Minor bug fixes.

2023-12-07 12:50:03 -06:00
parent cbf36a5b0b
commit 0dd51827a0
22 changed files with 308 additions and 370 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,7 +1,9 @@
+## 202312.02
+
 ## 202312.01

 - Control samples info now available in plate map.
- Backups will now create an regenerated xlsx file.
+- Backups will now create a regenerated xlsx file.
 - Report generator now does sums automatically.

 ## 202311.04
--- a/TODO.md
+++ b/TODO.md
@@ -1,9 +1,10 @@
+- [x] SubmissionReagentAssociation.query 
+- [x] Move as much from db.functions to objects as possible.
 - [x] Clean up DB objects after failed test fix.
 - [x] Fix tests.
- [ ] Fix pydant.PydSample.handle_duplicate_samples?
+- [x] Fix pydant.PydSample.handle_duplicate_samples?
 - [ ] See if the number of queries in BasicSubmission functions (and others) can be trimmed down.
 - [x] Document code 
-    - Done Submissions up to BasicSample
 - [x] Create a result object to facilitate returning function results.
 - [x] Refactor main_window_functions into as many objects (forms, etc.) as possible to clean it up.
 - [x] Integrate 'Construct First Strand' into the Artic import.
--- a/alembic.ini
+++ b/alembic.ini
@@ -55,9 +55,9 @@ version_path_separator = os  # Use os.pathsep. Default configuration used for ne
 # are written from script.py.mako
 # output_encoding = utf-8

-; sqlalchemy.url = sqlite:///L:\Robotics Laboratory Support\Submissions\submissions.db
+sqlalchemy.url = sqlite:///L:\Robotics Laboratory Support\Submissions\submissions.db
 ; sqlalchemy.url = sqlite:///C:\Users\lwark\Documents\Archives\Submissions_app_backups\DB_backups\submissions-new.db
-sqlalchemy.url = sqlite:///C:\Users\lwark\Documents\python\submissions\tests\test_assets\submissions-test.db
+; sqlalchemy.url = sqlite:///C:\Users\lwark\Documents\python\submissions\tests\test_assets\submissions-test.db


 [post_write_hooks]
--- a/alembic/versions/238c3c3e5863_submissionreagentassociations_added.py
+++ b/alembic/versions/238c3c3e5863_submissionreagentassociations_added.py
@@ -0,0 +1,44 @@
+"""SubmissionReagentAssociations added
+
+Revision ID: 238c3c3e5863
+Revises: 2684f065037c
+Create Date: 2023-12-05 12:57:17.446606
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '238c3c3e5863'
+down_revision = '2684f065037c'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('_reagents_submissions', schema=None) as batch_op:
+        batch_op.add_column(sa.Column('comments', sa.String(length=1024), nullable=True))
+        batch_op.alter_column('reagent_id',
+               existing_type=sa.INTEGER(),
+               nullable=False)
+        batch_op.alter_column('submission_id',
+               existing_type=sa.INTEGER(),
+               nullable=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('_reagents_submissions', schema=None) as batch_op:
+        batch_op.alter_column('submission_id',
+               existing_type=sa.INTEGER(),
+               nullable=True)
+        batch_op.alter_column('reagent_id',
+               existing_type=sa.INTEGER(),
+               nullable=True)
+        batch_op.drop_column('comments')
+
+    # ### end Alembic commands ###
--- a/src/submissions/init.py
+++ b/src/submissions/init.py
@@ -4,7 +4,7 @@ from pathlib import Path

 # Version of the realpython-reader package
 __project__ = "submissions"
-__version__ = "202312.1b"
+__version__ = "202312.2b"
 __author__ = {"name":"Landon Wark", "email":"Landon.Wark@phac-aspc.gc.ca"}
 __copyright__ = "2022-2023, Government of Canada"

