Make contains(json_pointer) return false instead of throwing on unrepresentable array-index tokens

contains(const json_pointer&) is documented to never throw, but a purely
numeric reference token that is syntactically a valid array index yet
numerically too large to be represented (exceeding size_type's max, or
exceeding ULLONG_MAX and causing strtoull() to set errno to ERANGE) made
it fall through to array_index(), which throws out_of_range.410/404.

Pre-check the token's magnitude the same way array_index() does, but
return false instead of throwing, mirroring how the surrounding code
already rejects other malformed tokens (leading zero, non-digit
characters, "-") without throwing. operator[]/at() are untouched and
keep throwing for these inputs.

Fixes #5395

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -996,21 +996,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a definite-length CBOR string
+    @brief reads a CBOR string
 
-    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length string can be read
-    into the same string.
+    This function first reads starting bytes to determine the expected
+    string length and then copies this number of bytes into a string.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  string the bytes are appended to
+    @param[out] result  created string
 
     @return whether string creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_string_chunk(string_t& result)
+    bool get_cbor_string(string_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -1066,6 +1068,20 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
+            case 0x7F: // UTF-8 string (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    string_t chunk;
+                    if (!get_cbor_string(chunk))
+                    {
+                        return false;
+                    }
+                    result.append(chunk);
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -1076,82 +1092,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a CBOR byte array
 
     This function first reads starting bytes to determine the expected
-    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
 
-    @param[out] result  created string
-
-    @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        // number of indefinite-length strings that have been opened and not
-        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
-        // but this reader has always accepted it, so the open levels are
-        // counted instead of recursed through, which overflowed the stack for
-        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
-        // to the same result, so no per-level state is needed.
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-            {
-                return false;
-            }
-
-            if (current == 0x7F) // UTF-8 string (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length string;
-            // outside of one it is not a string and falls through to the error
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
-    /*!
-    @brief reads a definite-length CBOR byte array
-
-    Reads everything @ref get_cbor_binary accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length byte array can be
-    read into the same byte array.
-
-    @param[out] result  byte array the bytes are appended to
+    @param[out] result  created byte array
 
     @return whether byte array creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_binary_chunk(binary_t& result)
+    bool get_cbor_binary(binary_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -1211,6 +1168,20 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
+            case 0x5F: // Binary data (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    binary_t chunk;
+                    if (!get_cbor_binary(chunk))
+                    {
+                        return false;
+                    }
+                    result.insert(result.end(), chunk.begin(), chunk.end());
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -1220,63 +1191,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR byte array
-
-    This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
-
-    @param[out] result  created byte array
-
-    @return whether byte array creation completed
-    */
-    bool get_cbor_binary(binary_t& result)
-    {
-        // the open indefinite-length byte arrays are counted rather than
-        // recursed through, for the reason given in @ref get_cbor_string
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
-            {
-                return false;
-            }
-
-            if (current == 0x5F) // Binary data (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length byte
-            // array; outside of one it falls through to the error below
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 

include/nlohmann/detail/json_pointer.hpp

@@ -748,6 +748,20 @@ class json_pointer
                         }
                     }
 
+                    // the reference token consists only of digits at this point (cf. checks
+                    // above); however, its numeric value might not be representable, in which
+                    // case array_index() would throw out_of_range.404/410 -- contains() must
+                    // 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.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)
+                    {
+                        // the array index cannot be represented as size_type
+                        return false;
+                    }
+
                     const auto idx = array_index<BasicJsonType>(reference_token);
                     if (idx >= ptr->size())
                     {

include/nlohmann/json.hpp

@@ -4473,11 +4473,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4493,11 +4490,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4522,11 +4516,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -4540,11 +4531,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4559,11 +4547,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4586,11 +4571,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -4604,11 +4586,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4623,11 +4602,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4650,11 +4626,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -4668,11 +4641,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4687,11 +4657,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -4705,11 +4672,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4724,11 +4688,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4751,11 +4712,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
     /// @}
 

single_include/nlohmann/json.hpp

@@ -11683,21 +11683,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a definite-length CBOR string
+    @brief reads a CBOR string
 
-    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length string can be read
-    into the same string.
+    This function first reads starting bytes to determine the expected
+    string length and then copies this number of bytes into a string.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  string the bytes are appended to
+    @param[out] result  created string
 
     @return whether string creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_string_chunk(string_t& result)
+    bool get_cbor_string(string_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -11753,6 +11755,20 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
+            case 0x7F: // UTF-8 string (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    string_t chunk;
+                    if (!get_cbor_string(chunk))
+                    {
+                        return false;
+                    }
+                    result.append(chunk);
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -11763,82 +11779,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a CBOR byte array
 
     This function first reads starting bytes to determine the expected
-    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
 
