Schema Info

Schema Name: sfdl_prod_segment.storagescout_invalid

created: 2019-06-04 12:55:39
disabled: False
format: raw
id: 703
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_prod_segment",
    "table": "storagescout_invalid"
}

type: segment

Schema Versions: 2

Version 125600

created: 2020-02-12 15:17:09

ddl:

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

hive_path: s3://sfdl-segment-storagescout-prod/separated_dt/invalid
id: 125600
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-02-12T21:16:54Z|s3://sfdl-segment-storagescout-prod/segment-logs/7e3jCTyCUW/1581465600000/1581541640777.2569a04bf190.e4797d0.1bf66a31-0e9a-429f-842e-19776db731ac.gz|segment_separator:37",
    "anonymousId": "f968b803-8c4e-43c9-b565-e6818c439219",
    "channel": "client",
    "context": {
        "ip": "172.58.21.247",
        "library": {
            "name": "analytics.js",
            "version": "3.11.0"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/az/camp-verde-storage-units/a-1-affordable-mini-rv-storage-200375/reserve/18150040/",
            "referrer": "https://www.google.com/",
            "search": "",
            "title": "Reserve a 5' x 10' unit at A-1 Affordable Mini RV Storage in Camp Verde - StorageScout.com",
            "url": "https://www.storagescout.com/self-storage/az/camp-verde-storage-units/a-1-affordable-mini-rv-storage-200375/reserve/18150040/"
        },
        "userAgent": "Mozilla/5.0 (Linux; Android 9; SM-G960U) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.116 Mobile Safari/537.36"
    },
    "event": "invalid",
    "integrations": {},
    "messageId": "ajs-ae7ae8c00401d9d06e1eea6d154e2d47",
    "originalTimestamp": "2020-02-12T20:57:21.240Z",
    "projectId": "7e3jCTyCUW",
    "properties": {
        "Hit Timestamp": 1581541041229,
        "category": "reservation form interactions-reservePage",
        "env": "production",
        "extra": {
            "facilityId": 200375,
            "unitId": 18150040
        },
        "isReact": true,
        "label": "email",
        "site_id": 417
    },
    "receivedAt": "2020-02-12T20:57:22.370Z",
    "sentAt": "2020-02-12T20:57:21.256Z",
    "timestamp": "2020-02-12T20:57:22.354Z",
    "type": "track",
    "userId": "71d8d4132ceedf1f53884b7aa431136a",
    "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.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 703
schema_scan_id: 32727243
updated: 2020-02-12 15:20:31

Version 79103

created: 2019-06-04 12:55:39

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`",
    "DROP TABLE IF EXISTS `sfdl_prod_segment.storagescout_invalid`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_segment.storagescout_invalid`\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>,`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-prod/separated_dt/invalid'\n",
    "MSCK REPAIR TABLE sfdl_prod_segment.storagescout_invalid"
]

hive_path: s3://sfdl-segment-storagescout-prod/separated_dt/invalid
id: 79103
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2019-06-04T17:55:29Z|s3://sfdl-segment-storagescout-prod/segment-logs/7e3jCTyCUW/1559606400000/1559670902426.040b170b980a.e4797d0.275498a9-c785-4ba3-9169-c98f1c93bca6.gz|segment_separator:37",
    "anonymousId": "d1568420-8634-409e-b187-df7af122a27e",
    "channel": "client",
    "context": {
        "ip": "66.162.93.78",
        "library": {
            "name": "analytics.js",
            "version": "3.8.2"
        },
        "page": {
            "path": "/self-storage/ok/tulsa-storage-units/attic-storage-brookside-208078/reserve/20188146/",
            "referrer": "https://beta.storagescout.com/search?location=poop",
            "search": "",
            "title": "Reserve a 3' x 6' unit with Ceiling: 10ft, Roll Up Door, Climate Controlled, 2nd Floor, Interior at Attic Storage Brookside in Tulsa - SelfStorage.com",
            "url": "https://beta.storagescout.com/self-storage/ok/tulsa-storage-units/attic-storage-brookside-208078/reserve/20188146/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"
    },
    "event": "invalid",
    "integrations": {},
    "messageId": "ajs-cd7a6c1b4608e9387062ee4be5984e94",
    "originalTimestamp": "2019-06-04T17:39:40.573Z",
    "projectId": "7e3jCTyCUW",
    "properties": {
        "Hit Timestamp": 1559669980570,
        "category": "reservation form interactions-reservePage",
        "env": "production",
        "extra": {
            "facilityId": 208078,
            "unitId": 20188146
        },
        "isReact": true,
        "label": "email",
        "site_id": 413
    },
    "receivedAt": "2019-06-04T17:39:40.615Z",
    "sentAt": "2019-06-04T17:39:40.578Z",
    "timestamp": "2019-06-04T17:39:40.610Z",
    "type": "track",
    "userId": "b702d4d0c041ead096265014d8afe0fc",
    "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.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 703
schema_scan_id: 25241512
updated: 2019-06-04 12:55:50