--- a/src/submissions/main.py
+++ b/src/submissions/main.py
@@ -1,7 +1,6 @@
-import sys
-import os
-# environment variable must be set to enable qtwebengine in network path
+import sys, os
 from tools import ctx, setup_logger, check_if_app
+# environment variable must be set to enable qtwebengine in network path
 if check_if_app():
    os.environ['QTWEBENGINE_DISABLE_SANDBOX'] = "1"
 # setup custom logger
--- a/src/submissions/backend/db/init.py
+++ b/src/submissions/backend/db/init.py
@@ -1,5 +1,21 @@
 '''
 All database related operations.
 '''
-from .functions import *
-from .models import *
+from sqlalchemy import event
+from sqlalchemy.engine import Engine
+
+@event.listens_for(Engine, "connect")
+def set_sqlite_pragma(dbapi_connection, connection_record):
+    """
+    *should* allow automatic creation of foreign keys in the database
+    I have no idea how it actually works.
+
+    Args:
+        dbapi_connection (_type_): _description_
+        connection_record (_type_): _description_
+    """    
+    cursor = dbapi_connection.cursor()
+    cursor.execute("PRAGMA foreign_keys=ON")
+    cursor.close()
+
+from .models import *
--- a/src/submissions/backend/db/functions.py
+++ b/src/submissions/backend/db/functions.py
@@ -1,211 +0,0 @@
-'''Contains or imports all database convenience functions'''
-from tools import Result, Report
-from sqlalchemy import event
-from sqlalchemy.engine import Engine
-from sqlalchemy.exc import OperationalError as AlcOperationalError, IntegrityError as AlcIntegrityError
-from sqlite3 import OperationalError as SQLOperationalError, IntegrityError as SQLIntegrityError
-import logging
-import pandas as pd
-import json
-from .models import *
-import logging
-from backend.validators.pydant import *
-
-logger = logging.getLogger(f"Submissions_{__name__}")
-
-@event.listens_for(Engine, "connect")
-def set_sqlite_pragma(dbapi_connection, connection_record):
-    """
-    *should* allow automatic creation of foreign keys in the database
-    I have no idea how it actually works.
-
-    Args:
-        dbapi_connection (_type_): _description_
-        connection_record (_type_): _description_
-    """    
-    cursor = dbapi_connection.cursor()
-    cursor.execute("PRAGMA foreign_keys=ON")
-    cursor.close()
-
-def submissions_to_df(submission_type:str|None=None, limit:int=0) -> pd.DataFrame:
-    """
-    Convert submissions looked up by type to dataframe
-
-    Args:
-        ctx (Settings): settings object passed by gui
-        submission_type (str | None, optional): submission type (should be string in D3 of excel sheet) Defaults to None.
-        limit (int): Maximum number of submissions to return. Defaults to 0.
-
-    Returns:
-        pd.DataFrame: dataframe constructed from retrieved submissions
-    """    
-    logger.debug(f"Querying Type: {submission_type}")
-    logger.debug(f"Using limit: {limit}")
-    # use lookup function to create list of dicts
-    # subs = [item.to_dict() for item in lookup_submissions(ctx=ctx, submission_type=submission_type, limit=limit)]
-    subs = [item.to_dict() for item in BasicSubmission.query(submission_type=submission_type, limit=limit)]
-    logger.debug(f"Got {len(subs)} submissions.")
-    # make df from dicts (records) in list
-    df = pd.DataFrame.from_records(subs)
-    # Exclude sub information
-    try:
-        df = df.drop("controls", axis=1)
-    except:
-        logger.warning(f"Couldn't drop 'controls' column from submissionsheet df.")
-    try:
-        df = df.drop("ext_info", axis=1)
-    except:
-        logger.warning(f"Couldn't drop 'ext_info' column from submissionsheet df.")
-    try:
-        df = df.drop("pcr_info", axis=1)
-    except:
-        logger.warning(f"Couldn't drop 'pcr_info' column from submissionsheet df.")
-    # NOTE: Moved to submissions_to_df function
-    try:
-        del df['samples']
-    except KeyError:
-        pass
-    try:
-        del df['reagents']
-    except KeyError:
-        pass
-    try:
-        del df['comments']
-    except KeyError:
-        pass
-    return df
-
-def get_control_subtypes(type:str, mode:str) -> list[str]:
-    """
-    Get subtypes for a control analysis mode
-
-    Args:
-        ctx (Settings): settings object passed from gui
-        type (str): control type name
-        mode (str): analysis mode name
-
-    Returns:
-        list[str]: list of subtype names
-    """    
-    # Only the first control of type is necessary since they all share subtypes
-    try:
-        # outs = lookup_controls(ctx=ctx, control_type=type, limit=1)
-        outs = Control.query(control_type=type, limit=1)
-    except (TypeError, IndexError):
-        return []
-    # Get analysis mode data as dict
-    jsoner = json.loads(getattr(outs, mode))
-    logger.debug(f"JSON out: {jsoner}")
-    try:
-        genera = list(jsoner.keys())[0]
-    except IndexError:
-        return []
-    subtypes = [item for item in jsoner[genera] if "_hashes" not in item and "_ratio" not in item]
-    return subtypes
-
-def update_last_used(reagent:Reagent, kit:KitType):
-    """
-    Updates the 'last_used' field in kittypes/reagenttypes
-
-    Args:
-        reagent (models.Reagent): reagent to be used for update
-        kit (models.KitType): kit to be used for lookup
-    """    
-    report = Report()
-    logger.debug(f"Attempting update of reagent type at intersection of ({reagent}), ({kit})")
-    rt = ReagentType.query(kit_type=kit, reagent=reagent)
-    if rt != None:
-        assoc = KitTypeReagentTypeAssociation.query(kit_type=kit, reagent_type=rt)
-        if assoc != None:
-            if assoc.last_used != reagent.lot:
-                logger.debug(f"Updating {assoc} last used to {reagent.lot}")
-                assoc.last_used = reagent.lot
-                result = assoc.save()
-                return(report.add_result(result))
-    return report.add_result(Result(msg=f"Updating last used {rt} was not performed.", status="Information"))
-
-
-def check_kit_integrity(sub:BasicSubmission|KitType|PydSubmission, reagenttypes:list=[]) -> Tuple[list, Report]:
-    """
-    Ensures all reagents expected in kit are listed in Submission
-
-    Args:
-        sub (BasicSubmission | KitType): Object containing complete list of reagent types.
-        reagenttypes (list | None, optional): List to check against complete list. Defaults to None.
-
-    Returns:
-        dict|None: Result object containing a message and any missing components.
-    """    
-    report = Report()
-    logger.debug(type(sub))
-    # What type is sub?
-    # reagenttypes = []
-    match sub:
-        case PydSubmission():
-            # ext_kit = lookup_kit_types(ctx=ctx, name=sub.extraction_kit['value'])
-            ext_kit = KitType.query(name=sub.extraction_kit['value'])
-            ext_kit_rtypes = [item.name for item in ext_kit.get_reagents(required=True, submission_type=sub.submission_type['value'])]
-            reagenttypes = [item.type for item in sub.reagents]
-        case BasicSubmission():
-            # Get all required reagent types for this kit.
-            ext_kit_rtypes = [item.name for item in sub.extraction_kit.get_reagents(required=True, submission_type=sub.submission_type_name)]
-            # Overwrite function parameter reagenttypes
-            for reagent in sub.reagents:
-                logger.debug(f"For kit integrity, looking up reagent: {reagent}")
-                try:
-                    # rt = list(set(reagent.type).intersection(sub.extraction_kit.reagent_types))[0].name
-                    # rt = lookup_reagent_types(ctx=ctx, kit_type=sub.extraction_kit, reagent=reagent)
-                    rt = ReagentType.query(kit_type=sub.extraction_kit, reagent=reagent)
-                    logger.debug(f"Got reagent type: {rt}")
-                    if isinstance(rt, ReagentType):
-                        reagenttypes.append(rt.name)
-                except AttributeError as e:
-                    logger.error(f"Problem parsing reagents: {[f'{reagent.lot}, {reagent.type}' for reagent in sub.reagents]}")
-                    reagenttypes.append(reagent.type[0].name)
-                except IndexError:
-                    logger.error(f"No intersection of {reagent} type {reagent.type} and {sub.extraction_kit.reagent_types}")
-                    raise ValueError(f"No intersection of {reagent} type {reagent.type} and {sub.extraction_kit.reagent_types}")
-        case KitType():
-            ext_kit_rtypes = [item.name for item in sub.get_reagents(required=True)]
-        case _:
-            raise ValueError(f"There was no match for the integrity object.\n\nCheck to make sure they are imported from the same place because it matters.")
-    logger.debug(f"Kit reagents: {ext_kit_rtypes}")
-    logger.debug(f"Submission reagents: {reagenttypes}")
-    # check if lists are equal
-    check = set(ext_kit_rtypes) == set(reagenttypes)
-    logger.debug(f"Checking if reagents match kit contents: {check}")
-    # what reagent types are in both lists?
-    missing = list(set(ext_kit_rtypes).difference(reagenttypes))
-    logger.debug(f"Missing reagents types: {missing}")
-    # if lists are equal return no problem
-    if len(missing)==0:
-        result = None
-    else:
-        result = Result(msg=f"The submission you are importing is missing some reagents expected by the kit.\n\nIt looks like you are missing: {[item.upper() for item in missing]}\n\nAlternatively, you may have set the wrong extraction kit.\n\nThe program will populate lists using existing reagents.\n\nPlease make sure you check the lots carefully!", status="Warning")
-    report.add_result(result)
-    return report
-
-def update_subsampassoc_with_pcr(submission:BasicSubmission, sample:BasicSample, input_dict:dict) -> dict|None:
-    """
-    Inserts PCR results into wastewater submission/sample association
-
-    Args:
-        ctx (Settings): settings object passed down from gui
-        submission (models.BasicSubmission): Submission object
-        sample (models.BasicSample): Sample object
-        input_dict (dict): dictionary with info to be updated.
-
-    Returns:
-        dict|None: result object
-    """    
-    # assoc = lookup_submission_sample_association(ctx, submission=submission, sample=sample)
-    assoc = SubmissionSampleAssociation.query(submission=submission, sample=sample, limit=1)
-    for k,v in input_dict.items():
-        try:
-            setattr(assoc, k, v)
-        except AttributeError:
-            logger.error(f"Can't set {k} to {v}")
-    # result = store_object(ctx=ctx, object=assoc)
-    result = assoc.save()
-    return result
-
--- a/src/submissions/backend/db/models/controls.py
+++ b/src/submissions/backend/db/models/controls.py
@@ -4,9 +4,8 @@ All control related models.
 from __future__ import annotations
 from sqlalchemy import Column, String, TIMESTAMP, JSON, INTEGER, ForeignKey
 from sqlalchemy.orm import relationship, Query
-import logging
+import logging, json
 from operator import itemgetter
-import json
 from . import BaseClass
 from tools import setup_lookup, query_return
 from datetime import date, datetime
@@ -51,6 +50,26 @@ class ControlType(BaseClass):
                pass
        return query_return(query=query, limit=limit)
    
