Schema Info

Schema Name: sfdl_stage_segment.storagescout_invalid

created: 2019-05-22 13:57:29
disabled: False
format: raw
id: 844
is_partitioned: True
is_schema_datatyped: False

name:

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

type: segment

Schema Versions: 2

Version 336068

created: 2021-06-23 16:21:00

ddl:

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

hive_path: s3://sfdl-segment-storagescout-stage/separated_dt/invalid
id: 336068
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "bundledIds": [
            "5cfe783d418588000189e438",
            "5ce847aa3bcc70000140d5a5"
        ],
        "unbundled": []
    },
    "_origin": "2021-06-23T21:20:29Z|s3://sfdl-segment-storagescout-stage/segment-logs/TYN5JDpyiK/1624406400000/1624483089358.519e5d6aa916.d65711d.8323304b-7eae-42e5-8b7e-2d19bdb052fe.gz|analytics-segment-separator-stage:$LATEST",
    "anonymousId": "4402262e-8cee-4073-8280-af7550923af2",
    "channel": "client",
    "context": {
        "ip": "34.239.223.223",
        "library": {
            "name": "analytics.js",
            "version": "4.1.8"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/ak/perryville-storage-units/fake-storage-facility-product-155558/reserve/21367897/",
            "referrer": "",
            "search": "",
            "title": "Reserve a 4' x 5' unit at Fake Storage Facility - Product in Perryville - USStorageSearch.com",
            "url": "https://www.usstoragesearch.extrameter.com/self-storage/ak/perryville-storage-units/fake-storage-facility-product-155558/reserve/21367897/"
        },
        "userAgent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36"
    },
    "event": "invalid",
    "integrations": {},
    "messageId": "ajs-7a282c340ba7330a4533755b4af5d9bf",
    "originalTimestamp": "2021-06-23T21:07:59.301Z",
    "projectId": "TYN5JDpyiK",
    "properties": {
        "Hit Timestamp": 1624482479298,
        "category": "reservation form interactions-reservePage",
        "env": "stage",
        "extra": {
            "facilityId": 155558,
            "unitId": 21367897
        },
        "isReact": true,
        "label": "email",
        "site_id": 413
    },
    "receivedAt": "2021-06-23T21:07:59.838Z",
    "sentAt": "2021-06-23T21:07:59.306Z",
    "timestamp": "2021-06-23T21:07:59.833Z",
    "type": "track",
    "userId": "09e2cde2e81db41fdbc52ef6d2e6f5dd",
    "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: 844
schema_scan_id: 3352486
updated: 2021-06-23 16:21:14

Version 205621

created: 2019-05-22 13:57:30

ddl:

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

hive_path: s3://sfdl-segment-storagescout-stage/separated_dt/invalid
id: 205621
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2019-05-22T18:57:15Z|s3://sfdl-segment-storagescout-stage/segment-logs/TYN5JDpyiK/1558483200000/1558551394045.78e68f4ff0c5.9f83b95.c44e3e01-bb6f-4f5f-a860-e18938c201d3.gz|segment_separator:37",
    "anonymousId": "26677769-bd5e-466a-9258-90cf1a2d7c92",
    "channel": "client",
    "context": {
        "ip": "68.248.142.128",
        "library": {
            "name": "analytics.js",
            "version": "3.8.2"
        },
        "page": {
            "path": "/self-storage/ak/perryville-storage-units/engineering-test-204142/reserve/21178453/",
            "referrer": "https://sparefoot.atlassian.net/browse/SF-7963",
            "search": "",
            "title": "Reserve a 300' x 300' unit with Ceiling: 300ft, Roll Up Door, Climate Controlled, Humidity Controlled, Air Cooled Only, Heated Only, Electricity, Alarm, ADA Accessible, Drive Up Access, Outdoor Access, Premium Location, Pullthrough, Shelves, Skybox, Lights, Vehicle, Available for enclosed vehicle storage at Engineering**Test in Perryville - SelfStorage.com",
            "url": "https://storagescout.extrameter.com/self-storage/ak/perryville-storage-units/engineering-test-204142/reserve/21178453/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36"
    },
    "event": "invalid",
    "integrations": {},
    "messageId": "ajs-4018b9eb24d560117306e548454b76c3",
    "originalTimestamp": "2019-05-22T18:32:00.928Z",
    "projectId": "TYN5JDpyiK",
    "properties": {
        "Hit Timestamp": 1558549920926,
        "category": "reservation form interactions-reservePage",
        "env": "stage",
        "extra": {
            "facilityId": 204142,
            "unitId": 21178453
        },
        "isReact": true,
        "label": "email",
        "site_id": 413
    },
    "receivedAt": "2019-05-22T18:32:00.965Z",
    "sentAt": "2019-05-22T18:32:00.934Z",
    "timestamp": "2019-05-22T18:32:00.959Z",
    "type": "track",
    "userId": "60f66e71ead7ed5b6f829361b15df784",
    "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: 844
schema_scan_id: 2149854
updated: 2019-05-22 13:57:44

