tol-sdk 1.7.5b4__py3-none-any.whl → 1.8.1__py3-none-any.whl

tol/benchling/sql/extraction_containers_dna.sql

@@ -0,0 +1,173 @@
+/* 
+## SQL Query: DNA Extraction Containers (Benchling Warehouse)
+
+This SQL query retrieves detailed information about DNA extraction containers managed by the ToL Core Laboratory, including metadata, container details, and the latest QC measurements.
+
+The resulting table includes identifiers for tissues, tissue preps, extractions, containers, and locations, as well as the most recent QC results (Nanodrop, Qubit, Femto, Yield, and Decision Making).
+
+Output: Table with columns:
+
+1) taxon_id: [character] Tissue metadata. Origin: STS
+2) eln_tissue_id: [character] Benchling ID for the tissue the extraction is derived from.
+3) eln_tissue_prep_id: [character] Benchling ID for the tissue prep the extraction is derived from.
+4) extraction_id: [character] DNA extraction entity ID (Benchling).
+5) programme_id: [character] ToLID. Origin: BWH.
+6) specimen_id: [character] Specimen ID. Origin: STS.
+7) creation_date: [date] Date the container was created.
+8) fluidx_container_id: [character] Primary key for the FluidX container.
+9) fluidx_id: [character] FluidX barcode.
+10) tube_type: [character] Type of tube/container.
+11) volume_ul: [numeric] Volume in microliters (0 if archived as 'Retired' or 'Expended').
+12) location: [character] Storage location name.
+13) rack: [character] Box/rack barcode.
+14) archive_purpose: [character] Reason for archiving the DNA extraction.
+15) nanodrop_concentration_ngul: [numeric] Latest Nanodrop concentration (ng/µL).
+16) dna_260_280_ratio: [numeric] Latest Nanodrop 260/280 ratio.
+17) dna_260_230_ratio: [numeric] Latest Nanodrop 260/230 ratio.
+18) qubit_concentration_ngul: [numeric] Latest Qubit concentration (ng/µL).
+19) yield_ng: [numeric] Latest yield (ng).
+20) femto_date_code: [character] Latest Femto date code.
+21) femto_description: [character] Latest Femto profile description.
+22) gqn_index: [numeric] Latest GQN index from Femto.
+23) next_step: [character] Latest decision making next step.
+24) extraction_qc_result: [character] Latest extraction QC result.
+
+NOTES:
+1) Only extractions from the 'ToL Core Lab' project and relevant folders are included.
+2) Containers archived as 'Made in error' or with names matching '%Nuclei isolation and tagmentation%' are excluded.
+3) Latest QC results are joined from their respective measurement tables.
+4) Volume is set to 0 for archived/expended extractions.
+5) Data types are preserved as in the Benchling Warehouse.
+
+*/
+
+WITH latest_nanodrop_conc AS (    
+    SELECT
+        nanod.sample_id,
+        nanod.nanodrop_concentration_ngul,
+        nanod._260_280_ratio AS "dna_260_280_ratio",
+        nanod._260_230_ratio AS "dna_260_230_ratio"
+    FROM nanodrop_measurements_v2$raw AS nanod
+    WHERE nanod.created_at$ = (        
+        SELECT MAX(sub.created_at$)
+        FROM nanodrop_measurements_v2$raw AS sub
+        WHERE sub.sample_id = nanod.sample_id
+    )
+),
+
+latest_qubit_conc AS (
+    SELECT
+        qbit.sample_id,
+        qbit.qubit_concentration_ngul
+    FROM qubit_measurements_v2$raw as qbit
+    WHERE qbit.created_at$ = (
+        SELECT MAX(sub.created_at$)
+        FROM qubit_measurements_v2$raw AS sub
+        WHERE sub.sample_id = qbit.sample_id
+    )
+),
+
+latest_yield AS (
+    SELECT
+        dnay.sample_id,
+        dnay.yield
+    FROM yield_v2$raw as dnay
+    WHERE dnay.created_at$ = (
+        SELECT MAX(sub.created_at$)
+        FROM yield_v2$raw AS sub
+        WHERE sub.sample_id = dnay.sample_id
+    )
+),
+
+latest_femto AS (
+    SELECT
+        femto.sample_id,
+        femto.femto_date_code,
+        femto.femto_profile_description AS femto_description,
+        femto.gqn_dnaex
+    FROM femto_dna_extract_v2$raw AS femto
+    WHERE femto.created_at$ = (
+        SELECT MAX(sub.created_at$)
+        FROM femto_dna_extract_v2$raw as sub
+        WHERE sub.sample_id = femto.sample_id
+    )
+),
+
+latest_decision_making AS (
+    SELECT
+        dnad.sample_id,
+        dnad.next_step,
+        qc_passfail AS extraction_qc_result
+    FROM dna_decision_making_v2$raw AS dnad
+    WHERE dnad.created_at$ = (
+        SELECT MAX(sub.created_at$)
+        FROM dna_decision_making_v2$raw AS sub
+        WHERE sub.sample_id = dnad.sample_id
+    )
+)
+
+SELECT DISTINCT
+    t.taxon_id,
+    t.id AS eln_tissue_id,
+    tp.id AS eln_tissue_prep_id,
+    dna.id AS extraction_id,
+    t.programme_id,
+    t.specimen_id,
+    DATE(con.created_at) AS creation_date,
+    con.id AS fluidx_container_id, -- primary key
+    con.barcode AS fluidx_id,
+    tube.type AS tube_type,
+    CASE
+        WHEN con.archive_purpose$ IN ('Retired', 'Expended') THEN 0 -- Retired or expended DNA extractions have a weight of 0
+        ELSE con.volume_si * 1000000
+    END AS volume_ul,
+    loc.name AS location,
+    box.barcode AS rack,
+    con.archive_purpose$ AS archive_purpose,
+    latest_nanodrop_conc.nanodrop_concentration_ngul,
+    latest_nanodrop_conc.dna_260_280_ratio,
+    latest_nanodrop_conc.dna_260_230_ratio,
+    latest_qubit_conc.qubit_concentration_ngul,
+    latest_yield.yield AS yield_ng,
+    latest_femto.femto_date_code,
+    latest_femto.femto_description,
+    latest_femto.gqn_dnaex AS gqn_index,
+    latest_decision_making.next_step,
+    latest_decision_making.extraction_qc_result
+FROM dna_extract$raw AS dna
+INNER JOIN container_content$raw AS cc -- Start of container/tube join
+     ON cc.entity_id = dna.id
+LEFT JOIN container$raw AS con
+     ON con.id = cc.container_id
+LEFT JOIN tube$raw AS tube
+     ON cc.container_id = tube.id -- End of container/tube join
+LEFT JOIN box$raw AS box -- Location chunk
+    ON con.box_id = box.id
+LEFT JOIN location$raw AS loc
+    ON loc.id = box.location_id -- End of location chunk
+LEFT JOIN tissue_prep$raw AS tp
+     ON tp.id = dna.tissue_prep
+LEFT JOIN tissue$raw AS t
+     ON t.id = tp.tissue
+LEFT JOIN latest_nanodrop_conc -- Results chunk
+    ON dna.id = latest_nanodrop_conc.sample_id
+LEFT JOIN latest_qubit_conc
+    ON dna.id = latest_qubit_conc.sample_id
+LEFT JOIN latest_yield
+    ON dna.id = latest_yield.sample_id
+LEFT JOIN latest_femto
+    ON dna.id = latest_femto.sample_id
+LEFT JOIN latest_decision_making
+    ON dna.id = latest_decision_making.sample_id -- End Results chunk
+LEFT JOIN folder$raw AS f
+     ON dna.folder_id$ = f.id
+LEFT JOIN project$raw AS proj
+    ON dna.project_id$ = proj.id
+LEFT JOIN registration_origin$raw AS reg
+	ON reg.entity_id = dna.id
+LEFT JOIN entry$raw AS ent
+	ON reg.origin_entry_id = ent.id
+WHERE proj.name = 'ToL Core Lab'
+    AND  (f.name IN ('Routine Throughput', 'DNA', 'Core Lab Entities', 'Benchling MS Project Move') OR f.name IS NULL)
+    AND (con.archive_purpose$ != ('Made in error') OR con.archive_purpose$ IS NULL)
+    AND ent.name NOT LIKE '%Nuclei isolation and tagmentation%'