+    def get_subtypes(self, mode:str) -> List[str]:
+        """
+        Get subtypes associated with this controltype
+
+        Args:
+            mode (str): analysis mode name
+
+        Returns:
+            List[str]: list of subtypes available
+        """        
+        outs = self.instances[0]
+        jsoner = json.loads(getattr(outs, mode))
+        logger.debug(f"JSON out: {jsoner.keys()}")
+        try:
+            genera = list(jsoner.keys())[0]
+        except IndexError:
+            return []
+        subtypes = [item for item in jsoner[genera] if "_hashes" not in item and "_ratio" not in item]
+        return subtypes
+          
 class Control(BaseClass):
    """
    Base class of a control sample.
@@ -249,4 +268,3 @@ class Control(BaseClass):
    def save(self):
        self.__database_session__.add(self)
        self.__database_session__.commit()
-
--- a/src/submissions/backend/db/models/kits.py
+++ b/src/submissions/backend/db/models/kits.py
@@ -183,15 +183,6 @@ class ReagentType(BaseClass):
    # creator function: https://stackoverflow.com/questions/11091491/keyerror-when-adding-objects-to-sqlalchemy-association-object/11116291#11116291
    kit_types = association_proxy("reagenttype_kit_associations", "kit_type", creator=lambda kit: KitTypeReagentTypeAssociation(kit_type=kit))

-    # def __str__(self) -> str:
-    #     """
-    #     string representing this object
-
-    #     Returns:
-    #         str: string representing this object's name
-    #     """        
-    #     return self.name
-    
    def __repr__(self):
        return f"<ReagentType({self.name})>"
    
@@ -379,7 +370,17 @@ class Reagent(BaseClass):
    name = Column(String(64)) #: reagent name
    lot = Column(String(64)) #: lot number of reagent
    expiry = Column(TIMESTAMP) #: expiry date - extended by eol_ext of parent programmatically
-    submissions = relationship("BasicSubmission", back_populates="reagents", uselist=True) #: submissions this reagent is used in
+    # submissions = relationship("BasicSubmission", back_populates="reagents", uselist=True) #: submissions this reagent is used in
+
+    reagent_submission_associations = relationship(
+        "SubmissionReagentAssociation",
+        back_populates="reagent",
+        cascade="all, delete-orphan",
+    ) #: Relation to SubmissionSampleAssociation
+    # association proxy of "user_keyword_associations" collection
+    # to "keyword" attribute
+    submissions = association_proxy("reagent_submission_associations", "submission") #: Association proxy to SubmissionSampleAssociation.samples
+

