[med-svn] [Git][med-team/catfishq][upstream] New upstream version 1.1.5+ds
Tony Mancill (@tmancill)
gitlab at salsa.debian.org
Tue Oct 26 04:04:03 BST 2021
Tony Mancill pushed to branch upstream at Debian Med / catfishq
Commits:
6e580da3 by tony mancill at 2021-10-25T19:37:11-07:00
New upstream version 1.1.5+ds
- - - - -
5 changed files:
- PKG-INFO
- catfishq.egg-info/PKG-INFO
- catfishq/__init__.py
- catfishq/cat_fastq.py
- setup.py
Changes:
=====================================
PKG-INFO
=====================================
@@ -1,6 +1,6 @@
Metadata-Version: 1.0
Name: catfishq
-Version: 1.1.3
+Version: 1.1.5
Summary: Cat FASTQ files
Home-page: UNKNOWN
Author: philres
=====================================
catfishq.egg-info/PKG-INFO
=====================================
@@ -1,6 +1,6 @@
Metadata-Version: 1.0
Name: catfishq
-Version: 1.1.3
+Version: 1.1.5
Summary: Cat FASTQ files
Home-page: UNKNOWN
Author: philres
=====================================
catfishq/__init__.py
=====================================
@@ -0,0 +1 @@
+__version__ = "1.1.5"
=====================================
catfishq/cat_fastq.py
=====================================
@@ -10,6 +10,9 @@ import sys
from pathlib import Path
from datetime import datetime, timedelta
+from . import __version__
+
+
LOOKUP = []
@@ -80,15 +83,19 @@ def parse_args(argv):
"-q", "--min-qscore", dest="MIN_QSCORE", type=int, default=0, help="Minimum q-score"
)
parser.add_argument(
- "--max-sequencing-time", dest="MAX_SEQ_TIME", type=int, default=0, help="Only output reads that where sequenced up to the given time (minutes)."
+ "--max-sequencing-time", dest="MAX_SEQ_TIME", type=int, default=None, help="Only output reads that where sequenced at or up to the given time (minutes)."
)
parser.add_argument(
- "--min-sequencing-time", dest="MIN_SEQ_TIME", type=int, default=0, help="Only output reads that where sequenced after the given time (minutes)."
+ "--min-sequencing-time", dest="MIN_SEQ_TIME", type=int, default=None, help="Only output reads that where sequenced at or after the given time (minutes)."
)
parser.add_argument(
"--start-time", dest="START_TIME", type=str, default=None, help="Starttime of the run as guppy time stamp (only required with --sequencing-time). If 'min' is given as argument the minimal time is detected automatically."
)
+ parser.add_argument(
+ "--filter-id", dest="FILTER_ID", type=str, default=None, help="Only print reads with IDs present in file."
+ )
+
parser.add_argument(
"--print-start-time", dest="PRINT_START_TIME", action="store_true", help="Print the minimal start_time of all fastq files"
)
@@ -122,6 +129,15 @@ def parse_args(argv):
help="FASTQ files or folders containing FASTQ files",
)
+ parser.add_argument(
+ "-v",
+ '--version',
+ action='version',
+ version='catfish ' + __version__,
+ help="Print version",
+ )
+
+
args = parser.parse_args(argv)
return args
@@ -159,7 +175,7 @@ def find_file_in_folder(
def check_seq_time(comment, max_start_time,min_start_time):
- #This tests if the start time of the respective read is between
+ #This tests if the start time of the respective read is between
#max_sequencing_time and min_sequencing_time
#If one of the times is not given the condition is automatically considered true
if (max_start_time == None and min_start_time == None):
@@ -168,15 +184,15 @@ def check_seq_time(comment, max_start_time,min_start_time):
matchObj = re.search( r'start_time=([^ ]+)', comment, re.M|re.I)
start_str = matchObj.group(1)
start = datetime.strptime(start_str,'%Y-%m-%dT%H:%M:%SZ')
-
+
bool_min=0
bool_max=0
-
+
if (max_start_time == None or start<=max_start_time):
bool_max=1
if (min_start_time == None or start>=min_start_time):
bool_min=1
-
+
if (bool_min == 1 and bool_max == 1):
return True
else:
@@ -195,8 +211,8 @@ def compare_start_time(comment,min_start_time):
return min_start_time
else:
return start_time
-
-
+
+
def parse_fastqs(filename, min_len=0, min_qscore=0, max_start_time=None, min_start_time=None):
with pysam.FastxFile(filename) as fh:
for entry in fh:
@@ -230,9 +246,9 @@ def get_file_names(path, recursive):
def get_start_time(paths,recursive=False):
"""
Only print the start time.