tol/benchling/sql/extraction_extraction_type_dna.sql

@@ -11,34 +11,20 @@ Output: Table with cols:
 
 1) sts_id: [integer] Tissue metadata. Origin: STS
 2) taxon_id: [character] Tissue metadata. Origin: STS
-3) eln_tissue_id: [character] Benchling id for the tissue the extractions is derived from.
-4) eln_tissue_prep_id: [character] Benchling id for the tissue prep the extractions is derived from.
+3) eln_tissue_id: [character] Benchling id for the tissue the extraction is derived from.
+4) eln_tissue_prep_id: [character] Benchling id for the tissue prep the extraction is derived from.
 5) eln_file_registry_id: [character] id in Benchling Registry.
 6) extraction_id: [character] Primary key. 
 7) programme_id: [character] ToLID. Origin: BWH
 8) specimen_id: [character] Specimen ID. Origin: STS
 9) completion_date: [date] Extraction date. This field coalesces created_at$ and created_on fields. Created_on is for bnt legacy data.
-10) extraction_name: [character] Entity name. 
-11) fluidx_id: [character] Fluidx ID.
-12) volume_ul: [double] volume of DNA available in the fluidx tube.
-13) location: [character] Physical locationo of the DNA extraction. Freezer shelf.
-14) rack: [character] Physical locationo of the DNA extraction. Rack barcode.
-15) bnt_id: [character] Batches and Tracking legacy id.
-16) manual_vs_automatic: [character].
-17) extraction_protocol: [character] DNA extraction protocol as recorded at the time of extraction
-18) tube_type: [character] Type of tube. Marked NULL or voucher.
-19) extraction_type: [character] dna.
-20) name: [character] Folder name.
-21) archive_purpose: [character] Reason for archiving the DNA extraction.
-22) nanodrop_concentration_ngul: [double] Concentration of DNA as measured by Nanodrop.
-23) dna_260_280_ratio: [double] Ratio of absorbance at 260:280nm as measured by spectrophotometer.
-24) dna_260_230_ratio: [double] Ratio of absorbance at 260:230nm as measured by spectrophotometer.
-25) qubit_concentration_ngul: [double] Concentration of DNA as measured by Qubit.
-26) yield_ng: [double] DNA yield after extraction.
-27) femto_date_code: [character] Femto date code.
-28) femto_description:[character] Categorical description of the femto pulse profile. 
-29) gqn_index: [character] Genomic Quality Number (GQN) index, calculated by the Femto software.
-30) extraction_qc_result: [character] QC result: Yes = Extraction passed; No = Extraction failed. 
+10) extraction_name: [character] Entity name.
+11) bnt_id: [character] Batches and Tracking legacy id.
+12) manual_vs_automatic: [character] Extraction method indicator.
+13) extraction_protocol: [character] DNA extraction protocol as recorded at the time of extraction.
+14) extraction_type: [character] Type of extraction, set to 'dna'.
+15) folder_name: [character] Folder name.
+16) archive_purpose: [character] Reason for archiving the DNA extraction.
 
