tol-sdk 1.7.5b0__py3-none-any.whl → 1.7.5b3__py3-none-any.whl

tol/core/operator/detail_getter.py

@@ -82,7 +82,7 @@ class DetailGetter(ABC):
         for id_ in object_ids:
             seekable_objects.seek(0)
             for obj in seekable_objects:
-                if obj.id == id_:
+                if str(obj.id) == str(id_):
                     yield obj
                     break
             else:

tol/ena/client.py

@@ -116,12 +116,13 @@ class EnaApiClient(HttpClient):
         Returns the URL and parameters for a detail query.
         """
         if object_type == 'checklist':
-            ids = ','.join(object_ids)
+            ids = ','.join(str(id_) for id_ in object_ids)
             url = f'{self.__ena_url}/ena/browser/api/xml/{ids}'
             params = {}
             return url, params
         if object_type == 'submittable_taxon':
-            ids = ','.join(object_ids)
+            # This is actually called separately for each taxon id
+            ids = ','.join(str(id_) for id_ in object_ids)
             url = f'{self.__ena_url}/ena/taxonomy/rest/tax-id/{ids}'
             params = {}
             return url, params

tol/flows/converters/__init__.py

@@ -34,6 +34,8 @@ from .gap_assembly_to_elastic_assembly_analysis_converter import GapAssemblyToEl
 from .genome_notes_genome_note_to_elastic_genome_note_converter import GenomeNotesGenomeNoteToElasticGenomeNoteConverter  # noqa F401
 from .goat_taxon_to_elastic_species_converter import GoatTaxonToElasticSpeciesConverter  # noqa F401
 from .grit_issue_to_elastic_curation_converter import GritIssueToElasticCurationConverter  # noqa F401
+from .incoming_sample_to_ena_sample_converter import IncomingSampleToEnaSampleConverter # noqa
+from .incoming_sample_to_incoming_sample_with_lists_converter import IncomingSampleToIncomingSampleWithListsConverter  # noqa F401
 from .informatics_tolid_to_elastic_tolid_converter import InformaticsTolidToElasticTolidConverter  # noqa F401
 from .labwhere_location_to_elastic_sample_update_converter import LabwhereLocationToElasticSampleUpdateConverter  # noqa F401
 from .labwhere_location_to_sts_tray_converter import LabwhereLocationToStsTrayConverter  # noqa F401

tol/flows/converters/incoming_sample_to_ena_sample_converter.py

@@ -0,0 +1,130 @@
+# SPDX-FileCopyrightText: 2025 Genome Research Ltd.
+# SPDX-License-Identifier: MIT
+
+import re
+from dataclasses import dataclass
+from typing import Iterable
+
+from tol.core import DataObject, DataObjectToDataObjectOrUpdateConverter
+
+
+class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter):
+
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        ena_checklist_id: str
+        project_name: str
+
+    __slots__ = ['__config']
+    __config: Config
+
+    def __init__(self, data_object_factory, config: Config) -> None:
+        super().__init__(data_object_factory)
+        self.__config = config
+        self._data_object_factory = data_object_factory
+
+    def convert(self, data_object: DataObject) -> Iterable[DataObject]:
+        """
+        converting the samples DataObject into ENA format
+        """
+        s = data_object
+        attributes = {
+            'ENA-CHECKLIST': self.__config.ena_checklist_id,
+            'organism part': self.__replace_underscores(
+                s.attributes.get('ORGANISM_PART')),
+            'lifestage': (
+                'spore-bearing structure'
+                if s.attributes.get('LIFESTAGE') == 'SPORE_BEARING_STRUCTURE'
+                else self.__replace_underscores(
+                    s.attributes.get('LIFESTAGE'))
+            ),
+            'project name':
+                self.__config.project_name,
+            'collected by':
+                self.__replace_underscores(
+                    s.attributes.get('COLLECTED_BY')),
+            'collection date':
+                self.__replace_underscores(
+                    s.attributes.get('DATE_OF_COLLECTION')).lower(),
+            'geographic location (country and/or sea)':
+                self.__collection_country(s).replace('_', ' '),
+            'geographic location (latitude)':
+                self.__replace_underscores(
+                    s.attributes.get('DECIMAL_LATITUDE')).lower(),
+            'geographic location (latitude) units':
+                'DD',
+            'geographic location (longitude)':
+                self.__replace_underscores(
+                    s.attributes.get('DECIMAL_LONGITUDE')).lower(),
+            'geographic location (longitude) units':
+                'DD',
+            'geographic location (region and locality)':
+                self.__collection_region(s).replace('_', ' '),
+            'identified_by':
+                self.__replace_underscores(
+                    s.attributes.get('IDENTIFIED_BY')),
+            'habitat':
+                self.__replace_underscores(
+                    s.attributes.get('HABITAT')),
+            'identifier_affiliation':
+                self.__replace_underscores(
+                    s.attributes.get('IDENTIFIER_AFFILIATION')),
+            'sex':
+                self.__replace_underscores(
+                    s.attributes.get('SEX')),
+            'relationship':
+                self.__replace_underscores(
+                    s.attributes.get('RELATIONSHIP')),
+            'SYMBIONT':
+                'Y' if s.attributes.get('SYMBIONT') == 'SYMBIONT' else 'N',
+            'collecting institution':
+                self.__replace_underscores(
+                    s.attributes.get('COLLECTOR_AFFILIATION'))
+        }
+        if self.__sanitise(s.attributes.get('DEPTH')) != '':
+            attributes['geographic location (depth)'] = s.attributes.get('DEPTH')
+            attributes['geographic location (depth) units'] = 'm'
+        if self.__sanitise(s.attributes.get('ELEVATION')) != '':
+            attributes['geographic location (elevation)'] = s.attributes.get('ELEVATION')
+            attributes['geographic location (elevation) units'] = 'm'
+        if self.__sanitise(s.attributes.get('ORIGINAL_COLLECTION_DATE')) != '':
+            attributes['original collection date'] = s.attributes.get('ORIGINAL_COLLECTION_DATE')
+        if self.__sanitise(s.attributes.get('ORIGINAL_GEOGRAPHIC_LOCATION')) != '':
+            attributes['original geographic location'] = self.__replace_underscores(s.attributes.get('ORIGINAL_GEOGRAPHIC_LOCATION'))  # noqa
+        if s.attributes.get('GAL') is not None:
+            attributes['GAL'] = s.attributes.get('GAL')
+        if s.attributes.get('VOUCHER_ID') is not None:
+            attributes['specimen_voucher'] = s.attributes.get('VOUCHER_ID')
+        if s.attributes.get('SPECIMEN_ID') is not None:
+            attributes['specimen_id'] = s.attributes.get('SPECIMEN_ID')
+        if s.attributes.get('GAL_SAMPLE_ID') is not None:
+            attributes['GAL_sample_id'] = s.attributes.get('GAL_SAMPLE_ID')
+        if s.attributes.get('CULTURE_OR_STRAIN_ID') is not None:
+            attributes['culture_or_strain_id'] = s.attributes.get('CULTURE_OR_STRAIN_ID')
+
+        ret = self._data_object_factory(
+            'sample',
+            s.id,
+            attributes=attributes,
+        )
+        yield ret
+
+    def __collection_country(self, data_object: DataObject):
+        return re.split(
+            r'\s*\|\s*',
+            data_object.attributes.get('COLLECTION_LOCATION'))[0]
+
+    def __collection_region(self, data_object: DataObject):
+        return ' | '.join(re.split(
+            r'\s*\|\s*',
+            data_object.attributes.get('COLLECTION_LOCATION'))[1:])
+
+    def __replace_underscores(self, value):
+        if type(value) != str:
+            return value
+        return self.__sanitise(value, '').replace('_', ' ')
+
+    def __sanitise(self, value, default_value=''):
+        if value is None:
+            return default_value
+        return value

