Normalize Unicode characters to ASCII characters

#   _____           _              _____        __      
#  |  __ \         (_)            |_   _|      / _|     
#  | |__) |___  ___ _ _ __   ___    | |  _ __ | |_ ___  
#  |  _  // _ \/ __| | '_ \ / _ \   | | | '_ \|  _/ _ \ 
#  | | \ \  __/ (__| | |_) |  __/  _| |_| | | | || (_) |
#  |_|  \_\___|\___|_| .__/ \___| |_____|_| |_|_| \___/ 
#                    | |                                
#                    |_|

# Project Name - NORMALIZE UNICODE CHARACTERS TO ASCII CHARACTERS

# Recipe URL - https://app.lingk.io/a/10932/tf/17884

# Description - # This recipe converts demonstrates normalizing Unicode text to ASCII values for systems that do not support Unicode characters.
                # To use this recipe, click Run!

# Industry - Higher Ed
# Business Process - Graduate Reporting

# Systems - 
# Connectors - JSON
# Data Flows - Single Direction
# Connection Type - JSON

# Add Recipe notes / Change log information here!

#    _____                            _                 
#   / ____|                          | |                
#  | |     ___  _ __  _ __   ___  ___| |_ ___  _ __ ___ 
#  | |    / _ \| '_ \| '_ \ / _ \/ __| __/ _ \| '__/ __|
#  | |___| (_) | | | | | | |  __/ (__| || (_) | |  \__ \
#   \_____\___/|_| |_|_| |_|\___|\___|\__\___/|_|  |___/
#

# CONNECTORS specify what data will be pulled into the in-memory database during processing

connectors:

# JSON Setup - https://help.lingk.io/en/articles/74-json-connector-reference

###### Start: JSON Connectors #######
-
    name: sourceLeadData
    type: json
    properties:
      jsonObject: >
       [
         { "leadId": "1", "firstName": "Jühn", "lastName": "Thomas", "leadScore": 88 },
         { "leadId": "2", "firstName": "Ȃnne", "lastName": "Jacobs", "leadScore": 32 },
         { "leadId": "3", "firstName": "orčpžsíáýd", "lastName": "Jacobs", "leadScore": 32 }
       ]

###### End: JSON Connectors #######

#    _____ _        _                            _       
#   / ____| |      | |                          | |      
#  | (___ | |_ __ _| |_ ___ _ __ ___   ___ _ __ | |_ ___ 
#   \___ \| __/ _` | __/ _ \ '_ ` _ \ / _ \ '_ \| __/ __|
#   ____) | || (_| | ||  __/ | | | | |  __/ | | | |_\__ \
#  |_____/ \__\__,_|\__\___|_| |_| |_|\___|_| |_|\__|___/

# STATEMENTS specify how the data should be processed while in memory

statements:

#******************************************************************** D I S C L A I M E R ***********************************************************************************************
#                                                                                                                                                                                       * 
# Note that in an effort to keep recipes optimized for DPH (Data Processing Hours), print statements should be commented out after development has concluded for a recipe.              *
# For more information on DPH optimization, please visit the following help article - https://help.lingk.io/en/articles/212-minimizing-data-processing-hours-on-the-lingk-platform      *
#                                                                                                                                                                                       * 
#******************************************************************** D I S C L A I M E R ***********************************************************************************************

#- statement: print sourceLeadData

# Normalization is the process to eliminate data redundancy and enhance data integrity in the table.
  # It is a multi-step process that sets the data into tabular form and removes the duplicated data from the relational tables. 
  - statement: |
      (transformedData) => select 
              leadId           lead_id, 
              normalize(firstName, "NFD") first_name_nfd,
              normalize(firstName, "NFC") first_name_nfc,
              normalize(firstName, "NFKC") first_name_NFKC,
              normalize(firstName, "NFKD") first_name_NFKD,
              lastName         last_name,
              leadScore        lead_score
            from sourceLeadData
  #- statement: print transformedData

# Add more statements to convert, join, aggregrate, transform, and integrate your data