Read C streams into a json_document in blocks

json_document::parse(FILE*) (and read(), accept(), parse_copy()) went through the
library's file input adapter and appended the text character by character
with fgetc. Read it with fread in blocks instead, like the std::istream
overload already does.

Parsing citm_catalog.json (1.7 MB) from a FILE*:
  Apple M1: 80.6 M -> 8.4 M instructions, 4.8 ms -> 0.55 ms (parse of the same text from a std::string: 8.7 M)
  Linux x86-64 Ir (whole run), GCC 13 / Clang 18: 47.0 M -> 13.7 M / 45.8 M -> 14.2 M
The parsed documents and the error cases are identical (checked over the test corpus
and 30 mutants of each file). A null FILE* is handled as before (by the library's adapter).

Belongs to the PR "json_view: read-side speedups".

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

include/nlohmann/detail/view/input.hpp

@@ -10,6 +10,9 @@
 
 #include <algorithm> // max
 #include <cstddef> // size_t
+#ifndef JSON_NO_IO
+    #include <cstdio> // FILE, fread
+#endif
 #include <istream> // istream, streambuf
 #include <string> // basic_string, char_traits, string
 #include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
@@ -154,6 +157,37 @@ inline void append_stream(std::string& buf, std::istream& is)
     is.clear(is.rdstate() | std::ios::eofbit);
 }
 
+/// a pointer to a C stream (never with JSON_NO_IO, which leaves out <cstdio>)
+template<typename T>
+struct is_c_stream
+#ifndef JSON_NO_IO
+    : std::is_same<T, std::FILE*>
+#else
+    : std::false_type
+#endif
+{};
+
+#ifndef JSON_NO_IO
+/// append the rest of a C stream: in blocks with fread, not character by
+/// character (the library's file adapter reads with fgetc);
+/// f is not null
+inline void append_file(std::string& buf, std::FILE* f)
+{
+    for (;;)
+    {
+        const std::size_t used = buf.size();
+        const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
+        buf.resize(used + room);
+        const std::size_t got = std::fread(&buf[used], 1, room, f);
+        buf.resize(used + got);
+        if (got < room)
+        {
+            break; // end of file, or an error (as fgetc, which returns EOF for both)
+        }
+    }
+}
+#endif
+
 }  // namespace view
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json_view.hpp

@@ -1528,7 +1528,8 @@ class basic_json_document
         // NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
         append_input_impl(buf, std::forward<T>(input), std::integral_constant < int, detail::is_contiguous_byte_container<D>::value ? 0
                           : std::is_base_of<std::istream, D>::value ? 1
-                          : detail::view::is_adapter_input<D>::value ? 2 : 3 > {});
+                          : detail::view::is_adapter_input<D>::value ? 2
+                          : detail::view::is_c_stream<D>::value ? 4 : 3 > {});
         // NOLINTEND(readability-avoid-nested-conditional-operator)
     }
 
@@ -1550,6 +1551,19 @@ class basic_json_document
         detail::view::append_adapter(buf, std::move(input.ia));
     }
 
+#ifndef JSON_NO_IO
+    static void append_input_impl(std::string& buf, std::FILE* file, std::integral_constant<int, 4> /*C stream*/)
+    {
+        if (file == nullptr)
+        {
+            // (as before: the library's adapter decides what a null stream yields)
+            detail::view::append_adapter(buf, detail::input_adapter(file));
+            return;
+        }
+        detail::view::append_file(buf, file);
+    }
+#endif
+
     template<typename T>
     static void append_input_impl(std::string& buf, T&& input, std::integral_constant<int, 3> /*other*/)
     {

single_include/nlohmann/json_view.hpp

@@ -5301,6 +5301,9 @@ NLOHMANN_JSON_NAMESPACE_END
 
 #include <algorithm> // max
 #include <cstddef> // size_t
+#ifndef JSON_NO_IO
+    #include <cstdio> // FILE, fread
+#endif
 #include <istream> // istream, streambuf
 #include <string> // basic_string, char_traits, string
 #include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
@@ -5446,6 +5449,37 @@ inline void append_stream(std::string& buf, std::istream& is)
     is.clear(is.rdstate() | std::ios::eofbit);
 }
 
