eido 0.2.2__tar.gz → 0.2.4__tar.gz

{eido-0.2.2/eido.egg-info → eido-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: eido
-Version: 0.2.2
+Version: 0.2.4
 Summary: A project metadata validator
 Home-page: https://github.com/pepkit/eido/
 Author: Michal Stolarczyk, Nathan Sheffield
@@ -15,10 +15,11 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
+Requires-Dist: importlib-metadata; python_version < "3.10"
 Requires-Dist: jsonschema>=3.0.1
 Requires-Dist: logmuse>=0.2.5
 Requires-Dist: pandas
-Requires-Dist: peppy>=0.35.7
+Requires-Dist: peppy>=0.40.7
 Requires-Dist: ubiquerg>=0.5.2
 
 # <img src="docs/img/eido.svg" alt="eido logo" height="70">
@@ -28,4 +29,4 @@ Requires-Dist: ubiquerg>=0.5.2
 [![PEP compatible](http://pepkit.github.io/img/PEP-compatible-green.svg)](http://pepkit.github.io)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-[PEP](http://pepkit.github.io) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://eido.databio.org) for usage.
+[PEP](https://pep.databio.org) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://pep.databio.org/eido) for usage.

{eido-0.2.2 → eido-0.2.4}/README.md

@@ -5,4 +5,4 @@
 [![PEP compatible](http://pepkit.github.io/img/PEP-compatible-green.svg)](http://pepkit.github.io)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-[PEP](http://pepkit.github.io) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://eido.databio.org) for usage.
+[PEP](https://pep.databio.org) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://pep.databio.org/eido) for usage.

eido-0.2.4/eido/_version.py

@@ -0,0 +1 @@
+__version__ = "0.2.4"

{eido-0.2.2 → eido-0.2.4}/eido/const.py

@@ -14,8 +14,11 @@ SUBPARSER_MSGS = {
     CONVERT_CMD: "Convert PEP format using filters",
 }
 PROP_KEY = "properties"
-REQUIRED_FILES_KEY = "required_files"
-FILES_KEY = "files"
+
+SAMPLES_KEY = "samples"
+
+TANGIBLE_KEY = "tangible"
+SIZING_KEY = "sizing"
 
 # sample schema input validation key names, these values are required by looper
 # to refer to the dict values
@@ -34,7 +37,9 @@ GENERAL = [
     "FILTERS_CMD",
     "SUBPARSER_MSGS",
 ]
-SCHEMA_SECTIONS = ["PROP_KEY", "REQUIRED_FILES_KEY", "FILES_KEY"]
+
+SCHEMA_SECTIONS = ["PROP_KEY", "TANGIBLE_KEY", "SIZING_KEY"]
+
 SCHEMA_VALIDAION_KEYS = [
     "MISSING_KEY",
     "REQUIRED_INPUTS_KEY",

{eido-0.2.2 → eido-0.2.4}/eido/conversion.py

@@ -1,12 +1,15 @@
-import inspect
 import sys
-import os
-from logging import getLogger
 
-from pkg_resources import iter_entry_points
+if sys.version_info < (3, 10):
+    from importlib_metadata import entry_points
+else:
+    from importlib.metadata import entry_points
+import inspect
+from logging import getLogger
+import os
+from typing import NoReturn
 
 from .exceptions import *
-from typing import NoReturn
 
 _LOGGER = getLogger(__name__)
 
@@ -21,7 +24,7 @@ def pep_conversion_plugins():
     :raise EidoFilterError: if any of the filters has an invalid signature.
     """
     plugins = {}
-    for ep in iter_entry_points("pep.filters"):
+    for ep in entry_points(group="pep.filters"):
         plugin_fun = ep.load()
         if len(list(inspect.signature(plugin_fun).parameters)) != 2:
             raise EidoFilterError(

{eido-0.2.2 → eido-0.2.4}/eido/conversion_plugins.py

@@ -1,4 +1,5 @@
 """ built-in PEP filters """
+
 from typing import Dict
 from .output_formatters import MultilineOutputFormatter
 
@@ -41,8 +42,7 @@ def yaml_pep_filter(p, **kwargs) -> Dict[str, str]:
     """
     from yaml import dump
 
