Created
April 9, 2013 12:55
-
-
Save m-ou-se/5345492 to your computer and use it in GitHub Desktop.
Ugly hacky code-duplication finder.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <fstream> | |
#include <map> | |
#include <set> | |
#include <vector> | |
#include <algorithm> | |
struct line { | |
std::string file; | |
size_t line_number; | |
std::string text; | |
line(std::string f, size_t l, std::string t) : file(f), line_number(l), text(t) {} | |
}; | |
int main(int argc, char * * argv) { | |
size_t min_match_length = 30; | |
std::map<std::string, std::vector<size_t>> m; | |
std::vector<line> v; | |
for (int i = 1; i < argc; ++i) { | |
std::string fn = argv[i]; | |
std::ifstream f{fn}; | |
std::string s; | |
size_t l = 0; | |
while (std::getline(f, s)) { | |
++l; | |
s.erase(std::remove_if(s.begin(), s.end(), [](char c) { return std::isspace(c); }), s.end()); | |
if (!s.empty()) v.emplace_back(fn, l, s); | |
} | |
} | |
for (size_t i = 0; i < v.size(); ++i) { | |
auto const & s = v[i].text; | |
auto & o = m[s]; | |
bool found_match = false; | |
for (size_t j : o) { | |
size_t m = s.size(); | |
size_t n = 1; | |
while (v[i+n].text == v[j+n].text) { | |
m += v[i+n].text.size(); | |
++n; | |
} | |
if (m >= min_match_length) { | |
found_match = true; | |
std::cout << v[i].file << ":" << v[i].line_number << ": Duplicate of ... " << std::endl; | |
std::cout << v[j].file << ":" << v[j].line_number << ": ... this." << std::endl; | |
i += n; | |
break; | |
} | |
} | |
if (!found_match) o.push_back(i); | |
} | |
} | |
/* | |
Some duplicated shit to test with: | |
for (size_t i = 0; i < v.size(); ++i) { | |
auto const & s = v[i].text; | |
auto & o = m[s]; | |
bool found_match = false; | |
for (size_t j : o) { | |
size_t m = s.size(); | |
size_t n = 1; | |
while (v[i+n].text == v[j+n].text) { | |
m += v[i+n].text.size(); | |
++n; | |
} | |
for (size_t i = 0; i < v.size(); ++i) { | |
auto const & s = v[i].text; | |
auto & o = m[s]; | |
bool found_match = false; | |
for (size_t j : o) { | |
*/ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment