def testAppendToBits(self):
a = Bits(BitArray())
with self.assertRaises(AttributeError):
a.append('0b1')
self.assertEqual(type(a), Bits)
b = bitstring.ConstBitStream(bitstring.BitStream())
self.assertEqual(type(b), bitstring.ConstBitStream)
def read_spk_folder(spk_folder, bin_size=1):
"""
Loads spike times from all spk files in a given folder.
The j-th item in the list corresponds to the j-th neuron.
It is the 1d array of spike times (microsec) for that neuron.
Parameters
----------
spk_folder : str
Path containing spk file names
bin_size : int, optional
Bin size in milliseconds (default 1)
Returns
-------
spikes : numpy array
numpy array containing binned spike times
"""
from bitstring import Bits
neuron_to_file = []
time_stamps = []
bin_size = bin_size or 1
fns = os.listdir(spk_folder)
for i, fn in enumerate(fns):
ext = os.path.splitext(fn)[1]
if ext in ('.spk', ): # Blanche spike format
neuron_to_file.append(fn)
f = open(os.path.join(spk_folder, fn), 'rb')
p = Bits(f)
fmt = str(p.length / 64) + ' * (intle:64)'
time_stamps.append(p.unpack(fmt))
spikes = SpkReader.load_from_spikes_times(time_stamps, bin_size=bin_size)
return Spikes(spikes)
def readCommand(hexbits):
bits = Bits(bytes=HexToByte(hexbits))
# print bits
alarm, state, data1, data2, checksum = bits.unpack("uint:4, uint:4, uint:8, uint:8, uint:8")
dic = {"state": state, "alarm": alarm, "data1": data1, "data2": data2, "checksum": checksum}
return dic
def uncompress_golomb_coding(coded_bytes, hash_length, M):
"""Given a bytstream produced using golomb_coded_bytes, uncompress it."""
ret_list = []
instream = BitStream(
bytes=coded_bytes, length=len(coded_bytes) * 8)
hash_len_bits = hash_length * 8
m_bits = int(math.log(M, 2))
# First item is a full hash value.
prev = instream.read("bits:%d" % hash_len_bits)
ret_list.append(prev.tobytes())
while (instream.bitpos + m_bits) <= instream.length:
# Read Unary-encoded value.
read_prefix = 0
curr_bit = instream.read("uint:1")
while curr_bit == 1:
read_prefix += 1
curr_bit = instream.read("uint:1")
assert curr_bit == 0
# Read r, assuming M bits were used to represent it.
r = instream.read("uint:%d" % m_bits)
curr_diff = read_prefix * M + r
curr_value_int = prev.uint + curr_diff
curr_value = Bits(uint=curr_value_int, length=hash_len_bits)
ret_list.append(curr_value.tobytes())
prev = curr_value
return ret_list
def read_spk_files(spk_files, bin_size=1):
"""
Loads spike times from a list of spk files.
The j-th item in the list corresponds to the j-th neuron.
It is the 1d array of spike times (microsec) for that neuron.
Parameters
----------
spk_files : list of str
List of strings containing spk file names
bin_size : int, optional
Bin size in milliseconds (default 1)
Returns
-------
spikes : numpy array
numpy array containing binned spike times
"""
from bitstring import Bits
neuron_to_file = []
time_stamps = []
bin_size = bin_size or 1
for fn in spk_files:
neuron_to_file.append(fn)
f = open(fn, 'rb')
p = Bits(f)
fmt = str(p.length / 64) + ' * (intle:64)'
time_stamps.append(p.unpack(fmt))
spikes = SpkReader.load_from_spikes_times(time_stamps, bin_size=bin_size)
return Spikes(spikes)
def testUnpack(self):
s = Bits('0b111000111')
x, y = s.unpack('3, pad:3, 3')
self.assertEqual((x, y), (7, 7))
x, y = s.unpack('2, pad:2, bin')
self.assertEqual((x, y), (3, '00111'))
x = s.unpack('pad:1, pad:2, pad:3')
self.assertEqual(x, [])
def to_comp1(n,v):
bits_raw=Bits(uint=abs(v),length=n)
if(v<0):
bits= (bits_raw.__invert__()).bin
else:
bits= bits_raw.bin
return bits
def solve(par):
N, K = par
results = []
for i in range(1 << N):
b = Bits(int=i, length=N + 1)
if b.count(1) == K:
results.append(b.bin[1:])
return '\n'.join(results)
def getStatusByte(byte1):
"""
Gets Two First Bytes, and returns a dictionary with:
Command
SetGroup
Address
"""
bits8 = Bits(bytes=byte1)
status1, status2 = bits8.unpack("uint:4,uint:4")
return dict(status1=getSt3st0(status1), status2=getSt7st4(status2))
def uncompress_golomb_coding(coded_bytes, hash_length, M):
ret_list = []
instream = BitStream(
bytes=coded_bytes, length=len(coded_bytes) * hash_length)
hash_len_bits = hash_length * 8
m_bits = int(math.log(M, 2))
prev = instream.read("bits:%d" % hash_len_bits)
ret_list.append(prev.tobytes())
while instream.bitpos < instream.length:
read_prefix = 0
curr_bit = instream.read("uint:1")
while curr_bit == 1:
read_prefix += 1
curr_bit = instream.read("uint:1")
assert curr_bit == 0
r = instream.read("uint:%d" % m_bits)
curr_diff = read_prefix * M + r
curr_value_int = prev.uint + curr_diff
curr_value = Bits(uint=curr_value_int, length=hash_len_bits)
ret_list.append(curr_value.tobytes())
prev = curr_value
return ret_list
def opcode(self, o):
self._opcode = Bits(uint=o, length=4)
def assemble(self):
return Bits("0b0101, 12*(0b0)").bin
def validateIncoming(byteStr):
bits32 = Bits(bytes=byteStr)
first, second, third, fourth = bits32.unpack("bytes:1,bytes:1,bytes:1,bytes:1")
check = countCheckSumIncoming(first, second, third)
assert str(check) == "0x" + str(ByteToHex(fourth)).lower()
def encode(self, value):
'''
:param value: value to encode
'''
return Bits(bytes=strToBytes(self.fmt % value))
def build_packet(self):
"""Build the complete encoded packet ready for transmission and return it as a BitArray"""
packet_words = []
# stat with the 3 word serial number
packet_words.extend([Bits(bin=s) for s in self.serial])
# build the first command word
cmd1 = BitArray()
cmd1.append('0b1' if self.pilot else '0b0') # 1 pilot bit
cmd1.append(Bits(uint=self.light, length=3)) # 3 light bits
cmd1.append('0b00') # 2 zero bits
cmd1.append('0b1' if self.thermostat else '0b0') # 1 thermostat bit
cmd1.append('0b1' if self.power else '0b0') # 1 power bit
cmd1.append('0x0') # 1 zero padding bit
packet_words.append(cmd1)
# build the second command word
cmd2 = BitArray()
cmd2.append('0b1' if self.front else '0b0') # 1 pilot bit
cmd2.append(Bits(uint=self.fan, length=3)) # 3 light bits
cmd2.append('0b1' if self.aux else '0b0') # 1 pilot bit
cmd2.append(Bits(uint=self.flame, length=3)) # 3 light bits
cmd2.append('0x0') # 1 zero padding bit
packet_words.append(cmd2)
# calculate the first ecc word
ecc1 = BitArray()
ecc1_high = (0xD ^ cmd1[0:4].uint ^ (cmd1[0:4].uint << 1) ^
(cmd1[4:8].uint << 1)) & 0xF
ecc1_low = cmd1[0:4].uint ^ cmd1[4:8].uint
ecc1.append(Bits(uint=ecc1_high, length=4)) # 4 high ecc bits
ecc1.append(Bits(uint=ecc1_low, length=4)) # 4 low ecc bits
ecc1.append('0x0') # 1 zero padding bit
packet_words.append(ecc1)
# calculate the second ecc word
ecc2 = BitArray()
ecc2_high = (cmd2[0:4].uint ^ (cmd2[0:4].uint << 1) ^
(cmd2[4:8].uint << 1)) & 0xF
ecc2_low = cmd2[0:4].uint ^ cmd2[4:8].uint ^ 0x7
ecc2.append(Bits(uint=ecc2_high, length=4)) # 4 high ecc bits
ecc2.append(Bits(uint=ecc2_low, length=4)) # 4 low ecc bits
ecc2.append('0x0') # 1 zero padding bit
packet_words.append(ecc2)
# convert the packet array to a bit string for encoding
packet_string = ''
for word in packet_words:
packet_string += 'S' # sync symbol
packet_string += '1' # start guard bit
packet_string += word[0:9].bin # data
parity = word.count('0x1') % 2 # calculate parity on all 9 bits
packet_string += Bits(uint=parity, length=1).bin # parity bit
packet_string += '1' # end guard bit 1
packet_string += 'Z' * 9 # zero padding at the end, required for burst separation
logging.debug('packet string:', packet_string)
logging.debug('packet string length:', len(packet_string))
for p in packet_string.split('S'):
if len(p) == 0:
continue
print('S{} {} {} {}'.format(p[0:1], p[1:5], p[5:9], p[9:12]))
# encode the packet in extended thomas manchester codes with sync and zero codes
manchester_codes = {'S': '11', '0': '01', '1': '10', 'Z': '00'}
packet_array = [manchester_codes[b] for b in packet_string]
packet = BitArray()
for b in packet_array:
packet.append(Bits(bin=b))
# return the result
logging.debug('manchester encoded packet:', packet.bin)
logging.debug('length:', len(packet.bin))
return packet
def make_exon_alignment(cursor, ensembl_db_name, human_exon_id, human_exon_known, mitochondrial,
min_similarity, flank_length):
sequence_pep = {}
sequence_dna = {}
shortest_l = -1 # Uninitialized leading padding length
shortest_r = -1 # Uninitialized trailing padding length
pep_aln_length = 0
dna_aln_length = 0
# find all other exons that map to the human exon
maps = get_maps(cursor, ensembl_db_name, human_exon_id, human_exon_known)
maps = filter (lambda m: not m.exon_id_2 is None, maps)
maps_sw = filter (lambda m: m.source=='sw_sharp' or m.source=='usearch', maps)
for map in maps:
if map.similarity < min_similarity: continue
# get the raw (unaligned) sequence for the exon that maps onto human
exon_seqs = get_exon_seqs(cursor, map.exon_id_2, map.exon_known_2, ensembl_db_name[map.species_2])
if (not exon_seqs):
print " exon_seqs for" , map.source
exit(1)
continue
[pepseq, pepseq_transl_start,
pepseq_transl_end, left_flank, right_flank, dna_seq] = exon_seqs[1:]
if len(pepseq)<3: continue
pepseq_noX = pepseq.replace ('X','')
if len(pepseq_noX)<3: continue
# check
dnaseq = Seq (dna_seq[pepseq_transl_start:pepseq_transl_end], generic_dna)
if (mitochondrial):
pepseq2 = dnaseq.translate(table="Vertebrate Mitochondrial").tostring()
else:
pepseq2 = dnaseq.translate().tostring()
if (not pepseq == pepseq2):
continue
# inflate the compressed sequence
if not map.bitmap:
continue
bs = Bits(bytes=map.bitmap)
if (not bs.count(1) == len(pepseq)): continue # check bitmap has correct number of 1s
usi = iter(pepseq)
#reconst_pepseq = "".join(('-' if c=='0' else next(usi) for c in bs.bin))
reconst_pepseq = ''
for c in bs.bin:
if c == '0': reconst_pepseq += '-'
else: reconst_pepseq += next(usi)
# come up with a unique name for this sequence
species = map.species_2
sequence_name = species + "_" + str(map.exon_id_2)+"_"+str(map.exon_known_2)
if reconst_pepseq:
sequence_pep[sequence_name] = reconst_pepseq
pep_aln_length = len(reconst_pepseq)
reconst_ntseq = expand_pepseq (reconst_pepseq, exon_seqs[1:], flank_length)
if reconst_ntseq:
sequence_dna[sequence_name] = reconst_ntseq
dna_aln_length = len(reconst_ntseq)
# strip common gaps
sequence_stripped_pep = strip_gaps (sequence_pep)
if not sequence_stripped_pep:
c=inspect.currentframe()
print " in %s:%d" % ( c.f_code.co_filename, c.f_lineno)
exit(1)
# strip common gaps
sequence_stripped_dna = strip_gaps (sequence_dna)
if not sequence_stripped_dna:
c=inspect.currentframe()
print " in %s:%d" % ( c.f_code.co_filename, c.f_lineno)
exit(1)
return [sequence_stripped_pep, sequence_stripped_dna]
def testFindAll(self):
a = Bits('0b0010011')
b = list(a.findall([1]))
self.assertEqual(b, [2, 5, 6])
def test_toilet(self):
name = 'Ftr_Toilet'
sys_actor = Actor('EventFlowSystemActor')
sys_actor.register_action(
Action(
('EventFlowSystemActor', ''),
'EventFlowActionWaitFrame',
[Param('WaitFrame', IntType)],
))
sys_actor.actions['EventFlowActionWaitFrame'].mark_used()
player_actor = Actor('Player')
player_actor.register_action(
Action(
('Player', ''),
'EventFlowActionOpenMessageWindow',
[
Param('MessageID', StrType),
Param('IsCloseMessageWindow', BoolType)
],
))
player_actor.register_action(
Action(
('Player', ''),
'EventFlowActionPlayerClearFoodPowerup',
[],
))
player_actor.actions['EventFlowActionOpenMessageWindow'].mark_used()
player_actor.actions[
'EventFlowActionPlayerClearFoodPowerup'].mark_used()
nodes: List[Node] = [
ActionNode(
'Event0',
player_actor.actions['EventFlowActionOpenMessageWindow'], {
'MessageID': TypedValue(StrType, 'TalkFtr/FTR_Toilet:001'),
'IsCloseMessageWindow': TypedValue(BoolType, False),
}),
ActionNode(
'Event2',
player_actor.actions['EventFlowActionPlayerClearFoodPowerup'],
{}),
ActionNode('Root', sys_actor.actions['EventFlowActionWaitFrame'], {
'WaitFrame': TypedValue(IntType, 30),
}),
ActionNode('Event4', sys_actor.actions['EventFlowActionWaitFrame'],
{
'WaitFrame': TypedValue(IntType, 33),
}),
RootNode('Root', []),
]
nodes[1].add_out_edge(nodes[3])
nodes[2].add_out_edge(nodes[1])
nodes[3].add_out_edge(nodes[0])
nodes[4].add_out_edge(nodes[2])
with open('tests/bfevfl/Ftr_Toilet.bfevfl', 'rb') as f:
expected = f.read()
file = File('Ftr_Toilet', [sys_actor, player_actor], nodes)
self.assertEqual(file.prepare_bitstream(), Bits(expected))
import os
import sys
from bitstring import Bits
sys.path.append(os.curdir)
from brangetree.util import iter_zipped_blocks, natural_sort
if len(sys.argv) < 2:
print("Expected one or more filenames")
raise SystemExit
paths = sys.argv[1:]
natural_sort(paths)
for filename in paths:
if not os.path.isfile(filename):
print("Not found:", filename)
continue
fsize = os.path.getsize(filename)
size = 0
filled = 0
for block in iter_zipped_blocks(filename):
size += len(block) * 8
filled += Bits(block).count(1)
print(filename, fsize, size, filled, round(filled / size * 100))
import warnings
from typing import Tuple, Set, Optional, List
from bitstring import Bits
from stegano.textanalyser import DEFAULT_ANALYSIS_FILE
from stegano.textanalyser import DEFAULT_SAMPLE_FILE
from stegano.textanalyser import TextAnalyser
Frequency = int
Symbol = Tuple[str, Frequency]
StringDefinitions = Set[Symbol]
DEFAULT_TREE_FILE = "..\\sample\\tree_article.json"
zero_bit = Bits(bin="0")
one_bit = Bits(bin="1")
class HuffmanTree:
def __init__(self,
left=None,
right=None,
value: Symbol = None,
path_code: Bits = None):
self.left = left
self.right = right
self.value = value
self.path_code = path_code
def __eq__(self, other):
def encode_bits_as_strings(tree: HuffmanTree,
bits: Bits,
string_prefix: str = "") -> Tuple[Bits, str]:
"""
Given a bit stream and a Huffman tree, return the appropriate
string of
symbols.
The output will match the statistical distribution of the
sample it was made
with as much as possible, although limited by the necessity of an
unambiguous HuffmanTree structure.
If the Huffman tree does not have path bits to match the input
exactly, it
will append 0s until the function can complete.
:param tree: a Huffman tree with path bits allocated
:param bits: the input bits
:param string_prefix: the so-far accumulated string. Leave
empty when
calling manually
:return: a Tuple of the remaining bits and the accumulated
string made up
of symbols in the Huffman tree
"""
if bits is None or bits.__eq__(Bits()):
return Bits(), string_prefix
if tree.left is not None and tree.right is not None:
# This tree has subtrees
left_tree = tree.left[1]
right_tree = tree.right[1]
if left_tree.path_code is None or right_tree.path_code is \
None:
raise HuffmanError(
"When encoding bits as strings, a node was missing "
"a path code")
else:
if bits.startswith(left_tree.path_code):
remaining_bits, accumulated_string = \
encode_bits_as_strings(
left_tree, bits, string_prefix)
elif bits.startswith(right_tree.path_code):
remaining_bits, accumulated_string = \
encode_bits_as_strings(
right_tree, bits, string_prefix)
else:
# Binary sequence does not match a leaf value. Must
# pad with 0s
padded_bits = bits.__add__(zero_bit)
return padded_bits, string_prefix
if tree.path_code is None:
# This tree is a root node
if bits is None:
# We are out of bits, so we can return the
# final string
return remaining_bits, accumulated_string
else: # Continue recursively processing the
# remaining bits
return encode_bits_as_strings(tree, remaining_bits,
accumulated_string)
else:
return remaining_bits, accumulated_string
elif tree.left is None and tree.right is None: # This tree is
# a leaf node
if tree.path_code is None:
raise HuffmanError("When encoding bits as strings, a leaf node was"
" missing a path code")
else:
if bits.startswith(tree.path_code):
accumulated_string = string_prefix + tree.value[0]
if bits.__eq__(tree.path_code):
remaining_bits = None
else:
remaining_bits = bits[tree.path_code.length:]
return remaining_bits, accumulated_string
else:
warnings.warn("When encoding bits as strings, some unencodable"
" bits were left over")
return bits, string_prefix
else:
raise HuffmanError(
"The given Huffman tree contained a node with exactly 1 "
"child tree")
def _mutate(self):
new_val = BitArray(self._default_value).copy()
start, end = self._start_end()
new_val.invert(range(start, end))
self.set_current_value(Bits(new_val))
def evaluate(self, s: Bits) -> Bits:
random.seed(a=s.uint) # sets the seed to the given seed
return Bits(uint=random.getrandbits(2 * n), length=2 * n)
def create(cls, value, masklen, bitlen, offset):
field = Bits.__new__(cls, uint=value, length=masklen)
field.__offset = offset
field.__bitlen = bitlen
return field
def main():
no_threads = 1
special = None
if len(sys.argv) > 1 and len(sys.argv)<3:
print "usage: %s <set name> <number of threads> " % sys.argv[0]
exit(1)
elif len(sys.argv)==3:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
# find db ids adn common names for each species db
[all_species, ensembl_db_name] = get_species (cursor)
species = 'homo_sapiens'
switch_to_db (cursor, ensembl_db_name[species])
if special:
print "using", special, "set"
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
else:
print "using all protein coding genes"
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
gene_list = get_gene_ids (cursor, biotype='protein_coding', is_known=1)
incomplete = 0
genes_checked = 0
#for gene_id in gene_list:
#for gene_id in [743609]:
for sampling_count in range(1000):
gene_id = choice(gene_list)
genes_checked += 1
with_map = 0
tot = 0
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
print gene2stable(cursor, gene_id), get_description (cursor, gene_id)
# find all exons we are tracking in the database
human_exons = gene2exon_list(cursor, gene_id)
human_exons.sort(key=lambda exon: exon.start_in_gene)
has_a_map = False
for human_exon in human_exons:
if (not human_exon.is_canonical or not human_exon.is_coding): continue
if verbose:
print
print "\t human", human_exon.exon_id, human_exon.is_known
print "\t ", get_exon_pepseq(cursor, human_exon, ensembl_db_name['homo_sapiens'])
print "\t checking maps ..."
