From d9f322e004caad03ff624e52d06ac719e1da6221 Mon Sep 17 00:00:00 2001
From: Sumit Chauhan <sc5271027@gmail.com>
Date: Mon, 7 Sep 2026 11:24:20 +0530
Subject: [PATCH] GH-33432: [R] Match base/stringr semantics for str_replace()
 with NA replacement

base::sub()/gsub() and stringr::str_replace()/str_replace_all() set the
whole string to NA when the replacement is NA and the pattern matches.
The Acero replace_substring[_regex] kernels instead splice a literal
"NA" into the string. Special-case an NA replacement in the binding and
rewrite it as if_else(<pattern matches>, NA, x).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 r/R/dplyr-funcs-string.R                   | 20 ++++++++++++++++
 r/tests/testthat/test-dplyr-funcs-string.R | 27 ++++++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/r/R/dplyr-funcs-string.R b/r/R/dplyr-funcs-string.R
index 158bae2db87c..4158932aa367 100644
--- a/r/R/dplyr-funcs-string.R
+++ b/r/R/dplyr-funcs-string.R
@@ -367,6 +367,26 @@ register_bindings_string_regex <- function() {
       if (length(replacement) != 1) {
         validation_error("`replacement` must be a length 1 character vector")
       }
+      # An NA replacement sets the whole string to NA wherever the pattern
+      # matches, matching base::sub()/gsub() and stringr::str_replace(). The
+      # replace_substring[_regex] kernels don't support this, so rewrite it as
+      # if_else(<pattern matches>, NA, x). GH-33432
+      if (is.na(replacement)) {
+        is_match <- Expression$create(
+          ifelse(fixed && !ignore.case, "match_substring", "match_substring_regex"),
+          x,
+          options = list(
+            pattern = format_string_pattern(pattern, ignore.case, fixed),
+            ignore_case = FALSE
+          )
+        )
+        return(Expression$create(
+          "if_else",
+          is_match,
+          Expression$scalar(NA_character_),
+          x
+        ))
+      }
       Expression$create(
         ifelse(fixed && !ignore.case, "replace_substring", "replace_substring_regex"),
         x,
diff --git a/r/tests/testthat/test-dplyr-funcs-string.R b/r/tests/testthat/test-dplyr-funcs-string.R
index 58da3ea23358..3b7488d74bee 100644
--- a/r/tests/testthat/test-dplyr-funcs-string.R
+++ b/r/tests/testthat/test-dplyr-funcs-string.R
@@ -428,6 +428,33 @@ test_that("sub and gsub with namespacing", {
   )
 })
 
+test_that("str_replace/sub with an NA replacement match base/stringr (GH-33432)", {
+  df <- tibble(x = c("", "one", "two", "three", "four", NA))
+
+  # A match sets the whole value to NA; non-matches and NA input are unchanged
+  compare_dplyr_binding(
+    .input |>
+      transmute(
+        regex = str_replace(x, "o", NA_character_),
+        regex_all = str_replace_all(x, "o", NA_character_),
+        fixed = str_replace_all(x, fixed("o"), NA_character_),
+        ci = str_replace_all(x, regex("O", ignore_case = TRUE), NA_character_)
+      ) |>
+      collect(),
+    df
+  )
+
+  compare_dplyr_binding(
+    .input |>
+      transmute(
+        subbed = sub("o", NA_character_, x),
+        gsubbed = gsub("o", NA_character_, x)
+      ) |>
+      collect(),
+    df
+  )
+})
+
 test_that("str_replace and str_replace_all", {
   x <- Expression$field_ref("x")