diff --git a/src/intersectFile/intersectFile.cpp b/src/intersectFile/intersectFile.cpp
index e61f4d23165c587cee7c01453964ac56ff9fbfd9..32643ac9fc851a20c5ef92b625ae4e31067976e4 100644
--- a/src/intersectFile/intersectFile.cpp
+++ b/src/intersectFile/intersectFile.cpp
@@ -97,7 +97,6 @@ bool FileIntersect::processUnsortedFiles()
}
queryFRM->deleteRecord(queryRecord);
}
- queryFRM->close();
//clean up.
delete binTree;
diff --git a/src/mapFile/mapMain.cpp b/src/mapFile/mapMain.cpp
index f08e56b3905727b3333e4743e53b9bb9e9aaa239..235c1fb72a31362ea755a56fa467492c58a608d1 100644
--- a/src/mapFile/mapMain.cpp
+++ b/src/mapFile/mapMain.cpp
@@ -48,18 +48,29 @@ void map_help(void) {
cerr << "Options: " << endl;
- cerr << "\t-c\t" << "Specify the column from the B file to map onto intervals in A." << endl;
- cerr << "\t\t - Default = 5." << endl << endl;
+ cerr << "\t-c\t" << "Specify columns from the B file to map onto intervals in A." << endl;
+ cerr << "\t\tDefault: 5." << endl;
+ cerr << "\t\tMultiple columns can be specified in a comma-delimited list." << endl << endl;
cerr << "\t-o\t" << "Specify the operation that should be applied to -c." << endl;
- cerr << "\t\t Valid operations:" << endl;
+ cerr << "\t\tValid operations:" << endl;
cerr << "\t\t sum, min, max, absmin, absmax," << endl;
cerr << "\t\t mean, median," << endl;
cerr << "\t\t collapse (i.e., print a comma separated list (duplicates allowed)), " << endl;
cerr << "\t\t distinct (i.e., print a comma separated list (NO duplicates allowed)), " << endl;
cerr << "\t\t count" << endl;
cerr << "\t\t count_distinct (i.e., a count of the unique values in the column), " << endl;
- cerr << "\t\t- Default: sum" << endl << endl;
+ cerr << "\t\tDefault: sum" << endl;
+ cerr << "\t\tMultiple operations can be specified in a comma-delimited list." << endl << endl;
+
+ cerr << "\t\tIf there is only column, but multiple operations, all operations will be" << endl;
+ cerr << "\t\tapplied on that column. Likewise, if there is only one operation, but" << endl;
+ cerr << "multiple columns, that operation will be applied to all columns." << endl;
+ cerr << "\t\tOtherwise, the number of columns must match the the number of operations," << endl;
+ cerr << "and will be applied in respective order." << endl;
+ cerr << "\t\tE.g., \"-c 5,4,6 -o sum,mean,count\" will give the sum of column 5," << endl;
+ cerr << "the mean of column 4, and the count of column 6." << endl;
+ cerr << "\t\tThe order of output columns will match the ordering given in the command." << endl << endl<<endl;
cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
diff --git a/src/utils/BinTree/BinTree.cpp b/src/utils/BinTree/BinTree.cpp
index f5cddd83fa5feef95ac47780770ddb6751266040..253dea2798320bfd7886931213612b2c21931baf 100644
--- a/src/utils/BinTree/BinTree.cpp
+++ b/src/utils/BinTree/BinTree.cpp
@@ -86,13 +86,6 @@ void BinTree::loadDB()
exit(1);
}
}
- _databaseFile->close();
-
- //TBD: give ERROR and return false if tree is empty.
- if (_mainMap.empty()) {
- fprintf(stderr, "ERROR: Tree is empty, no records added.\n");
- exit(1);
- }
}
void BinTree::getHits(Record *record, RecordKeyList &hitSet)
diff --git a/src/utils/Contexts/ContextBase.cpp b/src/utils/Contexts/ContextBase.cpp
index c76d29b45978d8fdc3e3d506cb33eedade6a72cc..55d5b6ad3b25965e26b6872cedc6fc7b637fbe69 100644
--- a/src/utils/Contexts/ContextBase.cpp
+++ b/src/utils/Contexts/ContextBase.cpp
@@ -233,6 +233,13 @@ bool ContextBase::openFiles() {
if (_allFilesOpened) {
return true;
}
+
+ if (_fileNames.size() == 0) {
+ //No input was specified. Error and exit.
+ _errorMsg += "\n***** ERROR: No input file given. Exiting. *****";
+ return false;
+ }
+
_files.resize(_fileNames.size());
for (int i = 0; i < (int)_fileNames.size(); i++) {
diff --git a/src/utils/Contexts/ContextMerge.cpp b/src/utils/Contexts/ContextMerge.cpp
index 5d6c58aac3cb051a8eb485c89be8bb91a033f96b..d17d3bdb6823041c497d5f596a758756e7463a1b 100644
--- a/src/utils/Contexts/ContextMerge.cpp
+++ b/src/utils/Contexts/ContextMerge.cpp
@@ -82,7 +82,30 @@ bool ContextMerge::isValidState()
}
if (_files.size() != 1) {
_errorMsg = "\n***** ERROR: input file not specified. *****";
- // Allow one and only input file for now
+ // Allow only one input file for now
+ return false;
+ }
+
+ //
+ // Tests for stranded merge
+ //
+ if (_desiredStrand != FileRecordMergeMgr::ANY_STRAND) { // requested stranded merge
+ // make sure file has strand.
+ if (!getFile(0)->recordsHaveStrand()) {
+ _errorMsg = "\n***** ERROR: stranded merge requested, but input file records do not have strand. *****";
+ return false;
+ }
+ //make sure file is not VCF.
