[アップデート] AWS Glue Data Catalog がビジネスコンテキストとセマンティック検索をサポートしたので試してみました（プレビュー）

% aws s3 mb s3://cm-datalake-20260622 --region us-east-1
make_bucket: cm-datalake-20260622

% aws glue create-database --region us-east-1 \
  --database-input '{"Name":"blog_demo","Description":"技術検証用"}'

% aws glue create-table --region us-east-1 --database-name blog_demo \
  --table-input '{
    "Name":"sales_transactions",
    "Description":"ユーザーごとの日次売上トランザクション",
    "TableType":"EXTERNAL_TABLE",
    "Parameters":{"classification":"csv","skip.header.line.count":"1"},
    "StorageDescriptor":{
      "Columns":[
        {"Name":"user_id","Type":"string"},
        {"Name":"login_date","Type":"date"},
        {"Name":"amount","Type":"double"}
      ],
      "Location":"s3://cm-datalake-20260622/sales_transactions/",
      "InputFormat":"org.apache.hadoop.mapred.TextInputFormat",
      "OutputFormat":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat",
      "SerdeInfo":{
        "SerializationLibrary":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe",
        "Parameters":{"field.delim":","}
      }
    }
  }'

% aws glue create-glossary --region us-east-1 \
  --name "enterprise_data_glossary" \
  --description "組織全体のデータ資産に関する標準化されたビジネス定義。"
{
    "Id": "5sbt95rvaddx2f",
    "Name": "enterprise_data_glossary",
    "Description": "組織全体のデータ資産に関する標準化されたビジネス定義。"
}

% aws glue create-glossary-term --region us-east-1 \
  --glossary-identifier "5sbt95rvaddx2f" \
  --name "Active User" \
  --short-description "直近30日のログインユーザー。" \
  --long-description "過去30日間に少なくとも1回ログインしたユーザー。"
{
    "Id": "bnm5ugtxv5kzvr",
    "GlossaryId": "5sbt95rvaddx2f",
    "Name": "Active User",
    "ShortDescription": "直近30日のログインユーザー。",
    "LongDescription": "過去30日間に少なくとも1回ログインしたユーザー。"
}

% aws glue associate-glossary-terms --region us-east-1 \
  --asset-identifier "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions" \
  --glossary-term-identifiers "bnm5ugtxv5kzvr"
{
    "AssetIdentifier": "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions",
    "GlossaryTerms": [
        "bnm5ugtxv5kzvr"
    ]
}

aws glue search --region us-east-1 --search-text "active users"

aws: [ERROR]: An error occurred (ParamValidation): argument operation: Found invalid choice 'search'

usage: aws [options] <command> <subcommand> [<subcommand> ...] [parameters]
To see help text, you can run:

  aws help
  aws <command> help
  aws <command> <subcommand> help

% aws glue search-assets --region us-east-1 --search-text "active users"
{
    "Items": [
        {
            "Id": "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions",
            "AssetName": "sales_transactions",
            "AssetDescription": "ユーザーごとの日次売上トランザクション",
            "UpdatedAt": "2026-06-22T22:26:02.452000+09:00",
            "AssetTypeId": "Table"
        }
    ]
}

%  aws glue search-assets --region us-east-1 --search-text "アクティブユーザー"
{
    "Items": []
}

% aws glue get-asset --region us-east-1 \
  --identifier "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions"
{
    "Id": "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions",
    "Name": "sales_transactions",
    "Description": "ユーザーごとの日次売上トランザクション",
    "CreatedAt": "2026-06-22T22:26:02.452000+09:00",
    "UpdatedAt": "2026-06-22T22:26:02.452000+09:00",
    "AssetTypeId": "amazon.glue::Table",
    "GlossaryTerms": [
        "bnm5ugtxv5kzvr"
    ],
    "Forms": {
        "amazon.glue::GlueTable": {
            "FormTypeId": "GlueTable",
            "Content": "{\"lakeFormationRegistration\":\"NotRegistered\",\"materializedViewStatus\":\"NotMaterializedView\",\"databaseName\":\"blog_demo\",\"serdeLibrary\":\"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe\",\"multiDialectViewStatus\":\"Disabled\",\"inputFormat\":\"org.apache.hadoop.mapred.TextInputFormat\",\"outputFormat\":\"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat\",\"retention\":0}"
        },
        "amazon::Table": {
            "FormTypeId": "Table",
            "Content": "{\"dataLocation\":\"s3://cm-datalake-20260622/sales_transactions/\",\"dataFormat\":\"csv\",\"type\":\"EXTERNAL_TABLE\"}"
        }
    },
    "Attachments": {},
    "IterableForms": {
        "columns": {
            "FormTypeId": "columns"
        }
    }
}

% aws glue search-assets --region us-east-1 \
  --search-text "active users" \
  --filter-clause '{"AttributeFilter":{"Attribute":"type","Operator":"equals","Value":{"StringValue":"Table"}}}' \
  --max-items 10

{
    "Items": [
        {
            "Id": "arn:aws:glue:us-east-1:123456789012:table/blog_demo/sales_transactions",
            "AssetName": "sales_transactions",
            "AssetDescription": "ユーザーごとの日次売上トランザクション",
            "UpdatedAt": "2026-06-22T22:26:02.452000+09:00",
            "AssetTypeId": "Table"
        }
    ]
}