SuffixTree::SuffixTree(int left, int right, std::vector <int> &buffer)
{
for (int i = left; i <= right; i++) {
line.push_back(buffer[i]);
}
initialization();
buildSuffixTree();
}
int main(int argc, char** args)
{
#ifdef DEBUG
clock_t start = clock();
#endif
scanf("%s\n", firstString);
Node* root = buildSuffixTree(firstString);
while(scanf("%s\n", otherString) == 1)
{
#ifdef DEBUG
printf("creating otherTree - #nodes: %ld\n", count);
#endif
Node* otherRoot = buildSuffixTree(otherString);
#ifdef DEBUG
printf("intersecting trees - #nodes: %ld\n", count);
#endif
intersectTrees(root, firstString, otherRoot, otherString);
#ifdef DEBUG
printf("deleting unused nodes - #nodes: %ld\n", count);
#endif
deleteNode(otherRoot);
#ifdef DEBUG
printf("round done - #nodes: %ld\n", count);
#endif
}
printf("%ld\n", calcLongestMatch(root));
deleteNode(root);
#ifdef DEBUG
clock_t end = clock();
double cpu_time = ((double)( end - start )) / CLOCKS_PER_SEC;
printf("%.3fsecs\n", cpu_time);
#endif
return 0;
}
//--------------------------------------------------------------------------------------------
// driver program to test above functions
int main(int argc, char *argv[])
{
strcpy(text, "GEEKSFORGEEKS$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "AAAAAAAAAA$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "ABCDEFG$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "ABABABA$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "ATCGATCGA$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "banana$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "abcpqrabpqpq$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
strcpy(text, "pqrpqpqabab$");
buildSuffixTree();
getLongestRepeatedSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
return 0;
}
// driver program to test above functions
int main(int argc, char *argv[])
{
// strcpy(text, "abc"); buildSuffixTree();
// strcpy(text, "xabxac#"); buildSuffixTree();
// strcpy(text, "xabxa"); buildSuffixTree();
// strcpy(text, "xabxa$"); buildSuffixTree();
strcpy(text, "abc$"); buildSuffixTree();
// strcpy(text, "geeksforgeeks$"); buildSuffixTree();
// strcpy(text, "THIS IS A TEST TEXT$"); buildSuffixTree();
// strcpy(text, "AABAACAADAABAAABAA$"); buildSuffixTree();
return 0;
}
// driver program to test above functions
int main(int argc, char *argv[])
{
for(int i=0;i<10;i++)
{
test* p=new test();
print("%d",*((int*)(p)));
printf("%d\n",HASH(p));
delete[] p;
}
return 0;
size1 = 7;
printf("Longest Common Substring in xabxac and abcabxabcd is: ");
strcpy(text, "xabxac#abcabxabcd$"); buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
size1 = 10;
printf("Longest Common Substring in xabxaabxa and babxba is: ");
strcpy(text, "xabxaabxa#babxba$"); buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
size1 = 14;
printf("Longest Common Substring in GeeksforGeeks and GeeksQuiz is: ");
strcpy(text, "GeeksforGeeks#GeeksQuiz$"); buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
size1 = 26;
printf("Longest Common Substring in OldSite:GeeksforGeeks.org");
printf(" and NewSite:GeeksQuiz.com is: ");
strcpy(text, "OldSite:GeeksforGeeks.org#NewSite:GeeksQuiz.com$");
buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
size1 = 6;
printf("Longest Common Substring in abcde and fghie is: ");
strcpy(text, "abcde#fghie$"); buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
size1 = 6;
printf("Longest Common Substring in pqrst and uvwxyz is: ");
strcpy(text, "pqrst#uvwxyz$"); buildSuffixTree();
getLongestCommonSubstring();
//Free the dynamically allocated memory
freeSuffixTreeByPostOrder(root);
return 0;
}
// Process command line options and arguments
static int
parse_opt (int key, char *arg, struct argp_state *state)
{
int *arg_count = state->input;
switch (key)
{
case 't': //Run the self test suite
{
self_test();
