diff options
author | Jean Boussier <[email protected]> | 2024-11-06 11:53:26 +0100 |
---|---|---|
committer | Jean Boussier <[email protected]> | 2024-11-06 23:31:30 +0100 |
commit | 6cea370b23b4adee92d5c43be9637cb24769f7d1 () | |
tree | f4c6b37d445ff9f42468c70b3890d40becdb5b05 /ext/json/parser/parser.rl | |
parent | 8254f6492c49ce7ace6b12af981034083066176e (diff) |
[ruby/json] parser.rl: parse_string implement a fast path
If we assume most string don't contain any escape sequence we can avoid a lot of costly operations when it holds true. Before: ``` == Parsing activitypub.json (58160 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 884.000 i/100ms oj 789.000 i/100ms Oj::Parser 943.000 i/100ms rapidjson 584.000 i/100ms Calculating ------------------------------------- json 8.897k (± 1.3%) i/s (112.40 μs/i) - 45.084k in 5.068520s oj 7.967k (± 1.5%) i/s (125.52 μs/i) - 40.239k in 5.051985s Oj::Parser 9.564k (± 1.4%) i/s (104.56 μs/i) - 48.093k in 5.029626s rapidjson 5.947k (± 1.4%) i/s (168.16 μs/i) - 29.784k in 5.009437s Comparison: json: 8896.5 i/s Oj::Parser: 9563.8 i/s - 1.08x faster oj: 7966.8 i/s - 1.12x slower rapidjson: 5946.7 i/s - 1.50x slower == Parsing twitter.json (567916 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 83.000 i/100ms oj 64.000 i/100ms Oj::Parser 77.000 i/100ms rapidjson 54.000 i/100ms Calculating ------------------------------------- json 823.083 (± 1.8%) i/s (1.21 ms/i) - 4.150k in 5.043805s oj 632.538 (± 1.4%) i/s (1.58 ms/i) - 3.200k in 5.060073s Oj::Parser 769.122 (± 1.8%) i/s (1.30 ms/i) - 3.850k in 5.007501s rapidjson 548.494 (± 1.5%) i/s (1.82 ms/i) - 2.754k in 5.022153s Comparison: json: 823.1 i/s Oj::Parser: 769.1 i/s - 1.07x slower oj: 632.5 i/s - 1.30x slower rapidjson: 548.5 i/s - 1.50x slower == Parsing citm_catalog.json (1727030 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 41.000 i/100ms oj 34.000 i/100ms Oj::Parser 45.000 i/100ms rapidjson 39.000 i/100ms Calculating ------------------------------------- json 427.162 (± 1.2%) i/s (2.34 ms/i) - 2.173k in 5.087666s oj 351.463 (± 2.8%) i/s (2.85 ms/i) - 1.768k in 5.035149s Oj::Parser 461.849 (± 3.7%) i/s (2.17 ms/i) - 2.340k in 5.074461s rapidjson 395.155 (± 1.8%) i/s (2.53 ms/i) - 1.989k in 5.034927s Comparison: json: 427.2 i/s Oj::Parser: 461.8 i/s - 1.08x faster rapidjson: 395.2 i/s - 1.08x slower oj: 351.5 i/s - 1.22x slower ``` After: ``` == Parsing activitypub.json (58160 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 953.000 i/100ms oj 813.000 i/100ms Oj::Parser 956.000 i/100ms rapidjson 563.000 i/100ms Calculating ------------------------------------- json 9.525k (± 1.2%) i/s (104.98 μs/i) - 47.650k in 5.003252s oj 8.117k (± 0.5%) i/s (123.20 μs/i) - 40.650k in 5.008283s Oj::Parser 9.590k (± 3.2%) i/s (104.27 μs/i) - 48.756k in 5.089794s rapidjson 6.020k (± 0.9%) i/s (166.10 μs/i) - 30.402k in 5.050155s Comparison: json: 9525.3 i/s Oj::Parser: 9590.1 i/s - same-ish: difference falls within error oj: 8116.7 i/s - 1.17x slower rapidjson: 6020.5 i/s - 1.58x slower == Parsing twitter.json (567916 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 87.000 i/100ms oj 64.000 i/100ms Oj::Parser 75.000 i/100ms rapidjson 55.000 i/100ms Calculating ------------------------------------- json 866.563 (± 0.8%) i/s (1.15 ms/i) - 4.350k in 5.020138s oj 643.567 (± 0.8%) i/s (1.55 ms/i) - 3.264k in 5.072101s Oj::Parser 777.346 (± 3.5%) i/s (1.29 ms/i) - 3.900k in 5.023933s rapidjson 557.158 (± 0.7%) i/s (1.79 ms/i) - 2.805k in 5.034731s Comparison: json: 866.6 i/s Oj::Parser: 777.3 i/s - 1.11x slower oj: 643.6 i/s - 1.35x slower rapidjson: 557.2 i/s - 1.56x slower == Parsing citm_catalog.json (1727030 bytes) ruby 3.4.0dev (2024-11-06T07:59:09Z precompute-hash-wh.. https://.com/ruby/json/commit/7943f98a8a) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- json 41.000 i/100ms oj 35.000 i/100ms Oj::Parser 40.000 i/100ms rapidjson 39.000 i/100ms Calculating ------------------------------------- json 429.216 (± 1.2%) i/s (2.33 ms/i) - 2.173k in 5.063351s oj 354.755 (± 1.1%) i/s (2.82 ms/i) - 1.785k in 5.032374s Oj::Parser 465.114 (± 3.7%) i/s (2.15 ms/i) - 2.360k in 5.081634s rapidjson 387.135 (± 1.3%) i/s (2.58 ms/i) - 1.950k in 5.037787s Comparison: json: 429.2 i/s Oj::Parser: 465.1 i/s - 1.08x faster rapidjson: 387.1 i/s - 1.11x slower oj: 354.8 i/s - 1.21x slower ``` https://.com/ruby/json/commit/96bd97c61e
-rw-r--r-- | ext/json/parser/parser.rl | 60 |
1 files changed, 46 insertions, 14 deletions
@@ -658,10 +658,10 @@ main := ignore* ( Vtrue @parse_true | VNaN @parse_nan | VInfinity @parse_infinity | - begin_number >parse_number | - begin_string >parse_string | - begin_array >parse_array | - begin_object >parse_object ) ignore* %*exit; }%% @@ -876,6 +876,26 @@ static inline VALUE build_string(const char *start, const char *end, bool intern return result; } static VALUE json_string_unescape(JSON_Parser *json, char *string, char *stringEnd, bool is_name, bool intern, bool symbolize) { size_t bufferSize = stringEnd - string; @@ -897,7 +917,7 @@ static VALUE json_string_unescape(JSON_Parser *json, char *string, char *stringE } pe = memchr(p, '\\', bufferSize); - if (RB_LIKELY(pe == NULL)) { return build_string(string, stringEnd, intern, symbolize); } @@ -1003,19 +1023,31 @@ static VALUE json_string_unescape(JSON_Parser *json, char *string, char *stringE write data; - action parse_string { *result = json_string_unescape(json, json->memo + 1, p, json->parsing_name, json->parsing_name || json-> freeze, json->parsing_name && json->symbolize_names); - if (NIL_P(*result)) { - fhold; - fbreak; - } else { - fexec p + 1; - } } - action exit { fhold; fbreak; } - main := '"' ((^([\"\\] | 0..0x1f) | '\\'[\"\\/bfnrt] | '\\u'[0-9a-fA-F]{4} | '\\'^([\"\\/bfnrtu]|0..0x1f))* %parse_string) '"' @exit; }%% static int |