Schema Info

Schema Name: sfdl_dev_segment.sfdc_click
  • created: 2021-01-29 12:57:48
  • disabled: False
  • format: raw
  • id: 1536
  • is_partitioned: True
  • is_schema_datatyped: False
  • name:
    {
        "database": "sfdl_dev_segment",
        "table": "sfdc_click"
    }
  • type: segment
Schema Versions: 1
    • created: 2021-01-29 12:57:49
    • ddl:
      [
          "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
          "DROP TABLE IF EXISTS `sfdl_dev_segment.sfdc_click`",
          "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sfdc_click`\n(\n`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`ip`:STRING>,`event`STRING,`messageId`STRING,`properties`struct<`Hit_Timestamp`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`channel`STRING,`originalTimestamp`STRING,`projectId`STRING,`version`STRING,`_origin`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-sfdc-dev/separated_dt/click'\n",
          "MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click"
      ]
    • hive_path: s3://sfdl-segment-sfdc-dev/separated_dt/click
    • id: 4684363
    • processed: 0
    • raw_data:
      {
          "_metadata": {
              "bundled": [
                  "Google Analytics",
                  "Segment.io"
              ],
              "unbundled": []
          },
          "_origin": "2021-01-29T18:37:12Z|s3://sfdl-segment-sfdc-dev/segment-logs/OIyQwmGWuW/1484006400000/1484085218711.74ad58a88154.1.10.5.7a0990ca-c759-4e86-8969-0e74c919379d.gz|segment_separator:1",
          "anonymousId": "46416c02-b828-469a-bf35-acca6a453113",
          "channel": "client",
          "context": {
              "campaign": {},
              "ip": "207.71.19.142",
              "library": {
                  "name": "analytics.js",
                  "version": "3.0.0"
              },
              "page": {
                  "path": "/search.html",
                  "referrer": "http://www.sparefoot.local/",
                  "search": "?moveInDate=&location=Dallas%2C+TX%2C+United+States&city=Dallas&state=TX&latitude=32.7766642&longitude=-96.79698789999998",
                  "title": "Find Self Storage Units and Facilities in Dallas, TX 75201 | SpareFoot",
                  "url": "http://www.sparefoot.local/search.html?moveInDate=&location=Dallas%2C+TX%2C+United+States&city=Dallas&state=TX&latitude=32.7766642&longitude=-96.79698789999998"
              },
              "userAgent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/55.0.2883.87 Chrome/55.0.2883.87 Safari/537.36"
          },
          "event": "click",
          "integrations": {},
          "messageId": "ajs-7e15401eb7efa9f40fea01464837113e",
          "originalTimestamp": "2017-01-10T21:48:55.440Z",
          "projectId": "OIyQwmGWuW",
          "properties": {
              "Hit Timestamp": 1484084935439,
              "activePhlags_sf_1933_improved_filter_visibility": "control",
              "activePhlags_sf_1936_search_help_widget": "help_widget",
              "activePhlags_sf_1994_map_zoom": "zoomed",
              "activePhlags_sf_2016_aa_groundhog_day": "variation",
              "activePhlags_sf_2063_stacked_ui_flow": "control",
              "activePhlags_sf_2064_mobile_map_v2": "control",
              "activePhlags_sf_2066_value_prop_mab": "find_compare",
              "activePhlags_sf_2081_mobile_map_ctr": "bold",
              "activePhlags_sf_2158_gate_page": "control",
              "category": "facility interactions-searchPage",
              "label": "unit-selfstorage-5x10",
              "site_id": "-1"
          },
          "receivedAt": "2017-01-10T21:48:55.550Z",
          "sentAt": "2017-01-10T21:48:55.444Z",
          "timestamp": "2017-01-10T21:48:55.546Z",
          "type": "track",
          "userId": "7757a24310d7e379347714535",
          "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.label": "string",
          "properties.site_id": "string",
          "receivedAt": "string",
          "sentAt": "string",
          "timestamp": "string",
          "type": "string",
          "userId": "string",
          "version": "string"
      }
    • schema_name_id: 1536
    • schema_scan_id: 5749517
    • updated: None
Schema Scans: 1
Last at 2021-01-29 12:57:48
    • duration: 0:07:54.830421
    • exit_message:
      {
          "exception": "failed to apply schema `Query failed: FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask. null `MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click``: ['CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`', 'DROP TABLE IF EXISTS `sfdl_dev_segment.sfdc_click`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_dev_segment.sfdc_click`\\n(\\n`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`ip`:STRING>,`event`STRING,`messageId`STRING,`properties`struct<`Hit_Timestamp`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`channel`STRING,`originalTimestamp`STRING,`projectId`STRING,`version`STRING,`_origin`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-sfdc-dev/separated_dt/click'\\n\", 'MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click']\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. null `MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click`\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 98, 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. null `MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click``: ['CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`', 'DROP TABLE IF EXISTS `sfdl_dev_segment.sfdc_click`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_dev_segment.sfdc_click`\\n(\\n`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`ip`:STRING>,`event`STRING,`messageId`STRING,`properties`struct<`Hit_Timestamp`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`channel`STRING,`originalTimestamp`STRING,`projectId`STRING,`version`STRING,`_origin`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-sfdc-dev/separated_dt/click'\\n\", 'MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click']\n: Expecting value: line 1 column 1 (char 0)"
