Merge branch 'master' into froll2025

Author: jangorecki

.ci/linters/c/alloc_linter.R

@@ -6,7 +6,7 @@ alloc_linter = function(c_obj) {
   lines = c_obj$lines
   # Be a bit more precise to avoid mentions in comments, and allow
   #   malloc(0) to be used for convenience (e.g. #6757)
-  alloc_lines = grep(R"{=\s*([(]\w+\s*[*][)])?[mc]alloc[(][^0]}", lines)
+  alloc_lines = grep(R"{=\s*([(]\s*\w+\s*[*]\s*[)])?\s*[mc]alloc[(][^0]}", lines)
   if (!length(alloc_lines)) return()
   # int *tmp=(int*)malloc(...); or just int tmp=malloc(...);
   alloc_keys = lines[alloc_lines] |>
@@ -31,7 +31,7 @@ alloc_linter = function(c_obj) {
       cat("FILE: ", c_obj$path, "; LINES: ", head(bad_lines_idx, 1L), "-", tail(bad_lines_idx, 1L), "\n", sep="")
       writeLines(lines[bad_lines_idx])
       cat(strrep("-", max(nchar(lines[bad_lines_idx]))), "\n", sep="")
-      stop("Expected the malloc()/calloc() usage above to be followed immediately by error checking.", call.=FALSE)
+      stop("Expected the malloc()/calloc() usage above to be followed immediately by error checking (using '!', not '==NULL').", call.=FALSE)
     }
   })
 }

.ci/linters/cocci/malloc_return_value_cast.cocci

@@ -0,0 +1,6 @@
+@malloc_return_value_cast expression@
+type T;
+expression E;
+@@
+- (T)
+  malloc(E)

DESCRIPTION

@@ -100,5 +100,6 @@ Authors@R: c(
   person("Vincent", "Rocher",      role="ctb"),
   person("Vijay", "Lulla",         role="ctb"),
   person("Aljaž", "Sluga",         role="ctb"),
-  person("Bill", "Evans",          role="ctb")
+  person("Bill", "Evans",          role="ctb"),
+  person("Reino", "Bruner",        role="ctb")
   )

NEWS.md

@@ -63,6 +63,7 @@ microbenchmark::microbenchmark(
 
 7. `fwrite()` now avoids a crash when translating strings into a different encoding, [#6883](https://github.com/Rdatatable/data.table/issues/6883). Thanks @filipemsc for the report and @aitap for the fix.
 
+8. `fread()` no longer warns on certain systems on R 4.5.0+ where the file owner can't be resolved, [#6918](https://github.com/Rdatatable/data.table/issues/6918). Thanks @ProfFancyPants for the report and PR.
 
 ## NOTES
 

R/data.table.R

@@ -904,7 +904,7 @@ replace_dot_alias = function(e) {
             if (length(byvars) == 1L) tt = byvars
             else {
               # take the first variable that is (1) not eval (#3758) and (2) starts with a character that can't start a variable name
-              tt = grep("^eval$|^[^[:alpha:]. ]", byvars, invert=TRUE, value=TRUE)
+              tt = grepv("^eval$|^[^[:alpha:]. ]", byvars, invert=TRUE)
               # byvars but exclude functions or `0`+`1` becomes `+`
               tt = if (length(tt)) tt[1L] else all.vars(bysubl[[jj+1L]])[1L]
             }

R/fread.R

@@ -88,7 +88,7 @@ yaml=FALSE, tmpdir=tempdir(), tz="UTC")
       on.exit(unlink(tmpFile), add=TRUE)
       # nocov end
     }
-    file_info = file.info(file)
+    file_info = file.info(file, extra_cols=FALSE)
     if (is.na(file_info$size)) stopf("File '%s' does not exist or is non-readable. getwd()=='%s'", file, getwd())
     if (isTRUE(file_info$isdir)) stopf("File '%s' is a directory. Not yet implemented.", file) # Could use dir.exists(), but we already ran file.info().
     if (!file_info$size) {

