void testCap_segmentCoordinatesReverseStrand(CuTest* testCase) {
/*
* Tests the coordinates of an segment and its 5 and 3 prime caps.
*/
cactusCapTestSetup();
Block *block = block_construct(3, flower);
Segment *segment = segment_construct2(block, 2, 0, sequence);
Cap *_5Cap = segment_get5Cap(segment);
Cap *_3Cap = segment_get3Cap(segment);
CuAssertTrue(testCase, cap_getSide(_5Cap));
CuAssertTrue(testCase, !cap_getSide(_3Cap));
CuAssertTrue(testCase, !cap_getStrand(_5Cap));
CuAssertTrue(testCase, !cap_getStrand(_3Cap));
CuAssertIntEquals(testCase, 4, cap_getCoordinate(_5Cap));
CuAssertIntEquals(testCase, 2, cap_getCoordinate(_3Cap));
CuAssertTrue(testCase, !segment_getStrand(segment));
CuAssertIntEquals(testCase, 4, segment_getStart(segment));
CuAssertIntEquals(testCase, 3, segment_getLength(segment));
CuAssertTrue(testCase, !cap_getSide(cap_getReverse(_5Cap)));
CuAssertTrue(testCase, cap_getSide(cap_getReverse(_3Cap)));
CuAssertTrue(testCase, cap_getStrand(cap_getReverse(_5Cap)));
CuAssertTrue(testCase, cap_getStrand(cap_getReverse(_3Cap)));
CuAssertIntEquals(testCase, 4, cap_getCoordinate(cap_getReverse(_5Cap)));
CuAssertIntEquals(testCase, 2, cap_getCoordinate(cap_getReverse(_3Cap)));
CuAssertTrue(testCase, segment_getStrand(segment_getReverse(segment)));
CuAssertIntEquals(testCase, 2, segment_getStart(segment_getReverse(segment)));
CuAssertIntEquals(testCase, 3, segment_getLength(segment_getReverse(segment)));
cactusCapTestTeardown();
}
static void debugScaffoldPaths(stList *haplotypePaths, stHash *haplotypePathToScaffoldPathHash,
stHash *haplotypeToMaximalHaplotypeLengthHash, stList *haplotypeEventStrings, stList *contaminationEventStrings, CapCodeParameters *capCodeParameters) {
stHash *segmentToMaximalHaplotypePathHash = buildSegmentToContigPathHash(haplotypePaths);
for (int64_t i = 0; i < stList_length(haplotypePaths); i++) {
stList *haplotypePath = stList_get(haplotypePaths, i);
assert(stList_length(haplotypePath) > 0);
//Traversing from 5' end..
Segment *_5Segment = stList_get(haplotypePath, 0);
Segment *_3Segment = stList_get(haplotypePath, stList_length(haplotypePath) - 1);
assert(segment_getStrand(_5Segment) == segment_getStrand(_3Segment));
if (!segment_getStrand(_5Segment)) {
Segment *j = _5Segment;
_5Segment = segment_getReverse(_3Segment);
_3Segment = segment_getReverse(j);
}
assert(segment_getStrand(_5Segment));
assert(segment_getStrand(_3Segment));
Cap *_5Cap = segment_get5Cap(_5Segment);
Cap *_3Cap = segment_get3Cap(_3Segment);
if (getAdjacentCapsSegment(_5Cap) != NULL) {
assert(!trueAdjacency(_5Cap, haplotypeEventStrings));
}
if (getAdjacentCapsSegment(_3Cap) != NULL) {
assert(!trueAdjacency(_3Cap, haplotypeEventStrings));
}
debugScaffoldPathsP(_5Cap, haplotypePath,
haplotypePathToScaffoldPathHash, haplotypeToMaximalHaplotypeLengthHash,
segmentToMaximalHaplotypePathHash, haplotypeEventStrings, contaminationEventStrings, capCodeParameters, 1);
debugScaffoldPathsP(_3Cap, haplotypePath,
haplotypePathToScaffoldPathHash, haplotypeToMaximalHaplotypeLengthHash,
segmentToMaximalHaplotypePathHash, haplotypeEventStrings, contaminationEventStrings, capCodeParameters, 0);
}
stHash_destruct(segmentToMaximalHaplotypePathHash);
}
static void getMaximalHaplotypePathsP2(Segment *segment,
stList *maximalHaplotypePath, stSortedSet *segmentSet, stList *eventStrings) {
/*
* Iterate all the way to one end of the contig then start the traversal to define the maximal
* haplotype path.
