diff --git a/.gitignore b/.gitignore
index f080b5bb752cd4bce30b0a06fc9acfdf4b201a16..b52dddc49bdb0d116111a6e3e4867c10a02be30d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -16,7 +16,7 @@
*\.pyc
*\.pyo
*\__pycache__/
-
+craw.egg-info
#########################
# distribution packages #
#########################
@@ -41,5 +41,11 @@ htmlcov/
######################
# Singularity images #
######################
-.img
-
+*\.img
+*\.simg
+
+#####################
+# My stuff
+#####################
+Sandbox/
+data/
\ No newline at end of file
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 94f511e06219f35645811f2a861a5a13c477bb9c..a8170acc20a15b598c3f4eeb57a3592e6c70deef 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -3,15 +3,11 @@ stages:
- coverage
- release
-variables:
- CRAW_HOME: ${CI_PROJECT_DIR}
- CRAW_VERSION: ${CI_COMMIT_REF_NAME}
-
testing:
stage: test
image: registry-gitlab.pasteur.fr/bneron/craw:centos-run-dep
script:
- - python3 ${CI_PROJECT_DIR}/tests/run_tests.py -vvv
+ - python36 setup.py test
except:
- /^feat.*$/
- /^fix.*$/
@@ -20,8 +16,7 @@ coverage:
stage: coverage
image: registry-gitlab.pasteur.fr/bneron/craw:coverage
script:
- - cd ${CI_PROJECT_DIR}
- - coverage run --source=craw tests/run_tests.py --unit
+ - coverage run --source=craw tests/run_tests.py
- coverage html
- coverage report
artifacts:
diff --git a/COPYRIGHT b/COPYRIGHT
index 9e43a85aaff719c7d35475b2d931d1004d8c6ad5..12a949ec154f3f56cb75fdb89c7b58de15ae9ea5 100644
--- a/COPYRIGHT
+++ b/COPYRIGHT
@@ -1,4 +1,4 @@
Counter RNAseq Window - compute the coverage of RNAseq experiments
on a specified window on both strand and display results as images.
-Copyright © 2017 Institut Pasteur (Paris).
\ No newline at end of file
+Copyright © 2017-2019 Institut Pasteur (Paris), and CNRS.
\ No newline at end of file
diff --git a/Docker/Docker_release/Dockerfile b/Docker/Docker_release/Dockerfile
index 9b7525ff6d5f86258ab8cc9c7ab85243b4bb1d04..4b17470cd0e8bff4febfdbed29d43b7b7bfcd27b 100644
--- a/Docker/Docker_release/Dockerfile
+++ b/Docker/Docker_release/Dockerfile
@@ -15,7 +15,7 @@ RUN yum install -y texlive-collection-latexrecommended \
COPY tabulary.sty fncychap.sty capt-of.sty \
eqparbox.sty environ.sty trimspaces.sty \
- /usr/lib64/python3.4/site-packages/sphinx/texinputs/
+ /usr/lib64/python3.6/site-packages/sphinx/texinputs/
CMD ["/bin/bash"]
diff --git a/Docker/Docker_run_dep/Dockerfile b/Docker/Docker_run_dep/Dockerfile
index 0b8b7a777502fce2a63872224168ebb5b8c7a712..8f15d01e0fb2a410acaba8509e7949a69a547cc7 100644
--- a/Docker/Docker_run_dep/Dockerfile
+++ b/Docker/Docker_run_dep/Dockerfile
@@ -6,19 +6,19 @@ USER root
RUN yum clean all && \
yum install -y epel-release &&\
- yum install -y make gcc gcc-c++ python34-devel zlib-devel python34-tkinter && \
+ yum install -y make gcc gcc-c++ python36-devel zlib-devel python36-tkinter && \
yum clean all
WORKDIR /tmp
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py &&\
- python3 get-pip.py
-RUN pip3 install psutil>=4.0.0
-RUN pip3 install pysam==0.9.1.4
-RUN pip3 install numpy==1.11.2
-RUN pip3 install cython && pip3 install pandas==0.17.1
-RUN pip3 install scipy==0.16.1
-RUN pip3 install matplotlib==1.5.3
-RUN pip3 install pillow==3.4.2
+ python36 get-pip.py
+RUN pip3 install psutil>=5.6
+RUN pip3 install pysam==0.15.2
+RUN pip3 install numpy==1.16.2
+RUN pip3 install cython && pip3 install pandas==0.24.2
+RUN pip3 install scipy==1.2.1
+RUN pip3 install matplotlib==3.0.3
+RUN pip3 install pillow==5.4.1
CMD ["/bin/bash"]
diff --git a/MANIFEST.in b/MANIFEST.in
index 7551840b4dcb77eaf3d8dd309cbb87b01406e8ca..6275f31a8e455f0093d5edf68a604ff125a95238 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -3,13 +3,10 @@ include RELEASE_NOTES.md
include COPYRIGHT
include COPYING
include requirements.txt
+include requirements_dev.txt
include setup.py
-include bin/craw_coverage
-include bin/craw_htmp
-
-include craw/*.py
recursive-include tests *.py
recursive-include tests/data *
diff --git a/README.md b/README.md
index c2a3ab9dbc0356173dbe3f1e2c5e8fdaead27456..b18627d668cd592afda506f44aa2f4018175f667 100644
--- a/README.md
+++ b/README.md
@@ -13,14 +13,14 @@ Installation
Requirements
------------
-- python > 3
-- psutil >= 4.0
-- pysam >= 0.9.1.4
-- pandas >= 0.17.1
-- scipy >= 0.18.1
-- numpy >= 1.11.2
-- matplotlib >= 1.5.3
-- pillow >= 3.4.2
+- python > 3.4
+- psutil >= 5.6
+- pysam == 0.15.2
+- pandas >= 0.24
+- scipy >= 0.16.1
+- numpy >= 1.16
+- matplotlib >= 3.0
+- pillow >= 5.4
From package
@@ -28,7 +28,7 @@ From package
using pip
-`pip install craw`
+`pip install craw==1.0.2`
if you use virtualenv do not forget to configure the matplotlib backend
@@ -60,10 +60,6 @@ clone the project and install with the setup.py
pip3 install dist/craw-master-devxxxxx.tar.gz
-You can also use the package without install it.
-You have to export the **CRAW_HOME** environment variable.
-Then you can use it directly
-
### Testing my installation
@@ -71,7 +67,7 @@ The release come from with some unit and functional tests.
to test if everything work fine.
cd craw
- python3 tests/run_tests.py -vvv
+ python3 tests/run_tests.py -vv
This step is only available from the sources (a *clone* of the repository or a *tarball* release).
You **cannot** perform tests if you installed craw from pypi (*pip install craw*)
diff --git a/Singularity b/Singularity
deleted file mode 100644
index 6d7584593ad7281065afbe1f3debcccb423a5661..0000000000000000000000000000000000000000
--- a/Singularity
+++ /dev/null
@@ -1,97 +0,0 @@
-Bootstrap: debootstrap
-OSVersion: zesty
-MirrorURL: http://archive.ubuntu.com/ubuntu/
-
-
-%labels
- maintainer Bertrand Neron <bneron@pasteur.fr>
- package.name craw
- package.version 1.0.0
- package.homepage https://gitlab.pasteur.fr/bneron/craw
- package.license GPLv3
-
-%post
- ####################################
- # Installing system #
- ####################################
-
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty main restricted" > /etc/apt/sources.list
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty-updates main restricted" >> /etc/apt/sources.list
-
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty universe" >> /etc/apt/sources.list
- echo "deb-src http://archive.ubuntu.com/ubuntu/ zesty universe" >> /etc/apt/sources.list
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty-updates universe" >> /etc/apt/sources.list
- echo "deb-src http://archive.ubuntu.com/ubuntu/ zesty-updates universe" >> /etc/apt/sources.list
-
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty multiverse" >> /etc/apt/sources.list
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty-updates multiverse" >> /etc/apt/sources.list
-
- echo "deb http://archive.ubuntu.com/ubuntu/ zesty-backports main restricted universe multiverse" >> /etc/apt/sources.list
-
- echo "deb http://security.ubuntu.com/ubuntu/ zesty-security main restricted" >> /etc/apt/sources.list
- echo "deb http://security.ubuntu.com/ubuntu/ zesty-security universe" >> /etc/apt/sources.list
- echo "deb-src http://security.ubuntu.com/ubuntu/ zesty-security universe" >> /etc/apt/sources.list
- echo "deb http://security.ubuntu.com/ubuntu/ zesty-security multiverse" >> /etc/apt/sources.list
-
- apt-get update -y
- apt-get install -y --no-install-recommends wget python3 python3-tk
- apt-get install -y python3-pip
-
- #################################
- # installing craw #
- #################################
- cd /
- CRAW_VERS="1.0.0"
- #wget -O craw-${CRAW_VERS}.tar.gz https://gitlab.pasteur.fr/bneron/craw/repository/${CRAW_VERS}/archive.tar.gz
- wget -O craw-${CRAW_VERS}.tar.gz https://gitlab.pasteur.fr/bneron/craw/repository/branch_1.0/archive.tar.gz
- mkdir craw-${CRAW_VERS} && tar xzf craw-${CRAW_VERS}.tar.gz -C craw-${CRAW_VERS} --strip-components 1
- cd craw-${CRAW_VERS}
- python3 setup.py sdist
- #pip3 install dist/craw-${CRAW_VERS}.tar.gz
- pip3 install dist/craw-*.tar.gz
-
- mkdir /craw
- mv tests /craw/
-
- #################################
- # cleaning image #
- #################################
- cd /
- rm craw-${CRAW_VERS}.tar.gz
- rm -Rf craw-${CRAW_VERS}
- apt-get purge -y wget
- apt-get autoremove -y
- apt-get clean -y
-
-%test
- /usr/bin/python3 /craw/tests/run_tests.py --functional -vv
-
-%help
- This singularity image contains the "Counter RNAseq Window (CRAW) package.
- Two commands are available \"coverage\" and \"htmp\.
- To run command:
- ./craw.img [coverage|htmp] [options]... [args]... .
-
- To get help about each command ./craw.img [coverage|htmp] --help.
- The detailed documentation is accessible here: http://bneron.pages.pasteur.fr/craw/
-
-%runscript
-
-# the following syntax allow to get the command and args
-# in POSIX manner so compliant with dash which
-# is the debian/ubuntu /bin/sh shell
-
-CMD="$1"
-shift
-ARGS=${@}
-
-case ${CMD} in
- coverage )
- exec /usr/local/bin/craw_coverage ${ARGS} ;;
- htmp )
- exec /usr/local/bin/craw_htmp ${ARGS} ;;
- * )
- echo "command \"${CMD}\" is not supported. available commands: \"coverage\"|\"htmp\""
- exit 127
- ;;
-esac
diff --git a/bin/craw_coverage b/bin/craw_coverage
deleted file mode 100755
index 94d30fcb7ac485232650436e19702704de2a99d1..0000000000000000000000000000000000000000
--- a/bin/craw_coverage
+++ /dev/null
@@ -1,467 +0,0 @@
-#! /usr/bin/env python3
-
-###########################################################################
-# #
-# This file is part of Counter RNAseq Window (craw) package. #
-# #
-# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
-# see COPYRIGHT file for details. #
-# #
-# craw is free software: you can redistribute it and/or modify #
-# it under the terms of the GNU General Public License as published by #
-# the Free Software Foundation, either version 3 of the License, or #
-# (at your option) any later version. #
-# #
-# craw is distributed in the hope that it will be useful, #
-# but WITHOUT ANY WARRANTY; without even the implied warranty of #
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
-# See the GNU General Public License for more details. #
-# #
-# You should have received a copy of the GNU General Public License #
-# along with craw (see COPYING file). #
-# If not, see <http://www.gnu.org/licenses/>. #
-# #
-###########################################################################
-
-import os
-import sys
-import argparse
-import itertools
-import logging
-import pysam
-
-if 'CRAW_HOME' in os.environ and os.environ['CRAW_HOME']:
- if os.environ['CRAW_HOME'] not in sys.path:
- sys.path.insert(0, os.environ['CRAW_HOME'])
-try:
- import craw
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- sys.exit(msg)
-
-from craw.util import progress
-from craw import argparse_util
-from craw import annotation, coverage
-from craw.wig import WigParser
-
-
-def positive_int(value):
- """
- Parse value given by the parser
-
- :param value: the value given by the parser
- :type value: string
- :return: the integer corresponding to the value
- :rtype: int
- :raise: :class:`argparse.ArgumentTypeError`
- """
- try:
- value = int(value)
- except ValueError:
- raise argparse.ArgumentTypeError("must be a positive integer, got: {}".format(value))
- if value < 0:
- msg = "must be a positive integer, got: {}".format(value)
- raise argparse.ArgumentTypeError(msg)
- return value
-
-
-def quality_checker(value):
- """
- Parse value given by the parser
-
- :param value: the value given by the parser
- :type value: string
- :return: the integer >=0 and <=42 corresponding to the value
- :rtype: int
- :raise: :class:`argparse.ArgumentTypeError` if value does not represent a integer >=0 and <=42
- """
-
- try:
- value = int(value)
- except ValueError:
- raise argparse.ArgumentTypeError("must be a integer between 0 and 42, got: {}".format(value))
- if not 0 <= value <= 42:
- raise argparse.ArgumentTypeError("must be a integer between 0 and 42, got: {}".format(value))
- return value
-
-
-def get_result_header(annot_parser, cmdline_args):
- """
-
- :param annot_parser:
- :param cmdline_args:
- :return:
- """
- def version_infos():
- header = "# Running Counter RnAseq Window craw_coverage\n"
- commented_ver = get_version_message().rstrip().replace('\n', '\n# ')
- header += """#
-# Version: {}
-#
-# craw_coverage run with the following arguments:
-""".format(commented_ver)
- return header
-
- def options():
- options = ''
- for a, v in sorted(cmdline_args.__dict__.items()):
- if v is None or v is False:
- continue
- else:
- if v is True:
- options += "# --{opt}\n".format(opt=a.replace('_', '-'))
- else:
- options += "# --{opt}={val}\n".format(opt=a.replace('_', '-'), val=v)
- options.rstrip() + '\n'
- return options
-
- def padded_header():
- metadata = '\t'.join([str(f) for f in annot_parser.header])
- if cmdline_args.start_col:
- max_left, max_right = annot_parser.max()
- pos = '\t'.join(str(p) for p in range(0 - max_left, max_right + 1))
- else:
- pos = '\t'.join(str(p) for p in range(0 - cmdline_args.before, cmdline_args.after + 1))
- s = "sense\t{metadata}\t{pos}".format(metadata=metadata, pos=pos)
- return s
-
- def sum_header():
- metadata = '\t'.join([str(f) for f in annot_parser.header])
- return "sense\t{metadata}\tcoverage".format(metadata=metadata)
-
- def resized_header(new_size):
- metadata = '\t'.join([str(f) for f in annot_parser.header])
- pos = '\t'.join([str(i) for i in range(new_size)])
- return "sense\t{metadata}\t{pos}".format(metadata=metadata, pos=pos)
-
- header = version_infos()
- header += options()
-
- if args.justify:
- header += resized_header(args.justify)
- elif args.sum:
- header += sum_header()
- else:
- header += padded_header()
- return header
-
-
-def get_version_message():
- version_text = craw.get_version_message()
- version_text += """
-Using:
- - pysam {pysam_ver} (samtools {samtools_ver})
- - scipy {sp_ver} (only for --justify opt)
-""".format(pysam_ver=pysam.__version__,
- samtools_ver=pysam.__samtools_version__,
- sp_ver=craw.coverage.scipy.__version__)
- return version_text
-
-
-def get_results_file(sense_opt, basename, suffix):
- if sense_opt == 'S':
- sense_filename = "{filename}.sense.{suffix}".format(filename=basename, suffix=suffix)
- sense = open(sense_filename, 'w')
- antisense = open(os.devnull, 'w')
- elif sense_opt == 'AS':
- sense = open(os.devnull, 'w')
- antisense_filename = "{filename}.antisense.{suffix}".format(filename=basename, suffix=suffix)
- antisense = open(antisense_filename, 'w')
- elif sense_opt == 'split':
- sense_filename = "{filename}.sense.{suffix}".format(filename=basename, suffix=suffix)
- sense = open(sense_filename, 'w')
- antisense_filename = "{filename}.antisense.{suffix}".format(filename=basename, suffix=suffix)
- antisense = open(antisense_filename, 'w')
- else:
- output_filename = "{filename}.{suffix}".format(filename=basename, suffix=suffix)
- sense = open(output_filename, 'w')
- antisense = sense
- return sense, antisense
-
-
-parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter)
-input_grp = parser.add_argument_group()
-input_grp.add_argument("-b", "--bam",
- help="""The path of the bam file to analyse.
---bam option is not compatible with any --wig or --wig-for or --wig-rev options.
-but at least --bam or any of --wig* options is required.""")
-input_grp.add_argument("-w", "--wig",
- help="""The path of the wig file to analyse.
-The file encode the coverage for the both strand.
-The positive coverage ar on the forward strand whereas the negative coverage a located on the reverse one.
-The --wig option is incompatible with both --bam or --wig-for or --wig-reverse options.""")
-input_grp.add_argument("--wig-for",
- metavar='FORWARD WIG',
- help="""The path of a wig file to analyse.
-This file encode the coverage for the forward strand.
-The --wig-for option is incompatible with both --bam or --wig options.""")
-input_grp.add_argument("--wig-rev",
- metavar='REVERSE WIG',
- help="""The path of a wig file to analyse.
-This file encode the coverage for the reverse strand.
-The --wig-rev option is incompatible with both --bam or --wig options.""")
-parser.add_argument("-a", "--annot",
- required=True,
- help="The path of the annotation file (required).")
-parser.add_argument("--qual-thr",
- dest='qual_thr',
- type=quality_checker,
- default=15,
- help="The minimal quality of read mapping to take it in account")
-parser.add_argument("-s", "--suffix",
- default="cov",
- help="The name of the suffix to use for the output file.")
-parser.add_argument('-o', '--output',
- dest='output',
- help="The path of the output (default= base name of annotation file with --suffix)")
-parser.add_argument('--sep',
- default='\t',
- help="the separator use to delimit the annotation fields")
-mutually_exclusive_opt = parser.add_mutually_exclusive_group()
-mutually_exclusive_opt.add_argument('--justify',
- type=positive_int,
- help="to resize all genes coverage to this new size.")
-mutually_exclusive_opt.add_argument('--sum',
- action='store_true',
- default=False,
- help="sum all the coverages on the window.")
-
-region_grp = parser.add_argument_group(title="region of interest",
- description="""Parameters which define regions to compute.
-
-There is 2 way to define regions:
- * all regions have same length.
- * each region have different lengths.
-
-In both case a position of reference must be define (--ref-col).
-
-If all regions have same length:
-
- --window define the number of nucleotide to take in account before and
- after the reference position (the window will be centered on reference)
- --before define the number of nucleotide to take in account before the
- reference position.
- --after define the number of nucleotide to take in account after the
- reference position.
- --before and --after allow to define non centered window.
-
- --after and --before options must be set together and are
- incompatible with --window option.
-
-If all regions have different lengths:
-
- The regions must be specified in the annotation file.
- --start-col define the name of the column in annotation file which define
- the start position of the region to compute.
- --stop-col define the name of the column in annotation file which define
- the stop position of the region to compute.
-""")
-region_grp.add_argument("--ref-col",
- default="position",
- help="The name of the column for the reference position (default: position).")
-region_grp.add_argument("--before",
- type=positive_int,
- help="The number of base to compute after the position of reference.")
-region_grp.add_argument("--after",
- type=positive_int,
- help="The number of base to compute before the position of reference.")
-region_grp.add_argument("--window",
- type=positive_int,
- help="The number of base to compute around the position of reference.")
-region_grp.add_argument("--start-col",
- help="The name of the column to define the start position.")
-region_grp.add_argument("--stop-col",
- help="The name of the column to define the stop position.")
-col_name = parser.add_argument_group(title="specify the name of columns")
-col_name.add_argument("--strand-col",
- default='strand',
- help="Specify the name of the column representing the strand (default: strand)")
-col_name.add_argument("--chr-col",
- default='chromosome',
- help="Specify the name of the column representing the chromosome (default: chromosome)")
-
-parser.add_argument("--sense",
- choices=('S', 'AS', 'split', 'mixed'),
- default='mixed',
- help="compute result only on: "
- "sense (S), "
- "antisense (AS), "
- "on both senses but produce two separated files (split), "
- "or in one file (mixed)."
- "(default: mixed)"
- )
-
-parser.add_argument("--version",
- action=argparse_util.VersionAction,
- version=get_version_message())
-parser.add_argument("-q", "--quiet",
- action="count",
- default=0,
- help="Reduce verbosity.")
-parser.add_argument("-v", "--verbose",
- action="count",
- default=0,
- help="Increase verbosity.")
-
-args = parser.parse_args()
-
-input_opt_group = (args.bam, args.wig, args.wig_for, args.wig_rev)
-wig_opt_group = (args.wig, args.wig_for, args.wig_rev)
-
-#############################
-# Check wig and bam options #
-#############################
-if not any(input_opt_group):
- raise argparse.ArgumentError(None, "At least one of these options must be specified"
- " '--bam', '--wig' , '--wig-for', '--wig-rev'.")
-elif all(input_opt_group):
- raise argparse.ArgumentError(None, "'--bam', '--wig' , '--wig-for', '--wig-rev' cannot specify at the same time.")
-elif args.bam and any(wig_opt_group):
- raise argparse.ArgumentError(None,"'--bam' option cannot be specified in the same time as"
- " '--wig', '--wig-for' or '--wig-rev' options.")