tol/flows/converters/incoming_sample_to_incoming_sample_with_lists_converter.py

@@ -0,0 +1,46 @@
+# SPDX-FileCopyrightText: 2025 Genome Research Ltd.
+# SPDX-License-Identifier: MIT
+
+from dataclasses import dataclass
+from typing import Iterable
+
+from tol.core import DataObject, DataObjectToDataObjectOrUpdateConverter
+
+
+class IncomingSampleToIncomingSampleWithListsConverter(DataObjectToDataObjectOrUpdateConverter):
+
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        fields_to_convert: str
+        separator: str = '|'
+
+    __slots__ = ['__config']
+    __config: Config
+
+    def __init__(self, data_object_factory, config: Config) -> None:
+        super().__init__(data_object_factory)
+        self.__config = config
+        self._data_object_factory = data_object_factory
+
+    def convert(self, data_object: DataObject) -> Iterable[DataObject]:
+        """
+        converting the samples DataObject into ENA format
+        """
+
+        ret = self._data_object_factory(
+            data_object.type,
+            data_object.id,
+            attributes={
+                k: v for k, v in data_object.attributes.items()
+                if k not in self.__config.fields_to_convert
+            } | {
+                field: self.__convert_to_list(data_object.get_field_by_name(field))
+                for field in self.__config.fields_to_convert
+            }
+        )
+        yield ret
+
+    def __convert_to_list(self, value: str | None) -> list[str]:
+        if not value:
+            return []
+        return [item.strip() for item in value.split(self.__config.separator)]

tol/sql/auth/models.py

@@ -19,6 +19,7 @@ from sqlalchemy.ext.declarative import declared_attr
 from sqlalchemy.orm import (
     Mapped,
     Session,
+    joinedload,
     mapped_column,
     relationship
 )
@@ -184,7 +185,7 @@ def create_models(
 
         id: Mapped[str] = mapped_column(  # noqa A003
             primary_key=True,
-            name=None if not prefix_with_name else 'state_id'
+            name='state_id' if prefix_with_name else None
         )
 
         created_at: Mapped[datetime] = mapped_column(
@@ -257,13 +258,13 @@ def create_models(
         id: Mapped[int] = mapped_column(  # noqa A003
             primary_key=True,
             autoincrement=True,
-            name=None if not prefix_with_name else 'user_id'
+            name='user_id' if prefix_with_name else None
         )
 
-        _tokens: Mapped[list['Token']] = relationship(
+        _tokens: Mapped[list[Token]] = relationship(
             back_populates='user'
         )
-        _role_bindings: Mapped[list['RoleBinding']] = relationship(
+        _role_bindings: Mapped[list[RoleBinding]] = relationship(
             back_populates='user'
         )
 
@@ -340,7 +341,7 @@ def create_models(
 
     class _TokenPKMixin:
         """
-        Has an integer has a primary key.
+        Has an integer as a primary key.
 
         This is all that is needed in most apps,
         and is the default.
@@ -403,11 +404,19 @@ def create_models(
             token: str
         ) -> Optional[Token]:
 
-            return sess.query(
-                cls
-            ).filter_by(
-                token=token
-            ).one_or_none()
+            return (
+                sess.query(cls)
+                .filter_by(token=token)
+                .options(
+                    # Join through to the Role table when fetching a Token so
+                    # that SQLAlchemy only fires one SELECT query instead of
+                    # four to get `token.user._role_bindings.role.name`
+                    joinedload(cls.user)
+                    .joinedload(User._role_bindings)
+                    .joinedload(RoleBinding.role)
+                )
+                .one_or_none()
+            )
 
         @classmethod
         def get_or_create(
@@ -475,14 +484,14 @@ def create_models(
         id: Mapped[int] = mapped_column(  # noqa A003
             primary_key=True,
             autoincrement=True,
-            name=None if not prefix_with_name else 'role_id'
+            name='role_id' if prefix_with_name else None
         )
 
         name: Mapped[str] = mapped_column(
             unique=True
         )
 