maps = get_maps(cursor, ensembl_db_name, human_exon.exon_id, human_exon.is_known)
tot += 1
if maps:
has_a_map = True
with_map += 1
#print "ok"
else:
print"no maps for exon", human_exon.exon_id
continue
if verbose:
for map in maps:
species = map.species_2
exon = map2exon(cursor, ensembl_db_name, map)
unaligned_sequence = get_exon_pepseq(cursor, exon, ensembl_db_name[species])
if ( map.similarity):
print "\t", species, map.source, map.exon_id_2, map.exon_known_2
print "\tmaps to ", map.exon_id_1, map.exon_known_1
print "\tsim", map.similarity,
print "\tsource", map.source
print "\t", unaligned_sequence
if not map.bitmap:
print "\t bitmap not assigned"
else:
bs = Bits(bytes=map.bitmap)
reconst_pepseq = ''
if (not bs.count(1) == len(unaligned_sequence)):
print "\talnd seq mismatch"
else:
usi = iter(unaligned_sequence)
for c in bs.bin:
if c == '0': reconst_pepseq += '-'
else: reconst_pepseq += next(usi)
print "\tbinary : ", bs.bin
print "\talnd seq: ", reconst_pepseq
print
if not tot== with_map:
print "#### gene id: %d total exons: %d with map: %d ( = %d%%) " % \
(gene_id, tot, with_map, int(float(with_map)/tot*100) )
incomplete += 1
print "genes checked: %d, incomplete: %d" % (genes_checked, incomplete)
cursor.close()
db.close()
print tot, with_map
def go_to_while():
global UDP_IP_ADDRESS, UDP_PORT_NO, strt, clo, file_path
if (strt == 1):
try:
serverSock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
serverSock.bind((UDP_IP_ADDRESS, UDP_PORT_NO))
except:
print('The requested address is not valid in its context')
print(str(UDP_IP_ADDRESS) + ' or ' + str(UDP_PORT_NO) + ' is not valid')
print('Please try again.....')
master.destroy()
return
one_t=0
csv_data=[]
while True:
if (clo == 0):
break
data_m, addr = serverSock.recvfrom(UDP_PORT_NO) #port no configured in webpage
for i in range(len(data_m)):
re = data_m[i]
arr.append(re)
header=(arr[0:3])
print((header[0:3]))
csv_data.append(header[0])
csv_data.append(header[1])
csv_data.append(header[2])
checksum=extract_val(arr,3,2)
header_dict['checksum']=checksum
print('checksum:',checksum)
csv_data.append(checksum)
msg_len=extract_val(arr,5,2)
print("messege length:",msg_len)
csv_data.append(msg_len)
week_no=extract_val(arr,7,2)
print("week no:",week_no)
csv_data.append(week_no)
towc=extract_val(arr,9,4)
print("towc:",towc)
csv_data.append(towc)
year=extract_val(arr,13,2)
print("year:",year)
csv_data.append(year)
month=extract_val(arr,15,1)
print("month:",month)
csv_data.append(month)
day=extract_val(arr,16,1)
print("day:",day)
csv_data.append(day)
hour=extract_val(arr,17,1)
print("hour:",hour)
csv_data.append(hour)
minn=extract_val(arr,18,1)
print("minn:",minn)
csv_data.append(minn)
sec=extract_val(arr,19,1)
print("sec:",sec)
csv_data.append(sec)
mode_of_sys=extract_val(arr,20,1)
print("mode_of_sys:",mode_of_sys)
csv_data.append(mode_of_sys)
if((arr[21]&0x07)==0):
print("Time reference:internal GNSS rx")
elif((arr[21]&0x07)==1):
print("Time reference:External GNSS rx")
elif((arr[21]&0x07)==2):
print("Time reference:NTP server")
elif((arr[21]&0x07)==3):
print("Time reference:manual")
elif((arr[21]&0x07)==4):
print("Time reference:TWSTFT master")
time_ref=(arr[21]&0x07)
csv_data.append(time_ref)
osc_lock=(arr[21]>>3 & 0x01)
if(osc_lock==0):
print("osc_lock:not locked")
elif(osc_lock==1):
print("osc_lock:locked")
csv_data.append(osc_lock)
clk_src=(arr[21]>>4 & 0x01)
if(clk_src==0):
print("clk_src:internal")
elif(osc_lock==1):
print("clk_src:external")
csv_data.append(clk_src)
Time_init_status=(arr[21]>>5 & 0x01)
if(Time_init_status==0):
print("Time_init_status:not initialized")
elif(Time_init_status==1):
print("Time_init_status:initialized")
csv_data.append(Time_init_status)
sync_status=(arr[21]>>6 & 0x03)
if(sync_status==0):
print("sync_status:sync")
elif(sync_status==1):
print("sync_status:no sync")
elif(sync_status==2):
print("sync_status:holdover")
csv_data.append(sync_status)
station_pos_mode=(arr[22] & 0x01)
if(station_pos_mode==0):
print("station_pos_mode:Manual")
elif(station_pos_mode==1):
print("station_pos_mode:External GNSS RX")
csv_data.append(station_pos_mode)
optical_port_output=(arr[22]>>1 & 0x03)
if(optical_port_output==0):
print("optical_port_output:1PPS")
elif(optical_port_output==1):
print("optical_port_output:10 MHz")
elif(optical_port_output==2):
print("optical_port_output:TOD(Time Of Day)")
csv_data.append(optical_port_output)
TX_signal_pow=(arr[22]>>3 & 0x01)
if(TX_signal_pow==0):
print("TX_signal_pow:OFF")
elif(optical_port_output==1):
print("TX_signal_pow:ON")
csv_data.append(TX_signal_pow)
Local_station_ID=extract_val(arr,25,1)
print("Local_station_ID:",Local_station_ID)
csv_data.append(Local_station_ID)
LS_latitude= extract_float(arr,26,4,1)
print("LS_latitude:",LS_latitude)
csv_data.append(LS_latitude)
LS_longitude= extract_float(arr,30,4,1)
print("LS_longitude:",LS_longitude)
csv_data.append(LS_longitude)
LS_altitude= extract_float(arr,34,4,1)
print("LS_altitude:",LS_altitude)
csv_data.append(LS_altitude)
SA_latitude= extract_float(arr,38,4,1)
print("SA_latitude:",SA_latitude)
csv_data.append(SA_latitude)
SA_longitude= extract_float(arr,42,4,1)
print("SA_longitude:",SA_longitude)
csv_data.append(SA_longitude)
SA_altitude= extract_float(arr,46,4,1)
print("SA_altitude:",SA_altitude)
csv_data.append(SA_altitude)
Tx_frequency=extract_float(arr,50,4,1)
print("Tx_frequency:",(Tx_frequency))
csv_data.append(Tx_frequency)
########################################################################
Rx_frequency=extract_float(arr,54,4,1)
print("Rx_frequency:",(Rx_frequency))
csv_data.append(Rx_frequency)
TX_power=extract_val(arr,58,4) #signed
binary = bin(TX_power)
bits = Bits(bin=binary)
TX_power = bits.int
print("TX_power:",(TX_power))
csv_data.append(TX_power)
Time_offset=extract_float(arr,62,8,2)
print("Time_offset:",Time_offset)
csv_data.append(Time_offset)
Freq_offset=extract_float(arr,70,8,2)
print("Freq_offset:",Freq_offset)
csv_data.append(Freq_offset)
Osc_control_voltage=extract_val(arr,78,4)
print("Osc_control_voltage:",Osc_control_voltage)
csv_data.append(Osc_control_voltage)
TSPO=extract_val(arr,82,4)
print("TSPO:",TSPO)
csv_data.append(TSPO)
NMEA_baud_rate=extract_val(arr,86,4)
print("NMEA_baud_rate:",NMEA_baud_rate)
csv_data.append(NMEA_baud_rate)
RS422_1PPS_delay=extract_val(arr,90,2)
print("RS422_1PPS_delay:",RS422_1PPS_delay)
csv_data.append(RS422_1PPS_delay)
RS422_10MHz_delay=extract_val(arr,92,2)
print("RS422_10MHz_delay:",RS422_10MHz_delay)
csv_data.append(RS422_10MHz_delay)
Offset_wrt_master=extract_val(arr,94,4)
binary = bin(Offset_wrt_master)
bits = Bits(bin=binary)
Offset_wrt_master = bits.int
print("Offset_wrt_master:",(Offset_wrt_master))
csv_data.append(Offset_wrt_master)
Fault_id=extract_val(arr,98,4)
print("Fault_id:",Fault_id)
csv_data.append(Fault_id)
# TX_power=extract_val(arr,54,4) #signed
# binary = bin(TX_power)
# bits = Bits(bin=binary)
# TX_power = bits.int
# print("TX_power:",(TX_power))
# csv_data.append(TX_power)
# Time_offset=extract_float(arr,58,8,2)
# print("Time_offset:",Time_offset)
# csv_data.append(Time_offset)
# Freq_offset=extract_float(arr,66,8,2)
# print("Freq_offset:",Freq_offset)
# csv_data.append(Freq_offset)
# Osc_control_voltage=extract_val(arr,74,4)
# print("Osc_control_voltage:",Osc_control_voltage)
# csv_data.append(Osc_control_voltage)
# TSPO=extract_val(arr,78,4)
# print("TSPO:",TSPO)
# csv_data.append(TSPO)
# NMEA_baud_rate=extract_val(arr,82,4)
# print("NMEA_baud_rate:",NMEA_baud_rate)
# csv_data.append(NMEA_baud_rate)
# RS422_1PPS_delay=extract_val(arr,86,2)
# print("RS422_1PPS_delay:",RS422_1PPS_delay)
# csv_data.append(RS422_1PPS_delay)
# RS422_10MHz_delay=extract_val(arr,88,2)
# print("RS422_10MHz_delay:",RS422_10MHz_delay)
# csv_data.append(RS422_10MHz_delay)
# Offset_wrt_master=extract_val(arr,90,4)
# binary = bin(Offset_wrt_master)
# bits = Bits(bin=binary)
# Offset_wrt_master = bits.int
# print("Offset_wrt_master:",(Offset_wrt_master))
# csv_data.append(Offset_wrt_master)
# Fault_id=extract_val(arr,94,4)
# print("Fault_id:",Fault_id)
# csv_data.append(Fault_id)
#
####################################channel data 1#####################################
##channel 1 data
PRN_channel1=extract_val(arr,126,1)
print("PRN_channel1:",PRN_channel1)
csv_data.append(PRN_channel1)
Channel_Track_Status=extract_val(arr,127,1)
if(Channel_Track_Status==0):
print("Channel_Track_Status:IDLE")
elif(Channel_Track_Status==1):
print("Channel_Track_Status:Acquisition")
elif(Channel_Track_Status==2):
print("Channel_Track_Status:FLL")
elif(Channel_Track_Status==3):
print("Channel_Track_Status:PLL")
elif(Channel_Track_Status==4):
print("Channel_Track_Status:Reacquisition")
csv_data.append(Channel_Track_Status)
Doppler=extract_float(arr,128,4,1)
print("Doppler:",Doppler)
csv_data.append(Doppler)
Lock_Count= extract_val(arr,132,4)
print("Lock_Count:",Lock_Count)
csv_data.append(Lock_Count)
C_N0=extract_float(arr,136,4,1)
print("C_N0:",(C_N0))
csv_data.append(C_N0)
Decryption_status=extract_val(arr,140,1)
print("Decryption_status:",Decryption_status)
csv_data.append(Decryption_status)
Authentication_status=extract_val(arr,141,1)
print("Authentication_status:",Authentication_status)
csv_data.append(Authentication_status)
LS_time_offset=extract_float(arr,142,8,2) #it was One_way_offset before
print("One_way_offset:",LS_time_offset)
csv_data.append(LS_time_offset)
RS_time_offset=extract_float(arr,150,8,2)
print("RS_time_offset:",RS_time_offset)
csv_data.append(RS_time_offset)
time_offset=extract_float(arr,158,8,2)
print("time_offset:",time_offset)
csv_data.append(time_offset)
Freq_offset=extract_float(arr,166,8,2)
print("Freq_offset:",Freq_offset)
csv_data.append(Freq_offset)
RS_tx_power=extract_float(arr,174,4,1)
print("RS_tx_power:",RS_tx_power)
csv_data.append(RS_tx_power)
RS_C_N0=extract_float(arr,178,4,1)
print("RS_C_N0:",RS_C_N0)
csv_data.append(RS_C_N0)
Year1=extract_val(arr,182,2)
Month1=extract_val(arr,184,1)
Day1=extract_val(arr,185,1)
Hour1=extract_val(arr,186,1)
Min1=extract_val(arr,187,1)
Sec1=extract_val(arr,188,1)
print("Last_sync_time:%s.%s.%s.%s/%s/%s"%(Hour1,Min1,Sec1,Day1,Month1,Year1))
csv_data.append(Year1)
csv_data.append(Month1)
csv_data.append(Day1)
csv_data.append(Hour1)
csv_data.append(Min1)
csv_data.append(Sec1)
RS_latitude1=extract_float(arr,189,4,1)
print("RS_latitude1:",RS_latitude1)
csv_data.append(RS_latitude1)
RS_longitude1=extract_float(arr,193,4,1)
print("RS_longitude1:",RS_longitude1)
csv_data.append(RS_longitude1)
RS_altitude1=extract_float(arr,197,4,1)
print("RS_altitude1:",RS_altitude1)
csv_data.append(RS_altitude1)
####################################channel data 1#####################################
# ##channel 1 data
# PRN_channel1=extract_val(arr,122,1)
# print("PRN_channel1:",PRN_channel1)
# csv_data.append(PRN_channel1)
# Channel_Track_Status=extract_val(arr,123,1)
# if(Channel_Track_Status==0):
# print("Channel_Track_Status:IDLE")
# elif(Channel_Track_Status==1):
# print("Channel_Track_Status:Acquisition")
# elif(Channel_Track_Status==2):
# print("Channel_Track_Status:FLL")
# elif(Channel_Track_Status==3):
# print("Channel_Track_Status:PLL")
# elif(Channel_Track_Status==4):
# print("Channel_Track_Status:Reacquisition")
# csv_data.append(Channel_Track_Status)
# Doppler=extract_float(arr,124,4,1)
# print("Doppler:",Doppler)
# csv_data.append(Doppler)
# Lock_Count= extract_val(arr,128,4)
# print("Lock_Count:",Lock_Count)
# csv_data.append(Lock_Count)
# C_N0=extract_float(arr,132,4,1)
# print("C_N0:",(C_N0))
# csv_data.append(C_N0)
# Decryption_status=extract_val(arr,136,1)
# print("Decryption_status:",Decryption_status)
# csv_data.append(Decryption_status)
# Authentication_status=extract_val(arr,137,1)
# print("Authentication_status:",Authentication_status)
# csv_data.append(Authentication_status)
# One_way_offset=extract_float(arr,138,8,2)
# print("One_way_offset:",One_way_offset)
# csv_data.append(One_way_offset)
# RS_time_offset=extract_float(arr,146,8,2)
# print("RS_time_offset:",RS_time_offset)
# csv_data.append(RS_time_offset)
# Freq_offset=extract_float(arr,154,8,2)
# print("Freq_offset:",Freq_offset)
# csv_data.append(Freq_offset)
# RS_tx_power=extract_float(arr,162,4,1)
# print("RS_tx_power:",RS_tx_power)
# csv_data.append(RS_tx_power)
# RS_C_N0=extract_float(arr,166,4,1)
# print("RS_C_N0:",RS_C_N0)
# csv_data.append(RS_C_N0)
# Year1=extract_val(arr,170,2)
# Month1=extract_val(arr,172,1)
# Day1=extract_val(arr,173,1)
# Hour1=extract_val(arr,174,1)
# Min1=extract_val(arr,175,1)
# Sec1=extract_val(arr,176,1)
# print("Last_sync_time:%s.%s.%s.%s/%s/%s"%(Hour1,Min1,Sec1,Day1,Month1,Year1))
# csv_data.append(Year1)
# csv_data.append(Month1)
# csv_data.append(Day1)
# csv_data.append(Hour1)
# csv_data.append(Min1)
# csv_data.append(Sec1)
# RS_latitude1=extract_float(arr,177,4,1)
# print("RS_latitude1:",RS_latitude1)
# csv_data.append(RS_latitude1)
# RS_longitude1=extract_float(arr,181,4,1)
# print("RS_longitude1:",RS_longitude1)
# csv_data.append(RS_longitude1)
# RS_altitude1=extract_float(arr,185,4,1)
# print("RS_altitude1:",RS_altitude1)
# csv_data.append(RS_altitude1)
###############################channel 2 data######################################
PRN_channel2=extract_val(arr,201,1)
print("PRN_channel2:",PRN_channel2)
csv_data.append(PRN_channel2)
Channel_Track_Status2=extract_val(arr,202,1)
if(Channel_Track_Status2==0):
print("Channel_Track_Status:IDLE")
elif(Channel_Track_Status2==1):
print("Channel_Track_Status:Acquisition")
elif(Channel_Track_Status2==2):
print("Channel_Track_Status:FLL")
elif(Channel_Track_Status2==3):
print("Channel_Track_Status:PLL")
elif(Channel_Track_Status2==4):
print("Channel_Track_Status:Reacquisition")
csv_data.append(Channel_Track_Status2)
Doppler2=extract_float(arr,203,4,1)
print("Doppler2:",Doppler2)
csv_data.append(Doppler2)
Lock_Count2= extract_val(arr,207,4)
print("Lock_Count2:",Lock_Count2)
csv_data.append(Lock_Count2)
C_N02=extract_float(arr,211,4,1)
print("C_N02:",C_N02)
csv_data.append(C_N02)
Decryption_status2=extract_val(arr,215,1)
print("Decryption_status2:",Decryption_status2)
csv_data.append(Decryption_status2)
Authentication_status2=extract_val(arr,216,1)
print("Authentication_status2:",Authentication_status2)
csv_data.append(Authentication_status2)
LS_time_offset2=extract_float(arr,217,8,2)
print("LS_time_offset2:",LS_time_offset2)
csv_data.append(LS_time_offset2)
RS_time_offset2=extract_float(arr,225,8,2)
print("RS_time_offset2:",RS_time_offset2)
csv_data.append(RS_time_offset2)
time_offset2=extract_float(arr,233,8,2)
print("time_offset2:",time_offset2)
csv_data.append(time_offset2)
Freq_offset2=extract_float(arr,241,8,2)
print("Freq_offset2:",Freq_offset2)
csv_data.append(Freq_offset2)
RS_tx_power2=extract_float(arr,249,4,1)
print("RS_tx_power2:",RS_tx_power2)
csv_data.append(RS_tx_power2)
RS_C_N02=extract_float(arr,253,4,1)
print("RS_C_N02:",RS_C_N02)
csv_data.append(RS_C_N02)
Year2=extract_val(arr,257,2)
Month2=extract_val(arr,259,1)
Day2=extract_val(arr,260,1)
Hour2=extract_val(arr,261,1)
Min2=extract_val(arr,262,1)
Sec2=extract_val(arr,263,1)
print("Last_sync_time:%s.%s.%s.%s/%s/%s"%(Hour2,Min2,Sec2,Day2,Month2,Year2))
csv_data.append(Year2)
csv_data.append(Month2)
csv_data.append(Day2)
csv_data.append(Hour2)
csv_data.append(Min2)
csv_data.append(Sec2)
RS_latitude2=extract_float(arr,264,4,1)
print("RS_latitude2:",RS_latitude2)
csv_data.append(RS_latitude2)
RS_longitude2=extract_float(arr,268,4,1)
print("RS_longitude2:",RS_longitude2)
csv_data.append(RS_longitude2)
RS_altitude2=extract_float(arr,272,4,1)
print("RS_altitude2:",RS_altitude2)
csv_data.append(RS_altitude2)
print("\n")
# PRN_channel2=extract_val(arr,189,1)
# print("PRN_channel2:",PRN_channel2)
# csv_data.append(PRN_channel2)
# Channel_Track_Status2=extract_val(arr,190,1)
# if(Channel_Track_Status2==0):
# print("Channel_Track_Status:IDLE")
# elif(Channel_Track_Status2==1):
# print("Channel_Track_Status:Acquisition")
# elif(Channel_Track_Status2==2):
# print("Channel_Track_Status:FLL")
# elif(Channel_Track_Status2==3):
# print("Channel_Track_Status:PLL")
# elif(Channel_Track_Status2==4):
# print("Channel_Track_Status:Reacquisition")
# csv_data.append(Channel_Track_Status2)
# Doppler2=extract_float(arr,191,4,1)
# print("Doppler:",Doppler2)
# csv_data.append(Doppler2)
# Lock_Count2= extract_val(arr,195,4)
# print("Lock_Count:",Lock_Count2)
# csv_data.append(Lock_Count2)
# C_N02=extract_float(arr,199,4,1)
# print("C_N0:",C_N02)
# csv_data.append(C_N02)
# Decryption_status2=extract_val(arr,203,1)
# print("Decryption_status:",Decryption_status2)
# csv_data.append(Decryption_status2)
# Authentication_status2=extract_val(arr,204,1)
# print("Authentication_status:",Authentication_status2)
# csv_data.append(Authentication_status2)
#
# One_way_offset2=extract_float(arr,205,8,2)
# print("One_way_offset:",One_way_offset2)
# csv_data.append(One_way_offset2)
#
# RS_time_offset2=extract_float(arr,213,8,2)
# print("RS_time_offset:",RS_time_offset2)
# csv_data.append(RS_time_offset2)
# Freq_offset2=extract_float(arr,221,8,2)
# print("Freq_offset:",Freq_offset2)
# csv_data.append(Freq_offset2)
# RS_tx_power2=extract_float(arr,229,4,1)
# print("RS_tx_power:",RS_tx_power2)
# csv_data.append(RS_tx_power2)
# RS_C_N02=extract_float(arr,233,4,1)
# print("RS_C_N0:",RS_C_N02)
# csv_data.append(RS_C_N02)
# Year2=extract_val(arr,237,2)
# Month2=extract_val(arr,239,1)
# Day2=extract_val(arr,240,1)
# Hour2=extract_val(arr,241,1)
# Min2=extract_val(arr,242,1)
# Sec2=extract_val(arr,243,1)
# print("Last_sync_time:%s.%s.%s.%s/%s/%s"%(Hour2,Min2,Sec2,Day2,Month2,Year2))
# csv_data.append(Year2)
# csv_data.append(Month2)
# csv_data.append(Day2)
# csv_data.append(Hour2)
# csv_data.append(Min2)
# csv_data.append(Sec2)
#
# RS_latitude2=extract_float(arr,244,4,1)
# print("RS_latitude2:",RS_latitude2)
# csv_data.append(RS_latitude2)
# RS_longitude2=extract_float(arr,248,4,1)
# print("RS_longitude2:",RS_longitude2)
# csv_data.append(RS_longitude2)
# RS_altitude2=extract_float(arr,252,4,1)
# print("RS_altitude2:",RS_altitude2)
# csv_data.append(RS_altitude2)
# print("\n")
###############################channel 2 data######################################
