Schema Info

Schema Name: sfdl_stage_segment.storagescout_con_pageview

created: 2019-05-02 11:05:42
disabled: False
format: raw
id: 834
is_partitioned: True
is_schema_datatyped: False

name:

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

type: segment

Schema Versions: 3

Version 267369

created: 2020-05-15 15:05:16

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_con_pageview`\n(\n`sentAt`STRING,`originalTimestamp`STRING,`event`STRING,`properties`struct<`env`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING,`site_id`:STRING,`CON`:struct<`page_subtype`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`timestamp`:STRING,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`date_end`:STRING,`page_type`:STRING>>,`site_content`:struct<`id`:STRING>,`facility`:struct<`title`:STRING,`id`:STRING>,`environment`:STRING,`search_result`:struct<`id`:STRING,`query`:STRING,`page`:STRING,`listing_ids`:array>,`page_type`:STRING,`unit`:struct<`price`:STRING,`id`:STRING>,`site_id`:STRING,`visit_id`:STRING>>,`channel`STRING,`userId`STRING,`messageId`STRING,`integrations`struct<`Google_Analytics`:STRING,`All`:STRING>,`timestamp`STRING,`projectId`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`search`:STRING,`referrer`:STRING,`path`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING,`locale`:STRING,`userAgent`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`_origin`STRING,`version`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/CON PAGEVIEW'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview"
]

hive_path: s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW
id: 267369
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-05-15T20:05:13Z|s3://sfdl-segment-storagescout-stage/segment-logs/TYN5JDpyiK/1589500800000/1589573098932.31bb1c92eddc.e4797d0.33b872d5-746c-4554-ac2b-0536680426ae.gz|segment_separator:37",
    "anonymousId": "befe1d34-5a22-4cf5-bc4f-6a9eaf471b38",
    "channel": "client",
    "context": {
        "ip": "34.239.223.223",
        "library": {
            "name": "analytics.js",
            "version": "3.13.1"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/nj/newark-storage-units/",
            "referrer": "",
            "search": "",
            "title": "Self Storage Deals & Discounts Near Me | StorageScout",
            "url": "https://storagescout.extrameter.com/self-storage/nj/newark-storage-units/"
        },
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:76.0) Gecko/20100101 Firefox/76.0"
    },
    "event": "CON PAGEVIEW",
    "integrations": {
        "All": true,
        "Google Analytics": false
    },
    "messageId": "ajs-a0e8495c105e91d9547baef8115e1940",
    "originalTimestamp": "2020-05-15T19:55:51.760Z",
    "projectId": "TYN5JDpyiK",
    "properties": {
        "CON": {
            "environment": "stage",
            "location": {
                "city": "Newark",
                "id": "23801750",
                "state": "NJ"
            },
            "page_subtype": "cityLandingPage",
            "page_type": "searchPage",
            "ppc": {
                "adwords": {
                    "date_end": "2020-05-29T00:00:00.000Z",
                    "date_start": "2020-05-15T00:00:00.000Z",
                    "page_type": "searchresults"
                }
            },
            "search_result": {
                "id": "19905ebef3c5961544.90491833",
                "listing_ids": [
                    202257,
                    211186,
                    214079,
                    214151,
                    216250,
                    216340,
                    108293,
                    107495,
                    216845,
                    203441,
                    214859,
                    62664,
                    212048,
                    103487,
                    211523
                ],
                "page": 1,
                "query": "newark, nj"
            },
            "site_content": {},
            "site_id": 413,
            "site_type": "desktop",
            "timestamp": "2020-05-15T19:55:49.000Z",
            "visit_id": "error"
        },
        "Hit Timestamp": 1589572551758,
        "env": "stage",
        "isReact": true,
        "site_id": 413
    },
    "receivedAt": "2020-05-15T19:55:51.921Z",
    "sentAt": "2020-05-15T19:55:51.760Z",
    "timestamp": "2020-05-15T19:55:51.921Z",
    "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.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",
    "integrations.All": "string",
    "integrations.Google_Analytics": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.CON.environment": "string",
    "properties.CON.facility.id": "string",
    "properties.CON.facility.title": "string",
    "properties.CON.location.city": "string",
    "properties.CON.location.id": "string",
    "properties.CON.location.state": "string",
    "properties.CON.page_subtype": "string",
    "properties.CON.page_type": "string",
    "properties.CON.ppc.adwords.date_end": "string",
    "properties.CON.ppc.adwords.date_start": "string",
    "properties.CON.ppc.adwords.page_type": "string",
    "properties.CON.search_result.id": "string",
    "properties.CON.search_result.listing_ids": [
        "int"
    ],
    "properties.CON.search_result.page": "string",
    "properties.CON.search_result.query": "string",
    "properties.CON.site_content.id": "string",
    "properties.CON.site_id": "string",
    "properties.CON.site_type": "string",
    "properties.CON.timestamp": "string",
    "properties.CON.transaction.confirmation_code": "string",
    "properties.CON.transaction.email": "string",
    "properties.CON.transaction.id": "string",
    "properties.CON.transaction.npv": "string",
    "properties.CON.unit.id": "string",
    "properties.CON.unit.price": "string",
    "properties.CON.visit_id": "string",
    "properties.Hit_Timestamp": "string",
    "properties.env": "string",
    "properties.isReact": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 834
schema_scan_id: 2740024
updated: 2020-05-15 15:07:09