    def __repr__(self):
        if self.name != None:
@@ -706,3 +707,69 @@ class SubmissionTypeKitTypeAssociation(BaseClass):
                query = query.join(KitType).filter(KitType.id==kit_type)
        limit = query.count()
        return query_return(query=query, limit=limit)
+
+class SubmissionReagentAssociation(BaseClass):
+
+    __tablename__ = "_reagents_submissions"
+
+    reagent_id = Column(INTEGER, ForeignKey("_reagents.id"), primary_key=True) #: id of associated sample
+    submission_id = Column(INTEGER, ForeignKey("_submissions.id"), primary_key=True)
+    comments = Column(String(1024))
+
+    submission = relationship("BasicSubmission", back_populates="submission_reagent_associations") #: associated submission
+
+    reagent = relationship(Reagent, back_populates="reagent_submission_associations")
+
+    def __repr__(self):
+        return f"<{self.submission.rsl_plate_num}&{self.reagent.lot}>"
+
+    def __init__(self, reagent=None, submission=None):
+        self.reagent = reagent
+        self.submission = submission
+        self.comments = ""
+
+    @classmethod
+    @setup_lookup
+    def query(cls, 
+              submission:"BasicSubmission"|str|int|None=None, 
+              reagent:Reagent|str|None=None,
+              limit:int=0) -> SubmissionReagentAssociation|List[SubmissionReagentAssociation]:
+        """
+        Lookup SubmissionReagentAssociations of interest.
+
+        Args:
+            submission (BasicSubmission&quot; | str | int | None, optional): Identifier of joined submission. Defaults to None.
+            reagent (Reagent | str | None, optional): Identifier of joined reagent. Defaults to None.
+            limit (int, optional): Maximum number of results to return (0 = all). Defaults to 0.
+
+        Returns:
+            SubmissionReagentAssociation|List[SubmissionReagentAssociation]: SubmissionReagentAssociation(s) of interest
+        """        
+        from . import BasicSubmission
+        query: Query = cls.__database_session__.query(cls)
+        match reagent:
+            case Reagent():
+                query = query.filter(cls.reagent==reagent)
+            case str():
+                # logger.debug(f"Filtering query with reagent: {reagent}")
+                reagent = Reagent.query(lot_number=reagent)
+                query = query.filter(cls.reagent==reagent)
+                # logger.debug([item.reagent.lot for item in query.all()])
+                # query = query.join(Reagent).filter(Reagent.lot==reagent)
+            case _:
+                pass
+        # logger.debug(f"Result of query after reagent: {query.all()}")
+        match submission:
+            case BasicSubmission():
+                query = query.filter(cls.submission==submission)
+            case str():
+                query = query.join(BasicSubmission).filter(BasicSubmission.rsl_plate_num==submission)
+            case int():
+                query = query.join(BasicSubmission).filter(BasicSubmission.id==submission)
+            case _:
+                pass
+        # logger.debug(f"Result of query after submission: {query.all()}")
+        # limit = query.count()
+        return query_return(query=query, limit=limit)
+
+
--- a/src/submissions/backend/db/models/submissions.py
+++ b/src/submissions/backend/db/models/submissions.py
@@ -6,13 +6,13 @@ from getpass import getuser
 import math, json, logging, uuid, tempfile, re, yaml
 from pprint import pformat
 from . import Reagent, SubmissionType, KitType, Organization
-from sqlalchemy import Column, String, TIMESTAMP, INTEGER, ForeignKey, Table, JSON, FLOAT, case
+from sqlalchemy import Column, String, TIMESTAMP, INTEGER, ForeignKey, JSON, FLOAT, case
 from sqlalchemy.orm import relationship, validates, Query
 from json.decoder import JSONDecodeError
 from sqlalchemy.ext.associationproxy import association_proxy
 import pandas as pd
 from openpyxl import Workbook
-from . import Base, BaseClass
+from . import BaseClass
 from tools import check_not_nan, row_map,  query_return, setup_lookup
 from datetime import datetime, date
 from typing import List
@@ -24,15 +24,6 @@ from pathlib import Path

 logger = logging.getLogger(f"submissions.{__name__}")

-# table containing reagents/submission relationships
-reagents_submissions = Table(
-                                "_reagents_submissions", 
-                                Base.metadata, 
-                                Column("reagent_id", INTEGER, ForeignKey("_reagents.id")), 
-                                Column("submission_id", INTEGER, ForeignKey("_submissions.id")),
-                                extend_existing = True
-                            )
-
 class BasicSubmission(BaseClass):
    """
    Concrete of basic submission which polymorphs into BacterialCulture and Wastewater
@@ -51,7 +42,7 @@ class BasicSubmission(BaseClass):
    submission_type_name = Column(String, ForeignKey("_submission_types.name", ondelete="SET NULL", name="fk_BS_subtype_name")) #: name of joined submission type
    technician = Column(String(64)) #: initials of processing tech(s)
    # Move this into custom types?
-    reagents = relationship("Reagent", back_populates="submissions", secondary=reagents_submissions) #: relationship to reagents
+    # reagents = relationship("Reagent", back_populates="submissions", secondary=reagents_submissions) #: relationship to reagents
    reagents_id = Column(String, ForeignKey("_reagents.id", ondelete="SET NULL", name="fk_BS_reagents_id")) #: id of used reagents
    extraction_info = Column(JSON) #: unstructured output from the extraction table logger.
    pcr_info = Column(JSON) #: unstructured output from pcr table logger or user(Artic)
@@ -69,6 +60,15 @@ class BasicSubmission(BaseClass):
    # to "keyword" attribute
    samples = association_proxy("submission_sample_associations", "sample") #: Association proxy to SubmissionSampleAssociation.samples

+    submission_reagent_associations = relationship(
+        "SubmissionReagentAssociation",
+        back_populates="submission",
+        cascade="all, delete-orphan",
+    ) #: Relation to SubmissionSampleAssociation
+    # association proxy of "user_keyword_associations" collection
+    # to "keyword" attribute
+    reagents = association_proxy("submission_reagent_associations", "reagent") #: Association proxy to SubmissionSampleAssociation.samples
+
    # Allows for subclassing into ex. BacterialCulture, Wastewater, etc.
    __mapper_args__ = {
        "polymorphic_identity": "Basic Submission",
@@ -438,6 +438,22 @@ class BasicSubmission(BaseClass):
        """        
        return "{{ rsl_plate_num }}"

