Schemas stage - Schema Manager

Schema Name: sfdl_stage_athena.explorations_marin_storagedc

created: 2024-01-19 06:13:05
disabled: False
format: raw
id: 2089
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_stage_athena",
    "table": "explorations_marin_storagedc"
}

type: athena

Schema Versions: 2

Version 658225

created: 2024-02-06 06:25:49

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_athena`",
    "DROP TABLE IF EXISTS `sfdl_stage_athena.explorations_marin_storagedc`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_athena.explorations_marin_storagedc`\n(\n `click_date`  string , `conv_date`  string , `keyword_id`  string , `creative_id`  string , `group_id`  string , `target_id`  string , `keyword`  string , `match_type`  string , `device`  string , `web_reservations_conv`  string , `web_reservations_rev`  string , `call_reservations_conv`  string , `call_reservations_rev`  string , `order_id`  string , `expected_rev_now`  string , `campaign_id`  string , `campaign_name`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = ',', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_athena.explorations_marin_storagedc"
]

hive_path: s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc
id: 658225
processed: 1

raw_data:

{
    "call_reservations_conv": 11,
    "call_reservations_rev": 12,
    "campaign_id": 15,
    "campaign_name": 16,
    "click_date": 0,
    "conv_date": 1,
    "creative_id": 3,
    "device": 8,
    "expected_rev_now": 14,
    "group_id": 4,
    "keyword": 6,
    "keyword_id": 2,
    "match_type": 7,
    "order_id": 13,
    "target_id": 5,
    "web_reservations_conv": 9,
    "web_reservations_rev": 10
}

schema_attributes:

{
    "call_reservations_conv": "string",
    "call_reservations_rev": "string",
    "campaign_id": "string",
    "campaign_name": "string",
    "click_date": "string",
    "conv_date": "string",
    "creative_id": "string",
    "device": "string",
    "expected_rev_now": "string",
    "group_id": "string",
    "keyword": "string",
    "keyword_id": "string",
    "match_type": "string",
    "order_id": "string",
    "target_id": "string",
    "web_reservations_conv": "string",
    "web_reservations_rev": "string"
}

schema_name_id: 2089
schema_scan_id: 5474467
updated: 2024-02-06 06:26:00

Version 650784

created: 2024-01-19 06:13:05

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_athena`",
    "DROP TABLE IF EXISTS `sfdl_stage_athena.explorations_marin_storagedc`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_athena.explorations_marin_storagedc`\n(\n `click_date`  string , `conv_date`  string , `keyword_id`  string , `creative_id`  string , `group_id`  string , `target_id`  string , `keyword`  string , `match_type`  string , `device`  string , `web_reservations_conv`  string , `web_reservations_rev`  string , `call_reservations_conv`  string , `call_reservations_rev`  string , `order_id`  string , `expected_rev_now`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = ',', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_athena.explorations_marin_storagedc"
]

hive_path: s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc
id: 650784
processed: 1

raw_data:

{
    "call_reservations_conv": 11,
    "call_reservations_rev": 12,
    "click_date": 0,
    "conv_date": 1,
    "creative_id": 3,
    "device": 8,
    "expected_rev_now": 14,
    "group_id": 4,
    "keyword": 6,
    "keyword_id": 2,
    "match_type": 7,
    "order_id": 13,
    "target_id": 5,
    "web_reservations_conv": 9,
    "web_reservations_rev": 10
}

schema_attributes:

{
    "call_reservations_conv": "string",
    "call_reservations_rev": "string",
    "click_date": "string",
    "conv_date": "string",
    "creative_id": "string",
    "device": "string",
    "expected_rev_now": "string",
    "group_id": "string",
    "keyword": "string",
    "keyword_id": "string",
    "match_type": "string",
    "order_id": "string",
    "target_id": "string",
    "web_reservations_conv": "string",
    "web_reservations_rev": "string"
}

schema_name_id: 2089
schema_scan_id: 5435136
updated: 2024-01-19 06:13:18

Schema Scans: 2

Last at 2024-02-06 06:25:49

Scan 5474467

duration: 0:00:14.044200

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 19,
    "partitions_applied": false,
    "success": true
}

id: 5474467

payload:

{
    "datatype_dict": null,
    "file_format": "csv",
    "file_properties": {
        "data_has_header_row": true
    },
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2024-02-05",
        "name": "dt",
        "type": "string",
        "value": "2024-02-05"
    },
    "s3": {
        "bucket": "sfdl-athena-explorations-stage",
        "hive_path": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc",
        "key": "raw_incremental/marin_storagedc/dt=2024-02-05/data.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_athena.explorations_marin_storagedc",
        "type": "athena"
    }
}

running: False
schema_name_id: 2089
start_time: 2024-02-06 06:25:49
success: True
trace_id: 702785574230078157

Scan 5435136

duration: 0:00:16.362919

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1,
    "partitions_applied": false,
    "success": true
}

id: 5435136

payload:

{
    "datatype_dict": null,
    "file_format": "csv",
    "file_properties": {
        "data_has_header_row": true
    },
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2024-01-18",
        "name": "dt",
        "type": "string",
        "value": "2024-01-18"
    },
    "s3": {
        "bucket": "sfdl-athena-explorations-stage",
        "hive_path": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc",
        "key": "raw_incremental/marin_storagedc/dt=2024-01-18/data.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_athena.explorations_marin_storagedc",
        "type": "athena"
    }
}

running: False
schema_name_id: 2089
start_time: 2024-01-19 06:13:05
success: True
trace_id: 11819851804249850719

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_athena.explorations_marin_storagedc`\nADD\n\n\n PARTITION (dt='2025-05-24') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-24/'\n PARTITION (dt='2025-05-25') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-25/'\n PARTITION (dt='2025-05-26') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-26/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 625356,
            "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-24/",
            "name": "dt",
            "value": "2025-05-24"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-05-25 11:41:05",
                "last_data": "2025-05-25 11:41:05"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 625493,
            "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-25/",
            "name": "dt",
            "value": "2025-05-25"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-05-26 11:43:51",
                "last_data": "2025-05-26 11:43:51"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 625628,
            "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-26/",
            "name": "dt",
            "value": "2025-05-26"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-05-27 11:40:52",
                "last_data": "2025-05-27 11:40:52"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "call_reservations_conv": "string",
    "call_reservations_rev": "string",
    "campaign_id": "string",
    "campaign_name": "string",
    "click_date": "string",
    "conv_date": "string",
    "creative_id": "string",
    "device": "string",
    "expected_rev_now": "string",
    "group_id": "string",
    "keyword": "string",
    "keyword_id": "string",
    "match_type": "string",
    "order_id": "string",
    "target_id": "string",
    "web_reservations_conv": "string",
    "web_reservations_rev": "string"
}

created: 2024-02-06 06:25:49

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_athena`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_athena.explorations_marin_storagedc`\n(\n `click_date`  string , `conv_date`  string , `keyword_id`  string , `creative_id`  string , `group_id`  string , `target_id`  string , `keyword`  string , `match_type`  string , `device`  string , `web_reservations_conv`  string , `web_reservations_rev`  string , `call_reservations_conv`  string , `call_reservations_rev`  string , `order_id`  string , `expected_rev_now`  string , `campaign_id`  string , `campaign_name`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = ',', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_athena.explorations_marin_storagedc`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_athena.explorations_marin_storagedc"
}

Server:

hostname: schemamanager-5c55c886bf-h2ts4
name: schema_manager
process_start: 2025-10-21 13:03:27
sf_env: stage
version: 2112174301

Raw:

{
    "name": {
        "created": "2024-01-19 06:13:05",
        "disabled": false,
        "format": "raw",
        "id": 2089,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_athena",
            "table": "explorations_marin_storagedc"
        },
        "type": "athena"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_athena.explorations_marin_storagedc`\nADD\n\n\n PARTITION (dt='2025-05-24') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-24/'\n PARTITION (dt='2025-05-25') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-25/'\n PARTITION (dt='2025-05-26') location 's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-26/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 625356,
                    "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-24/",
                    "name": "dt",
                    "value": "2025-05-24"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-05-25 11:41:05",
                        "last_data": "2025-05-25 11:41:05"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 625493,
                    "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-25/",
                    "name": "dt",
                    "value": "2025-05-25"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-05-26 11:43:51",
                        "last_data": "2025-05-26 11:43:51"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 625628,
                    "location": "s3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc/dt=2025-05-26/",
                    "name": "dt",
                    "value": "2025-05-26"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-05-27 11:40:52",
                        "last_data": "2025-05-27 11:40:52"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "call_reservations_conv": "string",
            "call_reservations_rev": "string",
            "campaign_id": "string",
            "campaign_name": "string",
            "click_date": "string",
            "conv_date": "string",
            "creative_id": "string",
            "device": "string",
            "expected_rev_now": "string",
            "group_id": "string",
            "keyword": "string",
            "keyword_id": "string",
            "match_type": "string",
            "order_id": "string",
            "target_id": "string",
            "web_reservations_conv": "string",
            "web_reservations_rev": "string"
        },
        "created": "2024-02-06 06:25:49",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_athena`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_athena.explorations_marin_storagedc`\n(\n `click_date`  string , `conv_date`  string , `keyword_id`  string , `creative_id`  string , `group_id`  string , `target_id`  string , `keyword`  string , `match_type`  string , `device`  string , `web_reservations_conv`  string , `web_reservations_rev`  string , `call_reservations_conv`  string , `call_reservations_rev`  string , `order_id`  string , `expected_rev_now`  string , `campaign_id`  string , `campaign_name`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = ',', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-athena-explorations-stage/raw_incremental/marin_storagedc'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_athena.explorations_marin_storagedc`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_athena.explorations_marin_storagedc"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}

Schema Info