src: refactor SplitString in util

[anonrig]

See quick-bench.com

benchmark code

#include<string_view>
#include<algorithm>// uses string::find_first_of
std::vector<std::string>
split(const std::string& str, const std::string& delims = "")
{
std::vector<std::string> output;
//output.reserve(str.length() / 4);size_t first = 0;
while (first < str.size())
{
constauto second = str.find_first_of(delims, first);
if (first != second)
{
output.emplace_back(str.substr(first, second-first));
}
if (second == std::string::npos)
break;
first = second + 1;
}
return output;
}
std::vector<std::string>
splitStd(const std::string& str, const std::string& delims = "")
{
std::vector<std::string> output;
auto first = std::cbegin(str);
while (first != std::cend(str))
{
constauto second = std::find_first_of(first, std::cend(str),
std::cbegin(delims), std::cend(delims));
if (first != second)
output.emplace_back(first, second);
if (second == std::cend(str))
break;
first = std::next(second);
}
return output;
}
std::vector<std::string> splitPtr(const std::string& str, const std::string& delims = "")
{
std::vector<std::string> output;
//	output.reserve(str.size() / 2);for (auto first = str.data(), second = str.data(), last = first + str.size(); second != last && first != last; first = second + 1) {
second = std::find_first_of(first, last, std::cbegin(delims), std::cend(delims));
if (first != second)
output.emplace_back(first, second);
}
return output;
}
std::vector<std::string_view>
splitSV(std::string_view strv, std::string_view delims = "")
{
std::vector<std::string_view> output;
size_t first = 0;
while (first < strv.size())
{
constauto second = strv.find_first_of(delims, first);
if (first != second)
output.emplace_back(strv.substr(first, second-first));
if (second == std::string_view::npos)
break;
first = second + 1;
}
return output;
}
std::vector<std::string_view>
splitSVStd(std::string_view strv, std::string_view delims = "")
{
std::vector<std::string_view> output;
//output.reserve(strv.length() / 4);auto first = strv.begin();
while (first != strv.end())
{
constauto second = std::find_first_of(first, std::cend(strv),
std::cbegin(delims), std::cend(delims));
//std::cout << first << ", " << second << '\n';if (first != second)
{
output.emplace_back(strv.substr(std::distance(strv.begin(), first), std::distance(first, second)));
}
if (second == strv.end())
break;
first = std::next(second);
}
return output;
}
std::vector<std::string_view> splitSVPtr(std::string_view str, std::string_view delims = "")
{
std::vector<std::string_view> output;
//output.reserve(str.size() / 2);for (auto first = str.data(), second = str.data(), last = first + str.size(); second != last && first != last; first = second + 1) {
second = std::find_first_of(first, last, std::cbegin(delims), std::cend(delims));
if (first != second)
output.emplace_back(first, second - first);
}
return output;
}
const std::string_view LoremIpsumStrv{ "Lorem ipsum dolor sit amet, consectetur adipiscing elit,""sed do eiusmod tempor incididuntsuperlongwordsuper ut labore et dolore magna aliqua. Ut enim ad minim veniam, ""quis nostrud exercitation ullamco laboris nisi ut aliquipsuperlongword ex ea commodo consequat. Duis aute""irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.""Excepteur sint occaecat cupidatatsuperlongword non proident, sunt in culpa qui officia deserunt mollit anim id est laborum." };
staticvoidStringSplit(benchmark::State& state) {
std::string str { LoremIpsumStrv };
// Code inside this loop is measured repeatedlyfor (auto _ : state) {
auto v = split(str);
benchmark::DoNotOptimize(v);
}
}
// Register the function as a benchmarkBENCHMARK(StringSplit);
staticvoidStringSplitStd(benchmark::State& state) {
std::string str { LoremIpsumStrv };
// Code inside this loop is measured repeatedlyfor (auto _ : state) {
auto v = splitStd(str);
benchmark::DoNotOptimize(v);
}
}
// Register the function as a benchmarkBENCHMARK(StringSplitStd);
staticvoidStringSplitPtr(benchmark::State& state) {
std::string str { LoremIpsumStrv };
// Code inside this loop is measured repeatedlyfor (auto _ : state) {
auto v = splitPtr(str);
benchmark::DoNotOptimize(v);
}
}
// Register the function as a benchmarkBENCHMARK(StringSplitPtr);
staticvoidStringViewSplit(benchmark::State& state) {
for (auto _ : state) {
auto v = splitSV(LoremIpsumStrv);
benchmark::DoNotOptimize(v);
}
}
BENCHMARK(StringViewSplit);
staticvoidStringViewSplitStd(benchmark::State& state) {
for (auto _ : state) {
auto v = splitSVStd(LoremIpsumStrv);
benchmark::DoNotOptimize(v);
}
}
BENCHMARK(StringViewSplitStd);
staticvoidStringViewSplitPtr(benchmark::State& state) {
for (auto _ : state) {
auto v = splitSVPtr(LoremIpsumStrv);
benchmark::DoNotOptimize(v);
}
}
BENCHMARK(StringViewSplitPtr);

[nodejs-github-bot]

Review requested:

• @nodejs/security-wg

[targos]

Please at least post the benchmark results in the PR. Your link may become dead in the future

[nodejs-github-bot]

CI: https://ci.nodejs.org/job/node-test-pull-request/52324/

[nodejs-github-bot]

CI: https://ci.nodejs.org/job/node-test-pull-request/52350/

[anonrig]

cc @nodejs/cpp-reviewers

[nodejs-github-bot]

CI: https://ci.nodejs.org/job/node-test-pull-request/52363/

[nodejs-github-bot]

Landed in 640a791