attempt to salvage really messy logic with simpler conditions

Author: MichaelChirico

R/data.table.R

@@ -541,22 +541,26 @@ replace_dot_alias = function(e) {
         if (!byjoin || nqbyjoin) {
           # Really, `anyDuplicated` in base is AWESOME!
           # allow.cartesian shouldn't error if a) not-join, b) 'i' has no duplicates
-          if (verbose) {last.started.at=proc.time();cat("Constructing irows for '!byjoin || nqbyjoin' ... ");flush.console()}
-          irows = if (allLen1) f__ else {
+          if (verbose) {last.started.at=proc.time();catf("Constructing irows for '!byjoin || nqbyjoin' ... ");flush.console()}
+          if (allLen1) {
+            irows = f__
+          } else {
             join.many = getOption("datatable.join.many") # #914, default TRUE for backward compatibility
-            anyDups = if (!join.many && length(f__)==1L && len__==nrow(x)) {
-              NULL # special case of scalar i match to const duplicated x, not handled by anyDuplicate: data.table(x=c(1L,1L))[data.table(x=1L), on="x"]
-            } else if (!notjoin && ( # #698. When notjoin=TRUE, ignore allow.cartesian. Rows in answer will never be > nrow(x).
-              !allow.cartesian ||
-              !join.many))
-              as.logical(anyDuplicated(f__, incomparables = c(0L, NA_integer_)))
-            limit = if (!is.null(anyDups) && anyDups) { # #742. If 'i' has no duplicates, ignore
+            anyDups = !notjoin &&
+              (
+                # #698. When notjoin=TRUE, ignore allow.cartesian. Rows in answer will never be > nrow(x).
+                (join.many && !allow.cartesian) ||
+                # special case of scalar i match to const duplicated x, not handled by anyDuplicate: data.table(x=c(1L,1L))[data.table(x=1L), on="x"]
+                (!join.many && (length(f__) != 1L || len__ != nrow(x)))
+              ) &&
+              anyDuplicated(f__, incomparables = c(0L, NA_integer_)) > 0L
+            limit = if (anyDups) { # #742. If 'i' has no duplicates, ignore
               if (!join.many) stopf("Joining resulted in many-to-many join. Perform quality check on your data, use mult!='all', or set 'datatable.join.many' option to TRUE to allow rows explosion.")
-              else if (!allow.cartesian && !notjoin) as.double(nrow(x)+nrow(i))
-              else internal_error("checking allow.cartesian and join.many, unexpected else branch reached") # nocov
+              if (allow.cartesian) internal_error("checking allow.cartesian and join.many, unexpected else branch reached") # nocov
+              as.double(nrow(x)+nrow(i)) # rows in i might not match to x so old max(nrow(x),nrow(i)) wasn't enough. But this limit now only applies when there are duplicates present so the reason now for nrow(x)+nrow(i) is just to nail it down and be bigger than max(nrow(x),nrow(i)).
             }
-            vecseq(f__, len__, limit)
-          } # rows in i might not match to x so old max(nrow(x),nrow(i)) wasn't enough. But this limit now only applies when there are duplicates present so the reason now for nrow(x)+nrow(i) is just to nail it down and be bigger than max(nrow(x),nrow(i)).
+            irows = vecseq(f__, len__, limit)
+          }
           if (verbose) {cat(timetaken(last.started.at),"\n"); flush.console()}
           # Fix for #1092 and #1074
           # TODO: implement better version of "any"/"all"/"which" to avoid