Schema Scans: 2

Last at 2020-02-12 15:17:09

Scan 32727243

duration: 0:02:27.504106

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 39,
    "partitions_applied": false,
    "success": true
}

id: 32727243

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2020-02-12/",
        "name": "dt",
        "type": "string",
        "value": "2020-02-12"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-prod",
        "hive_path": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid",
        "key": "separated_dt/invalid/dt=2020-02-12/1581541640777.2569a04bf190.e4797d0.1bf66a31-0e9a-429f-842e-19776db731ac.json.gz"
    },
    "schema": {
        "name": "sfdl_prod_segment.storagescout_invalid",
        "type": "segment"
    }
}

running: False
schema_name_id: 703
start_time: 2020-02-12 15:17:09
success: True
trace_id: 10281173180871841325

Scan 25241512

duration: 0:00:13.951677

exit_message:

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

id: 25241512

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2019-06-04/",
        "name": "dt",
        "type": "string",
        "value": "2019-06-04"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-prod",
        "hive_path": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid",
        "key": "separated_dt/invalid/dt=2019-06-04/1559670902426.040b170b980a.e4797d0.275498a9-c785-4ba3-9169-c98f1c93bca6.json.gz"
    },
    "schema": {
        "name": "sfdl_prod_segment.storagescout_invalid",
        "type": "segment"
    }
}

running: False
schema_name_id: 703
start_time: 2019-06-04 12:55:39
success: True
trace_id: 18141232926331752765

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_prod_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2021-07-19') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-07-19/'\n PARTITION (dt='2021-08-26') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-08-26/'\n PARTITION (dt='2021-11-04') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-11-04/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 595517,
            "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-07-19/",
            "name": "dt",
            "value": "2021-07-19"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-07-19 13:50:34",
                "last_data": "2021-07-19 13:50:34"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 603621,
            "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-08-26/",
            "name": "dt",
            "value": "2021-08-26"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-08-26 09:41:09",
                "last_data": "2021-08-26 09:49:10"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 675834,
            "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-11-04/",
            "name": "dt",
            "value": "2021-11-04"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-11-04 10:49:43",
                "last_data": "2021-11-04 11:58:07"
            },
            "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.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.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2020-02-12 15:17:09

ddl:

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

Server:

hostname: schemamanager-5475496c57-7dpqb
name: schema_manager
process_start: 2026-01-09 11:27:47
sf_env: prod
version: 2112174301

Raw:

{
    "name": {
        "created": "2019-06-04 12:55:39",
        "disabled": false,
        "format": "raw",
        "id": 703,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_prod_segment",
            "table": "storagescout_invalid"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_prod_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2021-07-19') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-07-19/'\n PARTITION (dt='2021-08-26') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-08-26/'\n PARTITION (dt='2021-11-04') location 's3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-11-04/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 595517,
                    "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-07-19/",
                    "name": "dt",
                    "value": "2021-07-19"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-07-19 13:50:34",
                        "last_data": "2021-07-19 13:50:34"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 603621,
                    "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-08-26/",
                    "name": "dt",
                    "value": "2021-08-26"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-08-26 09:41:09",
                        "last_data": "2021-08-26 09:49:10"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 675834,
                    "location": "s3://sfdl-segment-storagescout-prod/separated_dt/invalid/dt=2021-11-04/",
                    "name": "dt",
                    "value": "2021-11-04"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-11-04 10:49:43",
                        "last_data": "2021-11-04 11:58:07"
                    },
                    "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.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.site_id": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2020-02-12 15:17:09",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_segment.storagescout_invalid`\n(\n`receivedAt`STRING,`context`struct<`page`:struct<`search`:STRING,`referrer`:STRING,`url`:STRING,`title`:STRING,`path`:STRING>,`locale`:STRING,`userAgent`:STRING,`ip`:STRING,`library`:struct<`version`:STRING,`name`:STRING>>,`projectId`STRING,`channel`STRING,`version`STRING,`timestamp`STRING,`properties`struct<`env`:STRING,`site_id`:STRING,`isReact`:STRING,`extra`:struct<`facilityId`:STRING,`unitId`:STRING>,`label`:STRING,`category`:STRING,`Hit_Timestamp`:STRING>,`messageId`STRING,`sentAt`STRING,`userId`STRING,`originalTimestamp`STRING,`event`STRING,`type`STRING,`_origin`STRING,`anonymousId`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-prod/separated_dt/invalid'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_prod_segment.storagescout_invalid`",
            "repair_table": "MSCK REPAIR TABLE sfdl_prod_segment.storagescout_invalid"
        }
    },
    "server": {
        "hostname": "schemamanager-5475496c57-7dpqb",
        "name": "schema_manager",
        "process_start": "2026-01-09 11:27:47",
        "sf_env": "prod",
        "version": "2112174301"
    }
}