Schema Info

Schema Name: sfdl_stage_segment.ssdc_identify

created: 2017-11-02 10:55:25
disabled: False
format: raw
id: 291
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_stage_segment",
    "table": "ssdc_identify"
}

type: segment

Schema Versions: 3

Version 626436

created: 2023-11-21 05:00:49

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.ssdc_identify`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.ssdc_identify`\n(\n`original_key`STRING,`channel`STRING,`timestamp`STRING,`sentAt`STRING,`projectId`STRING,`type`STRING,`context`struct<`ip`:STRING,`locale`:STRING,`campaign`:struct<`content`:STRING,`source`:STRING,`medium`:STRING,`name`:STRING>,`timezone`:STRING,`userAgent`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`userAgentData`:struct<`platform`:STRING,`mobile`:STRING,`brands`:array>>,`page`:struct<`search`:STRING,`referrer`:STRING,`title`:STRING,`url`:STRING,`path`:STRING>>,`_metadata`struct<`bundled`:array,`unbundled`:array>,`_origin`STRING,`messageId`STRING,`receivedAt`STRING,`integrations`struct<`_empty_`:STRING>,`anonymousId`STRING,`originalTimestamp`STRING,`version`STRING,`traits`struct<`_empty_`:STRING>,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n WITH SERDEPROPERTIES ( 'mapping.ga_client_id' = 'GA Client ID' , 'mapping.GA_Client_ID' = 'GA Client ID' )\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-ssdc-stage/separated_dt/identify'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.ssdc_identify"
]

hive_path: s3://sfdl-segment-ssdc-stage/separated_dt/identify
id: 626436
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "bundledIds": [
            "whXwHySfze",
            "5ab2b2b670b7359f95e055fd"
        ],
        "unbundled": []
    },
    "_origin": "2023-11-21T11:00:34Z|s3://sfdl-segment-ssdc-stage/segment-logs/Mt3aW8s9vZ/1700524800000/1700564282199.events-archiver-480-24..ec729a53-f8b8-4b7b-be9d-1be543747e52.gz|analytics-segment-separator-stage:$LATEST",
    "anonymousId": "22a16c15-fb1f-45a2-92ea-aed3f0f23b3e",
    "channel": "client",
    "context": {
        "ip": "79.173.88.71",
        "library": {
            "name": "analytics.js",
            "version": "next-1.61.0"
        },
        "locale": "ru-RU",
        "page": {
            "path": "/self-storage/new-york/",
            "referrer": "",
            "search": "",
            "title": "The State of Self-Storage in New York: Self-Storage Industry Trends and Insights",
            "url": "https://www.selfstorage.extrameter.com/self-storage/new-york/"
        },
        "timezone": "Europe/Moscow",
        "userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0",
        "userAgentData": {
            "brands": [],
            "mobile": false,
            "platform": ""
        }
    },
    "integrations": {},
    "messageId": "ajs-next-aa6d1dd429cdb2c46b9f38c9451f6bc1",
    "originalTimestamp": "2023-11-21T10:57:51.484Z",
    "projectId": "Mt3aW8s9vZ",
    "receivedAt": "2023-11-21T10:57:50.304Z",
    "sentAt": "2023-11-21T10:57:51.537Z",
    "timestamp": "2023-11-21T10:57:50.251Z",
    "traits": {},
    "type": "identify",
    "userId": "2f5b94e05eafa05abb853b743a49b528",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.campaign.content": "string",
    "context.campaign.medium": "string",
    "context.campaign.name": "string",
    "context.campaign.source": "string",
    "context.ip": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "context.locale": "string",
    "context.page.path": "string",
    "context.page.referrer": "string",
    "context.page.search": "string",
    "context.page.title": "string",
    "context.page.url": "string",
    "context.timezone": "string",
    "context.userAgent": "string",
    "context.userAgentData.brands": [
        {
            "brand": "string",
            "version": "string"
        }
    ],
    "context.userAgentData.mobile": "string",
    "context.userAgentData.platform": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "original_key": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 291
schema_scan_id: 5325802
updated: 2023-11-21 05:07:40

Version 548188

created: 2023-06-09 09:25:16

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.ssdc_identify`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.ssdc_identify`\n(\n`channel`STRING,`receivedAt`STRING,`anonymousId`STRING,`_metadata`struct<`bundled`:array,`unbundled`:array>,`integrations`struct<`_empty_`:STRING>,`version`STRING,`type`STRING,`sentAt`STRING,`messageId`STRING,`userId`STRING,`_origin`STRING,`timestamp`STRING,`projectId`STRING,`context`struct<`userAgentData`:struct<`brands`:array>,`mobile`:STRING,`platform`:STRING>,`locale`:STRING,`userAgent`:STRING,`ip`:STRING,`campaign`:struct<`content`:STRING,`source`:STRING,`medium`:STRING,`name`:STRING>,`page`:struct<`referrer`:STRING,`path`:STRING,`title`:STRING,`search`:STRING,`url`:STRING>,`library`:struct<`name`:STRING,`version`:STRING>>,`originalTimestamp`STRING,`original_key`STRING,`traits`struct<`_empty_`:STRING>\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n WITH SERDEPROPERTIES ( 'mapping.ga_client_id' = 'GA Client ID' , 'mapping.GA_Client_ID' = 'GA Client ID' )\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-ssdc-stage/separated_dt/identify'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.ssdc_identify"
]

hive_path: s3://sfdl-segment-ssdc-stage/separated_dt/identify
id: 548188
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "bundledIds": [
            "whXwHySfze",
            "5ab2b2b670b7359f95e055fd"
        ],
        "unbundled": []
    },
    "_origin": "2023-06-09T14:25:14Z|s3://sfdl-segment-ssdc-stage/segment-logs/Mt3aW8s9vZ/1686268800000/1686320702758.events-archiver-480-45.8ebb200.61be79ce-af4d-4da0-918d-c35744f97d4d.gz|analytics-segment-separator-stage:$LATEST",
    "anonymousId": "f1a9c7e6-b337-4c80-955a-ad8525a8174d",
    "channel": "client",
    "context": {
        "campaign": {},
        "ip": "3.92.138.76",
        "library": {
            "name": "analytics.js",
            "version": "next-1.53.0"
        },
        "locale": "en-US",
        "page": {
            "path": "/",
            "referrer": "",
            "search": "?mgr=ssdr&SELENIUM=true&tsid=ABC",
            "title": "SelfStorage.com: Find Cheap Storage Units Near You",
            "url": "https://www.selfstorage.extrameter.com/?mgr=ssdr&SELENIUM=true&tsid=ABC"
        },
        "userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
        "userAgentData": {
            "brands": [
                {
                    "brand": "Not.A/Brand",
                    "version": "8"
                },
                {
                    "brand": "Chromium",
                    "version": "114"
                },
                {
                    "brand": "Google Chrome",
                    "version": "114"
                }
            ],
            "mobile": false,
            "platform": "Windows"
        }
    },
    "integrations": {},
    "messageId": "ajs-next-01a77739f163246bdee05953cbc806d0",
    "originalTimestamp": "2023-06-09T14:21:53.463Z",
    "projectId": "Mt3aW8s9vZ",
    "receivedAt": "2023-06-09T14:21:53.854Z",
    "sentAt": "2023-06-09T14:21:53.485Z",
    "timestamp": "2023-06-09T14:21:53.832Z",
    "traits": {},
    "type": "identify",
    "userId": "SELENIUM",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.campaign.content": "string",
    "context.campaign.medium": "string",
    "context.campaign.name": "string",
    "context.campaign.source": "string",
    "context.ip": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "context.locale": "string",
    "context.page.path": "string",
    "context.page.referrer": "string",
    "context.page.search": "string",
    "context.page.title": "string",
    "context.page.url": "string",
    "context.userAgent": "string",
    "context.userAgentData.brands": [
        {
            "brand": "string",
            "version": "string"
        }
    ],
    "context.userAgentData.mobile": "string",
    "context.userAgentData.platform": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "original_key": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 291
schema_scan_id: 4949375
updated: 2023-06-09 09:31:25

Version 245884

created: 2020-01-16 12:13:31

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.ssdc_identify`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.ssdc_identify`\n(\n`integrations`struct<`_empty_`:STRING>,`_metadata`struct<`bundled`:array,`unbundled`:array>,`originalTimestamp`STRING,`context`struct<`userAgent`:STRING,`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`referrer`:STRING,`path`:STRING,`search`:STRING,`url`:STRING,`title`:STRING>,`locale`:STRING,`campaign`:struct<`content`:STRING,`source`:STRING,`medium`:STRING,`name`:STRING>,`ip`:STRING>,`_origin`STRING,`original_key`STRING,`userId`STRING,`receivedAt`STRING,`version`STRING,`timestamp`STRING,`messageId`STRING,`traits`struct<`_empty_`:STRING>,`type`STRING,`anonymousId`STRING,`channel`STRING,`sentAt`STRING,`projectId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n WITH SERDEPROPERTIES ( 'mapping.ga_client_id' = 'GA Client ID' , 'mapping.GA_Client_ID' = 'GA Client ID' )\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-ssdc-stage/separated_dt/identify'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.ssdc_identify"
]

hive_path: s3://sfdl-segment-ssdc-stage/separated_dt/identify
id: 245884
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-01-16T18:09:57Z|s3://sfdl-segment-ssdc-stage/segment-logs/Mt3aW8s9vZ/1579132800000/1579198074776.83ac57d26ba8.e4797d0.a0f25895-78e9-4ab5-9188-58e97a7d8518.gz|segment_separator:37",
    "anonymousId": "2ecbdb42-2705-4a85-b0ac-a2a3bba1b817",
    "channel": "client",
    "context": {
        "campaign": {},
        "ip": "54.88.102.255",
        "library": {
            "name": "analytics.js",
            "version": "3.10.1"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/texas/austin/",
            "referrer": "",
            "search": "?facilityNotFound=true&location=austin%2C%20texas",
            "title": "SelfStorage.com: Find Cheap Storage Units Near You",
            "url": "https://www.selfstorage.extrameter.com/self-storage/texas/austin/?facilityNotFound=true&location=austin%2C%20texas"
        },
        "userAgent": "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3559.0 Mobile Safari/537.36"
    },
    "integrations": {},
    "messageId": "ajs-27cf4da3e9450ed0e8e45c26b897307e",
    "originalTimestamp": "2020-01-16T18:00:43.762Z",
    "projectId": "Mt3aW8s9vZ",
    "receivedAt": "2020-01-16T18:00:43.894Z",
    "sentAt": "2020-01-16T18:00:43.764Z",
    "timestamp": "2020-01-16T18:00:43.892Z",
    "traits": {},
    "type": "identify",
    "userId": "ac683cbb95079fb5ad3cb08435a3e5ae",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.campaign.content": "string",
    "context.campaign.medium": "string",
    "context.campaign.name": "string",
    "context.campaign.source": "string",
    "context.ip": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "context.locale": "string",
    "context.page.path": "string",
    "context.page.referrer": "string",
    "context.page.search": "string",
    "context.page.title": "string",
    "context.page.url": "string",
    "context.userAgent": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "original_key": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 291
schema_scan_id: 2522695
updated: 2020-01-16 12:29:27

Schema Scans: 3

Last at 2023-11-21 05:00:48

Scan 5325802

duration: 0:07:20.519123

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1301,
    "partitions_applied": false,
    "success": true
}

id: 5325802

payload:

{
    "datatype_dict": {
        "originalTimestamp": "timestamp_iso8601",
        "receivedAt": "timestamp_iso8601",
        "sentAt": "timestamp_iso8601",
        "timestamp": "timestamp_iso8601"
    },
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2023-11-21/",
        "name": "dt",
        "type": "string",
        "value": "2023-11-21"
    },
    "s3": {
        "bucket": "sfdl-segment-ssdc-stage",
        "hive_path": "s3://sfdl-segment-ssdc-stage/separated_dt/identify",
        "key": "separated_dt/identify/dt=2023-11-21/1700564282199.events-archiver-480-24..ec729a53-f8b8-4b7b-be9d-1be543747e52.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.ssdc_identify",
        "type": "segment"
    }
}

running: False
schema_name_id: 291
start_time: 2023-11-21 05:00:48
success: True
trace_id: 16763080550250480716

Scan 4949375

duration: 0:07:47.303926

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1226,
    "partitions_applied": false,
    "success": true
}

id: 4949375

payload:

{
    "datatype_dict": {
        "originalTimestamp": "timestamp_iso8601",
        "receivedAt": "timestamp_iso8601",
        "sentAt": "timestamp_iso8601",
        "timestamp": "timestamp_iso8601"
    },
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2023-06-09/",
        "name": "dt",
        "type": "string",
        "value": "2023-06-09"
    },
    "s3": {
        "bucket": "sfdl-segment-ssdc-stage",
        "hive_path": "s3://sfdl-segment-ssdc-stage/separated_dt/identify",
        "key": "separated_dt/identify/dt=2023-06-09/1686320702758.events-archiver-480-45.8ebb200.61be79ce-af4d-4da0-918d-c35744f97d4d.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.ssdc_identify",
        "type": "segment"
    }
}

running: False
schema_name_id: 291
start_time: 2023-06-09 09:25:15
success: True
trace_id: 13288173583838768140

Scan 2522695

duration: 0:07:06.292067

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 323,
    "partitions_applied": false,
    "success": true
}

id: 2522695

payload:

{
    "datatype_dict": {
        "originalTimestamp": "timestamp_iso8601",
        "receivedAt": "timestamp_iso8601",
        "sentAt": "timestamp_iso8601",
        "timestamp": "timestamp_iso8601"
    },
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2020-01-16/",
        "name": "dt",
        "type": "string",
        "value": "2020-01-16"
    },
    "s3": {
        "bucket": "sfdl-segment-ssdc-stage",
        "hive_path": "s3://sfdl-segment-ssdc-stage/separated_dt/identify",
        "key": "separated_dt/identify/dt=2020-01-16/1579198074776.83ac57d26ba8.e4797d0.a0f25895-78e9-4ab5-9188-58e97a7d8518.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.ssdc_identify",
        "type": "segment"
    }
}

running: False
schema_name_id: 291
start_time: 2020-01-16 12:13:31
success: True
trace_id: 4924961570644553333

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_segment.ssdc_identify`\nADD\n\n\n PARTITION (dt='2024-09-13') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-13/'\n PARTITION (dt='2024-09-16') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-16/'\n PARTITION (dt='2024-09-17') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-17/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 563389,
            "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-13/",
            "name": "dt",
            "value": "2024-09-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-09-13 10:54:15",
                "last_data": "2024-09-13 11:59:37"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 563742,
            "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-16/",
            "name": "dt",
            "value": "2024-09-16"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-09-15 22:51:47",
                "last_data": "2024-09-16 15:01:08"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 565958,
            "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-17/",
            "name": "dt",
            "value": "2024-09-17"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-09-17 10:31:02",
                "last_data": "2024-09-17 10:49:52"
            },
            "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.campaign.content": "string",
    "context.campaign.medium": "string",
    "context.campaign.name": "string",
    "context.campaign.source": "string",
    "context.ip": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "context.locale": "string",
    "context.page.path": "string",
    "context.page.referrer": "string",
    "context.page.search": "string",
    "context.page.title": "string",
    "context.page.url": "string",
    "context.timezone": "string",
    "context.userAgent": "string",
    "context.userAgentData.brands": [
        {
            "brand": "string",
            "version": "string"
        }
    ],
    "context.userAgentData.mobile": "string",
    "context.userAgentData.platform": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "original_key": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2023-11-21 05:00:49

