jonkeane commented on code in PR #43634: URL: https://github.com/apache/arrow/pull/43634#discussion_r1720359278
########## r/tests/testthat/test-extra-package-roundtrip.R: ########## @@ -0,0 +1,108 @@ +# 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. + +skip_on_cran() + +# Any additional package that we test here that is not already in DESCRIPTION should be +# added to dev/tasks/r/github.linux.extra.packages.yml in the r-lib/actions/setup-r-dependencies@v2 +# step so that they are installed + available in that CI job. + +# So that we can force these in CI +load_or_skip <- function(pkg) { + if (identical(tolower(Sys.getenv("ARROW_R_FORCE_EXTRA_PACKAGE_TESTS")), "true")) { + # because of this indirection on the package name we also avoid a CHECK note and + # we don't otherwise need to Suggest this + requireNamespace(pkg, quietly = TRUE) + } else { + skip_if(!requireNamespace(pkg, quietly = TRUE)) + } + attachNamespace(pkg) +} + +library(tibble) + +test_that("readr read csvs roundtrip", { + load_or_skip("readr") + + tbl <- example_data[, c("dbl", "lgl", "false", "chr")] + + tf <- tempfile() + on.exit(unlink(tf)) + write.csv(tbl, tf, row.names = FALSE) + + # we should still be able to turn this into a table + new_df <- read_csv(tf, show_col_types = FALSE) + expect_equal(new_df, as_tibble(arrow_table(new_df))) + + # we should still be able to turn this into a table + new_df <- read_csv(tf, show_col_types = FALSE, lazy = TRUE) + expect_equal(new_df, as_tibble(arrow_table(new_df))) + + # and can roundtrip to a parquet file Review Comment: Yeah, you're right. When I first started this I did the roundtrip to parquet because `as.data.frame` doesn't attach all of the metadata (which makes sense, since it's expected to return a data.frame not some other thing!). I've switched this over to use `collect` which pulls things into R and then _also_ applies the right class(es). We might consider exporting some other function (in case folks aren't using dplyr otherwise) that rehydrates these objects. -- 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]
