Schemas dev - Schema Manager

Schema Name: sfdl_dev_redshift.analytics_dwh_fact_visitor

created: 2018-03-30 14:19:56
disabled: False
format: raw
id: 716
is_partitioned: True
is_schema_datatyped: False

name:

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

type: redshift

Schema Versions: 3

Version 4686139

created: 2021-09-13 14:49:41

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_visitor`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_visitor`\n(\n `audit_id`  bigint , `visitor_key`  bigint , `visit_time`  timestamp , `day_key`  int , `day`  date , `site_key`  int , `traffic_source_key`  int , `user_agent`  varchar(255) , `device_type`  varchar(10) , `ip_address`  varchar(20) , `campaign_key`  varchar(255) , `keyword_key`  varchar(255) , `content_key`  varchar(255) , `request_uri`  varchar(512) , `referrer`  varchar(512) , `referrer_site_op_id`  int , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\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_visitor'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_visitor"
]

hive_path: s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor
id: 4686139
processed: 1

raw_data:

{
    "_origin": "16",
    "audit_id": "0",
    "campaign_key": "10",
    "content_key": "12",
    "day": "4",
    "day_key": "3",
    "device_type": "8",
    "ip_address": "9",
    "keyword_key": "11",
    "referrer": "14",
    "referrer_site_op_id": "15",
    "request_uri": "13",
    "site_key": "5",
    "traffic_source_key": "6",
    "user_agent": "7",
    "visit_time": "2",
    "visitor_key": "1"
}

schema_attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "campaign_key": "varchar(255)",
    "content_key": "varchar(255)",
    "day": "date",
    "day_key": "int",
    "device_type": "varchar(10)",
    "ip_address": "varchar(20)",
    "keyword_key": "varchar(255)",
    "referrer": "varchar(512)",
    "referrer_site_op_id": "int",
    "request_uri": "varchar(512)",
    "site_key": "int",
    "traffic_source_key": "int",
    "user_agent": "varchar(255)",
    "visit_time": "timestamp",
    "visitor_key": "bigint"
}

schema_name_id: 716
schema_scan_id: 5832333
updated: 2021-09-13 14:52:16

Version 4685951

created: 2021-08-31 11:47:05

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_visitor`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_visitor`\n(\n `audit_id`  bigint , `visitor_key`  bigint , `visit_time`  timestamp , `day_key`  int , `day`  date , `site_key`  int , `traffic_source_key`  int , `user_agent`  varchar(255) , `device_type`  varchar(10) , `ip_address`  varchar(20) , `campaign_key`  varchar(255) , `keyword_key`  varchar(255) , `content_key`  varchar(255) , `request_uri`  varchar(512) , `referrer`  varchar(512) , `referrer_site_op_id`  int , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\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/separated_dt/dwh_fact_visitor/2021-08-31/1630427913'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_visitor"
]

hive_path: s3://sfdl-redshift-analytics-dev/separated_dt/dwh_fact_visitor/2021-08-31/1630427913
id: 4685951
processed: 1

raw_data:

{
    "_origin": "16",
    "audit_id": "0",
    "campaign_key": "10",
    "content_key": "12",
    "day": "4",
    "day_key": "3",
    "device_type": "8",
    "ip_address": "9",
    "keyword_key": "11",
    "referrer": "14",
    "referrer_site_op_id": "15",
    "request_uri": "13",
    "site_key": "5",
    "traffic_source_key": "6",
    "user_agent": "7",
    "visit_time": "2",
    "visitor_key": "1"
}

schema_attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "campaign_key": "varchar(255)",
    "content_key": "varchar(255)",
    "day": "date",
    "day_key": "int",
    "device_type": "varchar(10)",
    "ip_address": "varchar(20)",
    "keyword_key": "varchar(255)",
    "referrer": "varchar(512)",
    "referrer_site_op_id": "int",
    "request_uri": "varchar(512)",
    "site_key": "int",
    "traffic_source_key": "int",
    "user_agent": "varchar(255)",
    "visit_time": "timestamp",
    "visitor_key": "bigint"
}

schema_name_id: 716
schema_scan_id: 5829058
updated: 2021-08-31 11:49:50

Version 4684910

created: 2021-05-28 12:44:19

ddl:

