def _termDictsFromContext(self, context, symbol):
vecs = NameToDictMap()
allNgrams = OccurrenceCounter()
context.neighbours.append(context.origin)
for neighbour in context.neighbours:
nOcc = neighbour.nOccurrences
location = neighbour.location
expressions = self.treeToExprConverter.getExpressionsForSymbol(location, symbol)
# expressions.append('@+$_+@')
# expressions.append('@+EXPR@+$_+@+@')
# print 'FOO %s: %s: %s' % (symbol, location, expressions)
neighbour.setExpressions(expressions)
# add null-vector for function if it does not contain expressions
if len(expressions) == 0:
vecs.add(None, location)
for expr in expressions:
# vecs.add(expr, location, 1.0/nOcc)
# vecs.add(expr, location, 1.0)
vecs.setItem(expr, location, 1.0)
allNgrams.add(expr)
context.neighbours.pop()
if len(vecs.d) == 0 or len(allNgrams.d) == 0:
return None
return (vecs, allNgrams)
def _termDictsFromContext(self, context, symbol):
vecs = NameToDictMap()
allNgrams = OccurrenceCounter()
context.neighbours.append(context.origin)
for neighbour in context.neighbours:
nOcc = neighbour.nOccurrences
location = neighbour.location
expressions = self.treeToExprConverter.getExpressionsForSymbol(
location, symbol)
# expressions.append('@+$_+@')
# expressions.append('@+EXPR@+$_+@+@')
# print 'FOO %s: %s: %s' % (symbol, location, expressions)
neighbour.setExpressions(expressions)
# add null-vector for function if it does not contain expressions
if len(expressions) == 0:
vecs.add(None, location)
for expr in expressions:
# vecs.add(expr, location, 1.0/nOcc)
# vecs.add(expr, location, 1.0)
vecs.setItem(expr, location, 1.0)
allNgrams.add(expr)
context.neighbours.pop()
if len(vecs.d) == 0 or len(allNgrams.d) == 0:
return None
return (vecs, allNgrams)
class SinkMatrixCreator:
def __init__(self, projectRoot):
self.projectRoot = projectRoot
self.programDir = '/'.join(self.projectRoot.split('/')[:-3]) + '/'
self.sinkUserProvider = SinkUserProvider(self.projectRoot + '../../')
def createMatrixForSink(self, sinkName):
(unused, callsToSink) = self.sinkUserProvider.getSinkByName(sinkName)
functionNames = self.uniq(
['%s%s' % (self.programDir, c[1]) for c in callsToSink])
return self.createMatrixForFunctionNames(functionNames)
"""
This operation looses TF-IDF. I don't think that's the way to go.
"""
def createMatrixForFunctionNames(self, functionNames):
self._loadFunc2SubtreesMap()
self.nameToDictMap = NameToDictMap()
self.allSymbolsDict = OccurrenceCounter()
nameDictMapToMatrix = NameDictMapToMatrix()
functions = [(doc, self.func2SubtreesMap.d[doc])
for doc in functionNames]
for (doc, func) in functions:
for (ngram, nOccurrences) in func.iteritems():
for unused in xrange(nOccurrences):
self.nameToDictMap.add(ngram, doc)
self.allSymbolsDict.add(ngram)
nameDictMapToMatrix.convertFromDicts(self.nameToDictMap,
self.allSymbolsDict)
newTermDocMatrix = nameDictMapToMatrix.termDocumentMatrix
return newTermDocMatrix
def _loadFunc2SubtreesMap(self):
filename = self.projectRoot + 'func2SubtreesMap.pickl'
self.func2SubtreesMap = pickle.load(file(filename))
def uniq(self, seq, idfun=None):
# order preserving
if idfun is None:
def idfun(x):
return x
seen = {}
result = []
for item in seq:
marker = idfun(item)
if marker in seen: continue
seen[marker] = 1
result.append(item)
return result
class SinkMatrixCreator:
def __init__(self, projectRoot):
self.projectRoot = projectRoot
self.programDir = '/'.join(self.projectRoot.split('/')[:-3]) + '/'
self.sinkUserProvider = SinkUserProvider(self.projectRoot + '../../')
def createMatrixForSink(self, sinkName):
(unused, callsToSink) = self.sinkUserProvider.getSinkByName(sinkName)
functionNames = self.uniq([ '%s%s' % (self.programDir, c[1]) for c in callsToSink])
return self.createMatrixForFunctionNames(functionNames)
"""
This operation looses TF-IDF. I don't think that's the way to go.
