Schemas stage - Schema Manager

Schema Name: sfdl_stage_rds.ess_esscore_blog_posts

created: 2021-07-12 13:39:54
disabled: False
format: raw
id: 1050
is_partitioned: False
is_schema_datatyped: True

name:

{
    "database": "sfdl_stage_rds",
    "table": "ess_esscore_blog_posts"
}

type: rds

Schema Versions: 4

Version 550959

created: 2023-06-15 19:04:36

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
    "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2023-06-16/1686873875'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
]

hive_path: s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2023-06-16/1686873875
id: 550959
processed: 1

raw_data:

{
    "body": 5,
    "created_at": 6,
    "id": 0,
    "meta_description": 3,
    "meta_keywords": 4,
    "published_at": 2,
    "site_id": 10,
    "slug": 8,
    "summary": 9,
    "title": 1,
    "updated_at": 7
}

schema_attributes:

{
    "body": "string",
    "created_at": "timestamp",
    "id": "int",
    "meta_description": "string",
    "meta_keywords": "varchar(255)",
    "published_at": "timestamp",
    "site_id": "int",
    "slug": "varchar(255)",
    "summary": "string",
    "title": "varchar(255)",
    "updated_at": "timestamp"
}

schema_name_id: 1050
schema_scan_id: 4963497
updated: 2023-06-15 19:04:47

Version 402886

created: 2022-06-22 20:34:38

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
    "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-23/1655948076'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
]

hive_path: s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-23/1655948076
id: 402886
processed: 1

raw_data:

{
    "body": 5,
    "created_at": 6,
    "id": 0,
    "meta_description": 3,
    "meta_keywords": 4,
    "published_at": 2,
    "site_id": 10,
    "slug": 8,
    "summary": 9,
    "title": 1,
    "updated_at": 7
}

schema_attributes:

{
    "body": "string",
    "created_at": "timestamp",
    "id": "int",
    "meta_description": "string",
    "meta_keywords": "varchar(255)",
    "published_at": "timestamp",
    "site_id": "int",
    "slug": "varchar(255)",
    "summary": "string",
    "title": "varchar(255)",
    "updated_at": "timestamp"
}

schema_name_id: 1050
schema_scan_id: 3933454
updated: 2022-06-22 20:34:49

Version 402761

created: 2022-06-22 15:30:22

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
    "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-22/1655929820'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
]

hive_path: s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-22/1655929820
id: 402761
processed: 1

raw_data:

{
    "body": 5,
    "created_at": 6,
    "id": 0,
    "meta_description": 3,
    "meta_keywords": 4,
    "published_at": 2,
    "site_id": 10,
    "slug": 8,
    "summary": 9,
    "title": 1,
    "updated_at": 7
}

schema_attributes:

{
    "body": "string",
    "created_at": "timestamp",
    "id": "int",
    "meta_description": "string",
    "meta_keywords": "varchar(255)",
    "published_at": "timestamp",
    "site_id": "int",
    "slug": "varchar(255)",
    "summary": "string",
    "title": "varchar(255)",
    "updated_at": "timestamp"
}

schema_name_id: 1050
schema_scan_id: 3932788
updated: 2022-06-22 15:30:33

Version 341479

created: 2021-07-23 23:15:57

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
    "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2021-07-24/1627100155'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
]

hive_path: s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2021-07-24/1627100155
id: 341479
processed: 1

raw_data:

{
    "body": 5,
    "created_at": 6,
    "id": 0,
    "meta_description": 3,
    "meta_keywords": 4,
    "published_at": 2,
    "site_id": 10,
    "slug": 8,
    "summary": 9,
    "title": 1,
    "updated_at": 7
}

schema_attributes:

{
    "body": "string",
    "created_at": "timestamp",
    "id": "int",
    "meta_description": "string",
    "meta_keywords": "varchar(255)",
    "published_at": "timestamp",
    "site_id": "int",
    "slug": "varchar(255)",
    "summary": "string",
    "title": "varchar(255)",
    "updated_at": "timestamp"
}

schema_name_id: 1050
schema_scan_id: 3410502
updated: 2021-07-23 23:16:08

Schema Scans: 4

Last at 2023-06-15 19:04:36

Scan 4963497

duration: 0:00:11.164184

exit_message:

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

id: 4963497

payload:

{
    "datatype_dict": {
        "body": "string",
        "created_at": "timestamp",
        "id": "int",
        "meta_description": "string",
        "meta_keywords": "varchar(255)",
        "published_at": "timestamp",
        "site_id": "int",
        "slug": "varchar(255)",
        "summary": "string",
        "title": "varchar(255)",
        "updated_at": "timestamp"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "~"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-rds-ess-stage",
        "hive_path": "s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2023-06-16/1686873875",
        "key": "raw/esscore_blog_posts/2023-06-16/1686873875/split.ess_core.blog_posts0.dat.gz"
    },
    "schema": {
        "name": "sfdl_stage_rds.ess_esscore_blog_posts",
        "type": "rds"
    }
}

running: False
schema_name_id: 1050
start_time: 2023-06-15 19:04:36
success: True
trace_id: 1473919345972766910

Scan 3933454

duration: 0:00:13.785146

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 0,
    "partitions_applied": false,
    "success": true
}

id: 3933454

payload:

{
    "datatype_dict": {
        "body": "string",
        "created_at": "timestamp",
        "id": "int",
        "meta_description": "string",
        "meta_keywords": "varchar(255)",
        "published_at": "timestamp",
        "site_id": "int",
        "slug": "varchar(255)",
        "summary": "string",
        "title": "varchar(255)",
        "updated_at": "timestamp"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "~"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-rds-ess-stage",
        "hive_path": "s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-23/1655948076",
        "key": "raw/esscore_blog_posts/2022-06-23/1655948076/split.ess_core.blog_posts0.dat.gz"
    },
    "schema": {
        "name": "sfdl_stage_rds.ess_esscore_blog_posts",
        "type": "rds"
    }
}

running: False
schema_name_id: 1050
start_time: 2022-06-22 20:34:38
success: True
trace_id: 2425067882344216950

Scan 3932788

duration: 0:00:13.906044

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 0,
    "partitions_applied": false,
    "success": true
}

id: 3932788

payload:

{
    "datatype_dict": {
        "body": "string",
        "created_at": "timestamp",
        "id": "int",
        "meta_description": "string",
        "meta_keywords": "varchar(255)",
        "published_at": "timestamp",
        "site_id": "int",
        "slug": "varchar(255)",
        "summary": "string",
        "title": "varchar(255)",
        "updated_at": "timestamp"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "~"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-rds-ess-stage",
        "hive_path": "s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2022-06-22/1655929820",
        "key": "raw/esscore_blog_posts/2022-06-22/1655929820/split.ess_core.blog_posts0.dat.gz"
    },
    "schema": {
        "name": "sfdl_stage_rds.ess_esscore_blog_posts",
        "type": "rds"
    }
}

running: False
schema_name_id: 1050
start_time: 2022-06-22 15:30:22
success: True
trace_id: 6621147895455450381

Scan 3410502

duration: 0:00:14.013083

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 0,
    "partitions_applied": false,
    "success": true
}

id: 3410502

payload:

{
    "datatype_dict": {
        "body": "string",
        "created_at": "timestamp",
        "id": "int",
        "meta_description": "string",
        "meta_keywords": "varchar(255)",
        "published_at": "timestamp",
        "site_id": "int",
        "slug": "varchar(255)",
        "summary": "string",
        "title": "varchar(255)",
        "updated_at": "timestamp"
    },
    "file_format": "dat",
    "file_properties": {
        "data_has_header_row": true,
        "serde_properties": {
            "separatorChar": "~"
        }
    },
    "is_schema_datatyped": true,
    "s3": {
        "bucket": "sfdl-rds-ess-stage",
        "hive_path": "s3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2021-07-24/1627100155",
        "key": "raw/esscore_blog_posts/2021-07-24/1627100155/split.ess_core.blog_posts0.dat.gz"
    },
    "schema": {
        "name": "sfdl_stage_rds.ess_esscore_blog_posts",
        "type": "rds"
    }
}

running: False
schema_name_id: 1050
start_time: 2021-07-23 23:15:57
success: True
trace_id: 10649785710546284987

Partitions:

count: 0
ddl: None
name: None
state:
```
[]
```
type: None

Schema:

attributes:

{
    "body": "string",
    "created_at": "timestamp",
    "id": "int",
    "meta_description": "string",
    "meta_keywords": "varchar(255)",
    "published_at": "timestamp",
    "site_id": "int",
    "slug": "varchar(255)",
    "summary": "string",
    "title": "varchar(255)",
    "updated_at": "timestamp"
}

created: 2023-06-15 19:04:36

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2023-06-16/1686873875'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
}

Server:

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

Raw:

{
    "name": {
        "created": "2021-07-12 13:39:54",
        "disabled": false,
        "format": "raw",
        "id": 1050,
        "is_partitioned": false,
        "is_schema_datatyped": true,
        "name": {
            "database": "sfdl_stage_rds",
            "table": "ess_esscore_blog_posts"
        },
        "type": "rds"
    },
    "partition": {
        "count": 0,
        "ddl": null,
        "name": null,
        "state": [],
        "type": null
    },
    "schema": {
        "attributes": {
            "body": "string",
            "created_at": "timestamp",
            "id": "int",
            "meta_description": "string",
            "meta_keywords": "varchar(255)",
            "published_at": "timestamp",
            "site_id": "int",
            "slug": "varchar(255)",
            "summary": "string",
            "title": "varchar(255)",
            "updated_at": "timestamp"
        },
        "created": "2023-06-15 19:04:36",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_rds`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_rds.ess_esscore_blog_posts`\n(\n `id`  int , `title`  varchar(255) , `published_at`  timestamp , `meta_description`  string , `meta_keywords`  varchar(255) , `body`  string , `created_at`  timestamp , `updated_at`  timestamp , `slug`  varchar(255) , `summary`  string , `site_id`  int \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'\n WITH SERDEPROPERTIES ( 'field.delim' = '~', 'quote.delim' = '\"', 'escape.delim' = '\\\\')\nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-ess-stage/raw/esscore_blog_posts/2023-06-16/1686873875'\nTBLPROPERTIES ('skip.header.line.count' = '1')",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_rds.ess_esscore_blog_posts`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_rds.ess_esscore_blog_posts"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}

Schema Info