fhir-sheets 2.1.0__tar.gz → 2.1.3__tar.gz

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fhir-sheets
-Version: 2.1.0
+Version: 2.1.3
 Summary: FhirSheets is a command-line tool that reads an Excel file in FHIR cohort format and generates FHIR bundle JSON files from it. Each row in the template Excel file is used to create an individual JSON file, outputting them to a specified folder.
 License-File: LICENSE
 Author: Michael Riley
@@ -14,6 +14,7 @@ Requires-Dist: jsonpath-ng (==1.6.1)
 Requires-Dist: openpyxl (==3.1.5)
 Requires-Dist: orjson (==3.10.7)
 Requires-Dist: ply (==3.11)
+Requires-Dist: pytest_cov (==7.0.0)
 Description-Content-Type: text/markdown
 
 # FHIRSheets

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "fhir-sheets"
-version = "2.1.0"
+version = "2.1.3"
 description = "FhirSheets is a command-line tool that reads an Excel file in FHIR cohort format and generates FHIR bundle JSON files from it. Each row in the template Excel file is used to create an individual JSON file, outputting them to a specified folder."
 authors = ["Michael Riley <Michael.Riley@gtri.gatech.edu>"]
 packages = [{include = "fhir_sheets", from = "src"}]
@@ -14,6 +14,7 @@ jsonpath-ng = "1.6.1"
 openpyxl = "3.1.5"
 orjson = "3.10.7"
 ply = "3.11"
+pytest_cov = "7.0.0"
 
 [build-system]
 requires = ["poetry-core"]

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/src/fhir_sheets/cli/main.py

@@ -29,7 +29,6 @@ def main(input_file, output_folder):
     if not output_folder_path.exists():
         output_folder_path.mkdir(parents=True, exist_ok=True)  # Create the folder if it doesn't exist
     resource_definition_entities, resource_link_entities, cohort_data = read_input.read_xlsx_and_process(input_file)
-    pprint(cohort_data)
     #For each index of patients
     for i in range(0,cohort_data.get_num_patients()):
         # Construct the file path for each JSON file

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/src/fhir_sheets/core/conversion.py

@@ -27,6 +27,19 @@ def create_transaction_bundle(resource_definition_entities: List[ResourceDefinit
         add_resource_to_transaction_bundle(root_bundle, fhir_resource)
     return root_bundle
 
+def create_singular_resource(singleton_entity_name: str, resource_definition_entities: List[ResourceDefinition], resource_link_entities: List[ResourceLink], cohort_data: CohortData, index = 0):
+    created_resources = {}
+    for resource_definition in resource_definition_entities:
+        entity_name = resource_definition.entity_name
+        #Create and collect fhir resources
+        fhir_resource = create_fhir_resource(resource_definition, cohort_data, index)
+        created_resources[entity_name] = fhir_resource
+        if entity_name == singleton_entity_name:
+            singleton_fhir_resource = fhir_resource
+    add_default_resource_links(created_resources, resource_link_entities)
+    create_resource_links(created_resources, resource_link_entities, preview_mode=True)
+    return singleton_fhir_resource
+
 #Initialize root bundle definition
 def initialize_bundle():
     root_bundle = {}
@@ -150,12 +163,21 @@ def add_default_resource_links(created_resources: dict, resource_link_entities:
     return
         
