def ingest_feature_file(self,f,context_stop_list):
"""Read the lines in a feature file; returns how many lines were procesed"""
drivename = None
count = 0
for line in f:
if type(line)==bytes:
line = line.decode('utf-8')
m = bulk_extractor_reader.get_property_line(line)
if m:
if m[0]=='Filename':
drivename = m[1]
self.drives.add(drivename)
print("Scanning {} for {}".format(drivename,self.name))
if bulk_extractor_reader.is_comment_line(line):
continue
count += 1
if context_stop_list != None:
(offset,feature,context) = line.split("\t")
context_stop_list.add((feature,context))
continue
feature = line.split("\t")[1]
featuredict = self.features[feature]
featuredict[drivename] = featuredict.get(drivename,0)+1
print(" processed {} features".format(count))
return count
def ingest_feature_file(self,f,context_stop_list):
"""Read the lines in a feature file; returns how many lines were procesed"""
drivename = None
count = 0
for line in f:
if type(line)==bytes:
line = line.decode('utf-8')
m = bulk_extractor_reader.get_property_line(line)
if m:
if m[0]=='Filename':
drivename = m[1]
self.drives.add(drivename)
print("Scanning {} for {}".format(drivename,self.name))
if bulk_extractor_reader.is_comment_line(line):
continue
count += 1
if context_stop_list != None:
(offset,feature,context) = line.split("\t")
context_stop_list.add((feature,context))
continue
feature = line.split("\t")[1]
featuredict = self.features[feature]
featuredict[drivename] = featuredict.get(drivename,0)+1
print(" processed {} features".format(count))
return count
def ingest_histogram_file(self,f):
drivename = None
for line in f:
if type(line)==bytes:
line = line.decode('utf-8')
m = bulk_extractor_reader.get_property_line(line)
if m:
if m[0]=='Filename':
drivename = m[1]
self.drives.add(drivename)
print("Scanning {} for {}".format(drivename,self.name))
continue
if bulk_extractor_reader.is_comment_line(line):
continue
fields = line.split("\t")
count = int(fields[0][2:])
feature = fields[1].strip()
featuredict = self.features[feature]
featuredict[drivename] = featuredict.get(drivename,0)+count
def ingest_histogram_file(self,f):
drivename = None
for line in f:
if type(line)==bytes:
line = line.decode('utf-8')
m = bulk_extractor_reader.get_property_line(line)
if m:
if m[0]=='Filename':
drivename = m[1]
self.drives.add(drivename)
print("Scanning {} for {}".format(drivename,self.name))
continue
if bulk_extractor_reader.is_comment_line(line):
continue
fields = line.split("\t")
count = int(fields[0][2:])
feature = fields[1].strip()
featuredict = self.features[feature]
featuredict[drivename] = featuredict.get(drivename,0)+count