4DF03124u},
-            {"50371905601e-2", 0x41BE062490028F5Cu, 0x4DF03125u},
-            {"503719056.000000000000000000001", 0x41BE062490000000u, 0x4DF03125u},
-            {"5.03719056000000000000000000000000000000e8", 0x41BE062490000000u, 0x4DF03124u},
-            {"-92331620", 0xC196037990000000u, 0xCCB01BCCu},
-            {"9.233163e7", 0x41960379B8000000u, 0x4CB01BCEu},
-            {"9233161e1", 0x4196037968000000u, 0x4CB01BCBu},
-            {"92331620.1", 0x4196037990666666u, 0x4CB01BCDu},
-            {"9.233162000000000000000000001e7", 0x4196037990000000u, 0x4CB01BCDu},
-            {"9233162000000000000000000000000000000e-29", 0x4196037990000000u, 0x4CB01BCCu},
-            {"3.002458625e6", 0x4146E82D50000000u, 0x4A37416Au},
-            {"3002458626e-3", 0x4146E82D5020C49Cu, 0x4A37416Bu},
-            {"3002458.624", 0x4146E82D4FDF3B64u, 0x4A37416Au},
-            {"-3.00245862501e6", 0xC146E82D500053E3u, 0xCA37416Bu},
-            {"3002458625000000000000000000001e-24", 0x4146E82D50000000u, 0x4A37416Bu},
-            {"3002458.625000000000000000000000000000000", 0x4146E82D50000000u, 0x4A37416Au},
-            {"-1095485584696182596504479582065262592e1", 0xC7A07BA830000000u, 0xFD03DD42u},
-            {"10954855846961825965044795820652625930", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"1.095485584696182596504479582065262591e37", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"109548558469618259650447958206526259201e-1", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"-10954855846961825965044795820652625920.00000000000000000001", 0xC7A07BA830000000u, 0xFD03DD42u},
-            {"1.095485584696182596504479582065262592000000000000000000000000000000e37", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"10954855846961825e21", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"10954855846961826000000000000000000000", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"10954855846961825960000000000000000000", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"1.095485584696182597e37", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"1.0954855846961825965e37", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"-10954855846961825966e18", 0xC7A07BA830000000u, 0xFD03DD42u},
-            {"10954855846961825965e18", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"10954855846961825965100000000000000000", 0x47A07BA830000000u, 0x7D03DD42u},
-            {"10954855846961825965044795820600000000", 0x47A07BA830000000u, 0x7D03DD41u},
-            {"-1.09548558469618259650447958207e37", 0xC7A07BA830000000u, 0xFD03DD42u},
-            {"1.6449216019182103706535606608388384863861375606575165875256061553955078126e-21", 0x3B9F125A50000000u, 0x1CF892D3u},
-            {"-16449216019182103706535606608388384863861375606575165875256061553955078124e-94", 0xBB9F125A50000000u, 0x9CF892D2u},
-            {"-0.0000000000000000000016449216019182103", 0xBB9F125A50000000u, 0x9CF892D2u},
-            {"-1.6449216019182104e-21", 0xBB9F125A50000000u, 0x9CF892D3u},
-            {"-1.64492160191821037e-21", 0xBB9F125A50000000u, 0x9CF892D2u},
-            {"-1644921601918210371e-39", 0xBB9F125A50000000u, 0x9CF892D3u},
-            {"-16449216019182103706e-40", 0xBB9F125A50000000u, 0x9CF892D2u},
-            {"0.0000000000000000000016449216019182103707", 0x3B9F125A50000000u, 0x1CF892D3u},
-            {"0.00000000000000000000164492160191821037065", 0x3B9F125A50000000u, 0x1CF892D2u},
-            {"1.64492160191821037066e-21", 0x3B9F125A50000000u, 0x1CF892D3u},
-            {"1.64492160191821037065356066083e-21", 0x3B9F125A50000000u, 0x1CF892D2u},
-            {"164492160191821037065356066084e-50", 0x3B9F125A50000000u, 0x1CF892D3u},
-            {"6.565061509609222412109375e-1", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"6565061509609222412109376e-25", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"0.6565061509609222412109374", 0x3FE5021930000000u, 0x3F2810C9u},
-            {"6.56506150960922241210937501e-1", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"6565061509609222412109375000000000000000000001e-46", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"-0.6565061509609222412109375000000000000000000000000000000", 0xBFE5021930000000u, 0xBF2810CAu},
-            {"6.5650615096092224e-1", 0x3FE5021930000000u, 0x3F2810C9u},
-            {"-65650615096092225e-17", 0xBFE5021930000000u, 0xBF2810CAu},
-            {"6565061509609222412e-19", 0x3FE5021930000000u, 0x3F2810C9u},
-            {"0.6565061509609222413", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"0.65650615096092224121", 0x3FE5021930000000u, 0x3F2810C9u},
-            {"6.5650615096092224122e-1", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"-6.5650615096092224121e-1", 0xBFE5021930000000u, 0xBF2810C9u},
-            {"656506150960922241211e-21", 0x3FE5021930000000u, 0x3F2810CAu},
-            {"18014627239033005156980393746124491372029297053813934326171875e-77", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"0.00000000000000018014627239033005156980393746124491372029297053813934326171876", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"-1.8014627239033005156980393746124491372029297053813934326171874e-16", 0xBCA9F63970000000u, 0xA54FB1CBu},
-            {"1801462723903300515698039374612449137202929705381393432617187501e-79", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"18014627239033005e-32", 0x3CA9F63970000000u, 0x254FB1CBu},
-            {"0.00000000000000018014627239033006", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"0.0000000000000001801462723903300515", 0x3CA9F63970000000u, 0x254FB1CBu},
-            {"-1.801462723903300516e-16", 0xBCA9F63970000000u, 0xA54FB1CCu},
-            {"-1.8014627239033005156e-16", 0xBCA9F63970000000u, 0xA54FB1CBu},
-            {"18014627239033005157e-35", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"180146272390330051569e-36", 0x3CA9F63970000000u, 0x254FB1CBu},
-            {"-0.00000000000000018014627239033005157", 0xBCA9F63970000000u, 0xA54FB1CCu},
-            {"0.000000000000000180146272390330051569803937461", 0x3CA9F63970000000u, 0x254FB1CBu},
-            {"1.80146272390330051569803937462e-16", 0x3CA9F63970000000u, 0x254FB1CCu},
-            {"0.05534819327294826507568359375", 0x3FAC569930000000u, 0x3D62B4CAu},
-            {"-5.534819327294826507568359376e-2", 0xBFAC569930000000u, 0xBD62B4CAu},
-            {"5534819327294826507568359374e-29", 0x3FAC569930000000u, 0x3D62B4C9u},
-            {"-0.0553481932729482650756835937501", 0xBFAC569930000000u, 0xBD62B4CAu},
-            {"5.534819327294826507568359375000000000000000000001e-2", 0x3FAC569930000000u, 0x3D62B4CAu},
-            {"5534819327294826507568359375000000000000000000000000000000e-59", 0x3FAC569930000000u, 0x3D62B4CAu},
-            {"0.055348193272948265", 0x3FAC569930000000u, 0x3D62B4C9u},
-            {"5.5348193272948266e-2", 0x3FAC569930000000u, 0x3D62B4CAu},
-            {"5.534819327294826507e-2", 0x3FAC569930000000u, 0x3D62B4C9u},
-            {"5534819327294826508e-20", 0x3FAC569930000000u, 0x3D62B4CAu},
-            {"55348193272948265075e-21", 0x3FAC569930000000u, 0x3D62B4C9u},
-            {"-0.055348193272948265076", 0xBFAC569930000000u, 0xBD62B4CAu},
-            {"0.0553481932729482650756", 0x3FAC569930000000u, 0x3D62B4C9u},
-            {"-5.53481932729482650757e-2", 0xBFAC569930000000u, 0xBD62B4CAu},
-            {"5.179692133247783258005389047985340416e36", 0x478F2C9450000000u, 0x7C7964A2u},
-            {"5179692133247783258005389047985340417e0", 0x478F2C9450000000u, 0x7C7964A3u},
-            {"5179692133247783258005389047985340415", 0x478F2C9450000000u, 0x7C7964A2u},
-            {"-5.17969213324778325800538904798534041601e36", 0xC78F2C9450000000u, 0xFC7964A3u},
-            {"-5179692133247783258005389047985340416000000000000000000001e-21", 0xC78F2C9450000000u, 0xFC7964A3u},
-            {"-5179692133247783258005389047985340416.000000000000000000000000000000", 0xC78F2C9450000000u, 0xFC7964A2u},
-            {"5.1796921332477832e36", 0x478F2C9450000000u, 0x7C7964A2u},
-            {"51796921332477833e20", 0x478F2C9450000000u, 0x7C7964A3u},
-            {"-5179692133247783258e18", 0xC78F2C9450000000u, 0xFC7964A2u},
-            {"5179692133247783259000000000000000000", 0x478F2C9450000000u, 0x7C7964A3u},
-            {"5179692133247783258000000000000000000", 0x478F2C9450000000u, 0x7C7964A2u},
-            {"5.1796921332477832581e36", 0x478F2C9450000000u, 0x7C7964A3u},
-            {"-5.179692133247783258e36", 0xC78F2C9450000000u, 0xFC7964A2u},
-            {"-517969213324778325801e16", 0xC78F2C9450000000u, 0xFC7964A3u},
-            {"517969213324778325800538904798e7", 0x478F2C9450000000u, 0x7C7964A2u},
-            {"5179692133247783258005389047990000000", 0x478F2C9450000000u, 0x7C7964A3u},
-            {
-                "0.22250738585072011360574097967091319759348195463516456480234261097248222220210769455165295239081350"
-                "8791414915891303962110687008643869459464552765720740782062174337998814106326732925355228688137214901"
-                "2981122451451889849057222307285255133155755015914397476397983411801999323962548289017107081850690630"
-                "6666559949382757725720157630626906633326475653000092458883164330377797918696120494973903778297049050"
-                "5108060994073026293712895895000358379996720725430436028407889577179615094551674824347103070260914462"
-                "1572289880258182545180325707018860872113128079512233426288368622321503775666622503982534335974568884"
-                "4239002654981983854879482922068947216898310996983658468140228542433306603398508864458040010349339704"
-                "2756718644338377048603786162277173854562306587467901408672332763671875e-307", 0x0010000000000000u, 0x00000000u
-            },
-            {
-                "2.22507385850720113605740979670913197593481954635164564802342610972482222202107694551652952390813508"
-                "7914149158913039621106870086438694594645527657207407820621743379988141063267329253552286881372149012"
-                "9811224514518898490572223072852551331557550159143974763979834118019993239625482890171070818506906306"
-                "6665599493827577257201576306269066333264756530000924588831643303777979186961204949739037782970490505"
-                "1080609940730262937128958950003583799967207254304360284078895771796150945516748243471030702609144621"
-                "5722898802581825451803257070188608721131280795122334262883686223215037756666225039825343359745688844"
-                "2390026549819838548794829220689472168983109969836584681402285424333066033985088644580400103493397042"
-                "756718644338377048603786162277173854562306587467901408672332763671875000000000000000000001e-308", 0x0010000000000000u, 0x00000000u
-            },
-            {
-                "0.11754942807573642917278829910357665133228589927589904276829631184250030649651730385585324256680905"
-                "8189392089843750000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "00000000000000000000000000000000000000000000000000000000000000000e-37", 0x380FFFFFE0000000u, 0x00800000u
-            },
-            {
-                "1175494280757364291727882991035766513322858992758990427682963118425003064965173038558532425668090581"
-                "8939208984375000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
-                "00000000000001e-751", 0x380FFFFFE0000000u, 0x00800000u
-            },
-            {"0", 0x0000000000000000u, 0x00000000u},
-            {"-0", 0x8000000000000000u, 0x80000000u},
-            {"0.0", 0x0000000000000000u, 0x00000000u},
-            {"-0.0", 0x8000000000000000u, 0x80000000u},
-            {"0e999999999999999999999", 0x0000000000000000u, 0x00000000u},
-            {"-0.000e-99999", 0x8000000000000000u, 0x80000000u},
-            {"1e-400", 0x0000000000000000u, 0x00000000u},
-            {"-1e-400", 0x8000000000000000u, 0x80000000u},
-            {"1e400", 0x7FF0000000000000u, 0x7F800000u},
-            {"-1e400", 0xFFF0000000000000u, 0xFF800000u},
-            {"1e-50", 0x358DEE7A4AD4B81Fu, 0x00000000u},
-            {"-1e-50", 0xB58DEE7A4AD4B81Fu, 0x80000000u},
-            {"1e39", 0x48078287F49C4A1Du, 0x7F800000u},
-            {"-1e39", 0xC8078287F49C4A1Du, 0xFF800000u},
-            {"1e99999999999999999999999999", 0x7FF0000000000000u, 0x7F800000u},
-            {"1e-99999999999999999999999999", 0x0000000000000000u, 0x00000000u},
-            {"1e0000000000000000000000000000000000000000308", 0x7FE1CCF385EBC8A0u, 0x7F800000u},
-            {"123456789012345678901234567890e-30", 0x3FBF9ADD3746F65Fu, 0x3DFCD6EAu},
-            {"18446744073709551615", 0x43F0000000000000u, 0x5F800000u},
-            {"18446744073709551616", 0x43F0000000000000u, 0x5F800000u},
-            {"-9223372036854775808", 0xC3E0000000000000u, 0xDF000000u},
-            {"-9223372036854775809", 0xC3E0000000000000u, 0xDF000000u},
-        }
-    };
-    return table;
-}
-
-} // namespace float_hard_cases