+ if (!getFile(0)->getFileType() == FileRecordTypeChecker::VCF_FILE_TYPE) {
+ _errorMsg = "\n***** ERROR: stranded merge not supported for VCF files. *****";
+ return false;
+ }
+ }
+
+ //column operations not allowed with BAM input
+ if ((!_keyListOps->getColumns().empty() || !_keyListOps->getOperations().empty()) &&
+ getFile(0)->getFileType() == FileRecordTypeChecker::BAM_FILE_TYPE) {
+ _errorMsg = "\n***** ERROR: stranded merge not supported for VCF files. *****";
return false;
}
return true;
@@ -108,36 +131,25 @@ bool ContextMerge::handle_d() {
bool ContextMerge::handle_n()
{
- //This is the same as telling map "-c any -o count"
- _keyListOps->addColumns("1"); //doesn't really matter which column, but the default column
- //for keyListOps is score, which not every record necessarily has.
- _keyListOps->addOperations("count");
markUsed(_i - _skipFirstArgs);
- return true;
+ _errorMsg = "\n***** ERROR: -n option is deprecated. Please see the documentation for the -c and -o column operation options. *****";
+ return false;
}
bool ContextMerge::handle_nms()
{
- //This is the same as telling map "-c 4 -o collapse"
- _keyListOps->addColumns("4");
- _keyListOps->addOperations("collapse");
markUsed(_i - _skipFirstArgs);
- return true;
+ _errorMsg = "\n***** ERROR: -nms option is deprecated. Please see the documentation for the -c and -o column operation options. *****";
+ return false;
+
}
bool ContextMerge::handle_scores()
{
- if ((_i+1) < _argc) {
- _keyListOps->addColumns("5");
- _keyListOps->addOperations(_argv[_i+1]);
- markUsed(_i - _skipFirstArgs);
- _i++;
- markUsed(_i - _skipFirstArgs);
- return true;
- }
- _errorMsg = "\n***** ERROR: -scores option given, but no operation specified. *****";
-
+ // No longer supporting this deprecated option.
+ markUsed(_i - _skipFirstArgs);
+ _errorMsg = "\n***** ERROR: -scores option is deprecated. Please see the documentation for the -c and -o column operation options. *****";
return false;
}
@@ -149,15 +161,20 @@ bool ContextMerge::handle_s() {
bool ContextMerge::handle_S() {
if ((_i+1) < _argc) {
+ bool validChar = false;
if (_argv[_i+1][0] == '+') {
_desiredStrand = FileRecordMergeMgr::SAME_STRAND_FORWARD;
+ validChar = true;
} else if (_argv[_i+1][0] == '-') {
+ validChar = true;
_desiredStrand = FileRecordMergeMgr::SAME_STRAND_REVERSE;
}
- markUsed(_i - _skipFirstArgs);
- _i++;
- markUsed(_i - _skipFirstArgs);
- return true;
+ if (validChar) {
+ markUsed(_i - _skipFirstArgs);
+ _i++;
+ markUsed(_i - _skipFirstArgs);
+ return true;
+ }
}
_errorMsg = "\n***** ERROR: -S option must be followed by + or -. *****";
return false;
diff --git a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp
index 27f07894c347c2b871201f933287ed410c555bd0..373b8d15a040471a40cb8f42b26ff527c296151f 100644
--- a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp
+++ b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp
@@ -73,7 +73,18 @@ bool BufferedStreamMgr::getTypeData()
if (!_typeChecker.scanBuffer(_currScanBuffer.c_str(), _currScanBuffer.size()) && !_typeChecker.needsMoreData()) {
return false;
} else if (_typeChecker.needsMoreData()) {
- _inputStreamMgr->populateScanBuffer();
+ if (!_inputStreamMgr->populateScanBuffer()) {
+ // We have found a file with just a header. If the file and record type are known,
+ //break here. Otherwise, assign those types to empty file and record type, then break.
+ if ((_typeChecker.getFileType() != FileRecordTypeChecker::UNKNOWN_FILE_TYPE) &&
+ (_typeChecker.getRecordType() != FileRecordTypeChecker::UNKNOWN_RECORD_TYPE)) {
+ break;
+ } else {
+ _typeChecker.setFileType(FileRecordTypeChecker::EMPTY_FILE_TYPE);
+ _typeChecker.setRecordType(FileRecordTypeChecker::EMPTY_RECORD_TYPE);
+ break;
+ }
+ }
_currScanBuffer.append(_inputStreamMgr->getSavedData());
}
} while (_typeChecker.needsMoreData());
diff --git a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp
index 2035b9c6529e8ac97f53766b22c2fd98c8eba56b..5736a5189114df908fb944b9e7f3789c6e00c838 100644
--- a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp
+++ b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp
@@ -125,7 +125,7 @@ int InputStreamMgr::read(char *data, size_t dataSize)
return origRead + _finalInputStream->gcount();
}
-void InputStreamMgr::populateScanBuffer()
+bool InputStreamMgr::populateScanBuffer()
{
_scanBuffer.clear();
_saveDataStr.clear();
@@ -133,8 +133,7 @@ void InputStreamMgr::populateScanBuffer()
int currChar = 0;
while (1) {
if (_isGzipped && _bamRuledOut) {
- readZipChunk();
- return;
+ return readZipChunk();
}
currChar = _pushBackStreamBuf->sbumpc();
//Stop when EOF hit.
@@ -145,7 +144,8 @@ void InputStreamMgr::populateScanBuffer()
_scanBuffer.push_back(currChar);
if (_isGzipped) {
if (!_bamRuledOut && detectBamOrBgzip(numChars, currChar)) {
- return;
+ //we now know the file is in bgzipped format
+ return true;
}
if (numChars == 0) {
continue; //this will only happen when we've just discovered that this
@@ -163,6 +163,9 @@ void InputStreamMgr::populateScanBuffer()
//append it to the savedDataStr.
