Keep a NUL byte ending a // comment as the end of input

With the default NUL handling (JSON_STRICT_NUL_HANDLING not set), a NUL
byte in the input is treated as the real end of input everywhere -
except when it immediately ends a `//` comment: scan_comment() matched
'\0' as a comment terminator like '\n', so the NUL was consumed as
part of the comment and scan() never saw it as end of input; the next
get() then kept reading past it. Multi-line comments and
JSON_STRICT_NUL_HANDLING=1 were unaffected, since there the NUL is
just part of the comment text.

Fix scan_comment() to leave the NUL unconsumed (unget()) instead of
returning it as part of the comment, so the following scan() reports
it as end of input, exactly as for a NUL anywhere else.

Fixes #5659.

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

include/nlohmann/detail/input/input_adapters.hpp

@@ -445,10 +445,8 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
         }
         else
         {
-            // get the current character; converted to an unsigned type so that
-            // a negative unit (wint_t is signed on some platforms) is not
-            // mistaken for an ASCII character or for EOF
-            const auto wc = static_cast<std::uint32_t>(input.get_character());
+            // get the current character
+            const auto wc = input.get_character();
 
             // UTF-32 to UTF-8 encoding
             if (wc < 0x80)
@@ -543,11 +541,9 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
                 bool valid_pair = false;
                 if (wc <= 0xDBFF && JSON_HEDLEY_UNLIKELY(!input.empty()))
                 {
-                    // only consume the next unit if it completes the pair
-                    const auto wc2 = static_cast<unsigned int>(*input.current);
+                    const auto wc2 = static_cast<unsigned int>(input.get_character());
                     if (0xDC00 <= wc2 && wc2 <= 0xDFFF)
                     {
-                        input.get_character();
                         const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
                         utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
                         utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
@@ -560,8 +556,7 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
 
                 if (!valid_pair)
                 {
-                    // emit a byte that is never valid UTF-8 (see the UTF-32 case)
-                    utf8_bytes[0] = 0xFF;
+                    utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                     utf8_bytes_filled = 1;
                 }
             }

include/nlohmann/detail/input/lexer.hpp

@@ -975,10 +975,15 @@ class lexer : public lexer_base<BasicJsonType>
                         case '\n':
                         case '\r':
                         case char_traits<char_type>::eof():
+                            return true;
+
 #if !JSON_STRICT_NUL_HANDLING
                         case '\0':
-#endif
+                            // a NUL byte is the end of the input (see scan()),
+                            // so leave it for scan() to see
+                            unget();
                             return true;
+#endif
 
                         default:
                             break;

single_include/nlohmann/json.hpp

@@ -7989,10 +7989,8 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
         }
         else
         {
-            // get the current character; converted to an unsigned type so that
-            // a negative unit (wint_t is signed on some platforms) is not
-            // mistaken for an ASCII character or for EOF
-            const auto wc = static_cast<std::uint32_t>(input.get_character());
+            // get the current character
+            const auto wc = input.get_character();
 
             // UTF-32 to UTF-8 encoding
             if (wc < 0x80)
@@ -8087,11 +8085,9 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
                 bool valid_pair = false;
                 if (wc <= 0xDBFF && JSON_HEDLEY_UNLIKELY(!input.empty()))
                 {
-                    // only consume the next unit if it completes the pair
-                    const auto wc2 = static_cast<unsigned int>(*input.current);
+                    const auto wc2 = static_cast<unsigned int>(input.get_character());
                     if (0xDC00 <= wc2 && wc2 <= 0xDFFF)
                     {
-                        input.get_character();
                         const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
                         utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
                         utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
@@ -8104,8 +8100,7 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
 
                 if (!valid_pair)
                 {
-                    // emit a byte that is never valid UTF-8 (see the UTF-32 case)
-                    utf8_bytes[0] = 0xFF;
+                    utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                     utf8_bytes_filled = 1;
                 }
             }
@@ -10072,10 +10067,15 @@ class lexer : public lexer_base<BasicJsonType>
                         case '\n':
                         case '\r':
                         case char_traits<char_type>::eof():
+                            return true;
+
 #if !JSON_STRICT_NUL_HANDLING
                         case '\0':
-#endif
+                            // a NUL byte is the end of the input (see scan()),
+                            // so leave it for scan() to see
+                            unget();
                             return true;
+#endif
 
                         default:
                             break;

tests/src/unit-class_parser.cpp

@@ -592,6 +592,45 @@ TEST_CASE("parser class")
 