exit(0);
}
case 'p': //Print the generated tree
{
opt_print_tree = 1;
break;
}
case 'l': //Find Longest Common Substring (LCS)
{
opt_lcs = 1;
break;
}
case 'a': //Find Longest Common Substring (LCS)
{
opt_acs = 1;
break;
}
case ARGP_KEY_ARG: //Process the command line arguments
{
(*arg_count)--;
if (*arg_count == 3){
input_text = (unsigned char*)arg;
}
else if (*arg_count == 2){
input_text2 = (unsigned char*)arg;
}
}
break;
case ARGP_KEY_END:
{
printf ("\n");
if (*arg_count >= 4){
argp_failure (state, 1, 0, "too few arguments");
}
else if (*arg_count < 0){
argp_failure (state, 1, 0, "too many arguments");
}
else {
if (opt_print_tree){
// Construct the tree and process based on supplied options
buildSuffixTree(input_text, input_text2, opt_print_tree);
freeSuffixTreeByPostOrder(root);
printf(tree_string, 's');
}
if (opt_lcs){
char *lcs;
if(!input_text2){
argp_failure (state, 1, 0, "missing comparison string");
}
printf("Longest Common Substring in %s and %s is: ",
input_text,
input_text2);
lcs = getLongestCommonSubstring(input_text,
input_text2,
opt_print_tree);
printf(lcs, 's');
}
if (opt_acs){
char *acs;
if(!input_text2){
argp_failure (state, 1, 0, "missing comparison string");
}
printf("All Common Substrings in %s and %s are: ",
input_text,
input_text2);
acs = getAllCommonSubstrings(input_text,
input_text2,
opt_print_tree);
printf(acs, 's');
}
}
}
break;
}
return 0;
}
/**
* run self tests
*/
void self_test(){
printf("Running Self Tests... \n");
printf("Build suffix tree test: \n");
char *tree_output = "$ [3]\n"
"abc$ [0]\n"
"bc$ [1]\n"
"c$ [2]\n"; //Expected output
printf("Building suffix tree for string: abc \n");
buildSuffixTree((unsigned char *)"abc", NULL, 1); //Build Suffix tree for this string
freeSuffixTreeByPostOrder(root);
printf(tree_string, 's');
int compare_result = strcmp(tree_string, tree_output);
assert(compare_result == 0);
memset(tree_string,0,strlen(tree_string)); //clear string from previous test
char *tree_output2 = "$ [10]\n"
"ab [-1]\n"
"c [-1]\n"
"abxabcd$ [0]\n"
"d$ [6]\n"
"xabcd$ [3]\n"
"b [-1]\n"
"c [-1]\n"
"abxabcd$ [1]\n"
"d$ [7]\n"
"xabcd$ [4]\n"
"c [-1]\n"
"abxabcd$ [2]\n"
"d$ [8]\n"
"d$ [9]\n"
"xabcd$ [5]\n"; //Expected output
printf("Building suffix tree for string: abcabxabcd \n");
buildSuffixTree((unsigned char *)"abcabxabcd", NULL, 1); //Build Suffix tree for this string
freeSuffixTreeByPostOrder(root);
printf(tree_string, 's');
int compare_result2 = strcmp(tree_string, tree_output2);
assert(compare_result2 == 0);
memset(tree_string,0,strlen(tree_string)); //clear string from previous test
printf("Suffix tree build test: Passed\n\n");
printf("Longest substrings test: \n");
char *lcs;
printf("Longest Common Substring in xabxac and abcabxabcd is: ");
lcs = getLongestCommonSubstring((unsigned char *)"xabxac",
(unsigned char *)"abcabxabcd",
0);
printf(lcs, 's');
int compare_result3 = strcmp(lcs, "abxa, of length: 4\n");
assert(compare_result3 == 0);
memset(lcs,0,strlen(lcs)); //clear string from previous test; //clear string from previous test
printf("Longest Common Substring in xabxaabxa and babxba is: ");
lcs = getLongestCommonSubstring((unsigned char *)"xabxaabxa",
(unsigned char *)"babxba",
0);
printf(lcs, 's');
int compare_result4 = strcmp(lcs, "abx, of length: 3\n");
assert(compare_result4 == 0);
memset(lcs,0,strlen(lcs)); //clear string from previous test;
printf("Longest Common Substring test: Passed\n\n");
printf("Substrings test: \n");
int is_substring = 0;
printf("\"test\" is a substring of \"this is a test\" \n");
is_substring = checkForSubString((unsigned char *)"test",
(unsigned char *)"this is a test");
assert(is_substring == 1);
printf("\"foo\" is a substring of \"this is a test\" \n");
is_substring = checkForSubString((unsigned char *)"foo",
(unsigned char *)"this is a test");
assert(is_substring == 0);
