void TopSegmentIsGapTest::createCallBack(Alignment *alignment) {
size_t numSequences = 3;
vector<Sequence::Info> seqVec(numSequences);
BottomSegmentIteratorPtr bi;
BottomSegmentStruct bs;
TopSegmentIteratorPtr ti;
TopSegmentStruct ts;
Genome *parent1 = alignment->addRootGenome("parent1");
Genome *child1 = alignment->addLeafGenome("child1", "parent1", 1);
// set up two genomes. each with three sequences. each sequence
// with 5 segments of length two. start with segment i in parent
// aligned with segment i in child.
for (size_t i = 0; i < numSequences; ++i) {
string name = "Sequence" + std::to_string(i);
seqVec[i] = Sequence::Info(name, 10, 5, 5);
}
parent1->setDimensions(seqVec);
child1->setDimensions(seqVec);
for (bi = parent1->getBottomSegmentIterator(); not bi->atEnd(); bi->toRight()) {
bs.set(bi->getBottomSegment()->getArrayIndex() * 2, 2);
bs._children.clear();
bs._children.push_back(pair<hal_size_t, bool>(bi->getBottomSegment()->getArrayIndex(), false));
bs.applyTo(bi);
}
for (ti = child1->getTopSegmentIterator(); not ti->atEnd(); ti->toRight()) {
ts.set(ti->getTopSegment()->getArrayIndex() * 2, 2, ti->getTopSegment()->getArrayIndex());
ts.applyTo(ti);
}
// insertion in middle (8th top segment)
bi = parent1->getBottomSegmentIterator(8);
ti = child1->getTopSegmentIterator(8);
assert(bi->getBottomSegment()->getChildIndex(0) == 8 && ti->getTopSegment()->getParentIndex() == 8);
bi->getBottomSegment()->setChildIndex(0, 9);
ti->getTopSegment()->setParentIndex(NULL_INDEX);
ti->toRight();
ti->getTopSegment()->setParentIndex(8);
// insertion at begining (10th top segment)
bi = parent1->getBottomSegmentIterator(10);
ti = child1->getTopSegmentIterator(10);
assert(bi->getBottomSegment()->getChildIndex(0) == 10 && ti->getTopSegment()->getParentIndex() == 10);
bi->getBottomSegment()->setChildIndex(0, 11);
ti->getTopSegment()->setParentIndex(NULL_INDEX);
ti->toRight();
ti->getTopSegment()->setParentIndex(10);
// just having a null parent is not enough for an insertion
bi = parent1->getBottomSegmentIterator(2);
ti = child1->getTopSegmentIterator(2);
assert(bi->getBottomSegment()->getChildIndex(0) == 2 && ti->getTopSegment()->getParentIndex() == 2);
ti->getTopSegment()->setParentIndex(NULL_INDEX);
}
void SequenceIteratorTest::checkCallBack(const Alignment *alignment) {
const Genome *ancGenome = alignment->openGenome("AncGenome");
hal_size_t numSequences = ancGenome->getNumSequences();
CuAssertTrue(_testCase, numSequences = 1000);
for (SequenceIteratorPtr seqIt = ancGenome->getSequenceIterator(); not seqIt->atEnd(); seqIt->toNext()) {
const Sequence *seq = seqIt->getSequence();
hal_size_t i = seq->getArrayIndex();
TopSegmentIteratorPtr tsIt = seq->getTopSegmentIterator();
hal_size_t numTopSegments = seq->getNumTopSegments();
for (hal_size_t j = 0; j < numTopSegments; ++j) {
TopSegmentIteratorPtr gtsIt = ancGenome->getTopSegmentIterator((i - 1) * 100 + j);
const TopSegment *gsTopSegment = gtsIt->getTopSegment();
const TopSegment *sqTopSegment = tsIt->getTopSegment();
CuAssertTrue(_testCase, gsTopSegment->getArrayIndex() == sqTopSegment->getArrayIndex());
tsIt->toRight();
}
BottomSegmentIteratorPtr bsIt = seq->getBottomSegmentIterator();
hal_size_t numBottomSegments = seq->getNumBottomSegments();
for (hal_size_t j = 0; j < numBottomSegments; ++j) {
BottomSegmentIteratorPtr gbsIt = ancGenome->getBottomSegmentIterator((i - 1) * 100 + j);
const BottomSegment *gsBottomSegment = gbsIt->getBottomSegment();
const BottomSegment *sqBottomSegment = bsIt->getBottomSegment();
CuAssertTrue(_testCase, gsBottomSegment->getArrayIndex() == sqBottomSegment->getArrayIndex());
bsIt->toRight();
}
}
}
void GappedBottomSegmentIterator::toRightNextUngapped(TopSegmentIteratorPtr topSeqIt) const {
while (topSeqIt->tseg()->hasParent() == false && topSeqIt->getLength() <= _gapThreshold) {
