[GitHub] [arrow] paleolimbot commented on a diff in pull request #13625: ARROW-16612: [R] Support inferring compression from filename for all readers/writers

[GitBox <gi...@apache.org>]

paleolimbot commented on code in PR #13625:
URL: https://github.com/apache/arrow/pull/13625#discussion_r927720953


##########
r/R/io.R:
##########
@@ -305,45 +284,36 @@ make_output_stream <- function(x, filesystem = NULL, compression = NULL) {
 
   if (inherits(x, "SubTreeFileSystem")) {
     filesystem <- x$base_fs
-    # SubTreeFileSystem adds a slash to base_path, but filesystems will reject file names
-    # with trailing slashes, so we need to remove it here.
-    x <- sub("/$", "", x$base_path)
+    # SubTreeFileSystem adds a slash to base_path, but filesystems will reject
+    # file names with trailing slashes, so we need to remove it here.
+    path <- sub("/$", "", x$base_path)
+    filesystem$OpenOutputStream(path)
   } else if (is_url(x)) {
     fs_and_path <- FileSystem$from_uri(x)
-    filesystem <- fs_and_path$fs
-    x <- fs_and_path$path
-  }
-
-  if (is.null(compression)) {
-    # Infer compression from sink
-    compression <- detect_compression(x)
-  }
-
-  assert_that(is.string(x))
-  if (is.null(filesystem) && is_compressed(compression)) {
-    CompressedOutputStream$create(x) ## compressed local
-  } else if (is.null(filesystem) && !is_compressed(compression)) {
-    FileOutputStream$create(x) ## uncompressed local
-  } else if (!is.null(filesystem) && is_compressed(compression)) {
-    CompressedOutputStream$create(filesystem$OpenOutputStream(x)) ## compressed remote
+    fs_and_path$fs$OpenOutputStream(fs_and_path$path)
   } else {
-    filesystem$OpenOutputStream(x) ## uncompressed remote
+    assert_that(is.string(x))
+    FileOutputStream$create(x)
   }
 }
 
 detect_compression <- function(path) {

Review Comment:
   If the .gz.parquet / .snappy.parquet naming convention is actually a thing, you could do
   
   ```r
   detect_internal_compression <- function(path, format) {
     if (detect_compression(path) != "uncompressed") warn("ignoring .whatever extension because that's not a thing")
     detect_compression(gsub(paste0("\\.", format, "$"), path)
   }
   ```



-- 
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: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org