Preinstall french data for running example

Author: jeroen

.travis.yml

@@ -30,6 +30,7 @@ addons:
       - libtesseract-dev
       - libleptonica-dev
       - tesseract-ocr-eng
+      - tesseract-ocr-fra
       - libpoppler-cpp-dev
       - libmagick++-dev
 

R/tessdata.R

@@ -26,12 +26,13 @@
 #' @param progress print progress while downloading
 #' @references [tesseract wiki: training data](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files)
 #' @examples \donttest{
-#' tesseract_download("fra")
+#' if(is.na(match("fra", tesseract_info()$available)))
+#'   tesseract_download("fra")
 #' french <- tesseract("fra")
 #' text <- ocr("https://jeroen.github.io/images/french_text.png", engine = french)
 #' cat(text)
 #' }
-tesseract_download <- function(lang, datapath = NULL, progress = TRUE){
+tesseract_download <- function(lang, datapath = NULL, progress = interactive()){
   if(!length(datapath)){
     warn_on_linux()
     datapath <- tesseract_info()$datapath

man/tessdata.Rd

@@ -1,7 +1,9 @@
 #include "tesseract_types.h"
 #include <tesseract/genericvector.h>
 
-/* NB: libtesseract now insists that the engine is loaded in 'C' locale.
+/* NB: libtesseract now insists that the engine is initiated in 'C' locale.
+ * We do this as exemplified in the example code in the libc manual:
+ * https://www.gnu.org/software/libc/manual/html_node/Setting-the-Locale.html
  * Hopefully this is temporary and it will be fixed upstream.
  * Full discussion: https://github.com/tesseract-ocr/tesseract/issues/1670
  */