-    data = p.config.to_dict()
-    return {"project": dump(data, default_flow_style=False)}
+    return {"project": dump(p.config, default_flow_style=False)}
 
 
 def csv_pep_filter(p, **kwargs) -> Dict[str, str]:
@@ -69,14 +69,16 @@ def processed_pep_filter(p, **kwargs) -> Dict[str, str]:
     samples_as_objects = kwargs.get("samples_as_objects")
     subsamples_as_objects = kwargs.get("subsamples_as_objects")
 
-    prj_repr = p.config.to_dict()
+    prj_repr = p.config
 
     return {
         "project": str(prj_repr),
-        "samples": str(p.samples)
-        if samples_as_objects
-        else str(p.sample_table.to_csv()),
-        "subsamples": str(p.subsamples)
-        if subsamples_as_objects
-        else str(p.subsample_table.to_csv()),
+        "samples": (
+            str(p.samples) if samples_as_objects else str(p.sample_table.to_csv())
+        ),
+        "subsamples": (
+            str(p.subsamples)
+            if subsamples_as_objects
+            else str(p.subsample_table.to_csv())
+        ),
     }

{eido-0.2.2 → eido-0.2.4}/eido/inspection.py

@@ -7,12 +7,13 @@ from ubiquerg import size
 
 from .const import (
     ALL_INPUTS_KEY,
-    FILES_KEY,
     INPUT_FILE_SIZE_KEY,
     MISSING_KEY,
     PROP_KEY,
-    REQUIRED_FILES_KEY,
     REQUIRED_INPUTS_KEY,
+    SIZING_KEY,
+    TANGIBLE_KEY,
+    SAMPLES_KEY,
 )
 from .schema import read_schema
 from .validation import _validate_sample_object, _get_attr_values
@@ -67,12 +68,12 @@ def get_input_files_size(sample, schema):
     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:
-        all_inputs.update(_get_attr_values(sample, sample_schema_dict[FILES_KEY]))
-    if REQUIRED_FILES_KEY in sample_schema_dict:
+    sample_schema_dict = schema[PROP_KEY][SAMPLES_KEY]["items"]
+    if SIZING_KEY in sample_schema_dict:
+        all_inputs.update(_get_attr_values(sample, sample_schema_dict[SIZING_KEY]))
+    if TANGIBLE_KEY in sample_schema_dict:
         required_inputs = set(
-            _get_attr_values(sample, sample_schema_dict[REQUIRED_FILES_KEY])
+            _get_attr_values(sample, sample_schema_dict[TANGIBLE_KEY])
         )
         all_inputs.update(required_inputs)
     with catch_warnings(record=True) as w:

{eido-0.2.2 → eido-0.2.4}/eido/output_formatters.py

@@ -110,7 +110,7 @@ class MultilineOutputFormatter(BaseOutputFormatter):
             ):
                 value = sample[attribute][sample_index]
             else:
-                value = sample[attribute]
+                value = sample.get(attribute)
 
             sample_row.append(value or "")
 

{eido-0.2.2 → eido-0.2.4}/eido/schema.py

@@ -2,7 +2,7 @@ from logging import getLogger
 
 from peppy.utils import load_yaml
 
-from .const import *
+from .const import SAMPLES_KEY, PROP_KEY
 
 _LOGGER = getLogger(__name__)
 