 NOTES: 
 1) Data types were casted explicitly to conserved the data type stored in BWH.
@@ -46,71 +32,6 @@ NOTES:
 
 */
 
-WITH latest_nanodrop_conc AS (    
-    SELECT
-        nanod.sample_id,
-        nanod.nanodrop_concentration_ngul,
-        nanod._260_280_ratio AS "dna_260_280_ratio",
-        nanod._260_230_ratio AS "dna_260_230_ratio"
-    FROM nanodrop_measurements_v2$raw AS nanod
-    WHERE nanod.created_at$ = (        
-        SELECT MAX(sub.created_at$)
-        FROM nanodrop_measurements_v2$raw AS sub
-        WHERE sub.sample_id = nanod.sample_id
-    )
-),
-
-latest_qubit_conc AS (
-    SELECT
-        qbit.sample_id,
-        qbit.qubit_concentration_ngul
-    FROM qubit_measurements_v2$raw as qbit
-    WHERE qbit.created_at$ = (
-        SELECT MAX(sub.created_at$)
-        FROM qubit_measurements_v2$raw AS sub
-        WHERE sub.sample_id = qbit.sample_id
-    )
-),
-
-latest_yield AS (
-    SELECT
-        dnay.sample_id,
-        dnay.yield
-    FROM yield_v2$raw as dnay
-    WHERE dnay.created_at$ = (
-        SELECT MAX(sub.created_at$)
-        FROM yield_v2$raw AS sub
-        WHERE sub.sample_id = dnay.sample_id
-    )
-),
-
-latest_femto AS (
-    SELECT
-        femto.sample_id,
-        femto.femto_date_code,
-        femto.femto_profile_description AS femto_description,
-        femto.gqn_dnaex
-    FROM femto_dna_extract_v2$raw AS femto
-    WHERE femto.created_at$ = (
-        SELECT MAX(sub.created_at$)
-        FROM femto_dna_extract_v2$raw as sub
-        WHERE sub.sample_id = femto.sample_id
-    )
-),
-
-latest_decision_making AS (
-    SELECT
-        dnad.sample_id,
-        dnad.next_step,
-        qc_passfail AS extraction_qc_result
-    FROM dna_decision_making_v2$raw AS dnad
-    WHERE dnad.created_at$ = (
-        SELECT MAX(sub.created_at$)
-        FROM dna_decision_making_v2$raw AS sub
-        WHERE sub.sample_id = dnad.sample_id
-    )
-)
-
 SELECT DISTINCT
     t.sts_id,
     t.taxon_id,
@@ -122,62 +43,26 @@ SELECT DISTINCT
     t.specimen_id,
     COALESCE(DATE(dna.created_on), DATE(dna.created_at$)) AS completion_date, -- Homogenising BnT and Benchling dates
     dna.name$ AS extraction_name,
-    con.barcode AS fluidx_id,
-    con.id AS fluidx_container_id,
-    CASE
-        WHEN con.archive_purpose$ IN ('Retired', 'Expended') THEN 0 -- Retired or expended DNA extractions have a weight of 0
-        ELSE con.volume_si * 1000000
-    END AS volume_ul,
-    loc.name AS location,
-    box.barcode AS rack,
     dna.bt_id AS bnt_id,
-	dna.manual_vs_automatic AS manual_vs_automatic,
+    dna.manual_vs_automatic AS manual_vs_automatic,
     dna.extraction_protocol,
-    tube.type AS tube_type,
     'dna'::varchar AS extraction_type,
-    f.name, dna.archive_purpose$,
-    latest_nanodrop_conc.nanodrop_concentration_ngul,
-    latest_nanodrop_conc.dna_260_280_ratio,
-    latest_nanodrop_conc.dna_260_230_ratio,
-    latest_qubit_conc.qubit_concentration_ngul,
-    latest_yield.yield AS yield_ng,
-    latest_femto.femto_date_code,
-    latest_femto.femto_description,
-    latest_femto.gqn_dnaex AS gqn_index,
-    latest_decision_making.next_step,
-    latest_decision_making.extraction_qc_result
+    f.name AS folder_name
 FROM dna_extract$raw AS dna
-LEFT JOIN container_content$raw AS cc
-     ON cc.entity_id = dna.id
-LEFT JOIN container$raw AS con
-     ON con.id = cc.container_id
 LEFT JOIN tissue_prep$raw AS tp
      ON tp.id = dna.tissue_prep
 LEFT JOIN tissue$raw AS t
      ON t.id = tp.tissue
-LEFT JOIN tube$raw AS tube
-     ON cc.container_id = tube.id
 LEFT JOIN folder$raw AS f
      ON dna.folder_id$ = f.id
 LEFT JOIN project$raw AS proj
     ON dna.project_id$ = proj.id
-LEFT JOIN latest_nanodrop_conc -- Results chunk
-    ON dna.id = latest_nanodrop_conc.sample_id
-LEFT JOIN latest_qubit_conc
-    ON dna.id = latest_qubit_conc.sample_id
-LEFT JOIN latest_yield
-    ON dna.id = latest_yield.sample_id
-LEFT JOIN latest_femto
-    ON dna.id = latest_femto.sample_id
-LEFT JOIN latest_decision_making
-    ON dna.id = latest_decision_making.sample_id -- End Results chunk
-LEFT JOIN box$raw AS box -- Location chunk
-    ON con.box_id = box.id
-LEFT JOIN location$raw AS loc
-    ON loc.id = box.location_id -- End of location chunk
+LEFT JOIN registration_origin$raw AS reg
+	ON reg.entity_id = dna.id
+LEFT JOIN entry$raw AS ent
+	ON reg.origin_entry_id = ent.id
 WHERE proj.name = 'ToL Core Lab'
     AND  (f.name IN ('Routine Throughput', 'DNA', 'Core Lab Entities', 'Benchling MS Project Move') OR f.name IS NULL)
     AND (dna.archive_purpose$ != ('Made in error') OR dna.archive_purpose$ IS NULL)
-    AND (con.archive_purpose$ != ('Made in error') OR con.archive_purpose$ IS NULL)
-    AND con.barcode NOT LIKE 'CON%'
+    AND ent.name NOT LIKE '%Nuclei isolation and tagmentation%'
 ORDER BY completion_date DESC

