[ci] Add debian-clang-devel CI job for the R package

.ci/test_r_package.sh

@@ -7,19 +7,6 @@ mkdir -p $R_LIB_PATH
 export R_LIBS=$R_LIB_PATH
 export PATH="$R_LIB_PATH/R/bin:$PATH"
 
-# hack to get around this:
-# https://stat.ethz.ch/pipermail/r-package-devel/2020q3/005930.html
-export _R_CHECK_SYSTEM_CLOCK_=0
-
-# ignore R CMD CHECK NOTE checking how long it has
-# been since the last submission
-export _R_CHECK_CRAN_INCOMING_REMOTE_=0
-
-# CRAN ignores the "installed size is too large" NOTE,
-# so our CI can too. Setting to a large value here just
-# to catch extreme problems
-export _R_CHECK_PKG_SIZES_THRESHOLD_=100
-
 # don't fail builds for long-running examples unless they're very long.
 # See https://github.com/microsoft/LightGBM/issues/4049#issuecomment-793412254.
 if [[ $R_BUILD_TYPE != "cran" ]]; then

.ci/test_r_package_windows.ps1

@@ -79,19 +79,6 @@ $env:CRAN_MIRROR = "https://cloud.r-project.org/"
 $env:CTAN_MIRROR = "https://ctan.math.illinois.edu/systems/win32/miktex"
 $env:CTAN_PACKAGE_ARCHIVE = "$env:CTAN_MIRROR/tm/packages/"
 
-# hack to get around this:
-# https://stat.ethz.ch/pipermail/r-package-devel/2020q3/005930.html
-$env:_R_CHECK_SYSTEM_CLOCK_ = 0
-
-# ignore R CMD CHECK NOTE checking how long it has
-# been since the last submission
-$env:_R_CHECK_CRAN_INCOMING_REMOTE_ = 0
-
-# CRAN ignores the "installed size is too large" NOTE,
-# so our CI can too. Setting to a large value here just
-# to catch extreme problems
-$env:_R_CHECK_PKG_SIZES_THRESHOLD_ = 100
-
 # don't fail builds for long-running examples unless they're very long.
 # See https://github.com/microsoft/LightGBM/issues/4049#issuecomment-793412254.
 if ($env:R_BUILD_TYPE -ne "cran") {

.github/workflows/r_package.yml

@@ -8,6 +8,18 @@ on:
     branches:
     - master
 
+env:
+  # hack to get around this:
+  # https://stat.ethz.ch/pipermail/r-package-devel/2020q3/005930.html
+  _R_CHECK_SYSTEM_CLOCK_: 0
+  # ignore R CMD CHECK NOTE checking how long it has
+  # been since the last submission
+  _R_CHECK_CRAN_INCOMING_REMOTE_: 0
+  # CRAN ignores the "installed size is too large" NOTE,
+  # so our CI can too. Setting to a large value here just
+  # to catch extreme problems
+  _R_CHECK_PKG_SIZES_THRESHOLD_: 100
+
 jobs:
   test:
     name: ${{ matrix.task }} (${{ matrix.os }}, ${{ matrix.compiler }}, R ${{ matrix.r_version }}, ${{ matrix.build_type }})
@@ -181,10 +193,37 @@ jobs:
           Rscriptdevel testthat.R 2>&1 > ubsan-tests.log
           cat ubsan-tests.log
           exit $(cat ubsan-tests.log | grep --count "runtime error")
+  test-r-debian-clang:
+    name: r-package (debian, R-devel, clang)
+    timeout-minutes: 60
+    runs-on: ubuntu-latest
+    container: rhub/debian-clang-devel
+    steps:
+      - name: Install Git before checkout
+        shell: bash
+        run: |
+          apt-get update
+          apt-get install --no-install-recommends -y git
+      - name: Checkout repository
+        uses: actions/checkout@v2.3.4
+        with:
+          fetch-depth: 5
+          submodules: true
+      - name: Install packages and run tests
+        shell: bash
+        run: |
+          export PATH=/opt/R-devel/bin/:${PATH}
+          Rscript -e "install.packages(c('R6', 'data.table', 'jsonlite', 'testthat'), repos = 'https://cran.r-project.org')"
+          sh build-cran-package.sh
+          R CMD check --as-cran --run-donttest lightgbm_*.tar.gz || exit -1
+          if grep -q -E "NOTE|WARNING|ERROR" lightgbm.Rcheck/00check.log; then
+              echo "NOTEs, WARNINGs, or ERRORs have been found by R CMD check"
+              exit -1
+          fi
   all-successful:
     # https://git.luolix.topmunity/t/is-it-possible-to-require-all-github-actions-tasks-to-pass-without-enumerating-them/117957/4?u=graingert
     runs-on: ubuntu-latest
-    needs: [test, test-r-sanitizers]
+    needs: [test, test-r-sanitizers, test-r-debian-clang]
     steps:
     - name: Note that all tests succeeded
       run: echo "🎉"

R-package/cran-comments.md

@@ -1,11 +1,27 @@
 # CRAN Submission History
 
-## v3.2.0 - Submission 1 - (TBD)
+## v3.2.1 - Submission 1 - (TBD)
 
 ### CRAN response
 
 ### Maintainer Notes
 
+## v3.2.0 - Submission 1 - (March 22, 2021)
+
+### CRAN response
+
+Package is failing checks in the `r-devel-linux-x86_64-debian-clang` environment (described [here](https://cran.r-project.org/web/checks/check_flavors.html#r-devel-linux-x86_64-debian-clang)). Specifically, one unit test on the use of non-ASCII feature names in `Booster$dump_model()` fails.
+
+> Apparently your package fails its checks in a strict Latin-1* locale,
+e.g. under Linux using LANG=en_US.iso88591 (see the debian-clang
+results).
+
+> Please correct before 2021-04-21 to safely retain your package on CRAN.
+
+### Maintainer Notes
+
+Submitted a version 3.2.1 to correct the errors noted.
+
 ## v3.1.1 - Submission 1 - (December 7, 2020)
 
 ### CRAN response

R-package/tests/testthat/test_basic.R

@@ -2,6 +2,11 @@ context("lightgbm()")
 
 ON_WINDOWS <- .Platform$OS.type == "windows"
 
+UTF8_LOCALE <- all(grepl(
+  pattern = "UTF-8$"
+  , x = Sys.getlocale(category = "LC_CTYPE")
+))
+
 data(agaricus.train, package = "lightgbm")
 data(agaricus.test, package = "lightgbm")
 train <- agaricus.train
@@ -1229,7 +1234,7 @@ test_that("lgb.train() supports non-ASCII feature names", {
   # UTF-8 strings are not well-supported on Windows
   # * https://developer.r-project.org/Blog/public/2020/05/02/utf-8-support-on-windows/
   # * https://developer.r-project.org/Blog/public/2020/07/30/windows/utf-8-build-of-r-and-cran-packages/index.html
-  if (!ON_WINDOWS) {
+  if (UTF8_LOCALE && !ON_WINDOWS) {
     expect_identical(
       dumped_model[["feature_names"]]
       , feature_names