fix: restore the character that terminates a number (#5340)

operator>> is documented to leave the stream positioned right after the
parsed value, so that concatenated JSON values can be read back to back.
That did not hold for numbers: a number is only terminated by the
character following it, and lexer::scan_number() reads that character
and calls unget() -- which is simulated and rewinds only the lexer's own
bookkeeping. input_stream_adapter consumes via sbumpc() with no matching
sungetc(), so the terminating character stayed consumed and the next
extraction started one byte too late ('1true' left the stream at 'rue').

Propagating unget() to the adapter directly does not work: next_unget
makes the following get() replay the cached character, so the terminator
would be delivered twice. Instead, restore the still-pending character
once at the end of a non-strict parse, where the input is handed back to
the caller:

- input_stream_adapter gains unget_character() (sungetc()) and advertises
  it via supports_unget, detected the same way as supports_seek.
- lexer::restore_pending_unget() turns a pending simulated unget of a
  real (non-EOF) character into a real one and clears next_unget so the
  character is not also replayed. It is a no-op for adapters that cannot
  unget, and reports failure when sungetc() fails, in which case the
  input is left as it was before.
- parser calls it on the three non-strict paths, i.e. for operator>> and
  sax_parse(strict = false).

Strict parse()/accept() are unaffected: they require the input to end
after the value, so the character is consumed by the end-of-input check
anyway. Parse error messages and reported positions are unchanged.

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

tests/src/unit-deserialization.cpp

@@ -14,10 +14,15 @@ using nlohmann::json;
     using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
 #endif
 
+#include <cstddef>
 #include <iostream>
 #include <iterator>
 #include <sstream>
+#include <streambuf>
+#include <string>
+#include <utility>
 #include <valarray>
+#include <vector>
 
 #if defined(_WIN32)
     #define NOMINMAX
@@ -219,6 +224,58 @@ class proxy_iterator
     iterator* m_it = nullptr;
 };
 
+// A streambuf whose get area is a single character and that refuses every
+// putback. Used to check that restoring the character that terminated a
+// number degrades gracefully when the streambuf cannot put it back.
+class no_putback_streambuf : public std::streambuf
+{
+  public:
+    explicit no_putback_streambuf(std::string s) : m_data(std::move(s)) {}
+
+  protected:
+    int_type underflow() override
+    {
+        if (m_pos >= m_data.size())
+        {
+            return traits_type::eof();
+        }
+        m_char = m_data[m_pos];
+        setg(&m_char, &m_char, &m_char + 1);
+        return traits_type::to_int_type(m_char);
+    }
+
+    int_type uflow() override
+    {
+        if (m_pos >= m_data.size())
+        {
+            return traits_type::eof();
+        }
+        return traits_type::to_int_type(m_data[m_pos++]);
+    }
+
+    int_type pbackfail(int_type /*c*/ = traits_type::eof()) override
+    {
+        return traits_type::eof();
+    }
+
+  private:
+    std::string m_data;
+    std::size_t m_pos = 0;
+    char m_char = 0;
+};
+
+// read the characters that are left in a stream
+std::string remaining(std::istream& is)
+{
+    std::string result;
+    char c = 0;
+    while (is.get(c))
+    {
+        result += c;
+    }
+    return result;
+}
+
 // JSON_HAS_CPP_20
 #if defined(__cpp_char8_t)
 bool check_utf8()
@@ -1157,6 +1214,121 @@ TEST_CASE("deserialization")
         }
     }
 
+    SECTION("stream position after extraction (#5340)")
+    {
+        SECTION("a number does not consume the character that terminates it")
+        {
+            // a number is only terminated by the character following it; that
+            // character must be given back so the stream is positioned right
+            // after the value
+            const std::vector<std::pair<std::string, std::string>> tests =
+            {
+                {"1true", "true"},
+                {"1[2]", "[2]"},
+                {"1{}", "{}"},
+                {R"(1"a")", R"("a")"},
+                {"1 true", " true"},
+                {"12,", ","},
+                {"-0.5e3x", "x"},
+                {"1null", "null"}
+            };
+
+            for (const auto& test : tests)
+            {
+                CAPTURE(test.first);
+                std::istringstream ss(test.first);
+                json j;
+                ss >> j;
+                CHECK(j == json(json::parse(test.first.substr(0, test.first.size() - test.second.size()))));
+                CHECK(remaining(ss) == test.second);
+            }
+        }
+
+        SECTION("values that are self-delimiting are unaffected")
+        {
+            const std::vector<std::pair<std::string, std::string>> tests =
+            {
+                {"truefalse", "false"},
+                {"[1][2]", "[2]"},
+                {R"({"a":1}{"b":2})", R"({"b":2})"},
+                {R"("a""b")", R"("b")"},
+                {"null null", " null"}
+            };
+
+            for (const auto& test : tests)
+            {
+                CAPTURE(test.first);
+                std::istringstream ss(test.first);
+                json j;
+                ss >> j;
+                CHECK(remaining(ss) == test.second);
+            }
+        }
+
+        SECTION("a number at the end of the input leaves nothing behind")
+        {
+            for (const std::string s :
+                    {"1", "12", "-3.5e2", " 7 "
+                    })
+            {
+                CAPTURE(s);
+                std::istringstream ss(s);
+                json j;
+                ss >> j;
+                CHECK(remaining(ss).find_first_not_of(" \t\n\r") == std::string::npos);
+            }
+        }
+
+        SECTION("repeated extraction of concatenated values")
+        {
+            std::istringstream ss(R"(1true[2]3"x"{"a":4}5)");
+            const std::vector<json> expected =
+            {
+                json(1), json(true), json::parse("[2]"), json(3),
+                json("x"), json::parse(R"({"a":4})"), json(5)
+            };
+
+            for (const auto& e : expected)
+            {
+                json j;
+                ss >> j;
+                CHECK(j == e);
+            }
+        }
+
+        SECTION("sax_parse with strict == false")
+        {
+            std::istringstream ss("1true");
+            SaxEventLogger l;
+            CHECK(json::sax_parse(ss, &l, nlohmann::detail::input_format_t::json, false));
+            CHECK(l.events.size() == 1);
+            CHECK(l.events[0] == "number_unsigned(1)");
+            CHECK(remaining(ss) == "true");
+        }
+
+        SECTION("strict parsing still rejects trailing data")
+        {
+            std::istringstream ss("1true");
+            CHECK_THROWS_WITH_AS(json::parse(ss),
+                                 "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - unexpected true literal; expected end of input", json::parse_error);
+
+            std::istringstream ss2("1true");
+            CHECK_FALSE(json::accept(ss2));
+        }
+
+        SECTION("a streambuf that cannot put back degrades gracefully")
+        {
+            // the character is lost, as it was before the fix, but nothing
+            // else may break
+            no_putback_streambuf buf("1true");
+            std::istream is(&buf);
+            json j;
+            is >> j;
+            CHECK(j == json(1));
+            CHECK(remaining(is) == "rue");
+        }
+    }
+
     // build with C++20
     // JSON_HAS_CPP_20
 #if defined(__cpp_char8_t)