mirror of
https://github.com/ruby/ruby.git
synced 2025-08-15 21:49:06 +02:00
165cc6cf40
If that assumption holds true, then we don't need to copy the string into a buffer to unescape it. For small string is just saves copying, but for large ones it also saves a malloc/free combo. Before: ``` == Parsing twitter.json (567916 bytes) ruby 3.3.4 (2024-07-09 revisionbe1089c8ec) +YJIT [arm64-darwin23] Warming up -------------------------------------- json 52.000 i/100ms oj 61.000 i/100ms oj strict 70.000 i/100ms Oj::Parser 71.000 i/100ms rapidjson 55.000 i/100ms Calculating ------------------------------------- json 510.111 (± 2.9%) i/s (1.96 ms/i) - 2.548k in 5.000029s oj 610.232 (± 3.1%) i/s (1.64 ms/i) - 3.050k in 5.003725s oj strict 713.231 (± 3.2%) i/s (1.40 ms/i) - 3.570k in 5.010902s Oj::Parser 762.598 (± 3.0%) i/s (1.31 ms/i) - 3.834k in 5.033130s rapidjson 553.029 (± 7.4%) i/s (1.81 ms/i) - 2.750k in 5.022630s Comparison: json: 510.1 i/s Oj::Parser: 762.6 i/s - 1.49x faster oj strict: 713.2 i/s - 1.40x faster oj: 610.2 i/s - 1.20x faster rapidjson: 553.0 i/s - same-ish: difference falls within error == Parsing citm_catalog.json (1727030 bytes) ruby 3.3.4 (2024-07-09 revisionbe1089c8ec) +YJIT [arm64-darwin23] Warming up -------------------------------------- json 28.000 i/100ms oj 33.000 i/100ms oj strict 37.000 i/100ms Oj::Parser 43.000 i/100ms rapidjson 38.000 i/100ms Calculating ------------------------------------- json 303.853 (± 3.6%) i/s (3.29 ms/i) - 1.540k in 5.076079s oj 348.009 (± 2.0%) i/s (2.87 ms/i) - 1.749k in 5.027738s oj strict 396.679 (± 3.3%) i/s (2.52 ms/i) - 1.998k in 5.042271s Oj::Parser 406.699 (± 2.2%) i/s (2.46 ms/i) - 2.064k in 5.077587s rapidjson 393.463 (± 3.3%) i/s (2.54 ms/i) - 1.976k in 5.028501s Comparison: json: 303.9 i/s Oj::Parser: 406.7 i/s - 1.34x faster oj strict: 396.7 i/s - 1.31x faster rapidjson: 393.5 i/s - 1.29x faster oj: 348.0 i/s - 1.15x faster ``` After: ``` == Parsing twitter.json (567916 bytes) ruby 3.3.4 (2024-07-09 revisionbe1089c8ec) +YJIT [arm64-darwin23] Warming up -------------------------------------- json 56.000 i/100ms oj 62.000 i/100ms oj strict 72.000 i/100ms Oj::Parser 77.000 i/100ms rapidjson 55.000 i/100ms Calculating ------------------------------------- json 568.025 (± 2.1%) i/s (1.76 ms/i) - 2.856k in 5.030272s oj 630.936 (± 1.4%) i/s (1.58 ms/i) - 3.162k in 5.012630s oj strict 705.784 (±11.2%) i/s (1.42 ms/i) - 3.456k in 5.006706s Oj::Parser 783.989 (± 1.7%) i/s (1.28 ms/i) - 3.927k in 5.010343s rapidjson 557.630 (± 2.0%) i/s (1.79 ms/i) - 2.805k in 5.032388s Comparison: json: 568.0 i/s Oj::Parser: 784.0 i/s - 1.38x faster oj strict: 705.8 i/s - 1.24x faster oj: 630.9 i/s - 1.11x faster rapidjson: 557.6 i/s - same-ish: difference falls within error == Parsing citm_catalog.json (1727030 bytes) ruby 3.3.4 (2024-07-09 revisionbe1089c8ec) +YJIT [arm64-darwin23] Warming up -------------------------------------- json 29.000 i/100ms oj 33.000 i/100ms oj strict 38.000 i/100ms Oj::Parser 43.000 i/100ms rapidjson 37.000 i/100ms Calculating ------------------------------------- json 319.271 (± 3.1%) i/s (3.13 ms/i) - 1.595k in 5.001128s oj 347.946 (± 1.7%) i/s (2.87 ms/i) - 1.749k in 5.028395s oj strict 396.914 (± 3.0%) i/s (2.52 ms/i) - 2.014k in 5.079645s Oj::Parser 409.311 (± 2.7%) i/s (2.44 ms/i) - 2.064k in 5.046626s rapidjson 394.752 (± 1.5%) i/s (2.53 ms/i) - 1.998k in 5.062776s Comparison: json: 319.3 i/s Oj::Parser: 409.3 i/s - 1.28x faster oj strict: 396.9 i/s - 1.24x faster rapidjson: 394.8 i/s - 1.24x faster oj: 347.9 i/s - 1.09x faster ```7e0f66546a