-elif args.wig and any((args.wig_for, args.wig_rev)):
- raise argparse.ArgumentError(None,"'--wig' option cannot be specified in the same time as"
- " '--wig-for' or '--wig-rev' options.")
-###########################
-# Checking window options #
-###########################
-group_one = (args.before, args.after, args.window)
-group_two = (args.start_col, args.stop_col)
-if all([v is None for v in itertools.chain(group_one, group_two)]):
- raise argparse.ArgumentError(None, "[--window or [--before, --after] or [--start-col, --stop-col] options"
- " must be specified")
-elif any([v is not None for v in group_one]) and any([v is not None for v in group_two]):
- raise argparse.ArgumentError(None, "Options [--before, --after, --window] and [--start-col, --stop-col] "
- "are mutually exclusives.")
-elif all([v is None for v in group_two]):
- if args.window is None:
- if any([v is None for v in (args.before, args.after)]):
- raise argparse.ArgumentError(None, "The two options --after and --before work together."
- " The both options must be specified in same time")
- else:
- pass
- # window is None, before and after are specify
- # => nothing to do
- else:
- # args.window is not None:
- if any([v is not None for v in (args.before, args.after)]):
- raise argparse.ArgumentError(None, "options [--before, --after] and --window are mutually exclusives.")
- else:
- # --before, --after are None
- args.before = args.after = args.window
-elif not all(group_two):
- raise argparse.ArgumentError(None, "The two options --start-col and --stop-col work together. "
- "The both options must be specified in same time")
-
-verbosity = max(logging.INFO + (args.quiet - args.verbose) * 10, 1)
-craw.init_logger(verbosity)
-
-#######################
-# Parsing input files #
-#######################
-
-annot_line_number = sum(1 for line in open(args.annot))
-annot_parser = annotation.AnnotationParser(args.annot, args.ref_col,
- chr_col=args.chr_col,
- strand_col=args.strand_col,
- start_col=args.start_col,
- stop_col=args.stop_col,
- sep=args.sep)
-
-if args.bam:
- # input_data is a samfile
- input_file = args.bam
- input_data = pysam.AlignmentFile(args.bam, "rb")
-elif args.wig:
- # input_data is a wig.Genome object
- input_file = args.wig
- wig_parser = WigParser(mixed_wig=args.wig)
- input_data = wig_parser.parse()
-else:
- # input_data is a wig.Genome object
- input_file = args.wig_for
- wig_parser = WigParser(for_wig=args.wig_for, rev_wig=args.wig_rev)
- input_data = wig_parser.parse()
-
-annotations = annot_parser.get_annotations()
-
-############################
-# checking outputs options #
-############################
-if not args.output:
- args.output = os.path.splitext(input_file)[0]
- out_name = args.output
- suffix = args.suffix
-else:
- out_name, suffix = os.path.splitext(args.output)
- suffix = suffix.strip('.')
- if not suffix:
- suffix = args.suffix
-
-sense_file, antisense_file = get_results_file(args.sense, out_name, suffix)
-
-###########################
-# Computing output matrix #
-###########################
-with sense_file, antisense_file:
- header = get_result_header(annot_parser, args)
-
- if args.sense in ('S', 'split', 'mixed'):
- # if args.sense is mixed the sense_file and antisense_file are the same object
- print(header, file=sense_file)
- if args.sense in ('AS', 'split'):
- print(header, file=antisense_file)
-
- # get the appropriate function according to the input type
- # the 2 functions
- # - get_wig_coverage
- # - get_bam_coverage
- # have exactly the same api
- if args.justify:
- get_coverage = coverage.resized_coverage_maker(input_data, args.justify, qual_thr=None)
- elif args.sum:
- get_coverage = coverage.sum_coverage_maker(input_data, qual_thr=args.qual_thr)
- else:
- if args.window is not None:
- max_left = max_right = args.window
- elif args.before and args.after:
- max_left = args.before
- max_right = args.after
- else:
- max_left, max_right = annot_parser.max()
- get_coverage = coverage.padded_coverage_maker(input_data, max_left, max_right, qual_thr=args.qual_thr)
-
- for annot_num, annot_entry in enumerate(annotations, 1):
- if verbosity <= logging.INFO:
- progress(annot_num, annot_line_number)
- if args.start_col:
- # pos in get_coverage functions are
- # 0 based whereas in annotation they are 1 based
- # start is included, stop is excluded
- start = annot_entry.start - 1
- stop = annot_entry.stop
- else:
- if annot_entry.strand == '+':
- start = annot_entry.ref - args.before - 1
- stop = annot_entry.ref + args.after
- else:
- # if feature is on reverse strand
- # the before and after are inverted
- start = annot_entry.ref - args.after - 1
- stop = annot_entry.ref + args.before
- forward_cov, reverse_cov = get_coverage(annot_entry, start=start, stop=stop)
-
- sens = 'S' if annot_entry.strand == '+' else 'AS'
- if sens == 'S':
- print(sens, annot_entry, *forward_cov, sep='\t', file=sense_file)
- else:
- print(sens, annot_entry, *forward_cov, sep='\t', file=antisense_file)
-
- sens = 'S' if annot_entry.strand == '-' else 'AS'
- if sens == 'S':
- print(sens, annot_entry, *reverse_cov, sep='\t', file=sense_file)
- else:
- print(sens, annot_entry, *reverse_cov, sep='\t', file=antisense_file)
-
-print(file=sys.stderr)
diff --git a/bin/craw_htmp b/bin/craw_htmp
deleted file mode 100755
index 2be0f414571df8dd49f8b78aed955882d03f57fb..0000000000000000000000000000000000000000
--- a/bin/craw_htmp
+++ /dev/null
@@ -1,525 +0,0 @@
-#! /usr/bin/env python3
-
-###########################################################################
-# #
-# This file is part of Counter RNAseq Window (craw) package. #
-# #
-# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
-# see COPYRIGHT file for details. #
-# #
-# craw is free software: you can redistribute it and/or modify #
-# it under the terms of the GNU General Public License as published by #
-# the Free Software Foundation, either version 3 of the License, or #
-# (at your option) any later version. #
-# #
-# craw is distributed in the hope that it will be useful, #
-# but WITHOUT ANY WARRANTY; without even the implied warranty of #
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
-# See the GNU General Public License for more details. #
-# #
-# You should have received a copy of the GNU General Public License #
-# along with craw (see COPYING file). #
-# If not, see <http://www.gnu.org/licenses/>. #
-# #
-###########################################################################
-
-import sys
-import os
-import argparse
-import logging
-
-import matplotlib as mtp
-
-
-if 'CRAW_HOME' in os.environ and os.environ['CRAW_HOME']:
- if os.environ['CRAW_HOME'] not in sys.path:
- sys.path.insert(0, os.environ['CRAW_HOME'])
-try:
- import craw
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- sys.exit(msg)
-
-
-root_logger = logging.getLogger()
-handler = logging.StreamHandler()
-formatter = logging.Formatter(fmt='{levelname} : {name} : {message}', style='{')
-handler.setFormatter(formatter)
-root_logger.addHandler(handler)
-root_logger.setLevel(logging.DEBUG)
-
-
-def _gene_size_parser(value):
- """
- Parse value given by the parser
-
- :param value: the value given by the parser for --sort-by-gene-size option
- :type value: string
- :return: name of column representing the start of gene, name of the column representing the end of gene
- :rtype: tuple of 2 string
- :raise: :class:`argparse.ArgumentError` object if value cannot be parsed
- """
- # this function is called only if value is provided to sort-by-gene-size option
- rv = value.split(',')
- if len(rv) == 0:
- rv = ['', '']
- elif len(rv) == 2:
- pass
- else:
- raise argparse.ArgumentError(None, "--sort-by-gene-size {} invalid value. "
- "Must be start_col, stop_col (separated by a comma), "
- "default= annotation_start,annotation_end".format(value)) from None
- return rv
-
-def _size_fig_parser(value):
- """
- Parse value given by the parser for --size option
- the value must follow the syntax widexheight[unit]
- if the unit is omitted unit is inch
- otherwise unit must be
- - 'mm' for millimeters
- - 'cm' for centimeters
- - 'in' for inches
- - 'px' for pixels
- wide and height must be positive integers.
-
- :param value: the size of the figure
- :type value: string
- :return: the size in inch aks by the user
- :rtype: tuple of float
- :raise: :class:`argparse.ArgumentError` object
- """
- def mm2in(value):
- return value * (1 / 25.4)
-
- def cm2in(value):
- return mm2in(value * 10)
-
- def px2in(value):
- dpi = plt.rcParams['figure.dpi']
- return value / dpi
-
- err_msg = """--size {} invalid value.
- The value must be widexheight[unit] or 'raw'.
- 'wide' and 'height' must be positive integers
- By default unit is in inches.
- eg: 7x10 or 7x10in for 7 inches wide by 10 inches height
- 70x100mm for 70 mm by 100 mm.
- default=7x10 or 10x7 depending of the figure orientation."""
- if value == 'raw':
- return 'raw'
- else:
- unit = 'in'
- if value[-2:] in ('mm', 'cm', 'in', 'px'):
- unit = value[-2:]
- value = value[:-2]
- try:
- wide, height = value.split('x')
- except ValueError:
- raise argparse.ArgumentError(None, err_msg.format(value))
- try:
- wide = int(wide)
- height = int(height)
- except ValueError:
- raise argparse.ArgumentError(None, err_msg.format(value))
- if wide < 0 or height < 0:
- raise argparse.ArgumentError(None, err_msg.format(value))
-
- if unit == 'mm':
- wide = mm2in(wide)
- height = mm2in(height)
- elif unit == 'cm':
- wide = cm2in(wide)
- height = cm2in(height)
- elif unit == 'px':
- wide = px2in(wide)
- height = px2in(height)
-
- return wide, height
-
-
-def get_version_message():
- """
-
- :return: a human readable of craw_htmp version and it's main dependencies.
- """
- # pyplot must be import after the argument parsing
- # because in function of the environment ($DYSPLAY and options) the craw_htmp behavior
- # is not the same
- # so heatmap cannot be import before argument parsing
- # so I import the dependencies in get_version_message.
- # it's not very important as get_version_message is called only when --version is set
- # so the program quit after displaying this message.
- import numpy as np
- import pandas as pd
- import matplotlib as mtp
- import PIL
- version_text = craw.get_version_message()
- version_text += """
-Using:
- - numpy {np_ver}
- - pandas {pd_ver}
- - matplotlib {mtp_ver}
- - pillow {pil_ver}
-""".format(np_ver=np.__version__,
- pd_ver=pd.__version__,
- mtp_ver=mtp.__version__,
- pil_ver=PIL.PILLOW_VERSION
- )
- return version_text
-
-parser = argparse.ArgumentParser(description="Compute a figure from a file of coverage compute by craw_coverage.",
- formatter_class=argparse.RawTextHelpFormatter)
-
-parser.add_argument(dest="cov_file",
- help="the path to the coverage file.")
-
-data_grp = parser.add_argument_group('optional data options')
-data_grp.add_argument("--crop",
- nargs=2,
- help="""crop the matrix.
-This option need two values the name of the first and last column to keep
-[start col, stop col] eg --crop -10 1000 .""")
-
-sort_grp = data_grp.add_mutually_exclusive_group()
-sort_grp.add_argument("--sort-using-col",
- default=False,
- help="sort the rows using the column COL.")
-sort_grp.add_argument("--sort-using-file",
- type=argparse.FileType('r'),
- help="""Sort the rows using a file.
-The file must have on the first line the name of the column
-which will use to sort.
-Each following lines must match to a value of this column in the data.""")
-sort_grp.add_argument("--sort-by-gene-size",
- type=_gene_size_parser,
- nargs='*',
- metavar='start_col,stop_col',
- help="""The rows will be sorted by gene size
-using start-col and stop-col to compute length.
-
-start-col and stop-col must be a string separated by comma.
-If start-col and stop-col are not specified annotation_start and annotation_end
-for start-col and stop-col respectively will be used.
-(Don't put this option without value just before the coverage file.)""")
-
-matrix_grp = data_grp.add_mutually_exclusive_group()
-matrix_grp.add_argument("--sense-only",
- action="store_true",
- default=False,
- help="Display only sense matrix (default is display both).")
-matrix_grp.add_argument("--antisense-only",
- action="store_true",
- default=False,
- help="Display only anti sense matrix (default is display both).")
-
-fig_grp = parser.add_argument_group("optional figure options")
-fig_grp.add_argument("--cmap",
- default="Blues",
- help="""The color map used to display data.
-The allowed values are defined in
-http:matplotlib.org/examples/color/colormaps_reference.html
-eg: Blues, BuGn, Greens, GnBu, ... (default: Blues).""")
-fig_grp.add_argument("--title",
- help="""The figure title.
-It will display on the top of the figure.
-(default: the name of the coverage file without extension).""")
-fig_grp.add_argument("--dpi",
- type=int,
- help="""The resolution of the output .
-This option work only if --out option is specified with size not raw.
-(default: matplolibrc figure.dpi""")
-fig_grp.add_argument("--size",
- type=_size_fig_parser,
- help="""Specify the figure size.
-The value must be widexheight[unit] or 'raw'.
-
-If value is raw it will be produce two image files (for sense and antisense) "
-with one pixel correspond to one coverage value for one nucleotide.
-
-Otherwise, 'wide' and 'height' must be positive integers
-By default units are in inches eg:
-
-* 7x10 or 7x10in for 7 inches wide by 10 inches height
-* 70x100mm for 70 mm by 100 mm.
-
-(default: 7x10 or 10x7 depending of the figure orientation).""")
-
-fig_grp.add_argument("--norm",
- choices=["lin", "log", "row", "log+row", "row+log"],
- default="lin",
- help="""Which normalization to apply to the data before display them.
-
- * lin a linear normalization is applied on the whole matrix.
- * log a 10 base logarithm will be applied on the data before matrix
- normalization.
- * row mean that a linear normalisation is compute row by row.
- * log+row mean a 10 base logarithm will be applied before a normalisation
- row by row. ('row+log' is an alias for 'log+row').
- (default: lin""")
-
-fig_grp.add_argument("--mark",
- action='append',
- nargs='*',
- metavar='POS [COLOR]',
- help="""* POS is mandatory and must be a positive integer.
-* COLOR is optional
- The supported color formats are:
- - Hexadecimal color specifiers, given as '#rgb' or '#rrggbb'. For example, '#ff0000' specifies pure red.
- - Common HTML color names.
-
-If COLOR is omitted the color corresponding to the highest value in the color map (--cmap) will be used.
-(this option cannot be the last one just before the coverage file, on the command line.)""")
-
-layout = fig_grp.add_mutually_exclusive_group()
-layout.add_argument("--sense-on-left",
- action="store_true",
- default=False,
- help="Where to display the sense matrix relative to antisense matrix (default is top).")
-layout.add_argument("--sense-on-right",
- action="store_true",
- default=False,
- help="Where to display the sense matrix relative to antisense matrix (default is top).")
-layout.add_argument("--sense-on-top",
- action="store_true",
- default=False,
- help="Where to display the sense matrix relative to antisense matrix (default is top).")
-layout.add_argument("--sense-on-bottom",
- action="store_true",
- default=False,
- help="Where to display the sense matrix relative to antisense matrix (default is top).")
-
-parser.add_argument("--out",
- help="""The name of the file (the format will based on the extension)
-to save the figure.
-Instead of displaying the figure on the screen, save it directly in this file.
-
-If this option is used with --size raw 2 files will be produced
-for respectively sense and anti sense.
-The extension 'sense' or 'antisense' will be added between the name and the suffix eg:
---size raw --out foo.png give 2 files 'foo.sense.png' and 'foo.antisense.png'.
-
-If no format (determine using the suffix) is given 'png' will be used.""")
-
-parser.add_argument("-v", "--verbose",
- action='count',
- default=0,
- help="Increase output verbosity.")
-parser.add_argument("-q", "--quiet",
- action="count",
- default=0,
- help="Reduce output verbosity.")
-parser.add_argument("--version",
- action='version',
- version=get_version_message(),
- help="display the version information and quit.")
-try:
- args = parser.parse_args()
-except Exception as err:
- print(err)
-
-verbosity = max(logging.INFO + (args.quiet - args.verbose) * 10, 1)
-craw.init_logger(verbosity)
-
-log = logging.getLogger('craw.htmp')
-
-
-log.debug("args={}".format(args))
-###########################
-# validating some options #
-###########################
-# test if DISPlAY
-if not os.environ.get('DISPLAY'):
- if args.out is not None:
- _, out_format = os.path.splitext(args.out)
- from craw.util import non_interactive_backends
- try:
- backend = non_interactive_backends[out_format.lstrip('.')]
- except KeyError:
- raise RuntimeError("The '{}' format is not supported, choose among {}.".format(
- out_format,
- list(non_interactive_backends.keys())
- ))
- mtp.use(backend)
- else:
- raise RuntimeError("""
-'DISPLAY' variable is not set (you probably run craw_htmp in non graphic environment)
-So you cannot use interactive output
-please specify an output file (--out).
-""")
-
-# the import of pyplot must be done after setting the backend
-import matplotlib.pyplot as plt
-from craw import heatmap
-
-
-try:
- color_map = plt.cm.get_cmap(args.cmap)
-except AttributeError as err:
- raise RuntimeError("{} : http:matplotlib.org/examples/color/colormaps_reference.html for example".format(err))
-
-if args.sort_by_gene_size == []:
- args.sort_by_gene_size = ['annotation_start', 'annotation_end']
-elif args.sort_by_gene_size:
- args.sort_by_gene_size = args.sort_by_gene_size[0]
-
-if args.out:
- out_dir = os.path.dirname(args.out) or '.'
- if not os.access(out_dir, os.W_OK):
- msg = "{} is not writable".format(out_dir)
- log.error(msg)
- raise RuntimeError(msg)
-
-
-log.info("Parsing coverage file")
-data = heatmap.get_data(args.cov_file)
-
-
-def mark_converter(data, marks):
- converted_marks = []
- for value in marks:
- pos = int(value[0])
- color = value[1] if len(value) == 2 else None
- converted_marks.append(heatmap.Mark(pos, data, color_map, color=color))
- return converted_marks
-
-if args.mark is not None:
- args.mark = mark_converter(data, args.mark)
-
-sense_data, antisense_data = heatmap.split_data(data)
-
-if args.sense_only:
- antisense_data = None
-if args.antisense_only:
- sense_data = None
-
-################
-# sorting data #
-################
-# if data is empty or data is None sort return data
-# so it's error safe, and not time and space consuming
-if args.sort_by_gene_size:
- start_col, stop_col = args.sort_by_gene_size
- sense_data = heatmap.sort(sense_data, 'by_gene_size', start_col=start_col, stop_col=stop_col)
- antisense_data = heatmap.sort(antisense_data, 'by_gene_size', start_col=start_col, stop_col=stop_col)
-elif args.sort_using_col:
- sense_data = heatmap.sort(sense_data, 'using_col', col=args.sort_using_col)
- antisense = heatmap.sort(antisense_data, 'using_col', col=args.sort_using_col)
-elif args.sort_using_file:
- sense_data = heatmap.sort(sense_data, 'using_file', file=args.sort_using_file)
- antisense_data = heatmap.sort(antisense_data, 'using_file', file=args.sort_using_file)
-
-sense_data = heatmap.remove_metadata(sense_data)
-antisense_data = heatmap.remove_metadata(antisense_data)
-
-################
-# croping data #
-################
-log.info("Croping matrix")
-if args.crop:
- start_col, stop_col = args.crop
- sense_data = heatmap.crop(sense_data, start_col, stop_col)
- antisense_data = heatmap.crop(antisense_data, start_col, stop_col)
-
-####################
-# Normalizing data #
-####################
-log.info("Normalizing data")
-
-if args.norm == "lin":
- log.info("Linear normalisation")
- sense_data = heatmap.lin_norm(sense_data)
- antisense_data = heatmap.lin_norm(antisense_data)
-elif args.norm == 'log':
- log.info("10 base logarithm normalisation")
- sense_data = heatmap.log_norm(sense_data)
- antisense_data = heatmap.log_norm(antisense_data)
-elif args.norm == 'row':
- log.info("Linear normalisation by row")
- sense_data = heatmap.lin_norm_row_by_row(sense_data)
- antisense_data = heatmap.lin_norm_row_by_row(antisense_data)
-else:
- # log+row or row+log
- log.info("10 base logarithm and normalisation by row")
- sense_data = heatmap.log_norm_row_by_row(sense_data)
- antisense_data = heatmap.log_norm_row_by_row(antisense_data)
-
-
-##################
-# Drawing figure #
-##################
-log.info("Drawing figure")
-if args.size == 'raw':
- # pillow backend
- if args.sense_only:
- sense_to_compute = ('sense', )
- elif args.antisense_only:
- sense_to_compute = ('antisense', )
- else:
- sense_to_compute = ('sense', 'antisense')
-
- if args.out:
- root_name, im_format = os.path.splitext(args.out)
- im_format = im_format.lstrip('.')