_scanBuffer.toStr(_saveDataStr, true);
+ if (_numBytesInBuffer == 0) return false;
+ return true;
+
}
bool InputStreamMgr::detectBamOrBgzip(int &numChars, int currChar)
@@ -239,7 +242,7 @@ bool InputStreamMgr::detectBamOrBgzip(int &numChars, int currChar)
return false;
}
-void InputStreamMgr::readZipChunk()
+bool InputStreamMgr::readZipChunk()
{
if (_tmpZipBuf == NULL) {
_tmpZipBuf = new char[SCAN_BUFFER_SIZE +1];
@@ -251,7 +254,8 @@ void InputStreamMgr::readZipChunk()
if ((int)numCharsRead < SCAN_BUFFER_SIZE) {
_streamFinished = true;
}
- return;
+ if (numCharsRead == 0) return false;
+ return true;
}
bool InputStreamMgr::resetStream()
diff --git a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h
index 1c463d37ebf5769c5b4ddf90c3181579fcee1fc3..058a247769c8e6934a19c94e4cf21ab40df5e949 100644
--- a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h
+++ b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h
@@ -30,7 +30,7 @@ public:
// istream *getFinalStream() { return _finalInputStream; }
const BTlist<int> &getScanBuffer() const { return _scanBuffer; }
int getBufferLength() const { return _numBytesInBuffer; }
- void populateScanBuffer();
+ bool populateScanBuffer();
const QuickString &getSavedData() const { return _saveDataStr; }
bool isGzipped() const { return _isGzipped; }
PushBackStreamBuf *getPushBackStreamBuf() const {return _pushBackStreamBuf; }
@@ -65,7 +65,7 @@ private:
BamTools::Internal::BgzfStream *_bgStream;
static const char *FIFO_STRING_LITERAL;
- void readZipChunk();
+ bool readZipChunk();
bool detectBamOrBgzip(int &numChars, int currChar);
// void decompressBuffer();
diff --git a/src/utils/FileRecordTools/FileRecordMgr.cpp b/src/utils/FileRecordTools/FileRecordMgr.cpp
index 0edf73a687a0a8feb0b77ae150f552b94ce610f9..56417fbb4e016fa18cafb5e7c4a142731d86d4a9 100644
--- a/src/utils/FileRecordTools/FileRecordMgr.cpp
+++ b/src/utils/FileRecordTools/FileRecordMgr.cpp
@@ -208,6 +208,7 @@ void FileRecordMgr::deleteRecord(RecordKeyList *keyList) {
void FileRecordMgr::allocateFileReader()
{
switch (_fileType) {
+ case FileRecordTypeChecker::EMPTY_FILE_TYPE:
case FileRecordTypeChecker::SINGLE_LINE_DELIM_TEXT_FILE_TYPE:
case FileRecordTypeChecker::VCF_FILE_TYPE:
_fileReader = new SingleLineDelimTextFileReader(_bufStreamMgr->getTypeChecker().getNumFields(), _bufStreamMgr->getTypeChecker().getDelimChar());
diff --git a/src/utils/FileRecordTools/Records/EmptyRecord.cpp b/src/utils/FileRecordTools/Records/EmptyRecord.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..81d16864b3ac6ce57ac2a901c32a8c21a76d730c
--- /dev/null
+++ b/src/utils/FileRecordTools/Records/EmptyRecord.cpp
@@ -0,0 +1,34 @@
+/*
+ * EmptyRecord.cpp
+ *
+ * Created on: Apr 14, 2014
+ * Author: nek3d
+ */
+
+
+#include "EmptyRecord.h"
+#include "SingleLineDelimTextFileReader.h"
+
+//Technically, there is nothing to do here. Just adding the file
+//to keep make happy.
+
+EmptyRecord::EmptyRecord() {
+
+}
+
+EmptyRecord::~EmptyRecord() {
+
+}
+
+bool EmptyRecord::initFromFile(FileReader *fileReader)
+{
+ SingleLineDelimTextFileReader *sldFileReader = static_cast<SingleLineDelimTextFileReader*>(fileReader);
+ return initFromFile(sldFileReader);
+}
+
+
+bool EmptyRecord::initFromFile(SingleLineDelimTextFileReader *fileReader)
+{
+ return true;
+}
+
diff --git a/src/utils/FileRecordTools/Records/EmptyRecord.h b/src/utils/FileRecordTools/Records/EmptyRecord.h
new file mode 100644
index 0000000000000000000000000000000000000000..29f6f4654a3fe5508d7605e5c92a7fc59c7baacc
--- /dev/null
+++ b/src/utils/FileRecordTools/Records/EmptyRecord.h
@@ -0,0 +1,30 @@
+/*
+ * EmptyRecord.h
+ *
+ * Created on: Apr 14, 2014
+ * Author: nek3d
+ */
+
+#ifndef EMPTYRECORD_H_
+#define EMPTYRECORD_H_
+
+#include "Record.h"
+
+class SingleLineDelimTextFileReader;
+
+class EmptyRecord : public Record {
+public:
+ //This is really just a place holder that doesn't have to do much.
+ //But in order for the rest of the code to not have to contain special
+ //ugly if statements for empty records, it at least has to instantiable,
+ //so any purely virtual functions from the base class will have to be overriden.
