mirror of
https://gitlab.com/mbunkus/mkvtoolnix.git
synced 2024-10-22 07:21:21 +00:00
c9884c3e77
Even `-O1` causes compilation time & memory usage to skyrocket, possibly exponentially, with the number of entries to `emplace_back()` into the vector. This isn't so bad with the current number of entries (489). In that case compilation with `-O3` only takes 7.2s. However, extending the list to cover ISO 639-3 means that the list will include 7160 entries. With that many entries things are much, much more severe: • with `-O1` alone compilation takes 11m 23s already. • with `-O3` memory usage exceeded 20 GB after six minutes when I had to abort due to other running applications getting killed. Runtime cost is negligible. I ran a micro benchmark. With all 7160 entries and no optimizations (`-O0`) the initialization takes ~1.4 milliseconds for the one-time initialization on startup; with optimizations (`-O1`) it still took ~570 microseconds. Part of the implementation of #3007.
66 lines
1.8 KiB
Ruby
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/iso639_types.h"
|
|
|
|
using namespace std::string_literals;
|
|
|
|
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
|