- if not im_format:
- im_format = 'png'
- else:
- im_format = 'png'
- root_name = os.path.splitext(args.cov_file)[0]
-
- out_filename = {}
- for sense in sense_to_compute:
- filename = "{filename}.{sense}.{format}".format(filename=root_name, sense=sense, format=im_format)
- out_filename[sense] = filename
- if os.path.exists(filename):
- msg = "{} already exists".format(filename)
- log.error(msg)
- raise RuntimeError(msg)
-
- for sense in sense_to_compute:
- log.info("Drawing {}".format(sense))
- data = globals()[sense + '_data']
- if data is not None:
- heatmap.draw_raw_image(data, out_filename[sense], color_map, marks=args.mark)
- else:
- log.warning("{} data are empty: skip drawing.".format(sense))
-else:
- # matplotlib backend
- ##########
- # layout #
- ##########
- if args.sense_on_left:
- sense_on = 'left'
- elif args.sense_on_right:
- sense_on = 'right'
- elif args.sense_on_top:
- sense_on = 'top'
- elif args.sense_on_bottom:
- sense_on = 'bottom'
- else:
- sense_on = 'top'
-
- if args.title is None:
- title = os.path.basename(os.path.splitext(args.cov_file)[0])
- else:
- title = args.title
-
- fig = heatmap.draw_heatmap(sense_data, antisense_data,
- color_map=color_map,
- title=title,
- sense_on=sense_on,
- size=args.size,
- marks=args.mark)
-
- if args.out:
- if os.path.exists(args.out):
- msg = "The output file: {} already exists.".format(args.out)
- log.error(msg)
- raise RuntimeError(msg)
-
- if args.dpi:
- fig.savefig(args.out, dpi=args.dpi)
- fig.savefig(args.out)
- else:
- plt.show()
diff --git a/craw/__init__.py b/craw/__init__.py
index 5a79ae4c75b1728e85d2378bc258af158c73a659..bc07de53501a4ca19eb7e7b6040da091dba67e5a 100644
--- a/craw/__init__.py
+++ b/craw/__init__.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -25,8 +25,10 @@
import sys
import logging
+import time
+
+__version__ = '1.dev{}'.format(time.strftime('%Y%m%d'))
-__version__ = '$VERSION'
def get_version_message():
"""
@@ -34,17 +36,13 @@ def get_version_message():
:return: A human readable version of the craw package version
:rtype: string
"""
- # if I keep '$ VERSION' (without space) as is
- # the setup.py will replace it by the value set in setup
- # so the test become True even if craw is installed using setup.py
- if __version__ == '$' + 'VERSION':
- version = "NOT packaged, it should be a development version"
- else:
- version = __version__
- version_text = "craw {0} | Python {1}.{2}".format(version, sys.version_info.major, sys.version_info.minor)
+ version_text = "craw {0} | Python {1}.{2}".format(__version__,
+ sys.version_info.major,
+ sys.version_info.minor)
return version_text
-def init_logger(log_level):
+
+def init_logger(log_level, out=True):
"""
Initiate the "root" logger for craw library
all logger create in craw package inherits from this root logger
@@ -54,9 +52,13 @@ def init_logger(log_level):
:type log_level: int
"""
craw_log = logging.getLogger('craw')
- handler = logging.StreamHandler()
- formatter = logging.Formatter(fmt='{levelname} : {name} : {message}', style='{')
- handler.setFormatter(formatter)
- craw_log.addHandler(handler)
+ if out:
+ handler = logging.StreamHandler()
+ formatter = logging.Formatter(fmt='{levelname} : {name} : {message}', style='{')
+ handler.setFormatter(formatter)
+ craw_log.addHandler(handler)
+ else:
+ null_handler = logging.NullHandler()
+ craw_log.addHandler(null_handler)
craw_log.setLevel(log_level)
craw_log.propagate = False
diff --git a/craw/annotation.py b/craw/annotation.py
index da8b18b1e65f5a458422dd9beb45b2a8156ab8ed..1811616489ca8b0a9b59dc11093ac5639b5118a1 100644
--- a/craw/annotation.py
+++ b/craw/annotation.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
diff --git a/craw/argparse_util.py b/craw/argparse_util.py
index 77bfae93455aa7e24da17363439240412503423c..9da41f87238b5693fa830f5d2e87dc404f873ff0 100644
--- a/craw/argparse_util.py
+++ b/craw/argparse_util.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright c 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
diff --git a/craw/coverage.py b/craw/coverage.py
index 451a35b785e67ec78d16af4975937621cb7b14c4..4a42e8cca6943475478aaa7941c62dde35bf0ebc 100644
--- a/craw/coverage.py
+++ b/craw/coverage.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -26,20 +26,13 @@ import logging
import numpy as np
import scipy.interpolate
-try:
- # for pysam>=0.9.1.4
- from pysam.calignmentfile import AlignmentFile
-except ImportError:
- # for pysam>=0.10
- from pysam import AlignmentFile
+from pysam import AlignmentFile
from .wig import Genome
_log = logging.getLogger(__name__)
-
-
def sum_coverage_maker(input_data, qual_thr=None):
"""
This function return a new function :func:`get_sum_coverage`
@@ -232,7 +225,6 @@ def get_raw_coverage_function(input):
"'pysam.calignmentfile.AlignmentFile' as Input, not {}".format(input.__class__.__name__))
-
def get_raw_wig_coverage(genome, annot_entry, start, stop, qual_thr=None):
"""
:param genome: The genome which store all coverages.
@@ -314,20 +306,24 @@ def get_raw_bam_coverage(sam_file, annot_entry, start, stop, qual_thr=15):
call_back = on_forward if strand == '+' else on_reverse
try:
- coverage = sam_file.count_coverage(reference=chromosome,
+ coverage = sam_file.count_coverage(chromosome,
start=start,
- end=stop,
+ stop=stop,
quality_threshold=qual,
read_callback=call_back)
except SystemError as err:
import sys
- print("ERROR when call count_coverage with following arguments\n",
- "reference=", chromosome, "\n",
- "start=", start, "\n",
- "end=", stop, "\n",
- "quality_threshold=", qual, "\n",
- "read_callback=", call_back,
- file=sys.stderr)
+ _log.critical("ERROR when call count_coverage with following arguments\n"
+ "reference= {chromosome} \n"
+ "start={start}\n"
+ "end={stop}\n"
+ "quality_threshold={qual}\n"
+ "read_callback={call_back}".format(chromosome=chromosome,
+ start=start,
+ stop=stop,
+ qual=qual,
+ call_back=call_back)
+ )
raise err
coverage = [array.tolist() for array in coverage]
diff --git a/craw/heatmap.py b/craw/heatmap.py
index 6651dccc0cf632542e3a668efb52c7a04e94d7e3..4e0c113cc859369bc350f244d03e7c22d847d6dd 100644
--- a/craw/heatmap.py
+++ b/craw/heatmap.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -41,7 +41,7 @@ def get_data(coverage_file):
:return: the data as 2 dimension dataframe
:rtype: a :class:`pandas.DataFrame` object
"""
- data = pd.read_table(coverage_file, comment='#', na_values='None')
+ data = pd.read_csv(coverage_file, sep="\t", comment='#', na_values='None')
return data
@@ -140,7 +140,7 @@ def _sort_using_file(data, file=None):
:rtype: a :class:`pandas.DataFrame` object.
"""
_log.info("Sorting data using file {}".format(file))
- ref = pd.read_table(file, comment="#")
+ ref = pd.read_csv(file, comment="#", sep='\t')
col_name = ref.columns[0]
# change the index of the data using the col_name
@@ -319,6 +319,8 @@ def draw_one_matrix(mat, ax, cmap=plt.cm.Blues, y_label=None, marks=None):
:type cmap: a :class:`matplotlib.pyplot.cm` object.
:param y_label: the label for the data draw on y-axis.
:type y_label: string
+ :param marks: list of vertical marks
+ :type marks: list of :class:`Mark` object
:return: the mtp image corresponding to data
:rtype: a :class:`matplotlib.image` object.
"""
@@ -342,7 +344,7 @@ def draw_one_matrix(mat, ax, cmap=plt.cm.Blues, y_label=None, marks=None):
ax.set_ylabel(y_label, size='large')
if marks:
for mark in marks:
- ax.axvline(x=mark.to_px(), linewidth=0.5, color=mark.rgb_float())
+ ax.axvline(x=mark.to_px(), linewidth=0.5, color=mark.rgb_float)
return mat_img
@@ -363,6 +365,8 @@ def draw_heatmap(sense, antisense, color_map=plt.cm.Blues, title='', sense_on='t
:type sense_on: string.
:param size: the size of the figure in inches (wide, height).
:type size: tuple of 2 float.
+ :param marks: list of vertical marks
+ :type marks: list of :class:`Mark` object
:return: The figure.
:rtype: a :class:`matplotlib.pyplot.Figure` object.
"""
diff --git a/craw/scripts/__init__.py b/craw/scripts/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..d7911b88114661ac217c46cc0ded248be64b8031
--- /dev/null
+++ b/craw/scripts/__init__.py
@@ -0,0 +1,23 @@
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
\ No newline at end of file
diff --git a/craw/scripts/craw_coverage.py b/craw/scripts/craw_coverage.py
new file mode 100755
index 0000000000000000000000000000000000000000..0ed034f7754de5189e99a09a9a55c2ca31442fa7
--- /dev/null
+++ b/craw/scripts/craw_coverage.py
@@ -0,0 +1,517 @@
+#! /usr/bin/env python3
+
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+import os
+import sys
+import argparse
+import itertools
+import logging
+import pysam
+
+import craw
+from craw.util import progress
+from craw import argparse_util
+from craw import annotation, coverage
+from craw.wig import WigParser
+
+
+def positive_int(value):
+ """
+ Parse value given by the parser
+
+ :param value: the value given by the parser
+ :type value: string
+ :return: the integer corresponding to the value
+ :rtype: int
+ :raise: :class:`argparse.ArgumentTypeError`
+ """
+ try:
+ value = int(value)
+ except ValueError:
+ raise argparse.ArgumentTypeError("must be a positive integer, got: {}".format(value))
+ if value < 0:
+ msg = "must be a positive integer, got: {}".format(value)
+ raise argparse.ArgumentTypeError(msg)
+ return value
+
+
+def quality_checker(value):
+ """
+ Parse value given by the parser
+
+ :param value: the value given by the parser
+ :type value: string
+ :return: the integer >=0 and <=42 corresponding to the value
+ :rtype: int
+ :raise: :class:`argparse.ArgumentTypeError` if value does not represent a integer >=0 and <=42
+ """
+
+ try:
+ value = int(value)
+ except ValueError:
+ raise argparse.ArgumentTypeError("must be a integer between 0 and 42, got: {}".format(value))
+ if not 0 <= value <= 42:
+ raise argparse.ArgumentTypeError("must be a integer between 0 and 42, got: {}".format(value))
+ return value
+
+
+def get_result_header(annot_parser, parsed_args):
+ """
+ Compute the header for the results.
+ the firts lines start with #
+ they contains some general information about the craw (version)
+ and options used (for tracbility)
+ the last line is the header of columns separated by --sep option
+ and can be used as header with pandas
+
+ :param annot_parser: the annotation parser
+ :type annot_parser: :class:`annotation.AnnotationParser` object
+ :param parsed_args: the command line argument parsed with argparse
+ :type parsed_args: :class:`argparse.Namespace`
+ :return: The header of the result file
+ :rtype: str
+ """
+ def version_infos():
+ header = "# Running Counter RnAseq Window craw_coverage\n"
+ commented_ver = get_version_message().rstrip().replace('\n', '\n# ')
+ header += """#
+# Version: {}
+#
+# craw_coverage run with the following arguments:
+""".format(commented_ver)
+ return header
+
+ def options():
+ options = ''
+ for a, v in sorted(parsed_args.__dict__.items()):
+ if v is None or v is False:
+ continue
+ else:
+ if v is True:
+ options += "# --{opt}\n".format(opt=a.replace('_', '-'))
+ else:
+ options += "# --{opt}={val}\n".format(opt=a.replace('_', '-'), val=v)
+ options.rstrip() + '\n'
+ return options
+
+ def padded_header():
+ metadata = '\t'.join([str(f) for f in annot_parser.header])
+ if parsed_args.start_col:
+ max_left, max_right = annot_parser.max()
+ pos = '\t'.join(str(p) for p in range(0 - max_left, max_right + 1))
+ else:
+ pos = '\t'.join(str(p) for p in range(0 - parsed_args.before, parsed_args.after + 1))
+ s = "sense\t{metadata}\t{pos}".format(metadata=metadata, pos=pos)
+ return s
+
+ def sum_header():
+ metadata = '\t'.join([str(f) for f in annot_parser.header])
+ return "sense\t{metadata}\tcoverage".format(metadata=metadata)
+
+ def resized_header(new_size):
+ metadata = '\t'.join([str(f) for f in annot_parser.header])
+ pos = '\t'.join([str(i) for i in range(new_size)])
+ return "sense\t{metadata}\t{pos}".format(metadata=metadata, pos=pos)
+
+ header = version_infos()
+ header += options()
+
+ if parsed_args.justify:
+ header += resized_header(parsed_args.justify)
+ elif parsed_args.sum:
+ header += sum_header()
+ else:
+ header += padded_header()
+ return header
+
+
+def get_version_message():
+ """
+ :return: The human readable CRAW version.
+ :rtype: str
+ """
+ version_text = craw.get_version_message()
+ version_text += """
+Using:
+ - pysam {pysam_ver} (samtools {samtools_ver})
+ - scipy {sp_ver} (only for --justify opt)
+""".format(pysam_ver=pysam.__version__,
+ samtools_ver=pysam.__samtools_version__,
+ sp_ver=craw.coverage.scipy.__version__)
+ return version_text
+
+
+def get_results_file(sense_opt, basename, suffix):
+ """
+
+ :param str sense_opt: how to managed the sense and antisense results
+
+ * **mixed**: sense and antisense are interleaved in same file
+ * **split**: sense and antisense are in separated files
+ * **S**: only sense results are write down
+ * **AS**: only antisense are write down
+
+ :param str basename: the basename of the results file
+ :param str suffix: the suffix of the results file
+ :return: the file objects where to write sense and antisense results
+ :rtype: tuple (`file object` sense, `file object` antisense)
+ """
+ if sense_opt == 'S':
+ sense_filename = "{filename}.sense.{suffix}".format(filename=basename, suffix=suffix)
+ sense = open(sense_filename, 'w')
+ antisense = open(os.devnull, 'w')
+ elif sense_opt == 'AS':
+ sense = open(os.devnull, 'w')
+ antisense_filename = "{filename}.antisense.{suffix}".format(filename=basename, suffix=suffix)
+ antisense = open(antisense_filename, 'w')
+ elif sense_opt == 'split':
+ sense_filename = "{filename}.sense.{suffix}".format(filename=basename, suffix=suffix)
+ sense = open(sense_filename, 'w')
+ antisense_filename = "{filename}.antisense.{suffix}".format(filename=basename, suffix=suffix)
+ antisense = open(antisense_filename, 'w')
+ else:
+ output_filename = "{filename}.{suffix}".format(filename=basename, suffix=suffix)
+ sense = open(output_filename, 'w')
+ antisense = sense
+ return sense, antisense
+
+
+def parse_args(args):
+ """
+
+ :param args: The options set on the command line (without the program name)
+ :type args: list of string
+ :return:
+ """
+ parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter)
+ input_grp = parser.add_argument_group()
+ input_grp.add_argument("-b", "--bam",
+ help="""The path of the bam file to analyse.
+ --bam option is not compatible with any --wig or --wig-for or --wig-rev options.
+ but at least --bam or any of --wig* options is required.""")
+ input_grp.add_argument("-w", "--wig",
+ help="""The path of the wig file to analyse.
+ The file encode the coverage for the both strand.
+ The positive coverage ar on the forward strand whereas the negative coverage a located on the reverse one.
+ The --wig option is incompatible with both --bam or --wig-for or --wig-reverse options.""")
+ input_grp.add_argument("--wig-for",
+ metavar='FORWARD WIG',
+ help="""The path of a wig file to analyse.
+ This file encode the coverage for the forward strand.
+ The --wig-for option is incompatible with both --bam or --wig options.""")
+ input_grp.add_argument("--wig-rev",
+ metavar='REVERSE WIG',
+ help="""The path of a wig file to analyse.
+ This file encode the coverage for the reverse strand.
+ The --wig-rev option is incompatible with both --bam or --wig options.""")
+ parser.add_argument("-a", "--annot",
+ required=True,
+ help="The path of the annotation file (required).")
+ parser.add_argument("--qual-thr",
+ dest='qual_thr',
+ type=quality_checker,
+ default=15,
+ help="The minimal quality of read mapping to take it in account")
+ parser.add_argument("-s", "--suffix",
+ default="cov",
+ help="The name of the suffix to use for the output file.")
+ parser.add_argument('-o', '--output',
+ dest='output',
+ help="The path of the output (default= base name of annotation file with --suffix)")
+ parser.add_argument('--sep',
+ default='\t',
+ help="the separator use to delimit the annotation fields")
+ mutually_exclusive_opt = parser.add_mutually_exclusive_group()
+ mutually_exclusive_opt.add_argument('--justify',
+ type=positive_int,
+ help="to resize all genes coverage to this new size.")
+ mutually_exclusive_opt.add_argument('--sum',
+ action='store_true',
+ default=False,
+ help="sum all the coverages on the window.")
+
+ region_grp = parser.add_argument_group(title="region of interest",
+ description="""Parameters which define regions to compute.
+
+ There is 2 way to define regions:
+ * all regions have same length.
+ * each region have different lengths.
+
+ In both case a position of reference must be define (--ref-col).
+
+ If all regions have same length:
+
+ --window define the number of nucleotide to take in account before and
+ after the reference position (the window will be centered on reference)
+ --before define the number of nucleotide to take in account before the
+ reference position.
+ --after define the number of nucleotide to take in account after the
+ reference position.
+ --before and --after allow to define non centered window.
+
+ --after and --before options must be set together and are
+ incompatible with --window option.
+
+ If all regions have different lengths:
+
+ The regions must be specified in the annotation file.
+ --start-col define the name of the column in annotation file which define
+ the start position of the region to compute.
+ --stop-col define the name of the column in annotation file which define
+ the stop position of the region to compute.
+ """)
+ region_grp.add_argument("--ref-col",
+ default="position",
+ help="The name of the column for the reference position (default: position).")
+ region_grp.add_argument("--before",
+ type=positive_int,
+ help="The number of base to compute after the position of reference.")
+ region_grp.add_argument("--after",
+ type=positive_int,
+ help="The number of base to compute before the position of reference.")
+ region_grp.add_argument("--window",
+ type=positive_int,
+ help="The number of base to compute around the position of reference.")
+ region_grp.add_argument("--start-col",
+ help="The name of the column to define the start position.")
+ region_grp.add_argument("--stop-col",
+ help="The name of the column to define the stop position.")
+ col_name = parser.add_argument_group(title="specify the name of columns")
+ col_name.add_argument("--strand-col",
+ default='strand',
+ help="Specify the name of the column representing the strand (default: strand)")
+ col_name.add_argument("--chr-col",
+ default='chromosome',
+ help="Specify the name of the column representing the chromosome (default: chromosome)")
+
+ parser.add_argument("--sense",
+ choices=('S', 'AS', 'split', 'mixed'),
+ default='mixed',
+ help="compute result only on: "
+ "sense (S), "
+ "antisense (AS), "
+ "on both senses but produce two separated files (split), "
+ "or in one file (mixed)."
+ "(default: mixed)"
+ )
+
+ parser.add_argument("--version",
+ action=argparse_util.VersionAction,
+ version=get_version_message())
+ parser.add_argument("-q", "--quiet",
+ action="count",
+ default=0,
+ help="Reduce verbosity.")
+ parser.add_argument("-v", "--verbose",
+ action="count",
+ default=0,
+ help="Increase verbosity.")
+
+ parsed_args = parser.parse_args(args)
+
+ input_opt_group = (parsed_args.bam, parsed_args.wig, parsed_args.wig_for, parsed_args.wig_rev)
+ wig_opt_group = (parsed_args.wig, parsed_args.wig_for, parsed_args.wig_rev)
+
+ #############################
+ # Check wig and bam options #
+ #############################
+ if not any(input_opt_group):
+ raise argparse.ArgumentError(None, "At least one of these options must be specified"
+ " '--bam', '--wig' , '--wig-for', '--wig-rev'.")
+ elif all(input_opt_group):
+ raise argparse.ArgumentError(None,
+ "'--bam', '--wig' , '--wig-for', '--wig-rev' cannot specify at the same time.")
+ elif parsed_args.bam and any(wig_opt_group):
+ raise argparse.ArgumentError(None, "'--bam' option cannot be specified in the same time as"
+ " '--wig', '--wig-for' or '--wig-rev' options.")
+ elif parsed_args.wig and any((parsed_args.wig_for, parsed_args.wig_rev)):
+ raise argparse.ArgumentError(None, "'--wig' option cannot be specified in the same time as"
+ " '--wig-for' or '--wig-rev' options.")
+ ###########################
+ # Checking window options #
+ ###########################
+ group_one = (parsed_args.before, parsed_args.after, parsed_args.window)
+ group_two = (parsed_args.start_col, parsed_args.stop_col)
+ if all([v is None for v in itertools.chain(group_one, group_two)]):
+ raise argparse.ArgumentError(None, "[--window or [--before, --after] or [--start-col, --stop-col] options"
+ " must be specified")
+ elif any([v is not None for v in group_one]) and any([v is not None for v in group_two]):
+ raise argparse.ArgumentError(None, "Options [--before, --after, --window] and [--start-col, --stop-col] "
+ "are mutually exclusives.")
+ elif all([v is None for v in group_two]):
+ if parsed_args.window is None:
+ if any([v is None for v in (parsed_args.before, parsed_args.after)]):
+ raise argparse.ArgumentError(None, "The two options --after and --before work together."
+ " The both options must be specified in same time")
+ else:
+ pass
+ # window is None, before and after are specify
+ # => nothing to do
+ else:
+ # parsed_args.window is not None:
+ if any([v is not None for v in (parsed_args.before, parsed_args.after)]):
+ raise argparse.ArgumentError(None, "options [--before, --after] and --window are mutually exclusives.")
