def __init__(self, theme):
"""Creates a new FASTAFormatter instance"""
import os
from cats.styles.sequence import SequenceFormatter
# Load sequence formatter
self.seq_formatter = SequenceFormatter(theme)
class FASTAFormatter(object):
"""Formatter for FASTA files"""
def __init__(self, theme):
"""Creates a new FASTAFormatter instance"""
import os
from cats.styles.sequence import SequenceFormatter
# Load sequence formatter
self.seq_formatter = SequenceFormatter(theme)
def format(self, inbuffer, outbuffer=None, **kwargs):
"""Format sequence records"""
import sys
# default/bold text
RESET = '\033[0m'
BOLD = '\033[1m'
# default to STDOUT for output
if outbuffer is None:
outbuffer = sys.stdout
# Iterate through and format each sequence record
if kwargs['color']:
for line in inbuffer:
line = line.decode()
# Reset formatting
outbuffer.write(RESET)
# Print description
if line.startswith('>'):
outbuffer.write(BOLD + line)
continue
# DNA/RNA
if kwargs['seq_type'] in ['dna', 'rna', 'nucleic_acid']:
outbuffer.write(self.seq_formatter.format_nucleic_acid(
line, kwargs['stop_codons'], kwargs['cpg']
))
else:
# Protein
outbuffer.write(self.seq_formatter.format_protein(line))
else:
for line in inbuffer:
outbuffer.write(line.decode())
class FASTQFormatter(object):
"""Formatter for FASTQ files"""
def __init__(self, theme):
"""Creates a new FASTQFormatter instance"""
import os
from cats.styles.sequence import SequenceFormatter
# Load sequence formatter
self.seq_formatter = SequenceFormatter(theme)
def format(self, inbuffer, outbuffer=None, **kwargs):
"""Format sequence records"""
import sys
# default/bold text
RESET = '\033[0m'
BOLD = '\033[1m'
# default to STDOUT for output
if outbuffer is None:
outbuffer = sys.stdout
# FASTQ line types
FASTQ_ID = 0
FASTQ_SEQ = 1
FASTQ_DESC = 2
FASTQ_QUAL = 3
# Iterate through and format each sequence record
if kwargs['color']:
for i, line in enumerate(inbuffer):
# Reset formatting
outbuffer.write(RESET)
# line = line.decode('ascii')
line = line.decode()
# Print description
if i % 4 == FASTQ_ID:
outbuffer.write(BOLD + line)
elif i % 4 == FASTQ_SEQ:
outbuffer.write(self.seq_formatter.format_nucleic_acid(line,
kwargs['stop_codons'],
kwargs['cpg']))
else:
outbuffer.write(line)
else:
for line in inbuffer:
outbuffer.write(line.decode())
class SeqStringFormatter(object):
"""Formatter for sequence strings"""
def __init__(self, theme):
"""Creates a new SeqStringFormatter instance"""
import os
from cats.styles.sequence import SequenceFormatter
# Load sequence formatter
self.seq_formatter = SequenceFormatter(theme)
def format(self, inbuffer, outbuffer=None, **kwargs):
"""Format sequence records"""
import sys
# default/bold text
RESET = '\033[0m'
BOLD = '\033[1m'
# default to STDOUT for output
if outbuffer is None:
outbuffer = sys.stdout
# Iterate through and format each sequence record
if kwargs['color']:
for i, line in enumerate(inbuffer):
# Reset formatting
outbuffer.write(RESET)
# Convert from byte-string if coming from gzip
#line = line.decode('ascii')
line = line.decode()
# Print description
outbuffer.write(self.seq_formatter.format_nucleic_acid(line,
kwargs['stop_codons'],
kwargs['cpg']))
else:
for line in inbuffer:
outbuffer.write(line.decode())
class SeqRecordFormatter(object):
"""Formatter for BioPython SeqRecord objects"""
def __init__(self, theme):
"""Creates a new SeqRecordFormatter instance"""
from cats.styles.sequence import SequenceFormatter
# Load sequence formatter
self.seq_formatter = SequenceFormatter(theme)
def format(self, seqs, outbuffer=None, **kwargs):
"""Format sequence records"""
# default to STDOUT for output
if outbuffer is None:
import sys
outbuffer = sys.stdout
# for x in range(1,10):
# print "\033[03%dmTEST \033[09%dmTEST" % (x,x)
# default/bold text
RESET = '\033[0m'
BOLD = '\033[1m'
# select translation table
# see: ftp://ftp.ncbi.nlm.nih.gov/entrez/misc/data/gc.prt
# Iterate through and format each sequence record
for seq in seqs:
# Reset formatting
outbuffer.write(RESET)
# Print description
if kwargs['color']:
outbuffer.write(BOLD)
outbuffer.write(">" + seq.description + "\n")
# line width
width = kwargs['line_width']
# Protein
if kwargs['translate']:
# determine frame to use
frame = abs(kwargs['translation_frame']) - 1
dna_str = seq.seq[frame:]
if kwargs['translation_frame'] < 0:
dna_str = seq.seq.reverse_complement()[frame:]
table = kwargs['translation_table']
translated = str(dna_str.translate(table=table))
# format and append to output buffer
if kwargs['color']:
_seq = self._fill(translated, width)
outbuffer.write(self.seq_formatter.format_protein(_seq))
else:
outbuffer.write(self._fill(translated, width))
# DNA
else:
if kwargs['color']:
_seq = self._fill(str(seq.seq), width)
outbuffer.write(self.seq_formatter.format_nucleic_acid(_seq,
kwargs['stop_codons'],
kwargs['cpg']))
else:
outbuffer.write(self._fill(str(seq.seq), width))
def _fill(self, text, width=70):
"""
Faster text-wrapping for long strings
source: http://stackoverflow.com/questions/2657693/insert-a-newline-character-every-64-characters-using-python/2657733#2657733
"""
return '\n'.join(text[i:i+width] for i in range(0, len(text), width))