Schema Info

Schema Name: sfdl_dev_segment.storagescout_valid

created: 2019-05-02 13:59:07
disabled: False
format: raw
id: 1243
is_partitioned: True
is_schema_datatyped: False

name:

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

type: segment

Schema Versions: 2

Version 4678644

created: 2020-05-14 15:07:26

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_valid`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.storagescout_valid`\n(\n`receivedAt`STRING,`_origin`STRING,`version`STRING,`userId`STRING,`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`ip`:STRING,`userAgent`:STRING,`page`:struct<`title`:STRING,`path`:STRING,`referrer`:STRING,`url`:STRING,`search`:STRING>,`locale`:STRING>,`timestamp`STRING,`originalTimestamp`STRING,`type`STRING,`messageId`STRING,`event`STRING,`sentAt`STRING,`channel`STRING,`properties`struct<`Hit_Timestamp`:STRING,`extra`:struct<`unitId`:STRING,`facilityId`:STRING>,`moveInDateSelected`:STRING,`env`:STRING,`isReact`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`projectId`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-storagescout-dev/separated_dt/valid'\n",
    "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_valid"
]

hive_path: s3://sfdl-segment-storagescout-dev/separated_dt/valid
id: 4678644
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-05-14T20:07:19Z|s3://sfdl-segment-storagescout-dev/segment-logs/adK1RCRyGa/1589414400000/1589486711113.31bb1c92eddc.e4797d0.d4fa9b2d-a4c5-4c63-a933-3292b47d7e63.gz|segment_separator:34",
    "anonymousId": "abc6bf47-e44d-4021-9813-a469bfbb1784",
    "channel": "client",
    "context": {
        "ip": "54.88.102.255",
        "library": {
            "name": "analytics.js",
            "version": "3.13.1"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/ak/perryville-storage-units/fake-storage-facility-product-155558/reserve/21367895/",
            "referrer": "",
            "search": "",
            "title": "Reserve a 5' x 5' unit at Fake Storage Facility - Product in Perryville - StorageScout.com",
            "url": "https://www.storagescout.moreyard.com/self-storage/ak/perryville-storage-units/fake-storage-facility-product-155558/reserve/21367895/"
        },
        "userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36"
    },
    "event": "valid",
    "integrations": {},
    "messageId": "ajs-bf91ebdd0bd8502d6a937ff9729b3839",
    "originalTimestamp": "2020-05-14T20:00:43.957Z",
    "projectId": "adK1RCRyGa",
    "properties": {
        "Hit Timestamp": 1589486443955,
        "category": "reservation form interactions-reservePage",
        "env": "dev",
        "extra": {
            "facilityId": 155558,
            "unitId": 21367895
        },
        "isReact": true,
        "label": "first_name",
        "site_id": 413
    },
    "receivedAt": "2020-05-14T20:00:43.211Z",
    "sentAt": "2020-05-14T20:00:43.961Z",
    "timestamp": "2020-05-14T20:00:43.207Z",
    "type": "track",
    "userId": "SELENIUM",
    "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",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.Hit_Timestamp": "string",
    "properties.category": "string",
    "properties.env": "string",
    "properties.extra.facilityId": "string",
    "properties.extra.unitId": "string",
    "properties.isReact": "string",
    "properties.label": "string",
    "properties.moveInDateSelected": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 1243
schema_scan_id: 5605885
updated: 2020-05-14 15:07:47

Version 4668951

created: 2019-05-14 14:57:49

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_valid`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.storagescout_valid`\n(\n`version`STRING,`timestamp`STRING,`projectId`STRING,`userId`STRING,`properties`struct<`category`:STRING,`Hit_Timestamp`:STRING,`extra`:struct<`facilityId`:STRING,`unitId`:STRING>,`isReact`:STRING,`site_id`:STRING,`label`:STRING,`env`:STRING,`moveInDateSelected`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`originalTimestamp`STRING,`context`struct<`ip`:STRING,`page`:struct<`url`:STRING,`path`:STRING,`search`:STRING,`title`:STRING,`referrer`:STRING>,`library`:struct<`version`:STRING,`name`:STRING>,`userAgent`: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-storagescout-dev/separated_dt/valid'\n",
    "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_valid"
]

