Schema Info

Schema Name: sfdl_test_rds.random_userdata_1_pq

created: 2022-05-23 17:02:00
disabled: False
format: raw
id: 1800
is_partitioned: False
is_schema_datatyped: False

name:

{
    "database": "sfdl_test_rds",
    "table": "random_userdata_1_pq"
}

type: rds

Schema Versions: 2

Version 4689200

created: 2022-05-24 12:44:20

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq"
]

hive_path: s3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23
id: 4689200
processed: 1

raw_data:

{
    "birthdate": "string",
    "cc": "string",
    "comments": "string",
    "country": "string",
    "email": "string",
    "first_name": "string",
    "gender": "string",
    "id": "int32",
    "ip_address": "string",
    "last_name": "string",
    "registration_dttm": "timestamp[ns]",
    "salary": "double",
    "title": "string"
}

schema_attributes:

{
    "birthdate": "string",
    "cc": "string",
    "comments": "string",
    "country": "string",
    "email": "string",
    "first_name": "string",
    "gender": "string",
    "id": "int",
    "ip_address": "string",
    "last_name": "string",
    "registration_dttm": "timestamp",
    "salary": "double",
    "title": "string"
}

schema_name_id: 1800
schema_scan_id: 5925338
updated: 2022-05-24 12:44:35

Version 4689199

created: 2022-05-24 12:08:08

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq"
]

hive_path: s3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23
id: 4689199
processed: 0

raw_data:

{
    "birthdate": "string",
    "cc": "string",
    "comments": "string",
    "country": "string",
    "email": "string",
    "first_name": "string",
    "gender": "string",
    "id": "int32",
    "ip_address": "string",
    "last_name": "string",
    "registration_dttm": "timestamp[ns]",
    "salary": "double",
    "title": "string"
}

schema_attributes:

{
    "birthdate": "string",
    "cc": "string",
    "comments": "string",
    "country": "string",
    "email": "string",
    "first_name": "string",
    "gender": "string",
    "id": "int",
    "ip_address": "string",
    "last_name": "string",
    "registration_dttm": "timestamp[ns]",
    "salary": "double",
    "title": "string"
}

schema_name_id: 1800
schema_scan_id: 5925285
updated: None

Schema Scans: 2

Last at 2022-05-24 12:44:13

Scan 5925338
- duration: 0:00:25.201782
- exit_message:
```
{
    "ddl_changed": true,
    "ingested_partitions": 0,
    "partitions_applied": false,
    "success": true
}
```
- id: 5925338
- payload:
```
{
    "datatype_dict": false,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": false,
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23",
        "key": "raw/random_datasets/userdata_1/2022-05-23/userdata1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.random_userdata_1_pq",
        "type": "rds"
    }
}
```
- running: False
- schema_name_id: 1800
- start_time: 2022-05-24 12:44:13
- success: True
- trace_id: 2982596475669719431

Scan 5925285

duration: 0:00:23.740994

exit_message:

{
    "exception": "failed to apply schema `Invalid ddl? `CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n` An error occurred (InvalidRequestException) when calling the StartQueryExecution operation: line 1:8: mismatched input 'EXTERNAL'. Expecting: 'OR', 'SCHEMA', 'TABLE', 'VIEW'`: ['CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`', 'DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_test_rds.random_userdata_1_pq`\\n(\\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \\n)\\nROW FORMAT SERDE\\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\\n \\nSTORED AS INPUTFORMAT\\n  'org.apache.hadoop.mapred.TextInputFormat'\\nOUTPUTFORMAT\\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\\nLOCATION\\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\\n\", 'MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq']\nTraceback (most recent call last):\n  File \"/src/athena-runner/athena_runner/runner.py\", line 93, in _run_single_query\n    query_id_response = self.client.start_query_execution(**athena_args)\n  File \"/usr/local/lib/python3.7/site-packages/botocore/client.py\", line 386, in _api_call\n    return self._make_api_call(operation_name, kwargs)\n  File \"/usr/local/lib/python3.7/site-packages/botocore/client.py\", line 705, in _make_api_call\n    raise error_class(parsed_response, operation_name)\nbotocore.errorfactory.InvalidRequestException: An error occurred (InvalidRequestException) when calling the StartQueryExecution operation: line 1:8: mismatched input 'EXTERNAL'. Expecting: 'OR', 'SCHEMA', 'TABLE', 'VIEW'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/schema_manager/schema_generator/table_generator.py\", line 24, in apply_latest_version\n    self.runner.run_multi_query(schema_version.ddl, timeout=DDLQueueWorker.TIMEOUT)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 133, in run_multi_query\n    result = self.run_single_query(query, timeout, database)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 51, in run_single_query\n    return self._run_single_query(query, timeout, database)\n  File \"/src/athena-runner/athena_runner/runner.py\", line 119, in _run_single_query\n    raise AthenaRunnerQueryException('Invalid ddl? `{}` {}'.format(query, e))\nathena_runner.exceptions.AthenaRunnerQueryException: Invalid ddl? `CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n` An error occurred (InvalidRequestException) when calling the StartQueryExecution operation: line 1:8: mismatched input 'EXTERNAL'. Expecting: 'OR', 'SCHEMA', 'TABLE', 'VIEW'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/schema_manager/schema_generator/schema_scanner.py\", line 102, in scan\n    response = service.run()\n  File \"/schema_manager/schema_generator/process_hive_table.py\", line 99, in run\n    response['ddl_changed'] = table_generator.run()\n  File \"/schema_manager/schema_generator/table_generator.py\", line 35, in run\n    self.apply_latest_version()\n  File \"/schema_manager/schema_generator/table_generator.py\", line 26, in apply_latest_version\n    raise Exception('failed to apply schema `{}`: {}'.format(e, schema_version.ddl))\nException: failed to apply schema `Invalid ddl? `CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n` An error occurred (InvalidRequestException) when calling the StartQueryExecution operation: line 1:8: mismatched input 'EXTERNAL'. Expecting: 'OR', 'SCHEMA', 'TABLE', 'VIEW'`: ['CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`', 'DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`', \"CREATE EXTERNAL TABLE IF NOT EXISTS\\n`sfdl_test_rds.random_userdata_1_pq`\\n(\\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp[ns] , `salary`  double , `title`  string \\n)\\nROW FORMAT SERDE\\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\\n \\nSTORED AS INPUTFORMAT\\n  'org.apache.hadoop.mapred.TextInputFormat'\\nOUTPUTFORMAT\\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\\nLOCATION\\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\\n\", 'MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq']\n: Expecting value: line 1 column 1 (char 0)"
}

id: 5925285

payload:

{
    "datatype_dict": null,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": false,
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23",
        "key": "raw/random_datasets/userdata_1/2022-05-23/userdata1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.random_userdata_1_pq",
        "type": "rds"
    }
}

running: False
schema_name_id: 1800
start_time: 2022-05-24 12:07:53
success: False
trace_id: 16115858325177331618

Partitions:

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

Schema:

attributes:

{
    "birthdate": "string",
    "cc": "string",
    "comments": "string",
    "country": "string",
    "email": "string",
    "first_name": "string",
    "gender": "string",
    "id": "int",
    "ip_address": "string",
    "last_name": "string",
    "registration_dttm": "timestamp",
    "salary": "double",
    "title": "string"
}

created: 2022-05-24 12:44:20

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`",
    "repair_table": "MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq"
}

Server:

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

Raw:

{
    "name": {
        "created": "2022-05-23 17:02:00",
        "disabled": false,
        "format": "raw",
        "id": 1800,
        "is_partitioned": false,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_test_rds",
            "table": "random_userdata_1_pq"
        },
        "type": "rds"
    },
    "partition": {
        "count": 0,
        "ddl": null,
        "name": null,
        "state": [],
        "type": null
    },
    "schema": {
        "attributes": {
            "birthdate": "string",
            "cc": "string",
            "comments": "string",
            "country": "string",
            "email": "string",
            "first_name": "string",
            "gender": "string",
            "id": "int",
            "ip_address": "string",
            "last_name": "string",
            "registration_dttm": "timestamp",
            "salary": "double",
            "title": "string"
        },
        "created": "2022-05-24 12:44:20",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.random_userdata_1_pq`\n(\n `birthdate`  string , `cc`  string , `comments`  string , `country`  string , `email`  string , `first_name`  string , `gender`  string , `id`  int , `ip_address`  string , `last_name`  string , `registration_dttm`  timestamp , `salary`  double , `title`  string \n)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/raw/random_datasets/userdata_1/2022-05-23'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_test_rds.random_userdata_1_pq`",
            "repair_table": "MSCK REPAIR TABLE sfdl_test_rds.random_userdata_1_pq"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}