check all BSON reads and add an EOF check for booleans (#5332)

Signed-off-by: Yash Bavadiya <krbavadiya11@gmail.com>

.github/workflows/codeql-analysis.yml

@@ -38,14 +38,14 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+      uses: github/codeql-action/init@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
       with:
         languages: c-cpp
 
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+      uses: github/codeql-action/autobuild@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+      uses: github/codeql-action/analyze@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2

.github/workflows/flawfinder.yml

@@ -43,6 +43,6 @@ jobs:
           output: 'flawfinder_results.sarif'
 
       - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
         with:
           sarif_file: ${{github.workspace}}/flawfinder_results.sarif

.github/workflows/scorecards.yml

@@ -46,7 +46,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@4eaacf0543bb3f2c246792bd56e8cdeffafb205a # v2.4.3
+        uses: ossf/scorecard-action@2d1146689b8cda280b9bc96326124645441f03bc # v2.4.4
         with:
           results_file: results.sarif
           results_format: sarif
@@ -76,6 +76,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -61,7 +61,7 @@ jobs:
 
       # Upload SARIF file generated in previous step
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+        uses: github/codeql-action/upload-sarif@e0647621c2984b5ed2f768cb892365bf2a616ad1 # v4.37.2
         with:
           sarif_file: semgrep.sarif
         if: always()

docs/mkdocs/docs/api/basic_json/binary_t.md

@@ -13,9 +13,8 @@ is compatible with both of the binary data formats that use binary subtyping, (t
 incompatible with each other, and it is up to the user to translate between them). The subtype is added to `BinaryType`
 via the helper type [byte_container_with_subtype](../byte_container_with_subtype/index.md).
 
-[CBOR's RFC 7049](https://tools.ietf.org/html/rfc7049) describes this type as:
-> Major type 2: a byte string. The string's length in bytes is represented following the rules for positive integers
-> (major type 0).
+[CBOR's RFC 8949](https://www.rfc-editor.org/rfc/rfc8949.html#section-3.1) describes this type as:
+> Major type 2: A byte string. The number of bytes in the string is equal to the argument.
 
 [MessagePack's documentation on the bin type
 family](https://github.com/msgpack/msgpack/blob/master/spec.md#bin-format-family) describes this type as:

docs/mkdocs/docs/features/binary_formats/cbor.md

@@ -7,12 +7,12 @@ extremely small code sizes, fairly small message size, and extensibility without
 
     - [CBOR Website](http://cbor.io) - the main source on CBOR
     - [CBOR Playground](http://cbor.me) - an interactive webpage to translate between JSON and CBOR
-    - [RFC 7049](https://tools.ietf.org/html/rfc7049) - the CBOR specification
+    - [RFC 8949](https://www.rfc-editor.org/rfc/rfc8949.html) - the CBOR specification
 
 ## Serialization
 
 The library uses the following mapping from JSON values types to CBOR types according to the CBOR specification
-([RFC 7049](https://www.rfc-editor.org/rfc/rfc7049.html)):
+([RFC 8949](https://www.rfc-editor.org/rfc/rfc8949.html)):
 
 | JSON value type | value/range                                | CBOR type                         | first byte |
 |-----------------|--------------------------------------------|-----------------------------------|------------|

include/nlohmann/detail/input/binary_reader.hpp

@@ -197,7 +197,10 @@ class binary_reader
     {
         const std::size_t document_start = chars_read;
         std::int32_t document_size{};
-        get_number<std::int32_t, true>(input_format_t::bson, document_size);
+        if (!get_number<std::int32_t, true>(input_format_t::bson, document_size))
+        {
+            return false;
+        }
 
         if (JSON_HEDLEY_UNLIKELY(!sax->start_object(detail::unknown_size())))
         {
@@ -287,7 +290,10 @@ class binary_reader
 