Version 247561

created: 2020-01-25 16:12:07

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_con_pageview`\n(\n`anonymousId`STRING,`originalTimestamp`STRING,`_origin`STRING,`event`STRING,`receivedAt`STRING,`userId`STRING,`sentAt`STRING,`context`struct<`userAgent`:STRING,`ip`:STRING,`locale`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`referrer`:STRING,`path`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>>,`properties`struct<`env`:STRING,`site_id`:STRING,`Hit_Timestamp`:STRING,`CON`:struct<`environment`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`page_type`:STRING,`site_id`:STRING,`page_subtype`:STRING,`visit_id`:STRING,`timestamp`:STRING,`facility`:struct<`title`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`page_type`:STRING,`date_end`:STRING>>,`search_result`:struct<`id`:STRING,`listing_ids`:array,`page`:STRING,`query`:STRING>,`site_content`:struct<`id`:STRING>,`unit`:struct<`price`:STRING,`id`:STRING>>,`isReact`:STRING>,`messageId`STRING,`projectId`STRING,`integrations`struct<`All`:STRING,`Google_Analytics`:STRING>,`timestamp`STRING,`version`STRING,`channel`STRING,`type`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/CON PAGEVIEW'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview"
]

hive_path: s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW
id: 247561
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-01-25T22:12:06Z|s3://sfdl-segment-storagescout-stage/segment-logs/TYN5JDpyiK/1579910400000/1579989892419.31bb1c92eddc.e4797d0.7d8acdcc-d183-4612-98f8-335b7d4a7837.gz|segment_separator:37",
    "anonymousId": "edb90040-43e9-4128-b872-04707401aa38",
    "channel": "client",
    "context": {
        "ip": "50.86.51.129",
        "library": {
            "name": "analytics.js",
            "version": "3.10.1"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/ms/coffeeville-storage-units/",
            "referrer": "https://www.google.com/",
            "search": "",
            "title": "Best Self-Storage Units in Coffeeville, MS - StorageScout",
            "url": "https://www.storagescout.extrameter.com/self-storage/ms/coffeeville-storage-units/"
        },
        "userAgent": "Mozilla/5.0 (Linux; Android 7.1.1; LG-US601) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Mobile Safari/537.36"
    },
    "event": "CON PAGEVIEW",
    "integrations": {
        "All": true,
        "Google Analytics": false
    },
    "messageId": "ajs-e44437cca8512d1e4145634e2a4d9d45",
    "originalTimestamp": "2020-01-25T21:31:01.027Z",
    "projectId": "TYN5JDpyiK",
    "properties": {
        "CON": {
            "environment": "stage",
            "location": {
                "city": "Coffeeville",
                "id": "24695959",
                "state": "MS"
            },
            "page_subtype": "cityLandingPage",
            "page_type": "searchPage",
            "ppc": {
                "adwords": {
                    "date_end": "2020-02-08T00:00:00.000Z",
                    "date_start": "2020-01-25T00:00:00.000Z",
                    "page_type": "searchresults"
                }
            },
            "search_result": {
                "id": "96975e2cb3908a97e7.70127689",
                "listing_ids": [],
                "page": 1,
                "query": "coffeeville, ms"
            },
            "site_content": {
                "id": "476820"
            },
            "site_id": 417,
            "site_type": "desktop",