+ else:
+ # --before, --after are None
+ parsed_args.before = parsed_args.after = parsed_args.window
+ elif not all(group_two):
+ raise argparse.ArgumentError(None, "The two options --start-col and --stop-col work together. "
+ "The both options must be specified in same time")
+ return parsed_args
+
+
+def main(args=None, log_level=None):
+ """
+ The entrypoint for craw_coverage script
+ It will generate a coverage matrix around the position of interest
+ and write the results in files
+
+ :param args: the arguments and options given on the command line
+ :type args: list of string as given by sys.argv without the program name
+ :param log_level: the level of logger
+ :type log_level: positive int or logging flag logging.DEBUG, logging.INFO, logging.ERROR, logging.CRITICAL
+ """
+ args = sys.argv[1:] if args is None else args
+ parsed_args = parse_args(args)
+
+ if log_level is None:
+ verbosity = max(logging.INFO + (parsed_args.quiet - parsed_args.verbose) * 10, 1)
+ else:
+ verbosity = log_level
+ craw.init_logger(verbosity)
+
+ #######################
+ # Parsing input files #
+ #######################
+ with open(parsed_args.annot) as annot_file:
+ annot_line_number = sum(1 for _ in annot_file)
+ annot_parser = annotation.AnnotationParser(parsed_args.annot, parsed_args.ref_col,
+ chr_col=parsed_args.chr_col,
+ strand_col=parsed_args.strand_col,
+ start_col=parsed_args.start_col,
+ stop_col=parsed_args.stop_col,
+ sep=parsed_args.sep)
+
+ if parsed_args.bam:
+ # input_data is a samfile
+ input_file = parsed_args.bam
+ input_data = pysam.AlignmentFile(parsed_args.bam, "rb")
+ elif parsed_args.wig:
+ # input_data is a wig.Genome object
+ input_file = parsed_args.wig
+ wig_parser = WigParser(mixed_wig=parsed_args.wig)
+ input_data = wig_parser.parse()
+ else:
+ # input_data is a wig.Genome object
+ input_file = parsed_args.wig_for
+ wig_parser = WigParser(for_wig=parsed_args.wig_for, rev_wig=parsed_args.wig_rev)
+ input_data = wig_parser.parse()
+
+ annotations = annot_parser.get_annotations()
+
+ ############################
+ # checking outputs options #
+ ############################
+ if not parsed_args.output:
+ parsed_args.output = os.path.splitext(input_file)[0]
+ out_name = parsed_args.output
+ suffix = parsed_args.suffix
+ else:
+ out_name, suffix = os.path.splitext(parsed_args.output)
+ suffix = suffix.strip('.')
+ if not suffix:
+ suffix = parsed_args.suffix
+
+ sense_file, antisense_file = get_results_file(parsed_args.sense, out_name, suffix)
+
+ ###########################
+ # Computing output matrix #
+ ###########################
+ with sense_file, antisense_file:
+ header = get_result_header(annot_parser, parsed_args)
+
+ if parsed_args.sense in ('S', 'split', 'mixed'):
+ # if parsed_args.sense is mixed the sense_file and antisense_file are the same object
+ print(header, file=sense_file)
+ if parsed_args.sense in ('AS', 'split'):
+ print(header, file=antisense_file)
+
+ # get the appropriate function according to the input type
+ # the 2 functions
+ # - get_wig_coverage
+ # - get_bam_coverage
+ # have exactly the same api
+ if parsed_args.justify:
+ get_coverage = coverage.resized_coverage_maker(input_data, parsed_args.justify, qual_thr=None)
+ elif parsed_args.sum:
+ get_coverage = coverage.sum_coverage_maker(input_data, qual_thr=parsed_args.qual_thr)
+ else:
+ if parsed_args.window is not None:
+ max_left = max_right = parsed_args.window
+ elif parsed_args.before and parsed_args.after:
+ max_left = parsed_args.before
+ max_right = parsed_args.after
+ else:
+ max_left, max_right = annot_parser.max()
+ get_coverage = coverage.padded_coverage_maker(input_data, max_left, max_right, qual_thr=parsed_args.qual_thr)
+
+ for annot_num, annot_entry in enumerate(annotations, 1):
+ if verbosity <= logging.INFO:
+ progress(annot_num, annot_line_number)
+ if parsed_args.start_col:
+ # pos in get_coverage functions are
+ # 0 based whereas in annotation they are 1 based
+ # start is included, stop is excluded
+ start = annot_entry.start - 1
+ stop = annot_entry.stop
+ else:
+ if annot_entry.strand == '+':
+ start = annot_entry.ref - parsed_args.before - 1
+ stop = annot_entry.ref + parsed_args.after
+ else:
+ # if feature is on reverse strand
+ # the before and after are inverted
+ start = annot_entry.ref - parsed_args.after - 1
+ stop = annot_entry.ref + parsed_args.before
+ forward_cov, reverse_cov = get_coverage(annot_entry, start=start, stop=stop)
+
+ sens = 'S' if annot_entry.strand == '+' else 'AS'
+ if sens == 'S':
+ print(sens, annot_entry, *forward_cov, sep='\t', file=sense_file)
+ else:
+ print(sens, annot_entry, *forward_cov, sep='\t', file=antisense_file)
+
+ sens = 'S' if annot_entry.strand == '-' else 'AS'
+ if sens == 'S':
+ print(sens, annot_entry, *reverse_cov, sep='\t', file=sense_file)
+ else:
+ print(sens, annot_entry, *reverse_cov, sep='\t', file=antisense_file)
+
+ print(file=sys.stderr)
+
+
+if __name__ == '__main__':
+ main()
diff --git a/craw/scripts/craw_htmp.py b/craw/scripts/craw_htmp.py
new file mode 100755
index 0000000000000000000000000000000000000000..da602a51348e7e1b5b89a507dd60140247d87477
--- /dev/null
+++ b/craw/scripts/craw_htmp.py
@@ -0,0 +1,556 @@
+#! /usr/bin/env python3
+
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+import sys
+import os
+import argparse
+import logging
+
+import matplotlib as mtp
+import matplotlib.pyplot as plt
+
+import craw
+
+
+def _file_readable(value):
+ """
+ check value given by the parser
+
+ :param str value: the value given by the parser for --sort-using-file option
+ :return: the normpath of the value
+ :raises: ArgumentError if the file does not exists, or is not a file, or not readable
+ """
+ if not os.path.exists(value):
+ raise argparse.ArgumentError(None, "No such file: {}".format(value))
+ elif not os.path.isfile(value):
+ raise argparse.ArgumentError(None, "{} is not a regular file".format(value))
+ elif not os.access(value, os.R_OK):
+ raise argparse.ArgumentError(None, "{} is not readable".format(value))
+ return os.path.normpath(value)
+
+
+def _gene_size_parser(value):
+ """
+ Parse value given by the parser
+
+ :param value: the value given by the parser for --sort-by-gene-size option
+ :type value: string
+ :return: name of column representing the start of gene, name of the column representing the end of gene
+ :rtype: tuple of 2 string
+ :raise: :class:`argparse.ArgumentError` object if value cannot be parsed
+ """
+ # this function is called only if value is provided to sort-by-gene-size option
+ rv = value.split(',')
+ if len(rv) == 0:
+ rv = ['', '']
+ elif len(rv) == 2:
+ pass
+ else:
+ raise argparse.ArgumentError(None, "--sort-by-gene-size {} invalid value. "
+ "Must be start_col, stop_col (separated by a comma), "
+ "default= annotation_start,annotation_end".format(value)) from None
+ return rv
+
+
+def _size_fig_parser(value):
+ """
+ Parse value given by the parser for --size option
+ the value must follow the syntax widexheight[unit]
+ if the unit is omitted unit is inch
+ otherwise unit must be
+
+ * 'mm' for millimeters
+ * 'cm' for centimeters
+ * 'in' for inches
+ * 'px' for pixels
+
+ wide and height must be positive integers.
+
+ :param value: the size of the figure
+ :type value: string
+ :return: the size in inch ask by the user
+ :rtype: tuple of float
+ :raise: :class:`argparse.ArgumentError` object
+ """
+ def mm2in(value):
+ return value * (1 / 25.4)
+
+ def cm2in(value):
+ return mm2in(value * 10)
+
+ def px2in(value):
+ dpi = plt.rcParams['figure.dpi']
+ return value / dpi
+
+ err_msg = """--size {} invalid value.
+ The value must be widexheight[unit] or 'raw'.
+ 'wide' and 'height' must be positive integers
+ By default unit is in inches.
+ eg: 7x10 or 7x10in for 7 inches wide by 10 inches height
+ 70x100mm for 70 mm by 100 mm.
+ default=7x10 or 10x7 depending of the figure orientation."""
+ if value == 'raw':
+ return 'raw'
+ else:
+ unit = 'in'
+ if value[-2:] in ('mm', 'cm', 'in', 'px'):
+ unit = value[-2:]
+ value = value[:-2]
+ try:
+ wide, height = value.split('x')
+ except ValueError:
+ raise argparse.ArgumentError(None, err_msg.format(value))
+ try:
+ wide = int(wide)
+ height = int(height)
+ except ValueError:
+ raise argparse.ArgumentError(None, err_msg.format(value))
+ if wide < 0 or height < 0:
+ raise argparse.ArgumentError(None, err_msg.format(value))
+
+ if unit == 'mm':
+ wide = mm2in(wide)
+ height = mm2in(height)
+ elif unit == 'cm':
+ wide = cm2in(wide)
+ height = cm2in(height)
+ elif unit == 'px':
+ wide = px2in(wide)
+ height = px2in(height)
+
+ return wide, height
+
+
+def get_version_message():
+ """
+ :return: a human readable of craw_htmp version and it's main dependencies.
+ :rtype: str
+ """
+ # pyplot must be import after the argument parsing
+ # because in function of the environment ($DYSPLAY and options) the craw_htmp behavior
+ # is not the same
+ # so heatmap cannot be import before argument parsing
+ # so I import the dependencies in get_version_message.
+ # it's not very important as get_version_message is called only when --version is set
+ # so the program quit after displaying this message.
+ import numpy as np
+ import pandas as pd
+ import matplotlib as mtp
+ import PIL
+ version_text = craw.get_version_message()
+ version_text += """
+Using:
+ - numpy {np_ver}
+ - pandas {pd_ver}
+ - matplotlib {mtp_ver}
+ - pillow {pil_ver}
+""".format(np_ver=np.__version__,
+ pd_ver=pd.__version__,
+ mtp_ver=mtp.__version__,
+ pil_ver=PIL.PILLOW_VERSION
+ )
+ return version_text
+
+
+def parse_args(args):
+ """
+ :param args: the arguments and option as provided by sys.argv without the program name
+ :return: the argument parsed
+ :rtype: :class:`argparse.Namespace` object
+ """
+ parser = argparse.ArgumentParser(description="Compute a figure from a file of coverage compute by craw_coverage.py.",
+ formatter_class=argparse.RawTextHelpFormatter)
+
+ parser.add_argument(dest="cov_file",
+ help="the path to the coverage file.")
+
+ data_grp = parser.add_argument_group('optional data options')
+ data_grp.add_argument("--crop",
+ nargs=2,
+ help="""crop the matrix.
+ This option need two values the name of the first and last column to keep
+ [start col, stop col] eg --crop -10 1000 .""")
+
+ sort_grp = data_grp.add_mutually_exclusive_group()
+ sort_grp.add_argument("--sort-using-col",
+ default=False,
+ help="sort the rows using the column COL.")
+ sort_grp.add_argument("--sort-using-file",
+ type=_file_readable,
+ help="""Sort the rows using a file.
+ The file must have on the first line the name of the column
+ which will use to sort.
+ Each following lines must match to a value of this column in the data.""")
+ sort_grp.add_argument("--sort-by-gene-size",
+ type=_gene_size_parser,
+ nargs='*',
+ metavar='start_col,stop_col',
+ help="""The rows will be sorted by gene size
+ using start-col and stop-col to compute length.
+
+ start-col and stop-col must be a string separated by comma.
+ If start-col and stop-col are not specified annotation_start and annotation_end
+ for start-col and stop-col respectively will be used.
+ (Don't put this option without value just before the coverage file.)""")
+
+ matrix_grp = data_grp.add_mutually_exclusive_group()
+ matrix_grp.add_argument("--sense-only",
+ action="store_true",
+ default=False,
+ help="Display only sense matrix (default is display both).")
+ matrix_grp.add_argument("--antisense-only",
+ action="store_true",
+ default=False,
+ help="Display only anti sense matrix (default is display both).")
+
+ fig_grp = parser.add_argument_group("optional figure options")
+ fig_grp.add_argument("--cmap",
+ default="Blues",
+ help="""The color map used to display data.
+ The allowed values are defined in
+ http:matplotlib.org/examples/color/colormaps_reference.html
+ eg: Blues, BuGn, Greens, GnBu, ... (default: Blues).""")
+ fig_grp.add_argument("--title",
+ help="""The figure title.
+ It will display on the top of the figure.
+ (default: the name of the coverage file without extension).""")
+ fig_grp.add_argument("--dpi",
+ type=int,
+ help="""The resolution of the output .
+ This option work only if --out option is specified with size not raw.
+ (default: matplolibrc figure.dpi""")
+ fig_grp.add_argument("--size",
+ type=_size_fig_parser,
+ help="""Specify the figure size.
+ The value must be widexheight[unit] or 'raw'.
+
+ If value is raw it will be produce two image files (for sense and antisense) "
+ with one pixel correspond to one coverage value for one nucleotide.
+
+ Otherwise, 'wide' and 'height' must be positive integers
+ By default units are in inches eg:
+
+ * 7x10 or 7x10in for 7 inches wide by 10 inches height
+ * 70x100mm for 70 mm by 100 mm.
+
+ (default: 7x10 or 10x7 depending of the figure orientation).""")
+
+ fig_grp.add_argument("--norm",
+ choices=["lin", "log", "row", "log+row", "row+log"],
+ default="lin",
+ help="""Which normalization to apply to the data before display them.
+
+ * lin a linear normalization is applied on the whole matrix.
+ * log a 10 base logarithm will be applied on the data before matrix
+ normalization.
+ * row mean that a linear normalisation is compute row by row.
+ * log+row mean a 10 base logarithm will be applied before a normalisation
+ row by row. ('row+log' is an alias for 'log+row').
+ (default: lin""")
+
+ fig_grp.add_argument("--mark",
+ action='append',
+ nargs='*',
+ metavar='POS [COLOR]',
+ help="""* POS is mandatory and must be a positive integer.
+ * COLOR is optional
+ The supported color formats are:
+ - Hexadecimal color specifiers, given as '#rgb' or '#rrggbb'. For example, '#ff0000' specifies pure red.
+ - Common HTML color names.
+
+ If COLOR is omitted the color corresponding to the highest value in the color map (--cmap) will be used.
+ (this option cannot be the last one just before the coverage file, on the command line.)""")
+
+ layout = fig_grp.add_mutually_exclusive_group()
+ layout.add_argument("--sense-on-left",
+ action="store_true",
+ default=False,
+ help="Where to display the sense matrix relative to antisense matrix (default is top).")
+ layout.add_argument("--sense-on-right",
+ action="store_true",
+ default=False,
+ help="Where to display the sense matrix relative to antisense matrix (default is top).")
+ layout.add_argument("--sense-on-top",
+ action="store_true",
+ default=False,
+ help="Where to display the sense matrix relative to antisense matrix (default is top).")
+ layout.add_argument("--sense-on-bottom",
+ action="store_true",
+ default=False,
+ help="Where to display the sense matrix relative to antisense matrix (default is top).")
+
+ parser.add_argument("--out",
+ help="""The name of the file (the format will based on the extension)
+ to save the figure.
+ Instead of displaying the figure on the screen, save it directly in this file.
+
+ If this option is used with --size raw 2 files will be produced
+ for respectively sense and anti sense.
+ The extension 'sense' or 'antisense' will be added between the name and the suffix eg:
+ --size raw --out foo.png give 2 files 'foo.sense.png' and 'foo.antisense.png'.
+
+ If no format (determine using the suffix) is given 'png' will be used.""")
+
+ parser.add_argument("-v", "--verbose",
+ action='count',
+ default=0,
+ help="Increase output verbosity.")
+ parser.add_argument("-q", "--quiet",
+ action="count",
+ default=0,
+ help="Reduce output verbosity.")
+ parser.add_argument("--version",
+ action='version',
+ version=get_version_message(),
+ help="display the version information and quit.")
+ parsed_args = parser.parse_args(args)
+ return parsed_args
+
+
+def main(args=None, log_level=None, logger_out=True):
+ """
+ The entrypoint for craw_html script
+
+ It will generate a heatmap representing the coverage matrix around the position of interest
+ it can display the results on the screen or write it on file depending the options
+
+ :param args: The arguments and option representing the command line
+ :type args: list of string
+ :param log_level: the level of verbosity
+ :param logger_out: True if you want to display logs on stdout, False otherwise
+ :return:
+ """
+ args = sys.argv[1:] if args is None else args
+ parsed_args = parse_args(args)
+
+ verbosity = max(logging.INFO + (parsed_args.quiet - parsed_args.verbose) * 10, 1)
+ craw.init_logger(verbosity, out=logger_out)
+
+ log = logging.getLogger('craw.htmp')
+ log.debug("args={}".format(parsed_args))
+ ###########################
+ # validating some options #
+ ###########################
+ # test if DISPlAY
+ if not os.environ.get('DISPLAY'):
+ if parsed_args.out is not None:
+ _, out_format = os.path.splitext(parsed_args.out)
+ if not out_format:
+ raise RuntimeError("""
+ 'DISPLAY' variable is not set (you probably run craw_htmp in non graphic environment)
+ So you must specify an output format (add ext to the output file option as 'my_file.png')
+ """)
+ from craw.util import non_interactive_backends
+ try:
+ backend = non_interactive_backends[out_format.lstrip('.')]
+ except KeyError:
+ raise RuntimeError("The '{}' format is not supported, choose among {}.".format(
+ out_format,
+ list(non_interactive_backends.keys())
+ ))
+ mtp.use(backend)
+ else:
+ raise RuntimeError("""
+ 'DISPLAY' variable is not set (you probably run craw_htmp in non graphic environment)
+ So you cannot use interactive output
+ please specify an output file (--out).
+ """)
+
+ # the import of pyplot must be done after setting the backend
+ import matplotlib.pyplot as plt
+ from craw import heatmap
+
+ try:
+ color_map = plt.cm.get_cmap(parsed_args.cmap)
+ except(AttributeError, ValueError) as err:
+ raise RuntimeError("{} : http:matplotlib.org/examples/color/colormaps_reference.html for example".format(err))
+
+ if parsed_args.sort_by_gene_size == []:
+ parsed_args.sort_by_gene_size = ['annotation_start', 'annotation_end']
+ elif parsed_args.sort_by_gene_size:
+ parsed_args.sort_by_gene_size = parsed_args.sort_by_gene_size[0]
+
+ if parsed_args.out:
+ out_dir = os.path.dirname(parsed_args.out) or '.'
+ if not os.access(out_dir, os.W_OK):
+ msg = "{} is not writable".format(out_dir)
+ log.error(msg)
+ raise RuntimeError(msg)
+
+ log.info("Parsing coverage file")
+ data = heatmap.get_data(parsed_args.cov_file)
+
+
+ def mark_converter(data, marks):
+ converted_marks = []
+ for value in marks:
+ pos = int(value[0])
+ color = value[1] if len(value) == 2 else None
+ converted_marks.append(heatmap.Mark(pos, data, color_map, color=color))
+ return converted_marks
+
+ if parsed_args.mark is not None:
+ parsed_args.mark = mark_converter(data, parsed_args.mark)
+
+ sense_data, antisense_data = heatmap.split_data(data)
+
+ if parsed_args.sense_only:
+ antisense_data = None
+ if parsed_args.antisense_only:
+ sense_data = None
+
+ ################
+ # sorting data #
+ ################
+ # if data is empty or data is None sort return data
+ # so it's error safe, and not time and space consuming
+ if parsed_args.sort_by_gene_size:
+ start_col, stop_col = parsed_args.sort_by_gene_size
+ sense_data = heatmap.sort(sense_data, 'by_gene_size', start_col=start_col, stop_col=stop_col)
+ antisense_data = heatmap.sort(antisense_data, 'by_gene_size', start_col=start_col, stop_col=stop_col)
+ elif parsed_args.sort_using_col:
+ sense_data = heatmap.sort(sense_data, 'using_col', col=parsed_args.sort_using_col)
+ antisense = heatmap.sort(antisense_data, 'using_col', col=parsed_args.sort_using_col)
+ elif parsed_args.sort_using_file:
+ sense_data = heatmap.sort(sense_data, 'using_file', file=parsed_args.sort_using_file)
+ antisense_data = heatmap.sort(antisense_data, 'using_file', file=parsed_args.sort_using_file)
+
+ sense_data = heatmap.remove_metadata(sense_data)
+ antisense_data = heatmap.remove_metadata(antisense_data)
+
+ ################
+ # croping data #
+ ################
+ log.info("Croping matrix")
+ if parsed_args.crop:
+ start_col, stop_col = parsed_args.crop
+ sense_data = heatmap.crop_matrix(sense_data, start_col, stop_col)
+ antisense_data = heatmap.crop_matrix(antisense_data, start_col, stop_col)
+
+ ####################
+ # Normalizing data #
+ ####################
+ log.info("Normalizing data")
+
+ if parsed_args.norm == "lin":
+ log.info("Linear normalisation")
+ sense_data = heatmap.lin_norm(sense_data)
+ antisense_data = heatmap.lin_norm(antisense_data)
+ elif parsed_args.norm == 'log':
+ log.info("10 base logarithm normalisation")
+ sense_data = heatmap.log_norm(sense_data)
+ antisense_data = heatmap.log_norm(antisense_data)
+ elif parsed_args.norm == 'row':
+ log.info("Linear normalisation by row")
+ sense_data = heatmap.lin_norm_row_by_row(sense_data)
+ antisense_data = heatmap.lin_norm_row_by_row(antisense_data)
+ else:
+ # log+row or row+log
+ log.info("10 base logarithm and normalisation by row")
+ sense_data = heatmap.log_norm_row_by_row(sense_data)
+ antisense_data = heatmap.log_norm_row_by_row(antisense_data)
+
+ ##################
+ # Drawing figure #
+ ##################
+ log.info("Drawing figure")
+ if parsed_args.size == 'raw':
+ # pillow backend
+ if parsed_args.sense_only:
+ sense_to_compute = ('sense', )
+ elif parsed_args.antisense_only:
+ sense_to_compute = ('antisense', )
+ else:
+ sense_to_compute = ('sense', 'antisense')
+
+ if parsed_args.out:
+ root_name, im_format = os.path.splitext(parsed_args.out)
+ im_format = im_format.lstrip('.')