78 lines
2.5 KiB
C++
78 lines
2.5 KiB
C++
#ifndef _PARSER_H_
|
|
#define _PARSER_H_
|
|
|
|
#include "ruby.h"
|
|
|
|
/* This is the fallback definition from Ruby 3.4 */
|
|
#ifndef RBIMPL_STDBOOL_H
|
|
#if defined(__cplusplus)
|
|
# if defined(HAVE_STDBOOL_H) && (__cplusplus >= 201103L)
|
|
# include <cstdbool>
|
|
# endif
|
|
#elif defined(HAVE_STDBOOL_H)
|
|
# include <stdbool.h>
|
|
#elif !defined(HAVE__BOOL)
|
|
typedef unsigned char _Bool;
|
|
# define bool _Bool
|
|
# define true ((_Bool)+1)
|
|
# define false ((_Bool)+0)
|
|
# define __bool_true_false_are_defined
|
|
#endif
|
|
#endif
|
|
|
|
#ifndef MAYBE_UNUSED
|
|
# define MAYBE_UNUSED(x) x
|
|
#endif
|
|
|
|
#define option_given_p(opts, key) (rb_hash_lookup2(opts, key, Qundef) != Qundef)
|
|
|
|
typedef struct JSON_ParserStruct {
|
|
VALUE Vsource;
|
|
char *source;
|
|
long len;
|
|
char *memo;
|
|
VALUE create_id;
|
|
VALUE object_class;
|
|
VALUE array_class;
|
|
VALUE decimal_class;
|
|
VALUE match_string;
|
|
FBuffer fbuffer;
|
|
int max_nesting;
|
|
char allow_nan;
|
|
char parsing_name;
|
|
char symbolize_names;
|
|
char freeze;
|
|
char create_additions;
|
|
char deprecated_create_additions;
|
|
} JSON_Parser;
|
|
|
|
#define GET_PARSER \
|
|
GET_PARSER_INIT; \
|
|
if (!json->Vsource) rb_raise(rb_eTypeError, "uninitialized instance")
|
|
#define GET_PARSER_INIT \
|
|
JSON_Parser *json; \
|
|
TypedData_Get_Struct(self, JSON_Parser, &JSON_Parser_type, json)
|
|
|
|
#define MinusInfinity "-Infinity"
|
|
#define EVIL 0x666
|
|
|
|
static uint32_t unescape_unicode(const unsigned char *p);
|
|
static int convert_UTF32_to_UTF8(char *buf, uint32_t ch);
|
|
static char *JSON_parse_object(JSON_Parser *json, char *p, char *pe, VALUE *result, int current_nesting);
|
|
static char *JSON_parse_value(JSON_Parser *json, char *p, char *pe, VALUE *result, int current_nesting);
|
|
static char *JSON_parse_integer(JSON_Parser *json, char *p, char *pe, VALUE *result);
|
|
static char *JSON_parse_float(JSON_Parser *json, char *p, char *pe, VALUE *result);
|
|
static char *JSON_parse_array(JSON_Parser *json, char *p, char *pe, VALUE *result, int current_nesting);
|
|
static VALUE json_string_unescape(char *string, char *stringEnd, bool intern, bool symbolize);
|
|
static char *JSON_parse_string(JSON_Parser *json, char *p, char *pe, VALUE *result);
|
|
static VALUE convert_encoding(VALUE source);
|
|
static VALUE cParser_initialize(int argc, VALUE *argv, VALUE self);
|
|
static VALUE cParser_parse(VALUE self);
|
|
static void JSON_mark(void *json);
|
|
static void JSON_free(void *json);
|
|
static VALUE cJSON_parser_s_allocate(VALUE klass);
|
|
static VALUE cParser_source(VALUE self);
|
|
|
|
static const rb_data_type_t JSON_Parser_type;
|
|
|
|
#endif
|