tests/src/fuzzer-parse_bjdata.cpp

@@ -45,6 +45,10 @@ 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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -59,6 +63,8 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // value-stable comparison for the round-trip checks below; see the note
@@ -71,11 +77,15 @@ 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)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bjdata(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -109,6 +119,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -117,6 +128,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bon8.cpp

@@ -19,6 +19,10 @@ It also checks that reading the data from a stream, which reads strings byte by
 byte, gives the same value or error as reading it from contiguous memory, which
 copies strings in bulk.
 
+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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -33,6 +37,8 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 namespace
@@ -56,6 +62,9 @@ std::string read_bon8(InputType&& input)
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     // contiguous and stream input must be read alike
     {
         std::istringstream stream(std::string(reinterpret_cast<const char*>(data), size));
@@ -67,6 +76,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bon8(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -88,6 +98,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -96,6 +107,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_bson.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_bson(vec)
 - assert(j1 == j2)
 
+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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bson(vec1);
+        assert(recovered_without_errors);
 
         if (j1.is_discarded())
         {
@@ -65,6 +75,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -73,6 +84,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors can occur during parsing, too
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_cbor.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_cbor(vec)
 - assert(j1 == j2)
 
+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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_cbor(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -60,6 +70,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -68,6 +79,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors can occur during parsing, too
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_json.cpp

@@ -16,6 +16,10 @@ array data, it performs the following steps:
 - s2 = serialize(j2)
 - assert(s1 == s2)
 
+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.
 */
@@ -23,6 +27,7 @@ drivers.
 #include <cassert>
 #include <iostream>
 #include <sstream>
+#include <string>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away
@@ -30,11 +35,20 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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));
+    }
+
     try
     {
         // step 1: parse input

tests/src/fuzzer-parse_msgpack.cpp

@@ -15,6 +15,10 @@ array data, it performs the following steps:
 - j2 = from_msgpack(vec)
 - assert(j1 == j2)
 
+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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -29,16 +33,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_msgpack(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -60,6 +70,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -68,6 +79,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

tests/src/fuzzer-parse_ubjson.cpp

@@ -24,6 +24,10 @@ 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).
+
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
@@ -38,16 +42,22 @@ drivers.
     #error "the fuzzer drivers must be built without NDEBUG"
 #endif
 
+#include "fuzzer-recovering_checker.hpp"
+
 using json = nlohmann::json;
 
 // see http://llvm.org/docs/LibFuzzer.html
 extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
+    // step 0: 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;
+
     try
     {
         // step 1: parse input
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_ubjson(vec1);
+        assert(recovered_without_errors);
 
         try
         {
@@ -79,6 +89,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::parse_error&)
     {
         // parse errors are ok, because input may be random bytes
+        assert(!recovered_without_errors);
     }
     catch (const json::type_error&)
     {
@@ -87,6 +98,7 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
     catch (const json::out_of_range&)
     {
         // out of range errors may happen if provided sizes are excessive
+        assert(!recovered_without_errors);
     }
 
     // return 0 - non-zero return values are reserved for future use

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/unit-alt-string.cpp

@@ -352,41 +352,6 @@ TEST_CASE("alternative string type")
         CHECK(j2.flatten().unflatten() == j2);
     }
 
-    SECTION("contains(json_pointer)")
-    {
-        // contains(json_pointer) must compile and work with a string_t that has
-        // no c_str() and no comparison with const char* (see #5666)
-        auto j = alt_json::parse(R"({"foo": ["bar", "baz"]})");
-
-        // present: object key and array indices
-        CHECK(j.contains(alt_json::json_pointer("/foo")));
-        CHECK(j.contains(alt_json::json_pointer("/foo/0")));
-        CHECK(j.contains(alt_json::json_pointer("/foo/1")));
-
-        // missing: absent object key and out-of-range array index
-        CHECK_FALSE(j.contains(alt_json::json_pointer("/bar")));
-        CHECK_FALSE(j.contains(alt_json::json_pointer("/foo/2")));
-
-        // "-" always fails the range check
-        CHECK_FALSE(j.contains(alt_json::json_pointer("/foo/-")));
-
-        // an array index must not have a leading zero
-        CHECK_FALSE(j.contains(alt_json::json_pointer("/foo/01")));
-
-        // a reference token that is not a number
-        CHECK_FALSE(j.contains(alt_json::json_pointer("/foo/bar")));
-    }
-
-    SECTION("operator/(std::size_t)")
-    {
-        // json_pointer::operator/=(std::size_t) must compile without string_t
-        // being constructible from std::string (see #5666)
-        auto j = alt_json::parse(R"({"foo": ["bar", "baz"]})");
-
-        CHECK(j.at(alt_json::json_pointer("/foo") / std::size_t(0)) == j["foo"][0]);
-        CHECK(j.at(alt_json::json_pointer("/foo") / std::size_t(1)) == j["foo"][1]);
-    }
-
     SECTION("patch")
     {
         alt_json const patch1 = alt_json::parse(R"([{ "op": "add", "path": "/a/b", "value": [ "foo", "bar" ] }])");
@@ -419,6 +384,46 @@ 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("strict enum")
     {
         // regression test for #5667: NLOHMANN_JSON_SERIALIZE_ENUM_STRICT's from_json

tests/src/unit-class_lexer.cpp

@@ -13,19 +13,15 @@
 using nlohmann::json;
 
