Dev: Added requirements.txt, Dockerfile and enabled data type insertion based on columns or rows.

.env

+MODULE_NAME=form-management
+MONGO_URI=mongodb://192.168.0.220:2717/
+METADATA_DB=ilens_configuration
+ILENS_ASSISTANT=ilens_assistant
+ILENS_ASSET_MODEL_DB=ilens_asset_model
+ASSISTANT_URI=postgresql://postgres:postgres@192.168.0.220:5432/ilens_assistant
+FORM_DE=http://192.168.0.220/formde/
+METADATA_SERVICES=http://192.168.0.220/ilens_api/
+KAIROS_URI=http://192.168.0.220:8080/
+BASE_PATH=opt/services/ilens2.0/volumes
+MOUNT_DIR=/form-management
+REDIS_HOST=192.168.0.220
+REDIS_PORT=6379
+KAFKA_HOST=192.168.0.220
+KAFKA_PORT=9092
+KAFKA_TOPIC=ilens_dev
+KAFKA_AUDIT_TOPIC=audit_logs
+MAINTENANCE_URI = postgresql://postgres:postgres@192.168.0.220:5432/maintenance_logbook
+FORM_MT = http://192.168.0.220/form-mt/
+PERIODIC_ENTRY_AUDITING=true
+FORM_NON_PERIODIC_AUDITING=true
+FORM_PERIODIC_AUDITING=true
+ENABLE_KAFKA_PARTITION=true
+ROUND_ROBIN_PARTITION=true
+INTERVAL=60
+EMAIL_SERVICE_PROXY=https://cloud.ilens.io/sms-util
+MQTT_URL=192.168.0.220
+MQTT_PORT=1883
+FILES_MAPPING={"Quality Report_AC2O.xlsx":{"Pure Tank":"A4:E7"}}
+COLUMN_BASED_SHEETS={"Quality Report_AC2O.xlsx":["Sheet1"]}
+TEMPLATE_PATH=data/templates
+DATA_PATH=C:/Users/harshavardhan.c/Downloads
\ No newline at end of file

Dockerfile

+FROM tiangolo/uvicorn-gunicorn-fastapi:python3.8-slim
+COPY . /app
+RUN pip install -r requirements.txt

requirements.txt

+pymongo~=3.11.3
+requests==2.24.0
+cryptography>=3.3.1
+PyJWT==2.0.1
+#python_bcrypt==0.3.2
+redis~=3.5.3
+Werkzeug>=2.0
+pandas~=1.2.3
+paho-mqtt==1.5.0
+python-dotenv==0.17.1
+pydantic~=1.7.3
+pydantic[dotenv]
+pyjwt[crypto]
+pycryptodome~=3.10.1
+python-multipart
+pendulum~=2.1.2
+iteration-utilities==0.11.0
+xlsxwriter==1.3.7
+uvicorn~=0.13.4
+pytz~=2021.1
+setuptools~=54.1.1
+configparser~=5.0.1
+aiofiles~=0.6.0
+fastapi~=0.63.0
+starlette~=0.13.6
+kafka-python
+ilens_kafka_publisher
+geopy==2.2.0
+shortuuid==1.0.8
+python-dateutil==2.8.1
+openpyxl==3.0.7
+Jinja2==2.11.3
+PyYAML==6.0
\ No newline at end of file

scripts/core/handlers/__init__.py

+import json
 import os.path
 import sys
 from datetime import datetime
@@ -14,9 +15,14 @@ enable_timestamp = os.environ.get("CURRENT_TIMESTAMP", default="true")
 code_timezone = os.environ.get("TIMEZONE", default="Asia/Kolkata")
 project_id = os.environ.get("PROJECT_ID", default="project_099")
 files_mapping = os.environ.get("FILES_MAPPING", default="")
+columns_based_sheets = os.environ.get("COLUMN_BASED_SHEETS", default={})
 if not files_mapping:
     print("Files Mapping Found empty, existing!!")
     sys.exit(0)
+if not columns_based_sheets:
+    print("Files Mapping Found empty, existing!!")
+    sys.exit(0)
+columns_based_sheets = json.loads(columns_based_sheets)
 
 
 class ExcelUploadHandler:
@@ -27,7 +33,7 @@ class ExcelUploadHandler:
         self.project_id = project_id
         self.kafka_conn = DataPush()
 
-    def parse_excel_data(self, template_file_path, data_file_path, template_fill_range,
+    def parse_excel_data(self, template_file_path, data_file_path, template_fill_range, file_name,
                          sheet_name="Sheet1"):
         try:
             if not os.path.join(template_file_path):
@@ -41,8 +47,7 @@ class ExcelUploadHandler:
             data_parameters = self.get_file_object_data(file=data_file_path, fill_range=template_fill_range,
                                                         sheet_name=sheet_name)
             self.execute_data_insertion(template_parameters=template_parameters, data_parameters=data_parameters,
-                                        fill_range=template_fill_range)
-            print(data_parameters)
+                                        fill_range=template_fill_range, file_name=file_name, sheet_name=sheet_name)
 
         except Exception as e:
             logger.exception(f"Exception occurred while parsing the excel data {e.args}")
@@ -69,7 +74,8 @@ class ExcelUploadHandler:
             logger.error(e.args)
             raise
 
