Mirror/zeek
1
0
Fork 0
mirror of https://github.com/zeek/zeek.git synced 2025-10-07 00:58:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

util: don't modify the input string in tokenize_string()

Browse source 
This saves one full copy of the input string and avoids moving memory
around at O(n^2) in the erase() call in each loop iteration.
This commit is contained in:
Max Kellermann 2020-01-31 11:31:10 +01:00
parent 70b45d1aba
commit e068ad8a53
2 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/util.cc
View file

@ -1501,26 +1501,27 @@ TEST_CASE("util tokenize_string")
CHECK(v2.size() == 1);
}
vector<string>* tokenize_string(string input, const string& delim,
vector<string>* tokenize_string(const string &input, const string& delim,
vector<string>* rval, int limit)
{
if ( ! rval )
rval = new vector<string>();
size_t pos = 0;
size_t n;
auto found = 0;
while ( (n = input.find(delim)) != string::npos )
while ( (n = input.find(delim, pos)) != string::npos )
{
++found;
rval->push_back(input.substr(0, n));
input.erase(0, n + 1);
rval->emplace_back(input.substr(pos, n - pos));
pos = n + 1;
if ( limit && found == limit )
break;
}
rval->push_back(input);
rval->emplace_back(input.substr(pos));
return rval;
}

2
src/util.h
View file

@ -145,7 +145,7 @@ inline std::string get_escaped_string(const std::string& str, bool escape_all)
return get_escaped_string(str.data(), str.length(), escape_all);
}
std::vector<std::string>* tokenize_string(std::string input,
std::vector<std::string>* tokenize_string(const std::string &input,
const std::string& delim,
std::vector<std::string>* rval = 0, int limit = 0);