R/print.data.table.R

@@ -19,6 +19,7 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
     stopf("Valid options for col.names are 'auto', 'top', and 'none'")
   if (length(trunc.cols) != 1L || !is.logical(trunc.cols) || is.na(trunc.cols))
     stopf("Valid options for trunc.cols are TRUE and FALSE")
+  stopifnot(isTRUEorFALSE(class))
   if (col.names == "none" && class)
     warningf("Column classes will be suppressed when col.names is 'none'")
   if (!shouldPrint(x)) {
@@ -52,11 +53,11 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
     ))
   }
   if (any(dim(x)==0L)) {
-    class = if (is.data.table(x)) "table" else "frame"  # a data.frame could be passed to print.data.table() directly, #3363
+    x_class = if (is.data.table(x)) "data.table" else "data.frame"  # a data.frame could be passed to print.data.table() directly, #3363
     if (all(dim(x)==0L)) {
-      catf("Null data.%s (0 rows and 0 cols)\n", class)  # See FAQ 2.5 and NEWS item in v1.8.9
+      catf("Null %s (0 rows and 0 cols)\n", x_class)  # See FAQ 2.5 and NEWS item in v1.8.9
     } else {
-      catf("Empty data.%s (%d rows and %d cols)", class, NROW(x), NCOL(x))
+      catf("Empty %s (%d rows and %d cols)", x_class, NROW(x), NCOL(x))
       if (length(x)>0L) cat(": ",paste(head(names(x),6L),collapse=","),if(length(x)>6L)"...",sep="") # notranslate
       cat("\n") # notranslate
     }
@@ -94,7 +95,7 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
   if (is.null(names(x)) || !any(nzchar(names(x), keepNA=TRUE)))
     # fixes bug #97 and #545
     colnames(toprint)=rep("", ncol(toprint))
-  if (isTRUE(class) && col.names != "none") {
+  if (class && col.names != "none") {
     #Matching table for most common types & their abbreviations
     class_abb = c(list = "<list>", integer = "<int>", numeric = "<num>",
       character = "<char>", Date = "<Date>", complex = "<cplx>",
@@ -105,8 +106,9 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
     if ( length(idx <- which(is.na(abbs))) ) abbs[idx] = paste0("<", classes[idx], ">")
     toprint = rbind(abbs, toprint)
     rownames(toprint)[1L] = ""
+  } else {
+    abbs = ""
   }
-  if (isFALSE(class) || (isTRUE(class) && col.names == "none")) abbs = ""
   if (quote) colnames(toprint) <- paste0('"', old <- colnames(toprint), '"')
   if (isTRUE(trunc.cols)) {
     # allow truncation of columns to print only what will fit in console PR #4074
@@ -131,9 +133,9 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
   }
   if (printdots) {
     if (isFALSE(row.names)) {
-      toprint = rbind(head(toprint, topn + isTRUE(class)), "---", tail(toprint, topn)) # 4083
+      toprint = rbind(head(toprint, topn + class), "---", tail(toprint, topn)) # 4083
     } else {
-      toprint = rbind(head(toprint, topn + isTRUE(class)), "---"="", tail(toprint, topn))
+      toprint = rbind(head(toprint, topn + class), "---"="", tail(toprint, topn))
     }
     rownames(toprint) = format(rownames(toprint), justify="right")
     print_default(toprint)
@@ -145,7 +147,7 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
     toprint = rbind(
       toprint,
       matrix(if (quote) old else colnames(toprint), nrow=1L), # see #97
-      if (isTRUE(class)) matrix(if (trunc.cols) abbs[cols_to_print] else abbs, nrow=1L) # #6902
+      if (class) matrix(if (trunc.cols) abbs[cols_to_print] else abbs, nrow=1L) # #6902
     )
   print_default(toprint)
   invisible(x)
@@ -169,7 +171,7 @@ shouldPrint = function(x) {
 # for removing the head (column names) of matrix output entirely,
 #   as opposed to printing a blank line, for excluding col.names per PR #1483
 # be sure to remove colnames from any row where they exist, #4270
-cut_colnames = function(x) writeLines(grep("^\\s*(?:[0-9]+:|---)", capture.output(x), value=TRUE))
+cut_colnames = function(x) writeLines(grepv("^\\s*(?:[0-9]+:|---)", capture.output(x)))
 
 # for printing the dims for list columns #3671; used by format.data.table()
 paste_dims = function(x) {

R/test.data.table.R

@@ -458,7 +458,7 @@ test = function(num,x,y=TRUE,error=NULL,warning=NULL,message=NULL,output=NULL,no
       # if a warning containing this string occurs, ignore it. First need for #4182 where warning about 'timedatectl' only
       # occurs in R 3.4, and maybe only on docker too not for users running test.data.table().
       stopifnot(is.character(ignore.warning), !anyNA(ignore.warning), nchar(ignore.warning)>=1L)
-      for (msg in ignore.warning) observed = grep(msg, observed, value=TRUE, invert=TRUE) # allow multiple for translated messages rather than relying on '|' to always work
+      for (msg in ignore.warning) observed = grepv(msg, observed, invert=TRUE) # allow multiple for translated messages rather than relying on '|' to always work
     }
     if (length(expected) != length(observed) && (!foreign || is.null(ignore.warning))) {
       # nocov start

R/utils.R

@@ -24,6 +24,9 @@ nan_is_na = function(x) {
 # R 4.4.0
 if (!exists("%||%", "package:base")) `%||%` <- function(x, y) if (is.null(x)) y else x # nolint: coalesce_linter.
 
+# R 4.5.0
+if (!exists("grepv", "package:base")) grepv <- function(...) grep(..., value=TRUE)
+
 internal_error = function(...) {
   e1 = gettext("Internal error in")
   e2 = deparse(head(tail(sys.calls(), 2L), 1L)[[1L]][[1L]])

inst/tests/tests.Rraw

@@ -21147,3 +21147,11 @@ dt = data.table(id = 1:25)
 test(2314.1, any(grepl("<int>", tail(capture.output(print(dt, class = TRUE)), 2))), TRUE)
 # Test that class=TRUE with col.names="top" doesn't show classes at bottom
 test(2314.2, !any(grepl("<int>", tail(capture.output(print(dt, class = TRUE, col.names = "top")), 2))), TRUE)
+
+# forder.c coverage
+N <- 70000L
+DT <- data.table(i = rep(2:1, c(1L, N-1L)))
+test(2315.1, tail(DT[order(i), i], 2L), 1:2)
+# wider range of numbers needed for further coverage
+DT[1L, i := 1000L]
+test(2315.2, tail(DT[order(i), i], 2L), c(1L, 1000L))