+    @classmethod
+    def submissions_to_df(cls, submission_type:str|None=None, limit:int=0) -> pd.DataFrame:
+        logger.debug(f"Querying Type: {submission_type}")
+        logger.debug(f"Using limit: {limit}")
+        # use lookup function to create list of dicts
+        subs = [item.to_dict() for item in cls.query(submission_type=submission_type, limit=limit)]
+        logger.debug(f"Got {len(subs)} submissions.")
+        df = pd.DataFrame.from_records(subs)
+        # Exclude sub information
+        for item in ['controls', 'extraction_info', 'pcr_info', 'comment', 'comments', 'samples', 'reagents']:
+            try:
+                df = df.drop(item, axis=1)
+            except:
+                logger.warning(f"Couldn't drop '{item}' column from submissionsheet df.")
+        return df
+
    def set_attribute(self, key:str, value):
        """
        Performs custom attribute setting based on values.
@@ -479,6 +495,11 @@ class BasicSubmission(BaseClass):
                    field_value = value
            case "ctx" | "csv" | "filepath":
                return
+            case "comment":
+                if value == "" or value == None or value == 'null':
+                    field_value = None
+                else:
+                    field_value = dict(name="submitter", text=value, time=datetime.now())
            case _:
                field_value = value
        # insert into field
@@ -595,7 +616,8 @@ class BasicSubmission(BaseClass):
                start_date:date|str|int|None=None,
                end_date:date|str|int|None=None,
                reagent:Reagent|str|None=None,
-                chronologic:bool=False, limit:int=0, 
+                chronologic:bool=False, 
+                limit:int=0, 
                **kwargs
                ) -> BasicSubmission | List[BasicSubmission]:
        """
--- a/src/submissions/backend/excel/parser.py
+++ b/src/submissions/backend/excel/parser.py
@@ -9,9 +9,8 @@ import numpy as np
 from pathlib import Path
 from backend.db.models import *
 from backend.validators import PydSubmission, PydReagent, RSLNamer, PydSample
-import logging
+import logging, re
 from collections import OrderedDict
-import re
 from datetime import date
 from dateutil.parser import parse, ParserError
 from tools import check_not_nan, convert_nans_to_nones, Settings
@@ -256,8 +255,12 @@ class ReagentParser(object):
                    name = df.iat[relevant[item]['name']['row']-1, relevant[item]['name']['column']-1]
                    lot = df.iat[relevant[item]['lot']['row']-1, relevant[item]['lot']['column']-1]
                    expiry = df.iat[relevant[item]['expiry']['row']-1, relevant[item]['expiry']['column']-1]
+                    if 'comment' in relevant[item].keys():
+                        comment = df.iat[relevant[item]['comment']['row']-1, relevant[item]['comment']['column']-1]
+                    else:
+                        comment = ""
                except (KeyError, IndexError):
-                    listo.append(PydReagent(type=item.strip(), lot=None, expiry=None, name=None, missing=True))
+                    listo.append(PydReagent(type=item.strip(), lot=None, expiry=None, name=None, comment="", missing=True))
                    continue
                # If the cell is blank tell the PydReagent
                if check_not_nan(lot):
@@ -266,8 +269,8 @@ class ReagentParser(object):
                    missing = True
                # logger.debug(f"Got lot for {item}-{name}: {lot} as {type(lot)}")
                lot = str(lot)
-                logger.debug(f"Going into pydantic: name: {name}, lot: {lot}, expiry: {expiry}, type: {item.strip()}")
-                listo.append(PydReagent(type=item.strip(), lot=lot, expiry=expiry, name=name, missing=missing))
+                logger.debug(f"Going into pydantic: name: {name}, lot: {lot}, expiry: {expiry}, type: {item.strip()}, comment: {comment}")
+                listo.append(PydReagent(type=item.strip(), lot=lot, expiry=expiry, name=name, comment=comment, missing=missing))
        # logger.debug(f"Returning listo: {listo}")
        return listo

--- a/src/submissions/backend/excel/reports.py
+++ b/src/submissions/backend/excel/reports.py
@@ -2,9 +2,8 @@
 Contains functions for generating summary reports
 '''
 from pandas import DataFrame
-import logging
+import logging, re
 from datetime import date, timedelta
-import re
 from typing import List, Tuple
 from tools import jinja_template_loading, Settings

--- a/src/submissions/backend/validators/init.py
+++ b/src/submissions/backend/validators/init.py
@@ -3,7 +3,6 @@ from pathlib import Path
 from openpyxl import load_workbook
 from backend.db.models import BasicSubmission, SubmissionType

-
 logger = logging.getLogger(f"submissions.{__name__}")

 class RSLNamer(object):
--- a/src/submissions/backend/validators/pydant.py
+++ b/src/submissions/backend/validators/pydant.py
@@ -2,7 +2,7 @@
 Contains pydantic models and accompanying validators
 '''
 from operator import attrgetter
-import uuid
+import uuid, re, logging
 from pydantic import BaseModel, field_validator, Field
 from datetime import date, datetime, timedelta
 from dateutil.parser import parse
@@ -10,8 +10,6 @@ from dateutil.parser._parser import ParserError
 from typing import List, Any, Tuple
 from . import RSLNamer
 from pathlib import Path
-import re
-import logging
 from tools import check_not_nan, convert_nans_to_nones, jinja_template_loading, Report, Result, row_map
 from backend.db.models import *
 from sqlalchemy.exc import StatementError, IntegrityError
@@ -28,6 +26,14 @@ class PydReagent(BaseModel):
    expiry: date|None
    name: str|None
    missing: bool = Field(default=True)
+    comment: str|None = Field(default="", validate_default=True)
+
+    @field_validator('comment', mode='before')
+    @classmethod
+    def create_comment(cls, value):
+        if value == None:
+            return ""
+        return value

    @field_validator("type", mode='before')
    @classmethod
@@ -88,7 +94,7 @@ class PydReagent(BaseModel):
        else:
            return values.data['type']

-    def toSQL(self) -> Tuple[Reagent, Report]:
+    def toSQL(self, submission:BasicSubmission|str=None) -> Tuple[Reagent, Report]:
        """
        Converts this instance into a backend.db.models.kit.Reagent instance

