def test_semanticAlignment_bug1(self):
"""test_semanticAlignment_bug1:
A bug on the semantic alignment has been identified which prevent
the computation of a valid regex. This test verifies the bug is not comming back.
@date 18/04/2013
"""
firstname1 = "antoine"
email1 = "*****@*****.**"
firstname2 = "luc"
email2 = "*****@*****.**"
msg1 = RawMessage(uuid.uuid4(), None, TypeConvertor.stringToNetzobRaw("6" + firstname1 + "GAHFSHQS" + email1))
msg2 = RawMessage(uuid.uuid4(), None, TypeConvertor.stringToNetzobRaw("3" + firstname2 + "CVSDHISD" + email2))
project = Project(uuid.uuid4(), "Experiment", datetime.now(), "")
nwEngine = NeedlemanAndWunsch(8, project, False, None)
symbol = Symbol(uuid.uuid4(), "Test", project)
symbol.addMessages([msg1, msg2])
msg1.addSemanticTag("firstname", 2, 2 + len(firstname1) * 2)
msg1.addSemanticTag("email", 2 + len(firstname1) * 2 + 16, 2 + len(firstname1) * 2 + 16 + len(email1) * 2)
msg2.addSemanticTag("firstname", 2, 2 + len(firstname2) * 2)
msg2.addSemanticTag("email", 2 + len(firstname2) * 2 + 16, 2 + len(firstname2) * 2 + 16 + len(email2) * 2)
nwEngine.alignField(symbol.getField())
symbol.getField().setFormat(Format.STRING)
print("Computed Regex : {0}".format(symbol.getRegex()))
print("=======")
print(symbol.getCells(True))
computedFields = symbol.getExtendedFields()
self.assertTrue(len(computedFields) > 1, "Only one field has been computed which tells us something went wrong.")
def test_AlignementOfMessages(self):
alignmentSolution = NeedlemanAndWunsch(4)
nbTest = 100
for iTest in range(0, nbTest):
messages = []
# Generate a random number of message to serialize
nbMessage = random.randint(2, 50)
for iMessage in range(0, nbMessage):
data = TypeConvertor.stringToNetzobRaw(
"bonjour" + self.generateRandomString(5, 30) +
", tout va bien ?")
message = RawMessage(str(uuid.uuid4()), str(time.time()), data)
messages.append(message)
(alignment, scores) = alignmentSolution.align(False, messages)
(score1, score2, score3) = scores
(alignmentBis, scoresBis) = alignmentSolution.align(True, messages)
(scoreBis1, scoreBis2, scoreBis3) = scoresBis
print(alignment)
print(alignmentBis)
self.assertGreaterEqual(scoreBis1, score1)
self.assertGreaterEqual(scoreBis1, 90)
def test_semanticAlignment_bug1(self):
"""test_semanticAlignment_bug1:
A bug on the semantic alignment has been identified which prevent
the computation of a valid regex. This test verifies the bug is not comming back.
@date 18/04/2013
"""
firstname1 = "antoine"
email1 = "*****@*****.**"
firstname2 = "luc"
email2 = "*****@*****.**"
msg1 = RawMessage(uuid.uuid4(), None, TypeConvertor.stringToNetzobRaw("6" + firstname1 + "GAHFSHQS" + email1))
msg2 = RawMessage(uuid.uuid4(), None, TypeConvertor.stringToNetzobRaw("3" + firstname2 + "CVSDHISD" + email2))
project = Project(uuid.uuid4(), "Experiment", datetime.now(), "")
nwEngine = NeedlemanAndWunsch(8, project, False, None)
symbol = Symbol(uuid.uuid4(), "Test", project)
symbol.addMessages([msg1, msg2])
msg1.addSemanticTag("firstname", 2, 2 + len(firstname1) * 2)
msg1.addSemanticTag("email", 2 + len(firstname1) * 2 + 16, 2 + len(firstname1) * 2 + 16 + len(email1) * 2)
msg2.addSemanticTag("firstname", 2, 2 + len(firstname2) * 2)
msg2.addSemanticTag("email", 2 + len(firstname2) * 2 + 16, 2 + len(firstname2) * 2 + 16 + len(email2) * 2)
nwEngine.alignField(symbol.getField())
symbol.getField().setFormat(Format.STRING)
print("Computed Regex : {0}".format(symbol.getRegex()))
print(symbol.getCells(True))
computedFields = symbol.getExtendedFields()
self.assertTrue(len(computedFields) > 1, "Only one field has been computed which tells us something went wrong.")
def test_semanticAlignment_simple(self):
"""test_semanticAlignment_simple:
Test that messages with embedded semantic are efficiently aligned.
Format : <random 10 bytes><random username><random 5 ASCII><random email>
Optimal Needleman & Wunsch Parameters :
// Cost definitions for the alignment
static const short int MATCH = 5;
static const short int SEMANTIC_MATCH = 30;
static const short int MISMATCH = -5;
static const short int GAP = 0;
static const short int BLEN = 10;
// Consts for the definition of a mask
static const unsigned char END = 2;
static const unsigned char DIFFERENT = 1;
static const unsigned char EQUAL = 0;
"""
project = Project(uuid.uuid4(), "Experiment", datetime.now(), "")
symbol = Symbol(uuid.uuid4(), "Test", project)
nbMessage = 500
usernames = []
emails = []
for iMessage in range(0, nbMessage):
str_username = self.generateRandomString(4, 10)
username = TypeConvertor.stringToNetzobRaw(str_username)
usernames.append(str_username)
email_prefix = self.generateRandomString(4, 10)
email_domain = self.generateRandomString(4, 10)
email_extension = self.generateRandomString(2, 3)
str_email = "{0}@{1}.{2}".format(email_prefix, email_domain, email_extension)
emails.append(str_email)
email = TypeConvertor.stringToNetzobRaw(str_email)
random10Bytes = self.generateRandomBytes(10, 10)
random5ASCII = TypeConvertor.stringToNetzobRaw(self.generateRandomString(5, 5))
data = "{0}{1}{2}{3}".format(random10Bytes, username, random5ASCII, email)
message = RawMessage(uuid.uuid4(), None, data)
message.addSemanticTag("username", len(random10Bytes), len(random10Bytes) + len(username))
message.addSemanticTag("email", len(random10Bytes) + len(username) + len(random5ASCII), len(random10Bytes) + len(username) + len(random5ASCII) + len(email))
symbol.addMessage(message)
nwEngine = NeedlemanAndWunsch(8, project, False, None)
nwEngine.alignField(symbol.getField())
symbol.getField().setFormat(Format.STRING)
print("Number of computed fields : {0}".format(len(symbol.getExtendedFields())))
self.assertEqual(4, len(symbol.getExtendedFields()))
nbValidMessages = 0
for message in symbol.getMessages():
isValid = symbol.getField().isRegexValidForMessage(message)
if isValid:
nbValidMessages += 1
self.assertTrue(isValid)
print(symbol.getCells())
print("Computed regex is valid for {0}/{1} messages.".format(nbValidMessages, len(symbol.getMessages())))
def test_semanticAlignment_simple(self):
"""test_semanticAlignment_simple:
Test that messages with embedded semantic are efficiently aligned.
Format : <random 10 bytes><random username><random 5 ASCII><random email>
Optimal Needleman & Wunsch Parameters :
// Cost definitions for the alignment
static const short int MATCH = 5;
static const short int SEMANTIC_MATCH = 30;
static const short int MISMATCH = -5;
static const short int GAP = 0;
static const short int BLEN = 10;
// Consts for the definition of a mask
static const unsigned char END = 2;
static const unsigned char DIFFERENT = 1;
static const unsigned char EQUAL = 0;
"""
project = Project(uuid.uuid4(), "Experiment", datetime.now(), "")
symbol = Symbol(uuid.uuid4(), "Test", project)
nbMessage = 500
usernames = []
emails = []
for iMessage in range(0, nbMessage):
str_username = self.generateRandomString(4, 10)
username = TypeConvertor.stringToNetzobRaw(str_username)
usernames.append(str_username)
email_prefix = self.generateRandomString(4, 10)
email_domain = self.generateRandomString(4, 10)
email_extension = self.generateRandomString(2, 3)
str_email = "{0}@{1}.{2}".format(email_prefix, email_domain, email_extension)
emails.append(str_email)
email = TypeConvertor.stringToNetzobRaw(str_email)
random10Bytes = self.generateRandomBytes(10, 10)
random5ASCII = TypeConvertor.stringToNetzobRaw(self.generateRandomString(5, 5))
data = "{0}{1}{2}{3}".format(random10Bytes, username, random5ASCII, email)
message = RawMessage(uuid.uuid4(), None, data)
message.addSemanticTag("username", len(random10Bytes), len(random10Bytes) + len(username))
message.addSemanticTag("email", len(random10Bytes) + len(username) + len(random5ASCII), len(random10Bytes) + len(username) + len(random5ASCII) + len(email))
symbol.addMessage(message)
nwEngine = NeedlemanAndWunsch(8, project, False, None)
nwEngine.alignField(symbol.getField())
symbol.getField().setFormat(Format.STRING)
print("Number of computed fields : {0}".format(len(symbol.getExtendedFields())))
self.assertEqual(4, len(symbol.getExtendedFields()))
nbValidMessages = 0
for message in symbol.getMessages():
isValid = symbol.getField().isRegexValidForMessage(message)
if isValid:
nbValidMessages += 1
self.assertTrue(isValid)
print(symbol.getCells())
print("Computed regex is valid for {0}/{1} messages.".format(nbValidMessages, len(symbol.getMessages())))
def test_executingClustering(self):
# We create 6 messages of 2 group
# group1
originalSymbol1 = Symbol(str(uuid.uuid4()), "TestSymbol", None)
message1 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("bonjour " +
self.generateRandomString(20, 30) +
" comment vas-tu ?"))