printf("Substrings test: Passed\n\n");
printf("All occurrences of Substring test: \n");
int *all_substrings;
size_t i = 0;
printf("Text: AABAACAADAABAAABAA, Pattern to search: AABA\n");
all_substrings = checkAllSubStringOccurences((unsigned char *)"AABA",
(unsigned char *)"AABAACAADAABAAABAA");
assert(all_substrings[0] == 3);
assert(all_substrings[1] == 13);
assert(all_substrings[2] == 9);
assert(all_substrings[3] == 0);
printf("Substring found count: %d\n", all_substrings[0]);
printf("Substrings found at positions: ");
for( i = 1; i <all_substrings[0] + 1; i++)
{
printf ("%d,",all_substrings[i]);
}
free(all_substrings);
printf("\n\nText: AABAACAADAABAAABAA, Pattern to search: AABAACAAD\n");
all_substrings = checkAllSubStringOccurences((unsigned char *)"AABAACAAD",
(unsigned char *)"AABAACAADAABAAABAA");
assert(all_substrings[0] == 1);
assert(all_substrings[1] == 0);
printf("Substring found count: %d\n", all_substrings[0]);
printf("Substrings found at position: %d", all_substrings[1]);
free(all_substrings);
printf("\n\nText: AABAACAADAABAAABAA, Pattern to search: AA\n");
all_substrings = checkAllSubStringOccurences((unsigned char *)"AA",
(unsigned char *)"AABAACAADAABAAABAA");
assert(all_substrings[0] == 7);
assert(all_substrings[1] == 16);
assert(all_substrings[2] == 12);
assert(all_substrings[3] == 13);
assert(all_substrings[4] == 9);
assert(all_substrings[5] == 0);
assert(all_substrings[6] == 3);
assert(all_substrings[7] == 6);
printf("Substring found count: %d\n", all_substrings[0]);
printf("Substrings found at positions: ");
for( i = 1; i <all_substrings[0] + 1; i++)
{
printf ("%d,",all_substrings[i]);
}
free(all_substrings);
printf("\n\nText: AABAACAADAABAAABAA, Pattern to search: ZZ\n");
all_substrings = checkAllSubStringOccurences((unsigned char *)"ZZ",
(unsigned char *)"AABAACAADAABAAABAA");
assert(all_substrings[0] == 0);
printf("No Substrings found\n");
printf("\nAll occurences of Substring test: Passed\n\n");
printf("Longest Repeated Substring test: \n");
char * lrs;
int lcs_compare;
printf("Longest Repeated Substring in AAAAAAAAAA is: ");
lrs = getLongestRepeatedSubstring((unsigned char *)"AAAAAAAAAA");
lcs_compare = strcmp(lrs, "AAAAAAAAA");
assert(lcs_compare == 0);
printf(lrs, 's');
memset(lrs,0,strlen(lrs)); //clear string from previous test;
printf("\nLongest Repeated Substring in ABABABA is: ");
lrs = getLongestRepeatedSubstring((unsigned char *)"ABABABA");
lcs_compare = strcmp(lrs, "ABABA");
assert(lcs_compare == 0);
printf(lrs, 's');
memset(lrs,0,strlen(lrs)); //clear string from previous test;
printf("\nLongest Repeated Substring in ABCDEFG is: ");
lrs = getLongestRepeatedSubstring((unsigned char *)"ABCDEFG");
lcs_compare = strcmp(lrs, "No repeated substring");
assert(lcs_compare == 0);
printf(lrs, 's');
memset(lrs,0,strlen(lrs)); //clear string from previous test;
printf("\nLongest Repeated Substring in pqrpqpqabab is: ");
lrs = getLongestRepeatedSubstring((unsigned char *)"pqrpqpqabab");
lcs_compare = strcmp(lrs, "ab");
assert(lcs_compare == 0);
printf(lrs, 's');
memset(lrs,0,strlen(lrs)); //clear string from previous test;
printf("\nLongest Repeated Substring in abcpqrabpqpq is: ");
lrs = getLongestRepeatedSubstring((unsigned char *)"abcpqrabpqpq");
lcs_compare = strcmp(lrs, "ab");
assert(lcs_compare == 0);
printf(lrs, 's');
memset(lrs,0,strlen(lrs)); //clear string from previous test;
printf("\nLongest Repeated Substring test: Passed\n\n");
// printf("All Common substrings test: \n");
//
// printf("All Common Substrings in orangeisatypeoffruit and fruitsomestugfruitgoeshereorange are: \n");
// getAllCommonSubstrings((unsigned char *)"orangeisatypeoffruit",
// (unsigned char *)"fruitsomestugfruitgoeshereorange",
// 0);
printf("done");
}
/**
* Compresses the input text and writes the compressed data to a file.