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.ssdc_identify`\n(\n`original_key`STRING,`channel`STRING,`timestamp`STRING,`sentAt`STRING,`projectId`STRING,`type`STRING,`context`struct<`ip`:STRING,`locale`:STRING,`campaign`:struct<`content`:STRING,`source`:STRING,`medium`:STRING,`name`:STRING>,`timezone`:STRING,`userAgent`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`userAgentData`:struct<`platform`:STRING,`mobile`:STRING,`brands`:array>>,`page`:struct<`search`:STRING,`referrer`:STRING,`title`:STRING,`url`:STRING,`path`:STRING>>,`_metadata`struct<`bundled`:array,`unbundled`:array>,`_origin`STRING,`messageId`STRING,`receivedAt`STRING,`integrations`struct<`_empty_`:STRING>,`anonymousId`STRING,`originalTimestamp`STRING,`version`STRING,`traits`struct<`_empty_`:STRING>,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n WITH SERDEPROPERTIES ( 'mapping.ga_client_id' = 'GA Client ID' , 'mapping.GA_Client_ID' = 'GA Client ID' )\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-ssdc-stage/separated_dt/identify'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.ssdc_identify`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.ssdc_identify"
}

Server:

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

Raw:

{
    "name": {
        "created": "2017-11-02 10:55:25",
        "disabled": false,
        "format": "raw",
        "id": 291,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_segment",
            "table": "ssdc_identify"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_segment.ssdc_identify`\nADD\n\n\n PARTITION (dt='2024-09-13') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-13/'\n PARTITION (dt='2024-09-16') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-16/'\n PARTITION (dt='2024-09-17') location 's3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-17/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 563389,
                    "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-13/",
                    "name": "dt",
                    "value": "2024-09-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-09-13 10:54:15",
                        "last_data": "2024-09-13 11:59:37"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 563742,
                    "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-16/",
                    "name": "dt",
                    "value": "2024-09-16"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-09-15 22:51:47",
                        "last_data": "2024-09-16 15:01:08"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 565958,
                    "location": "s3://sfdl-segment-ssdc-stage/separated_dt/identify/dt=2024-09-17/",
                    "name": "dt",
                    "value": "2024-09-17"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-09-17 10:31:02",
                        "last_data": "2024-09-17 10:49:52"
                    },
                    "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.campaign.content": "string",
            "context.campaign.medium": "string",
            "context.campaign.name": "string",
            "context.campaign.source": "string",
            "context.ip": "string",
            "context.library.name": "string",
            "context.library.version": "string",
            "context.locale": "string",
            "context.page.path": "string",
            "context.page.referrer": "string",
            "context.page.search": "string",
            "context.page.title": "string",
            "context.page.url": "string",
            "context.timezone": "string",
            "context.userAgent": "string",
            "context.userAgentData.brands": [
                {
                    "brand": "string",
                    "version": "string"
                }
            ],
            "context.userAgentData.mobile": "string",
            "context.userAgentData.platform": "string",
            "messageId": "string",
            "originalTimestamp": "string",
            "original_key": "string",
            "projectId": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2023-11-21 05:00:49",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.ssdc_identify`\n(\n`original_key`STRING,`channel`STRING,`timestamp`STRING,`sentAt`STRING,`projectId`STRING,`type`STRING,`context`struct<`ip`:STRING,`locale`:STRING,`campaign`:struct<`content`:STRING,`source`:STRING,`medium`:STRING,`name`:STRING>,`timezone`:STRING,`userAgent`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`userAgentData`:struct<`platform`:STRING,`mobile`:STRING,`brands`:array>>,`page`:struct<`search`:STRING,`referrer`:STRING,`title`:STRING,`url`:STRING,`path`:STRING>>,`_metadata`struct<`bundled`:array,`unbundled`:array>,`_origin`STRING,`messageId`STRING,`receivedAt`STRING,`integrations`struct<`_empty_`:STRING>,`anonymousId`STRING,`originalTimestamp`STRING,`version`STRING,`traits`struct<`_empty_`:STRING>,`userId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n WITH SERDEPROPERTIES ( 'mapping.ga_client_id' = 'GA Client ID' , 'mapping.GA_Client_ID' = 'GA Client ID' )\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-segment-ssdc-stage/separated_dt/identify'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.ssdc_identify`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.ssdc_identify"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}