Lock a FILE once per parse instead of once per character

Parsing from a FILE* reads one character at a time with std::fgetc, which
locks and unlocks the FILE object for every character. file_input_adapter
now locks the file once when it is created and unlocks it when it is
destroyed - also when parsing throws - and reads with the unlocked stdio
functions in between: flockfile/getc_unlocked/funlockfile with glibc,
Apple, Android, and the BSDs, and _lock_file/_fgetc_nolock/_unlock_file
with the Microsoft C runtime. Other C libraries keep std::fgetc. The lock
is recursive, so fread() in the binary readers and stdio calls of a SAX
handler or parser callback on the same thread keep working.

On an Apple M1 Max, parsing from a FILE* is 2.9 to 4.0 times as fast
(twitter.json 14.3 -> 4.1 ms, citm_catalog.json 35.4 -> 8.8 ms); with
glibc, whose locking is cheaper, 1.1 to 1.3 times. The values and the
position of the file after parsing are unchanged.

Other threads that use the same FILE object now wait until parsing is
done instead of interleaving their reads with the parser's.
JSON_DISABLE_UNLOCKED_FILE_IO restores std::fgetc, for programs in which a
SAX handler waits for another thread that uses the same FILE. The new
tests check from a second thread that the lock is released after success
and after a parse error, and run again with the macro.

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

include/nlohmann/detail/input/input_adapters.hpp

@@ -32,6 +32,23 @@
 #include <nlohmann/detail/meta/type_traits.hpp>
 #include <nlohmann/detail/string_utils.hpp>
 
+#ifndef JSON_NO_IO
+    // Which unlocked stdio functions file_input_adapter uses (see
+    // JSON_DISABLE_UNLOCKED_FILE_IO): 1 = POSIX flockfile/getc_unlocked,
+    // 2 = Microsoft CRT _lock_file/_fgetc_nolock, 0 = none (std::fgetc, which
+    // locks the file for every character). Only C libraries known to declare
+    // the functions are listed; the macros are tested after <cstdio>, which
+    // defines __GLIBC__.
+    #if JSON_DISABLE_UNLOCKED_FILE_IO
+        #define JSON_UNLOCKED_FILE_IO 0
+    #elif defined(_MSC_VER)
+        #define JSON_UNLOCKED_FILE_IO 2
+    #elif defined(__GLIBC__) || defined(__APPLE__) || defined(__ANDROID__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__)
+        #define JSON_UNLOCKED_FILE_IO 1
+    #else
+        #define JSON_UNLOCKED_FILE_IO 0
+    #endif
+#endif  // JSON_NO_IO
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -59,18 +76,38 @@ class file_input_adapter
         : m_file(f)
     {
         JSON_ASSERT(m_file != nullptr);
+        lock();
     }
 
     // make class move-only
     file_input_adapter(const file_input_adapter&) = delete;
-    file_input_adapter(file_input_adapter&&) noexcept = default;
+    file_input_adapter(file_input_adapter&& rhs) noexcept
+        : m_file(rhs.m_file)
+    {
+        // the lock is owned by the thread, not the adapter: hand it over
+        rhs.m_file = nullptr;
+    }
     file_input_adapter& operator=(const file_input_adapter&) = delete;
     file_input_adapter& operator=(file_input_adapter&&) = delete;
-    ~file_input_adapter() = default;
+    ~file_input_adapter()
+    {
+        if (m_file != nullptr)
+        {
+            unlock();
+        }
+    }
 
     std::char_traits<char>::int_type get_character() noexcept
     {
+        // the file is locked for the lifetime of the adapter, so the
+        // per-character lock of std::fgetc can be skipped
+#if JSON_UNLOCKED_FILE_IO == 1
+        return getc_unlocked(m_file);
+#elif JSON_UNLOCKED_FILE_IO == 2
+        return _fgetc_nolock(m_file);
+#else
         return std::fgetc(m_file);
+#endif
     }
 
     // returns the number of characters successfully read
@@ -81,6 +118,27 @@ class file_input_adapter
     }
 
   private:
+    // Lock the file once for the whole parse instead of once per character.
+    // The lock is recursive, so fread() and the user's own stdio calls on the
+    // same thread keep working.
+    void lock() noexcept
+    {
+#if JSON_UNLOCKED_FILE_IO == 1
+        flockfile(m_file);
+#elif JSON_UNLOCKED_FILE_IO == 2
+        _lock_file(m_file);
+#endif
+    }
+
+    void unlock() noexcept
+    {
+#if JSON_UNLOCKED_FILE_IO == 1
+        funlockfile(m_file);
+#elif JSON_UNLOCKED_FILE_IO == 2
+        _unlock_file(m_file);
+#endif
+    }
+
     /// the file pointer to read from
     std::FILE* m_file;
 };

include/nlohmann/detail/macro_scope.hpp

@@ -899,3 +899,7 @@
 #ifndef JSON_DISABLE_STREAM_BULK_SCAN
     #define JSON_DISABLE_STREAM_BULK_SCAN 0
 #endif
+
+#ifndef JSON_DISABLE_UNLOCKED_FILE_IO
+    #define JSON_DISABLE_UNLOCKED_FILE_IO 0
+#endif

include/nlohmann/detail/macro_unscope.hpp

@@ -22,6 +22,8 @@
 #undef JSON_DISABLE_ENUM_SERIALIZATION
 #undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
 #undef JSON_DISABLE_STREAM_BULK_SCAN
+#undef JSON_DISABLE_UNLOCKED_FILE_IO
+#undef JSON_UNLOCKED_FILE_IO
 
 #ifndef JSON_TEST_KEEP_MACROS
     #undef JSON_CATCH