Schemas prod - Schema Manager

Schema Name: sfdl_prod_firehose.services_compared_searches

created: 2018-08-29 05:58:28
disabled: False
format: raw
id: 526
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_prod_firehose",
    "table": "services_compared_searches"
}

type: firehose

Schema Versions: 1

Version 41908

created: 2018-08-29 05:58:28

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
    "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_compared_searches`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_compared_searches`\n(\n `algorithm_id_2`  string , `algorithm_id_1`  string , `job_id`  string , `timestamp`  string , `algorithm_1`  string , `isoTimestamp`  string , `algorithm_2`  string , `object_name`  string , `sample_group`  string , `source_search_id`  string , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/compared_searches'\n",
    "MSCK REPAIR TABLE sfdl_prod_firehose.services_compared_searches"
]

hive_path: s3://sfdl-firehose-services-prod/separated_dt/compared_searches
id: 41908
processed: 1

raw_data:

{
    "_origin": "2018-08-29T10:58:11Z|separated_dt/compared_searches/dt=2018-08-29/compared_searches-2-2018-08-29-10-57-53-39093851-497b-4717-a64c-2cd10e92086a.gz|firehose-prod",
    "algorithm_1": "DistanceOon",
    "algorithm_2": "SlidingMIRBand",
    "algorithm_id_1": "dd035b867c39d70bc6.62833464",
    "algorithm_id_2": "ace95b867c3a0d57d6.78133821",
    "isoTimestamp": "2018-08-29T05:58:02-05:00",
    "job_id": "b2bf5983-20ea-498c-a111-f31eae5860dc",
    "object_name": "compared_searches",
    "sample_group": "userSearch",
    "source_search_id": "00025b607325b5ca36.89041698",
    "timestamp": "20180829 05:58:02.1446"
}

schema_attributes:

{
    "_origin": "string",
    "algorithm_1": "string",
    "algorithm_2": "string",
    "algorithm_id_1": "string",
    "algorithm_id_2": "string",
    "isoTimestamp": "string",
    "job_id": "string",
    "object_name": "string",
    "sample_group": "string",
    "source_search_id": "string",
    "timestamp": "string"
}

schema_name_id: 526
schema_scan_id: 16478273
updated: 2018-08-29 05:58:40

Schema Scans: 1

Last at 2018-08-29 05:58:28

Scan 16478273

duration: 0:00:13.730392

exit_message:

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

id: 16478273

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2018-08-29/",
        "name": "dt",
        "type": "string",
        "value": "2018-08-29"
    },
    "s3": {
        "bucket": "sfdl-firehose-services-prod",
        "hive_path": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches",
        "key": "separated_dt/compared_searches/dt=2018-08-29/compared_searches-2-2018-08-29-10-57-53-39093851-497b-4717-a64c-2cd10e92086a.gz"
    },
    "schema": {
        "name": "sfdl_prod_firehose.services_compared_searches",
        "type": "firehose"
    }
}

running: False
schema_name_id: 526
start_time: 2018-08-29 05:58:28
success: True
trace_id: 7637634755070948081

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_prod_firehose.services_compared_searches`\nADD\n\n\n PARTITION (dt='2019-06-06') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-06/'\n PARTITION (dt='2019-06-07') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-07/'\n PARTITION (dt='2019-12-10') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-12-10/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 426940,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-06/",
            "name": "dt",
            "value": "2019-06-06"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-06-06 00:04:18",
                "last_data": "2019-06-06 02:12:55"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 427084,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-07/",
            "name": "dt",
            "value": "2019-06-07"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-06-07 00:04:33",
                "last_data": "2019-06-07 01:59:32"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 456053,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-12-10/",
            "name": "dt",
            "value": "2019-12-10"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2019-12-10 13:37:07",
                "last_data": "2019-12-10 15:01:41"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "algorithm_1": "string",
    "algorithm_2": "string",
    "algorithm_id_1": "string",
    "algorithm_id_2": "string",
    "isoTimestamp": "string",
    "job_id": "string",
    "object_name": "string",
    "sample_group": "string",
    "source_search_id": "string",
    "timestamp": "string"
}

created: 2018-08-29 05:58:28

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_compared_searches`\n(\n `algorithm_id_2`  string , `algorithm_id_1`  string , `job_id`  string , `timestamp`  string , `algorithm_1`  string , `isoTimestamp`  string , `algorithm_2`  string , `object_name`  string , `sample_group`  string , `source_search_id`  string , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/compared_searches'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_compared_searches`",
    "repair_table": "MSCK REPAIR TABLE sfdl_prod_firehose.services_compared_searches"
}

Server:

hostname: schemamanager-5475496c57-7dpqb
name: schema_manager
process_start: 2026-01-09 11:27:47
sf_env: prod
version: 2112174301

Raw:

{
    "name": {
        "created": "2018-08-29 05:58:28",
        "disabled": false,
        "format": "raw",
        "id": 526,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_prod_firehose",
            "table": "services_compared_searches"
        },
        "type": "firehose"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_prod_firehose.services_compared_searches`\nADD\n\n\n PARTITION (dt='2019-06-06') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-06/'\n PARTITION (dt='2019-06-07') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-07/'\n PARTITION (dt='2019-12-10') location 's3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-12-10/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 426940,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-06/",
                    "name": "dt",
                    "value": "2019-06-06"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-06-06 00:04:18",
                        "last_data": "2019-06-06 02:12:55"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 427084,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-06-07/",
                    "name": "dt",
                    "value": "2019-06-07"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-06-07 00:04:33",
                        "last_data": "2019-06-07 01:59:32"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 456053,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/compared_searches/dt=2019-12-10/",
                    "name": "dt",
                    "value": "2019-12-10"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2019-12-10 13:37:07",
                        "last_data": "2019-12-10 15:01:41"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "algorithm_1": "string",
            "algorithm_2": "string",
            "algorithm_id_1": "string",
            "algorithm_id_2": "string",
            "isoTimestamp": "string",
            "job_id": "string",
            "object_name": "string",
            "sample_group": "string",
            "source_search_id": "string",
            "timestamp": "string"
        },
        "created": "2018-08-29 05:58:28",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_compared_searches`\n(\n `algorithm_id_2`  string , `algorithm_id_1`  string , `job_id`  string , `timestamp`  string , `algorithm_1`  string , `isoTimestamp`  string , `algorithm_2`  string , `object_name`  string , `sample_group`  string , `source_search_id`  string , `_origin`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/compared_searches'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_compared_searches`",
            "repair_table": "MSCK REPAIR TABLE sfdl_prod_firehose.services_compared_searches"
        }
    },
    "server": {
        "hostname": "schemamanager-5475496c57-7dpqb",
        "name": "schema_manager",
        "process_start": "2026-01-09 11:27:47",
        "sf_env": "prod",
        "version": "2112174301"
    }
}

Schema Info