 #include <array> // array
+#include <cfloat> // FLT_EVAL_METHOD
 #include <cstdint> // uint32_t, uint64_t
-#include <cstdio> // snprintf
 #include <cstdlib> // strtod
 #include <cstring> // memcpy
-#include <map> // map
-#include <random> // mt19937
 #include <sstream> // stringstream
 #include <string> // string
 #include <utility> // pair
 #include <vector> // vector
 
-#include "float_hard_cases.hpp"
-
 namespace
 {
 // shortcut to scan a string literal
@@ -261,7 +257,7 @@ TEST_CASE("lexer number fast path")
             "123456789012345678901234567890",  // huge -> float
             "0.30000000000000004", "2.2250738585072014e-308", "1e308",
             // high-precision / wide-exponent values that exercise the
-            // Eisel-Lemire path beyond the Clinger subset
+            // std::from_chars (Eisel-Lemire) path beyond the Clinger subset
             "1.7976931348623157e308", "1.2345678901234567e-250",
             "9007199254740993", "5e-324", "1e-320"
         };
@@ -283,18 +279,20 @@ TEST_CASE("lexer number fast path")
         }
     }
 
-    SECTION("significant digits around Clinger's fast path")
+    SECTION("significant-digit gate for the Clinger fast path")
     {
-        // Clinger's fast path needs a significand of at most 2^53, which
-        // tokens with 17 or more significant digits exceed. The conversion
-        // splits the token at the positions the scanners recorded, so leading
-        // zeros must not count as digits - "0.1234567890123456" has 16
-        // significant digits, not 17 - and both scanners must agree.
+        // Clinger's fast path needs a significand below 2^53, so it cannot
+        // succeed once the mantissa has 17 or more significant digits (the
+        // significand would be at least 10^16). The lexer skips the attempt
+        // there. That is only allowed to save work: every value must still come
+        // out bit-exactly, and both scanners must agree. In particular the gate
+        // must not fire for tokens whose leading zeros merely look like extra
+        // digits - "0.1234567890123456" has 16 significant digits, not 17.
         const std::vector<std::string> numbers =
         {
             "1234567890123456",                  // 16 significant digits
-            "12345678901234567",                 // 17
-            "123456789012345678",                // 18
+            "12345678901234567",                 // 17 -> attempt skipped
+            "123456789012345678",                // 18 -> attempt skipped
             "0.1234567890123456",                // 16: the leading "0" is not significant
             "0.12345678901234567",               // 17
             "0.00000000000000001",               // 1, in a long token
@@ -665,323 +663,46 @@ TEST_CASE("lexer string fast path")
     }
 }
 
-TEST_CASE("lexer escape fast path")
+TEST_CASE("parse_float_fast declines what it cannot convert exactly")
 {
-    // json::accept() never throws, so this section stays covered without
-    // exceptions; it pins which of the cases below are valid/invalid and
-    // checks the contiguous and streaming paths agree on that classification.
-    SECTION("accept() parity")
+    // The lexer only hands well-formed numbers to parse_float_fast, so the
+    // malformed ones below can only be passed to it directly. Declining is
+    // always safe: the caller then falls back to a slower, exact conversion.
+    const auto fast = [](const std::string & s, double & out)
     {
-        const std::vector<std::pair<std::string, bool>> cases =
-        {
-            {"\\u0041", true}, {"\\u00e4", true}, {"\\u00E4", true},
-            {"\\uD83D\\uDE00", true},
-            {"\\u12", false}, {"\\u12G4", false}, {"\\uXYZW", false},
-            {"\\uD800", false}, {"\\uD800A", false}, {"\\uD800\\u0041", false},
-            {"\\uDC00", false}, {"\\u", false}
-        };
-
-        for (const auto& c : cases)
-        {
-            for (const std::size_t offset :
-                    {
-                        std::size_t{0}, std::size_t{9}
-                    })
-            {
-                const std::string doc = "[\"" + std::string(offset, 'a') + c.first + "\"]";
-                CAPTURE(doc);
-                CHECK(json::accept(doc) == c.second);
-                std::stringstream ss(doc);
-                CHECK(json::accept(ss) == c.second);
-            }
-        }
-    }
-
-#if !defined(JSON_NOEXCEPTION)
-    // the full outcome of parsing @a doc: the parsed value, or the exact
-    // error message, so a mismatch in either is caught
-    const auto outcome = [](const std::string & doc, bool streaming) -> std::string
-    {
-        try
-        {
-            if (streaming)
-            {
-                std::stringstream ss(doc);
-                const json j = json::parse(ss);
-                return j.dump();
-            }
-            const json j = json::parse(doc);
-            return j.dump();
-        }
-        catch (const json::exception& e)
-        {
-            return {e.what()};
-        }
+        return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), out);
     };
+    double out = 0;
 
-    SECTION("contiguous vs streaming parity")
-    {
-        const std::vector<std::string> escapes =
-        {
-            "\\u0041",             // "A"
-            "\\u00e4",             // "ä" (lowercase hex)
-            "\\u00E4",             // "ä" (uppercase hex)
-            "\\uD83D\\uDE00",      // valid surrogate pair (an emoji)
-            "\\u12",               // truncated: only 2 hex digits before the closing quote
-            "\\u12G4",             // invalid hex digit at the 3rd position
-            "\\uXYZW",             // all 4 bytes invalid
-            "\\uD800",             // lone high surrogate, string ends right after
-            "\\uD800A",            // high surrogate not followed by another \u escape
-            "\\uD800\\u0041",      // high surrogate followed by \u, but not a low surrogate
-            "\\uDC00",             // lone low surrogate
-            "\\u",                 // '\u' with nothing after (closing quote right away)
-        };
-
-        // once at the start of the string and once past the first 8-byte SWAR
-        // word of the outer string_bulk_run, so the escape is reached both
-        // right after the opening quote and mid-run
-        for (const auto& escape : escapes)
-        {
-            for (const std::size_t offset :
-                    {
-                        std::size_t{0}, std::size_t{9}
-                    })
-            {
-                const std::string doc = "[\"" + std::string(offset, 'a') + escape + "\"]";
-                CAPTURE(doc);
-                CHECK(outcome(doc, false) == outcome(doc, true));
-            }
-
-            // the escape is the last thing before end of input: no closing
-            // quote at all
-            const std::string truncated_doc = "[\"" + escape;
-            CAPTURE(truncated_doc);
-            CHECK(outcome(truncated_doc, false) == outcome(truncated_doc, true));
-        }
-    }
-
-    SECTION("truncated \\u escape at every distance from the end of input")
-    {
-        // ia.bulk_remaining() must correctly report fewer than 4 bytes for
-        // every possible count of trailing hex-looking bytes (0, 1, 2, or 3)
-        // before end of input, so the fast path declines and the byte path
-        // alone reports the "must be followed by 4 hex digits" error, at the
-        // same position, in every case
-        for (const std::string& tail :
-                {
-                    std::string{}, std::string("1"), std::string("12"), std::string("123")
-                })
-        {
-            const std::string doc = "[\"\\u" + tail;
-            CAPTURE(doc);
-            CHECK(outcome(doc, false) == outcome(doc, true));
-            CHECK(outcome(doc, false).find("must be followed by 4 hex digits") != std::string::npos);
-        }
-    }
-
-    SECTION("invalid hex digit at every position of the 4")
-    {
-        // the fast path must decline for *any* invalid byte among the 4, not
-        // just the first, and the byte path must then stop at exactly that
-        // position - same as it always has
-        for (std::size_t bad_pos = 0; bad_pos < 4; ++bad_pos)
-        {
-            std::string digits = "1234";
-            digits[bad_pos] = 'g'; // not a hex digit
-            const std::string doc = "[\"\\u" + digits + "\"]";
-            CAPTURE(doc);
-            CHECK(outcome(doc, false) == outcome(doc, true));
-            CHECK(outcome(doc, false).find("must be followed by 4 hex digits") != std::string::npos);
-        }
-    }
-
-    SECTION("random escapes")
-    {
-        // A seeded PRNG builds the 4 bytes following `\u` from a mix of hex
-        // digits and non-hex bytes, at varying distances from the start of
-        // the string, to compare the two scanners on many more shapes than
-        // are practical to enumerate by hand.
-        std::mt19937 gen(7654321); // NOLINT(cert-msc32-c,cert-msc51-cpp)
-        const std::string hex_alphabet = "0123456789AaBbCcDdEeFf";
-        std::uniform_int_distribution<std::size_t> pick_hex(0, hex_alphabet.size() - 1);
-        std::uniform_int_distribution<int> pick_byte(1, 255); // never NUL
-        std::uniform_int_distribution<int> pick_is_hex(0, 4); // 4-in-5 chance of a hex digit
-        std::uniform_int_distribution<std::size_t> pick_offset(0, 12);
-
-        std::vector<std::string> mismatches;
-        for (int iter = 0; iter < 3000; ++iter)
-        {
-            std::string digits;
-            for (int i = 0; i < 4; ++i)
-            {
-                if (pick_is_hex(gen) != 0)
-                {
-                    digits += hex_alphabet[pick_hex(gen)];
-                }
-                else
-                {
-                    char c = static_cast<char>(pick_byte(gen));
-                    if (c == '"' || c == '\\')
-                    {
-                        // keep the string well-formed apart from the escape
-                        // itself, so any mismatch is attributable to the \u
-                        // handling and not to an unrelated quote/escape
-                        c = 'z';
-                    }
-                    digits += c;
-                }
-            }
-            const std::string doc = "[\"" + std::string(pick_offset(gen), 'a') + "\\u" + digits + "\"]";
-            if (outcome(doc, false) != outcome(doc, true))
-            {
-                mismatches.push_back(doc);
-            }
-        }
-        CAPTURE(mismatches);
-        CHECK(mismatches.empty());
-    }
+#if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
+    // without true double precision, the fast path declines everything
+    CHECK_FALSE(fast("1.5", out));
+#else
+    CHECK(fast("1.5", out));
+    CHECK(out == 1.5);
+    CHECK(fast("+2.5e1", out));
+    CHECK(out == 25.0);
+    CHECK(fast("-25E-1", out));
+    CHECK(out == -2.5);
+    CHECK(fast("1e", out));
+    CHECK(out == 1.0);
 #endif
-}
 
