Object Storage Service:Scalar search (Python SDK V2)

The following sample code shows how to enable the metadata management feature for a specified bucket. When you enable this feature for a bucket, OSS creates a metadata index library for the bucket and indexes the metadata of all objects in it. After the metadata index library is created, OSS performs Near Real-Time incremental scans on new files in the bucket and creates metadata indexes for these files.

import argparse
import alibabacloud_oss_v2 as oss

# Create a command-line parameter parser and add a description.
parser = argparse.ArgumentParser(description="open meta query sample")
# Add the required --region command-line parameter, which specifies the region where the bucket is located.
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
# Add the required --bucket command-line parameter, which specifies the name of the bucket to operate on.
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
# Add the optional --endpoint command-line parameter, which specifies the domain name to use when you access OSS.
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')

def main():
    # Parse command-line arguments.
    args = parser.parse_args()

    # Load authentication information from environment variables.
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # Use the default configurations provided by the SDK.
    cfg = oss.config.load_default()
    # Set the authentication information provider.
    cfg.credentials_provider = credentials_provider
    # Set the region based on command-line arguments.
    cfg.region = args.region
    # If an endpoint is provided, update the endpoint in the configuration.
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    # Create an OSS client.
    client = oss.Client(cfg)

    # Initiate a request to enable meta query.
    result = client.open_meta_query(oss.OpenMetaQueryRequest(
            bucket=args.bucket,
    ))

    # Print the status code and request ID of the request.
    print(f'status code: {result.status_code},'
          f' request id: {result.request_id},'
          )

# Call the main function when run as the main program.
if __name__ == "__main__":
    main()

The following sample code shows how to retrieve information about the metadata index library of a specified bucket.

import argparse
import alibabacloud_oss_v2 as oss

# Create a command-line parameter parser and add the necessary parameters.
parser = argparse.ArgumentParser(description="get meta query status sample")
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')

def main():
    # Parse command-line arguments.
    args = parser.parse_args()

    # Load credential information from environment variables.
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # Use the default configurations of the SDK.
    cfg = oss.config.load_default()
    # Set the credential provider to the one obtained from environment variables.
    cfg.credentials_provider = credentials_provider
    # Set the region where the OSS service is located.
    cfg.region = args.region
    # If an endpoint is provided, set a custom endpoint.
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    # Create an OSS client.
    client = oss.Client(cfg)

    # Call the get_meta_query_status method to obtain the metadata query status of the specified bucket.
    result = client.get_meta_query_status(oss.GetMetaQueryStatusRequest(
            bucket=args.bucket,
    ))

    # Print relevant information from the result, including the status code, request ID, creation time, update time, state, and phase.
    print(f'status code: {result.status_code},'
            f' request id: {result.request_id},'
            f' create time: {result.meta_query_status.create_time},'
            f' update time: {result.meta_query_status.update_time},'
            f' state: {result.meta_query_status.state},'
            f' phase: {result.meta_query_status.phase},'
    )

# Call the main function when the script is run directly.
if __name__ == "__main__":
    main()

The following sample code shows how to use the scalar search feature to query objects that meet specified conditions and list the object information based on a specified field and sorting method.

import argparse
import alibabacloud_oss_v2 as oss

# Create a command-line parameter parser to accept user input parameters.
parser = argparse.ArgumentParser(description="do meta query sample")
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')

def main():
    # Parse command-line arguments.
    args = parser.parse_args()

    # Load authentication information from environment variables.
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # Use the default configurations of the SDK.
    cfg = oss.config.load_default()
    # Set the authentication provider.
    cfg.credentials_provider = credentials_provider
    # Set the region based on the input parameters.
    cfg.region = args.region
    # If an endpoint is provided, update the endpoint in the configuration.
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    # Create an OSS client.
    client = oss.Client(cfg)

    # Execute the meta query operation.
    result = client.do_meta_query(oss.DoMetaQueryRequest(
            bucket=args.bucket,  # Specify the bucket to query.
            meta_query=oss.MetaQuery(  # Define the specific content of the query.
                aggregations=oss.MetaQueryAggregations(  # Define the aggregate operation.
                    aggregations=[  # Aggregation list.
                        oss.MetaQueryAggregation(  # First aggregation: calculate the total size.
                            field='Size',
                            operation='sum',
                        ),
                        oss.MetaQueryAggregation(  # Second aggregation: find the maximum value.
                            field='Size',
                            operation='max',
                        )
                    ],
                ),
                next_token='',  # Pagination token.
                max_results=80369,  # Maximum number of results to return.
                query='{"Field": "Size","Value": "1048576","Operation": "gt"}',  # Query condition.
                sort='Size',  # Sort field.
                order=oss.MetaQueryOrderType.DESC,  # Sort order.
            ),
    ))

