new_contributors.R

#' new_contributors.R
#'
#' Produce a list of names of new contributors between two git refs. The method
#' this uses is to first get the list of unique contrbutors referancable from
#' the first ref, then the second ref, and then compute the set difference and
#' return that.
#'
#' Usage
#'
#'   Launch an R session from the directory containing the git repo you want to
#'   query against.
#'
#'   Run this to get a list of new contributors between the refs
#'   "apache-arrow-13.0.0" and "apache-arrow-14.0.0" for commits that touched
#'   the "r" subdirectory":
#
#'   print_new_contributors(
#'     "apache-arrow-13.0.0",
#'     "apache-arrow-14.0.0",
#'     "r"
#'   )
#'
#'   Note that the third argument, subdirectory, is optional. If omitted, it
#'   will use the root directory.

stopunlesscommand <- function(command, arguments) {
  out <- tryCatch({
    system2("git", arguments, stdout = TRUE)
  },
  warning = function(w) {
    stop(w)
  },
  error = function(e) {
    stop(e)
  })

  TRUE
}

stopfinotinrepo <- function() {
  stopunlesscommand("git", "reflog main")
}

stopifnotref <- function(ref) {
  stopifnot(is.character(ref))
  stopifnot(nchar(ref) > 0)
  stopunlesscommand("git", paste("reflog", ref))
}

make_git_log_prev_args <- function(ref_from, subdirectory) {
  paste0("log --pretty='format: %an' ", ref_from, " ", subdirectory, " | sort | uniq")
}

make_git_log_next_args <- function(ref_from, ref_to, subdirectory) {
  paste0("log --pretty='format: %an' ", ref_from, "..", ref_to, " ", subdirectory, " | sort | uniq")
}

print_new_contributors <- function(ref_from, ref_to, subdirectory = ".") {
  stopfinotinrepo()
  stopifnotref(ref_from)
  stopifnotref(ref_to)
  stopifnot(file.exists(subdirectory))

  prev_out <- trimws(system2("git", make_git_log_prev_args(ref_from, subdirectory), stdout = TRUE))
  new_out <- trimws(system2("git", make_git_log_next_args(ref_from, ref_to, subdirectory), stdout = TRUE))

  setdiff(new_out, prev_out)
}