"""
def createMatrixForFunctionNames(self, functionNames):
self._loadFunc2SubtreesMap()
self.nameToDictMap = NameToDictMap()
self.allSymbolsDict = OccurrenceCounter()
nameDictMapToMatrix = NameDictMapToMatrix()
functions = [(doc ,self.func2SubtreesMap.d[doc]) for doc in functionNames]
for (doc, func) in functions:
for (ngram, nOccurrences) in func.iteritems():
for unused in xrange(nOccurrences):
self.nameToDictMap.add(ngram, doc)
self.allSymbolsDict.add(ngram)
nameDictMapToMatrix.convertFromDicts(self.nameToDictMap, self.allSymbolsDict)
newTermDocMatrix = nameDictMapToMatrix.termDocumentMatrix
return newTermDocMatrix
def _loadFunc2SubtreesMap(self):
filename = self.projectRoot + 'func2SubtreesMap.pickl'
self.func2SubtreesMap = pickle.load(file(filename))
def uniq(self, seq, idfun=None):
# order preserving
if idfun is None:
def idfun(x): return x
seen = {}
result = []
for item in seq:
marker = idfun(item)
if marker in seen: continue
seen[marker] = 1
result.append(item)
return result
class FeatureArray(object):
def __init__(self):
self.vecs = NameToDictMap()
self.allSymbols = OccurrenceCounter()
def add(self, label, items):
if len(items) == 0:
self.vecs.add(None, label)
return
for item in items:
itemStr = str(item)
self.vecs.add(itemStr, label)
self.allSymbols.add(itemStr)
def __iter__(self):
for x in self.vecs.iteritems():
yield x
def createMatrixForFunctionNames(self, functionNames):
self._loadFunc2SubtreesMap()
self.nameToDictMap = NameToDictMap()
self.allSymbolsDict = OccurrenceCounter()
nameDictMapToMatrix = NameDictMapToMatrix()
functions = [(doc, self.func2SubtreesMap.d[doc])
for doc in functionNames]
for (doc, func) in functions:
for (ngram, nOccurrences) in func.iteritems():
for unused in xrange(nOccurrences):
self.nameToDictMap.add(ngram, doc)
self.allSymbolsDict.add(ngram)
nameDictMapToMatrix.convertFromDicts(self.nameToDictMap,
self.allSymbolsDict)
newTermDocMatrix = nameDictMapToMatrix.termDocumentMatrix
return newTermDocMatrix
def createMatrixForFunctionNames(self, functionNames):
self._loadFunc2SubtreesMap()
self.nameToDictMap = NameToDictMap()
self.allSymbolsDict = OccurrenceCounter()
nameDictMapToMatrix = NameDictMapToMatrix()
functions = [(doc ,self.func2SubtreesMap.d[doc]) for doc in functionNames]
for (doc, func) in functions:
for (ngram, nOccurrences) in func.iteritems():
for unused in xrange(nOccurrences):
self.nameToDictMap.add(ngram, doc)
self.allSymbolsDict.add(ngram)
nameDictMapToMatrix.convertFromDicts(self.nameToDictMap, self.allSymbolsDict)
newTermDocMatrix = nameDictMapToMatrix.termDocumentMatrix
return newTermDocMatrix
def __init__(self):
self.vecs = NameToDictMap()
self.allSymbols = OccurrenceCounter()