if ((!topSeqIt->getReversed() && topSeqIt->getTopSegment()->isLast()) ||
(topSeqIt->getReversed() && topSeqIt->getTopSegment()->isFirst())) {
break;
}
topSeqIt->toRight();
}
}
void TopSegmentSequenceTest::checkCallBack(const Alignment *alignment) {
const Genome *ancGenome = alignment->openGenome("Anc0");
TopSegmentIteratorPtr tsIt = ancGenome->getTopSegmentIterator(100);
CuAssertTrue(_testCase, tsIt->getTopSegment()->getStartPosition() == 500);
CuAssertTrue(_testCase, tsIt->getTopSegment()->getLength() == 9);
string seq;
tsIt->getString(seq);
CuAssertTrue(_testCase, seq == "CACACATTC");
tsIt->toReverse();
tsIt->getString(seq);
CuAssertTrue(_testCase, seq == "GAATGTGTG");
}
void TopSegmentSimpleIteratorTest::checkCallBack(const Alignment *alignment) {
const Genome *ancGenome = alignment->openGenome("Anc0");
CuAssertTrue(_testCase, ancGenome->getNumTopSegments() == _topSegments.size());
TopSegmentIteratorPtr tsIt = ancGenome->getTopSegmentIterator(0);
for (size_t i = 0; i < ancGenome->getNumTopSegments(); ++i) {
CuAssertTrue(_testCase, (size_t)tsIt->getTopSegment()->getArrayIndex() == i);
_topSegments[i].compareTo(tsIt, _testCase);
tsIt->toRight();
}
tsIt = ancGenome->getTopSegmentIterator(ancGenome->getNumTopSegments() - 1);
for (hal_index_t i = ancGenome->getNumTopSegments() - 1; i >= 0; --i) {
CuAssertTrue(_testCase, tsIt->getTopSegment()->getArrayIndex() == i);
_topSegments[i].compareTo(tsIt, _testCase);
tsIt->toLeft();
}
tsIt = ancGenome->getTopSegmentIterator(0);
tsIt->slice(0, tsIt->getLength() - 1);
for (hal_index_t i = 0; i < (hal_index_t)ancGenome->getSequenceLength(); ++i) {
CuAssertTrue(_testCase, tsIt->getLength() == 1);
CuAssertTrue(_testCase, tsIt->getStartPosition() == i);
tsIt->toRight(tsIt->getStartPosition() + 1);
}
tsIt = ancGenome->getTopSegmentIterator(ancGenome->getNumTopSegments() - 1);
tsIt->slice(tsIt->getLength() - 1, 0);
for (hal_index_t i = ancGenome->getSequenceLength() - 1; i >= 0; --i) {
CuAssertTrue(_testCase, tsIt->getLength() == 1);
CuAssertTrue(_testCase, tsIt->getStartPosition() == i);
tsIt->toLeft(tsIt->getStartPosition() - 1);
}
tsIt = ancGenome->getTopSegmentIterator(0);
tsIt->toReverse();
CuAssertTrue(_testCase, tsIt->getReversed() == true);
tsIt->slice(tsIt->getLength() - 1, 0);
for (hal_index_t i = 0; i < (hal_index_t)ancGenome->getSequenceLength(); ++i) {
CuAssertTrue(_testCase, tsIt->getLength() == 1);
CuAssertTrue(_testCase, tsIt->getStartPosition() == i);
tsIt->toLeft(tsIt->getStartPosition() + 1);
}
tsIt = ancGenome->getTopSegmentIterator(ancGenome->getNumTopSegments() - 1);
tsIt->toReverse();
tsIt->slice(0, tsIt->getLength() - 1);
for (hal_index_t i = ancGenome->getSequenceLength() - 1; i >= 0; --i) {
CuAssertTrue(_testCase, tsIt->getLength() == 1);
CuAssertTrue(_testCase, tsIt->getStartPosition() == i);
tsIt->toRight(tsIt->getStartPosition() - 1);
}
}
void TopSegmentSimpleIteratorTest::createCallBack(Alignment *alignment) {
Genome *ancGenome = alignment->addRootGenome("Anc0", 0);
size_t numChildren = 9;
for (size_t i = 0; i < numChildren; ++i) {
alignment->addLeafGenome("Leaf" + std::to_string(i), "Anc0", 0.1);
}
vector<Sequence::Info> seqVec(1);
seqVec[0] = Sequence::Info("Sequence", 1000000, 5000, 10000);
ancGenome->setDimensions(seqVec);
CuAssertTrue(_testCase, ancGenome->getNumChildren() == numChildren);
_topSegments.clear();
for (size_t i = 0; i < ancGenome->getNumTopSegments(); ++i) {
TopSegmentStruct topSeg;
topSeg.setRandom();
topSeg._length = ancGenome->getSequenceLength() / ancGenome->getNumTopSegments();
topSeg._startPosition = i * topSeg._length;
_topSegments.push_back(topSeg);
}
TopSegmentIteratorPtr tsIt = ancGenome->getTopSegmentIterator(0);
for (size_t i = 0; not tsIt->atEnd(); tsIt->toRight(), ++i) {