[
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_visitor`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_dwh_fact_visitor`\n(\n `audit_id`  bigint , `visitor_key`  bigint , `visit_time`  timestamp , `day_key`  int , `day`  date , `site_key`  int , `traffic_source_key`  int , `user_agent`  varchar(255) , `device_type`  varchar(10) , `ip_address`  varchar(20) , `campaign_key`  varchar(255) , `keyword_key`  varchar(255) , `content_key`  varchar(255) , `request_uri`  varchar(512) , `referrer`  varchar(512) , `referrer_site_op_id`  int , `_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/separated_dt/dwh_fact_visitor/2021-05-28/1622222733'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_visitor"
]

hive_path: s3://sfdl-redshift-analytics-dev/separated_dt/dwh_fact_visitor/2021-05-28/1622222733
id: 4684910
processed: 1

raw_data:

{
    "_origin": "16",
    "audit_id": "0",
    "campaign_key": "10",
    "content_key": "12",
    "day": "4",
    "day_key": "3",
    "device_type": "8",
    "ip_address": "9",
    "keyword_key": "11",
    "referrer": "14",
    "referrer_site_op_id": "15",
    "request_uri": "13",
    "site_key": "5",
    "traffic_source_key": "6",
    "user_agent": "7",
    "visit_time": "2",
    "visitor_key": "1"
}

schema_attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "campaign_key": "varchar(255)",
    "content_key": "varchar(255)",
    "day": "date",
    "day_key": "int",
    "device_type": "varchar(10)",
    "ip_address": "varchar(20)",
    "keyword_key": "varchar(255)",
    "referrer": "varchar(512)",
    "referrer_site_op_id": "int",
    "request_uri": "varchar(512)",
    "site_key": "int",
    "traffic_source_key": "int",
    "user_agent": "varchar(255)",
    "visit_time": "timestamp",
    "visitor_key": "bigint"
}

schema_name_id: 716
schema_scan_id: None
updated: 2021-05-28 12:47:20

Schema Scans: 2

Last at 2021-09-13 14:49:41

Scan 5832333

duration: 0:02:40.614130

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 619,
    "partitions_applied": false,
    "success": true
}

id: 5832333

payload:

{
    "datatype_dict": {
        "audit_id": "bigint",
        "campaign_key": "varchar(255)",
        "content_key": "varchar(255)",
        "day": "date",
        "day_key": "int",
        "device_type": "varchar(10)",
        "ip_address": "varchar(20)",
        "keyword_key": "varchar(255)",
        "origin_key": "varchar",
        "referrer": "varchar(512)",
        "referrer_site_op_id": "int",
        "request_uri": "varchar(512)",
        "site_key": "int",
        "traffic_source_key": "int",
        "user_agent": "varchar(255)",
        "visit_time": "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_visitor/2021-09-13/1631561852/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2021-05-25",
        "name": "dt",
        "type": "string",
        "value": "2021-05-25"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor",
        "key": "raw_incremental/dwh_fact_visitor/dt=2021-05-25/0002_part_00.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_dwh_fact_visitor",
        "type": "redshift"
    },
    "trace_context": {
        "parent_id": 3513866088909262056,
        "service_name": "redshift_unloads",
        "span_id": 12082146333486774277,
        "trace_id": 123010239256910725
    }
}

running: False
schema_name_id: 716
start_time: 2021-09-13 14:49:41
success: True
trace_id: 123010239256910725

Scan 5829058

duration: 0:02:50.276508

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 632,
    "partitions_applied": false,
    "success": true
}

id: 5829058

payload:

{
    "datatype_dict": {
        "audit_id": "bigint",
        "campaign_key": "varchar(255)",
        "content_key": "varchar(255)",
        "day": "date",
        "day_key": "int",
        "device_type": "varchar(10)",
        "ip_address": "varchar(20)",
        "keyword_key": "varchar(255)",
        "origin_key": "varchar",
        "referrer": "varchar(512)",
        "referrer_site_op_id": "int",
        "request_uri": "varchar(512)",
        "site_key": "int",
        "traffic_source_key": "int",
        "user_agent": "varchar(255)",
        "visit_time": "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_visitor/2021-08-31/1630427913/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/separated_dt/dwh_fact_visitor/2021-08-31/1630427913/dt=2019-09-02",
        "name": "dt",
        "type": "string",
        "value": "2019-09-02"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/separated_dt/dwh_fact_visitor/2021-08-31/1630427913",
        "key": "separated_dt/dwh_fact_visitor/2021-08-31/1630427913/dt=2019-09-02/0000_part_00.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_dwh_fact_visitor",
        "type": "redshift"
    },
    "trace_context": {
        "parent_id": 10592918808620132518,
        "service_name": "redshift_unloads",
        "span_id": 12737314407043455327,
        "trace_id": 5496752020883762702
    }
}

running: False
schema_name_id: 716
start_time: 2021-08-31 11:47:05
success: True
trace_id: 5496752020883762702