@@ -96,6 +102,8 @@ class PydReagent(BaseModel):
            Tuple[Reagent, Report]: Reagent instance and result of function
        """        
        report = Report()
+        if self.model_extra != None:
+            self.__dict__.update(self.model_extra)
        logger.debug(f"Reagent SQL constructor is looking up type: {self.type}, lot: {self.lot}")
        reagent = Reagent.query(lot_number=self.lot)
        logger.debug(f"Result: {reagent}")
@@ -117,6 +125,11 @@ class PydReagent(BaseModel):
                            reagent.type.append(reagent_type)
                    case "name":
                        reagent.name = value
+                    case "comment":
+                        continue
+                assoc = SubmissionReagentAssociation(reagent=reagent, submission=submission)
+                assoc.comments = self.comment
+                reagent.reagent_submission_associations.append(assoc)
            # add end-of-life extension from reagent type to expiry date
            # NOTE: this will now be done only in the reporting phase to account for potential changes in end-of-life extensions
        return reagent, report
@@ -203,9 +216,17 @@ class PydSubmission(BaseModel, extra='allow'):
    extraction_kit: dict|None
    technician: dict|None
    submission_category: dict|None = Field(default=dict(value=None, missing=True), validate_default=True)
+    comment: dict|None = Field(default=dict(value="", missing=True), validate_default=True)
    reagents: List[dict]|List[PydReagent] = []
    samples: List[Any]

+    @field_validator('comment', mode='before')
+    @classmethod
+    def create_comment(cls, value):
+        if value == None:
+            return ""
+        return value
+
    @field_validator("submitter_plate_num")
    @classmethod
    def enforce_with_uuid(cls, value):
@@ -218,13 +239,19 @@ class PydSubmission(BaseModel, extra='allow'):
    @field_validator("submitted_date", mode="before")
    @classmethod
    def rescue_date(cls, value):
-        if value == None:
+        logger.debug(f"\n\nDate coming into pydantic: {value}\n\n")
+        try:
+            check = value['value'] == None
+        except TypeError:
+            check = True
+        if check:
            return dict(value=date.today(), missing=True)
        return value

    @field_validator("submitted_date")
    @classmethod
    def strip_datetime_string(cls, value):
+        
        if isinstance(value['value'], datetime):
            return value
        if isinstance(value['value'], date):
@@ -307,7 +334,6 @@ class PydSubmission(BaseModel, extra='allow'):
    @field_validator("submission_type", mode='before')
    @classmethod
    def make_submission_type(cls, value, values):
-        logger.debug(f"Submission type coming into pydantic: {value}")
        if not isinstance(value, dict):
            value = {"value": value}
        if check_not_nan(value['value']):
@@ -331,8 +357,8 @@ class PydSubmission(BaseModel, extra='allow'):

    def handle_duplicate_samples(self):
        """
-        Collapses multiple samples with same submitter id into one with lists for rows, columns
-        TODO: Find out if this is really necessary
+        Collapses multiple samples with same submitter id into one with lists for rows, columns.
+        Necessary to prevent trying to create duplicate samples in SQL creation.
        """        
        submitter_ids = list(set([sample.submitter_id for sample in self.samples]))
        output = []
@@ -581,9 +607,37 @@ class PydSubmission(BaseModel, extra='allow'):
        logger.debug(f"Template rendered as: {render}")
        return render

-class PydContact(BaseModel):
-    
+    def check_kit_integrity(self, reagenttypes:list=[]) -> Report:
+        """
+        Ensures all reagents expected in kit are listed in Submission
+       
+        Args:
+            reagenttypes (list | None, optional): List to check against complete list. Defaults to None.

+        Returns:
+            Report: Result object containing a message and any missing components.
+        """    
+        report = Report()
+        ext_kit = KitType.query(name=self.extraction_kit['value'])
+        ext_kit_rtypes = [item.name for item in ext_kit.get_reagents(required=True, submission_type=self.submission_type['value'])]
+        reagenttypes = [item.type for item in self.reagents]
+        logger.debug(f"Kit reagents: {ext_kit_rtypes}")
+        logger.debug(f"Submission reagents: {reagenttypes}")
+        # check if lists are equal
+        check = set(ext_kit_rtypes) == set(reagenttypes)
+        logger.debug(f"Checking if reagents match kit contents: {check}")
+        # what reagent types are in both lists?
+        missing = list(set(ext_kit_rtypes).difference(reagenttypes))
+        logger.debug(f"Missing reagents types: {missing}")
+        # if lists are equal return no problem
+        if len(missing)==0:
+            result = None
+        else:
+            result = Result(msg=f"The submission you are importing is missing some reagents expected by the kit.\n\nIt looks like you are missing: {[item.upper() for item in missing]}\n\nAlternatively, you may have set the wrong extraction kit.\n\nThe program will populate lists using existing reagents.\n\nPlease make sure you check the lots carefully!", status="Warning")
+        report.add_result(result)
+        return report
+
+class PydContact(BaseModel):
    name: str
    phone: str|None
    email: str|None
--- a/src/submissions/frontend/visualizations/control_charts.py
+++ b/src/submissions/frontend/visualizations/control_charts.py
@@ -194,73 +194,6 @@ def construct_chart(df:pd.DataFrame, modes:list, ytitle:str|None=None) -> Figure
        fig.add_traces(bar.data)
    return generic_figure_markers(fig=fig, modes=modes, ytitle=ytitle)