hive_path: s3://sfdl-segment-storagescout-dev/separated_dt/valid
id: 4668951
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2019-05-14T19:57:15Z|s3://sfdl-segment-storagescout-dev/segment-logs/adK1RCRyGa/1557792000000/1557863795971.f38b02cc5633.9f83b95.a89b6a67-0450-4301-92eb-9804a3f97cc2.gz|segment_separator:34",
    "anonymousId": "f5187868-ebd2-4179-ba1b-b2530a468043",
    "channel": "client",
    "context": {
        "ip": "66.68.131.155",
        "library": {
            "name": "analytics.js",
            "version": "3.8.2"
        },
        "page": {
            "path": "/self-storage/ak/perryville-storage-units/fake-storage-facility-percent-cpa-158519/reserve/17307993/",
            "referrer": "",
            "search": "",
            "title": "Reserve a 5' x 5' unit with Interior at Fake Storage Facility - Percent CPA in Perryville - SelfStorage.com",
            "url": "http://localhost:9125/self-storage/ak/perryville-storage-units/fake-storage-facility-percent-cpa-158519/reserve/17307993/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
    },
    "event": "valid",
    "integrations": {},
    "messageId": "ajs-82a3fe184472782e22639e73b529f9e3",
    "originalTimestamp": "2019-05-14T19:35:35.206Z",
    "projectId": "adK1RCRyGa",
    "properties": {
        "Hit Timestamp": 1557862535204,
        "category": "reservation form interactions-reservePage",
        "env": "development",
        "extra": {
            "facilityId": 158519,
            "unitId": 17307993
        },
        "isReact": true,
        "label": "move_in_date",
        "moveInDateSelected": "05/15/2019",
        "site_id": 27
    },
    "receivedAt": "2019-05-14T19:35:35.280Z",
    "sentAt": "2019-05-14T19:35:35.211Z",
    "timestamp": "2019-05-14T19:35:35.275Z",
    "type": "track",
    "userId": "3f7cf670cc36272f254a1e16f67cb852",
    "version": 2
}

schema_attributes:

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.ip": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "context.page.path": "string",
    "context.page.referrer": "string",
    "context.page.search": "string",
    "context.page.title": "string",
    "context.page.url": "string",
    "context.userAgent": "string",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.Hit_Timestamp": "string",
    "properties.category": "string",
    "properties.env": "string",
    "properties.extra.facilityId": "string",
    "properties.extra.unitId": "string",
    "properties.isReact": "string",
    "properties.label": "string",
    "properties.moveInDateSelected": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 1243
schema_scan_id: 4963260
updated: 2019-05-14 14:58:02

Schema Scans: 2

Last at 2020-05-14 15:07:26

Scan 5605885

duration: 0:00:24.214624

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 35,
    "partitions_applied": false,
    "success": true
}

id: 5605885

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2020-05-14/",
        "name": "dt",
        "type": "string",
        "value": "2020-05-14"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-dev",
        "hive_path": "s3://sfdl-segment-storagescout-dev/separated_dt/valid",
        "key": "separated_dt/valid/dt=2020-05-14/1589486711113.31bb1c92eddc.e4797d0.d4fa9b2d-a4c5-4c63-a933-3292b47d7e63.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.storagescout_valid",
        "type": "segment"
    }
}

running: False
schema_name_id: 1243
start_time: 2020-05-14 15:07:26
success: True
trace_id: 8952149992457617744

Scan 4963260

duration: 0:00:16.489707

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 8,
    "partitions_applied": false,
    "success": true
}

id: 4963260

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2019-05-14/",
        "name": "dt",
        "type": "string",
        "value": "2019-05-14"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-dev",
        "hive_path": "s3://sfdl-segment-storagescout-dev/separated_dt/valid",
        "key": "separated_dt/valid/dt=2019-05-14/1557863795971.f38b02cc5633.9f83b95.a89b6a67-0450-4301-92eb-9804a3f97cc2.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.storagescout_valid",
        "type": "segment"
    }
}

running: False
schema_name_id: 1243
start_time: 2019-05-14 14:57:49
success: True
trace_id: 12930010667065994294