-        _role_bindings: Mapped[list['RoleBinding']] = relationship(
+        _role_bindings: Mapped[list[RoleBinding]] = relationship(
             back_populates='role'
         )
 

tol/validators/__init__.py

@@ -6,6 +6,8 @@ from .allowed_keys import AllowedKeysValidator  # noqa
 from .allowed_values import AllowedValuesValidator  # noqa
 from .allowed_values_from_datasource import AllowedValuesFromDataSourceValidator  # noqa
 from .assert_on_condition import AssertOnConditionValidator  # noqa
+from .converter_and_validate import ConverterAndValidateValidator  # noqa
+from .ena_checklist import EnaChecklistValidator # noqa
 from .mutually_exclusive import MutuallyExclusiveValidator  # noqa
 from .ena_submittable import EnaSubmittableValidator  # noqa
 from .regex import Regex, RegexValidator  # noqa
@@ -15,6 +17,5 @@ from .sts_fields import StsFieldsValidator  # noqa
 from .tolid import TolidValidator  # noqa
 from .unique_values import UniqueValuesValidator  # noqa
 from .unique_whole_organisms import UniqueWholeOrganismsValidator  # noqa
-# Conditions are used where validators are defined, not just within validators
 from .interfaces import Condition  # noqa
 from .min_one_valid_value import MinOneValidValueValidator   # noqa

tol/validators/allowed_keys.py

@@ -26,7 +26,8 @@ class AllowedKeysValidator(Validator):
 
     def __init__(
         self,
-        config: Config
+        config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/allowed_values.py

@@ -27,7 +27,8 @@ class AllowedValuesValidator(Validator):
 
     def __init__(
         self,
-        config: Config
+        config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/allowed_values_from_datasource.py

@@ -17,7 +17,6 @@ class AllowedValuesFromDataSourceValidator(Validator):
     """
     @dataclass(slots=True, frozen=True, kw_only=True)
     class Config:
-        allowed_values: List[str | int | float] | None = None
         datasource_instance_id: int
         datasource_object_type: str
         datasource_field_name: str
@@ -30,22 +29,19 @@ class AllowedValuesFromDataSourceValidator(Validator):
     def __init__(
         self,
         config: Config,
+        allowed_values: List[str | int | float] | None = None,  # For testing
+        **kwargs
     ) -> None:
 
         super().__init__()
 
         self.__config = config
-        self.__cached_list = self.__config.allowed_values \
+        self.__cached_list = allowed_values \
             or self.__initialize_list_from_datasource()
 
-        if self.__config.allowed_values is None:
-            self.__cached_list = self.__initialize_list_from_datasource()
-        else:
-            self.__cached_list = self.__config.allowed_values
-
     def __initialize_list_from_datasource(self) -> List[str | int | float]:
         dsi = portaldb().get_one('data_source_instance', self.__config.datasource_instance_id)
-        ds = DataSourceUtils.get_data_source_by_data_source_instance(dsi)
+        ds = DataSourceUtils.get_datasource_by_datasource_instance(dsi)
         return [
             obj.get_field_by_name(
                 self.__config.datasource_field_name
@@ -59,8 +55,11 @@ class AllowedValuesFromDataSourceValidator(Validator):
         obj: DataObject
     ) -> None:
         field_value = obj.get_field_by_name(self.__config.field_name)
-        if field_value not in self.__cached_list:
-            print(self.__cached_list)
+        if not field_value:
+            return
+        if not isinstance(field_value, list):
+            field_value = [field_value]
+        if any(value not in self.__cached_list for value in field_value):
             multiple_cached_values = len(self.__cached_list) > 1
 
             cached_list_str = ''

tol/validators/assert_on_condition.py

@@ -7,7 +7,7 @@ from typing import List
 
 from tol.core import DataObject, Validator
 
-from .interfaces import Condition, ConditionEvaluator
+from .interfaces import Condition, ConditionDict, ConditionEvaluator
 
 
 class AssertOnConditionValidator(Validator, ConditionEvaluator):
@@ -19,13 +19,13 @@ class AssertOnConditionValidator(Validator, ConditionEvaluator):
     """
     @dataclass(slots=True, frozen=True, kw_only=True)
     class Config:
-        condition: Condition
-        assertions: List[Condition]
+        condition: ConditionDict
+        assertions: List[ConditionDict]
 
     __slots__ = ['__config']
     __config: Config
 
-    def __init__(self, config: Config) -> None:
+    def __init__(self, config: Config, **kwargs) -> None:
         super().__init__()
 
         self.__config = config
@@ -33,10 +33,10 @@ class AssertOnConditionValidator(Validator, ConditionEvaluator):
     def _validate_data_object(self, obj: DataObject) -> None:
         # Check condition atribute
         # (only perform the assertions if the condition passes)
-        if self._does_condition_pass(self.__config.condition, obj):
+        if self._does_condition_pass(Condition.from_dict(self.__config.condition), obj):
             # Perform each assertion
             for assertion in self.__config.assertions:
-                self.__perform_assertion(obj, assertion)
+                self.__perform_assertion(obj, Condition.from_dict(assertion))
 
     def __perform_assertion(self, obj: DataObject, assertion: Condition) -> None:
         # There's only an error or warning if the assertion condition fails

