Schemas dev - Schema Manager

Schema Name: sfdl_dev_redshift.analytics_helper_visitor_status

created: 2018-05-03 12:25:02
disabled: False
format: raw
id: 906
is_partitioned: True
is_schema_datatyped: True

name:

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

type: redshift

Schema Versions: 3

Version 4708846

created: 2024-08-14 13:40:08

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_helper_visitor_status`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_helper_visitor_status`\n(\n `visitor_key`  bigint , `is_good_visitor`  int , `visitor_day_key`  int , `is_image_verified`  int , `is_filtered_ip`  int , `is_problem_visitor`  int , `is_bad_api_site_visitor`  int , `has_web_valid_res`  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/helper_visitor_status/2024-08-14/1723660745'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_helper_visitor_status"
]

hive_path: s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745
id: 4708846
processed: 1

raw_data:

{
    "_origin": "8",
    "has_web_valid_res": "7",
    "is_bad_api_site_visitor": "6",
    "is_filtered_ip": "4",
    "is_good_visitor": "1",
    "is_image_verified": "3",
    "is_problem_visitor": "5",
    "visitor_day_key": "2",
    "visitor_key": "0"
}

schema_attributes:

{
    "_origin": "string",
    "has_web_valid_res": "int",
    "is_bad_api_site_visitor": "int",
    "is_filtered_ip": "int",
    "is_good_visitor": "int",
    "is_image_verified": "int",
    "is_problem_visitor": "int",
    "visitor_day_key": "int",
    "visitor_key": "bigint"
}

schema_name_id: 906
schema_scan_id: 6565825
updated: 2024-08-14 13:40:25

Version 4705892

created: 2024-05-14 05:54:31

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_helper_visitor_status`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_helper_visitor_status`\n(\n `visitor_key`  bigint , `is_good_visitor`  int , `visitor_day_key`  int , `is_image_verified`  int , `is_filtered_ip`  int , `is_problem_visitor`  int , `is_bad_api_site_visitor`  int , `has_web_valid_res`  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/helper_visitor_status/2024-05-14/1715683964'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_helper_visitor_status"
]

hive_path: s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964
id: 4705892
processed: 1

raw_data:

{
    "_origin": "8",
    "has_web_valid_res": "7",
    "is_bad_api_site_visitor": "6",
    "is_filtered_ip": "4",
    "is_good_visitor": "1",
    "is_image_verified": "3",
    "is_problem_visitor": "5",
    "visitor_day_key": "2",
    "visitor_key": "0"
}

schema_attributes:

{
    "_origin": "string",
    "has_web_valid_res": "int",
    "is_bad_api_site_visitor": "int",
    "is_filtered_ip": "int",
    "is_good_visitor": "int",
    "is_image_verified": "int",
    "is_problem_visitor": "int",
    "visitor_day_key": "int",
    "visitor_key": "bigint"
}

schema_name_id: 906
schema_scan_id: 6490576
updated: 2024-05-14 05:54:50

Version 4705778

created: 2024-05-13 15:45:12

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_helper_visitor_status`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_helper_visitor_status`\n(\n `visitor_key`  bigint , `is_good_visitor`  int , `visitor_day_key`  int , `is_image_verified`  int , `is_filtered_ip`  int , `is_problem_visitor`  int , `is_bad_api_site_visitor`  int , `has_web_valid_res`  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/helper_visitor_status/2024-05-13/1715633028'\n",
    "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_helper_visitor_status"
]

hive_path: s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028
id: 4705778
processed: 1

raw_data:

{
    "_origin": "8",
    "has_web_valid_res": "7",
    "is_bad_api_site_visitor": "6",
    "is_filtered_ip": "4",
    "is_good_visitor": "1",
    "is_image_verified": "3",
    "is_problem_visitor": "5",
    "visitor_day_key": "2",
    "visitor_key": "0"
}

schema_attributes:

{
    "_origin": "string",
    "has_web_valid_res": "int",
    "is_bad_api_site_visitor": "int",
    "is_filtered_ip": "int",
    "is_good_visitor": "int",
    "is_image_verified": "int",
    "is_problem_visitor": "int",
    "visitor_day_key": "int",
    "visitor_key": "bigint"
}

schema_name_id: 906
schema_scan_id: 6490223
updated: 2024-05-13 15:45:31

Schema Scans: 3

Last at 2024-08-14 13:40:08

Scan 6565825

duration: 0:00:22.324025

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 181,
    "partitions_applied": false,
    "success": true
}

id: 6565825

payload:

{
    "datatype_dict": {
        "has_web_valid_res": "int",
        "is_bad_api_site_visitor": "int",
        "is_filtered_ip": "int",
        "is_good_visitor": "int",
        "is_image_verified": "int",
        "is_problem_visitor": "int",
        "origin_key": "varchar",
        "visitor_day_key": "int",
        "visitor_key": "bigint"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": false,
        "header_s3_object": {
            "bucket": "sfdl-redshift-analytics-dev",
            "key": "meta/helper_visitor_status/2024-08-14/1723660745/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13",
        "name": "dt",
        "type": "string",
        "value": "2024-08-13"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745",
        "key": "separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13/0003_part_00.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_helper_visitor_status",
        "type": "redshift"
    },
    "trace_context": {
        "parent_id": 12483237817040340776,
        "service_name": "redshift_unloads",
        "span_id": 10404570892480835826,
        "trace_id": 17109712464846186444
    }
}

running: False
schema_name_id: 906
start_time: 2024-08-14 13:40:08
success: True
trace_id: 17109712464846186444

Scan 6490576

duration: 0:00:26.613296

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 273,
    "partitions_applied": false,
    "success": true
}

id: 6490576

payload:

{
    "datatype_dict": {
        "has_web_valid_res": "int",
        "is_bad_api_site_visitor": "int",
        "is_filtered_ip": "int",
        "is_good_visitor": "int",
        "is_image_verified": "int",
        "is_problem_visitor": "int",
        "origin_key": "varchar",
        "visitor_day_key": "int",
        "visitor_key": "bigint"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": false,
        "header_s3_object": {
            "bucket": "sfdl-redshift-analytics-dev",
            "key": "meta/helper_visitor_status/2024-05-14/1715683964/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13",
        "name": "dt",
        "type": "string",
        "value": "2024-05-13"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964",
        "key": "separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13/0006_part_00.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_helper_visitor_status",
        "type": "redshift"
    },
    "trace_context": {
        "parent_id": 16156662288923001677,
        "service_name": "redshift_unloads",
        "span_id": 1093726690869912233,
        "trace_id": 4737539295351240124
    }
}

running: False
schema_name_id: 906
start_time: 2024-05-14 05:54:30
success: True
trace_id: 4737539295351240124

Scan 6490223

duration: 0:00:26.369718

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 272,
    "partitions_applied": false,
    "success": true
}

id: 6490223

payload:

{
    "datatype_dict": {
        "has_web_valid_res": "int",
        "is_bad_api_site_visitor": "int",
        "is_filtered_ip": "int",
        "is_good_visitor": "int",
        "is_image_verified": "int",
        "is_problem_visitor": "int",
        "origin_key": "varchar",
        "visitor_day_key": "int",
        "visitor_key": "bigint"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": false,
        "header_s3_object": {
            "bucket": "sfdl-redshift-analytics-dev",
            "key": "meta/helper_visitor_status/2024-05-13/1715633028/header.json"
        },
        "serde_properties": {
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12",
        "name": "dt",
        "type": "string",
        "value": "2024-05-12"
    },
    "s3": {
        "bucket": "sfdl-redshift-analytics-dev",
        "hive_path": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028",
        "key": "separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12/0003_part_00.gz"
    },
    "schema": {
        "name": "sfdl_dev_redshift.analytics_helper_visitor_status",
        "type": "redshift"
    },
    "trace_context": {
        "parent_id": 2937229591555988294,
        "service_name": "redshift_unloads",
        "span_id": 18151840149868286805,
        "trace_id": 7648763068307111328
    }
}

running: False
schema_name_id: 906
start_time: 2024-05-13 15:45:11
success: True
trace_id: 7648763068307111328