originalSymbol1.addMessage(message1)
originalSymbol2 = Symbol(str(uuid.uuid4()), "TestSymbol2", None)
message2 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("bonjour " +
self.generateRandomString(20, 30) +
" comment vas-tu ?"))
originalSymbol2.addMessage(message2)
originalSymbol3 = Symbol(str(uuid.uuid4()), "TestSymbol3", None)
message3 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("bonjour " +
self.generateRandomString(20, 30) +
" comment vas-tu ?"))
originalSymbol3.addMessage(message3)
# group2
originalSymbol4 = Symbol(str(uuid.uuid4()), "TestSymbol4", None)
message4 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("salut à toi " +
self.generateRandomString(10, 15) +
" what's up ?"))
originalSymbol4.addMessage(message4)
originalSymbol5 = Symbol(str(uuid.uuid4()), "TestSymbol5", None)
message5 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("salut à toi " +
self.generateRandomString(10, 15) +
" what's up ?"))
originalSymbol5.addMessage(message5)
originalSymbol6 = Symbol(str(uuid.uuid4()), "TestSymbol6", None)
message6 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw("salut à toi " +
self.generateRandomString(10, 15) +
" what's up ?"))
originalSymbol6.addMessage(message6)
symbols = [
originalSymbol1, originalSymbol2, originalSymbol3, originalSymbol4,
originalSymbol5, originalSymbol6
]
# Start the clustering
clusteringSolution = UPGMA(None, symbols, True, 100, 90, True,
Format.ASCII)
result = clusteringSolution.executeClustering()
for symbol in result:
print("Symbol: " + str(symbol.getName()))
for m in symbol.getMessages():
print(" + " + str(m.getStringData()))
def test_executingClusteringWithOrphanReduction(self):
# We create 6 messages of 2 group
# group1
originalSymbol1 = Symbol(str(uuid.uuid4()), "TestSymbol", None)
message1 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"bonjour " + self.generateRandomString(200, 1000)))
originalSymbol1.addMessage(message1)
originalSymbol2 = Symbol(str(uuid.uuid4()), "TestSymbol2", None)
message2 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"bonjour " + self.generateRandomString(200, 1000)))
originalSymbol2.addMessage(message2)
originalSymbol3 = Symbol(str(uuid.uuid4()), "TestSymbol3", None)
message3 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"bonjour " + self.generateRandomString(200, 1000)))
originalSymbol3.addMessage(message3)
# group2
originalSymbol4 = Symbol(str(uuid.uuid4()), "TestSymbol4", None)
message4 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"salut " + self.generateRandomString(200, 1000)))
originalSymbol4.addMessage(message4)
originalSymbol5 = Symbol(str(uuid.uuid4()), "TestSymbol5", None)
message5 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"salut " + self.generateRandomString(200, 1000)))
originalSymbol5.addMessage(message5)
originalSymbol6 = Symbol(str(uuid.uuid4()), "TestSymbol6", None)
message6 = RawMessage(
str(uuid.uuid4()), str(time.time()),
TypeConvertor.stringToNetzobRaw(
"salut " + self.generateRandomString(200, 1000)))
originalSymbol6.addMessage(message6)
symbols = [
originalSymbol1, originalSymbol2, originalSymbol3, originalSymbol4,
originalSymbol5, originalSymbol6
]
# Start the clustering
clusteringSolution = UPGMA(None, symbols, True, 100, 80, True,
Format.ASCII)
resultBeforeOrphan = clusteringSolution.executeClustering()
resultAfterOrphan = clusteringSolution.executeOrphanReduction()
if (len(resultAfterOrphan) < len(resultBeforeOrphan)):
print("Before Orphan Reduction: ")
for symbol in resultBeforeOrphan:
print("Symbol: " + str(symbol.getName()))
for m in symbol.getMessages():
print(" + " + str(m.getStringData()))
print("After Orphan Reduction: ")
for symbol in resultAfterOrphan:
print("Symbol: " + str(symbol.getName()))
for m in symbol.getMessages():
print(" + " + str(m.getStringData()))
self.assertGreaterEqual(len(resultBeforeOrphan),
len(resultAfterOrphan))