* @param[in] filename name and path of the file to compress.
* @param[in] compressed name and path of the compressed output file.
* @param[in] algorithm the algorithm that will be used to build the suffix tree (Ukkonnen or Kurtz).
* @param[in] see if see will be used.
*/
static void zip(char *filename, char *compressed, BOOL algorithm, int parts, BOOL see) {
Uchar *origText, *prevText = NULL;
Uint origTextLen, partTextLen, currentTextLen;
FILE *compressed_file;
int i, part;
fsmTree_t stree = NULL, prevTree = NULL;
BOOL alloc = False;
#ifdef WIN32
HANDLE hndl;
origText = (Uchar *) file2String(filename, &origTextLen, &hndl);
#else
origText = (Uchar *) file2String(filename, &origTextLen);
#endif
if(origText == NULL) {
fprintf(stderr,"Cannot open file %s\n", filename);
exit(EXIT_FAILURE);
}
/*if(textLen > MAXTEXTLEN)
{
fprintf(stderr,"Sorry, textlen = %lu is larger than maximal textlen = %lu\n",
(Showuint) textLen,(Showuint) MAXTEXTLEN);
exit(EXIT_FAILURE);
}*/
if (!compressed) {
CALLOC(compressed, Uchar, strlen(filename) + 5);
strcpy(compressed, filename);
strcat(compressed, ".ctx");
alloc = True;
}
compressed_file = fopen(compressed, "wb");
if (!compressed_file) {
printf( "Could not open output file");
exit(1);
}
if (alloc) FREE(compressed);
buildAlpha(origText, origTextLen);
printf ("Alphasize: %ld\n", alphasize);
printf("Algorithm %d\n", algorithm);
setMaxCount();
/* write magic number */
putc(MAGIC >> 8, compressed_file);
putc(MAGIC, compressed_file);
/* write # of parts */
putc(parts, compressed_file);
initialize_output_bitstream();
initialize_arithmetic_encoder();
writeAlphabet(compressed_file);
currentTextLen = 0;
for (part = 1; part <= parts; part++) {
printf("---------- part %d ---------------\n", part);
if (part != parts) {
partTextLen = floor(origTextLen / parts);
}
else {
partTextLen = origTextLen - (floor(origTextLen / parts) * (parts - 1));
}
if (part > 1) {
prevText = text;
prevTree = stree;
}
textlen = partTextLen;
CALLOC(text, Uchar, textlen);
reversestring(origText + currentTextLen, textlen, text);
if (algorithm == UKKONEN) {
suffixTree_t tree = initSuffixTree();
buildSuffixTree(tree);
printf("Tree built\n");
pruneSuffixTree(tree);
stree = fsmSuffixTree(tree);
}
else {
stree = buildSTree();
printf("Tree built\n");
}
/*if (part > 1) {
copyStatistics(prevTree, stree, prevText);
FREE(prevText);
freeFsmTree(prevTree);
}*/
DEBUGCODE(printf("gamma hits: %d gamma Misses: %d\n", getHits(), getMisses()));
printf("height: %ld\n", getHeight(stree));
/* write textlen */
for (i=3; i>=0; i--) {
writeByte(textlen >> (8 * i), compressed_file);
}
printf ("Textlen: %ld\n", textlen);
writeFsmTree(stree, compressed_file);
printf("FSM...\n");
makeFsm(stree);
DEBUGCODE(printFsmTree(stree));
printf("Encoding...\n");
encode(stree, compressed_file, origText + currentTextLen, partTextLen, see);
currentTextLen += partTextLen;
}
FREE(text);
freeFsmTree(stree);
flush_arithmetic_encoder(compressed_file);
flush_output_bitstream(compressed_file);
#ifdef WIN32
freetextspace(origText, hndl);
#else
freetextspace(origText, origTextLen);
#endif
fclose(compressed_file);
}
