mkvtoolnix/rake.d/iso639.rb
Moritz Bunkus 5276839f16
BCP 47: use emplace_back for initialization of ISO 639 language list
It's much faster than using the initializer lists. Here's the result
from a micro benchmark I ran:

2021-01-25T23:49:20+01:00
Running ./bench.g++
Run on (8 X 4500 MHz CPU s)
CPU Caches:
  L1 Data 32 KiB (x4)
  L1 Instruction 32 KiB (x4)
  L2 Unified 256 KiB (x4)
  L3 Unified 8192 KiB (x1)
Load Average: 1.08, 0.72, 0.60
-------------------------------------------------------------
Benchmark                   Time             CPU   Iterations
-------------------------------------------------------------
BM_InitializerList      59667 ns        59625 ns        70526
BM_EmplaceBack          24515 ns        24497 ns       176817
BM_EmplaceBack2         16970 ns        16961 ns       247652
BM_PushBack             52831 ns        52796 ns        79202
BM_PushBack2            52858 ns        52823 ns        79004

The five benchmarks were:

• BM_InitializerList — the old way with initializer lists. Basically
  the same code currently being replaced.

• BM_EmplaceBack — Reserving space & adding each entry with
  g_languages.emplace_back(). A constructor was added to language_t
  struct taking the std::strings as const references (std::string
  const &), assigning them to the member variables normally.

• BM_EmplaceBack2 — Reserving space & adding each entry with
  g_languages.emplace_back(). A constructor was added to language_t
  struct taking the std::strings as rvalue references (std::string &&)
  assigning them to the member variables using std::move().

• BM_PushBack — Reserving space & adding each entry with
  g_languages.push_back(). A constructor was added to language_t
  struct taking the std::strings as const references (std::string
  const &), assigning them to the member variables normally.

• BM_PushBack2 — Reserving space & adding each entry with
  g_languages.push_back(). A constructor was added to language_t
  struct taking the std::strings as rvalue references (std::string &&)
  assigning them to the member variables using std::move().
2021-01-26 14:53:30 +01:00

66 lines
1.8 KiB
Ruby

def create_iso639_language_list_file
cpp_file_name = "src/common/iso639_language_list.cpp"
iso639_2 = JSON.parse(IO.readlines("/usr/share/iso-codes/json/iso_639-2.json").join(''))
rows = iso639_2["639-2"].
reject { |entry| %r{^qaa}.match(entry["alpha_3"]) }.
map do |entry|
[ entry["name"].to_u8_cpp_string,
(entry["bibliographic"] || entry["alpha_3"]).to_cpp_string,
(entry["alpha_2"] || '').to_cpp_string,
entry["bibliographic"] ? entry["alpha_3"].to_cpp_string : '""s',
'true ',
]
end
rows += ("a".."d").map do |letter|
[ %Q{u8"Reserved for local use: qa#{letter}"s},
%Q{u8"qa#{letter}"s},
'""s',
'""s',
'true ',
]
end
header = <<EOT
/*
mkvmerge -- utility for splicing together matroska files
from component media subtypes
Distributed under the GPL v2
see the file COPYING for details
or visit https://www.gnu.org/licenses/old-licenses/gpl-2.0.html
ISO 639 language definitions, lookup functions
Written by Moritz Bunkus <moritz@bunkus.org>.
*/
// -----------------------------------------------------------------------
// NOTE: this file is auto-generated by the "dev:iso639_list" rake target.
// -----------------------------------------------------------------------
#include "common/common_pch.h"
#include "common/iso639.h"
namespace mtx::iso639 {
std::vector<language_t> g_languages;
void
init() {
g_languages.reserve(#{rows.size});
EOT
footer = <<EOT
}
} // namespace mtx::iso639
EOT
content = header + format_table(rows.sort, :column_suffix => ',', :row_prefix => " g_languages.emplace_back(", :row_suffix => ");").join("\n") + "\n" + footer
runq("write", cpp_file_name) { IO.write("#{$source_dir}/#{cpp_file_name}", content); 0 }
end