Case-insensitive joins for dplyr

insensitive.R

a <- data.frame(letter = letters[1:10], num = 1:10)
b <- data.frame(letter = LETTERS[1:5], num2 = c(1:3, 9:10), val = 11:15)

library(dplyr)

insensitive <- function(fun = inner_join) {
  new_fun <- fun
  body(new_fun) <- substitute({
    by <- dplyr:::common_by(by, x, y)

    tmp_by_x <- paste0("_", by$x, "_")
    tmp_by_y <- paste0("_", by$y, "_")
    for (i in seq_along(by$x)) {
      x[[tmp_by_x[[i]]]] <- tolower(x[[by$x[[i]]]])
      y[[tmp_by_y[[i]]]] <- tolower(y[[by$y[[i]]]])
      y[[by$y[[i]]]] <- NULL
    }

    res <- fun(x, y, list(x = tmp_by_x, y = tmp_by_y))
    res[tmp_by_x] <- list(NULL)

    res
  })

  new_fun
}

insensitive(inner_join)(a, b)
#> Joining by: "letter"
#>   letter num num2 val
#> 1      a   1    1  11
#> 2      b   2    2  12
#> 3      c   3    3  13
#> 4      d   4    9  14
#> 5      e   5   10  15

insensitive(inner_join)(a, b,
  by = list(x = c('letter', 'num'), y = c('letter', 'num2')))
#>   letter num val
#> 1      a   1  11
#> 2      b   2  12
#> 3      c   3  13

insensitive(left_join)(a, b,
  by = list(x = c('letter', 'num'), y = c('letter', 'num2')))
#>    letter num val
#> 1       a   1  11
#> 2       b   2  12
#> 3       c   3  13
#> 4       d   4  NA
#> 5       e   5  NA
#> 6       f   6  NA
#> 7       g   7  NA
#> 8       h   8  NA
#> 9       i   9  NA
#> 10      j  10  NA