             
-#Create resource references/links with created entities
-def create_resource_links(created_resources, resource_link_entites):
+#List function to create resource references/links with created entities
+def create_resource_links(created_resources, resource_link_entites, preview_mode = False):
+    #TODO: Build resource links
+    print("Building resource links")
+    for resource_link_entity in resource_link_entites:
+        create_resource_link(created_resources, resource_link_entity, preview_mode)
+    return
+    
+#Singular function to create a resource link.
+def create_resource_link(created_resources, resource_link_entity, preview_mode = False):
+    # template scaffolding
     reference_json_block = {
         "reference" : "$value"
     }
-
+    #Special reference handling blocks, in the form of (origin_resource, destination_resource, reference_path)
     arrayType_references = [
         ('diagnosticreport', 'specimen', 'specimen'),
         ('diagnosticreport', 'practitioner', 'performer'),
@@ -165,35 +187,36 @@ def create_resource_links(created_resources, resource_link_entites):
         ('diagnosticreport', 'observation', 'result'),
         ('diagnosticreport', 'imagingStudy', 'imagingStudy'),
     ]
-    #TODO: Build resource links
-    print("Building resource links")
-    for resource_link_entity in resource_link_entites:
-        try:
-            origin_resource = created_resources[resource_link_entity.origin_resource]
-        except KeyError:
-            print(f"WARNING: In ResourceLinks tab, found a Origin Resource of : {resource_link_entity.origin_resource}  but no such entity found in PatientData")
-            continue
-        try:
-            destination_resource = created_resources[resource_link_entity.destination_resource]
-        except KeyError:
-            print(f"WARNING: In ResourceLinks tab, found a Desitnation Resource  of : {resource_link_entity.destination_resource}  but no such entity found in PatientData")
-            continue
-        destination_resource_type = created_resources[resource_link_entity.destination_resource]['resourceType']
-        destination_resource_id = created_resources[resource_link_entity.destination_resource]['id']
-        link_tuple = (created_resources[resource_link_entity.origin_resource]['resourceType'].strip().lower(),
-                      created_resources[resource_link_entity.destination_resource]['resourceType'].strip().lower(),
-                      resource_link_entity.reference_path.strip().lower())
-        if link_tuple in arrayType_references:
-            if resource_link_entity.reference_path.strip().lower() not in origin_resource:
-                origin_resource[resource_link_entity.reference_path.strip().lower()] = []
-            new_reference = reference_json_block.copy()
-            new_reference['reference'] = destination_resource_type + "/" + destination_resource_id
-            origin_resource[resource_link_entity.reference_path.strip().lower()].append(new_reference)
-        else:
-            origin_resource[resource_link_entity.reference_path.strip().lower()] = reference_json_block.copy()
-            origin_resource[resource_link_entity.reference_path.strip().lower()]["reference"] = destination_resource_type + "/" + destination_resource_id
+    #Find the origin and destination resource from the link
+    try:
+        origin_resource = created_resources[resource_link_entity.origin_resource]
+    except KeyError:
+        print(f"WARNING: In ResourceLinks tab, found a Origin Resource of : {resource_link_entity.origin_resource}  but no such entity found in PatientData")
+        return
+    try:
+        destination_resource = created_resources[resource_link_entity.destination_resource]
+    except KeyError:
+        print(f"WARNING: In ResourceLinks tab, found a Desitnation Resource  of : {resource_link_entity.destination_resource}  but no such entity found in PatientData")
+        return
+    #Estable the value of the refence
+    if preview_mode:
+        reference_value = destination_resource['resourceType'] + "/" + resource_link_entity.destination_resource
+    else:
+        reference_value = destination_resource['resourceType'] + "/" + destination_resource['id']
+    link_tuple = (origin_resource['resourceType'].strip().lower(),
+                    destination_resource['resourceType'].strip().lower(),
+                    resource_link_entity.reference_path.strip().lower())
+    if link_tuple in arrayType_references:
+        if resource_link_entity.reference_path.strip().lower() not in origin_resource:
+            origin_resource[resource_link_entity.reference_path.strip().lower()] = []
+        new_reference = reference_json_block.copy()
+        new_reference['reference'] = reference_value
+        origin_resource[resource_link_entity.reference_path.strip().lower()].append(new_reference)
+    else:
+        origin_resource[resource_link_entity.reference_path.strip().lower()] = reference_json_block.copy()
+        origin_resource[resource_link_entity.reference_path.strip().lower()]["reference"] = reference_value
     return
-    
+
 def add_resource_to_transaction_bundle(root_bundle, fhir_resource):
     entry = {}
     entry['fullUrl'] = "urn:uuid:"+fhir_resource['id']
@@ -235,7 +258,7 @@ def build_structure(current_struct: Dict, json_path: str, resource_definition: R
     #SPECIAL HANDLING CLAUSE
     matching_handler = next((handler for handler in special_values.custom_handlers if (json_path.startswith(handler) or json_path == handler)), None)
     if matching_handler is not None:
-        return special_values.custom_handlers[matching_handler].assign_value(json_path, resource_definition,  current_struct, parts[-1], value)
+        return special_values.custom_handlers[matching_handler].assign_value(json_path, resource_definition, dataType,  current_struct, parts[-1], value)
     #Ignore dollar sign ($) and drill farther down
     if part == '$' or part == resource_definition.resource_type.strip():
         #Ignore the dollar sign and the resourcetype

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/src/fhir_sheets/core/model/resource_definition_entity.py

@@ -17,4 +17,4 @@ class ResourceDefinition:
         self.profiles = entity_data.get('Profile(s)')
 
     def __repr__(self) -> str:
-        return f"FhirEntity(entity_name='{self.entity_name}', resource_type='{self.resource_type}', profiles={self.profiles})"
+        return f"ResourceDefinition(entity_name='{self.entity_name}', resource_type='{self.resource_type}', profiles={self.profiles})"