            "timestamp": "2020-01-25T21:30:59.000Z",
            "visit_id": "47bb89de1b0f97f851710fba0ebbe671"
        },
        "Hit Timestamp": 1579987860240,
        "env": "stage",
        "isReact": true,
        "site_id": 417
    },
    "receivedAt": "2020-01-25T21:31:01.917Z",
    "sentAt": "2020-01-25T21:31:01.072Z",
    "timestamp": "2020-01-25T21:31:01.872Z",
    "type": "track",
    "userId": "47bb89de1b0f97f851710fba0ebbe671",
    "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",
    "integrations.All": "string",
    "integrations.Google_Analytics": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.CON.environment": "string",
    "properties.CON.facility.id": "string",
    "properties.CON.facility.title": "string",
    "properties.CON.location.city": "string",
    "properties.CON.location.id": "string",
    "properties.CON.location.state": "string",
    "properties.CON.page_subtype": "string",
    "properties.CON.page_type": "string",
    "properties.CON.ppc.adwords.date_end": "string",
    "properties.CON.ppc.adwords.date_start": "string",
    "properties.CON.ppc.adwords.page_type": "string",
    "properties.CON.search_result.id": "string",
    "properties.CON.search_result.listing_ids": [
        "string"
    ],
    "properties.CON.search_result.page": "string",
    "properties.CON.search_result.query": "string",
    "properties.CON.site_content.id": "string",
    "properties.CON.site_id": "string",
    "properties.CON.site_type": "string",
    "properties.CON.timestamp": "string",
    "properties.CON.transaction.confirmation_code": "string",
    "properties.CON.transaction.email": "string",
    "properties.CON.transaction.id": "string",
    "properties.CON.transaction.npv": "string",
    "properties.CON.unit.id": "string",
    "properties.CON.unit.price": "string",
    "properties.CON.visit_id": "string",
    "properties.Hit_Timestamp": "string",
    "properties.env": "string",
    "properties.isReact": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 834
schema_scan_id: 2538104
updated: 2020-01-25 16:12:38

Version 247078

created: 2020-01-23 04:08:14

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_con_pageview`\n(\n`anonymousId`STRING,`originalTimestamp`STRING,`_origin`STRING,`event`STRING,`receivedAt`STRING,`userId`STRING,`sentAt`STRING,`context`struct<`userAgent`:STRING,`locale`:STRING,`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`referrer`:STRING,`path`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING>,`properties`struct<`env`:STRING,`site_id`:STRING,`Hit_Timestamp`:STRING,`CON`:struct<`environment`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`search_result`:struct<`id`:STRING,`listing_ids`:array,`page`:STRING,`query`:STRING>,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`page_type`:STRING,`site_id`:STRING,`visit_id`:STRING,`timestamp`:STRING,`facility`:struct<`title`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`page_type`:STRING,`date_end`:STRING>>,`unit`:struct<`price`:STRING,`id`:STRING>,`site_content`:struct<`id`:STRING>,`page_subtype`:STRING>,`isReact`:STRING>,`messageId`STRING,`projectId`STRING,`integrations`struct<`All`:STRING,`Google_Analytics`:STRING>,`timestamp`STRING,`version`STRING,`channel`STRING,`type`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/CON PAGEVIEW'\n",
    "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview"
]

hive_path: s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW
id: 247078
processed: 1

raw_data:

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2020-01-23T10:08:13Z|s3://sfdl-segment-storagescout-stage/segment-logs/TYN5JDpyiK/1579737600000/1579774039343.4b8bf6068e8b.e4797d0.e04b3c9a-0046-46a7-8d84-fe45d921cc0b.gz|segment_separator:37",
    "anonymousId": "0424d396-007f-4002-992a-824eec8cbab3",
    "channel": "client",
    "context": {
        "ip": "66.249.83.119",
        "library": {
            "name": "analytics.js",
            "version": "3.10.1"
        },
        "locale": "en-US",
        "page": {
            "path": "/self-storage/fl/dade-city-storage-units/",
            "referrer": "",
            "search": "",
            "title": "Best Self-Storage Units in Dade City, FL - StorageScout",
            "url": "https://www.storagescout.extrameter.com/self-storage/fl/dade-city-storage-units/"
        },
        "userAgent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36"
    },
    "event": "CON PAGEVIEW",
    "integrations": {
        "All": true,
        "Google Analytics": false
    },
    "messageId": "ajs-2298423d18e81a0c465384776560a634",
    "originalTimestamp": "2020-01-23T09:49:51.359Z",
    "projectId": "TYN5JDpyiK",
    "properties": {
        "CON": {
            "environment": "stage",
            "location": {
                "city": "Dade City",
                "id": "23805539",
                "state": "FL"
            },
            "page_subtype": "cityLandingPage",
            "page_type": "searchPage",
            "ppc": {
                "adwords": {
                    "date_end": "2020-02-06T00:00:00.000Z",
                    "date_start": "2020-01-23T00:00:00.000Z",
                    "page_type": "searchresults"
                }
            },
            "search_result": {
                "id": "7c885e296c37753af8.08520228",
                "listing_ids": [
                    109323,
                    153749,
                    212490,
                    213372,
                    213001,
                    213239,
                    213470,
                    213337,
                    213143,
                    213249,
                    212109,
                    213340,
                    213295,
                    200448,
                    50528
                ],
                "page": 1,
                "query": "dade-city, fl"
            },
            "site_content": {
                "id": "474171"
            },
            "site_id": 413,
            "site_type": "desktop",
            "timestamp": "2020-01-23T09:49:51.000Z",
            "visit_id": "03bc93b763ffbaaa616f5583f1f9c04b"
        },
        "Hit Timestamp": 1579772991294,
        "env": "stage",
        "isReact": true,
        "site_id": 413
    },
    "receivedAt": "2020-01-23T09:49:52.942Z",
    "sentAt": "2020-01-23T09:49:51.367Z",
    "timestamp": "2020-01-23T09:49:52.934Z",
    "type": "track",
    "userId": "03bc93b763ffbaaa616f5583f1f9c04b",
    "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",
    "integrations.All": "string",
    "integrations.Google_Analytics": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.CON.environment": "string",
    "properties.CON.facility.id": "string",
    "properties.CON.facility.title": "string",
    "properties.CON.location.city": "string",
    "properties.CON.location.id": "string",
    "properties.CON.location.state": "string",
    "properties.CON.page_subtype": "string",
    "properties.CON.page_type": "string",
    "properties.CON.ppc.adwords.date_end": "string",
    "properties.CON.ppc.adwords.date_start": "string",
    "properties.CON.ppc.adwords.page_type": "string",
    "properties.CON.search_result.id": "string",
    "properties.CON.search_result.listing_ids": [
        "int"
    ],
    "properties.CON.search_result.page": "string",
    "properties.CON.search_result.query": "string",
    "properties.CON.site_content.id": "string",
    "properties.CON.site_id": "string",
    "properties.CON.site_type": "string",
    "properties.CON.timestamp": "string",
    "properties.CON.transaction.confirmation_code": "string",
    "properties.CON.transaction.email": "string",
    "properties.CON.transaction.id": "string",
    "properties.CON.transaction.npv": "string",
    "properties.CON.unit.id": "string",
    "properties.CON.unit.price": "string",
    "properties.CON.visit_id": "string",
    "properties.Hit_Timestamp": "string",
    "properties.env": "string",
    "properties.isReact": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

schema_name_id: 834
schema_scan_id: 2533240
updated: 2020-01-23 04:08:46

Schema Scans: 3

Last at 2020-05-15 15:05:16

Scan 2740024

duration: 0:00:26.103021

exit_message:

{
    "exception": "failed to apply schema `Query failed: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask `MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview``: ['CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`', 'DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_stage_segment.storagescout_con_pageview`\\n(\\n`sentAt`STRING,`originalTimestamp`STRING,`event`STRING,`properties`struct<`env`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING,`site_id`:STRING,`CON`:struct<`page_subtype`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`timestamp`:STRING,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`date_end`:STRING,`page_type`:STRING>>,`site_content`:struct<`id`:STRING>,`facility`:struct<`title`:STRING,`id`:STRING>,`environment`:STRING,`search_result`:struct<`id`:STRING,`query`:STRING,`page`:STRING,`listing_ids`:array>,`page_type`:STRING,`unit`:struct<`price`:STRING,`id`:STRING>,`site_id`:STRING,`visit_id`:STRING>>,`channel`STRING,`userId`STRING,`messageId`STRING,`integrations`struct<`Google_Analytics`:STRING,`All`:STRING>,`timestamp`STRING,`projectId`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`search`:STRING,`referrer`:STRING,`path`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING,`locale`:STRING,`userAgent`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`_origin`STRING,`version`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/CON PAGEVIEW'\\n\", 'MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview']\nTraceback (most recent call last):\n  File \"/schema_manager/schema_generator/table_generator.py\", line 24, in apply_latest_version\n    self.runner.run_multi_query(schema_version.ddl, timeout=DDLQueueWorker.TIMEOUT)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 133, in run_multi_query\n    result = self.run_single_query(query, timeout, database)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 51, in run_single_query\n    return self._run_single_query(query, timeout, database)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 120, in _run_single_query\n    raise e\n  File \"/src/athena-runner/athena_runner/runner.py\", line 103, in _run_single_query\n    raise AthenaRunnerQueryException('Query failed: {} `{}`'.format(info['QueryExecution']['Status']['StateChangeReason'], query))\nathena_runner.exceptions.AthenaRunnerQueryException: Query failed: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask `MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview`\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/schema_manager/schema_generator/schema_scanner.py\", line 102, in scan\n    response = service.run()\n  File \"/schema_manager/schema_generator/process_hive_table.py\", line 95, in run\n    response['ddl_changed'] = table_generator.run()\n  File \"/schema_manager/schema_generator/table_generator.py\", line 35, in run\n    self.apply_latest_version()\n  File \"/schema_manager/schema_generator/table_generator.py\", line 26, in apply_latest_version\n    raise Exception('failed to apply schema `{}`: {}'.format(e, schema_version.ddl))\nException: failed to apply schema `Query failed: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask `MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview``: ['CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`', 'DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_stage_segment.storagescout_con_pageview`\\n(\\n`sentAt`STRING,`originalTimestamp`STRING,`event`STRING,`properties`struct<`env`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING,`site_id`:STRING,`CON`:struct<`page_subtype`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`timestamp`:STRING,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`date_end`:STRING,`page_type`:STRING>>,`site_content`:struct<`id`:STRING>,`facility`:struct<`title`:STRING,`id`:STRING>,`environment`:STRING,`search_result`:struct<`id`:STRING,`query`:STRING,`page`:STRING,`listing_ids`:array>,`page_type`:STRING,`unit`:struct<`price`:STRING,`id`:STRING>,`site_id`:STRING,`visit_id`:STRING>>,`channel`STRING,`userId`STRING,`messageId`STRING,`integrations`struct<`Google_Analytics`:STRING,`All`:STRING>,`timestamp`STRING,`projectId`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`search`:STRING,`referrer`:STRING,`path`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING,`locale`:STRING,`userAgent`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`_origin`STRING,`version`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/CON PAGEVIEW'\\n\", 'MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview']\n: Expecting value: line 1 column 1 (char 0)"
}

id: 2740024

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2020-05-15/",
        "name": "dt",
        "type": "string",
        "value": "2020-05-15"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-stage",
        "hive_path": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW",
        "key": "separated_dt/CON PAGEVIEW/dt=2020-05-15/1589573098932.31bb1c92eddc.e4797d0.33b872d5-746c-4554-ac2b-0536680426ae.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagescout_CON_PAGEVIEW",
        "type": "segment"
    }
}

running: False
schema_name_id: 834
start_time: 2020-05-15 15:05:16
success: False
trace_id: 4319712798087593773

Scan 2538104

duration: 0:00:34.503885

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 104,
    "partitions_applied": false,
    "success": true
}

id: 2538104

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2020-01-25/",
        "name": "dt",
        "type": "string",
        "value": "2020-01-25"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-stage",
        "hive_path": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW",
        "key": "separated_dt/CON PAGEVIEW/dt=2020-01-25/1579989892419.31bb1c92eddc.e4797d0.7d8acdcc-d183-4612-98f8-335b7d4a7837.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagescout_CON_PAGEVIEW",
        "type": "segment"
    }
}

running: False
schema_name_id: 834
start_time: 2020-01-25 16:12:07
success: True
trace_id: 3116266151760712253