                 // parsing from a string literal is unaffected either way
                 CHECK(json::parse("123") == json(123));
+
+                // a NUL byte that ends a // comment ends the input just
+                // like a NUL byte anywhere else (issue #5659); before the
+                // fix, the NUL was consumed as part of the comment, and
+                // scanning continued with whatever followed it
+                {
+                    // same as "//c" alone (real end of input after the
+                    // comment), rather than continuing with "[1]"
+                    std::string s1 = "//c";
+                    s1.push_back('\0');
+                    s1 += "[1]";
+                    json _; // NOLINT(readability-identifier-naming)
+                    CHECK_THROWS_WITH_AS(_ = json::parse(s1, nullptr, true, true),
+                                         "[json.exception.parse_error.101] parse error at line 1, column 4: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal",
+                                         json::parse_error&);
+                    CHECK_FALSE(json::accept(s1, true, true));
+                }
+
+                {
+                    // same as "[1, //c" alone, rather than continuing with " 2]"
+                    std::string s2 = "[1, //c";
+                    s2.push_back('\0');
+                    s2 += " 2]";
+                    json _; // NOLINT(readability-identifier-naming)
+                    CHECK_THROWS_WITH_AS(_ = json::parse(s2, nullptr, true, true),
+                                         "[json.exception.parse_error.101] parse error at line 1, column 8: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal",
+                                         json::parse_error&);
+                    CHECK_FALSE(json::accept(s2, true, true));
+                }
+
+                {
+                    // same as "1 //c" alone: the comment (and the NUL that
+                    // ends it) is ignored, and "x" is never reached
+                    std::string s3 = "1 //c";
+                    s3.push_back('\0');
+                    s3 += "x";
+                    CHECK(json::parse(s3, nullptr, true, true) == json(1));
+                    CHECK(json::accept(s3, true, true));
+                }
             }
 #endif
 

tests/src/unit-wstring.cpp

@@ -8,7 +8,6 @@
 
 #include "doctest_compatibility.h"
 
-#include <cwchar>
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
@@ -99,15 +98,15 @@ TEST_CASE("wide strings")
             CHECK_THROWS_AS(_ = json::parse(w), json::parse_error&);
 
             // a lone low surrogate cannot start a pair
-            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
             // a high surrogate followed by a non-low-surrogate unit is invalid
-            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xD800, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xD800, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
             // ... also when the unit is above the low surrogates
-            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xD800, 0xE000, u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xD800, 0xE000, u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
             // a lone low surrogate must not swallow the following unit: pairing
             // it with any second unit would produce valid UTF-8, so the error
             // has to report an ill-formed byte at the surrogate's own position
-            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
             // a valid surrogate pair is still decoded (U+1F600)
             CHECK(json::parse(std::u16string{u'"', 0xD83D, 0xDE00, u'"'}).get<std::string>() == "\xF0\x9F\x98\x80");
         }
@@ -142,56 +141,5 @@ TEST_CASE("wide strings")
             CHECK_THROWS_WITH_AS(_ = json::parse(std::u32string{U'"', static_cast<char32_t>(0xFFFFFFFF), U'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xFF'", json::parse_error&);
         }
     }
-
-    SECTION("malformed wide-string input outside strings (#5645)")
-    {
-        json _;
-
-        // a lone low surrogate inside a literal must not be truncated to its
-        // low byte and mistaken for the letter the literal expects next
-        // (0xDC72 truncates to 'r', which is what "true" expects after 't')
-        CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u't', static_cast<char16_t>(0xDC72), u'u', u'e'}),
-                             "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid literal; last read: 't\xFF'", json::parse_error&);
-
-        // ... also when the lone surrogate is the last unit of the input
-        CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'f', u'a', u'l', u's', static_cast<char16_t>(0xDD65)}),
-                             "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: 'fals\xFF'", json::parse_error&);
-
-        // a high surrogate followed by a unit that is not its low surrogate
-        // must not silently swallow that unit
-        CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u't', static_cast<char16_t>(0xD872), u'X', u'u', u'e'}),
-                             "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid literal; last read: 't\xFF'", json::parse_error&);
-
-        // ... in particular, if the swallowed unit is the newline that ends a
-        // // comment, the comment must not extend over the following line
-        CHECK(json::parse(std::u16string{u'[', u'1', u' ', u'/', u'/', static_cast<char16_t>(0xD800), u'\n',
-                                         u',', u'2', u' ', u'/', u'/', u'\n', u']'},
-                          nullptr, true, /*ignore_comments*/true) == json::parse("[1,2]"));
-        CHECK(json::accept(std::u16string{u'[', u'1', u' ', u'/', u'/', static_cast<char16_t>(0xD800), u'\n',
-                                          u',', u'2', u' ', u'/', u'/', u'\n', u']'}, /*ignore_comments*/true));
-
-        // cases 5 and 6 use a 32-bit wchar_t (Linux, macOS, the BSDs) to reach
-        // the UTF-32 helper tested above via u32string; the 16-bit wchar_t of
-        // Windows goes through the UTF-16 helper instead, already covered by
-        // the u16string cases above
-#if WCHAR_MAX > 0xFFFFu
-        // a negative wchar_t must not be mistaken for
-        // char_traits<char>::eof() and silently end the input, letting
-        // trailing garbage pass the strict end-of-input check (only observable
-        // where wint_t is signed, e.g. macOS/the BSDs; on Linux wint_t is
-        // unsigned and this was already handled by #5348)
-        std::wstring w = L"[1]";
-        w.push_back(static_cast<wchar_t>(-1));
-        w += L"garbage";
-        CHECK(!json::accept(w));
-        CHECK_THROWS_WITH_AS(_ = json::parse(w),
-                             "[json.exception.parse_error.101] parse error at line 1, column 4: syntax error while parsing value - invalid literal; last read: '1]\xFF'; expected end of input", json::parse_error&);
-
-        // other negative wchar_t units must not be truncated to their low
-        // byte (0xFFFFFF72 truncates to 'r', as in the u16string case above)
-        CHECK_THROWS_WITH_AS(_ = json::parse(std::wstring{L't', static_cast<wchar_t>(0xFFFFFF72), L'u', L'e'}),
-                             "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid literal; last read: 't\xFF'", json::parse_error&);
-#endif
-    }
 }
 #endif