Schema Info

Schema Name: sfdl_stage_segment.storagedc_identify

created: 2023-11-08 12:25:50
disabled: False
format: raw
id: 2083
is_partitioned: True
is_schema_datatyped: False

name:

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

type: segment

Schema Versions: 2

Version 646701

created: 2024-01-09 11:22:50

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.storagedc_identify`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagedc_identify`\n(\n`version`STRING,`type`STRING,`anonymousId`STRING,`originalTimestamp`STRING,`sentAt`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`timezone`:STRING,`locale`:STRING,`userAgent`:STRING,`ip`:STRING,`userAgentData`:struct<`brands`:array>,`platform`:STRING,`mobile`:STRING>,`page`:struct<`search`:STRING,`url`:STRING,`referrer`:STRING,`title`:STRING,`path`:STRING>>,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`_origin`STRING,`channel`STRING,`messageId`STRING,`timestamp`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-storagedc-stage/separated_dt/identify'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.storagedc_identify"
]

hive_path: s3://sfdl-segment-storagedc-stage/separated_dt/identify
id: 646701
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Tag Manager",
            "Segment.io"
        ],
        "bundledIds": [
            "6202b8b2c9768867dfc663bd"
        ],
        "unbundled": []
    },
    "_origin": "2024-01-09T17:22:44Z|s3://sfdl-segment-storagedc-stage/segment-logs/dxi6iTNi7ct2csUdYniZc9/1704758400000/1704820920367.events-archiver-480-58..0e470018-4e11-4351-aae5-d86318f2cc5e.gz|analytics-segment-separator-stage:$LATEST",
    "anonymousId": "6c8a0126-bcfd-487a-a4af-c364771d972d",
    "channel": "client",
    "context": {
        "ip": "54.175.218.140",
        "library": {
            "name": "analytics.js",
            "version": "next-1.62.0"
        },
        "locale": "en-US",
        "page": {
            "path": "/",
            "referrer": "",
            "search": "",
            "title": "Find & Rent Self Storage Units Near You - Storage.com",
            "url": "https://www.storage.extrameter.com/"
        },
        "timezone": "America/Mexico_City",
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
        "userAgentData": {
            "brands": [
                {
                    "brand": "Not_A Brand",
                    "version": "8"
                },
                {
                    "brand": "Chromium",
                    "version": "120"
                },
                {
                    "brand": "Google Chrome",
                    "version": "120"
                }
            ],
            "mobile": false,
            "platform": "macOS"
        }
    },
    "integrations": {},
    "messageId": "ajs-next-b758187c071e114060e06f49e1e7c834",
    "originalTimestamp": "2024-01-09T16:58:00.477Z",
    "projectId": "dxi6iTNi7ct2csUdYniZc9",
    "receivedAt": "2024-01-09T16:58:01.000Z",
    "sentAt": "2024-01-09T16:58:00.487Z",
    "timestamp": "2024-01-09T16:58:00.990Z",
    "traits": {},
    "type": "identify",
    "userId": "5f2a76a257d3770e35e45246ac1bd569",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "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",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 2083
schema_scan_id: 5415666
updated: 2024-01-09 11:23:04

Version 621563

created: 2023-11-08 12:25:51

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.storagedc_identify`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagedc_identify`\n(\n`anonymousId`STRING,`channel`STRING,`context`struct<`ip`:STRING,`library`:struct<`name`:STRING,`version`:STRING>,`locale`:STRING,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`userAgentData`:struct<`brands`:array>,`mobile`:STRING,`platform`:STRING>>,`messageId`STRING,`originalTimestamp`STRING,`projectId`STRING,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`version`STRING,`_origin`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-storagedc-stage/separated_dt/identify'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.storagedc_identify"
]

hive_path: s3://sfdl-segment-storagedc-stage/separated_dt/identify
id: 621563
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Tag Manager",
            "Segment.io"
        ],
        "bundledIds": [
            "6202b8b2c9768867dfc663bd"
        ],
        "unbundled": []
    },
    "_origin": "2023-11-08T18:25:49Z|s3://sfdl-segment-storagedc-stage/segment-logs/dxi6iTNi7ct2csUdYniZc9/1699401600000/1699467896294.events-archiver-480-31..c42024f9-e78e-4165-a7d2-d9816b28af34.gz|analytics-segment-separator-stage:$LATEST",
    "anonymousId": "bbf78767-ced1-48ae-b3dc-42ca2449fbd1",
    "channel": "client",
    "context": {
        "ip": "54.175.218.140",
        "library": {
            "name": "analytics.js",
            "version": "next-1.55.0"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/alaska/perryville/99648/475-brooks-road/",
            "referrer": "https://www.storage.extrameter.com/search/?location=perryville%2C%20ak",
            "search": "",
            "title": "",
            "url": "https://www.storage.extrameter.com/self-storage/alaska/perryville/99648/475-brooks-road/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
        "userAgentData": {
            "brands": [
                {
                    "brand": "Google Chrome",
                    "version": "119"
                },
                {
                    "brand": "Chromium",
                    "version": "119"
                },
                {
                    "brand": "Not?A_Brand",
                    "version": "24"
                }
            ],
            "mobile": false,
            "platform": "macOS"
        }
    },
    "integrations": {},
    "messageId": "ajs-next-25916e07a2156bbbec20ade1ab0fe7f2",
    "originalTimestamp": "2023-11-08T18:21:36.360Z",
    "projectId": "dxi6iTNi7ct2csUdYniZc9",
    "receivedAt": "2023-11-08T18:21:36.594Z",
    "sentAt": "2023-11-08T18:21:36.363Z",
    "timestamp": "2023-11-08T18:21:36.591Z",
    "traits": {},
    "type": "identify",
    "userId": "1e09866b89bd6573227a928bac61ab95",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "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",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 2083
schema_scan_id: 5306334
updated: 2023-11-08 12:26:05