tol/validators/converter_and_validate.py

@@ -0,0 +1,93 @@
+# SPDX-FileCopyrightText: 2025 Genome Research Ltd.
+#
+# SPDX-License-Identifier: MIT
+
+import importlib
+from dataclasses import dataclass
+
+from tol.core import DataObject
+from tol.core.factory import DataObjectFactory
+from tol.core.validate import ValidationResult, Validator
+
+
+class ConverterAndValidateValidator(Validator):
+    """
+    Convert DataObjects, validate the converted ones, and return the original
+    input unchanged. Inner validator results are not merged here.
+
+    {
+        "converters": [{
+            "module": "<path.to.module>",
+            "class_name": "<path.to.ConverterClass>",
+            "config": { ... }
+        }],
+        "validators": [{
+            "module": "<path.to.module>",
+            "class_name": "<path.to.ValidatorClass>",
+            "config": { ... }
+        }]
+    }
+
+    """
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        converters: list[dict]
+        validators: list[dict]
+
+    __slots__ = [
+        '__converters',
+        '__validators'
+    ]
+
+    def __init__(
+        self,
+        config: Config,
+        data_object_factory: DataObjectFactory,
+        **kwargs
+    ) -> None:
+        super().__init__()
+        self.__converters = []
+        self.__validators = []
+
+        for conv in config.converters:
+            __module = importlib.import_module(conv.get('module'))
+            converter_class = getattr(__module, conv.get('class_name'))
+
+            converter_conf = converter_class.Config(
+                **conv.get('config')
+            )
+            self.__converters.append(converter_class(
+                data_object_factory=data_object_factory,
+                config=converter_conf,
+            ))
+        for val in config.validators:
+            __module = importlib.import_module(val.get('module'))
+            validator_class = getattr(__module, val.get('class_name'))
+
+            validator_conf = validator_class.Config(
+                **val.get('config')
+            )
+            self.__validators.append(validator_class(
+                data_object_factory=data_object_factory,
+                config=validator_conf,
+            ))
+
+    def _validate_data_object(self, obj: DataObject) -> None:
+        converted_objs = [obj]
+        for converter in self.__converters:
+            converted_objs = converter.convert_iterable(converted_objs)
+        for obj in converted_objs:
+            for validator in self.__validators:
+                validator._validate_data_object(obj)
+
+    @property
+    def results(self) -> list[ValidationResult]:
+        return [result for validator in self.__validators for result in validator.results]
+
+    @property
+    def warnings(self) -> list[ValidationResult]:
+        return [warning for validator in self.__validators for warning in validator.warnings]
+
+    @property
+    def errors(self) -> list[ValidationResult]:
+        return [error for validator in self.__validators for error in validator.errors]

tol/validators/ena_checklist.py

@@ -0,0 +1,73 @@
+# SPDX-FileCopyrightText: 2025 Genome Research Ltd.
+#
+# SPDX-License-Identifier: MIT
+
+import re
+from dataclasses import dataclass
+
+from tol.core import DataSource
+from tol.core.data_object import DataObject
+from tol.core.validate import Validator
+from tol.sources.ena import ena
+
+
+class EnaChecklistValidator(Validator):
+    """
+    validates the ENA_CHECKLIST for each samples
+    """
+
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        ena_checklist_id: str
+
+    __slots__ = ['__config']
+    __config: Config
+
+    def __init__(self, config: Config, datasource: DataSource = ena(), **kwargs) -> None:
+        super().__init__()
+        self.__config = config
+        self._datasource = datasource
+
+    def _validate_data_object(self, obj: DataObject) -> None:
+        ena_datasource = self._datasource
+        ena_checklist = ena_datasource.get_one('checklist', self.__config.ena_checklist_id)
+
+        validations = ena_checklist.attributes['checklist']
+        for key in validations:
+            field_name = key
+            if 'field' in validations[key]:
+                field_name = validations[key]['field']
+            if 'mandatory' in validations[key] and key not in obj.attributes:
+                self.add_error(object_id=obj.id, detail='Must be given', field=[field_name])
+                continue
+            if 'mandatory' in validations[key] and obj.attributes[key] is None:
+                self.add_error(object_id=obj.id, detail='Must be given', field=[field_name])
+                continue
+            if 'mandatory' in validations[key] and obj.attributes.get(key) == '':
+                self.add_error(
+                    object_id=obj.id,
+                    detail='Must not be empty', field=[field_name]
+                )
+
+            if 'restricted text' in validations[key] and key in obj.attributes:
+                for condition in validations[key]:
+                    if type(condition) == str and '(' in condition:
+                        regex = condition
+                compiled_re = re.compile(regex)
+                if not compiled_re.search(obj.attributes.get(key)):
+                    self.add_error(
+                        object_id=obj.id,
+                        detail='Must match specific pattern', field=[field_name]
+                    )
+
+            # Check against allowed values
+            if 'text choice' in validations[key] and key in obj.attributes:
+                for condition in validations[key]:
+                    if type(condition) == list:
+                        allowed_values = condition
+                if obj.attributes.get(key).lower() not in \
+                        [x.lower() for x in allowed_values]:
+                    self.add_error(
+                        object_id=obj.id,
+                        detail='Must be in allowed values', field=[field_name]
+                    )

tol/validators/ena_submittable.py

@@ -28,6 +28,7 @@ class EnaSubmittableValidator(Validator):
         self,
         config: Config,
         ena_datasource: DataSource | None = ena(),  # For testing
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/interfaces/__init__.py

@@ -2,4 +2,4 @@
 #
 # SPDX-License-Identifier: MIT
 
-from .condition_evaluator import Condition, ConditionEvaluator  # noqa
+from .condition_evaluator import Condition, ConditionDict, ConditionEvaluator  # noqa

tol/validators/interfaces/condition_evaluator.py

@@ -4,11 +4,18 @@
 
 from abc import ABC
 from dataclasses import dataclass
-from typing import Any, Tuple
+from typing import Any, Dict, Tuple, cast
 
 from tol.core import DataObject
 
 
+ConditionDict = Dict[str, str | Any | bool]
+"""
+The dict representation of a Condition. Conditions can be constructed
+from such a dict through Condition.from_dict(condition_dict)
+"""
+
+
 @dataclass(slots=True)
 class Condition:
     field: str
@@ -21,6 +28,40 @@ class Condition:
     def __repr__(self) -> str:
         return f'{self.field} {self.operator} {self.value}'
 
+    @staticmethod
+    def from_dict(condition_dict: ConditionDict) -> 'Condition':
+        """
+        A means of instantiating a Condition from a dictionary.
+        This is a separate method (rather than constructing with kwargs
+        like `Condition(**condition_dict))`) to allow for both precense
+        and type checking for each field.
+        """
+        try:
+            # Extract fields
+            field = condition_dict['field']
+            operator = condition_dict['operator']
+            value = condition_dict['value']
+            is_error = condition_dict.get('is_error', True)
+
+            # Ensure fields are the correct type
+            if not isinstance(field, str) and not isinstance(operator, str):
+                raise Exception(
+                    f'Dictionary {condition_dict} not in valid format '
+                    f'to convert to Condition (type of condition dict incorrect)'
+                )
+
+            return Condition(
+                cast(str, field),
+                cast(str, operator),
+                value,
+                cast(bool, is_error),
+            )
+        except IndexError as e:
+            raise Exception(
+                f'Dictionary {condition_dict} not in valid format '
+                f'to convert to Condition (key "{e.args[0]}" not found)'
+            )
+
 
 class ConditionEvaluator(ABC):
     """

tol/validators/min_one_valid_value.py

@@ -24,6 +24,7 @@ class MinOneValidValueValidator(Validator):
     def __init__(
         self,
         config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/mutually_exclusive.py

