def split(field, delimiter):
"""Split a field (or symbol) with a specific delimiter. The
delimiter can be passed either as an ASCII, a Raw, an
HexaString, or any objects that inherit from AbstractType.
>>> from netzob.all import *
>>> samples = ["aaaaff000000ff10", "bbff110010ff00000011", "ccccccccfffe1f000000ff12"]
>>> messages = [RawMessage(data=sample) for sample in samples]
>>> symbol = Symbol(messages=messages[:3])
>>> Format.splitDelimiter(symbol, ASCII("ff"))
>>> print symbol
Field-0 | Field-sep-6666 | Field-2 | Field-sep-6666 | Field-4
---------- | -------------- | ------------ | -------------- | ----------
'aaaa' | 'ff' | '000000' | 'ff' | '10'
'bb' | 'ff' | '110010' | 'ff' | '00000011'
'cccccccc' | 'ff' | 'fe1f000000' | 'ff' | '12'
---------- | -------------- | ------------ | -------------- | ----------
>>> samples = ["434d446964656e74696679230400000066726564", "5245536964656e74696679230000000000000000", "434d44696e666f2300000000", "524553696e666f230000000004000000696e666f","434d4473746174732300000000","52455373746174732300000000050000007374617473","434d4461757468656e7469667923090000006d7950617373776421","52455361757468656e74696679230000000000000000","434d44656e6372797074230a00000031323334353674657374","524553656e637279707423000000000a00000073707176777436273136","434d4464656372797074230a00000073707176777436273136","5245536465637279707423000000000a00000031323334353674657374","434d446279652300000000","524553627965230000000000000000","434d446964656e746966792307000000526f626572746f","5245536964656e74696679230000000000000000","434d44696e666f2300000000","524553696e666f230000000004000000696e666f","434d4473746174732300000000","52455373746174732300000000050000007374617473","434d4461757468656e74696679230a000000615374726f6e67507764","52455361757468656e74696679230000000000000000","434d44656e63727970742306000000616263646566","524553656e6372797074230000000006000000232021262724","434d44646563727970742306000000232021262724","52455364656372797074230000000006000000616263646566","434d446279652300000000","524553627965230000000000000000"]
>>> messages = [RawMessage(data=TypeConverter.convert(sample, HexaString, Raw)) for sample in samples]
>>> symbol = Symbol(messages=messages)
>>> symbol.encodingFunctions.add(TypeEncodingFunction(ASCII)) # Change visualization to hexastring
>>> Format.splitDelimiter(symbol, ASCII("#"))
>>> print symbol
Field-0 | Field-sep-23 | Field-2 | Field-sep-23 | Field-4
--------------- | ------------ | -------------------- | ------------ | -------
'CMDidentify' | '#' | '....fred' | '' | ''
'RESidentify' | '#' | '........' | '' | ''
'CMDinfo' | '#' | '....' | '' | ''
'RESinfo' | '#' | '........info' | '' | ''
'CMDstats' | '#' | '....' | '' | ''
'RESstats' | '#' | '........stats' | '' | ''
'CMDauthentify' | '#' | '....myPasswd!' | '' | ''
'RESauthentify' | '#' | '........' | '' | ''
'CMDencrypt' | '#' | '....123456test' | '' | ''
'RESencrypt' | '#' | "........spqvwt6'16" | '' | ''
'CMDdecrypt' | '#' | "....spqvwt6'16" | '' | ''
'RESdecrypt' | '#' | '........123456test' | '' | ''
'CMDbye' | '#' | '....' | '' | ''
'RESbye' | '#' | '........' | '' | ''
'CMDidentify' | '#' | '....Roberto' | '' | ''
'RESidentify' | '#' | '........' | '' | ''
'CMDinfo' | '#' | '....' | '' | ''
'RESinfo' | '#' | '........info' | '' | ''
