data.table names handling for unnamed matrix (#4363)

* data.table names handling for unnamed matrix

* tweak NEWS

* tighten up tests

* walk back update for check.names default

* retain column vector's name, if present

* further shrink diff

---------

Co-authored-by: Michael Chirico <[email protected]>

Author: jangorecki

NEWS.md

@@ -46,6 +46,8 @@
 
 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.
+
 ### 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

@@ -142,7 +142,11 @@ 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 && is.null(colnames(xi))) { # 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)) {

inst/tests/tests.Rraw

@@ -21130,16 +21130,16 @@ class(DF) = c("tbl_df", "tbl", "data.frame")
 test(2309.02, key(as.data.table(DF, key="t")), "t")
 
 # data.table keyed with "b"
-DT = data.table(a = 1:5, b = 1:5, x = 1:5, key = "b") 
-test(2309.03, key(as.data.table(DT, key="a")), "a")   
-test(2309.04, key(as.data.table(DT)), "b")            
-test(2309.05, key(as.data.table(DT, key=NULL)), NULL) 
+DT = data.table(a = 1:5, b = 1:5, x = 1:5, key = "b")
+test(2309.03, key(as.data.table(DT, key="a")), "a")
+test(2309.04, key(as.data.table(DT)), "b")
+test(2309.05, key(as.data.table(DT, key=NULL)), NULL)
 
 # non-keyed data.table
 DT = data.table(a = 1:5, b = 1:5, x = 1:5)
-test(2309.06, key(as.data.table(DT, key="a")), "a")   
-test(2309.07, key(as.data.table(DT)), NULL)          
-test(2309.08, key(as.data.table(DT, key=NULL)), NULL) 
+test(2309.06, key(as.data.table(DT, key="a")), "a")
+test(2309.07, key(as.data.table(DT)), NULL)
+test(2309.08, key(as.data.table(DT, key=NULL)), NULL)
 
 # as.data.table(x, keep.rownames=TRUE) keeps rownames for class(x)==c("*", "data.frame")
 df = structure(list(i = 1:2), class = c("tbl", "data.frame"), row.names = c("a","b"))
@@ -21228,3 +21228,12 @@ if (test_R.utils) local({
   })
   test(2320.2, fread(tmp), error="R.utils::decompressFile failed to decompress", warning="invalid")
 })
+
+# 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))))
+## 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))))