nealrichardson commented on a change in pull request #10780: URL: https://github.com/apache/arrow/pull/10780#discussion_r675127935
########## File path: r/R/duckdb.R ########## @@ -0,0 +1,117 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +#' Create a (virtual) DuckDB table from an Arrow object +#' +#' This will do the necessary configuration to create a (virtual) table in DuckDB +#' that is backed by the Arrow object given. No data is copied or modified until +#' `collect()` or `compute()` are called or a query is run against the table. +#' +#' The result is a dbplyr-compatible object that can be used in d(b)plyr pipelines. +#' +#' @param src the Arrow object (e.g. Dataset, Table) to use for the DuckDB table +#' @param con a DuckDB connection to use (default will create one and store it +#' in `options("arrow_duck_con")`) +#' @param table_name a name to use in DuckDB for this object. The default is a +#' unique string `"arrow_"` followed by numbers. +#' @param auto_disconnect should the table be automatically cleaned up when the +#' resulting object is removed (and garbage collected)? Default: `TRUE` +#' +#' @return A tbl of the new table in DuckDB +#' +#' @keywords internal +#' @name to_duckdb +NULL + +arrow_duck_connection <- function() { + con <- getOption("arrow_duck_con") + if (is.null(con) || !DBI::dbIsValid(con)) { + con <- DBI::dbConnect(duckdb::duckdb()) + # Use the same CPU count that the arrow library is set to + DBI::dbExecute(con, paste0("PRAGMA threads=", cpu_count())) + options(arrow_duck_con = con) + } + con +} + +# Adapted from dbplyr +unique_arrow_tablename <- function () { + i <- getOption("arrow_table_name", 0) + 1 + options(arrow_table_name = i) + sprintf("arrow_%03i", i) +} + +.alchemize_to_duckdb <- function( + src, + con = arrow_duck_connection(), + table_name = unique_arrow_tablename(), + auto_disconnect = TRUE) { + duckdb::duckdb_register_arrow(con, table_name, src) + + tbl <- tbl(con, table_name) + groups <- src$group + if (length(groups) > 0 && !is.null(groups)) { + tbl <- dplyr::group_by(tbl, !!rlang::sym(groups)) + } + + if (auto_disconnect) { + # this will add the correct connection disconnection when the tbl is gced. + # we should probably confirm that this use of src$disco is kosher. + tbl$src$disco <- duckdb_disconnector(con, table_name) + } + + tbl +} + +#' @rdname to_duckdb +#' @export +to_duckdb <- function(src, con, table_name, auto_disconnect) UseMethod("to_duckdb", src) + +#' @rdname to_duckdb +#' @export +to_duckdb.Dataset <- .alchemize_to_duckdb + +#' @rdname to_duckdb +#' @export +to_duckdb.Table <- .alchemize_to_duckdb + +#' @rdname to_duckdb +#' @export +to_duckdb.arrow_dplyr_query <- .alchemize_to_duckdb + +summarise_duck <- function(.data, ...) { Review comment: If this is all that summarize_duck does, we can just inline it in summarize.arrow_dplyr_query -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
