glue-catalog-table

Terraform module to provision AWS Glue Catalog Tables.

Usage

module "s3_bucket_source" {
  source  = "cloudposse/s3-bucket/aws"
  version = "2.0.3"

  acl                          = "private"
  versioning_enabled           = false
  force_destroy                = true
  allow_encrypted_uploads_only = true
  allow_ssl_requests_only      = true
  block_public_acls            = true
  block_public_policy          = true
  ignore_public_acls           = true
  restrict_public_buckets      = true

  attributes = ["source"]
  context    = module.this.context
}

module "glue_catalog_database" {
  source = "cloudposse/glue/aws//modules/glue-catalog-database"
  # Cloud Posse recommends pinning every module to a specific version
  # version     = "x.x.x"

  catalog_database_name        = "analytics"
  catalog_database_description = "Glue Catalog database using data located in an S3 bucket"
  location_uri                 = format("s3://%s", module.s3_bucket_source.bucket_id)

  context = module.this.context
}

module "glue_catalog_table" {
  source = "cloudposse/glue/aws//modules/glue-catalog-table"
  # Cloud Posse recommends pinning every module to a specific version
  # version     = "x.x.x"

  catalog_table_name        = "geo"
  catalog_table_description = "region/state/county Glue Catalog table"
  database_name             = module.glue_catalog_database.name

  parameters = {
    "lakeformation.aso.status" = true
    "classification"           = "parquet"
  }

  storage_descriptor = {
    # List of reducer grouping columns, clustering columns, and bucketing columns in the table
    bucket_columns = null
    # Configuration block for columns in the table
    columns = [
      {
        name = "county",
        type = "string"
      },
      {
        name = "state",
        type = "string"
      },
      {
        name = "region",
        type = "string"
      }
    ]
    # Whether the data in the table is compressed
    compressed = false
    # Input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format
    input_format = "org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat"
    # Physical location of the table. By default this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name
    location = format("s3://%s/geo",  module.s3_bucket_source.bucket_id)
    #  Must be specified if the table contains any dimension columns
    number_of_buckets = 0
    # Output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format
    output_format = "org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat"
    # Configuration block for serialization and deserialization ("SerDe") information
    ser_de_info = {
      # Map of initialization parameters for the SerDe, in key-value form
      parameters = {
        "serialization.format" = "1"
      }
      # Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
      serialization_library = "org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe"
    }
    # Whether the table data is stored in subdirectories
    stored_as_sub_directories = false
  }