'CMDstats' | '#' | '....' | '' | ''
'RESstats' | '#' | '........stats' | '' | ''
'CMDauthentify' | '#' | '....aStrongPwd' | '' | ''
'RESauthentify' | '#' | '........' | '' | ''
'CMDencrypt' | '#' | '....abcdef' | '' | ''
'RESencrypt' | '#' | '........' | '#' | " !&'$"
'CMDdecrypt' | '#' | '....' | '#' | " !&'$"
'RESdecrypt' | '#' | '........abcdef' | '' | ''
'CMDbye' | '#' | '....' | '' | ''
'RESbye' | '#' | '........' | '' | ''
--------------- | ------------ | -------------------- | ------------ | -------
>>> print symbol.fields[0]._str_debug()
Field-0
|-- Alt
|-- Data (Raw='CMDidentify' ((0, 88)))
|-- Data (Raw='RESidentify' ((0, 88)))
|-- Data (Raw='CMDinfo' ((0, 56)))
|-- Data (Raw='RESinfo' ((0, 56)))
|-- Data (Raw='CMDstats' ((0, 64)))
|-- Data (Raw='RESstats' ((0, 64)))
|-- Data (Raw='CMDauthentify' ((0, 104)))
|-- Data (Raw='RESauthentify' ((0, 104)))
|-- Data (Raw='CMDencrypt' ((0, 80)))
|-- Data (Raw='RESencrypt' ((0, 80)))
|-- Data (Raw='CMDdecrypt' ((0, 80)))
|-- Data (Raw='RESdecrypt' ((0, 80)))
|-- Data (Raw='CMDbye' ((0, 48)))
|-- Data (Raw='RESbye' ((0, 48)))
:param field : the field to consider when spliting
:type: :class:`netzob.Common.Models.Vocabulary.AbstractField.AbstractField`
:param delimiter : the delimiter used to split messages of the field
:type: :class:`netzob.Common.Models.Types.AbstractType.AbstractType`
"""
if delimiter is None:
raise TypeError("Delimiter cannot be None.")
if field is None:
raise TypeError("Field cannot be None.")
if len(field.messages) < 1:
raise ValueError(
"The associated symbol does not contain any message.")
# Find message substrings after applying delimiter
splittedMessages = []
for cell in field.getValues(encoded=False, styled=False):
splittedMessage = cell.split(delimiter.value.tobytes())
splittedMessages.append(splittedMessage)
import itertools
# Inverse the array, so that columns contains observed values for each field
splittedMessages = list(itertools.izip_longest(*splittedMessages))
# If the delimiter does not create splitted fields
if len(splittedMessages) <= 1:
return
# Else, we add (2*len(splittedMessages)-1) fields
newFields = []
iField = -1
for i in range(len(splittedMessages)):
iField += 1
fieldDomain = list()
# temporary set that hosts all the observed values to prevent useless duplicate ones
observedValues = set()
has_inserted_empty_value = False
isEmptyField = True # To avoid adding an empty field
for v in splittedMessages[i]:
if v != "" and v is not None:
isEmptyField = False
if v not in observedValues:
fieldDomain.append(Raw(v))
observedValues.add(v)
else:
if not has_inserted_empty_value:
fieldDomain.append(Raw(nbBytes=0))
has_inserted_empty_value = True
if not isEmptyField:
newField = Field(
domain=DomainFactory.normalizeDomain(fieldDomain),
name="Field-" + str(iField))
newField.encodingFunctions = field.encodingFunctions.values()
newFields.append(newField)
iField += 1
fieldName = "Field-sep-" + TypeConverter.convert(
delimiter.value, BitArray, HexaString)
newFields.append(
Field(domain=Alt([delimiter, Raw(nbBytes=0)]), name=fieldName))
newFields.pop()
# Reset the field
from netzob.Inference.Vocabulary.Format import Format
Format.resetFormat(field)
# Create a field for each entry
field.fields = newFields
def mergeFields(self, field1, field2):
"""Merge specified fields.