Schema Scans: 2

Last at 2024-01-09 11:22:48

Scan 5415666

duration: 0:00:17.894182

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 3,
    "partitions_applied": false,
    "success": true
}

id: 5415666

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-01-09/",
        "name": "dt",
        "type": "string",
        "value": "2024-01-09"
    },
    "s3": {
        "bucket": "sfdl-segment-storagedc-stage",
        "hive_path": "s3://sfdl-segment-storagedc-stage/separated_dt/identify",
        "key": "separated_dt/identify/dt=2024-01-09/1704820920367.events-archiver-480-58..0e470018-4e11-4351-aae5-d86318f2cc5e.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagedc_identify",
        "type": "segment"
    }
}

running: False
schema_name_id: 2083
start_time: 2024-01-09 11:22:48
success: True
trace_id: 14497949301247279980

Scan 5306334

duration: 0:00:17.764343

exit_message:

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

id: 5306334

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2023-11-08/",
        "name": "dt",
        "type": "string",
        "value": "2023-11-08"
    },
    "s3": {
        "bucket": "sfdl-segment-storagedc-stage",
        "hive_path": "s3://sfdl-segment-storagedc-stage/separated_dt/identify",
        "key": "separated_dt/identify/dt=2023-11-08/1699467896294.events-archiver-480-31..c42024f9-e78e-4165-a7d2-d9816b28af34.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagedc_identify",
        "type": "segment"
    }
}

running: False
schema_name_id: 2083
start_time: 2023-11-08 12:25:50
success: True
trace_id: 5530526294084903113

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_segment.storagedc_identify`\nADD\n\n\n PARTITION (dt='2024-12-10') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-10/'\n PARTITION (dt='2024-12-28') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-28/'\n PARTITION (dt='2025-01-02') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2025-01-02/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 586061,
            "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-10/",
            "name": "dt",
            "value": "2024-12-10"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-12-10 09:15:12",
                "last_data": "2024-12-10 09:21:51"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 589469,
            "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-28/",
            "name": "dt",
            "value": "2024-12-28"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-12-28 17:19:34",
                "last_data": "2024-12-28 17:28:49"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 590311,
            "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2025-01-02/",
            "name": "dt",
            "value": "2025-01-02"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-01-02 10:55:37",
                "last_data": "2025-01-02 11:02:55"
            },
            "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.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",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2024-01-09 11:22:50

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagedc_identify`\n(\n`version`STRING,`type`STRING,`anonymousId`STRING,`originalTimestamp`STRING,`sentAt`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`timezone`:STRING,`locale`:STRING,`userAgent`:STRING,`ip`:STRING,`userAgentData`:struct<`brands`:array>,`platform`:STRING,`mobile`:STRING>,`page`:struct<`search`:STRING,`url`:STRING,`referrer`:STRING,`title`:STRING,`path`:STRING>>,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`_origin`STRING,`channel`STRING,`messageId`STRING,`timestamp`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-storagedc-stage/separated_dt/identify'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.storagedc_identify`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.storagedc_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": "2023-11-08 12:25:50",
        "disabled": false,
        "format": "raw",
        "id": 2083,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_segment",
            "table": "storagedc_identify"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_segment.storagedc_identify`\nADD\n\n\n PARTITION (dt='2024-12-10') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-10/'\n PARTITION (dt='2024-12-28') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-28/'\n PARTITION (dt='2025-01-02') location 's3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2025-01-02/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 586061,
                    "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-10/",
                    "name": "dt",
                    "value": "2024-12-10"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-12-10 09:15:12",
                        "last_data": "2024-12-10 09:21:51"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 589469,
                    "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2024-12-28/",
                    "name": "dt",
                    "value": "2024-12-28"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-12-28 17:19:34",
                        "last_data": "2024-12-28 17:28:49"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 590311,
                    "location": "s3://sfdl-segment-storagedc-stage/separated_dt/identify/dt=2025-01-02/",
                    "name": "dt",
                    "value": "2025-01-02"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-01-02 10:55:37",
                        "last_data": "2025-01-02 11:02:55"
                    },
                    "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.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",
            "projectId": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2024-01-09 11:22:50",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagedc_identify`\n(\n`version`STRING,`type`STRING,`anonymousId`STRING,`originalTimestamp`STRING,`sentAt`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`timezone`:STRING,`locale`:STRING,`userAgent`:STRING,`ip`:STRING,`userAgentData`:struct<`brands`:array>,`platform`:STRING,`mobile`:STRING>,`page`:struct<`search`:STRING,`url`:STRING,`referrer`:STRING,`title`:STRING,`path`:STRING>>,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`_origin`STRING,`channel`STRING,`messageId`STRING,`timestamp`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-storagedc-stage/separated_dt/identify'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.storagedc_identify`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.storagedc_identify"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}