Schemas dev - Schema Manager

Schema Name: sfdl_dev_segment.sepoc_daily_analytics

created: 2020-12-16 23:23:14
disabled: False
format: raw
id: 1526
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_dev_segment",
    "table": "sepoc_daily_analytics"
}

type: segment

Schema Versions: 2

Version 4684277

created: 2020-12-18 15:16:04

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_daily_analytics`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_daily_analytics`\n(\n`anonymousId`STRING,`timestamp`STRING,`event`STRING,`_origin`STRING,`receivedAt`STRING,`channel`STRING,`version`STRING,`originalTimestamp`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`projectId`STRING,`messageId`STRING,`properties`struct<`units_occupied`:STRING,`units_insured`:STRING,`activities_move_ins`:STRING,`units_total`:STRING,`units_vacant`:STRING>,`sentAt`STRING,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics'\n",
    "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_daily_analytics"
]

hive_path: s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics
id: 4684277
processed: 1

raw_data:

{
    "_origin": "2020-12-18T21:15:33Z|s3://sfdl-segment-sepoc-dev/segment-logs/vErcW4u2PEpKLdcWg1WRoL/1608249600000/1608326116098.8bcaf413aec8.fde281a.7d0dee2d-31bf-4ec9-a3c8-1e8fa02d9cb1.gz|segment_separator:34",
    "anonymousId": null,
    "channel": "server",
    "context": {
        "library": {
            "name": "simple_segment",
            "version": "1.2.0"
        }
    },
    "event": "Daily Analytics",
    "integrations": {},
    "messageId": "api-1lqTDXNeqk17PZZBiYHZWpScV22",
    "originalTimestamp": "2020-12-18T14:31:41-06:00",
    "projectId": "vErcW4u2PEpKLdcWg1WRoL",
    "properties": {
        "activities_move_ins": 0,
        "units_insured": 0,
        "units_occupied": 150,
        "units_total": 156
    },
    "receivedAt": "2020-12-18T20:31:40.610Z",
    "sentAt": "2020-12-18T20:31:41.000Z",
    "timestamp": "2020-12-18T20:31:40.610Z",
    "type": "track",
    "userId": "8bf438b3-d99c-4a68-9b1b-e3f8dd49a4d5",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.activities_move_ins": "string",
    "properties.units_insured": "string",
    "properties.units_occupied": "string",
    "properties.units_total": "string",
    "properties.units_vacant": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 1526
schema_scan_id: 5737222
updated: 2020-12-18 15:16:18

Version 4684275

created: 2020-12-16 23:23:14

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_daily_analytics`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_daily_analytics`\n(\n`version`STRING,`timestamp`STRING,`projectId`STRING,`userId`STRING,`properties`struct<`units_vacant`:STRING,`units_occupied`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`originalTimestamp`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`messageId`STRING,`_origin`STRING,`type`STRING,`event`STRING,`channel`STRING,`sentAt`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics'\n",
    "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_daily_analytics"
]

hive_path: s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics
id: 4684275
processed: 1

raw_data:

{
    "_origin": "2020-12-17T05:22:58Z|s3://sfdl-segment-sepoc-dev/segment-logs/vErcW4u2PEpKLdcWg1WRoL/1608163200000/1608182128722.a9b5dd643d48.fde281a.a40b0922-09b3-42ee-8633-fcecb5e9096a.gz|segment_separator:34",
    "anonymousId": null,
    "channel": "server",
    "context": {
        "library": {
            "name": "simple_segment",
            "version": "1.2.0"
        }
    },
    "event": "Daily Analytics",
    "integrations": {},
    "messageId": "api-1llo3fQ6OTEFiIiSe2tbcTFypnE",
    "originalTimestamp": "2020-12-16T22:53:59-06:00",
    "projectId": "vErcW4u2PEpKLdcWg1WRoL",
    "properties": {
        "units_occupied": 10,
        "units_vacant": 2
    },
    "receivedAt": "2020-12-17T04:53:59.182Z",
    "sentAt": "2020-12-17T04:53:59.000Z",
    "timestamp": "2020-12-17T04:53:59.182Z",
    "type": "track",
    "userId": "facility-131",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.units_occupied": "string",
    "properties.units_vacant": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 1526
schema_scan_id: 5736831
updated: 2020-12-16 23:23:25

Schema Scans: 2

Last at 2020-12-18 15:16:04

Scan 5737222

duration: 0:00:17.199035

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 2,
    "partitions_applied": false,
    "success": true
}

id: 5737222

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-18/",
        "name": "dt",
        "type": "string",
        "value": "2020-12-18"
    },
    "s3": {
        "bucket": "sfdl-segment-sepoc-dev",
        "hive_path": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics",
        "key": "separated_dt/Daily Analytics/dt=2020-12-18/1608326116098.8bcaf413aec8.fde281a.7d0dee2d-31bf-4ec9-a3c8-1e8fa02d9cb1.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.sepoc_Daily_Analytics",
        "type": "segment"
    }
}

running: False
schema_name_id: 1526
start_time: 2020-12-18 15:16:04
success: True
trace_id: 17124626697539882860

Scan 5736831

duration: 0:00:14.579698

exit_message:

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

id: 5736831

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-17/",
        "name": "dt",
        "type": "string",
        "value": "2020-12-17"
    },
    "s3": {
        "bucket": "sfdl-segment-sepoc-dev",
        "hive_path": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics",
        "key": "separated_dt/Daily Analytics/dt=2020-12-17/1608182128722.a9b5dd643d48.fde281a.a40b0922-09b3-42ee-8633-fcecb5e9096a.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.sepoc_Daily_Analytics",
        "type": "segment"
    }
}

running: False
schema_name_id: 1526
start_time: 2020-12-16 23:23:14
success: True
trace_id: 11040579682419394853

Partitions:

count: 2

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_segment.sepoc_daily_analytics`\nADD\n\n\n PARTITION (dt='2020-12-17') location 's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-17/'\n PARTITION (dt='2020-12-18') location 's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-18/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 163271,
            "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-17/",
            "name": "dt",
            "value": "2020-12-17"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-12-16 23:23:14",
                "last_data": "2020-12-16 23:23:14"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 163350,
            "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-18/",
            "name": "dt",
            "value": "2020-12-18"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-12-18 15:16:04",
                "last_data": "2020-12-18 15:29:07"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.activities_move_ins": "string",
    "properties.units_insured": "string",
    "properties.units_occupied": "string",
    "properties.units_total": "string",
    "properties.units_vacant": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2020-12-18 15:16:04

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_daily_analytics`\n(\n`anonymousId`STRING,`timestamp`STRING,`event`STRING,`_origin`STRING,`receivedAt`STRING,`channel`STRING,`version`STRING,`originalTimestamp`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`projectId`STRING,`messageId`STRING,`properties`struct<`units_occupied`:STRING,`units_insured`:STRING,`activities_move_ins`:STRING,`units_total`:STRING,`units_vacant`:STRING>,`sentAt`STRING,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_daily_analytics`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_daily_analytics"
}

Server:

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

Raw:

{
    "name": {
        "created": "2020-12-16 23:23:14",
        "disabled": false,
        "format": "raw",
        "id": 1526,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_segment",
            "table": "sepoc_daily_analytics"
        },
        "type": "segment"
    },
    "partition": {
        "count": 2,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_segment.sepoc_daily_analytics`\nADD\n\n\n PARTITION (dt='2020-12-17') location 's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-17/'\n PARTITION (dt='2020-12-18') location 's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-18/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 163271,
                    "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-17/",
                    "name": "dt",
                    "value": "2020-12-17"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-12-16 23:23:14",
                        "last_data": "2020-12-16 23:23:14"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 163350,
                    "location": "s3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics/dt=2020-12-18/",
                    "name": "dt",
                    "value": "2020-12-18"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-12-18 15:16:04",
                        "last_data": "2020-12-18 15:29:07"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "anonymousId": "string",
            "channel": "string",
            "context.library.name": "string",
            "context.library.version": "string",
            "event": "string",
            "messageId": "string",
            "originalTimestamp": "string",
            "projectId": "string",
            "properties.activities_move_ins": "string",
            "properties.units_insured": "string",
            "properties.units_occupied": "string",
            "properties.units_total": "string",
            "properties.units_vacant": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2020-12-18 15:16:04",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_daily_analytics`\n(\n`anonymousId`STRING,`timestamp`STRING,`event`STRING,`_origin`STRING,`receivedAt`STRING,`channel`STRING,`version`STRING,`originalTimestamp`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`projectId`STRING,`messageId`STRING,`properties`struct<`units_occupied`:STRING,`units_insured`:STRING,`activities_move_ins`:STRING,`units_total`:STRING,`units_vacant`:STRING>,`sentAt`STRING,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-sepoc-dev/separated_dt/Daily Analytics'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_daily_analytics`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_daily_analytics"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info