         // All BSON binary values have a subtype
         std::uint8_t subtype{};
-        get_number<std::uint8_t>(input_format_t::bson, subtype);
+        if (JSON_HEDLEY_UNLIKELY(!get_number<std::uint8_t>(input_format_t::bson, subtype)))
+        {
+            return false;
+        }
         result.set_subtype(subtype);
 
         return get_binary(input_format_t::bson, len, result);
@@ -340,7 +346,8 @@ class binary_reader
 
             case 0x08: // boolean
             {
-                return sax->boolean(get() != 0);
+                std::uint8_t value{};
+                return get_number<std::uint8_t>(input_format_t::bson, value) && sax->boolean(value != 0);
             }
 
             case 0x0A: // null
@@ -431,7 +438,10 @@ class binary_reader
     {
         const std::size_t document_start = chars_read;
         std::int32_t document_size{};
-        get_number<std::int32_t, true>(input_format_t::bson, document_size);
+        if (!get_number<std::int32_t, true>(input_format_t::bson, document_size))
+        {
+            return false;
+        }
 
         if (JSON_HEDLEY_UNLIKELY(!sax->start_array(detail::unknown_size())))
         {
@@ -896,7 +906,7 @@ class binary_reader
                 const auto byte1 = static_cast<unsigned char>(byte1_raw);
                 const auto byte2 = static_cast<unsigned char>(byte2_raw);
 
-                // Code from RFC 7049, Appendix D, Figure 3:
+                // Code from RFC 8949, Appendix D, Figure 3:
                 // As half-precision floating-point numbers were only added
                 // to IEEE 754 in 2008, today's programming platforms often
                 // still only have limited support for them. It is very
@@ -909,8 +919,8 @@ class binary_reader
                 {
                     const int exp = (half >> 10u) & 0x1Fu;
                     const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(0 <= exp&& exp <= 32);
-                    JSON_ASSERT(mant <= 1024);
+                    JSON_ASSERT(exp <= 31);
+                    JSON_ASSERT(mant <= 1023);
                     switch (exp)
                     {
                         case 0:
@@ -2484,7 +2494,7 @@ class binary_reader
                 const auto byte1 = static_cast<unsigned char>(byte1_raw);
                 const auto byte2 = static_cast<unsigned char>(byte2_raw);
 
-                // Code from RFC 7049, Appendix D, Figure 3:
+                // Code from RFC 8949, Appendix D, Figure 3:
                 // As half-precision floating-point numbers were only added
                 // to IEEE 754 in 2008, today's programming platforms often
                 // still only have limited support for them. It is very
@@ -2497,8 +2507,8 @@ class binary_reader
                 {
                     const int exp = (half >> 10u) & 0x1Fu;
                     const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(0 <= exp&& exp <= 32);
-                    JSON_ASSERT(mant <= 1024);
+                    JSON_ASSERT(exp <= 31);
+                    JSON_ASSERT(mant <= 1023);
                     switch (exp)
                     {
                         case 0:

single_include/nlohmann/json.hpp

@@ -10746,7 +10746,10 @@ class binary_reader
     {
         const std::size_t document_start = chars_read;
         std::int32_t document_size{};
-        get_number<std::int32_t, true>(input_format_t::bson, document_size);
+        if (!get_number<std::int32_t, true>(input_format_t::bson, document_size))
+        {
+            return false;
+        }
 
         if (JSON_HEDLEY_UNLIKELY(!sax->start_object(detail::unknown_size())))
         {
@@ -10836,7 +10839,10 @@ class binary_reader
 