-namespace
-{
-// the index of the decimal point (or npos) and of the end of the mantissa of a
-// number token, which the lexer records while scanning it
-std::pair<std::size_t, std::size_t> float_token_layout(const std::string& s)
-{
-    std::size_t dot = std::string::npos;
-    std::size_t mantissa_end = s.size();
-    for (std::size_t i = 0; i < s.size(); ++i)
-    {
-        if (s[i] == '.')
-        {
-            dot = i;
-        }
-        else if (s[i] == 'e' || s[i] == 'E')
-        {
-            mantissa_end = i;
-            break;
-        }
-    }
-    return {dot, mantissa_end};
-}
+    // not a number
+    CHECK_FALSE(fast("", out));
+    CHECK_FALSE(fast("-", out));
+    CHECK_FALSE(fast(".", out));
+    CHECK_FALSE(fast("1.2.3", out));
+    CHECK_FALSE(fast("1x", out));
+    CHECK_FALSE(fast("1e+", out));
+    CHECK_FALSE(fast("1e1x", out));
 
-template<typename FloatType>
-FloatType parse_native(const std::string& s)
-{
-    const auto layout = float_token_layout(s);
-    return nlohmann::detail::parse_float_native<FloatType>(s.data(), s.data() + s.size(), layout.first, layout.second);
-}
-
-std::uint64_t bits_of(double d)
-{
-    std::uint64_t b = 0;
-    std::memcpy(&b, &d, sizeof(b));
-    return b;
-}
-
-std::uint32_t bits_of(float f)
-{
-    std::uint32_t b = 0;
-    std::memcpy(&b, &f, sizeof(b));
-    return b;
-}
-
-std::uint64_t native_bits64(const std::string& s)
-{
-    return bits_of(parse_native<double>(s));
-}
-
-std::uint32_t native_bits32(const std::string& s)
-{
-    return bits_of(parse_native<float>(s));
-}
-} // namespace
-
-TEST_CASE("parse_float_native rounds correctly")
-{
-    SECTION("double")
-    {
-        CHECK(native_bits64("1.5") == 0x3FF8000000000000u);
-        CHECK(native_bits64("0.1") == 0x3FB999999999999Au);
-        CHECK(native_bits64("-0.0") == 0x8000000000000000u);
-        CHECK(native_bits64("0e999999999999999999999") == 0u);
-        // 2^53 + 1 is exactly between two doubles: ties to even, unless more digits follow
-        CHECK(native_bits64("9007199254740993") == 0x4340000000000000u);
-        CHECK(native_bits64("9007199254740993.0000000000000000001") == 0x4340000000000001u);
-        CHECK(native_bits64("9007199254740992.9999999999999999999") == 0x4340000000000000u);
-        // 1 + 2^-53 exactly (a tie), and one unit in the 55th digit around it
-        CHECK(native_bits64("1.00000000000000011102230246251565404236316680908203125") == 0x3FF0000000000000u);
-        CHECK(native_bits64("1.00000000000000011102230246251565404236316680908203126") == 0x3FF0000000000001u);
-        CHECK(native_bits64("1.00000000000000011102230246251565404236316680908203124") == 0x3FF0000000000000u);
-        // subnormal and overflow boundaries
-        CHECK(native_bits64("2.4703282292062327e-324") == 0u);
-        CHECK(native_bits64("2.4703282292062328e-324") == 1u);
-        CHECK(native_bits64("2.2250738585072011e-308") == 0x000FFFFFFFFFFFFFu);
-        CHECK(native_bits64("2.2250738585072012e-308") == 0x0010000000000000u);
-        CHECK(native_bits64("1.7976931348623157e308") == 0x7FEFFFFFFFFFFFFFu);
-        CHECK(native_bits64("1.7976931348623159e308") == 0x7FF0000000000000u);
-        CHECK(native_bits64("-1e400") == 0xFFF0000000000000u);
-        CHECK(native_bits64("-1e-400") == 0x8000000000000000u);
-        // exponents and zeros far beyond the range cancel out
-        CHECK(native_bits64("0." + std::string(1000, '0') + "1e1001") == 0x3FF0000000000000u);
-        CHECK(native_bits64("1" + std::string(1000, '0') + "e-1000") == 0x3FF0000000000000u);
-        CHECK(native_bits64("1e-99999999999999999999999") == 0u);
-        CHECK(native_bits64("1E+99999999999999999999999") == 0x7FF0000000000000u);
-        // more digits than any midpoint has (769): only whether a nonzero digit follows matters
-        const std::string tie = "1.00000000000000011102230246251565404236316680908203125";
-        CHECK(native_bits64(tie + std::string(800, '0')) == 0x3FF0000000000000u);
-        CHECK(native_bits64(tie + std::string(800, '0') + "1") == 0x3FF0000000000001u);
-    }
-
-    SECTION("float")
-    {
-        CHECK(native_bits32("1.5") == 0x3FC00000u);
-        CHECK(native_bits32("0.1") == 0x3DCCCCCDu);
-        CHECK(native_bits32("-0.0") == 0x80000000u);
-        // 2^24 + 1 is exactly between two floats
-        CHECK(native_bits32("16777217") == 0x4B800000u);
-        CHECK(native_bits32("16777217.000000000000000000001") == 0x4B800001u);
-        CHECK(native_bits32("16777218.999999999999999999999") == 0x4B800001u);
-        CHECK(native_bits32("16777219") == 0x4B800002u);
-        // subnormal and overflow boundaries
-        CHECK(native_bits32("3.4028235677973366e38") == 0x7F7FFFFFu);
-        CHECK(native_bits32("3.4028235677973367e38") == 0x7F800000u);
-        CHECK(native_bits32("7.006492321624085e-46") == 0u);
-        CHECK(native_bits32("7.006492321624086e-46") == 1u);
-        CHECK(native_bits32("1.1754942e-38") == 0x007FFFFFu);
-        CHECK(native_bits32("-1.17549435e-38") == 0x80800000u);
-        CHECK(native_bits32("1e39") == 0x7F800000u);
-        CHECK(native_bits32("-1e-50") == 0x80000000u);
-        // not rounded through double: its double would round to another float
-        CHECK(native_bits32("1.00000005960464477539062500000000001") == 0x3F800001u);
-        CHECK(native_bits32("9007199254740993") == 0x5A000000u);
-    }
-
-    SECTION("the conversion shared with other parsers")
-    {
-        // convert_float() gives the lexer's results, for every type
-        const std::vector<std::string> tokens =
-        {
-            "0", "-0.0", "1.5", "0.1", "1e-400", "-2.5E+3", "123456789012345678901234567890",
-            "9007199254740993.0000000000000000001", "4.9406564584124654e-324"
-        };
-        using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
-        using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
-        for (const auto& t : tokens)
-        {
-            CAPTURE(t);
-            const auto layout = float_token_layout(t);
-            const char* const first = t.data();
-            const char* const last = first + t.size();
-            const auto d = nlohmann::detail::convert_float<double>(first, last, layout.first, layout.second);
-            const auto f = nlohmann::detail::convert_float<float>(first, last, layout.first, layout.second);
-            const auto ld = nlohmann::detail::convert_float<long double>(first, last, layout.first, layout.second);
-            CHECK(bits_of(d) == bits_of(json::parse(t).get<double>()));
-            CHECK(bits_of(f) == bits_of(float_json::parse(t).get<float>()));
-            CHECK(ld == long_double_json::parse(t).get<long double>());
-        }
-    }
+    // numbers that are not represented exactly on the fast path
+    CHECK_FALSE(fast("12345678901234567890", out));
+    CHECK_FALSE(fast("1e10000", out));
+    CHECK_FALSE(fast("9007199254740993", out));
+    CHECK_FALSE(fast("1e23", out));
+    CHECK_FALSE(fast("1e-23", out));
 }
 
