Merge pull request #1 from dstrib/master

Version 0.1.8, Publish to PyPi/pip

README.rst

@@ -2,9 +2,15 @@
 hybkit
 ==================================
 
+.. image:: https://img.shields.io/github/v/release/RenneLab/hybkit
+   :alt: GitHub release (latest by date)
+.. image:: https://badge.fury.io/py/hybkit.svg
+   :target: https://badge.fury.io/py/hybkit
 .. image:: https://readthedocs.org/projects/hybkit/badge/?version=latest
-    :target: https://hybkit.readthedocs.io/en/latest/?badge=latest
-    :alt: Documentation Status
+   :target: https://hybkit.readthedocs.io/en/latest/?badge=latest
+   :alt: Documentation Status
+.. image:: https://img.shields.io/pypi/pyversions/hybkit
+   :alt: PyPI - Python Version
 
 
 | Welcome to *hybkit*, a toolkit for analysis of ".hyb" format genomic sequence data 
@@ -131,3 +137,7 @@ Followed by installation using python's setuptools::
     $ python setup.py install
 
 
+
+.. |hybkit Toolkit| replace:: *hybkit Toolkit*
+.. |Example Pipelines| replace:: *Example Pipelines*
+.. |hybkit API| replace:: *hybkit API*

docs/requirements.txt

@@ -1 +1,2 @@
 matplotlib
+importlib_resources

hybkit/__about__.py

@@ -8,22 +8,48 @@
 '''
 
 import os
+import sys
+if sys.version_info.major >= 3 and sys.version_info.minor >= 7:
+    from importlib import resources as importlib_resources
+else:
+    import importlib_resources
 
-# Set package directory and code directory
-package_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
-code_dir = os.path.join(package_dir, 'hybkit')
-data_dir = os.path.join(package_dir, 'databases')
-
-# Preparation for initial PIP release, not yet completed.
 project_name = 'hybkit'
-description = 'Toolkit for analysis of .hyb format genomic sequence data.'
+version = "0.1.8"
+description = 'Toolkit for analysis of .hyb format genomic '
+description += 'sequence data from ribonomics experiments.'
 project_url = 'https://github.com/RenneLab/hybkit'
+project_download_url = 'https://github.com/RenneLab/hybkit' + '/tarball/' + version
 keywords = 'genetics genomics ribonomics bioinformatics hyb CLASH qCLASH miRNA '
 keywords += 'RNA DNA vienna viennad unafold'
+name_and_version = project_name + '-' + version
+
+module_dir = importlib_resources.files('hybkit')
+prefix_data_dir = os.path.join(sys.prefix, name_and_version)
+#Putting in try block to allow use with exec()
+try:
+    local_data_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
+except NameError:
+    local_data_dir = 'using_with_exec'
+
+if os.path.isdir(os.path.join(prefix_data_dir, 'databases')):
+    hybkit_data_dir = prefix_data_dir
+elif os.path.isdir(os.path.join(local_data_dir, 'databases')):
+    hybkit_data_dir = local_data_dir
+else:
+    print('WARNING: hybkit_data_dir variable cannot be set.')
+    hybkit_data_dir = ''
+
+databases_dir = os.path.join(hybkit_data_dir, 'databases')
+reference_data_dir = os.path.join(hybkit_data_dir, 'reference_data')
+docs_dir = os.path.join(hybkit_data_dir, 'docs')
+scripts_extra_dir = os.path.join(hybkit_data_dir, 'scripts_extra')
+
+default_string_match_params = os.path.join(module_dir, 'string_match_params.csv')
 
 # For a list of valid classifiers, see https://pypi.org/classifiers/
 classifiers = [
-    'Development Status :: 2 - Pre-Alpha',
+    'Development Status :: 4 - Beta',
     'Natural Language :: English',
     'Intended Audience :: Science/Research',
     'Intended Audience :: Developers',
@@ -48,11 +74,11 @@
 __author__ = "Daniel Stribling"
 __contact__ = "ds@ufl.edu"
 __credits__ = ["Daniel B. Stribling", "Rolf Renne"]
-__date__ = "YYYY/MM/DD"
+__date__ = "2020/03/10"
 __deprecated__ = False
 __email__ = "ds@ufl.edu"
 __license__ = "GPLv3"
 __maintainer__ = "Renne Group, University of Florida"
 __status__ = "Development"
-__version__ = "0.1.0"
+__version__ = version
 spec_version = __version__  # Define separate specification version.

hybkit/__init__.py

@@ -1510,7 +1510,7 @@ def find_seg_type_string_match(seg_info, find_type_params={}, check_complete=Fal
     # HybRecord : Public Staticmethods : find_seg_type
     @staticmethod
     def make_string_match_parameters(
-            legend_file=os.path.join(hybkit.__about__.code_dir, 'find_type_string_match.csv')
+            legend_file=hybkit.__about__.default_string_match_params
             ):
         """Read csv and return a dict of search parameters for :func:`find_seg_type_string_match`.
 

sample_01_summary_analysis/analysis_python.py

@@ -13,10 +13,6 @@
 
 import os
 import sys
-
-# Ensure hybkit is accessible
-analysis_dir = os.path.abspath(os.path.dirname(__file__))
-sys.path.append(os.path.join(analysis_dir, '..'))
 import hybkit
 
 # Set count_mode:

sample_02_target_analysis/analysis_python.py

@@ -13,10 +13,6 @@
 
 import os
 import sys
-
-# Ensure hybkit is accessible
-analysis_dir = os.path.abspath(os.path.dirname(__file__))
-sys.path.append(os.path.join(analysis_dir, '..'))
 import hybkit
 
