thisisnic commented on a change in pull request #10141:
URL: https://github.com/apache/arrow/pull/10141#discussion_r625079599
##########
File path: r/tests/testthat/test-csv.R
##########
@@ -15,13 +15,101 @@
# specific language governing permissions and limitations
# under the License.
-context("CsvTableReader")
-
# Not all types round trip via CSV 100% identical by default
tbl <- example_data[, c("dbl", "lgl", "false", "chr")]
+tbl_no_dates <- tbl
# Add a date to test its parsing
tbl$date <- Sys.Date() + 1:10
+csv_file <- tempfile()
+
+test_that("Write a CSV file with header", {
+ tbl_out <- write_csv_arrow(tbl_no_dates, csv_file)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out, tbl_no_dates)
+
+ tbl_in <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in, tbl_no_dates)
+
+ skip("Doesn't yet work with date columns due to ARROW-12540")
+
+ tbl_out <- write_csv_arrow(tbl, csv_file)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out, tbl)
+
+ tbl_in <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in, tbl)
+})
+
+
+test_that("Write a CSV file with no header", {
+
+ tbl_out <- write_csv_arrow(tbl_no_dates, csv_file, include_header = FALSE)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out, tbl_no_dates)
+ tbl_in <- read_csv_arrow(csv_file, col_names = FALSE)
+
+ tbl_expected <- tbl_no_dates
+ names(tbl_expected) <- c("f0", "f1", "f2", "f3")
+
+ expect_identical(tbl_in, tbl_expected)
+
+ skip("Doesn't yet work with date columns due to ARROW-12540")
+
+ tbl_out <- write_csv_arrow(tbl, csv_file, include_header = FALSE)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out, tbl)
+ tbl_in <- read_csv_arrow(csv_file, col_names = FALSE)
+
+ tbl_expected <- tbl
+ names(tbl_expected) <- c("f0", "f1", "f2", "f3", "f4")
+
+ expect_identical(tbl_in, tbl_expected)
+})
+
+test_that("Write a CSV file with different batch sizes", {
+
+ tbl_out1 <- write_csv_arrow(tbl_no_dates, csv_file, batch_size = 1)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out1, tbl_no_dates)
+ tbl_in1 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in1, tbl_no_dates)
+
+ tbl_out2 <- write_csv_arrow(tbl_no_dates, csv_file, batch_size = 2)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out2, tbl_no_dates)
+ tbl_in2 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in2, tbl_no_dates)
+
+ tbl_out3 <- write_csv_arrow(tbl_no_dates, csv_file, batch_size = 12)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out3, tbl_no_dates)
+ tbl_in3 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in3, tbl_no_dates)
+
+ skip("Doesn't yet work with date columns due to ARROW-12540")
+
+ tbl_out1 <- write_csv_arrow(tbl, csv_file, batch_size = 1)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out1, tbl)
+ tbl_in1 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in1, tbl)
+
+ tbl_out2 <- write_csv_arrow(tbl, csv_file, batch_size = 2)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out2, tbl)
+ tbl_in2 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in2, tbl)
+
+ tbl_out3 <- write_csv_arrow(tbl, csv_file, batch_size = 12)
+ expect_true(file.exists(csv_file))
+ expect_identical(tbl_out3, tbl)
+ tbl_in3 <- read_csv_arrow(csv_file)
+ expect_identical(tbl_in3, tbl)
+
+})
+
+
Review comment:
Done
--
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:
[email protected]
