def match(self):
# tokenize the message
if self.lexerType == LEXER_TOKENS:
tokens = scanTokens(self.msg, self.ws)
else:
tokens = scanNgrams(self.msg)
if len(tokens) != len(self.template.content):
# no match due to different token count
return None
fields = []
match = True
for (tok, msg) in zip(self.template.content, tokens):
curVal = msg[1]
# check for field
if tok == "":
fields.append(curVal)
else:
if urllib.quote(curVal) != tok:
match = False
break
if match:
ret = fields
else:
ret = None
return ret
def match(self):
# tokenize the message
# somehow self.lexerType is a boolean..?
# thus always ngrams was picked and failed
# due to token length missmatch
# if self.lexerType == LEXER_TOKENS:
if self.lexerType == False:
tokens = scanTokens(self.msg, self.ws)
else:
tokens = scanNgrams(self.msg)
if len(tokens) != len(self.template.content):
# no match due to different token count
return None
fields = []
match = True
for (tok, msg) in zip(self.template.content, tokens):
curVal = msg[1]
# check for field
if tok == "":
fields.append(curVal)
else:
if urllib.quote(curVal) != tok:
match = False
break
if match:
ret = fields
else:
ret = None
return ret
def match(self):
# tokenize the message
if self.lexerType == LEXER_TOKENS:
tokens = scanTokens(self.msg, self.ws)
else:
tokens = scanNgrams(self.msg)
fields = []
for (tok, msg) in zip(self.template.content, tokens):
curVal = msg[1]
# check for field
if tok == "":
fields.append(curVal)
# find distance between msg and template
template_str = ''.join([t for t in self.template.content])
d = distance(self.msg, template_str)
return fields, d
def match(self):
# tokenize the message
if self.lexerType == LEXER_TOKENS:
tokens = scanTokens(self.msg, self.ws)
else:
tokens = scanNgrams(self.msg)
fields = []
for (tok, msg) in zip(self.template.content, tokens):
curVal = msg[1]
# check for field
if tok == "":
fields.append(curVal)
# find distance between msg and template
template_str = ''.join([t for t in self.template.content])
d = distance(self.msg, template_str)
return fields, d
def match(self):
if self.lexerType == LEXER_TOKENS:
tokens = scanTokens(self.msg, self.ws)
else:
tokens = scanNgrams(self.msg)
if len(tokens) != len(self.template.content):
# no match due to different token count
return None
fields = []
match = True
for (tok, msg) in zip(self.template.content, tokens):
curVal = msg[1]
# check for field
if tok == "":
fields.append(curVal)
else:
if urllib.quote(curVal) != tok:
match = False
break
if match:
ret = fields
else:
ret = None
return ret
def getTokensForMsg(self, msgIndex):
if self.ngram == 0:
return scanTokens(self.messages[msgIndex], self.whitespace)
else:
return scanNgrams(self.messages[msgIndex])
def getTokensForMsg(self, msgIndex):
if self.ngram == 0:
return scanTokens(self.messages[msgIndex], self.whitespace)
else:
return scanNgrams(self.messages[msgIndex])