void checkBlock(mafBlock_t *block) {
// read through each line of a mafBlock and filter duplicates.
// Report the top scoring duplication only.
mafLine_t *ml = maf_mafBlock_getHeadLine(block);
unsigned n = maf_mafLine_getNumberOfSequences(ml);
char **species = (char **) de_malloc(sizeof(char *) * n);
char **sequences = (char **) de_malloc(sizeof(char *) * n);
int index = 0;
bool containsDuplicates = false;
duplicate_t *d = NULL, *dupSpeciesHead = NULL;
while (ml != NULL) {
if (maf_mafLine_getType(ml) != 's') {
// skip non-sequence lines
ml = maf_mafLine_getNext(ml);
continue;
}
species[index] = de_strdup(maf_mafLine_getSpecies(ml));
sequences[index] = de_strdup(maf_mafLine_getSequence(ml));
duplicate_t *thisDup = findDuplicate(dupSpeciesHead, maf_mafLine_getSpecies(ml));
if (thisDup == NULL) {
// first instance of species, add to list
if (dupSpeciesHead == NULL) {
dupSpeciesHead = newDuplicate();
d = dupSpeciesHead;
} else {
d->next = newDuplicate();
d = d->next;
}
d->species = de_strdup(maf_mafLine_getSpecies(ml));
// create the mafline linked list
d->headScoredMaf = newScoredMafLine();
d->headScoredMaf->mafLine = ml;
d->tailScoredMaf = d->headScoredMaf;
} else {
// this sequence is a duplicate, extend the duplicate list.
containsDuplicates = true;
++(thisDup->numSequences);
scoredMafLine_t *sml = thisDup->tailScoredMaf;
sml->next = newScoredMafLine();
sml = sml->next;
sml->mafLine = ml;
thisDup->tailScoredMaf = sml;
}
++index;
ml = maf_mafLine_getNext(ml);
}
if (!containsDuplicates) {
reportBlock(block);
destroyStringArray(species, n);
destroyStringArray(sequences, n);
destroyDuplicates(dupSpeciesHead);
return;
}
// this block contains duplicates
char *consensus = (char *) de_malloc(longestLine(block) + 1);
consensus[0] = '\0';
buildConsensus(consensus, sequences, n,
maf_mafLine_getLineNumber(maf_mafBlock_getHeadLine(block))); // lineno used for error reporting
findBestDupes(dupSpeciesHead, consensus);
reportBlockWithDuplicates(block, dupSpeciesHead);
// clean up
destroyStringArray(species, n);
destroyStringArray(sequences, n);
destroyDuplicates(dupSpeciesHead);
free(consensus);
}
void checkBlock(mafBlock_t *block) {
// read through each line of a mafBlock and filter duplicates.
// Report the top scoring duplication only.
unsigned n = maf_numberOfSequencesMafLineList(block->headLine);
char **species = (char **) de_malloc(sizeof(char *) * n);
char **sequences = (char **) de_malloc(sizeof(char *) * n);
int index = 0;
bool containsDuplicates = false;
mafLine_t *m = block->headLine;
duplicate_t *d = NULL, *dupSpeciesHead = NULL;
while (m != NULL) {
if (m->type != 's') {
// skip non-sequence lines
m = m->next;
continue;
}
species[index] = (char *) de_malloc(kMaxSeqName);
sequences[index] = (char *) de_malloc(strlen(m->sequence) + 1);
strcpy(species[index], m->species);
strcpy(sequences[index], m->sequence);
duplicate_t *thisDup = findDuplicate(dupSpeciesHead, m->species);
if (thisDup == NULL) {
// add new duplicate species
debug("adding new species %s\n", m->species);
if (dupSpeciesHead == NULL) {
dupSpeciesHead = newDuplicate();
d = dupSpeciesHead;
} else {
d->next = newDuplicate();
d = d->next;
}
d->species = (char *) de_malloc(kMaxSeqName);
strcpy(d->species, m->species);
// create the mafline linked list
d->headScoredMaf = newScoredMafLine();
d->headScoredMaf->mafLine = m;
} else {
// this sequence is a duplicate, extend the duplicate list.
debug("extending duplicate on species %s\n", m->species);
containsDuplicates = true;
scoredMafLine_t *ml = thisDup->headScoredMaf;
while (ml->next != NULL)
ml = ml->next;
ml->next = newScoredMafLine();
ml = ml->next;
ml->mafLine = m;
}
++index;
m = m->next;
}
if (!containsDuplicates) {
reportBlock(block);
destroyStringArray(species, n);
destroyStringArray(sequences, n);
destroyDuplicates(dupSpeciesHead);
return;
}
// this block contains duplicates
char *consensus = (char *) de_malloc(longestLine(block) + 1);
consensus[0] = '\0';
buildConsensus(consensus, sequences, n, block->headLine->lineNumber);
findBestDupes(dupSpeciesHead, consensus);
reportBlockWithDuplicates(block, dupSpeciesHead);
destroyStringArray(species, n);
destroyStringArray(sequences, n);
destroyDuplicates(dupSpeciesHead);
free(consensus);
}