 namespace
@@ -1085,6 +806,40 @@ std::size_t big_bit_length(const big_uint& a)
     }
     return n;
 }
+
+std::uint64_t bits_of(double d)
+{
+    std::uint64_t b = 0;
+    std::memcpy(&b, &d, sizeof(b));
+    return b;
+}
+
+bool eisel_lemire(const std::string& s, double& out)
+{
+    return nlohmann::detail::parse_float_eisel_lemire(s.data(), s.data() + s.size(), out);
+}
+
+// significant digits of a token, without trailing zeros
+std::size_t significant_digits(const std::string& s)
+{
+    std::string digits;
+    for (const char c : s)
+    {
+        if (c == 'e' || c == 'E')
+        {
+            break;
+        }
+        if (c >= '0' && c <= '9' && !(digits.empty() && c == '0'))
+        {
+            digits += c;
+        }
+    }
+    while (!digits.empty() && digits.back() == '0')
+    {
+        digits.pop_back();
+    }
+    return digits.size();
+}
 } // namespace
 
 TEST_CASE("Eisel-Lemire float conversion")
@@ -1482,33 +1237,26 @@ TEST_CASE("Eisel-Lemire float conversion")
         for (const auto& c : known)
         {
             CAPTURE(c.first);
-            CHECK(native_bits64(c.first) == c.second);
+            double out = 0;
+            if (eisel_lemire(c.first, out))
+            {
+                CHECK(bits_of(out) == c.second);
+            }
+            else
+            {
+                // only tokens with more than 19 significant digits are left to
+                // strtod: those whose value lies too close to a tie
+                CHECK(significant_digits(c.first) > 19);
+            }
         }
     }
 
-    SECTION("binary32")
-    {
-        using binary32 = nlohmann::detail::ieee_binary_format<24>;
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(0, 1) == 0x3F800000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-1, 1) == 0x3DCCCCCDu);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-1, 15) == 0x3FC00000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(0, 16777217) == 0x4B800000u); // tie, to even
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(0, 16777219) == 0x4B800002u); // tie, to even
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-45, 1) == 0x00000001u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-46, 7) == 0x00000000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-46, 8) == 0x00000001u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-65, 9999999999999999999u) == 0x00000000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(20, 3402823466385288598u) == 0x7F7FFFFFu);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(20, 3402823669209384635u) == 0x7F800000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(39, 1) == 0x7F800000u);
-        CHECK(nlohmann::detail::eisel_lemire<binary32>(-5, 0) == 0x00000000u);
-    }
-
     SECTION("round trip")
     {
-        // every double written by to_chars and read back, and its 17-digit
-        // form with trailing digits that make the token longer than 19 digits
+        // every double written by to_chars and read back, also with trailing
+        // digits that make the token longer than 19 digits
         std::uint64_t state = 5295;
+        std::size_t declined = 0;
         for (int i = 0; i < 200000; ++i)
         {
             state ^= state << 13u;
@@ -1530,51 +1278,30 @@ TEST_CASE("Eisel-Lemire float conversion")
             const char* end = nlohmann::detail::to_chars(buffer.data(), buffer.data() + buffer.size(), d);
             const std::string token(buffer.data(), static_cast<std::size_t>(end - buffer.data()));
             CAPTURE(token);
-            CHECK(native_bits64(token) == b);
+            double out = 0;
+            REQUIRE(eisel_lemire(token, out));
+            CHECK(bits_of(out) == b);
 
-            // insert digits before the exponent of the 17-digit form: that
-            // form lies strictly inside the rounding interval of the double
-            // (the shortest one may lie on its boundary), and the digits move
-            // it by far less than the distance to the boundary, so the value
-            // must not change
-            std::array<char, 64> digits17{};
-            static_cast<void>(std::snprintf(digits17.data(), digits17.size(), "%.17g", d)); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
-            std::string longer = digits17.data();
+            // insert digits before the exponent: the value moves by far less
+            // than the distance to the rounding boundary, so it must not change
+            std::string longer = token;
             const std::size_t e = longer.find('e');
             const std::size_t dot = longer.find('.');
             const std::string extra = dot == std::string::npos ? ".000000000000000000001" : "000000000000000000001";
             longer.insert(e == std::string::npos ? longer.size() : e, extra);
             CAPTURE(longer);
-            CHECK(native_bits64(longer) == b);
-        }
-    }
-
-    SECTION("round trip, binary32")
-    {
-        std::uint32_t state = 5295;
-        for (int i = 0; i < 100000; ++i)
-        {
-            state ^= state << 13u;
-            state ^= state >> 17u;
-            state ^= state << 5u;
-            std::uint32_t b = state;
-            if ((b & 0x7F800000u) == 0x7F800000u)
+            if (eisel_lemire(longer, out))
             {
-                continue; // infinity or NaN
+                CHECK(bits_of(out) == b);
             }
-            if (i % 4 == 0)
+            else
             {
-                b &= 0x807FFFFFu; // subnormals
+                // w and w + 1 round differently: only when the value is very
+                // close to a rounding boundary
+                ++declined;
             }
-            float f = 0;
-            std::memcpy(&f, &b, sizeof(f));
-
-            std::array<char, 64> buffer{};
-            const char* end = nlohmann::detail::to_chars(buffer.data(), buffer.data() + buffer.size(), f);
-            const std::string token(buffer.data(), static_cast<std::size_t>(end - buffer.data()));
-            CAPTURE(token);
-            CHECK(native_bits32(token) == b);
         }
+        CHECK(declined < 1000); // 107 of the 200,000
     }
 