+ if not im_format:
+ im_format = 'png'
+ else:
+ im_format = 'png'
+ root_name = os.path.splitext(parsed_args.cov_file)[0]
+
+ out_filename = {}
+ for sense in sense_to_compute:
+ filename = "{filename}.{sense}.{format}".format(filename=root_name, sense=sense, format=im_format)
+ out_filename[sense] = filename
+ if os.path.exists(filename):
+ msg = "{} already exists".format(filename)
+ log.error(msg)
+ raise RuntimeError(msg)
+
+ for sense in sense_to_compute:
+ log.info("Drawing {}".format(sense))
+ data = locals()[sense + '_data']
+ if data is not None:
+ heatmap.draw_raw_image(data, out_filename[sense], color_map, marks=parsed_args.mark)
+ else:
+ log.warning("{} data are empty: skip drawing.".format(sense))
+ else:
+ # matplotlib backend
+ ##########
+ # layout #
+ ##########
+ if parsed_args.sense_on_left:
+ sense_on = 'left'
+ elif parsed_args.sense_on_right:
+ sense_on = 'right'
+ elif parsed_args.sense_on_top:
+ sense_on = 'top'
+ elif parsed_args.sense_on_bottom:
+ sense_on = 'bottom'
+ else:
+ sense_on = 'top'
+
+ if parsed_args.title is None:
+ title = os.path.basename(os.path.splitext(parsed_args.cov_file)[0])
+ else:
+ title = parsed_args.title
+
+ fig = heatmap.draw_heatmap(sense_data, antisense_data,
+ color_map=color_map,
+ title=title,
+ sense_on=sense_on,
+ size=parsed_args.size,
+ marks=parsed_args.mark)
+
+ if parsed_args.out:
+ if os.path.exists(parsed_args.out):
+ msg = "The output file: {} already exists.".format(parsed_args.out)
+ log.error(msg)
+ raise RuntimeError(msg)
+
+ if parsed_args.dpi:
+ fig.savefig(parsed_args.out, dpi=parsed_args.dpi)
+ fig.savefig(parsed_args.out)
+ else:
+ plt.show()
+
+
+if __name__ == '__name__':
+ main()
diff --git a/craw/wig.py b/craw/wig.py
index bcc272df5774855dad3f9eee73ca7a25ade5e515..27ce458f278686b336ce5d08e684c6ac75c2f5ad 100644
--- a/craw/wig.py
+++ b/craw/wig.py
@@ -3,7 +3,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright (c) 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
diff --git a/doc/source/craw_coverage.rst b/doc/source/craw_coverage.rst
new file mode 100644
index 0000000000000000000000000000000000000000..3ab79b42f45a48d629968b11dc2ef2e672bc43cf
--- /dev/null
+++ b/doc/source/craw_coverage.rst
@@ -0,0 +1,14 @@
+.. _craw_coverage:
+
+=============
+craw_coverage
+=============
+
+
+`craw_coverage.py` is the entry point script to compute coverage.
+
+.. automodule:: craw.scripts.craw_coverage
+ :members:
+ :private-members:
+ :special-members:
+
diff --git a/doc/source/craw_htmp.rst b/doc/source/craw_htmp.rst
new file mode 100644
index 0000000000000000000000000000000000000000..7f4a22ee46b88f6e81c1c0fe0e8d37536ca62207
--- /dev/null
+++ b/doc/source/craw_htmp.rst
@@ -0,0 +1,14 @@
+.. _craw_htmp:
+
+=========
+craw_htmp
+=========
+
+
+`craw_htmp.py` is the entry point script to compute heatmap.
+
+.. automodule:: craw.scripts.craw_htmp
+ :members:
+ :private-members:
+ :special-members:
+
diff --git a/doc/source/index.rst b/doc/source/index.rst
index 4e6ee288b690f42190dd38204a0049220dfa4781..8eb3bb89e081d73908a812ebd57d042fe240ce30 100644
--- a/doc/source/index.rst
+++ b/doc/source/index.rst
@@ -46,6 +46,8 @@ reference API
coverage
heatmap
argparse_util
+ craw_coverage
+ craw_htmp
.. only:: html
diff --git a/doc/source/installation.rst b/doc/source/installation.rst
index 6b8a6b0874c2db7981c9156d4ba4ff0dcd06d8f7..ccf18f2547eaef416ea05ae3c09e50362bb3ab97 100644
--- a/doc/source/installation.rst
+++ b/doc/source/installation.rst
@@ -17,12 +17,13 @@ For craw_coverage
For craw_htmp
-------------
- - python > 3
- - pysam >= 0.9.1.4
- - pandas >= 0.17.1
- - numpy >= 1.11.2
- - matplotlib >= 1.5.3
- - pillow >= 3.4.2
+ - python >= 3.5
+ - pysam == 0.15.2
+ - pandas >= 0.24
+ - numpy >= 1.16
+ - matplotlib >= 3.0
+ - pillow >= 5.4
+ - scipy >= 0.16.1
Installation
@@ -61,7 +62,7 @@ Clone the project and install with the setup.py ::
git clone https://gitlab.pasteur.fr/bneron/craw.git
cd craw
- python3 setup.py install
+ pip install .
.. note::
Instead of installing craw you can directly use the scripts from the repository.
diff --git a/doc/source/overview.rst b/doc/source/overview.rst
index 309f8dd7f8186fd6d4f5f36a230acef43dd7d984..57847b5f46ac1b0a289a6ec9cc2094976da66f03 100644
--- a/doc/source/overview.rst
+++ b/doc/source/overview.rst
@@ -93,6 +93,6 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU General Public License for more details.
-Authors: Bertrand Néron
-Copyright © 2017 Institut Pasteur (Paris).
+Authors: Bertrand Neron
+Copyright © 2017-2019 Institut Pasteur (Paris).
see COPYRIGHT file for details.
diff --git a/requirements.txt b/requirements.txt
index 833198647c04bb7cb1d21e60b9c752e1c6d82753..51d2d8dec1292ff5e78b6c23b3ac8eb9fce6ee53 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,7 @@
-# integron_finder requirements are specified in setup.py
-
---index-url https://pypi.python.org/simple/
-
--e .
\ No newline at end of file
+pysam==0.15.2
+matplotlib>=3.0
+pandas>=0.24
+numpy>=1.16
+pillow>=5.4
+psutil>=5.6
+scipy>=0.16.1
\ No newline at end of file
diff --git a/requirements_dev.txt b/requirements_dev.txt
new file mode 100644
index 0000000000000000000000000000000000000000..9cfac1170c84f44ea3b9f438d63700b132fc6593
--- /dev/null
+++ b/requirements_dev.txt
@@ -0,0 +1,3 @@
+sphinx
+sphinx_rtd_theme
+coverage
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 22ee7f538492b00d9d0e0b29444387ac3c2a3d33..4d0616f5384b2cb293c354328bae9b98446dbdcf 100644
--- a/setup.py
+++ b/setup.py
@@ -5,7 +5,7 @@
# This file is part of Counter RNAseq Window (craw) package. #
# #
# Authors: Bertrand Neron #
-# Copyright c 2017 Institut Pasteur (Paris). #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -24,73 +24,13 @@
# #
###########################################################################
-
-import sys
-if sys.version_info[0] == 2:
- sys.exit("Sorry, Python 2 is not supported")
-
import os
-import time
import sysconfig
-from distutils.errors import DistutilsFileError
-from distutils.util import subst_vars as distutils_subst_vars
-
-from setuptools import setup
+from setuptools import setup, find_packages
from setuptools.dist import Distribution
-from setuptools.command.install_scripts import install_scripts as _install_scripts
-from setuptools.command.install_lib import install_lib as _install_lib
-
-
-
-class install_lib(_install_lib):
-
- def finalize_options(self):
- _install_lib.finalize_options(self)
-
- def run(self):
- def subst_file(_file, vars_2_subst):
- input_file = os.path.join(self.build_dir, _file)
- output_file = input_file + '.tmp'
- subst_vars(input_file, output_file, vars_2_subst)
- os.unlink(input_file)
- self.move_file(output_file, input_file)
-
- inst = self.distribution.command_options.get('install')
- if inst:
- if self.distribution.fix_lib is not None:
- vars_2_subst = {'PREFIX': inst['prefix'][1] if 'prefix' in inst else '',
- 'VERSION': self.distribution.get_version()
- }
- for _file in self.distribution.fix_lib:
- subst_file(_file, vars_2_subst)
- _install_lib.run(self)
-
-class install_scripts(_install_scripts):
-
- def finalize_options(self):
- inst = self.distribution.command_options.get('install')
- inst = {} if inst is None else inst
- _install_scripts.finalize_options(self)
-
- def run(self):
- def subst_file(_file, vars_2_subst):
- input_file = os.path.join(self.build_dir, _file)
- output_file = input_file + '.tmp'
- subst_vars(input_file, output_file, vars_2_subst)
- os.unlink(input_file)
- self.move_file(output_file, input_file)
-
- inst = self.distribution.command_options.get('install')
- inst = {} if inst is None else inst
- if self.distribution.fix_scripts is not None:
- vars_2_subst = {'PREFIX': inst['prefix'][1] if 'prefix' in inst else '',
- 'PREFIXDATA': os.path.join(get_install_data_dir(inst), 'craw'),
- }
- for _file in self.distribution.fix_scripts:
- subst_file(_file, vars_2_subst)
- _install_scripts.run(self)
+from craw import __version__ as cr_vers
class UsageDistribution(Distribution):
@@ -99,13 +39,13 @@ class UsageDistribution(Distribution):
# It's important to define options before to call __init__
# otherwise AttributeError: UsageDistribution instance has no attribute 'conf_files'
self.fix_lib = None
- self.fix_scripts = None
Distribution.__init__(self, attrs=attrs)
self.common_usage = """\
Common commands: (see '--help-commands' for more)
setup.py build will build the package underneath 'build/'
setup.py install will install the package
+ setup.py test run tests after in-place build
"""
@@ -138,30 +78,6 @@ def get_install_data_dir(inst):
return install_dir
-def subst_vars(src, dst, vars):
- """
- substitute variables (string starting with $) in file
- :param src: the file containing variable to substitute
- :type src: string
- :param dst: the destination file
- :type dst: string
- :param vars: the variables to substitute in dict key are variable name
- :type vars: dict
- """
- try:
- src_file = open(src, "r")
- except os.error as err:
- raise DistutilsFileError("could not open '{0}': {1}".format(src, err))
- try:
- dest_file = open(dst, "w")
- except os.error as err:
- raise DistutilsFileError("could not create '{0}': {1}".format(dst, err))
- with src_file, dest_file:
- for line in src_file:
- new_line = distutils_subst_vars(line, vars)
- dest_file.write(new_line)
-
-
def expand_data(data_to_expand):
"""
From data structure like setup.py data_files (see http://)
@@ -199,18 +115,12 @@ def expand_data(data_to_expand):
data_struct.append((base_dest_dir, [one_src]))
return data_struct
-try:
- from pypandoc import convert
- def read_md(f):
- return convert(f, 'rst')
-except ImportError:
- print("warning: pypandoc module not found, "
- "could not convert Markdown to RST")
- def read_md(f): return open(f, 'r').read()
+def read_md(f): return open(f, 'r').read()
+
setup(name="craw",
- version='branch1.0.dev{}'.format(time.strftime('%Y%m%d')),
+ version=cr_vers,
author='Bertrand Neron',
author_email='bneron@pasteur.fr',
url="https://gitlab.pasteur.fr/bneron/craw",
@@ -221,29 +131,27 @@ setup(name="craw",
'Intended Audience :: Science/Research',
'Operating System :: Unix',
'Programming Language :: Python :: 3 :: Only',
- 'Topic :: Scientific/Engineering :: Bio-Informatics'
+ 'Topic :: Scientific/Engineering :: Bio-Informatics',
+ 'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
],
- description="Counter RNA seq Window is a package which aim to compute and visualize the coverage of RNA seq experiment.",
- # gitlab and github use md format for README whereas pypi use restructuredtext
- # so to display correctly the readme on the pypi page we need
- # to convert md -> rst using pandoc/pypandoc
+ description="Counter RNA seq Window is a package which aim to compute and "
+ "visualize the coverage of RNA seq experiment.",
long_description=read_md('README.md'),
+ long_description_content_type='text/markdown',
platforms=["Unix"],
- install_requires=['pysam>=0.9.1.4', 'matplotlib>=1.5.3', 'pandas>=0.17.1', 'numpy>=1.11.2', 'pillow>=3.4.2',
- 'psutil>=4.0.0', 'scipy>=0.16.1'],
- packages=['craw'],
- scripts=['bin/craw_coverage', 'bin/craw_htmp'],
+ python_requires='>=3.5',
+ install_requires=open("requirements.txt").read().split(),
+ extras_require={'dev': open("requirements_dev.txt").read().split()},
+ packages=find_packages(),
+ entry_points={
+ 'console_scripts': [
+ 'craw_coverage=craw.scripts.craw_coverage:main',
+ 'craw_htmp=craw.scripts.craw_htmp:main',
+ ]
+ },
data_files=expand_data([('share/craw/doc/html', ['doc/build/html/']),
('share/craw/doc/pdf/', ['doc/build/latex/CounterRNAseqWindow.pdf'])]),
- # library file where some variable must be fix by install_lib
- fix_lib=['craw/__init__.py'],
- # scripts file where some variable must be fix by install_scripts
- fix_scripts=['craw_coverage'],
-
- cmdclass={'install_lib': install_lib,
- 'install_scripts': install_scripts,
- },
distclass=UsageDistribution
)
diff --git a/singularity/Singularity b/singularity/Singularity
new file mode 100644
index 0000000000000000000000000000000000000000..f5620ce4e34e831798d58d4ba48850b8def563f4
--- /dev/null
+++ b/singularity/Singularity
@@ -0,0 +1,74 @@
+Bootstrap: docker
+from: ubuntu:bionic
+
+
+%labels
+ maintainer Bertrand Neron <bneron@pasteur.fr>
+ package.name craw
+ package.version latest
+ package.homepage https://gitlab.pasteur.fr/bneron/craw
+ package.license GPLv3
+
+%post
+ ####################################
+ # Installing system #
+ ####################################
+
+ apt-get update -y
+ apt-get install -y --no-install-recommends python3 python3-tk
+ apt-get install -y git
+ apt-get install -y python3-pip
+
+ #################################
+ # installing craw #
+ #################################
+ cd /
+ CRAW_VERS="1.0.2"
+ git clone https://gitlab.pasteur.fr/bneron/craw/
+ cd craw
+ pip3 install .
+
+ mkdir /craw
+ mv tests /craw/
+
+ #################################
+ # cleaning image #
+ #################################
+ cd /
+ rm -Rf craw
+ apt-get purge -y git
+ apt-get autoremove -y
+ apt-get clean -y
+
+%test
+ /usr/bin/python3 /craw/tests/run_tests.py -vv
+
+%help
+ This singularity image contains the "Counter RNAseq Window (CRAW) package.
+ Two commands are available \"coverage\" and \"htmp\.
+ To run command:
+ ./craw.img [coverage|htmp] [options]... [args]... .
+
+ To get help about each command ./craw.img [coverage|htmp] --help.
+ The detailed documentation is accessible here: http://bneron.pages.pasteur.fr/craw/
+
+%runscript
+
+# the following syntax allow to get the command and args
+# in POSIX manner so compliant with dash which
+# is the debian/ubuntu /bin/sh shell
+
+CMD="$1"
+shift
+ARGS=${@}
+
+case ${CMD} in
+ coverage )
+ exec /usr/local/bin/craw_coverage ${ARGS} ;;
+ htmp )
+ exec /usr/local/bin/craw_htmp ${ARGS} ;;
+ * )
+ echo "command \"${CMD}\" is not supported. available commands: \"coverage\"|\"htmp\""
+ exit 127
+ ;;
+esac
diff --git a/tests/__init__.py b/tests/__init__.py
index 29ccf1e1aa727257778b8c3839ef6fcdd4343e9e..1863f47cb1cbc87305cf2b3fb001d38e6f1c56f3 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -1,6 +1,34 @@
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+import logging
import os.path
import unittest
import platform
+from contextlib import contextmanager
+from io import StringIO
+
import numpy as np
from PIL import ImageChops
@@ -39,6 +67,17 @@ class CRAWTest(unittest.TestCase):
msg = self._formatMessage(msg, 'image 1 != image 2 within {} delta'.format(delta))
raise self.failureException(msg)
+ @contextmanager
+ def catch_log(self):
+ logger = logging.getLogger('craw')
+ handlers_ori = logger.handlers
+ fake_handler = logging.StreamHandler(StringIO())
+ try:
+ logger.handlers = [fake_handler]
+ yield LoggerWrapper(logger)
+ finally:
+ logger.handlers = handlers_ori
+
def which(name, flags=os.X_OK):
"""
@@ -63,3 +102,16 @@ def which(name, flags=os.X_OK):
result = p
break
return result
+
+
+class LoggerWrapper(object):
+
+ def __init__(self, logger):
+ self.logger = logger
+
+ def __getattr__(self, item):
+ return getattr(self.logger, item)
+
+ def get_value(self):
+ return self.logger.handlers[0].stream.getvalue()
+
diff --git a/tests/data/4_htmp.antisense.png b/tests/data/4_htmp.antisense.png
new file mode 100644
index 0000000000000000000000000000000000000000..ccdd95123bd88b412317946feba3e92a50b61ca3
Binary files /dev/null and b/tests/data/4_htmp.antisense.png differ
diff --git a/tests/data/4_htmp.sense.png b/tests/data/4_htmp.sense.png
new file mode 100644
index 0000000000000000000000000000000000000000..bc226115c9664e1e97dac0a130bd8f92b0df22c4
Binary files /dev/null and b/tests/data/4_htmp.sense.png differ
diff --git a/tests/data/4_htmp_sorting_file.txt b/tests/data/4_htmp_sorting_file.txt
new file mode 100644
index 0000000000000000000000000000000000000000..64a061f4694101c4ab98af74966e94f3f08da2e1
--- /dev/null
+++ b/tests/data/4_htmp_sorting_file.txt
@@ -0,0 +1,9 @@
+name
+YPR036W
+YEL043W
+snR67
+YEL071W
+YEL072W
+
+
+
diff --git a/tests/data/htmp_raw_lin+row.antisense.png b/tests/data/htmp_raw_lin+row.antisense.png
new file mode 100644
index 0000000000000000000000000000000000000000..ccdd95123bd88b412317946feba3e92a50b61ca3
Binary files /dev/null and b/tests/data/htmp_raw_lin+row.antisense.png differ
diff --git a/tests/data/htmp_raw_lin+row.sense.png b/tests/data/htmp_raw_lin+row.sense.png
new file mode 100644
index 0000000000000000000000000000000000000000..bc226115c9664e1e97dac0a130bd8f92b0df22c4
Binary files /dev/null and b/tests/data/htmp_raw_lin+row.sense.png differ
diff --git a/tests/data/htmp_raw_lin_crop.antisense.png b/tests/data/htmp_raw_lin_crop.antisense.png
new file mode 100644
index 0000000000000000000000000000000000000000..dd084f8ed123f0f63a917a5ad5b977d3913e61ac
Binary files /dev/null and b/tests/data/htmp_raw_lin_crop.antisense.png differ
diff --git a/tests/data/htmp_raw_lin_crop.sense.png b/tests/data/htmp_raw_lin_crop.sense.png
new file mode 100644
index 0000000000000000000000000000000000000000..95e02db22b9c881492f19c01be900333e7011ef7
Binary files /dev/null and b/tests/data/htmp_raw_lin_crop.sense.png differ
diff --git a/tests/data/htmp_raw_lin_sort_file.antisense.png b/tests/data/htmp_raw_lin_sort_file.antisense.png
new file mode 100644
index 0000000000000000000000000000000000000000..4158ecbae65eb42f5d03823919878c8afd39d6d6
Binary files /dev/null and b/tests/data/htmp_raw_lin_sort_file.antisense.png differ
diff --git a/tests/data/htmp_raw_lin_sort_file.sense.png b/tests/data/htmp_raw_lin_sort_file.sense.png
new file mode 100644
index 0000000000000000000000000000000000000000..293c2e9d7e1fd90672aa86454e384b30e5d6617d
Binary files /dev/null and b/tests/data/htmp_raw_lin_sort_file.sense.png differ
diff --git a/tests/data/htmp_raw_log_marks.antisense.png b/tests/data/htmp_raw_log_marks.antisense.png
new file mode 100644
index 0000000000000000000000000000000000000000..d7afb34596f70a6801f1f129a40d3292d24c8913
Binary files /dev/null and b/tests/data/htmp_raw_log_marks.antisense.png differ
diff --git a/tests/data/htmp_raw_log_marks.sense.png b/tests/data/htmp_raw_log_marks.sense.png
new file mode 100644
index 0000000000000000000000000000000000000000..fc1dca5da515fccc85bb1570bf0d16b0f66b59c1
Binary files /dev/null and b/tests/data/htmp_raw_log_marks.sense.png differ
diff --git a/tests/data/small.cov b/tests/data/small.cov
index 41600ffb51030b5491bcefe5f925ff14afc0a631..55842ba1162ed5fe5008465d1ebc6504410128b2 100644
--- a/tests/data/small.cov
+++ b/tests/data/small.cov
@@ -1,17 +1,17 @@
# Running Counter RnAseq Window craw_coverage
#
-# Version: craw NOT packaged, it should be a development version | Python 3.4
+# Version: craw NOT packaged, it should be a development version | Python 3.7
# Using:
-# - pysam 0.9.1.4 (samtools 1.3.1)
-# - scipy 0.18.1 (only for --justify opt)
+# - pysam 0.15.2 (samtools 1.9)
+# - scipy 1.2.1 (only for --justify opt)
#
# craw_coverage run with the following arguments:
# --after=3
-# --annot=/home/bneron/Projects/gwenael/src/tests/data/annotation_wo_start.txt
-# --bam=/home/bneron/Projects/gwenael/src/tests/data/small.bam
+# --annot=tests/data/annotation_wo_start.txt
+# --bam=tests/data/small.bam
# --before=5
# --chr-col=chromosome
-# --output=/tmp/craw_test/small.cov
+# --output=tests/data/small
# --qual-thr=0
# --quiet=1
# --ref-col=Position
diff --git a/tests/functional/__init__.py b/tests/functional/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/tests/functional/test_craw_coverage.py b/tests/functional/test_craw_coverage.py
deleted file mode 100644
index f3cb46499f459392ad0e94381da27f352b0b43ce..0000000000000000000000000000000000000000
--- a/tests/functional/test_craw_coverage.py
+++ /dev/null
@@ -1,854 +0,0 @@
-###########################################################################
-# #
-# This file is part of Counter RNAseq Window (craw) package. #
-# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
-# see COPYRIGHT file for details. #
-# #
-# craw is free software: you can redistribute it and/or modify #
-# it under the terms of the GNU General Public License as published by #
-# the Free Software Foundation, either version 3 of the License, or #
-# (at your option) any later version. #
-# #
-# craw is distributed in the hope that it will be useful, #
-# but WITHOUT ANY WARRANTY; without even the implied warranty of #
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
-# See the GNU General Public License for more details. #
-# #
-# You should have received a copy of the GNU General Public License #
-# along with craw (see COPYING file). #
-# If not, see <http://www.gnu.org/licenses/>. #
-# #
-###########################################################################
-
-import shutil
-import tempfile
-import os
-from subprocess import Popen, PIPE
-from itertools import zip_longest
-
-from tests import CRAWTest, which
-
-
-class Test(CRAWTest):
-
- def setUp(self):
- if 'CRAW_HOME' in os.environ:
- self.craw_home = os.environ['CRAW_HOME']
- self.local_install = True
- else:
- self.local_install = False
- self.craw_home = os.path.normpath(os.path.abspath(os.path.join(os.path.dirname(__file__), '..' '..')))
- self.tmp_dir = tempfile.gettempdir()
- self.bin = os.path.join(self.craw_home, 'bin', 'craw_coverage') if self.local_install else which('craw_coverage')
-
-
- def tearDown(self):
- try:
- shutil.rmtree(self.out_dir)
- pass
- except:
- pass
-
-
- def test_bam_with_fixed_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'small.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --bam={bam_file} --annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- bam_file=os.path.join(self._data_dir, 'small.bam'),
- annot_file=os.path.join(self._data_dir, 'annotation_wo_start.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_bam_with_chr_strand_col(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'coverage_fix_window_chr_strand_col.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --bam={bam_file} --annot={annot_file} " \
- "--chr-col={chr_col} " \
- "--strand-col={strand_col} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- bam_file=os.path.join(self._data_dir, 'small.bam'),
- annot_file=os.path.join(self._data_dir, 'annotation_wo_start_chr_strand_col.txt'),
- ref_col='Position',
- chr_col='chr',
- strand_col='brin',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_bam_with_var_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'coverage_var_window.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --bam={bam_file} --annot={annot_file} " \
- "--ref-col={ref_col} " \
- "--start-col={start_col} " \
- "--stop-col={stop_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- bam_file=os.path.join(self._data_dir, 'small.bam'),
- annot_file=os.path.join(self._data_dir, 'annotation_w_start.txt'),
- ref_col='Position',
- start_col='beg',
- stop_col='end',
- qual=15,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_wig_with_fixed_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_fixed_window.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig={wig_file} --annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_file=os.path.join(self._data_dir, 'small_fixed.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_wig_with_var_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_var_window.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig={wig_file} --annot={annot_file} " \
- "--ref-col={ref_col} " \
- "--start-col={start_col} " \
- "--stop-col={stop_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
- ref_col='Position',
- start_col='beg',
- stop_col='end',
- qual=15,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_2wig_with_fixed_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_splited_fixed_window.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig-for={wig_for} --wig-rev={wig_rev} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_for=os.path.join(self._data_dir, 'small_fixed.wig'),
- wig_rev=os.path.join(self._data_dir, 'small_fixed_reverse.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_only_forward_wig(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_only_forward.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig-for={wig_for} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_for=os.path.join(self._data_dir, 'small_fixed.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_only_reverse_wig(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_only_reverse.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig-rev={wig_rev} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_rev=os.path.join(self._data_dir, 'small_fixed_reverse.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_forward_n_mixed_wig(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_only_forward.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig={wig_file} " \
- "--wig-for={wig_for} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
- wig_for=os.path.join(self._data_dir, 'small_fixed.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 1)
- last_line = cov_process.stderr.readlines()[-1].decode('utf-8')
- self.assertEqual(last_line,
- "argparse.ArgumentError: '--wig' option cannot be specified in the same time as '--wig-for' or '--wig-rev' options.\n")
-
-
- def test_bam_n_wig(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_only_forward.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} " \
- "--bam={bam_file} " \
- "--wig={wig_file} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- bam_file=os.path.join(self._data_dir, 'small.bam'),
- wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 1)
- last_line = cov_process.stderr.readlines()[-1].decode('utf-8')
- self.assertEqual(last_line,
- "argparse.ArgumentError: '--bam' option cannot be specified in the same time as '--wig', '--wig-for' or '--wig-rev' options.\n")
-
- def test_no_input_file(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_only_forward.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} " \
- "--annot={annot_file} " \
- "--before={before} " \
- "--after={after} " \
- "--ref-col={ref_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} ".format(
- bin=self.bin,
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
- ref_col='Position',
- before=5,
- after=3,
- qual=0,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 1)
- last_line = cov_process.stderr.readlines()[-1].decode('utf-8')
- self.assertEqual(last_line,
- "argparse.ArgumentError: At least one of these options must be specified '--bam', '--wig' , '--wig-for', '--wig-rev'.\n")
-
-
- def test_resized_var_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_var_window_justify.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig={wig_file} --annot={annot_file} " \
- "--ref-col={ref_col} " \
- "--start-col={start_col} " \
- "--stop-col={stop_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} " \
- "--justify 10".format(
- bin=self.bin,
- wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
- ref_col='Position',
- start_col='beg',
- stop_col='end',
- qual=15,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
- def test_sum_var_window(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'wig_var_window_sum.cov'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} --wig={wig_file} --annot={annot_file} " \
- "--ref-col={ref_col} " \
- "--start-col={start_col} " \
- "--stop-col={stop_col} " \
- "--qual-thr={qual} " \
- "--quiet " \
- "--output={out_file} " \
- "--sum".format(
- bin=self.bin,
- wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
- annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
- ref_col='Position',
- start_col='beg',
- stop_col='end',
- qual=15,
- out_file=test_result_path
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "coverage execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "coverage finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
-
- expected_result_path = os.path.join(self._data_dir, output_filename)
- with open(expected_result_path) as expected_result_file:
- expected_result = expected_result_file.readlines()
-
- with open(test_result_path) as test_result_file:
- test_result = test_result_file.readlines()
-
- self._check_coverage_file(expected_result, test_result)
-
-
-
- def _check_coverage_file(self, expected_result, test_result):
- for expected, result in zip_longest(expected_result, test_result, fillvalue=''):
- if expected.startswith("# Version:"):
- continue
- elif expected.startswith("# - pysam"):
- continue
- elif expected.startswith("# - scipy"):
- continue
- elif expected.startswith("# --annot="):
- continue
- elif expected.startswith("# --bam="):
- continue
- elif expected.startswith("# --wig="):
- continue
- elif expected.startswith("# --wig-for="):
- continue
- elif expected.startswith("# --wig-rev="):
- continue
- elif expected.startswith("# --output="):
- continue
- else:
- self.assertEqual(expected, result)
-
diff --git a/tests/functional/test_craw_htmp.py b/tests/functional/test_craw_htmp.py
deleted file mode 100644
index 32ed22cad099f5618f25850fb4c3a1de9c44c48d..0000000000000000000000000000000000000000
--- a/tests/functional/test_craw_htmp.py
+++ /dev/null
@@ -1,221 +0,0 @@
-###########################################################################
-# #
-# This file is part of Counter RNAseq Window (craw) package. #
-# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
-# see COPYRIGHT file for details. #
-# #
-# craw is free software: you can redistribute it and/or modify #
-# it under the terms of the GNU General Public License as published by #
-# the Free Software Foundation, either version 3 of the License, or #
-# (at your option) any later version. #
-# #
-# craw is distributed in the hope that it will be useful, #
-# but WITHOUT ANY WARRANTY; without even the implied warranty of #
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
-# See the GNU General Public License for more details. #
-# #
-# You should have received a copy of the GNU General Public License #
-# along with craw (see COPYING file). #
-# If not, see <http://www.gnu.org/licenses/>. #
-# #
-###########################################################################
-
-import shutil
-import tempfile
-import os
-from subprocess import Popen, PIPE
-from PIL import Image
-
-from tests import CRAWTest, which
-
-
-class Test(CRAWTest):
-
- def setUp(self):
- if 'CRAW_HOME' in os.environ:
- self.craw_home = os.environ['CRAW_HOME']
- self.local_install = True
- else:
- self.local_install = False
- self.craw_home = os.path.normpath(os.path.abspath(os.path.join(os.path.dirname(__file__), '..' '..')))
- self.tmp_dir = tempfile.gettempdir()
- self.bin = os.path.join(self.craw_home, 'bin', 'craw_htmp') if self.local_install else which('craw_htmp')
-
-
- def tearDown(self):
- try:
- shutil.rmtree(self.out_dir)
- except:
- pass
-
-
- def test_raw(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'htmp_raw_lin.png'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} " \
- "--size {size} " \
- "--out={out_file} " \
- "--quiet " \
- "{cov_file}".format(
- bin=self.bin,
- size='raw',
- out_file=test_result_path,
- cov_file=os.path.join(self._data_dir, '4_htmp.cov')
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "craw_htmp execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "craw_htmp finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
- for sense in ('sense', 'antisense'):
- filename, suffix = os.path.splitext(output_filename)
- filename = "{}.{}{}".format(filename, sense, suffix)
- expected_result_path = os.path.join(self._data_dir, filename)
- expected_img = Image.open(expected_result_path)
- result_path, suffix = os.path.splitext(test_result_path)
- result_path = "{}.{}{}".format(result_path, sense, suffix)
- result_img = Image.open(result_path)
- self.assertImageAlmostEqual(expected_img, result_img)
-
-
- def test_raw_log(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'htmp_raw_log.png'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} " \
- "--size {size} " \
- "--norm {norm} " \
- "--out={out_file} " \
- "--quiet " \
- "{cov_file}".format(
- bin=self.bin,
- size='raw',
- norm='log',
- out_file=test_result_path,
- cov_file=os.path.join(self._data_dir, '4_htmp.cov')
- )
- ##print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "craw_htmp execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "craw_htmp finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
- for sense in ('sense', 'antisense'):
- filename, suffix = os.path.splitext(output_filename)
- filename = "{}.{}{}".format(filename, sense, suffix)
- expected_result_path = os.path.join(self._data_dir, filename)
- result_path, suffix = os.path.splitext(test_result_path)
- result_path = "{}.{}{}".format(result_path, sense, suffix)
- expected_img = Image.open(expected_result_path)
- result_img = Image.open(result_path)
- self.assertImageAlmostEqual(expected_img, result_img, delta=1.0, msg=sense)
-
-
- def test_raw_log_row(self):
- """
- | test if returncode of coverage is 0 and
- | then test if the generated file is the same as a reference file
- """
- self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
- os.makedirs(self.out_dir)
- output_filename = 'htmp_raw_log+row.png'
- test_result_path = os.path.join(self.out_dir, output_filename)
- command = "{bin} " \
- "--size {size} " \
- "--norm {norm} " \
- "--out={out_file} " \
- "--quiet " \
- "{cov_file}".format(
- bin=self.bin,
- size='raw',
- norm='log+row',
- out_file=test_result_path,
- cov_file=os.path.join(self._data_dir, '4_htmp.cov')
- )
- # print("\n@@@", command)
- if not self.bin:
- raise RuntimeError('coverage not found, CRAW_HOME must be either in your path or CRAW_HOME must be defined '
- 'command launch: \n{}'.format(command))
-
- try:
- cov_process = Popen(command,
- shell=True,
- stdin=None,
- stderr=PIPE,
- close_fds=False
- )
- except Exception as err:
- msg = "craw_htmp execution failed: command = {0} : {1}".format(command, err)
- print()
- print(msg)
- raise err from None
-
- cov_process.wait()
- self.assertEqual(cov_process.returncode, 0,
- "craw_htmp finished with non zero exit code: {0} command launched=\n{1}\n{2}".format(
- cov_process.returncode,
- command,
- ''.join([l.decode('utf-8') for l in cov_process.stderr.readlines()]),
- ))
- for sense in ('sense', 'antisense'):
- filename, suffix = os.path.splitext(output_filename)
- filename = "{}.{}{}".format(filename, sense, suffix)
- expected_result_path = os.path.join(self._data_dir, filename)
- result_path, suffix = os.path.splitext(test_result_path)
- result_path = "{}.{}{}".format(result_path, sense, suffix)
- expected_img = Image.open(expected_result_path)
- result_img = Image.open(result_path)
- self.assertImageAlmostEqual(expected_img, result_img)
-
diff --git a/tests/run_tests.py b/tests/run_tests.py
index f65568920eab7af083619573366df8a27b2fc49b..cf4723ff658f0bcdaecd0851aea01cc775c3c905 100644
--- a/tests/run_tests.py
+++ b/tests/run_tests.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -28,10 +28,15 @@ import sys
import os
-def _run(test_files, test_root_path, verbosity=0):
+def discover(test_files=None, test_root_path=None):
+ if not test_root_path:
+ test_root_path = os.path.dirname(__file__)
+
if not test_files:
suite = unittest.TestLoader().discover(test_root_path, pattern="test_*.py")
+
else:
+ test_files = [os.path.abspath(f) for f in test_files]
test_files = [t for t in test_files if test_root_path in t]
suite = unittest.TestSuite()
for test_file in test_files:
@@ -44,31 +49,12 @@ def _run(test_files, test_root_path, verbosity=0):
else:
sys.stderr.write("{0} : no such file or directory\n".format(test_file))
- test_runner = unittest.TextTestRunner(verbosity=verbosity).run(suite)
- return test_runner
+ return suite
-def run_unittests(test_files, verbosity=0):
+def run_tests(test_files, verbosity=0):
"""
Execute Unit Tests
-
- :param test_files: the file names of tests to run.
- of it is empty, discover recursively tests from 'tests/unit' directory.
- a test is python module with the test_*.py pattern
- :type test_files: list of string
- :param verbosity: the verbosity of the output
- :type verbosity: positive int
- :return: True if the test passed successfully, False otherwise.
- :rtype: bool
- """
- test_root_path = os.path.join(os.path.dirname(__file__), 'unit')
- return _run(test_files, test_root_path, verbosity)
-
-
-def run_functional_tests(test_files, verbosity=0):
- """
- Execute Functional Tests
-
:param test_files: the file names of tests to run.
of it is empty, discover recursively tests from 'tests/unit' directory.
a test is python module with the test_*.py pattern
@@ -78,12 +64,15 @@ def run_functional_tests(test_files, verbosity=0):
:return: True if the test passed successfully, False otherwise.
:rtype: bool
"""
- test_root_path = os.path.join(os.path.dirname(__file__), 'functional')
- return _run(test_files, test_root_path, verbosity)
-
+ test_root_path = os.path.abspath(os.path.dirname(__file__))
+ suite = discover(test_files, test_root_path)
+ test_runner = unittest.TextTestRunner(verbosity=verbosity).run(suite)
+ return test_runner
-if __name__ == '__main__':
+def main(args=None):
+ if args is None:
+ args = sys.argv[1:]
from argparse import ArgumentParser
parser = ArgumentParser()
parser.add_argument("tests",
@@ -91,18 +80,6 @@ if __name__ == '__main__':
default=False,
help="name of test to execute")
- parser.add_argument("--unit",
- dest='unit',
- action='store_true',
- default=False,
- help="execute unit tests")
-
- parser.add_argument("--functional",
- dest='functional',
- action='store_true',
- default=False,
- help="execute functional tests")
-
parser.add_argument("-v", "--verbose",
dest="verbosity",
action="count",
@@ -110,52 +87,27 @@ if __name__ == '__main__':
default=0
)
- args = parser.parse_args()
- if not any((args.unit, args.functional)):
- args.unit, args.functional = True, True
-
- result_all_tests = []
-
- if args.unit:
- print("\n", "#" * 70, sep='')
- print("Test Runner: Unit tests")
- print("#" * 70)
-
- old_path = sys.path
- if 'CRAW_HOME' in os.environ and os.environ['CRAW_HOME']:
- CRAW_HOME = os.environ['CRAW_HOME']
- if CRAW_HOME not in sys.path:
- sys.path.insert(0, CRAW_HOME)
- test_runner = run_unittests(args.tests, verbosity=args.verbosity)
- unit_results = test_runner.wasSuccessful()
- result_all_tests.append(unit_results)
- sys.path = old_path
-
- if args.functional:
- print("\n", "#" * 70, sep='')
- print("Test Runner: Functional tests")
- print("#" * 70)
-
- old_path = sys.path
- if 'CRAW_HOME' in os.environ and os.environ['CRAW_HOME']:
- CRAW_HOME = os.environ['CRAW_HOME']
- if CRAW_HOME not in sys.path:
- sys.path.insert(0, CRAW_HOME)
- else:
- home_tests = os.path.normpath(os.path.join(os.path.dirname(__file__), '..'))
- # we are in the case where we tests an installed CRAW
- # so the libraries are already in PYTHONPATH
- # but test are not
- # we must had tests parent dir in pythonpath
- # but after the standard libraries containing craw
- # as we want to run CRAW using installed libraries
- sys.path.append(home_tests)
- test_runner = run_functional_tests(args.tests, verbosity=args.verbosity)
- functional_results = test_runner.wasSuccessful()
- result_all_tests.append(functional_results)
- sys.path = old_path
-
- if all(result_all_tests):
+ args = parser.parse_args(args)
+
+ CRAW_HOME = os.path.abspath(os.path.join(__file__, '..', '..'))
