Merge pull request #23 from pepkit/dev

v0.1.3

docs/changelog.md

@@ -2,6 +2,11 @@
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format. 
 
+## [0.1.3] - 2020-10-07
+### Changed
+- `validate_inputs` function now returns a dictionary with validation data, i.e missing, required_inputs, all_inputs, input_file_size rather than a list of missing files
+- `validate_inputs` function does not modify `Sample` objects
+
 ## [0.1.2] - 2020-08-06
 ### Added
 - license in the package source distribution

eido/_version.py

@@ -1 +1 @@
-__version__ = "0.1.2"
+__version__ = "0.1.3"

eido/const.py

@@ -12,3 +12,17 @@
 PROP_KEY = "properties"
 REQUIRED_FILES_KEY = "required_files"
 FILES_KEY = "files"
+
+# sample schema input validation key names, these values are required by looper
+# to refer to the dict values
+MISSING_KEY = "missing"
+REQUIRED_INPUTS_KEY = "required_inputs"
+ALL_INPUTS_KEY = "all_inputs"
+INPUT_FILE_SIZE_KEY = "input_file_size"
+
+# groups of constants
+GENERAL = ["LOGGING_LEVEL", "PKG_NAME", "INSPECT_CMD", "VALIDATE_CMD", "SUBPARSER_MSGS"]
+SCHEMA_SECTIONS = ["PROP_KEY", "REQUIRED_FILES_KEY", "FILES_KEY"]
+SCHEMA_VALIDAION_KEYS = ["MISSING_KEY", "REQUIRED_INPUTS_KEY", "ALL_INPUTS_KEY", "INPUT_FILE_SIZE_KEY"]
+
+__all__ = GENERAL + SCHEMA_SECTIONS + SCHEMA_VALIDAION_KEYS

eido/eido.py

@@ -4,6 +4,7 @@
 import os
 from copy import deepcopy as dpcpy
 from warnings import catch_warnings as cw
+from pandas.core.common import flatten
 
 from logmuse import init_logger
 from ubiquerg import VersionInHelpParser, size
@@ -234,29 +235,50 @@ def validate_inputs(sample, schema):
 
     :param peppy.Sample sample: sample to investigate
     :param dict schema: schema dict to validate against
-    :return list[str]: list of missing required file paths,
-        empty if all exist.
+    :return dict: dictionary with validation data, i.e missing,
+        required_inputs, all_inputs, input_file_size
     """
-    sample.all_inputs = set()
-    sample.required_inputs = set()
+    def _get_attr_values(obj, attrlist):
+        """
+        Get value corresponding to each given attribute.
+
+        :param Mapping obj: an object to get the attributes from
+        :param str | Iterable[str] attrlist: names of attributes to
+            retrieve values for
+        :return dict: value corresponding to
+            each named attribute; null if this Sample's value for the
+            attribute given by the argument to the "attrlist" parameter is
+            empty/null, or if this Sample lacks the indicated attribute
+        """
+        # If attribute is None, then value is also None.
+        if not attrlist:
+            return None
+        if not isinstance(attrlist, list):
+            attrlist = [attrlist]
+        # Strings contained here are appended later so shouldn't be null.
+        return list(flatten([getattr(obj, attr, "") for attr in attrlist]))
+
+    all_inputs = set()
+    required_inputs = set()
     schema = schema[-1]  # use only first schema, in case there are imports
     sample_schema_dict = schema["properties"]["samples"]["items"]
     if FILES_KEY in sample_schema_dict:
-        sample[FILES_KEY] = sample_schema_dict[FILES_KEY]
-        sample.all_inputs.update(sample.get_attr_values(sample[FILES_KEY]))
+        all_inputs.update(
+            _get_attr_values(sample, sample_schema_dict[FILES_KEY]))
     if REQUIRED_FILES_KEY in sample_schema_dict:
-        sample[REQUIRED_FILES_KEY] = sample_schema_dict[REQUIRED_FILES_KEY]
-        sample.required_inputs = \
-            sample.get_attr_values(sample[REQUIRED_FILES_KEY])
-        sample.all_inputs.update(sample.required_inputs)
+        required_inputs = set(_get_attr_values(
+            sample, sample_schema_dict[REQUIRED_FILES_KEY]))
+        all_inputs.update(required_inputs)
     with cw(record=True) as w:
-        sample.input_file_size = \
-            sum([size(f, size_str=False) or 0.0
-                 for f in sample.all_inputs if f != ""])/(1024 ** 3)
+        input_file_size = sum([size(f, size_str=False) or 0.0
+                               for f in all_inputs if f != ""])/(1024 ** 3)
         if w:
-            _LOGGER.warning("{} input files missing, job input size was not"
-                            " calculated accurately".format(len(w)))
-    return [i for i in sample.required_inputs if not os.path.exists(i)]
+            _LOGGER.warning(f"{len(w)} input files missing, job input size was "
+                            f"not calculated accurately")
+
+    return {MISSING_KEY: [i for i in required_inputs if not os.path.exists(i)],
+            REQUIRED_INPUTS_KEY: required_inputs, ALL_INPUTS_KEY: all_inputs,
+            INPUT_FILE_SIZE_KEY: input_file_size}
 
 
 def inspect_project(p, sample_names=None, max_attr=10):

requirements/requirements-all.txt

@@ -1,5 +1,6 @@
 ubiquerg>=0.5.2
 logmuse>=0.2.5
 jsonschema>=3.0.1
-peppy>=0.30.1
+peppy>=0.31.0
 yacman>=0.6.7
+pandas

requirements/requirements-dev.txt

@@ -1,2 +0,0 @@
-mock>=2.0.0
-pytest>=3.0.7

requirements/requirements-test.txt

@@ -1,3 +1,4 @@
+mock>=2.0.0
 pytest>=4.6.9
 pytest-cov>=2.8.1
 coveralls