*/
Cap *_5Cap = segment_get5Cap(segment);
assert(hasCapInEvents(cap_getEnd(segment_get3Cap(segment)), eventStrings)); //isHaplotypeEnd(cap_getEnd(segment_get3Cap(segment))));
if (trueAdjacency(_5Cap, eventStrings)) { //Check that the adjacency is supported by a haplotype path
Segment *otherSegment = getAdjacentCapsSegment(_5Cap);
assert(segment != otherSegment);
assert(segment_getReverse(segment) != otherSegment);
if (otherSegment != NULL) {
assert(stSortedSet_search(segmentSet, otherSegment) == NULL);
assert(stSortedSet_search(segmentSet, segment_getReverse(
otherSegment)) == NULL);
assert(hasCapInEvents(cap_getEnd(segment_get3Cap(otherSegment)), eventStrings)); //isHaplotypeEnd(cap_getEnd(segment_get3Cap(otherSegment))));
getMaximalHaplotypePathsP2(otherSegment, maximalHaplotypePath,
segmentSet, eventStrings);
} else { //We need to start the maximal haplotype recursion
getMaximalHaplotypePathsP3(segment, maximalHaplotypePath,
segmentSet, eventStrings);
}
} else {
getMaximalHaplotypePathsP3(segment, maximalHaplotypePath, segmentSet, eventStrings);
}
}
static stList *getSubstringsForFlowerSegments(stList *flowers) {
/*
* Get the set of substrings representing the strings in the segments of the given flowers.
*/
stList *substrings = stList_construct3(0, (void (*)(void *)) substring_destruct);
for (int64_t i = 0; i < stList_length(flowers); i++) {
Flower *flower = stList_get(flowers, i);
Flower_EndIterator *blockIt = flower_getBlockIterator(flower);
Block *block;
while ((block = flower_getNextBlock(blockIt)) != NULL) {
Block_InstanceIterator *instanceIt = block_getInstanceIterator(block);
Segment *segment;
while ((segment = block_getNext(instanceIt)) != NULL) {
Sequence *sequence;
if ((sequence = segment_getSequence(segment)) != NULL) {
segment = segment_getStrand(segment) ? segment : segment_getReverse(segment);
assert(segment_getLength(segment) > 0);
stList_append(substrings,
substring_construct(sequence_getMetaSequence(sequence)->stringName,
segment_getStart(segment) - sequence_getStart(sequence),
segment_getLength(segment)));
}
}
block_destructInstanceIterator(instanceIt);
}
flower_destructBlockIterator(blockIt);
}
return substrings;
}
static void debugScaffoldPathsP(Cap *cap, stList *haplotypePath,
stHash *haplotypePathToScaffoldPathHash, stHash *haplotypeToMaximalHaplotypeLengthHash,
stHash *segmentToMaximalHaplotypePathHash, stList *haplotypeEventStrings, stList *contaminationEventStrings, CapCodeParameters *capCodeParameters, bool capDir) {
int64_t insertLength;
int64_t deleteLength;
Cap *otherCap;
enum CapCode capCode = getCapCode(cap, &otherCap, haplotypeEventStrings, contaminationEventStrings, &insertLength, &deleteLength, capCodeParameters);
if (capCode == SCAFFOLD_GAP || capCode == AMBIGUITY_GAP) {
Segment *adjacentSegment = getAdjacentCapsSegment(cap);
assert(adjacentSegment != NULL);
while (!hasCapInEvents(cap_getEnd(capDir ? segment_get5Cap(adjacentSegment) : segment_get3Cap(adjacentSegment)), haplotypeEventStrings)) {
