Source code for samsifter.tools.filter_taxon_list
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Filter SAM files for a list of taxon IDs.
.. moduleauthor:: Florian Aldehoff <faldehoff@student.uni-tuebingen.de>
"""
import sys
if not (sys.version_info[0] >= 3):
print("Error, I need python 3.x or newer")
exit(1)
import argparse
import fileinput
import csv
from os.path import basename, splitext
""" custom libraries """
from samsifter.models.filter import FilterItem
from samsifter.models.parameter import FilterSwitch, FilterFilepath
from samsifter.util.arg_sanitation import check_sam, check_csv
from samsifter.util.filters import pattern_filter
""" global variables """
TEXT = "Filter taxa by list of taxon IDs"
DESC = ("filtering references by a list of NCBI taxon IDs given in a "
"tab-separated CSV file")
[docs]def item():
"""Create item representing this tool in list and tree views.
Returns
-------
FilterItem
Item for use in item-based list and tree views.
"""
item = FilterItem(text=TEXT, desc=DESC)
item.set_command(splitext(basename(__file__))[0])
item.add_parameter(FilterFilepath(
text="taxon list file",
desc="tab-separated CSV file with NCBI taxon IDs in first column",
cli_name="--list",
default="taxa.csv",
extensions=['csv'],
required=True
))
item.add_parameter(FilterSwitch(
text="filter direction",
desc="Keep or discard entries passing the filter criteria?",
cli_name="--discard",
default=0,
options=["discard", "keep"]
))
return item
[docs]def main():
"""Executable to filter SAM files for a list of taxon IDs.
See ``--help`` for details on expected arguments. Takes input from
either STDIN, or optional, or positional arguments. Logs messages to
STDERR and writes processed SAM files to STDOUT.
"""
# parse arguments
parser = argparse.ArgumentParser(description=DESC)
parser.add_argument('-i', '--input',
type=check_sam,
help="specify SAM file to be analysed (default: "
"STDIN)",
required=False)
parser.add_argument('-l', '--list',
type=check_csv,
help="tab-separated CSV file with accession numbers "
"in first column",
required=True)
parser.add_argument('--discard',
type=int,
help="keep or discard entries passing the filter "
"criteria?",
required=False,
default=0)
(args, remainArgs) = parser.parse_known_args()
# generate pattern list from CSV file
patterns = []
with open(args.list, newline='') as csvfile:
reader = csv.reader(csvfile, delimiter='\t')
for row in reader:
patterns.append("tax|" + row[0] + "|")
# open SAM file from either command line argument or STDIN
if args.input:
handle = open(args.input, 'r')
else:
handle = fileinput.input(remainArgs)
pattern_filter(patterns, handle, discard=(args.discard == 0))
handle.close()
exit()
if __name__ == "__main__":
main()