time_sec = time.time()
result = time.localtime(time_sec)
hhh = result.tm_hour
mmm = result.tm_min
sss = result.tm_sec
final_time = hhh*60*60 + mmm*60 + sss
#################################CSV File handling############################################
# file_name = file_path + 'TWSTFT_' + str(final_time) + '_' + str(UDP_PORT_NO) + '.csv'
if(one_t==0):
file_name = file_path + 'TWSTFT_log_' + str(final_time) + '_' + str(UDP_PORT_NO) + '.csv'
with open(file_name, 'w+',newline='') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(row)
writer.writerow(csv_data)
one_t=1
else:
with open(file_name, 'a+',newline='') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csv_data)
#############################################################################
csv_data.clear()
arr.clear()
else:
pass
def multiple_exon_alnmt(gene_list, db_info):
print "process pid: %d, length of gene list: %d" % ( get_process_id(), len(gene_list))
[local_db, ensembl_db_name] = db_info
db = connect_to_mysql()
cfg = ConfigurationReader()
acg = AlignmentCommandGenerator()
cursor = db.cursor()
# find db ids adn common names for each species db
[all_species, ensembl_db_name] = get_species (cursor)
species = 'homo_sapiens'
switch_to_db (cursor, ensembl_db_name[species])
gene_ids = get_gene_ids (cursor, biotype='protein_coding', is_known=1)
# for each human gene
gene_ct = 0
tot = 0
ok = 0
no_maps = 0
no_pepseq = 0
no_orthologues = 0
min_similarity = cfg.get_value('min_accptbl_exon_sim')
#gene_list.reverse()
for gene_id in gene_list:
start = time()
gene_ct += 1
if not gene_ct%10: print gene_ct, "genes out of", len(gene_list)
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
print gene_ct, len(gene_ids), gene_id, gene2stable(cursor, gene_id), get_description (cursor, gene_id)
human_exons = filter (lambda e: e.is_known==1 and e.is_coding and e.covering_exon<0, gene2exon_list(cursor, gene_id))
human_exons.sort(key=lambda exon: exon.start_in_gene)
##################################################################
for human_exon in human_exons:
tot += 1
# find all orthologous exons the human exon maps to
maps = get_maps(cursor, ensembl_db_name, human_exon.exon_id, human_exon.is_known)
if verbose:
print "\texon no.", tot, " id", human_exon.exon_id,
if not maps:
print " no maps"
print human_exon
print
if not maps:
no_maps += 1
continue
# human sequence to fasta:
seqname = "{0}:{1}:{2}".format('homo_sapiens', human_exon.exon_id, human_exon.is_known)
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
[exon_seq_id, pepseq, pepseq_transl_start, pepseq_transl_end,
left_flank, right_flank, dna_seq] = get_exon_seqs (cursor, human_exon.exon_id, human_exon.is_known)
if (not pepseq):
if verbose and human_exon.is_coding and human_exon.covering_exon <0: # this should be a master exon
print "no pep seq for", human_exon.exon_id, "coding ", human_exon.is_coding,
print "canonical: ", human_exon.is_canonical
print "length of dna ", len(dna_seq)
no_pepseq += 1
continue
# collect seq from all maps, and output them in fasta format
hassw = False
headers = []
sequences = {}
exons_per_species = {}
for map in maps:
switch_to_db (cursor, ensembl_db_name[map.species_2])
if map.similarity < min_similarity: continue
exon = map2exon(cursor, ensembl_db_name, map)
pepseq = get_exon_pepseq (cursor,exon)
if (not pepseq):
continue
if map.source == 'sw_sharp':
exon_known_code = 2
hassw = True
elif map.source == 'usearch':
exon_known_code = 3
hassw = True
else:
exon_known_code = map.exon_known_2
seqname = "{0}:{1}:{2}".format(map.species_2, map.exon_id_2, exon_known_code)
headers.append(seqname)
sequences[seqname] = pepseq
# for split exon concatenation (see below)
if not map.species_2 in exons_per_species.keys():
exons_per_species[map.species_2] = []
exons_per_species[map.species_2].append ([ map.exon_id_2, exon_known_code]);
if (len(headers) <=1 ):
if verbose: print "single species in the alignment"
no_orthologues += 1
continue
# concatenate exons from the same gene - the alignment program might go wrong otherwise
concatenated = concatenate_exons (cursor, ensembl_db_name, sequences, exons_per_species)
fasta_fnm = "{0}/{1}.fa".format( cfg.dir_path['scratch'], human_exon.exon_id)
output_fasta (fasta_fnm, sequences.keys(), sequences)
# align
afa_fnm = "{0}/{1}.afa".format( cfg.dir_path['scratch'], human_exon.exon_id)
mafftcmd = acg.generate_mafft_command (fasta_fnm, afa_fnm)
ret = commands.getoutput(mafftcmd)
if (verbose): print 'almt to', afa_fnm
# read in the alignment
inf = erropen(afa_fnm, "r")
aligned_seqs = {}
for record in SeqIO.parse(inf, "fasta"):
aligned_seqs[record.id] = str(record.seq)
inf.close()
# split back the concatenated exons
if concatenated: split_concatenated_exons (aligned_seqs, concatenated)
human_seq_seen = False
for seq_name, sequence in aligned_seqs.iteritems():
# if this is one of the concatenated seqs, split them back to two
### store the alignment as bitstring
# Generate the bitmap
bs = Bits(bin='0b' + re.sub("[^0]","1", sequence.replace('-','0')))
# The returned value of tobytes() will be padded at the end
# with between zero and seven 0 bits to make it byte aligned.
# I will end up with something that looks like extra alignment gaps, that I'll have to return
msa_bitmap = bs.tobytes()
# Retrieve information on the cognate
cognate_species, cognate_exon_id, cognate_exon_known = seq_name.split(':')
if cognate_exon_known == '2':
source = 'sw_sharp'
elif cognate_exon_known == '3':
source = 'usearch'
else:
source = 'ensembl'
if (cognate_species == 'homo_sapiens'):
human_seq_seen = True
cognate_genome_db_id = species2genome_db_id(cursor, cognate_species) # moves the cursor
switch_to_db(cursor, ensembl_db_name['homo_sapiens']) # so move it back to h**o sapiens
# Write the bitmap to the database
#if (cognate_species == 'homo_sapiens'):
if verbose: # and (source=='sw_sharp' or source=='usearch'):
print "storing"
print human_exon.exon_id, human_exon.is_known
print cognate_species, cognate_genome_db_id, cognate_exon_id, cognate_exon_known, source
print sequence
if not msa_bitmap:
print "no msa_bitmap"
continue
store_or_update(cursor, "exon_map", {"cognate_genome_db_id":cognate_genome_db_id,
"cognate_exon_id":cognate_exon_id ,"cognate_exon_known" :cognate_exon_known,
"source": source, "exon_id" :human_exon.exon_id, "exon_known":human_exon.is_known},
{"msa_bitstring":MySQLdb.escape_string(msa_bitmap)})
ok += 1
commands.getoutput("rm "+afa_fnm+" "+fasta_fnm)
if verbose: print " time: %8.3f\n" % (time()-start);
print "tot: ", tot, "ok: ", ok
print "no maps ", no_pepseq
print "no pepseq ", no_pepseq
print "no orthologues ", no_orthologues
print
def gprMax_to_dzt(filename, rx, rxcomponent, centerFreq, distTx_Rx,
trace_step):
import h5py as h5
import os
import sys
import struct
import bitstruct
import datetime
from bitstring import Bits
from scipy import signal
# ------------------------------- Information specified by the user ---------------------------------------
# Specify gprMax file path name
file_path_name = filename
# Specify center frequency (MHz)
center_freq = centerFreq
# Specify Tx-Rx distance
distance = distTx_Rx
# Trace step
trace_step = trace_step
# Choose E-field component
comp = rxcomponent
# ---------------------------------------------------------------------------------------------------------
# Read gprMax data
bscan, _, _ = gprMax_Bscan(filename + '.out', rx, rxcomponent)
data = np.array(bscan)
# Read time step
#file = h5.File(filename[0:-4]+'1.out', 'r')
file = h5.File(filename + '1.out', 'r')
time_step = file.attrs['dt']
file.close()
data = (data * 32767) / np.max(np.abs(data))
data[data > 32767] = 32767
data[data < -32768] = -32768
data = np.round(data)
# Number of samples and traces
[noSamples, noTraces] = np.shape(data)
# Convert time step to ns
time_step = time_step * 10**9
# Sampling frequency (MHz)
sampling_freq = (1 / time_step) * 10**3
# Time window (ns)
time_window = time_step * noSamples
# DZT file name
fileName = filename
# Resample data to 1024 samples
data = signal.resample(data, 1024)
time_step = time_window / np.shape(data)[0]
sampling_freq = (1 / time_step) * 10**3
# ------------------------------------------------ DZT file header -----------------------------------------------------
tag = 255 # 0x00ff if header, 0xfnff for old file Header
dataOffset = 1024 # Constant 1024
noSamples = np.shape(data)[0] # Number of samples
bits = 16 # Bits per data word (8 or 16)
binaryOffset = 32768 # Binary offset (8 bit -> 128, 16 bit -> 32768)
sps = 0 # Scans per second
spm = 1 / trace_step # Scans per metre
mpm = 0 # Meters per mark
position = 0 # Position (ns)
time_window = time_window # Time window (ns)
noScans = 0 # Number of passes for 2D files
dateTime = datetime.datetime.now() # Current datetime
