def run(s1, s2, mML=3, treshold=[0.03, 0.31]):
"""This method runs a comparison on the two given strings s1 and s2 returning
a PlagResult object containing the similarity value, the similarities as
list of tiles and a boolean value indicating suspected plagiarism.
Input: s1 and s2 : normalized Strings
Options:
========
mML : minimumMatchingLength
treshold : could be a single number(Resemblance)
or a list of two numbers(Resemblance
and Containment)
Output: PlagResult
"""
#check if the preconditions are fullfilled
if mML < 1:
raise OutOfRangeError, 'minimum Matching Length mML needs to be greater than 0'
if type(treshold) == type([]):
if len(treshold) != 2:
raise AssertionError, 'Treshold must be a single Value (Resemblance) or a list of two Values [Resemblance, Containment]'
elif not (0 <= treshold[0] <= 1) or not (0 <= treshold[1] <= 1):
raise OutOfRangeError, 'tresholds values need to be 0<=t<=1'
elif not (0 <= treshold <= 1):
raise OutOfRangeError, 'treshold t needs to be 0<=t<=1'
if s1 == None or s2 == None:
raise NoValidArgumentError, 'input must be of type string not None'
if type(s1) != type('') or type(s2) != type(''):
raise NoValidArgumentError, 'input must be of type string'
if s1 == '' or s2 == '':
return PlagResult(hash(s1),
hash(s2)) #TODO: Identifierbildung ueberdenken..
#create NGrams for strings
ngramDict1 = createNGrams(s1, mML)
ngramDict2 = createNGrams(s2, mML)
#no nGrams found -> return empty initialized PlagResult
if ngramDict1 == {} or ngramDict2 == {}:
return PlagResult(hash(s1), hash(s2))
#compute similarity
simResult = calcSimilarity(set(ngramDict1.keys()), set(ngramDict2.keys()),
treshold)
similarity = simResult[0]
#compute tiles
tiles = calcTiles(ngramDict1, ngramDict2, simResult[1], mML)
#create PlagResult and set attributes
result = PlagResult()
result.setIdentifier(hash(s1), hash(s2))
result.setTiles(tiles)
result.setSimilarity(similarity)
result.setSuspectedPlagiarism(simResult[2])
result.setIdStringLength(len(s1.split()), len(s2.split()))
#return result of similarity check as PlagResult object
return result
def run(s1, s2, mML=3, treshold=[0.03, 0.31]):
"""This method runs a comparison on the two given strings s1 and s2 returning
a PlagResult object containing the similarity value, the similarities as
list of tiles and a boolean value indicating suspected plagiarism.
Input: s1 and s2 : normalized Strings
Options:
========
mML : minimumMatchingLength
treshold : could be a single number(Resemblance)
or a list of two numbers(Resemblance
and Containment)
Output: PlagResult
"""
#check if the preconditions are fullfilled
if mML<1:
raise OutOfRangeError, 'minimum Matching Length mML needs to be greater than 0'
if type(treshold) == type([]):
if len(treshold) != 2:
raise AssertionError, 'Treshold must be a single Value (Resemblance) or a list of two Values [Resemblance, Containment]'
elif not (0 <= treshold[0] <= 1) or not (0 <= treshold[1] <= 1):
raise OutOfRangeError, 'tresholds values need to be 0<=t<=1'
elif not (0 <= treshold <= 1):
raise OutOfRangeError, 'treshold t needs to be 0<=t<=1'
if s1 == None or s2 == None:
raise NoValidArgumentError, 'input must be of type string not None'
if type(s1) != type('') or type(s2) != type(''):
raise NoValidArgumentError, 'input must be of type string'
if s1 == '' or s2 == '':
return PlagResult(hash(s1), hash(s2)) #TODO: Identifierbildung ueberdenken..