Scan 2533240

duration: 0:00:34.574348

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 103,
    "partitions_applied": false,
    "success": true
}

id: 2533240

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2020-01-23/",
        "name": "dt",
        "type": "string",
        "value": "2020-01-23"
    },
    "s3": {
        "bucket": "sfdl-segment-storagescout-stage",
        "hive_path": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW",
        "key": "separated_dt/CON PAGEVIEW/dt=2020-01-23/1579774039343.4b8bf6068e8b.e4797d0.e04b3c9a-0046-46a7-8d84-fe45d921cc0b.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_segment.storagescout_CON_PAGEVIEW",
        "type": "segment"
    }
}

running: False
schema_name_id: 834
start_time: 2020-01-23 04:08:14
success: True
trace_id: 13645744966665118032

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_segment.storagescout_con_pageview`\nADD\n\n\n PARTITION (dt='2021-02-08') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-08/'\n PARTITION (dt='2021-02-09') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-09/'\n PARTITION (dt='2021-02-10') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-10/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 177379,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-08/",
            "name": "dt",
            "value": "2021-02-08"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-02-08 11:21:08",
                "last_data": "2021-02-08 11:27:06"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 181890,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-09/",
            "name": "dt",
            "value": "2021-02-09"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-02-09 11:17:33",
                "last_data": "2021-02-09 12:19:50"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 182004,
            "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-10/",
            "name": "dt",
            "value": "2021-02-10"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-02-10 13:16:20",
                "last_data": "2021-02-10 15:28:50"
            },
            "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",
    "integrations.All": "string",
    "integrations.Google_Analytics": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "properties.CON.environment": "string",
    "properties.CON.facility.id": "string",
    "properties.CON.facility.title": "string",
    "properties.CON.location.city": "string",
    "properties.CON.location.id": "string",
    "properties.CON.location.state": "string",
    "properties.CON.page_subtype": "string",
    "properties.CON.page_type": "string",
    "properties.CON.ppc.adwords.date_end": "string",
    "properties.CON.ppc.adwords.date_start": "string",
    "properties.CON.ppc.adwords.page_type": "string",
    "properties.CON.search_result.id": "string",
    "properties.CON.search_result.listing_ids": [
        "int"
    ],
    "properties.CON.search_result.page": "string",
    "properties.CON.search_result.query": "string",
    "properties.CON.site_content.id": "string",
    "properties.CON.site_id": "string",
    "properties.CON.site_type": "string",
    "properties.CON.timestamp": "string",
    "properties.CON.transaction.confirmation_code": "string",
    "properties.CON.transaction.email": "string",
    "properties.CON.transaction.id": "string",
    "properties.CON.transaction.npv": "string",
    "properties.CON.unit.id": "string",
    "properties.CON.unit.price": "string",
    "properties.CON.visit_id": "string",
    "properties.Hit_Timestamp": "string",
    "properties.env": "string",
    "properties.isReact": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

created: 2020-05-15 15:05:16

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_con_pageview`\n(\n`sentAt`STRING,`originalTimestamp`STRING,`event`STRING,`properties`struct<`env`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING,`site_id`:STRING,`CON`:struct<`page_subtype`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`timestamp`:STRING,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`date_end`:STRING,`page_type`:STRING>>,`site_content`:struct<`id`:STRING>,`facility`:struct<`title`:STRING,`id`:STRING>,`environment`:STRING,`search_result`:struct<`id`:STRING,`query`:STRING,`page`:STRING,`listing_ids`:array>,`page_type`:STRING,`unit`:struct<`price`:STRING,`id`:STRING>,`site_id`:STRING,`visit_id`:STRING>>,`channel`STRING,`userId`STRING,`messageId`STRING,`integrations`struct<`Google_Analytics`:STRING,`All`:STRING>,`timestamp`STRING,`projectId`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`search`:STRING,`referrer`:STRING,`path`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING,`locale`:STRING,`userAgent`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`_origin`STRING,`version`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/CON PAGEVIEW'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview"
}

Server:

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

Raw:

{
    "name": {
        "created": "2019-05-02 11:05:42",
        "disabled": false,
        "format": "raw",
        "id": 834,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_segment",
            "table": "storagescout_con_pageview"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_segment.storagescout_con_pageview`\nADD\n\n\n PARTITION (dt='2021-02-08') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-08/'\n PARTITION (dt='2021-02-09') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-09/'\n PARTITION (dt='2021-02-10') location 's3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-10/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 177379,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-08/",
                    "name": "dt",
                    "value": "2021-02-08"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-02-08 11:21:08",
                        "last_data": "2021-02-08 11:27:06"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 181890,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-09/",
                    "name": "dt",
                    "value": "2021-02-09"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-02-09 11:17:33",
                        "last_data": "2021-02-09 12:19:50"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 182004,
                    "location": "s3://sfdl-segment-storagescout-stage/separated_dt/CON PAGEVIEW/dt=2021-02-10/",
                    "name": "dt",
                    "value": "2021-02-10"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-02-10 13:16:20",
                        "last_data": "2021-02-10 15:28:50"
                    },
                    "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",
            "integrations.All": "string",
            "integrations.Google_Analytics": "string",
            "messageId": "string",
            "originalTimestamp": "string",
            "projectId": "string",
            "properties.CON.environment": "string",
            "properties.CON.facility.id": "string",
            "properties.CON.facility.title": "string",
            "properties.CON.location.city": "string",
            "properties.CON.location.id": "string",
            "properties.CON.location.state": "string",
            "properties.CON.page_subtype": "string",
            "properties.CON.page_type": "string",
            "properties.CON.ppc.adwords.date_end": "string",
            "properties.CON.ppc.adwords.date_start": "string",
            "properties.CON.ppc.adwords.page_type": "string",
            "properties.CON.search_result.id": "string",
            "properties.CON.search_result.listing_ids": [
                "int"
            ],
            "properties.CON.search_result.page": "string",
            "properties.CON.search_result.query": "string",
            "properties.CON.site_content.id": "string",
            "properties.CON.site_id": "string",
            "properties.CON.site_type": "string",
            "properties.CON.timestamp": "string",
            "properties.CON.transaction.confirmation_code": "string",
            "properties.CON.transaction.email": "string",
            "properties.CON.transaction.id": "string",
            "properties.CON.transaction.npv": "string",
            "properties.CON.unit.id": "string",
            "properties.CON.unit.price": "string",
            "properties.CON.visit_id": "string",
            "properties.Hit_Timestamp": "string",
            "properties.env": "string",
            "properties.isReact": "string",
            "properties.site_id": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2020-05-15 15:05:16",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_segment.storagescout_con_pageview`\n(\n`sentAt`STRING,`originalTimestamp`STRING,`event`STRING,`properties`struct<`env`:STRING,`isReact`:STRING,`Hit_Timestamp`:STRING,`site_id`:STRING,`CON`:struct<`page_subtype`:STRING,`site_type`:STRING,`location`:struct<`id`:STRING,`state`:STRING,`city`:STRING>,`timestamp`:STRING,`transaction`:struct<`confirmation_code`:STRING,`npv`:STRING,`email`:STRING,`id`:STRING>,`ppc`:struct<`adwords`:struct<`date_start`:STRING,`date_end`:STRING,`page_type`:STRING>>,`site_content`:struct<`id`:STRING>,`facility`:struct<`title`:STRING,`id`:STRING>,`environment`:STRING,`search_result`:struct<`id`:STRING,`query`:STRING,`page`:STRING,`listing_ids`:array>,`page_type`:STRING,`unit`:struct<`price`:STRING,`id`:STRING>,`site_id`:STRING,`visit_id`:STRING>>,`channel`STRING,`userId`STRING,`messageId`STRING,`integrations`struct<`Google_Analytics`:STRING,`All`:STRING>,`timestamp`STRING,`projectId`STRING,`type`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>,`page`:struct<`search`:STRING,`referrer`:STRING,`path`:STRING,`title`:STRING,`url`:STRING>,`ip`:STRING,`locale`:STRING,`userAgent`:STRING>,`receivedAt`STRING,`anonymousId`STRING,`_origin`STRING,`version`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/CON PAGEVIEW'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_segment.storagescout_con_pageview`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_segment.storagescout_con_pageview"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}