Niels Lohmann 16de05b930 Copy small binary reads straight from the streambuf get area ...

The binary readers read every number and string with get_elements(), which
called the virtual std::streambuf::sgetn() each time. When the requested
bytes are in the get area, input_stream_adapter now copies them (and moves
the get pointer) inline, which is what sgetn() does for them anyway.

Instructions relative to the previous commit, from an ifstream (macOS, 5
parses): CBOR CITM 235M -> 226M, twitter 156M -> 151M, canada 495M -> 463M;
MessagePack CITM 232M -> 222M; UBJSON CITM 258M -> 241M, canada 638M ->
623M. Linux Ir (GCC / Clang): CBOR twitter 34.0M / 41.9M -> 32.2M / 40.0M,
CBOR CITM 51.4M / 58.2M -> 47.7M / 54.6M, MessagePack CITM 50.5M / 57.0M ->
46.8M / 53.4M, UBJSON CITM 56.6M / 64.1M -> 50.7M / 57.9M. Against develop
the three binary readers are 5-12 % cheaper in instructions with this series.

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

2026-10-22 09:28:36 +02:00

..

binary_reader.hpp

Fix compiler warnings on develop from the API performance stack (#5858)

2026-10-15 22:42:46 +02:00

input_adapters.hpp

Copy small binary reads straight from the streambuf get area

2026-10-22 09:28:36 +02:00

json_sax.hpp

Move object keys into the value when parsing (#5855)

2026-10-21 20:00:51 +02:00

lexer.hpp

Match literals without a stack array and keep parser states in bytes (#5854)

2026-10-21 20:00:51 +02:00

number_parse.hpp

Use standard library helpers where available, with C++11 fallbacks (#5876)

2026-10-21 20:14:59 +02:00

parser.hpp

Match literals without a stack array and keep parser states in bytes (#5854)

2026-10-21 20:00:51 +02:00

position_t.hpp

📄 adjust year (#5044)

2026-01-01 20:00:39 +01:00

pow5_table.hpp

Speed up the lexer: own float parser, string scan, and \u table (#5738)

2026-10-14 17:38:36 +02:00

simd_scan.hpp

Scan strings with SSE2, SSSE3, or NEON (#5853)

2026-10-21 20:00:50 +02:00

string_scan.hpp

Scan strings with SSE2, SSSE3, or NEON (#5853)

2026-10-21 20:00:50 +02:00