>>> import binascii
>>> from netzob.all import *
>>> samples = ["00ff2f000000", "000010000000", "00fe1f000000"]
>>> messages = [RawMessage(data=binascii.unhexlify(sample)) for sample in samples]
>>> f1 = Field(Raw(nbBytes=1), name="f1")
>>> f2 = Field(Raw(nbBytes=2), name="f2")
>>> f3 = Field(Raw(nbBytes=2), name="f3")
>>> f4 = Field(Raw(nbBytes=1), name="f4")
>>> symbol = Symbol([f1, f2, f3, f4], messages=messages)
>>> symbol.addEncodingFunction(TypeEncodingFunction(HexaString))
>>> print symbol
f1 | f2 | f3 | f4
---- | ------ | ------ | ----
'00' | 'ff2f' | '0000' | '00'
'00' | '0010' | '0000' | '00'
'00' | 'fe1f' | '0000' | '00'
---- | ------ | ------ | ----
>>> fo = FieldOperations()
>>> fo.mergeFields(f2, f3)
>>> print symbol
f1 | Merge | f4
---- | ---------- | ----
'00' | 'ff2f0000' | '00'
'00' | '00100000' | '00'
'00' | 'fe1f0000' | '00'
---- | ---------- | ----
>>> fo.mergeFields(symbol.fields[0], symbol.fields[1])
>>> print symbol
Merge | f4
------------ | ----
'00ff2f0000' | '00'
'0000100000' | '00'
'00fe1f0000' | '00'
------------ | ----
>>> fo.mergeFields(symbol.fields[0], symbol.fields[1])
>>> print symbol
Merge
--------------
'00ff2f000000'
'000010000000'
'00fe1f000000'
--------------
:param field1: the left field to merge
:type field1: :class:`netzob.Common.Models.Vocabulary.AbstractField.AbstractField`
:param field2: the right field to merge
:type field2: :class:`netzob.Common.Models.Vocabulary.AbstractField.AbstractField`
:raise Exception if something bad happens
"""
if field1 is None or field2 is None:
raise TypeError("Fields cannot be None")
if field1 == field2:
raise ValueError("Cannot merge a unique field (field1 == field2)")
self._logger.debug("Merging field {0} with field {1}".format(field1.name, field2.name))
if field1.parent is not field2.parent:
raise ValueError("Specified fields don't have the same parent, only fields with same parents can be merged.")
# retrieve indexes of specified fields
iField1 = None
iField2 = None
for iField, field in enumerate(field1.parent.fields):
if field == field1:
iField1 = iField
elif field == field2:
iField2 = iField
if iField1 is None:
raise ValueError("Cannot retrieve position of field1 in its parent fields")
if iField2 is None:
raise ValueError("Cannot retrieve position of field2 in its parent fields")
if iField2 != iField1 + 1:
raise ValueError("Field1 must be directly on the left of field2 (iField1={0}, iField2={1})".format(iField1, iField2))
# build a new field domain
newDomain = Agg([field1.domain, field2.domain])
newField = Field(domain=newDomain, name="Merge")
newField.encodingFunctions = field1.encodingFunctions.values()
parent = field1.parent
before = parent.fields[:iField1]
after = parent.fields[iField2 + 1:]
parent.fields = before + [newField] + after
def split(field, delimiter):
"""Split a field (or symbol) with a specific delimiter. The
delimiter can be passed either as an ASCII, a Raw, an
HexaString, or any objects that inherit from AbstractType.
>>> from netzob.all import *
>>> samples = ["aaaaff000000ff10", "bbff110010ff00000011", "ccccccccfffe1f000000ff12"]
>>> messages = [RawMessage(data=sample) for sample in samples]
>>> symbol = Symbol(messages=messages[:3])
>>> Format.splitDelimiter(symbol, ASCII("ff"))
>>> print symbol
'aaaa' | 'ff' | '000000' | 'ff' | '10'
'bb' | 'ff' | '110010' | 'ff' | '00000011'
'cccccccc' | 'ff' | 'fe1f000000' | 'ff' | '12'
>>> samples = ["434d446964656e74696679230400000066726564", "5245536964656e74696679230000000000000000", "434d44696e666f2300000000", "524553696e666f230000000004000000696e666f","434d4473746174732300000000","52455373746174732300000000050000007374617473","434d4461757468656e7469667923090000006d7950617373776421","52455361757468656e74696679230000000000000000","434d44656e6372797074230a00000031323334353674657374","524553656e637279707423000000000a00000073707176777436273136","434d4464656372797074230a00000073707176777436273136","5245536465637279707423000000000a00000031323334353674657374","434d446279652300000000","524553627965230000000000000000","434d446964656e746966792307000000526f626572746f","5245536964656e74696679230000000000000000","434d44696e666f2300000000","524553696e666f230000000004000000696e666f","434d4473746174732300000000","52455373746174732300000000050000007374617473","434d4461757468656e74696679230a000000615374726f6e67507764","52455361757468656e74696679230000000000000000","434d44656e63727970742306000000616263646566","524553656e6372797074230000000006000000232021262724","434d44646563727970742306000000232021262724","52455364656372797074230000000006000000616263646566","434d446279652300000000","524553627965230000000000000000"]
