small PR to use cpp11

DESCRIPTION

@@ -1,28 +1,35 @@
 Package: tesseract
 Type: Package
 Title: Open Source OCR Engine
-Version: 5.2.1
-Authors@R: person("Jeroen", "Ooms", role = c("aut", "cre"), email = "[email protected]",
-    comment = c(ORCID = "0000-0002-4035-0289"))
+Version: 5.3.0
+Authors@R: c(person("Jeroen", "Ooms",
+                    role = c("aut", "cre"),
+                    email = "[email protected]",
+                    comment = c(ORCID = "0000-0002-4035-0289")),
+             person("Mauricio", "Vargas Sepulveda",
+                    role = "aut", 
+                    email = "[email protected]", 
+                    comment = c(ORCID = "0000-0003-1017-7574")))
 Description: Bindings to 'Tesseract': 
-     a powerful optical character recognition (OCR) engine that supports over 100 languages.
-     The engine is highly configurable in order to tune the detection algorithms and
-     obtain the best possible results.
+     a powerful optical character recognition (OCR) engine that supports over
+     100 languages. The engine is highly configurable in order to tune the
+     detection algorithms and obtain the best possible results.
 License: Apache License 2.0
 URL: https://docs.ropensci.org/tesseract/ (website) 
     https://github.com/ropensci/tesseract (devel)
 BugReports: https://github.com/ropensci/tesseract/issues
-SystemRequirements: Tesseract >= 3.03 (libtesseract-dev / tesseract-devel) and
-    Leptonica (libleptonica-dev / leptonica-devel). On Debian you need to install
-    the English training data separately (tesseract-ocr-eng)
+SystemRequirements: Tesseract >= 5.0.0 (libtesseract-dev / tesseract-devel) and
+    Leptonica (libleptonica-dev / leptonica-devel). On Debian you need to
+    install the English and other languages training data separately
+    (e.g. tesseract-ocr-eng or tesseract-ocr-spa).
 Imports:
-    Rcpp (>= 0.12.12),
     pdftools (>= 1.5),    
     curl,
     rappdirs,
     digest
-LinkingTo: Rcpp
-RoxygenNote: 7.2.3
+LinkingTo: 
+    cpp11
+RoxygenNote: 7.3.1
 Roxygen: list(markdown = TRUE)
 Suggests:
     magick (>= 1.7),

NAMESPACE

@@ -7,5 +7,4 @@ export(tesseract)
 export(tesseract_download)
 export(tesseract_info)
 export(tesseract_params)
-importFrom(Rcpp,sourceCpp)
-useDynLib(tesseract)
+useDynLib(tesseract, .registration = TRUE)

R/cpp11.R

@@ -0,0 +1,45 @@
+# Generated by cpp11: do not edit by hand
+
+tesseract_config <- function() {
+  .Call(`_tesseract_tesseract_config`)
+}
+
+tesseract_engine_internal <- function(datapath, language, confpaths, opt_names, opt_values) {
+  .Call(`_tesseract_tesseract_engine_internal`, datapath, language, confpaths, opt_names, opt_values)
+}
+
+tesseract_engine_set_variable <- function(ptr, name, value) {
+  .Call(`_tesseract_tesseract_engine_set_variable`, ptr, name, value)
+}
+
+validate_params <- function(params) {
+  .Call(`_tesseract_validate_params`, params)
+}
+
+engine_info_internal <- function(ptr) {
+  .Call(`_tesseract_engine_info_internal`, ptr)
+}
+
+print_params <- function(filename) {
+  .Call(`_tesseract_print_params`, filename)
+}
+
+get_param_values <- function(api, params) {
+  .Call(`_tesseract_get_param_values`, api, params)
+}
+
+ocr_raw <- function(input, ptr, HOCR) {
+  .Call(`_tesseract_ocr_raw`, input, ptr, HOCR)
+}
+
+ocr_file <- function(file, ptr, HOCR) {
+  .Call(`_tesseract_ocr_file`, file, ptr, HOCR)
+}
+
+ocr_raw_data <- function(input, ptr) {
+  .Call(`_tesseract_ocr_raw_data`, input, ptr)
+}
+
+ocr_file_data <- function(file, ptr) {
+  .Call(`_tesseract_ocr_file_data`, file, ptr)
+}

R/ocr.R

@@ -10,15 +10,13 @@
 #' each word in the text.
 #'
 #' @export
-#' @useDynLib tesseract
 #' @family tesseract
 #' @param image file path, url, or raw vector to image (png, tiff, jpeg, etc)
 #' @param engine a tesseract engine created with [tesseract()]. Alternatively a
 #' language string which will be passed to [tesseract()].
 #' @param HOCR if `TRUE` return results as HOCR xml instead of plain text
 #' @rdname ocr
 #' @references [Tesseract: Improving Quality](https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality)
-#' @importFrom Rcpp sourceCpp
 #' @examples # Simple example
 #' text <- ocr("https://jeroen.github.io/images/testocr.png")
 #' cat(text)
@@ -48,7 +46,7 @@
 ocr <- function(image, engine = tesseract("eng"), HOCR = FALSE) {
   if(is.character(engine))
     engine <- tesseract(engine)
-  stopifnot(inherits(engine, "tesseract"))
+  stopifnot(inherits(engine, "externalptr"))
   if(inherits(image, "magick-image")){
     vapply(image, function(x){
       tmp <- tempfile(fileext = ".png")
@@ -71,7 +69,7 @@ ocr <- function(image, engine = tesseract("eng"), HOCR = FALSE) {
 ocr_data <- function(image, engine = tesseract("eng")) {
   if(is.character(engine))
     engine <- tesseract(engine)
-  stopifnot(inherits(engine, "tesseract"))
+  stopifnot(inherits(engine, "externalptr"))
   df_list <- if(inherits(image, "magick-image")){
     lapply(image, function(x){
       tmp <- tempfile(fileext = ".png")

R/tesseract-package.R

@@ -0,0 +1,11 @@
+#' @title Open Source OCR Engine
+#'
+#' @description
+#' Bindings to 'Tesseract':
+#' a powerful optical character recognition (OCR) engine that supports over 100
+#' languages. The engine is highly configurable in order to tune the detection
+#' algorithms and obtain the best possible results.
+#'
+#' @name tesseract-package
+#' @useDynLib tesseract, .registration = TRUE
+"_PACKAGE"

inst/WORDLIST

@@ -1,3 +1,4 @@
+chinese
 config
 EPEL
 github
@@ -15,12 +16,15 @@ Magick
 Nederlands
 ocr
 opensource
+ORCID
 pdftools
 png
 rmarkdown
 spanish
+Sepulveda
 tessdata
 toc
+utrecht
 VignetteEncoding
 VignetteEngine
 VignetteIndexEntry

src/.gitignore

@@ -0,0 +1,3 @@
+*.o
+*.so
+*.dll