7117302237

Committed 06 Dec 2023 04:23PM UTC coverage: 75.482% (+1.8%) from 73.729%

Build # 7117302237

Build Type

push

github

Committed by

cokelaer

Commit Message

Update version

Run Details

13709 of 18162 relevant lines covered (75.48%)

2.26 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

35.42

/sequana/scripts/main/fasta.py

#  This file is part of Sequana software
#
#  Copyright (c) 2016-2020 - Sequana Development Team
#
#  Distributed under the terms of the 3-clause BSD license.
#  The full license is in the LICENSE file, distributed with this software.
#
#  website: https://github.com/sequana/sequana
#  documentation: http://sequana.readthedocs.io
#
##############################################################################
import glob
import os
import subprocess
import sys

import colorlog
import rich_click as click

from sequana.fasta import FastA
from sequana.scripts.utils import CONTEXT_SETTINGS

logger = colorlog.getLogger(__name__)


@click.command(context_settings=CONTEXT_SETTINGS)
@click.argument("filename", type=click.STRING, nargs=-1)
@click.option(
    "-o",
    "--output",
    help="filename where to save results. to be used with --head, --tail",
)
@click.option("--count-sequences", is_flag=True)
@click.option("--merge", is_flag=True, help="merge all compressed input fasta files into a single file")
@click.option("--save-contig-name", help="save sequence corresponding to this contig name")
@click.option("--explode", is_flag=True, help="Create a fasta file for each sequence found in the original files")
def fasta(**kwargs):
    """Set of useful utilities for FastA manipulation."""
    filenames = kwargs["filename"]
    # users may provide a wildcards such as "A*gz" or list of files.
    if len(filenames) == 1:
        # if existing files or glob, a glob would give the same answer.
        filenames = glob.glob(filenames[0])
    for filename in filenames:
        os.path.exists(filename)

    # could be simplified calling count_reads only once
    if kwargs["count_sequences"]:
        for filename in filenames:
            f = FastA(filename)
            Nreads = len(f)
            print(f"Number of reads in {filename}: {Nreads}")
    elif kwargs["merge"]:
        # merge all input files (assuming gz extension)
        extensions = [filename.split(".")[-1] for filename in filenames]
        if set(extensions) != set(["gz"]):
            raise ValueError("Your input FastA files must be zipped")
        output_filename = kwargs["output"]
        if output_filename is None:
            logger.error("You must use --output filename.gz")
            sys.exit(1)
        if output_filename.endswith(".gz") is False:
            raise ValueError("your output file must end in .gz")
        p1 = subprocess.Popen(["zcat"] + list(filenames), stdout=subprocess.PIPE)
        fout = open(output_filename, "wb")
        subprocess.run(["pigz"], stdin=p1.stdout, stdout=fout)
    elif kwargs["explode"]:
        for filename in filenames:
            f = FastA(filename)
            f.explode()
    elif kwargs["save_contig_name"]:
        f = FastA(filename)
        outname = kwargs["output"]
        f.save_ctg_to_fasta(kwargs["save_contig_name"], outname)

1	# This file is part of Sequana software
2	#
3	# Copyright (c) 2016-2020 - Sequana Development Team
4	#
5	# Distributed under the terms of the 3-clause BSD license.
6	# The full license is in the LICENSE file, distributed with this software.
7	#
8	# website: https://github.com/sequana/sequana
9	# documentation: http://sequana.readthedocs.io
10	#
11	##############################################################################
12	import glob	3✔
13	import os	3✔
14	import subprocess	3✔
15	import sys	3✔
16
17	import colorlog	3✔
18	import rich_click as click	3✔
19
20	from sequana.fasta import FastA	3✔
21	from sequana.scripts.utils import CONTEXT_SETTINGS	3✔
22
23	logger = colorlog.getLogger(__name__)	3✔
24
25
26	@click.command(context_settings=CONTEXT_SETTINGS)	3✔
27	@click.argument("filename", type=click.STRING, nargs=-1)	3✔
28	@click.option(	3✔
29	"-o",
30	"--output",
31	help="filename where to save results. to be used with --head, --tail",
32	)
33	@click.option("--count-sequences", is_flag=True)	3✔
34	@click.option("--merge", is_flag=True, help="merge all compressed input fasta files into a single file")	3✔
35	@click.option("--save-contig-name", help="save sequence corresponding to this contig name")	3✔
36	@click.option("--explode", is_flag=True, help="Create a fasta file for each sequence found in the original files")	3✔
37	def fasta(**kwargs):	3✔
38	"""Set of useful utilities for FastA manipulation."""
39	filenames = kwargs["filename"]	×
40	# users may provide a wildcards such as "A*gz" or list of files.
41	if len(filenames) == 1:	×
42	# if existing files or glob, a glob would give the same answer.
43	filenames = glob.glob(filenames[0])	×
44	for filename in filenames:	×
45	os.path.exists(filename)	×
46
47	# could be simplified calling count_reads only once
48	if kwargs["count_sequences"]:	×
49	for filename in filenames:	×
50	f = FastA(filename)	×
51	Nreads = len(f)	×
52	print(f"Number of reads in {filename}: {Nreads}")	×
53	elif kwargs["merge"]:	×
54	# merge all input files (assuming gz extension)
55	extensions = [filename.split(".")[-1] for filename in filenames]	×
56	if set(extensions) != set(["gz"]):	×
57	raise ValueError("Your input FastA files must be zipped")	×
58	output_filename = kwargs["output"]	×
59	if output_filename is None:	×
60	logger.error("You must use --output filename.gz")	×
61	sys.exit(1)	×
62	if output_filename.endswith(".gz") is False:	×
63	raise ValueError("your output file must end in .gz")	×
64	p1 = subprocess.Popen(["zcat"] + list(filenames), stdout=subprocess.PIPE)	×
65	fout = open(output_filename, "wb")	×
66	subprocess.run(["pigz"], stdin=p1.stdout, stdout=fout)	×
67	elif kwargs["explode"]:	×
68	for filename in filenames:	×
69	f = FastA(filename)	×
70	f.explode()	×
71	elif kwargs["save_contig_name"]:	×
72	f = FastA(filename)	×
73	outname = kwargs["output"]	×
74	f.save_ctg_to_fasta(kwargs["save_contig_name"], outname)	×

cokelaer / sequana / 7117302237

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous