merger master

Author: Mukulyadav2004

.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.

GOVERNANCE.md

@@ -63,7 +63,7 @@ Functionality that is out of current scope:
 ## Committer
 
 * Definition: permission to commit to, and merge PRs into, master branch. 
-* How to obtain this role: after a Reviewer has a consistent history of careful reviews of others' PRs, then a current Committer should ask all other current Committers if they approve promoting the Reviewer to Committer, and it should be done if there is Consensus among active Committers. 
+* How to obtain this role: after a Reviewer has a consistent history of careful reviews of others' substantial PRs, then a current Committer should ask all other current Committers if they approve promoting the Reviewer to Committer, and it should be done if there is Consensus among active Committers. 
 * How this role is recognized: credited via role="aut" in DESCRIPTION (so they appear in Author list on CRAN), and added to https://github.com/orgs/Rdatatable/teams/committers which gives permission to merge PRs into master branch. 
 
 ## CRAN Maintainer
@@ -139,6 +139,8 @@ data.table Version line in DESCRIPTION typically has the following meanings
 
 # Governance history
 
+July 2025: require potential new committers' considered history to be of "substantial" PRs
+
 May 2025: update Finance and CoC language for NumFOCUS incorporation.
 
 Feb 2025: add Finances and Funding section, update Code of Conduct section to be a brief summary and reference the broader CoC document.

NEWS.md

@@ -40,7 +40,7 @@
     # 2:     2     6     4     5
     ```
 
-8. `groupingsets()` gets a new argument `enclos` for use together with the `jj` argument in functions wrapping `groupingsets()`, including the existing wrappers `rollup()` and `cube()`. When forwarding a `j`-expression as `groupingsets(jj = substitute(j))`, make sure to pass `enclos = parent.frame()` as well, so that the `j`-expression will be evaluated in the right context. This makes it possible for `j` to refer to variables outside the `data.table`.
+8. `groupingsets()` gets a new argument `enclos` for use together with the `jj` argument in functions wrapping `groupingsets()`, including the existing wrappers `rollup()` and `cube()`, [#5560](https://github.com/Rdatatable/data.table/issues/5560). When forwarding a `j`-expression as `groupingsets(jj = substitute(j))`, make sure to pass `enclos = parent.frame()` as well, so that the `j`-expression will be evaluated in the right context. This makes it possible for `j` to refer to variables outside the `data.table`. Thanks @sindribaldur for the report and @aitap for the fix.
 
 ### BUG FIXES
 
@@ -70,7 +70,7 @@
 
 13. In rare cases, `data.table` failed to expand ALTREP columns when assigning a full column by reference. This could result in the target column getting modified unintentionally if the next call to the data.table was a modification by reference of the source column. E.g. in `DT[, b := as.character(a)]` the string conversion gets deferred and subsequent modification of column `a` would also modify column `b`, [#5400](https://github.com/Rdatatable/data.table/issues/5400). Thanks to @aquasync for the report and Václav Tlapák for the PR.
 
-14. `data.table()` function is now more aligned with `data.frame()` with respect to the names of the output when one of its inputs is a single-column matrix object, [#4124](https://github.com/Rdatatable/data.table/issues/4124). Thanks @PavoDive for the report and @jangorecki for the PR.
+14. `data.table()` function is now more aligned with `data.frame()` with respect to the names of the output when one of its inputs is a single-column matrix object, [#4124](https://github.com/Rdatatable/data.table/issues/4124). Thanks @PavoDive for the report, @jangorecki for the PR, and @MichaelChirico for a follow-up for back-compatibility.
 
 15. Including an `ITime` object as a named input to `data.frame()` respects the provided name, i.e. `data.frame(a = as.ITime(...))` will have column `a`, [#4673](https://github.com/Rdatatable/data.table/issues/4673). Thanks @shrektan for the report and @MichaelChirico for the fix.
 
@@ -84,6 +84,8 @@
  
 20. `droplevels()` works on 0-row data.tables, [#7043](https://github.com/Rdatatable/data.table/issues/7043). The result will have factor columns `factor(character())`, consistent with the data.frame method. Thanks @advieser for the report and @MichaelChirico for the fix.
 
+21. `print(..., col.names = 'none')` now correctly adapts column widths to the data content, ignoring the original column names and producing a more compact output, [#6882](https://github.com/Rdatatable/data.table/issues/6882). Thanks to @brooksambrose for the report and @venom1204 for the PR.
+
 ### NOTES
 
 1. Continued work to remove non-API C functions, [#6180](https://github.com/Rdatatable/data.table/issues/6180). Thanks Ivan Krylov for the PRs and for writing a clear and concise guide about the R API: https://aitap.codeberg.page/R-api/.

