def get(self, md5):
self._check_connection()
util.check_md5(md5)
r = pyaccumulo.Range(srow=md5, erow=md5, scf='file{', ecf='file}')
entries = [x for x in self.conn.scan(self.file_table, scanrange=r)]
if len(entries) == 0:
return None
projects = []
paths = []
size = None
tags = False
for entry in self.conn.scan(self.file_table, scanrange=r):
if entry.cf == 'file|path':
paths.append(entry.cq)
elif entry.cf == 'file|project':
projects.append(entry.cq)
elif entry.cf == 'file|size' and entry.cq == 'size':
size = int(entry.val)
elif entry.cf == 'twosix' and entry.cq == 'tags':
tags = bool(entry.val)
elif entry.cf == 'file|content' and entry.cq == 'content':
content = entry.val
else:
raise ValueError('cf {}, cq {} not recognized'.format(
entry.cf, entry.cq))
return projects, paths, size, content, tags
def range(self, start, end):
"""
Return md5s in the range of (start, end)
"""
self._check_connection()
hashes = set()
r = pyaccumulo.Range(srow=start, erow=end)
for entry in self.conn.scan(self.file_table,
scanrange=r,
cols=[['file|size']]):
hashes.add(entry.row)
return sorted(list(hashes))
def prefix(self, pre):
"""
Return md5s starting with the prefix
"""
self._check_connection()
hashes = set()
r = pyaccumulo.Range(srow=pre, erow=pre + '}')
for entry in self.conn.scan(self.file_table,
scanrange=r,
cols=[['file|size']]):
hashes.add(entry.row)
return sorted(list(hashes))
def range_uuid_name(self, start, end):
"""
Return a list of tuples from md5 to filename
"""
self._check_connection()
md5 = None
r = pyaccumulo.Range(srow=start, erow=end)
for entry in self.conn.scan(self.file_table,
scanrange=r,
cols=[['file|path']]):
if entry.row != md5:
md5 = entry.row
filepath = entry.cq
uuid = filepath[:36]
filename = os.path.basename(filepath)
yield md5, uuid, filename
def read(self, md5):
util.check_md5(md5)
r = pyaccumulo.Range(srow=md5, erow=md5, scf='file{', ecf='file}')
entries = [x for x in self.conn.scan(self.file_table, scanrange=r)]
if len(entries) == 0:
return None
projects = []
paths = []
size = None
for entry in entries:
if entry.cf == 'file|path':
paths.append(entry.cq)
elif entry.cf == 'file|project':
projects.append(entry.cq)
elif entry.cf == 'file|size' and entry.cq == 'size':
size = int(entry.val)
def run_search(conn=None,
table='demo',
config_name = 'expressive',
PKI_object=None,
row_range='Analytics'):
""" Retrieves and decrypts values from the specified table,
outputting the appropriate error messages if not.
Arguments:
conn - the Accumulo connection to use
data - the list to insert into the Accumulo table
table - the name of the table to insert to
config_filept - file pointer to the configuration file for encryption
PKI_object - matches the interface on encryption PKI OBJECT, default is
DummyEncryptionPKI
row_range - the keyword to search for
"""
if conn is None:
conn = pyaccumulo.Accumulo(host='localhost',
port=42424,
user='******',
password='******')
if PKI_object is None:
PKI_object = DummyEncryptionPKI(conn=conn)
total = 0
enc_config_filept = StringIO(schema[config_name])
dec_config_filept = StringIO(schema[config_name])
encrypter = AccumuloEncrypt(enc_config_filept, PKI_object)
enc_row, _ = encrypter.encrypt_search(row_range, None)
range = pyaccumulo.Range(srow = enc_row, sinclude = True,
erow = enc_row, einclude = True)
for entry in conn.scan(table, scanrange=range):
total = total + 1
try:
cell = encrypter.decrypt(entry)
print "Entry: (%s, %s, %s, %s)" % (cell.row, cell.cf, cell.cq, cell.val)
except DecryptionException as ve:
print 'Error: Entry failed to decrypt.'
print 'Error message:', ve.msg
print
print 'Finished, decrypted %d total entries.' %(total)