CuAssertTrue(_testCase, (size_t)tsIt->getTopSegment()->getArrayIndex() == i);
_topSegments[i].applyTo(tsIt);
}
}
void TopSegmentStruct::compareTo(TopSegmentIteratorPtr it, CuTest *testCase) const {
const TopSegment *seg = it->getTopSegment();
CuAssertTrue(testCase, _length == seg->getLength());
CuAssertTrue(testCase, _startPosition == seg->getStartPosition());
CuAssertTrue(testCase, _nextParalogyIndex == seg->getNextParalogyIndex());
CuAssertTrue(testCase, _parentIndex == seg->getParentIndex());
CuAssertTrue(testCase, _bottomParseIndex == seg->getBottomParseIndex());
}
void TopSegmentStruct::applyTo(TopSegmentIteratorPtr it) const {
TopSegment *seg = it->getTopSegment();
seg->setCoordinates(_startPosition, _length);
seg->setNextParalogyIndex(_nextParalogyIndex);
seg->setParentIndex(_parentIndex);
seg->setParentReversed(_parentReversed);
seg->setBottomParseIndex(_bottomParseIndex);
}
void Genome::fixParseInfo()
{
if (getParent() == NULL || getNumChildren() == 0)
{
return;
}
// copied from CactusHalConverter::updateRootParseInfo() in
// cactus2hal/src/cactusHalConverter.cpp
BottomSegmentIteratorPtr bottomIterator =
getBottomSegmentIterator();
TopSegmentIteratorPtr topIterator = getTopSegmentIterator();
BottomSegmentIteratorConstPtr bend = getBottomSegmentEndIterator();
TopSegmentIteratorConstPtr tend = getTopSegmentEndIterator();
int top = 0, bot = 0;
while (bottomIterator != bend && topIterator != tend)
{
bool bright = false;
bool tright = false;
BottomSegment* bseg = bottomIterator->getBottomSegment();
TopSegment* tseg = topIterator->getTopSegment();
hal_index_t bstart = bseg->getStartPosition();
hal_index_t bendidx = bstart + (hal_index_t)bseg->getLength();
hal_index_t tstart = tseg->getStartPosition();
hal_index_t tendidx = tstart + (hal_index_t)tseg->getLength();
if (bstart >= tstart && bstart < tendidx)
{
bseg->setTopParseIndex(tseg->getArrayIndex());
}
if (bendidx <= tendidx || bstart == bendidx)
{
bright = true;
}
if (tstart >= bstart && tstart < bendidx)
{
tseg->setBottomParseIndex(bseg->getArrayIndex());
}
if (tendidx <= bendidx || tstart == tendidx)
{
tright = true;
}
assert(bright || tright);
if (bright == true)
{
bot += 1;
bottomIterator->toRight();
}
if (tright == true)
{
top += 1;
topIterator->toRight();
}
}
}
void TopSegmentSequenceTest::createCallBack(Alignment *alignment) {
Genome *ancGenome = alignment->addRootGenome("Anc0", 0);
vector<Sequence::Info> seqVec(1);
seqVec[0] = Sequence::Info("Sequence", 1000000, 5000, 700000);
ancGenome->setDimensions(seqVec);
ancGenome->setSubString("CACACATTC", 500, 9);
TopSegmentIteratorPtr tsIt = ancGenome->getTopSegmentIterator(100);
tsIt->getTopSegment()->setCoordinates(500, 9);
}
void TopSegmentIteratorToSiteTest::checkGenome(const Genome *genome) {
TopSegmentIteratorPtr ti = genome->getTopSegmentIterator();
for (hal_index_t pos = 0; pos < (hal_index_t)genome->getSequenceLength(); ++pos) {
ti->toSite(pos);
CuAssertTrue(_testCase, ti->getStartPosition() == pos);
CuAssertTrue(_testCase, ti->getLength() == 1);
ti->toSite(pos, false);
CuAssertTrue(_testCase, pos >= ti->getStartPosition() && pos < ti->getStartPosition() + (hal_index_t)ti->getLength());
CuAssertTrue(_testCase, ti->getLength() == ti->getTopSegment()->getLength());
}
}
void GappedSegmentSimpleIteratorTest::createCallBack(AlignmentPtr alignment)
{
addIdenticalParentChild(alignment, 2, 100, 5);
Genome* parent = alignment->openGenome(alignment->getRootName());
Genome* child = parent->getChild(0);
TopSegmentIteratorPtr ti = child->getTopSegmentIterator();
BottomSegmentIteratorPtr bi = parent->getBottomSegmentIterator();
int i = 0;
while (ti != child->getTopSegmentEndIterator())
{
if (i++ % 2)
{
ti->getTopSegment()->setParentReversed(true);
bi->getBottomSegment()->setChildReversed(0, true);
}
ti->toRight();
bi->toRight();
}
}