Add a NEWS linter for checking GitHub link consistency

.ci/linters/md/news_linter.R

@@ -25,10 +25,37 @@ check_section_numbering = function(news) {
   return(any_mismatch)
 }
 
+# ensure that GitHub link text & URL actually agree
+check_gh_links = function(news) {
+  gh_links_info = gregexpr(
+    "\\[#(?<md_number>[0-9]+)\\]\\(https://github.com/Rdatatable/data.table/(?<link_type>[^/]+)/(?<link_number>[0-9]+)\\)",
+    news,
+    perl=TRUE # required for within-group indices
+  )
+  gh_link_metadata = do.call(rbind, lapply(seq_along(gh_links_info), function(idx) {
+    x = gh_links_info[[idx]]
+    if (x[1L] <= 0L) return(NULL)
+    match_mat = attr(x, "capture.start") # matrix seeded with the correct dimensions
+    match_mat[] = substring(news[idx], match_mat, match_mat + attr(x, "capture.length") - 1L)
+    match_df = data.frame(match_mat)
+    match_df$line_number = idx
+    match_df
+  }))
+  matched = gh_link_metadata$md_number == gh_link_metadata$link_number
+  if (all(matched)) return(FALSE)
+
+  cat(sep = "", with(gh_link_metadata[!matched, ], sprintf(
+    "In line %d, link pointing to %s %s is written #%s\n",
+    line_number, link_type, link_number, md_number
+  )))
+  return(TRUE)
+}
+
 any_error = FALSE
 for (news in list.files(pattern = "NEWS")) {
   cat(sprintf("Checking NEWS file %s...\n", news))
   news_lines = readLines("NEWS.md")
   any_error = any_error || check_section_numbering(news_lines)
+  any_error = any_error || check_gh_links(news_lines)
 }
 if (any_error) stop("Please fix the NEWS issues above.")

.github/workflows/code-quality.yaml

@@ -55,3 +55,4 @@ jobs:
       - name: Lint
         run: |
           for (f in list.files('.ci/linters/md', full.names=TRUE)) source(f)
+        shell: Rscript {0}

NEWS.md

@@ -346,7 +346,7 @@ This feature resolves [#4387](https://github.com/Rdatatable/data.table/issues/43
 
 23. `DT[, head(.SD,n), by=grp]` and `tail` are now optimized when `n>1`, [#5060](https://github.com/Rdatatable/data.table/issues/5060) [#523](https://github.com/Rdatatable/data.table/issues/523#issuecomment-162934391). `n==1` was already optimized. Thanks to Jan Gorecki and Michael Young for requesting, and Benjamin Schwendinger for the PR.
 
-24. `setcolorder()` gains `before=` and `after=`, [#4385](https://github.com/Rdatatable/data.table/issues/4358). Thanks to Matthias Gomolka for the request, and both Benjamin Schwendinger and Xianghui Dong for implementing. Also thanks to Manuel López-Ibáñez for testing dev and mentioning needed documentation before release.
+24. `setcolorder()` gains `before=` and `after=`, [#4358](https://github.com/Rdatatable/data.table/issues/4358). Thanks to Matthias Gomolka for the request, and both Benjamin Schwendinger and Xianghui Dong for implementing. Also thanks to Manuel López-Ibáñez for testing dev and mentioning needed documentation before release.
 
 25. `base::droplevels()` gains a fast method for `data.table`, [#647](https://github.com/Rdatatable/data.table/issues/647). Thanks to Steve Lianoglou for requesting, Boniface Kamgang and Martin Binder for testing, and Jan Gorecki and Benjamin Schwendinger for the PR. `fdroplevels()` for use on vectors has also been added.