  context = module.this.context
}

Requirements

Name	Version
terraform	>= 1.0
aws	>= 3.74.0

Providers

Name	Version
aws	>= 3.74.0

Modules

Name	Source	Version
this	cloudposse/label/null	0.25.0

Resources

Name	Type
aws_glue_catalog_table.this	resource

Inputs

Name	Description	Type	Default	Required
additional_tag_map	Additional key-value pairs to add to each map in tags_as_list_of_maps. Not added to tags or id. This is for some rare cases where resources want additional configuration of tags and therefore take a list of maps with tag key, value, and additional configuration.	map(string)	{}	no
attributes	ID element. Additional attributes (e.g. workers or cluster) to add to id, in the order they appear in the list. New attributes are appended to the end of the list. The elements of the list are joined by the delimiter and treated as a single ID element.	list(string)	[]	no
catalog_id	ID of the Glue Catalog and database to create the table in. If omitted, this defaults to the AWS Account ID plus the database name.	string	null	no
catalog_table_description	Description of the table.	string	null	no
catalog_table_name	Name of the table.	string	null	no
context	Single object for setting entire context at once. See description of individual variables for details. Leave string and numeric variables as null to use default value. Individual variable settings (non-null) override settings in context object, except for attributes, tags, and additional_tag_map, which are merged.	any	{ "additional_tag_map": {}, "attributes": [], "delimiter": null, "descriptor_formats": {}, "enabled": true, "environment": null, "id_length_limit": null, "label_key_case": null, "label_order": [], "label_value_case": null, "labels_as_tags": [ "unset" ], "name": null, "namespace": null, "regex_replace_chars": null, "stage": null, "tags": {}, "tenant": null }	no
database_name	Name of the metadata database where the table metadata resides.	string	n/a	yes
delimiter	Delimiter to be used between ID elements. Defaults to - (hyphen). Set to "" to use no delimiter at all.	string	null	no
descriptor_formats	Describe additional descriptors to be output in the descriptors output map. Map of maps. Keys are names of descriptors. Values are maps of the form {<br/> format = string<br/> labels = list(string)<br/>} (Type is any so the map values can later be enhanced to provide additional options.) format is a Terraform format string to be passed to the format() function. labels is a list of labels, in order, to pass to format() function. Label values will be normalized before being passed to format() so they will be identical to how they appear in id. Default is {} (descriptors output will be empty).	any	{}	no
enabled	Set to false to prevent the module from creating any resources	bool	null	no
environment	ID element. Usually used for region e.g. 'uw2', 'us-west-2', OR role 'prod', 'staging', 'dev', 'UAT'	string	null	no
id_length_limit	Limit id to this many characters (minimum 6). Set to 0 for unlimited length. Set to null for keep the existing setting, which defaults to 0. Does not affect id_full.	number	null	no
label_key_case	Controls the letter case of the tags keys (label names) for tags generated by this module. Does not affect keys of tags passed in via the tags input. Possible values: lower, title, upper. Default value: title.	string	null	no
label_order	The order in which the labels (ID elements) appear in the id. Defaults to ["namespace", "environment", "stage", "name", "attributes"]. You can omit any of the 6 labels ("tenant" is the 6th), but at least one must be present.	list(string)	null	no
label_value_case	Controls the letter case of ID elements (labels) as included in id, set as tag values, and output by this module individually. Does not affect values of tags passed in via the tags input. Possible values: lower, title, upper and none (no transformation). Set this to title and set delimiter to "" to yield Pascal Case IDs. Default value: lower.	string	null	no
labels_as_tags	Set of labels (ID elements) to include as tags in the tags output. Default is to include all labels. Tags with empty values will not be included in the tags output. Set to [] to suppress all generated tags. Notes: The value of the name tag, if included, will be the id, not the name. Unlike other null-label inputs, the initial setting of labels_as_tags cannot be changed in later chained modules. Attempts to change it will be silently ignored.	set(string)	[ "default" ]	no
name	ID element. Usually the component or solution name, e.g. 'app' or 'jenkins'. This is the only ID element not also included as a tag. The "name" tag is set to the full id string. There is no tag with the value of the name input.	string	null	no
namespace	ID element. Usually an abbreviation of your organization name, e.g. 'eg' or 'cp', to help ensure generated IDs are globally unique	string	null	no
owner	Owner of the table.	string	null	no
parameters	Properties associated with this table, as a map of key-value pairs.	map(string)	null	no
partition_index	Configuration block for a maximum of 3 partition indexes.	object({ index_name = string keys = list(string) })	null	no
partition_keys	Configuration block of columns by which the table is partitioned. Only primitive types are supported as partition keys.	map(any)	{}	no
regex_replace_chars	Terraform regular expression (regex) string. Characters matching the regex will be removed from the ID elements. If not set, "/[^a-zA-Z0-9-]/" is used to remove all characters other than hyphens, letters and digits.	string	null	no
retention	Retention time for the table.	number	null	no
stage	ID element. Usually used to indicate role, e.g. 'prod', 'staging', 'source', 'build', 'test', 'deploy', 'release'	string	null	no
storage_descriptor	Configuration block for information about the physical storage of this table.	any	null	no
table_type	Type of this table (EXTERNAL_TABLE, VIRTUAL_VIEW, etc.). While optional, some Athena DDL queries such as ALTER TABLE and SHOW CREATE TABLE will fail if this argument is empty.	string	null	no
tags	Additional tags (e.g. {'BusinessUnit': 'XYZ'}). Neither the tag keys nor the tag values will be modified by this module.	map(string)	{}	no
target_table	Configuration block of a target table for resource linking.	object({ catalog_id = string database_name = string name = string })	null	no
tenant	ID element _(Rarely used, not included by default)_. A customer identifier, indicating who this instance of a resource is for	string	null	no
view_expanded_text	If the table is a view, the expanded text of the view; otherwise null.	string	null	no
view_original_text	If the table is a view, the original text of the view; otherwise null.	string	null	no

Outputs

Name	Description
arn	Glue catalog table ARN
id	Glue catalog table ID
name	Glue catalog table name