From 27b1571f862434e61af79dc9b933f44164fb089e Mon Sep 17 00:00:00 2001
From: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
Date: Fri, 26 Apr 2024 17:11:31 +0200
Subject: [PATCH] details section

---
 R/io_parquet.R         |  4 ++--
 man/IO_read_parquet.Rd | 24 +++++++++++++++++++++++-
 man/IO_scan_parquet.Rd |  2 +-
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/R/io_parquet.R b/R/io_parquet.R
index 3f525ede7..677b2e40d 100644
--- a/R/io_parquet.R
+++ b/R/io_parquet.R
@@ -16,7 +16,7 @@
 #' can be skipped from reading.
 #' @param storage_options Experimental. List of options necessary to scan
 #' parquet files from different cloud storage providers (GCP, AWS, Azure).
-#' See the @details section.
+#' See the 'Details' section.
 #' @rdname IO_scan_parquet
 #' @details
 #' ## Connecting to cloud providers
@@ -89,7 +89,7 @@ pl_scan_parquet = function(
 #' Read a parquet file
 #' @rdname IO_read_parquet
 #' @inherit pl_read_csv return
-#' @inheritParams pl_scan_parquet
+#' @inherit pl_scan_parquet params details
 #' @examplesIf requireNamespace("arrow", quietly = TRUE) && arrow::arrow_with_dataset() && arrow::arrow_with_parquet()
 #' temp_dir = tempfile()
 #' # Write a hive-style partitioned parquet dataset
diff --git a/man/IO_read_parquet.Rd b/man/IO_read_parquet.Rd
index e420363ea..991d85e46 100644
--- a/man/IO_read_parquet.Rd
+++ b/man/IO_read_parquet.Rd
@@ -47,7 +47,7 @@ the final DataFrame into contiguous memory chunks.}
 
 \item{storage_options}{Experimental. List of options necessary to scan
 parquet files from different cloud storage providers (GCP, AWS, Azure).
-See the @details section.}
+See the 'Details' section.}
 
 \item{use_statistics}{Use statistics in the parquet file to determine if pages
 can be skipped from reading.}
@@ -60,6 +60,28 @@ can be skipped from reading.}
 \description{
 Read a parquet file
 }
+\details{
+\subsection{Connecting to cloud providers}{
+
+Polars supports scanning parquet files from different cloud providers.
+The cloud providers currently supported are AWS, GCP, and Azure.
+The supported keys to pass to the \code{storage_options} argument can be found
+here:
+\itemize{
+\item \href{https://docs.rs/object_store/latest/object_store/aws/enum.AmazonS3ConfigKey.html}{aws}
+\item \href{https://docs.rs/object_store/latest/object_store/gcp/enum.GoogleConfigKey.html}{gcp}
+\item \href{https://docs.rs/object_store/latest/object_store/azure/enum.AzureConfigKey.html}{azure}
+}
+\subsection{Implementation details}{
+\itemize{
+\item Currently it is impossible to scan public parquet files from GCP without
+a valid service account. Be sure to always include a service account in the
+\code{storage_options} argument.
+}
+}
+
+}
+}
 \examples{
 \dontshow{if (requireNamespace("arrow", quietly = TRUE) && arrow::arrow_with_dataset() && arrow::arrow_with_parquet()) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
 temp_dir = tempfile()
diff --git a/man/IO_scan_parquet.Rd b/man/IO_scan_parquet.Rd
index 70bca6d5d..0cfcd0ccb 100644
--- a/man/IO_scan_parquet.Rd
+++ b/man/IO_scan_parquet.Rd
@@ -47,7 +47,7 @@ the final DataFrame into contiguous memory chunks.}
 
 \item{storage_options}{Experimental. List of options necessary to scan
 parquet files from different cloud storage providers (GCP, AWS, Azure).
-See the @details section.}
+See the 'Details' section.}
 
 \item{use_statistics}{Use statistics in the parquet file to determine if pages
 can be skipped from reading.}