Merge branch 'master' into litedown

Author: ben-schwen

.ci/.lintr.R

@@ -21,6 +21,7 @@ linters = c(dt_linters, all_linters(
     message = "Use messagef to avoid fragmented translations.",
     warning = "Use warningf to avoid fragmented translations.",
     stop = "Use stopf to avoid fragmented translations.",
+    rev = "Use frev internally, or setfrev if by-reference is safe.",
     NULL
   )),
   # undesirable_function_linter(modify_defaults(

.ci/atime/tests.R

@@ -277,5 +277,14 @@ test.list <- atime::atime_test_list(
     Slow = "73d79edf8ff8c55163e90631072192301056e336",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/8397dc3c993b61a07a81c786ca68c22bc589befc)
     Fast = "8397dc3c993b61a07a81c786ca68c22bc589befc"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7019/commits) that removes inefficiency
 
+  "isoweek improved in #7144" = atime::atime_test(
+    setup = {
+      set.seed(349)
+      x = sample(Sys.Date() - 0:5000, N, replace=TRUE)
+    },
+    expr = data.table::isoweek(x),
+    Slow = "548410d23dd74b625e8ea9aeb1a5d2e9dddd2927",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/548410d23dd74b625e8ea9aeb1a5d2e9dddd2927)
+    Fast = "c0b32a60466bed0e63420ec105bc75c34590865e"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7144/commits) that uses a much faster implementation
+
     tests=extra.test.list)
 # nolint end: undesirable_operator_linter.

.ci/linters/md/news_linter.R …rs/md/news_github_link_mismatch_linter.R.ci/linters/md/news_linter.R renamed to .ci/linters/md/news_github_link_mismatch_linter.R .ci/linters/md/news_linter.R renamed to .ci/linters/md/news_github_link_mismatch_linter.R

@@ -1,32 +1,6 @@
-# ensure that numbered list in each section is in sequence
-check_section_numbering = function(news) {
-  if (!grepl("NEWS", news)) return(invisible())
-  news = readLines(news)
-  # plain '#' catches some examples; 'd' for 'data.table'
-  sections = grep("^#+ [A-Zd]", news)
-  entries = grep("^[0-9]+[.]", news)
-  entry_value = as.integer(gsub("^([0-9]+)[.].*", "\\1", news[entries]))
-  section_id = findInterval(entries, sections)
-
-  any_mismatch = FALSE
-  for (id in unique(section_id)) {
-    section_entries = entry_value[section_id == id]
-    intended_value = seq_along(section_entries)
-    matched = section_entries == intended_value
-    if (all(matched)) next
-    any_mismatch = TRUE
-    section_header = news[sections[id]]
-    cat(sprintf(
-      "In section '%s' (line %d), bad numbering:\n%s\n",
-      section_header, sections[id],
-      paste0("  [", section_entries[!matched], " --> ", intended_value[!matched], "]", collapse="\n")
-    ))
-  }
-  stopifnot("Please fix the NEWS issues above" = !any_mismatch)
-}
-
 # ensure that GitHub link text & URL actually agree
-check_gh_links = function(news) {
+news_github_link_mismatch_linter = function(news) {
+  if (!grepl("NEWS", news)) return(invisible())
   news = readLines(news)
   gh_links_info = gregexpr(
     "\\[#(?<md_number>[0-9]+)\\]\\(https://github.com/Rdatatable/data.table/(?<link_type>[^/]+)/(?<link_number>[0-9]+)\\)",

.ci/linters/md/news_section_numbering_linter.R

@@ -0,0 +1,26 @@
+# ensure that numbered list in each section is in sequence
+news_section_numbering_linter = function(news) {
+  if (!grepl("NEWS", news)) return(invisible())
+  news = readLines(news)
+  # plain '#' catches some examples; 'd' for 'data.table'
+  sections = grep("^#+ [A-Zd]", news)
+  entries = grep("^[0-9]+[.]", news)
+  entry_value = as.integer(gsub("^([0-9]+)[.].*", "\\1", news[entries]))
+  section_id = findInterval(entries, sections)
+
+  any_mismatch = FALSE
+  for (id in unique(section_id)) {
+    section_entries = entry_value[section_id == id]
+    intended_value = seq_along(section_entries)
+    matched = section_entries == intended_value
+    if (all(matched)) next
+    any_mismatch = TRUE
+    section_header = news[sections[id]]
+    cat(sprintf(
+      "In section '%s' (line %d), bad numbering:\n%s\n",
+      section_header, sections[id],
+      paste0("  [", section_entries[!matched], " --> ", intended_value[!matched], "]", collapse="\n")
+    ))
+  }
+  stopifnot("Please fix the NEWS issues above" = !any_mismatch)
+}

.ci/linters/md/heading_id_linter.R …/linters/md/vignette_heading_id_linter.R.ci/linters/md/heading_id_linter.R renamed to .ci/linters/md/vignette_heading_id_linter.R .ci/linters/md/heading_id_linter.R renamed to .ci/linters/md/vignette_heading_id_linter.R

@@ -1,6 +1,6 @@
 # ensure that ids are limited to alphanumerics and dashes
 # (in particular, dots and underscores break the links)
-check_header_ids = function(md) {
+vignette_heading_id_linter = function(md) {
   if (!grepl('[.]Rmd$', md)) return(invisible())
   md = readLines(md)
   # A bit surprisingly, some headings don't start with a letter.

