ianmcook commented on a change in pull request #9521:
URL: https://github.com/apache/arrow/pull/9521#discussion_r581367505
##########
File path: r/R/dplyr.R
##########
@@ -309,8 +344,27 @@ collect.arrow_dplyr_query <- function(x, as_data_frame =
TRUE, ...) {
# See dataset.R for Dataset and Scanner(Builder) classes
Review comment:
I think it would be cleaner and more dplyr-like to define a `compute()`
method and put all the code for forcing computation of lazy ops there. Then we
could reserve `collect()` as strictly for the `as_data_frame = TRUE` case.
Unfortunately `dplyr::compute()` has a required `name` argument that I think
might throw a wrench in that?
##########
File path: r/tests/testthat/test-dplyr-mutate.R
##########
@@ -0,0 +1,311 @@
+# 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.
+
+library(dplyr)
+library(stringr)
+
+tbl <- example_data
+# Add some better string data
+tbl$verses <- verses[[1]]
+# c(" a ", " b ", " c ", ...) increasing padding
+# nchar = 3 5 7 9 11 13 15 17 19 21
+tbl$padded_strings <- stringr::str_pad(letters[1:10], width = 2*(1:10)+1, side
= "both")
+
+test_that("mutate() is lazy", {
+ expect_is(
+ tbl %>% record_batch() %>% mutate(int = int + 6L),
+ "arrow_dplyr_query"
+ )
+})
+
+test_that("basic mutate", {
+ expect_dplyr_equal(
+ input %>%
+ select(int, chr) %>%
+ filter(int > 5) %>%
+ mutate(int = int + 6L) %>%
+ collect(),
+ tbl
+ )
+})
+
+test_that("transmute", {
+ expect_dplyr_equal(
+ input %>%
+ select(int, chr) %>%
+ filter(int > 5) %>%
+ transmute(int = int + 6L) %>%
+ collect(),
+ tbl
+ )
+})
+
+test_that("mutate and refer to previous mutants", {
+ expect_dplyr_equal(
+ input %>%
+ select(int, padded_strings) %>%
+ mutate(
+ line_lengths = nchar(padded_strings),
+ longer = line_lengths * 10
+ ) %>%
+ filter(line_lengths > 15) %>%
+ collect(),
+ tbl
+ )
+})
+
+test_that("mutate with .data pronoun", {
+ expect_dplyr_equal(
+ input %>%
+ select(int, padded_strings) %>%
+ mutate(
+ line_lengths = nchar(padded_strings),
+ longer = .data$line_lengths * 10
+ ) %>%
+ filter(line_lengths > 15) %>%
+ collect(),
+ tbl
+ )
+})
+
+test_that("mutate with single value for recycling", {
+ skip("Not implemented (ARROW-11705")
Review comment:
The error happening here is different than what's happening in the
examples in ARROW-11705
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