@@ -21,23 +21,15 @@ def preprocess_schema(schema_dict):
     :return dict: preprocessed schema
     """
     _LOGGER.debug(f"schema ori: {schema_dict}")
-    if "config" in schema_dict[PROP_KEY]:
-        schema_dict[PROP_KEY]["_config"] = schema_dict[PROP_KEY]["config"]
-        del schema_dict[PROP_KEY]["config"]
-    else:
-        _LOGGER.debug("No config section found in schema")
-    if "samples" in schema_dict[PROP_KEY]:
-        schema_dict[PROP_KEY]["_samples"] = schema_dict[PROP_KEY]["samples"]
-        del schema_dict[PROP_KEY]["samples"]
-        if "required" in schema_dict:
-            schema_dict["required"][
-                schema_dict["required"].index("samples")
-            ] = "_samples"
+    if "project" not in schema_dict[PROP_KEY]:
+        _LOGGER.debug("No project section found in schema")
+
+    if SAMPLES_KEY in schema_dict[PROP_KEY]:
         if (
-            "items" in schema_dict[PROP_KEY]["_samples"]
-            and PROP_KEY in schema_dict[PROP_KEY]["_samples"]["items"]
+            "items" in schema_dict[PROP_KEY][SAMPLES_KEY]
+            and PROP_KEY in schema_dict[PROP_KEY][SAMPLES_KEY]["items"]
         ):
-            s_props = schema_dict[PROP_KEY]["_samples"]["items"][PROP_KEY]
+            s_props = schema_dict[PROP_KEY][SAMPLES_KEY]["items"][PROP_KEY]
             for prop, val in s_props.items():
                 if "type" in val and val["type"] in ["string", "number", "boolean"]:
                     s_props[prop] = {}

{eido-0.2.2 → eido-0.2.4}/eido/validation.py

@@ -1,4 +1,5 @@
 import os
+from typing import NoReturn, Mapping, Union
 from copy import deepcopy as dpcpy
 from logging import getLogger
 
@@ -6,28 +7,25 @@ from warnings import warn
 
 from .exceptions import EidoValidationError
 
-
 from pandas.core.common import flatten
 from jsonschema import Draft7Validator
+import peppy
 
-from .const import (
-    FILES_KEY,
-    PROP_KEY,
-    REQUIRED_FILES_KEY,
-)
+from .const import PROP_KEY, SIZING_KEY, TANGIBLE_KEY, SAMPLES_KEY
 from .exceptions import PathAttrNotFoundError
 from .schema import preprocess_schema, read_schema
 
 _LOGGER = getLogger(__name__)
 
 
-def _validate_object(obj, schema, sample_name_colname=False):
+def _validate_object(obj: Mapping, schema: Union[str, dict], sample_name_colname=False):
     """
     Generic function to validate object against a schema
 
     :param Mapping obj: an object to validate
     :param str | dict schema: schema dict to validate against or a path to one
         from the error. Useful when used ith large projects
+
     :raises EidoValidationError: if validation is unsuccessful
     """
     validator = Draft7Validator(schema)
@@ -45,6 +43,10 @@ def _validate_object(obj, schema, sample_name_colname=False):
                 instance_name = error.instance[sample_name_colname]
             except KeyError:
                 instance_name = "project"
+            except TypeError:
+                instance_name = obj["samples"][error.absolute_path[1]][
+                    sample_name_colname
+                ]
             errors_by_type[error.message].append(
                 {
                     "type": error.message,
@@ -58,13 +60,16 @@ def _validate_object(obj, schema, sample_name_colname=False):
         _LOGGER.debug("Validation was successful...")
 
 
-def validate_project(project, schema):
+def validate_project(project: peppy.Project, schema: Union[str, dict]) -> NoReturn:
     """
     Validate a project object against a schema
 
     :param peppy.Project project: a project object to validate
     :param str | dict schema: schema dict to validate against or a path to one
     from the error. Useful when used ith large projects
+
+    :return: NoReturn
+    :raises EidoValidationError: if validation is unsuccessful
     """
     sample_name_colname = project.sample_name_colname
     schema_dicts = read_schema(schema=schema)
@@ -76,7 +81,7 @@ def validate_project(project, schema):
         _LOGGER.debug("Project validation successful")
 
 
-def _validate_sample_object(sample, schemas):
+def _validate_sample_object(sample: peppy.Sample, schemas):
     """
     Internal function that allows to validate a peppy.Sample object without
     requiring a reference to peppy.Project.
@@ -86,20 +91,24 @@ def _validate_sample_object(sample, schemas):
     """
     for schema_dict in schemas:
         schema_dict = preprocess_schema(schema_dict)
-        sample_schema_dict = schema_dict[PROP_KEY]["_samples"]["items"]
+        sample_schema_dict = schema_dict[PROP_KEY][SAMPLES_KEY]["items"]
         _validate_object(sample.to_dict(), sample_schema_dict)
         _LOGGER.debug(
             f"{getattr(sample, 'sample_name', '')} sample validation successful"
         )
 