tol/benchling/sql/extraction_extraction_type_lres.sql

@@ -28,8 +28,8 @@ SELECT DISTINCT
 	tp.name$ AS eln_tissue_prep_name,
 	ssid.sanger_sample_id,
 	ssid.sanger_sample_id AS extraction_id,
-	c.barcode AS fluidx_id,
-	c.id AS fluidx_container_id,
+	sub_con.barcode AS fluidx_id,
+	sub_con.id AS fluidx_container_id,
 	DATE(tpsub.submitted_submission_date) AS completion_date,
 	'lres'::varchar AS extraction_type
 FROM tissue_prep$raw AS tp
@@ -41,8 +41,16 @@ LEFT JOIN container$raw AS c
 	ON cc.container_id = c.id
 LEFT JOIN tissue_prep_submission_workflow_output$raw AS tpsub
 	ON c.id = tpsub.sample_tube_id
+LEFT JOIN container$raw AS sub_con
+	ON tpsub.sample_tube_id = sub_con.id
 LEFT JOIN storage$raw AS stor 
 	ON c.location_id = stor.id
 LEFT JOIN sanger_sample_id$raw AS ssid 
 	ON c.id = ssid.sample_tube
-WHERE stor.name$ = 'SciOps ToL Lab'
+LEFT JOIN project$raw AS proj
+	ON tp.project_id$ = proj.id
+LEFT JOIN folder$raw AS f 
+	ON tp.folder_id$ = f.id
+WHERE sub_con.id IS NOT NULL
+	AND proj.name = 'ToL Core Lab'
+	AND f.name = 'Sample Prep'

tol/core/data_object_converter.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 
 from abc import ABC, abstractmethod
+from dataclasses import dataclass
 from typing import Iterable
 
 from more_itertools import flatten
@@ -95,9 +96,14 @@ class DefaultDataObjectToDataObjectConverter(DataObjectToDataObjectOrUpdateConve
 
 class SanitisingConverter(DataObjectToDataObjectOrUpdateConverter):
 
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        pass
+
     def __init__(
         self,
         data_object_factory: DataObjectFactory,
+        config: Config,
         **kwargs
     ):
         super().__init__(data_object_factory)

tol/excel/excel_datasource.py

@@ -65,7 +65,7 @@ class ExcelDataSource(
     ) -> Iterable[DataObject]:
 
         return (
-            self.__marshal_row(row_index + 1, row)
+            self.__marshal_row(row_index + 2, row)  # Add 1 for header, 1 for 1-based ID
             for row_index, row
             in self.__df.iterrows()
         )
@@ -115,6 +115,14 @@ class ExcelDataSource(
         __v: Any,
     ) -> Any:
 
+        # Convert pandas Timestamp to Python datetime
+        if isinstance(__v, pd.Timestamp):
+            __v = datetime.fromtimestamp(__v.timestamp())
+
+        # If float and is whole number, convert to int
+        if isinstance(__v, float) and __v.is_integer():
+            __v = int(__v)
+
         if __k not in self.__mappings:
             return __v
 

tol/flows/converters/incoming_sample_to_ena_sample_converter.py

@@ -3,6 +3,7 @@
 
 import re
 from dataclasses import dataclass
+from datetime import datetime
 from typing import Iterable
 
 from tol.core import DataObject, DataObjectToDataObjectOrUpdateConverter
@@ -30,8 +31,10 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
         s = data_object
         attributes = {
             'ENA-CHECKLIST': self.__config.ena_checklist_id,
-            'organism part': self.__replace_underscores(
-                s.attributes.get('ORGANISM_PART')),
+            'organism part': self.__join_list([
+                self.__replace_underscores(v)
+                for v in s.attributes.get('ORGANISM_PART', [])
+            ]),
             'lifestage': (
                 'spore-bearing structure'
                 if s.attributes.get('LIFESTAGE') == 'SPORE_BEARING_STRUCTURE'
@@ -40,35 +43,38 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
             ),
             'project name':
                 self.__config.project_name,
-            'collected by':
-                self.__replace_underscores(
-                    s.attributes.get('COLLECTED_BY')),
+            'collected_by': self.__join_list([
+                self.__replace_underscores(v)
+                for v in s.attributes.get('COLLECTED_BY', [])
+            ]),
             'collection date':
-                self.__replace_underscores(
-                    s.attributes.get('DATE_OF_COLLECTION')).lower(),
+                self.__format_date(
+                    s.attributes.get('DATE_OF_COLLECTION')),
             'geographic location (country and/or sea)':
                 self.__collection_country(s).replace('_', ' '),
             'geographic location (latitude)':
                 self.__replace_underscores(
-                    s.attributes.get('DECIMAL_LATITUDE')).lower(),
+                    str(s.attributes.get('DECIMAL_LATITUDE'))).lower(),
             'geographic location (latitude) units':
                 'DD',
             'geographic location (longitude)':
                 self.__replace_underscores(
-                    s.attributes.get('DECIMAL_LONGITUDE')).lower(),
+                    str(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')),
+            'identified_by': self.__join_list([
+                self.__replace_underscores(v)
+                for v in s.attributes.get('IDENTIFIED_BY', [])
+            ]),
             'habitat':
                 self.__replace_underscores(
                     s.attributes.get('HABITAT')),
-            'identifier_affiliation':
-                self.__replace_underscores(
-                    s.attributes.get('IDENTIFIER_AFFILIATION')),
+            'identifier_affiliation': self.__join_list([
+                self.__replace_underscores(v)
+                for v in s.attributes.get('IDENTIFIER_AFFILIATION', [])
+            ]),
             'sex':
                 self.__replace_underscores(
                     s.attributes.get('SEX')),
@@ -77,9 +83,10 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
                     s.attributes.get('RELATIONSHIP')),
             'SYMBIONT':
                 'Y' if s.attributes.get('SYMBIONT') == 'SYMBIONT' else 'N',
-            'collecting institution':
-                self.__replace_underscores(
-                    s.attributes.get('COLLECTOR_AFFILIATION'))
+            'collecting institution': self.__join_list([
+                self.__replace_underscores(v)
+                for v in s.attributes.get('COLLECTOR_AFFILIATION', [])
+            ]),
         }
         if self.__sanitise(s.attributes.get('DEPTH')) != '':
             attributes['geographic location (depth)'] = s.attributes.get('DEPTH')
@@ -88,9 +95,11 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
             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')
+            attributes['original collection date'] = \
+                self.__format_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
+            attributes['original geographic location'] = \
+                self.__replace_underscores(s.attributes.get('ORIGINAL_GEOGRAPHIC_LOCATION'))
         if s.attributes.get('GAL') is not None:
             attributes['GAL'] = s.attributes.get('GAL')
         if s.attributes.get('VOUCHER_ID') is not None:
@@ -103,7 +112,7 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
             attributes['culture_or_strain_id'] = s.attributes.get('CULTURE_OR_STRAIN_ID')
 