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_redshift.analytics_helper_visitor_status`\nADD\n\n\n PARTITION (dt='2024-05-12') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12/'\n PARTITION (dt='2024-05-13') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 253961,
            "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12/",
            "name": "dt",
            "value": "2024-05-12"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-13 15:45:12",
                "last_data": "2024-05-13 15:45:12"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 254010,
            "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13/",
            "name": "dt",
            "value": "2024-05-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-05-14 05:54:31",
                "last_data": "2024-05-14 05:54:31"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 259711,
            "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13/",
            "name": "dt",
            "value": "2024-08-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-08-14 13:40:08",
                "last_data": "2024-08-14 13:40:08"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "has_web_valid_res": "int",
    "is_bad_api_site_visitor": "int",
    "is_filtered_ip": "int",
    "is_good_visitor": "int",
    "is_image_verified": "int",
    "is_problem_visitor": "int",
    "visitor_day_key": "int",
    "visitor_key": "bigint"
}

created: 2024-08-14 13:40:08

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_helper_visitor_status`\n(\n `visitor_key`  bigint , `is_good_visitor`  int , `visitor_day_key`  int , `is_image_verified`  int , `is_filtered_ip`  int , `is_problem_visitor`  int , `is_bad_api_site_visitor`  int , `has_web_valid_res`  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/helper_visitor_status/2024-08-14/1723660745'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_helper_visitor_status`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_helper_visitor_status"
}

Server:

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

Raw:

{
    "name": {
        "created": "2018-05-03 12:25:02",
        "disabled": false,
        "format": "raw",
        "id": 906,
        "is_partitioned": true,
        "is_schema_datatyped": true,
        "name": {
            "database": "sfdl_dev_redshift",
            "table": "analytics_helper_visitor_status"
        },
        "type": "redshift"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_redshift.analytics_helper_visitor_status`\nADD\n\n\n PARTITION (dt='2024-05-12') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12/'\n PARTITION (dt='2024-05-13') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13/'\n PARTITION (dt='2024-08-13') location 's3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 253961,
                    "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-13/1715633028/dt=2024-05-12/",
                    "name": "dt",
                    "value": "2024-05-12"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-13 15:45:12",
                        "last_data": "2024-05-13 15:45:12"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 254010,
                    "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-05-14/1715683964/dt=2024-05-13/",
                    "name": "dt",
                    "value": "2024-05-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-05-14 05:54:31",
                        "last_data": "2024-05-14 05:54:31"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 259711,
                    "location": "s3://sfdl-redshift-analytics-dev/separated_dt/helper_visitor_status/2024-08-14/1723660745/dt=2024-08-13/",
                    "name": "dt",
                    "value": "2024-08-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-08-14 13:40:08",
                        "last_data": "2024-08-14 13:40:08"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "has_web_valid_res": "int",
            "is_bad_api_site_visitor": "int",
            "is_filtered_ip": "int",
            "is_good_visitor": "int",
            "is_image_verified": "int",
            "is_problem_visitor": "int",
            "visitor_day_key": "int",
            "visitor_key": "bigint"
        },
        "created": "2024-08-14 13:40:08",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_redshift`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_redshift.analytics_helper_visitor_status`\n(\n `visitor_key`  bigint , `is_good_visitor`  int , `visitor_day_key`  int , `is_image_verified`  int , `is_filtered_ip`  int , `is_problem_visitor`  int , `is_bad_api_site_visitor`  int , `has_web_valid_res`  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/helper_visitor_status/2024-08-14/1723660745'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_redshift.analytics_helper_visitor_status`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_redshift.analytics_helper_visitor_status"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info