@@ -7,7 +7,7 @@ from typing import Any, List
 
 from tol.core import DataObject, Validator
 
-from .interfaces import Condition, ConditionEvaluator
+from .interfaces import Condition, ConditionDict, ConditionEvaluator
 
 
 class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
@@ -19,12 +19,16 @@ class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
     """
     @dataclass(slots=True, frozen=True, kw_only=True)
     class Config:
-        first_field_where: Condition
-        second_field_where: Condition
+        first_field_where: ConditionDict
+        second_field_where: ConditionDict
         target_fields: List[str]
         detail: str | None = None
 
         def _get_error_message(self) -> str:
+            # Extract conditions
+            first_condition = Condition.from_dict(self.first_field_where)
+            second_condition = Condition.from_dict(self.second_field_where)
+
             # Use a pre-defined, hard-coded detail message if one was not provided
             if self.detail is None:
                 multiple_target_fields = len(self.target_fields) > 1
@@ -47,8 +51,8 @@ class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
 
                 return (
                     f'The field{possible_plural} {target_fields_str} cannot have the same '
-                    f'value{possible_plural} both when {self.first_field_where} and when '
-                    f'{self.second_field_where}'
+                    f'value{possible_plural} both when {first_condition} and when '
+                    f'{second_condition}'
                 )
             else:
                 return self.detail
@@ -58,7 +62,7 @@ class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
     __first_list: List[Any]
     __second_list: List[Any]
 
-    def __init__(self, config: Config) -> None:
+    def __init__(self, config: Config, **kwargs) -> None:
         super().__init__()
 
         self.__config = config
@@ -67,7 +71,7 @@ class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
 
     def _validate_data_object(self, obj: DataObject) -> None:
         # Check first field
-        if self._does_condition_pass(self.__config.first_field_where, obj):
+        if self._does_condition_pass(Condition.from_dict(self.__config.first_field_where), obj):
             # Check whether the values of the target fields were found in the second list
             if [
                 obj.get_field_by_name(target_field)
@@ -86,7 +90,7 @@ class MutuallyExclusiveValidator(Validator, ConditionEvaluator):
                 ]
             )
         # Check second field (same as the first condition, but for the second!)
-        elif self._does_condition_pass(self.__config.second_field_where, obj):
+        elif self._does_condition_pass(Condition.from_dict(self.__config.second_field_where), obj):
             # Check whether the values of the target fields were found in the first list
             if [
                 obj.get_field_by_name(target_field)

tol/validators/regex.py

@@ -10,6 +10,12 @@ from tol.core import DataObject
 from tol.core.validate import Validator
 
 
+RegexDict = dict[
+    str,
+    str | bool | list[Any],
+]
+
+
 @dataclass(frozen=True, kw_only=True)
 class Regex:
     key: str
@@ -20,7 +26,10 @@ class Regex:
 
     def is_allowed(self, __v: Any) -> bool:
         # Check regex
-        return re.search(self.regex, str(__v or ''))
+        return bool(re.search(
+            self.regex,
+            str(__v) if __v is not None else ''
+        ))
 
 
 class RegexValidator(Validator):
@@ -31,19 +40,20 @@ class RegexValidator(Validator):
     """
     @dataclass(slots=True, frozen=True, kw_only=True)
     class Config:
-        regexes: List[Regex]
+        regexes: List[Regex | RegexDict]
 
     __slots__ = ['__config']
     __config: Config
 
     def __init__(
         self,
-        config: Config
+        config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()
 
-        self.__config = config
+        self.__config = self.__get_config(config)
 
     def _validate_data_object(
         self,
@@ -93,3 +103,18 @@ class RegexValidator(Validator):
                 detail=c.detail,
                 field=c.key,
             )
+
+    def __get_config(
+        self,
+        config: Config,
+    ) -> Config:
+
+        # Ensure config is in Regex format
+        # (as you can either pass in a list of Regex or a RegexDict,
+        # which can be used to initialize a Regex)
+        return self.Config(
+            regexes=[
+                c if isinstance(c, Regex) else Regex(**c)
+                for c in config.regexes
+            ]
+        )

tol/validators/regex_by_value.py

@@ -8,7 +8,7 @@ from typing import Dict, List
 from tol.core import DataObject
 from tol.core.validate import Validator
 
-from .regex import Regex
+from .regex import Regex, RegexDict
 
 
 class RegexByValueValidator(Validator):
@@ -20,19 +20,20 @@ class RegexByValueValidator(Validator):
     @dataclass(slots=True, frozen=True, kw_only=True)
     class Config:
         key_column: str
-        regexes: Dict[str, List[Regex]]
+        regexes: Dict[str, List[Regex | RegexDict]]
 
     __slots__ = ['__config']
     config: Config
 
     def __init__(
         self,
-        config: Config
+        config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()
 
-        self.__config = config
+        self.__config = self.__get_config(config)
 
     def _validate_data_object(
         self,
@@ -78,3 +79,22 @@ class RegexByValueValidator(Validator):
                 detail=c.detail,
                 field=c.key,
             )
+
+    def __get_config(
+        self,
+        config: Config,
+    ) -> Config:
+
+        # Ensure config is in Regex format
+        # (as you can either pass in a list of Regex or a RegexDict,
+        # which can be used to initialize a Regex)
+        return self.Config(
+            key_column=config.key_column,
+            regexes={
+                k: [
+                    c if isinstance(c, Regex) else Regex(**c)
+                    for c in v
+                ]
+                for k, v in config.regexes.items()
+            }
+        )

tol/validators/specimens_have_same_taxon.py

@@ -25,7 +25,7 @@ class SpecimensHaveSameTaxonValidator(Validator):
     __config: Config
     __seen: Dict[str, str]
 
