Schema Info

Schema Name: sfdl_dev_segment.storagescout_invalid

created: 2019-05-02 16:06:50
disabled: False
format: raw
id: 1244
is_partitioned: True
is_schema_datatyped: False

name:

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

type: segment

Schema Versions: 1

Version 4668995

created: 2019-05-15 17:03:07

ddl:

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

hive_path: s3://sfdl-segment-storagescout-dev/separated_dt/invalid
id: 4668995
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2019-05-15T22:03:03Z|s3://sfdl-segment-storagescout-dev/segment-logs/adK1RCRyGa/1557878400000/1557957416202.d0782f0ef52f.9f83b95.13d0d3f7-5ab0-4c99-811d-a4ecc4608563.gz|segment_separator:34",
    "anonymousId": "53a69c96-8f0b-433d-afb1-68fe663bc924",
    "channel": "client",
    "context": {
        "ip": "34.239.223.223",
        "library": {
            "name": "analytics.js",
            "version": "3.8.2"
        },
        "page": {
            "path": "/self-storage/ak/perryville-storage-units/engineering-test-204142/reserve/21178453/",
            "referrer": "",
            "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": "http://localhost:9125/self-storage/ak/perryville-storage-units/engineering-test-204142/reserve/21178453/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36"
    },
    "event": "invalid",
    "integrations": {},
    "messageId": "ajs-f94752a86eff40da1072a7e0d22a3fb2",
    "originalTimestamp": "2019-05-15T21:41:04.843Z",
    "projectId": "adK1RCRyGa",
    "properties": {
        "Hit Timestamp": 1557956464841,
        "category": "reservation form interactions-reservePage",
        "env": "development",
        "extra": {
            "facilityId": 204142,
            "unitId": 21178453
        },
        "isReact": true,
        "label": "email",
        "site_id": 27
    },
    "receivedAt": "2019-05-15T21:41:04.930Z",
    "sentAt": "2019-05-15T21:41:04.847Z",
    "timestamp": "2019-05-15T21:41:04.926Z",
    "type": "track",
    "userId": "error",
    "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: 1244
schema_scan_id: 4965476
updated: 2019-05-15 17:03:21

Schema Scans: 1

Last at 2019-05-15 17:03:07

Scan 4965476

duration: 0:00:16.875551

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 5,
    "partitions_applied": false,
    "success": true
}

id: 4965476

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-05-15/",
        "name": "dt",
        "type": "string",
        "value": "2019-05-15"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-dev",
        "hive_path": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid",
        "key": "separated_dt/invalid/dt=2019-05-15/1557957416202.d0782f0ef52f.9f83b95.13d0d3f7-5ab0-4c99-811d-a4ecc4608563.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.storagescout_invalid",
        "type": "segment"
    }
}

running: False
schema_name_id: 1244
start_time: 2019-05-15 17:03:07
success: True
trace_id: 15254860895731755149

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2019-05-21') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-05-21/'\n PARTITION (dt='2019-06-07') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-07/'\n PARTITION (dt='2019-06-24') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-24/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 140311,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-05-21/",
            "name": "dt",
            "value": "2019-05-21"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-05-21 11:58:37",
                "last_data": "2019-05-21 12:02:17"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 141097,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-07/",
            "name": "dt",
            "value": "2019-06-07"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-06-07 09:57:11",
                "last_data": "2019-06-07 10:14:11"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 141878,
            "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-24/",
            "name": "dt",
            "value": "2019-06-24"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-06-24 17:02:01",
                "last_data": "2019-06-24 17:02:01"
            },
            "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.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: 2019-05-15 17:03:07

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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-dev/separated_dt/invalid'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_invalid`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_invalid"
}

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 16:06:50",
        "disabled": false,
        "format": "raw",
        "id": 1244,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_segment",
            "table": "storagescout_invalid"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_segment.storagescout_invalid`\nADD\n\n\n PARTITION (dt='2019-05-21') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-05-21/'\n PARTITION (dt='2019-06-07') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-07/'\n PARTITION (dt='2019-06-24') location 's3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-24/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 140311,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-05-21/",
                    "name": "dt",
                    "value": "2019-05-21"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-05-21 11:58:37",
                        "last_data": "2019-05-21 12:02:17"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 141097,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-07/",
                    "name": "dt",
                    "value": "2019-06-07"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-06-07 09:57:11",
                        "last_data": "2019-06-07 10:14:11"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 141878,
                    "location": "s3://sfdl-segment-storagescout-dev/separated_dt/invalid/dt=2019-06-24/",
                    "name": "dt",
                    "value": "2019-06-24"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-06-24 17:02:01",
                        "last_data": "2019-06-24 17:02:01"
                    },
                    "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.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": "2019-05-15 17:03:07",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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-dev/separated_dt/invalid'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.storagescout_invalid`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.storagescout_invalid"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}