Addition of procedure parser in import.

src/submissions/backend/excel/parsers/__init__.py

@@ -1,14 +1,15 @@
 """
 
 """
+from __future__ import annotations
 import logging, re
 from pathlib import Path
-from typing import Generator, Tuple
-from openpyxl import load_workbook
+from typing import Generator, Tuple, TYPE_CHECKING
 from pandas import DataFrame
 from backend.validators import pydant
-from backend.db.models import Procedure
-from dataclasses import dataclass
+if TYPE_CHECKING:
+    from backend.db.models import ProcedureType
+
 
 logger = logging.getLogger(f"submissions.{__name__}")
 
@@ -30,7 +31,7 @@ class DefaultParser(object):
         return instance
 
 
-    def __init__(self, filepath: Path | str, procedure: Procedure|None=None, range_dict: dict | None = None, *args, **kwargs):
+    def __init__(self, filepath: Path | str, proceduretype: ProcedureType|None=None, range_dict: dict | None = None, *args, **kwargs):
         """
 
         Args:
@@ -40,7 +41,7 @@ class DefaultParser(object):
             *args ():
             **kwargs ():
         """
-        self.procedure = procedure
+        self.proceduretype = proceduretype
         try:
             self._pyd_object = getattr(pydant, f"Pyd{self.__class__.__name__.replace('Parser', '')}")
         except AttributeError:
@@ -58,6 +59,13 @@ class DefaultParser(object):
         data['filepath'] = self.filepath
         return self._pyd_object(**data)
 
+    @classmethod
+    def correct_procedure_type(cls, proceduretype: str | "ProcedureType"):
+        from backend.db.models import ProcedureType
+        if isinstance(proceduretype, str):
+            proceduretype = ProcedureType.query(name=proceduretype)
+        return proceduretype
+
 
 class DefaultKEYVALUEParser(DefaultParser):
 
@@ -90,7 +98,6 @@ class DefaultTABLEParser(DefaultParser):
 
     default_range_dict = [dict(
         header_row=20,
-        end_row=116,
         sheet="Sample List"
     )]
 
@@ -98,15 +105,25 @@ class DefaultTABLEParser(DefaultParser):
     def parsed_info(self):
         for item in self.range_dict:
             list_worksheet = self.workbook[item['sheet']]
-            list_df = DataFrame([item for item in list_worksheet.values][item['header_row'] - 1:])
+            if "end_row" in item.keys():
+                list_df = DataFrame([item for item in list_worksheet.values][item['header_row'] - 1:item['end_row']-1])
+            else:
+                list_df = DataFrame([item for item in list_worksheet.values][item['header_row'] - 1:])
             list_df.columns = list_df.iloc[0]
             list_df = list_df[1:]
             list_df = list_df.dropna(axis=1, how='all')
             for ii, row in enumerate(list_df.iterrows()):
-                output = {key.lower().replace(" ", "_"): value for key, value in row[1].to_dict().items()}
+                output = {}
+                for key, value in row[1].to_dict().items():
+                    if isinstance(key, str):
+                        key = key.lower().replace(" ", "_")
+                        key = re.sub(r"_(\(.*\)|#)", "", key)
+                    logger.debug(f"Row {ii} values: {key}: {value}")
+                    output[key] = value
                 yield output
 
     def to_pydantic(self, **kwargs):
         return [self._pyd_object(**output) for output in self.parsed_info]
 
-from .submission_parser import *
+from .clientsubmission_parser import *
+from backend.excel.parsers.results_parsers.pcr_results_parser import *