adjacentSegment = getAdjacentCapsSegment(capDir ? segment_get5Cap(adjacentSegment) : segment_get3Cap(adjacentSegment));
assert(adjacentSegment != NULL);
}
assert(adjacentSegment != NULL);
assert(hasCapInEvents(cap_getEnd(segment_get5Cap(adjacentSegment)), haplotypeEventStrings)); //isHaplotypeEnd(cap_getEnd(segment_get5Cap(adjacentSegment))));
stIntTuple *j = stHash_search(haplotypeToMaximalHaplotypeLengthHash, haplotypePath);
(void)j;
assert(j != NULL);
stList *adjacentHaplotypePath = stHash_search(segmentToMaximalHaplotypePathHash, adjacentSegment);
if (adjacentHaplotypePath == NULL) {
adjacentHaplotypePath = stHash_search(segmentToMaximalHaplotypePathHash,
segment_getReverse(adjacentSegment));
}
assert(adjacentHaplotypePath != NULL);
assert(adjacentHaplotypePath != haplotypePath);
stIntTuple *k = stHash_search(haplotypeToMaximalHaplotypeLengthHash, adjacentHaplotypePath);
(void)k;
assert(k != NULL);
assert(stIntTuple_get(j, 0) == stIntTuple_get(k, 0));
assert(stHash_search(haplotypePathToScaffoldPathHash, haplotypePath) ==
stHash_search(haplotypePathToScaffoldPathHash, adjacentHaplotypePath));
}
}
static void getMaximalHaplotypePathsCheck(Flower *flower,
stSortedSet *segmentSet, const char *eventString, stList *eventStrings) {
/*
* Do debug checks that the haplotypes paths are well formed.
*/
Flower_SegmentIterator *segmentIt = flower_getSegmentIterator(flower);
Segment *segment;
while ((segment = flower_getNextSegment(segmentIt)) != NULL) {
if (strcmp(event_getHeader(segment_getEvent(segment)), eventString) == 0) {
if (hasCapInEvents(cap_getEnd(segment_get5Cap(segment)), eventStrings)) { //isHaplotypeEnd(cap_getEnd(segment_get5Cap(segment)))) {
assert(stSortedSet_search(segmentSet, segment) != NULL
|| stSortedSet_search(segmentSet, segment_getReverse(
segment)) != NULL);
}
}
}
flower_destructSegmentIterator(segmentIt);
Flower_GroupIterator *groupIt = flower_getGroupIterator(flower);
Group *group;
while ((group = flower_getNextGroup(groupIt)) != NULL) {
if (group_getNestedFlower(group) != NULL) {
getMaximalHaplotypePathsCheck(group_getNestedFlower(group),
segmentSet, eventString, eventStrings);
}
}
flower_destructGroupIterator(groupIt);
}
void block_check(Block *block) {
//Check is connected to flower properly
cactusCheck(flower_getBlock(block_getFlower(block), block_getName(block)) == block_getPositiveOrientation(block));
//Check we have actually set built blocks for the flower..
cactusCheck(flower_builtBlocks(block_getFlower(block)));
//Checks the two ends are block ends.
End *_5End = block_get5End(block);
End *_3End = block_get3End(block);
cactusCheck(end_isBlockEnd(_5End));
cactusCheck(end_isBlockEnd(_3End));
cactusCheck(end_getOrientation(_5End) == block_getOrientation(block));
cactusCheck(end_getOrientation(_3End) == block_getOrientation(block));
cactusCheck(end_getBlock(_5End) == block);
cactusCheck(end_getBlock(_3End) == block);
cactusCheck(end_getSide(_5End)); //Check the sides of the ends are consistent.
