GetTables 搭配 AWS SDK 或 CLI 使用

    /// <summary>
    /// Get a list of tables for an AWS Glue database.
    /// </summary>
    /// <param name="dbName">The name of the database.</param>
    /// <returns>A list of Table objects.</returns>
    public async Task<List<Table>> GetTablesAsync(string dbName)
    {
        var request = new GetTablesRequest { DatabaseName = dbName };
        var tables = new List<Table>();

        // Get a paginator for listing the tables.
        var tablePaginator = _amazonGlue.Paginators.GetTables(request);

        await foreach (var response in tablePaginator.Responses)
        {
            tables.AddRange(response.TableList);
        }

        return tables;
    }

        Aws::Client::ClientConfiguration clientConfig;
        // Optional: Set to the AWS Region in which the bucket was created (overrides config file).
        // clientConfig.region = "us-east-1";

    Aws::Glue::GlueClient client(clientConfig);

        Aws::Glue::Model::GetTablesRequest request;
        request.SetDatabaseName(CRAWLER_DATABASE_NAME);
        std::vector<Aws::Glue::Model::Table> all_tables;
        Aws::String nextToken; // Used for pagination.
        do {
            Aws::Glue::Model::GetTablesOutcome outcome = client.GetTables(request);

            if (outcome.IsSuccess()) {
                const std::vector<Aws::Glue::Model::Table> &tables = outcome.GetResult().GetTableList();
                all_tables.insert(all_tables.end(), tables.begin(), tables.end());
                nextToken = outcome.GetResult().GetNextToken();
            }
            else {
                std::cerr << "Error getting the tables. "
                          << outcome.GetError().GetMessage()
                          << std::endl;
                deleteAssets(CRAWLER_NAME, CRAWLER_DATABASE_NAME, "", bucketName,
                             clientConfig);
                return false;
            }
        } while (!nextToken.empty());

        std::cout << "The database contains " << all_tables.size()
                  << (all_tables.size() == 1 ?
                      " table." : "tables.") << std::endl;
        std::cout << "Here is a list of the tables in the database.";
        for (size_t index = 0; index < all_tables.size(); ++index) {
            std::cout << "    " << index + 1 << ":  " << all_tables[index].GetName()
                      << std::endl;
        }

        if (!all_tables.empty()) {
            int tableIndex = askQuestionForIntRange(
                    "Enter an index to display the database detail ",
                    1, static_cast<int>(all_tables.size()));
            std::cout << all_tables[tableIndex - 1].Jsonize().View().WriteReadable()
                      << std::endl;

            tableName = all_tables[tableIndex - 1].GetName();
        }

列出指定資料庫中部分或全部資料表的定義

下列 get-tables 範例會傳回指定資料庫中資料表的相關資訊。

aws glue get-tables --database-name 'tempdb'

輸出：

{
    "TableList": [
        {
            "Name": "my-s3-sink",
            "DatabaseName": "tempdb",
            "CreateTime": 1602730539.0,
            "UpdateTime": 1602730539.0,
            "Retention": 0,
            "StorageDescriptor": {
                "Columns": [
                    {
                        "Name": "sensorid",
                        "Type": "int"
                    },
                    {
                        "Name": "currenttemperature",
                        "Type": "int"
                    },
                    {
                        "Name": "status",
                        "Type": "string"
                    }
                ],
                "Location": "s3://janetst-bucket-01/test-s3-output/",
                "Compressed": false,
                "NumberOfBuckets": 0,
                "SerdeInfo": {
                    "SerializationLibrary": "org.openx.data.jsonserde.JsonSerDe"
                },
                "SortColumns": [],
                "StoredAsSubDirectories": false
            },
            "Parameters": {
                "classification": "json"
            },
            "CreatedBy": "arn:aws:iam::007436865787:user/JRSTERN",
            "IsRegisteredWithLakeFormation": false,
            "CatalogId": "007436865787"
        },
        {
            "Name": "s3-source",
            "DatabaseName": "tempdb",
            "CreateTime": 1602730658.0,
            "UpdateTime": 1602730658.0,
            "Retention": 0,
            "StorageDescriptor": {
                "Columns": [
                    {
                        "Name": "sensorid",
                        "Type": "int"
                    },
                    {
                        "Name": "currenttemperature",
                        "Type": "int"
                    },
                    {
                        "Name": "status",
                        "Type": "string"
                    }
                ],
                "Location": "s3://janetst-bucket-01/",
                "Compressed": false,
                "NumberOfBuckets": 0,
                "SortColumns": [],
                "StoredAsSubDirectories": false
            },
            "Parameters": {
                "classification": "json"
            },
            "CreatedBy": "arn:aws:iam::007436865787:user/JRSTERN",
            "IsRegisteredWithLakeFormation": false,
            "CatalogId": "007436865787"
        },
        {
            "Name": "test-kinesis-input",
            "DatabaseName": "tempdb",
            "CreateTime": 1601507001.0,
            "UpdateTime": 1601507001.0,
            "Retention": 0,
            "StorageDescriptor": {
                "Columns": [
                    {
                        "Name": "sensorid",
                        "Type": "int"
                    },
                    {
                        "Name": "currenttemperature",
                        "Type": "int"
                    },
                    {
                        "Name": "status",
                        "Type": "string"
                    }
                ],
                "Location": "my-testing-stream",
                "Compressed": false,
                "NumberOfBuckets": 0,
                "SerdeInfo": {
                    "SerializationLibrary": "org.openx.data.jsonserde.JsonSerDe"
                },
                "SortColumns": [],
                "Parameters": {
                    "kinesisUrl": "https://kinesis.us-east-1.amazonaws.com",
                    "streamName": "my-testing-stream",
                    "typeOfData": "kinesis"
                },
                "StoredAsSubDirectories": false
            },
            "Parameters": {
                "classification": "json"
            },
            "CreatedBy": "arn:aws:iam::007436865787:user/JRSTERN",
            "IsRegisteredWithLakeFormation": false,
            "CatalogId": "007436865787"
        }
    ]
}

