Schemas stage - Schema Manager

Schema Name: sfdl_stage_marin.sparefoot_fact_product_target

created: 2021-08-30 15:22:43
disabled: False
format: raw
id: 1169
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_stage_marin",
    "table": "sparefoot_fact_product_target"
}

type: marin

Schema Versions: 1

Version 353717

created: 2021-08-30 15:22:43

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_marin`",
    "DROP TABLE IF EXISTS `sfdl_stage_marin.sparefoot_fact_product_target`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_marin.sparefoot_fact_product_target`\n(\n `product_target_id`  string , `group_id`  string , `date`  string , `impressions`  string , `clicks`  string , `publisher_cost`  string , `avg_pos`  string , `avg_cpc`  string , `conversion_type_id`  string , `conversions`  string , `revenue`  string , `last_modified`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = '\u0001', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_marin.sparefoot_fact_product_target"
]

hive_path: s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target
id: 353717
processed: 1

raw_data:

{
    "avg_cpc": 7,
    "avg_pos": 6,
    "clicks": 4,
    "conversion_type_id": 8,
    "conversions": 9,
    "date": 2,
    "group_id": 1,
    "impressions": 3,
    "last_modified": 11,
    "product_target_id": 0,
    "publisher_cost": 5,
    "revenue": 10
}

schema_attributes:

{
    "avg_cpc": "string",
    "avg_pos": "string",
    "clicks": "string",
    "conversion_type_id": "string",
    "conversions": "string",
    "date": "string",
    "group_id": "string",
    "impressions": "string",
    "last_modified": "string",
    "product_target_id": "string",
    "publisher_cost": "string",
    "revenue": "string"
}

schema_name_id: 1169
schema_scan_id: 3486200
updated: 2021-08-30 15:26:10

Schema Scans: 1

Last at 2021-08-30 15:22:43

Scan 3486200

duration: 0:03:45.487117

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 851,
    "partitions_applied": false,
    "success": true
}

id: 3486200

payload:

{
    "datatype_dict": {
        "string": "string"
    },
    "file_format": "csv",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "quoteChar": "\"",
            "separatorChar": "\u0001"
        }
    },
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2021-08-30",
        "name": "dt",
        "type": "string",
        "value": "2021-08-30"
    },
    "s3": {
        "bucket": "sfdl-marin-sparefoot-stage",
        "hive_path": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target",
        "key": "raw_incremental/fact_product_target/dt=2021-08-30/fact_product_target.csv.gz"
    },
    "schema": {
        "name": "sfdl_stage_marin.sparefoot_fact_product_target",
        "type": "marin"
    },
    "trace_context": {
        "parent_id": 6608000530995777440,
        "service_name": "preloading",
        "span_id": 3849818807748112156,
        "trace_id": 13994411656030082082
    }
}

running: False
schema_name_id: 1169
start_time: 2021-08-30 15:22:43
success: True
trace_id: 13994411656030082082

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_marin.sparefoot_fact_product_target`\nADD\n\n\n PARTITION (dt='2025-02-19') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-19/'\n PARTITION (dt='2025-02-20') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-20/'\n PARTITION (dt='2025-02-21') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-21/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 606858,
            "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-19/",
            "name": "dt",
            "value": "2025-02-19"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-02-20 07:01:23",
                "last_data": "2025-02-20 07:01:23"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 606957,
            "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-20/",
            "name": "dt",
            "value": "2025-02-20"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-02-21 07:01:18",
                "last_data": "2025-02-21 07:01:18"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 607051,
            "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-21/",
            "name": "dt",
            "value": "2025-02-21"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2025-02-22 07:01:12",
                "last_data": "2025-02-22 07:01:12"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "avg_cpc": "string",
    "avg_pos": "string",
    "clicks": "string",
    "conversion_type_id": "string",
    "conversions": "string",
    "date": "string",
    "group_id": "string",
    "impressions": "string",
    "last_modified": "string",
    "product_target_id": "string",
    "publisher_cost": "string",
    "revenue": "string"
}

created: 2021-08-30 15:22:43

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_marin`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_marin.sparefoot_fact_product_target`\n(\n `product_target_id`  string , `group_id`  string , `date`  string , `impressions`  string , `clicks`  string , `publisher_cost`  string , `avg_pos`  string , `avg_cpc`  string , `conversion_type_id`  string , `conversions`  string , `revenue`  string , `last_modified`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = '\u0001', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_marin.sparefoot_fact_product_target`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_marin.sparefoot_fact_product_target"
}

Server:

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

Raw:

{
    "name": {
        "created": "2021-08-30 15:22:43",
        "disabled": false,
        "format": "raw",
        "id": 1169,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_stage_marin",
            "table": "sparefoot_fact_product_target"
        },
        "type": "marin"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_marin.sparefoot_fact_product_target`\nADD\n\n\n PARTITION (dt='2025-02-19') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-19/'\n PARTITION (dt='2025-02-20') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-20/'\n PARTITION (dt='2025-02-21') location 's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-21/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 606858,
                    "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-19/",
                    "name": "dt",
                    "value": "2025-02-19"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-02-20 07:01:23",
                        "last_data": "2025-02-20 07:01:23"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 606957,
                    "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-20/",
                    "name": "dt",
                    "value": "2025-02-20"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-02-21 07:01:18",
                        "last_data": "2025-02-21 07:01:18"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 607051,
                    "location": "s3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target/dt=2025-02-21/",
                    "name": "dt",
                    "value": "2025-02-21"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2025-02-22 07:01:12",
                        "last_data": "2025-02-22 07:01:12"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "avg_cpc": "string",
            "avg_pos": "string",
            "clicks": "string",
            "conversion_type_id": "string",
            "conversions": "string",
            "date": "string",
            "group_id": "string",
            "impressions": "string",
            "last_modified": "string",
            "product_target_id": "string",
            "publisher_cost": "string",
            "revenue": "string"
        },
        "created": "2021-08-30 15:22:43",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_marin`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_marin.sparefoot_fact_product_target`\n(\n `product_target_id`  string , `group_id`  string , `date`  string , `impressions`  string , `clicks`  string , `publisher_cost`  string , `avg_pos`  string , `avg_cpc`  string , `conversion_type_id`  string , `conversions`  string , `revenue`  string , `last_modified`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.OpenCSVSerde'\n WITH SERDEPROPERTIES ( 'separatorChar' = '\u0001', 'quoteChar' = '\"', 'escapeChar' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-marin-sparefoot-stage/raw_incremental/fact_product_target'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_marin.sparefoot_fact_product_target`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_marin.sparefoot_fact_product_target"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}

Schema Info