cactusCheck(!end_getSide(_3End));
cactusCheck(block_getLength(block) > 0); //check block has non-zero length
//Check reverse
Block *rBlock = block_getReverse(block);
cactusCheck(rBlock != NULL);
cactusCheck(block_getReverse(block) == rBlock);
cactusCheck(block_getOrientation(block) == !block_getOrientation(rBlock));
cactusCheck(block_getLength(block) == block_getLength(rBlock));
cactusCheck(block_get5End(block) == end_getReverse(block_get3End(rBlock)));
cactusCheck(block_get3End(block) == end_getReverse(block_get5End(rBlock)));
cactusCheck(block_getInstanceNumber(block) == block_getInstanceNumber(rBlock));
if(block_getInstanceNumber(block) > 0) {
cactusCheck(block_getFirst(block) == segment_getReverse(block_getFirst(rBlock)));
if(block_getRootInstance(block) == NULL) {
cactusCheck(block_getRootInstance(rBlock) == NULL);
}
else {
cactusCheck(block_getRootInstance(block) == segment_getReverse(block_getRootInstance(rBlock)));
}
}
//For each segment calls segment_check.
Block_InstanceIterator *iterator = block_getInstanceIterator(block);
Segment *segment;
while((segment = block_getNext(iterator)) != NULL) {
segment_check(segment);
}
block_destructInstanceIterator(iterator);
}
void testBlock_getFirst(CuTest* testCase) {
cactusBlockTestSetup();
CuAssertTrue(testCase, block_getFirst(block) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, block_getFirst(block_getReverse(block)) == rootSegment);
Block *block2 = block_construct(1, flower);
CuAssertTrue(testCase, block_getFirst(block2) == NULL);
CuAssertTrue(testCase, block_getFirst(block_getReverse(block2)) == NULL);
cactusBlockTestTeardown();
}
void testBlock_getSegmentForEvent(CuTest* testCase) {
cactusBlockTestSetup();
CuAssertPtrEquals(testCase, block_getSegmentForEvent(block_getReverse(block), event_getName(rootEvent)), rootSegment);
Segment *segment = block_getSegmentForEvent(block, event_getName(leafEvent));
CuAssertTrue(testCase, segment == leaf1Segment || segment == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getSegmentForEvent(block, NULL_NAME) == NULL);
cactusBlockTestTeardown();
}
void testBlock_getSetRootInstance(CuTest *testCase) {
cactusBlockTestSetup();
Block *block2 = block_construct(1, flower);
CuAssertTrue(testCase, block_getRootInstance(block2) == NULL);
block_destruct(block2);
//block_setRootInstance(block, segment_getReverse(rootSegment)); //set in the constructor code of the test.
CuAssertTrue(testCase, block_getRootInstance(block) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, end_getRootInstance(block_get5End(block)) == segment_get5Cap(segment_getReverse(rootSegment)));
CuAssertTrue(testCase, end_getRootInstance(block_get3End(block)) == segment_get3Cap(segment_getReverse(rootSegment)));
cactusBlockTestTeardown();
}
void testBlock_serialisation(CuTest* testCase) {
cactusBlockTestSetup();
Name rootInstanceName = segment_getName(rootSegment);
Name leaf1InstanceName = segment_getName(leaf1Segment);
Name leaf2InstanceName = segment_getName(leaf2Segment);
int64_t i;
void
*vA =
binaryRepresentation_makeBinaryRepresentation(block,
(void(*)(void *, void(*)(const void *, size_t,
size_t))) block_writeBinaryRepresentation,
&i);
CuAssertTrue(testCase, i > 0);
block_destruct(block);
void *vA2 = vA;
block = block_loadFromBinaryRepresentation(&vA2, flower);
rootSegment
= segment_getReverse(block_getInstance(block, rootInstanceName));
leaf1Segment = block_getInstance(block, leaf1InstanceName);
leaf2Segment = segment_getReverse(block_getInstance(block,
leaf2InstanceName));
free(vA);
nestedTest = 1;
testBlock_getName(testCase);
testBlock_getOrientation(testCase);
testBlock_getReverse(testCase);
testBlock_getLength(testCase);
testBlock_getFlower(testCase);
