def transition(n, profil, pos, withTransitions):
# This is the transition function as described
# by table 4.1
#
# Note that the current profil is the state's
# characteristic vector (CV), not the current
# position's CV. It means that position's CV
# is in fact:
#
# profil[pos.i:min(n - e + 1, w - i)]
#
# (See Definition 4.0.22)
i = pos.i
e = pos.e
w = len(profil)
positions = []
if pos.isTransposition:
# if we are a transposition position, the only
# accepting position if profil is [0, 1]
if profil[i] == 1:
return [fsc.StandardPosition(i + 2, e)]
else:
return positions
if withTransitions and (w - i) >= 2 and profil[i:i + 2] == [0, 1]:
positions += [fsc.TPosition(i, e + 1)]
# Return directly if this is a match.
if i < w and profil[i] is 1:
return [fsc.StandardPosition(i + 1, e)]
# Basic positions: deletion, subsitution
positions += [
fsc.StandardPosition(i, e + 1),
fsc.StandardPosition(i + 1, e + 1)
]
# Addition operation:
if i < w:
k = fsc.positiveK(profil[i:i + min(n - e + 1, len(profil) - i)])
if k is not None:
positions.append(fsc.StandardPosition(i + k, e + k - 1))
# remove positions that goes beyong profil.
positions = [s for s in positions if s.i <= w]
# remove positions that goes beyong allowed edit mistakes
positions = [s for s in positions if s.e <= n]
return positions
def testNotSubsumming(self):
"""
Test if the subsumming test is okay.
"""
areSubsummed = [[(1, 0), (1, 0)], [(1, 0), (0, 0)], [(1, 0), (2, 0)],
[(1, 0), (3, 0)], [(1, 0), (3, 1)], [(1, 0), (4, 0)],
[(1, 0), (4, 1)], [(1, 0), (4, 2)], [(1, 0), (5, 0)],
[(1, 0), (5, 1)], [(1, 0), (5, 2)], [(1, 0), (5, 3)],
[(1, 0), (6, 0)], [(1, 0), (6, 1)], [(1, 0), (6, 2)],
[(1, 0), (6, 3)], [(1, 0), (6, 4)]]
n = 1
for entry in areSubsummed:
errorMsg = "The entry " + str(entry[0]) + " is not supposed to subsume " +\
"the entry " + str(entry[1]) + " but it is"
self.assertTrue(not fsc.isSubsumming(fsc.StandardPosition(entry[0][0], entry[0][1]), \
fsc.StandardPosition(entry[1][0], entry[1][1]), n), msg = errorMsg)
def testSubsumming(self):
"""
Test if the subsumming test is okay.
"""
areSubsummed = [[(1, 0), (0, 1)], [(1, 0), (1, 1)], [(1, 0), (2, 1)],
[(1, 0), (0, 2)], [(1, 0), (1, 2)], [(1, 0), (2, 2)],
[(1, 0), (3, 2)], [(1, 0), (0, 3)], [(1, 0), (1, 3)],
[(1, 0), (2, 3)], [(1, 0), (3, 3)], [(1, 0), (4, 3)],
[(2, 0), (1, 1)], [(2, 0), (2, 1)], [(2, 0), (3, 1)],
[(2, 0), (0, 2)], [(2, 0), (1, 2)], [(2, 0), (2, 2)],
[(2, 0), (3, 2)], [(2, 0), (4, 2)], [(2, 0), (0, 3)],
[(2, 0), (1, 3)], [(2, 0), (2, 3)], [(2, 0), (3, 3)],
[(2, 0), (4, 3)], [(2, 0), (5, 3)]]
n = 1
for entry in areSubsummed:
errorMsg = "The entry " + str(entry[0]) + " is supposed to subsume " +\
"the entry " + str(entry[1]) + " but it isn't"
self.assert_(fsc.isSubsumming(fsc.StandardPosition(entry[0][0], entry[0][1]), \
fsc.StandardPosition(entry[1][0], entry[1][1]), n), msg = errorMsg)
def genTransitions(n, withTransitions = True):
allProfils = genAllProfilPowerSet(n)
transitions = [{} for i in range(2 * n + 2)]
# Add the initial state
processedStates = []
unprocessedStates = [[fsc.StandardPosition(0,0)]]
while len(unprocessedStates) > 0:
state = unprocessedStates.pop()
processedStates.append(state)
profilLenMin, profilLenMax = determineRelevantSubwordLenghts(n, state)
for profilLen in range(profilLenMin, profilLenMax + 1):
for profil in allProfils[profilLen]:
# for the current characteristic vector check what
# is the next state.
nextState, difference = getNextState(n, profil, state, withTransitions)
transitions[profilLen].setdefault(str(profil), {}).setdefault(str(state), (nextState, difference))
if nextState != [] and not nextState in processedStates and not nextState in unprocessedStates:
unprocessedStates.append(nextState)
return transitions