.ci/linters/r/eval_parse_linter.R

@@ -0,0 +1,8 @@
+eval_parse_linter = make_linter_from_xpath(
+  "//SYMBOL_FUNCTION_CALL[text() = 'parse']
+     /ancestor::expr
+     /preceding-sibling::expr[SYMBOL_FUNCTION_CALL[text() = 'eval']]
+     /parent::expr
+  ",
+  "Avoid eval(parse()); build the language directly, possibly using substitute2()."
+)

.ci/linters/rd/condition_class_docs_check.R

@@ -0,0 +1,51 @@
+# Ensure that data.table condition classes in code match documentation
+condition_classes_documentation_linter = function(rd_file) {
+  if (!grepl("\\name{data.table-condition-classes}", readChar(rd_file, 100L), fixed = TRUE)) return(invisible())
+
+  # Find condition classes in R code 
+  walk_r_ast_for_classes = function(expr) {
+    if (is.call(expr) && is.name(e <- expr[[1L]]) && as.character(e) %in% c("stopf", "warningf", "messagef", "packageStartupMessagef") && is.character(class_arg <- expr[["class"]]) && startsWith(class_arg, "dt_")) {
+      class_arg
+    } else if (is.recursive(expr)) {
+      unlist(lapply(expr, walk_r_ast_for_classes))
+    }
+  }
+
+  # Find condition classes in documentation  
+  walk_rd_ast_for_classes = function(rd_element) {
+    if (!is.list(rd_element)) return(character())
+
+    result = character()
+    if (isTRUE(attr(rd_element, "Rd_tag") == "\\code") && length(rd_element) >= 1L) {
+      content = rd_element[[1L]]
+      if (is.character(content) && startsWith(content, "dt_")) {
+        result = content
+      }
+    }
+    c(result, unlist(lapply(rd_element, walk_rd_ast_for_classes)))
+  }
+
+  code_classes = list.files("R", pattern = "\\.R$", full.names = TRUE) |>
+    lapply(\(f) lapply(parse(f), walk_r_ast_for_classes)) |>
+    unlist() |>
+    unique()
+
+  doc_classes = rd_file |>
+    tools::parse_Rd() |>
+    walk_rd_ast_for_classes() |>
+    unique()
+
+  miss_in_doc = setdiff(code_classes, doc_classes)
+  miss_in_code = setdiff(doc_classes, code_classes)
+
+  if (length(miss_in_doc) > 0L || length(miss_in_code) > 0L) {
+    if (length(miss_in_doc) > 0L) {
+      cat(sprintf("Condition classes in code but missing from docs: %s\n", toString(miss_in_doc)))
+    }
+    if (length(miss_in_code) > 0L) {
+      cat(sprintf("Condition classes in docs but not in code: %s\n", toString(miss_in_code)))
+    }
+    stop("Please sync man/datatable-condition-classes.Rd with code condition classes")
+  }
+}
+

.dev/CRAN_Release.cmd

@@ -584,26 +584,29 @@ bunzip2 inst/tests/*.Rraw.bz2  # decompress *.Rraw again so as not to commit com
 # Many thanks!
 # Best, Tyson
 # ------------------------------------------------------------
-# DO NOT commit or push to GitHub. Leave 4 files (.dev/CRAN_Release.cmd, DESCRIPTION, NEWS and init.c) edited and not committed. Include these in a single and final bump commit below.
-# DO NOT even use a PR. Because PRs build binaries and we don't want any binary versions of even release numbers available from anywhere other than CRAN.
+
 # Leave milestone open with a 'release checks' issue open. Keep updating status there.
 # ** If on EC2, shutdown instance. Otherwise get charged for potentially many days/weeks idle time with no alerts **
 # If it's evening, SLEEP.
 # It can take a few days for CRAN's checks to run. If any issues arise, backport locally. Resubmit the same even version to CRAN.
 # CRAN's first check is automatic and usually received within an hour. WAIT FOR THAT EMAIL.
 # When CRAN's email contains "Pretest results OK pending a manual inspection" (or similar), or if not and it is known why not and ok, then bump dev.
 
