kraken convert

Overview

Converts records using a mapping record

github

https://github.com/tactik8/krakenconvert2

pypi

methods:

• convert: converts records

How to use:

Basics

input_records = [
        {
        "record_id": "1234",
        "firstName": "firstName1",
        "lastName": "lastName1",
        "email": "test1@test.com"
        }
    ]

    mapping_record = {
        "@type": "'test'",
        "@id": "'/system/table/' + str(r.record_id)",
        "givenName": "r.firstName",
        "familyName": "r.lastName",
        "email": "r.email"
    }

    results = convert(input_records, map)
    print(results)

Structure of record

mapping_record = {
    "@type": "dataset",
    "name": "NAME OF THE DATASER",
    "distribution": {
        "@type": "DataDownload",
        "contentUrl": "URL WHERE TO DOWNLOAD DATASET",
        "encodingFormat": "text/tab-separated-values"
      },
    "variableMeasured": EXAMPLE OF RECORD (NOT USED, SIMPLY FOR REFERENCE),
    "potentialAction": [

        LIST OF ACTIONS
        EACH REPLACEACTION REPLACE A GIVEN VALUE
        - * MEANS EVERY PROPERTYID
        
        EACH CREATEACTION CREATES A BRAND NEW RECORD
        - R.NAME REFERS TO THE NAME PROPERTY OF THE RECORD
        
        {
            "@type": "replaceAction",
            "replacee": {
                "@type": "propertyValue",
                "propertyID": "*",
                "value": ".."
            },
            "replacer": {
                "@type": "propertyValue",
                "propertyID": "*",
                "value": "NoneValue"
            }
        },
        {
            "@type": "replaceAction",
            "replacee": {
                "@type": "propertyValue",
                "propertyID": "derived_NAICS",
                "value": "44"
            },
            "replacer": {
                "@type": "propertyValue",
                "propertyID": "derived_NAICS",
                "value": "22"
            }
        },
        {
            "@type": "createAction",
            "instrument": {
                "@type": "'organization'",
                "name": "r.business_name",
                "legalName": "r.business_name",
                "naics": [
                    "r.derived_NAICS", 
                    "r.source_NAICS_primary",
                    "r.source_NAICS_secondary"
                ],
                "numberOfEmployees": "r.get('total_no_employees', None)",
                "brand": "r.alt_business_name",
                "description":  "r.get('business_description', None)",
                "taxID": "r.get('business_id_no', None)",
                "location": {
                    "@type": "'place'",
                    "latitude": "r.latitude",
                    "longitude": "r.longitude",
                    "address": {
                        "@type": "'PostalAddress'",
                        "streetAddress": "(r.unit + ', ' + r.street_no + ' ' +  r.street_name) if r.unit else (r.street_no + ' ' +  r.street_name)",
                        "addressLocality": "r.city",
                        "addressRegion":  "r.prov_terr",
                        "postalCode": "r.postal_code",
                        "addressCountry": "'CA'"
                    }
                }
            }
        }
    ],
}

Example of record

mapping_record = {
    "@type": "dataset",
    "name": "company directory records from GoC opendata",
    "distribution": {
        "@type": "DataDownload",
        "contentUrl": "https://www150.statcan.gc.ca/n1/pub/21-26-0003/212600032023001-eng.htm",
        "encodingFormat": "text/tab-separated-values"
      },
    "variableMeasured": {
        "idx": "87cfdddd858f54356f04", 
        "business_name": "Innomar Pharmacy Inc.", 
        "alt_business_name": "..", 
        "business_sector": "Community Pharmacy", 
        "business_subsector": "..", 
        "business_description": "..", 
        "business_id_no": "..", 
        "licence_number": "..", 
        "licence_type": "..", 
        "derived_NAICS": "44", 
        "source_NAICS_primary": "..", 
        "source_NAICS_secondary": "..", 
        "NAICS_descr": "..", 
        "NAICS_descr2": "..", 
        "latitude": "46.10593", 
        "longitude": "-64.80623", 
        "full_address": "100 Arden Street, Suite 309, Moncton Nb", 
        "postal_code": "..", 
        "unit": "..", 
        "street_no": "100", 
        "street_name": "Arden Street", 
        "street_direction": "..", 
        "street_type": "..", 
        "city": "Moncton", 
        "prov_terr": "NB", 
        "total_no_employees": "..", 
        "status": "..", 
        "provider": "City of Moncton", 
        "geo_source": "Source", 
        "CSDUID": "1307022", 
        "CSDNAME": "Moncton", 
        "PRUID": "13"
    },
    "potentialAction": [
        {
            "@type": "replaceAction",
            "replacee": {
                "@type": "propertyValue",
                "propertyID": "*",
                "value": ".."
            },
            "replacer": {
                "@type": "propertyValue",
                "propertyID": "*",
                "value": "NoneValue"
            }
        },
        {
            "@type": "replaceAction",
            "replacee": {
                "@type": "propertyValue",
                "propertyID": "derived_NAICS",
                "value": "44"
            },
            "replacer": {
                "@type": "propertyValue",
                "propertyID": "derived_NAICS",
                "value": "22"
            }
        },
        {
            "@type": "createAction",
            "instrument": {
                "@type": "'organization'",
                "name": "r.business_name",
                "legalName": "r.business_name",
                "naics": [
                    "r.derived_NAICS", 
                    "r.source_NAICS_primary",
                    "r.source_NAICS_secondary"
                ],
                "numberOfEmployees": "r.get('total_no_employees', None)",
                "brand": "r.alt_business_name",
                "description":  "r.get('business_description', None)",
                "taxID": "r.get('business_id_no', None)",
                "location": {
                    "@type": "'place'",
                    "latitude": "r.latitude",
                    "longitude": "r.longitude",
                    "address": {
                        "@type": "'PostalAddress'",
                        "streetAddress": "(r.unit + ', ' + r.street_no + ' ' +  r.street_name) if r.unit else (r.street_no + ' ' +  r.street_name)",
                        "addressLocality": "r.city",
                        "addressRegion":  "r.prov_terr",
                        "postalCode": "r.postal_code",
                        "addressCountry": "'CA'"
                    }
                }
            }
        }
    ],
    "url": "https://www150.statcan.gc.ca/n1/pub/21-26-0003/212600032023001-eng.htm"
}