# Date and time created
createdSec = dateTime.second
if createdSec > 29: createdSec = 29
createdMin = dateTime.minute
createdHour = dateTime.hour
createdDay = dateTime.day
createdMonth = dateTime.month
createdYear = dateTime.year - 1980
# Date and time modified
modifiedSec = dateTime.second
if modifiedSec > 29: modifiedSec = 29
modifiedMin = dateTime.minute
modifiedHour = dateTime.hour
modifiedDay = dateTime.day
modifiedMonth = dateTime.month
modifiedYear = dateTime.year - 1980
offsetRG = 0 # Offset to range gain function
sizeRG = 0 # Size of range gain function
offsetText = 0 # Offset to text
sizeText = 0 # Size of text
offsetPH = 0 # Offset to processing history
sizePH = 0 # Size of processing history
noChannels = 1 # Number of channels
epsr = 5 # Average dielectric constant
topPosition = 0 # Top position (m)
vel = (299792458 / np.sqrt(epsr)) * 10**-9
range0 = vel * (time_window / 2) # Range (meters)
xStart = 0 # X start coordinate
xFinish = noTraces * trace_step - trace_step # X finish coordinate
servoLevel = 0 # Gain servo level
reserved = 0 # Reserved
antConfig = 0 # Antenna Configuration
setupConfig = 0 # Setup Configuration
spp = 0 # Scans per pass
noLine = 0 # Line number
yStart = 0 # Y start coordinate
yFinish = 0 # Y finish coordinate
lineOrder = 0
dataType = 2 # Data type
antennaName = 'antName'
if len(antennaName) > 14:
antennaName = antennaName[0:14]
elif len(antennaName) < 14:
antennaName = antennaName.ljust(14)
channelMask = 0 # Channel mask
fName = fileName # File name
if len(fName) > 12:
fName = fName[0:12]
elif len(fName) < 12:
fName = fName.ljust(12)
checkSum = 0 # Check sum for header
# -------------------------------------------------------------------------------------------------------------------
# ----------------------------------------- Convert to bytes and write to file --------------------------------------
# Open file to write
with open(fileName + '.dzt', 'wb') as fid:
# Write header
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, tag)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, dataOffset)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, noSamples)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, bits)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('s16<', dataStruct, 0, binaryOffset)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, sps)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, spm)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, mpm)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, position)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, time_window)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, noScans)
fid.write(dataStruct)
sec = Bits(uint=createdSec, length=5)
min = Bits(uint=createdMin, length=6)
hour = Bits(uint=createdHour, length=5)
day = Bits(uint=createdDay, length=5)
month = Bits(uint=createdMonth, length=4)
year = Bits(uint=createdYear, length=7)
b = Bits().join([year, month, day, hour, min, sec])
createDate = b.tobytes()
fid.write(bitstruct.pack('>r32<', createDate))
sec = Bits(uint=modifiedSec, length=5)
min = Bits(uint=modifiedMin, length=6)
hour = Bits(uint=modifiedHour, length=5)
day = Bits(uint=modifiedDay, length=5)
month = Bits(uint=modifiedMonth, length=4)
year = Bits(uint=modifiedYear, length=7)
b = Bits().join([year, month, day, hour, min, sec])
modifiedDate = b.tobytes()
fid.write(bitstruct.pack('>r32<', modifiedDate))
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, offsetRG)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, sizeRG)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, offsetText)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, sizeText)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, offsetPH)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, sizePH)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, noChannels)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, epsr)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, topPosition)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, range0)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, xStart)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, xFinish)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, servoLevel)
fid.write(dataStruct)
dataStruct = bytearray(3)
bitstruct.pack_into('r24<', dataStruct, 0, reserved)
fid.write(dataStruct)
dataStruct = bytearray(1)
bitstruct.pack_into('u8<', dataStruct, 0, antConfig)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, setupConfig)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, spp)
fid.write(dataStruct)
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, noLine)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, yStart)
fid.write(dataStruct)
dataStruct = bytearray(4)
bitstruct.pack_into('f32<', dataStruct, 0, yFinish)
fid.write(dataStruct)
dataStruct = bytearray(1)
bitstruct.pack_into('u8<', dataStruct, 0, lineOrder)
fid.write(dataStruct)
dataStruct = bytearray(1)
bitstruct.pack_into('r8<', dataStruct, 0, dataType)
fid.write(dataStruct)
fid.write(bitstruct.pack('t14<', antennaName))
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, channelMask)
fid.write(dataStruct)
fid.write(bitstruct.pack('t12<', fName))
dataStruct = bytearray(2)
bitstruct.pack_into('u16<', dataStruct, 0, checkSum)
fid.write(dataStruct)
# Move to 1024 to write data
fid.seek(dataOffset)
data = data + binaryOffset
data = np.array(data, dtype='<H')
fid.write(data.T.astype('<H').tobytes())
# Close file
fid.close()
print('Dzt file has been written!')
def testFind(self):
a = Bits('0xabcd')
r = a.find('0xbc')
self.assertEqual(r[0], 4)
r = a.find('0x23462346246', bytealigned=True)
self.assertFalse(r)
def _val_to_bits(conv, val, length):
if val is -1:
return Bits(int=-1, length=length)
return Bits(bytes=conv(val), length=length)
'''
from __future__ import print_function
__author__ = 'Ryan Helinski, Sandia National Laboratories'
from bitstring import Bits
from bientropy.pybientropy import bin_deriv_k
from bientropy import bien, tbien
if __name__ == '__main__':
# When this file is run as a script, the following tests are executed
from bientropy.testvectors import BIENTROPY_2BITS, BIENTROPY_4BITS, \
ORDERING_4BIT, BIENTROPY_8BITS, TBIENTROPY_8BITS
assert bin_deriv_k(Bits('0b01010101'), 1) == Bits('0b1111111')
assert bin_deriv_k(Bits('0b00010001'), 3) == Bits('0b11111')
assert bin_deriv_k(Bits('0b00011111'), 6) == Bits('0b01')
assert abs(bien(Bits('0b1011')) - 0.95) < 0.01
assert abs(tbien(Bits('0b1001')) - 0.54) < 0.01
for s, v in BIENTROPY_2BITS:
assert abs(bien(s) - v) < 0.01
for s, v in BIENTROPY_4BITS:
assert abs(bien(s) - v) < 0.01
for y in ORDERING_4BIT:
print(' '.join([
if operation.__eq__("encrypt"):
input_filename: str = prefix_filename(args.subfolder, args.input)
output_filename: str = prefix_filename(args.subfolder, args.output)
key: bytes = None if args.key is None else bytes(args.key,
encoding=DEFAULT_ENCODING)
if input_filename is None:
raise ValueError("Filename for input was not provided.")
if output_filename is None:
raise ValueError("Filename for output was not provided.")
if key is None:
key = DEFAULT_KEY
message_bits = read_input_file(input_filename)
try:
ciphertext_bits = Bits(bin=message_bits)
except CreationError:
raise ValueError("Provided input was not a valid bitstring.")
if ciphertext_bits.__eq__(Bits()):
raise ValueError("Provided input was empty.")
bits = Bits(bytes=Encryptor(key).encrypt_bytes(ciphertext_bits.bytes))
print("Input encrypted.")
write_output_file(output_filename, bits.bin)
print("Ciphertext written to {}".format(output_filename))
elif operation.__eq__("decrypt"):
input_filename: str = prefix_filename(args.subfolder, args.input)
output_filename: str = prefix_filename(args.subfolder, args.output)
key: bytes = None if args.key is None else bytes(args.key,
def encode(self, value):
'''
:type value: ``str``
:param value: value to encode
'''
return Bits(bytes=strToBytes(value))
from bitstring import Bits
X_LOC = 0 #beginning of bits for locations of x's
O_LOC = 81 #beginning of bits for locations of o's
PREV_MOV = 162 #beginning of bits for previous move location
TURN = 171 #bit for player to move
X_VIC = 172 #beginning of bits for x field victories
O_VIC = 181 #beginning of bits for o field victories
X_W = 190 #bit for x won
O_W = 191 #bit for o won
#full bitstring length = 192
VICTORIES = (
Bits(bin='0b111000000'), #across top
Bits(bin='0b000111000'), #across middle
Bits(bin='0b000000111'), #across bottom
Bits(bin='0b100100100'), #down left
Bits(bin='0b010010010'), #down middle
Bits(bin='0b001001001'), #down right
Bits(bin='0b100010001'), #diagonal \
Bits(bin='0b001010100'), #diagonal /
)
def possible_moves(gamestate):
moves = []
lastmove = 9
for i, b in enumerate(
gamestate[PREV_MOV:PREV_MOV +
9]): #set lastmove to the location of the previous move
if b:
def read(self):
'''Reads 32 bits of the SPI bus for processing and stores as 32-bit bitstring.'''
