Schemas dev - Schema Manager

Schema Name: sfdl_dev_redshift.analytics_dwh_fact_impression

created: 2018-03-26 14:41:06
disabled: False
format: raw
id: 680
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_dev_redshift",
    "table": "analytics_dwh_fact_impression"
}

type: redshift

Schema Versions: 1

Version 4408197

created: 2018-09-10 23:09:12

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_impression`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_impression`\n(\n `audit_id`  bigint , `day_key`  int , `day`  date , `listing_impression_key`  bigint , `visitor_key`  bigint , `facility_key`  int , `search_key`  bigint , `time_of_search`  timestamp , `page_num`  int , `page_position`  int , `rank`  bigint , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'quote.delim' = '\"', 'escape.delim' = '\\\\', 'field.delim' = '\u0001')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_impression"
]

hive_path: s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression
id: 4408197
processed: 1

raw_data:

{
    "_origin": "11",
    "audit_id": "0",
    "day": "2",
    "day_key": "1",
    "facility_key": "5",
    "listing_impression_key": "3",
    "page_num": "8",
    "page_position": "9",
    "rank": "10",
    "search_key": "6",
    "time_of_search": "7",
    "visitor_key": "4"
}

schema_attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "day": "date",
    "day_key": "int",
    "facility_key": "int",
    "listing_impression_key": "bigint",
    "page_num": "int",
    "page_position": "int",
    "rank": "bigint",
    "search_key": "bigint",
    "time_of_search": "timestamp",
    "visitor_key": "bigint"
}

schema_name_id: 680
schema_scan_id: 4129807
updated: 2018-09-10 23:15:08

Schema Scans: 1

Last at 2018-09-10 23:09:12

Scan 4129807

duration: 0:06:21.943590

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 3178,
    "partitions_applied": false,
    "success": true
}

id: 4129807

payload:

{
    "datatype_dict": {
        "audit_id": "bigint",
        "day": "date",
        "day_key": "int",
        "facility_key": "int",
        "listing_impression_key": "bigint",
        "page_num": "int",
        "page_position": "int",
        "rank": "bigint",
        "search_key": "bigint",
        "time_of_search": "timestamp",
        "visitor_key": "bigint"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": false,
        "header_s3_object": {
            "bucket": "sfdl-redshift-analytics-dev",
            "key": "meta/dwh_fact_impression/2018-09-10/1536638939/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2018-09-09",
        "name": "dt",
        "type": "string",
        "value": "2018-09-09"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression",
        "key": "raw_incremental/dwh_fact_impression/dt=2018-09-09/fact_impression.dat000.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_dwh_fact_impression",
        "type": "redshift"
    }
}

running: False
schema_name_id: 680
start_time: 2018-09-10 23:09:12
success: True
trace_id: 13268378068987014682

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_redshift.analytics_dwh_fact_impression`\nADD\n\n\n PARTITION (dt='2024-05-12') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-12/'\n PARTITION (dt='2024-05-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-08-13/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 253954,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-12/",
            "name": "dt",
            "value": "2024-05-12"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-13 15:07:25",
                "last_data": "2024-05-13 15:07:25"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 254011,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-13/",
            "name": "dt",
            "value": "2024-05-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-14 06:05:31",
                "last_data": "2024-05-14 06:05:31"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 259701,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-08-13/",
            "name": "dt",
            "value": "2024-08-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-08-14 11:56:44",
                "last_data": "2024-08-14 11:56:44"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "day": "date",
    "day_key": "int",
    "facility_key": "int",
    "listing_impression_key": "bigint",
    "page_num": "int",
    "page_position": "int",
    "rank": "bigint",
    "search_key": "bigint",
    "time_of_search": "timestamp",
    "visitor_key": "bigint"
}

created: 2018-09-10 23:09:12

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_impression`\n(\n `audit_id`  bigint , `day_key`  int , `day`  date , `listing_impression_key`  bigint , `visitor_key`  bigint , `facility_key`  int , `search_key`  bigint , `time_of_search`  timestamp , `page_num`  int , `page_position`  int , `rank`  bigint , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'quote.delim' = '\"', 'escape.delim' = '\\\\', 'field.delim' = '\u0001')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_impression`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_impression"
}

Server:

hostname: schemamanager-5447774fc6-4w58v
name: schema_manager
process_start: 2026-04-02 21:43:44
sf_env: dev
version: 2427328685

Raw:

{
    "name": {
        "created": "2018-03-26 14:41:06",
        "disabled": false,
        "format": "raw",
        "id": 680,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_redshift",
            "table": "analytics_dwh_fact_impression"
        },
        "type": "redshift"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_redshift.analytics_dwh_fact_impression`\nADD\n\n\n PARTITION (dt='2024-05-12') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-12/'\n PARTITION (dt='2024-05-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-08-13/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 253954,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-12/",
                    "name": "dt",
                    "value": "2024-05-12"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-13 15:07:25",
                        "last_data": "2024-05-13 15:07:25"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 254011,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-05-13/",
                    "name": "dt",
                    "value": "2024-05-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-14 06:05:31",
                        "last_data": "2024-05-14 06:05:31"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 259701,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression/dt=2024-08-13/",
                    "name": "dt",
                    "value": "2024-08-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-08-14 11:56:44",
                        "last_data": "2024-08-14 11:56:44"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "audit_id": "bigint",
            "day": "date",
            "day_key": "int",
            "facility_key": "int",
            "listing_impression_key": "bigint",
            "page_num": "int",
            "page_position": "int",
            "rank": "bigint",
            "search_key": "bigint",
            "time_of_search": "timestamp",
            "visitor_key": "bigint"
        },
        "created": "2018-09-10 23:09:12",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_impression`\n(\n `audit_id`  bigint , `day_key`  int , `day`  date , `listing_impression_key`  bigint , `visitor_key`  bigint , `facility_key`  int , `search_key`  bigint , `time_of_search`  timestamp , `page_num`  int , `page_position`  int , `rank`  bigint , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'quote.delim' = '\"', 'escape.delim' = '\\\\', 'field.delim' = '\u0001')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_impression'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_impression`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_impression"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info