testBlock_getLeftEnd(testCase);
testBlock_getRightEnd(testCase);
testBlock_getSetRootInstance(testCase);
testBlock_getInstanceNumber(testCase);
testBlock_getInstance(testCase);
testBlock_getFirst(testCase);
testBlock_instanceIterator(testCase);
testBlock_makeNewickString(testCase);
testBlock_getChain(testCase);
testBlock_getSegmentForEvent(testCase);
nestedTest = 0;
cactusBlockTestTeardown();
}
void testBlock_getInstance(CuTest* testCase) {
cactusBlockTestSetup();
CuAssertTrue(testCase, block_getInstance(block, segment_getName(rootSegment)) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, block_getInstance(block, segment_getName(leaf1Segment)) == leaf1Segment);
CuAssertTrue(testCase, block_getInstance(block, segment_getName(leaf2Segment)) == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getInstance(block_getReverse(block), segment_getName(rootSegment)) == rootSegment);
CuAssertTrue(testCase, block_getInstance(block_getReverse(block), segment_getName(leaf1Segment)) == segment_getReverse(leaf1Segment));
CuAssertTrue(testCase, block_getInstance(block_getReverse(block), segment_getName(leaf2Segment)) == leaf2Segment);
cactusBlockTestTeardown();
}
void testBlock_instanceIterator(CuTest* testCase) {
cactusBlockTestSetup();
Block_InstanceIterator *iterator;
iterator = block_getInstanceIterator(block);
CuAssertTrue(testCase, iterator != NULL);
CuAssertTrue(testCase, block_getNext(iterator) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, block_getNext(iterator) == leaf1Segment);
Block_InstanceIterator *iterator2 = block_copyInstanceIterator(iterator);
CuAssertTrue(testCase, block_getNext(iterator) == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getNext(iterator) == NULL);
CuAssertTrue(testCase, block_getPrevious(iterator) == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getPrevious(iterator) == leaf1Segment);
CuAssertTrue(testCase, block_getPrevious(iterator) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, block_getPrevious(iterator) == NULL);
CuAssertTrue(testCase, block_getNext(iterator2) == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getNext(iterator2) == NULL);
CuAssertTrue(testCase, block_getPrevious(iterator2) == segment_getReverse(leaf2Segment));
CuAssertTrue(testCase, block_getPrevious(iterator2) == leaf1Segment);
CuAssertTrue(testCase, block_getPrevious(iterator2) == segment_getReverse(rootSegment));
CuAssertTrue(testCase, block_getPrevious(iterator2) == NULL);
block_destructInstanceIterator(iterator);
block_destructInstanceIterator(iterator2);
iterator = block_getInstanceIterator(block_getReverse(block));
CuAssertTrue(testCase, block_getNext(iterator) == rootSegment);
CuAssertTrue(testCase, block_getNext(iterator) == segment_getReverse(leaf1Segment));
CuAssertTrue(testCase, block_getNext(iterator) == leaf2Segment);
CuAssertTrue(testCase, block_getNext(iterator) == NULL);
CuAssertTrue(testCase, block_getPrevious(iterator) == leaf2Segment);
CuAssertTrue(testCase, block_getPrevious(iterator) == segment_getReverse(leaf1Segment));
CuAssertTrue(testCase, block_getPrevious(iterator) == rootSegment);
CuAssertTrue(testCase, block_getPrevious(iterator) == NULL);
block_destructInstanceIterator(iterator);
cactusBlockTestTeardown();
}
static void getMaximalHaplotypePathsP3(Segment *segment,
stList *maximalHaplotypePath, stSortedSet *segmentSet, stList *eventStrings) {
stList_append(maximalHaplotypePath, segment);
assert(stSortedSet_search(segmentSet, segment) == NULL);
assert(stSortedSet_search(segmentSet, segment_getReverse(segment)) == NULL);
stSortedSet_insert(segmentSet, segment);
Cap *_3Cap = segment_get3Cap(segment);
if (trueAdjacency(_3Cap, eventStrings)) { //Continue on..
