Schema Info

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`",
    "DROP TABLE IF EXISTS `sfdl_prod_segment.ssdc_completed`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_segment.ssdc_completed`\n(\n `version`  string , `timestamp`  string , `messageId`  string , `userId`  string , `event`  string , `receivedAt`  string ,`_metadata`   struct< `bundled`:array , `unbundled`:array >, `anonymousId`  string , `originalTimestamp`  string ,`context`   struct< `ip` : string ,`campaign` :  struct< `source` : string , `medium` : string , `name` : string >,`page` :  struct< `url` : string , `path` : string , `search` : string , `referrer` : string , `title` : string >,`library` :  struct< `version` : string , `name` : string >, `userAgent` : string >, `projectId`  string , `_origin`  string , `type`  string ,`properties`   struct< `category` : string , `Hit_Timestamp` : string , `site_id` : string , `label` : 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-ssdc-prod/separated_dt/completed'\n",
    "MSCK REPAIR TABLE sfdl_prod_segment.ssdc_completed"
]

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2018-05-03T22:23:48Z|s3://sfdl-segment-ssdc-prod/segment-logs/5yGJd9z7eL/1525305600000/1525386141715.bd18ea9b2eda.1.11.1.5a76564b-8b91-4ab0-bbfc-1b19e6c2ec3b.gz|segment_separator:37",
    "anonymousId": "47b0ecea-6ebc-4b9a-8681-8b1e22c0fc87",
    "channel": "client",
    "context": {
        "campaign": {
            "medium": "email",
            "name": "SSDC_MIDC_CUST_TRXN_SF-4401",
            "source": "Emarsys"
        },
        "ip": "107.77.236.6",
        "library": {
            "name": "analytics.js",
            "version": "3.5.2"
        },
        "page": {
            "path": "/self-storage/north-carolina/durham/cubesmart-self-storage-durham-205170/",
            "referrer": "http://click.sparefoot.com/u/nrd.php?p=Gti9wNmp9R_1203_822453_1_9&ems_l=802151&i=1&d=aHR0cHM6Ly93d3cuc2VsZnN0b3JhZ2UuY29t%7CV1lGQVdWUEhR%7CMzQwNTU1NDQ%3D%7CR3RpOXdObXA5Ug%3D%3D%7CU1NEQ19NSURDX0NVU1RfVFJYTl9TRi00NDAx%7CYTdmNmVkODhjNDU4ZWU0MTE%3D%7C",
            "search": "?sc_src=email_822453&sc_lid=34055544&sc_uid=Gti9wNmp9R&sc_llid=1203&utm_source=Emarsys&utm_medium=email&utm_campaign=SSDC_MIDC_CUST_TRXN_SF-4401&sc_eh=a7f6ed88c458ee411",
            "title": "Reservation Confirmed for CubeSmart Self Storage - Durham | SelfStorage.com",
            "url": "https://www.selfstorage.com/self-storage/north-carolina/durham/cubesmart-self-storage-durham-205170/?sc_src=email_822453&sc_lid=34055544&sc_uid=Gti9wNmp9R&sc_llid=1203&utm_source=Emarsys&utm_medium=email&utm_campaign=SSDC_MIDC_CUST_TRXN_SF-4401&sc_eh=a7f6ed88c458ee411"
        },
        "userAgent": "Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_2 like Mac OS X) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.0 Mobile/14F89 Safari/602.1"
    },
    "event": "completed",
    "integrations": {},
    "messageId": "ajs-ae2c30a6e0799437e5d42bb7da22ea40",
    "originalTimestamp": "2018-05-03T21:48:02.079Z",
    "projectId": "5yGJd9z7eL",
    "properties": {
        "Hit Timestamp": 1525384082068,
        "category": "add another name to reservation form interactions-ssdc_res_confirmation_page",
        "label": "last name",
        "site_id": "144"
    },
    "receivedAt": "2018-05-03T21:48:02.215Z",
    "sentAt": "2018-05-03T21:48:02.080Z",
    "timestamp": "2018-05-03T21:48:02.214Z",
    "type": "track",
    "userId": "805aeb831930c8f9893366732",
    "version": 2
}