-###### Bump dev for NON-PATCH RELEASE
-# 0. Close milestone to prevent new issues being tagged with it. The final 'release checks' issue can be left open in a closed milestone.
-# 1. Check that 'git status' shows 4 files in modified and uncommitted state: DESCRIPTION, NEWS.md, init.c and this .dev/CRAN_Release.cmd
-# 2. Bump minor version in DESCRIPTION to next odd number. Note that DESCRIPTION was in edited and uncommitted state so even number never appears in git.
-# 3. Add new heading in NEWS for the next dev version. Add "(submitted to CRAN on <today>)" on the released heading.
-# 4. Bump minor version in dllVersion() in init.c
-# 5. Bump 3 minor version numbers in Makefile
-# 6. Search and replace this .dev/CRAN_Release.cmd to update 1.16.99 to 1.16.99 inc below, 1.16.0 to 1.17.0 above, 1.15.0 to 1.16.0 below
-# 7. Another final gd to view all diffs using meld. (I have `alias gd='git difftool &> /dev/null'` and difftool meld: http://meldmerge.org/)
-# 8. Push to master with this consistent commit message: "1.17.0 on CRAN. Bump to 1.17.99"
-# 9. Take sha from the previous step and run `git tag 1.17.0 96c..sha..d77` then `git push origin 1.16.0` (not `git push --tags` according to https://stackoverflow.com/a/5195913/403310)
+###### After submission for NON-PATCH RELEASE
+# 0. Start a new branch `cran-x.y.0` with the code as submitted to CRAN
+#    - Check that 'git status' shows 4 files in modified and uncommitted state: DESCRIPTION, NEWS.md, init.c and this .dev/CRAN_Release.cmd
+#    - The branch should have one commit with precisely these 4 files being edited
+# 1. Follow up with a commit with this consistent commit message like: "1.17.0 on CRAN. Bump to 1.17.99" to this branch bumping to the next dev version
+#    - Bump minor version in DESCRIPTION to next odd number. Note that DESCRIPTION was in edited and uncommitted state so even number never appears in git.
+#    - Add new heading in NEWS for the next dev version. Add "(submitted to CRAN on <today>)" on the released heading.
+#    - Bump minor version in dllVersion() in init.c
+#    - Bump 3 minor version numbers in Makefile
+#    - Search and replace this .dev/CRAN_Release.cmd to update 1.16.99 to 1.16.99 inc below, 1.16.0 to 1.17.0 above, 1.15.0 to 1.16.0 below
+#    - Another final gd to view all diffs using meld. (I have `alias gd='git difftool &> /dev/null'` and difftool meld: http://meldmerge.org/)
+# 2. Ideally, no PRs are reviewed while a CRAN submission is pending. Any reviews that do happen MUST target this branch, NOT master!
+# 3. Once the submission lands on CRAN, merge this branch WITHOUT SQUASHING!
+# 4. Close milestone to prevent new issues being tagged with it. The final 'release checks' issue can be left open in a closed milestone.
+# 5. Take SHA from the "...on CRAN. Bump to ..." commit and run `git tag 1.17.0 96c..sha..d77` then `git push origin 1.17.0` (not `git push --tags` according to https://stackoverflow.com/a/5195913/403310)
 ######
 
 ###### Branching policy for PATCH RELEASE

.github/workflows/cran-status-check.yaml

@@ -0,0 +1,66 @@
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 6 * * 1,3,5' # Runs at 06:00 on Mon/Wed/Fri
+
+name: check-cran-status
+
+jobs:
+  fetch-deadlines:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          packages: |
+            gh
+            glue
+
+      - name: Check for existing CRAN issues
+        id: check-issues
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Count open issues with CRAN-related labels
+          ISSUE_COUNT=$(gh issue list --label "cran-deadline" --state open --json number | jq length)
+          if [ $ISSUE_COUNT -eq 0 ]; then
+            echo "should-run=true" >> $GITHUB_OUTPUT
+            echo "✅ Will run CRAN check"
+          else
+            echo "should-run=false" >> $GITHUB_OUTPUT
+            echo "⏭️ Skipping CRAN check - existing issues found"
+          fi
+
+      - name: Fetch deadline for this package
+        if: steps.check-issues.outputs.should-run == 'true'
+        shell: Rscript {0}
+        run: |
+          pkgname <- drop(read.dcf("DESCRIPTION", "Package"))
+
+          deadline <- subset(tools::CRAN_package_db(), Package == pkgname, "Deadline", drop=TRUE)
+
+          if (is.na(deadline)) {
+            quit()
+          }
+
+          gh::gh(
+            "POST /repos/{owner_repo}/issues",
+            owner_repo = Sys.getenv("GITHUB_REPOSITORY"),
+            title = paste("Fix CRAN R CMD check issues by", deadline),
+            body = glue::glue(
+              "This package is failing CRAN checks and is at risk of archival.",
+              "https://cran.r-project.org/web/checks/check_results_{pkgname}.html",
+              "This issue was opened by https://github.com/{Sys.getenv('GITHUB_REPOSITORY')}/actions/runs/{Sys.getenv('GITHUB_RUN_ID')}.",
+              .sep = "\n\n"
+            ),
+            labels = list("cran-deadline")
+          )

.gitlab-ci.yml

@@ -114,6 +114,7 @@ test-lin-rel:
   variables:
     _R_CHECK_FORCE_SUGGESTS_: "TRUE"
     OPENBLAS_MAIN_FREE: "1"
+    _R_CHECK_RD_CHECKRD_MINLEVEL_: "-Inf"
   script:
     - *install-deps
     - echo 'CFLAGS=-g -O3 -flto=auto -fno-common -fopenmp -Wall -Wvla -pedantic -fstack-protector-strong -D_FORTIFY_SOURCE=2' > ~/.R/Makevars