     SECTION("used by the lexer")
@@ -1588,177 +1315,3 @@ TEST_CASE("Eisel-Lemire float conversion")
                              "[json.exception.out_of_range.406] number overflow parsing '1.7976931348623159e308'", json::out_of_range&);
     }
 }
-
-namespace
-{
-using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
-
-// the bits of the float that parse() gives for a token, via both scanners;
-// the value must be the same for both
-template<typename Json, typename Bits>
-void check_parse(const std::string& token, Bits expected, Bits infinity)
-{
-    std::stringstream stream(token);
-    if ((expected & ~(Bits{1} << (8 * sizeof(Bits) - 1))) == infinity)
-    {
-        Json _;
-        CHECK_THROWS_WITH_AS(_ = Json::parse(token), ("[json.exception.out_of_range.406] number overflow parsing '" + token + "'").c_str(), typename Json::out_of_range&);
-        CHECK_THROWS_WITH_AS(_ = Json::parse(stream), ("[json.exception.out_of_range.406] number overflow parsing '" + token + "'").c_str(), typename Json::out_of_range&);
-        return;
-    }
-    const Json contiguous = Json::parse(token);
-    const Json streamed = Json::parse(stream);
-    if (contiguous.is_number_float()) // not an integer that fits
-    {
-        CHECK(bits_of(contiguous.template get<typename Json::number_float_t>()) == expected);
-        CHECK(bits_of(streamed.template get<typename Json::number_float_t>()) == expected);
-    }
-    else
-    {
-        CHECK(streamed.is_number_integer());
-    }
-}
-} // namespace
-
-TEST_CASE("float conversion of hard cases")
-{
-    // see float_hard_cases.hpp
-    for (const auto& c : float_hard_cases::cases())
-    {
-        const std::string token = c.token;
-        CAPTURE(token);
-        CHECK(native_bits64(token) == c.bits64);
-        CHECK(native_bits32(token) == c.bits32);
-        check_parse<json>(token, c.bits64, std::uint64_t{0x7FF0000000000000u});
-        check_parse<float_json>(token, c.bits32, std::uint32_t{0x7F800000u});
-    }
-}
-
-TEST_CASE("float overflow and underflow in the parser")
-{
-    SECTION("double")
-    {
-        check_parse<json>("1.7976931348623157e308", std::uint64_t{0x7FEFFFFFFFFFFFFFu}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("1.7976931348623159e308", std::uint64_t{0x7FF0000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("-1e309", std::uint64_t{0xFFF0000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("1" + std::string(400, '0'), std::uint64_t{0x7FF0000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("1e99999999999999999999", std::uint64_t{0x7FF0000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        // an underflow gives a zero with the sign of the token
-        check_parse<json>("1e-400", std::uint64_t{0}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("-1e-400", std::uint64_t{0x8000000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("-2.4703282292062327e-324", std::uint64_t{0x8000000000000000u}, std::uint64_t{0x7FF0000000000000u});
-        check_parse<json>("0." + std::string(400, '0') + "1", std::uint64_t{0}, std::uint64_t{0x7FF0000000000000u});
-    }
-
-    SECTION("float")
-    {
-        check_parse<float_json>("3.4028234e38", std::uint32_t{0x7F7FFFFFu}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("3.4028236e38", std::uint32_t{0x7F800000u}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("-1e39", std::uint32_t{0xFF800000u}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("1e-46", std::uint32_t{0}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("-1e-46", std::uint32_t{0x80000000u}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("-7.006492321624085e-46", std::uint32_t{0x80000000u}, std::uint32_t{0x7F800000u});
-        check_parse<float_json>("-7.006492321624086e-46", std::uint32_t{0x80000001u}, std::uint32_t{0x7F800000u});
-    }
-}
-
-TEST_CASE("string scanning kernels")
-{
-    // the word-at-a-time kernels must stop exactly where a byte-by-byte scan
-    // stops, for any content, length, and alignment
-    const auto reference_special = [](const unsigned char* data, std::size_t n)
-    {
-        std::size_t i = 0;
-        while (i < n && !nlohmann::detail::is_string_special(data[i]))
-        {
-            ++i;
-        }
-        return i;
-    };
-    const auto reference_copyable = [](const unsigned char* data, std::size_t n)
-    {
-        std::size_t i = 0;
-        while (i < n && nlohmann::detail::is_ascii_copyable(data[i]))
-        {
-            ++i;
-        }
-        return i;
-    };
-    const auto reference_bulk_run = [](const unsigned char* data, std::size_t n)
-    {
-        std::size_t i = 0;
-        while (i < n)
-        {
-            if (data[i] < 0x80u)
-            {
-                if (nlohmann::detail::is_string_special(data[i]))
-                {
-                    break;
-                }
-                ++i;
-                continue;
-            }
-            const std::size_t seq = nlohmann::detail::validate_one_utf8(data + i, n - i);
-            if (seq == 0)
-            {
-                break;
-            }
-            i += seq;
-        }
-        return i;
-    };
-
-    // pieces: ordinary ASCII, stops, DEL, well-formed sequences of every
-    // length, and ill-formed or truncated ones
-    const std::vector<std::string> pieces =
-    {
-        "a", "Z", " ", "~", "0123456789", "\"", "\\", std::string(1, '\0'), "\n", "\x1F", "\x7F",
-        "\xC3\xA4", "\xE2\x82\xAC", "\xE6\x97\xA5\xE6\x9C\xAC", "\xF0\x9F\x98\x80", "\xED\x9F\xBF",
-        "\x80", "\xC0\x80", "\xC3", "\xE2\x82", "\xED\xA0\x80", "\xF4\x90\x80\x80", "\xFF",
-    };
-    std::uint64_t state = 5295;
-    const auto next = [&state]()
-    {
-        state ^= state << 13u;
-        state ^= state >> 7u;
-        state ^= state << 17u;
-        return state;
-    };
-    // the upper half as a 32-bit value: converts to std::size_t implicitly on
-    // every platform (a cast of std::uint64_t is useless where both are the
-    // same type, and required where std::size_t is 32 bits wide)
-    const auto next_small = [&next]()
-    {
-        return static_cast<std::uint32_t>(next() >> 32u);
-    };
-    for (int round = 0; round < 100000; ++round)
-    {
-        // mostly ordinary text, so that runs span several words
-        std::string text(next_small() % 8u, '.');
-        const std::size_t count = next_small() % 12u;
-        for (std::size_t k = 0; k < count; ++k)
-        {
-            const std::size_t p = (next() % 4 == 0) ? next_small() % pieces.size() : 0;
-            text += pieces[p];
-            text += std::string(next_small() % 10u, 'x');
-        }
-        const auto* data = reinterpret_cast<const unsigned char*>(text.data()); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        for (std::size_t offset = 0; offset < 3 && offset <= text.size(); ++offset)
-        {
-            const std::size_t n = text.size() - offset;
-            CAPTURE(text);
-            CAPTURE(offset);
-            CHECK(nlohmann::detail::find_string_special(data + offset, n) == reference_special(data + offset, n));
-            CHECK(nlohmann::detail::find_ascii_copyable_run(data + offset, n) == reference_copyable(data + offset, n));
-            CHECK(nlohmann::detail::scalar_string_bulk_run(data + offset, n) == reference_bulk_run(data + offset, n));
-        }
-    }
-
-    // the trailing-zero count, whichever implementation the compiler gets
-    for (int k = 0; k < 64; ++k)
-    {
-        const std::uint64_t bit = std::uint64_t{1} << k;
-        CHECK(nlohmann::detail::count_trailing_zeros(bit) == k);
-        CHECK(nlohmann::detail::count_trailing_zeros(bit | (bit << 1u) | 0x8000000000000000u) == k);
-    }
-}

tests/src/unit-class_parser.cpp

@@ -143,11 +143,13 @@ class SaxEventLogger
     {
         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;
 };
 
 class SaxCountdown : public nlohmann::json::json_sax_t
@@ -2937,3 +2939,583 @@ 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 SaxCountdown
+{
+  public:
+    using SaxCountdown::SaxCountdown;
+
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
+    {
+        return true;
+    }
+};
+
+/// 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());
+            }
+        }
+    }
+}

tests/src/unit-diagnostics.cpp

@@ -19,7 +19,6 @@ using nlohmann::json;
 
 #include <map>
 #include <unordered_map>
-#include <sstream>
 
 TEST_CASE("Better diagnostics")
 {
@@ -493,21 +492,6 @@ TEST_CASE("Regression tests for extended diagnostics")
             CHECK(copy == j);
         }
     }
-
-    SECTION("Regression test for issue #5652 - operator>> leaves a partial value in its target on a parse error")
-    {
-        json j = "old value";
-        std::istringstream is("[1, x");
-        CHECK_THROWS_WITH_AS(is >> j, "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: '1, x'", json::parse_error);
-
-        // j must be left unchanged, as json::parse() guarantees for its result
-        CHECK(j == "old value");
-
-        // copying j must not trigger assert_invariant(): a failed parse must
-        // not leave array/object elements without a parent pointer
-        json const copy = j; // NOLINT(performance-unnecessary-copy-initialization)
-        CHECK(copy == j);
-    }
 }
 
 TEST_CASE("Better diagnostics past the descent bound of update() and merge_patch()")