    # Output the basic information of the query result.
    print(f'status code: {result.status_code},'
          f' request id: {result.request_id},'
          # The following commented out sections can be enabled as needed to obtain more detailed information.
          # f' files: {result.files},'
          # f' file: {result.files.file},'
          # f' file modified time: {result.files.file.file_modified_time},'
          # f' etag: {result.files.file.etag},'
          # f' server side encryption: {result.files.file.server_side_encryption},'
          # f' oss tagging count: {result.files.file.oss_tagging_count},'
          # f' oss tagging: {result.files.file.oss_tagging},'
          # f' key: {result.files.file.oss_tagging.taggings[0].key},'
          # f' value: {result.files.file.oss_tagging.taggings[0].value},'
          # f' key: {result.files.file.oss_tagging.taggings[1].key},'
          # f' value: {result.files.file.oss_tagging.taggings[1].value},'
          # f' oss user meta: {result.files.file.oss_user_meta},'
          # f' key: {result.files.file.oss_user_meta.user_metas[0].key},'
          # f' value: {result.files.file.oss_user_meta.user_metas[0].value},'
          # f' key: {result.files.file.oss_user_meta.user_metas[1].key},'
          # f' value: {result.files.file.oss_user_meta.user_metas[1].value},'
          # f' filename: {result.files.file.filename},'
          # f' size: {result.files.file.size},'
          # f' oss object type: {result.files.file.oss_object_type},'
          # f' oss storage class: {result.files.file.oss_storage_class},'
          # f' object acl: {result.files.file.object_acl},'
          # f' oss crc64: {result.files.file.oss_crc64},'
          # f' server side encryption customer algorithm: {result.files.file.server_side_encryption_customer_algorithm},'
          # f' aggregations: {result.aggregations},'
          f' field: {result.aggregations.aggregations[0].field},'
          f' operation: {result.aggregations.aggregations[0].operation},'
          f' field: {result.aggregations.aggregations[1].field},'
          f' operation: {result.aggregations.aggregations[1].operation},'
          f' next token: {result.next_token},'
    )

    # If file information exists, print the tags and user-defined metadata.
    if result.files:
        if result.files.file.oss_tagging.taggings:
            for r in result.files.file.oss_tagging.taggings:
                print(f'result: key: {r.key}, value: {r.value}')
        if result.files.file.oss_user_meta.user_metas:
            for r in result.files.file.oss_user_meta.user_metas:
                print(f'result: key: {r.key}, value: {r.value}')
    # Print the results of all aggregations.
    if result.aggregations.aggregations:
        for r in result.aggregations.aggregations:
            print(f'result: field: {r.field}, operation: {r.operation}')

if __name__ == "__main__":
    main()

The following sample code shows how to disable the metadata management feature for a specified bucket.

import argparse
import alibabacloud_oss_v2 as oss

# Create an ArgumentParser object to process command-line arguments.
parser = argparse.ArgumentParser(description="close meta query sample")
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')

def main():
    # Parse command-line arguments.
    args = parser.parse_args()

    # Load credential information from environment variables.
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # Use the default configurations of the SDK.
    cfg = oss.config.load_default()
    # Set the credential provider to the one obtained from environment variables.
    cfg.credentials_provider = credentials_provider
    # Set the region information in the configuration.
    cfg.region = args.region
    # If an endpoint is provided, set the endpoint in the configuration.
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    # Create an OSS client.
    client = oss.Client(cfg)

    # Call the close_meta_query method to disable the meta query feature for the specified bucket.
    result = client.close_meta_query(oss.CloseMetaQueryRequest(
            bucket=args.bucket,
    ))

    # Print the status code and request ID of the response.
    print(f'status code: {result.status_code}, request id: {result.request_id}')

# Call the main function when this script is run directly.
if __name__ == "__main__":
    main()