#create NGrams for strings
ngramDict1 = createNGrams(s1, mML)
ngramDict2 = createNGrams(s2, mML)
#no nGrams found -> return empty initialized PlagResult
if ngramDict1 == {} or ngramDict2 == {}:
return PlagResult(hash(s1), hash(s2))
#compute similarity
simResult = calcSimilarity(set(ngramDict1.keys()), set(ngramDict2.keys()), treshold)
similarity = simResult[0]
#compute tiles
tiles = calcTiles(ngramDict1, ngramDict2, simResult[1], mML)
#create PlagResult and set attributes
result = PlagResult()
result.setIdentifier(hash(s1), hash(s2))
result.setTiles(tiles)
result.setSimilarity(similarity)
result.setSuspectedPlagiarism(simResult[2])
result.setIdStringLength(len(s1.split()), len(s2.split()))
#return result of similarity check as PlagResult object
return result
def resultFromXML(xmlString):
"""Returns a PlagResult object from the given XML representation.
@param xmlString XML representation (whole file with a single PlagResult)
@return A PlagResult object of the given XML representation.
"""
from xml.dom import minidom
dom_object = minidom.parseString(xmlString)
# get all PlagResult tags in the XML representation
list = dom_object.getElementsByTagName("PlagResult")
# get the first PlagResult tag
plagResultTag = list[0]
# create a PlagResult object
plagResult = PlagResult()
# read attributes from XML and fill PlagResult
plagResult.setIdentifier(
plagResultTag.getElementsByTagName("Identifier")[0].getAttribute("Id1"),
plagResultTag.getElementsByTagName("Identifier")[0].getAttribute("Id2"),
)
plagResult.setAlgorithmName(plagResultTag.getElementsByTagName("Algorithm")[0].firstChild.data)
plagResult.setNormalizerName(plagResultTag.getElementsByTagName("Normalizer")[0].firstChild.data)
plagResult.setSimilarity(float(plagResultTag.getElementsByTagName("Similarity")[0].firstChild.data))
plagResult.setSuspectedPlagiarism(
bool(plagResultTag.getElementsByTagName("SuspectedPlagiarism")[0].firstChild.data)
)
tileTags = plagResultTag.getElementsByTagName("Tiles")[0].getElementsByTagName("Tile")
tiles = []
for tileTag in tileTags:
tile = (
int(tileTag.getAttribute("posId1")),
int(tileTag.getAttribute("posId2")),
int(tileTag.getAttribute("length")),
)
tiles.append(tile)
plagResult.setTiles(tiles)
plagResult.setIdStringLength(
int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId1")),
int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId2")),
)
return plagResult
def run(s1, s2, mML=3, treshold=0.5):
"""This method runs a comparison on the two given strings s1 and s2 returning
a PlagResult object containing the similarity value, the similarities as
list of tiles and a boolean value indicating suspected plagiarism.
Input: s1 and s2 : normalized Strings
mML : minimumMatchingLength
treshold : a single value between 0 and 1
Output: PlagResult
"""
#check if the preconditions are fullfilled
if mML < 1:
raise OutOfRangeError, 'minimum Matching Length mML needs to be greater than 0'
if not (0 <= treshold <= 1):
raise OutOfRangeError, 'treshold t needs to be 0<=t<=1'
if s1 == None or s2 == None:
raise NoValidArgumentError, 'input must be of type string not None'
if type(s1) != type('') or type(s2) != type(''):
raise NoValidArgumentError, 'input must be of type string'
if s1 == '' or s2 == '':
return PlagResult(hash(s1),
hash(s2)) #TODO: Identifierbildung ueberdenken..
#compute tiles
global tiles, matchList
tiles = [] #TODO: anders regeln ? tiles
matchList = [] #TODO: anders regeln`? matchList
tiles = RKR_GST(s1, s2, mML)
#compute similarity
simResult = calcSimilarity(s1.split(), s2.split(), tiles, treshold)
similarity = simResult[0]
if similarity > 1: similarity = 1
#create PlagResult and set attributes
result = PlagResult()
result.setIdentifier(hash(s1), hash(s2))
result.setTiles(tiles)
result.setSimilarity(similarity)
result.setSuspectedPlagiarism(simResult[1])
#return result of similarity check as PlagResult object
return result
def run(s1, s2, mML=3, treshold=0.5):
"""This method runs a comparison on the two given strings s1 and s2 returning
a PlagResult object containing the similarity value, the similarities as
list of tiles and a boolean value indicating suspected plagiarism.