tests/src/unit-json_view_builder.cpp

@@ -1,399 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-#include <nlohmann/detail/view/builder.hpp>
-#include <nlohmann/detail/view/string_ref.hpp>
-using nlohmann::json;
-
-#include <cstdint>
-#include <fstream>
-#include <map>
-#include <memory>
-#include <random>
-#include <sstream>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include <test_data.hpp>
-
-namespace
-{
-using nlohmann::detail::view::document_data;
-using nlohmann::detail::view::node;
-
-// the node index of a text; a vector input has no terminating NUL, so that
-// AddressSanitizer catches any read past the last byte
-struct built
-{
-    std::unique_ptr<document_data, document_data::deleter> data{}; // NOLINT(readability-redundant-member-init)
-    std::vector<char> copy{}; // NOLINT(readability-redundant-member-init)
-    bool ok = false;
-    nlohmann::detail::view::parse_failure failure{};
-};
-
-template<typename FloatType = double>
-built build(const std::string& text, bool comments, bool trailing_commas, bool sentinel)
-{
-    built r;
-    r.data.reset(document_data::create(nlohmann::detail::view::estimate_nodes(text.data(), text.size())));
-    const char* src = text.c_str();
-    if (!sentinel)
-    {
-        r.copy.assign(text.begin(), text.end());
-        src = r.copy.data();
-    }
-    r.ok = nlohmann::detail::view::build < FloatType, !nlohmann::detail::abi_config::strict_nul_handling > (*r.data, src, text.size(), comments, trailing_commas, sentinel, r.failure);
-    r.data->src = src;
-    r.data->base[0] = src;
-    r.data->base[1] = r.data->arena.data();
-    return r;
-}
-
-// the value of a subtree, as json::parse would build it
-json value_of(const document_data& d, const node*& n)
-{
-    const node& x = *n;
-    ++n;
-    switch (static_cast<json::value_t>(x.kind))
-    {
-        case json::value_t::object:
-        {
-            json o = json::object();
-            const node* const end = &x + x.next;
-            while (n != end)
-            {
-                const std::string key(d.str(*n), n->len);
-                ++n;
-                o[key] = value_of(d, n);
-            }
-            return o;
-        }
-        case json::value_t::array:
-        {
-            json a = json::array();
-            const node* const end = &x + x.next;
-            while (n != end)
-            {
-                a.push_back(value_of(d, n));
-            }
-            return a;
-        }
-        case json::value_t::string:
-            return std::string(d.str(x), x.len);
-        case json::value_t::boolean:
-            return (x.flags & nlohmann::detail::view::node_flags::is_true) != 0;
-        case json::value_t::number_integer:
-            return static_cast<std::int64_t>(nlohmann::detail::view::integer_bits(x));
-        case json::value_t::number_unsigned:
-            return nlohmann::detail::view::integer_bits(x);
-        case json::value_t::number_float:
-            return json::parse(std::string(d.src + x.off, x.len)).get<double>();
-        case json::value_t::null:
-        case json::value_t::binary:
-        case json::value_t::discarded:
-        default:
-            return nullptr;
-    }
-}
-
-json value_of(const built& b)
-{
-    const node* n = b.data->tape;
-    json v = value_of(*b.data, n);
-    CHECK(n == b.data->tape + b.data->tape_size);
-    return v;
-}
-
-// accept/reject and the value must match json::parse, for all options and
-// with and without a NUL after the text
-void check_same(const std::string& text)
-{
-    CAPTURE(text);
-    for (int options = 0; options < 4; ++options)
-    {
-        const bool comments = (options & 1) != 0;
-        const bool trailing_commas = (options & 2) != 0;
-        const bool accepted = json::accept(text, comments, trailing_commas);
-        for (const bool sentinel :
-                {
-                    true, false
-                })
-        {
-            const built b = build(text, comments, trailing_commas, sentinel);
-            CHECK(b.ok == accepted);
-            if (b.ok && accepted)
-            {
-                CHECK(value_of(b) == json::parse(text, nullptr, true, comments, trailing_commas));
-            }
-        }
-    }
-}
-
-// a small deterministic generator of documents
-struct generator
-{
-    std::mt19937 rng{5295}; // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
-
-    int r(int n)
-    {
-        return static_cast<int>(rng() % static_cast<unsigned>(n));
-    }
-
-    void ws(std::string& o)
-    {
-        for (int n = r(4) == 0 ? r(12) : r(2); n > 0; --n)
-        {
-            o += " \n\t\r  "[r(6)];
-        }
-    }
-
-    void str(std::string& o)
-    {
-        static const char* const pieces[] = {"a", "Z", " ", "~", "\\n", "\\\"", "\\\\", "\\/", "\\u00e9", "\\ud83d\\ude00", "\xc3\xa9", "\xe3\x81\x82", "\xf0\x9f\x98\x80", "\x7f", "\\u001f", "long enough text to leave the first 16 bytes"}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-        o += '"';
-        for (int n = r(3) == 0 ? r(20) : r(6); n > 0; --n)
-        {
-            o += pieces[r(16)];
-        }
-        o += '"';
-    }
-
-    void num(std::string& o)
-    {
-        static const char* const numbers[] = {"0", "-0", "1", "-1", "12", "123456789", "1234567890123456789", "9223372036854775807", "-9223372036854775808", // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-                                              "9223372036854775808", "18446744073709551615", "18446744073709551616", "-9223372036854775809",
-                                              "1.5", "-2.25e-3", "1e10", "1E+2", "0.000001", "3.141592653589793238462643", "1e308", "-1e-400", "123.456e7"
-                                             };
-        o += numbers[r(22)];
-    }
-
-    void value(std::string& o, int depth)
-    {
-        ws(o);
-        const int k = depth > 5 ? 2 + r(6) : r(8);
-        if (k == 0 || k == 1)
-        {
-            const bool object = k == 0;
-            o += object ? '{' : '[';
-            for (int i = r(5); i > 0; --i)
-            {
-                ws(o);
-                if (object)
-                {
-                    str(o);
-                    ws(o);
-                    o += ':';
-                }
-                value(o, depth + 1);
-                o += i > 1 ? "," : "";
-            }
-            ws(o);
-            o += object ? '}' : ']';
-        }
-        else if (k < 4)
-        {
-            str(o);
-        }
-        else if (k < 6)
-        {
-            num(o);
-        }
-        else
-        {
-            static const char* const literals[] = {"true", "false", "null"}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-            o += literals[r(3)];
-        }
-        ws(o);
-    }
-};
-} // namespace
-
-TEST_CASE("json_view string_ref")
-{
-    // std::string_view in C++17, a stand-in with the same members before
-    using nlohmann::detail::view::string_ref;
-    const std::string text = "abc";
-    const string_ref r(text);
-    CHECK(r.length() == 3);
-    CHECK(std::string(r.begin(), r.end()) == "abc");
-    CHECK(r[1] == 'b');
-    CHECK(r != string_ref("abd"));
-    CHECK_FALSE(r != string_ref("abcd", 3));
-    std::ostringstream o;
-    o << r;
-    CHECK(o.str() == "abc");
-}
-
-TEST_CASE("json_view builder")
-{
-    SECTION("scalars and containers")
-    {
-        for (const char* text :
-                {
-                    "null", "true", "false", "0", "-0", "42", "-42", "1.5", "\"\"", "\"abc\"", "[]", "{}", "[1,2,3]", "{\"a\":1,\"b\":[true,null]}", // NOLINT(modernize-raw-string-literal)
-                    " [ 1 , 2 ] ", "{\"a\" : {\"b\" : {}}}", "[[[]]]", "\"\\u00e4\\n\\ud83d\\ude00\"", "{\"a\":1,\"a\":2}", "18446744073709551616", // NOLINT(modernize-raw-string-literal)
-                    "-9223372036854775809", "123456789012345678901234567890", "1e400", "-1e400", "1.7976931348623157e308"
-                })
-        {
-            check_same(text);
-        }
-
-        // the midpoint between the largest double and 2^1024 rounds to
-        // infinity (an overflow), one less to the largest double: with more
-        // than 19 digits, Eisel-Lemire cannot decide these, and the overflow
-        // check needs the exact comparison with the midpoint
-        const std::string midpoint = "179769313486231580793728971405303415079934132710037826936173778980444968292764750946649017977587207096330286416692887910946555547851940402630657488671505820681908902000708383676273854845817711531764475730270069855571366959622842914819860834936475292719074168444365510704342711559699508093042880177904174497792";
-        const std::string below = "179769313486231580793728971405303415079934132710037826936173778980444968292764750946649017977587207096330286416692887910946555547851940402630657488671505820681908902000708383676273854845817711531764475730270069855571366959622842914819860834936475292719074168444365510704342711559699508093042880177904174497791";
-        check_same(midpoint);
-        check_same("-" + midpoint);
-        check_same(below);
-        check_same("[" + below + "," + midpoint + "]");
-
-        // the check uses the floating-point type of the document: with float,
-        // the view rejects what parse() rejects (out_of_range.406), and a
-        // double document is not affected
-        using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
-        CHECK_FALSE(float_json::accept("1e39"));
-        CHECK(float_json::accept("3.4028235e38"));
-        CHECK_FALSE(float_json::accept("3.4028236e38"));
-        for (const char* text :
-                {
-                    "1e39", "-1e39", "3.4028235e38", "-3.4028235e38", "3.4028236e38", "-3.4028236e38", "3.4028234663852886e38", "1e38",
-                    "340282356779733661637539395458142568448", "340282356779733661637539395458142568447.99", "0.00034028236e42",
-                    "[1.5e38, 3.5e38]", "{\"a\": 1e-50, \"b\": 1e39}"
-                })
-        {
-            CAPTURE(text);
-            const bool float_accepted = float_json::accept(text);
-            for (const bool sentinel :
-                    {
-                        true, false
-                    })
-            {
-                const built f = build<float>(text, false, false, sentinel);
-                CHECK(f.ok == float_accepted);
-                if (!f.ok)
-                {
-                    CHECK(f.failure.code == nlohmann::detail::view::error_code::number_overflow);
-                }
-                CHECK(build<double>(text, false, false, sentinel).ok == json::accept(text));
-            }
-        }
-    }
-
-    SECTION("malformed input")
-    {
-        for (const char* text :
-                {
-                    "", " ", "[", "]", "{", "}", "[1,]", "{\"a\":1,}", "[1 2]", "{\"a\" 1}", "{1:2}", "tru", "nul", "fals", "truex", "-", "01", "1.", ".5", "1e", "1e+",
-                    "\"", "\"abc", "\"\\x\"", "\"\\u12\"", "\"\\u12G4\"", "\"\\ud800\"", "\"\\udc00\"", "\"\\ud800\\u0041\"", "\"\x01\"", "\"\xff\"", "\"\xc3\"", // NOLINT(modernize-raw-string-literal)
-                    "\"\xe0\x80\x80\"", "\"\xed\xa0\x80\"", "[1]x", "[1] [2]", "/", "/*", "/* */ 1", "// c\n1", "1 // c", "[1,/*c*/2]", "[1,2,]"
-                })
-        {
-            check_same(text);
-        }
-    }
-
-    SECTION("NUL, BOM, and whitespace")
-    {
-        // a NUL inside a string is a control character, as for json::parse
-        // (where a NUL ends the input, it does so only between values)
-        for (const bool sentinel :
-                {
-                    true, false
-                })
-        {
-            const built b = build(std::string("[\"ab\0cd\"]", 9), false, false, sentinel);
-            CHECK(!b.ok);
-            CHECK(b.failure.code == nlohmann::detail::view::error_code::string_control_character);
-            CHECK(b.failure.offset == 4);
-        }
-        check_same(std::string("[1]\0garbage", 11));
-        check_same(std::string("[1\0]", 4));
-        check_same(std::string("[1, // c\0\n2]", 12));
-        check_same(std::string("[1, /* c\0 */ 2]", 15));
-        check_same("\xEF\xBB\xBF[1]");
-        check_same("\xEF\xBB[1]");
-        check_same(" \t\r\n 7 \n");
-        for (const char* text :
-                {"[1]\r", "[1]\n", "[1]\r\n", "[1,\r2]", "[1,\r\n2]", "7\r", "\"x\"\r", "{\"a\":\r\n1}\r", "[\n  1,\n  2\n]", "{\n    \"a\": [\n        1\n    ]\n}"
-                })
-        {
-            check_same(text);
-        }
-    }
-
-    SECTION("deep nesting")
-    {
-        // the open containers beyond 64 levels live on the heap
-        for (const std::size_t depth :
-                {
-                    63u, 64u, 65u, 1000u, 100000u
-                })
-        {
-            const std::string arrays = std::string(depth, '[') + std::string(depth, ']');
-            const built b = build(arrays, false, false, false);
-            REQUIRE(b.ok);
-            CHECK(b.data->tape_size == depth);
-            CHECK(b.data->tape[0].next == depth);
-            std::string objects;
-            for (std::size_t i = 0; i < depth; ++i)
-            {
-                objects += "{\"a\":";
-            }
-            objects += '1' + std::string(depth, '}');
-            const built o = build(objects, false, false, false);
-            REQUIRE(o.ok);
-            CHECK(o.data->tape_size == (2 * depth) + 1);
-            CHECK(!build(std::string(depth, '[') + std::string(depth - 1, ']'), false, false, false).ok);
-        }
-    }
-
-    SECTION("generated documents and damaged copies")
-    {
-        generator g;
-        for (int i = 0; i < 3000; ++i)
-        {
-            std::string text;
-            g.value(text, 0);
-            check_same(text);
-            // damage: flip one byte, or cut the text
-            std::string damaged = text;
-            const auto at = static_cast<std::size_t>(g.r(static_cast<int>(damaged.size())));
-            static const char replacements[] = {'x', '"', '\\', ',', ':', ']', '}', '[', '{', '1', '-', '.', 'e', '\0', '\n', '/'}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
-            damaged[at] = replacements[g.r(16)];
-            check_same(damaged);
-            check_same(text.substr(0, at));
-        }
-    }
-
-    SECTION("test files")
-    {
-        for (const char* name :
-                {
-                    "/json.org/1.json", "/json.org/2.json", "/json.org/3.json", "/json.org/4.json", "/json.org/5.json",
-                    "/json_testsuite/sample.json", "/nativejson-benchmark/canada.json", "/nativejson-benchmark/citm_catalog.json",
-                    "/nativejson-benchmark/twitter.json", "/json_tests/pass1.json", "/json_tests/pass2.json", "/json_tests/pass3.json"
-                })
-        {
-            CAPTURE(name);
-            std::ifstream f(std::string(TEST_DATA_DIRECTORY) + name, std::ios::binary);
-            std::stringstream ss;
-            ss << f.rdbuf();
-            const std::string text = ss.str();
-            REQUIRE(!text.empty());
-            const built b = build(text, false, false, true);
-            REQUIRE(b.ok);
-            CHECK(value_of(b) == json::parse(text));
-        }
-    }
-}