R/as.data.table.R

@@ -48,6 +48,9 @@ as.data.table.matrix = function(x, keep.rownames=FALSE, key=NULL, ...) {
   if (!identical(keep.rownames, FALSE)) {
     # can specify col name to keep.rownames, #575
     ans = data.table(rn=rownames(x), x, keep.rownames=FALSE)
+    # auto-inferred name 'x' is not back-compatible & inconsistent, #7145
+    if (ncol(x) == 1L && is.null(colnames(x)))
+      setnames(ans, 'x', 'V1')
     if (is.character(keep.rownames))
       setnames(ans, 'rn', keep.rownames[1L])
     return(ans)

R/print.data.table.R

@@ -141,6 +141,8 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
     print_default(toprint)
     return(invisible(x))
   }
+  if (col.names == "none")
+    colnames(toprint) = rep.int("", ncol(toprint))
   if (nrow(toprint)>20L && col.names == "auto")
     # repeat colnames at the bottom if over 20 rows so you don't have to scroll up to see them
     #   option to shut this off per request of Oleg Bondar on SO, #1482

inst/tests/tests.Rraw

@@ -21276,13 +21276,46 @@ if (test_R.utils) local({
 })
 
 # Create a data.table when one vector is transposed doesn't respect the name defined by user #4124
-test(2321.1, DT <- data.table(a=1:2, b=matrix(1:2)), data.table(a=1:2, b=1:2))
-test(2321.2, names(DT), names(data.frame(a=1:2, b=matrix(1:2))))
-test(2321.3, DT <- data.table(a=integer(), b=matrix(1L, nrow=0L, ncol=1L)), data.table(a=integer(), b=integer()))
-test(2321.4, names(DT), names(data.frame(a=integer(), b=matrix(1L, nrow=0L, ncol=1L))))
+test(2321.01, DT <- data.table(a=1:2, b=matrix(1:2)), data.table(a=1:2, b=1:2))
+test(2321.02, names(DT), names(data.frame(a=1:2, b=matrix(1:2))))
+test(2321.03, DT <- data.table(a=integer(), b=matrix(1L, nrow=0L, ncol=1L)), data.table(a=integer(), b=integer()))
+test(2321.04, names(DT), names(data.frame(a=integer(), b=matrix(1L, nrow=0L, ncol=1L))))
 ## but respect named column vectors
-test(2321.5, DT <- data.table(a=1:2, cbind(b=3:4)), data.table(a=1:2, b=3:4))
-test(2321.6, names(DT), names(data.frame(a=1:2, cbind(b=3:4))))
+test(2321.05, DT <- data.table(a=1:2, cbind(b=3:4)), data.table(a=1:2, b=3:4))
+test(2321.06, names(DT), names(data.frame(a=1:2, cbind(b=3:4))))
+## also respect old naming pattern when invoked indirectly, #7145
+M = cbind(1:3)
+test(2321.07, as.data.table(M), data.table(V1=1:3))
+rownames(M) = c('a', 'b', 'c')
+test(2321.08, as.data.table(M), data.table(V1=1:3))
+test(2321.09, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), V1=1:3))
+colnames(M) = 'zz'
+test(2321.10, as.data.table(M), data.table(zz=1:3))
+test(2321.11, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), zz=1:3))
+colnames(M) = 'x'
+test(2321.12, as.data.table(M), data.table(x=1:3))
+test(2321.13, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), x=1:3))
+M = cbind(M, y=4:6)
+test(2321.14, as.data.table(M), data.table(x=1:3, y=4:6))
+test(2321.15, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), x=1:3, y=4:6))
+colnames(M) = c('A', 'B')
+test(2321.16, as.data.table(M), data.table(A=1:3, B=4:6))
+test(2321.17, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), A=1:3, B=4:6))
+colnames(M) = NULL
+test(2321.18, as.data.table(M), data.table(V1=1:3, V2=4:6))
+test(2321.19, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), V1=1:3, V2=4:6))
+colnames(M) = c('x', '')
+test(2321.20, as.data.table(M), data.table(x=1:3, V2=4:6))
+test(2321.21, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), x=1:3, V2=4:6))
+colnames(M) = c('', 'x')
+test(2321.22, as.data.table(M), data.table(V1=1:3, x=4:6))
+test(2321.23, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), V1=1:3, x=4:6))
+colnames(M) = c('', '')
+test(2321.24, as.data.table(M), data.table(V1=1:3, V2=4:6))
+test(2321.25, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), V1=1:3, V2=4:6))
+colnames(M) = c('A', '')
+test(2321.26, as.data.table(M), data.table(A=1:3, V2=4:6))
+test(2321.27, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), A=1:3, V2=4:6))
 
 # New fctr() helper: like factor() but retaining order by default #4837
 test(2322.01, levels(fctr(c("b","a","c"))), c("b","a","c"))