+ EmptyRecord();
+ ~EmptyRecord();
+
+ bool initFromFile(FileReader *);
+ virtual bool initFromFile(SingleLineDelimTextFileReader *);
+ int getNumFields() const { return 0; }
+};
+
+
+#endif /* EMPTYRECORD_H_ */
diff --git a/src/utils/FileRecordTools/Records/Makefile b/src/utils/FileRecordTools/Records/Makefile
index 556cc82df90188cbaf17e2e325a178abef9918a0..f471e666f110fa39f3cc4dde99b879ec580e07f1 100644
--- a/src/utils/FileRecordTools/Records/Makefile
+++ b/src/utils/FileRecordTools/Records/Makefile
@@ -17,12 +17,12 @@ INCLUDES = -I$(UTILITIES_DIR)/FileRecordTools/FileReaders/ \
# ----------------------------------
# define our source and object files
# ----------------------------------
-SOURCES= RecordMgr.cpp RecordMgr.h Record.h Record.cpp Bed3Interval.h Bed3Interval.cpp \
+SOURCES= RecordMgr.cpp RecordMgr.h Record.h Record.cpp EmptyRecord.h EmptyRecord.cpp Bed3Interval.h Bed3Interval.cpp \
Bed4Interval.h Bed4Interval.cpp BedGraphInterval.h BedGraphInterval.cpp Bed5Interval.h Bed5Interval.cpp \
Bed6Interval.h Bed6Interval.cpp \
BedPlusInterval.h BedPlusInterval.cpp Bed12Interval.h Bed12Interval.cpp BamRecord.h BamRecord.cpp VcfRecord.h VcfRecord.cpp \
GffRecord.h GffRecord.cpp RecordKeyList.h RecordKeyList.cpp BlockMgr.h BlockMgr.cpp StrandQueue.h StrandQueue.cpp
-OBJECTS= RecordMgr.o Record.o Bed3Interval.o Bed4Interval.o BedGraphInterval.o Bed5Interval.o Bed6Interval.o BedPlusInterval.o Bed12Interval.o BamRecord.o \
+OBJECTS= RecordMgr.o Record.o EmptyRecord.o Bed3Interval.o Bed4Interval.o BedGraphInterval.o Bed5Interval.o Bed6Interval.o BedPlusInterval.o Bed12Interval.o BamRecord.o \
VcfRecord.o GffRecord.o RecordKeyList.o BlockMgr.o StrandQueue.o
_EXT_OBJECTS=ParseTools.o QuickString.o ChromIdLookup.o
EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS))
@@ -38,7 +38,7 @@ $(BUILT_OBJECTS): $(SOURCES)
clean:
@echo "Cleaning up."
- @rm -f $(OBJ_DIR)/RecordMgr.o $(OBJ_DIR)/Record.o $(OBJ_DIR)/Bed3Interval.o $(OBJ_DIR)/Bed4Interval.o \
+ @rm -f $(OBJ_DIR)/RecordMgr.o $(OBJ_DIR)/Record.o $(OBJ_DIR)/EmptyRecord.o $(OBJ_DIR)/Bed3Interval.o $(OBJ_DIR)/Bed4Interval.o \
$(OBJ_DIR)/BedGraphInterval.o $(OBJ_DIR)/Bed5Interval.o $(OBJ_DIR)/Bed6Interval.o \
$(OBJ_DIR)/BedPlusInterval.o $(OBJ_DIR)/Bed12Interval.o $(OBJ_DIR)/BamRecord.o $(OBJ_DIR)/VcfRecord.o $(OBJ_DIR)/GffRecord.o $(OBJ_DIR)/BlockMgr.o $(OBJ_DIR)/StrandQueue.o
diff --git a/src/utils/FileRecordTools/Records/RecordMgr.cpp b/src/utils/FileRecordTools/Records/RecordMgr.cpp
index 9799fedc325d208fa502cee814a1f29f6ca471e6..92d9dc54ad714a47fd65aa4edf929dda78635962 100644
--- a/src/utils/FileRecordTools/Records/RecordMgr.cpp
+++ b/src/utils/FileRecordTools/Records/RecordMgr.cpp
@@ -8,6 +8,13 @@ RecordMgr::RecordMgr(FileRecordTypeChecker::RECORD_TYPE recType, int blockSize)
_freeListBlockSize(blockSize)
{
switch(_recordType) {
+ case FileRecordTypeChecker::EMPTY_RECORD_TYPE:
+ {
+ _freeList = new FreeList<EmptyRecord>(0);
+ break;
+ }
+
+
case FileRecordTypeChecker::BED3_RECORD_TYPE:
{
_freeList = new FreeList<Bed3Interval>(_freeListBlockSize);
@@ -72,6 +79,11 @@ RecordMgr::RecordMgr(FileRecordTypeChecker::RECORD_TYPE recType, int blockSize)
RecordMgr::~RecordMgr()
{
switch(_recordType) {
+ case FileRecordTypeChecker::EMPTY_RECORD_TYPE:
+ {
+ delete (FreeList<EmptyRecord> *)_freeList;
+ break;
+ }
case FileRecordTypeChecker::BED3_RECORD_TYPE:
{
delete (FreeList<Bed3Interval> *)_freeList;
@@ -138,6 +150,12 @@ Record *RecordMgr::allocateRecord()
{
Record *record = NULL;
switch(_recordType) {
+ case FileRecordTypeChecker::EMPTY_RECORD_TYPE:
+ {
+ EmptyRecord *er = ((FreeList<EmptyRecord> *)_freeList)->newObj();
+ record = er;
+ break;
+ }
case FileRecordTypeChecker::BED3_RECORD_TYPE:
{
Bed3Interval *b3i = ((FreeList<Bed3Interval> *)_freeList)->newObj();
@@ -215,6 +233,12 @@ Record *RecordMgr::allocateRecord()
void RecordMgr::deleteRecord(const Record *record)
{
switch(_recordType) {
+ case FileRecordTypeChecker::EMPTY_RECORD_TYPE:
+ {
+ ((FreeList<EmptyRecord> *)_freeList)->deleteObj(static_cast<const EmptyRecord *>(record));
+ break;
+ }
+
case FileRecordTypeChecker::BED3_RECORD_TYPE:
{
((FreeList<Bed3Interval> *)_freeList)->deleteObj(static_cast<const Bed3Interval *>(record));
diff --git a/src/utils/FileRecordTools/Records/RecordMgr.h b/src/utils/FileRecordTools/Records/RecordMgr.h
index 1d73f9055877fc42f76cc2cf0d10efd498101a51..37193b9c8137c72c64df2d48f3eac4d2e93d52ff 100644
--- a/src/utils/FileRecordTools/Records/RecordMgr.h
+++ b/src/utils/FileRecordTools/Records/RecordMgr.h
@@ -10,6 +10,7 @@
//include headers for all Records and derivative classes
#include "Record.h"
+#include "EmptyRecord.h"
#include "Bed3Interval.h"
#include "Bed4Interval.h"
#include "Bed5Interval.h"
diff --git a/src/utils/NewChromsweep/NewChromsweep.cpp b/src/utils/NewChromsweep/NewChromsweep.cpp
index c04fefb19b1cdfcb99f3cf03486074d4dd21c1aa..34647d678c448ccdfefbe32adcd856a81476b58b 100644
--- a/src/utils/NewChromsweep/NewChromsweep.cpp
+++ b/src/utils/NewChromsweep/NewChromsweep.cpp
@@ -41,9 +41,9 @@ bool NewChromSweep::init() {
_databaseFRM = _context->getFile(_context->getDatabaseFileIdx());
nextRecord(false);
- if (_currDatabaseRec == NULL) {
- return false;
- }
+// if (_currDatabaseRec == NULL) {
+// return false;
+// }
//determine whether to stop when the database end is hit, or keep going until the
//end of the query file is hit as well.