-    @param[out] result  created string
-
-    @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        // number of indefinite-length strings that have been opened and not
-        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
-        // but this reader has always accepted it, so the open levels are
-        // counted instead of recursed through, which overflowed the stack for
-        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
-        // to the same result, so no per-level state is needed.
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-            {
-                return false;
-            }
-
-            if (current == 0x7F) // UTF-8 string (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length string;
-            // outside of one it is not a string and falls through to the error
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
-    /*!
-    @brief reads a definite-length CBOR byte array
-
-    Reads everything @ref get_cbor_binary accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length byte array can be
-    read into the same byte array.
-
-    @param[out] result  byte array the bytes are appended to
+    @param[out] result  created byte array
 
     @return whether byte array creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_binary_chunk(binary_t& result)
+    bool get_cbor_binary(binary_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -11898,6 +11855,20 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
+            case 0x5F: // Binary data (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    binary_t chunk;
+                    if (!get_cbor_binary(chunk))
+                    {
+                        return false;
+                    }
+                    result.insert(result.end(), chunk.begin(), chunk.end());
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -11907,63 +11878,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR byte array
-
-    This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
-
-    @param[out] result  created byte array
-
-    @return whether byte array creation completed
-    */
-    bool get_cbor_binary(binary_t& result)
-    {
-        // the open indefinite-length byte arrays are counted rather than
-        // recursed through, for the reason given in @ref get_cbor_string
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
-            {
-                return false;
-            }
-
-            if (current == 0x5F) // Binary data (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length byte
-            // array; outside of one it falls through to the error below
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 
@@ -16480,6 +16394,20 @@ class json_pointer
                         }
                     }
 
+                    // the reference token consists only of digits at this point (cf. checks
+                    // above); however, its numeric value might not be representable, in which
+                    // case array_index() would throw out_of_range.404/410 -- contains() must
+                    // 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.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)
+                    {
+                        // the array index cannot be represented as size_type
+                        return false;
+                    }
+
                     const auto idx = array_index<BasicJsonType>(reference_token);
                     if (idx >= ptr->size())
                     {
@@ -25987,11 +25915,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26007,11 +25932,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26036,11 +25958,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -26054,11 +25973,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26073,11 +25989,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26100,11 +26013,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -26118,11 +26028,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26137,11 +26044,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26164,11 +26068,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -26182,11 +26083,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26201,11 +26099,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -26219,11 +26114,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26238,11 +26130,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26265,11 +26154,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
     /// @}
 

tests/src/unit-cbor.cpp

@@ -2035,58 +2035,6 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
     }
 }
 
-TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
-{
-    // Reading an indefinite-length string or byte array used to call itself
-    // once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
-    // the call stack before any of the input was rejected. The open levels are
-    // counted now, and the levels below prove the reader still reads the same
-    // values and reports the same errors at the same byte offsets.
-    json _;
-
-    SECTION("many open levels are reported, not crashed on")
-    {
-        const std::vector<uint8_t> input(200000, 0x7F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
-        CHECK(json::from_cbor(input, true, false).is_discarded());
-    }
-
-    SECTION("many open levels are reported, not crashed on (binary)")
-    {
-        const std::vector<uint8_t> input(200000, 0x5F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
-        CHECK(json::from_cbor(input, true, false).is_discarded());
-    }
-
-    SECTION("chunks are still concatenated")
-    {
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
-        // nested indefinite-length strings are concatenated across levels
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
-    }
-
-    SECTION("chunks are still concatenated (binary)")
-    {
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
-    }
-
-    SECTION("a chunk that is not a string is still rejected")
-    {
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
-    }
-
-    SECTION("a break marker outside an indefinite-length string is not a string")
-    {
-        // 0xFF only closes a string that was opened; on its own it is not one
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
-    }
-}
-
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")

tests/src/unit-json_pointer.cpp

@@ -319,6 +319,44 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token that is a
+                // syntactically valid array index but numerically exceeds ULLONG_MAX
+                // (causing strtoull() to set errno to ERANGE) -- it should just report
+                // that the pointer does not resolve to an element
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: same as above, but using the exact reproduction from the issue
+                json::json_pointer const jp("/99999999999999999999");
+                std::string const throw_msg = "[json.exception.out_of_range.404] unresolved reference token '99999999999999999999'";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: a reference token that is numerically representable in
+                // unsigned long long but exceeds size_type's max (e.g. ULLONG_MAX
+                // itself on typical 64-bit platforms, where size_type's max equals
+                // ULLONG_MAX) must not make contains() throw either
+                json::json_pointer const jp("/18446744073709551615");
+                std::string const throw_msg = "[json.exception.out_of_range.410] array index 18446744073709551615 exceeds size_type";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             // on some machines, the check below is not constant
@@ -334,6 +372,10 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token exceeding size_type's max
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             DOCTEST_MSVC_SUPPRESS_WARNING_POP