         ret = self._data_object_factory(
-            'sample',
+            data_object.type,
             s.id,
             attributes=attributes,
         )
@@ -128,3 +137,19 @@ class IncomingSampleToEnaSampleConverter(DataObjectToDataObjectOrUpdateConverter
         if value is None:
             return default_value
         return value
+
+    def __join_list(self, value_list):
+        if value_list is None:
+            return ''
+        if not isinstance(value_list, list):
+            return str(value_list)
+        return ' | '.join(str(v) for v in value_list)
+
+    def __format_date(self, value):
+        """Format date to YYYY-mm-dd format"""
+        if value is None:
+            return ''
+        if isinstance(value, datetime):
+            return value.strftime('%Y-%m-%d')
+
+        return str(value)

tol/validators/__init__.py

@@ -15,6 +15,7 @@ from .regex_by_value import RegexByValueValidator  # noqa
 from .specimens_have_same_taxon import SpecimensHaveSameTaxonValidator # noqa
 from .sts_fields import StsFieldsValidator  # noqa
 from .tolid import TolidValidator  # noqa
+from .types import TypesValidator  # noqa
 from .unique_values import UniqueValuesValidator  # noqa
 from .unique_whole_organisms import UniqueWholeOrganismsValidator  # noqa
 from .interfaces import Condition  # noqa

tol/validators/converter_and_validate.py

@@ -19,12 +19,12 @@ class ConverterAndValidateValidator(Validator):
         "converters": [{
             "module": "<path.to.module>",
             "class_name": "<path.to.ConverterClass>",
-            "config": { ... }
+            "config_details": { ... }
         }],
         "validators": [{
             "module": "<path.to.module>",
             "class_name": "<path.to.ValidatorClass>",
-            "config": { ... }
+            "config_details": { ... }
         }]
     }
 
@@ -54,7 +54,7 @@ class ConverterAndValidateValidator(Validator):
             converter_class = getattr(__module, conv.get('class_name'))
 
             converter_conf = converter_class.Config(
-                **conv.get('config')
+                **conv.get('config_details')
             )
             self.__converters.append(converter_class(
                 data_object_factory=data_object_factory,
@@ -65,7 +65,7 @@ class ConverterAndValidateValidator(Validator):
             validator_class = getattr(__module, val.get('class_name'))
 
             validator_conf = validator_class.Config(
-                **val.get('config')
+                **val.get('config_details')
             )
             self.__validators.append(validator_class(
                 data_object_factory=data_object_factory,

tol/validators/ena_checklist.py

@@ -27,31 +27,31 @@ class EnaChecklistValidator(Validator):
         super().__init__()
         self.__config = config
         self._datasource = datasource
+        self.__ena_checklist = datasource.get_one(
+            'checklist',
+            self.__config.ena_checklist_id
+        ).checklist
 
     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:
+        for key, validation in self.__ena_checklist.items():
             field_name = key
-            if 'field' in validations[key]:
-                field_name = validations[key]['field']
-            if 'mandatory' in validations[key] and key not in obj.attributes:
+            if 'field' in validation:
+                field_name = validation['field']
+            if 'mandatory' in validation 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:
+            if 'mandatory' in validation 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) == '':
+            if 'mandatory' in validation 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:
+            if 'restricted text' in validation and key in obj.attributes:
+                for condition in validation:
+                    if isinstance(condition, str) and '(' in condition:
                         regex = condition
                 compiled_re = re.compile(regex)
                 if not compiled_re.search(obj.attributes.get(key)):
@@ -61,9 +61,9 @@ class EnaChecklistValidator(Validator):
                     )
 
             # Check against allowed values
-            if 'text choice' in validations[key] and key in obj.attributes:
-                for condition in validations[key]:
-                    if type(condition) == list:
+            if 'text choice' in validation and key in obj.attributes:
+                for condition in validation:
+                    if isinstance(condition, list):
                         allowed_values = condition
                 if obj.attributes.get(key).lower() not in \
                         [x.lower() for x in allowed_values]:

tol/validators/regex.py

@@ -26,9 +26,9 @@ class Regex:
 
     def is_allowed(self, __v: Any) -> bool:
         # Check regex
-        return bool(re.search(
+        return __v is None or __v == '' or bool(re.search(
             self.regex,
-            str(__v) if __v is not None else ''
+            str(__v)
         ))
 