+
+ old_path = sys.path
+
+ if CRAW_HOME not in sys.path:
+ # need to add tests in path
+ # tests inherits from IntegronTest which is located in tests/__init__.py
+ sys.path.insert(0, CRAW_HOME)
+
+ test_runner = run_tests(args.tests, verbosity=args.verbosity)
+ unit_results = test_runner.wasSuccessful()
+ sys.path = old_path
+ return unit_results
+
+
+if __name__ == '__main__':
+
+ unit_results = main(sys.argv[1:])
+ if unit_results:
sys.exit(0)
else:
sys.exit(1)
diff --git a/tests/unit/test_annotation.py b/tests/test_annotation.py
similarity index 97%
rename from tests/unit/test_annotation.py
rename to tests/test_annotation.py
index 07d4e5c00fdfd6dd47782645b273e3bbe2daf4f1..7e575e8fbafd9a6dbb3138bb35053a7ceb8c67a9 100644
--- a/tests/unit/test_annotation.py
+++ b/tests/test_annotation.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -24,12 +24,7 @@
import os
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
-
+from tests import CRAWTest
from craw.annotation import Entry, Idx, new_entry_type, AnnotationParser
diff --git a/tests/unit/test_coverage.py b/tests/test_coverage.py
similarity index 87%
rename from tests/unit/test_coverage.py
rename to tests/test_coverage.py
index f5ddb84acb699004e8507ec102a43250a555a17b..161f362f5d8d6823799ff3cde897c23c41aa5708 100644
--- a/tests/unit/test_coverage.py
+++ b/tests/test_coverage.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -28,15 +28,11 @@ import pysam
import logging
from itertools import zip_longest
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
+from tests import CRAWTest
from craw.wig import Genome, WigParser, _log
-from craw.coverage import get_raw_bam_coverage, get_raw_wig_coverage, get_raw_coverage_function
-from craw.coverage import sum_coverage_maker, padded_coverage_maker, resized_coverage_maker
+import craw.coverage
+
from craw.annotation import new_entry_type
@@ -49,13 +45,13 @@ class TestCoverage(CRAWTest):
def test_get_coverage_function(self):
sam_path = os.path.join(self._data_dir, 'small.bam')
bam_obj = pysam.AlignmentFile(sam_path, "rb")
- func = get_raw_coverage_function(bam_obj)
- self.assertEqual(get_raw_bam_coverage, func)
+ func = craw.coverage.get_raw_coverage_function(bam_obj)
+ self.assertEqual(craw.coverage.get_raw_bam_coverage, func)
genome = Genome()
- func = get_raw_coverage_function(genome)
- self.assertEqual(func, get_raw_wig_coverage)
+ func = craw.coverage.get_raw_coverage_function(genome)
+ self.assertEqual(func, craw.coverage.get_raw_wig_coverage)
with self.assertRaises(RuntimeError) as ctx:
- get_raw_coverage_function('foo')
+ craw.coverage.get_raw_coverage_function('foo')
self.assertEqual(str(ctx.exception),
"get_coverage support only 'wig.Genome' or 'pysam.calignmentfile.AlignmentFile' "
"as Input, not str")
@@ -100,15 +96,35 @@ class TestCoverage(CRAWTest):
stop = values[-1] + before
start = max(start, 0)
stop = max(stop, 0)
- forward_cov, reverse_cov = get_raw_bam_coverage(sam_file,
- annot_entry,
- start,
- stop,
- qual_thr=0)
+ forward_cov, reverse_cov = craw.coverage.get_raw_bam_coverage(sam_file,
+ annot_entry,
+ start,
+ stop,
+ qual_thr=0)
self.assertListEqual(forward_cov, exp_val['for'])
self.assertListEqual(reverse_cov, exp_val['rev'])
+ def test_get_raw_bam_coverage_bad_pysam(self):
+ class FakeAlignmentFile:
+ def __init__(self, *args, **kwargs):
+ pass
+
+ def count_coverage(self, *args, **kwarg):
+ raise SystemError
+
+ annot_fields = ['name', 'gene', 'chromosome', 'strand', 'Position']
+ ref_col = 'Position'
+ ne_class = new_entry_type('Foo', annot_fields, ref_col)
+ annot_entry = ne_class(['YEL072W', 'RMD6', 'chrV', '+', '14415'])
+ with self.catch_log():
+ with self.assertRaises(SystemError) as ctx:
+ craw.coverage.get_raw_bam_coverage(FakeAlignmentFile(),
+ annot_entry,
+ 0,
+ 3,
+ qual_thr=0)
+
def test_get_raw_wig_coverage(self):
wig_parser = WigParser(os.path.join(self._data_dir, 'small_fixed.wig'))
@@ -156,7 +172,7 @@ class TestCoverage(CRAWTest):
stop = (values[-1] - 1) + before + 1
start = max(start, 0)
stop = max(stop, 0)
- forward_cov, reverse_cov = get_raw_wig_coverage(genome,
+ forward_cov, reverse_cov = craw.coverage.get_raw_wig_coverage(genome,
annot_entry,
start,
stop,
@@ -192,7 +208,7 @@ class TestCoverage(CRAWTest):
# get_wig_coverage work with 0-based positions
# whereas annot_entry with 1-based positions
- get_coverage = padded_coverage_maker(genome, 5, 9, qual_thr=0)
+ get_coverage = craw.coverage.padded_coverage_maker(genome, 5, 9, qual_thr=0)
for values, exp_val in zip_longest(value_lines, exp_values):
annot_entry = ne_class([str(v) for v in values])
# get_bam_coverage work with 0-based positions
@@ -237,7 +253,7 @@ class TestCoverage(CRAWTest):
before = 5
after = 3
- get_coverage = padded_coverage_maker(genome, 5, 3, qual_thr=0)
+ get_coverage = craw.coverage.padded_coverage_maker(genome, 5, 3, qual_thr=0)
for values, exp_val in zip_longest(value_lines, exp_values):
annot_entry = ne_class([str(v) for v in values])
# get_wig_coverage work with 0-based positions
@@ -288,7 +304,7 @@ class TestCoverage(CRAWTest):
before = 5
after = 3
- get_coverage = sum_coverage_maker(genome, qual_thr=0)
+ get_coverage = craw.coverage.sum_coverage_maker(genome, qual_thr=0)
for values, exp_val in zip_longest(value_lines, exp_values):
annot_entry = ne_class([str(v) for v in values])
# get_wig_coverage work with 0-based positions
@@ -331,7 +347,7 @@ class TestCoverage(CRAWTest):
###################################
# keep the number of values as is #
###################################
- get_coverage = resized_coverage_maker(genome, 8)
+ get_coverage = craw.coverage.resized_coverage_maker(genome, 8)
annot_entry = ne_class([str(v) for v in value_line])
# get_bam_coverage work with 0-based positions
# whereas annot_entry with 1-based positions
@@ -353,7 +369,7 @@ class TestCoverage(CRAWTest):
'rev': [12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0]
}
- get_coverage = resized_coverage_maker(genome, 15)
+ get_coverage = craw.coverage.resized_coverage_maker(genome, 15)
forward_cov, reverse_cov = get_coverage(annot_entry, start, stop)
self.assertListEqual(forward_cov, exp_values['for'])
@@ -364,7 +380,7 @@ class TestCoverage(CRAWTest):
###############################
value_line = ['YEL072W', 'RMD6', 'chrV', '+', 15, 12, 18]
annot_entry = ne_class([str(v) for v in value_line])
- get_coverage = resized_coverage_maker(genome, 4)
+ get_coverage = craw.coverage.resized_coverage_maker(genome, 4)
start = annot_entry.start - 1
stop = annot_entry.stop
forward_cov, reverse_cov = get_coverage(annot_entry, start, stop)
@@ -379,7 +395,7 @@ class TestCoverage(CRAWTest):
###########################
value_line = ['YEL072W', 'RMD6', 'chrV', '+', 2, -2, 4]
annot_entry = ne_class([str(v) for v in value_line])
- get_coverage = resized_coverage_maker(genome, 5)
+ get_coverage = craw.coverage.resized_coverage_maker(genome, 5)
start = annot_entry.start - 1
stop = annot_entry.stop
forward_cov, reverse_cov = get_coverage(annot_entry, start, stop)
diff --git a/tests/unit/test_craw.py b/tests/test_craw.py
similarity index 75%
rename from tests/unit/test_craw.py
rename to tests/test_craw.py
index fd632a0ad8527c3a8b24708f2b55beb8c3c5dca7..189d644fa25d6d3e13df1728ad78c440826f3596 100644
--- a/tests/unit/test_craw.py
+++ b/tests/test_craw.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -24,22 +24,20 @@
import logging
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
-
+from tests import CRAWTest
import craw
+
class MyTestCase(CRAWTest):
def test_get_version_message(self):
- self.assertTrue(craw.get_version_message().startswith(
- "craw NOT packaged, it should be a development version | Python 3."))
+ craw_version = craw.__version__
craw.__version__ = 1.0
- self.assertTrue(craw.get_version_message().startswith("craw 1.0 | Python 3."))
+ try:
+ self.assertTrue(craw.get_version_message().startswith("craw 1.0 | Python 3."))
+ finally:
+ craw.__version__ = craw_version
def test_init_logger(self):
@@ -49,4 +47,4 @@ class MyTestCase(CRAWTest):
craw_log = logging.getLogger('craw')
self.assertEqual(len(craw_log.handlers), 1)
self.assertEqual(craw_log.handlers[0].__class__.__name__, 'StreamHandler')
- self.assertEqual(craw_log.getEffectiveLevel(), log_level)
\ No newline at end of file
+ self.assertEqual(craw_log.getEffectiveLevel(), log_level)
diff --git a/tests/test_craw_coverage.py b/tests/test_craw_coverage.py
new file mode 100644
index 0000000000000000000000000000000000000000..ee8b239ae88e9216168aa220e64fe580db842d1d
--- /dev/null
+++ b/tests/test_craw_coverage.py
@@ -0,0 +1,635 @@
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+import shutil
+import tempfile
+import os
+from builtins import type
+from itertools import zip_longest
+import argparse
+import sys
+import pysam
+
+import craw
+from craw.scripts import craw_coverage as craw_cov
+from tests import CRAWTest
+
+
+class TestCoverage(CRAWTest):
+
+ def setUp(self):
+ tmp_dir = tempfile.gettempdir()
+ self.out_dir = os.path.join(tmp_dir, 'test_craw')
+ if os.path.exists(self.out_dir) and os.path.isdir(self.out_dir):
+ shutil.rmtree(self.out_dir)
+ os.makedirs(self.out_dir)
+ self.bin = 'craw_coverage'
+
+
+ def tearDown(self):
+ try:
+ shutil.rmtree(self.out_dir)
+ pass
+ except:
+ pass
+
+
+ def test_positive_int(self):
+ self.assertEqual(craw_cov.positive_int(3), 3)
+
+ with self.assertRaises(argparse.ArgumentTypeError) as ctx:
+ craw_cov.positive_int('Foo')
+ self.assertEqual(str(ctx.exception), "must be a positive integer, got: Foo")
+
+ with self.assertRaises(argparse.ArgumentTypeError) as ctx:
+ craw_cov.positive_int(-1)
+ self.assertEqual(str(ctx.exception), "must be a positive integer, got: -1")
+
+
+ def test_quality_checker(self):
+ self.assertEqual(craw_cov.quality_checker(3), 3)
+
+ with self.assertRaises(argparse.ArgumentTypeError) as ctx:
+ craw_cov.quality_checker('Foo')
+ self.assertEqual(str(ctx.exception), "must be a integer between 0 and 42, got: Foo")
+
+ with self.assertRaises(argparse.ArgumentTypeError) as ctx:
+ craw_cov.quality_checker(-1)
+ self.assertEqual(str(ctx.exception), "must be a integer between 0 and 42, got: -1")
+
+ with self.assertRaises(argparse.ArgumentTypeError) as ctx:
+ craw_cov.quality_checker(45)
+ self.assertEqual(str(ctx.exception), "must be a integer between 0 and 42, got: 45")
+
+
+ def test_get_result_header(self):
+ header = """# Running Counter RnAseq Window craw_coverage
+#
+# Version: craw {cr_ver} | Python {py}
+# Using:
+# - pysam {pysam} (samtools {sam})
+# - scipy {scipy} (only for --justify opt)
+#
+# craw_coverage run with the following arguments:
+# --after=3
+# --annot=tests/data/annotation_wo_start.txt
+# --bam=tests/data/small.bam
+# --before=5
+# --chr-col=chromosome
+# --output=foo.cov
+# --qual-thr=0
+# --quiet=1
+# --ref-col=Position
+# --sense=mixed
+# --sep=\t
+# --strand-col=strand
+# --suffix=cov
+# --verbose=0
+sense\tname\tgene\tchromosome\tstrand\tPosition\t-5\t-4\t-3\t-2\t-1\t0\t1\t2\t3""".format(
+ cr_ver=craw.__version__,
+ py='{}.{}'.format(sys.version_info.major, sys.version_info.minor),
+ pysam=pysam.__version__,
+ sam=pysam.__samtools_version__,
+ scipy=craw.coverage.scipy.__version__)
+
+ args = argparse.Namespace()
+ args.bam = 'tests/data/small.bam'
+ args.annot = 'tests/data/annotation_wo_start.txt'
+ args.ref_col = 'Position'
+ args.before = 5
+ args.after = 3
+ args.qual_thr = 0
+ args.quiet = 1
+ args.output = 'foo.cov'
+ args.justify = False
+ args.sum = False
+ args.start_col = False
+ args.chr_col = 'chromosome'
+ args.sense = 'mixed'
+ args.sep = '\t'
+ args.strand_col = 'strand'
+ args.suffix = 'cov'
+ args.verbose = 0
+
+ annot = self.fake_annotation_parser(['name', 'gene', 'chromosome', 'strand', 'Position'], (0, 0))
+ self.maxDiff = None
+
+ self.assertEqual(craw_cov.get_result_header(annot, args),
+ header.rstrip())
+
+ def test_get_version_message(self):
+ msg = """craw {cr_ver} | Python {py}
+Using:
+ - pysam {pysam} (samtools {sam})
+ - scipy {scipy} (only for --justify opt)
+""".format(cr_ver=craw.__version__,
+ py='{}.{}'.format(sys.version_info.major, sys.version_info.minor),
+ pysam=pysam.__version__,
+ sam=pysam.__samtools_version__,
+ scipy=craw.coverage.scipy.__version__)
+
+ self.assertEqual(craw_cov.get_version_message(),
+ msg)
+
+ def test_get_results_file(self):
+ try:
+ sense, antisense = craw_cov.get_results_file('S', os.path.join(self.out_dir, 'foo'), 'cov')
+ sense_file_name = os.path.join(self.out_dir, 'foo.sense.cov')
+ self.assertTrue(os.path.exists(
+ sense_file_name)
+ )
+ self.assertEqual(sense.name, sense_file_name)
+ self.assertEqual(antisense.name, os.devnull)
+ finally:
+ sense.close()
+ antisense.close()
+ self.tearDown()
+
+ try:
+ self.setUp()
+ sense, antisense = craw_cov.get_results_file('AS', os.path.join(self.out_dir, 'foo'), 'cov')
+ antisense_file_name = os.path.join(self.out_dir, 'foo.antisense.cov')
+ self.assertTrue(os.path.exists(
+ antisense_file_name)
+ )
+ self.assertEqual(sense.name, os.devnull)
+ self.assertEqual(antisense.name, antisense_file_name)
+ finally:
+ sense.close()
+ antisense.close()
+ self.tearDown()
+
+ try:
+ self.setUp()
+ sense, antisense = craw_cov.get_results_file('split', os.path.join(self.out_dir, 'foo'), 'cov')
+ sense_file_name = os.path.join(self.out_dir, 'foo.sense.cov')
+ antisense_file_name = os.path.join(self.out_dir, 'foo.antisense.cov')
+ self.assertTrue(os.path.exists(
+ sense_file_name)
+ )
+ self.assertTrue(os.path.exists(
+ antisense_file_name)
+ )
+ self.assertEqual(sense.name, sense_file_name)
+ self.assertEqual(antisense.name, antisense_file_name)
+ finally:
+ sense.close()
+ antisense.close()
+ self.tearDown()
+
+ try:
+ self.setUp()
+ sense, antisense = craw_cov.get_results_file('mixed', os.path.join(self.out_dir, 'foo'), 'cov')
+ output_file_name = os.path.join(self.out_dir, 'foo.cov')
+ self.assertTrue(os.path.exists(
+ output_file_name)
+ )
+ self.assertEqual(sense.name, output_file_name)
+ self.assertIs(antisense, sense)
+ finally:
+ sense.close()
+ antisense.close()
+ self.tearDown()
+
+
+ def test_parse_args(self):
+ args = {'bam': 'small.bam',
+ 'annot': 'annotation_wo_start.txt',
+ 'ref_col': 'Position',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': 'result_path'}
+ command = "--bam {bam} --annot {annot} --before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual_thr} --quiet --output={output} ".format(**args)
+ self.check_args(args, command)
+
+ args = {'bam': 'small.bam',
+ 'annot': 'annotation_wo_start_chr_strand_col.txt',
+ 'ref_col': 'Position',
+ 'chr_col': 'chr',
+ 'strand_col': 'brin',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': 'test_result_path'
+ }
+ command = "--bam={bam} --annot={annot} --chr-col={chr_col} " \
+ "--strand-col={strand_col} --before={before} --after={after} --ref-col={ref_col} " \
+ "--qual-thr={qual_thr} --quiet --output={output}"
+ self.check_args(args, command)
+
+ args = {'bam': 'small.bam',
+ 'annot': 'annotation_w_start.txt',
+ 'ref_col': 'Position',
+ 'start_col': 'beg',
+ 'stop_col': 'end',
+ 'qual_thr': 15,
+ 'output': 'result_path'}
+
+ command = "--bam={bam} --annot={annot} " \
+ "--ref-col={ref_col} --start-col={start_col} --stop-col={stop_col} " \
+ "--qual-thr={qual_thr} --quiet --output={output}"
+ self.check_args(args, command)
+
+ args = {'wig': 'small_fixed.wig',
+ 'annot': 'annotation_4_wig_fixed_win.txt',
+ 'ref_col': 'Position',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': 'result_path'}
+ command = "--wig={wig} --annot={annot} --before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual_thr} --quiet --output={output} "
+ self.check_args(args, command)
+
+ args = {'wig': 'small_fixed.wig',
+ 'annot': 'annotation_4_wig_fixed_win.txt',
+ 'ref_col': 'Position',
+ 'window': 5,
+ 'qual_thr': 0,
+ 'output': 'result_path'}
+ command = "--wig={wig} --annot={annot} --window={window} " \
+ "--ref-col={ref_col} --qual-thr={qual_thr} --quiet --output={output} "
+ self.check_args(args, command)
+
+ command = "--annot=annot_file --before=3 --after=5 --ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "At least one of these options must be specified "
+ "'--bam', '--wig' , '--wig-for', '--wig-rev'.")
+
+ command = "--wig=wig --bam=bam --wig-for=wig_for --wig-rev=wig_rev --annot=annot_file " \
+ "--before=3 --after=5 --ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception),
+ "'--bam', '--wig' , '--wig-for', '--wig-rev' cannot specify at the same time.")
+
+ command = "--wig=wig --bam=bam --annot=annot_file " \
+ "--before=3 --after=5 --ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "'--bam' option cannot be specified in the same time as "
+ "'--wig', '--wig-for' or '--wig-rev' options.")
+
+ command = "--wig=wig --wig-for=wig_for --wig-rev=wig_rev --annot=annot_file " \
+ "--before=3 --after=5 --ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "'--wig' option cannot be specified in the same time as "
+ "'--wig-for' or '--wig-rev' options.")
+
+ command = "--wig=wig --annot=annot_file " \
+ "--ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "[--window or [--before, --after] or [--start-col, --stop-col] options "
+ "must be specified")
+
+ command = "--wig=wig --annot=annot_file " \
+ "--window=5 --before=3 --after=5 --ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "options [--before, --after] and --window are mutually exclusives.")
+
+ command = "--wig=wig --annot=annot_file --after=3 --start-col=start --stop-col=stop " \
+ "--ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "Options [--before, --after, --window] and [--start-col, --stop-col] "
+ "are mutually exclusives.")
