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>

tests/src/unit-file_input.cpp

@@ -0,0 +1,236 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+using nlohmann::json;
+
+#include <array>
+#include <cstdint>
+#include <cstdio>
+#include <fstream>
+#include <memory>
+#include <random>
+#include <string>
+#include <thread>
+#include <vector>
+
+// Parsing from a FILE* locks the file once and reads it with the unlocked
+// stdio functions (see JSON_DISABLE_UNLOCKED_FILE_IO). These tests pin that
+// this is not observable: the results are the same, the file is unlocked
+// again when parsing ends - also with an exception - and the same thread can
+// keep using the file while it is locked, e.g., from a SAX callback.
+
+namespace
+{
+// a file name of its own for every run: the test runs for several C++
+// standards and configurations at the same time, in the same directory
+std::string temp_file_name()
+{
+    std::random_device rd;
+    return "unit-file_input-" + std::to_string(rd()) + ".tmp";
+}
+
+using file_ptr = std::unique_ptr<std::FILE, int (*)(std::FILE*)>;
+
+// write @a content to the file @a name and open it for reading
+file_ptr open_with(const char* name, const std::string& content)
+{
+    {
+        std::ofstream file(name, std::ios::binary);
+        file << content;
+    }
+    return {std::fopen(name, "rb"), &std::fclose};
+}
+
+// The stdio lock is recursive, so whether parsing released it can only be
+// seen from another thread: ftrylockfile() fails there while this thread
+// holds the lock. ftrylockfile() is POSIX; elsewhere, the check is skipped.
+#if defined(__GLIBC__) || defined(__APPLE__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__)
+void check_unlocked(std::FILE* f)
+{
+    int result = -1;
+    std::thread other([f, &result]
+    {
+        result = ftrylockfile(f);
+        if (result == 0)
+        {
+            funlockfile(f);
+        }
+    });
+    other.join();
+    CHECK(result == 0);
+}
+#else
+void check_unlocked(std::FILE* /*f*/) {}
+#endif
+
+// SAX consumer that also reads the position of the file it is parsing, which
+// takes the file's lock again on the same thread
+class position_reading_sax : public nlohmann::json_sax<json>
+{
+  public:
+    explicit position_reading_sax(std::FILE* f) : m_file(f) {}
+    position_reading_sax(const position_reading_sax&) = delete;
+    position_reading_sax(position_reading_sax&&) = delete;
+    position_reading_sax& operator=(const position_reading_sax&) = delete;
+    position_reading_sax& operator=(position_reading_sax&&) = delete;
+    ~position_reading_sax() override = default;
+
+    bool null() override
+    {
+        return record();
+    }
+    bool boolean(bool /*val*/) override
+    {
+        return record();
+    }
+    bool number_integer(number_integer_t /*val*/) override
+    {
+        return record();
+    }
+    bool number_unsigned(number_unsigned_t /*val*/) override
+    {
+        return record();
+    }
+    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
+    {
+        return record();
+    }
+    bool string(string_t& /*val*/) override
+    {
+        return record();
+    }
+    bool binary(binary_t& /*val*/) override
+    {
+        return record();
+    }
+    bool start_object(std::size_t /*elements*/) override
+    {
+        return record();
+    }
+    bool key(string_t& /*val*/) override
+    {
+        return record();
+    }
+    bool end_object() override
+    {
+        return record();
+    }
+    bool start_array(std::size_t /*elements*/) override
+    {
+        return record();
+    }
+    bool end_array() override
+    {
+        return record();
+    }
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const nlohmann::detail::exception& /*ex*/) override
+    {
+        return false;
+    }
+
+    const std::vector<long>& positions() const
+    {
+        return m_positions;
+    }
+
+  private:
+    bool record()
+    {
+        m_positions.push_back(std::ftell(m_file));
+        return true;
+    }
+
+    std::FILE* m_file;
+    std::vector<long> m_positions{}; // NOLINT(readability-redundant-member-init)
+};
+}  // namespace
+
+TEST_CASE("parsing from a FILE*")
+{
+    const std::string temp_name = temp_file_name();
+    const char* const name = temp_name.c_str();
+    const std::string input = "{\"a\": [1, -2.5, \"three\", true, null], \"b\": {\"c\": \"caf\xc3\xa9\"}}";
+
+    SECTION("values are the same as when parsing from a string")
+    {
+        const file_ptr f = open_with(name, input);
+        REQUIRE(f != nullptr);
+        CHECK(json::parse(f.get()) == json::parse(input));
+        // the whole input was consumed
+        std::array<char, 8> rest{};
+        CHECK(std::fgets(rest.data(), static_cast<int>(rest.size()), f.get()) == nullptr);
+        check_unlocked(f.get());
+    }
+
+    SECTION("the file is unlocked after a parse error")
+    {
+        const file_ptr f = open_with(name, "[1, 2, x]");
+        REQUIRE(f != nullptr);
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::parse(f.get()),
+                             "[json.exception.parse_error.101] parse error at line 1, column 8: syntax error while parsing value - invalid literal; last read: '2, x'",
+                             json::parse_error&);
+        check_unlocked(f.get());
+
+        // the file is still usable: the rest of the input is there
+        std::array<char, 8> rest{};
+        CHECK(std::fgets(rest.data(), static_cast<int>(rest.size()), f.get()) != nullptr);
+        CHECK(std::string(rest.data()) == "]");
+    }
+
+    SECTION("the file can be parsed again and read with stdio afterwards")
+    {
+        const file_ptr f = open_with(name, "[1] [2] tail");
+        REQUIRE(f != nullptr);
+
+        // sax_parse with strict == false stops after the first value; an array
+        // ends with its closing bracket, so the space after it is not read
+        json j;
+        nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax1(j);
+        CHECK(json::sax_parse(f.get(), &sax1, json::input_format_t::json, false));
+        CHECK(j == json({1}));
+        check_unlocked(f.get());
+
+        json k;
+        nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax2(k);
+        CHECK(json::sax_parse(f.get(), &sax2, json::input_format_t::json, false));
+        CHECK(k == json({2}));
+        check_unlocked(f.get());
+
+        std::array<char, 8> rest{};
+        CHECK(std::fgets(rest.data(), static_cast<int>(rest.size()), f.get()) != nullptr);
+        CHECK(std::string(rest.data()) == " tail");
+    }
+
+    SECTION("the same thread can use the file while it is parsed")
+    {
+        const file_ptr f = open_with(name, "[10, 20, 30]");
+        REQUIRE(f != nullptr);
+        position_reading_sax sax(f.get());
+        CHECK(json::sax_parse(f.get(), &sax));
+        // start_array, three numbers, end_array
+        CHECK(sax.positions().size() == 5);
+        CHECK(sax.positions().front() == 1);
+        check_unlocked(f.get());
+    }
+
+    SECTION("binary formats read from a FILE*")
+    {
+        const json j = {{"string", std::string(300, 'x')}, {"array", {1, 2, 3}}, {"number", 1.5}};
+        const std::vector<std::uint8_t> cbor = json::to_cbor(j);
+        const file_ptr f = open_with(name, std::string(cbor.begin(), cbor.end()));
+        REQUIRE(f != nullptr);
+        CHECK(json::from_cbor(f.get()) == j);
+        check_unlocked(f.get());
+    }
+
+    static_cast<void>(std::remove(name));
+}