merge

Author: Mukulyadav2004

.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/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")
+  }
+}
+

.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")
+          )

NAMESPACE

@@ -59,6 +59,7 @@ export(nafill)
 export(setnafill)
 export(.Last.updated)
 export(fcoalesce)
+export(mergelist, setmergelist)
 export(cbindlist, setcbindlist)
 export(substitute2)
 #export(DT)  # mtcars |> DT(i,j,by)  #4872 #5472
@@ -208,6 +209,7 @@ S3method(format_list_item, data.frame)
 
 export(fdroplevels, setdroplevels)
 S3method(droplevels, data.table)
+export(frev)
 
 # sort_by added in R 4.4.0, #6662, https://stat.ethz.ch/pipermail/r-announce/2024/000701.html
 if (getRversion() >= "4.4.0") S3method(sort_by, data.table)