-    def __init__(self, config: Config) -> None:
+    def __init__(self, config: Config, **kwargs) -> None:
         super().__init__()
         self.__seen = {}
         self.__config = config

tol/validators/sts_fields.py

@@ -28,6 +28,7 @@ class StsFieldsValidator(Validator):
         self,
         config: Config,
         datasource: DataSource = sts(),  # For testing
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/tolid.py

@@ -34,6 +34,7 @@ class TolidValidator(Validator):
         self,
         config: Config,
         datasource=tolid(),
+        **kwargs
     ) -> None:
 
         super().__init__()
@@ -90,7 +91,7 @@ class TolidValidator(Validator):
                 f.and_ = {'specimen_id': {'eq': {'value': specimen_id}}}
                 self.__cached_tolids[specimen_id] = list(self.__datasource.get_list(
                     object_type='specimen',
-                    filters=f
+                    object_filters=f
                 ))
 
             if (len(self.__cached_tolids[specimen_id]) == 0):

tol/validators/unique_values.py

@@ -27,7 +27,8 @@ class UniqueValuesValidator(Validator):
 
     def __init__(
         self,
-        config: Config
+        config: Config,
+        **kwargs
     ) -> None:
 
         super().__init__()

tol/validators/unique_whole_organisms.py

@@ -28,7 +28,7 @@ class UniqueWholeOrganismsValidator(Validator):
     __whole_organisms: List[str]
     __part_organisms: List[str]
 
-    def __init__(self, config: Config) -> None:
+    def __init__(self, config: Config, **kwargs) -> None:
         super().__init__()
         self.__whole_organisms = []
         self.__part_organisms = []

{tol_sdk-1.7.5b0.dist-info → tol_sdk-1.7.5b3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tol-sdk
-Version: 1.7.5b0
+Version: 1.7.5b3
 Summary: SDK for interaction with ToL, Sanger and external services
 Author-email: ToL Platforms Team <tol-platforms@sanger.ac.uk>
 License: MIT