 
-def validate_sample(project, sample_name, schema):
+def validate_sample(
+    project: peppy.Project, sample_name: Union[str, int], schema: Union[str, dict]
+) -> NoReturn:
     """
     Validate the selected sample object against a schema
 
     :param peppy.Project project: a project object to validate
     :param str | int sample_name: name or index of the sample to validate
     :param str | dict schema: schema dict to validate against or a path to one
+
+    :raises EidoValidationError: if validation is unsuccessful
     """
     sample = (
         project.samples[sample_name]
@@ -112,7 +121,9 @@ def validate_sample(project, sample_name, schema):
     )
 
 
-def validate_config(project, schema):
+def validate_config(
+    project: Union[peppy.Project, dict], schema: Union[str, dict]
+) -> NoReturn:
     """
     Validate the config part of the Project object against a schema
 
@@ -123,17 +134,21 @@ def validate_config(project, schema):
     for schema_dict in schema_dicts:
         schema_cpy = preprocess_schema(dpcpy(schema_dict))
         try:
-            del schema_cpy[PROP_KEY]["_samples"]
+            del schema_cpy[PROP_KEY][SAMPLES_KEY]
         except KeyError:
             pass
         if "required" in schema_cpy:
             try:
-                schema_cpy["required"].remove("_samples")
+                schema_cpy["required"].remove(SAMPLES_KEY)
             except ValueError:
                 pass
-        project_dict = project.to_dict()
-        _validate_object(project_dict, schema_cpy)
-        _LOGGER.debug("Config validation successful")
+        if isinstance(project, dict):
+            _validate_object({"project": project}, schema_cpy)
+
+        else:
+            project_dict = project.to_dict()
+            _validate_object(project_dict, schema_cpy)
+            _LOGGER.debug("Config validation successful")
 
 
 def _get_attr_values(obj, attrlist):
@@ -157,7 +172,11 @@ def _get_attr_values(obj, attrlist):
     return list(flatten([getattr(obj, attr, "") for attr in attrlist]))
 
 
-def validate_input_files(project, schemas, sample_name=None):
+def validate_input_files(
+    project: peppy.Project,
+    schemas: Union[str, dict],
+    sample_name: Union[str, int] = None,
+):
     """
     Determine which of the required and optional files are missing.
 
@@ -197,12 +216,12 @@ def validate_input_files(project, schemas, sample_name=None):
         all_inputs = set()
         required_inputs = set()
         schema = schemas[-1]  # use only first schema, in case there are imports
-        sample_schema_dict = schema["properties"]["_samples"]["items"]
-        if FILES_KEY in sample_schema_dict:
-            all_inputs.update(_get_attr_values(sample, sample_schema_dict[FILES_KEY]))
-        if REQUIRED_FILES_KEY in sample_schema_dict:
+        sample_schema_dict = schema[PROP_KEY][SAMPLES_KEY]["items"]
+        if SIZING_KEY in sample_schema_dict:
+            all_inputs.update(_get_attr_values(sample, sample_schema_dict[SIZING_KEY]))
+        if TANGIBLE_KEY in sample_schema_dict:
             required_inputs = set(
-                _get_attr_values(sample, sample_schema_dict[REQUIRED_FILES_KEY])
+                _get_attr_values(sample, sample_schema_dict[TANGIBLE_KEY])
             )
             all_inputs.update(required_inputs)
 

{eido-0.2.2 → eido-0.2.4/eido.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: eido
-Version: 0.2.2
+Version: 0.2.4
 Summary: A project metadata validator
 Home-page: https://github.com/pepkit/eido/
 Author: Michal Stolarczyk, Nathan Sheffield
@@ -15,10 +15,11 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
+Requires-Dist: importlib-metadata; python_version < "3.10"
 Requires-Dist: jsonschema>=3.0.1
 Requires-Dist: logmuse>=0.2.5
 Requires-Dist: pandas
-Requires-Dist: peppy>=0.35.7
+Requires-Dist: peppy>=0.40.7
 Requires-Dist: ubiquerg>=0.5.2
 