Schema Scans: 2

Last at 2021-06-23 16:21:00

Scan 3352486

duration: 0:00:16.748989

exit_message:

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

id: 3352486

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-23/",
        "name": "dt",
        "type": "string",
        "value": "2021-06-23"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-stage",
        "hive_path": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid",
        "key": "separated_dt/invalid/dt=2021-06-23/1624483089358.519e5d6aa916.d65711d.8323304b-7eae-42e5-8b7e-2d19bdb052fe.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagescout_invalid",
        "type": "segment"
    }
}

running: False
schema_name_id: 844
start_time: 2021-06-23 16:21:00
success: True
trace_id: 38798562531189462

Scan 2149854

duration: 0:00:17.771078

exit_message:

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

id: 2149854

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2019-05-22/",
        "name": "dt",
        "type": "string",
        "value": "2019-05-22"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-stage",
        "hive_path": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid",
        "key": "separated_dt/invalid/dt=2019-05-22/1558551394045.78e68f4ff0c5.9f83b95.c44e3e01-bb6f-4f5f-a860-e18938c201d3.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagescout_invalid",
        "type": "segment"
    }
}

running: False
schema_name_id: 844
start_time: 2019-05-22 13:57:29
success: True
trace_id: 2376527341832742535

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2019-05-22') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2019-05-22/'\n PARTITION (dt='2021-06-23') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-23/'\n PARTITION (dt='2021-06-25') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-25/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 111640,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2019-05-22/",
            "name": "dt",
            "value": "2019-05-22"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-05-22 13:57:30",
                "last_data": "2019-05-22 15:00:15"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 202644,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-23/",
            "name": "dt",
            "value": "2021-06-23"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-06-23 16:21:00",
                "last_data": "2021-06-23 16:21:00"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 202890,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-25/",
            "name": "dt",
            "value": "2021-06-25"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-06-25 16:27:14",
                "last_data": "2021-06-25 16:27:14"
            },
            "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: 2021-06-23 16:21:00

ddl:

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

Server:

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

Raw:

{
    "name": {
        "created": "2019-05-22 13:57:29",
        "disabled": false,
        "format": "raw",
        "id": 844,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_segment",
            "table": "storagescout_invalid"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2019-05-22') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2019-05-22/'\n PARTITION (dt='2021-06-23') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-23/'\n PARTITION (dt='2021-06-25') location 's3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-25/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 111640,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2019-05-22/",
                    "name": "dt",
                    "value": "2019-05-22"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-05-22 13:57:30",
                        "last_data": "2019-05-22 15:00:15"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 202644,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-23/",
                    "name": "dt",
                    "value": "2021-06-23"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-06-23 16:21:00",
                        "last_data": "2021-06-23 16:21:00"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 202890,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/invalid/dt=2021-06-25/",
                    "name": "dt",
                    "value": "2021-06-25"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-06-25 16:27:14",
                        "last_data": "2021-06-25 16:27:14"
                    },
                    "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": "2021-06-23 16:21:00",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_invalid`\n(\n`projectId`STRING,`event`STRING,`channel`STRING,`originalTimestamp`STRING,`sentAt`STRING,`properties`struct<`category`:STRING,`label`:STRING,`env`:STRING,`extra`:struct<`facilityId`:STRING,`unitId`:STRING>,`site_id`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING>,`timestamp`STRING,`anonymousId`STRING,`type`STRING,`receivedAt`STRING,`_origin`STRING,`userId`STRING,`messageId`STRING,`version`STRING,`context`struct<`page`:struct<`url`:STRING,`search`:STRING,`path`:STRING,`referrer`:STRING,`title`:STRING>,`userAgent`:STRING,`ip`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`locale`: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-stage/separated_dt/invalid'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_invalid`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_invalid"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}