jonkeane commented on a change in pull request #12030:
URL: https://github.com/apache/arrow/pull/12030#discussion_r779133978
##########
File path: r/tests/testthat/test-csv.R
##########
@@ -290,6 +292,50 @@ test_that("more informative error when reading a CSV with
headers and schema", {
)
})
+test_that("CSV reader works on files with non-UTF-8 encoding", {
+ strings <- c("a", "\u00e9", "\U0001f4a9")
+ file_string <- paste0(
+ "col1,col2\n",
+ paste(strings, 1:30, sep = ",", collapse = "\n")
+ )
+ file_bytes_utf16 <- iconv(
+ file_string,
+ from = Encoding(file_string),
+ to = "UTF-16LE",
+ toRaw = TRUE
+ )[[1]]
+
+ tf <- tempfile()
+ on.exit(unlink(tf))
+ con <- file(tf, open = "wb")
+ writeBin(file_bytes_utf16, con)
+ close(con)
+
+ fs <- LocalFileSystem$create()
+ reader <- CsvTableReader$create(
+ fs$OpenInputStream(tf),
+ read_options = CsvReadOptions$create(encoding = "UTF-16LE")
+ )
Review comment:
_nods_ I was wondering more if there is any sort of error / detection.
Altering your reprex below slightly, I see now we get binary columns out.
That's not the worst (and there's probably not a good way to detect and do
something differently with that reliably anyway):
``` r
library(arrow, warn.conflicts = FALSE)
# generate a data frame with funky characters
latin1_chars <- iconv(
# exclude the comma and control characters
list(as.raw(setdiff(c(38:126, 161:255), 44))),
"latin1", "UTF-8"
)
make_text_col <- function(chars,
chars_per_item_min = 1, chars_per_item_max = 20,
n_items = 20) {
choices <- unlist(strsplit(chars, ""))
text_col <- character(n_items)
for (i in seq_along(text_col)) {
text_col[i] <- paste0(
sample(
choices,
round(runif(1, chars_per_item_min, chars_per_item_max)),
replace = TRUE
),
collapse = ""
)
}
text_col
}
set.seed(1843)
n_items <- 1e6
df_latin1 <- data.frame(
n = 1:n_items,
latin1_chars = make_text_col(latin1_chars, n_items = n_items)
)
# now check the CSV reader
library(arrow, warn.conflicts = FALSE)
# make some files
tf_latin1_utf8 <- tempfile()
tf_latin1_latin1 <- tempfile()
readr::write_csv(df_latin1, tf_latin1_utf8)
readr::write_file(
iconv(list(readr::read_file_raw(tf_latin1_utf8)), "UTF-8", "latin1", toRaw
= TRUE)[[1]],
tf_latin1_latin1
)
fs <- LocalFileSystem$create()
reader <- CsvTableReader$create(
fs$OpenInputStream(tf_latin1_latin1)
)
tibble::as_tibble(reader$Read())
#> # A tibble: 1,000,000 × 2
#> n
latin1_chars
#> <int>
<arrw_bnr>
#> 1 1 be, 31, 4f, e3, d8, d4, 5c, f9, e9,
76, cd
#> 2 2 5c, ad, bf, ed,
62, dd
#> 3 3 fe, 63, ec, 48, c7, 37, 45, e1, 71, 6b, 77, ca, a4,
a6, 3b
#> 4 4 47, 2f, 67, cc, a9, e3, 51, b0, 38, 52, f8,
74, f3
#> 5 5
48
#> 6 6 7c, 47, 50, f4, e5, 49, cc, e3, 65, b7, 64, 61, b7, 64, 5d, 7a,
51, a1
#> 7 7 39, f8, f9,
c4, 70
#> 8 8 4f, 78,
65, b1
#> 9 9 fa, 71, 65, ff,
ed, ca
#> 10 10 6f, 26, f9, b8, 69, c9, 42, 64, a8, 39, 77,
7d, 58
#> # … with 999,990 more rows
```
<sup>Created on 2022-01-05 by the [reprex
package](https://reprex.tidyverse.org) (v2.0.1)</sup>
--
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]
