Schemas stage - Schema Manager

Schema Name: sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned

created: 2024-08-03 01:01:56
disabled: False
format: raw
id: 2185
is_partitioned: False
is_schema_datatyped: True

name:

{
    "database": "sfdl_stage_postgres",
    "table": "keplernormies_private_insurance_fact_cleaned"
}

type: postgres

Schema Versions: 3

Version 868480

created: 2025-09-26 01:02:45

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_postgres`",
    "DROP TABLE IF EXISTS `sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`\n(\n `private_insurance_fact_id`  int , `provider`  string , `provider_id`  string , `date_dim_id`  int , `company_dim_id`  int , `facility_dim_id`  int , `tenant_dim_id`  int , `unit_dim_id`  int , `effective_on_date_dim_id`  int , `received_epoch`  bigint , `start_date`  date , `end_date`  date \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-26/1758866559'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned"
]

hive_path: s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-26/1758866559
id: 868480
processed: 1

raw_data:

{
    "company_dim_id": 4,
    "date_dim_id": 3,
    "effective_on_date_dim_id": 8,
    "end_date": 11,
    "facility_dim_id": 5,
    "private_insurance_fact_id": 0,
    "provider": 1,
    "provider_id": 2,
    "received_epoch": 9,
    "start_date": 10,
    "tenant_dim_id": 6,
    "unit_dim_id": 7
}

schema_attributes:

{
    "company_dim_id": "int",
    "date_dim_id": "int",
    "effective_on_date_dim_id": "int",
    "end_date": "date",
    "facility_dim_id": "int",
    "private_insurance_fact_id": "int",
    "provider": "string",
    "provider_id": "string",
    "received_epoch": "bigint",
    "start_date": "date",
    "tenant_dim_id": "int",
    "unit_dim_id": "int"
}

schema_name_id: 2185
schema_scan_id: 6326452
updated: 2025-09-26 01:02:56

Version 868249

created: 2025-09-25 01:00:44

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_postgres`",
    "DROP TABLE IF EXISTS `sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`\n(\n `private_insurance_fact_id`  int , `provider`  string , `provider_id`  string , `date_dim_id`  int , `company_dim_id`  int , `facility_dim_id`  int , `tenant_dim_id`  int , `unit_dim_id`  int , `effective_on_date_dim_id`  int , `received_epoch`  bigint , `start_date`  date , `end_date`  date \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-25/1758780012'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned"
]

hive_path: s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-25/1758780012
id: 868249
processed: 1

raw_data:

{
    "company_dim_id": 4,
    "date_dim_id": 3,
    "effective_on_date_dim_id": 8,
    "end_date": 11,
    "facility_dim_id": 5,
    "private_insurance_fact_id": 0,
    "provider": 1,
    "provider_id": 2,
    "received_epoch": 9,
    "start_date": 10,
    "tenant_dim_id": 6,
    "unit_dim_id": 7
}

schema_attributes:

{
    "company_dim_id": "int",
    "date_dim_id": "int",
    "effective_on_date_dim_id": "int",
    "end_date": "date",
    "facility_dim_id": "int",
    "private_insurance_fact_id": "int",
    "provider": "string",
    "provider_id": "string",
    "received_epoch": "bigint",
    "start_date": "date",
    "tenant_dim_id": "int",
    "unit_dim_id": "int"
}

schema_name_id: 2185
schema_scan_id: 6326016
updated: 2025-09-25 01:00:55

Version 868032

created: 2025-09-24 00:52:33

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_postgres`",
    "DROP TABLE IF EXISTS `sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`\n(\n `private_insurance_fact_id`  int , `provider`  string , `provider_id`  string , `date_dim_id`  int , `company_dim_id`  int , `facility_dim_id`  int , `tenant_dim_id`  int , `unit_dim_id`  int , `effective_on_date_dim_id`  int , `received_epoch`  bigint , `start_date`  date , `end_date`  date \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-24/1758693146'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned"
]

hive_path: s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-24/1758693146
id: 868032
processed: 1

raw_data:

{
    "company_dim_id": 4,
    "date_dim_id": 3,
    "effective_on_date_dim_id": 8,
    "end_date": 11,
    "facility_dim_id": 5,
    "private_insurance_fact_id": 0,
    "provider": 1,
    "provider_id": 2,
    "received_epoch": 9,
    "start_date": 10,
    "tenant_dim_id": 6,
    "unit_dim_id": 7
}

schema_attributes:

{
    "company_dim_id": "int",
    "date_dim_id": "int",
    "effective_on_date_dim_id": "int",
    "end_date": "date",
    "facility_dim_id": "int",
    "private_insurance_fact_id": "int",
    "provider": "string",
    "provider_id": "string",
    "received_epoch": "bigint",
    "start_date": "date",
    "tenant_dim_id": "int",
    "unit_dim_id": "int"
}

schema_name_id: 2185
schema_scan_id: 6325595
updated: 2025-09-24 00:52:47

Schema Scans: 3

Last at 2025-09-26 01:02:44

Scan 6326452

duration: 0:00:11.911744

exit_message:

{
    "ddl_changed": true,
    "partitions_applied": false,
    "success": true
}

id: 6326452

payload:

