added error recognition in spreadsheet

backend/app/services/spreadsheet_service.py

@@ -1,5 +1,3 @@
-# sample_spreadsheet_importer.py
-
 import logging
 import openpyxl
 from pydantic import ValidationError
@@ -10,11 +8,9 @@ from app.sample_models import SpreadsheetModel
 logging.basicConfig(level=logging.DEBUG)
 logger = logging.getLogger(__name__)
 
-
 class SpreadsheetImportError(Exception):
     pass
 
-
 class SampleSpreadsheetImporter:
     def __init__(self):
         self.filename = None
@@ -44,7 +40,18 @@ class SampleSpreadsheetImporter:
     def import_spreadsheet(self, file):
         return self.import_spreadsheet_with_errors(file)
 
-    def import_spreadsheet_with_errors(self, file) -> Tuple[List[SpreadsheetModel], List[dict], List[dict]]:
+    def get_expected_type(self, col_name):
+        type_mapping = {
+            'dewarname': str,
+            'puckname': str,
+            'positioninpuck': int,
+            'priority': int,
+            'oscillation': float,
+            # Add all other mappings based on model requirements
+        }
+        return type_mapping.get(col_name, str)  # Default to `str`
+
+    def import_spreadsheet_with_errors(self, file) -> Tuple[List[SpreadsheetModel], List[dict], List[dict], List[str]]:
         self.model = []
         self.filename = file.filename
         logger.info(f"Importing spreadsheet from .xlsx file: {self.filename}")
@@ -67,12 +74,17 @@ class SampleSpreadsheetImporter:
             logger.error(f"Failed to read the file: {str(e)}")
             raise SpreadsheetImportError(f"Failed to read the file: {str(e)}")
 
-        return self.process_spreadsheet(sheet)
+        # Unpack four values from the process_spreadsheet method
+        model, errors, raw_data, headers = self.process_spreadsheet(sheet)
 
-    def process_spreadsheet(self, sheet) -> Tuple[List[SpreadsheetModel], List[dict], List[dict]]:
+        # Now, return the values correctly
+        return model, errors, raw_data, headers
+
+    def process_spreadsheet(self, sheet) -> Tuple[List[SpreadsheetModel], List[dict], List[dict], List[str]]:
         model = []
         errors = []
         raw_data = []
+        headers = []
 
         # Skip the first 3 rows
         rows = list(sheet.iter_rows(min_row=4, values_only=True))
@@ -84,6 +96,16 @@ class SampleSpreadsheetImporter:
 
         expected_columns = 32  # Number of columns expected based on the model
 
+        # Add the headers (the first row in the spreadsheet or map them explicitly)
+        headers = [
+            'dewarname', 'puckname', 'pucktype', 'crystalname', 'positioninpuck', 'priority',
+            'comments', 'directory', 'proteinname', 'oscillation', 'aperture', 'exposure',
+            'totalrange', 'transmission', 'dose', 'targetresolution', 'datacollectiontype',
+            'processingpipeline', 'spacegroupnumber', 'cellparameters', 'rescutkey', 'rescutvalue',
+            'userresolution', 'pdbid', 'autoprocfull', 'procfull', 'adpenabled', 'noano',
+            'ffcscampaign', 'trustedhigh', 'autoprocextraparams', 'chiphiangles'
+        ]
+
         for index, row in enumerate(rows):
             if not any(row):
                 logger.debug(f"Skipping empty row at index {index}")
@@ -96,6 +118,7 @@ class SampleSpreadsheetImporter:
             if len(row) < expected_columns:
                 row = list(row) + [None] * (expected_columns - len(row))
 
+            # Prepare the record with the cleaned values
             record = {
                 'dewarname': self._clean_value(row[0], str),
                 'puckname': self._clean_value(row[1], str),
@@ -186,4 +209,4 @@ class SampleSpreadsheetImporter:
 
         self.model = model
         logger.info(f"Finished processing {len(model)} records with {len(errors)} errors")
-        return self.model, errors, raw_data
+        return self.model, errors, raw_data, headers  # Include headers in the response