{
    "_origin": "string",
    "anonymousId": "string",
    "channel": "string",
    "context.campaign.medium": "string",
    "context.campaign.name": "string",
    "context.campaign.source": "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.label": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`",
    "DROP TABLE IF EXISTS `sfdl_prod_segment.ssdc_completed`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_segment.ssdc_completed`\n(\n `version`  string , `timestamp`  string , `projectId`  string , `userId`  string ,`properties`   struct< `category` : string , `Hit_Timestamp` : string , `site_id` : string , `label` : string >, `receivedAt`  string ,`_metadata`   struct< `bundled`:array , `unbundled`:array >, `anonymousId`  string , `originalTimestamp`  string ,`context`   struct< `ip` : string ,`page` :  struct< `url` : string , `path` : string , `search` : string , `referrer` : string , `title` : 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-ssdc-prod/separated_dt/completed'\n",
    "MSCK REPAIR TABLE sfdl_prod_segment.ssdc_completed"
]

{
    "_metadata": {
        "bundled": [
            "Google Analytics",
            "Google Tag Manager",
            "Segment.io"
        ],
        "unbundled": []
    },
    "_origin": "2018-05-03T22:01:27Z|s3://sfdl-segment-ssdc-prod/segment-logs/5yGJd9z7eL/1525305600000/1525384870010.efa9ce6076c4.1.11.1.6d5b6d15-cb63-496b-a03c-602acd960874.gz|segment_separator:37",
    "anonymousId": "fa45d50c-8dbd-492e-8730-80d34adfda07",
    "channel": "client",
    "context": {
        "campaign": {},
        "ip": "70.126.13.155",
        "library": {
            "name": "analytics.js",
            "version": "3.5.2"
        },
        "page": {
            "path": "/self-storage/florida/hudson/castle-keep-hudson-203424/",
            "referrer": "https://www.selfstorage.com/self-storage/florida/hudson/castle-keep-hudson-203424/",
            "search": "?k=e05df53e1ac03f3d4a0981785f958eb6",
            "title": "Reservation Confirmed for Castle Keep - Hudson | SelfStorage.com",
            "url": "https://www.selfstorage.com/self-storage/florida/hudson/castle-keep-hudson-203424/?k=e05df53e1ac03f3d4a0981785f958eb6"
        },
        "userAgent": "Mozilla/5.0 (iPad; CPU OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/11.0 Mobile/15E148 Safari/604.1"
    },
    "event": "completed",
    "integrations": {},
    "messageId": "ajs-433575b3c27b0d2a43607d4ba2442ff7",
    "originalTimestamp": "2018-05-03T21:26:58.678Z",
    "projectId": "5yGJd9z7eL",
    "properties": {
        "Hit Timestamp": 1525382818675,
        "category": "add another name to reservation form interactions-ssdc_res_confirmation_page",
        "label": "first name",
        "site_id": "144"
    },
    "receivedAt": "2018-05-03T21:26:58.740Z",
    "sentAt": "2018-05-03T21:26:58.680Z",
    "timestamp": "2018-05-03T21:26:58.738Z",
    "type": "track",
    "userId": "655aeb7d0d781bb5207708118",
    "version": 2
}

{
    "_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.label": "string",
    "properties.site_id": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string"
}