Segment *otherSegment = getAdjacentCapsSegment(_3Cap);
if (otherSegment != NULL) {
getMaximalHaplotypePathsP3(otherSegment, maximalHaplotypePath,
segmentSet, eventStrings);
}
}
}
stHash *buildSegmentToContigPathHash(stList *maximalHaplotypePaths) {
stHash *segmentToMaximalHaplotypePathHash = stHash_construct();
for (int64_t i = 0; i < stList_length(maximalHaplotypePaths); i++) {
stList *maximalHaplotypePath = stList_get(maximalHaplotypePaths, i);
assert(stList_length(maximalHaplotypePath) > 0);
for (int64_t j = 0; j < stList_length(maximalHaplotypePath); j++) {
Segment *segment = stList_get(maximalHaplotypePath, j);
assert(stHash_search(segmentToMaximalHaplotypePathHash, segment)
== NULL);
assert(stHash_search(segmentToMaximalHaplotypePathHash,
segment_getReverse(segment)) == NULL);
stHash_insert(segmentToMaximalHaplotypePathHash, segment,
maximalHaplotypePath);
}
}
return segmentToMaximalHaplotypePathHash;
}
static int64_t getBoundingNs(Cap *cap) {
assert(cap != NULL);
Segment *segment = getCapsSegment(cap);
if (segment == NULL) {
return 0;
}
Cap *_5TerminalCap = getTerminalCap(segment_get5Cap(segment));
Cap *_3TerminalCap = getTerminalCap(segment_get3Cap(segment));
(void)_3TerminalCap;
assert(_5TerminalCap != NULL);
assert(_3TerminalCap != NULL);
//return 0;
if (cap_getName(_5TerminalCap) == cap_getName(cap)) {
return getBoundingNsP(segment);
} else {
assert(cap_getName(_3TerminalCap) == cap_getName(cap));
return getBoundingNsP(segment_getReverse(segment));
}
}
static bool duplicated(Segment *segment) {
Sequence *sequence = segment_getSequence(segment);
assert(sequence != NULL);
MetaSequence *metaSequence = sequence_getMetaSequence(sequence);
Block *block = segment_getBlock(segment);
Block_InstanceIterator *it = block_getInstanceIterator(block);
Segment *segment2;
while((segment2 = block_getNext(it)) != NULL) {
if(segment != segment2) {
assert(segment != segment_getReverse(segment2));
Sequence *sequence2 = segment_getSequence(segment2);
if(sequence2 != NULL && sequence_getMetaSequence(sequence2) == metaSequence) {
block_destructInstanceIterator(it);
return 1;
}
}
}
block_destructInstanceIterator(it);
return 0;
}
static void getMaximalHaplotypePathsP(Flower *flower,
stList *maximalHaplotypePaths, stSortedSet *segmentSet,
const char *eventString,
stList *eventStrings) {
/*
* Iterate through the segments in this flower.
*/
Flower_SegmentIterator *segmentIt = flower_getSegmentIterator(flower);
Segment *segment;
while ((segment = flower_getNextSegment(segmentIt)) != NULL) {
if (stSortedSet_search(segmentSet, segment) == NULL
&& stSortedSet_search(segmentSet, segment_getReverse(segment))
== NULL) { //Check we haven't yet seen this segment
if (strcmp(event_getHeader(segment_getEvent(segment)), eventString)
== 0) { //Check if the segment is in the assembly
if (hasCapInEvents(cap_getEnd(segment_get5Cap(segment)), eventStrings)) { //Is a block in a haplotype segment
assert(hasCapInEvents(cap_getEnd(segment_get3Cap(segment)), eventStrings)); //isHaplotypeEnd(cap_getEnd(segment_get3Cap(segment))));
stList *maximalHaplotypePath = stList_construct();
stList_append(maximalHaplotypePaths, maximalHaplotypePath);
getMaximalHaplotypePathsP2(segment, maximalHaplotypePath,
segmentSet, eventStrings);
} else {
assert(!hasCapInEvents(cap_getEnd(segment_get3Cap(segment)), eventStrings));//assert(!isHaplotypeEnd(cap_getEnd(segment_get3Cap(segment))));
}
}
}
}
flower_destructSegmentIterator(segmentIt);
/*
* Now recurse on the contained flowers.