diff --git a/src/utils/RecordOutputMgr/RecordOutputMgr.cpp b/src/utils/RecordOutputMgr/RecordOutputMgr.cpp
index 9ab8b52b060163e1cc47753a4e2f446f1c36f531..9aaa511bc3d2e10c73c15706bbd42e29808f435a 100644
--- a/src/utils/RecordOutputMgr/RecordOutputMgr.cpp
+++ b/src/utils/RecordOutputMgr/RecordOutputMgr.cpp
@@ -37,6 +37,10 @@ RecordOutputMgr::RecordOutputMgr()
RecordOutputMgr::~RecordOutputMgr()
{
+ // In the rare case when a file had a header but was otherwise empty,
+ // we'll need to make a last check to see if the header still needs to be printed.
+ checkForHeader();
+
if (_outBuf.size() > 0) {
flush();
}
@@ -122,7 +126,10 @@ void RecordOutputMgr::printRecord(const Record *record, const QuickString & valu
{
_afterVal = value;
printRecord(record);
- _outBuf.append(value);
+ if (!value.empty()) {
+ tab();
+ _outBuf.append(value);
+ }
newline();
if (needsFlush()) {
@@ -152,9 +159,8 @@ void RecordOutputMgr::printRecord(RecordKeyList &keyList, RecordKeyList *blockLi
}
//The first time we print a record is when we print any header, because the header
//hasn't been read from the query file until after the first record has also been read.
- if (_context->getPrintHeader()) {
- checkForHeader();
- }
+ checkForHeader();
+
const_cast<Record *>(keyList.getKey())->undoZeroLength();
_currBamBlockList = blockList;
@@ -208,9 +214,11 @@ void RecordOutputMgr::printRecord(RecordKeyList &keyList, RecordKeyList *blockLi
_currBamBlockList = NULL;
return;
} else if (_context->getProgram() == ContextBase::MAP) {
- if (!printKeyAndTerminate(keyList)) {
- tab();
- }
+ printKeyAndTerminate(keyList);
+ _currBamBlockList = NULL;
+ return;
+ } else if (_context->getProgram() == ContextBase::MERGE) {
+ printKeyAndTerminate(keyList);
_currBamBlockList = NULL;
return;
} else if (_context->getProgram() == ContextBase::MERGE) {
@@ -228,6 +236,9 @@ void RecordOutputMgr::printRecord(RecordKeyList &keyList, RecordKeyList *blockLi
}
void RecordOutputMgr::checkForHeader() {
+ // Do we need to print a header?
+ if (!_context->getPrintHeader()) return;
+
//if the program is based on intersection, we want the header from the query file.
if (_context->hasIntersectMethods()) {
int queryIdx = (static_cast<ContextIntersect *>(_context))->getQueryFileIdx();
diff --git a/src/utils/fileType/FileRecordTypeChecker.cpp b/src/utils/fileType/FileRecordTypeChecker.cpp
index 370cfffa7eb5d418618f29af1e928813e76a2049..fb81f09c53e489d62c83a88fb421527532fc41fd 100644
--- a/src/utils/fileType/FileRecordTypeChecker.cpp
+++ b/src/utils/fileType/FileRecordTypeChecker.cpp
@@ -12,7 +12,7 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_isText = false;
_isBed = false;
_isDelimited = false;
- _delimChar = '\0';
+ _delimChar = '\t'; //tab by default
_lines.clear();
_firstValidDataLineIdx = -1;
_isVCF = false;
@@ -21,8 +21,10 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_isGzipped = false;
_insufficientData = false;
_fourthFieldNumeric = false;
+ _givenEmptyBuffer = false;
_hasName[UNKNOWN_RECORD_TYPE] = false;
+ _hasName[EMPTY_RECORD_TYPE] = false;
_hasName[BED3_RECORD_TYPE] = false;
_hasName[BED6_RECORD_TYPE] = true;
_hasName[BED12_RECORD_TYPE] = true;
@@ -32,6 +34,7 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_hasName[GFF_RECORD_TYPE] = true;
_hasScore[UNKNOWN_RECORD_TYPE] = false;
+ _hasScore[EMPTY_RECORD_TYPE] = false;
_hasScore[BED3_RECORD_TYPE] = false;
_hasScore[BED6_RECORD_TYPE] = true;
_hasScore[BED12_RECORD_TYPE] = true;
@@ -41,6 +44,7 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_hasScore[GFF_RECORD_TYPE] = true;
_hasStrand[UNKNOWN_RECORD_TYPE] = false;
+ _hasStrand[EMPTY_RECORD_TYPE] = false;
_hasStrand[BED3_RECORD_TYPE] = false;
_hasStrand[BED6_RECORD_TYPE] = true;
_hasStrand[BED12_RECORD_TYPE] = true;
@@ -50,6 +54,7 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_hasStrand[GFF_RECORD_TYPE] = true;
_recordTypeNames[UNKNOWN_RECORD_TYPE] = "Unknown record type";
+ _recordTypeNames[EMPTY_RECORD_TYPE] = "Empty record type";
_recordTypeNames[BED3_RECORD_TYPE] = "Bed3 record type";
_recordTypeNames[BED6_RECORD_TYPE] = "Bed6 record type";
_recordTypeNames[BED12_RECORD_TYPE] = "Bed12 record type";
@@ -58,11 +63,8 @@ FileRecordTypeChecker::FileRecordTypeChecker()
_recordTypeNames[VCF_RECORD_TYPE] = "VCF record type";
_recordTypeNames[GFF_RECORD_TYPE] = "GFF record type";
-// UNKNOWN_FILE_TYPE, SINGLE_LINE_DELIM_TEXT_FILE_TYPE,
-// MULTI_LINE_ENTRY_TEXT_FILE_TYPE,
-// GFF_FILE_TYPE, GZIP_FILE_TYPE, BAM_FILE_TYPE
-
_fileTypeNames[UNKNOWN_FILE_TYPE] = "Unknown file type";
+ _fileTypeNames[EMPTY_FILE_TYPE] = "Empty file type";
_fileTypeNames[SINGLE_LINE_DELIM_TEXT_FILE_TYPE] = "Delimited text file type";
_fileTypeNames[GZIP_FILE_TYPE] = "Gzip file type";
_fileTypeNames[BAM_FILE_TYPE] = "BAM file type";
@@ -77,8 +79,9 @@ bool FileRecordTypeChecker::scanBuffer(const char *buffer, size_t len)
}
_numBytesInBuffer = len;
if (_numBytesInBuffer == 0) {
- cerr << "Error: " << _filename << " is an empty file."<< endl;
- exit(1);
+ _fileType = EMPTY_FILE_TYPE;
+ _recordType = EMPTY_RECORD_TYPE;
+ return true;
}
//special: the first thing we do is look for a gzipped file.