{
    "exception": "failed to apply schema `Invalid ddl? `CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment```: [u'CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`', u'DROP TABLE IF EXISTS `sfdl_prod_segment.ssdc_completed`', u\"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_prod_segment.ssdc_completed`\\n(\\n `version`  string , `timestamp`  string , `messageId`  string , `userId`  string , `event`  string , `receivedAt`  string ,`_metadata`   struct< `bundled`:array , `unbundled`:array >, `anonymousId`  string , `originalTimestamp`  string ,`context`   struct< `ip` : string ,`campaign` :  struct< `source` : string , `medium` : string , `name` : string >,`page` :  struct< `url` : string , `path` : string , `search` : string , `referrer` : string , `title` : string >,`library` :  struct< `version` : string , `name` : string >, `userAgent` : string >, `projectId`  string , `_origin`  string , `type`  string ,`properties`   struct< `category` : string , `Hit_Timestamp` : string , `site_id` : string , `label` : 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-ssdc-prod/separated_dt/completed'\\n\", u'MSCK REPAIR TABLE sfdl_prod_segment.ssdc_completed']\nTraceback (most recent call last):\n  File \"schema_generator/schema_scanner.py\", line 84, in scan\n    response = service.run()\n  File \"schema_generator/process_hive_table.py\", line 95, in run\n    response['ddl_changed'] = table_generator.run()\n  File \"schema_generator/table_generator.py\", line 34, in run\n    self.apply_latest_version()\n  File \"schema_generator/table_generator.py\", line 25, in apply_latest_version\n    raise Exception('failed to apply schema `{}`: {}'.format(e.message, ddl_list))\nException: failed to apply schema `Invalid ddl? `CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment```: [u'CREATE DATABASE IF NOT EXISTS `sfdl_prod_segment`', u'DROP TABLE IF EXISTS `sfdl_prod_segment.ssdc_completed`', u\"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_prod_segment.ssdc_completed`\\n(\\n `version`  string , `timestamp`  string , `messageId`  string , `userId`  string , `event`  string , `receivedAt`  string ,`_metadata`   struct< `bundled`:array , `unbundled`:array >, `anonymousId`  string , `originalTimestamp`  string ,`context`   struct< `ip` : string ,`campaign` :  struct< `source` : string , `medium` : string , `name` : string >,`page` :  struct< `url` : string , `path` : string , `search` : string , `referrer` : string , `title` : string >,`library` :  struct< `version` : string , `name` : string >, `userAgent` : string >, `projectId`  string , `_origin`  string , `type`  string ,`properties`   struct< `category` : string , `Hit_Timestamp` : string , `site_id` : string , `label` : 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-ssdc-prod/separated_dt/completed'\\n\", u'MSCK REPAIR TABLE sfdl_prod_segment.ssdc_completed']\n: Expecting value: line 1 column 1 (char 0)"
}

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-ssdc-prod/separated_dt/completed/dt=2018-05-03/",
        "name": "dt",
        "type": "string",
        "value": "2018-05-03"
    },
    "s3": {
        "bucket": "sfdl-segment-ssdc-prod",
        "hive_path": "s3://sfdl-segment-ssdc-prod/separated_dt/completed",
        "key": "separated_dt/completed/dt=2018-05-03/1525386141715.bd18ea9b2eda.1.11.1.5a76564b-8b91-4ab0-bbfc-1b19e6c2ec3b.json.gz"
    },
    "schema": {
        "name": "sfdl_prod_segment.ssdc_completed",
        "type": "segment"
    }
}

{
    "ddl_changed": true,
    "ingested_partitions": 527,
    "partitions_applied": false,
    "success": true
}

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-ssdc-prod/separated_dt/completed/dt=2018-05-03/",
        "name": "dt",
        "type": "string",
        "value": "2018-05-03"
    },
    "s3": {
        "bucket": "sfdl-segment-ssdc-prod",
        "hive_path": "s3://sfdl-segment-ssdc-prod/separated_dt/completed",
        "key": "separated_dt/completed/dt=2018-05-03/1525384870010.efa9ce6076c4.1.11.1.6d5b6d15-cb63-496b-a03c-602acd960874.json.gz"
    },
    "schema": {
        "name": "sfdl_prod_segment.ssdc_completed",
        "type": "segment"
    }
}