data.table names handling for unnamed matrix

Author: jangorecki

NEWS.md

@@ -107,6 +107,8 @@ unit = "s")
 
 12. `rbindlist` no longer errors when coercing complex vectors to character vectors, [#4202](https://github.com/Rdatatable/data.table/issues/4202). Thanks to @sritchie73 for reporting and the PR.
 
+13. `data.table` function is now more aligned to base R about names of the output when one of its input is a single column matrix object, [#4124](https://github.com/Rdatatable/data.table/issues/4124). Thanks to @PavoDive for reporting. For matrix column objects it will also ensure to return non-duplicated names, [#3193](https://github.com/Rdatatable/data.table/issues/3193).
+
 ## NOTES
 
 0. Retrospective license change permission was sought from and granted by 4 contributors who were missed in [PR#2456](https://github.com/Rdatatable/data.table/pull/2456), [#4140](https://github.com/Rdatatable/data.table/pull/4140). We had used [GitHub's contributor page](https://github.com/Rdatatable/data.table/graphs/contributors) which omits 3 of these due to invalid email addresses, unlike GitLab's contributor page which includes the ids. The 4th omission was a PR to a script which should not have been excluded; a script is code too. We are sorry these contributors were not properly credited before. They have now been added to the contributors list as displayed on CRAN. All the contributors of code to data.table hold its copyright jointly; your contributions belong to you. You contributed to data.table when it had a particular license at that time, and you contributed on that basis. This is why in the last license change, all contributors of code were consulted and each had a veto.

R/as.data.table.R

@@ -127,7 +127,8 @@ as.data.table.list = function(x,
   n = length(x)
   eachnrow = integer(n)          # vector of lengths of each column. may not be equal if silent repetition is required.
   eachncol = integer(n)
-  missing.check.names = missing(check.names)
+  missing.check.names = missing(check.names) || is.null(check.names) # is.null for #3193
+  if (missing.check.names) check.names = FALSE
   origListNames = if (missing(.named)) names(x) else NULL  # as.data.table called directly, not from inside data.table() which provides .named, #3854
   for (i in seq_len(n)) {
     xi = x[[i]]
@@ -138,7 +139,11 @@ as.data.table.list = function(x,
       xi = x[[i]] = as.POSIXct(xi)
     } else if (is.matrix(xi) || is.data.frame(xi)) {
       if (!is.data.table(xi)) {
-        xi = x[[i]] = as.data.table(xi, keep.rownames=keep.rownames)  # we will never allow a matrix to be a column; always unpack the columns
+        if (is.matrix(xi) && NCOL(xi)<=1L) { # 1 column matrix naming #4124
+          xi = x[[i]] = c(xi)
+        } else {
+          xi = x[[i]] = as.data.table(xi, keep.rownames=keep.rownames)  # we will never allow a matrix to be a column; always unpack the columns
+        }
       }
       # else avoid dispatching to as.data.table.data.table (which exists and copies)
     } else if (is.table(xi)) {

R/data.table.R

@@ -58,6 +58,7 @@ data.table = function(..., keep.rownames=FALSE, check.names=FALSE, key=NULL, str
   names(x) = nd$vnames
   if (length(x)==0L) return( null.data.table() )
   if (length(x)==1L && (is.null(x[[1L]]) || (is.list(x[[1L]]) && length(x[[1L]])==0L))) return( null.data.table() ) #48
+  if (missing(check.names)) check.names = NULL ## inherit missingness #3193
   ans = as.data.table.list(x, keep.rownames=keep.rownames, check.names=check.names, .named=nd$.named)  # see comments inside as.data.table.list re copies
   if (!is.null(key)) {
     if (!is.character(key)) stop("key argument of data.table() must be character")

inst/tests/tests.Rraw

@@ -16846,3 +16846,13 @@ A = data.table(A=c(complex(real = 1:3, imaginary=c(0, -1, 1)), NaN))
 test(2138.3, rbind(A,B), data.table(A=c(as.character(A$A), B$A)))
 A = data.table(A=as.complex(rep(NA, 5)))
 test(2138.4, rbind(A,B), data.table(A=c(as.character(A$A), B$A)))
+
+# Create a data.table when one vector is transposed doesn't respect the name defined by user #4124
+test(2139.1, data.table(a=1:2, b=matrix(1:2)), data.table(a=1:2, b=1:2))
+test(2139.2, names(data.table(a=1:2, b=matrix(1:2))), names(data.frame(a=1:2, b=matrix(1:2))))
+test(2139.3, data.table(a=1L[0L], b=matrix(1L)[0L]), data.table(a=1L[0L], b=1L[0L])) # length 0
+test(2139.4, names(data.table(a=1L[0L], b=matrix(1L)[0L])), names(data.frame(a=1L[0L], b=matrix(1L)[0L])))
+# data.table(vector, matrix) can return duplicate column names #3193
+is.unq = function(x) length(unique(x)) == length(x)
+test(2139.5, is.unq(names(data.table(1:5, matrix(6:15, nrow = 5L)))))
+test(2139.6, is.unq(names(data.table(1L[0L], matrix(6:15, nrow=5L)[0L]))))