Allow SAX parsing of tagged CBOR (#5740)

* Allow SAX parsing of tagged CBOR

Signed-off-by: Tyagiquamar <mohdquamartyagi@gmail.com>

* Consolidate sax_parse overloads with default tag_handler parameter

Signed-off-by: Tyagiquamar <mohdquamartyagi@gmail.com>

* Add version history entry for tag_handler in sax_parse documentation

---------

Signed-off-by: Tyagiquamar <mohdquamartyagi@gmail.com>
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
Co-authored-by: Niels Lohmann <mail@nlohmann.me>

docs/mkdocs/docs/api/basic_json/cbor_tag_handler_t.md

@@ -9,10 +9,10 @@ enum class cbor_tag_handler_t
 };
 ```
 
-This enumeration is used in the [`from_cbor`](from_cbor.md) function to choose how to treat tags:
+This enumeration is used in [`from_cbor`](from_cbor.md) and [`sax_parse`](sax_parse.md) to choose how to treat tags:
 
 error
-:   throw a `parse_error` exception in case of a tag
+:   report a parse error in case of a tag (the `from_cbor` overloads throw a `parse_error` exception by default)
 
 ignore
 :   ignore tags

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

@@ -8,7 +8,8 @@ static bool sax_parse(InputType&& i,
                       input_format_t format = input_format_t::json,
                       const bool strict = true,
                       const bool ignore_comments = false,
-                      const bool ignore_trailing_commas = false);
+                      const bool ignore_trailing_commas = false,
+                      const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error);
 
 // (2)
 template<class IteratorType, class SAX, class SentinelType = IteratorType>
@@ -17,13 +18,14 @@ static bool sax_parse(IteratorType first, SentinelType last,
                       input_format_t format = input_format_t::json,
                       const bool strict = true,
                       const bool ignore_comments = false,
-                      const bool ignore_trailing_commas = false);
+                      const bool ignore_trailing_commas = false,
+                      const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error);
 ```
 
 Read from input and generate SAX events
 
 1. Read from a compatible input.
-2. Read from a pair of character iterators, or an iterator and a sentinel of a different type (C++20 ranges support)
+2. Read from a pair of character iterators, or an iterator and a sentinel of a different type (C++20 ranges support).
     
     The value_type of the iterator must be an integral type with a size of 1, 2, or 4 bytes, which will be interpreted
     respectively as UTF-8, UTF-16, and UTF-32. If `SentinelType` differs from `IteratorType`, it must be comparable to
@@ -82,6 +84,10 @@ The SAX event lister must follow the interface of [`json_sax`](../json_sax/index
 :   whether trailing commas in arrays or objects should be ignored and treated like whitespace (`#!cpp true`) or yield a parse error
     (`#!cpp false`); (optional, `#!cpp false` by default)
 
+`tag_handler` (in)
+:   how to handle CBOR tags; see [`cbor_tag_handler_t`](cbor_tag_handler_t.md). Ignored for formats other than CBOR
+    (optional, `cbor_tag_handler_t::error` by default).
+
 `first` (in)
 :   iterator to the start of a character range
 
@@ -137,6 +143,7 @@ A UTF-8 byte order mark is silently ignored.
 - Added in version 3.2.0.
 - Ignoring comments via `ignore_comments` added in version 3.9.0.
 - Added `ignore_trailing_commas` in version 3.13.0.
+- Added `tag_handler` in version 3.13.0.
 - Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
 - 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

include/nlohmann/json.hpp

@@ -5671,12 +5671,13 @@ public:
                           input_format_t format = input_format_t::json,
                           const bool strict = true,
                           const bool ignore_comments = false,
-                          const bool ignore_trailing_commas = false)
+                          const bool ignore_trailing_commas = false,
+                          const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
     {
         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(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 
     /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -5688,12 +5689,13 @@ public:
                           input_format_t format = input_format_t::json,
                           const bool strict = true,
                           const bool ignore_comments = false,
-                          const bool ignore_trailing_commas = false)
+                          const bool ignore_trailing_commas = false,
+                          const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
     {
         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(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 
     /// @brief generate SAX events
@@ -5721,7 +5723,8 @@ public:
                           input_format_t format = input_format_t::json,
                           const bool strict = true,
                           const bool ignore_comments = false,
-                          const bool ignore_trailing_commas = false)
+                          const bool ignore_trailing_commas = false,
+                          const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
 #if JSON_DELETE_DEPRECATED_FUNCTIONS
     = delete;
 #else
@@ -5731,7 +5734,7 @@ public:
                // 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(sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);
     }
 #endif
 #if defined(__clang__)

tests/src/unit-regression3.cpp

@@ -862,6 +862,46 @@ TEST_CASE("issue #5338 - truncated CBOR tagged binary subtype is rejected")
     }
 }
 
+TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
+{
+    const json expected = json::binary({1, 2, 3}, 42);
+    const auto cbor = json::to_cbor(expected);
+
+    nlohmann::detail::json_sax_acceptor<json> acceptor;
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                                true, false, false, json::cbor_tag_handler_t::error));
+
+    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::ignore));
+
+    json parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
+    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(parsed == expected);
+
+    json iterator_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
+    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(iterator_parsed == expected);
+
+    json span_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
+                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(span_parsed == expected);
+
+    const std::string text = "null";
+    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
+                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
+}
+
 TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with an object")
 {
     json t = {{"k", 1}};