-    def execute_data_insertion(self, template_parameters: dict, data_parameters: dict, fill_range):
+    def execute_data_insertion(self, template_parameters: dict, data_parameters: dict, fill_range, sheet_name: str,
+                               file_name: str):
         try:
             __start_coords__, __end_coords__ = self.excel.get_row_column(fill_range)
             start_row, start_column = __start_coords__
@@ -82,31 +88,32 @@ class ExcelUploadHandler:
                            'retain_flag': True, 'msg_id': 1, "p_id": ""}
             key_mapping_json = dict(zip(template_parameters.values(), template_parameters.keys()))
             date_keys = [item for item in list(key_mapping_json.keys()) if item and item.startswith("date")]
-            for _row in rows_range:
-                res = [item for item in list(template_parameters.keys()) if item.endswith(_row)]
-                _dict = {template_parameters[_element]: data_parameters[_element] for _element in res if
-                         template_parameters.get(_element) and data_parameters.get(
-                             _element) and (
-                                 "$" in template_parameters.get(_element) or "date" in template_parameters.get(
-                             _element))}
-                insert_data = self.prepare_data_processor_json(input_json=_dict, data_parameters=data_parameters,
-                                                               key_mapping_json=key_mapping_json,
-                                                               date_keys=date_keys, insert_data=insert_data)
-            for _column in columns_range:
-                res = [item for item in list(template_parameters.keys()) if item.startswith(_column)]
-                _dict = {template_parameters[_element]: data_parameters[_element] for _element in res if
-                         template_parameters.get(_element) and data_parameters.get(_element) and
-                         ("$" in template_parameters.get(_element) or "date" in template_parameters.get(_element))}
-                insert_data = self.prepare_data_processor_json(input_json=_dict, data_parameters=data_parameters,
-                                                               key_mapping_json=key_mapping_json,
-                                                               date_keys=date_keys, insert_data=insert_data)
+            if sheet_name not in columns_based_sheets.get(file_name):
+                for _row in rows_range:
+                    res = [item for item in list(template_parameters.keys()) if item.endswith(_row)]
+                    _dict = {template_parameters[_element]: data_parameters[_element] for _element in res if
+                             template_parameters.get(_element) and data_parameters.get(
+                                 _element) and (
+                                     "$" in template_parameters.get(_element) or "date" in template_parameters.get(
+                                 _element))}
+                    insert_data = self.prepare_data_processor_json(input_json=_dict, data_parameters=data_parameters,
+                                                                   key_mapping_json=key_mapping_json,
+                                                                   date_keys=date_keys, insert_data=insert_data)
+            else:
+                for _column in columns_range:
+                    res = [item for item in list(template_parameters.keys()) if item.startswith(_column)]
+                    _dict = {template_parameters[_element]: data_parameters[_element] for _element in res if
+                             template_parameters.get(_element) and data_parameters.get(_element) and
+                             ("$" in template_parameters.get(_element) or "date" in template_parameters.get(_element))}
+                    insert_data = self.prepare_data_processor_json(input_json=_dict, data_parameters=data_parameters,
+                                                                   key_mapping_json=key_mapping_json,
+                                                                   date_keys=date_keys, insert_data=insert_data)
             msg_counter = 1
             for k, v in insert_data.items():
                 timestamp = int(k)
                 insert_json.update({
                     "data": v, "p_id": project_id, "msg_id": msg_counter, "timestamp": timestamp
                 })
-                msg_counter += 1
                 logger.debug(f"Timestamp: {timestamp}, Values: {insert_data}")
                 self.kafka_conn.publish_message(msg=insert_json)
                 msg_counter += 1
@@ -130,7 +137,8 @@ class ExcelUploadHandler:
                                     insert_data: dict):
         try:
             date_key = [item for item in list(input_json.keys()) if item and item.startswith("date")]
-            timestamp_value = self.convert_date_string_to_timestamp(input_data=date_key)
+            date_key = date_key[0] if date_key else ""
+            timestamp_value = self.convert_date_string_to_timestamp(input_data=input_json[date_key]) if date_key else ''
             if not timestamp_value and date_keys:
                 timestamp_value = data_parameters[key_mapping_json[data_parameters[0]]]
                 timestamp_value = self.convert_date_string_to_timestamp(input_data=timestamp_value)
@@ -140,6 +148,8 @@ class ExcelUploadHandler:
             timestamp_str = str(timestamp_value)
             if timestamp_value not in insert_data:
                 insert_data[timestamp_str] = {}
+            if date_key:
+                input_json.pop(date_key, None)
             insert_data[timestamp_str].update(input_json)
         except Exception as e:
             logger.exception(f"Exception occurred while json creation {e.args}")