Input: s1 and s2 : normalized Strings
mML : minimumMatchingLength
treshold : a single value between 0 and 1
Output: PlagResult
"""
#check if the preconditions are fullfilled
if mML<1:
raise OutOfRangeError, 'minimum Matching Length mML needs to be greater than 0'
if not (0 <= treshold <= 1):
raise OutOfRangeError, 'treshold t needs to be 0<=t<=1'
if s1 == None or s2 == None:
raise NoValidArgumentError, 'input must be of type string not None'
if type(s1) != type('') or type(s2) != type(''):
raise NoValidArgumentError, 'input must be of type string'
if s1 == '' or s2 == '':
return PlagResult(hash(s1), hash(s2)) #TODO: Identifierbildung ueberdenken..
#compute tiles
global tiles, matchList
tiles = [] #TODO: anders regeln ? tiles
matchList = [] #TODO: anders regeln`? matchList
tiles = RKR_GST(s1, s2, mML)
#compute similarity
simResult = calcSimilarity(s1.split(), s2.split(), tiles, treshold)
similarity = simResult[0]
if similarity>1: similarity = 1
#create PlagResult and set attributes
result = PlagResult()
result.setIdentifier(hash(s1), hash(s2))
result.setTiles(tiles)
result.setSimilarity(similarity)
result.setSuspectedPlagiarism(simResult[1])
#return result of similarity check as PlagResult object
return result
def resultFromXML(xmlString):
"""Returns a PlagResult object from the given XML representation.
@param xmlString XML representation (whole file with a single PlagResult)
@return A PlagResult object of the given XML representation.
"""
from xml.dom import minidom
dom_object = minidom.parseString(xmlString)
#get all PlagResult tags in the XML representation
list = dom_object.getElementsByTagName("PlagResult")
#get the first PlagResult tag
plagResultTag = list[0]
#create a PlagResult object
plagResult = PlagResult()
#read attributes from XML and fill PlagResult
plagResult.setIdentifier(plagResultTag.getElementsByTagName("Identifier")[0].getAttribute("Id1"),
plagResultTag.getElementsByTagName("Identifier")[0].getAttribute("Id2"))
plagResult.setAlgorithmName(plagResultTag.getElementsByTagName("Algorithm")[0].firstChild.data)
plagResult.setNormalizerName(plagResultTag.getElementsByTagName("Normalizer")[0].firstChild.data)
plagResult.setSimilarity(float(plagResultTag.getElementsByTagName("Similarity")[0].firstChild.data))
plagResult.setSuspectedPlagiarism(bool(plagResultTag.getElementsByTagName("SuspectedPlagiarism")[0].firstChild.data))
tileTags = plagResultTag.getElementsByTagName("Tiles")[0].getElementsByTagName("Tile")
tiles = []
for tileTag in tileTags:
tile = (int(tileTag.getAttribute("posId1")),
int(tileTag.getAttribute("posId2")),
int(tileTag.getAttribute("length")))
tiles.append(tile)
plagResult.setTiles(tiles)
plagResult.setIdStringLength(int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId1")),
int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId2")))
return plagResult
def run(s1, s2, mML=3, treshold=0.5):
"""Tuned Version of GST
Input: s1 and s2 : normalized Strings
mML : minimumMatchingLength
treshold : a single value between 0 and 1
Output: PlagResult
"""
#check if the preconditions are fullfilled
if mML<1:
raise OutOfRangeError, 'minimum Matching Length mML needs to be greater than 0'
if not (0 <= treshold <= 1):
raise OutOfRangeError, 'treshold t needs to be 0<=t<=1'
if s1 == None or s2 == None:
raise NoValidArgumentError, 'input must be of type string not None'
if type(s1) != type('') or type(s2) != type(''):
raise NoValidArgumentError, 'input must be of type string'
if s1 == '' or s2 == '':
return PlagResult(hash(s1), hash(s2)) #TODO: Identifierbildung ueberdenken..
#compute tiles
tiles = []
tiles = GSTPrechelt(s1, s2, mML)
#compute similarity
simResult = calcSimilarity(s1.split(), s2.split(), tiles, treshold)
similarity = simResult[0]
if similarity>1: similarity = 1
#create PlagResult and set attributes
result = PlagResult()
result.setIdentifier(hash(s1), hash(s2))
result.setTiles(tiles)
result.setSimilarity(similarity)
result.setSuspectedPlagiarism(simResult[1])
#return result of similarity check as PlagResult object
return result
@return A list containing only positive, i.e. suspected, PlagResult objects.