diff --git a/src/utils/fileType/FileRecordTypeChecker.h b/src/utils/fileType/FileRecordTypeChecker.h
index 6d598acea456c8a2e5852a97ca8c3dacd0d72b4e..4af5a80206ff3d53582fb0526465b4a6dd44413c 100644
--- a/src/utils/fileType/FileRecordTypeChecker.h
+++ b/src/utils/fileType/FileRecordTypeChecker.h
@@ -25,11 +25,11 @@ public:
FileRecordTypeChecker();
~FileRecordTypeChecker() {}
- typedef enum { UNKNOWN_FILE_TYPE, SINGLE_LINE_DELIM_TEXT_FILE_TYPE,
+ typedef enum { UNKNOWN_FILE_TYPE, EMPTY_FILE_TYPE, SINGLE_LINE_DELIM_TEXT_FILE_TYPE,
MULTI_LINE_ENTRY_TEXT_FILE_TYPE,
GFF_FILE_TYPE, GZIP_FILE_TYPE, BAM_FILE_TYPE, VCF_FILE_TYPE} FILE_TYPE;
- typedef enum { UNKNOWN_RECORD_TYPE, BED3_RECORD_TYPE, BED4_RECORD_TYPE, BEDGRAPH_RECORD_TYPE, BED5_RECORD_TYPE,
+ typedef enum { UNKNOWN_RECORD_TYPE, EMPTY_RECORD_TYPE, BED3_RECORD_TYPE, BED4_RECORD_TYPE, BEDGRAPH_RECORD_TYPE, BED5_RECORD_TYPE,
BED6_RECORD_TYPE, BED12_RECORD_TYPE, BED_PLUS_RECORD_TYPE, BAM_RECORD_TYPE, VCF_RECORD_TYPE, GFF_RECORD_TYPE} RECORD_TYPE;
void setFilename(const QuickString & filename) { _filename = filename; }
@@ -41,7 +41,12 @@ public:
bool recordTypeHasStrand(RECORD_TYPE type) const { return _hasStrand.find(type) != _hasStrand.end(); }
FILE_TYPE getFileType() const { return _fileType; }
+ void setFileType(FILE_TYPE type) { _fileType = type; }
+
+
RECORD_TYPE getRecordType() const { return _recordType; }
+ void setRecordType(RECORD_TYPE type) { _recordType = type; }
+
const string &getFileTypeName() const {
return _fileTypeNames.find(_fileType)->second;
}
@@ -99,6 +104,7 @@ private:
bool _isGzipped;
bool _insufficientData; //set to true if scan buffer had only header lines.
bool _fourthFieldNumeric; //this is just to distinguish between Bed4 and BedGraph files.
+ bool _givenEmptyBuffer;
map<RECORD_TYPE, string> _recordTypeNames;
map<FILE_TYPE, string> _fileTypeNames;
diff --git a/test/intersect/headerOnly.vcf b/test/intersect/headerOnly.vcf
new file mode 100644
index 0000000000000000000000000000000000000000..9863ae581046b88e4a9f1b8d957480b03dafe165
--- /dev/null
+++ b/test/intersect/headerOnly.vcf
@@ -0,0 +1,121 @@
+##fileformat=VCFv4.1
+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/all.conc.on.pos.dedup.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/home/arq5x/cphg-home/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name= source=UNBOUND) out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub debug_file=null metrics_file=null annotation=[] excludeAnnotation=[] filter_mismatching_base_and_quals=false"
+##contig=<ID=chr1,length=249250621,assembly=hg19>
+##contig=<ID=chr10,length=135534747,assembly=hg19>
+##contig=<ID=chr11,length=135006516,assembly=hg19>
+##contig=<ID=chr11_gl000202_random,length=40103,assembly=hg19>
+##contig=<ID=chr12,length=133851895,assembly=hg19>
+##contig=<ID=chr13,length=115169878,assembly=hg19>
+##contig=<ID=chr14,length=107349540,assembly=hg19>
+##contig=<ID=chr15,length=102531392,assembly=hg19>
+##contig=<ID=chr16,length=90354753,assembly=hg19>
+##contig=<ID=chr17,length=81195210,assembly=hg19>
+##contig=<ID=chr17_ctg5_hap1,length=1680828,assembly=hg19>
+##contig=<ID=chr17_gl000203_random,length=37498,assembly=hg19>
+##contig=<ID=chr17_gl000204_random,length=81310,assembly=hg19>
+##contig=<ID=chr17_gl000205_random,length=174588,assembly=hg19>
+##contig=<ID=chr17_gl000206_random,length=41001,assembly=hg19>
+##contig=<ID=chr18,length=78077248,assembly=hg19>
+##contig=<ID=chr18_gl000207_random,length=4262,assembly=hg19>
+##contig=<ID=chr19,length=59128983,assembly=hg19>
+##contig=<ID=chr19_gl000208_random,length=92689,assembly=hg19>
+##contig=<ID=chr19_gl000209_random,length=159169,assembly=hg19>
+##contig=<ID=chr1_gl000191_random,length=106433,assembly=hg19>
+##contig=<ID=chr1_gl000192_random,length=547496,assembly=hg19>
+##contig=<ID=chr2,length=243199373,assembly=hg19>
+##contig=<ID=chr20,length=63025520,assembly=hg19>
+##contig=<ID=chr21,length=48129895,assembly=hg19>
+##contig=<ID=chr21_gl000210_random,length=27682,assembly=hg19>
+##contig=<ID=chr22,length=51304566,assembly=hg19>
+##contig=<ID=chr3,length=198022430,assembly=hg19>
+##contig=<ID=chr4,length=191154276,assembly=hg19>
+##contig=<ID=chr4_ctg9_hap1,length=590426,assembly=hg19>
+##contig=<ID=chr4_gl000193_random,length=189789,assembly=hg19>
+##contig=<ID=chr4_gl000194_random,length=191469,assembly=hg19>
+##contig=<ID=chr5,length=180915260,assembly=hg19>
+##contig=<ID=chr6,length=171115067,assembly=hg19>