- This function automatically detects the minmal start_time of
+ This function automatically detects the minmal start_time of
all the given fastq files
-
+
:param paths: Input FASTQ files or folders containing FASTQ files
:return: min_start_time
@@ -249,7 +265,7 @@ def get_start_time(paths,recursive=False):
return min_start_time
-def format_fq(paths, out_filename, min_len=0, min_qscore=0, max_n=0, max_bp=0, recursive=False, dedup=False, max_seq_time=0, min_seq_time=0, start_time=0):
+def format_fq(paths, out_filename, min_len=0, min_qscore=0, max_n=0, max_bp=0, recursive=False, dedup=False, max_seq_time=0, min_seq_time=0, start_time=0, filter_read_ids_file=None):
"""
Concatenate FASTQ files
@@ -261,18 +277,33 @@ def format_fq(paths, out_filename, min_len=0, min_qscore=0, max_n=0, max_bp=0, r
max_start_time = None
min_start_time = None
+ keep_ids = None
+ if filter_read_ids_file:
+ keep_ids = set()
+ with open(filter_read_ids_file, "r") as fh:
+ for line in fh:
+ read_id = line.strip()
+ keep_ids.add(read_id)
+ logging.info("Found {} read ids.".format(len(keep_ids)))
+
+
if start_time:
if not start_time=="min":
start = datetime.strptime(start_time,'%Y-%m-%dT%H:%M:%SZ')
- max_start_time = start + timedelta(minutes=min_seq_time)
- min_start_time = start + timedelta(minutes=max_seq_time)
+
+ if(max_seq_time):
+ max_start_time = start + timedelta(minutes=max_seq_time)
+ if(min_seq_time):
+ min_start_time = start + timedelta(minutes=min_seq_time)
else:
- #This option allows to automatically use the minmal start_time of
+ #This option allows to automatically use the minmal start_time of
#all the given fastq files as input for --start-time
auto_start_time=get_start_time(paths,recursive)
- max_start_time=auto_start_time + timedelta(minutes=max_seq_time)
- min_start_time=auto_start_time + timedelta(minutes=min_seq_time)
+ if(max_seq_time):
+ max_start_time = start + timedelta(minutes=max_seq_time)
+ if(min_seq_time):
+ min_start_time = start + timedelta(minutes=min_seq_time)
read_ids = set()
n = 0
@@ -288,6 +319,9 @@ def format_fq(paths, out_filename, min_len=0, min_qscore=0, max_n=0, max_bp=0, r
if dedup and entry.name in read_ids:
continue
+ if keep_ids and entry.name not in keep_ids:
+ continue
+
fout.write(str(entry) + "\n")
if dedup:
read_ids.add(entry.name)
@@ -328,7 +362,8 @@ def main(argv=sys.argv[1:]):
dedup=args.DEDUP,
max_seq_time=args.MAX_SEQ_TIME,
min_seq_time=args.MIN_SEQ_TIME,
- start_time=args.START_TIME
+ start_time=args.START_TIME,
+ filter_read_ids_file=args.FILTER_ID
)
=====================================
setup.py
=====================================
@@ -5,9 +5,9 @@ CatfishQ
import os
from setuptools import setup, find_packages
-os.environ['GIT_SSL_NO_VERIFY'] = 'true'
+from catfishq import __version__
-__version__ = '1.1.3'
+os.environ['GIT_SSL_NO_VERIFY'] = 'true'
setup(
name='catfishq',
View it on GitLab: https://salsa.debian.org/med-team/catfishq/-/commit/6e580da315004eac7e4e6599a713d04310c3b692
--
View it on GitLab: https://salsa.debian.org/med-team/catfishq/-/commit/6e580da315004eac7e4e6599a713d04310c3b692
You're receiving this email because of your account on salsa.debian.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-commit/attachments/20211026/738e933a/attachment-0001.htm>
More information about the debian-med-commit
mailing list