Merge branch 'bigbio:master' into extended

.gitignore

@@ -1,8 +1,123 @@
-.idea/
-.idea*
-dist/
-build/
-*egg-info/
+# repo specific
 /experimental_design.tsv
 /openms.tsv
-__pycache__
+
+## Typical Python package ignorance
+
+.DS_Store
+
+.coverage
+.pytest_cache
+docs/api/_build
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+testing*
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# backup files
+*~
+*\?
+
+# Jetbrains IDEs
+.idea
+pip-wheel-metadata
+.vscode
+.*.sw?

sdrf_pipelines/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.21"

sdrf_pipelines/maxquant/__init__.py

@@ -1 +0,0 @@
-

sdrf_pipelines/maxquant/maxquant.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 Created on Sun Apr 19 09:46:14 2020
 
@@ -992,7 +991,7 @@ def maxquant_convert(
                         for j in range(arr.shape[1]):
                             arr[i][j] = sorted(arr[i])[j]
 
-                label_arr = np.array(list(set([tuple(t) for t in arr])))
+                label_arr = np.array(list({tuple(t) for t in arr}))
                 file2silac_shape[raw] = label_arr.shape
                 label_arr.sort()
                 if label_arr.shape[0] == 2:  # Support two or three silac labels
@@ -1099,7 +1098,7 @@ def maxquant_convert(
         fastaFilePath_node = doc.createElement("fastaFilePath")
         fastaFilePath_node.appendChild(doc.createTextNode(fastaFilePath))
         identifierParseRule = doc.createElement("identifierParseRule")
-        identifierParseRule.appendChild(doc.createTextNode(">([^\s]*)"))
+        identifierParseRule.appendChild(doc.createTextNode(r">([^\s]*)"))
         descriptionParseRule = doc.createElement("descriptionParseRule")
         descriptionParseRule.appendChild(doc.createTextNode(">(.*)"))
         taxonomyParseRule = doc.createElement("taxonomyParseRule")

sdrf_pipelines/msstats/msstats.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-
-
 import re
 
 import pandas as pd

sdrf_pipelines/openms/unimod.py

@@ -62,14 +62,14 @@ def search_mods_by_keyword(self, keyword: str = None):
         return found_list
 
     def _get_elements(self, node):
-        for e in node.findall("%selements/%selem" % (self.xmlns, self.xmlns)):
+        for e in node.findall(f"{self.xmlns}elements/{self.xmlns}elem"):
             ea = e.attrib
             self.elements[ea["title"]] = ea
             if re.match(r"[A-Z]", ea["title"][:1]):
-                self.elements["%s%s" % (int(round(float(ea["mono_mass"]))), ea["title"])] = ea
+                self.elements["{}{}".format(int(round(float(ea["mono_mass"]))), ea["title"])] = ea
 
     def _get_modifications(self, node):
-        for e in node.findall("%smodifications/%smod" % (self.xmlns, self.xmlns)):
+        for e in node.findall(f"{self.xmlns}modifications/{self.xmlns}mod"):
             ma = e.attrib
             d = e.findall("%sdelta" % self.xmlns)[0]
             for k in d.attrib.keys():

sdrf_pipelines/parse_sdrf.py

@@ -9,6 +9,7 @@
 import click
 import pandas as pd
 
+from sdrf_pipelines import __version__
 from sdrf_pipelines.maxquant.maxquant import Maxquant
 from sdrf_pipelines.msstats.msstats import Msstats
 from sdrf_pipelines.normalyzerde.normalyzerde import NormalyzerDE
@@ -22,6 +23,7 @@
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
 
 
+@click.version_option(version=__version__, package_name="sdrf_pipelines", message="%(package)s %(version)s")
 @click.group(context_settings=CONTEXT_SETTINGS)
 def cli():
     """

sdrf_pipelines/sdrf/sdrf_schema.py

@@ -104,7 +104,7 @@ def default_message(self):
         Return a message for the validation of the Ontology Term
         :return:
         """
-        return "the term name or title can't be found in the ontology -- {}".format(self._ontology_name)
+        return f"the term name or title can't be found in the ontology -- {self._ontology_name}"
 
     @staticmethod
     def validate_ontology_terms(cell_value, labels):
@@ -285,7 +285,7 @@ def _get_column_pairs(self, panda_sdrf):
 
         for column in columns_to_pair:
             if column.name not in panda_sdrf and column._optional is False:
-                message = "The column {} is not present in the SDRF".format(column.name)
+                message = f"The column {column.name} is not present in the SDRF"
                 errors.append(LogicError(message, error_type=logging.ERROR))
             elif column.name in panda_sdrf:
                 column_pairs.append((panda_sdrf[column.name], column))

sdrf_pipelines/utils/exceptions.py

@@ -26,12 +26,12 @@ def __str__(self) -> str:
                 self.row, self.column, self.value, self.message, logging.getLevelName(self._error_type)
             )
         else:
-            return "{} -- {}".format(self.message, logging.getLevelName(self._error_type))
+            return f"{self.message} -- {logging.getLevelName(self._error_type)}"
 
 
 class AppConfigException(AppException):
     def __init__(self, value):
-        super(AppConfigException, self).__init__(value)
+        super().__init__(value)
 
 
 class ConfigManagerException(Exception):

sdrf_pipelines/zooma/ols.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """
 OLS API wrapper
 

setup.py

@@ -1,14 +1,30 @@
-from __future__ import print_function
+import codecs
+import os.path
 
 from setuptools import find_packages
 from setuptools import setup
 
-with open("README.md", "r", encoding="UTF-8") as fh:
+with open("README.md", encoding="UTF-8") as fh:
     long_description = fh.read()
 
+
+def read(rel_path):
+    here = os.path.abspath(os.path.dirname(__file__))
+    with codecs.open(os.path.join(here, rel_path), "r") as fp:
+        return fp.read()
+
+
+def get_version(rel_path):
+    for line in read(rel_path).splitlines():
+        if line.startswith("__version__"):
+            delim = '"' if '"' in line else "'"
+            return line.split(delim)[1]
+    raise RuntimeError("Unable to find version string.")
+
+
 setup(
     name="sdrf-pipelines",
-    version="0.0.21",
+    version=get_version("sdrf_pipelines/__init__.py"),
     author="BigBio Team",
     author_email="[email protected]",
     description="Translate, convert SDRF to configuration pipelines",