+
+ command = "--wig=wig --annot=annot_file --after=3 " \
+ "--ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "The two options --after and --before work together. "
+ "The both options must be specified in same time")
+
+ command = "--wig=wig --annot=annot_file --start-col=start " \
+ "--ref-col=Position --qual-thr=0 --quiet --output=output"
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_cov.parse_args(command.split())
+ self.assertEqual(str(ctx.exception), "The two options --start-col and --stop-col work together. "
+ "The both options must be specified in same time")
+
+
+ def check_args(self, args, tpl):
+ command = tpl.format(**args)
+ got_args = craw_cov.parse_args(command.split())
+ for opt in args:
+ self.assertEqual(getattr(got_args, opt), args[opt])
+
+
+ def test_bam_with_fixed_window(self):
+ output_filename = 'small.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+
+ args = {'bam': os.path.join(self._data_dir, 'small.bam'),
+ 'annot': os.path.join(self._data_dir, 'annotation_wo_start.txt'),
+ 'ref_col': 'Position',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': test_result_path}
+ command = "--bam {bam} --annot {annot} --before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual_thr} --quiet --output={output} ".format(**args)
+ craw_cov.main(command.split())
+
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_bam_with_chr_strand_col(self):
+ output_filename = 'coverage_fix_window_chr_strand_col.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ args = {'bam': os.path.join(self._data_dir, 'small.bam'),
+ 'annot': os.path.join(self._data_dir, 'annotation_wo_start_chr_strand_col.txt'),
+ 'ref_col': 'Position',
+ 'chr_col': 'chr',
+ 'strand_col': 'brin',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': test_result_path
+ }
+ command = "--bam={bam} --annot={annot} --chr-col={chr_col} " \
+ "--strand-col={strand_col} --before={before} --after={after} --ref-col={ref_col} " \
+ "--qual-thr={qual_thr} --quiet --output={output}".format(**args)
+
+ craw_cov.main(command.split())
+
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_bam_with_var_window(self):
+ output_filename = 'coverage_var_window.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ args = {'bam': os.path.join(self._data_dir, 'small.bam'),
+ 'annot': os.path.join(self._data_dir, 'annotation_w_start.txt'),
+ 'ref_col': 'Position',
+ 'start_col': 'beg',
+ 'stop_col': 'end',
+ 'qual_thr': 15,
+ 'output': test_result_path
+ }
+ command = "--bam={bam} --annot={annot} " \
+ "--ref-col={ref_col} --start-col={start_col} --stop-col={stop_col} " \
+ "--qual-thr={qual_thr} --quiet --output={output}".format(**args)
+
+ craw_cov.main(command.split())
+
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_wig_with_fixed_window(self):
+ output_filename = 'wig_fixed_window.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ args = {'wig': os.path.join(self._data_dir, 'small_fixed.wig'),
+ 'annot': os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
+ 'ref_col': 'Position',
+ 'before': 5,
+ 'after': 3,
+ 'qual_thr': 0,
+ 'output': test_result_path}
+ command = "--wig={wig} --annot={annot} --before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual_thr} --quiet --output={output}".format(**args)
+ craw_cov.main(command.split())
+
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_wig_with_var_window(self):
+ output_filename = 'wig_var_window.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig={wig_file} --annot={annot_file} " \
+ "--ref-col={ref_col} --start-col={start_col} --stop-col={stop_col} " \
+ "--qual-thr={qual} --quiet --output={out_file} ".format(
+ wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
+ ref_col='Position',
+ start_col='beg',
+ stop_col='end',
+ qual=15,
+ out_file=test_result_path
+ )
+
+ craw_cov.main(command.split())
+
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_2wig_with_fixed_window(self):
+ """
+ """
+ output_filename = 'wig_splited_fixed_window.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig-for={wig_for} --wig-rev={wig_rev} --annot={annot_file} " \
+ "--before={before} --after={after} --ref-col={ref_col} " \
+ "--qual-thr={qual} --quiet " \
+ "--output={out_file} ".format(wig_for=os.path.join(self._data_dir, 'small_fixed.wig'),
+ wig_rev=os.path.join(self._data_dir, 'small_fixed_reverse.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
+ ref_col='Position',
+ before=5,
+ after=3,
+ qual=0,
+ out_file=test_result_path
+ )
+ craw_cov.main(command.split())
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_only_forward_wig(self):
+ """
+ """
+ output_filename = 'wig_only_forward.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig-for={wig_for} --annot={annot_file} " \
+ "--before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual} " \
+ "--quiet --output={out_file} ".format(
+ wig_for=os.path.join(self._data_dir, 'small_fixed.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
+ ref_col='Position',
+ before=5,
+ after=3,
+ qual=0,
+ out_file=test_result_path
+ )
+ craw_cov.main(command.split())
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_only_reverse_wig(self):
+ """
+ """
+ output_filename = 'wig_only_reverse.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig-rev={wig_rev} --annot={annot_file} " \
+ "--before={before} --after={after} " \
+ "--ref-col={ref_col} --qual-thr={qual} --quiet " \
+ "--output={out_file} ".format(wig_rev=os.path.join(self._data_dir, 'small_fixed_reverse.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_fixed_win.txt'),
+ ref_col='Position',
+ before=5,
+ after=3,
+ qual=0,
+ out_file=test_result_path
+ )
+ craw_cov.main(command.split())
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_resized_var_window(self):
+ """
+ """
+ output_filename = 'wig_var_window_justify.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig={wig_file} --annot={annot_file} " \
+ "--ref-col={ref_col} --start-col={start_col} --stop-col={stop_col} " \
+ "--qual-thr={qual} --quiet --output={out_file} " \
+ "--justify 10".format(wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
+ ref_col='Position',
+ start_col='beg',
+ stop_col='end',
+ qual=15,
+ out_file=test_result_path
+ )
+ craw_cov.main(command.split())
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def test_sum_var_window(self):
+ """
+ """
+ output_filename = 'wig_var_window_sum.cov'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--wig={wig_file} --annot={annot_file} " \
+ "--ref-col={ref_col} --start-col={start_col} --stop-col={stop_col} " \
+ "--qual-thr={qual} --quiet --output={out_file} " \
+ "--sum".format(wig_file=os.path.join(self._data_dir, 'small_variable.wig'),
+ annot_file=os.path.join(self._data_dir, 'annotation_4_wig_var_win.txt'),
+ ref_col='Position',
+ start_col='beg',
+ stop_col='end',
+ qual=15,
+ out_file=test_result_path
+ )
+ craw_cov.main(command.split())
+ expected_result_path = os.path.join(self._data_dir, output_filename)
+ with open(expected_result_path) as expected_result_file:
+ expected_result = expected_result_file.readlines()
+
+ with open(test_result_path) as test_result_file:
+ test_result = test_result_file.readlines()
+ self._check_coverage_file(expected_result, test_result)
+
+
+ def _check_coverage_file(self, expected_result, test_result):
+ for expected, result in zip_longest(expected_result, test_result, fillvalue=''):
+ if expected.startswith("# Version:"):
+ continue
+ elif expected.startswith("# - pysam"):
+ continue
+ elif expected.startswith("# - scipy"):
+ continue
+ elif expected.startswith("# --annot="):
+ continue
+ elif expected.startswith("# --bam="):
+ continue
+ elif expected.startswith("# --wig="):
+ continue
+ elif expected.startswith("# --wig-for="):
+ continue
+ elif expected.startswith("# --wig-rev="):
+ continue
+ elif expected.startswith("# --output="):
+ continue
+ else:
+ self.assertEqual(expected, result)
+
+
+ def fake_annotation_parser(self, header, max):
+ return type("AnnotationParser",
+ (object,),
+ {"header": header,
+ "max": lambda: max})
diff --git a/tests/test_craw_htmp.py b/tests/test_craw_htmp.py
new file mode 100644
index 0000000000000000000000000000000000000000..99c5f2d9ad9763160b1523bf87a0ee54290b2260
--- /dev/null
+++ b/tests/test_craw_htmp.py
@@ -0,0 +1,720 @@
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+import shutil
+import tempfile
+import os
+import stat
+import argparse
+import logging
+
+import PIL
+from PIL import Image
+import numpy as np
+import pandas as pd
+import matplotlib as mtp
+
+from tests import CRAWTest
+import craw
+from craw.scripts import craw_htmp
+from unittest import skipIf
+
+
+class TestCrawHtmp(CRAWTest):
+
+ def setUp(self):
+ self.tmp_dir = tempfile.gettempdir()
+ self.bin = 'craw_htmp'
+
+
+ def tearDown(self):
+ try:
+ shutil.rmtree(self.out_dir)
+ logger = logging.getLogger('craw')
+ logger.handlers = []
+ except:
+ pass
+
+ def test_file_readable(self):
+ self.assertEqual(craw_htmp._file_readable(__file__), __file__)
+
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_htmp._file_readable('nimportnaoik')
+ self.assertEqual(str(ctx.exception), "No such file: {}".format('nimportnaoik'))
+
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_htmp._file_readable(os.path.dirname(__file__))
+ self.assertEqual(str(ctx.exception),
+ "{} is not a regular file".format(os.path.dirname(__file__)))
+
+
+ @skipIf(os.getuid() == 0, "root have always right to access file")
+ def test_file_readable_bad_permission(self):
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.mkdir(self.out_dir)
+ file = os.path.join(self.out_dir, 'fake_file')
+ open(file, 'w').close()
+ os.chmod(file, stat.S_IWUSR)
+ with self.assertRaises(argparse.ArgumentError) as ctx:
+ craw_htmp._file_readable(file)
+ self.assertEqual(str(ctx.exception),
+ "{} is not readable".format(file))
+
+
+ def test_gene_size_parser(self):
+ self.assertListEqual(craw_htmp._gene_size_parser("start,stop"), ['start', 'stop'])
+ with self.assertRaises(argparse.ArgumentError):
+ craw_htmp._gene_size_parser("start_stop")
+
+ with self.assertRaises(argparse.ArgumentError):
+ craw_htmp._gene_size_parser("start,middle,stop")
+
+
+ def test_size_fig_parser(self):
+ self.assertTupleEqual(craw_htmp._size_fig_parser("12x22"), (12, 22))
+ self.assertTupleEqual(craw_htmp._size_fig_parser("12x22in"), (12, 22))
+ wide, height = craw_htmp._size_fig_parser("12x22cm")
+ self.assertAlmostEqual(wide, 4.72, places=2)
+ self.assertAlmostEqual(height, 8.66, places=2)
+ wide, height = craw_htmp._size_fig_parser("12x22mm")
+ self.assertAlmostEqual(wide, 0.472, places=3)
+ self.assertAlmostEqual(height, 0.866, places=3)
+ self.assertTupleEqual(craw_htmp._size_fig_parser("12x22px"), (0.12, 0.22))
+ self.assertEqual(craw_htmp._size_fig_parser("raw"), "raw")
+
+ with self.assertRaises(argparse.ArgumentError):
+ craw_htmp._size_fig_parser("12cm")
+
+ with self.assertRaises(argparse.ArgumentError):
+ craw_htmp._size_fig_parser("douze_x_vingtcm")
+
+ with self.assertRaises(argparse.ArgumentError):
+ craw_htmp._size_fig_parser("-2x22")
+
+
+ def test_get_version_message(self):
+ msg_expected = craw.get_version_message()
+ msg_expected += """
+Using:
+ - numpy {np_ver}
+ - pandas {pd_ver}
+ - matplotlib {mtp_ver}
+ - pillow {pil_ver}
+""".format(np_ver=np.__version__,
+ pd_ver=pd.__version__,
+ mtp_ver=mtp.__version__,
+ pil_ver=PIL.PILLOW_VERSION
+ )
+ get_message = craw_htmp.get_version_message()
+ self.assertEqual(msg_expected, get_message)
+
+
+ def test_parse_args(self):
+ output_filename = 'htmp_raw_lin.png'
+ test_result_path = os.path.join('result_dir', output_filename)
+ command = "--size {size} " \
+ "--out={out_file} " \
+ "--sort-using-col {sort_using_col} " \
+ "-q " \
+ "{cov_file}".format(size='raw',
+ out_file=test_result_path,
+ sort_using_col="start",
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ args = craw_htmp.parse_args(command.split())
+ expected_args = self.get_expected_htmp_args(size='raw',
+ out=test_result_path,
+ quiet=1,
+ sort_using_col="start",
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ for k in expected_args.__dict__:
+ self.assertEqual(getattr(args, k), getattr(expected_args, k),
+ msg="for option {}".format(k))
+
+
+ def test_raw(self):
+ """
+ | test if returncode of coverage is 0 and
+ | then test if the generated file is the same as a reference file
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ bin=self.bin,
+ size='raw',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ #print("\n@@@", command)
+
+ craw_htmp.main(command.split())
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ expected_img = Image.open(expected_result_path)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+
+ def test_raw_log(self):
+ """
+ | test if returncode of coverage is 0 and
+ | then test if the generated file is the same as a reference file
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_log.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ ##print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img, delta=1.0, msg=sense)
+
+
+ def test_raw_log_row(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_log+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log+row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+
+ def test_raw_lin_row(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+
+ def test_with_marks(self):
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_log_marks.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--mark -2 red " \
+ "--mark 2 green " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+ def test_raw_sense_only(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--sense-only " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ sense = 'sense'
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+ self.assertFalse(os.path.exists("{}.{}{}".format(result_path, 'antisense', suffix)))
+
+
+ def test_raw_antisense_only(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--antisense-only " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+
+ sense = 'antisense'
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+ self.assertFalse(os.path.exists("{}.{}{}".format(result_path, 'sense', suffix)))
+
+
+ def test_raw_crop(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin_crop'
+ ext = '.png'
+ test_result_path = os.path.join(self.out_dir, output_filename + ext)
+ command = "--size {size} " \
+ "--out={out_file} " \
+ "--crop -2 2 " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+ for sense in ('sense', 'antisense'):
+ filename = "{}.{}{}".format(output_filename, sense, ext)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+ def test_raw_sort(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin'
+ ext = '.png'
+ test_result_path = os.path.join(self.out_dir, output_filename + ext)
+ command = "--size {size} " \
+ "--out={out_file} " \
+ "--sort-using-col Position " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+ for sense in ('sense', 'antisense'):
+ filename = "{}.{}{}".format(output_filename, sense, ext)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+
+ def test_raw_sort_file(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin_sort_file'
+ ext = '.png'
+ test_result_path = os.path.join(self.out_dir, output_filename + ext)
+ command = "--size {size} " \
+ "--out={out_file} " \
+ "--sort-using-file {sort_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ out_file=test_result_path,
+ sort_file=os.path.join(self._data_dir, '4_htmp_sorting_file.txt'),
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ craw_htmp.main(command.split())
+ for sense in ('sense', 'antisense'):
+ filename = "{}.{}{}".format(output_filename, sense, ext)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+
+ def test_raw_no_fmt(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp'
+ ext = 'png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ if 'DISPLAY' in os.environ:
+ craw_htmp.main(command.split())
+ for sense in ('sense', 'antisense'):
+ self.assertTrue(os.path.exists(os.path.join(self.out_dir,
+ "{}.{}.{}".format(output_filename, sense, ext))
+ )
+ )
+ else:
+ with self.assertRaises(RuntimeError) as ctx:
+ craw_htmp.main(command.split())
+ self.assertEqual(str(ctx.exception),
+ """
+ 'DISPLAY' variable is not set (you probably run craw_htmp in non graphic environment)
+ So you must specify an output format (add ext to the output file option as 'my_file.png')
+ """)
+
+ @skipIf('DISPLAY' not in os.environ, "run in non interactive environment")
+ def test_raw_no_out(self):
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ dir_ori = os.getcwd()
+ output_filename = '4_htmp'
+ # craw_htmp create result_file beside source file if --out is not specify
+ shutil.copy(os.path.join(self._data_dir, output_filename + '.cov'),
+ self.out_dir)
+ os.chdir(self.out_dir)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ cov_file=os.path.join(self.out_dir, output_filename + '.cov')
+ )
+ # print("\n@@@", command)
+ try:
+ craw_htmp.main(command.split())
+ for sense in ('sense', 'antisense'):
+ path = "{}.{}.{}".format(output_filename, sense, 'png')
+ self.assertTrue(os.path.exists(path))
+ finally:
+ os.chdir(dir_ori)
+
+
+ def test_non_display(self):
+ """
+ """
+ #############################################################
+ # run in not interactive environment
+ #############################################################
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_log+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log+row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ display = os.environ.get('DISPLAY', None)
+ if display:
+ del os.environ['DISPLAY']
+ # print("\n@@@", command)
+ try:
+ craw_htmp.main(command.split())
+ finally:
+ if display:
+ os.environ['DISPLAY'] = display
+
+ for sense in ('sense', 'antisense'):
+ filename, suffix = os.path.splitext(output_filename)
+ filename = "{}.{}{}".format(filename, sense, suffix)
+ expected_result_path = os.path.join(self._data_dir, filename)
+ result_path, suffix = os.path.splitext(test_result_path)
+ result_path = "{}.{}{}".format(result_path, sense, suffix)
+ expected_img = Image.open(expected_result_path)
+ result_img = Image.open(result_path)
+ self.assertImageAlmostEqual(expected_img, result_img)
+
+ #############################################################
+ # use file not compatible with not interactive environment
+ #############################################################
+ output_filename = 'htmp_raw_log+row.nimpornaoik'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log+row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ display = os.environ.get('DISPLAY', None)
+ if display:
+ del os.environ['DISPLAY']
+ # print("\n@@@", command)
+ try:
+ with self.assertRaises(RuntimeError)as ctx:
+ craw_htmp.main(command.split())
+ finally:
+ if display:
+ os.environ['DISPLAY'] = display
+ self.assertTrue(str(ctx.exception).strip().startswith(
+ "The '.nimpornaoik' format is not supported, choose among"
+ ))
+
+ #############################################################
+ # not interactive environment and no file specified
+ #############################################################
+ command = "--quiet " \
+ "{cov_file}".format(
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ #print("\n@@@", command)
+
+ display = os.environ.get('DISPLAY', None)
+ if display:
+ del os.environ['DISPLAY']
+ try:
+ with self.assertRaises(RuntimeError)as ctx:
+ craw_htmp.main(command.split())
+ finally:
+ if display:
+ os.environ['DISPLAY'] = display
+ self.assertEqual(str(ctx.exception).strip(),
+ """
+ 'DISPLAY' variable is not set (you probably run craw_htmp in non graphic environment)
+ So you cannot use interactive output
+ please specify an output file (--out).""".strip())
+
+
+ def test_bad_cmap(self):
+ output_filename = 'htmp_raw_log+row.png'
+ test_result_path = os.path.join('foo', output_filename)
+
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--cmap=nimportnaoik "\
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log+row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ with self.assertRaises(RuntimeError)as ctx:
+ craw_htmp.main(command.split())
+ self.assertTrue(str(ctx.exception).strip().startswith(
+ "Colormap nimportnaoik is not recognized. Possible values are:"
+ ))
+
+ @skipIf(os.getuid() == 0, 'root has always right write')
+ def test_bad_outdir(self):
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ os.chmod(self.out_dir, stat.S_IRUSR|stat.S_IXUSR|stat.S_IRGRP|stat.S_IROTH)
+ output_filename = 'htmp_raw_log+row.png'
+ test_result_path = os.path.join(self.out_dir, output_filename)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='log+row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ # print("\n@@@", command)
+ with self.catch_log() as log:
+ with self.assertRaises(RuntimeError) as ctx:
+ craw_htmp.main(command.split(), logger_out=False)
+ self.assertEqual(str(ctx.exception), "/tmp/craw_test is not writable")
+
+
+ def test_output_exists(self):
+ """
+ """
+ self.out_dir = os.path.join(self.tmp_dir, 'craw_test')
+ os.makedirs(self.out_dir)
+ output_filename = 'htmp_raw_lin+row'
+ ext = '.png'
+ test_result_path = os.path.join(self.out_dir, output_filename + ext)
+ command = "--size {size} " \
+ "--norm {norm} " \
+ "--out={out_file} " \
+ "--quiet " \
+ "{cov_file}".format(
+ size='raw',
+ norm='row',
+ out_file=test_result_path,
+ cov_file=os.path.join(self._data_dir, '4_htmp.cov')
+ )
+ with open(os.path.join(self.out_dir, '{}.sense{}'.format(output_filename, ext)), 'w'):
+ pass
+ # print("\n@@@", command)
+ with self.assertRaises(RuntimeError) as ctx:
+ craw_htmp.main(command.split(), logger_out=False)
+
+
+ def get_expected_htmp_args(self, **kwargs):
+ default_args = argparse.Namespace(antisense_only=False,
+ cmap='Blues',
+ cov_file=None,
+ crop=None,
+ dpi=None,
+ mark=None,
+ norm='lin',
+ out=None,
+ quiet=0,
+ sense_on_bottom=False,
+ sense_on_left=False,
+ sense_on_right=False,
+ sense_on_top=False,
+ sense_only=False,
+ size=None,
+ sort_by_gene_size=None,
+ sort_using_col=False,
+ sort_using_file=None,
+ title=None,
+ verbose=0)
+ for k, v in kwargs.items():
+ setattr(default_args, k, v)
+ return default_args
\ No newline at end of file
diff --git a/tests/unit/test_heatmap.py b/tests/test_heatmap.py
similarity index 97%
rename from tests/unit/test_heatmap.py
rename to tests/test_heatmap.py
index db6aba72ef53dc6a21e13f120cb16d2706c92c82..7b10081078a4d141ca8a45d4123b7ee611412502 100644
--- a/tests/unit/test_heatmap.py
+++ b/tests/test_heatmap.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -34,17 +34,13 @@ from pandas.util.testing import assert_frame_equal
from PIL import Image
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
-
+from tests import CRAWTest
import craw.heatmap as htmp
class TestHeatmap(CRAWTest):
+
@classmethod
def setUpClass(cls):
htmp._log.setLevel(logging.ERROR)
@@ -147,6 +143,9 @@ class TestHeatmap(CRAWTest):
received_data = htmp._sort_using_col(data, col='name')
assert_frame_equal(expected_data, received_data)
+ with self.assertRaises(RuntimeError) as ctx:
+ htmp._sort_using_col(data)
+ self.assertEqual(str(ctx.exception), "You must specify the column used to sort.")
def test_sort_using_file(self):
data = pd.DataFrame([
diff --git a/tests/test_util.py b/tests/test_util.py
new file mode 100644
index 0000000000000000000000000000000000000000..7b27c9614e5b66a6ca97f55602af191bee7eb386
--- /dev/null
+++ b/tests/test_util.py
@@ -0,0 +1,40 @@
+###########################################################################
+# #
+# This file is part of Counter RNAseq Window (craw) package. #
+# #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
+# see COPYRIGHT file for details. #
+# #
+# craw is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# craw is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. #
+# See the GNU General Public License for more details. #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with craw (see COPYING file). #
+# If not, see <http://www.gnu.org/licenses/>. #
+# #
+###########################################################################
+
+
+
+from tests import CRAWTest
+from craw.util import progress
+
+
+class TestUtil(CRAWTest):
+
+
+ def test_progress(self):
+ import io
+ stream = io.StringIO()
+ progress(10, 100, status="", file=stream)
+ self.assertEqual('[======> ] 10.0% ... of 100 annotations\r',
+ stream.getvalue())
+
diff --git a/tests/unit/test_wig.py b/tests/test_wig.py
similarity index 98%
rename from tests/unit/test_wig.py
rename to tests/test_wig.py
index d8904facaef853534aaef1d8a094a85aa6d81bda..3436bba6795b5c1b4b6b4c73091884bde460d76a 100644
--- a/tests/unit/test_wig.py
+++ b/tests/test_wig.py
@@ -2,8 +2,8 @@
# #
# This file is part of Counter RNAseq Window (craw) package. #
# #
-# Authors: Bertrand Néron #
-# Copyright © 2017 Institut Pasteur (Paris). #
+# Authors: Bertrand Neron #
+# Copyright (c) 2017-2019 Institut Pasteur (Paris). #
# see COPYRIGHT file for details. #
# #
# craw is free software: you can redistribute it and/or modify #
@@ -26,17 +26,10 @@ import logging
import psutil
import numpy as np
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
-
+from tests import CRAWTest
from craw.wig import WigError, FixedChunk, VariableChunk, Chromosome, Genome, WigParser, _log
-
-
class TestFixedChunk(CRAWTest):
@classmethod
diff --git a/tests/unit/__init__.py b/tests/unit/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/tests/unit/test_util.py b/tests/unit/test_util.py
deleted file mode 100644
index 36617356c3d8b5c4ebb7a1dc52cb4c82dbf2704b..0000000000000000000000000000000000000000
--- a/tests/unit/test_util.py
+++ /dev/null
@@ -1,19 +0,0 @@
-try:
- from tests import CRAWTest
-except ImportError as err:
- msg = "Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err)
- raise ImportError("Cannot import craw, check your installation or your CRAW_HOME variable : {0!s}".format(err))
-
-from craw.util import progress
-
-
-class TestUtil(CRAWTest):
-
-
- def test_progress(self):
- import io
- stream = io.StringIO()
- progress(10, 100, status="", file=stream)
- self.assertEqual('[======> ] 10.0% ... of 100 annotations\r',
- stream.getvalue())
-