*/
Flower_GroupIterator *groupIt = flower_getGroupIterator(flower);
Group *group;
while ((group = flower_getNextGroup(groupIt)) != NULL) {
if (group_getNestedFlower(group) != NULL) {
getMaximalHaplotypePathsP(group_getNestedFlower(group),
maximalHaplotypePaths, segmentSet, eventString, eventStrings);
}
}
flower_destructGroupIterator(groupIt);
}
static void getOrderedSegmentsP(Flower *flower,
stSortedSet *segments) {
Flower_SegmentIterator *segmentIt = flower_getSegmentIterator(flower);
Segment *segment;
while ((segment = flower_getNextSegment(segmentIt)) != NULL) {
if (!segment_getStrand(segment)) {
segment = segment_getReverse(segment);
}
assert(stSortedSet_search(segments, segment) == NULL);
stSortedSet_insert(segments, segment);
}
flower_destructSegmentIterator(segmentIt);
//Recurse over the flowers
Flower_GroupIterator *groupIt = flower_getGroupIterator(flower);
Group *group;
while ((group = flower_getNextGroup(groupIt)) != NULL) {
if (group_getNestedFlower(group) != NULL) {
getOrderedSegmentsP(group_getNestedFlower(group),
segments);
}
}
flower_destructGroupIterator(groupIt);
}
Segment *block_getInstanceP(Block *block, Segment *connectedSegment) {
return block_getOrientation(block) || connectedSegment == NULL ? connectedSegment : segment_getReverse(connectedSegment);
}
void testCap_getSegment(CuTest* testCase) {
cactusCapTestSetup();
Block *block = block_construct(2, flower);
Segment *segment = segment_construct(block, rootEvent);
CuAssertTrue(testCase, cap_getSegment(segment_get5Cap(segment)) == segment);
CuAssertTrue(testCase, cap_getSegment(segment_get3Cap(segment)) == segment);
CuAssertTrue(testCase, cap_getOrientation(segment_get5Cap(segment)) == segment_getOrientation(segment));
CuAssertTrue(testCase, cap_getOrientation(segment_get3Cap(segment)) == segment_getOrientation(segment));
CuAssertTrue(testCase, cap_getSegment(cap_getReverse(segment_get5Cap(segment))) == segment_getReverse(segment));
CuAssertTrue(testCase, cap_getSegment(cap_getReverse(segment_get3Cap(segment))) == segment_getReverse(segment));
cactusCapTestTeardown();
}
static stHash *getScaffoldPathsP(stList *haplotypePaths, stHash *haplotypePathToScaffoldPathHash,
stList *haplotypeEventStrings, stList *contaminationEventStrings, CapCodeParameters *capCodeParameters) {
stHash *haplotypeToMaximalHaplotypeLengthHash = buildContigPathToContigPathLengthHash(haplotypePaths);
stHash *segmentToMaximalHaplotypePathHash = buildSegmentToContigPathHash(haplotypePaths);
for (int64_t i = 0; i < stList_length(haplotypePaths); i++) {
stSortedSet *bucket = stSortedSet_construct();
stHash_insert(haplotypePathToScaffoldPathHash, stList_get(haplotypePaths, i), bucket);
stSortedSet_insert(bucket, stList_get(haplotypePaths, i));
}
for (int64_t i = 0; i < stList_length(haplotypePaths); i++) {
stList *haplotypePath = stList_get(haplotypePaths, i);
assert(stList_length(haplotypePath) > 0);
Segment *_5Segment = stList_get(haplotypePath, 0);
if (!segment_getStrand(_5Segment)) {
_5Segment = segment_getReverse(stList_get(haplotypePath, stList_length(haplotypePath) - 1));