+##contig=<ID=chr6_apd_hap1,length=4622290,assembly=hg19>
+##contig=<ID=chr6_cox_hap2,length=4795371,assembly=hg19>
+##contig=<ID=chr6_dbb_hap3,length=4610396,assembly=hg19>
+##contig=<ID=chr6_mann_hap4,length=4683263,assembly=hg19>
+##contig=<ID=chr6_mcf_hap5,length=4833398,assembly=hg19>
+##contig=<ID=chr6_qbl_hap6,length=4611984,assembly=hg19>
+##contig=<ID=chr6_ssto_hap7,length=4928567,assembly=hg19>
+##contig=<ID=chr7,length=159138663,assembly=hg19>
+##contig=<ID=chr7_gl000195_random,length=182896,assembly=hg19>
+##contig=<ID=chr8,length=146364022,assembly=hg19>
+##contig=<ID=chr8_gl000196_random,length=38914,assembly=hg19>
+##contig=<ID=chr8_gl000197_random,length=37175,assembly=hg19>
+##contig=<ID=chr9,length=141213431,assembly=hg19>
+##contig=<ID=chr9_gl000198_random,length=90085,assembly=hg19>
+##contig=<ID=chr9_gl000199_random,length=169874,assembly=hg19>
+##contig=<ID=chr9_gl000200_random,length=187035,assembly=hg19>
+##contig=<ID=chr9_gl000201_random,length=36148,assembly=hg19>
+##contig=<ID=chrM,length=16571,assembly=hg19>
+##contig=<ID=chrUn_gl000211,length=166566,assembly=hg19>
+##contig=<ID=chrUn_gl000212,length=186858,assembly=hg19>
+##contig=<ID=chrUn_gl000213,length=164239,assembly=hg19>
+##contig=<ID=chrUn_gl000214,length=137718,assembly=hg19>
+##contig=<ID=chrUn_gl000215,length=172545,assembly=hg19>
+##contig=<ID=chrUn_gl000216,length=172294,assembly=hg19>
+##contig=<ID=chrUn_gl000217,length=172149,assembly=hg19>
+##contig=<ID=chrUn_gl000218,length=161147,assembly=hg19>
+##contig=<ID=chrUn_gl000219,length=179198,assembly=hg19>
+##contig=<ID=chrUn_gl000220,length=161802,assembly=hg19>
+##contig=<ID=chrUn_gl000221,length=155397,assembly=hg19>
+##contig=<ID=chrUn_gl000222,length=186861,assembly=hg19>
+##contig=<ID=chrUn_gl000223,length=180455,assembly=hg19>
+##contig=<ID=chrUn_gl000224,length=179693,assembly=hg19>
+##contig=<ID=chrUn_gl000225,length=211173,assembly=hg19>
+##contig=<ID=chrUn_gl000226,length=15008,assembly=hg19>
+##contig=<ID=chrUn_gl000227,length=128374,assembly=hg19>
+##contig=<ID=chrUn_gl000228,length=129120,assembly=hg19>
+##contig=<ID=chrUn_gl000229,length=19913,assembly=hg19>
+##contig=<ID=chrUn_gl000230,length=43691,assembly=hg19>
+##contig=<ID=chrUn_gl000231,length=27386,assembly=hg19>
+##contig=<ID=chrUn_gl000232,length=40652,assembly=hg19>
+##contig=<ID=chrUn_gl000233,length=45941,assembly=hg19>
+##contig=<ID=chrUn_gl000234,length=40531,assembly=hg19>
+##contig=<ID=chrUn_gl000235,length=34474,assembly=hg19>
+##contig=<ID=chrUn_gl000236,length=41934,assembly=hg19>
+##contig=<ID=chrUn_gl000237,length=45867,assembly=hg19>
+##contig=<ID=chrUn_gl000238,length=39939,assembly=hg19>
+##contig=<ID=chrUn_gl000239,length=33824,assembly=hg19>
+##contig=<ID=chrUn_gl000240,length=41933,assembly=hg19>
+##contig=<ID=chrUn_gl000241,length=42152,assembly=hg19>
+##contig=<ID=chrUn_gl000242,length=43523,assembly=hg19>
+##contig=<ID=chrUn_gl000243,length=43341,assembly=hg19>
+##contig=<ID=chrUn_gl000244,length=39929,assembly=hg19>
+##contig=<ID=chrUn_gl000245,length=36651,assembly=hg19>
+##contig=<ID=chrUn_gl000246,length=38154,assembly=hg19>
+##contig=<ID=chrUn_gl000247,length=36422,assembly=hg19>
+##contig=<ID=chrUn_gl000248,length=39786,assembly=hg19>
+##contig=<ID=chrUn_gl000249,length=38502,assembly=hg19>
+##contig=<ID=chrX,length=155270560,assembly=hg19>
+##contig=<ID=chrY,length=59373566,assembly=hg19>
+##reference=file:///home/arq5x/cphg-home/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa
+##SnpEffVersion="SnpEff 3.0g (build 2012-08-31), by Pablo Cingolani"
+##SnpEffCmd="SnpEff -i vcf -o vcf GRCh37.66 /home/udp3f/cphg-home/projects/rs-exome/varCalling/2012-Feb-01/all.raw.nobaq.vcf "
+##INFO=<ID=EFF,Number=.,Type=String,Description="Predicted effects for this variant.Format: 'Effect ( Effect_Impact | Functional_Class | Codon_Change | Amino_Acid_change| Amino_Acid_length | Gene_Name | Gene_BioType | Coding | Transcript | Exon [ | ERRORS | WARNINGS ] )' ">
+#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT 1094PC0005 1094PC0009 1094PC0012 1094PC0013
diff --git a/test/intersect/new_test-intersect.sh b/test/intersect/new_test-intersect.sh
index 4bdcdf05a1b208d1339dd21c416ef924d59d089e..3b7722239ba0217ad98e55f35466845b25430d01 100755
--- a/test/intersect/new_test-intersect.sh
+++ b/test/intersect/new_test-intersect.sh
@@ -609,12 +609,12 @@ check obs exp
rm obs exp
###########################################################
-# Test that we throw an error for empty files