-# Below are the individual construction functions. They must be named "construct_{mode}_chart" and 
-# take only json_in and mode to hook into the main processor.
-
-# def construct_refseq_chart(df:pd.DataFrame, group_name:str, mode:str) -> Figure:
-#     """
-#     Constructs intial refseq chart for both contains and matches (depreciated).
-
-#     Args:
-#         df (pd.DataFrame): dataframe containing all sample data for the group.
-#         group_name (str): name of the group being processed.
-#         mode (str): contains or matches, overwritten by hardcoding, so don't think about it too hard.
-
-#     Returns:
-#         Figure: initial figure with contains and matches traces.
-#     """    
-#     # This overwrites the mode from the signature, might get confusing.
-#     fig = Figure()
-#     modes = ['contains', 'matches']
-#     for ii, mode in enumerate(modes): 
-#         bar = px.bar(df, x="submitted_date", 
-#             y=f"{mode}_ratio", 
-#             color="target", 
-#             title=f"{group_name}_{mode}", 
-#             barmode='stack', 
-#             hover_data=["genus", "name", f"{mode}_hashes"], 
-#             text="genera"
-#         )
-#         bar.update_traces(visible = ii == 0)
-#         # Plotly express returns a full figure, so we have to use the data from that figure only.
-#         fig.add_traces(bar.data)
-#     # sys.exit(f"number of traces={len(fig.data)}")
-#     return generic_figure_markers(fig=fig, modes=modes)
-
-# def construct_kraken_chart(settings:dict, df:pd.DataFrame, group_name:str, mode:str) -> Figure:
-#     """
-#     Constructs intial refseq chart for each mode in the kraken config settings. (depreciated)
-
-#     Args:
-#         settings (dict): settings passed down from click.
-#         df (pd.DataFrame): dataframe containing all sample data for the group.
-#         group_name (str): name of the group being processed.
-#         mode (str): kraken modes retrieved from config file by setup.
-
-#     Returns:
-#         Figure: initial figure with traces for modes
-#     """    
-#     df[f'{mode}_count'] = pd.to_numeric(df[f'{mode}_count'],errors='coerce')
-#     df = df.groupby('submitted_date')[f'{mode}_count'].nlargest(2)
-    
-#     # The actual percentage from kraken was off due to exclusion of NaN, recalculating.
-#     df[f'{mode}_percent'] = 100 * df[f'{mode}_count'] / df.groupby('submitted_date')[f'{mode}_count'].transform('sum')
-#     modes = settings['modes'][mode]
-#     # This overwrites the mode from the signature, might get confusing.
-#     fig = Figure()
-#     for ii, entry in enumerate(modes):         
-#         bar = px.bar(df, x="submitted_date", 
-#             y=entry,
-#             color="genus",
-#             title=f"{group_name}_{entry}", 
-#             barmode="stack", 
-#             hover_data=["genus", "name", "target"],
-#             text="genera",
-#         )
-#         bar.update_traces(visible = ii == 0)
-#         fig.add_traces(bar.data)
-#     return generic_figure_markers(fig=fig, modes=modes)
-
 def divide_chunks(input_list:list, chunk_count:int):
    """
    Divides a list into {chunk_count} equal parts
--- a/src/submissions/frontend/visualizations/plate_map.py
+++ b/src/submissions/frontend/visualizations/plate_map.py
@@ -1,9 +1,8 @@
 from pathlib import Path
-import sys
 from PIL import Image, ImageDraw, ImageFont
 import numpy as np
 from tools import check_if_app, jinja_template_loading
-import logging
+import logging, sys

 logger = logging.getLogger(f"submissions.{__name__}")

--- a/src/submissions/frontend/widgets/app.py
+++ b/src/submissions/frontend/widgets/app.py
@@ -1,8 +1,6 @@
 '''
 Constructs main application.
-TODO: Complete.
 '''
-import sys
 from PyQt6.QtWidgets import (
    QTabWidget, QWidget, QVBoxLayout,
    QHBoxLayout, QScrollArea, QMainWindow, 
@@ -14,14 +12,12 @@ from backend.validators import PydReagent
 from tools import check_if_app, Settings, Report
 from .pop_ups import  AlertPop
 from .misc import AddReagentForm, LogParser
-import logging
+import logging, webbrowser, sys
 from datetime import date
-import webbrowser
 from .submission_table import SubmissionsSheet
 from .submission_widget import SubmissionFormContainer
 from .controls_chart import ControlsViewer
 from .kit_creator import KitAdder
-import webbrowser

 logger = logging.getLogger(f'submissions.{__name__}')
 logger.info("Hello, I am a logger")
--- a/src/submissions/frontend/widgets/controls_chart.py
+++ b/src/submissions/frontend/widgets/controls_chart.py
@@ -3,8 +3,8 @@ from PyQt6.QtWidgets import (
    QWidget, QVBoxLayout, QComboBox, QHBoxLayout,
    QDateEdit, QLabel, QSizePolicy
 )
-from PyQt6.QtCore import QSignalBlocker, QLoggingCategory
-from backend.db import ControlType, Control, get_control_subtypes
+from PyQt6.QtCore import QSignalBlocker
+from backend.db import ControlType, Control#, get_control_subtypes
 from PyQt6.QtCore import QDate, QSize
 import logging, sys
 from tools import Report, Result
@@ -88,7 +88,8 @@ class ControlsViewer(QWidget):
        self.mode = self.mode_typer.currentText()
        self.sub_typer.clear()
        # lookup subtypes
-        sub_types = get_control_subtypes(type=self.con_type, mode=self.mode)
+        # sub_types = get_control_subtypes(type=self.con_type, mode=self.mode)
+        sub_types = ControlType.query(name=self.con_type).get_subtypes(mode=self.mode)
        # sub_types = lookup_controls(ctx=obj.ctx, control_type=obj.con_type)
        if sub_types != []:
            # block signal that will rerun controls getter and update sub_typer
--- a/src/submissions/frontend/widgets/submission_table.py
+++ b/src/submissions/frontend/widgets/submission_table.py
@@ -15,7 +15,6 @@ from PyQt6.QtWidgets import (
 from PyQt6.QtWebEngineWidgets import QWebEngineView
 from PyQt6.QtCore import Qt, QAbstractTableModel, QSortFilterProxyModel
 from PyQt6.QtGui import QAction, QCursor, QPixmap, QPainter
-from backend.db.functions import submissions_to_df
 from backend.db.models import BasicSubmission
 from backend.excel import make_report_html, make_report_xlsx
 from tools import check_if_app, Report, Result, jinja_template_loading, get_first_blank_df_row, row_map
@@ -102,7 +101,8 @@ class SubmissionsSheet(QTableView):
        """
        sets data in model
        """        
-        self.data = submissions_to_df()
+        # self.data = submissions_to_df()
+        self.data = BasicSubmission.submissions_to_df()
        try:
            self.data['id'] = self.data['id'].apply(str)
            self.data['id'] = self.data['id'].str.zfill(3)
--- a/src/submissions/frontend/widgets/submission_widget.py
+++ b/src/submissions/frontend/widgets/submission_widget.py
@@ -5,23 +5,20 @@ from PyQt6.QtWidgets import (
 from PyQt6.QtCore import pyqtSignal
 from pathlib import Path
 from . import select_open_file, select_save_file
-import logging
+import logging, difflib, inspect, json, sys
 from pathlib import Path
 from tools import Report, Result, check_not_nan
 from backend.excel.parser import SheetParser, PCRParser
 from backend.validators import PydSubmission, PydReagent
 from backend.db import (
-    check_kit_integrity, KitType, Organization, SubmissionType, Reagent, 
+    KitType, Organization, SubmissionType, Reagent, 
    ReagentType, KitTypeReagentTypeAssociation, BasicSubmission
 )
 from pprint import pformat
 from .pop_ups import QuestionAsker, AlertPop
 # from .misc import ReagentFormWidget
 from typing import List, Tuple
-import difflib
 from datetime import date
-import inspect
-import json