 
@@ -90,7 +90,6 @@ class RegexValidator(Validator):
         obj: DataObject,
         c: Regex,
     ) -> None:
-
         if c.is_error:
             self.add_error(
                 object_id=obj.id,

tol/validators/sts_fields.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 
 from dataclasses import dataclass
+from datetime import datetime, timedelta
 from typing import List
 
 from tol.core import DataObject, DataSource
@@ -51,39 +52,178 @@ class StsFieldsValidator(Validator):
         obj: DataObject
     ) -> None:
         for field in self.__fields.values():
+            # Ignore inactive fields
+            if field.get('status') == 'Inactive':
+                continue
             # Get the value from the data object
             field_value = obj.get_field_by_name(field.get('data_input_key'))
-            if field.get('mandatory_input') and (field_value is None or field_value == ''):
+            if isinstance(field_value, list):
+                field_value = ' | '.join(str(v) for v in field_value)
+
+            # mandatory_input fields must be present
+            if field.get('mandatory_input') and field.get('data_input_key') not in obj.attributes:
                 self.add_error(
                     object_id=obj.id,
                     detail=f'Field {field.get("data_input_key")} is required '
                            f'for project {self.__config.project_code}',
                     field=field.get('data_input_key'),
                 )
-            elif field.get('allowed_values') and field_value not in field.get('allowed_values'):
-                self.add_error(
-                    object_id=obj.id,
-                    detail=f'Field {field.get("data_input_key")} value '
-                           f'"{field_value}" not found in allowed values '
-                           f'{field.get("allowed_values")} for project '
-                           f'{self.__config.project_code}',
-                    field=field.get('data_input_key'),
-                )
-            elif field.get('min') and field_value < field.get('min'):
+                continue
+
+            # Skip further validations if validation is not mandatory
+            if not field.get('mandatory_validation'):
+                continue
+
+            # Mandatory validation fields must have a value
+            if field_value is None or field_value == '':
                 self.add_error(
                     object_id=obj.id,
-                    detail=f'Field {field.get("data_input_key")} value '
-                           f'"{field_value}" is less than minimum value '
-                           f'"{field.get("min")}" for project '
-                           f'{self.__config.project_code}',
+                    detail=f'Field {field.get("data_input_key")} is required to have a value '
+                           f'for project {self.__config.project_code}',
                     field=field.get('data_input_key'),
                 )
-            elif field.get('max') and field_value > field.get('max'):
+                continue
+
+            # Allowed values
+            if field.get('allowed_values'):
+                allowed_values = [
+                    value.get('value') for value in field.get('allowed_values', [])
+                ]
+                if field_value not in allowed_values:
+                    self.add_error(
+                        object_id=obj.id,
+                        detail=f'Field {field.get("data_input_key")} value '
+                               f'"{field_value}" not found in allowed values '
+                               f'{allowed_values} for project '
+                               f'{self.__config.project_code}',
+                        field=field.get('data_input_key'),
+                    )
+
+            if field.get('type') in ['String', 'TextArea']:
+                self.__validate_string(obj, field, field_value)
+
+            if field.get('type') in ['Integer', 'Decimal', 'Percentage']:
+                self.__validate_number(obj, field, field_value)
+
+            if field.get('type') in ['Boolean']:
+                self.__validate_boolean(obj, field, field_value)
+
+            if field.get('type') in ['Date']:
+                self.__validate_date(obj, field, field_value)
+
+    def __validate_string(
+        self,
+        obj: DataObject,
+        field: dict,
+        field_value: str | int | float | None
+    ) -> None:
+        # Check type is a string
+        # if not isinstance(field_value, str):
+        #     self.add_error(
+        #         object_id=obj.id,
+        #         detail=f'Field {field.get("data_input_key")} value '
+        #                 f'"{field_value}" is not a string for project '
+        #                 f'{self.__config.project_code}',
+        #         field=field.get('data_input_key'),
+        #     )
+        #     return
+
+        # Min/Max validations for string
+        if field.get('min') and len(field_value) < field.get('min'):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is shorter than minimum length '
+                       f'"{field.get("min")}" for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+        if field.get('max') and len(field_value) > field.get('max'):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is longer than maximum length '
+                       f'"{field.get("max")}" for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+
+    def __validate_number(
+        self,
+        obj: DataObject,
+        field: dict,
+        field_value: str | int | float | None
+    ) -> None:
+        # Check type is a number
+        if not isinstance(field_value, (int, float)):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is not a number for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+            return
+
+        # Min/Max validations for number
+        if field.get('min') is not None and field_value < field.get('min'):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is less than minimum value '
+                       f'"{field.get("min")}" for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+        if field.get('max') is not None and field_value > field.get('max'):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is greater than maximum value '
+                       f'"{field.get("max")}" for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+
+    def __validate_boolean(
+        self,
+        obj: DataObject,
+        field: dict,
+        field_value: str | int | float | None
+    ) -> None:
+        # Check type is a boolean
+        if field_value not in ['Y', 'N']:
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is not a boolean (Y/N) for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+
+    def __validate_date(
+        self,
+        obj: DataObject,
+        field: dict,
+        field_value: str | int | float | None
+    ) -> None:
+        if not isinstance(field_value, datetime):
+            self.add_error(
+                object_id=obj.id,
+                detail=f'Field {field.get("data_input_key")} value '
+                       f'"{field_value}" is not a date string for project '
+                       f'{self.__config.project_code}',
+                field=field.get('data_input_key'),
+            )
+            return
+        if field.get('range_limit'):
+            earliest_date = datetime.now() - timedelta(days=field.get('min'))
+            latest_date = datetime.now() + timedelta(days=field.get('max'))
+            if field_value < earliest_date or field_value > latest_date:
                 self.add_error(
                     object_id=obj.id,
                     detail=f'Field {field.get("data_input_key")} value '
-                           f'"{field_value}" is greater than maximum value '
-                           f'"{field.get("max")}" for project '
-                           f'{self.__config.project_code}',
+                           f'"{field_value}" is not within the allowed date '
+                           f'range for project {self.__config.project_code}',
                     field=field.get('data_input_key'),
                 )

tol/validators/tolid.py

@@ -103,7 +103,7 @@ class TolidValidator(Validator):
 
                 if str(obj.get_field_by_name(self.__config.species_id_field)) not in taxons:
                     self.add_error(
-                        object_id=obj.id,
+                        object_id=obj.id + 1,
                         detail=f'Specimen ID {specimen_id} does not match Taxon ID '
                                f'{obj.get_field_by_name(self.__config.species_id_field)}'
                                'in TolID source',