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/src/fhir_sheets/core/read_input.py

@@ -33,7 +33,7 @@ def process_sheet_resource_definitions(sheet):
     headers = [cell.value for cell in next(sheet.iter_rows(min_row=1, max_row=1))]  # Get headers
 
     for row in sheet.iter_rows(min_row=3, values_only=True):
-        row_data = dict(zip(headers, row))  # Create a dictionary for each row
+        row_data = dict((h, r) for h, r in zip(headers, row) if h is not None)  # Create a dictionary for each row
         if all(cell is None or cell == "" for cell in row_data.values()):
             continue
         # Split 'Profile(s)' column into a list of URLs
@@ -41,7 +41,7 @@ def process_sheet_resource_definitions(sheet):
             row_data["Profile(s)"] = [url.strip() for url in row_data["Profile(s)"].split(",")]
         resource_definition_entities.append(ResourceDefinition(row_data))
         resource_definitions.append(row_data)
-
+    print(f"Resource Definitions\n----------{resource_definitions}")
     return resource_definition_entities
 
 # Function to process the specific sheet with 'OriginResource', 'ReferencePath', and 'DestinationResource'
@@ -55,57 +55,9 @@ def process_sheet_resource_links(sheet):
             continue
         resource_links.append(row_data)
         resource_link_entities.append(ResourceLink(row_data))
-
+    print(f"Resource Links\n----------{resource_links}")
     return resource_link_entities
 
-# Function to process the "PatientData" sheet
-def process_sheet_patient_data(sheet, resource_definition_entities):
-    # Initialize the dictionary to store the processed data
-    patient_data = {}
-    cohort_data = CohortData()
-    # Extract the data from the first 6 rows (Entity To Query, JsonPath, etc.)
-    for col in sheet.iter_cols(min_row=1, max_row=6, min_col=3, values_only=True):  # Start from 3rd column
-        if all(entry is None for entry in col):
-            continue
-        entity_name = col[0]  # The entity name comes from the first row (Entity To Query)
-        field_name = col[5]  #The "Data Element" comes from the fifth row
-        if (entity_name is None or entity_name == "") and (field_name is not None and field_name != ""):
-            print(f"WARNING: - Reading Patient Data Issue - {field_name} - 'Entity To Query' cell missing for column labelled '{field_name}', please provide entity name from the ResourceDefinitions tab.")
-
-        if entity_name not in [entry.entity_name for entry in resource_definition_entities]:
-            print(f"WARNING: - Reading Patient Data Issue - {field_name} - 'Entity To Query' cell has entity named '{entity_name}', however, the ResourceDefinition tab has no matching resource. Please provide a corresponding entry in the ResourceDefinition tab.")
-        # Create structure for this entity if not already present
-        if entity_name not in patient_data:
-            patient_data[entity_name] = {}
-            cohort_data.insert_entity(entity_name, EntityData({}))
-
-        # Add jsonpath, valuesets, and initialize an empty list for 'values'
-        if field_name not in patient_data[entity_name]:
-            field_data = {
-                "jsonpath": col[1],  # JsonPath from the second row
-                "valueType": col[2], # Value Type from the third row
-                "valuesets": col[3], # Value Set from the fourth row
-                "values": []         # Initialize empty list for actual values
-            }
-            patient_data[entity_name][field_name] = field_data
-            cohort_data.entities[entity_name].insert(field_name, FieldEntry(field_data))
-    
-    # Now process the rows starting from the 6th row (the actual data entries)
-    num_entries = 0
-    for row in sheet.iter_rows(min_row=7, values_only=True):  # Start from row 6 for actual data
-        if all(cell is None for cell in row):
-            continue
-        num_entries = num_entries + 1
-        entity_name = row[0]  # The entity name comes from the first column of each row
-        for i, value in enumerate(row[2:], start=1):  # Iterate through the values in the columns
-            entity_name = sheet.cell(row=1, column=i + 2).value
-            field_name = sheet.cell(row=6, column=i + 2).value  # Get the Data Element for this column
-            if entity_name in patient_data and field_name in patient_data[entity_name]:
-                # Append the actual data values to the 'values' array
-                cohort_data.entities[entity_name].fields[field_name].values.append(value)
-    cohort_data.num_entries = num_entries
-    return cohort_data
-
 # Function to process the "PatientData" sheet for the Revised CohortData
 def process_sheet_patient_data_revised(sheet, resource_definition_entities):
     headers = []
@@ -141,5 +93,7 @@ def process_sheet_patient_data_revised(sheet, resource_definition_entities):
             patients.extend([{}] * needed_count)
         for patient_dict, value in zip(patients, values):
             patient_dict[(entity_name, field_name)] = value
+    print(f"Headers\n----------{headers}")
+    print(f"Patients\n----------{patients}")
     cohort_data = CohortData(headers=headers, patients=patients)
     return cohort_data