}
assert(segment_getStrand(_5Segment));
if (getAdjacentCapsSegment(segment_get5Cap(_5Segment)) != NULL) {
assert(!trueAdjacency(segment_get5Cap(_5Segment), haplotypeEventStrings));
}
int64_t insertLength;
int64_t deleteLength;
Cap *otherCap;
enum CapCode _5CapCode = getCapCode(segment_get5Cap(_5Segment), &otherCap, haplotypeEventStrings, contaminationEventStrings, &insertLength, &deleteLength, capCodeParameters);
if (_5CapCode == SCAFFOLD_GAP || _5CapCode == AMBIGUITY_GAP) {
assert(stHash_search(haplotypeToMaximalHaplotypeLengthHash, haplotypePath) != NULL);
int64_t j = stIntTuple_get(stHash_search(haplotypeToMaximalHaplotypeLengthHash, haplotypePath), 0);
Segment *adjacentSegment = getAdjacentCapsSegment(segment_get5Cap(_5Segment));
assert(adjacentSegment != NULL);
while (!hasCapInEvents(cap_getEnd(segment_get5Cap(adjacentSegment)), haplotypeEventStrings)) { //is not a haplotype end
adjacentSegment = getAdjacentCapsSegment(segment_get5Cap(adjacentSegment));
assert(adjacentSegment != NULL);
}
assert(adjacentSegment != NULL);
assert(hasCapInEvents(cap_getEnd(segment_get5Cap(adjacentSegment)), haplotypeEventStrings)); //is a haplotype end
stList *adjacentHaplotypePath = stHash_search(segmentToMaximalHaplotypePathHash, adjacentSegment);
if (adjacentHaplotypePath == NULL) {
adjacentHaplotypePath = stHash_search(segmentToMaximalHaplotypePathHash, segment_getReverse(
adjacentSegment));
}
assert(adjacentHaplotypePath != NULL);
assert(adjacentHaplotypePath != haplotypePath);
assert(stHash_search(haplotypeToMaximalHaplotypeLengthHash, adjacentHaplotypePath) != NULL);
int64_t k = stIntTuple_get(stHash_search(haplotypeToMaximalHaplotypeLengthHash, adjacentHaplotypePath), 0);
//Now merge the buckets and make new int tuples..
stSortedSet *bucket1 = stHash_search(haplotypePathToScaffoldPathHash, haplotypePath);
stSortedSet *bucket2 = stHash_search(haplotypePathToScaffoldPathHash, adjacentHaplotypePath);
assert(bucket1 != NULL);
assert(bucket2 != NULL);
assert(bucket1 != bucket2);
stSortedSet *bucket3 = stSortedSet_getUnion(bucket1, bucket2);
stSortedSetIterator *bucketIt = stSortedSet_getIterator(bucket3);
stList *l;
while ((l = stSortedSet_getNext(bucketIt)) != NULL) {
//Do the bucket first
assert(stHash_search(haplotypePathToScaffoldPathHash, l) == bucket1 || stHash_search(haplotypePathToScaffoldPathHash, l) == bucket2);
stHash_remove(haplotypePathToScaffoldPathHash, l);
stHash_insert(haplotypePathToScaffoldPathHash, l, bucket3);
//Now the length
stIntTuple *m = stHash_remove(haplotypeToMaximalHaplotypeLengthHash, l);
assert(m != NULL);
assert(stIntTuple_get(m, 0) == j || stIntTuple_get(m, 0) == k);
stHash_insert(haplotypeToMaximalHaplotypeLengthHash, l, stIntTuple_construct1( j + k));
stIntTuple_destruct(m);
}
assert(stHash_search(haplotypePathToScaffoldPathHash, haplotypePath) == bucket3);
assert(stHash_search(haplotypePathToScaffoldPathHash, adjacentHaplotypePath) == bucket3);
stSortedSet_destructIterator(bucketIt);
}
}
stHash_destruct(segmentToMaximalHaplotypePathHash);
return haplotypeToMaximalHaplotypeLengthHash;
}