Schemas dev - Schema Manager

Schema Name: sfdl_dev_segment.sepoc_test_message

created: 2020-12-15 16:22:19
disabled: False
format: raw
id: 1523
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_dev_segment",
    "table": "sepoc_test_message"
}

type: segment

Schema Versions: 1

Version 4684268

created: 2020-12-15 16:22:19

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_test_message`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_test_message`\n(\n`writeKey`STRING,`timestamp`STRING,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`version`STRING,`originalTimestamp`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`messageId`STRING,`_origin`STRING,`message`STRING,`type`STRING,`event`STRING,`channel`STRING,`sentAt`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-segment-sepoc-dev/separated_dt/test message'\n",
    "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_test_message"
]

hive_path: s3://sfdl-segment-sepoc-dev/separated_dt/test message
id: 4684268
processed: 1

raw_data:

{
    "_metadata": {
        "nodeVersion": "12.18.3"
    },
    "_origin": "2020-12-15T22:21:42Z|s3://sfdl-segment-sepoc-dev/segment-logs/vGNNKCe3kJAh37cnzoabXy/1607990400000/1608070526252.cbbd40dad261.fde281a.62d2e84f-bf1c-43ea-8a99-707d9247965f.gz|segment_separator:34",
    "channel": "server",
    "context": {
        "library": {
            "name": "analytics-node",
            "version": "3.4.0-beta.3"
        }
    },
    "event": "test message",
    "integrations": {},
    "message": "I hope this gets to the data lake",
    "messageId": "node-4a383f00ca7692e64d7e8dad1305982e-dd76405c-4fef-40e5-9ed0-3d3ef98a1d09",
    "originalTimestamp": "2020-12-15T21:31:52.917Z",
    "projectId": "vGNNKCe3kJAh37cnzoabXy",
    "receivedAt": "2020-12-15T21:31:53.161Z",
    "sentAt": "2020-12-15T21:31:52.918Z",
    "timestamp": "2020-12-15T21:31:53.160Z",
    "type": "track",
    "userId": "grandma",
    "version": 2,
    "writeKey": "cDNwuBcCR3LTKBVcGrQxnorQy7EnMUOr"
}

schema_attributes:

{
    "_origin": "string",
    "channel": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "event": "string",
    "message": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string",
    "writeKey": "string"
}

schema_name_id: 1523
schema_scan_id: 5736174
updated: 2020-12-15 16:22:33

Schema Scans: 1

Last at 2020-12-15 16:22:19

Scan 5736174

duration: 0:00:16.994907

exit_message:

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

id: 5736174

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "partition": {
        "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-15/",
        "name": "dt",
        "type": "string",
        "value": "2020-12-15"
    },
    "s3": {
        "bucket": "sfdl-segment-sepoc-dev",
        "hive_path": "s3://sfdl-segment-sepoc-dev/separated_dt/test message",
        "key": "separated_dt/test message/dt=2020-12-15/1608070526252.cbbd40dad261.fde281a.62d2e84f-bf1c-43ea-8a99-707d9247965f.gz.json.gz"
    },
    "schema": {
        "name": "sfdl_dev_segment.sepoc_test_message",
        "type": "segment"
    }
}

running: False
schema_name_id: 1523
start_time: 2020-12-15 16:22:19
success: True
trace_id: 6747914548572633479

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_dev_segment.sepoc_test_message`\nADD\n\n\n PARTITION (dt='2020-12-15') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-15/'\n PARTITION (dt='2020-12-18') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-18/'\n PARTITION (dt='2021-01-21') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2021-01-21/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 163208,
            "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-15/",
            "name": "dt",
            "value": "2020-12-15"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-12-15 16:22:19",
                "last_data": "2020-12-15 16:22:19"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 163356,
            "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-18/",
            "name": "dt",
            "value": "2020-12-18"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-12-18 15:29:09",
                "last_data": "2020-12-18 15:29:09"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    },
    {
        "info": {
            "id": 164341,
            "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2021-01-21/",
            "name": "dt",
            "value": "2021-01-21"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2021-01-20 21:16:08",
                "last_data": "2021-01-20 21:16:08"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": true
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "channel": "string",
    "context.library.name": "string",
    "context.library.version": "string",
    "event": "string",
    "message": "string",
    "messageId": "string",
    "originalTimestamp": "string",
    "projectId": "string",
    "receivedAt": "string",
    "sentAt": "string",
    "timestamp": "string",
    "type": "string",
    "userId": "string",
    "version": "string",
    "writeKey": "string"
}

created: 2020-12-15 16:22:19

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_test_message`\n(\n`writeKey`STRING,`timestamp`STRING,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`version`STRING,`originalTimestamp`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`messageId`STRING,`_origin`STRING,`message`STRING,`type`STRING,`event`STRING,`channel`STRING,`sentAt`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-segment-sepoc-dev/separated_dt/test message'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_test_message`",
    "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_test_message"
}

Server:

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

Raw:

{
    "name": {
        "created": "2020-12-15 16:22:19",
        "disabled": false,
        "format": "raw",
        "id": 1523,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_dev_segment",
            "table": "sepoc_test_message"
        },
        "type": "segment"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_dev_segment.sepoc_test_message`\nADD\n\n\n PARTITION (dt='2020-12-15') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-15/'\n PARTITION (dt='2020-12-18') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-18/'\n PARTITION (dt='2021-01-21') location 's3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2021-01-21/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 163208,
                    "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-15/",
                    "name": "dt",
                    "value": "2020-12-15"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-12-15 16:22:19",
                        "last_data": "2020-12-15 16:22:19"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 163356,
                    "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2020-12-18/",
                    "name": "dt",
                    "value": "2020-12-18"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-12-18 15:29:09",
                        "last_data": "2020-12-18 15:29:09"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            },
            {
                "info": {
                    "id": 164341,
                    "location": "s3://sfdl-segment-sepoc-dev/separated_dt/test message/dt=2021-01-21/",
                    "name": "dt",
                    "value": "2021-01-21"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2021-01-20 21:16:08",
                        "last_data": "2021-01-20 21:16:08"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": true
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "channel": "string",
            "context.library.name": "string",
            "context.library.version": "string",
            "event": "string",
            "message": "string",
            "messageId": "string",
            "originalTimestamp": "string",
            "projectId": "string",
            "receivedAt": "string",
            "sentAt": "string",
            "timestamp": "string",
            "type": "string",
            "userId": "string",
            "version": "string",
            "writeKey": "string"
        },
        "created": "2020-12-15 16:22:19",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_dev_segment`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_dev_segment.sepoc_test_message`\n(\n`writeKey`STRING,`timestamp`STRING,`projectId`STRING,`userId`STRING,`receivedAt`STRING,`version`STRING,`originalTimestamp`STRING,`context`struct<`library`:struct<`version`:STRING,`name`:STRING>>,`messageId`STRING,`_origin`STRING,`message`STRING,`type`STRING,`event`STRING,`channel`STRING,`sentAt`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-segment-sepoc-dev/separated_dt/test message'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_dev_segment.sepoc_test_message`",
            "repair_table": "MSCK REPAIR TABLE sfdl_dev_segment.sepoc_test_message"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info