tol/validators/types.py

@@ -0,0 +1,90 @@
+# SPDX-FileCopyrightText: 2025 Genome Research Ltd.
+#
+# SPDX-License-Identifier: MIT
+
+from dataclasses import dataclass
+from datetime import datetime, time
+
+from tol.core import DataObject
+from tol.core.validate import Validator
+
+
+class TypesValidator(Validator):
+    """
+    Validates an incoming stream of `DataObject` instances,
+    ensuring that they only have attributes of the given
+    allowed keys.
+    """
+    @dataclass(slots=True, frozen=True, kw_only=True)
+    class Config:
+        allowed_types: dict[str, str]
+        is_error: bool = True
+        detail: str = 'Value is of incorrect type'
+
+    __slots__ = ['__config']
+    __config: Config
+
+    def __init__(
+        self,
+        config: Config,
+        **kwargs
+    ) -> None:
+
+        super().__init__()
+        self.__config = config
+
+    def _validate_data_object(
+        self,
+        obj: DataObject
+    ) -> None:
+
+        type_map = {
+            'str': str,
+            'int': int,
+            'float': float,
+            'bool': bool,
+            'list': list,
+            'dict': dict,
+            'datetime': datetime,
+            'time': time
+        }
+        for key, expected_type in self.__config.allowed_types.items():
+            if key in obj.attributes:
+                actual_value = obj.get_field_by_name(key)
+                if actual_value is None:
+                    continue
+                type_class = type_map.get(expected_type)
+                if type_class and not isinstance(actual_value, type_class):
+                    self.__add_result(
+                        obj,
+                        key,
+                        detail=f'Field {key} value "{actual_value}" is not of type '
+                               f'"{expected_type}"',
+                    )
+                if type_class and isinstance(actual_value, type_class):
+                    # Special case for bool since isinstance(True, int) is True
+                    if expected_type == 'int' and isinstance(actual_value, bool):
+                        self.__add_result(
+                            obj,
+                            key,
+                        )
+
+    def __add_result(
+        self,
+        obj: DataObject,
+        key: str,
+        detail: str = None,
+    ) -> None:
+
+        if self.__config.is_error:
+            self.add_error(
+                object_id=obj.id,
+                detail=detail or self.__config.detail,
+                field=key,
+            )
+        else:
+            self.add_warning(
+                object_id=obj.id,
+                detail=self.__config.detail,
+                field=key,
+            )

{tol_sdk-1.7.5b4.dist-info → tol_sdk-1.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tol-sdk
-Version: 1.7.5b4
+Version: 1.8.1
 Summary: SDK for interaction with ToL, Sanger and external services
 Author-email: ToL Platforms Team <tol-platforms@sanger.ac.uk>
 License: MIT
@@ -50,6 +50,8 @@ Requires-Dist: openpyxl>=3.0.10; extra == "sheets"
 Requires-Dist: XlsxWriter==3.1.9; extra == "sheets"
 Requires-Dist: xlrd==2.0.1; extra == "sheets"
 Requires-Dist: gspread>=5.12.0; extra == "sheets"
+Provides-Extra: s3
+Requires-Dist: minio==7.2.15; extra == "s3"
 Provides-Extra: all
 Requires-Dist: tol-sdk[api-base]; extra == "all"
 Requires-Dist: tol-sdk[benchling]; extra == "all"

