Schemas dev - Schema Manager

Schema Name: sfdl_dev_firehose.services_compared_searches

created: 2018-08-23 12:31:40
disabled: False
format: raw
id: 1006
is_partitioned: True
is_schema_datatyped: False

name:

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

type: firehose

Schema Versions: 2

Version 2498889

created: 2018-08-23 16:07:50

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_firehose`",
    "DROP TABLE IF EXISTS `sfdl_dev_firehose.services_compared_searches`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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-dev/separated_dt/compared_searches'\n",
    "MSCK REPAIR TABLE sfdl_dev_firehose.services_compared_searches"
]

hive_path: s3://sfdl-firehose-services-dev/separated_dt/compared_searches
id: 2498889
processed: 1

raw_data:

{
    "_origin": "2018-08-23T21:07:42Z|separated_dt/compared_searches/dt=2018-08-23/compared_searches-dev-1-2018-08-23-21-06-36-bc5f02a6-5fc0-463c-a966-d4fc1e1f8666.gz|firehose-dev",
    "algorithm_1": "Distance",
    "algorithm_2": "HeavyMir",
    "algorithm_id_1": "25975b7f21dbd160d1.81569025",
    "algorithm_id_2": "67145b7f21dc52b505.79244760",
    "isoTimestamp": "2018-08-23T21:06:43+00:00",
    "job_id": "a7c82d49-a76b-40a4-bc7f-9001eb3ea57e",
    "object_name": "compared_searches",
    "sample_group": "userSearch",
    "source_search_id": "00375b5817275c0061.29922268",
    "timestamp": "20180823 21:06:43.6862"
}

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: 1006
schema_scan_id: 4085799
updated: 2018-08-23 16:08:01

Version 2491720

created: 2018-08-23 12:31:40

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_firehose`",
    "DROP TABLE IF EXISTS `sfdl_dev_firehose.services_compared_searches`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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 \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-dev/separated_dt/compared_searches'\n",
    "MSCK REPAIR TABLE sfdl_dev_firehose.services_compared_searches"
]

hive_path: s3://sfdl-firehose-services-dev/separated_dt/compared_searches
id: 2491720
processed: 1

raw_data:

{
    "algorithm_1": "Distance",
    "algorithm_2": "HeavyMir",
    "algorithm_id_1": "25bb5b7eef30b847b0.91188350",
    "algorithm_id_2": "11765b7eef31368f42.02555620",
    "isoTimestamp": "2018-08-23T17:30:31+00:00",
    "job_id": "b7f3a285-c5d4-40e2-9d31-f4d7c2b19826",
    "object_name": "compared_searches",
    "sample_group": "userSearch",
    "source_search_id": "00005b66498f300f92.02277583",
    "timestamp": "20180823 17:30:31.5566"
}

schema_attributes:

{
    "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: 1006
schema_scan_id: 4084684
updated: 2018-08-23 12:31:51

Schema Scans: 2

Last at 2018-08-23 16:07:50

Scan 4085799

duration: 0:00:14.718150

exit_message:

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

id: 4085799

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/",
        "name": "dt",
        "type": "string",
        "value": "2018-08-23"
    },
    "s3": {
        "bucket": "sfdl-firehose-services-dev",
        "hive_path": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches",
        "key": "separated_dt/compared_searches/dt=2018-08-23/compared_searches-dev-1-2018-08-23-21-06-36-bc5f02a6-5fc0-463c-a966-d4fc1e1f8666.gz"
    },
    "schema": {
        "name": "sfdl_dev_firehose.services_compared_searches",
        "type": "firehose"
    }
}

running: False
schema_name_id: 1006
start_time: 2018-08-23 16:07:50
success: True
trace_id: 2064408169159769712

Scan 4084684

duration: 0:00:13.826185

exit_message:

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

id: 4084684

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/",
        "name": "dt",
        "type": "string",
        "value": "2018-08-23"
    },
    "s3": {
        "bucket": "sfdl-firehose-services-dev",
        "hive_path": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches",
        "key": "separated_dt/compared_searches/dt=2018-08-23/compared_searches-dev-1-2018-08-23-17-30-27-08aa83a8-ed68-4b02-b2b7-202bb9350761.gz"
    },
    "schema": {
        "name": "sfdl_dev_firehose.services_compared_searches",
        "type": "firehose"
    }
}

running: False
schema_name_id: 1006
start_time: 2018-08-23 12:31:40
success: True
trace_id: 13829112188457606361

Partitions:

count: 2

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_firehose.services_compared_searches`\nADD\n\n\n PARTITION (dt='2018-08-23') location 's3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/'\n PARTITION (dt='2018-08-24') location 's3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-24/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 113391,
            "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/",
            "name": "dt",
            "value": "2018-08-23"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2018-08-23 12:31:40",
                "last_data": "2018-08-23 16:20:27"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 113526,
            "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-24/",
            "name": "dt",
            "value": "2018-08-24"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2018-08-24 08:41:56",
                "last_data": "2018-08-24 15:33:00"
            },
            "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: 2018-08-23 16:07:50

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_firehose`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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-dev/separated_dt/compared_searches'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_firehose.services_compared_searches`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_firehose.services_compared_searches"
}

Server:

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

Raw:

{
    "name": {
        "created": "2018-08-23 12:31:40",
        "disabled": false,
        "format": "raw",
        "id": 1006,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_firehose",
            "table": "services_compared_searches"
        },
        "type": "firehose"
    },
    "partition": {
        "count": 2,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_firehose.services_compared_searches`\nADD\n\n\n PARTITION (dt='2018-08-23') location 's3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/'\n PARTITION (dt='2018-08-24') location 's3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-24/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 113391,
                    "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-23/",
                    "name": "dt",
                    "value": "2018-08-23"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2018-08-23 12:31:40",
                        "last_data": "2018-08-23 16:20:27"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 113526,
                    "location": "s3://sfdl-firehose-services-dev/separated_dt/compared_searches/dt=2018-08-24/",
                    "name": "dt",
                    "value": "2018-08-24"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2018-08-24 08:41:56",
                        "last_data": "2018-08-24 15:33:00"
                    },
                    "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": "2018-08-23 16:07:50",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_firehose`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_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-dev/separated_dt/compared_searches'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_firehose.services_compared_searches`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_firehose.services_compared_searches"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info