{tol_sdk-1.7.5b0.dist-info → tol_sdk-1.7.5b3.dist-info}/RECORD

@@ -110,7 +110,7 @@ tol/core/operator/counter.py,sha256=aD7CRcSfHUfH-ASivJhUSncbLc8gvwdbQUDONjHp4oo,
 tol/core/operator/cursor.py,sha256=G8RkuLpQS6vDAXhE2D1WXLSEuGDkqv3YwSrW_QhGTlc,3960
 tol/core/operator/declare.py,sha256=W1jngGKNy-5D8T8nt_-6lpfOFTa-ilVr9YalRdJNG3w,333
 tol/core/operator/deleter.py,sha256=v8C6aBSQGwVCYmZ_PIeGVQExSyilQi5C-6G-wuACCBg,755
-tol/core/operator/detail_getter.py,sha256=0O4VXWqupSuAtVrrib0dWZ2B78IVGokm1b3hzwE3VQI,2785
+tol/core/operator/detail_getter.py,sha256=EG7EuVh73ZzHjXh4fmIy0WtTJii5bHgqzoqbT8OuHqk,2795
 tol/core/operator/enricher.py,sha256=ijJvE8aYCIVsOpmU2EHiTB8NPGwnGucebcDccm5o7qg,4079
 tol/core/operator/enum.py,sha256=JsJkj7LIMLoCnx2n1rdSX9LxGK9bbfoloXVie4rR_3M,1651
 tol/core/operator/group_statter.py,sha256=jZ45J3OGtypOfosWChWAwe05POpBejaoDNAO2qJP1GM,897
@@ -133,7 +133,7 @@ tol/eln/entities.py,sha256=3-Z4ibZR11zepz5Nw74PnkpxA_HA31FsRUx61FSPYUo,1209
 tol/eln/generators.py,sha256=ghRUiohLakiAcMzGVPJrPxYmdWijs63YxfRTqmKu3Zc,1227
 tol/eln/sanitise.py,sha256=fMj-VrQTnw4zn2X0wnjWQAI8gWAa8RYqNuv23LXQssI,406
 tol/ena/__init__.py,sha256=T3TCqaHpgi2Uk2PjPGu60GaG2V8cTrHJlVLtZfLFhTQ,174
-tol/ena/client.py,sha256=0LzSzUuCAV5tRQwArROZnfHFpscG0i0a8jGOMpKlk3c,6624
+tol/ena/client.py,sha256=ldmm7Z9_auQf1zVWjsFLXYgbKvGtSHTsr88YO3zfv2Y,6731
 tol/ena/converter.py,sha256=nxbo4IFzzOvKNMq3Aeiw5iDqVWvY33nTngLppjHAoGY,1144
 tol/ena/ena_datasource.py,sha256=jEvyUaH4pfFxmdtn6O_PwOdjPz6u80uAT3SLlR2f5nM,8968
 tol/ena/ena_methods.py,sha256=jgpLssZq-F-vgkO-fYu4jrXenmNkdFpFKAY3VKp5HHE,9209
@@ -148,7 +148,7 @@ tol/flows/__init__.py,sha256=M7iSvnBJs6fJ8M38cW0bYQa9WW0TN8FHAMjIHPDNAJ4,166
 tol/flows/logger.py,sha256=rWXbaknGcPEZRFvC1CiB1qkhFRZsQk435w7VyJ3cpyw,170
 tol/flows/secrets.py,sha256=1mlbsxaahzYRfVAx3XdztHOmUCtDMSJDzHysdbaCtj0,352
 tol/flows/sequencing_submissions.py,sha256=ukz_y5be-BCBN2y3JPQ2EK6b3jwOCh-187j-jnw3EUY,11027
-tol/flows/converters/__init__.py,sha256=t4Y7jldbvi-bVC-oPkQOlFPrcqblYRvX4D6SpnbcqKk,5928
+tol/flows/converters/__init__.py,sha256=Ee1yMFWwsRoG71ZFCsqtNwF45AR8farmV9h3ERrK994,6154
 tol/flows/converters/benchling_entity_to_benchling_worklist_item_converter_factory.py,sha256=PN27fcvN4JLBnLrtPPAot1cWjAwPQHVcIDoMfPDeKzU,1210
 tol/flows/converters/benchling_extraction_to_elastic_extraction_converter.py,sha256=S8pbmIeKlcXrLPRJHYBUGP0-Q7jTOV2QQk2TeA2naWo,1966
 tol/flows/converters/benchling_extraction_to_elastic_sequencing_request_converter.py,sha256=2RiyRvGRSWzpUwEI4p-s0afshJpFUUxPqv2z-nyDSVg,1992
@@ -180,6 +180,8 @@ tol/flows/converters/gap_assembly_to_elastic_assembly_converter.py,sha256=XK-es-
 tol/flows/converters/genome_notes_genome_note_to_elastic_genome_note_converter.py,sha256=AaUWbVTaWU-NXnUQPaPwI41TE7a-nC4zlg-jrWpPT2s,1166
 tol/flows/converters/goat_taxon_to_elastic_species_converter.py,sha256=1NGs9427OdXGsBaMB467nOF7aTlJsUKYCuoSoABw9L4,1074
 tol/flows/converters/grit_issue_to_elastic_curation_converter.py,sha256=XpRpoRn589MxTqEk6zPWGn6tamJiqY9Ctxk8v0q-dvA,3953
+tol/flows/converters/incoming_sample_to_ena_sample_converter.py,sha256=HmGsg-VCE4W9Dl3lAlcNhWfkVYp1d22DZlFoTaFzeqA,5560
+tol/flows/converters/incoming_sample_to_incoming_sample_with_lists_converter.py,sha256=5Fp1_ojsYqvRcKTgXJbyWqetPisi_vtWFcWr6RtGZoA,1504
 tol/flows/converters/informatics_tolid_to_elastic_tolid_converter.py,sha256=VrvtsDTPlc5Xa3K4rcAMHwV4n71zOH7q5EfALLLQ1tI,587
 tol/flows/converters/labwhere_location_to_elastic_sample_update_converter.py,sha256=NJNmG9sCc2WXc-2J5XfCKXhb2sDH82nZUBekd16PHcw,656
 tol/flows/converters/labwhere_location_to_sts_tray_converter.py,sha256=dSBP5HfdvyIGvNQD6bhi0RKvkwhN8jq69g-0hOXUqEg,672
@@ -302,7 +304,7 @@ tol/sql/action/__init__.py,sha256=T1zAsCza_lvsNtXF1ecSLt9OFGup8tGnIs68YylBmXI,14
 tol/sql/action/factory.py,sha256=HkareJp_57ud0_Bdd9Kwz3_Rnq2l211sGJgftohFAHg,3589
 tol/sql/auth/__init__.py,sha256=e3JuwugXmXobklqZ1Mt1w03qPgb1WdUaJVM7oblzHyk,202
 tol/sql/auth/blueprint.py,sha256=u0vT_TC9IMKrg08QFa9W29_83mT0y0jzLj3DvXy1BBw,25906
-tol/sql/auth/models.py,sha256=4xNWBvyGiI3mwRyDY5ty48Bv9178ApQXPR-YjIdCsvk,11879
+tol/sql/auth/models.py,sha256=U4CsKMMyzGMg6hj4tp_iRenr3_Q--64WJmHWvxQ2--Q,12297
 tol/sql/pipeline_step/__init__.py,sha256=O7u4RrLfuoB0mwLcPxFoUrdTBZGB_4bE1vWCn5ho-qw,147
 tol/sql/pipeline_step/factory.py,sha256=E5_Bs1379UGlRajKnb77iPmqhXBMemQR1C53SSPjXB4,5134
 tol/sql/standard/__init__.py,sha256=2NbLXFk0rneGZosZ2ESIRcT0WMK0KncmPWaLPqvX-i4,142
@@ -318,26 +320,28 @@ tol/treeval/treeval_datasource.py,sha256=GzY6JwH67b5QdV-UVdCFJfgGAIuZ96J2nl53YxZ