tests/src/unit-locale-cpp.cpp

@@ -257,11 +257,10 @@ struct LocaleSwitchingSax final: public nlohmann::json_sax<json>
 
 TEST_CASE("locale changes between lexer construction and number conversion (#5198)")
 {
-    // float and double are converted without the locale. A long double that
-    // is not binary64 can take the strtold fallback, which honors the locale
-    // that is current at conversion time. The numbers are chosen so that it
-    // does: too many significant digits for Clinger's fast path, an underflow
-    // that std::from_chars rejects, and a plain value.
+    // The numbers are chosen so that the conversion also takes the strtod
+    // fallback, which honors the locale that is current at conversion time:
+    // too many significant digits for Clinger's fast path, an underflow that
+    // std::from_chars rejects, and a plain value.
     const std::vector<std::string> numbers = {"3.14159265358979323846", "1.5e-400", "12.34", "-0.000123456789012345678"};
     std::string text = "[";
     for (const auto& n : numbers)
@@ -325,8 +324,7 @@ TEST_CASE("locale changes between lexer construction and number conversion (#519
             }
         }
 
-        // a long double goes through std::strtold unless it is binary64 or
-        // std::from_chars supports it
+        // a long double goes through std::strtold unless std::from_chars supports it
         {
             bool switched = false;
             const auto cb = [&](int /*depth*/, long_double_json::parse_event_t event, long_double_json& /*parsed*/) noexcept
@@ -352,15 +350,8 @@ TEST_CASE("locale with a multi-byte decimal point")
 {
     // Some locales use a decimal point that is not a single character, e.g.
     // U+066B ARABIC DECIMAL SEPARATOR (two bytes in UTF-8). It cannot be
-    // substituted in place for '.', so the strtold fallback (only for long
-    // double formats other than binary64) converts a copy of the token with
-    // the whole decimal point instead (#5660). The values must be those of the
-    // "C" locale.
-    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
-    const char* const long_double_numbers = "[3.14159265358979323846, 1.5e-400, -0.000123456789012345678]";
-    REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-    const long_double_json expected_long_double = long_double_json::parse(long_double_numbers);
-
+    // substituted in place for '.', so the strtod fallback stops early. The
+    // conversion must still terminate rather than retry forever.
     const std::array<const char*, 6> names = {{"ar_EG.UTF-8", "ar_SA.UTF-8", "fa_IR.UTF-8", "ps_AF.UTF-8", "ar_EG", "fa_IR"}};
     bool tested = false;
     for (const char* name : names)
@@ -378,20 +369,12 @@ TEST_CASE("locale with a multi-byte decimal point")
         tested = true;
 
         // too many significant digits for Clinger's fast path, and an underflow
-        // that std::from_chars rejects: double does not depend on the locale
+        // that std::from_chars rejects: both reach the strtod fallback
         json j;
         CHECK_NOTHROW(j = json::parse("[3.14159265358979323846, 1.5e-400, -0.000123456789012345678]"));
         CHECK(j.is_array());
-        CHECK(j[0] == 3.14159265358979323846);
-        CHECK(j[1] == 0.0);
-        CHECK(j[2] == -0.000123456789012345678);
         CHECK(json::accept("3.14159265358979323846"));
 
-        // a long double that reaches the strtold fallback is not truncated
-        long_double_json ld;
-        CHECK_NOTHROW(ld = long_double_json::parse(long_double_numbers));
-        CHECK(ld == expected_long_double);
-
         // a value the locale-independent paths convert is not affected
         CHECK(json::parse("12.5") == 12.5);
     }

tests/src/unit-regression2.cpp

@@ -870,4 +870,585 @@ TEST_CASE("regression test - excessive binary container size honors allow_except
     CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
 }
 
+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)
+class RecoveringParser
+{
+  public:
+    explicit RecoveringParser(json& j)
+        : dom(j, false)
+    {}
+
+    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)
+    {
+        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<json> 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;
+            }
+        }
+    }
+
+};
+
+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);
+}
+
+template<typename... Parts>
+std::vector<std::uint8_t> concatenated(const std::vector<std::uint8_t>& first, const Parts& ... rest)
+{
+    std::vector<std::uint8_t> result = first;
+    for (const auto& part : std::initializer_list<std::vector<std::uint8_t>> {rest...})
+    {
+        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: ill-formed UTF-8 becomes U+FFFD, also in keys
+            {json::input_format_t::cbor, {0xA1, 0x61, 0xFF, 0x62, 0xC3, 0x28}, {{replacement_character(), replacement_character() + "("}}, 2},
+            // 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},
+            // MessagePack: ill-formed UTF-8 becomes U+FFFD
+            {json::input_format_t::msgpack, {0x92, 0xA2, 0xC3, 0x28, 0xA3, 0xE2, 0x82, 'x'}, {replacement_character() + "(", replacement_character() + "x"}, 2},
+            // 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},
+            // 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
+            },
+        };
+
+        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 negative integer below the range of number_integer_t
+        const auto cbor = parse_binary_recovering({0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}, json::input_format_t::cbor);
+        CHECK(cbor.errors == 1);
+        CHECK(cbor.value.is_number_float());
+        CHECK(cbor.value.get<double>() == -18446744073709551616.0);
+
+        // 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}}));
+
+        // 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
+        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 == 1);
+        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,]"));
+    }
+}
+
 DOCTEST_CLANG_SUPPRESS_WARNING_POP