Criar uma visualização autorizada

Criar uma visualização autorizada usando dados públicos do GitHub.

Mais informações

Para ver a documentação detalhada que inclui este exemplo de código, consulte:

Exemplo de código

Java

Antes de testar esta amostra, siga as instruções de configuração do Java no Guia de início rápido do BigQuery: como usar bibliotecas de cliente. Para mais informações, consulte a documentação de referência da API BigQuery em Java.

Para autenticar no BigQuery, configure o Application Default Credentials. Para mais informações, acesse Configurar a autenticação para bibliotecas de cliente. 

// Create a source dataset to store your table.
final Dataset sourceDataset = bigquery.create(DatasetInfo.of(sourceDatasetId));
// Populate a source table
String tableQuery =
    "SELECT commit, author, committer, repo_name"
        + " FROM `bigquery-public-data.github_repos.commits`"
        + " LIMIT 1000";
QueryJobConfiguration queryConfig =
    QueryJobConfiguration.newBuilder(tableQuery)
        .setDestinationTable(TableId.of(sourceDatasetId, sourceTableId))
        .build();
bigquery.query(queryConfig);
// Create a separate dataset to store your view
Dataset sharedDataset = bigquery.create(DatasetInfo.of(sharedDatasetId));
// Create the view in the new dataset
String viewQuery =
    String.format(
        "SELECT commit, author.name as author, "
            + "committer.name as committer, repo_name FROM %s.%s.%s",
        projectId, sourceDatasetId, sourceTableId);
ViewDefinition viewDefinition = ViewDefinition.of(viewQuery);
Table view =
    bigquery.create(TableInfo.of(TableId.of(sharedDatasetId, sharedViewId), viewDefinition));
// Assign access controls to the dataset containing the view
List<Acl> viewAcl = new ArrayList<>(sharedDataset.getAcl());
viewAcl.add(Acl.of(new Acl.Group("example-analyst-group@google.com"), Acl.Role.READER));
sharedDataset.toBuilder().setAcl(viewAcl).build().update();
// Authorize the view to access the source dataset
List<Acl> srcAcl = new ArrayList<>(sourceDataset.getAcl());
srcAcl.add(Acl.of(new Acl.View(view.getTableId())));
sourceDataset.toBuilder().setAcl(srcAcl).build().update();

Python

Antes de testar esta amostra, siga as instruções de configuração do Python no Guia de início rápido do BigQuery: como usar bibliotecas de cliente. Para mais informações, consulte a documentação de referência da API BigQuery em Python.

Para autenticar no BigQuery, configure o Application Default Credentials. Para mais informações, acesse Configurar a autenticação para bibliotecas de cliente. 

# Create a source dataset
from google.cloud import bigquery
from google.cloud.bigquery.enums import EntityTypes

client = bigquery.Client()
source_dataset_id = "github_source_data"
source_dataset_id_full = "{}.{}".format(client.project, source_dataset_id)


source_dataset = bigquery.Dataset(source_dataset_id_full)
# Specify the geographic location where the dataset should reside.
source_dataset.location = "US"
source_dataset = client.create_dataset(source_dataset)  # API request

# Populate a source table
source_table_id = "github_contributors"
job_config = bigquery.QueryJobConfig()
job_config.destination = source_dataset.table(source_table_id)
sql = """
    SELECT commit, author, committer, repo_name
    FROM `bigquery-public-data.github_repos.commits`
    LIMIT 1000
"""
client.query_and_wait(
    sql,
    # Location must match that of the dataset(s) referenced in the query
    # and of the destination table.
    location="US",
    job_config=job_config,
)  # API request - starts the query and waits for query to finish

# Create a separate dataset to store your view
shared_dataset_id = "shared_views"
shared_dataset_id_full = "{}.{}".format(client.project, shared_dataset_id)


shared_dataset = bigquery.Dataset(shared_dataset_id_full)
shared_dataset.location = "US"
shared_dataset = client.create_dataset(shared_dataset)  # API request

# Create the view in the new dataset
shared_view_id = "github_analyst_view"
view = bigquery.Table(shared_dataset.table(shared_view_id))
sql_template = """
    SELECT
        commit, author.name as author,
        committer.name as committer, repo_name
    FROM
        `{}.{}.{}`
"""
view.view_query = sql_template.format(
    client.project, source_dataset_id, source_table_id
)
view = client.create_table(view)  # API request

# Assign access controls to the dataset containing the view
# analyst_group_email = 'data_analysts@example.com'
access_entries = shared_dataset.access_entries
access_entries.append(
    bigquery.AccessEntry("READER", EntityTypes.GROUP_BY_EMAIL, analyst_group_email)
)
shared_dataset.access_entries = access_entries
shared_dataset = client.update_dataset(
    shared_dataset, ["access_entries"]
)  # API request

# Authorize the view to access the source dataset
access_entries = source_dataset.access_entries
access_entries.append(
    bigquery.AccessEntry(None, EntityTypes.VIEW, view.reference.to_api_repr())
)
source_dataset.access_entries = access_entries
source_dataset = client.update_dataset(
    source_dataset, ["access_entries"]
)  # API request

Terraform

Para saber como aplicar ou remover uma configuração do Terraform, consulte Comandos básicos do Terraform. Para mais informações, consulte a documentação de referência do provedor Terraform. 

# Creates an authorized view.

# Create a dataset to contain the view.
resource "google_bigquery_dataset" "view_dataset" {
  dataset_id  = "view_dataset"
  description = "Dataset that contains the view"
  location    = "us-west1"
}

# Create the view to authorize.
resource "google_bigquery_table" "movie_view" {
  project     = google_bigquery_dataset.view_dataset.project
  dataset_id  = google_bigquery_dataset.view_dataset.dataset_id
  table_id    = "movie_view"
  description = "View to authorize"

  view {
    query          = "SELECT item_id, avg(rating) FROM `movie_project.movie_dataset.movie_ratings` GROUP BY item_id ORDER BY item_id;"
    use_legacy_sql = false
  }
}


# Authorize the view to access the dataset
# that the query data originates from.
resource "google_bigquery_dataset_access" "view_authorization" {
  project    = "movie_project"
  dataset_id = "movie_dataset"

  view {
    project_id = google_bigquery_table.movie_view.project
    dataset_id = google_bigquery_table.movie_view.dataset_id
    table_id   = google_bigquery_table.movie_view.table_id
  }
}

# Specify the IAM policy for principals that can access
# the authorized view. These users should already
# have the roles/bigqueryUser role at the project level.
data "google_iam_policy" "principals_policy" {
  binding {
    role = "roles/bigquery.dataViewer"
    members = [
      "group:example-group@example.com",
    ]
  }
}

# Set the IAM policy on the authorized  view.
resource "google_bigquery_table_iam_policy" "authorized_view_policy" {
  project     = google_bigquery_table.movie_view.project
  dataset_id  = google_bigquery_table.movie_view.dataset_id
  table_id    = google_bigquery_table.movie_view.table_id
  policy_data = data.google_iam_policy.principals_policy.policy_data
}

A seguir

Para pesquisar e filtrar exemplos de código de outros Google Cloud produtos, consulte a Google Cloud pesquisa de exemplos de código.