         // All BSON binary values have a subtype
         std::uint8_t subtype{};
-        get_number<std::uint8_t>(input_format_t::bson, subtype);
+        if (JSON_HEDLEY_UNLIKELY(!get_number<std::uint8_t>(input_format_t::bson, subtype)))
+        {
+            return false;
+        }
         result.set_subtype(subtype);
 
         return get_binary(input_format_t::bson, len, result);
@@ -10889,7 +10895,8 @@ class binary_reader
 
             case 0x08: // boolean
             {
-                return sax->boolean(get() != 0);
+                std::uint8_t value{};
+                return get_number<std::uint8_t>(input_format_t::bson, value) && sax->boolean(value != 0);
             }
 
             case 0x0A: // null
@@ -10980,7 +10987,10 @@ class binary_reader
     {
         const std::size_t document_start = chars_read;
         std::int32_t document_size{};
-        get_number<std::int32_t, true>(input_format_t::bson, document_size);
+        if (!get_number<std::int32_t, true>(input_format_t::bson, document_size))
+        {
+            return false;
+        }
 
         if (JSON_HEDLEY_UNLIKELY(!sax->start_array(detail::unknown_size())))
         {
@@ -11445,7 +11455,7 @@ class binary_reader
                 const auto byte1 = static_cast<unsigned char>(byte1_raw);
                 const auto byte2 = static_cast<unsigned char>(byte2_raw);
 
-                // Code from RFC 7049, Appendix D, Figure 3:
+                // Code from RFC 8949, Appendix D, Figure 3:
                 // As half-precision floating-point numbers were only added
                 // to IEEE 754 in 2008, today's programming platforms often
                 // still only have limited support for them. It is very
@@ -11458,8 +11468,8 @@ class binary_reader
                 {
                     const int exp = (half >> 10u) & 0x1Fu;
                     const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(0 <= exp&& exp <= 32);
-                    JSON_ASSERT(mant <= 1024);
+                    JSON_ASSERT(exp <= 31);
+                    JSON_ASSERT(mant <= 1023);
                     switch (exp)
                     {
                         case 0:
@@ -13033,7 +13043,7 @@ class binary_reader
                 const auto byte1 = static_cast<unsigned char>(byte1_raw);
                 const auto byte2 = static_cast<unsigned char>(byte2_raw);
 
-                // Code from RFC 7049, Appendix D, Figure 3:
+                // Code from RFC 8949, Appendix D, Figure 3:
                 // As half-precision floating-point numbers were only added
                 // to IEEE 754 in 2008, today's programming platforms often
                 // still only have limited support for them. It is very
@@ -13046,8 +13056,8 @@ class binary_reader
                 {
                     const int exp = (half >> 10u) & 0x1Fu;
                     const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(0 <= exp&& exp <= 32);
-                    JSON_ASSERT(mant <= 1024);
+                    JSON_ASSERT(exp <= 31);
+                    JSON_ASSERT(mant <= 1023);
                     switch (exp)
                     {
                         case 0:

tests/src/unit-bson.cpp

@@ -825,6 +825,41 @@ TEST_CASE("Incomplete BSON Input")
         CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
     }
 
+    SECTION("Incomplete BSON Input 5")
+    {
+        std::vector<std::uint8_t> const incomplete_bson =
+        {
+            0x09, 0x00, 0x00, 0x00, // size (little endian)
+            0x08,                   // entry: boolean
+            'b', '\x00'             // key, unexpected EOF before the value
+        };
+
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 8: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
+        CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
+
+        SaxCountdown scp(0);
+        CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
+    }
+
+    SECTION("Incomplete BSON Input 6")
+    {
+        std::vector<std::uint8_t> const incomplete_bson =
+        {
+            0x0F, 0x00, 0x00, 0x00, // size (little endian)
+            0x05,                   // entry: binary
+            'b', '\x00',            // key
+            0x00, 0x00, 0x00, 0x00  // length, unexpected EOF before the subtype
+        };
+
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 12: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
+        CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
+
+        SaxCountdown scp(0);
+        CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
+    }
+
     SECTION("Improve coverage")
     {
         SECTION("key")

tests/src/unit-cbor.cpp

@@ -2309,7 +2309,7 @@ TEST_CASE("all CBOR first bytes")
 }
 #endif
 
-TEST_CASE("examples from RFC 7049 Appendix A")
+TEST_CASE("examples from RFC 8949 Appendix A")
 {
     SECTION("numbers")
     {