From 79b75c224049023b8887941d5534100ca40f03f5 Mon Sep 17 00:00:00 2001
From: Vedha Viyash <49812166+vedhav@users.noreply.github.com>
Date: Tue, 10 Dec 2024 14:08:14 +0530
Subject: [PATCH] Fix windows build in r-universe (#632)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the [package build in
windows](https://github.com/r-universe/pharmaverse/actions/runs/12161651762/job/33917098250)
due to test failure.

### Root cause
Non-Perl compatible regex was causing different behavior when Unicode
text was used as id for the namespace.

As far as I know using perl compatible regex is recommended for complex
regex (like using lookbehind) or when dealing with unicode characters,
the only advantage of non-perl compatible regex is that it performs
better and we do not have a performance issue in our case as we're
dealing with a small vector of texts.

#### Windows reprex 🐛
``` r
pattern_escape <- "[^0-9A-Za-z_]"
id <- "\U5F4AA"
gsub(pattern_escape, "_", id, perl = FALSE)
#> [1] "__"
gsub(pattern_escape, "_", id, perl = TRUE)
#> [1] "_"
```

<sup>Created on 2024-12-10 with [reprex
v2.1.1](https://reprex.tidyverse.org)</sup>

#### Linux reprex 👌
``` r
pattern_escape <- "[^0-9A-Za-z_]"
id <- "\U5F4AA"
gsub(pattern_escape, "_", id, perl = FALSE)
#> [1] "_"
gsub(pattern_escape, "_", id, perl = TRUE)
#> [1] "_"
```

<sup>Created on 2024-12-10 with [reprex
v2.0.2](https://reprex.tidyverse.org)</sup>

#### macOS reprex 👌
``` r
pattern_escape <- "[^0-9A-Za-z_]"
id <- "\U1F4AA"
gsub(pattern_escape, "_", id, perl = FALSE)
#> [1] "_"
gsub(pattern_escape, "_", id, perl = TRUE)
#> [1] "_"
```

<sup>Created on 2024-12-10 with [reprex
v2.1.0](https://reprex.tidyverse.org/)</sup>
---
 R/utils.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/utils.R b/R/utils.R
index d29cb9b7b..0728d80a5 100644
--- a/R/utils.R
+++ b/R/utils.R
@@ -84,7 +84,7 @@ make_c_call <- function(choices) {
 sanitize_id <- function(id) {
   pattern_escape <- "[^0-9A-Za-z_]"
 
-  id_new <- gsub(pattern_escape, "_", id)
+  id_new <- gsub(pattern_escape, "_", id, perl = TRUE)
   hashes <- vapply(id[id != id_new], rlang::hash, character(1), USE.NAMES = FALSE)
 
   id[id != id_new] <- paste0("h", substr(hashes, 1, 4), "_", id_new[id != id_new])