Created
September 25, 2012 13:58
-
-
Save rafaelbrandao/3782077 to your computer and use it in GitHub Desktop.
Program to handle files subset.
This file contains 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 <cstdio> | |
#include <cstring> | |
#include <set> | |
using namespace std; | |
typedef unsigned long long uint64; | |
const uint64 hash_base = 263; | |
uint64 hash(const char* s) { | |
uint64 h = 0; | |
for (int i=0, j=strlen(s); i < j; ++i) | |
h = (h*hash_base) + (s[i]+1); | |
return h; | |
} | |
// This is useful if you have a subset of tests that are failing and the set of tests you've run originally. | |
// The output of this file is the complement of that subset: the list of tests that are passing. | |
int main(int argc, char* argv[]) { | |
if (argc != 3) { | |
printf("Usage: ./files-list-diff-subset-set {subset-file} {set-file}\n"); | |
return 0; | |
} | |
FILE* in; | |
set<uint64> hashes; | |
char line[2000000]; | |
in = fopen(argv[1], "r"); | |
while (fscanf(in, "%s", line) == 1) | |
hashes.insert(hash(line)); | |
fclose(in); | |
in = fopen(argv[2], "r"); | |
while (fscanf(in, "%s", line) == 1) { | |
if (!hashes.count(hash(line))) | |
printf("%s\n", line); | |
} | |
fclose(in); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment