def _commonComplementGtrackFile(origFn, dbFn, intersectingFactor, gtrackColsToAdd, genome):
origGESource = GtrackGenomeElementSource(origFn, genome)
dbGESource = GtrackGenomeElementSource(dbFn, genome)
dbPrefixes = dbGESource.getPrefixList()
if intersectingFactor == 'id':
fullDbDict = IdFullInfoDict(dbGESource, dbPrefixes)
elif intersectingFactor == 'position':
fullDbDict = TupleFullInfoDict(dbGESource, dbPrefixes)
else:
ShouldNotOccurError
forcedHeaderDict = {}
dbHeaderDict = dbGESource.getHeaderDict()
if 'value' in gtrackColsToAdd:
forcedHeaderDict['value type'] = dbHeaderDict['value type']
forcedHeaderDict['value dimension'] = dbHeaderDict['value dimension']
if 'edges' in gtrackColsToAdd:
forcedHeaderDict['edge weight type'] = dbHeaderDict['edge weight type']
forcedHeaderDict['edge weight dimension'] = dbHeaderDict['edge weight dimension']
composerCls = ExtendedGtrackComposer if origGESource.isExtendedGtrackFile() else StdGtrackComposer
composedFile = composerCls( ElementComplementer(origGESource, fullDbDict, gtrackColsToAdd), \
forcedHeaderDict=forcedHeaderDict).returnComposed()
return expandHeadersOfGtrackFileAndReturnComposer('', genome, strToUseInsteadOfFn=composedFile)
def _commonComplementGtrackFile(origFn, dbFn, intersectingFactor, gtrackColsToAdd, genome):
origGESource = GtrackGenomeElementSource(origFn, genome)
dbGESource = GtrackGenomeElementSource(dbFn, genome)
dbPrefixes = dbGESource.getPrefixList()
if intersectingFactor == 'id':
fullDbDict = IdFullInfoDict(dbGESource, dbPrefixes)
elif intersectingFactor == 'position':
fullDbDict = TupleFullInfoDict(dbGESource, dbPrefixes)
else:
ShouldNotOccurError
forcedHeaderDict = {}
dbHeaderDict = dbGESource.getHeaderDict()
if 'value' in gtrackColsToAdd:
forcedHeaderDict['value type'] = dbHeaderDict['value type']
forcedHeaderDict['value dimension'] = dbHeaderDict['value dimension']
if 'edges' in gtrackColsToAdd:
forcedHeaderDict['edge weight type'] = dbHeaderDict['edge weight type']
forcedHeaderDict['edge weight dimension'] = dbHeaderDict['edge weight dimension']
composerCls = ExtendedGtrackComposer if origGESource.isExtendedGtrackFile() else StdGtrackComposer
composedFile = composerCls( ElementComplementer(origGESource, fullDbDict, gtrackColsToAdd), \
forcedHeaderDict=forcedHeaderDict).returnComposed()
return expandHeadersOfGtrackFileAndReturnComposer('', genome, strToUseInsteadOfFn=composedFile)
def _determineIfFileCompliesToSubtypes(self, hbColumns, columns):
if 'subtype url' in self._forcedHeaderDict:
subtypeUrlList = [self._forcedHeaderDict['subtype url']] \
if self._forcedHeaderDict['subtype url'] != '' else []
else:
subtypeUrlList = self.GTRACK_PRIORITIZED_SUBTYPE_LIST
for subtypeUrl in subtypeUrlList:
subtypeGESource = Gtrack.getSubtypeGESource(subtypeUrl)
subtypeColumns = subtypeGESource.getColumns(orig=False)
subtypeHeaders = subtypeGESource.getHeaderDict()
numRepeats = 2 if subtypeHeaders[
'subtype adherence'] == 'redefinable' else 1
for repeat in range(numRepeats):
self._setHeaderDict('1-indexed', subtypeHeaders['1-indexed'])
self._setHeaderDict('end inclusive',
subtypeHeaders['end inclusive'])
if subtypeHeaders['subtype adherence'] in [
'reorderable', 'free'
]:
rearrangedColumns = columns
rearrangedHbColumns = hbColumns
else:
colSet = set(columns)
subtypeColSet = set(subtypeColumns)
if subtypeHeaders['subtype adherence'] == 'redefinable':
colsRemoved = list(subtypeColSet - colSet)
colsAdded = list(colSet - subtypeColSet)
if len(colsRemoved) != len(colsAdded) or len(
colsRemoved) > 2:
continue
colsRedefinedTo = [
'value', 'edges'
] if repeat == 1 else ['edges', 'value']
rearrangedColumns = []
i, j = (0, 0)
for col in subtypeColumns:
if col in colsRemoved:
rearrangedColumns.append(colsRedefinedTo[i])
i += 1
elif col in colsRedefinedTo:
rearrangedColumns.append(colsAdded[j])
j += 1
else:
rearrangedColumns.append(col)
for col in columns:
if col in colsAdded[j:]:
rearrangedColumns.append(col)
else:
rearrangedColumns = [x for x in subtypeColumns if x in colSet] + \
[x for x in columns if x not in subtypeColSet]
rearrangedHbColumns = self._getHbColumnsFromGtrackColumns(
rearrangedColumns)
try:
tempFile = StringIO()
self._composeContents(tempFile, rearrangedHbColumns, rearrangedColumns, \
deepcopy(self._geSource), onlyNonDefault=True, singleDataLine=True)
gtrackGESource = Gtrack('subtypeTest.' + self.getDefaultFileNameSuffix(), printWarnings=False, \
strToUseInsteadOfFn=tempFile.getvalue())
tempFile.close()
if gtrackGESource.compliesWithSubtype(subtypeUrl):
gtrackGESource._headerDict['subtype url'] = subtypeUrl
gtrackGESource._updateHeadersAccordingToSubtype()
updatedHeaders = OrderedDict([(key, val) for key,val in gtrackGESource.getHeaderDict().iteritems() \
if val != Gtrack.DEFAULT_HEADER_DICT.get(key)])
for header in updatedHeaders:
self._setHeaderDict(header, updatedHeaders[header])
return rearrangedHbColumns, rearrangedColumns, True
except Exception, e:
continue
def _determineIfFileCompliesToSubtypes(self, hbColumns, columns):
if 'subtype url' in self._forcedHeaderDict:
subtypeUrlList = [self._forcedHeaderDict['subtype url']] \
if self._forcedHeaderDict['subtype url'] != '' else []
else:
subtypeUrlList = self.GTRACK_PRIORITIZED_SUBTYPE_LIST
for subtypeUrl in subtypeUrlList:
subtypeGESource = Gtrack.getSubtypeGESource(subtypeUrl)
subtypeColumns = subtypeGESource.getColumns(orig=False)
subtypeHeaders = subtypeGESource.getHeaderDict()
numRepeats = 2 if subtypeHeaders['subtype adherence'] == 'redefinable' else 1
for repeat in range(numRepeats):
self._setHeaderDict('1-indexed', subtypeHeaders['1-indexed'])
self._setHeaderDict('end inclusive', subtypeHeaders['end inclusive'])
if subtypeHeaders['subtype adherence'] in ['reorderable', 'free']:
rearrangedColumns = columns
rearrangedHbColumns = hbColumns
else:
colSet = set(columns)
subtypeColSet = set(subtypeColumns)
if subtypeHeaders['subtype adherence'] == 'redefinable':
colsRemoved = list(subtypeColSet - colSet)
colsAdded = list(colSet - subtypeColSet)
if len(colsRemoved) != len(colsAdded) or len(colsRemoved) > 2:
continue
colsRedefinedTo = ['value', 'edges'] if repeat == 1 else ['edges', 'value']
rearrangedColumns = []
i,j = (0,0)
for col in subtypeColumns:
if col in colsRemoved:
rearrangedColumns.append(colsRedefinedTo[i])
i += 1
elif col in colsRedefinedTo:
rearrangedColumns.append(colsAdded[j])
j += 1
else:
rearrangedColumns.append(col)
for col in columns:
if col in colsAdded[j:]:
rearrangedColumns.append(col)
else:
rearrangedColumns = [x for x in subtypeColumns if x in colSet] + \
[x for x in columns if x not in subtypeColSet]
rearrangedHbColumns = self._getHbColumnsFromGtrackColumns(rearrangedColumns)
try:
tempFile = StringIO()
self._composeContents(tempFile, rearrangedHbColumns, rearrangedColumns, \
deepcopy(self._geSource), onlyNonDefault=True, singleDataLine=True)
gtrackGESource = Gtrack('subtypeTest.' + self.getDefaultFileNameSuffix(), printWarnings=False, \
strToUseInsteadOfFn=tempFile.getvalue())
tempFile.close()
if gtrackGESource.compliesWithSubtype(subtypeUrl):
gtrackGESource._headerDict['subtype url'] = subtypeUrl
gtrackGESource._updateHeadersAccordingToSubtype()
updatedHeaders = OrderedDict([(key, val) for key,val in gtrackGESource.getHeaderDict().iteritems() \
if val != Gtrack.DEFAULT_HEADER_DICT.get(key)])
for header in updatedHeaders:
self._setHeaderDict(header, updatedHeaders[header])
return rearrangedHbColumns, rearrangedColumns, True
except Exception, e:
continue