def GSTPrechelt(s1, s2, minimalMatchingLength):
"""TODO: Beschreibung
"""
s1List = s1.split()
s2List = s2.split()
matches = set([])
hashList = computeHashList(s1List, minimalMatchingLength)
i = 0
while (i < len(s2List)-minimalMatchingLength): #for i in xrange(len(s2List)-minimatchingLength):
h = createKRHashValue(" ".join(s2List[i:i+minimalMatchingLength]))
#get positions for hashvalue from string s1
positions = hashList.get(h)
if positions:
for pos in positions:
#check if substrings are equal
j = 0
while (pos+j<len(s1List) and i+j<len(s2List) and s1List[pos+j] == s2List[i+j]):
j += 1
#try to extend the match
if j >= minimalMatchingLength:
#match
matches = matches | set([(pos, i, j)]) #pos1, pos2, length
# foundMatch = True
else:
#no match
pass
#foundMatch = False
#insert match
i += 1
#return matches as List
return reduceMatches(list(matches))
def computeHashList(s, minimalMatchingLength):
hashList = GSTHashtable()
for i in xrange(len(s)-minimalMatchingLength):
hashList.add(createKRHashValue(" ".join(s[i:i+minimalMatchingLength])), i)
return hashList