>>> messages = [RawMessage(data=TypeConverter.convert(sample, HexaString, Raw)) for sample in samples]
>>> symbol = Symbol(messages=messages)
>>> symbol.encodingFunctions.add(TypeEncodingFunction(ASCII)) # Change visualization to hexastring
>>> Format.splitDelimiter(symbol, ASCII("#"))
>>> print symbol
'CMDidentify' | '#' | '....fred' | '' | ''
'RESidentify' | '#' | '........' | '' | ''
'CMDinfo' | '#' | '....' | '' | ''
'RESinfo' | '#' | '........info' | '' | ''
'CMDstats' | '#' | '....' | '' | ''
'RESstats' | '#' | '........stats' | '' | ''
'CMDauthentify' | '#' | '....myPasswd!' | '' | ''
'RESauthentify' | '#' | '........' | '' | ''
'CMDencrypt' | '#' | '....123456test' | '' | ''
'RESencrypt' | '#' | "........spqvwt6'16" | '' | ''
'CMDdecrypt' | '#' | "....spqvwt6'16" | '' | ''
'RESdecrypt' | '#' | '........123456test' | '' | ''
'CMDbye' | '#' | '....' | '' | ''
'RESbye' | '#' | '........' | '' | ''
'CMDidentify' | '#' | '....Roberto' | '' | ''
'RESidentify' | '#' | '........' | '' | ''
'CMDinfo' | '#' | '....' | '' | ''
'RESinfo' | '#' | '........info' | '' | ''
'CMDstats' | '#' | '....' | '' | ''
'RESstats' | '#' | '........stats' | '' | ''
'CMDauthentify' | '#' | '....aStrongPwd' | '' | ''
'RESauthentify' | '#' | '........' | '' | ''
'CMDencrypt' | '#' | '....abcdef' | '' | ''
'RESencrypt' | '#' | '........' | '#' | " !&'$"
'CMDdecrypt' | '#' | '....' | '#' | " !&'$"
'RESdecrypt' | '#' | '........abcdef' | '' | ''
'CMDbye' | '#' | '....' | '' | ''
'RESbye' | '#' | '........' | '' | ''
:param field : the field to consider when spliting
:type: :class:`netzob.Common.Models.Vocabulary.AbstractField.AbstractField`
:param delimiter : the delimiter used to split messages of the field
:type: :class:`netzob.Common.Models.Types.AbstractType.AbstractType`
"""
if delimiter is None:
raise TypeError("Delimiter cannot be None.")
if field is None:
raise TypeError("Field cannot be None.")
if len(field.messages) < 1:
raise ValueError("The associated symbol does not contain any message.")
# Find message substrings after applying delimiter
splittedMessages = []
for cell in field.getValues(encoded=False, styled=False):
splittedMessage = cell.split(delimiter.value.tobytes())
splittedMessages.append(splittedMessage)
import itertools
# Inverse the array, so that columns contains observed values for each field
splittedMessages = list(itertools.izip_longest(*splittedMessages))
# If the delimiter does not create splitted fields
if len(splittedMessages) <= 1:
return
# Else, we add (2*len(splittedMessages)-1) fields
newFields = []
iField = -1
for i in range(len(splittedMessages)):
iField += 1
fieldDomain = set()
isEmptyField = True # To avoid adding an empty field
emptyValueFound = False
for v in splittedMessages[i]:
if v != "" and v is not None:
isEmptyField = False
fieldDomain.add(Raw(v))
else:
fieldDomain.add(Raw(nbBytes=0))
if not isEmptyField:
fieldDomain = list(fieldDomain)
newField = Field(domain=DomainFactory.normalizeDomain(fieldDomain), name="Field-"+str(iField))
newField.encodingFunctions = field.encodingFunctions.values()
newFields.append(newField)
iField += 1
fieldName = "Field-sep-" + TypeConverter.convert(delimiter.value, BitArray, HexaString)
newFields.append(Field(domain=Alt([delimiter, Raw(nbBytes=0)]), name=fieldName))
newFields.pop()
# Reset the field
from netzob.Inference.Vocabulary.Format import Format
Format.resetFormat(field)
# Create a field for each entry
field.fields = newFields