{fhir_sheets-2.1.0 → fhir_sheets-2.1.3}/src/fhir_sheets/core/special_values.py

@@ -7,7 +7,7 @@ from abc import ABC, abstractmethod
 class AbstractCustomValueHandler(ABC):
     
     @abstractmethod
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         pass
     
 class PatientRaceExtensionValueHandler(AbstractCustomValueHandler):
@@ -67,7 +67,7 @@ class PatientRaceExtensionValueHandler(AbstractCustomValueHandler):
       "url" : "http://hl7.org/fhir/us/core/StructureDefinition/us-core-race"
     }
     #Create an ombcategory and detailed section of race extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the race extension if it exists; make it if it does not.
         if 'extension' not in final_struct:
             final_struct['extension'] = []
@@ -128,7 +128,7 @@ class PatientEthnicityExtensionValueHandler(AbstractCustomValueHandler):
       "url" : "http://hl7.org/fhir/us/core/StructureDefinition/us-core-ethnicity"
     }
     #Create an ombcategory and detailed section of ethnicitiy extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the ethncitiy extension if it exists; make it if it does not.
         if 'extension' not in final_struct:
             final_struct['extension'] = []
@@ -154,7 +154,7 @@ class PatientBirthSexExtensionValueHandler(AbstractCustomValueHandler):
       "valueCode" : "$value"
     }
     #Assigna birthsex extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the birthsex extension if it exists; make it if it does not.
         if 'extension' not in final_struct:
             final_struct['extension'] = []
@@ -182,7 +182,7 @@ class PatientMRNIdentifierValueHandler(AbstractCustomValueHandler):
       "value" : "$value"
     }
     #Assign a MRN identifier
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the MRN identifier if it exists; make it if it does not.
         target_identifier = self.patient_mrn_block
         new_identifier = True
@@ -215,7 +215,7 @@ class PatientSSNIdentifierValueHandler(AbstractCustomValueHandler):
       "value" : "$value"
     }
     #Assign a MRN identifier
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the MRN identifier if it exists; make it if it does not.
         target_identifier = self.patient_mrn_block
         new_identifier = True
@@ -238,7 +238,7 @@ class OrganizationIdentiferNPIValueHandler(AbstractCustomValueHandler):
       "value" : "$value"
     }
     #Assigna birthsex extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the birthsex extension if it exists; make it if it does not.
         if 'identifier' not in final_struct:
             final_struct['identifier'] = []
@@ -255,7 +255,7 @@ class OrganizationIdentiferCLIAValueHandler(AbstractCustomValueHandler):
       "value" : "$value"
     }
     #Assign a birthsex extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the birthsex extension if it exists; make it if it does not.
         if 'identifier' not in final_struct:
             final_struct['identifier'] = []
@@ -272,7 +272,7 @@ class PractitionerIdentiferNPIValueHandler(AbstractCustomValueHandler):
       "value" : "$value"
     }
     #Assigna birthsex extension
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Retrieve the birthsex extension if it exists; make it if it does not.
         if 'identifier' not in final_struct:
             final_struct['identifier'] = []
@@ -309,7 +309,7 @@ class ObservationComponentHandler(AbstractCustomValueHandler):
       }
     }
     #Find the appropriate component for the observaiton; then call build_structure again to continue the drill down
-    def assign_value(self, json_path, resource_definition, final_struct, key, value):
+    def assign_value(self, json_path, resource_definition, dataType, final_struct, key, value):
         #Check to make sure the component part exists
         if 'component' not in final_struct:
           final_struct['component'] = []
@@ -330,7 +330,8 @@ class ObservationComponentHandler(AbstractCustomValueHandler):
           if target_component is self.pulse_oximetry_oxygen_concentration:
             components.append(target_component)
         #Recurse back down into 
-        return conversion.build_structure(target_component, '.'.join(parts[2:]), resource_definition, parts[2:], value, parts[:2])
+        # current_struct: Dict, json_path: str, resource_definition: ResourceDefinition, dataType: str, parts: List[str], value: Any, previous_parts: List[str]
+        return conversion.build_structure(target_component, '.'.join(parts[2:]), resource_definition, dataType, parts[2:], value, parts[:2])
         pass
 
 def utilFindExtensionWithURL(extension_block, url):