Export speakers count table

Author: gaborcsardi

NAMESPACE

@@ -2,4 +2,5 @@
 
 export(franc)
 export(franc_all)
+export(speakers)
 importFrom(jsonlite,fromJSON)

R/franc.R

@@ -56,7 +56,7 @@ und <- function() lang("und")
 #'    default), to make the detection reasonably fast.
 #' @param min_speakers Languages with at least this many speakers are
 #'   checked. By default this is one million. Set it to zero to
-#'   include all languages known by franc.
+#'   include all languages known by franc. See also \code{\link{speakers}}.
 #' @param whitelist List of three letter language codes to check against.
 #' @param blacklist List of three letter language codes not to check
 #'   againts.
@@ -68,7 +68,8 @@ und <- function() lang("und")
 #'   language codes. The \code{score} column contains the scores.
 #'
 #' @encoding utf8
-#' @seealso \code{\link{franc}} if you only want the top result.
+#' @seealso \code{\link{franc}} if you only want the top result,
+#'   \code{\link{speakers}}.
 #' @export
 #' @examples
 #' head(franc_all("O Brasil caiu 26 posições em"))
@@ -125,7 +126,7 @@ franc_all <- function(text, min_speakers = 1000000, whitelist = NULL,
 #'    default), to make the detection reasonably fast.
 #' @param min_speakers Languages with at least this many speakers are
 #'   checked. By default this is one million. Set it to zero to
-#'   include all languages known by franc.
+#'   include all languages known by franc. See also \code{\link{speakers}}.
 #' @param whitelist List of three letter language codes to check against.
 #' @param blacklist List of three letter language codes not to check
 #'   againts.
@@ -136,7 +137,8 @@ franc_all <- function(text, min_speakers = 1000000, whitelist = NULL,
 #'   language of the text. \code{"und"} is returned for too short input.
 #'
 #' @encoding utf8
-#' @seealso \code{\link{franc_all}} for scores against many languages.
+#' @seealso \code{\link{franc_all}} for scores against many languages,
+#'   \code{\link{speakers}}.
 #' @export
 #' @examples
 #' ## afr

R/speakers.R

@@ -1,8 +1,29 @@
 
-#' @importFrom jsonlite fromJSON
-
 speakers_file <- system.file("speakers.json", package = packageName())
 
+#' Number of speakers for 370 languages
+#'
+#' This is a superset of all languages detected by franc. Numbers were
+#' collected by Titus Wormer. To quote him: \emph{Painstakingly crawled by
+#' hand from OHCHR, the numbers are (in some cases, very) rough estimates
+#' or out-of-date.}.
+#'
+#' @format
+#' A data frame with columns:
+#' \describe{
+#'   \item{language}{Three letter language code.}
+#'   \item{speakers}{Number of speakers.}
+#'   \item{name}{Full name of language.}
+#'   \item{iso6391}{ISO 639-1 codes. See more at
+#'     \url{http://en.wikipedia.org/wiki/ISO_639}.}
+#'   \item{iso6392}{ISO 639-2T codes. See more at
+#'     \url{http://en.wikipedia.org/wiki/ISO_639}.}
+#' }
+#'
+#' @docType data
+#' @importFrom jsonlite fromJSON
+#' @export
+
 speakers <- jsonlite::fromJSON(speakers_file, simplifyVector = FALSE)
 
 for (i in seq_along(speakers)) {
@@ -14,7 +35,7 @@ speakers <- data.frame(
   stringsAsFactors = FALSE,
   row.names = NULL,
   language = names(speakers),
-  speakers = vapply(speakers, "[[", 1, "speakers"),
+  speakers = as.integer(vapply(speakers, "[[", 1, "speakers")),
   name     = vapply(speakers, "[[", "", "name"),
   iso6391  = vapply(speakers, "[[", "", "iso6391"),
   iso6392  = vapply(speakers, "[[", "", "iso6392")