Assign in i

NEWS.md

@@ -113,6 +113,20 @@ unit = "s")
 
 5. `frank(..., ties.method="random", na.last=NA)` now returns the same random ordering that `base::rank` does, [#4243](https://github.com/Rdatatable/data.table/pull/4243).
 
+6. The error message when mistakenly using `:=` in `i` instead of `j` has been much improved, [#4227](https://github.com/Rdatatable/data.table/issues/4227). Thanks to Hugh Parsonage for the detailed suggestion.
+
+    ```R
+    > DT = data.table(A=1:2)
+    > DT[B:=3]
+    Error: Operator := detected in i, the first argument inside DT[...], but is only valid in the second argument, j. Most often, this happens when forgetting the first comma (e.g. DT[newvar := 5] instead of DT[ , new_var := 5]). Please double-check the syntax. Run traceback(), and debugger() to get a line number.
+    > DT[,B:=3]
+    > DT
+           A     B
+       <int> <num>
+    1:     1     3
+    2:     2     3
+    ```
+
 
 # data.table [v1.12.8](https://github.com/Rdatatable/data.table/milestone/15?closed=1)  (09 Dec 2019)
 

R/data.table.R

@@ -2611,7 +2611,19 @@ vecseq = function(x,y,clamp) .Call(Cvecseq,x,y,clamp)
 # .Call(Caddress, x) increments NAM() when x is vector with NAM(1). Referring object within non-primitive function is enough to increment reference.
 address = function(x) .Call(Caddress, eval(substitute(x), parent.frame()))
 
-":=" = function(...) stop('Check that is.data.table(DT) == TRUE. Otherwise, := and `:=`(...) are defined for use in j, once only and in particular ways. See help(":=").')
+":=" = function(...) {
+  # detect common mistake -- using := in i due to forgetting a comma to leave it blank, #4227
+  find_doteq_in_i = function(e) {
+    if (is.call(e)) {
+      if (is.symbol(e[[1L]]) && e[[1L]] == '[.data.table' && is.call(e[[3L]]) && is.symbol(e[[3L]][[1L]]) && e[[3L]][[1L]] == ':=') {
+        stop("Operator := detected in i, the first argument inside DT[...], but is only valid in the second argument, j. Most often, this happens when forgetting the first comma (e.g. DT[newvar := 5] instead of DT[ , new_var := 5]). Please double-check the syntax. Run traceback(), and debugger() to get a line number.")
+      }
+      else lapply(e[-1L], find_doteq_in_i)
+    }
+  }
+  for (calli in sys.calls()) find_doteq_in_i(calli)
+  stop('Check that is.data.table(DT) == TRUE. Otherwise, := and `:=`(...) are defined for use in j, once only and in particular ways. See help(":=").')
+}
 
 setDF = function(x, rownames=NULL) {
   if (!is.list(x)) stop("setDF only accepts data.table, data.frame or list of equal length as input")

inst/tests/tests.Rraw

@@ -16792,7 +16792,8 @@ if (test_xts) {
   test(2133.5, as.data.table(xts, keep.rownames = NA_character_),
        error = "keep.rownames must not be NA")
 }
-
-########################
-#  Add new tests here  #
-########################
+
+# friendlier error for common mistake of using := in i instead of j, #4227
+DT = data.table(a = 1)
+test(2134.1, DT[b := 2], error="Operator := detected in i, the first argument inside DT[...], but is only valid in the second argument, j.")
+test(2134.2, DT[DT[mpg_per_cl := mpg/cyl], on='ast'], error="Operator := detected in i, the first argument inside")