+/// a pointer to a C stream (never with JSON_NO_IO, which leaves out <cstdio>)
+template<typename T>
+struct is_c_stream
+#ifndef JSON_NO_IO
+    : std::is_same<T, std::FILE*>
+#else
+    : std::false_type
+#endif
+{};
+
+#ifndef JSON_NO_IO
+/// append the rest of a C stream: in blocks with fread, not character by
+/// character (the library's file adapter reads with fgetc);
+/// f is not null
+inline void append_file(std::string& buf, std::FILE* f)
+{
+    for (;;)
+    {
+        const std::size_t used = buf.size();
+        const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
+        buf.resize(used + room);
+        const std::size_t got = std::fread(&buf[used], 1, room, f);
+        buf.resize(used + got);
+        if (got < room)
+        {
+            break; // end of file, or an error (as fgetc, which returns EOF for both)
+        }
+    }
+}
+#endif
+
 }  // namespace view
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END
@@ -8823,7 +8857,8 @@ class basic_json_document
         // NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
         append_input_impl(buf, std::forward<T>(input), std::integral_constant < int, detail::is_contiguous_byte_container<D>::value ? 0
                           : std::is_base_of<std::istream, D>::value ? 1
-                          : detail::view::is_adapter_input<D>::value ? 2 : 3 > {});
+                          : detail::view::is_adapter_input<D>::value ? 2
+                          : detail::view::is_c_stream<D>::value ? 4 : 3 > {});
         // NOLINTEND(readability-avoid-nested-conditional-operator)
     }
 
@@ -8845,6 +8880,19 @@ class basic_json_document
         detail::view::append_adapter(buf, std::move(input.ia));
     }
 
+#ifndef JSON_NO_IO
+    static void append_input_impl(std::string& buf, std::FILE* file, std::integral_constant<int, 4> /*C stream*/)
+    {
+        if (file == nullptr)
+        {
+            // (as before: the library's adapter decides what a null stream yields)
+            detail::view::append_adapter(buf, detail::input_adapter(file));
+            return;
+        }
+        detail::view::append_file(buf, file);
+    }
+#endif
+
     template<typename T>
     static void append_input_impl(std::string& buf, T&& input, std::integral_constant<int, 3> /*other*/)
     {

tests/src/unit-json_view.cpp

@@ -410,6 +410,31 @@ TEST_CASE("json_view")
         std::istringstream rvalue_source("[1]");
         CHECK(json_document::parse_copy(std::move(rvalue_source)).owns_source());
 
+        // a C stream is read in blocks as well (more than one block, and a
+        // text whose length is a multiple of the block size)
+        for (const std::size_t extra :
+                {
+                    std::size_t{0}, std::size_t{1}
+                })
+        {
+            std::FILE* long_file = std::tmpfile(); // NOLINT(cppcoreguidelines-owning-memory)
+            if (long_file != nullptr)
+            {
+                std::string padded = text;
+                padded.append((4096 - (padded.size() % 4096)) % 4096 + extra, ' ');
+                CHECK(std::fwrite(padded.data(), 1, padded.size(), long_file) == padded.size());
+                CHECK(std::fseek(long_file, 0, SEEK_SET) == 0);
+                const json_document from_long_file = json_document::parse(long_file);
+                CHECK(from_long_file.source() == padded);
+                CHECK(from_long_file.root().materialize() == json::parse(text));
+                CHECK(std::fclose(long_file) == 0); // NOLINT(cppcoreguidelines-owning-memory)
+            }
+        }
+        {
+            json_document from_null;
+            CHECK_THROWS_AS(from_null = json_document::parse(static_cast<std::FILE*>(nullptr)), json::parse_error&);
+        }
+
         // a stream without a buffer is an empty input
         std::istream no_buffer(nullptr);
         CHECK(json_document::parse(no_buffer, false).is_discarded());