Partitions:

count: 3

ddl:

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

name: dt

state:

[
    {
        "info": {
            "id": 253958,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-12/",
            "name": "dt",
            "value": "2024-05-12"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-13 15:27:06",
                "last_data": "2024-05-13 15:27:06"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 254012,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-13/",
            "name": "dt",
            "value": "2024-05-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-14 06:07:08",
                "last_data": "2024-05-14 06:07:08"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 259707,
            "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-08-13/",
            "name": "dt",
            "value": "2024-08-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-08-14 12:14:50",
                "last_data": "2024-08-14 12:14:50"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "audit_id": "bigint",
    "campaign_key": "varchar(255)",
    "content_key": "varchar(255)",
    "day": "date",
    "day_key": "int",
    "device_type": "varchar(10)",
    "ip_address": "varchar(20)",
    "keyword_key": "varchar(255)",
    "referrer": "varchar(512)",
    "referrer_site_op_id": "int",
    "request_uri": "varchar(512)",
    "site_key": "int",
    "traffic_source_key": "int",
    "user_agent": "varchar(255)",
    "visit_time": "timestamp",
    "visitor_key": "bigint"
}

created: 2021-09-13 14:49:41

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_visitor`\n(\n `audit_id`  bigint , `visitor_key`  bigint , `visit_time`  timestamp , `day_key`  int , `day`  date , `site_key`  int , `traffic_source_key`  int , `user_agent`  varchar(255) , `device_type`  varchar(10) , `ip_address`  varchar(20) , `campaign_key`  varchar(255) , `keyword_key`  varchar(255) , `content_key`  varchar(255) , `request_uri`  varchar(512) , `referrer`  varchar(512) , `referrer_site_op_id`  int , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\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_visitor'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_visitor`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_visitor"
}

Server:

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

Raw:

{
    "name": {
        "created": "2018-03-30 14:19:56",
        "disabled": false,
        "format": "raw",
        "id": 716,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_redshift",
            "table": "analytics_dwh_fact_visitor"
        },
        "type": "redshift"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_redshift.analytics_dwh_fact_visitor`\nADD\n\n\n PARTITION (dt='2024-05-12') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-12/'\n PARTITION (dt='2024-05-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-08-13/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 253958,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-12/",
                    "name": "dt",
                    "value": "2024-05-12"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-13 15:27:06",
                        "last_data": "2024-05-13 15:27:06"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 254012,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-05-13/",
                    "name": "dt",
                    "value": "2024-05-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-14 06:07:08",
                        "last_data": "2024-05-14 06:07:08"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 259707,
                    "location": "s3://sfdl-redshift-analytics-dev/raw_incremental/dwh_fact_visitor/dt=2024-08-13/",
                    "name": "dt",
                    "value": "2024-08-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-08-14 12:14:50",
                        "last_data": "2024-08-14 12:14:50"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "audit_id": "bigint",
            "campaign_key": "varchar(255)",
            "content_key": "varchar(255)",
            "day": "date",
            "day_key": "int",
            "device_type": "varchar(10)",
            "ip_address": "varchar(20)",
            "keyword_key": "varchar(255)",
            "referrer": "varchar(512)",
            "referrer_site_op_id": "int",
            "request_uri": "varchar(512)",
            "site_key": "int",
            "traffic_source_key": "int",
            "user_agent": "varchar(255)",
            "visit_time": "timestamp",
            "visitor_key": "bigint"
        },
        "created": "2021-09-13 14:49:41",
        "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_visitor`\n(\n `audit_id`  bigint , `visitor_key`  bigint , `visit_time`  timestamp , `day_key`  int , `day`  date , `site_key`  int , `traffic_source_key`  int , `user_agent`  varchar(255) , `device_type`  varchar(10) , `ip_address`  varchar(20) , `campaign_key`  varchar(255) , `keyword_key`  varchar(255) , `content_key`  varchar(255) , `request_uri`  varchar(512) , `referrer`  varchar(512) , `referrer_site_op_id`  int , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\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_visitor'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_dwh_fact_visitor`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_dwh_fact_visitor"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info