{tol_sdk-1.7.5b4.dist-info → tol_sdk-1.8.1.dist-info}/RECORD

@@ -47,8 +47,9 @@ tol/benchling/benchling_converter.py,sha256=CO7BMvMAM52uIFjQWZFedRve0XNSmC9YtumJ
 tol/benchling/benchling_datasource.py,sha256=aHoGOJYX_dsL3G-9lXlY0bQQl4pMXf4a852sAkl-sKs,35112
 tol/benchling/benchling_warehouse_datasource.py,sha256=opsdvHz8l06NTmt84HrIgUJxV_DsurVgFtGs3_5PMoM,4635
 tol/benchling/sql/__init__.py,sha256=4LbvDIZOOG7p-ebbvivP7NvrJeApUvGEIcDL58ahQJE,85
-tol/benchling/sql/extraction_extraction_type_dna.sql,sha256=hd6-Qt4FyNMh42aT3Oxph4W4A5Cv1mwsEBT9uPfHDPg,7291
-tol/benchling/sql/extraction_extraction_type_lres.sql,sha256=3FHMz_8aw-N1aaBip9bC7G0f8K-xkD3Gc_L91rY8c9o,1306
+tol/benchling/sql/extraction_containers_dna.sql,sha256=YRQ0W1d-BjXB9gcMpf5ZyjHbPVp2VU0KkYi4e0JvYtA,6680
+tol/benchling/sql/extraction_extraction_type_dna.sql,sha256=UvxboWBoXXp7RHUdRKNiQTS-AXdLdz8bFEXCS6q9SoE,3094
+tol/benchling/sql/extraction_extraction_type_lres.sql,sha256=7Y6a8v0V-jjU5Kg3czuZjcPLvGSfrnUDekpHo2mUgnc,1556
 tol/benchling/sql/extraction_extraction_type_pooled_dna.sql,sha256=fNjCJPaViGrR6D8sLwZK2Zg5LqQqh16HB0s7ZeqTqdg,4480
 tol/benchling/sql/extraction_extraction_type_rna.sql,sha256=Vy3uV_ns4uO9CwuOFo1KPhI0yK6dsSO47wObcwJbHXQ,3861
 tol/benchling/sql/pacbio_prep.sql,sha256=a3dR-kcp8fT3ZZkbX8pV4StnweWGvcVl4fZNMVNCvbQ,4070
@@ -89,7 +90,7 @@ tol/core/attribute_metadata.py,sha256=wYD3NXDdStrpkUZoyTUiEpp7c14f7MLIcyooT1G4GE
 tol/core/core_converter.py,sha256=Gn4J507BtqDjnOWV2MFRYGz8YElJAKQItmnCrD72s7k,4504
 tol/core/data_loader.py,sha256=k-ET1nIohIz6PcADbEn9Y7k9TupoiBYxKDkcAl_9pGY,14710
 tol/core/data_object.py,sha256=GxG04JMcICaiHU1rufkhoD8jb9YQLhE0QWlFU2ZkQsM,4241
-tol/core/data_object_converter.py,sha256=FUNUXGi5FIdIe34B0g32hhRf8GGzWTHW7vLhb1GXG6E,3783
+tol/core/data_object_converter.py,sha256=GESpLvwrAEwmCfBwy3GxcSCuHz0xt7ECCBPE2stxBdI,3927
 tol/core/data_source_attribute_metadata.py,sha256=NHvJ_Gmw7-Oej1MoFCohvq4f6emDJ2HF483UmW2Qd_c,4407
 tol/core/data_source_dict.py,sha256=d-hSmoWTwG6IOc0cQTLap1EBslsxYIWGUd3ScSoeH_Q,1705
 tol/core/datasource.py,sha256=e9GaeDPfO_Gs7cgQhmNxCiSDlRNf64reegzFebcMNkA,6303
@@ -142,7 +143,7 @@ tol/ena/filter.py,sha256=UzOx5ivXvA0TY2QuNzFmS-zDPVNnaAx07DMVkAwVsAE,3370
 tol/ena/parser.py,sha256=Z4YmUnpfLKng4QwmZkLEj1hUfwYb_bqr-DWgF1Gw-EY,3253
 tol/excel/__init__.py,sha256=M0xL9w9Au8kYOLWzFGuijJ7WoZENOMkZ1XV1ephhlDY,229
 tol/excel/excel.py,sha256=rcA-wfXY9R14OfNKS-NX2sn__9gmQ_G8LoUgWseF1Gk,2124
-tol/excel/excel_datasource.py,sha256=nIMvkCZ1edx8djqsVsPTRi6yCfyKc_dIokTpLy16rwY,3091
+tol/excel/excel_datasource.py,sha256=WhkqIk4Qg-iDBczI4l1OFoLNDX32riwgj4SdGhr4DIs,3423
 tol/excel/s3_factory.py,sha256=4lGyKrSvarPXWndyvm7K-tel0FoM0My8wnz-Mzwt0yQ,1245
 tol/flows/__init__.py,sha256=M7iSvnBJs6fJ8M38cW0bYQa9WW0TN8FHAMjIHPDNAJ4,166
 tol/flows/logger.py,sha256=rWXbaknGcPEZRFvC1CiB1qkhFRZsQk435w7VyJ3cpyw,170
@@ -180,7 +181,7 @@ 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_ena_sample_converter.py,sha256=SAVYWENG3GS7B1rM6rYwxfLQH75nZl7mEzphH5CBxRw,6353
 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
@@ -321,28 +322,29 @@ 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=mJDlsI_W2y5jxazwOlyf-COl_Vlj1Xk1yC5xASouGH8,1134
+tol/validators/__init__.py,sha256=QI5ykFzsTLsIQXcL4vF_aaVGdSr2l0X0Qkssbnxumss,1176
 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/converter_and_validate.py,sha256=O1uYdrU4YDZ8eZjb7Koots4-8fMVOkJFXESg-LVw2o8,2992
+tol/validators/ena_checklist.py,sha256=M10VAFGpaxnm7rWO4jmFhTWkYRlCmU0Ox2IUEDFGKbo,2812
 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.py,sha256=dLAi_vQt9_DsT6wQZmbYC7X5-Wp15l0leUE6XkPaItg,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/sts_fields.py,sha256=aYbzy15btEg4-ocDT1qrspe7-atoWRrOJ_KmuPU6J14,8936
+tol/validators/tolid.py,sha256=yODebLYbKtlem3IpVcv8XImvq90r-AK68asH9JEawqo,3897
+tol/validators/types.py,sha256=KDBNqx5isJG5XI1l2V9Wmi9135ZwDace3MU6Qij3J6E,2612
 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-1.7.5b4.dist-info/licenses/LICENSE,sha256=RF9Jacy-9BpUAQQ20INhTgtaNBkmdTolYCHtrrkM2-8,1077
-tol_sdk-1.7.5b4.dist-info/METADATA,sha256=ZR7pMG-jGHoasPgY1zqvDMJMc4rm4rbqRi0hiC5pyN4,3081
-tol_sdk-1.7.5b4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tol_sdk-1.7.5b4.dist-info/entry_points.txt,sha256=jH3HfTwxjzog7E3lq8CKpUWGIRY9FSXbyL6CpUmv6D0,36
-tol_sdk-1.7.5b4.dist-info/top_level.txt,sha256=PwKMQLphyZNvagBoriVbl8uwHXQl8IC1niawVG0iXMM,10
-tol_sdk-1.7.5b4.dist-info/RECORD,,
+tol_sdk-1.8.1.dist-info/licenses/LICENSE,sha256=RF9Jacy-9BpUAQQ20INhTgtaNBkmdTolYCHtrrkM2-8,1077
+tol_sdk-1.8.1.dist-info/METADATA,sha256=wXZU-uS5CIiiWYa0EGwD8YiK2Z9eOJz5x78yTUPFMmk,3142
+tol_sdk-1.8.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tol_sdk-1.8.1.dist-info/entry_points.txt,sha256=jH3HfTwxjzog7E3lq8CKpUWGIRY9FSXbyL6CpUmv6D0,36
+tol_sdk-1.8.1.dist-info/top_level.txt,sha256=PwKMQLphyZNvagBoriVbl8uwHXQl8IC1niawVG0iXMM,10
+tol_sdk-1.8.1.dist-info/RECORD,,