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_segment.storagescout_valid`\nADD\n\n\n PARTITION (dt='2021-03-04') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-03-04/'\n PARTITION (dt='2021-07-20') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-07-20/'\n PARTITION (dt='2022-02-28') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2022-02-28/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 171636,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-03-04/",
            "name": "dt",
            "value": "2021-03-04"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-03-04 16:27:33",
                "last_data": "2021-03-04 17:29:17"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 177592,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-07-20/",
            "name": "dt",
            "value": "2021-07-20"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-07-20 14:42:03",
                "last_data": "2021-07-20 14:50:21"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 183447,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2022-02-28/",
            "name": "dt",
            "value": "2022-02-28"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2022-02-28 14:13:14",
                "last_data": "2022-02-28 14:25:20"
            },
            "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.userAgent": "string",
    "event": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.Hit_Timestamp": "string",
    "properties.category": "string",
    "properties.env": "string",
    "properties.extra.facilityId": "string",
    "properties.extra.unitId": "string",
    "properties.isReact": "string",
    "properties.label": "string",
    "properties.moveInDateSelected": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2020-05-14 15:07:26

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.storagescout_valid`\n(\n`receivedAt`STRING,`_origin`STRING,`version`STRING,`userId`STRING,`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`ip`:STRING,`userAgent`:STRING,`page`:struct<`title`:STRING,`path`:STRING,`referrer`:STRING,`url`:STRING,`search`:STRING>,`locale`:STRING>,`timestamp`STRING,`originalTimestamp`STRING,`type`STRING,`messageId`STRING,`event`STRING,`sentAt`STRING,`channel`STRING,`properties`struct<`Hit_Timestamp`:STRING,`extra`:struct<`unitId`:STRING,`facilityId`:STRING>,`moveInDateSelected`:STRING,`env`:STRING,`isReact`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`projectId`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-storagescout-dev/separated_dt/valid'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_valid`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_valid"
}

Server:

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

Raw:

{
    "name": {
        "created": "2019-05-02 13:59:07",
        "disabled": false,
        "format": "raw",
        "id": 1243,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_segment",
            "table": "storagescout_valid"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_segment.storagescout_valid`\nADD\n\n\n PARTITION (dt='2021-03-04') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-03-04/'\n PARTITION (dt='2021-07-20') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-07-20/'\n PARTITION (dt='2022-02-28') location 's3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2022-02-28/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 171636,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-03-04/",
                    "name": "dt",
                    "value": "2021-03-04"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-03-04 16:27:33",
                        "last_data": "2021-03-04 17:29:17"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 177592,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2021-07-20/",
                    "name": "dt",
                    "value": "2021-07-20"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-07-20 14:42:03",
                        "last_data": "2021-07-20 14:50:21"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 183447,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/valid/dt=2022-02-28/",
                    "name": "dt",
                    "value": "2022-02-28"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2022-02-28 14:13:14",
                        "last_data": "2022-02-28 14:25:20"
                    },
                    "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.userAgent": "string",
            "event": "string",
            "messageId": "string",
            "originalTimestamp": "string",
            "projectId": "string",
            "properties.Hit_Timestamp": "string",
            "properties.category": "string",
            "properties.env": "string",
            "properties.extra.facilityId": "string",
            "properties.extra.unitId": "string",
            "properties.isReact": "string",
            "properties.label": "string",
            "properties.moveInDateSelected": "string",
            "properties.site_id": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2020-05-14 15:07:26",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.storagescout_valid`\n(\n`receivedAt`STRING,`_origin`STRING,`version`STRING,`userId`STRING,`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`ip`:STRING,`userAgent`:STRING,`page`:struct<`title`:STRING,`path`:STRING,`referrer`:STRING,`url`:STRING,`search`:STRING>,`locale`:STRING>,`timestamp`STRING,`originalTimestamp`STRING,`type`STRING,`messageId`STRING,`event`STRING,`sentAt`STRING,`channel`STRING,`properties`struct<`Hit_Timestamp`:STRING,`extra`:struct<`unitId`:STRING,`facilityId`:STRING>,`moveInDateSelected`:STRING,`env`:STRING,`isReact`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`projectId`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-storagescout-dev/separated_dt/valid'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_valid`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_valid"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}