{
    "datatype_dict": {
        "company_dim_id": "int",
        "date_dim_id": "int",
        "effective_on_date_dim_id": "int",
        "end_date": "date",
        "facility_dim_id": "int",
        "private_insurance_fact_id": "int",
        "provider": "string",
        "provider_id": "string",
        "received_epoch": "bigint",
        "start_date": "date",
        "tenant_dim_id": "int",
        "unit_dim_id": "int"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-postgres-keplernormies-stage",
        "hive_path": "s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-26/1758866559",
        "key": "raw/private_insurance_fact_cleaned/2025-09-26/1758866559/data_0.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned",
        "type": "postgres"
    },
    "trace_context": {
        "parent_id": 5879314910746946883,
        "service_name": "kepler-normies",
        "span_id": 16288858608001013516,
        "trace_id": 5879314910746946883
    }
}

running: False
schema_name_id: 2185
start_time: 2025-09-26 01:02:44
success: True
trace_id: 5879314910746946883

Scan 6326016

duration: 0:00:12.065804

exit_message:

{
    "ddl_changed": true,
    "partitions_applied": false,
    "success": true
}

id: 6326016

payload:

{
    "datatype_dict": {
        "company_dim_id": "int",
        "date_dim_id": "int",
        "effective_on_date_dim_id": "int",
        "end_date": "date",
        "facility_dim_id": "int",
        "private_insurance_fact_id": "int",
        "provider": "string",
        "provider_id": "string",
        "received_epoch": "bigint",
        "start_date": "date",
        "tenant_dim_id": "int",
        "unit_dim_id": "int"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-postgres-keplernormies-stage",
        "hive_path": "s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-25/1758780012",
        "key": "raw/private_insurance_fact_cleaned/2025-09-25/1758780012/data_0.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned",
        "type": "postgres"
    },
    "trace_context": {
        "parent_id": 13578939338900065165,
        "service_name": "kepler-normies",
        "span_id": 423298320542744882,
        "trace_id": 13578939338900065165
    }
}

running: False
schema_name_id: 2185
start_time: 2025-09-25 01:00:43
success: True
trace_id: 13578939338900065165

Scan 6325595

duration: 0:00:14.515002

exit_message:

{
    "ddl_changed": true,
    "partitions_applied": false,
    "success": true
}

id: 6325595

payload:

{
    "datatype_dict": {
        "company_dim_id": "int",
        "date_dim_id": "int",
        "effective_on_date_dim_id": "int",
        "end_date": "date",
        "facility_dim_id": "int",
        "private_insurance_fact_id": "int",
        "provider": "string",
        "provider_id": "string",
        "received_epoch": "bigint",
        "start_date": "date",
        "tenant_dim_id": "int",
        "unit_dim_id": "int"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-postgres-keplernormies-stage",
        "hive_path": "s3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-24/1758693146",
        "key": "raw/private_insurance_fact_cleaned/2025-09-24/1758693146/data_0.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned",
        "type": "postgres"
    },
    "trace_context": {
        "parent_id": 3208005933154051546,
        "service_name": "kepler-normies",
        "span_id": 19689713913090313,
        "trace_id": 3208005933154051546
    }
}

running: False
schema_name_id: 2185
start_time: 2025-09-24 00:52:32
success: True
trace_id: 3208005933154051546

Partitions:

count: 0
ddl: None
name: None
state:
```
[]
```
type: None

Schema:

attributes:

{
    "company_dim_id": "int",
    "date_dim_id": "int",
    "effective_on_date_dim_id": "int",
    "end_date": "date",
    "facility_dim_id": "int",
    "private_insurance_fact_id": "int",
    "provider": "string",
    "provider_id": "string",
    "received_epoch": "bigint",
    "start_date": "date",
    "tenant_dim_id": "int",
    "unit_dim_id": "int"
}

created: 2025-09-26 01:02:45

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_postgres`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`\n(\n `private_insurance_fact_id`  int , `provider`  string , `provider_id`  string , `date_dim_id`  int , `company_dim_id`  int , `facility_dim_id`  int , `tenant_dim_id`  int , `unit_dim_id`  int , `effective_on_date_dim_id`  int , `received_epoch`  bigint , `start_date`  date , `end_date`  date \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-26/1758866559'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned"
}

Server:

hostname: schemamanager-5c55c886bf-h2ts4
name: schema_manager
process_start: 2025-10-21 13:03:27
sf_env: stage
version: 2112174301

Raw:

{
    "name": {
        "created": "2024-08-03 01:01:56",
        "disabled": false,
        "format": "raw",
        "id": 2185,
        "is_partitioned": false,
        "is_schema_datatyped": true,
        "name": {
            "database": "sfdl_stage_postgres",
            "table": "keplernormies_private_insurance_fact_cleaned"
        },
        "type": "postgres"
    },
    "partition": {
        "count": 0,
        "ddl": null,
        "name": null,
        "state": [],
        "type": null
    },
    "schema": {
        "attributes": {
            "company_dim_id": "int",
            "date_dim_id": "int",
            "effective_on_date_dim_id": "int",
            "end_date": "date",
            "facility_dim_id": "int",
            "private_insurance_fact_id": "int",
            "provider": "string",
            "provider_id": "string",
            "received_epoch": "bigint",
            "start_date": "date",
            "tenant_dim_id": "int",
            "unit_dim_id": "int"
        },
        "created": "2025-09-26 01:02:45",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_postgres`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`\n(\n `private_insurance_fact_id`  int , `provider`  string , `provider_id`  string , `date_dim_id`  int , `company_dim_id`  int , `facility_dim_id`  int , `tenant_dim_id`  int , `unit_dim_id`  int , `effective_on_date_dim_id`  int , `received_epoch`  bigint , `start_date`  date , `end_date`  date \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-postgres-keplernormies-stage/raw/private_insurance_fact_cleaned/2025-09-26/1758866559'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_postgres.keplernormies_private_insurance_fact_cleaned"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}

Schema Info