Schemas dev - Schema Manager

Schema Name: sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal

created: 2022-11-03 16:03:19
disabled: False
format: raw
id: 2105
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_dev_rds",
    "table": "sparefoot_sparefoot_visits_filtered_temporal"
}

type: rds

Schema Versions: 3

Version 4695749

created: 2023-04-21 15:02:48

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_rds`",
    "DROP TABLE IF EXISTS `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\n(\n `created`  timestamp , `dt_partition`  date , `is_good_visit`  smallint , `num_page_views`  int , `num_web_bookings`  int , `reasons`  string , `updated`  timestamp , `visit_id`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal'\n",
    "MSCK REPAIR TABLE sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal"
]

hive_path: s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal
id: 4695749
processed: 1

raw_data:

{
    "created": "timestamp[ns]",
    "dt_partition": "date32[day]",
    "is_good_visit": "int16",
    "num_page_views": "int32",
    "num_web_bookings": "int32",
    "reasons": "string",
    "updated": "timestamp[ns]",
    "visit_id": "string"
}

schema_attributes:

{
    "created": "timestamp",
    "dt_partition": "date",
    "is_good_visit": "smallint",
    "num_page_views": "int",
    "num_web_bookings": "int",
    "reasons": "string",
    "updated": "timestamp",
    "visit_id": "string"
}

schema_name_id: 2105
schema_scan_id: 6175075
updated: 2023-04-21 15:03:01

Version 4693971

created: 2023-04-20 14:58:33

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_rds`",
    "DROP TABLE IF EXISTS `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\n(\n `created`  timestamp , `dt_partition`  timestamp , `is_good_visit`  string , `num_page_views`  string , `num_web_bookings`  string , `reasons`  string , `updated`  timestamp , `visit_id`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal'\n",
    "MSCK REPAIR TABLE sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal"
]

hive_path: s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal
id: 4693971
processed: 1

raw_data:

{
    "created": "timestamp[ns]",
    "dt_partition": "timestamp[ns]",
    "is_good_visit": "string",
    "num_page_views": "string",
    "num_web_bookings": "string",
    "reasons": "string",
    "updated": "timestamp[ns]",
    "visit_id": "string"
}

schema_attributes:

{
    "created": "timestamp",
    "dt_partition": "timestamp",
    "is_good_visit": "string",
    "num_page_views": "string",
    "num_web_bookings": "string",
    "reasons": "string",
    "updated": "timestamp",
    "visit_id": "string"
}

schema_name_id: 2105
schema_scan_id: 6170368
updated: 2023-04-20 14:58:47

Version 4690317

created: 2022-11-03 16:03:19

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_rds`",
    "DROP TABLE IF EXISTS `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\n(\n `created`  timestamp , `dt_partition`  date , `is_good_visit`  smallint , `num_page_views`  int , `num_web_bookings`  int , `reasons`  string , `updated`  timestamp , `visit_id`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal'\n",
    "MSCK REPAIR TABLE sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal"
]

hive_path: s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal
id: 4690317
processed: 1

raw_data:

{
    "created": "timestamp[ns]",
    "dt_partition": "date32[day]",
    "is_good_visit": "int16",
    "num_page_views": "int32",
    "num_web_bookings": "int32",
    "reasons": "string",
    "updated": "timestamp[ns]",
    "visit_id": "string"
}

schema_attributes:

{
    "created": "timestamp",
    "dt_partition": "date",
    "is_good_visit": "smallint",
    "num_page_views": "int",
    "num_web_bookings": "int",
    "reasons": "string",
    "updated": "timestamp",
    "visit_id": "string"
}

schema_name_id: 2105
schema_scan_id: 5999489
updated: 2022-11-03 16:03:33

Schema Scans: 3

Last at 2023-04-21 15:02:47

Scan 6175075

duration: 0:00:17.190821

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 13,
    "partitions_applied": false,
    "success": true
}

id: 6175075

payload:

{
    "datatype_dict": null,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2023-04-20",
        "name": "dt",
        "type": "string",
        "value": "2023-04-20"
    },
    "s3": {
        "bucket": "sfdl-rds-sparefoot-dev",
        "hive_path": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal",
        "key": "raw_incremental/sparefoot_visits_filtered_temporal/dt=2023-04-20/visits_filtered_temporal_1.parquet.gz"
    },
    "schema": {
        "name": "sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal",
        "type": "rds"
    },
    "trace_context": {
        "parent_id": 14127988439747109905,
        "service_name": "sparefoot",
        "span_id": 1511585185019991599,
        "trace_id": 14127988439747109905
    }
}

running: False
schema_name_id: 2105
start_time: 2023-04-21 15:02:47
success: True
trace_id: 14127988439747109905

Scan 6170368

duration: 0:00:17.623375

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 12,
    "partitions_applied": false,
    "success": true
}

id: 6170368

payload:

{
    "datatype_dict": null,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2023-04-19",
        "name": "dt",
        "type": "string",
        "value": "2023-04-19"
    },
    "s3": {
        "bucket": "sfdl-rds-sparefoot-dev",
        "hive_path": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal",
        "key": "raw_incremental/sparefoot_visits_filtered_temporal/dt=2023-04-19/visits_filtered_temporal_1.parquet.gz"
    },
    "schema": {
        "name": "sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal",
        "type": "rds"
    },
    "trace_context": {
        "parent_id": 2184336583320815458,
        "service_name": "sparefoot",
        "span_id": 9536428259106015052,
        "trace_id": 2184336583320815458
    }
}

running: False
schema_name_id: 2105
start_time: 2023-04-20 14:58:33
success: True
trace_id: 2184336583320815458

Scan 5999489

duration: 0:00:19.696161

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1,
    "partitions_applied": false,
    "success": true
}

id: 5999489

payload:

{
    "datatype_dict": null,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2022-11-03",
        "name": "dt",
        "type": "string",
        "value": "2022-11-03"
    },
    "s3": {
        "bucket": "sfdl-rds-sparefoot-dev",
        "hive_path": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal",
        "key": "raw_incremental/sparefoot_visits_filtered_temporal/dt=2022-11-03/visits_filtered_temporal_1.parquet.gz"
    },
    "schema": {
        "name": "sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal",
        "type": "rds"
    },
    "trace_context": {
        "parent_id": 3847242464787555832,
        "service_name": "sparefoot",
        "span_id": 12868437840229473669,
        "trace_id": 3847242464787555832
    }
}

running: False
schema_name_id: 2105
start_time: 2022-11-03 16:03:19
success: True
trace_id: 3847242464787555832

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\nADD\n\n\n PARTITION (dt='2024-05-13') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-08-13/'\n PARTITION (dt='2025-07-02') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2025-07-02/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 253989,
            "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-05-13/",
            "name": "dt",
            "value": "2024-05-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-14 02:36:30",
                "last_data": "2024-05-14 02:36:30"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 259575,
            "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-08-13/",
            "name": "dt",
            "value": "2024-08-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-08-14 08:44:30",
                "last_data": "2024-08-14 08:44:30"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 297993,
            "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2025-07-02/",
            "name": "dt",
            "value": "2025-07-02"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-07-02 15:16:34",
                "last_data": "2025-07-02 15:16:34"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "created": "timestamp",
    "dt_partition": "date",
    "is_good_visit": "smallint",
    "num_page_views": "int",
    "num_web_bookings": "int",
    "reasons": "string",
    "updated": "timestamp",
    "visit_id": "string"
}

created: 2023-04-21 15:02:48

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_rds`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\n(\n `created`  timestamp , `dt_partition`  date , `is_good_visit`  smallint , `num_page_views`  int , `num_web_bookings`  int , `reasons`  string , `updated`  timestamp , `visit_id`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal"
}

Server:

hostname: schemamanager-5447774fc6-4w58v
name: schema_manager
process_start: 2026-04-02 21:43:44
sf_env: dev
version: 2427328685

Raw:

{
    "name": {
        "created": "2022-11-03 16:03:19",
        "disabled": false,
        "format": "raw",
        "id": 2105,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_rds",
            "table": "sparefoot_sparefoot_visits_filtered_temporal"
        },
        "type": "rds"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\nADD\n\n\n PARTITION (dt='2024-05-13') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-08-13/'\n PARTITION (dt='2025-07-02') location 's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2025-07-02/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 253989,
                    "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-05-13/",
                    "name": "dt",
                    "value": "2024-05-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-14 02:36:30",
                        "last_data": "2024-05-14 02:36:30"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 259575,
                    "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2024-08-13/",
                    "name": "dt",
                    "value": "2024-08-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-08-14 08:44:30",
                        "last_data": "2024-08-14 08:44:30"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 297993,
                    "location": "s3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal/dt=2025-07-02/",
                    "name": "dt",
                    "value": "2025-07-02"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-07-02 15:16:34",
                        "last_data": "2025-07-02 15:16:34"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "created": "timestamp",
            "dt_partition": "date",
            "is_good_visit": "smallint",
            "num_page_views": "int",
            "num_web_bookings": "int",
            "reasons": "string",
            "updated": "timestamp",
            "visit_id": "string"
        },
        "created": "2023-04-21 15:02:48",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_rds`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`\n(\n `created`  timestamp , `dt_partition`  date , `is_good_visit`  smallint , `num_page_views`  int , `num_web_bookings`  int , `reasons`  string , `updated`  timestamp , `visit_id`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-sparefoot-dev/raw_incremental/sparefoot_visits_filtered_temporal'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_rds.sparefoot_sparefoot_visits_filtered_temporal"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info