 # <img src="docs/img/eido.svg" alt="eido logo" height="70">
@@ -28,4 +29,4 @@ Requires-Dist: ubiquerg>=0.5.2
 [![PEP compatible](http://pepkit.github.io/img/PEP-compatible-green.svg)](http://pepkit.github.io)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-[PEP](http://pepkit.github.io) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://eido.databio.org) for usage.
+[PEP](https://pep.databio.org) validation tool based on [jsonschema](https://github.com/Julian/jsonschema). See [documentation](http://pep.databio.org/eido) for usage.

eido-0.2.4/eido.egg-info/requires.txt

@@ -0,0 +1,8 @@
+jsonschema>=3.0.1
+logmuse>=0.2.5
+pandas
+peppy>=0.40.7
+ubiquerg>=0.5.2
+
+[:python_version < "3.10"]
+importlib-metadata

eido-0.2.4/requirements/requirements-all.txt

@@ -0,0 +1,6 @@
+importlib-metadata; python_version < '3.10'
+jsonschema>=3.0.1
+logmuse>=0.2.5
+pandas
+peppy>=0.40.7
+ubiquerg>=0.5.2

{eido-0.2.2 → eido-0.2.4}/tests/test_conversions.py

@@ -1,4 +1,10 @@
-from eido.conversion import *
+from eido.conversion import (
+    run_filter,
+    get_available_pep_filters,
+    pep_conversion_plugins,
+    convert_project,
+)
+import peppy
 
 
 class TestConversionInfrastructure:
@@ -74,3 +80,27 @@ class TestConversionInfrastructure:
 
         assert save_result_mock.called
         assert conv_result == {"samples": output_pep_nextflow_taxprofiler}
+
+    def test_multiple_subsamples(self, test_multiple_subs):
+        project = peppy.Project(test_multiple_subs, sample_table_index="sample_id")
+
+        conversion = convert_project(
+            project,
+            "csv",
+        )
+        assert isinstance(conversion["samples"], str)
+        conversion = convert_project(
+            project,
+            "basic",
+        )
+        assert isinstance(conversion["project"], str)
+        conversion = convert_project(
+            project,
+            "yaml",
+        )
+        assert isinstance(conversion["project"], str)
+        conversion = convert_project(
+            project,
+            "yaml-samples",
+        )
+        assert isinstance(conversion["samples"], str)

{eido-0.2.2 → eido-0.2.4}/tests/test_validations.py

@@ -1,7 +1,6 @@
 import urllib
 
 import pytest
-from jsonschema.exceptions import ValidationError
 from peppy import Project
 from peppy.utils import load_yaml
 
@@ -140,9 +139,15 @@ class TestProjectWithoutConfigValidation:
             )
 
     def test_validate_file_existance(
-        self, test_file_existance_pep, test_file_existence_schema
+        self, test_file_existing_pep, test_file_existing_schema
     ):
-        schema_path = test_file_existence_schema
-        prj = Project(test_file_existance_pep)
+        schema_path = test_file_existing_schema
+        prj = Project(test_file_existing_pep)
         with pytest.raises(PathAttrNotFoundError):
             validate_input_files(prj, schema_path)
+
+    def test_validation_values(self, test_schema_value_check, test_file_value_check):
+        schema_path = test_schema_value_check
+        prj = Project(test_file_value_check)
+        with pytest.raises(EidoValidationError):
+            validate_project(project=prj, schema=schema_path)

eido-0.2.2/eido/_version.py

@@ -1 +0,0 @@
-__version__ = "0.2.2"

eido-0.2.2/eido.egg-info/requires.txt

@@ -1,5 +0,0 @@
-jsonschema>=3.0.1
-logmuse>=0.2.5
-pandas
-peppy>=0.35.7
-ubiquerg>=0.5.2

eido-0.2.2/requirements/requirements-all.txt

@@ -1,5 +0,0 @@
-jsonschema>=3.0.1
-logmuse>=0.2.5
-pandas
-peppy>=0.35.7
-ubiquerg>=0.5.2