raw_spi = self.spi.transaction(Spibus.reading(4))
self.data = Bits(bytes=raw_spi[0], length=32)
self.checkErrors()
def identity(gamestate):
return Bits(bin=gamestate.bin)
# Requires bitstring module
# $ pip install bitstring
import socket
from time import sleep
from bitstring import Bits
UDP_ADDR = "10.0.0.9"
UDP_PORT = 5040
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
while True:
for servo_value in range(150,600):
bits = Bits('uint:16=' + str(servo_value))
print bits.bin
s.sendto(bits.tobytes(), (UDP_ADDR, UDP_PORT))
sleep(0.1)
def huffman_encode(self):
"encode given text/string with generated tree/code"
self.string = BitArray()
for a in self.text:
self.string.append(Bits(bin=self.code[a]))
return self.string
def length(self, l):
self._length = Bits(uint=self._format_length(l), length=7)
def output_hoard_riddle_rows(self):
hoard_riddle_output_file = open(self.hoard_riddle_output_file_name,
'wb')
hoard_riddle_string = ''.join(self.hoard_riddle_rows)
Bits(bin=hoard_riddle_string).tofile(hoard_riddle_output_file)
def testDouble(self):
a = array.array('d', [0.0, 1.0, 2.5])
b = Bits(a)
self.assertEqual(b.length, 192)
c, d, e = b.unpack('3*floatne:64')
self.assertEqual((c, d, e), (0.0, 1.0, 2.5))
#!/usr/bin/env python3
import requests
import re
from os import path
from bitstring import Bits
targetUrl = 'https://jupiter.challenges.picoctf.org/static/95be9526e162185c741259a75dffa0ab/whitepages.txt'
targetFilename = 'whitepages.txt'
if not path.exists(targetFilename):
with open(targetFilename, 'xb') as f:
r = requests.get(targetUrl)
f.write(r.content)
with open(targetFilename, 'r') as f:
fileContent = f.read()
uniqueChars = ''.join(sorted(set(fileContent)))
mapping = {ch: i for ch, i in zip(uniqueChars, reversed(range(2)))}
bits = []
for ch in fileContent:
bits.append(mapping[ch])
message = Bits(bits).tobytes().decode()
flag = re.search('picoCTF{.*?}', message)[0]
print(f"Flag: {flag}")
def multiple_exon_alnmt(species_list, db_info):
[local_db, ensembl_db_name] = db_info
verbose = False
db = connect_to_mysql()
cfg = ConfigurationReader()
acg = AlignmentCommandGenerator()
cursor = db.cursor()
for species in species_list:
print
print "############################"
print species
switch_to_db (cursor, ensembl_db_name[species])
gene_ids = get_gene_ids (cursor, biotype='protein_coding')
#gene_ids = get_theme_ids(cursor, cfg, 'wnt_pathway')
if not gene_ids:
print "no gene_ids"
continue
gene_ct = 0
tot = 0
ok = 0
no_maps = 0
no_pepseq = 0
no_paralogues = 0
for gene_id in gene_ids:
if verbose: start = time()
gene_ct += 1
if not gene_ct%100: print species, gene_ct, "genes out of", len(gene_ids)
if verbose:
print
print gene_id, gene2stable(cursor, gene_id), get_description (cursor, gene_id)
# get the paralogues - only the representative for the family will have this
paralogues = get_paras (cursor, gene_id)
if not paralogues:
if verbose: print "\t not a template or no paralogues"
continue
if verbose: print "paralogues: ", paralogues
# get _all_ exons
template_exons = gene2exon_list(cursor, gene_id)
if (not template_exons):
if verbose: print 'no exons for ', gene_id
continue
# find all template exons we are tracking in the database
for template_exon in template_exons:
if verbose: print template_exon.exon_id
maps = get_maps(cursor, ensembl_db_name, template_exon.exon_id,
template_exon.is_known, species=species, table='para_exon_map')
if not maps:
no_maps += 1
continue
# output to fasta:
seqname = "{0}:{1}:{2}".format('template', template_exon.exon_id, template_exon.is_known)
exon_seqs_info = get_exon_seqs (cursor, template_exon.exon_id, template_exon.is_known)
if not exon_seqs_info: continue
[exon_seq_id, pepseq, pepseq_transl_start, pepseq_transl_end,
left_flank, right_flank, dna_seq] = exon_seqs_info
if (not pepseq):
if ( template_exon.is_coding and template_exon.covering_exon <0): # this should be a master exon
print "no pep seq for", template_exon.exon_id, "coding ", template_exon.is_coding,
print "canonical: ", template_exon.is_canonical
print "length of dna ", len(dna_seq)
no_pepseq += 1
continue
tot += 1
sequences = {seqname:pepseq}
headers = [seqname]
for map in maps:
exon = map2exon(cursor, ensembl_db_name, map, paralogue=True)
pepseq = get_exon_pepseq (cursor,exon)
if (not pepseq):
continue
seqname = "{0}:{1}:{2}".format('para', map.exon_id_2, map.exon_known_2)
headers.append(seqname)
sequences[seqname] = pepseq
fasta_fnm = "{0}/{1}_{2}_{3}.fa".format( cfg.dir_path['scratch'], species, template_exon.exon_id, template_exon.is_known)
output_fasta (fasta_fnm, headers, sequences)
if (len(headers) <=1 ):
print "single species in the alignment (?)"
no_paralogues += 1
continue
# align
afa_fnm = "{0}/{1}_{2}_{3}.afa".format( cfg.dir_path['scratch'], species, template_exon.exon_id, template_exon.is_known)
mafftcmd = acg.generate_mafft_command (fasta_fnm, afa_fnm)
ret = commands.getoutput(mafftcmd)
# read in the alignment
inf = erropen(afa_fnm, "r")
if not inf:
print gene_id
continue
template_seq_seen = False
for record in SeqIO.parse(inf, "fasta"):
### store the alignment as bitstring
# Generate the bitmap
bs = Bits(bin='0b' + re.sub("[^0]","1", str(record.seq).replace('-','0')))
msa_bitmap = bs.tobytes()
# Retrieve information on the cognate
label, cognate_exon_id, cognate_exon_known = record.id.split(':')
if (label == 'template'):
template_seq_seen = True
# Write the bitmap to the database
#print "updating: ", template_exon.exon_id
store_or_update(cursor, "para_exon_map", {"cognate_exon_id" :cognate_exon_id,
"cognate_exon_known" :cognate_exon_known,
"exon_id" :template_exon.exon_id,
"exon_known" :template_exon.is_known},
{"msa_bitstring":MySQLdb.escape_string(msa_bitmap)})
inf.close()
ok += 1
commands.getoutput("rm "+afa_fnm+" "+fasta_fnm)
if verbose: print " time: %8.3f\n" % (time()-start);
outstr = species + " done \n"
outstr += "tot: %d ok: %d \n" % (tot, ok)
outstr += "no maps %d \n" % no_pepseq
outstr += "no pepseq %d \n" % no_pepseq
outstr += "no paralogues %d \n" % no_paralogues
outstr += "\n"
print outstr
params = {}
msgLen, genDegree, generator = taskParameters.split('|')
crcWidth = len(generator) - 1
msgLen = int(msgLen)
#print(str(msgLen)+" "+str(genDegree)+" " +str(generator)+" "+genString)
##########################################
######## GENERATE THE TESTVECTORS ########
##########################################
numVectors = randrange(10, 20)
testVectors = []
for i in range(0, numVectors):
msg = Bits(uint=randrange(0, 2**msgLen), length=msgLen).bin
crc = genCRC(msg, generator)
testVectors.append('("{0}","{1}")'.format(msg, crc))
for i in range(numVectors - 1):
testVectors[i] += ","
testPattern = ("\n" + 12 * " ").join(testVectors) #format and join
##########################################
## SET PARAMETERS FOR TESTBENCH TEMPLATE #
##########################################
params.update({
"CRCWIDTH": crcWidth,
"MSGLEN": msgLen,
def hamming_distance(str1, str2):
"""Calculate the hamming distance between two byte strings. """
bit_str1 = BitArray(str1)
bit_str2 = BitArray(str2)
return (Bits("0b" + bit_str2.bin) ^ Bits("0b" + bit_str1.bin)).count(True)
def encode(self, value):
'''
:param value: value to encode
'''
encoded = strToBytes(value) + b'\x00'
return Bits(bytes=encoded)
def make_exon_alignment(cursor, ensembl_db_name, human_exon_id, human_exon_known, mitochondrial,
min_similarity, flank_length, first_human_exon = True):
sequence_pep = {}
sequence_dna = {}
shortest_l = -1 # Uninitialized leading padding length
shortest_r = -1 # Uninitialized trailing padding length
pep_aln_length = 0
dna_aln_length = 0
# find all other exons that map to the human exon
maps = get_maps(cursor, ensembl_db_name, human_exon_id, human_exon_known)
maps = filter (lambda m: not m.exon_id_2 is None, maps)
maps_sw = filter (lambda m: m.source=='sw_sharp' or m.source=='usearch', maps)
for map in maps:
if map.similarity < min_similarity: continue
# get the raw (unaligned) sequence for the exon that maps onto human
exon_seqs = get_exon_seqs(cursor, map.exon_id_2, map.exon_known_2, ensembl_db_name[map.species_2])
if (not exon_seqs):
#print " exon_seqs for" , map.source
continue
[pepseq, pepseq_transl_start,
pepseq_transl_end, left_flank, right_flank, dna_seq] = exon_seqs[1:]