 logger = logging.getLogger(f"submissions.{__name__}")

@@ -143,14 +140,14 @@ class SubmissionFormContainer(QWidget):
            return
        except AttributeError:
            self.prsr = SheetParser(ctx=self.app.ctx, filepath=fname)
-        try:
-            logger.debug(f"Submission dictionary:\n{pformat(self.prsr.sub)}")
-            self.pyd = self.prsr.to_pydantic()
-            logger.debug(f"Pydantic result: \n\n{pformat(self.pyd)}\n\n")
-        except Exception as e:
-            report.add_result(Result(msg=f"Problem creating pydantic model:\n\n{e}", status="Critical"))
-            self.report.add_result(report)
-            return
+        # try:
+        logger.debug(f"Submission dictionary:\n{pformat(self.prsr.sub)}")
+        self.pyd = self.prsr.to_pydantic()
+        logger.debug(f"Pydantic result: \n\n{pformat(self.pyd)}\n\n")
+        # except Exception as e:
+        #     report.add_result(Result(msg=f"Problem creating pydantic model:\n\n{e}", status="Critical"))
+        #     self.report.add_result(report)
+        #     return
        self.form = self.pyd.toForm(parent=self)
        self.layout().addWidget(self.form)
        kit_widget = self.form.find_widgets(object_name="extraction_kit")[0].input
@@ -265,7 +262,8 @@ class SubmissionFormContainer(QWidget):
        self.pyd: PydSubmission = self.form.parse_form()
        logger.debug(f"Submission: {pformat(self.pyd)}")
        logger.debug("Checking kit integrity...")
-        result = check_kit_integrity(sub=self.pyd)
+        # result = check_kit_integrity(sub=self.pyd)
+        result = self.pyd.check_kit_integrity()
        report.add_result(result)
        if len(result.results) > 0:
            self.report.add_result(report)
@@ -417,7 +415,8 @@ class SubmissionFormWidget(QWidget):
        # self.ignore = [None, "", "qt_spinbox_lineedit", "qt_scrollarea_viewport", "qt_scrollarea_hcontainer",
        #                "qt_scrollarea_vcontainer", "submit_btn"
        #                ]
-        self.ignore = ['filepath', 'samples', 'reagents', 'csv', 'ctx']
+        self.ignore = ['filepath', 'samples', 'reagents', 'csv', 'ctx', 'comment']
+        self.recover = ['filepath', 'samples', 'csv', 'comment']
        layout = QVBoxLayout()
        for k, v in kwargs.items():
            if k not in self.ignore:
@@ -448,8 +447,6 @@ class SubmissionFormWidget(QWidget):
        logger.debug(f"Hello from form parser!")
        info = {}
        reagents = []
-        if hasattr(self, 'csv'):
-            info['csv'] = self.csv
        for widget in self.findChildren(QWidget):
            # logger.debug(f"Parsed widget of type {type(widget)}")
            match widget:
@@ -463,9 +460,13 @@ class SubmissionFormWidget(QWidget):
                        info[field] = value
        logger.debug(f"Info: {pformat(info)}")
        logger.debug(f"Reagents: {pformat(reagents)}")
-        # sys.exit()
+        # logger.debug(f"Attrs not in info: {[k for k, v in self.__dict__.items() if k not in info.keys()]}")
+        for item in self.recover:
+            if hasattr(self, item):
+                info[item] = getattr(self, item)
        # app = self.parent().parent().parent().parent().parent().parent().parent().parent
-        submission = PydSubmission(filepath=self.filepath, reagents=reagents, samples=self.samples, **info)
+        # submission = PydSubmission(filepath=self.filepath, reagents=reagents, samples=self.samples, **info)
+        submission = PydSubmission(reagents=reagents, **info)
        return submission
    
    class InfoItem(QWidget):
--- a/src/submissions/tools.py
+++ b/src/submissions/tools.py
@@ -5,12 +5,9 @@ from __future__ import annotations
 from pathlib import Path
 import re
 import numpy as np
-import logging
+import logging, re, yaml, sys, os, stat, platform, getpass, inspect
 import pandas as pd
 from jinja2 import Environment, FileSystemLoader
-import yaml
-import sys, os, stat, platform, getpass
-import logging
 from logging import handlers
 from pathlib import Path
 from sqlalchemy.orm import Query, Session
@@ -18,8 +15,6 @@ from sqlalchemy import create_engine
 from pydantic import field_validator, BaseModel, Field
 from pydantic_settings import BaseSettings, SettingsConfigDict
 from typing import Any, Tuple, Literal, List
-import inspect
-

 logger = logging.getLogger(f"submissions.{__name__}")