"""
return [r for r in resultList if r.isSuspectPlagiarism()]
#===============================================================================
# Test
#===============================================================================
if __name__ == '__main__':
print "Start Tests - PlagResultList helper methods"
#create Test PlagResult1
plagResult = PlagResult("Test1", "Test2")
plagResult.setAlgorithmName("NGRAM")
plagResult.setNormalizerName("NORMAL")
plagResult.setSimilarity(0.65)
plagResult.setSuspectedPlagiarism(True)
plagResult.setIdStringLength(52, 45)
plagResult.setTiles([(3, 5, 4), (12, 23, 5), (34, 2, 3)])
#create Test PlagResult2
plagResult2 = PlagResult("Test3", "Test4")
plagResult2.setAlgorithmName("NGRAM")
plagResult2.setNormalizerName("NORMAL")
plagResult2.setSimilarity(0.45)
plagResult2.setSuspectedPlagiarism(False)
plagResult2.setIdStringLength(152, 145)
plagResult2.setTiles([(3, 5, 4), (12, 23, 5), (34, 2, 3)])
#create Test PlagResult3
plagResult3 = PlagResult("Test5", "Test6")
plagResult3.setAlgorithmName("NGRAM")
plagResult3.setNormalizerName("NORMAL")
plagResult3.setSimilarity(0.75)
tile = (int(tileTag.getAttribute("posId1")),
int(tileTag.getAttribute("posId2")),
int(tileTag.getAttribute("length")))
tiles.append(tile)
plagResult.setTiles(tiles)
plagResult.setIdStringLength(int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId1")),
int(plagResultTag.getElementsByTagName("IdStringLength")[0].getAttribute("lengthId2")))
return plagResult
#===============================================================================
# Test
#===============================================================================
if __name__ == '__main__':
print "Start Test - Transfrom PlagResult to XML and Back"
#create Test PlagResult
plagResult = PlagResult("Test1", "Test2")
plagResult.setAlgorithmName("NGRAM")
plagResult.setNormalizerName("NORMAL")
plagResult.setSimilarity(0.65)
plagResult.setSuspectedPlagiarism(True)
plagResult.setIdStringLength(52, 45)
plagResult.setTiles([(3,5,4),(12,23,5),(34,2,3)])
#test transfrom to xml and back should result in the same PlagResult object
result = resultFromXML(resultToXML(plagResult))
assert plagResult.__eq__(plagResult), "plagResult changed through transformation to xml and back"
print "End Test - Transfrom PlagResult to XML and Back"
@param resultList list containing PlagResult objects
@return A list containing only positive, i.e. suspected, PlagResult objects.
"""
return [r for r in resultList if r.isSuspectPlagiarism()]
#===============================================================================
# Test
#===============================================================================
if __name__ == '__main__':
print "Start Tests - PlagResultList helper methods"
#create Test PlagResult1
plagResult = PlagResult("Test1", "Test2")
plagResult.setAlgorithmName("NGRAM")
plagResult.setNormalizerName("NORMAL")
plagResult.setSimilarity(0.65)
plagResult.setSuspectedPlagiarism(True)
plagResult.setIdStringLength(52, 45)
plagResult.setTiles([(3,5,4),(12,23,5),(34,2,3)])
#create Test PlagResult2
plagResult2 = PlagResult("Test3", "Test4")
plagResult2.setAlgorithmName("NGRAM")
plagResult2.setNormalizerName("NORMAL")
plagResult2.setSimilarity(0.45)
plagResult2.setSuspectedPlagiarism(False)
plagResult2.setIdStringLength(152, 145)
plagResult2.setTiles([(3,5,4),(12,23,5),(34,2,3)])
#create Test PlagResult3
plagResult3 = PlagResult("Test5", "Test6")
plagResult3.setAlgorithmName("NGRAM")
plagResult3.setNormalizerName("NORMAL")
plagResult3.setSimilarity(0.75)
