Closes #1072. Auto indexing with %in% and no matches doesn't error.

R/data.table.R

@@ -522,7 +522,7 @@ chmatch2 <- function(x, table, nomatch=NA_integer_) {
                 leftcols = 1L
                 ans = bmerge(i, x, leftcols, rightcols, io<-FALSE, xo, roll=0.0, rollends=c(FALSE,FALSE), nomatch=0L, verbose=verbose)
                 # No need to shallow copy i before passing to bmerge; we just created i above ourselves
-                i = if (ans$allLen1 && !identical(suppressWarnings(max(ans$starts)), 0L)) ans$starts else vecseq(ans$starts, ans$lens, NULL)
+                i = if (ans$allLen1 && !identical(suppressWarnings(min(ans$starts)), 0L)) ans$starts else vecseq(ans$starts, ans$lens, NULL)
                 if (length(xo)) i = fsort(xo[i])
                 leftcols = rightcols = NULL  # these are used later to know whether a join was done, affects column order of result. So reset.
             }

README.md

@@ -78,6 +78,7 @@
       * Works fine when RHS is of `list` type - quite unusual operation but could happen. Closes [#961](https://github.com/Rdatatable/data.table/issues/961). Thanks to @Gsee for the minimal report.
       * Auto indexing errored in some cases when LHS and RHS were not of same type. This is fixed now. Closes [#957](https://github.com/Rdatatable/data.table/issues/957). Thanks to @GSee for the minimal report.
       * `DT[x == 2.5]` where `x` is integer type resulted in `val` being coerced to integer (for binary search) and therefore returned incorrect result. This is now identified using the function `isReallyReal()` and if so, auto indexing is turned off. Closes [#1050](https://github.com/Rdatatable/data.table/issues/1050).
+      * Auto indexing errored during `DT[x %in% val]` when `val` has some values not present in `x`. Closes [#1072](https://github.com/Rdatatable/data.table/issues/1072). Thanks to @CarlosCinelli for asking on [StackOverflow](http://stackoverflow.com/q/28932742/559784).
 
   7. `as.data.table.list` with list input having 0-length items, e.g. `x = list(a=integer(0), b=3:4)`. `as.data.table(x)` recycles item `a` with `NA`s to fit the length of the longer column `b` (length=2), as before now, but with an additional warning message that the item has been recycled with `NA`. Closes [#847](https://github.com/Rdatatable/data.table/issues/847). Thanks to @tvinodr for the report. This was a regression from 1.9.2.
 

inst/tests/tests.Rraw

@@ -6119,6 +6119,14 @@ DT = data.table(x=1, y=2, z=3, a=4, b=5, c=6)
 test(1498.1, DT[, .SD, .SDcols=c(T,F)], DT[, c("x", "z", "b"), with=FALSE])
 test(1498.2, DT[, .SD, .SDcols=!c(T,F)], DT[, !c("x", "z", "b"), with=FALSE])
 
+# Fix for #1072
+dt <- data.table(group1 = "a", group2 = "z", value  = 1)
+options(datatable.auto.index=FALSE)
+ans1 = dt[group1 %in% c("a", "b"), sum(value), group2]
+options(datatable.auto.index=TRUE)
+ans2 = dt[group1 %in% c("a", "b"), sum(value), group2]
+test(1499, ans1, ans2)
+
 ##########################