# rpl11 starts with an exon that translates into 2 aa's,
# rpl10A has a single methionine (or so they say) followed by a split codon
# *supposedly there is evidence at the protein level
# but will this give me tons of junk elsewhere? ...
pepseq_noX = pepseq.replace ('X','')
if len(pepseq_noX)<3:
# if this is the first exon, and if it starts with M, we'll let it off the hook
# abd then if it's human, we'll also salvage it at any price
if first_human_exon and pepseq_noX[0] == 'M' or map.species_2=='homo_sapiens':
pass
else:
continue
# check
dnaseq = Seq (dna_seq[pepseq_transl_start:pepseq_transl_end], generic_dna)
if (mitochondrial):
pepseq2 = dnaseq.translate(table="Vertebrate Mitochondrial").tostring()
else:
pepseq2 = dnaseq.translate().tostring()
if (not pepseq == pepseq2):
continue
# inflate the compressed sequence
if not map.bitmap:
continue
bs = Bits(bytes=map.bitmap)
if (not bs.count(1) == len(pepseq)): continue # check bitmap has correct number of 1s
usi = iter(pepseq)
#reconst_pepseq = "".join(('-' if c=='0' else next(usi) for c in bs.bin))
reconst_pepseq = ''
for c in bs.bin:
if c == '0': reconst_pepseq += '-'
else: reconst_pepseq += next(usi)
# come up with a unique name for this sequence
species = map.species_2
# let's also have the start in gene here - might make our lives easier later
exon2 = get_exon (cursor, map.exon_id_2, map.exon_known_2, ensembl_db_name[species])
sequence_name = species + "_" + str(map.exon_id_2)+"_"+str(map.exon_known_2)+"_"+str(exon2.start_in_gene)
if reconst_pepseq:
sequence_pep[sequence_name] = reconst_pepseq
pep_aln_length = len(reconst_pepseq)
reconst_ntseq = expand_pepseq (reconst_pepseq, exon_seqs[1:], flank_length)
if reconst_ntseq:
sequence_dna[sequence_name] = reconst_ntseq
dna_aln_length = len(reconst_ntseq)
# strip common gaps
sequence_stripped_pep = strip_gaps (sequence_pep)
if not sequence_stripped_pep:
c=inspect.currentframe()
#print " in %s:%d" % ( c.f_code.co_filename, c.f_lineno)
return ['','']
# strip common gaps
sequence_stripped_dna = strip_gaps (sequence_dna)
if not sequence_stripped_dna:
c=inspect.currentframe()
#print " in %s:%d" % ( c.f_code.co_filename, c.f_lineno)
return ['', '']
return [sequence_stripped_pep, sequence_stripped_dna]
def encode(self, value, length, signed):
return Bits(bytes=strToBytes(self._fmt % value))
def testRfind(self):
a = Bits('0b11101010010010')
b = a.rfind('0b010')
self.assertEqual(b[0], 11)
def encode(self, value):
'''
:param value: value to encode
'''
packed = pack(self.fmt, value)
return Bits(bytes=packed)
def testCut(self):
s = Bits(30)
for t in s.cut(3):
self.assertEqual(t, [0] * 3)
def bits_to_signed_int(s):
return Bits(bin=s).int
def _lzw_unpack_compressed(packed_ints): ints_count = len(packed_ints) * 8 // _LZW_NUM_SIZE; bits = Bits(bytes=packed_ints, length=ints_count * _LZW_NUM_SIZE) return [chunk.uint for chunk in bits.cut(_LZW_NUM_SIZE)]
def decode_compressed(bits, descriptors, n_subsets, operators, descriptor_overlay):
"""
:param bits: Bit stream to decode from
:param descriptors: Descriptor iterator
:param n_subsets: Number of subsets to decode
:param dict operators: Operators in effect, indexed by opcode
:param dict descriptor_overlay: Overlay descriptors affected by CHANGE_REFERENCE_VALUES operator
"""
subsets = [[] for x in range(n_subsets)]
for descriptor in descriptors:
descriptor = descriptor_overlay.get(descriptor.code, descriptor)
if isinstance(descriptor, ElementDescriptor):
op_crf = operators.get(OpCode.CHANGE_REFERENCE_VALUES, None)
if op_crf is not None:
dummy_descriptors = iter([ElementDescriptor(fxy2int("999999"), op_crf.bits(), 0, 0, "ASSOCIATED FIELD", "NUMERIC")])
_subsets = decode_compressed(bits, dummy_descriptors, n_subsets, {}, {})
raw_vals = [subset[0].raw_value for subset in _subsets]
if len(set(raw_vals)) != 1:
raise ValueError("Encountered different reference values for different subsets: %s", raw_vals)
ref_value = raw_vals[0]
top_bit_mask = (1 << op_crf.bits()-1)
if ref_value & top_bit_mask:
ref_value = -(ref_value & ~top_bit_mask)
overlay_descriptor = ElementDescriptor(descriptor.code, descriptor.length, descriptor.scale, ref_value, descriptor.significance, descriptor.unit)
descriptor_overlay[descriptor.code] = overlay_descriptor
continue
op_aaf = operators.get(OpCode.ADD_ASSOCIATED_FIELD, None)
if op_aaf is not None and descriptor.code != fxy2int("031021"):
# Don't apply to ASSOCIATED FIELD SIGNIFICANCE
# Use dummy descriptor 999999 for associated field, like Geo::BUFR and libbufr
dummy_descriptors = iter([ElementDescriptor(fxy2int("999999"), op_aaf.bits(), 0, 0, "ASSOCIATED FIELD", "NUMERIC")])
vals = decode_compressed(bits, dummy_descriptors, n_subsets, {}, {})
for i,ss in enumerate(vals):
subsets[i].extend(ss)
read_length = _calculate_read_length(descriptor, operators)
if descriptor.unit == 'CCITTIA5':
ref_value = Bits._readhex(bits, read_length, bits.pos)
else:
ref_value = Bits._readuint(bits, read_length, bits.pos)
bits.pos += read_length
n_bits = Bits._readuint(bits, 6, bits.pos)
bits.pos += 6
for i in range(n_subsets):
if descriptor.unit == 'CCITTIA5':
n_chars = n_bits
if n_chars:
raw_value = Bits._readhex(bits, n_chars*8, bits.pos)
bits.pos += n_chars*8
value = _decode_raw_value(raw_value, descriptor, operators)
else:
value = _decode_raw_value(ref_value, descriptor, operators)
else:
if n_bits:
increment = Bits._readuint(bits, n_bits, bits.pos)
bits.pos += n_bits
if increment ^ ((1 << n_bits)-1) == 0: # Missing value, all-ones
value = _decode_raw_value((1 << descriptor.length)-1, descriptor, operators)
else:
value = _decode_raw_value(ref_value + increment, descriptor, operators)
else:
value = _decode_raw_value(ref_value, descriptor, operators)
subsets[i].append(value)
elif isinstance(descriptor, ReplicationDescriptor):
aggregations = [[] for x in range(n_subsets)]
if descriptor.count:
bval = None
count = descriptor.count
else:
bval = decode_compressed(bits, itertools.islice(descriptors, 1), n_subsets, {}, {})[0][0]
count = bval.value
n_fields = descriptor.fields
field_descriptors = list(itertools.islice(descriptors, n_fields))
if bval is None or bval.descriptor.code in REPLICATION_DESCRIPTORS:
# Regular replication, X elements repeated Y or <element value> times in the file
for _ in range(count):
replication = decode_compressed(bits, iter(field_descriptors), n_subsets, operators, descriptor_overlay)
for subset_idx in range(n_subsets):
aggregations[subset_idx].append(replication[subset_idx])
elif bval.descriptor.code in REPETITION_DESCRIPTORS:
# Repeated replication, X elements present once in the file, output <element value> times
replication = decode_compressed(bits, iter(field_descriptors), n_subsets, operators, descriptor_overlay)
for _ in range(count):
for subset_idx in range(n_subsets):
aggregations[subset_idx].append(replication[subset_idx])
else:
raise ValueError("Unexpected delayed replication element %s" %bval)
for subset_idx in range(n_subsets):
subsets[subset_idx].append(aggregations[subset_idx])
elif isinstance(descriptor, OperatorDescriptor):
op = descriptor.operator
if op.opcode in (1,2,3,4,7):
if op.neutral():
del operators[op.opcode]
else:
op.check_conflict(operators)
operators[op.opcode] = op
else:
raise NotImplementedError("Can only decode operators 201-204 and 207 for compressed BUFR data at the moment, please file an issue on GitHub, found operator: 2%02d" %op.opcode)
elif isinstance(descriptor, SequenceDescriptor):
comp = decode_compressed(bits, iter(descriptor.descriptors), n_subsets, operators, descriptor_overlay)
for i,subset in enumerate(comp):
subsets[i].extend(subset)
else:
raise NotImplementedError("Unknown descriptor type: %s" % descriptor)
return subsets
def encode(self, value):
encoded = self._func(strToBytes(value))
return Bits(bytes=encoded)
def decode(bits, descriptors, operators, descriptor_overlay):
"""
:param bits: Bit stream to decode from
:param descriptors: Descriptor iterator
:param dict operators: Operators in effect, indexed by opcode
:param dict descriptor_overlay: Overlay descriptors affected by CHANGE_REFERENCE_VALUES operator
"""
values = []
for descriptor in descriptors:
descriptor = descriptor_overlay.get(descriptor.code, descriptor)
if isinstance(descriptor, ElementDescriptor):
op_crf = operators.get(OpCode.CHANGE_REFERENCE_VALUES, None)
if op_crf is not None:
ref_value = Bits._readuint(bits, op_crf.bits(), bits.pos)
bits.pos += op_crf.bits()
top_bit_mask = (1 << op_crf.bits()-1)
if ref_value & top_bit_mask:
ref_value = -(ref_value & ~top_bit_mask)
overlay_descriptor = ElementDescriptor(descriptor.code, descriptor.length, descriptor.scale, ref_value, descriptor.significance, descriptor.unit)
descriptor_overlay[descriptor.code] = overlay_descriptor
continue
op_aaf = operators.get(OpCode.ADD_ASSOCIATED_FIELD, None)
if op_aaf is not None and descriptor.code != fxy2int("031021"):
# Don't apply to ASSOCIATED FIELD SIGNIFICANCE
associated_value = Bits._readuint(bits, op_aaf.bits(), bits.pos)
bits.pos += op_aaf.bits()
# Use dummy descriptor 999999 for associated field, like Geo::BUFR and libbufr
dummy_descriptor = ElementDescriptor(fxy2int("999999"), op_aaf.bits(), 0, 0, "ASSOCIATED FIELD", "NUMERIC")
values.append(BufrValue(associated_value, associated_value, dummy_descriptor))
read_length = _calculate_read_length(descriptor, operators)
if descriptor.unit == 'CCITTIA5':
raw_value = Bits._readhex(bits, read_length, bits.pos)
else:
raw_value = Bits._readuint(bits, read_length, bits.pos)
bits.pos += read_length
values.append(_decode_raw_value(raw_value, descriptor, operators))
elif isinstance(descriptor, ReplicationDescriptor):
aggregation = []
if descriptor.count:
bval = None
count = descriptor.count
else:
bval = decode(bits, itertools.islice(descriptors, 1), {}, {})[0]
count = bval.value
n_fields = descriptor.fields
field_descriptors = list(itertools.islice(descriptors, n_fields))
if bval is None or bval.descriptor.code in REPLICATION_DESCRIPTORS:
# Regular replication, X elements repeated Y or <element value> times in the file
for _ in range(count):
aggregation.append(decode(bits, iter(field_descriptors), operators, descriptor_overlay))
elif bval.descriptor.code in REPETITION_DESCRIPTORS:
# Repeated replication, X elements present once in the file, output <element value> times
repeated_values = decode(bits, iter(field_descriptors), operators, descriptor_overlay)
for _ in range(count):
aggregation.append(repeated_values)
else:
raise ValueError("Unexpected delayed replication element %s" %bval)
values.append(aggregation)
elif isinstance(descriptor, OperatorDescriptor):
op = descriptor.operator
if op.immediate:
if op.opcode == OpCode.SIGNIFY_CHARACTER:
raw_value = Bits._readhex(bits, op.bits(), bits.pos)
bits.pos += op.bits()
char_descriptor = ElementDescriptor(fxy2int(op.code), op.bits(), 0, 0, "CHARACTER INFORMATION", "CCITTIA5")
value = _decode_raw_value(raw_value, char_descriptor, {})
values.append(value)
elif op.opcode == OpCode.SIGNIFY_LOCAL_DESCRIPTOR:
base_descriptor = itertools.islice(descriptors, 1)[0]
mod_descriptor = ElementDescriptor(base_descriptor.code, op.bits(), base_descriptor.scale, base_descriptor.ref, base_descriptor.significance, base_descriptor.unit)
values.add(decode(bits, descriptors, {}, {})[0].value)
else:
raise NotImplementedError("Unknown immediate operator: %s" % str(descriptor))
else:
if op.neutral():
del operators[op.opcode]
else:
op.check_conflict(operators)
operators[op.opcode] = op
elif isinstance(descriptor, SequenceDescriptor):
seq = decode(bits, iter(descriptor.descriptors), operators, descriptor_overlay)
values.extend(seq)
else:
raise NotImplementedError("Unknown descriptor type: %s" % descriptor)
return values