 tol/utils/__init__.py,sha256=764-Na1OaNGUDWpMIu51ZtXG7n_nB5MccUFK6LmkWRI,138
 tol/utils/csv.py,sha256=mihww25fSn72c4h-RFeqD_pFIG6KHZP4v1_C0rx81ws,421
 tol/utils/s3.py,sha256=aoYCwJ-qcMqFrpxmViFqPa0O1jgp0phtztO3-0CSNjw,491
-tol/validators/__init__.py,sha256=ch1rBBNx28lFABIbq79gdbKnNdV1UTnQQwxkks2g_CA,1083
-tol/validators/allowed_keys.py,sha256=fX4KqpxOJNmmVNqQq215MtX27v4dbKSjCM1laXuXfZE,1488
-tol/validators/allowed_values.py,sha256=Sxsb6EhiR8Ey90sfPoyGqkehkJN0hHSNXlLYSL_k5f4,1518
-tol/validators/allowed_values_from_datasource.py,sha256=JYF8y-NxFpJh-j2cNWizwIHk6TPQ3lgbnlt3ZXLTGzE,3249
-tol/validators/assert_on_condition.py,sha256=PFPqwzMicVRp8JAZZaGz1btfMNSvRzBWWZzWtheYfDI,1952
-tol/validators/ena_submittable.py,sha256=ruryfVcQtRJ5JsAFBcVZ_3hzTDwRWGXpdPUAfdrYmWg,1948
-tol/validators/min_one_valid_value.py,sha256=3Fv-b-fojvPLpiWwUqrFfO0YMGtV40KEp15zTmdOlyI,1425
-tol/validators/mutually_exclusive.py,sha256=d21WRsph18JkiWx2JmCML4gM304AQ4eyt3U4vT7aZ2A,4247
-tol/validators/regex.py,sha256=q78OrSELZRwb5LPHAm75fWsMx8RChmWqWrSLbrNDugM,2019
-tol/validators/regex_by_value.py,sha256=7wheyYZkKW75UhqZPn_dL3pb6F6N1OoipTl9hujVEQ0,1981
-tol/validators/specimens_have_same_taxon.py,sha256=BrkYXhr1KVnJcDe-PrKXf0AF9740BbFV2XVMrtu98CQ,2167
-tol/validators/sts_fields.py,sha256=piHqdzuGepIEv-ZSSwdkYE6ybQpqc4hBN8hN8UrN4Vg,3442
-tol/validators/tolid.py,sha256=T1e92X3uVzKDEkf-SOKjB7aJAy2p7bL0SI9uKji4RFY,3869
-tol/validators/unique_values.py,sha256=CZvIdg7GC2VmVAGuPToxJ_r-2YCwy2xkQKp2qwVwbzU,3096
-tol/validators/unique_whole_organisms.py,sha256=Z-PUjlCcn-WHDKMYDyt_WhalXzQFfqLWItM6qywVt_Y,5725
-tol/validators/interfaces/__init__.py,sha256=l9jsty1Czoa3Ipmc-u6Wdy1QD23nv7efJ5CiyqSGGR0,157
-tol/validators/interfaces/condition_evaluator.py,sha256=hF_S1SEAxTjF43jlsv-fR5Dux9KEBnbwQwsKcgwzXl4,2246
-tol_sdk-1.7.5b0.dist-info/licenses/LICENSE,sha256=RF9Jacy-9BpUAQQ20INhTgtaNBkmdTolYCHtrrkM2-8,1077
-tol_sdk-1.7.5b0.dist-info/METADATA,sha256=kFF-51RamzYZ4SjsVGblDAD4IXkNZrvPIlTfEzv6VpE,3081
-tol_sdk-1.7.5b0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tol_sdk-1.7.5b0.dist-info/entry_points.txt,sha256=jH3HfTwxjzog7E3lq8CKpUWGIRY9FSXbyL6CpUmv6D0,36
-tol_sdk-1.7.5b0.dist-info/top_level.txt,sha256=PwKMQLphyZNvagBoriVbl8uwHXQl8IC1niawVG0iXMM,10
-tol_sdk-1.7.5b0.dist-info/RECORD,,
+tol/validators/__init__.py,sha256=mJDlsI_W2y5jxazwOlyf-COl_Vlj1Xk1yC5xASouGH8,1134
+tol/validators/allowed_keys.py,sha256=RJcHBiguL84B8hjSRaXLNES21yZqaKFwJNp2Tz9zvh0,1506
+tol/validators/allowed_values.py,sha256=-Yy3Sqo1WYacGKlot_dn3M2o7Oj5MXOioJrJmrWCCxs,1536
+tol/validators/allowed_values_from_datasource.py,sha256=ICFO6FcYXDN7M2Cv1OwpyN38CdhmY7oU-njzIatA3-w,3185
+tol/validators/assert_on_condition.py,sha256=eBGgSVfIQ6e45SheM-ZDg7daXJjyZxRVS5L8AWvbXag,2027
+tol/validators/converter_and_validate.py,sha256=YjhLsh0qMcyZEnHK2GJFotJfZssOtr8qU4uszcPQmrg,2960
+tol/validators/ena_checklist.py,sha256=VGJeDrHH-XzueforuyyCEgEi6y9NurhvuOSL-gSDoOE,2885
+tol/validators/ena_submittable.py,sha256=CujF9t4mA4N3Wm_5rA5MRp401aW19kbioOZpfWVXg6I,1965
+tol/validators/min_one_valid_value.py,sha256=gZUHtfRA-Lvpw0d1FJoAA31cRJpLbbxAJCC9DCt5lCY,1442
+tol/validators/mutually_exclusive.py,sha256=6blZK-2IY4Eq79fHKKrm-pxsQ6B5DNH5ldtxOFVCPhU,4492
+tol/validators/regex.py,sha256=YdFHPcvEo6jNbXxDPTnpAQeOv3kSX4OUZUKfWmFFWl0,2602
+tol/validators/regex_by_value.py,sha256=XM5EnT4vgD17rfpR3bUE9I56IemSw26BI9MZtMakd4E,2582
+tol/validators/specimens_have_same_taxon.py,sha256=m2LLRIZMdhPj1fzyioDJOraI6UHXgy1l963xhezgk7E,2177
+tol/validators/sts_fields.py,sha256=A_NkQFn2TMNFv2yU_ercs7CXlh-oib33ZmDZtc6SuKQ,3459
+tol/validators/tolid.py,sha256=kgo-OWW3at6jK4DQtdgVFjO06sDvqG4QulGkI-jjVRU,3893
+tol/validators/unique_values.py,sha256=o5IrfUNLEmlEp8kpInTtFnTq-FqiHSC9TItKdf-LI1o,3114
+tol/validators/unique_whole_organisms.py,sha256=RdqA1GzIf3LTdrmNGGdxv0aW2udDY2P9EaqZb40hhik,5735
+tol/validators/interfaces/__init__.py,sha256=jtOxnwnwqV_29xjmmMcS_kvlt-pQiWwQYJn2YRP07_w,172
+tol/validators/interfaces/condition_evaluator.py,sha256=nj8Cb8hi47OBy6OVNfeLhF-Pjwtr8MiOSymYL6hfVes,3766
+tol_sdk-1.7.5b3.dist-info/licenses/LICENSE,sha256=RF9Jacy-9BpUAQQ20INhTgtaNBkmdTolYCHtrrkM2-8,1077
+tol_sdk-1.7.5b3.dist-info/METADATA,sha256=EJao_K6Vaa6nFKvIM8iw1vx73RocSQXiK4KkuFfQRVM,3081
+tol_sdk-1.7.5b3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tol_sdk-1.7.5b3.dist-info/entry_points.txt,sha256=jH3HfTwxjzog7E3lq8CKpUWGIRY9FSXbyL6CpUmv6D0,36
+tol_sdk-1.7.5b3.dist-info/top_level.txt,sha256=PwKMQLphyZNvagBoriVbl8uwHXQl8IC1niawVG0iXMM,10
+tol_sdk-1.7.5b3.dist-info/RECORD,,