 # Set count_mode:

sample_03_grouped_target_analysis/analysis_python.py

@@ -13,10 +13,6 @@
 
 import os
 import sys
-
-# Ensure hybkit is accessible
-analysis_dir = os.path.abspath(os.path.dirname(__file__))
-sys.path.append(os.path.join(analysis_dir, '..'))
 import hybkit
 
 # Set count_mode:

sample_04_fold_analysis/analysis_python.py

@@ -13,10 +13,6 @@
 
 import os
 import sys
-
-# Ensure hybkit is accessible
-analysis_dir = os.path.abspath(os.path.dirname(__file__))
-sys.path.append(os.path.join(analysis_dir, '..'))
 import hybkit
 
 # Set count_mode:

sample_04_fold_analysis/prepare_data.sh

@@ -8,8 +8,8 @@
 echo -e "\nPreparing data for sample fold analysis."
 
 echo -e "\nCopying data to analysis directory."
-cp -v ../databases/WT_BR1_comp_hOH7_KSHV_hybrids_ua.hyb.gz \
-      ../databases/WT_BR1_comp_hOH7_KSHV_hybrids_ua.viennad.gz \
+cp -v ../reference_data/WT_BR1_comp_hOH7_KSHV_hybrids_ua.hyb.gz \
+      ../reference_data/WT_BR1_comp_hOH7_KSHV_hybrids_ua.viennad.gz \
       ./
 
 

sample_05_fold_target_region_analysis/analysis_python.py

@@ -13,10 +13,6 @@
 
 import os
 import sys
-
-# Ensure hybkit is accessible
-analysis_dir = os.path.abspath(os.path.dirname(__file__))
-sys.path.append(os.path.join(analysis_dir, '..'))
 import hybkit
 
 # Set count_mode:

sample_05_fold_target_region_analysis/prepare_data.sh

@@ -8,8 +8,8 @@
 echo -e "\nPreparing data for sample fold analysis."
 
 echo -e "\nCopying data to analysis directory."
-cp -v ../databases/WT_BR1_comp_hOH7_KSHV_hybrids_ua.hyb.gz \
-      ../databases/WT_BR1_comp_hOH7_KSHV_hybrids_ua.viennad.gz \
+cp -v ../reference_data/WT_BR1_comp_hOH7_KSHV_hybrids_ua.hyb.gz \
+      ../reference_data/WT_BR1_comp_hOH7_KSHV_hybrids_ua.viennad.gz \
       ./
 
 

setup.py

@@ -9,35 +9,78 @@
 
 import setuptools
 import os
+import hybkit
+import glob
 
 # Set project directory
 proj_dir = os.path.abspath(os.path.dirname(__file__))
 
 # Get the long description from the README file
-with open(os.path.join(proj_dir, 'README.md'), encoding='utf-8') as f:
+with open(os.path.join(proj_dir, 'README.rst'), encoding='utf-8') as f:
     long_description = f.read()
 
 # Get the remaining project details variables from the "__about__.py" file.
 about_vars = {}
 with open(os.path.join(proj_dir, 'hybkit', '__about__.py')) as f:
     exec(f.read(), about_vars)
 
+# Dynamically generate reference data file tuples:
+data_files = []
+data_file_dirs = ['scripts', 'scripts_extra', 'databases', 'reference_data', 'hybkit']
+sample_directory_dirs = glob.glob('sample_0*')
+data_file_dirs += sample_directory_dirs
+for item in glob.glob('docs/**', recursive=True):
+    if os.path.isdir(item) and not item.startswith(os.path.join('docs','_')):
+        data_file_dirs.append(item)
+
+for dir_name in data_file_dirs:
+    file_list = [f for f in glob.glob(os.path.join(dir_name, '*'))
+                 if not (
+                         (os.path.isdir(f)) 
+                         or ('/output' in f)
+                         or (f.endswith('.hyb'))
+                         or (f.endswith('.viennad'))
+                         or (f.endswith('.vienna'))
+                         or (f.endswith('.ct'))
+                         or (f.endswith('__'))
+                         or (f.endswith('.pyc'))
+
+                        )]
+    target_dir_name = os.path.join(about_vars['name_and_version'], dir_name)
+    data_files.append((target_dir_name, file_list))
+
 setuptools.setup(
     name='hybkit',
     version=about_vars['__version__'],
     description=about_vars['description'],
     long_description=long_description,
-    long_description_content_type='text/markdown',
+    long_description_content_type='text/x-rst',
     url=about_vars['project_url'],
+    download_url=about_vars['project_download_url'],
     author=about_vars['__author__'],
     author_email=about_vars['__contact__'],
     classifiers=about_vars['classifiers'],
     keywords='genetics genomics ribonomics bioinformatics CLASH qCLASH miRNA',
-    packages=setuptools.find_packages(where='src'),
+    packages=['hybkit'],
+    package_dir={'hybkit': 'hybkit'},
+    package_data={
+                  'hybkit': [os.path.basename(f) for f in glob.glob('hybkit/*')
+                             if not (os.path.basename(f).endswith('.py')
+                             or os.path.basename(f).endswith('__'))]
+                 },
     python_requires='>=3.6',
     project_urls=about_vars['info_urls'],
+    data_files=data_files,
+               #[
+               # ('databases', glob.glob('databases/*')),
+               # ('reference_data', glob.glob('reference_data/*')),
+               #],
+
 
-    install_requires=['matplotlib'],  # Optional
+    install_requires=[
+                      'matplotlib',
+                      'importlib_resources',
+                     ],  # Optional
 
     # To provide executable scripts, use entry points in preference to the
     # "scripts" keyword. Entry points provide cross-platform support and allow