(arrow) branch main updated: Revert "GH-35806: [R] Improve error message for null type inference with sparse CSV data"

[thisisnic]

This is an automated email from the ASF dual-hosted git repository.

thisisnic pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git


The following commit(s) were added to refs/heads/main by this push:
     new 99d1304fc3 Revert "GH-35806: [R] Improve error message for null type 
inference with sparse CSV data"
99d1304fc3 is described below

commit 99d1304fc33c2ac72726091f0a0b2e99e7b962e8
Author: Nic Crane <thisis...@gmail.com>
AuthorDate: Thu Feb 19 09:25:37 2026 +0000

    Revert "GH-35806: [R] Improve error message for null type inference with 
sparse CSV data"
    
    This reverts commit c20a04a0bf3c4e437b7f6370342b2ba8314a4257.
---
 r/R/util.R                          | 15 ---------------
 r/tests/testthat/test-dataset-csv.R | 18 ------------------
 2 files changed, 33 deletions(-)

diff --git a/r/R/util.R b/r/R/util.R
index acbd39e203..c63e1ee545 100644
--- a/r/R/util.R
+++ b/r/R/util.R
@@ -196,21 +196,6 @@ repeat_value_as_array <- function(object, n) {
 }
 
 handle_csv_read_error <- function(msg, call, schema) {
-  # Handle null type inference issue with sparse data
-  if (grepl("conversion error to null", msg)) {
-    msg <- c(
-      msg,
-      i = paste(
-        "Column type was inferred as null because the first block of data",
-        "(default 1MB, set via `block_size` in read options) contained only",
-        "missing values. Try specifying the column types explicitly using the",
-        "`col_types` or `schema` argument."
-      )
-    )
-    abort(msg, call = call)
-  }
-
-  # Handle schema + header row issue
   if (grepl("conversion error", msg) && inherits(schema, "Schema")) {
     msg <- c(
       msg,
diff --git a/r/tests/testthat/test-dataset-csv.R 
b/r/tests/testthat/test-dataset-csv.R
index 145a376da9..749d1672ac 100644
--- a/r/tests/testthat/test-dataset-csv.R
+++ b/r/tests/testthat/test-dataset-csv.R
@@ -711,21 +711,3 @@ test_that("open_dataset() with `decimal_point` argument", {
     tibble(x = 1.2, y = "c")
   )
 })
-
-
-test_that("more informative error when column inferred as null due to sparse 
data (GH-35806)", {
-  tf <- tempfile()
-  on.exit(unlink(tf))
-
-  # Create a CSV where the second column has NAs in the first rows
-  # but a value later - this causes Arrow to infer null type
-  writeLines(c("x,y", paste0(1:100, ",")), tf)
-  write("101,foo", tf, append = TRUE)
-
-  # Use small block_size to force type inference from only the first rows
-  expect_error(
-    open_dataset(tf, format = "csv", read_options = 
csv_read_options(block_size = 100L)) |>
-      collect(),
-    "inferred as null"
-  )
-})