+# Test that we allow empty query files
############################################################
echo " intersect.new.t51...\c"
-echo "is an empty file." > exp
+touch exp
touch dummy.txt
-$BT intersect -a dummy.txt -b b.bed 2>&1 > /dev/null | cut -f3-6 -d ' ' > obs
+$BT intersect -a dummy.txt -b b.bed 2>&1 > /dev/null | cat - > obs
check obs exp
rm obs exp dummy.txt
@@ -664,5 +664,86 @@ $BT intersect -a gdc.gff -b gdc_one.bed > obs
check obs exp
rm obs exp
+###########################################################
+# Test that we allow empty database files, unsorted
+############################################################
+echo " intersect.new.t56...\c"
+touch exp
+touch dummy.txt
+$BT intersect -a a.bed -b dummy.txt 2>&1 > /dev/null | cat - > obs
+check obs exp
+rm obs exp dummy.txt
+
+###########################################################
+# Test that we allow empty database files, sorted
+############################################################
+echo " intersect.new.t57...\c"
+touch exp
+touch dummy.txt
+$BT intersect -a a.bed -b dummy.txt -sorted 2>&1 > /dev/null | cat - > obs
+check obs exp
+rm obs exp dummy.txt
+
+
+###########################################################
+# Test that we allow empty database files, unsorted, with
+# -v (noHit) option
+############################################################
+echo " intersect.new.t58...\c"
+touch dummy.txt
+$BT intersect -a a.bed -b dummy.txt -v > obs
+check obs a.bed
+rm obs dummy.txt
+
+
+###########################################################
+# Test that an empty query with header run with -header
+# option will print header
+############################################################
+echo " intersect.new.t59...\c"
+echo "#Random Header" >dummy.txt
+$BT intersect -a dummy.txt -b a.bed -header > obs
+check obs dummy.txt
+rm obs dummy.txt
+
+
+###########################################################
+# Test that an empty query with header, gzipped, that
+# runs with -header option will print header
+############################################################
+echo " intersect.new.t60...\c"
+echo "#Random Header" >dummy.txt
+gzip dummy.txt
+echo "#Random Header" >exp
+$BT intersect -a dummy.txt.gz -b a.bed -header > obs
+check obs exp
+rm obs dummy.txt.gz exp
+
+###########################################################
+# Test that an empty query with header, bgzipped, that
+# runs with -header option will print header
+############################################################
+echo " intersect.new.t61...\c"
+echo "#Random Header" >dummy.txt
+bgzip dummy.txt
+echo "#Random Header" >exp
+$BT intersect -a dummy.txt.gz -b a.bed -header > obs
+check obs exp
+rm obs dummy.txt.gz exp
+
+
+###########################################################
+# Test that an empty VCF query with header that
+# runs with -header option will print header
+############################################################
+echo " intersect.new.t62...\c"
+$BT intersect -a headerOnly.vcf -b a.bed -header > obs
+check obs headerOnly.vcf
+rm obs
+
+
+
+
+
diff --git a/test/sample/test-sample.sh b/test/sample/test-sample.sh
index 5a65085cb5ea6a7ebf4f3581fa422069272336ed..0994994627de09915e29463f4c7c059173b18e86 100644
--- a/test/sample/test-sample.sh
+++ b/test/sample/test-sample.sh
@@ -40,21 +40,19 @@ rm obs
############################################################
echo " sample.new.t02...\c"
echo "***** ERROR: Unrecognized parameter: -wrongArg *****" > exp
-$BT sample -wrongArg 2>&1 > /dev/null | head -2 | tail -1 > obs
+$BT sample -i mainFile.bed -wrongArg 2>&1 > /dev/null | head -2 | tail -1 > obs
check obs exp
rm obs exp
-
###########################################################
-# Test that we throw an error when no input file is given
+# Test that we throw an error when no input file was given.
############################################################
echo " sample.new.t03...\c"
-echo "***** ERROR: input file not specified. *****" > exp
+echo "***** ERROR: No input file given. Exiting. *****" > exp;
$BT sample -n 10 2>&1 > /dev/null | head -2 | tail -1 > obs
check obs exp
rm obs exp
-
###########################################################
# Test that we throw an error for -i without input file
############################################################
@@ -116,6 +114,9 @@ $BT sample -i mainFile.bed -n 10 -header | head -1 > obs
check obs exp
rm obs exp
+
+
+
rm mainFile.bed