      }
    • id: 5749517
    • payload:
      {
          "datatype_dict": null,
          "file_format": "json",
          "is_schema_datatyped": false,
          "partition": {
              "location": "s3://sfdl-segment-sfdc-dev/separated_dt/click/dt=2017-01-10/",
              "name": "dt",
              "type": "string",
              "value": "2017-01-10"
          },
          "s3": {
              "bucket": "sfdl-segment-sfdc-dev",
              "hive_path": "s3://sfdl-segment-sfdc-dev/separated_dt/click",
              "key": "separated_dt/click/dt=2017-01-10/1484085218711.74ad58a88154.1.10.5.7a0990ca-c759-4e86-8969-0e74c919379d.json.gz"
          },
          "schema": {
              "name": "sfdl_dev_segment.sfdc_click",
              "type": "segment"
          }
      }
    • running: False
    • schema_name_id: 1536
    • start_time: 2021-01-29 12:57:48
    • success: False
    • trace_id: 1017350304767167075
Partitions:
  • count: 1
  • ddl:
    [
        "ALTER TABLE\n    `sfdl_dev_segment.sfdc_click`\nADD\n\n\n PARTITION (dt='2017-01-10') location 's3://sfdl-segment-sfdc-dev/separated_dt/click/dt=2017-01-10/'\n;"
    ]
  • name: dt
  • state:
    [
        {
            "info": {
                "id": 164650,
                "location": "s3://sfdl-segment-sfdc-dev/separated_dt/click/dt=2017-01-10/",
                "name": "dt",
                "value": "2017-01-10"
            },
            "state": {
                "arrival": {
                    "athena_discovery": false,
                    "first_data": "2021-01-29 12:57:49",
                    "last_data": "2021-01-29 14:38:29"
                },
                "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.label": "string",
        "properties.site_id": "string",
        "receivedAt": "string",
        "sentAt": "string",
        "timestamp": "string",
        "type": "string",
        "userId": "string",
        "version": "string"
    }
  • created: 2021-01-29 12:57:49
  • ddl:
    {
        "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
        "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sfdc_click`\n(\n`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`ip`:STRING>,`event`STRING,`messageId`STRING,`properties`struct<`Hit_Timestamp`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`channel`STRING,`originalTimestamp`STRING,`projectId`STRING,`version`STRING,`_origin`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-sfdc-dev/separated_dt/click'\n",
        "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sfdc_click`",
        "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click"
    }
Server:
  • hostname: schemamanager-5447774fc6-4w58v
  • name: schema_manager
  • process_start: 2026-04-02 21:43:44
  • sf_env: dev
  • version: 2427328685
Raw:
{
    "name": {
        "created": "2021-01-29 12:57:48",
        "disabled": false,
        "format": "raw",
        "id": 1536,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_segment",
            "table": "sfdc_click"
        },
        "type": "segment"
    },
    "partition": {
        "count": 1,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_segment.sfdc_click`\nADD\n\n\n PARTITION (dt='2017-01-10') location 's3://sfdl-segment-sfdc-dev/separated_dt/click/dt=2017-01-10/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 164650,
                    "location": "s3://sfdl-segment-sfdc-dev/separated_dt/click/dt=2017-01-10/",
                    "name": "dt",
                    "value": "2017-01-10"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": false,
                        "first_data": "2021-01-29 12:57:49",
                        "last_data": "2021-01-29 14:38:29"
                    },
                    "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.label": "string",
            "properties.site_id": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string"
        },
        "created": "2021-01-29 12:57:49",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sfdc_click`\n(\n`anonymousId`STRING,`context`struct<`library`:struct<`name`:STRING,`version`:STRING>,`page`:struct<`path`:STRING,`referrer`:STRING,`search`:STRING,`title`:STRING,`url`:STRING>,`userAgent`:STRING,`ip`:STRING>,`event`STRING,`messageId`STRING,`properties`struct<`Hit_Timestamp`:STRING,`category`:STRING,`label`:STRING,`site_id`:STRING>,`receivedAt`STRING,`sentAt`STRING,`timestamp`STRING,`type`STRING,`userId`STRING,`channel`STRING,`originalTimestamp`STRING,`projectId`STRING,`version`STRING,`_origin`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-sfdc-dev/separated_dt/click'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sfdc_click`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sfdc_click"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}