Program to handle files subset.

files-list-diff-subset-set.cpp

#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;
}