如需詳細資訊，請參閱 Glue AWS 開發人員指南中的 Glue Data Catalog 中的定義資料表。 AWS

    /**
     * Retrieves the names of the tables in the specified Glue database.
     *
     * @param glueClient the Glue client to use for the operation
     * @param dbName     the name of the Glue database to retrieve the table names from
     * @return the name of the first table retrieved, or an empty string if no tables were found
     */
    public static String getGlueTables(GlueClient glueClient, String dbName) {
        String myTableName = "";
        try {
            GetTablesRequest tableRequest = GetTablesRequest.builder()
                .databaseName(dbName)
                .build();

            GetTablesResponse response = glueClient.getTables(tableRequest);
            List<Table> tables = response.tableList();
            if (tables.isEmpty()) {
                System.out.println("No tables were returned");
            } else {
                for (Table table : tables) {
                    myTableName = table.name();
                    System.out.println("Table name is: " + myTableName);
                }
            }

        } catch (GlueException e) {
            throw e;
        }
        return myTableName;
    }

const getTables = (databaseName) => {
  const client = new GlueClient({});

  const command = new GetTablesCommand({
    DatabaseName: databaseName,
  });

  return client.send(command);
};

        $databaseName = "doc-example-database-$uniqid";

        $tables = $glueService->getTables($databaseName);

    public function getTables($databaseName): Result
    {
        return $this->glueClient->getTables([
            'DatabaseName' => $databaseName,
        ]);
    }

class GlueWrapper:
    """Encapsulates AWS Glue actions."""

    def __init__(self, glue_client):
        """
        :param glue_client: A Boto3 Glue client.
        """
        self.glue_client = glue_client


    def get_tables(self, db_name):
        """
        Gets a list of tables in a Data Catalog database.

        :param db_name: The name of the database to query.
        :return: The list of tables in the database.
        """
        try:
            response = self.glue_client.get_tables(DatabaseName=db_name)
        except ClientError as err:
            logger.error(
                "Couldn't get tables %s. Here's why: %s: %s",
                db_name,
                err.response["Error"]["Code"],
                err.response["Error"]["Message"],
            )
            raise
        else:
            return response["TableList"]

# The `GlueWrapper` class serves as a wrapper around the AWS Glue API, providing a simplified interface for common operations.
# It encapsulates the functionality of the AWS SDK for Glue and provides methods for interacting with Glue crawlers, databases, tables, jobs, and S3 resources.
# The class initializes with a Glue client and a logger, allowing it to make API calls and log any errors or informational messages.
class GlueWrapper
  def initialize(glue_client, logger)
    @glue_client = glue_client
    @logger = logger
  end

  # Retrieves a list of tables in the specified database.
  #
  # @param db_name [String] The name of the database to retrieve tables from.
  # @return [Array<Aws::Glue::Types::Table>]
  def get_tables(db_name)
    response = @glue_client.get_tables(database_name: db_name)
    response.table_list
  rescue Aws::Glue::Errors::GlueException => e
    @logger.error("Glue could not get tables #{db_name}: \n#{e.message}")
    raise
  end

        let tables = glue
            .get_tables()
            .database_name(self.database())
            .send()
            .await
            .map_err(GlueMvpError::from_glue_sdk)?;

        let tables = tables.table_list();